From 9ca8dbcc65cfc63d6f5ef3312a33184e1d726e00 Mon Sep 17 00:00:00 2001 From: Yunhong Jiang Date: Tue, 4 Aug 2015 12:17:53 -0700 Subject: Add the rt linux 4.1.3-rt3 as base Import the rt linux 4.1.3-rt3 as OPNFV kvm base. It's from git://git.kernel.org/pub/scm/linux/kernel/git/rt/linux-rt-devel.git linux-4.1.y-rt and the base is: commit 0917f823c59692d751951bf5ea699a2d1e2f26a2 Author: Sebastian Andrzej Siewior Date: Sat Jul 25 12:13:34 2015 +0200 Prepare v4.1.3-rt3 Signed-off-by: Sebastian Andrzej Siewior We lose all the git history this way and it's not good. We should apply another opnfv project repo in future. Change-Id: I87543d81c9df70d99c5001fbdf646b202c19f423 Signed-off-by: Yunhong Jiang --- kernel/kernel/.gitignore | 8 + kernel/kernel/Kconfig.freezer | 2 + kernel/kernel/Kconfig.hz | 58 + kernel/kernel/Kconfig.locks | 243 + kernel/kernel/Kconfig.preempt | 87 + kernel/kernel/Makefile | 209 + kernel/kernel/acct.c | 602 ++ kernel/kernel/async.c | 328 + kernel/kernel/audit.c | 2036 ++++++ kernel/kernel/audit.h | 328 + kernel/kernel/audit_tree.c | 988 +++ kernel/kernel/audit_watch.c | 519 ++ kernel/kernel/auditfilter.c | 1416 ++++ kernel/kernel/auditsc.c | 2426 +++++++ kernel/kernel/backtracetest.c | 91 + kernel/kernel/bounds.c | 25 + kernel/kernel/bpf/Makefile | 2 + kernel/kernel/bpf/arraymap.c | 156 + kernel/kernel/bpf/core.c | 674 ++ kernel/kernel/bpf/hashtab.c | 367 + kernel/kernel/bpf/helpers.c | 113 + kernel/kernel/bpf/syscall.c | 621 ++ kernel/kernel/bpf/verifier.c | 2146 ++++++ kernel/kernel/capability.c | 449 ++ kernel/kernel/cgroup.c | 5602 +++++++++++++++ kernel/kernel/cgroup_freezer.c | 484 ++ kernel/kernel/compat.c | 1176 +++ kernel/kernel/configs.c | 99 + kernel/kernel/configs/tiny.config | 4 + kernel/kernel/context_tracking.c | 195 + kernel/kernel/cpu.c | 1146 +++ kernel/kernel/cpu_pm.c | 233 + kernel/kernel/cpuset.c | 2700 +++++++ kernel/kernel/crash_dump.c | 46 + kernel/kernel/cred.c | 810 +++ kernel/kernel/debug/Makefile | 6 + kernel/kernel/debug/debug_core.c | 1088 +++ kernel/kernel/debug/debug_core.h | 85 + kernel/kernel/debug/gdbstub.c | 1145 +++ kernel/kernel/debug/kdb/.gitignore | 1 + kernel/kernel/debug/kdb/Makefile | 25 + kernel/kernel/debug/kdb/kdb_bp.c | 560 ++ kernel/kernel/debug/kdb/kdb_bt.c | 210 + kernel/kernel/debug/kdb/kdb_cmds | 31 + kernel/kernel/debug/kdb/kdb_debugger.c | 186 + kernel/kernel/debug/kdb/kdb_io.c | 872 +++ kernel/kernel/debug/kdb/kdb_keyboard.c | 263 + kernel/kernel/debug/kdb/kdb_main.c | 2954 ++++++++ kernel/kernel/debug/kdb/kdb_private.h | 261 + kernel/kernel/debug/kdb/kdb_support.c | 927 +++ kernel/kernel/delayacct.c | 158 + kernel/kernel/dma.c | 160 + kernel/kernel/elfcore.c | 24 + kernel/kernel/events/Makefile | 9 + kernel/kernel/events/callchain.c | 209 + kernel/kernel/events/core.c | 9084 ++++++++++++++++++++++++ kernel/kernel/events/hw_breakpoint.c | 655 ++ kernel/kernel/events/internal.h | 231 + kernel/kernel/events/ring_buffer.c | 751 ++ kernel/kernel/events/uprobes.c | 1993 ++++++ kernel/kernel/exec_domain.c | 58 + kernel/kernel/exit.c | 1632 +++++ kernel/kernel/extable.c | 144 + kernel/kernel/fork.c | 2109 ++++++ kernel/kernel/freezer.c | 179 + kernel/kernel/futex.c | 3126 ++++++++ kernel/kernel/futex_compat.c | 201 + kernel/kernel/gcov/Kconfig | 82 + kernel/kernel/gcov/Makefile | 7 + kernel/kernel/gcov/base.c | 161 + kernel/kernel/gcov/fs.c | 791 +++ kernel/kernel/gcov/gcc_3_4.c | 562 ++ kernel/kernel/gcov/gcc_4_7.c | 565 ++ kernel/kernel/gcov/gcov.h | 85 + kernel/kernel/groups.c | 277 + kernel/kernel/hung_task.c | 251 + kernel/kernel/irq/Kconfig | 103 + kernel/kernel/irq/Makefile | 9 + kernel/kernel/irq/autoprobe.c | 185 + kernel/kernel/irq/chip.c | 993 +++ kernel/kernel/irq/debug.h | 45 + kernel/kernel/irq/devres.c | 139 + kernel/kernel/irq/dummychip.c | 62 + kernel/kernel/irq/generic-chip.c | 608 ++ kernel/kernel/irq/handle.c | 203 + kernel/kernel/irq/internals.h | 212 + kernel/kernel/irq/irqdesc.c | 648 ++ kernel/kernel/irq/irqdomain.c | 1238 ++++ kernel/kernel/irq/manage.c | 1983 ++++++ kernel/kernel/irq/migration.c | 72 + kernel/kernel/irq/msi.c | 337 + kernel/kernel/irq/pm.c | 206 + kernel/kernel/irq/proc.c | 501 ++ kernel/kernel/irq/resend.c | 91 + kernel/kernel/irq/settings.h | 168 + kernel/kernel/irq/spurious.c | 475 ++ kernel/kernel/irq_work.c | 217 + kernel/kernel/jump_label.c | 460 ++ kernel/kernel/kallsyms.c | 608 ++ kernel/kernel/kcmp.c | 198 + kernel/kernel/kexec.c | 2769 ++++++++ kernel/kernel/kmod.c | 694 ++ kernel/kernel/kprobes.c | 2472 +++++++ kernel/kernel/ksysfs.c | 255 + kernel/kernel/kthread.c | 692 ++ kernel/kernel/latencytop.c | 292 + kernel/kernel/livepatch/Kconfig | 18 + kernel/kernel/livepatch/Makefile | 3 + kernel/kernel/livepatch/core.c | 1011 +++ kernel/kernel/locking/Makefile | 36 + kernel/kernel/locking/lglock.c | 132 + kernel/kernel/locking/lockdep.c | 4306 +++++++++++ kernel/kernel/locking/lockdep_internals.h | 170 + kernel/kernel/locking/lockdep_proc.c | 695 ++ kernel/kernel/locking/lockdep_states.h | 9 + kernel/kernel/locking/locktorture.c | 814 +++ kernel/kernel/locking/mcs_spinlock.h | 111 + kernel/kernel/locking/mutex-debug.c | 120 + kernel/kernel/locking/mutex-debug.h | 55 + kernel/kernel/locking/mutex.c | 972 +++ kernel/kernel/locking/mutex.h | 48 + kernel/kernel/locking/osq_lock.c | 203 + kernel/kernel/locking/percpu-rwsem.c | 165 + kernel/kernel/locking/qrwlock.c | 132 + kernel/kernel/locking/rt.c | 461 ++ kernel/kernel/locking/rtmutex-debug.c | 184 + kernel/kernel/locking/rtmutex-debug.h | 39 + kernel/kernel/locking/rtmutex-tester.c | 420 ++ kernel/kernel/locking/rtmutex.c | 2300 ++++++ kernel/kernel/locking/rtmutex.h | 36 + kernel/kernel/locking/rtmutex_common.h | 159 + kernel/kernel/locking/rwsem-spinlock.c | 303 + kernel/kernel/locking/rwsem-xadd.c | 531 ++ kernel/kernel/locking/rwsem.c | 166 + kernel/kernel/locking/rwsem.h | 20 + kernel/kernel/locking/semaphore.c | 263 + kernel/kernel/locking/spinlock.c | 414 ++ kernel/kernel/locking/spinlock_debug.c | 307 + kernel/kernel/module-internal.h | 12 + kernel/kernel/module.c | 3917 ++++++++++ kernel/kernel/module_signing.c | 250 + kernel/kernel/notifier.c | 562 ++ kernel/kernel/nsproxy.c | 259 + kernel/kernel/padata.c | 1105 +++ kernel/kernel/panic.c | 521 ++ kernel/kernel/params.c | 954 +++ kernel/kernel/pid.c | 609 ++ kernel/kernel/pid_namespace.c | 409 ++ kernel/kernel/power/Kconfig | 303 + kernel/kernel/power/Makefile | 15 + kernel/kernel/power/autosleep.c | 128 + kernel/kernel/power/block_io.c | 103 + kernel/kernel/power/console.c | 151 + kernel/kernel/power/hibernate.c | 1173 +++ kernel/kernel/power/main.c | 646 ++ kernel/kernel/power/power.h | 297 + kernel/kernel/power/poweroff.c | 46 + kernel/kernel/power/process.c | 237 + kernel/kernel/power/qos.c | 713 ++ kernel/kernel/power/snapshot.c | 2607 +++++++ kernel/kernel/power/suspend.c | 540 ++ kernel/kernel/power/suspend_test.c | 218 + kernel/kernel/power/swap.c | 1512 ++++ kernel/kernel/power/user.c | 478 ++ kernel/kernel/power/wakelock.c | 268 + kernel/kernel/printk/Makefile | 2 + kernel/kernel/printk/braille.c | 49 + kernel/kernel/printk/braille.h | 48 + kernel/kernel/printk/console_cmdline.h | 14 + kernel/kernel/printk/printk.c | 3156 ++++++++ kernel/kernel/profile.c | 613 ++ kernel/kernel/ptrace.c | 1224 ++++ kernel/kernel/range.c | 163 + kernel/kernel/rcu/Makefile | 7 + kernel/kernel/rcu/rcu.h | 146 + kernel/kernel/rcu/rcutorture.c | 1861 +++++ kernel/kernel/rcu/srcu.c | 676 ++ kernel/kernel/rcu/tiny.c | 288 + kernel/kernel/rcu/tiny_plugin.h | 173 + kernel/kernel/rcu/tree.c | 4254 +++++++++++ kernel/kernel/rcu/tree.h | 618 ++ kernel/kernel/rcu/tree_plugin.h | 2984 ++++++++ kernel/kernel/rcu/tree_trace.c | 505 ++ kernel/kernel/rcu/update.c | 833 +++ kernel/kernel/reboot.c | 557 ++ kernel/kernel/relay.c | 1356 ++++ kernel/kernel/resource.c | 1534 ++++ kernel/kernel/sched/Makefile | 21 + kernel/kernel/sched/auto_group.c | 253 + kernel/kernel/sched/auto_group.h | 64 + kernel/kernel/sched/clock.c | 435 ++ kernel/kernel/sched/completion.c | 317 + kernel/kernel/sched/core.c | 8726 +++++++++++++++++++++++ kernel/kernel/sched/cpuacct.c | 283 + kernel/kernel/sched/cpuacct.h | 17 + kernel/kernel/sched/cpudeadline.c | 246 + kernel/kernel/sched/cpudeadline.h | 32 + kernel/kernel/sched/cpupri.c | 248 + kernel/kernel/sched/cpupri.h | 31 + kernel/kernel/sched/cputime.c | 870 +++ kernel/kernel/sched/deadline.c | 1819 +++++ kernel/kernel/sched/debug.c | 681 ++ kernel/kernel/sched/fair.c | 8285 +++++++++++++++++++++ kernel/kernel/sched/features.h | 106 + kernel/kernel/sched/idle.c | 298 + kernel/kernel/sched/idle_task.c | 109 + kernel/kernel/sched/proc.c | 584 ++ kernel/kernel/sched/rt.c | 2348 ++++++ kernel/kernel/sched/sched.h | 1746 +++++ kernel/kernel/sched/stats.c | 138 + kernel/kernel/sched/stats.h | 267 + kernel/kernel/sched/stop_task.c | 136 + kernel/kernel/sched/wait-simple.c | 115 + kernel/kernel/sched/wait.c | 624 ++ kernel/kernel/sched/work-simple.c | 172 + kernel/kernel/seccomp.c | 904 +++ kernel/kernel/signal.c | 3775 ++++++++++ kernel/kernel/smp.c | 741 ++ kernel/kernel/smpboot.c | 472 ++ kernel/kernel/smpboot.h | 20 + kernel/kernel/softirq.c | 1245 ++++ kernel/kernel/stacktrace.c | 75 + kernel/kernel/stop_machine.c | 686 ++ kernel/kernel/sys.c | 2408 +++++++ kernel/kernel/sys_ni.c | 245 + kernel/kernel/sysctl.c | 2792 ++++++++ kernel/kernel/sysctl_binary.c | 1494 ++++ kernel/kernel/system_certificates.S | 20 + kernel/kernel/system_keyring.c | 106 + kernel/kernel/task_work.c | 128 + kernel/kernel/taskstats.c | 710 ++ kernel/kernel/test_kprobes.c | 389 + kernel/kernel/time/Kconfig | 199 + kernel/kernel/time/Makefile | 31 + kernel/kernel/time/alarmtimer.c | 873 +++ kernel/kernel/time/clockevents.c | 792 +++ kernel/kernel/time/clocksource.c | 1020 +++ kernel/kernel/time/hrtimer.c | 2140 ++++++ kernel/kernel/time/itimer.c | 302 + kernel/kernel/time/jiffies.c | 137 + kernel/kernel/time/ntp.c | 1008 +++ kernel/kernel/time/ntp_internal.h | 12 + kernel/kernel/time/posix-clock.c | 446 ++ kernel/kernel/time/posix-cpu-timers.c | 1661 +++++ kernel/kernel/time/posix-timers.c | 1159 +++ kernel/kernel/time/sched_clock.c | 303 + kernel/kernel/time/test_udelay.c | 168 + kernel/kernel/time/tick-broadcast-hrtimer.c | 113 + kernel/kernel/time/tick-broadcast.c | 964 +++ kernel/kernel/time/tick-common.c | 500 ++ kernel/kernel/time/tick-internal.h | 139 + kernel/kernel/time/tick-oneshot.c | 116 + kernel/kernel/time/tick-sched.c | 1255 ++++ kernel/kernel/time/tick-sched.h | 74 + kernel/kernel/time/time.c | 785 ++ kernel/kernel/time/timeconst.bc | 108 + kernel/kernel/time/timeconv.c | 127 + kernel/kernel/time/timecounter.c | 112 + kernel/kernel/time/timekeeping.c | 2074 ++++++ kernel/kernel/time/timekeeping.h | 30 + kernel/kernel/time/timekeeping_debug.c | 74 + kernel/kernel/time/timekeeping_internal.h | 29 + kernel/kernel/time/timer.c | 1787 +++++ kernel/kernel/time/timer_list.c | 396 ++ kernel/kernel/time/timer_stats.c | 425 ++ kernel/kernel/torture.c | 741 ++ kernel/kernel/trace/Kconfig | 745 ++ kernel/kernel/trace/Makefile | 74 + kernel/kernel/trace/blktrace.c | 1819 +++++ kernel/kernel/trace/bpf_trace.c | 222 + kernel/kernel/trace/ftrace.c | 5951 ++++++++++++++++ kernel/kernel/trace/latency_hist.c | 1178 +++ kernel/kernel/trace/power-traces.c | 18 + kernel/kernel/trace/ring_buffer.c | 5014 +++++++++++++ kernel/kernel/trace/ring_buffer_benchmark.c | 483 ++ kernel/kernel/trace/rpm-traces.c | 20 + kernel/kernel/trace/trace.c | 7215 +++++++++++++++++++ kernel/kernel/trace/trace.h | 1322 ++++ kernel/kernel/trace/trace_benchmark.c | 198 + kernel/kernel/trace/trace_benchmark.h | 41 + kernel/kernel/trace/trace_branch.c | 411 ++ kernel/kernel/trace/trace_clock.c | 137 + kernel/kernel/trace/trace_entries.h | 324 + kernel/kernel/trace/trace_event_perf.c | 384 + kernel/kernel/trace/trace_events.c | 2945 ++++++++ kernel/kernel/trace/trace_events_filter.c | 2432 +++++++ kernel/kernel/trace/trace_events_filter_test.h | 50 + kernel/kernel/trace/trace_events_trigger.c | 1437 ++++ kernel/kernel/trace/trace_export.c | 195 + kernel/kernel/trace/trace_functions.c | 689 ++ kernel/kernel/trace/trace_functions_graph.c | 1470 ++++ kernel/kernel/trace/trace_irqsoff.c | 775 ++ kernel/kernel/trace/trace_kdb.c | 140 + kernel/kernel/trace/trace_kprobe.c | 1495 ++++ kernel/kernel/trace/trace_mmiotrace.c | 364 + kernel/kernel/trace/trace_nop.c | 99 + kernel/kernel/trace/trace_output.c | 1270 ++++ kernel/kernel/trace/trace_output.h | 45 + kernel/kernel/trace/trace_printk.c | 366 + kernel/kernel/trace/trace_probe.c | 723 ++ kernel/kernel/trace/trace_probe.h | 394 + kernel/kernel/trace/trace_sched_switch.c | 101 + kernel/kernel/trace/trace_sched_wakeup.c | 816 +++ kernel/kernel/trace/trace_selftest.c | 1215 ++++ kernel/kernel/trace/trace_selftest_dynamic.c | 13 + kernel/kernel/trace/trace_seq.c | 377 + kernel/kernel/trace/trace_stack.c | 484 ++ kernel/kernel/trace/trace_stat.c | 359 + kernel/kernel/trace/trace_stat.h | 33 + kernel/kernel/trace/trace_syscalls.c | 750 ++ kernel/kernel/trace/trace_uprobe.c | 1336 ++++ kernel/kernel/tracepoint.c | 520 ++ kernel/kernel/tsacct.c | 180 + kernel/kernel/uid16.c | 217 + kernel/kernel/up.c | 84 + kernel/kernel/user-return-notifier.c | 44 + kernel/kernel/user.c | 228 + kernel/kernel/user_namespace.c | 1012 +++ kernel/kernel/utsname.c | 139 + kernel/kernel/utsname_sysctl.c | 138 + kernel/kernel/watchdog.c | 901 +++ kernel/kernel/workqueue.c | 5180 ++++++++++++++ kernel/kernel/workqueue_internal.h | 75 + 323 files changed, 249067 insertions(+) create mode 100644 kernel/kernel/.gitignore create mode 100644 kernel/kernel/Kconfig.freezer create mode 100644 kernel/kernel/Kconfig.hz create mode 100644 kernel/kernel/Kconfig.locks create mode 100644 kernel/kernel/Kconfig.preempt create mode 100644 kernel/kernel/Makefile create mode 100644 kernel/kernel/acct.c create mode 100644 kernel/kernel/async.c create mode 100644 kernel/kernel/audit.c create mode 100644 kernel/kernel/audit.h create mode 100644 kernel/kernel/audit_tree.c create mode 100644 kernel/kernel/audit_watch.c create mode 100644 kernel/kernel/auditfilter.c create mode 100644 kernel/kernel/auditsc.c create mode 100644 kernel/kernel/backtracetest.c create mode 100644 kernel/kernel/bounds.c create mode 100644 kernel/kernel/bpf/Makefile create mode 100644 kernel/kernel/bpf/arraymap.c create mode 100644 kernel/kernel/bpf/core.c create mode 100644 kernel/kernel/bpf/hashtab.c create mode 100644 kernel/kernel/bpf/helpers.c create mode 100644 kernel/kernel/bpf/syscall.c create mode 100644 kernel/kernel/bpf/verifier.c create mode 100644 kernel/kernel/capability.c create mode 100644 kernel/kernel/cgroup.c create mode 100644 kernel/kernel/cgroup_freezer.c create mode 100644 kernel/kernel/compat.c create mode 100644 kernel/kernel/configs.c create mode 100644 kernel/kernel/configs/tiny.config create mode 100644 kernel/kernel/context_tracking.c create mode 100644 kernel/kernel/cpu.c create mode 100644 kernel/kernel/cpu_pm.c create mode 100644 kernel/kernel/cpuset.c create mode 100644 kernel/kernel/crash_dump.c create mode 100644 kernel/kernel/cred.c create mode 100644 kernel/kernel/debug/Makefile create mode 100644 kernel/kernel/debug/debug_core.c create mode 100644 kernel/kernel/debug/debug_core.h create mode 100644 kernel/kernel/debug/gdbstub.c create mode 100644 kernel/kernel/debug/kdb/.gitignore create mode 100644 kernel/kernel/debug/kdb/Makefile create mode 100644 kernel/kernel/debug/kdb/kdb_bp.c create mode 100644 kernel/kernel/debug/kdb/kdb_bt.c create mode 100644 kernel/kernel/debug/kdb/kdb_cmds create mode 100644 kernel/kernel/debug/kdb/kdb_debugger.c create mode 100644 kernel/kernel/debug/kdb/kdb_io.c create mode 100644 kernel/kernel/debug/kdb/kdb_keyboard.c create mode 100644 kernel/kernel/debug/kdb/kdb_main.c create mode 100644 kernel/kernel/debug/kdb/kdb_private.h create mode 100644 kernel/kernel/debug/kdb/kdb_support.c create mode 100644 kernel/kernel/delayacct.c create mode 100644 kernel/kernel/dma.c create mode 100644 kernel/kernel/elfcore.c create mode 100644 kernel/kernel/events/Makefile create mode 100644 kernel/kernel/events/callchain.c create mode 100644 kernel/kernel/events/core.c create mode 100644 kernel/kernel/events/hw_breakpoint.c create mode 100644 kernel/kernel/events/internal.h create mode 100644 kernel/kernel/events/ring_buffer.c create mode 100644 kernel/kernel/events/uprobes.c create mode 100644 kernel/kernel/exec_domain.c create mode 100644 kernel/kernel/exit.c create mode 100644 kernel/kernel/extable.c create mode 100644 kernel/kernel/fork.c create mode 100644 kernel/kernel/freezer.c create mode 100644 kernel/kernel/futex.c create mode 100644 kernel/kernel/futex_compat.c create mode 100644 kernel/kernel/gcov/Kconfig create mode 100644 kernel/kernel/gcov/Makefile create mode 100644 kernel/kernel/gcov/base.c create mode 100644 kernel/kernel/gcov/fs.c create mode 100644 kernel/kernel/gcov/gcc_3_4.c create mode 100644 kernel/kernel/gcov/gcc_4_7.c create mode 100644 kernel/kernel/gcov/gcov.h create mode 100644 kernel/kernel/groups.c create mode 100644 kernel/kernel/hung_task.c create mode 100644 kernel/kernel/irq/Kconfig create mode 100644 kernel/kernel/irq/Makefile create mode 100644 kernel/kernel/irq/autoprobe.c create mode 100644 kernel/kernel/irq/chip.c create mode 100644 kernel/kernel/irq/debug.h create mode 100644 kernel/kernel/irq/devres.c create mode 100644 kernel/kernel/irq/dummychip.c create mode 100644 kernel/kernel/irq/generic-chip.c create mode 100644 kernel/kernel/irq/handle.c create mode 100644 kernel/kernel/irq/internals.h create mode 100644 kernel/kernel/irq/irqdesc.c create mode 100644 kernel/kernel/irq/irqdomain.c create mode 100644 kernel/kernel/irq/manage.c create mode 100644 kernel/kernel/irq/migration.c create mode 100644 kernel/kernel/irq/msi.c create mode 100644 kernel/kernel/irq/pm.c create mode 100644 kernel/kernel/irq/proc.c create mode 100644 kernel/kernel/irq/resend.c create mode 100644 kernel/kernel/irq/settings.h create mode 100644 kernel/kernel/irq/spurious.c create mode 100644 kernel/kernel/irq_work.c create mode 100644 kernel/kernel/jump_label.c create mode 100644 kernel/kernel/kallsyms.c create mode 100644 kernel/kernel/kcmp.c create mode 100644 kernel/kernel/kexec.c create mode 100644 kernel/kernel/kmod.c create mode 100644 kernel/kernel/kprobes.c create mode 100644 kernel/kernel/ksysfs.c create mode 100644 kernel/kernel/kthread.c create mode 100644 kernel/kernel/latencytop.c create mode 100644 kernel/kernel/livepatch/Kconfig create mode 100644 kernel/kernel/livepatch/Makefile create mode 100644 kernel/kernel/livepatch/core.c create mode 100644 kernel/kernel/locking/Makefile create mode 100644 kernel/kernel/locking/lglock.c create mode 100644 kernel/kernel/locking/lockdep.c create mode 100644 kernel/kernel/locking/lockdep_internals.h create mode 100644 kernel/kernel/locking/lockdep_proc.c create mode 100644 kernel/kernel/locking/lockdep_states.h create mode 100644 kernel/kernel/locking/locktorture.c create mode 100644 kernel/kernel/locking/mcs_spinlock.h create mode 100644 kernel/kernel/locking/mutex-debug.c create mode 100644 kernel/kernel/locking/mutex-debug.h create mode 100644 kernel/kernel/locking/mutex.c create mode 100644 kernel/kernel/locking/mutex.h create mode 100644 kernel/kernel/locking/osq_lock.c create mode 100644 kernel/kernel/locking/percpu-rwsem.c create mode 100644 kernel/kernel/locking/qrwlock.c create mode 100644 kernel/kernel/locking/rt.c create mode 100644 kernel/kernel/locking/rtmutex-debug.c create mode 100644 kernel/kernel/locking/rtmutex-debug.h create mode 100644 kernel/kernel/locking/rtmutex-tester.c create mode 100644 kernel/kernel/locking/rtmutex.c create mode 100644 kernel/kernel/locking/rtmutex.h create mode 100644 kernel/kernel/locking/rtmutex_common.h create mode 100644 kernel/kernel/locking/rwsem-spinlock.c create mode 100644 kernel/kernel/locking/rwsem-xadd.c create mode 100644 kernel/kernel/locking/rwsem.c create mode 100644 kernel/kernel/locking/rwsem.h create mode 100644 kernel/kernel/locking/semaphore.c create mode 100644 kernel/kernel/locking/spinlock.c create mode 100644 kernel/kernel/locking/spinlock_debug.c create mode 100644 kernel/kernel/module-internal.h create mode 100644 kernel/kernel/module.c create mode 100644 kernel/kernel/module_signing.c create mode 100644 kernel/kernel/notifier.c create mode 100644 kernel/kernel/nsproxy.c create mode 100644 kernel/kernel/padata.c create mode 100644 kernel/kernel/panic.c create mode 100644 kernel/kernel/params.c create mode 100644 kernel/kernel/pid.c create mode 100644 kernel/kernel/pid_namespace.c create mode 100644 kernel/kernel/power/Kconfig create mode 100644 kernel/kernel/power/Makefile create mode 100644 kernel/kernel/power/autosleep.c create mode 100644 kernel/kernel/power/block_io.c create mode 100644 kernel/kernel/power/console.c create mode 100644 kernel/kernel/power/hibernate.c create mode 100644 kernel/kernel/power/main.c create mode 100644 kernel/kernel/power/power.h create mode 100644 kernel/kernel/power/poweroff.c create mode 100644 kernel/kernel/power/process.c create mode 100644 kernel/kernel/power/qos.c create mode 100644 kernel/kernel/power/snapshot.c create mode 100644 kernel/kernel/power/suspend.c create mode 100644 kernel/kernel/power/suspend_test.c create mode 100644 kernel/kernel/power/swap.c create mode 100644 kernel/kernel/power/user.c create mode 100644 kernel/kernel/power/wakelock.c create mode 100644 kernel/kernel/printk/Makefile create mode 100644 kernel/kernel/printk/braille.c create mode 100644 kernel/kernel/printk/braille.h create mode 100644 kernel/kernel/printk/console_cmdline.h create mode 100644 kernel/kernel/printk/printk.c create mode 100644 kernel/kernel/profile.c create mode 100644 kernel/kernel/ptrace.c create mode 100644 kernel/kernel/range.c create mode 100644 kernel/kernel/rcu/Makefile create mode 100644 kernel/kernel/rcu/rcu.h create mode 100644 kernel/kernel/rcu/rcutorture.c create mode 100644 kernel/kernel/rcu/srcu.c create mode 100644 kernel/kernel/rcu/tiny.c create mode 100644 kernel/kernel/rcu/tiny_plugin.h create mode 100644 kernel/kernel/rcu/tree.c create mode 100644 kernel/kernel/rcu/tree.h create mode 100644 kernel/kernel/rcu/tree_plugin.h create mode 100644 kernel/kernel/rcu/tree_trace.c create mode 100644 kernel/kernel/rcu/update.c create mode 100644 kernel/kernel/reboot.c create mode 100644 kernel/kernel/relay.c create mode 100644 kernel/kernel/resource.c create mode 100644 kernel/kernel/sched/Makefile create mode 100644 kernel/kernel/sched/auto_group.c create mode 100644 kernel/kernel/sched/auto_group.h create mode 100644 kernel/kernel/sched/clock.c create mode 100644 kernel/kernel/sched/completion.c create mode 100644 kernel/kernel/sched/core.c create mode 100644 kernel/kernel/sched/cpuacct.c create mode 100644 kernel/kernel/sched/cpuacct.h create mode 100644 kernel/kernel/sched/cpudeadline.c create mode 100644 kernel/kernel/sched/cpudeadline.h create mode 100644 kernel/kernel/sched/cpupri.c create mode 100644 kernel/kernel/sched/cpupri.h create mode 100644 kernel/kernel/sched/cputime.c create mode 100644 kernel/kernel/sched/deadline.c create mode 100644 kernel/kernel/sched/debug.c create mode 100644 kernel/kernel/sched/fair.c create mode 100644 kernel/kernel/sched/features.h create mode 100644 kernel/kernel/sched/idle.c create mode 100644 kernel/kernel/sched/idle_task.c create mode 100644 kernel/kernel/sched/proc.c create mode 100644 kernel/kernel/sched/rt.c create mode 100644 kernel/kernel/sched/sched.h create mode 100644 kernel/kernel/sched/stats.c create mode 100644 kernel/kernel/sched/stats.h create mode 100644 kernel/kernel/sched/stop_task.c create mode 100644 kernel/kernel/sched/wait-simple.c create mode 100644 kernel/kernel/sched/wait.c create mode 100644 kernel/kernel/sched/work-simple.c create mode 100644 kernel/kernel/seccomp.c create mode 100644 kernel/kernel/signal.c create mode 100644 kernel/kernel/smp.c create mode 100644 kernel/kernel/smpboot.c create mode 100644 kernel/kernel/smpboot.h create mode 100644 kernel/kernel/softirq.c create mode 100644 kernel/kernel/stacktrace.c create mode 100644 kernel/kernel/stop_machine.c create mode 100644 kernel/kernel/sys.c create mode 100644 kernel/kernel/sys_ni.c create mode 100644 kernel/kernel/sysctl.c create mode 100644 kernel/kernel/sysctl_binary.c create mode 100644 kernel/kernel/system_certificates.S create mode 100644 kernel/kernel/system_keyring.c create mode 100644 kernel/kernel/task_work.c create mode 100644 kernel/kernel/taskstats.c create mode 100644 kernel/kernel/test_kprobes.c create mode 100644 kernel/kernel/time/Kconfig create mode 100644 kernel/kernel/time/Makefile create mode 100644 kernel/kernel/time/alarmtimer.c create mode 100644 kernel/kernel/time/clockevents.c create mode 100644 kernel/kernel/time/clocksource.c create mode 100644 kernel/kernel/time/hrtimer.c create mode 100644 kernel/kernel/time/itimer.c create mode 100644 kernel/kernel/time/jiffies.c create mode 100644 kernel/kernel/time/ntp.c create mode 100644 kernel/kernel/time/ntp_internal.h create mode 100644 kernel/kernel/time/posix-clock.c create mode 100644 kernel/kernel/time/posix-cpu-timers.c create mode 100644 kernel/kernel/time/posix-timers.c create mode 100644 kernel/kernel/time/sched_clock.c create mode 100644 kernel/kernel/time/test_udelay.c create mode 100644 kernel/kernel/time/tick-broadcast-hrtimer.c create mode 100644 kernel/kernel/time/tick-broadcast.c create mode 100644 kernel/kernel/time/tick-common.c create mode 100644 kernel/kernel/time/tick-internal.h create mode 100644 kernel/kernel/time/tick-oneshot.c create mode 100644 kernel/kernel/time/tick-sched.c create mode 100644 kernel/kernel/time/tick-sched.h create mode 100644 kernel/kernel/time/time.c create mode 100644 kernel/kernel/time/timeconst.bc create mode 100644 kernel/kernel/time/timeconv.c create mode 100644 kernel/kernel/time/timecounter.c create mode 100644 kernel/kernel/time/timekeeping.c create mode 100644 kernel/kernel/time/timekeeping.h create mode 100644 kernel/kernel/time/timekeeping_debug.c create mode 100644 kernel/kernel/time/timekeeping_internal.h create mode 100644 kernel/kernel/time/timer.c create mode 100644 kernel/kernel/time/timer_list.c create mode 100644 kernel/kernel/time/timer_stats.c create mode 100644 kernel/kernel/torture.c create mode 100644 kernel/kernel/trace/Kconfig create mode 100644 kernel/kernel/trace/Makefile create mode 100644 kernel/kernel/trace/blktrace.c create mode 100644 kernel/kernel/trace/bpf_trace.c create mode 100644 kernel/kernel/trace/ftrace.c create mode 100644 kernel/kernel/trace/latency_hist.c create mode 100644 kernel/kernel/trace/power-traces.c create mode 100644 kernel/kernel/trace/ring_buffer.c create mode 100644 kernel/kernel/trace/ring_buffer_benchmark.c create mode 100644 kernel/kernel/trace/rpm-traces.c create mode 100644 kernel/kernel/trace/trace.c create mode 100644 kernel/kernel/trace/trace.h create mode 100644 kernel/kernel/trace/trace_benchmark.c create mode 100644 kernel/kernel/trace/trace_benchmark.h create mode 100644 kernel/kernel/trace/trace_branch.c create mode 100644 kernel/kernel/trace/trace_clock.c create mode 100644 kernel/kernel/trace/trace_entries.h create mode 100644 kernel/kernel/trace/trace_event_perf.c create mode 100644 kernel/kernel/trace/trace_events.c create mode 100644 kernel/kernel/trace/trace_events_filter.c create mode 100644 kernel/kernel/trace/trace_events_filter_test.h create mode 100644 kernel/kernel/trace/trace_events_trigger.c create mode 100644 kernel/kernel/trace/trace_export.c create mode 100644 kernel/kernel/trace/trace_functions.c create mode 100644 kernel/kernel/trace/trace_functions_graph.c create mode 100644 kernel/kernel/trace/trace_irqsoff.c create mode 100644 kernel/kernel/trace/trace_kdb.c create mode 100644 kernel/kernel/trace/trace_kprobe.c create mode 100644 kernel/kernel/trace/trace_mmiotrace.c create mode 100644 kernel/kernel/trace/trace_nop.c create mode 100644 kernel/kernel/trace/trace_output.c create mode 100644 kernel/kernel/trace/trace_output.h create mode 100644 kernel/kernel/trace/trace_printk.c create mode 100644 kernel/kernel/trace/trace_probe.c create mode 100644 kernel/kernel/trace/trace_probe.h create mode 100644 kernel/kernel/trace/trace_sched_switch.c create mode 100644 kernel/kernel/trace/trace_sched_wakeup.c create mode 100644 kernel/kernel/trace/trace_selftest.c create mode 100644 kernel/kernel/trace/trace_selftest_dynamic.c create mode 100644 kernel/kernel/trace/trace_seq.c create mode 100644 kernel/kernel/trace/trace_stack.c create mode 100644 kernel/kernel/trace/trace_stat.c create mode 100644 kernel/kernel/trace/trace_stat.h create mode 100644 kernel/kernel/trace/trace_syscalls.c create mode 100644 kernel/kernel/trace/trace_uprobe.c create mode 100644 kernel/kernel/tracepoint.c create mode 100644 kernel/kernel/tsacct.c create mode 100644 kernel/kernel/uid16.c create mode 100644 kernel/kernel/up.c create mode 100644 kernel/kernel/user-return-notifier.c create mode 100644 kernel/kernel/user.c create mode 100644 kernel/kernel/user_namespace.c create mode 100644 kernel/kernel/utsname.c create mode 100644 kernel/kernel/utsname_sysctl.c create mode 100644 kernel/kernel/watchdog.c create mode 100644 kernel/kernel/workqueue.c create mode 100644 kernel/kernel/workqueue_internal.h (limited to 'kernel/kernel') diff --git a/kernel/kernel/.gitignore b/kernel/kernel/.gitignore new file mode 100644 index 000000000..790d83c7d --- /dev/null +++ b/kernel/kernel/.gitignore @@ -0,0 +1,8 @@ +# +# Generated files +# +config_data.h +config_data.gz +timeconst.h +hz.bc +x509_certificate_list diff --git a/kernel/kernel/Kconfig.freezer b/kernel/kernel/Kconfig.freezer new file mode 100644 index 000000000..a3bb4cb52 --- /dev/null +++ b/kernel/kernel/Kconfig.freezer @@ -0,0 +1,2 @@ +config FREEZER + def_bool PM_SLEEP || CGROUP_FREEZER diff --git a/kernel/kernel/Kconfig.hz b/kernel/kernel/Kconfig.hz new file mode 100644 index 000000000..2a202a846 --- /dev/null +++ b/kernel/kernel/Kconfig.hz @@ -0,0 +1,58 @@ +# +# Timer Interrupt Frequency Configuration +# + +choice + prompt "Timer frequency" + default HZ_250 + help + Allows the configuration of the timer frequency. It is customary + to have the timer interrupt run at 1000 Hz but 100 Hz may be more + beneficial for servers and NUMA systems that do not need to have + a fast response for user interaction and that may experience bus + contention and cacheline bounces as a result of timer interrupts. + Note that the timer interrupt occurs on each processor in an SMP + environment leading to NR_CPUS * HZ number of timer interrupts + per second. + + + config HZ_100 + bool "100 HZ" + help + 100 Hz is a typical choice for servers, SMP and NUMA systems + with lots of processors that may show reduced performance if + too many timer interrupts are occurring. + + config HZ_250 + bool "250 HZ" + help + 250 Hz is a good compromise choice allowing server performance + while also showing good interactive responsiveness even + on SMP and NUMA systems. If you are going to be using NTSC video + or multimedia, selected 300Hz instead. + + config HZ_300 + bool "300 HZ" + help + 300 Hz is a good compromise choice allowing server performance + while also showing good interactive responsiveness even + on SMP and NUMA systems and exactly dividing by both PAL and + NTSC frame rates for video and multimedia work. + + config HZ_1000 + bool "1000 HZ" + help + 1000 Hz is the preferred choice for desktop systems and other + systems requiring fast interactive responses to events. + +endchoice + +config HZ + int + default 100 if HZ_100 + default 250 if HZ_250 + default 300 if HZ_300 + default 1000 if HZ_1000 + +config SCHED_HRTICK + def_bool HIGH_RES_TIMERS diff --git a/kernel/kernel/Kconfig.locks b/kernel/kernel/Kconfig.locks new file mode 100644 index 000000000..c61e9131e --- /dev/null +++ b/kernel/kernel/Kconfig.locks @@ -0,0 +1,243 @@ +# +# The ARCH_INLINE foo is necessary because select ignores "depends on" +# +config ARCH_INLINE_SPIN_TRYLOCK + bool + +config ARCH_INLINE_SPIN_TRYLOCK_BH + bool + +config ARCH_INLINE_SPIN_LOCK + bool + +config ARCH_INLINE_SPIN_LOCK_BH + bool + +config ARCH_INLINE_SPIN_LOCK_IRQ + bool + +config ARCH_INLINE_SPIN_LOCK_IRQSAVE + bool + +config ARCH_INLINE_SPIN_UNLOCK + bool + +config ARCH_INLINE_SPIN_UNLOCK_BH + bool + +config ARCH_INLINE_SPIN_UNLOCK_IRQ + bool + +config ARCH_INLINE_SPIN_UNLOCK_IRQRESTORE + bool + + +config ARCH_INLINE_READ_TRYLOCK + bool + +config ARCH_INLINE_READ_LOCK + bool + +config ARCH_INLINE_READ_LOCK_BH + bool + +config ARCH_INLINE_READ_LOCK_IRQ + bool + +config ARCH_INLINE_READ_LOCK_IRQSAVE + bool + +config ARCH_INLINE_READ_UNLOCK + bool + +config ARCH_INLINE_READ_UNLOCK_BH + bool + +config ARCH_INLINE_READ_UNLOCK_IRQ + bool + +config ARCH_INLINE_READ_UNLOCK_IRQRESTORE + bool + + +config ARCH_INLINE_WRITE_TRYLOCK + bool + +config ARCH_INLINE_WRITE_LOCK + bool + +config ARCH_INLINE_WRITE_LOCK_BH + bool + +config ARCH_INLINE_WRITE_LOCK_IRQ + bool + +config ARCH_INLINE_WRITE_LOCK_IRQSAVE + bool + +config ARCH_INLINE_WRITE_UNLOCK + bool + +config ARCH_INLINE_WRITE_UNLOCK_BH + bool + +config ARCH_INLINE_WRITE_UNLOCK_IRQ + bool + +config ARCH_INLINE_WRITE_UNLOCK_IRQRESTORE + bool + +config UNINLINE_SPIN_UNLOCK + bool + +# +# lock_* functions are inlined when: +# - DEBUG_SPINLOCK=n and GENERIC_LOCKBREAK=n and ARCH_INLINE_*LOCK=y +# +# trylock_* functions are inlined when: +# - DEBUG_SPINLOCK=n and ARCH_INLINE_*LOCK=y +# +# unlock and unlock_irq functions are inlined when: +# - DEBUG_SPINLOCK=n and ARCH_INLINE_*LOCK=y +# or +# - DEBUG_SPINLOCK=n and PREEMPT=n +# +# unlock_bh and unlock_irqrestore functions are inlined when: +# - DEBUG_SPINLOCK=n and ARCH_INLINE_*LOCK=y +# + +if !DEBUG_SPINLOCK + +config INLINE_SPIN_TRYLOCK + def_bool y + depends on ARCH_INLINE_SPIN_TRYLOCK + +config INLINE_SPIN_TRYLOCK_BH + def_bool y + depends on ARCH_INLINE_SPIN_TRYLOCK_BH + +config INLINE_SPIN_LOCK + def_bool y + depends on !GENERIC_LOCKBREAK && ARCH_INLINE_SPIN_LOCK + +config INLINE_SPIN_LOCK_BH + def_bool y + depends on !GENERIC_LOCKBREAK && ARCH_INLINE_SPIN_LOCK_BH + +config INLINE_SPIN_LOCK_IRQ + def_bool y + depends on !GENERIC_LOCKBREAK && ARCH_INLINE_SPIN_LOCK_IRQ + +config INLINE_SPIN_LOCK_IRQSAVE + def_bool y + depends on !GENERIC_LOCKBREAK && ARCH_INLINE_SPIN_LOCK_IRQSAVE + +config INLINE_SPIN_UNLOCK_BH + def_bool y + depends on ARCH_INLINE_SPIN_UNLOCK_BH + +config INLINE_SPIN_UNLOCK_IRQ + def_bool y + depends on !PREEMPT || ARCH_INLINE_SPIN_UNLOCK_IRQ + +config INLINE_SPIN_UNLOCK_IRQRESTORE + def_bool y + depends on ARCH_INLINE_SPIN_UNLOCK_IRQRESTORE + + +config INLINE_READ_TRYLOCK + def_bool y + depends on ARCH_INLINE_READ_TRYLOCK + +config INLINE_READ_LOCK + def_bool y + depends on !GENERIC_LOCKBREAK && ARCH_INLINE_READ_LOCK + +config INLINE_READ_LOCK_BH + def_bool y + depends on !GENERIC_LOCKBREAK && ARCH_INLINE_READ_LOCK_BH + +config INLINE_READ_LOCK_IRQ + def_bool y + depends on !GENERIC_LOCKBREAK && ARCH_INLINE_READ_LOCK_IRQ + +config INLINE_READ_LOCK_IRQSAVE + def_bool y + depends on !GENERIC_LOCKBREAK && ARCH_INLINE_READ_LOCK_IRQSAVE + +config INLINE_READ_UNLOCK + def_bool y + depends on !PREEMPT || ARCH_INLINE_READ_UNLOCK + +config INLINE_READ_UNLOCK_BH + def_bool y + depends on ARCH_INLINE_READ_UNLOCK_BH + +config INLINE_READ_UNLOCK_IRQ + def_bool y + depends on !PREEMPT || ARCH_INLINE_READ_UNLOCK_IRQ + +config INLINE_READ_UNLOCK_IRQRESTORE + def_bool y + depends on ARCH_INLINE_READ_UNLOCK_IRQRESTORE + + +config INLINE_WRITE_TRYLOCK + def_bool y + depends on ARCH_INLINE_WRITE_TRYLOCK + +config INLINE_WRITE_LOCK + def_bool y + depends on !GENERIC_LOCKBREAK && ARCH_INLINE_WRITE_LOCK + +config INLINE_WRITE_LOCK_BH + def_bool y + depends on !GENERIC_LOCKBREAK && ARCH_INLINE_WRITE_LOCK_BH + +config INLINE_WRITE_LOCK_IRQ + def_bool y + depends on !GENERIC_LOCKBREAK && ARCH_INLINE_WRITE_LOCK_IRQ + +config INLINE_WRITE_LOCK_IRQSAVE + def_bool y + depends on !GENERIC_LOCKBREAK && ARCH_INLINE_WRITE_LOCK_IRQSAVE + +config INLINE_WRITE_UNLOCK + def_bool y + depends on !PREEMPT || ARCH_INLINE_WRITE_UNLOCK + +config INLINE_WRITE_UNLOCK_BH + def_bool y + depends on ARCH_INLINE_WRITE_UNLOCK_BH + +config INLINE_WRITE_UNLOCK_IRQ + def_bool y + depends on !PREEMPT || ARCH_INLINE_WRITE_UNLOCK_IRQ + +config INLINE_WRITE_UNLOCK_IRQRESTORE + def_bool y + depends on ARCH_INLINE_WRITE_UNLOCK_IRQRESTORE + +endif + +config ARCH_SUPPORTS_ATOMIC_RMW + bool + +config MUTEX_SPIN_ON_OWNER + def_bool y + depends on SMP && !DEBUG_MUTEXES && ARCH_SUPPORTS_ATOMIC_RMW && !PREEMPT_RT_FULL + +config RWSEM_SPIN_ON_OWNER + def_bool y + depends on SMP && RWSEM_XCHGADD_ALGORITHM && ARCH_SUPPORTS_ATOMIC_RMW && !PREEMPT_RT_FULL + +config LOCK_SPIN_ON_OWNER + def_bool y + depends on MUTEX_SPIN_ON_OWNER || RWSEM_SPIN_ON_OWNER + +config ARCH_USE_QUEUE_RWLOCK + bool + +config QUEUE_RWLOCK + def_bool y if ARCH_USE_QUEUE_RWLOCK + depends on SMP diff --git a/kernel/kernel/Kconfig.preempt b/kernel/kernel/Kconfig.preempt new file mode 100644 index 000000000..11dbe26a8 --- /dev/null +++ b/kernel/kernel/Kconfig.preempt @@ -0,0 +1,87 @@ +config PREEMPT + bool + select PREEMPT_COUNT + +config PREEMPT_RT_BASE + bool + select PREEMPT + +config HAVE_PREEMPT_LAZY + bool + +config PREEMPT_LAZY + def_bool y if HAVE_PREEMPT_LAZY && PREEMPT_RT_FULL + +choice + prompt "Preemption Model" + default PREEMPT_NONE + +config PREEMPT_NONE + bool "No Forced Preemption (Server)" + help + This is the traditional Linux preemption model, geared towards + throughput. It will still provide good latencies most of the + time, but there are no guarantees and occasional longer delays + are possible. + + Select this option if you are building a kernel for a server or + scientific/computation system, or if you want to maximize the + raw processing power of the kernel, irrespective of scheduling + latencies. + +config PREEMPT_VOLUNTARY + bool "Voluntary Kernel Preemption (Desktop)" + help + This option reduces the latency of the kernel by adding more + "explicit preemption points" to the kernel code. These new + preemption points have been selected to reduce the maximum + latency of rescheduling, providing faster application reactions, + at the cost of slightly lower throughput. + + This allows reaction to interactive events by allowing a + low priority process to voluntarily preempt itself even if it + is in kernel mode executing a system call. This allows + applications to run more 'smoothly' even when the system is + under load. + + Select this if you are building a kernel for a desktop system. + +config PREEMPT__LL + bool "Preemptible Kernel (Low-Latency Desktop)" + select PREEMPT + select UNINLINE_SPIN_UNLOCK if !ARCH_INLINE_SPIN_UNLOCK + help + This option reduces the latency of the kernel by making + all kernel code (that is not executing in a critical section) + preemptible. This allows reaction to interactive events by + permitting a low priority process to be preempted involuntarily + even if it is in kernel mode executing a system call and would + otherwise not be about to reach a natural preemption point. + This allows applications to run more 'smoothly' even when the + system is under load, at the cost of slightly lower throughput + and a slight runtime overhead to kernel code. + + Select this if you are building a kernel for a desktop or + embedded system with latency requirements in the milliseconds + range. + +config PREEMPT_RTB + bool "Preemptible Kernel (Basic RT)" + select PREEMPT_RT_BASE + help + This option is basically the same as (Low-Latency Desktop) but + enables changes which are preliminary for the full preemptible + RT kernel. + +config PREEMPT_RT_FULL + bool "Fully Preemptible Kernel (RT)" + depends on IRQ_FORCED_THREADING + select PREEMPT_RT_BASE + select PREEMPT_RCU + help + All and everything + +endchoice + +config PREEMPT_COUNT + bool \ No newline at end of file diff --git a/kernel/kernel/Makefile b/kernel/kernel/Makefile new file mode 100644 index 000000000..60c302cfb --- /dev/null +++ b/kernel/kernel/Makefile @@ -0,0 +1,209 @@ +# +# Makefile for the linux kernel. +# + +obj-y = fork.o exec_domain.o panic.o \ + cpu.o exit.o softirq.o resource.o \ + sysctl.o sysctl_binary.o capability.o ptrace.o user.o \ + signal.o sys.o kmod.o workqueue.o pid.o task_work.o \ + extable.o params.o \ + kthread.o sys_ni.o nsproxy.o \ + notifier.o ksysfs.o cred.o reboot.o \ + async.o range.o smpboot.o + +obj-$(CONFIG_MULTIUSER) += groups.o + +ifdef CONFIG_FUNCTION_TRACER +# Do not trace debug files and internal ftrace files +CFLAGS_REMOVE_cgroup-debug.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_irq_work.o = $(CC_FLAGS_FTRACE) +endif + +# cond_syscall is currently not LTO compatible +CFLAGS_sys_ni.o = $(DISABLE_LTO) + +obj-y += sched/ +obj-y += locking/ +obj-y += power/ +obj-y += printk/ +obj-y += irq/ +obj-y += rcu/ +obj-y += livepatch/ + +obj-$(CONFIG_CHECKPOINT_RESTORE) += kcmp.o +obj-$(CONFIG_FREEZER) += freezer.o +obj-$(CONFIG_PROFILING) += profile.o +obj-$(CONFIG_STACKTRACE) += stacktrace.o +obj-y += time/ +obj-$(CONFIG_FUTEX) += futex.o +ifeq ($(CONFIG_COMPAT),y) +obj-$(CONFIG_FUTEX) += futex_compat.o +endif +obj-$(CONFIG_GENERIC_ISA_DMA) += dma.o +obj-$(CONFIG_SMP) += smp.o +ifneq ($(CONFIG_SMP),y) +obj-y += up.o +endif +obj-$(CONFIG_UID16) += uid16.o +obj-$(CONFIG_SYSTEM_TRUSTED_KEYRING) += system_keyring.o system_certificates.o +obj-$(CONFIG_MODULES) += module.o +obj-$(CONFIG_MODULE_SIG) += module_signing.o +obj-$(CONFIG_KALLSYMS) += kallsyms.o +obj-$(CONFIG_BSD_PROCESS_ACCT) += acct.o +obj-$(CONFIG_KEXEC) += kexec.o +obj-$(CONFIG_BACKTRACE_SELF_TEST) += backtracetest.o +obj-$(CONFIG_COMPAT) += compat.o +obj-$(CONFIG_CGROUPS) += cgroup.o +obj-$(CONFIG_CGROUP_FREEZER) += cgroup_freezer.o +obj-$(CONFIG_CPUSETS) += cpuset.o +obj-$(CONFIG_UTS_NS) += utsname.o +obj-$(CONFIG_USER_NS) += user_namespace.o +obj-$(CONFIG_PID_NS) += pid_namespace.o +obj-$(CONFIG_IKCONFIG) += configs.o +obj-$(CONFIG_SMP) += stop_machine.o +obj-$(CONFIG_KPROBES_SANITY_TEST) += test_kprobes.o +obj-$(CONFIG_AUDIT) += audit.o auditfilter.o +obj-$(CONFIG_AUDITSYSCALL) += auditsc.o +obj-$(CONFIG_AUDIT_WATCH) += audit_watch.o +obj-$(CONFIG_AUDIT_TREE) += audit_tree.o +obj-$(CONFIG_GCOV_KERNEL) += gcov/ +obj-$(CONFIG_KPROBES) += kprobes.o +obj-$(CONFIG_KGDB) += debug/ +obj-$(CONFIG_DETECT_HUNG_TASK) += hung_task.o +obj-$(CONFIG_LOCKUP_DETECTOR) += watchdog.o +obj-$(CONFIG_SECCOMP) += seccomp.o +obj-$(CONFIG_RELAY) += relay.o +obj-$(CONFIG_SYSCTL) += utsname_sysctl.o +obj-$(CONFIG_TASK_DELAY_ACCT) += delayacct.o +obj-$(CONFIG_TASKSTATS) += taskstats.o tsacct.o +obj-$(CONFIG_TRACEPOINTS) += tracepoint.o +obj-$(CONFIG_LATENCYTOP) += latencytop.o +obj-$(CONFIG_BINFMT_ELF) += elfcore.o +obj-$(CONFIG_COMPAT_BINFMT_ELF) += elfcore.o +obj-$(CONFIG_BINFMT_ELF_FDPIC) += elfcore.o +obj-$(CONFIG_FUNCTION_TRACER) += trace/ +obj-$(CONFIG_TRACING) += trace/ +obj-$(CONFIG_TRACE_CLOCK) += trace/ +obj-$(CONFIG_RING_BUFFER) += trace/ +obj-$(CONFIG_TRACEPOINTS) += trace/ +obj-$(CONFIG_IRQ_WORK) += irq_work.o +obj-$(CONFIG_CPU_PM) += cpu_pm.o +obj-$(CONFIG_BPF) += bpf/ + +obj-$(CONFIG_PERF_EVENTS) += events/ + +obj-$(CONFIG_USER_RETURN_NOTIFIER) += user-return-notifier.o +obj-$(CONFIG_PADATA) += padata.o +obj-$(CONFIG_CRASH_DUMP) += crash_dump.o +obj-$(CONFIG_JUMP_LABEL) += jump_label.o +obj-$(CONFIG_CONTEXT_TRACKING) += context_tracking.o +obj-$(CONFIG_TORTURE_TEST) += torture.o + +$(obj)/configs.o: $(obj)/config_data.h + +# config_data.h contains the same information as ikconfig.h but gzipped. +# Info from config_data can be extracted from /proc/config* +targets += config_data.gz +$(obj)/config_data.gz: $(KCONFIG_CONFIG) FORCE + $(call if_changed,gzip) + + filechk_ikconfiggz = (echo "static const char kernel_config_data[] __used = MAGIC_START"; cat $< | scripts/basic/bin2c; echo "MAGIC_END;") +targets += config_data.h +$(obj)/config_data.h: $(obj)/config_data.gz FORCE + $(call filechk,ikconfiggz) + +############################################################################### +# +# Roll all the X.509 certificates that we can find together and pull them into +# the kernel so that they get loaded into the system trusted keyring during +# boot. +# +# We look in the source root and the build root for all files whose name ends +# in ".x509". Unfortunately, this will generate duplicate filenames, so we +# have make canonicalise the pathnames and then sort them to discard the +# duplicates. +# +############################################################################### +ifeq ($(CONFIG_SYSTEM_TRUSTED_KEYRING),y) +X509_CERTIFICATES-y := $(wildcard *.x509) $(wildcard $(srctree)/*.x509) +X509_CERTIFICATES-$(CONFIG_MODULE_SIG) += $(objtree)/signing_key.x509 +X509_CERTIFICATES-raw := $(sort $(foreach CERT,$(X509_CERTIFICATES-y), \ + $(or $(realpath $(CERT)),$(CERT)))) +X509_CERTIFICATES := $(subst $(realpath $(objtree))/,,$(X509_CERTIFICATES-raw)) + +ifeq ($(X509_CERTIFICATES),) +$(warning *** No X.509 certificates found ***) +endif + +ifneq ($(wildcard $(obj)/.x509.list),) +ifneq ($(shell cat $(obj)/.x509.list),$(X509_CERTIFICATES)) +$(info X.509 certificate list changed) +$(shell rm $(obj)/.x509.list) +endif +endif + +kernel/system_certificates.o: $(obj)/x509_certificate_list + +quiet_cmd_x509certs = CERTS $@ + cmd_x509certs = cat $(X509_CERTIFICATES) /dev/null >$@ $(foreach X509,$(X509_CERTIFICATES),; $(kecho) " - Including cert $(X509)") + +targets += $(obj)/x509_certificate_list +$(obj)/x509_certificate_list: $(X509_CERTIFICATES) $(obj)/.x509.list + $(call if_changed,x509certs) + +targets += $(obj)/.x509.list +$(obj)/.x509.list: + @echo $(X509_CERTIFICATES) >$@ +endif + +clean-files := x509_certificate_list .x509.list + +ifeq ($(CONFIG_MODULE_SIG),y) +############################################################################### +# +# If module signing is requested, say by allyesconfig, but a key has not been +# supplied, then one will need to be generated to make sure the build does not +# fail and that the kernel may be used afterwards. +# +############################################################################### +ifndef CONFIG_MODULE_SIG_HASH +$(error Could not determine digest type to use from kernel config) +endif + +signing_key.priv signing_key.x509: x509.genkey + @echo "###" + @echo "### Now generating an X.509 key pair to be used for signing modules." + @echo "###" + @echo "### If this takes a long time, you might wish to run rngd in the" + @echo "### background to keep the supply of entropy topped up. It" + @echo "### needs to be run as root, and uses a hardware random" + @echo "### number generator if one is available." + @echo "###" + openssl req -new -nodes -utf8 -$(CONFIG_MODULE_SIG_HASH) -days 36500 \ + -batch -x509 -config x509.genkey \ + -outform DER -out signing_key.x509 \ + -keyout signing_key.priv 2>&1 + @echo "###" + @echo "### Key pair generated." + @echo "###" + +x509.genkey: + @echo Generating X.509 key generation config + @echo >x509.genkey "[ req ]" + @echo >>x509.genkey "default_bits = 4096" + @echo >>x509.genkey "distinguished_name = req_distinguished_name" + @echo >>x509.genkey "prompt = no" + @echo >>x509.genkey "string_mask = utf8only" + @echo >>x509.genkey "x509_extensions = myexts" + @echo >>x509.genkey + @echo >>x509.genkey "[ req_distinguished_name ]" + @echo >>x509.genkey "#O = Unspecified company" + @echo >>x509.genkey "CN = Build time autogenerated kernel key" + @echo >>x509.genkey "#emailAddress = unspecified.user@unspecified.company" + @echo >>x509.genkey + @echo >>x509.genkey "[ myexts ]" + @echo >>x509.genkey "basicConstraints=critical,CA:FALSE" + @echo >>x509.genkey "keyUsage=digitalSignature" + @echo >>x509.genkey "subjectKeyIdentifier=hash" + @echo >>x509.genkey "authorityKeyIdentifier=keyid" +endif diff --git a/kernel/kernel/acct.c b/kernel/kernel/acct.c new file mode 100644 index 000000000..74963d192 --- /dev/null +++ b/kernel/kernel/acct.c @@ -0,0 +1,602 @@ +/* + * linux/kernel/acct.c + * + * BSD Process Accounting for Linux + * + * Author: Marco van Wieringen + * + * Some code based on ideas and code from: + * Thomas K. Dyas + * + * This file implements BSD-style process accounting. Whenever any + * process exits, an accounting record of type "struct acct" is + * written to the file specified with the acct() system call. It is + * up to user-level programs to do useful things with the accounting + * log. The kernel just provides the raw accounting information. + * + * (C) Copyright 1995 - 1997 Marco van Wieringen - ELM Consultancy B.V. + * + * Plugged two leaks. 1) It didn't return acct_file into the free_filps if + * the file happened to be read-only. 2) If the accounting was suspended + * due to the lack of space it happily allowed to reopen it and completely + * lost the old acct_file. 3/10/98, Al Viro. + * + * Now we silently close acct_file on attempt to reopen. Cleaned sys_acct(). + * XTerms and EMACS are manifestations of pure evil. 21/10/98, AV. + * + * Fixed a nasty interaction with with sys_umount(). If the accointing + * was suspeneded we failed to stop it on umount(). Messy. + * Another one: remount to readonly didn't stop accounting. + * Question: what should we do if we have CAP_SYS_ADMIN but not + * CAP_SYS_PACCT? Current code does the following: umount returns -EBUSY + * unless we are messing with the root. In that case we are getting a + * real mess with do_remount_sb(). 9/11/98, AV. + * + * Fixed a bunch of races (and pair of leaks). Probably not the best way, + * but this one obviously doesn't introduce deadlocks. Later. BTW, found + * one race (and leak) in BSD implementation. + * OK, that's better. ANOTHER race and leak in BSD variant. There always + * is one more bug... 10/11/98, AV. + * + * Oh, fsck... Oopsable SMP race in do_process_acct() - we must hold + * ->mmap_sem to walk the vma list of current->mm. Nasty, since it leaks + * a struct file opened for write. Fixed. 2/6/2000, AV. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include /* sector_div */ +#include +#include + +/* + * These constants control the amount of freespace that suspend and + * resume the process accounting system, and the time delay between + * each check. + * Turned into sysctl-controllable parameters. AV, 12/11/98 + */ + +int acct_parm[3] = {4, 2, 30}; +#define RESUME (acct_parm[0]) /* >foo% free space - resume */ +#define SUSPEND (acct_parm[1]) /* needcheck)) + goto out; + + /* May block */ + if (vfs_statfs(&acct->file->f_path, &sbuf)) + goto out; + + if (acct->active) { + u64 suspend = sbuf.f_blocks * SUSPEND; + do_div(suspend, 100); + if (sbuf.f_bavail <= suspend) { + acct->active = 0; + pr_info("Process accounting paused\n"); + } + } else { + u64 resume = sbuf.f_blocks * RESUME; + do_div(resume, 100); + if (sbuf.f_bavail >= resume) { + acct->active = 1; + pr_info("Process accounting resumed\n"); + } + } + + acct->needcheck = jiffies + ACCT_TIMEOUT*HZ; +out: + return acct->active; +} + +static void acct_put(struct bsd_acct_struct *p) +{ + if (atomic_long_dec_and_test(&p->count)) + kfree_rcu(p, rcu); +} + +static inline struct bsd_acct_struct *to_acct(struct fs_pin *p) +{ + return p ? container_of(p, struct bsd_acct_struct, pin) : NULL; +} + +static struct bsd_acct_struct *acct_get(struct pid_namespace *ns) +{ + struct bsd_acct_struct *res; +again: + smp_rmb(); + rcu_read_lock(); + res = to_acct(ACCESS_ONCE(ns->bacct)); + if (!res) { + rcu_read_unlock(); + return NULL; + } + if (!atomic_long_inc_not_zero(&res->count)) { + rcu_read_unlock(); + cpu_relax(); + goto again; + } + rcu_read_unlock(); + mutex_lock(&res->lock); + if (res != to_acct(ACCESS_ONCE(ns->bacct))) { + mutex_unlock(&res->lock); + acct_put(res); + goto again; + } + return res; +} + +static void acct_pin_kill(struct fs_pin *pin) +{ + struct bsd_acct_struct *acct = to_acct(pin); + mutex_lock(&acct->lock); + do_acct_process(acct); + schedule_work(&acct->work); + wait_for_completion(&acct->done); + cmpxchg(&acct->ns->bacct, pin, NULL); + mutex_unlock(&acct->lock); + pin_remove(pin); + acct_put(acct); +} + +static void close_work(struct work_struct *work) +{ + struct bsd_acct_struct *acct = container_of(work, struct bsd_acct_struct, work); + struct file *file = acct->file; + if (file->f_op->flush) + file->f_op->flush(file, NULL); + __fput_sync(file); + complete(&acct->done); +} + +static int acct_on(struct filename *pathname) +{ + struct file *file; + struct vfsmount *mnt, *internal; + struct pid_namespace *ns = task_active_pid_ns(current); + struct bsd_acct_struct *acct; + struct fs_pin *old; + int err; + + acct = kzalloc(sizeof(struct bsd_acct_struct), GFP_KERNEL); + if (!acct) + return -ENOMEM; + + /* Difference from BSD - they don't do O_APPEND */ + file = file_open_name(pathname, O_WRONLY|O_APPEND|O_LARGEFILE, 0); + if (IS_ERR(file)) { + kfree(acct); + return PTR_ERR(file); + } + + if (!S_ISREG(file_inode(file)->i_mode)) { + kfree(acct); + filp_close(file, NULL); + return -EACCES; + } + + if (!(file->f_mode & FMODE_CAN_WRITE)) { + kfree(acct); + filp_close(file, NULL); + return -EIO; + } + internal = mnt_clone_internal(&file->f_path); + if (IS_ERR(internal)) { + kfree(acct); + filp_close(file, NULL); + return PTR_ERR(internal); + } + err = mnt_want_write(internal); + if (err) { + mntput(internal); + kfree(acct); + filp_close(file, NULL); + return err; + } + mnt = file->f_path.mnt; + file->f_path.mnt = internal; + + atomic_long_set(&acct->count, 1); + init_fs_pin(&acct->pin, acct_pin_kill); + acct->file = file; + acct->needcheck = jiffies; + acct->ns = ns; + mutex_init(&acct->lock); + INIT_WORK(&acct->work, close_work); + init_completion(&acct->done); + mutex_lock_nested(&acct->lock, 1); /* nobody has seen it yet */ + pin_insert(&acct->pin, mnt); + + rcu_read_lock(); + old = xchg(&ns->bacct, &acct->pin); + mutex_unlock(&acct->lock); + pin_kill(old); + mnt_drop_write(mnt); + mntput(mnt); + return 0; +} + +static DEFINE_MUTEX(acct_on_mutex); + +/** + * sys_acct - enable/disable process accounting + * @name: file name for accounting records or NULL to shutdown accounting + * + * Returns 0 for success or negative errno values for failure. + * + * sys_acct() is the only system call needed to implement process + * accounting. It takes the name of the file where accounting records + * should be written. If the filename is NULL, accounting will be + * shutdown. + */ +SYSCALL_DEFINE1(acct, const char __user *, name) +{ + int error = 0; + + if (!capable(CAP_SYS_PACCT)) + return -EPERM; + + if (name) { + struct filename *tmp = getname(name); + + if (IS_ERR(tmp)) + return PTR_ERR(tmp); + mutex_lock(&acct_on_mutex); + error = acct_on(tmp); + mutex_unlock(&acct_on_mutex); + putname(tmp); + } else { + rcu_read_lock(); + pin_kill(task_active_pid_ns(current)->bacct); + } + + return error; +} + +void acct_exit_ns(struct pid_namespace *ns) +{ + rcu_read_lock(); + pin_kill(ns->bacct); +} + +/* + * encode an unsigned long into a comp_t + * + * This routine has been adopted from the encode_comp_t() function in + * the kern_acct.c file of the FreeBSD operating system. The encoding + * is a 13-bit fraction with a 3-bit (base 8) exponent. + */ + +#define MANTSIZE 13 /* 13 bit mantissa. */ +#define EXPSIZE 3 /* Base 8 (3 bit) exponent. */ +#define MAXFRACT ((1 << MANTSIZE) - 1) /* Maximum fractional value. */ + +static comp_t encode_comp_t(unsigned long value) +{ + int exp, rnd; + + exp = rnd = 0; + while (value > MAXFRACT) { + rnd = value & (1 << (EXPSIZE - 1)); /* Round up? */ + value >>= EXPSIZE; /* Base 8 exponent == 3 bit shift. */ + exp++; + } + + /* + * If we need to round up, do it (and handle overflow correctly). + */ + if (rnd && (++value > MAXFRACT)) { + value >>= EXPSIZE; + exp++; + } + + /* + * Clean it up and polish it off. + */ + exp <<= MANTSIZE; /* Shift the exponent into place */ + exp += value; /* and add on the mantissa. */ + return exp; +} + +#if ACCT_VERSION == 1 || ACCT_VERSION == 2 +/* + * encode an u64 into a comp2_t (24 bits) + * + * Format: 5 bit base 2 exponent, 20 bits mantissa. + * The leading bit of the mantissa is not stored, but implied for + * non-zero exponents. + * Largest encodable value is 50 bits. + */ + +#define MANTSIZE2 20 /* 20 bit mantissa. */ +#define EXPSIZE2 5 /* 5 bit base 2 exponent. */ +#define MAXFRACT2 ((1ul << MANTSIZE2) - 1) /* Maximum fractional value. */ +#define MAXEXP2 ((1 << EXPSIZE2) - 1) /* Maximum exponent. */ + +static comp2_t encode_comp2_t(u64 value) +{ + int exp, rnd; + + exp = (value > (MAXFRACT2>>1)); + rnd = 0; + while (value > MAXFRACT2) { + rnd = value & 1; + value >>= 1; + exp++; + } + + /* + * If we need to round up, do it (and handle overflow correctly). + */ + if (rnd && (++value > MAXFRACT2)) { + value >>= 1; + exp++; + } + + if (exp > MAXEXP2) { + /* Overflow. Return largest representable number instead. */ + return (1ul << (MANTSIZE2+EXPSIZE2-1)) - 1; + } else { + return (value & (MAXFRACT2>>1)) | (exp << (MANTSIZE2-1)); + } +} +#endif + +#if ACCT_VERSION == 3 +/* + * encode an u64 into a 32 bit IEEE float + */ +static u32 encode_float(u64 value) +{ + unsigned exp = 190; + unsigned u; + + if (value == 0) + return 0; + while ((s64)value > 0) { + value <<= 1; + exp--; + } + u = (u32)(value >> 40) & 0x7fffffu; + return u | (exp << 23); +} +#endif + +/* + * Write an accounting entry for an exiting process + * + * The acct_process() call is the workhorse of the process + * accounting system. The struct acct is built here and then written + * into the accounting file. This function should only be called from + * do_exit() or when switching to a different output file. + */ + +static void fill_ac(acct_t *ac) +{ + struct pacct_struct *pacct = ¤t->signal->pacct; + u64 elapsed, run_time; + struct tty_struct *tty; + + /* + * Fill the accounting struct with the needed info as recorded + * by the different kernel functions. + */ + memset(ac, 0, sizeof(acct_t)); + + ac->ac_version = ACCT_VERSION | ACCT_BYTEORDER; + strlcpy(ac->ac_comm, current->comm, sizeof(ac->ac_comm)); + + /* calculate run_time in nsec*/ + run_time = ktime_get_ns(); + run_time -= current->group_leader->start_time; + /* convert nsec -> AHZ */ + elapsed = nsec_to_AHZ(run_time); +#if ACCT_VERSION == 3 + ac->ac_etime = encode_float(elapsed); +#else + ac->ac_etime = encode_comp_t(elapsed < (unsigned long) -1l ? + (unsigned long) elapsed : (unsigned long) -1l); +#endif +#if ACCT_VERSION == 1 || ACCT_VERSION == 2 + { + /* new enlarged etime field */ + comp2_t etime = encode_comp2_t(elapsed); + + ac->ac_etime_hi = etime >> 16; + ac->ac_etime_lo = (u16) etime; + } +#endif + do_div(elapsed, AHZ); + ac->ac_btime = get_seconds() - elapsed; +#if ACCT_VERSION==2 + ac->ac_ahz = AHZ; +#endif + + spin_lock_irq(¤t->sighand->siglock); + tty = current->signal->tty; /* Safe as we hold the siglock */ + ac->ac_tty = tty ? old_encode_dev(tty_devnum(tty)) : 0; + ac->ac_utime = encode_comp_t(jiffies_to_AHZ(cputime_to_jiffies(pacct->ac_utime))); + ac->ac_stime = encode_comp_t(jiffies_to_AHZ(cputime_to_jiffies(pacct->ac_stime))); + ac->ac_flag = pacct->ac_flag; + ac->ac_mem = encode_comp_t(pacct->ac_mem); + ac->ac_minflt = encode_comp_t(pacct->ac_minflt); + ac->ac_majflt = encode_comp_t(pacct->ac_majflt); + ac->ac_exitcode = pacct->ac_exitcode; + spin_unlock_irq(¤t->sighand->siglock); +} +/* + * do_acct_process does all actual work. Caller holds the reference to file. + */ +static void do_acct_process(struct bsd_acct_struct *acct) +{ + acct_t ac; + unsigned long flim; + const struct cred *orig_cred; + struct file *file = acct->file; + + /* + * Accounting records are not subject to resource limits. + */ + flim = current->signal->rlim[RLIMIT_FSIZE].rlim_cur; + current->signal->rlim[RLIMIT_FSIZE].rlim_cur = RLIM_INFINITY; + /* Perform file operations on behalf of whoever enabled accounting */ + orig_cred = override_creds(file->f_cred); + + /* + * First check to see if there is enough free_space to continue + * the process accounting system. + */ + if (!check_free_space(acct)) + goto out; + + fill_ac(&ac); + /* we really need to bite the bullet and change layout */ + ac.ac_uid = from_kuid_munged(file->f_cred->user_ns, orig_cred->uid); + ac.ac_gid = from_kgid_munged(file->f_cred->user_ns, orig_cred->gid); +#if ACCT_VERSION == 1 || ACCT_VERSION == 2 + /* backward-compatible 16 bit fields */ + ac.ac_uid16 = ac.ac_uid; + ac.ac_gid16 = ac.ac_gid; +#endif +#if ACCT_VERSION == 3 + { + struct pid_namespace *ns = acct->ns; + + ac.ac_pid = task_tgid_nr_ns(current, ns); + rcu_read_lock(); + ac.ac_ppid = task_tgid_nr_ns(rcu_dereference(current->real_parent), + ns); + rcu_read_unlock(); + } +#endif + /* + * Get freeze protection. If the fs is frozen, just skip the write + * as we could deadlock the system otherwise. + */ + if (file_start_write_trylock(file)) { + /* it's been opened O_APPEND, so position is irrelevant */ + loff_t pos = 0; + __kernel_write(file, (char *)&ac, sizeof(acct_t), &pos); + file_end_write(file); + } +out: + current->signal->rlim[RLIMIT_FSIZE].rlim_cur = flim; + revert_creds(orig_cred); +} + +/** + * acct_collect - collect accounting information into pacct_struct + * @exitcode: task exit code + * @group_dead: not 0, if this thread is the last one in the process. + */ +void acct_collect(long exitcode, int group_dead) +{ + struct pacct_struct *pacct = ¤t->signal->pacct; + cputime_t utime, stime; + unsigned long vsize = 0; + + if (group_dead && current->mm) { + struct vm_area_struct *vma; + + down_read(¤t->mm->mmap_sem); + vma = current->mm->mmap; + while (vma) { + vsize += vma->vm_end - vma->vm_start; + vma = vma->vm_next; + } + up_read(¤t->mm->mmap_sem); + } + + spin_lock_irq(¤t->sighand->siglock); + if (group_dead) + pacct->ac_mem = vsize / 1024; + if (thread_group_leader(current)) { + pacct->ac_exitcode = exitcode; + if (current->flags & PF_FORKNOEXEC) + pacct->ac_flag |= AFORK; + } + if (current->flags & PF_SUPERPRIV) + pacct->ac_flag |= ASU; + if (current->flags & PF_DUMPCORE) + pacct->ac_flag |= ACORE; + if (current->flags & PF_SIGNALED) + pacct->ac_flag |= AXSIG; + task_cputime(current, &utime, &stime); + pacct->ac_utime += utime; + pacct->ac_stime += stime; + pacct->ac_minflt += current->min_flt; + pacct->ac_majflt += current->maj_flt; + spin_unlock_irq(¤t->sighand->siglock); +} + +static void slow_acct_process(struct pid_namespace *ns) +{ + for ( ; ns; ns = ns->parent) { + struct bsd_acct_struct *acct = acct_get(ns); + if (acct) { + do_acct_process(acct); + mutex_unlock(&acct->lock); + acct_put(acct); + } + } +} + +/** + * acct_process + * + * handles process accounting for an exiting task + */ +void acct_process(void) +{ + struct pid_namespace *ns; + + /* + * This loop is safe lockless, since current is still + * alive and holds its namespace, which in turn holds + * its parent. + */ + for (ns = task_active_pid_ns(current); ns != NULL; ns = ns->parent) { + if (ns->bacct) + break; + } + if (unlikely(ns)) + slow_acct_process(ns); +} diff --git a/kernel/kernel/async.c b/kernel/kernel/async.c new file mode 100644 index 000000000..4c3773c0b --- /dev/null +++ b/kernel/kernel/async.c @@ -0,0 +1,328 @@ +/* + * async.c: Asynchronous function calls for boot performance + * + * (C) Copyright 2009 Intel Corporation + * Author: Arjan van de Ven + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; version 2 + * of the License. + */ + + +/* + +Goals and Theory of Operation + +The primary goal of this feature is to reduce the kernel boot time, +by doing various independent hardware delays and discovery operations +decoupled and not strictly serialized. + +More specifically, the asynchronous function call concept allows +certain operations (primarily during system boot) to happen +asynchronously, out of order, while these operations still +have their externally visible parts happen sequentially and in-order. +(not unlike how out-of-order CPUs retire their instructions in order) + +Key to the asynchronous function call implementation is the concept of +a "sequence cookie" (which, although it has an abstracted type, can be +thought of as a monotonically incrementing number). + +The async core will assign each scheduled event such a sequence cookie and +pass this to the called functions. + +The asynchronously called function should before doing a globally visible +operation, such as registering device numbers, call the +async_synchronize_cookie() function and pass in its own cookie. The +async_synchronize_cookie() function will make sure that all asynchronous +operations that were scheduled prior to the operation corresponding with the +cookie have completed. + +Subsystem/driver initialization code that scheduled asynchronous probe +functions, but which shares global resources with other drivers/subsystems +that do not use the asynchronous call feature, need to do a full +synchronization with the async_synchronize_full() function, before returning +from their init function. This is to maintain strict ordering between the +asynchronous and synchronous parts of the kernel. + +*/ + +#include +#include +#include +#include +#include +#include +#include +#include + +#include "workqueue_internal.h" + +static async_cookie_t next_cookie = 1; + +#define MAX_WORK 32768 +#define ASYNC_COOKIE_MAX ULLONG_MAX /* infinity cookie */ + +static LIST_HEAD(async_global_pending); /* pending from all registered doms */ +static ASYNC_DOMAIN(async_dfl_domain); +static DEFINE_SPINLOCK(async_lock); + +struct async_entry { + struct list_head domain_list; + struct list_head global_list; + struct work_struct work; + async_cookie_t cookie; + async_func_t func; + void *data; + struct async_domain *domain; +}; + +static DECLARE_WAIT_QUEUE_HEAD(async_done); + +static atomic_t entry_count; + +static async_cookie_t lowest_in_progress(struct async_domain *domain) +{ + struct list_head *pending; + async_cookie_t ret = ASYNC_COOKIE_MAX; + unsigned long flags; + + spin_lock_irqsave(&async_lock, flags); + + if (domain) + pending = &domain->pending; + else + pending = &async_global_pending; + + if (!list_empty(pending)) + ret = list_first_entry(pending, struct async_entry, + domain_list)->cookie; + + spin_unlock_irqrestore(&async_lock, flags); + return ret; +} + +/* + * pick the first pending entry and run it + */ +static void async_run_entry_fn(struct work_struct *work) +{ + struct async_entry *entry = + container_of(work, struct async_entry, work); + unsigned long flags; + ktime_t uninitialized_var(calltime), delta, rettime; + + /* 1) run (and print duration) */ + if (initcall_debug && system_state == SYSTEM_BOOTING) { + pr_debug("calling %lli_%pF @ %i\n", + (long long)entry->cookie, + entry->func, task_pid_nr(current)); + calltime = ktime_get(); + } + entry->func(entry->data, entry->cookie); + if (initcall_debug && system_state == SYSTEM_BOOTING) { + rettime = ktime_get(); + delta = ktime_sub(rettime, calltime); + pr_debug("initcall %lli_%pF returned 0 after %lld usecs\n", + (long long)entry->cookie, + entry->func, + (long long)ktime_to_ns(delta) >> 10); + } + + /* 2) remove self from the pending queues */ + spin_lock_irqsave(&async_lock, flags); + list_del_init(&entry->domain_list); + list_del_init(&entry->global_list); + + /* 3) free the entry */ + kfree(entry); + atomic_dec(&entry_count); + + spin_unlock_irqrestore(&async_lock, flags); + + /* 4) wake up any waiters */ + wake_up(&async_done); +} + +static async_cookie_t __async_schedule(async_func_t func, void *data, struct async_domain *domain) +{ + struct async_entry *entry; + unsigned long flags; + async_cookie_t newcookie; + + /* allow irq-off callers */ + entry = kzalloc(sizeof(struct async_entry), GFP_ATOMIC); + + /* + * If we're out of memory or if there's too much work + * pending already, we execute synchronously. + */ + if (!entry || atomic_read(&entry_count) > MAX_WORK) { + kfree(entry); + spin_lock_irqsave(&async_lock, flags); + newcookie = next_cookie++; + spin_unlock_irqrestore(&async_lock, flags); + + /* low on memory.. run synchronously */ + func(data, newcookie); + return newcookie; + } + INIT_LIST_HEAD(&entry->domain_list); + INIT_LIST_HEAD(&entry->global_list); + INIT_WORK(&entry->work, async_run_entry_fn); + entry->func = func; + entry->data = data; + entry->domain = domain; + + spin_lock_irqsave(&async_lock, flags); + + /* allocate cookie and queue */ + newcookie = entry->cookie = next_cookie++; + + list_add_tail(&entry->domain_list, &domain->pending); + if (domain->registered) + list_add_tail(&entry->global_list, &async_global_pending); + + atomic_inc(&entry_count); + spin_unlock_irqrestore(&async_lock, flags); + + /* mark that this task has queued an async job, used by module init */ + current->flags |= PF_USED_ASYNC; + + /* schedule for execution */ + queue_work(system_unbound_wq, &entry->work); + + return newcookie; +} + +/** + * async_schedule - schedule a function for asynchronous execution + * @func: function to execute asynchronously + * @data: data pointer to pass to the function + * + * Returns an async_cookie_t that may be used for checkpointing later. + * Note: This function may be called from atomic or non-atomic contexts. + */ +async_cookie_t async_schedule(async_func_t func, void *data) +{ + return __async_schedule(func, data, &async_dfl_domain); +} +EXPORT_SYMBOL_GPL(async_schedule); + +/** + * async_schedule_domain - schedule a function for asynchronous execution within a certain domain + * @func: function to execute asynchronously + * @data: data pointer to pass to the function + * @domain: the domain + * + * Returns an async_cookie_t that may be used for checkpointing later. + * @domain may be used in the async_synchronize_*_domain() functions to + * wait within a certain synchronization domain rather than globally. A + * synchronization domain is specified via @domain. Note: This function + * may be called from atomic or non-atomic contexts. + */ +async_cookie_t async_schedule_domain(async_func_t func, void *data, + struct async_domain *domain) +{ + return __async_schedule(func, data, domain); +} +EXPORT_SYMBOL_GPL(async_schedule_domain); + +/** + * async_synchronize_full - synchronize all asynchronous function calls + * + * This function waits until all asynchronous function calls have been done. + */ +void async_synchronize_full(void) +{ + async_synchronize_full_domain(NULL); +} +EXPORT_SYMBOL_GPL(async_synchronize_full); + +/** + * async_unregister_domain - ensure no more anonymous waiters on this domain + * @domain: idle domain to flush out of any async_synchronize_full instances + * + * async_synchronize_{cookie|full}_domain() are not flushed since callers + * of these routines should know the lifetime of @domain + * + * Prefer ASYNC_DOMAIN_EXCLUSIVE() declarations over flushing + */ +void async_unregister_domain(struct async_domain *domain) +{ + spin_lock_irq(&async_lock); + WARN_ON(!domain->registered || !list_empty(&domain->pending)); + domain->registered = 0; + spin_unlock_irq(&async_lock); +} +EXPORT_SYMBOL_GPL(async_unregister_domain); + +/** + * async_synchronize_full_domain - synchronize all asynchronous function within a certain domain + * @domain: the domain to synchronize + * + * This function waits until all asynchronous function calls for the + * synchronization domain specified by @domain have been done. + */ +void async_synchronize_full_domain(struct async_domain *domain) +{ + async_synchronize_cookie_domain(ASYNC_COOKIE_MAX, domain); +} +EXPORT_SYMBOL_GPL(async_synchronize_full_domain); + +/** + * async_synchronize_cookie_domain - synchronize asynchronous function calls within a certain domain with cookie checkpointing + * @cookie: async_cookie_t to use as checkpoint + * @domain: the domain to synchronize (%NULL for all registered domains) + * + * This function waits until all asynchronous function calls for the + * synchronization domain specified by @domain submitted prior to @cookie + * have been done. + */ +void async_synchronize_cookie_domain(async_cookie_t cookie, struct async_domain *domain) +{ + ktime_t uninitialized_var(starttime), delta, endtime; + + if (initcall_debug && system_state == SYSTEM_BOOTING) { + pr_debug("async_waiting @ %i\n", task_pid_nr(current)); + starttime = ktime_get(); + } + + wait_event(async_done, lowest_in_progress(domain) >= cookie); + + if (initcall_debug && system_state == SYSTEM_BOOTING) { + endtime = ktime_get(); + delta = ktime_sub(endtime, starttime); + + pr_debug("async_continuing @ %i after %lli usec\n", + task_pid_nr(current), + (long long)ktime_to_ns(delta) >> 10); + } +} +EXPORT_SYMBOL_GPL(async_synchronize_cookie_domain); + +/** + * async_synchronize_cookie - synchronize asynchronous function calls with cookie checkpointing + * @cookie: async_cookie_t to use as checkpoint + * + * This function waits until all asynchronous function calls prior to @cookie + * have been done. + */ +void async_synchronize_cookie(async_cookie_t cookie) +{ + async_synchronize_cookie_domain(cookie, &async_dfl_domain); +} +EXPORT_SYMBOL_GPL(async_synchronize_cookie); + +/** + * current_is_async - is %current an async worker task? + * + * Returns %true if %current is an async worker task. + */ +bool current_is_async(void) +{ + struct worker *worker = current_wq_worker(); + + return worker && worker->current_func == async_run_entry_fn; +} diff --git a/kernel/kernel/audit.c b/kernel/kernel/audit.c new file mode 100644 index 000000000..1c13e4267 --- /dev/null +++ b/kernel/kernel/audit.c @@ -0,0 +1,2036 @@ +/* audit.c -- Auditing support + * Gateway between the kernel (e.g., selinux) and the user-space audit daemon. + * System-call specific features have moved to auditsc.c + * + * Copyright 2003-2007 Red Hat Inc., Durham, North Carolina. + * All Rights Reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * + * Written by Rickard E. (Rik) Faith + * + * Goals: 1) Integrate fully with Security Modules. + * 2) Minimal run-time overhead: + * a) Minimal when syscall auditing is disabled (audit_enable=0). + * b) Small when syscall auditing is enabled and no audit record + * is generated (defer as much work as possible to record + * generation time): + * i) context is allocated, + * ii) names from getname are stored without a copy, and + * iii) inode information stored from path_lookup. + * 3) Ability to disable syscall auditing at boot time (audit=0). + * 4) Usable by other parts of the kernel (if audit_log* is called, + * then a syscall record will be generated automatically for the + * current syscall). + * 5) Netlink interface to user-space. + * 6) Support low-overhead kernel-based filtering to minimize the + * information that must be passed to user-space. + * + * Example user-space utilities: http://people.redhat.com/sgrubb/audit/ + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +#include +#include +#include +#ifdef CONFIG_SECURITY +#include +#endif +#include +#include +#include +#include + +#include "audit.h" + +/* No auditing will take place until audit_initialized == AUDIT_INITIALIZED. + * (Initialization happens after skb_init is called.) */ +#define AUDIT_DISABLED -1 +#define AUDIT_UNINITIALIZED 0 +#define AUDIT_INITIALIZED 1 +static int audit_initialized; + +#define AUDIT_OFF 0 +#define AUDIT_ON 1 +#define AUDIT_LOCKED 2 +u32 audit_enabled; +u32 audit_ever_enabled; + +EXPORT_SYMBOL_GPL(audit_enabled); + +/* Default state when kernel boots without any parameters. */ +static u32 audit_default; + +/* If auditing cannot proceed, audit_failure selects what happens. */ +static u32 audit_failure = AUDIT_FAIL_PRINTK; + +/* + * If audit records are to be written to the netlink socket, audit_pid + * contains the pid of the auditd process and audit_nlk_portid contains + * the portid to use to send netlink messages to that process. + */ +int audit_pid; +static __u32 audit_nlk_portid; + +/* If audit_rate_limit is non-zero, limit the rate of sending audit records + * to that number per second. This prevents DoS attacks, but results in + * audit records being dropped. */ +static u32 audit_rate_limit; + +/* Number of outstanding audit_buffers allowed. + * When set to zero, this means unlimited. */ +static u32 audit_backlog_limit = 64; +#define AUDIT_BACKLOG_WAIT_TIME (60 * HZ) +static u32 audit_backlog_wait_time_master = AUDIT_BACKLOG_WAIT_TIME; +static u32 audit_backlog_wait_time = AUDIT_BACKLOG_WAIT_TIME; +static u32 audit_backlog_wait_overflow = 0; + +/* The identity of the user shutting down the audit system. */ +kuid_t audit_sig_uid = INVALID_UID; +pid_t audit_sig_pid = -1; +u32 audit_sig_sid = 0; + +/* Records can be lost in several ways: + 0) [suppressed in audit_alloc] + 1) out of memory in audit_log_start [kmalloc of struct audit_buffer] + 2) out of memory in audit_log_move [alloc_skb] + 3) suppressed due to audit_rate_limit + 4) suppressed due to audit_backlog_limit +*/ +static atomic_t audit_lost = ATOMIC_INIT(0); + +/* The netlink socket. */ +static struct sock *audit_sock; +static int audit_net_id; + +/* Hash for inode-based rules */ +struct list_head audit_inode_hash[AUDIT_INODE_BUCKETS]; + +/* The audit_freelist is a list of pre-allocated audit buffers (if more + * than AUDIT_MAXFREE are in use, the audit buffer is freed instead of + * being placed on the freelist). */ +static DEFINE_SPINLOCK(audit_freelist_lock); +static int audit_freelist_count; +static LIST_HEAD(audit_freelist); + +static struct sk_buff_head audit_skb_queue; +/* queue of skbs to send to auditd when/if it comes back */ +static struct sk_buff_head audit_skb_hold_queue; +static struct task_struct *kauditd_task; +static DECLARE_WAIT_QUEUE_HEAD(kauditd_wait); +static DECLARE_WAIT_QUEUE_HEAD(audit_backlog_wait); + +static struct audit_features af = {.vers = AUDIT_FEATURE_VERSION, + .mask = -1, + .features = 0, + .lock = 0,}; + +static char *audit_feature_names[2] = { + "only_unset_loginuid", + "loginuid_immutable", +}; + + +/* Serialize requests from userspace. */ +DEFINE_MUTEX(audit_cmd_mutex); + +/* AUDIT_BUFSIZ is the size of the temporary buffer used for formatting + * audit records. Since printk uses a 1024 byte buffer, this buffer + * should be at least that large. */ +#define AUDIT_BUFSIZ 1024 + +/* AUDIT_MAXFREE is the number of empty audit_buffers we keep on the + * audit_freelist. Doing so eliminates many kmalloc/kfree calls. */ +#define AUDIT_MAXFREE (2*NR_CPUS) + +/* The audit_buffer is used when formatting an audit record. The caller + * locks briefly to get the record off the freelist or to allocate the + * buffer, and locks briefly to send the buffer to the netlink layer or + * to place it on a transmit queue. Multiple audit_buffers can be in + * use simultaneously. */ +struct audit_buffer { + struct list_head list; + struct sk_buff *skb; /* formatted skb ready to send */ + struct audit_context *ctx; /* NULL or associated context */ + gfp_t gfp_mask; +}; + +struct audit_reply { + __u32 portid; + struct net *net; + struct sk_buff *skb; +}; + +static void audit_set_portid(struct audit_buffer *ab, __u32 portid) +{ + if (ab) { + struct nlmsghdr *nlh = nlmsg_hdr(ab->skb); + nlh->nlmsg_pid = portid; + } +} + +void audit_panic(const char *message) +{ + switch (audit_failure) { + case AUDIT_FAIL_SILENT: + break; + case AUDIT_FAIL_PRINTK: + if (printk_ratelimit()) + pr_err("%s\n", message); + break; + case AUDIT_FAIL_PANIC: + /* test audit_pid since printk is always losey, why bother? */ + if (audit_pid) + panic("audit: %s\n", message); + break; + } +} + +static inline int audit_rate_check(void) +{ + static unsigned long last_check = 0; + static int messages = 0; + static DEFINE_SPINLOCK(lock); + unsigned long flags; + unsigned long now; + unsigned long elapsed; + int retval = 0; + + if (!audit_rate_limit) return 1; + + spin_lock_irqsave(&lock, flags); + if (++messages < audit_rate_limit) { + retval = 1; + } else { + now = jiffies; + elapsed = now - last_check; + if (elapsed > HZ) { + last_check = now; + messages = 0; + retval = 1; + } + } + spin_unlock_irqrestore(&lock, flags); + + return retval; +} + +/** + * audit_log_lost - conditionally log lost audit message event + * @message: the message stating reason for lost audit message + * + * Emit at least 1 message per second, even if audit_rate_check is + * throttling. + * Always increment the lost messages counter. +*/ +void audit_log_lost(const char *message) +{ + static unsigned long last_msg = 0; + static DEFINE_SPINLOCK(lock); + unsigned long flags; + unsigned long now; + int print; + + atomic_inc(&audit_lost); + + print = (audit_failure == AUDIT_FAIL_PANIC || !audit_rate_limit); + + if (!print) { + spin_lock_irqsave(&lock, flags); + now = jiffies; + if (now - last_msg > HZ) { + print = 1; + last_msg = now; + } + spin_unlock_irqrestore(&lock, flags); + } + + if (print) { + if (printk_ratelimit()) + pr_warn("audit_lost=%u audit_rate_limit=%u audit_backlog_limit=%u\n", + atomic_read(&audit_lost), + audit_rate_limit, + audit_backlog_limit); + audit_panic(message); + } +} + +static int audit_log_config_change(char *function_name, u32 new, u32 old, + int allow_changes) +{ + struct audit_buffer *ab; + int rc = 0; + + ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_CONFIG_CHANGE); + if (unlikely(!ab)) + return rc; + audit_log_format(ab, "%s=%u old=%u", function_name, new, old); + audit_log_session_info(ab); + rc = audit_log_task_context(ab); + if (rc) + allow_changes = 0; /* Something weird, deny request */ + audit_log_format(ab, " res=%d", allow_changes); + audit_log_end(ab); + return rc; +} + +static int audit_do_config_change(char *function_name, u32 *to_change, u32 new) +{ + int allow_changes, rc = 0; + u32 old = *to_change; + + /* check if we are locked */ + if (audit_enabled == AUDIT_LOCKED) + allow_changes = 0; + else + allow_changes = 1; + + if (audit_enabled != AUDIT_OFF) { + rc = audit_log_config_change(function_name, new, old, allow_changes); + if (rc) + allow_changes = 0; + } + + /* If we are allowed, make the change */ + if (allow_changes == 1) + *to_change = new; + /* Not allowed, update reason */ + else if (rc == 0) + rc = -EPERM; + return rc; +} + +static int audit_set_rate_limit(u32 limit) +{ + return audit_do_config_change("audit_rate_limit", &audit_rate_limit, limit); +} + +static int audit_set_backlog_limit(u32 limit) +{ + return audit_do_config_change("audit_backlog_limit", &audit_backlog_limit, limit); +} + +static int audit_set_backlog_wait_time(u32 timeout) +{ + return audit_do_config_change("audit_backlog_wait_time", + &audit_backlog_wait_time_master, timeout); +} + +static int audit_set_enabled(u32 state) +{ + int rc; + if (state > AUDIT_LOCKED) + return -EINVAL; + + rc = audit_do_config_change("audit_enabled", &audit_enabled, state); + if (!rc) + audit_ever_enabled |= !!state; + + return rc; +} + +static int audit_set_failure(u32 state) +{ + if (state != AUDIT_FAIL_SILENT + && state != AUDIT_FAIL_PRINTK + && state != AUDIT_FAIL_PANIC) + return -EINVAL; + + return audit_do_config_change("audit_failure", &audit_failure, state); +} + +/* + * Queue skbs to be sent to auditd when/if it comes back. These skbs should + * already have been sent via prink/syslog and so if these messages are dropped + * it is not a huge concern since we already passed the audit_log_lost() + * notification and stuff. This is just nice to get audit messages during + * boot before auditd is running or messages generated while auditd is stopped. + * This only holds messages is audit_default is set, aka booting with audit=1 + * or building your kernel that way. + */ +static void audit_hold_skb(struct sk_buff *skb) +{ + if (audit_default && + (!audit_backlog_limit || + skb_queue_len(&audit_skb_hold_queue) < audit_backlog_limit)) + skb_queue_tail(&audit_skb_hold_queue, skb); + else + kfree_skb(skb); +} + +/* + * For one reason or another this nlh isn't getting delivered to the userspace + * audit daemon, just send it to printk. + */ +static void audit_printk_skb(struct sk_buff *skb) +{ + struct nlmsghdr *nlh = nlmsg_hdr(skb); + char *data = nlmsg_data(nlh); + + if (nlh->nlmsg_type != AUDIT_EOE) { + if (printk_ratelimit()) + pr_notice("type=%d %s\n", nlh->nlmsg_type, data); + else + audit_log_lost("printk limit exceeded"); + } + + audit_hold_skb(skb); +} + +static void kauditd_send_skb(struct sk_buff *skb) +{ + int err; + /* take a reference in case we can't send it and we want to hold it */ + skb_get(skb); + err = netlink_unicast(audit_sock, skb, audit_nlk_portid, 0); + if (err < 0) { + BUG_ON(err != -ECONNREFUSED); /* Shouldn't happen */ + if (audit_pid) { + pr_err("*NO* daemon at audit_pid=%d\n", audit_pid); + audit_log_lost("auditd disappeared"); + audit_pid = 0; + audit_sock = NULL; + } + /* we might get lucky and get this in the next auditd */ + audit_hold_skb(skb); + } else + /* drop the extra reference if sent ok */ + consume_skb(skb); +} + +/* + * kauditd_send_multicast_skb - send the skb to multicast userspace listeners + * + * This function doesn't consume an skb as might be expected since it has to + * copy it anyways. + */ +static void kauditd_send_multicast_skb(struct sk_buff *skb, gfp_t gfp_mask) +{ + struct sk_buff *copy; + struct audit_net *aunet = net_generic(&init_net, audit_net_id); + struct sock *sock = aunet->nlsk; + + if (!netlink_has_listeners(sock, AUDIT_NLGRP_READLOG)) + return; + + /* + * The seemingly wasteful skb_copy() rather than bumping the refcount + * using skb_get() is necessary because non-standard mods are made to + * the skb by the original kaudit unicast socket send routine. The + * existing auditd daemon assumes this breakage. Fixing this would + * require co-ordinating a change in the established protocol between + * the kaudit kernel subsystem and the auditd userspace code. There is + * no reason for new multicast clients to continue with this + * non-compliance. + */ + copy = skb_copy(skb, gfp_mask); + if (!copy) + return; + + nlmsg_multicast(sock, copy, 0, AUDIT_NLGRP_READLOG, gfp_mask); +} + +/* + * flush_hold_queue - empty the hold queue if auditd appears + * + * If auditd just started, drain the queue of messages already + * sent to syslog/printk. Remember loss here is ok. We already + * called audit_log_lost() if it didn't go out normally. so the + * race between the skb_dequeue and the next check for audit_pid + * doesn't matter. + * + * If you ever find kauditd to be too slow we can get a perf win + * by doing our own locking and keeping better track if there + * are messages in this queue. I don't see the need now, but + * in 5 years when I want to play with this again I'll see this + * note and still have no friggin idea what i'm thinking today. + */ +static void flush_hold_queue(void) +{ + struct sk_buff *skb; + + if (!audit_default || !audit_pid) + return; + + skb = skb_dequeue(&audit_skb_hold_queue); + if (likely(!skb)) + return; + + while (skb && audit_pid) { + kauditd_send_skb(skb); + skb = skb_dequeue(&audit_skb_hold_queue); + } + + /* + * if auditd just disappeared but we + * dequeued an skb we need to drop ref + */ + if (skb) + consume_skb(skb); +} + +static int kauditd_thread(void *dummy) +{ + set_freezable(); + while (!kthread_should_stop()) { + struct sk_buff *skb; + + flush_hold_queue(); + + skb = skb_dequeue(&audit_skb_queue); + + if (skb) { + if (skb_queue_len(&audit_skb_queue) <= audit_backlog_limit) + wake_up(&audit_backlog_wait); + if (audit_pid) + kauditd_send_skb(skb); + else + audit_printk_skb(skb); + continue; + } + + wait_event_freezable(kauditd_wait, skb_queue_len(&audit_skb_queue)); + } + return 0; +} + +int audit_send_list(void *_dest) +{ + struct audit_netlink_list *dest = _dest; + struct sk_buff *skb; + struct net *net = dest->net; + struct audit_net *aunet = net_generic(net, audit_net_id); + + /* wait for parent to finish and send an ACK */ + mutex_lock(&audit_cmd_mutex); + mutex_unlock(&audit_cmd_mutex); + + while ((skb = __skb_dequeue(&dest->q)) != NULL) + netlink_unicast(aunet->nlsk, skb, dest->portid, 0); + + put_net(net); + kfree(dest); + + return 0; +} + +struct sk_buff *audit_make_reply(__u32 portid, int seq, int type, int done, + int multi, const void *payload, int size) +{ + struct sk_buff *skb; + struct nlmsghdr *nlh; + void *data; + int flags = multi ? NLM_F_MULTI : 0; + int t = done ? NLMSG_DONE : type; + + skb = nlmsg_new(size, GFP_KERNEL); + if (!skb) + return NULL; + + nlh = nlmsg_put(skb, portid, seq, t, size, flags); + if (!nlh) + goto out_kfree_skb; + data = nlmsg_data(nlh); + memcpy(data, payload, size); + return skb; + +out_kfree_skb: + kfree_skb(skb); + return NULL; +} + +static int audit_send_reply_thread(void *arg) +{ + struct audit_reply *reply = (struct audit_reply *)arg; + struct net *net = reply->net; + struct audit_net *aunet = net_generic(net, audit_net_id); + + mutex_lock(&audit_cmd_mutex); + mutex_unlock(&audit_cmd_mutex); + + /* Ignore failure. It'll only happen if the sender goes away, + because our timeout is set to infinite. */ + netlink_unicast(aunet->nlsk , reply->skb, reply->portid, 0); + put_net(net); + kfree(reply); + return 0; +} +/** + * audit_send_reply - send an audit reply message via netlink + * @request_skb: skb of request we are replying to (used to target the reply) + * @seq: sequence number + * @type: audit message type + * @done: done (last) flag + * @multi: multi-part message flag + * @payload: payload data + * @size: payload size + * + * Allocates an skb, builds the netlink message, and sends it to the port id. + * No failure notifications. + */ +static void audit_send_reply(struct sk_buff *request_skb, int seq, int type, int done, + int multi, const void *payload, int size) +{ + u32 portid = NETLINK_CB(request_skb).portid; + struct net *net = sock_net(NETLINK_CB(request_skb).sk); + struct sk_buff *skb; + struct task_struct *tsk; + struct audit_reply *reply = kmalloc(sizeof(struct audit_reply), + GFP_KERNEL); + + if (!reply) + return; + + skb = audit_make_reply(portid, seq, type, done, multi, payload, size); + if (!skb) + goto out; + + reply->net = get_net(net); + reply->portid = portid; + reply->skb = skb; + + tsk = kthread_run(audit_send_reply_thread, reply, "audit_send_reply"); + if (!IS_ERR(tsk)) + return; + kfree_skb(skb); +out: + kfree(reply); +} + +/* + * Check for appropriate CAP_AUDIT_ capabilities on incoming audit + * control messages. + */ +static int audit_netlink_ok(struct sk_buff *skb, u16 msg_type) +{ + int err = 0; + + /* Only support initial user namespace for now. */ + /* + * We return ECONNREFUSED because it tricks userspace into thinking + * that audit was not configured into the kernel. Lots of users + * configure their PAM stack (because that's what the distro does) + * to reject login if unable to send messages to audit. If we return + * ECONNREFUSED the PAM stack thinks the kernel does not have audit + * configured in and will let login proceed. If we return EPERM + * userspace will reject all logins. This should be removed when we + * support non init namespaces!! + */ + if (current_user_ns() != &init_user_ns) + return -ECONNREFUSED; + + switch (msg_type) { + case AUDIT_LIST: + case AUDIT_ADD: + case AUDIT_DEL: + return -EOPNOTSUPP; + case AUDIT_GET: + case AUDIT_SET: + case AUDIT_GET_FEATURE: + case AUDIT_SET_FEATURE: + case AUDIT_LIST_RULES: + case AUDIT_ADD_RULE: + case AUDIT_DEL_RULE: + case AUDIT_SIGNAL_INFO: + case AUDIT_TTY_GET: + case AUDIT_TTY_SET: + case AUDIT_TRIM: + case AUDIT_MAKE_EQUIV: + /* Only support auditd and auditctl in initial pid namespace + * for now. */ + if (task_active_pid_ns(current) != &init_pid_ns) + return -EPERM; + + if (!netlink_capable(skb, CAP_AUDIT_CONTROL)) + err = -EPERM; + break; + case AUDIT_USER: + case AUDIT_FIRST_USER_MSG ... AUDIT_LAST_USER_MSG: + case AUDIT_FIRST_USER_MSG2 ... AUDIT_LAST_USER_MSG2: + if (!netlink_capable(skb, CAP_AUDIT_WRITE)) + err = -EPERM; + break; + default: /* bad msg */ + err = -EINVAL; + } + + return err; +} + +static int audit_log_common_recv_msg(struct audit_buffer **ab, u16 msg_type) +{ + int rc = 0; + uid_t uid = from_kuid(&init_user_ns, current_uid()); + pid_t pid = task_tgid_nr(current); + + if (!audit_enabled && msg_type != AUDIT_USER_AVC) { + *ab = NULL; + return rc; + } + + *ab = audit_log_start(NULL, GFP_KERNEL, msg_type); + if (unlikely(!*ab)) + return rc; + audit_log_format(*ab, "pid=%d uid=%u", pid, uid); + audit_log_session_info(*ab); + audit_log_task_context(*ab); + + return rc; +} + +int is_audit_feature_set(int i) +{ + return af.features & AUDIT_FEATURE_TO_MASK(i); +} + + +static int audit_get_feature(struct sk_buff *skb) +{ + u32 seq; + + seq = nlmsg_hdr(skb)->nlmsg_seq; + + audit_send_reply(skb, seq, AUDIT_GET_FEATURE, 0, 0, &af, sizeof(af)); + + return 0; +} + +static void audit_log_feature_change(int which, u32 old_feature, u32 new_feature, + u32 old_lock, u32 new_lock, int res) +{ + struct audit_buffer *ab; + + if (audit_enabled == AUDIT_OFF) + return; + + ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_FEATURE_CHANGE); + audit_log_task_info(ab, current); + audit_log_format(ab, " feature=%s old=%u new=%u old_lock=%u new_lock=%u res=%d", + audit_feature_names[which], !!old_feature, !!new_feature, + !!old_lock, !!new_lock, res); + audit_log_end(ab); +} + +static int audit_set_feature(struct sk_buff *skb) +{ + struct audit_features *uaf; + int i; + + BUILD_BUG_ON(AUDIT_LAST_FEATURE + 1 > ARRAY_SIZE(audit_feature_names)); + uaf = nlmsg_data(nlmsg_hdr(skb)); + + /* if there is ever a version 2 we should handle that here */ + + for (i = 0; i <= AUDIT_LAST_FEATURE; i++) { + u32 feature = AUDIT_FEATURE_TO_MASK(i); + u32 old_feature, new_feature, old_lock, new_lock; + + /* if we are not changing this feature, move along */ + if (!(feature & uaf->mask)) + continue; + + old_feature = af.features & feature; + new_feature = uaf->features & feature; + new_lock = (uaf->lock | af.lock) & feature; + old_lock = af.lock & feature; + + /* are we changing a locked feature? */ + if (old_lock && (new_feature != old_feature)) { + audit_log_feature_change(i, old_feature, new_feature, + old_lock, new_lock, 0); + return -EPERM; + } + } + /* nothing invalid, do the changes */ + for (i = 0; i <= AUDIT_LAST_FEATURE; i++) { + u32 feature = AUDIT_FEATURE_TO_MASK(i); + u32 old_feature, new_feature, old_lock, new_lock; + + /* if we are not changing this feature, move along */ + if (!(feature & uaf->mask)) + continue; + + old_feature = af.features & feature; + new_feature = uaf->features & feature; + old_lock = af.lock & feature; + new_lock = (uaf->lock | af.lock) & feature; + + if (new_feature != old_feature) + audit_log_feature_change(i, old_feature, new_feature, + old_lock, new_lock, 1); + + if (new_feature) + af.features |= feature; + else + af.features &= ~feature; + af.lock |= new_lock; + } + + return 0; +} + +static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) +{ + u32 seq; + void *data; + int err; + struct audit_buffer *ab; + u16 msg_type = nlh->nlmsg_type; + struct audit_sig_info *sig_data; + char *ctx = NULL; + u32 len; + + err = audit_netlink_ok(skb, msg_type); + if (err) + return err; + + /* As soon as there's any sign of userspace auditd, + * start kauditd to talk to it */ + if (!kauditd_task) { + kauditd_task = kthread_run(kauditd_thread, NULL, "kauditd"); + if (IS_ERR(kauditd_task)) { + err = PTR_ERR(kauditd_task); + kauditd_task = NULL; + return err; + } + } + seq = nlh->nlmsg_seq; + data = nlmsg_data(nlh); + + switch (msg_type) { + case AUDIT_GET: { + struct audit_status s; + memset(&s, 0, sizeof(s)); + s.enabled = audit_enabled; + s.failure = audit_failure; + s.pid = audit_pid; + s.rate_limit = audit_rate_limit; + s.backlog_limit = audit_backlog_limit; + s.lost = atomic_read(&audit_lost); + s.backlog = skb_queue_len(&audit_skb_queue); + s.feature_bitmap = AUDIT_FEATURE_BITMAP_ALL; + s.backlog_wait_time = audit_backlog_wait_time_master; + audit_send_reply(skb, seq, AUDIT_GET, 0, 0, &s, sizeof(s)); + break; + } + case AUDIT_SET: { + struct audit_status s; + memset(&s, 0, sizeof(s)); + /* guard against past and future API changes */ + memcpy(&s, data, min_t(size_t, sizeof(s), nlmsg_len(nlh))); + if (s.mask & AUDIT_STATUS_ENABLED) { + err = audit_set_enabled(s.enabled); + if (err < 0) + return err; + } + if (s.mask & AUDIT_STATUS_FAILURE) { + err = audit_set_failure(s.failure); + if (err < 0) + return err; + } + if (s.mask & AUDIT_STATUS_PID) { + int new_pid = s.pid; + + if ((!new_pid) && (task_tgid_vnr(current) != audit_pid)) + return -EACCES; + if (audit_enabled != AUDIT_OFF) + audit_log_config_change("audit_pid", new_pid, audit_pid, 1); + audit_pid = new_pid; + audit_nlk_portid = NETLINK_CB(skb).portid; + audit_sock = skb->sk; + } + if (s.mask & AUDIT_STATUS_RATE_LIMIT) { + err = audit_set_rate_limit(s.rate_limit); + if (err < 0) + return err; + } + if (s.mask & AUDIT_STATUS_BACKLOG_LIMIT) { + err = audit_set_backlog_limit(s.backlog_limit); + if (err < 0) + return err; + } + if (s.mask & AUDIT_STATUS_BACKLOG_WAIT_TIME) { + if (sizeof(s) > (size_t)nlh->nlmsg_len) + return -EINVAL; + if (s.backlog_wait_time > 10*AUDIT_BACKLOG_WAIT_TIME) + return -EINVAL; + err = audit_set_backlog_wait_time(s.backlog_wait_time); + if (err < 0) + return err; + } + break; + } + case AUDIT_GET_FEATURE: + err = audit_get_feature(skb); + if (err) + return err; + break; + case AUDIT_SET_FEATURE: + err = audit_set_feature(skb); + if (err) + return err; + break; + case AUDIT_USER: + case AUDIT_FIRST_USER_MSG ... AUDIT_LAST_USER_MSG: + case AUDIT_FIRST_USER_MSG2 ... AUDIT_LAST_USER_MSG2: + if (!audit_enabled && msg_type != AUDIT_USER_AVC) + return 0; + + err = audit_filter_user(msg_type); + if (err == 1) { /* match or error */ + err = 0; + if (msg_type == AUDIT_USER_TTY) { + err = tty_audit_push_current(); + if (err) + break; + } + mutex_unlock(&audit_cmd_mutex); + audit_log_common_recv_msg(&ab, msg_type); + if (msg_type != AUDIT_USER_TTY) + audit_log_format(ab, " msg='%.*s'", + AUDIT_MESSAGE_TEXT_MAX, + (char *)data); + else { + int size; + + audit_log_format(ab, " data="); + size = nlmsg_len(nlh); + if (size > 0 && + ((unsigned char *)data)[size - 1] == '\0') + size--; + audit_log_n_untrustedstring(ab, data, size); + } + audit_set_portid(ab, NETLINK_CB(skb).portid); + audit_log_end(ab); + mutex_lock(&audit_cmd_mutex); + } + break; + case AUDIT_ADD_RULE: + case AUDIT_DEL_RULE: + if (nlmsg_len(nlh) < sizeof(struct audit_rule_data)) + return -EINVAL; + if (audit_enabled == AUDIT_LOCKED) { + audit_log_common_recv_msg(&ab, AUDIT_CONFIG_CHANGE); + audit_log_format(ab, " audit_enabled=%d res=0", audit_enabled); + audit_log_end(ab); + return -EPERM; + } + err = audit_rule_change(msg_type, NETLINK_CB(skb).portid, + seq, data, nlmsg_len(nlh)); + break; + case AUDIT_LIST_RULES: + err = audit_list_rules_send(skb, seq); + break; + case AUDIT_TRIM: + audit_trim_trees(); + audit_log_common_recv_msg(&ab, AUDIT_CONFIG_CHANGE); + audit_log_format(ab, " op=trim res=1"); + audit_log_end(ab); + break; + case AUDIT_MAKE_EQUIV: { + void *bufp = data; + u32 sizes[2]; + size_t msglen = nlmsg_len(nlh); + char *old, *new; + + err = -EINVAL; + if (msglen < 2 * sizeof(u32)) + break; + memcpy(sizes, bufp, 2 * sizeof(u32)); + bufp += 2 * sizeof(u32); + msglen -= 2 * sizeof(u32); + old = audit_unpack_string(&bufp, &msglen, sizes[0]); + if (IS_ERR(old)) { + err = PTR_ERR(old); + break; + } + new = audit_unpack_string(&bufp, &msglen, sizes[1]); + if (IS_ERR(new)) { + err = PTR_ERR(new); + kfree(old); + break; + } + /* OK, here comes... */ + err = audit_tag_tree(old, new); + + audit_log_common_recv_msg(&ab, AUDIT_CONFIG_CHANGE); + + audit_log_format(ab, " op=make_equiv old="); + audit_log_untrustedstring(ab, old); + audit_log_format(ab, " new="); + audit_log_untrustedstring(ab, new); + audit_log_format(ab, " res=%d", !err); + audit_log_end(ab); + kfree(old); + kfree(new); + break; + } + case AUDIT_SIGNAL_INFO: + len = 0; + if (audit_sig_sid) { + err = security_secid_to_secctx(audit_sig_sid, &ctx, &len); + if (err) + return err; + } + sig_data = kmalloc(sizeof(*sig_data) + len, GFP_KERNEL); + if (!sig_data) { + if (audit_sig_sid) + security_release_secctx(ctx, len); + return -ENOMEM; + } + sig_data->uid = from_kuid(&init_user_ns, audit_sig_uid); + sig_data->pid = audit_sig_pid; + if (audit_sig_sid) { + memcpy(sig_data->ctx, ctx, len); + security_release_secctx(ctx, len); + } + audit_send_reply(skb, seq, AUDIT_SIGNAL_INFO, 0, 0, + sig_data, sizeof(*sig_data) + len); + kfree(sig_data); + break; + case AUDIT_TTY_GET: { + struct audit_tty_status s; + struct task_struct *tsk = current; + + spin_lock(&tsk->sighand->siglock); + s.enabled = tsk->signal->audit_tty; + s.log_passwd = tsk->signal->audit_tty_log_passwd; + spin_unlock(&tsk->sighand->siglock); + + audit_send_reply(skb, seq, AUDIT_TTY_GET, 0, 0, &s, sizeof(s)); + break; + } + case AUDIT_TTY_SET: { + struct audit_tty_status s, old; + struct task_struct *tsk = current; + struct audit_buffer *ab; + + memset(&s, 0, sizeof(s)); + /* guard against past and future API changes */ + memcpy(&s, data, min_t(size_t, sizeof(s), nlmsg_len(nlh))); + /* check if new data is valid */ + if ((s.enabled != 0 && s.enabled != 1) || + (s.log_passwd != 0 && s.log_passwd != 1)) + err = -EINVAL; + + spin_lock(&tsk->sighand->siglock); + old.enabled = tsk->signal->audit_tty; + old.log_passwd = tsk->signal->audit_tty_log_passwd; + if (!err) { + tsk->signal->audit_tty = s.enabled; + tsk->signal->audit_tty_log_passwd = s.log_passwd; + } + spin_unlock(&tsk->sighand->siglock); + + audit_log_common_recv_msg(&ab, AUDIT_CONFIG_CHANGE); + audit_log_format(ab, " op=tty_set old-enabled=%d new-enabled=%d" + " old-log_passwd=%d new-log_passwd=%d res=%d", + old.enabled, s.enabled, old.log_passwd, + s.log_passwd, !err); + audit_log_end(ab); + break; + } + default: + err = -EINVAL; + break; + } + + return err < 0 ? err : 0; +} + +/* + * Get message from skb. Each message is processed by audit_receive_msg. + * Malformed skbs with wrong length are discarded silently. + */ +static void audit_receive_skb(struct sk_buff *skb) +{ + struct nlmsghdr *nlh; + /* + * len MUST be signed for nlmsg_next to be able to dec it below 0 + * if the nlmsg_len was not aligned + */ + int len; + int err; + + nlh = nlmsg_hdr(skb); + len = skb->len; + + while (nlmsg_ok(nlh, len)) { + err = audit_receive_msg(skb, nlh); + /* if err or if this message says it wants a response */ + if (err || (nlh->nlmsg_flags & NLM_F_ACK)) + netlink_ack(skb, nlh, err); + + nlh = nlmsg_next(nlh, &len); + } +} + +/* Receive messages from netlink socket. */ +static void audit_receive(struct sk_buff *skb) +{ + mutex_lock(&audit_cmd_mutex); + audit_receive_skb(skb); + mutex_unlock(&audit_cmd_mutex); +} + +/* Run custom bind function on netlink socket group connect or bind requests. */ +static int audit_bind(struct net *net, int group) +{ + if (!capable(CAP_AUDIT_READ)) + return -EPERM; + + return 0; +} + +static int __net_init audit_net_init(struct net *net) +{ + struct netlink_kernel_cfg cfg = { + .input = audit_receive, + .bind = audit_bind, + .flags = NL_CFG_F_NONROOT_RECV, + .groups = AUDIT_NLGRP_MAX, + }; + + struct audit_net *aunet = net_generic(net, audit_net_id); + + aunet->nlsk = netlink_kernel_create(net, NETLINK_AUDIT, &cfg); + if (aunet->nlsk == NULL) { + audit_panic("cannot initialize netlink socket in namespace"); + return -ENOMEM; + } + aunet->nlsk->sk_sndtimeo = MAX_SCHEDULE_TIMEOUT; + return 0; +} + +static void __net_exit audit_net_exit(struct net *net) +{ + struct audit_net *aunet = net_generic(net, audit_net_id); + struct sock *sock = aunet->nlsk; + if (sock == audit_sock) { + audit_pid = 0; + audit_sock = NULL; + } + + RCU_INIT_POINTER(aunet->nlsk, NULL); + synchronize_net(); + netlink_kernel_release(sock); +} + +static struct pernet_operations audit_net_ops __net_initdata = { + .init = audit_net_init, + .exit = audit_net_exit, + .id = &audit_net_id, + .size = sizeof(struct audit_net), +}; + +/* Initialize audit support at boot time. */ +static int __init audit_init(void) +{ + int i; + + if (audit_initialized == AUDIT_DISABLED) + return 0; + + pr_info("initializing netlink subsys (%s)\n", + audit_default ? "enabled" : "disabled"); + register_pernet_subsys(&audit_net_ops); + + skb_queue_head_init(&audit_skb_queue); + skb_queue_head_init(&audit_skb_hold_queue); + audit_initialized = AUDIT_INITIALIZED; + audit_enabled = audit_default; + audit_ever_enabled |= !!audit_default; + + audit_log(NULL, GFP_KERNEL, AUDIT_KERNEL, "initialized"); + + for (i = 0; i < AUDIT_INODE_BUCKETS; i++) + INIT_LIST_HEAD(&audit_inode_hash[i]); + + return 0; +} +__initcall(audit_init); + +/* Process kernel command-line parameter at boot time. audit=0 or audit=1. */ +static int __init audit_enable(char *str) +{ + audit_default = !!simple_strtol(str, NULL, 0); + if (!audit_default) + audit_initialized = AUDIT_DISABLED; + + pr_info("%s\n", audit_default ? + "enabled (after initialization)" : "disabled (until reboot)"); + + return 1; +} +__setup("audit=", audit_enable); + +/* Process kernel command-line parameter at boot time. + * audit_backlog_limit= */ +static int __init audit_backlog_limit_set(char *str) +{ + u32 audit_backlog_limit_arg; + + pr_info("audit_backlog_limit: "); + if (kstrtouint(str, 0, &audit_backlog_limit_arg)) { + pr_cont("using default of %u, unable to parse %s\n", + audit_backlog_limit, str); + return 1; + } + + audit_backlog_limit = audit_backlog_limit_arg; + pr_cont("%d\n", audit_backlog_limit); + + return 1; +} +__setup("audit_backlog_limit=", audit_backlog_limit_set); + +static void audit_buffer_free(struct audit_buffer *ab) +{ + unsigned long flags; + + if (!ab) + return; + + if (ab->skb) + kfree_skb(ab->skb); + + spin_lock_irqsave(&audit_freelist_lock, flags); + if (audit_freelist_count > AUDIT_MAXFREE) + kfree(ab); + else { + audit_freelist_count++; + list_add(&ab->list, &audit_freelist); + } + spin_unlock_irqrestore(&audit_freelist_lock, flags); +} + +static struct audit_buffer * audit_buffer_alloc(struct audit_context *ctx, + gfp_t gfp_mask, int type) +{ + unsigned long flags; + struct audit_buffer *ab = NULL; + struct nlmsghdr *nlh; + + spin_lock_irqsave(&audit_freelist_lock, flags); + if (!list_empty(&audit_freelist)) { + ab = list_entry(audit_freelist.next, + struct audit_buffer, list); + list_del(&ab->list); + --audit_freelist_count; + } + spin_unlock_irqrestore(&audit_freelist_lock, flags); + + if (!ab) { + ab = kmalloc(sizeof(*ab), gfp_mask); + if (!ab) + goto err; + } + + ab->ctx = ctx; + ab->gfp_mask = gfp_mask; + + ab->skb = nlmsg_new(AUDIT_BUFSIZ, gfp_mask); + if (!ab->skb) + goto err; + + nlh = nlmsg_put(ab->skb, 0, 0, type, 0, 0); + if (!nlh) + goto out_kfree_skb; + + return ab; + +out_kfree_skb: + kfree_skb(ab->skb); + ab->skb = NULL; +err: + audit_buffer_free(ab); + return NULL; +} + +/** + * audit_serial - compute a serial number for the audit record + * + * Compute a serial number for the audit record. Audit records are + * written to user-space as soon as they are generated, so a complete + * audit record may be written in several pieces. The timestamp of the + * record and this serial number are used by the user-space tools to + * determine which pieces belong to the same audit record. The + * (timestamp,serial) tuple is unique for each syscall and is live from + * syscall entry to syscall exit. + * + * NOTE: Another possibility is to store the formatted records off the + * audit context (for those records that have a context), and emit them + * all at syscall exit. However, this could delay the reporting of + * significant errors until syscall exit (or never, if the system + * halts). + */ +unsigned int audit_serial(void) +{ + static atomic_t serial = ATOMIC_INIT(0); + + return atomic_add_return(1, &serial); +} + +static inline void audit_get_stamp(struct audit_context *ctx, + struct timespec *t, unsigned int *serial) +{ + if (!ctx || !auditsc_get_stamp(ctx, t, serial)) { + *t = CURRENT_TIME; + *serial = audit_serial(); + } +} + +/* + * Wait for auditd to drain the queue a little + */ +static long wait_for_auditd(long sleep_time) +{ + DECLARE_WAITQUEUE(wait, current); + set_current_state(TASK_UNINTERRUPTIBLE); + add_wait_queue_exclusive(&audit_backlog_wait, &wait); + + if (audit_backlog_limit && + skb_queue_len(&audit_skb_queue) > audit_backlog_limit) + sleep_time = schedule_timeout(sleep_time); + + __set_current_state(TASK_RUNNING); + remove_wait_queue(&audit_backlog_wait, &wait); + + return sleep_time; +} + +/** + * audit_log_start - obtain an audit buffer + * @ctx: audit_context (may be NULL) + * @gfp_mask: type of allocation + * @type: audit message type + * + * Returns audit_buffer pointer on success or NULL on error. + * + * Obtain an audit buffer. This routine does locking to obtain the + * audit buffer, but then no locking is required for calls to + * audit_log_*format. If the task (ctx) is a task that is currently in a + * syscall, then the syscall is marked as auditable and an audit record + * will be written at syscall exit. If there is no associated task, then + * task context (ctx) should be NULL. + */ +struct audit_buffer *audit_log_start(struct audit_context *ctx, gfp_t gfp_mask, + int type) +{ + struct audit_buffer *ab = NULL; + struct timespec t; + unsigned int uninitialized_var(serial); + int reserve = 5; /* Allow atomic callers to go up to five + entries over the normal backlog limit */ + unsigned long timeout_start = jiffies; + + if (audit_initialized != AUDIT_INITIALIZED) + return NULL; + + if (unlikely(audit_filter_type(type))) + return NULL; + + if (gfp_mask & __GFP_WAIT) { + if (audit_pid && audit_pid == current->pid) + gfp_mask &= ~__GFP_WAIT; + else + reserve = 0; + } + + while (audit_backlog_limit + && skb_queue_len(&audit_skb_queue) > audit_backlog_limit + reserve) { + if (gfp_mask & __GFP_WAIT && audit_backlog_wait_time) { + long sleep_time; + + sleep_time = timeout_start + audit_backlog_wait_time - jiffies; + if (sleep_time > 0) { + sleep_time = wait_for_auditd(sleep_time); + if (sleep_time > 0) + continue; + } + } + if (audit_rate_check() && printk_ratelimit()) + pr_warn("audit_backlog=%d > audit_backlog_limit=%d\n", + skb_queue_len(&audit_skb_queue), + audit_backlog_limit); + audit_log_lost("backlog limit exceeded"); + audit_backlog_wait_time = audit_backlog_wait_overflow; + wake_up(&audit_backlog_wait); + return NULL; + } + + if (!reserve) + audit_backlog_wait_time = audit_backlog_wait_time_master; + + ab = audit_buffer_alloc(ctx, gfp_mask, type); + if (!ab) { + audit_log_lost("out of memory in audit_log_start"); + return NULL; + } + + audit_get_stamp(ab->ctx, &t, &serial); + + audit_log_format(ab, "audit(%lu.%03lu:%u): ", + t.tv_sec, t.tv_nsec/1000000, serial); + return ab; +} + +/** + * audit_expand - expand skb in the audit buffer + * @ab: audit_buffer + * @extra: space to add at tail of the skb + * + * Returns 0 (no space) on failed expansion, or available space if + * successful. + */ +static inline int audit_expand(struct audit_buffer *ab, int extra) +{ + struct sk_buff *skb = ab->skb; + int oldtail = skb_tailroom(skb); + int ret = pskb_expand_head(skb, 0, extra, ab->gfp_mask); + int newtail = skb_tailroom(skb); + + if (ret < 0) { + audit_log_lost("out of memory in audit_expand"); + return 0; + } + + skb->truesize += newtail - oldtail; + return newtail; +} + +/* + * Format an audit message into the audit buffer. If there isn't enough + * room in the audit buffer, more room will be allocated and vsnprint + * will be called a second time. Currently, we assume that a printk + * can't format message larger than 1024 bytes, so we don't either. + */ +static void audit_log_vformat(struct audit_buffer *ab, const char *fmt, + va_list args) +{ + int len, avail; + struct sk_buff *skb; + va_list args2; + + if (!ab) + return; + + BUG_ON(!ab->skb); + skb = ab->skb; + avail = skb_tailroom(skb); + if (avail == 0) { + avail = audit_expand(ab, AUDIT_BUFSIZ); + if (!avail) + goto out; + } + va_copy(args2, args); + len = vsnprintf(skb_tail_pointer(skb), avail, fmt, args); + if (len >= avail) { + /* The printk buffer is 1024 bytes long, so if we get + * here and AUDIT_BUFSIZ is at least 1024, then we can + * log everything that printk could have logged. */ + avail = audit_expand(ab, + max_t(unsigned, AUDIT_BUFSIZ, 1+len-avail)); + if (!avail) + goto out_va_end; + len = vsnprintf(skb_tail_pointer(skb), avail, fmt, args2); + } + if (len > 0) + skb_put(skb, len); +out_va_end: + va_end(args2); +out: + return; +} + +/** + * audit_log_format - format a message into the audit buffer. + * @ab: audit_buffer + * @fmt: format string + * @...: optional parameters matching @fmt string + * + * All the work is done in audit_log_vformat. + */ +void audit_log_format(struct audit_buffer *ab, const char *fmt, ...) +{ + va_list args; + + if (!ab) + return; + va_start(args, fmt); + audit_log_vformat(ab, fmt, args); + va_end(args); +} + +/** + * audit_log_hex - convert a buffer to hex and append it to the audit skb + * @ab: the audit_buffer + * @buf: buffer to convert to hex + * @len: length of @buf to be converted + * + * No return value; failure to expand is silently ignored. + * + * This function will take the passed buf and convert it into a string of + * ascii hex digits. The new string is placed onto the skb. + */ +void audit_log_n_hex(struct audit_buffer *ab, const unsigned char *buf, + size_t len) +{ + int i, avail, new_len; + unsigned char *ptr; + struct sk_buff *skb; + + if (!ab) + return; + + BUG_ON(!ab->skb); + skb = ab->skb; + avail = skb_tailroom(skb); + new_len = len<<1; + if (new_len >= avail) { + /* Round the buffer request up to the next multiple */ + new_len = AUDIT_BUFSIZ*(((new_len-avail)/AUDIT_BUFSIZ) + 1); + avail = audit_expand(ab, new_len); + if (!avail) + return; + } + + ptr = skb_tail_pointer(skb); + for (i = 0; i < len; i++) + ptr = hex_byte_pack_upper(ptr, buf[i]); + *ptr = 0; + skb_put(skb, len << 1); /* new string is twice the old string */ +} + +/* + * Format a string of no more than slen characters into the audit buffer, + * enclosed in quote marks. + */ +void audit_log_n_string(struct audit_buffer *ab, const char *string, + size_t slen) +{ + int avail, new_len; + unsigned char *ptr; + struct sk_buff *skb; + + if (!ab) + return; + + BUG_ON(!ab->skb); + skb = ab->skb; + avail = skb_tailroom(skb); + new_len = slen + 3; /* enclosing quotes + null terminator */ + if (new_len > avail) { + avail = audit_expand(ab, new_len); + if (!avail) + return; + } + ptr = skb_tail_pointer(skb); + *ptr++ = '"'; + memcpy(ptr, string, slen); + ptr += slen; + *ptr++ = '"'; + *ptr = 0; + skb_put(skb, slen + 2); /* don't include null terminator */ +} + +/** + * audit_string_contains_control - does a string need to be logged in hex + * @string: string to be checked + * @len: max length of the string to check + */ +int audit_string_contains_control(const char *string, size_t len) +{ + const unsigned char *p; + for (p = string; p < (const unsigned char *)string + len; p++) { + if (*p == '"' || *p < 0x21 || *p > 0x7e) + return 1; + } + return 0; +} + +/** + * audit_log_n_untrustedstring - log a string that may contain random characters + * @ab: audit_buffer + * @len: length of string (not including trailing null) + * @string: string to be logged + * + * This code will escape a string that is passed to it if the string + * contains a control character, unprintable character, double quote mark, + * or a space. Unescaped strings will start and end with a double quote mark. + * Strings that are escaped are printed in hex (2 digits per char). + * + * The caller specifies the number of characters in the string to log, which may + * or may not be the entire string. + */ +void audit_log_n_untrustedstring(struct audit_buffer *ab, const char *string, + size_t len) +{ + if (audit_string_contains_control(string, len)) + audit_log_n_hex(ab, string, len); + else + audit_log_n_string(ab, string, len); +} + +/** + * audit_log_untrustedstring - log a string that may contain random characters + * @ab: audit_buffer + * @string: string to be logged + * + * Same as audit_log_n_untrustedstring(), except that strlen is used to + * determine string length. + */ +void audit_log_untrustedstring(struct audit_buffer *ab, const char *string) +{ + audit_log_n_untrustedstring(ab, string, strlen(string)); +} + +/* This is a helper-function to print the escaped d_path */ +void audit_log_d_path(struct audit_buffer *ab, const char *prefix, + const struct path *path) +{ + char *p, *pathname; + + if (prefix) + audit_log_format(ab, "%s", prefix); + + /* We will allow 11 spaces for ' (deleted)' to be appended */ + pathname = kmalloc(PATH_MAX+11, ab->gfp_mask); + if (!pathname) { + audit_log_string(ab, ""); + return; + } + p = d_path(path, pathname, PATH_MAX+11); + if (IS_ERR(p)) { /* Should never happen since we send PATH_MAX */ + /* FIXME: can we save some information here? */ + audit_log_string(ab, ""); + } else + audit_log_untrustedstring(ab, p); + kfree(pathname); +} + +void audit_log_session_info(struct audit_buffer *ab) +{ + unsigned int sessionid = audit_get_sessionid(current); + uid_t auid = from_kuid(&init_user_ns, audit_get_loginuid(current)); + + audit_log_format(ab, " auid=%u ses=%u", auid, sessionid); +} + +void audit_log_key(struct audit_buffer *ab, char *key) +{ + audit_log_format(ab, " key="); + if (key) + audit_log_untrustedstring(ab, key); + else + audit_log_format(ab, "(null)"); +} + +void audit_log_cap(struct audit_buffer *ab, char *prefix, kernel_cap_t *cap) +{ + int i; + + audit_log_format(ab, " %s=", prefix); + CAP_FOR_EACH_U32(i) { + audit_log_format(ab, "%08x", + cap->cap[CAP_LAST_U32 - i]); + } +} + +static void audit_log_fcaps(struct audit_buffer *ab, struct audit_names *name) +{ + kernel_cap_t *perm = &name->fcap.permitted; + kernel_cap_t *inh = &name->fcap.inheritable; + int log = 0; + + if (!cap_isclear(*perm)) { + audit_log_cap(ab, "cap_fp", perm); + log = 1; + } + if (!cap_isclear(*inh)) { + audit_log_cap(ab, "cap_fi", inh); + log = 1; + } + + if (log) + audit_log_format(ab, " cap_fe=%d cap_fver=%x", + name->fcap.fE, name->fcap_ver); +} + +static inline int audit_copy_fcaps(struct audit_names *name, + const struct dentry *dentry) +{ + struct cpu_vfs_cap_data caps; + int rc; + + if (!dentry) + return 0; + + rc = get_vfs_caps_from_disk(dentry, &caps); + if (rc) + return rc; + + name->fcap.permitted = caps.permitted; + name->fcap.inheritable = caps.inheritable; + name->fcap.fE = !!(caps.magic_etc & VFS_CAP_FLAGS_EFFECTIVE); + name->fcap_ver = (caps.magic_etc & VFS_CAP_REVISION_MASK) >> + VFS_CAP_REVISION_SHIFT; + + return 0; +} + +/* Copy inode data into an audit_names. */ +void audit_copy_inode(struct audit_names *name, const struct dentry *dentry, + const struct inode *inode) +{ + name->ino = inode->i_ino; + name->dev = inode->i_sb->s_dev; + name->mode = inode->i_mode; + name->uid = inode->i_uid; + name->gid = inode->i_gid; + name->rdev = inode->i_rdev; + security_inode_getsecid(inode, &name->osid); + audit_copy_fcaps(name, dentry); +} + +/** + * audit_log_name - produce AUDIT_PATH record from struct audit_names + * @context: audit_context for the task + * @n: audit_names structure with reportable details + * @path: optional path to report instead of audit_names->name + * @record_num: record number to report when handling a list of names + * @call_panic: optional pointer to int that will be updated if secid fails + */ +void audit_log_name(struct audit_context *context, struct audit_names *n, + struct path *path, int record_num, int *call_panic) +{ + struct audit_buffer *ab; + ab = audit_log_start(context, GFP_KERNEL, AUDIT_PATH); + if (!ab) + return; + + audit_log_format(ab, "item=%d", record_num); + + if (path) + audit_log_d_path(ab, " name=", path); + else if (n->name) { + switch (n->name_len) { + case AUDIT_NAME_FULL: + /* log the full path */ + audit_log_format(ab, " name="); + audit_log_untrustedstring(ab, n->name->name); + break; + case 0: + /* name was specified as a relative path and the + * directory component is the cwd */ + audit_log_d_path(ab, " name=", &context->pwd); + break; + default: + /* log the name's directory component */ + audit_log_format(ab, " name="); + audit_log_n_untrustedstring(ab, n->name->name, + n->name_len); + } + } else + audit_log_format(ab, " name=(null)"); + + if (n->ino != (unsigned long)-1) + audit_log_format(ab, " inode=%lu" + " dev=%02x:%02x mode=%#ho" + " ouid=%u ogid=%u rdev=%02x:%02x", + n->ino, + MAJOR(n->dev), + MINOR(n->dev), + n->mode, + from_kuid(&init_user_ns, n->uid), + from_kgid(&init_user_ns, n->gid), + MAJOR(n->rdev), + MINOR(n->rdev)); + if (n->osid != 0) { + char *ctx = NULL; + u32 len; + if (security_secid_to_secctx( + n->osid, &ctx, &len)) { + audit_log_format(ab, " osid=%u", n->osid); + if (call_panic) + *call_panic = 2; + } else { + audit_log_format(ab, " obj=%s", ctx); + security_release_secctx(ctx, len); + } + } + + /* log the audit_names record type */ + audit_log_format(ab, " nametype="); + switch(n->type) { + case AUDIT_TYPE_NORMAL: + audit_log_format(ab, "NORMAL"); + break; + case AUDIT_TYPE_PARENT: + audit_log_format(ab, "PARENT"); + break; + case AUDIT_TYPE_CHILD_DELETE: + audit_log_format(ab, "DELETE"); + break; + case AUDIT_TYPE_CHILD_CREATE: + audit_log_format(ab, "CREATE"); + break; + default: + audit_log_format(ab, "UNKNOWN"); + break; + } + + audit_log_fcaps(ab, n); + audit_log_end(ab); +} + +int audit_log_task_context(struct audit_buffer *ab) +{ + char *ctx = NULL; + unsigned len; + int error; + u32 sid; + + security_task_getsecid(current, &sid); + if (!sid) + return 0; + + error = security_secid_to_secctx(sid, &ctx, &len); + if (error) { + if (error != -EINVAL) + goto error_path; + return 0; + } + + audit_log_format(ab, " subj=%s", ctx); + security_release_secctx(ctx, len); + return 0; + +error_path: + audit_panic("error in audit_log_task_context"); + return error; +} +EXPORT_SYMBOL(audit_log_task_context); + +void audit_log_d_path_exe(struct audit_buffer *ab, + struct mm_struct *mm) +{ + struct file *exe_file; + + if (!mm) + goto out_null; + + exe_file = get_mm_exe_file(mm); + if (!exe_file) + goto out_null; + + audit_log_d_path(ab, " exe=", &exe_file->f_path); + fput(exe_file); + return; +out_null: + audit_log_format(ab, " exe=(null)"); +} + +void audit_log_task_info(struct audit_buffer *ab, struct task_struct *tsk) +{ + const struct cred *cred; + char comm[sizeof(tsk->comm)]; + char *tty; + + if (!ab) + return; + + /* tsk == current */ + cred = current_cred(); + + spin_lock_irq(&tsk->sighand->siglock); + if (tsk->signal && tsk->signal->tty && tsk->signal->tty->name) + tty = tsk->signal->tty->name; + else + tty = "(none)"; + spin_unlock_irq(&tsk->sighand->siglock); + + audit_log_format(ab, + " ppid=%d pid=%d auid=%u uid=%u gid=%u" + " euid=%u suid=%u fsuid=%u" + " egid=%u sgid=%u fsgid=%u tty=%s ses=%u", + task_ppid_nr(tsk), + task_pid_nr(tsk), + from_kuid(&init_user_ns, audit_get_loginuid(tsk)), + from_kuid(&init_user_ns, cred->uid), + from_kgid(&init_user_ns, cred->gid), + from_kuid(&init_user_ns, cred->euid), + from_kuid(&init_user_ns, cred->suid), + from_kuid(&init_user_ns, cred->fsuid), + from_kgid(&init_user_ns, cred->egid), + from_kgid(&init_user_ns, cred->sgid), + from_kgid(&init_user_ns, cred->fsgid), + tty, audit_get_sessionid(tsk)); + + audit_log_format(ab, " comm="); + audit_log_untrustedstring(ab, get_task_comm(comm, tsk)); + + audit_log_d_path_exe(ab, tsk->mm); + audit_log_task_context(ab); +} +EXPORT_SYMBOL(audit_log_task_info); + +/** + * audit_log_link_denied - report a link restriction denial + * @operation: specific link opreation + * @link: the path that triggered the restriction + */ +void audit_log_link_denied(const char *operation, struct path *link) +{ + struct audit_buffer *ab; + struct audit_names *name; + + name = kzalloc(sizeof(*name), GFP_NOFS); + if (!name) + return; + + /* Generate AUDIT_ANOM_LINK with subject, operation, outcome. */ + ab = audit_log_start(current->audit_context, GFP_KERNEL, + AUDIT_ANOM_LINK); + if (!ab) + goto out; + audit_log_format(ab, "op=%s", operation); + audit_log_task_info(ab, current); + audit_log_format(ab, " res=0"); + audit_log_end(ab); + + /* Generate AUDIT_PATH record with object. */ + name->type = AUDIT_TYPE_NORMAL; + audit_copy_inode(name, link->dentry, d_backing_inode(link->dentry)); + audit_log_name(current->audit_context, name, link, 0, NULL); +out: + kfree(name); +} + +/** + * audit_log_end - end one audit record + * @ab: the audit_buffer + * + * netlink_unicast() cannot be called inside an irq context because it blocks + * (last arg, flags, is not set to MSG_DONTWAIT), so the audit buffer is placed + * on a queue and a tasklet is scheduled to remove them from the queue outside + * the irq context. May be called in any context. + */ +void audit_log_end(struct audit_buffer *ab) +{ + if (!ab) + return; + if (!audit_rate_check()) { + audit_log_lost("rate limit exceeded"); + } else { + struct nlmsghdr *nlh = nlmsg_hdr(ab->skb); + + nlh->nlmsg_len = ab->skb->len; + kauditd_send_multicast_skb(ab->skb, ab->gfp_mask); + + /* + * The original kaudit unicast socket sends up messages with + * nlmsg_len set to the payload length rather than the entire + * message length. This breaks the standard set by netlink. + * The existing auditd daemon assumes this breakage. Fixing + * this would require co-ordinating a change in the established + * protocol between the kaudit kernel subsystem and the auditd + * userspace code. + */ + nlh->nlmsg_len -= NLMSG_HDRLEN; + + if (audit_pid) { + skb_queue_tail(&audit_skb_queue, ab->skb); + wake_up_interruptible(&kauditd_wait); + } else { + audit_printk_skb(ab->skb); + } + ab->skb = NULL; + } + audit_buffer_free(ab); +} + +/** + * audit_log - Log an audit record + * @ctx: audit context + * @gfp_mask: type of allocation + * @type: audit message type + * @fmt: format string to use + * @...: variable parameters matching the format string + * + * This is a convenience function that calls audit_log_start, + * audit_log_vformat, and audit_log_end. It may be called + * in any context. + */ +void audit_log(struct audit_context *ctx, gfp_t gfp_mask, int type, + const char *fmt, ...) +{ + struct audit_buffer *ab; + va_list args; + + ab = audit_log_start(ctx, gfp_mask, type); + if (ab) { + va_start(args, fmt); + audit_log_vformat(ab, fmt, args); + va_end(args); + audit_log_end(ab); + } +} + +#ifdef CONFIG_SECURITY +/** + * audit_log_secctx - Converts and logs SELinux context + * @ab: audit_buffer + * @secid: security number + * + * This is a helper function that calls security_secid_to_secctx to convert + * secid to secctx and then adds the (converted) SELinux context to the audit + * log by calling audit_log_format, thus also preventing leak of internal secid + * to userspace. If secid cannot be converted audit_panic is called. + */ +void audit_log_secctx(struct audit_buffer *ab, u32 secid) +{ + u32 len; + char *secctx; + + if (security_secid_to_secctx(secid, &secctx, &len)) { + audit_panic("Cannot convert secid to context"); + } else { + audit_log_format(ab, " obj=%s", secctx); + security_release_secctx(secctx, len); + } +} +EXPORT_SYMBOL(audit_log_secctx); +#endif + +EXPORT_SYMBOL(audit_log_start); +EXPORT_SYMBOL(audit_log_end); +EXPORT_SYMBOL(audit_log_format); +EXPORT_SYMBOL(audit_log); diff --git a/kernel/kernel/audit.h b/kernel/kernel/audit.h new file mode 100644 index 000000000..d641f9bb3 --- /dev/null +++ b/kernel/kernel/audit.h @@ -0,0 +1,328 @@ +/* audit -- definition of audit_context structure and supporting types + * + * Copyright 2003-2004 Red Hat, Inc. + * Copyright 2005 Hewlett-Packard Development Company, L.P. + * Copyright 2005 IBM Corporation + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + */ + +#include +#include +#include +#include + +/* AUDIT_NAMES is the number of slots we reserve in the audit_context + * for saving names from getname(). If we get more names we will allocate + * a name dynamically and also add those to the list anchored by names_list. */ +#define AUDIT_NAMES 5 + +/* At task start time, the audit_state is set in the audit_context using + a per-task filter. At syscall entry, the audit_state is augmented by + the syscall filter. */ +enum audit_state { + AUDIT_DISABLED, /* Do not create per-task audit_context. + * No syscall-specific audit records can + * be generated. */ + AUDIT_BUILD_CONTEXT, /* Create the per-task audit_context, + * and fill it in at syscall + * entry time. This makes a full + * syscall record available if some + * other part of the kernel decides it + * should be recorded. */ + AUDIT_RECORD_CONTEXT /* Create the per-task audit_context, + * always fill it in at syscall entry + * time, and always write out the audit + * record at syscall exit time. */ +}; + +/* Rule lists */ +struct audit_watch; +struct audit_tree; +struct audit_chunk; + +struct audit_entry { + struct list_head list; + struct rcu_head rcu; + struct audit_krule rule; +}; + +struct audit_cap_data { + kernel_cap_t permitted; + kernel_cap_t inheritable; + union { + unsigned int fE; /* effective bit of file cap */ + kernel_cap_t effective; /* effective set of process */ + }; +}; + +/* When fs/namei.c:getname() is called, we store the pointer in name and bump + * the refcnt in the associated filename struct. + * + * Further, in fs/namei.c:path_lookup() we store the inode and device. + */ +struct audit_names { + struct list_head list; /* audit_context->names_list */ + + struct filename *name; + int name_len; /* number of chars to log */ + bool hidden; /* don't log this record */ + + unsigned long ino; + dev_t dev; + umode_t mode; + kuid_t uid; + kgid_t gid; + dev_t rdev; + u32 osid; + struct audit_cap_data fcap; + unsigned int fcap_ver; + unsigned char type; /* record type */ + /* + * This was an allocated audit_names and not from the array of + * names allocated in the task audit context. Thus this name + * should be freed on syscall exit. + */ + bool should_free; +}; + +struct audit_proctitle { + int len; /* length of the cmdline field. */ + char *value; /* the cmdline field */ +}; + +/* The per-task audit context. */ +struct audit_context { + int dummy; /* must be the first element */ + int in_syscall; /* 1 if task is in a syscall */ + enum audit_state state, current_state; + unsigned int serial; /* serial number for record */ + int major; /* syscall number */ + struct timespec ctime; /* time of syscall entry */ + unsigned long argv[4]; /* syscall arguments */ + long return_code;/* syscall return code */ + u64 prio; + int return_valid; /* return code is valid */ + /* + * The names_list is the list of all audit_names collected during this + * syscall. The first AUDIT_NAMES entries in the names_list will + * actually be from the preallocated_names array for performance + * reasons. Except during allocation they should never be referenced + * through the preallocated_names array and should only be found/used + * by running the names_list. + */ + struct audit_names preallocated_names[AUDIT_NAMES]; + int name_count; /* total records in names_list */ + struct list_head names_list; /* struct audit_names->list anchor */ + char *filterkey; /* key for rule that triggered record */ + struct path pwd; + struct audit_aux_data *aux; + struct audit_aux_data *aux_pids; + struct sockaddr_storage *sockaddr; + size_t sockaddr_len; + /* Save things to print about task_struct */ + pid_t pid, ppid; + kuid_t uid, euid, suid, fsuid; + kgid_t gid, egid, sgid, fsgid; + unsigned long personality; + int arch; + + pid_t target_pid; + kuid_t target_auid; + kuid_t target_uid; + unsigned int target_sessionid; + u32 target_sid; + char target_comm[TASK_COMM_LEN]; + + struct audit_tree_refs *trees, *first_trees; + struct list_head killed_trees; + int tree_count; + + int type; + union { + struct { + int nargs; + long args[6]; + } socketcall; + struct { + kuid_t uid; + kgid_t gid; + umode_t mode; + u32 osid; + int has_perm; + uid_t perm_uid; + gid_t perm_gid; + umode_t perm_mode; + unsigned long qbytes; + } ipc; + struct { + mqd_t mqdes; + struct mq_attr mqstat; + } mq_getsetattr; + struct { + mqd_t mqdes; + int sigev_signo; + } mq_notify; + struct { + mqd_t mqdes; + size_t msg_len; + unsigned int msg_prio; + struct timespec abs_timeout; + } mq_sendrecv; + struct { + int oflag; + umode_t mode; + struct mq_attr attr; + } mq_open; + struct { + pid_t pid; + struct audit_cap_data cap; + } capset; + struct { + int fd; + int flags; + } mmap; + struct { + int argc; + } execve; + }; + int fds[2]; + struct audit_proctitle proctitle; +}; + +extern u32 audit_ever_enabled; + +extern void audit_copy_inode(struct audit_names *name, + const struct dentry *dentry, + const struct inode *inode); +extern void audit_log_cap(struct audit_buffer *ab, char *prefix, + kernel_cap_t *cap); +extern void audit_log_name(struct audit_context *context, + struct audit_names *n, struct path *path, + int record_num, int *call_panic); + +extern int audit_pid; + +#define AUDIT_INODE_BUCKETS 32 +extern struct list_head audit_inode_hash[AUDIT_INODE_BUCKETS]; + +static inline int audit_hash_ino(u32 ino) +{ + return (ino & (AUDIT_INODE_BUCKETS-1)); +} + +/* Indicates that audit should log the full pathname. */ +#define AUDIT_NAME_FULL -1 + +extern int audit_match_class(int class, unsigned syscall); +extern int audit_comparator(const u32 left, const u32 op, const u32 right); +extern int audit_uid_comparator(kuid_t left, u32 op, kuid_t right); +extern int audit_gid_comparator(kgid_t left, u32 op, kgid_t right); +extern int parent_len(const char *path); +extern int audit_compare_dname_path(const char *dname, const char *path, int plen); +extern struct sk_buff *audit_make_reply(__u32 portid, int seq, int type, + int done, int multi, + const void *payload, int size); +extern void audit_panic(const char *message); + +struct audit_netlink_list { + __u32 portid; + struct net *net; + struct sk_buff_head q; +}; + +int audit_send_list(void *); + +struct audit_net { + struct sock *nlsk; +}; + +extern int selinux_audit_rule_update(void); + +extern struct mutex audit_filter_mutex; +extern void audit_free_rule_rcu(struct rcu_head *); +extern struct list_head audit_filter_list[]; + +extern struct audit_entry *audit_dupe_rule(struct audit_krule *old); + +extern void audit_log_d_path_exe(struct audit_buffer *ab, + struct mm_struct *mm); + +/* audit watch functions */ +#ifdef CONFIG_AUDIT_WATCH +extern void audit_put_watch(struct audit_watch *watch); +extern void audit_get_watch(struct audit_watch *watch); +extern int audit_to_watch(struct audit_krule *krule, char *path, int len, u32 op); +extern int audit_add_watch(struct audit_krule *krule, struct list_head **list); +extern void audit_remove_watch_rule(struct audit_krule *krule); +extern char *audit_watch_path(struct audit_watch *watch); +extern int audit_watch_compare(struct audit_watch *watch, unsigned long ino, dev_t dev); +#else +#define audit_put_watch(w) {} +#define audit_get_watch(w) {} +#define audit_to_watch(k, p, l, o) (-EINVAL) +#define audit_add_watch(k, l) (-EINVAL) +#define audit_remove_watch_rule(k) BUG() +#define audit_watch_path(w) "" +#define audit_watch_compare(w, i, d) 0 + +#endif /* CONFIG_AUDIT_WATCH */ + +#ifdef CONFIG_AUDIT_TREE +extern struct audit_chunk *audit_tree_lookup(const struct inode *); +extern void audit_put_chunk(struct audit_chunk *); +extern int audit_tree_match(struct audit_chunk *, struct audit_tree *); +extern int audit_make_tree(struct audit_krule *, char *, u32); +extern int audit_add_tree_rule(struct audit_krule *); +extern int audit_remove_tree_rule(struct audit_krule *); +extern void audit_trim_trees(void); +extern int audit_tag_tree(char *old, char *new); +extern const char *audit_tree_path(struct audit_tree *); +extern void audit_put_tree(struct audit_tree *); +extern void audit_kill_trees(struct list_head *); +#else +#define audit_remove_tree_rule(rule) BUG() +#define audit_add_tree_rule(rule) -EINVAL +#define audit_make_tree(rule, str, op) -EINVAL +#define audit_trim_trees() (void)0 +#define audit_put_tree(tree) (void)0 +#define audit_tag_tree(old, new) -EINVAL +#define audit_tree_path(rule) "" /* never called */ +#define audit_kill_trees(list) BUG() +#endif + +extern char *audit_unpack_string(void **, size_t *, size_t); + +extern pid_t audit_sig_pid; +extern kuid_t audit_sig_uid; +extern u32 audit_sig_sid; + +#ifdef CONFIG_AUDITSYSCALL +extern int __audit_signal_info(int sig, struct task_struct *t); +static inline int audit_signal_info(int sig, struct task_struct *t) +{ + if (unlikely((audit_pid && t->tgid == audit_pid) || + (audit_signals && !audit_dummy_context()))) + return __audit_signal_info(sig, t); + return 0; +} +extern void audit_filter_inodes(struct task_struct *, struct audit_context *); +extern struct list_head *audit_killed_trees(void); +#else +#define audit_signal_info(s,t) AUDIT_DISABLED +#define audit_filter_inodes(t,c) AUDIT_DISABLED +#endif + +extern struct mutex audit_cmd_mutex; diff --git a/kernel/kernel/audit_tree.c b/kernel/kernel/audit_tree.c new file mode 100644 index 000000000..b0f987727 --- /dev/null +++ b/kernel/kernel/audit_tree.c @@ -0,0 +1,988 @@ +#include "audit.h" +#include +#include +#include +#include +#include + +struct audit_tree; +struct audit_chunk; + +struct audit_tree { + atomic_t count; + int goner; + struct audit_chunk *root; + struct list_head chunks; + struct list_head rules; + struct list_head list; + struct list_head same_root; + struct rcu_head head; + char pathname[]; +}; + +struct audit_chunk { + struct list_head hash; + struct fsnotify_mark mark; + struct list_head trees; /* with root here */ + int dead; + int count; + atomic_long_t refs; + struct rcu_head head; + struct node { + struct list_head list; + struct audit_tree *owner; + unsigned index; /* index; upper bit indicates 'will prune' */ + } owners[]; +}; + +static LIST_HEAD(tree_list); +static LIST_HEAD(prune_list); +static struct task_struct *prune_thread; + +/* + * One struct chunk is attached to each inode of interest. + * We replace struct chunk on tagging/untagging. + * Rules have pointer to struct audit_tree. + * Rules have struct list_head rlist forming a list of rules over + * the same tree. + * References to struct chunk are collected at audit_inode{,_child}() + * time and used in AUDIT_TREE rule matching. + * These references are dropped at the same time we are calling + * audit_free_names(), etc. + * + * Cyclic lists galore: + * tree.chunks anchors chunk.owners[].list hash_lock + * tree.rules anchors rule.rlist audit_filter_mutex + * chunk.trees anchors tree.same_root hash_lock + * chunk.hash is a hash with middle bits of watch.inode as + * a hash function. RCU, hash_lock + * + * tree is refcounted; one reference for "some rules on rules_list refer to + * it", one for each chunk with pointer to it. + * + * chunk is refcounted by embedded fsnotify_mark + .refs (non-zero refcount + * of watch contributes 1 to .refs). + * + * node.index allows to get from node.list to containing chunk. + * MSB of that sucker is stolen to mark taggings that we might have to + * revert - several operations have very unpleasant cleanup logics and + * that makes a difference. Some. + */ + +static struct fsnotify_group *audit_tree_group; + +static struct audit_tree *alloc_tree(const char *s) +{ + struct audit_tree *tree; + + tree = kmalloc(sizeof(struct audit_tree) + strlen(s) + 1, GFP_KERNEL); + if (tree) { + atomic_set(&tree->count, 1); + tree->goner = 0; + INIT_LIST_HEAD(&tree->chunks); + INIT_LIST_HEAD(&tree->rules); + INIT_LIST_HEAD(&tree->list); + INIT_LIST_HEAD(&tree->same_root); + tree->root = NULL; + strcpy(tree->pathname, s); + } + return tree; +} + +static inline void get_tree(struct audit_tree *tree) +{ + atomic_inc(&tree->count); +} + +static inline void put_tree(struct audit_tree *tree) +{ + if (atomic_dec_and_test(&tree->count)) + kfree_rcu(tree, head); +} + +/* to avoid bringing the entire thing in audit.h */ +const char *audit_tree_path(struct audit_tree *tree) +{ + return tree->pathname; +} + +static void free_chunk(struct audit_chunk *chunk) +{ + int i; + + for (i = 0; i < chunk->count; i++) { + if (chunk->owners[i].owner) + put_tree(chunk->owners[i].owner); + } + kfree(chunk); +} + +void audit_put_chunk(struct audit_chunk *chunk) +{ + if (atomic_long_dec_and_test(&chunk->refs)) + free_chunk(chunk); +} + +static void __put_chunk(struct rcu_head *rcu) +{ + struct audit_chunk *chunk = container_of(rcu, struct audit_chunk, head); + audit_put_chunk(chunk); +} + +static void audit_tree_destroy_watch(struct fsnotify_mark *entry) +{ + struct audit_chunk *chunk = container_of(entry, struct audit_chunk, mark); + call_rcu(&chunk->head, __put_chunk); +} + +static struct audit_chunk *alloc_chunk(int count) +{ + struct audit_chunk *chunk; + size_t size; + int i; + + size = offsetof(struct audit_chunk, owners) + count * sizeof(struct node); + chunk = kzalloc(size, GFP_KERNEL); + if (!chunk) + return NULL; + + INIT_LIST_HEAD(&chunk->hash); + INIT_LIST_HEAD(&chunk->trees); + chunk->count = count; + atomic_long_set(&chunk->refs, 1); + for (i = 0; i < count; i++) { + INIT_LIST_HEAD(&chunk->owners[i].list); + chunk->owners[i].index = i; + } + fsnotify_init_mark(&chunk->mark, audit_tree_destroy_watch); + chunk->mark.mask = FS_IN_IGNORED; + return chunk; +} + +enum {HASH_SIZE = 128}; +static struct list_head chunk_hash_heads[HASH_SIZE]; +static __cacheline_aligned_in_smp DEFINE_SPINLOCK(hash_lock); + +static inline struct list_head *chunk_hash(const struct inode *inode) +{ + unsigned long n = (unsigned long)inode / L1_CACHE_BYTES; + return chunk_hash_heads + n % HASH_SIZE; +} + +/* hash_lock & entry->lock is held by caller */ +static void insert_hash(struct audit_chunk *chunk) +{ + struct fsnotify_mark *entry = &chunk->mark; + struct list_head *list; + + if (!entry->inode) + return; + list = chunk_hash(entry->inode); + list_add_rcu(&chunk->hash, list); +} + +/* called under rcu_read_lock */ +struct audit_chunk *audit_tree_lookup(const struct inode *inode) +{ + struct list_head *list = chunk_hash(inode); + struct audit_chunk *p; + + list_for_each_entry_rcu(p, list, hash) { + /* mark.inode may have gone NULL, but who cares? */ + if (p->mark.inode == inode) { + atomic_long_inc(&p->refs); + return p; + } + } + return NULL; +} + +int audit_tree_match(struct audit_chunk *chunk, struct audit_tree *tree) +{ + int n; + for (n = 0; n < chunk->count; n++) + if (chunk->owners[n].owner == tree) + return 1; + return 0; +} + +/* tagging and untagging inodes with trees */ + +static struct audit_chunk *find_chunk(struct node *p) +{ + int index = p->index & ~(1U<<31); + p -= index; + return container_of(p, struct audit_chunk, owners[0]); +} + +static void untag_chunk(struct node *p) +{ + struct audit_chunk *chunk = find_chunk(p); + struct fsnotify_mark *entry = &chunk->mark; + struct audit_chunk *new = NULL; + struct audit_tree *owner; + int size = chunk->count - 1; + int i, j; + + fsnotify_get_mark(entry); + + spin_unlock(&hash_lock); + + if (size) + new = alloc_chunk(size); + + spin_lock(&entry->lock); + if (chunk->dead || !entry->inode) { + spin_unlock(&entry->lock); + if (new) + free_chunk(new); + goto out; + } + + owner = p->owner; + + if (!size) { + chunk->dead = 1; + spin_lock(&hash_lock); + list_del_init(&chunk->trees); + if (owner->root == chunk) + owner->root = NULL; + list_del_init(&p->list); + list_del_rcu(&chunk->hash); + spin_unlock(&hash_lock); + spin_unlock(&entry->lock); + fsnotify_destroy_mark(entry, audit_tree_group); + goto out; + } + + if (!new) + goto Fallback; + + fsnotify_duplicate_mark(&new->mark, entry); + if (fsnotify_add_mark(&new->mark, new->mark.group, new->mark.inode, NULL, 1)) { + fsnotify_put_mark(&new->mark); + goto Fallback; + } + + chunk->dead = 1; + spin_lock(&hash_lock); + list_replace_init(&chunk->trees, &new->trees); + if (owner->root == chunk) { + list_del_init(&owner->same_root); + owner->root = NULL; + } + + for (i = j = 0; j <= size; i++, j++) { + struct audit_tree *s; + if (&chunk->owners[j] == p) { + list_del_init(&p->list); + i--; + continue; + } + s = chunk->owners[j].owner; + new->owners[i].owner = s; + new->owners[i].index = chunk->owners[j].index - j + i; + if (!s) /* result of earlier fallback */ + continue; + get_tree(s); + list_replace_init(&chunk->owners[j].list, &new->owners[i].list); + } + + list_replace_rcu(&chunk->hash, &new->hash); + list_for_each_entry(owner, &new->trees, same_root) + owner->root = new; + spin_unlock(&hash_lock); + spin_unlock(&entry->lock); + fsnotify_destroy_mark(entry, audit_tree_group); + fsnotify_put_mark(&new->mark); /* drop initial reference */ + goto out; + +Fallback: + // do the best we can + spin_lock(&hash_lock); + if (owner->root == chunk) { + list_del_init(&owner->same_root); + owner->root = NULL; + } + list_del_init(&p->list); + p->owner = NULL; + put_tree(owner); + spin_unlock(&hash_lock); + spin_unlock(&entry->lock); +out: + fsnotify_put_mark(entry); + spin_lock(&hash_lock); +} + +static int create_chunk(struct inode *inode, struct audit_tree *tree) +{ + struct fsnotify_mark *entry; + struct audit_chunk *chunk = alloc_chunk(1); + if (!chunk) + return -ENOMEM; + + entry = &chunk->mark; + if (fsnotify_add_mark(entry, audit_tree_group, inode, NULL, 0)) { + fsnotify_put_mark(entry); + return -ENOSPC; + } + + spin_lock(&entry->lock); + spin_lock(&hash_lock); + if (tree->goner) { + spin_unlock(&hash_lock); + chunk->dead = 1; + spin_unlock(&entry->lock); + fsnotify_destroy_mark(entry, audit_tree_group); + fsnotify_put_mark(entry); + return 0; + } + chunk->owners[0].index = (1U << 31); + chunk->owners[0].owner = tree; + get_tree(tree); + list_add(&chunk->owners[0].list, &tree->chunks); + if (!tree->root) { + tree->root = chunk; + list_add(&tree->same_root, &chunk->trees); + } + insert_hash(chunk); + spin_unlock(&hash_lock); + spin_unlock(&entry->lock); + fsnotify_put_mark(entry); /* drop initial reference */ + return 0; +} + +/* the first tagged inode becomes root of tree */ +static int tag_chunk(struct inode *inode, struct audit_tree *tree) +{ + struct fsnotify_mark *old_entry, *chunk_entry; + struct audit_tree *owner; + struct audit_chunk *chunk, *old; + struct node *p; + int n; + + old_entry = fsnotify_find_inode_mark(audit_tree_group, inode); + if (!old_entry) + return create_chunk(inode, tree); + + old = container_of(old_entry, struct audit_chunk, mark); + + /* are we already there? */ + spin_lock(&hash_lock); + for (n = 0; n < old->count; n++) { + if (old->owners[n].owner == tree) { + spin_unlock(&hash_lock); + fsnotify_put_mark(old_entry); + return 0; + } + } + spin_unlock(&hash_lock); + + chunk = alloc_chunk(old->count + 1); + if (!chunk) { + fsnotify_put_mark(old_entry); + return -ENOMEM; + } + + chunk_entry = &chunk->mark; + + spin_lock(&old_entry->lock); + if (!old_entry->inode) { + /* old_entry is being shot, lets just lie */ + spin_unlock(&old_entry->lock); + fsnotify_put_mark(old_entry); + free_chunk(chunk); + return -ENOENT; + } + + fsnotify_duplicate_mark(chunk_entry, old_entry); + if (fsnotify_add_mark(chunk_entry, chunk_entry->group, chunk_entry->inode, NULL, 1)) { + spin_unlock(&old_entry->lock); + fsnotify_put_mark(chunk_entry); + fsnotify_put_mark(old_entry); + return -ENOSPC; + } + + /* even though we hold old_entry->lock, this is safe since chunk_entry->lock could NEVER have been grabbed before */ + spin_lock(&chunk_entry->lock); + spin_lock(&hash_lock); + + /* we now hold old_entry->lock, chunk_entry->lock, and hash_lock */ + if (tree->goner) { + spin_unlock(&hash_lock); + chunk->dead = 1; + spin_unlock(&chunk_entry->lock); + spin_unlock(&old_entry->lock); + + fsnotify_destroy_mark(chunk_entry, audit_tree_group); + + fsnotify_put_mark(chunk_entry); + fsnotify_put_mark(old_entry); + return 0; + } + list_replace_init(&old->trees, &chunk->trees); + for (n = 0, p = chunk->owners; n < old->count; n++, p++) { + struct audit_tree *s = old->owners[n].owner; + p->owner = s; + p->index = old->owners[n].index; + if (!s) /* result of fallback in untag */ + continue; + get_tree(s); + list_replace_init(&old->owners[n].list, &p->list); + } + p->index = (chunk->count - 1) | (1U<<31); + p->owner = tree; + get_tree(tree); + list_add(&p->list, &tree->chunks); + list_replace_rcu(&old->hash, &chunk->hash); + list_for_each_entry(owner, &chunk->trees, same_root) + owner->root = chunk; + old->dead = 1; + if (!tree->root) { + tree->root = chunk; + list_add(&tree->same_root, &chunk->trees); + } + spin_unlock(&hash_lock); + spin_unlock(&chunk_entry->lock); + spin_unlock(&old_entry->lock); + fsnotify_destroy_mark(old_entry, audit_tree_group); + fsnotify_put_mark(chunk_entry); /* drop initial reference */ + fsnotify_put_mark(old_entry); /* pair to fsnotify_find mark_entry */ + return 0; +} + +static void audit_tree_log_remove_rule(struct audit_krule *rule) +{ + struct audit_buffer *ab; + + ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_CONFIG_CHANGE); + if (unlikely(!ab)) + return; + audit_log_format(ab, "op="); + audit_log_string(ab, "remove_rule"); + audit_log_format(ab, " dir="); + audit_log_untrustedstring(ab, rule->tree->pathname); + audit_log_key(ab, rule->filterkey); + audit_log_format(ab, " list=%d res=1", rule->listnr); + audit_log_end(ab); +} + +static void kill_rules(struct audit_tree *tree) +{ + struct audit_krule *rule, *next; + struct audit_entry *entry; + + list_for_each_entry_safe(rule, next, &tree->rules, rlist) { + entry = container_of(rule, struct audit_entry, rule); + + list_del_init(&rule->rlist); + if (rule->tree) { + /* not a half-baked one */ + audit_tree_log_remove_rule(rule); + rule->tree = NULL; + list_del_rcu(&entry->list); + list_del(&entry->rule.list); + call_rcu(&entry->rcu, audit_free_rule_rcu); + } + } +} + +/* + * finish killing struct audit_tree + */ +static void prune_one(struct audit_tree *victim) +{ + spin_lock(&hash_lock); + while (!list_empty(&victim->chunks)) { + struct node *p; + + p = list_entry(victim->chunks.next, struct node, list); + + untag_chunk(p); + } + spin_unlock(&hash_lock); + put_tree(victim); +} + +/* trim the uncommitted chunks from tree */ + +static void trim_marked(struct audit_tree *tree) +{ + struct list_head *p, *q; + spin_lock(&hash_lock); + if (tree->goner) { + spin_unlock(&hash_lock); + return; + } + /* reorder */ + for (p = tree->chunks.next; p != &tree->chunks; p = q) { + struct node *node = list_entry(p, struct node, list); + q = p->next; + if (node->index & (1U<<31)) { + list_del_init(p); + list_add(p, &tree->chunks); + } + } + + while (!list_empty(&tree->chunks)) { + struct node *node; + + node = list_entry(tree->chunks.next, struct node, list); + + /* have we run out of marked? */ + if (!(node->index & (1U<<31))) + break; + + untag_chunk(node); + } + if (!tree->root && !tree->goner) { + tree->goner = 1; + spin_unlock(&hash_lock); + mutex_lock(&audit_filter_mutex); + kill_rules(tree); + list_del_init(&tree->list); + mutex_unlock(&audit_filter_mutex); + prune_one(tree); + } else { + spin_unlock(&hash_lock); + } +} + +static void audit_schedule_prune(void); + +/* called with audit_filter_mutex */ +int audit_remove_tree_rule(struct audit_krule *rule) +{ + struct audit_tree *tree; + tree = rule->tree; + if (tree) { + spin_lock(&hash_lock); + list_del_init(&rule->rlist); + if (list_empty(&tree->rules) && !tree->goner) { + tree->root = NULL; + list_del_init(&tree->same_root); + tree->goner = 1; + list_move(&tree->list, &prune_list); + rule->tree = NULL; + spin_unlock(&hash_lock); + audit_schedule_prune(); + return 1; + } + rule->tree = NULL; + spin_unlock(&hash_lock); + return 1; + } + return 0; +} + +static int compare_root(struct vfsmount *mnt, void *arg) +{ + return d_backing_inode(mnt->mnt_root) == arg; +} + +void audit_trim_trees(void) +{ + struct list_head cursor; + + mutex_lock(&audit_filter_mutex); + list_add(&cursor, &tree_list); + while (cursor.next != &tree_list) { + struct audit_tree *tree; + struct path path; + struct vfsmount *root_mnt; + struct node *node; + int err; + + tree = container_of(cursor.next, struct audit_tree, list); + get_tree(tree); + list_del(&cursor); + list_add(&cursor, &tree->list); + mutex_unlock(&audit_filter_mutex); + + err = kern_path(tree->pathname, 0, &path); + if (err) + goto skip_it; + + root_mnt = collect_mounts(&path); + path_put(&path); + if (IS_ERR(root_mnt)) + goto skip_it; + + spin_lock(&hash_lock); + list_for_each_entry(node, &tree->chunks, list) { + struct audit_chunk *chunk = find_chunk(node); + /* this could be NULL if the watch is dying else where... */ + struct inode *inode = chunk->mark.inode; + node->index |= 1U<<31; + if (iterate_mounts(compare_root, inode, root_mnt)) + node->index &= ~(1U<<31); + } + spin_unlock(&hash_lock); + trim_marked(tree); + drop_collected_mounts(root_mnt); +skip_it: + put_tree(tree); + mutex_lock(&audit_filter_mutex); + } + list_del(&cursor); + mutex_unlock(&audit_filter_mutex); +} + +int audit_make_tree(struct audit_krule *rule, char *pathname, u32 op) +{ + + if (pathname[0] != '/' || + rule->listnr != AUDIT_FILTER_EXIT || + op != Audit_equal || + rule->inode_f || rule->watch || rule->tree) + return -EINVAL; + rule->tree = alloc_tree(pathname); + if (!rule->tree) + return -ENOMEM; + return 0; +} + +void audit_put_tree(struct audit_tree *tree) +{ + put_tree(tree); +} + +static int tag_mount(struct vfsmount *mnt, void *arg) +{ + return tag_chunk(d_backing_inode(mnt->mnt_root), arg); +} + +/* + * That gets run when evict_chunk() ends up needing to kill audit_tree. + * Runs from a separate thread. + */ +static int prune_tree_thread(void *unused) +{ + for (;;) { + set_current_state(TASK_INTERRUPTIBLE); + if (list_empty(&prune_list)) + schedule(); + __set_current_state(TASK_RUNNING); + + mutex_lock(&audit_cmd_mutex); + mutex_lock(&audit_filter_mutex); + + while (!list_empty(&prune_list)) { + struct audit_tree *victim; + + victim = list_entry(prune_list.next, + struct audit_tree, list); + list_del_init(&victim->list); + + mutex_unlock(&audit_filter_mutex); + + prune_one(victim); + + mutex_lock(&audit_filter_mutex); + } + + mutex_unlock(&audit_filter_mutex); + mutex_unlock(&audit_cmd_mutex); + } + return 0; +} + +static int audit_launch_prune(void) +{ + if (prune_thread) + return 0; + prune_thread = kthread_create(prune_tree_thread, NULL, + "audit_prune_tree"); + if (IS_ERR(prune_thread)) { + pr_err("cannot start thread audit_prune_tree"); + prune_thread = NULL; + return -ENOMEM; + } else { + wake_up_process(prune_thread); + return 0; + } +} + +/* called with audit_filter_mutex */ +int audit_add_tree_rule(struct audit_krule *rule) +{ + struct audit_tree *seed = rule->tree, *tree; + struct path path; + struct vfsmount *mnt; + int err; + + rule->tree = NULL; + list_for_each_entry(tree, &tree_list, list) { + if (!strcmp(seed->pathname, tree->pathname)) { + put_tree(seed); + rule->tree = tree; + list_add(&rule->rlist, &tree->rules); + return 0; + } + } + tree = seed; + list_add(&tree->list, &tree_list); + list_add(&rule->rlist, &tree->rules); + /* do not set rule->tree yet */ + mutex_unlock(&audit_filter_mutex); + + if (unlikely(!prune_thread)) { + err = audit_launch_prune(); + if (err) + goto Err; + } + + err = kern_path(tree->pathname, 0, &path); + if (err) + goto Err; + mnt = collect_mounts(&path); + path_put(&path); + if (IS_ERR(mnt)) { + err = PTR_ERR(mnt); + goto Err; + } + + get_tree(tree); + err = iterate_mounts(tag_mount, tree, mnt); + drop_collected_mounts(mnt); + + if (!err) { + struct node *node; + spin_lock(&hash_lock); + list_for_each_entry(node, &tree->chunks, list) + node->index &= ~(1U<<31); + spin_unlock(&hash_lock); + } else { + trim_marked(tree); + goto Err; + } + + mutex_lock(&audit_filter_mutex); + if (list_empty(&rule->rlist)) { + put_tree(tree); + return -ENOENT; + } + rule->tree = tree; + put_tree(tree); + + return 0; +Err: + mutex_lock(&audit_filter_mutex); + list_del_init(&tree->list); + list_del_init(&tree->rules); + put_tree(tree); + return err; +} + +int audit_tag_tree(char *old, char *new) +{ + struct list_head cursor, barrier; + int failed = 0; + struct path path1, path2; + struct vfsmount *tagged; + int err; + + err = kern_path(new, 0, &path2); + if (err) + return err; + tagged = collect_mounts(&path2); + path_put(&path2); + if (IS_ERR(tagged)) + return PTR_ERR(tagged); + + err = kern_path(old, 0, &path1); + if (err) { + drop_collected_mounts(tagged); + return err; + } + + mutex_lock(&audit_filter_mutex); + list_add(&barrier, &tree_list); + list_add(&cursor, &barrier); + + while (cursor.next != &tree_list) { + struct audit_tree *tree; + int good_one = 0; + + tree = container_of(cursor.next, struct audit_tree, list); + get_tree(tree); + list_del(&cursor); + list_add(&cursor, &tree->list); + mutex_unlock(&audit_filter_mutex); + + err = kern_path(tree->pathname, 0, &path2); + if (!err) { + good_one = path_is_under(&path1, &path2); + path_put(&path2); + } + + if (!good_one) { + put_tree(tree); + mutex_lock(&audit_filter_mutex); + continue; + } + + failed = iterate_mounts(tag_mount, tree, tagged); + if (failed) { + put_tree(tree); + mutex_lock(&audit_filter_mutex); + break; + } + + mutex_lock(&audit_filter_mutex); + spin_lock(&hash_lock); + if (!tree->goner) { + list_del(&tree->list); + list_add(&tree->list, &tree_list); + } + spin_unlock(&hash_lock); + put_tree(tree); + } + + while (barrier.prev != &tree_list) { + struct audit_tree *tree; + + tree = container_of(barrier.prev, struct audit_tree, list); + get_tree(tree); + list_del(&tree->list); + list_add(&tree->list, &barrier); + mutex_unlock(&audit_filter_mutex); + + if (!failed) { + struct node *node; + spin_lock(&hash_lock); + list_for_each_entry(node, &tree->chunks, list) + node->index &= ~(1U<<31); + spin_unlock(&hash_lock); + } else { + trim_marked(tree); + } + + put_tree(tree); + mutex_lock(&audit_filter_mutex); + } + list_del(&barrier); + list_del(&cursor); + mutex_unlock(&audit_filter_mutex); + path_put(&path1); + drop_collected_mounts(tagged); + return failed; +} + + +static void audit_schedule_prune(void) +{ + wake_up_process(prune_thread); +} + +/* + * ... and that one is done if evict_chunk() decides to delay until the end + * of syscall. Runs synchronously. + */ +void audit_kill_trees(struct list_head *list) +{ + mutex_lock(&audit_cmd_mutex); + mutex_lock(&audit_filter_mutex); + + while (!list_empty(list)) { + struct audit_tree *victim; + + victim = list_entry(list->next, struct audit_tree, list); + kill_rules(victim); + list_del_init(&victim->list); + + mutex_unlock(&audit_filter_mutex); + + prune_one(victim); + + mutex_lock(&audit_filter_mutex); + } + + mutex_unlock(&audit_filter_mutex); + mutex_unlock(&audit_cmd_mutex); +} + +/* + * Here comes the stuff asynchronous to auditctl operations + */ + +static void evict_chunk(struct audit_chunk *chunk) +{ + struct audit_tree *owner; + struct list_head *postponed = audit_killed_trees(); + int need_prune = 0; + int n; + + if (chunk->dead) + return; + + chunk->dead = 1; + mutex_lock(&audit_filter_mutex); + spin_lock(&hash_lock); + while (!list_empty(&chunk->trees)) { + owner = list_entry(chunk->trees.next, + struct audit_tree, same_root); + owner->goner = 1; + owner->root = NULL; + list_del_init(&owner->same_root); + spin_unlock(&hash_lock); + if (!postponed) { + kill_rules(owner); + list_move(&owner->list, &prune_list); + need_prune = 1; + } else { + list_move(&owner->list, postponed); + } + spin_lock(&hash_lock); + } + list_del_rcu(&chunk->hash); + for (n = 0; n < chunk->count; n++) + list_del_init(&chunk->owners[n].list); + spin_unlock(&hash_lock); + mutex_unlock(&audit_filter_mutex); + if (need_prune) + audit_schedule_prune(); +} + +static int audit_tree_handle_event(struct fsnotify_group *group, + struct inode *to_tell, + struct fsnotify_mark *inode_mark, + struct fsnotify_mark *vfsmount_mark, + u32 mask, void *data, int data_type, + const unsigned char *file_name, u32 cookie) +{ + return 0; +} + +static void audit_tree_freeing_mark(struct fsnotify_mark *entry, struct fsnotify_group *group) +{ + struct audit_chunk *chunk = container_of(entry, struct audit_chunk, mark); + + evict_chunk(chunk); + + /* + * We are guaranteed to have at least one reference to the mark from + * either the inode or the caller of fsnotify_destroy_mark(). + */ + BUG_ON(atomic_read(&entry->refcnt) < 1); +} + +static const struct fsnotify_ops audit_tree_ops = { + .handle_event = audit_tree_handle_event, + .freeing_mark = audit_tree_freeing_mark, +}; + +static int __init audit_tree_init(void) +{ + int i; + + audit_tree_group = fsnotify_alloc_group(&audit_tree_ops); + if (IS_ERR(audit_tree_group)) + audit_panic("cannot initialize fsnotify group for rectree watches"); + + for (i = 0; i < HASH_SIZE; i++) + INIT_LIST_HEAD(&chunk_hash_heads[i]); + + return 0; +} +__initcall(audit_tree_init); diff --git a/kernel/kernel/audit_watch.c b/kernel/kernel/audit_watch.c new file mode 100644 index 000000000..6e30024d9 --- /dev/null +++ b/kernel/kernel/audit_watch.c @@ -0,0 +1,519 @@ +/* audit_watch.c -- watching inodes + * + * Copyright 2003-2009 Red Hat, Inc. + * Copyright 2005 Hewlett-Packard Development Company, L.P. + * Copyright 2005 IBM Corporation + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include "audit.h" + +/* + * Reference counting: + * + * audit_parent: lifetime is from audit_init_parent() to receipt of an FS_IGNORED + * event. Each audit_watch holds a reference to its associated parent. + * + * audit_watch: if added to lists, lifetime is from audit_init_watch() to + * audit_remove_watch(). Additionally, an audit_watch may exist + * temporarily to assist in searching existing filter data. Each + * audit_krule holds a reference to its associated watch. + */ + +struct audit_watch { + atomic_t count; /* reference count */ + dev_t dev; /* associated superblock device */ + char *path; /* insertion path */ + unsigned long ino; /* associated inode number */ + struct audit_parent *parent; /* associated parent */ + struct list_head wlist; /* entry in parent->watches list */ + struct list_head rules; /* anchor for krule->rlist */ +}; + +struct audit_parent { + struct list_head watches; /* anchor for audit_watch->wlist */ + struct fsnotify_mark mark; /* fsnotify mark on the inode */ +}; + +/* fsnotify handle. */ +static struct fsnotify_group *audit_watch_group; + +/* fsnotify events we care about. */ +#define AUDIT_FS_WATCH (FS_MOVE | FS_CREATE | FS_DELETE | FS_DELETE_SELF |\ + FS_MOVE_SELF | FS_EVENT_ON_CHILD) + +static void audit_free_parent(struct audit_parent *parent) +{ + WARN_ON(!list_empty(&parent->watches)); + kfree(parent); +} + +static void audit_watch_free_mark(struct fsnotify_mark *entry) +{ + struct audit_parent *parent; + + parent = container_of(entry, struct audit_parent, mark); + audit_free_parent(parent); +} + +static void audit_get_parent(struct audit_parent *parent) +{ + if (likely(parent)) + fsnotify_get_mark(&parent->mark); +} + +static void audit_put_parent(struct audit_parent *parent) +{ + if (likely(parent)) + fsnotify_put_mark(&parent->mark); +} + +/* + * Find and return the audit_parent on the given inode. If found a reference + * is taken on this parent. + */ +static inline struct audit_parent *audit_find_parent(struct inode *inode) +{ + struct audit_parent *parent = NULL; + struct fsnotify_mark *entry; + + entry = fsnotify_find_inode_mark(audit_watch_group, inode); + if (entry) + parent = container_of(entry, struct audit_parent, mark); + + return parent; +} + +void audit_get_watch(struct audit_watch *watch) +{ + atomic_inc(&watch->count); +} + +void audit_put_watch(struct audit_watch *watch) +{ + if (atomic_dec_and_test(&watch->count)) { + WARN_ON(watch->parent); + WARN_ON(!list_empty(&watch->rules)); + kfree(watch->path); + kfree(watch); + } +} + +static void audit_remove_watch(struct audit_watch *watch) +{ + list_del(&watch->wlist); + audit_put_parent(watch->parent); + watch->parent = NULL; + audit_put_watch(watch); /* match initial get */ +} + +char *audit_watch_path(struct audit_watch *watch) +{ + return watch->path; +} + +int audit_watch_compare(struct audit_watch *watch, unsigned long ino, dev_t dev) +{ + return (watch->ino != (unsigned long)-1) && + (watch->ino == ino) && + (watch->dev == dev); +} + +/* Initialize a parent watch entry. */ +static struct audit_parent *audit_init_parent(struct path *path) +{ + struct inode *inode = d_backing_inode(path->dentry); + struct audit_parent *parent; + int ret; + + parent = kzalloc(sizeof(*parent), GFP_KERNEL); + if (unlikely(!parent)) + return ERR_PTR(-ENOMEM); + + INIT_LIST_HEAD(&parent->watches); + + fsnotify_init_mark(&parent->mark, audit_watch_free_mark); + parent->mark.mask = AUDIT_FS_WATCH; + ret = fsnotify_add_mark(&parent->mark, audit_watch_group, inode, NULL, 0); + if (ret < 0) { + audit_free_parent(parent); + return ERR_PTR(ret); + } + + return parent; +} + +/* Initialize a watch entry. */ +static struct audit_watch *audit_init_watch(char *path) +{ + struct audit_watch *watch; + + watch = kzalloc(sizeof(*watch), GFP_KERNEL); + if (unlikely(!watch)) + return ERR_PTR(-ENOMEM); + + INIT_LIST_HEAD(&watch->rules); + atomic_set(&watch->count, 1); + watch->path = path; + watch->dev = (dev_t)-1; + watch->ino = (unsigned long)-1; + + return watch; +} + +/* Translate a watch string to kernel respresentation. */ +int audit_to_watch(struct audit_krule *krule, char *path, int len, u32 op) +{ + struct audit_watch *watch; + + if (!audit_watch_group) + return -EOPNOTSUPP; + + if (path[0] != '/' || path[len-1] == '/' || + krule->listnr != AUDIT_FILTER_EXIT || + op != Audit_equal || + krule->inode_f || krule->watch || krule->tree) + return -EINVAL; + + watch = audit_init_watch(path); + if (IS_ERR(watch)) + return PTR_ERR(watch); + + audit_get_watch(watch); + krule->watch = watch; + + return 0; +} + +/* Duplicate the given audit watch. The new watch's rules list is initialized + * to an empty list and wlist is undefined. */ +static struct audit_watch *audit_dupe_watch(struct audit_watch *old) +{ + char *path; + struct audit_watch *new; + + path = kstrdup(old->path, GFP_KERNEL); + if (unlikely(!path)) + return ERR_PTR(-ENOMEM); + + new = audit_init_watch(path); + if (IS_ERR(new)) { + kfree(path); + goto out; + } + + new->dev = old->dev; + new->ino = old->ino; + audit_get_parent(old->parent); + new->parent = old->parent; + +out: + return new; +} + +static void audit_watch_log_rule_change(struct audit_krule *r, struct audit_watch *w, char *op) +{ + if (audit_enabled) { + struct audit_buffer *ab; + ab = audit_log_start(NULL, GFP_NOFS, AUDIT_CONFIG_CHANGE); + if (unlikely(!ab)) + return; + audit_log_format(ab, "auid=%u ses=%u op=", + from_kuid(&init_user_ns, audit_get_loginuid(current)), + audit_get_sessionid(current)); + audit_log_string(ab, op); + audit_log_format(ab, " path="); + audit_log_untrustedstring(ab, w->path); + audit_log_key(ab, r->filterkey); + audit_log_format(ab, " list=%d res=1", r->listnr); + audit_log_end(ab); + } +} + +/* Update inode info in audit rules based on filesystem event. */ +static void audit_update_watch(struct audit_parent *parent, + const char *dname, dev_t dev, + unsigned long ino, unsigned invalidating) +{ + struct audit_watch *owatch, *nwatch, *nextw; + struct audit_krule *r, *nextr; + struct audit_entry *oentry, *nentry; + + mutex_lock(&audit_filter_mutex); + /* Run all of the watches on this parent looking for the one that + * matches the given dname */ + list_for_each_entry_safe(owatch, nextw, &parent->watches, wlist) { + if (audit_compare_dname_path(dname, owatch->path, + AUDIT_NAME_FULL)) + continue; + + /* If the update involves invalidating rules, do the inode-based + * filtering now, so we don't omit records. */ + if (invalidating && !audit_dummy_context()) + audit_filter_inodes(current, current->audit_context); + + /* updating ino will likely change which audit_hash_list we + * are on so we need a new watch for the new list */ + nwatch = audit_dupe_watch(owatch); + if (IS_ERR(nwatch)) { + mutex_unlock(&audit_filter_mutex); + audit_panic("error updating watch, skipping"); + return; + } + nwatch->dev = dev; + nwatch->ino = ino; + + list_for_each_entry_safe(r, nextr, &owatch->rules, rlist) { + + oentry = container_of(r, struct audit_entry, rule); + list_del(&oentry->rule.rlist); + list_del_rcu(&oentry->list); + + nentry = audit_dupe_rule(&oentry->rule); + if (IS_ERR(nentry)) { + list_del(&oentry->rule.list); + audit_panic("error updating watch, removing"); + } else { + int h = audit_hash_ino((u32)ino); + + /* + * nentry->rule.watch == oentry->rule.watch so + * we must drop that reference and set it to our + * new watch. + */ + audit_put_watch(nentry->rule.watch); + audit_get_watch(nwatch); + nentry->rule.watch = nwatch; + list_add(&nentry->rule.rlist, &nwatch->rules); + list_add_rcu(&nentry->list, &audit_inode_hash[h]); + list_replace(&oentry->rule.list, + &nentry->rule.list); + } + + audit_watch_log_rule_change(r, owatch, "updated_rules"); + + call_rcu(&oentry->rcu, audit_free_rule_rcu); + } + + audit_remove_watch(owatch); + goto add_watch_to_parent; /* event applies to a single watch */ + } + mutex_unlock(&audit_filter_mutex); + return; + +add_watch_to_parent: + list_add(&nwatch->wlist, &parent->watches); + mutex_unlock(&audit_filter_mutex); + return; +} + +/* Remove all watches & rules associated with a parent that is going away. */ +static void audit_remove_parent_watches(struct audit_parent *parent) +{ + struct audit_watch *w, *nextw; + struct audit_krule *r, *nextr; + struct audit_entry *e; + + mutex_lock(&audit_filter_mutex); + list_for_each_entry_safe(w, nextw, &parent->watches, wlist) { + list_for_each_entry_safe(r, nextr, &w->rules, rlist) { + e = container_of(r, struct audit_entry, rule); + audit_watch_log_rule_change(r, w, "remove_rule"); + list_del(&r->rlist); + list_del(&r->list); + list_del_rcu(&e->list); + call_rcu(&e->rcu, audit_free_rule_rcu); + } + audit_remove_watch(w); + } + mutex_unlock(&audit_filter_mutex); + + fsnotify_destroy_mark(&parent->mark, audit_watch_group); +} + +/* Get path information necessary for adding watches. */ +static int audit_get_nd(struct audit_watch *watch, struct path *parent) +{ + struct dentry *d = kern_path_locked(watch->path, parent); + if (IS_ERR(d)) + return PTR_ERR(d); + mutex_unlock(&d_backing_inode(parent->dentry)->i_mutex); + if (d_is_positive(d)) { + /* update watch filter fields */ + watch->dev = d_backing_inode(d)->i_sb->s_dev; + watch->ino = d_backing_inode(d)->i_ino; + } + dput(d); + return 0; +} + +/* Associate the given rule with an existing parent. + * Caller must hold audit_filter_mutex. */ +static void audit_add_to_parent(struct audit_krule *krule, + struct audit_parent *parent) +{ + struct audit_watch *w, *watch = krule->watch; + int watch_found = 0; + + BUG_ON(!mutex_is_locked(&audit_filter_mutex)); + + list_for_each_entry(w, &parent->watches, wlist) { + if (strcmp(watch->path, w->path)) + continue; + + watch_found = 1; + + /* put krule's and initial refs to temporary watch */ + audit_put_watch(watch); + audit_put_watch(watch); + + audit_get_watch(w); + krule->watch = watch = w; + break; + } + + if (!watch_found) { + audit_get_parent(parent); + watch->parent = parent; + + list_add(&watch->wlist, &parent->watches); + } + list_add(&krule->rlist, &watch->rules); +} + +/* Find a matching watch entry, or add this one. + * Caller must hold audit_filter_mutex. */ +int audit_add_watch(struct audit_krule *krule, struct list_head **list) +{ + struct audit_watch *watch = krule->watch; + struct audit_parent *parent; + struct path parent_path; + int h, ret = 0; + + mutex_unlock(&audit_filter_mutex); + + /* Avoid calling path_lookup under audit_filter_mutex. */ + ret = audit_get_nd(watch, &parent_path); + + /* caller expects mutex locked */ + mutex_lock(&audit_filter_mutex); + + if (ret) + return ret; + + /* either find an old parent or attach a new one */ + parent = audit_find_parent(d_backing_inode(parent_path.dentry)); + if (!parent) { + parent = audit_init_parent(&parent_path); + if (IS_ERR(parent)) { + ret = PTR_ERR(parent); + goto error; + } + } + + audit_add_to_parent(krule, parent); + + /* match get in audit_find_parent or audit_init_parent */ + audit_put_parent(parent); + + h = audit_hash_ino((u32)watch->ino); + *list = &audit_inode_hash[h]; +error: + path_put(&parent_path); + return ret; +} + +void audit_remove_watch_rule(struct audit_krule *krule) +{ + struct audit_watch *watch = krule->watch; + struct audit_parent *parent = watch->parent; + + list_del(&krule->rlist); + + if (list_empty(&watch->rules)) { + audit_remove_watch(watch); + + if (list_empty(&parent->watches)) { + audit_get_parent(parent); + fsnotify_destroy_mark(&parent->mark, audit_watch_group); + audit_put_parent(parent); + } + } +} + +/* Update watch data in audit rules based on fsnotify events. */ +static int audit_watch_handle_event(struct fsnotify_group *group, + struct inode *to_tell, + struct fsnotify_mark *inode_mark, + struct fsnotify_mark *vfsmount_mark, + u32 mask, void *data, int data_type, + const unsigned char *dname, u32 cookie) +{ + struct inode *inode; + struct audit_parent *parent; + + parent = container_of(inode_mark, struct audit_parent, mark); + + BUG_ON(group != audit_watch_group); + + switch (data_type) { + case (FSNOTIFY_EVENT_PATH): + inode = d_backing_inode(((struct path *)data)->dentry); + break; + case (FSNOTIFY_EVENT_INODE): + inode = (struct inode *)data; + break; + default: + BUG(); + inode = NULL; + break; + }; + + if (mask & (FS_CREATE|FS_MOVED_TO) && inode) + audit_update_watch(parent, dname, inode->i_sb->s_dev, inode->i_ino, 0); + else if (mask & (FS_DELETE|FS_MOVED_FROM)) + audit_update_watch(parent, dname, (dev_t)-1, (unsigned long)-1, 1); + else if (mask & (FS_DELETE_SELF|FS_UNMOUNT|FS_MOVE_SELF)) + audit_remove_parent_watches(parent); + + return 0; +} + +static const struct fsnotify_ops audit_watch_fsnotify_ops = { + .handle_event = audit_watch_handle_event, +}; + +static int __init audit_watch_init(void) +{ + audit_watch_group = fsnotify_alloc_group(&audit_watch_fsnotify_ops); + if (IS_ERR(audit_watch_group)) { + audit_watch_group = NULL; + audit_panic("cannot create audit fsnotify group"); + } + return 0; +} +device_initcall(audit_watch_init); diff --git a/kernel/kernel/auditfilter.c b/kernel/kernel/auditfilter.c new file mode 100644 index 000000000..72e1660a7 --- /dev/null +++ b/kernel/kernel/auditfilter.c @@ -0,0 +1,1416 @@ +/* auditfilter.c -- filtering of audit events + * + * Copyright 2003-2004 Red Hat, Inc. + * Copyright 2005 Hewlett-Packard Development Company, L.P. + * Copyright 2005 IBM Corporation + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include "audit.h" + +/* + * Locking model: + * + * audit_filter_mutex: + * Synchronizes writes and blocking reads of audit's filterlist + * data. Rcu is used to traverse the filterlist and access + * contents of structs audit_entry, audit_watch and opaque + * LSM rules during filtering. If modified, these structures + * must be copied and replace their counterparts in the filterlist. + * An audit_parent struct is not accessed during filtering, so may + * be written directly provided audit_filter_mutex is held. + */ + +/* Audit filter lists, defined in */ +struct list_head audit_filter_list[AUDIT_NR_FILTERS] = { + LIST_HEAD_INIT(audit_filter_list[0]), + LIST_HEAD_INIT(audit_filter_list[1]), + LIST_HEAD_INIT(audit_filter_list[2]), + LIST_HEAD_INIT(audit_filter_list[3]), + LIST_HEAD_INIT(audit_filter_list[4]), + LIST_HEAD_INIT(audit_filter_list[5]), +#if AUDIT_NR_FILTERS != 6 +#error Fix audit_filter_list initialiser +#endif +}; +static struct list_head audit_rules_list[AUDIT_NR_FILTERS] = { + LIST_HEAD_INIT(audit_rules_list[0]), + LIST_HEAD_INIT(audit_rules_list[1]), + LIST_HEAD_INIT(audit_rules_list[2]), + LIST_HEAD_INIT(audit_rules_list[3]), + LIST_HEAD_INIT(audit_rules_list[4]), + LIST_HEAD_INIT(audit_rules_list[5]), +}; + +DEFINE_MUTEX(audit_filter_mutex); + +static void audit_free_lsm_field(struct audit_field *f) +{ + switch (f->type) { + case AUDIT_SUBJ_USER: + case AUDIT_SUBJ_ROLE: + case AUDIT_SUBJ_TYPE: + case AUDIT_SUBJ_SEN: + case AUDIT_SUBJ_CLR: + case AUDIT_OBJ_USER: + case AUDIT_OBJ_ROLE: + case AUDIT_OBJ_TYPE: + case AUDIT_OBJ_LEV_LOW: + case AUDIT_OBJ_LEV_HIGH: + kfree(f->lsm_str); + security_audit_rule_free(f->lsm_rule); + } +} + +static inline void audit_free_rule(struct audit_entry *e) +{ + int i; + struct audit_krule *erule = &e->rule; + + /* some rules don't have associated watches */ + if (erule->watch) + audit_put_watch(erule->watch); + if (erule->fields) + for (i = 0; i < erule->field_count; i++) + audit_free_lsm_field(&erule->fields[i]); + kfree(erule->fields); + kfree(erule->filterkey); + kfree(e); +} + +void audit_free_rule_rcu(struct rcu_head *head) +{ + struct audit_entry *e = container_of(head, struct audit_entry, rcu); + audit_free_rule(e); +} + +/* Initialize an audit filterlist entry. */ +static inline struct audit_entry *audit_init_entry(u32 field_count) +{ + struct audit_entry *entry; + struct audit_field *fields; + + entry = kzalloc(sizeof(*entry), GFP_KERNEL); + if (unlikely(!entry)) + return NULL; + + fields = kcalloc(field_count, sizeof(*fields), GFP_KERNEL); + if (unlikely(!fields)) { + kfree(entry); + return NULL; + } + entry->rule.fields = fields; + + return entry; +} + +/* Unpack a filter field's string representation from user-space + * buffer. */ +char *audit_unpack_string(void **bufp, size_t *remain, size_t len) +{ + char *str; + + if (!*bufp || (len == 0) || (len > *remain)) + return ERR_PTR(-EINVAL); + + /* Of the currently implemented string fields, PATH_MAX + * defines the longest valid length. + */ + if (len > PATH_MAX) + return ERR_PTR(-ENAMETOOLONG); + + str = kmalloc(len + 1, GFP_KERNEL); + if (unlikely(!str)) + return ERR_PTR(-ENOMEM); + + memcpy(str, *bufp, len); + str[len] = 0; + *bufp += len; + *remain -= len; + + return str; +} + +/* Translate an inode field to kernel respresentation. */ +static inline int audit_to_inode(struct audit_krule *krule, + struct audit_field *f) +{ + if (krule->listnr != AUDIT_FILTER_EXIT || + krule->inode_f || krule->watch || krule->tree || + (f->op != Audit_equal && f->op != Audit_not_equal)) + return -EINVAL; + + krule->inode_f = f; + return 0; +} + +static __u32 *classes[AUDIT_SYSCALL_CLASSES]; + +int __init audit_register_class(int class, unsigned *list) +{ + __u32 *p = kcalloc(AUDIT_BITMASK_SIZE, sizeof(__u32), GFP_KERNEL); + if (!p) + return -ENOMEM; + while (*list != ~0U) { + unsigned n = *list++; + if (n >= AUDIT_BITMASK_SIZE * 32 - AUDIT_SYSCALL_CLASSES) { + kfree(p); + return -EINVAL; + } + p[AUDIT_WORD(n)] |= AUDIT_BIT(n); + } + if (class >= AUDIT_SYSCALL_CLASSES || classes[class]) { + kfree(p); + return -EINVAL; + } + classes[class] = p; + return 0; +} + +int audit_match_class(int class, unsigned syscall) +{ + if (unlikely(syscall >= AUDIT_BITMASK_SIZE * 32)) + return 0; + if (unlikely(class >= AUDIT_SYSCALL_CLASSES || !classes[class])) + return 0; + return classes[class][AUDIT_WORD(syscall)] & AUDIT_BIT(syscall); +} + +#ifdef CONFIG_AUDITSYSCALL +static inline int audit_match_class_bits(int class, u32 *mask) +{ + int i; + + if (classes[class]) { + for (i = 0; i < AUDIT_BITMASK_SIZE; i++) + if (mask[i] & classes[class][i]) + return 0; + } + return 1; +} + +static int audit_match_signal(struct audit_entry *entry) +{ + struct audit_field *arch = entry->rule.arch_f; + + if (!arch) { + /* When arch is unspecified, we must check both masks on biarch + * as syscall number alone is ambiguous. */ + return (audit_match_class_bits(AUDIT_CLASS_SIGNAL, + entry->rule.mask) && + audit_match_class_bits(AUDIT_CLASS_SIGNAL_32, + entry->rule.mask)); + } + + switch(audit_classify_arch(arch->val)) { + case 0: /* native */ + return (audit_match_class_bits(AUDIT_CLASS_SIGNAL, + entry->rule.mask)); + case 1: /* 32bit on biarch */ + return (audit_match_class_bits(AUDIT_CLASS_SIGNAL_32, + entry->rule.mask)); + default: + return 1; + } +} +#endif + +/* Common user-space to kernel rule translation. */ +static inline struct audit_entry *audit_to_entry_common(struct audit_rule_data *rule) +{ + unsigned listnr; + struct audit_entry *entry; + int i, err; + + err = -EINVAL; + listnr = rule->flags & ~AUDIT_FILTER_PREPEND; + switch(listnr) { + default: + goto exit_err; +#ifdef CONFIG_AUDITSYSCALL + case AUDIT_FILTER_ENTRY: + if (rule->action == AUDIT_ALWAYS) + goto exit_err; + case AUDIT_FILTER_EXIT: + case AUDIT_FILTER_TASK: +#endif + case AUDIT_FILTER_USER: + case AUDIT_FILTER_TYPE: + ; + } + if (unlikely(rule->action == AUDIT_POSSIBLE)) { + pr_err("AUDIT_POSSIBLE is deprecated\n"); + goto exit_err; + } + if (rule->action != AUDIT_NEVER && rule->action != AUDIT_ALWAYS) + goto exit_err; + if (rule->field_count > AUDIT_MAX_FIELDS) + goto exit_err; + + err = -ENOMEM; + entry = audit_init_entry(rule->field_count); + if (!entry) + goto exit_err; + + entry->rule.flags = rule->flags & AUDIT_FILTER_PREPEND; + entry->rule.listnr = listnr; + entry->rule.action = rule->action; + entry->rule.field_count = rule->field_count; + + for (i = 0; i < AUDIT_BITMASK_SIZE; i++) + entry->rule.mask[i] = rule->mask[i]; + + for (i = 0; i < AUDIT_SYSCALL_CLASSES; i++) { + int bit = AUDIT_BITMASK_SIZE * 32 - i - 1; + __u32 *p = &entry->rule.mask[AUDIT_WORD(bit)]; + __u32 *class; + + if (!(*p & AUDIT_BIT(bit))) + continue; + *p &= ~AUDIT_BIT(bit); + class = classes[i]; + if (class) { + int j; + for (j = 0; j < AUDIT_BITMASK_SIZE; j++) + entry->rule.mask[j] |= class[j]; + } + } + + return entry; + +exit_err: + return ERR_PTR(err); +} + +static u32 audit_ops[] = +{ + [Audit_equal] = AUDIT_EQUAL, + [Audit_not_equal] = AUDIT_NOT_EQUAL, + [Audit_bitmask] = AUDIT_BIT_MASK, + [Audit_bittest] = AUDIT_BIT_TEST, + [Audit_lt] = AUDIT_LESS_THAN, + [Audit_gt] = AUDIT_GREATER_THAN, + [Audit_le] = AUDIT_LESS_THAN_OR_EQUAL, + [Audit_ge] = AUDIT_GREATER_THAN_OR_EQUAL, +}; + +static u32 audit_to_op(u32 op) +{ + u32 n; + for (n = Audit_equal; n < Audit_bad && audit_ops[n] != op; n++) + ; + return n; +} + +/* check if an audit field is valid */ +static int audit_field_valid(struct audit_entry *entry, struct audit_field *f) +{ + switch(f->type) { + case AUDIT_MSGTYPE: + if (entry->rule.listnr != AUDIT_FILTER_TYPE && + entry->rule.listnr != AUDIT_FILTER_USER) + return -EINVAL; + break; + }; + + switch(f->type) { + default: + return -EINVAL; + case AUDIT_UID: + case AUDIT_EUID: + case AUDIT_SUID: + case AUDIT_FSUID: + case AUDIT_LOGINUID: + case AUDIT_OBJ_UID: + case AUDIT_GID: + case AUDIT_EGID: + case AUDIT_SGID: + case AUDIT_FSGID: + case AUDIT_OBJ_GID: + case AUDIT_PID: + case AUDIT_PERS: + case AUDIT_MSGTYPE: + case AUDIT_PPID: + case AUDIT_DEVMAJOR: + case AUDIT_DEVMINOR: + case AUDIT_EXIT: + case AUDIT_SUCCESS: + case AUDIT_INODE: + /* bit ops are only useful on syscall args */ + if (f->op == Audit_bitmask || f->op == Audit_bittest) + return -EINVAL; + break; + case AUDIT_ARG0: + case AUDIT_ARG1: + case AUDIT_ARG2: + case AUDIT_ARG3: + case AUDIT_SUBJ_USER: + case AUDIT_SUBJ_ROLE: + case AUDIT_SUBJ_TYPE: + case AUDIT_SUBJ_SEN: + case AUDIT_SUBJ_CLR: + case AUDIT_OBJ_USER: + case AUDIT_OBJ_ROLE: + case AUDIT_OBJ_TYPE: + case AUDIT_OBJ_LEV_LOW: + case AUDIT_OBJ_LEV_HIGH: + case AUDIT_WATCH: + case AUDIT_DIR: + case AUDIT_FILTERKEY: + break; + case AUDIT_LOGINUID_SET: + if ((f->val != 0) && (f->val != 1)) + return -EINVAL; + /* FALL THROUGH */ + case AUDIT_ARCH: + if (f->op != Audit_not_equal && f->op != Audit_equal) + return -EINVAL; + break; + case AUDIT_PERM: + if (f->val & ~15) + return -EINVAL; + break; + case AUDIT_FILETYPE: + if (f->val & ~S_IFMT) + return -EINVAL; + break; + case AUDIT_FIELD_COMPARE: + if (f->val > AUDIT_MAX_FIELD_COMPARE) + return -EINVAL; + break; + }; + return 0; +} + +/* Translate struct audit_rule_data to kernel's rule respresentation. */ +static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data, + size_t datasz) +{ + int err = 0; + struct audit_entry *entry; + void *bufp; + size_t remain = datasz - sizeof(struct audit_rule_data); + int i; + char *str; + + entry = audit_to_entry_common(data); + if (IS_ERR(entry)) + goto exit_nofree; + + bufp = data->buf; + for (i = 0; i < data->field_count; i++) { + struct audit_field *f = &entry->rule.fields[i]; + + err = -EINVAL; + + f->op = audit_to_op(data->fieldflags[i]); + if (f->op == Audit_bad) + goto exit_free; + + f->type = data->fields[i]; + f->val = data->values[i]; + + /* Support legacy tests for a valid loginuid */ + if ((f->type == AUDIT_LOGINUID) && (f->val == AUDIT_UID_UNSET)) { + f->type = AUDIT_LOGINUID_SET; + f->val = 0; + entry->rule.pflags |= AUDIT_LOGINUID_LEGACY; + } + + err = audit_field_valid(entry, f); + if (err) + goto exit_free; + + err = -EINVAL; + switch (f->type) { + case AUDIT_LOGINUID: + case AUDIT_UID: + case AUDIT_EUID: + case AUDIT_SUID: + case AUDIT_FSUID: + case AUDIT_OBJ_UID: + f->uid = make_kuid(current_user_ns(), f->val); + if (!uid_valid(f->uid)) + goto exit_free; + break; + case AUDIT_GID: + case AUDIT_EGID: + case AUDIT_SGID: + case AUDIT_FSGID: + case AUDIT_OBJ_GID: + f->gid = make_kgid(current_user_ns(), f->val); + if (!gid_valid(f->gid)) + goto exit_free; + break; + case AUDIT_ARCH: + entry->rule.arch_f = f; + break; + case AUDIT_SUBJ_USER: + case AUDIT_SUBJ_ROLE: + case AUDIT_SUBJ_TYPE: + case AUDIT_SUBJ_SEN: + case AUDIT_SUBJ_CLR: + case AUDIT_OBJ_USER: + case AUDIT_OBJ_ROLE: + case AUDIT_OBJ_TYPE: + case AUDIT_OBJ_LEV_LOW: + case AUDIT_OBJ_LEV_HIGH: + str = audit_unpack_string(&bufp, &remain, f->val); + if (IS_ERR(str)) + goto exit_free; + entry->rule.buflen += f->val; + + err = security_audit_rule_init(f->type, f->op, str, + (void **)&f->lsm_rule); + /* Keep currently invalid fields around in case they + * become valid after a policy reload. */ + if (err == -EINVAL) { + pr_warn("audit rule for LSM \'%s\' is invalid\n", + str); + err = 0; + } + if (err) { + kfree(str); + goto exit_free; + } else + f->lsm_str = str; + break; + case AUDIT_WATCH: + str = audit_unpack_string(&bufp, &remain, f->val); + if (IS_ERR(str)) + goto exit_free; + entry->rule.buflen += f->val; + + err = audit_to_watch(&entry->rule, str, f->val, f->op); + if (err) { + kfree(str); + goto exit_free; + } + break; + case AUDIT_DIR: + str = audit_unpack_string(&bufp, &remain, f->val); + if (IS_ERR(str)) + goto exit_free; + entry->rule.buflen += f->val; + + err = audit_make_tree(&entry->rule, str, f->op); + kfree(str); + if (err) + goto exit_free; + break; + case AUDIT_INODE: + err = audit_to_inode(&entry->rule, f); + if (err) + goto exit_free; + break; + case AUDIT_FILTERKEY: + if (entry->rule.filterkey || f->val > AUDIT_MAX_KEY_LEN) + goto exit_free; + str = audit_unpack_string(&bufp, &remain, f->val); + if (IS_ERR(str)) + goto exit_free; + entry->rule.buflen += f->val; + entry->rule.filterkey = str; + break; + } + } + + if (entry->rule.inode_f && entry->rule.inode_f->op == Audit_not_equal) + entry->rule.inode_f = NULL; + +exit_nofree: + return entry; + +exit_free: + if (entry->rule.watch) + audit_put_watch(entry->rule.watch); /* matches initial get */ + if (entry->rule.tree) + audit_put_tree(entry->rule.tree); /* that's the temporary one */ + audit_free_rule(entry); + return ERR_PTR(err); +} + +/* Pack a filter field's string representation into data block. */ +static inline size_t audit_pack_string(void **bufp, const char *str) +{ + size_t len = strlen(str); + + memcpy(*bufp, str, len); + *bufp += len; + + return len; +} + +/* Translate kernel rule respresentation to struct audit_rule_data. */ +static struct audit_rule_data *audit_krule_to_data(struct audit_krule *krule) +{ + struct audit_rule_data *data; + void *bufp; + int i; + + data = kmalloc(sizeof(*data) + krule->buflen, GFP_KERNEL); + if (unlikely(!data)) + return NULL; + memset(data, 0, sizeof(*data)); + + data->flags = krule->flags | krule->listnr; + data->action = krule->action; + data->field_count = krule->field_count; + bufp = data->buf; + for (i = 0; i < data->field_count; i++) { + struct audit_field *f = &krule->fields[i]; + + data->fields[i] = f->type; + data->fieldflags[i] = audit_ops[f->op]; + switch(f->type) { + case AUDIT_SUBJ_USER: + case AUDIT_SUBJ_ROLE: + case AUDIT_SUBJ_TYPE: + case AUDIT_SUBJ_SEN: + case AUDIT_SUBJ_CLR: + case AUDIT_OBJ_USER: + case AUDIT_OBJ_ROLE: + case AUDIT_OBJ_TYPE: + case AUDIT_OBJ_LEV_LOW: + case AUDIT_OBJ_LEV_HIGH: + data->buflen += data->values[i] = + audit_pack_string(&bufp, f->lsm_str); + break; + case AUDIT_WATCH: + data->buflen += data->values[i] = + audit_pack_string(&bufp, + audit_watch_path(krule->watch)); + break; + case AUDIT_DIR: + data->buflen += data->values[i] = + audit_pack_string(&bufp, + audit_tree_path(krule->tree)); + break; + case AUDIT_FILTERKEY: + data->buflen += data->values[i] = + audit_pack_string(&bufp, krule->filterkey); + break; + case AUDIT_LOGINUID_SET: + if (krule->pflags & AUDIT_LOGINUID_LEGACY && !f->val) { + data->fields[i] = AUDIT_LOGINUID; + data->values[i] = AUDIT_UID_UNSET; + break; + } + /* fallthrough if set */ + default: + data->values[i] = f->val; + } + } + for (i = 0; i < AUDIT_BITMASK_SIZE; i++) data->mask[i] = krule->mask[i]; + + return data; +} + +/* Compare two rules in kernel format. Considered success if rules + * don't match. */ +static int audit_compare_rule(struct audit_krule *a, struct audit_krule *b) +{ + int i; + + if (a->flags != b->flags || + a->pflags != b->pflags || + a->listnr != b->listnr || + a->action != b->action || + a->field_count != b->field_count) + return 1; + + for (i = 0; i < a->field_count; i++) { + if (a->fields[i].type != b->fields[i].type || + a->fields[i].op != b->fields[i].op) + return 1; + + switch(a->fields[i].type) { + case AUDIT_SUBJ_USER: + case AUDIT_SUBJ_ROLE: + case AUDIT_SUBJ_TYPE: + case AUDIT_SUBJ_SEN: + case AUDIT_SUBJ_CLR: + case AUDIT_OBJ_USER: + case AUDIT_OBJ_ROLE: + case AUDIT_OBJ_TYPE: + case AUDIT_OBJ_LEV_LOW: + case AUDIT_OBJ_LEV_HIGH: + if (strcmp(a->fields[i].lsm_str, b->fields[i].lsm_str)) + return 1; + break; + case AUDIT_WATCH: + if (strcmp(audit_watch_path(a->watch), + audit_watch_path(b->watch))) + return 1; + break; + case AUDIT_DIR: + if (strcmp(audit_tree_path(a->tree), + audit_tree_path(b->tree))) + return 1; + break; + case AUDIT_FILTERKEY: + /* both filterkeys exist based on above type compare */ + if (strcmp(a->filterkey, b->filterkey)) + return 1; + break; + case AUDIT_UID: + case AUDIT_EUID: + case AUDIT_SUID: + case AUDIT_FSUID: + case AUDIT_LOGINUID: + case AUDIT_OBJ_UID: + if (!uid_eq(a->fields[i].uid, b->fields[i].uid)) + return 1; + break; + case AUDIT_GID: + case AUDIT_EGID: + case AUDIT_SGID: + case AUDIT_FSGID: + case AUDIT_OBJ_GID: + if (!gid_eq(a->fields[i].gid, b->fields[i].gid)) + return 1; + break; + default: + if (a->fields[i].val != b->fields[i].val) + return 1; + } + } + + for (i = 0; i < AUDIT_BITMASK_SIZE; i++) + if (a->mask[i] != b->mask[i]) + return 1; + + return 0; +} + +/* Duplicate LSM field information. The lsm_rule is opaque, so must be + * re-initialized. */ +static inline int audit_dupe_lsm_field(struct audit_field *df, + struct audit_field *sf) +{ + int ret = 0; + char *lsm_str; + + /* our own copy of lsm_str */ + lsm_str = kstrdup(sf->lsm_str, GFP_KERNEL); + if (unlikely(!lsm_str)) + return -ENOMEM; + df->lsm_str = lsm_str; + + /* our own (refreshed) copy of lsm_rule */ + ret = security_audit_rule_init(df->type, df->op, df->lsm_str, + (void **)&df->lsm_rule); + /* Keep currently invalid fields around in case they + * become valid after a policy reload. */ + if (ret == -EINVAL) { + pr_warn("audit rule for LSM \'%s\' is invalid\n", + df->lsm_str); + ret = 0; + } + + return ret; +} + +/* Duplicate an audit rule. This will be a deep copy with the exception + * of the watch - that pointer is carried over. The LSM specific fields + * will be updated in the copy. The point is to be able to replace the old + * rule with the new rule in the filterlist, then free the old rule. + * The rlist element is undefined; list manipulations are handled apart from + * the initial copy. */ +struct audit_entry *audit_dupe_rule(struct audit_krule *old) +{ + u32 fcount = old->field_count; + struct audit_entry *entry; + struct audit_krule *new; + char *fk; + int i, err = 0; + + entry = audit_init_entry(fcount); + if (unlikely(!entry)) + return ERR_PTR(-ENOMEM); + + new = &entry->rule; + new->flags = old->flags; + new->pflags = old->pflags; + new->listnr = old->listnr; + new->action = old->action; + for (i = 0; i < AUDIT_BITMASK_SIZE; i++) + new->mask[i] = old->mask[i]; + new->prio = old->prio; + new->buflen = old->buflen; + new->inode_f = old->inode_f; + new->field_count = old->field_count; + + /* + * note that we are OK with not refcounting here; audit_match_tree() + * never dereferences tree and we can't get false positives there + * since we'd have to have rule gone from the list *and* removed + * before the chunks found by lookup had been allocated, i.e. before + * the beginning of list scan. + */ + new->tree = old->tree; + memcpy(new->fields, old->fields, sizeof(struct audit_field) * fcount); + + /* deep copy this information, updating the lsm_rule fields, because + * the originals will all be freed when the old rule is freed. */ + for (i = 0; i < fcount; i++) { + switch (new->fields[i].type) { + case AUDIT_SUBJ_USER: + case AUDIT_SUBJ_ROLE: + case AUDIT_SUBJ_TYPE: + case AUDIT_SUBJ_SEN: + case AUDIT_SUBJ_CLR: + case AUDIT_OBJ_USER: + case AUDIT_OBJ_ROLE: + case AUDIT_OBJ_TYPE: + case AUDIT_OBJ_LEV_LOW: + case AUDIT_OBJ_LEV_HIGH: + err = audit_dupe_lsm_field(&new->fields[i], + &old->fields[i]); + break; + case AUDIT_FILTERKEY: + fk = kstrdup(old->filterkey, GFP_KERNEL); + if (unlikely(!fk)) + err = -ENOMEM; + else + new->filterkey = fk; + } + if (err) { + audit_free_rule(entry); + return ERR_PTR(err); + } + } + + if (old->watch) { + audit_get_watch(old->watch); + new->watch = old->watch; + } + + return entry; +} + +/* Find an existing audit rule. + * Caller must hold audit_filter_mutex to prevent stale rule data. */ +static struct audit_entry *audit_find_rule(struct audit_entry *entry, + struct list_head **p) +{ + struct audit_entry *e, *found = NULL; + struct list_head *list; + int h; + + if (entry->rule.inode_f) { + h = audit_hash_ino(entry->rule.inode_f->val); + *p = list = &audit_inode_hash[h]; + } else if (entry->rule.watch) { + /* we don't know the inode number, so must walk entire hash */ + for (h = 0; h < AUDIT_INODE_BUCKETS; h++) { + list = &audit_inode_hash[h]; + list_for_each_entry(e, list, list) + if (!audit_compare_rule(&entry->rule, &e->rule)) { + found = e; + goto out; + } + } + goto out; + } else { + *p = list = &audit_filter_list[entry->rule.listnr]; + } + + list_for_each_entry(e, list, list) + if (!audit_compare_rule(&entry->rule, &e->rule)) { + found = e; + goto out; + } + +out: + return found; +} + +static u64 prio_low = ~0ULL/2; +static u64 prio_high = ~0ULL/2 - 1; + +/* Add rule to given filterlist if not a duplicate. */ +static inline int audit_add_rule(struct audit_entry *entry) +{ + struct audit_entry *e; + struct audit_watch *watch = entry->rule.watch; + struct audit_tree *tree = entry->rule.tree; + struct list_head *list; + int err; +#ifdef CONFIG_AUDITSYSCALL + int dont_count = 0; + + /* If either of these, don't count towards total */ + if (entry->rule.listnr == AUDIT_FILTER_USER || + entry->rule.listnr == AUDIT_FILTER_TYPE) + dont_count = 1; +#endif + + mutex_lock(&audit_filter_mutex); + e = audit_find_rule(entry, &list); + if (e) { + mutex_unlock(&audit_filter_mutex); + err = -EEXIST; + /* normally audit_add_tree_rule() will free it on failure */ + if (tree) + audit_put_tree(tree); + goto error; + } + + if (watch) { + /* audit_filter_mutex is dropped and re-taken during this call */ + err = audit_add_watch(&entry->rule, &list); + if (err) { + mutex_unlock(&audit_filter_mutex); + /* + * normally audit_add_tree_rule() will free it + * on failure + */ + if (tree) + audit_put_tree(tree); + goto error; + } + } + if (tree) { + err = audit_add_tree_rule(&entry->rule); + if (err) { + mutex_unlock(&audit_filter_mutex); + goto error; + } + } + + entry->rule.prio = ~0ULL; + if (entry->rule.listnr == AUDIT_FILTER_EXIT) { + if (entry->rule.flags & AUDIT_FILTER_PREPEND) + entry->rule.prio = ++prio_high; + else + entry->rule.prio = --prio_low; + } + + if (entry->rule.flags & AUDIT_FILTER_PREPEND) { + list_add(&entry->rule.list, + &audit_rules_list[entry->rule.listnr]); + list_add_rcu(&entry->list, list); + entry->rule.flags &= ~AUDIT_FILTER_PREPEND; + } else { + list_add_tail(&entry->rule.list, + &audit_rules_list[entry->rule.listnr]); + list_add_tail_rcu(&entry->list, list); + } +#ifdef CONFIG_AUDITSYSCALL + if (!dont_count) + audit_n_rules++; + + if (!audit_match_signal(entry)) + audit_signals++; +#endif + mutex_unlock(&audit_filter_mutex); + + return 0; + +error: + if (watch) + audit_put_watch(watch); /* tmp watch, matches initial get */ + return err; +} + +/* Remove an existing rule from filterlist. */ +static inline int audit_del_rule(struct audit_entry *entry) +{ + struct audit_entry *e; + struct audit_watch *watch = entry->rule.watch; + struct audit_tree *tree = entry->rule.tree; + struct list_head *list; + int ret = 0; +#ifdef CONFIG_AUDITSYSCALL + int dont_count = 0; + + /* If either of these, don't count towards total */ + if (entry->rule.listnr == AUDIT_FILTER_USER || + entry->rule.listnr == AUDIT_FILTER_TYPE) + dont_count = 1; +#endif + + mutex_lock(&audit_filter_mutex); + e = audit_find_rule(entry, &list); + if (!e) { + mutex_unlock(&audit_filter_mutex); + ret = -ENOENT; + goto out; + } + + if (e->rule.watch) + audit_remove_watch_rule(&e->rule); + + if (e->rule.tree) + audit_remove_tree_rule(&e->rule); + + list_del_rcu(&e->list); + list_del(&e->rule.list); + call_rcu(&e->rcu, audit_free_rule_rcu); + +#ifdef CONFIG_AUDITSYSCALL + if (!dont_count) + audit_n_rules--; + + if (!audit_match_signal(entry)) + audit_signals--; +#endif + mutex_unlock(&audit_filter_mutex); + +out: + if (watch) + audit_put_watch(watch); /* match initial get */ + if (tree) + audit_put_tree(tree); /* that's the temporary one */ + + return ret; +} + +/* List rules using struct audit_rule_data. */ +static void audit_list_rules(__u32 portid, int seq, struct sk_buff_head *q) +{ + struct sk_buff *skb; + struct audit_krule *r; + int i; + + /* This is a blocking read, so use audit_filter_mutex instead of rcu + * iterator to sync with list writers. */ + for (i=0; ibuflen); + if (skb) + skb_queue_tail(q, skb); + kfree(data); + } + } + skb = audit_make_reply(portid, seq, AUDIT_LIST_RULES, 1, 1, NULL, 0); + if (skb) + skb_queue_tail(q, skb); +} + +/* Log rule additions and removals */ +static void audit_log_rule_change(char *action, struct audit_krule *rule, int res) +{ + struct audit_buffer *ab; + uid_t loginuid = from_kuid(&init_user_ns, audit_get_loginuid(current)); + unsigned int sessionid = audit_get_sessionid(current); + + if (!audit_enabled) + return; + + ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_CONFIG_CHANGE); + if (!ab) + return; + audit_log_format(ab, "auid=%u ses=%u" ,loginuid, sessionid); + audit_log_task_context(ab); + audit_log_format(ab, " op="); + audit_log_string(ab, action); + audit_log_key(ab, rule->filterkey); + audit_log_format(ab, " list=%d res=%d", rule->listnr, res); + audit_log_end(ab); +} + +/** + * audit_rule_change - apply all rules to the specified message type + * @type: audit message type + * @portid: target port id for netlink audit messages + * @seq: netlink audit message sequence (serial) number + * @data: payload data + * @datasz: size of payload data + */ +int audit_rule_change(int type, __u32 portid, int seq, void *data, + size_t datasz) +{ + int err = 0; + struct audit_entry *entry; + + entry = audit_data_to_entry(data, datasz); + if (IS_ERR(entry)) + return PTR_ERR(entry); + + switch (type) { + case AUDIT_ADD_RULE: + err = audit_add_rule(entry); + audit_log_rule_change("add_rule", &entry->rule, !err); + break; + case AUDIT_DEL_RULE: + err = audit_del_rule(entry); + audit_log_rule_change("remove_rule", &entry->rule, !err); + break; + default: + err = -EINVAL; + WARN_ON(1); + } + + if (err || type == AUDIT_DEL_RULE) + audit_free_rule(entry); + + return err; +} + +/** + * audit_list_rules_send - list the audit rules + * @request_skb: skb of request we are replying to (used to target the reply) + * @seq: netlink audit message sequence (serial) number + */ +int audit_list_rules_send(struct sk_buff *request_skb, int seq) +{ + u32 portid = NETLINK_CB(request_skb).portid; + struct net *net = sock_net(NETLINK_CB(request_skb).sk); + struct task_struct *tsk; + struct audit_netlink_list *dest; + int err = 0; + + /* We can't just spew out the rules here because we might fill + * the available socket buffer space and deadlock waiting for + * auditctl to read from it... which isn't ever going to + * happen if we're actually running in the context of auditctl + * trying to _send_ the stuff */ + + dest = kmalloc(sizeof(struct audit_netlink_list), GFP_KERNEL); + if (!dest) + return -ENOMEM; + dest->net = get_net(net); + dest->portid = portid; + skb_queue_head_init(&dest->q); + + mutex_lock(&audit_filter_mutex); + audit_list_rules(portid, seq, &dest->q); + mutex_unlock(&audit_filter_mutex); + + tsk = kthread_run(audit_send_list, dest, "audit_send_list"); + if (IS_ERR(tsk)) { + skb_queue_purge(&dest->q); + kfree(dest); + err = PTR_ERR(tsk); + } + + return err; +} + +int audit_comparator(u32 left, u32 op, u32 right) +{ + switch (op) { + case Audit_equal: + return (left == right); + case Audit_not_equal: + return (left != right); + case Audit_lt: + return (left < right); + case Audit_le: + return (left <= right); + case Audit_gt: + return (left > right); + case Audit_ge: + return (left >= right); + case Audit_bitmask: + return (left & right); + case Audit_bittest: + return ((left & right) == right); + default: + BUG(); + return 0; + } +} + +int audit_uid_comparator(kuid_t left, u32 op, kuid_t right) +{ + switch (op) { + case Audit_equal: + return uid_eq(left, right); + case Audit_not_equal: + return !uid_eq(left, right); + case Audit_lt: + return uid_lt(left, right); + case Audit_le: + return uid_lte(left, right); + case Audit_gt: + return uid_gt(left, right); + case Audit_ge: + return uid_gte(left, right); + case Audit_bitmask: + case Audit_bittest: + default: + BUG(); + return 0; + } +} + +int audit_gid_comparator(kgid_t left, u32 op, kgid_t right) +{ + switch (op) { + case Audit_equal: + return gid_eq(left, right); + case Audit_not_equal: + return !gid_eq(left, right); + case Audit_lt: + return gid_lt(left, right); + case Audit_le: + return gid_lte(left, right); + case Audit_gt: + return gid_gt(left, right); + case Audit_ge: + return gid_gte(left, right); + case Audit_bitmask: + case Audit_bittest: + default: + BUG(); + return 0; + } +} + +/** + * parent_len - find the length of the parent portion of a pathname + * @path: pathname of which to determine length + */ +int parent_len(const char *path) +{ + int plen; + const char *p; + + plen = strlen(path); + + if (plen == 0) + return plen; + + /* disregard trailing slashes */ + p = path + plen - 1; + while ((*p == '/') && (p > path)) + p--; + + /* walk backward until we find the next slash or hit beginning */ + while ((*p != '/') && (p > path)) + p--; + + /* did we find a slash? Then increment to include it in path */ + if (*p == '/') + p++; + + return p - path; +} + +/** + * audit_compare_dname_path - compare given dentry name with last component in + * given path. Return of 0 indicates a match. + * @dname: dentry name that we're comparing + * @path: full pathname that we're comparing + * @parentlen: length of the parent if known. Passing in AUDIT_NAME_FULL + * here indicates that we must compute this value. + */ +int audit_compare_dname_path(const char *dname, const char *path, int parentlen) +{ + int dlen, pathlen; + const char *p; + + dlen = strlen(dname); + pathlen = strlen(path); + if (pathlen < dlen) + return 1; + + parentlen = parentlen == AUDIT_NAME_FULL ? parent_len(path) : parentlen; + if (pathlen - parentlen != dlen) + return 1; + + p = path + parentlen; + + return strncmp(p, dname, dlen); +} + +static int audit_filter_user_rules(struct audit_krule *rule, int type, + enum audit_state *state) +{ + int i; + + for (i = 0; i < rule->field_count; i++) { + struct audit_field *f = &rule->fields[i]; + pid_t pid; + int result = 0; + u32 sid; + + switch (f->type) { + case AUDIT_PID: + pid = task_pid_nr(current); + result = audit_comparator(pid, f->op, f->val); + break; + case AUDIT_UID: + result = audit_uid_comparator(current_uid(), f->op, f->uid); + break; + case AUDIT_GID: + result = audit_gid_comparator(current_gid(), f->op, f->gid); + break; + case AUDIT_LOGINUID: + result = audit_uid_comparator(audit_get_loginuid(current), + f->op, f->uid); + break; + case AUDIT_LOGINUID_SET: + result = audit_comparator(audit_loginuid_set(current), + f->op, f->val); + break; + case AUDIT_MSGTYPE: + result = audit_comparator(type, f->op, f->val); + break; + case AUDIT_SUBJ_USER: + case AUDIT_SUBJ_ROLE: + case AUDIT_SUBJ_TYPE: + case AUDIT_SUBJ_SEN: + case AUDIT_SUBJ_CLR: + if (f->lsm_rule) { + security_task_getsecid(current, &sid); + result = security_audit_rule_match(sid, + f->type, + f->op, + f->lsm_rule, + NULL); + } + break; + } + + if (!result) + return 0; + } + switch (rule->action) { + case AUDIT_NEVER: *state = AUDIT_DISABLED; break; + case AUDIT_ALWAYS: *state = AUDIT_RECORD_CONTEXT; break; + } + return 1; +} + +int audit_filter_user(int type) +{ + enum audit_state state = AUDIT_DISABLED; + struct audit_entry *e; + int rc, ret; + + ret = 1; /* Audit by default */ + + rcu_read_lock(); + list_for_each_entry_rcu(e, &audit_filter_list[AUDIT_FILTER_USER], list) { + rc = audit_filter_user_rules(&e->rule, type, &state); + if (rc) { + if (rc > 0 && state == AUDIT_DISABLED) + ret = 0; + break; + } + } + rcu_read_unlock(); + + return ret; +} + +int audit_filter_type(int type) +{ + struct audit_entry *e; + int result = 0; + + rcu_read_lock(); + if (list_empty(&audit_filter_list[AUDIT_FILTER_TYPE])) + goto unlock_and_return; + + list_for_each_entry_rcu(e, &audit_filter_list[AUDIT_FILTER_TYPE], + list) { + int i; + for (i = 0; i < e->rule.field_count; i++) { + struct audit_field *f = &e->rule.fields[i]; + if (f->type == AUDIT_MSGTYPE) { + result = audit_comparator(type, f->op, f->val); + if (!result) + break; + } + } + if (result) + goto unlock_and_return; + } +unlock_and_return: + rcu_read_unlock(); + return result; +} + +static int update_lsm_rule(struct audit_krule *r) +{ + struct audit_entry *entry = container_of(r, struct audit_entry, rule); + struct audit_entry *nentry; + int err = 0; + + if (!security_audit_rule_known(r)) + return 0; + + nentry = audit_dupe_rule(r); + if (IS_ERR(nentry)) { + /* save the first error encountered for the + * return value */ + err = PTR_ERR(nentry); + audit_panic("error updating LSM filters"); + if (r->watch) + list_del(&r->rlist); + list_del_rcu(&entry->list); + list_del(&r->list); + } else { + if (r->watch || r->tree) + list_replace_init(&r->rlist, &nentry->rule.rlist); + list_replace_rcu(&entry->list, &nentry->list); + list_replace(&r->list, &nentry->rule.list); + } + call_rcu(&entry->rcu, audit_free_rule_rcu); + + return err; +} + +/* This function will re-initialize the lsm_rule field of all applicable rules. + * It will traverse the filter lists serarching for rules that contain LSM + * specific filter fields. When such a rule is found, it is copied, the + * LSM field is re-initialized, and the old rule is replaced with the + * updated rule. */ +int audit_update_lsm_rules(void) +{ + struct audit_krule *r, *n; + int i, err = 0; + + /* audit_filter_mutex synchronizes the writers */ + mutex_lock(&audit_filter_mutex); + + for (i = 0; i < AUDIT_NR_FILTERS; i++) { + list_for_each_entry_safe(r, n, &audit_rules_list[i], list) { + int res = update_lsm_rule(r); + if (!err) + err = res; + } + } + mutex_unlock(&audit_filter_mutex); + + return err; +} diff --git a/kernel/kernel/auditsc.c b/kernel/kernel/auditsc.c new file mode 100644 index 000000000..9fb9d1cb8 --- /dev/null +++ b/kernel/kernel/auditsc.c @@ -0,0 +1,2426 @@ +/* auditsc.c -- System-call auditing support + * Handles all system-call specific auditing features. + * + * Copyright 2003-2004 Red Hat Inc., Durham, North Carolina. + * Copyright 2005 Hewlett-Packard Development Company, L.P. + * Copyright (C) 2005, 2006 IBM Corporation + * All Rights Reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * + * Written by Rickard E. (Rik) Faith + * + * Many of the ideas implemented here are from Stephen C. Tweedie, + * especially the idea of avoiding a copy by using getname. + * + * The method for actual interception of syscall entry and exit (not in + * this file -- see entry.S) is based on a GPL'd patch written by + * okir@suse.de and Copyright 2003 SuSE Linux AG. + * + * POSIX message queue support added by George Wilson , + * 2006. + * + * The support of additional filter rules compares (>, <, >=, <=) was + * added by Dustin Kirkland , 2005. + * + * Modified by Amy Griffis to collect additional + * filesystem information. + * + * Subject and object context labeling support added by + * and for LSPP certification compliance. + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "audit.h" + +/* flags stating the success for a syscall */ +#define AUDITSC_INVALID 0 +#define AUDITSC_SUCCESS 1 +#define AUDITSC_FAILURE 2 + +/* no execve audit message should be longer than this (userspace limits) */ +#define MAX_EXECVE_AUDIT_LEN 7500 + +/* max length to print of cmdline/proctitle value during audit */ +#define MAX_PROCTITLE_AUDIT_LEN 128 + +/* number of audit rules */ +int audit_n_rules; + +/* determines whether we collect data for signals sent */ +int audit_signals; + +struct audit_aux_data { + struct audit_aux_data *next; + int type; +}; + +#define AUDIT_AUX_IPCPERM 0 + +/* Number of target pids per aux struct. */ +#define AUDIT_AUX_PIDS 16 + +struct audit_aux_data_pids { + struct audit_aux_data d; + pid_t target_pid[AUDIT_AUX_PIDS]; + kuid_t target_auid[AUDIT_AUX_PIDS]; + kuid_t target_uid[AUDIT_AUX_PIDS]; + unsigned int target_sessionid[AUDIT_AUX_PIDS]; + u32 target_sid[AUDIT_AUX_PIDS]; + char target_comm[AUDIT_AUX_PIDS][TASK_COMM_LEN]; + int pid_count; +}; + +struct audit_aux_data_bprm_fcaps { + struct audit_aux_data d; + struct audit_cap_data fcap; + unsigned int fcap_ver; + struct audit_cap_data old_pcap; + struct audit_cap_data new_pcap; +}; + +struct audit_tree_refs { + struct audit_tree_refs *next; + struct audit_chunk *c[31]; +}; + +static int audit_match_perm(struct audit_context *ctx, int mask) +{ + unsigned n; + if (unlikely(!ctx)) + return 0; + n = ctx->major; + + switch (audit_classify_syscall(ctx->arch, n)) { + case 0: /* native */ + if ((mask & AUDIT_PERM_WRITE) && + audit_match_class(AUDIT_CLASS_WRITE, n)) + return 1; + if ((mask & AUDIT_PERM_READ) && + audit_match_class(AUDIT_CLASS_READ, n)) + return 1; + if ((mask & AUDIT_PERM_ATTR) && + audit_match_class(AUDIT_CLASS_CHATTR, n)) + return 1; + return 0; + case 1: /* 32bit on biarch */ + if ((mask & AUDIT_PERM_WRITE) && + audit_match_class(AUDIT_CLASS_WRITE_32, n)) + return 1; + if ((mask & AUDIT_PERM_READ) && + audit_match_class(AUDIT_CLASS_READ_32, n)) + return 1; + if ((mask & AUDIT_PERM_ATTR) && + audit_match_class(AUDIT_CLASS_CHATTR_32, n)) + return 1; + return 0; + case 2: /* open */ + return mask & ACC_MODE(ctx->argv[1]); + case 3: /* openat */ + return mask & ACC_MODE(ctx->argv[2]); + case 4: /* socketcall */ + return ((mask & AUDIT_PERM_WRITE) && ctx->argv[0] == SYS_BIND); + case 5: /* execve */ + return mask & AUDIT_PERM_EXEC; + default: + return 0; + } +} + +static int audit_match_filetype(struct audit_context *ctx, int val) +{ + struct audit_names *n; + umode_t mode = (umode_t)val; + + if (unlikely(!ctx)) + return 0; + + list_for_each_entry(n, &ctx->names_list, list) { + if ((n->ino != -1) && + ((n->mode & S_IFMT) == mode)) + return 1; + } + + return 0; +} + +/* + * We keep a linked list of fixed-sized (31 pointer) arrays of audit_chunk *; + * ->first_trees points to its beginning, ->trees - to the current end of data. + * ->tree_count is the number of free entries in array pointed to by ->trees. + * Original condition is (NULL, NULL, 0); as soon as it grows we never revert to NULL, + * "empty" becomes (p, p, 31) afterwards. We don't shrink the list (and seriously, + * it's going to remain 1-element for almost any setup) until we free context itself. + * References in it _are_ dropped - at the same time we free/drop aux stuff. + */ + +#ifdef CONFIG_AUDIT_TREE +static void audit_set_auditable(struct audit_context *ctx) +{ + if (!ctx->prio) { + ctx->prio = 1; + ctx->current_state = AUDIT_RECORD_CONTEXT; + } +} + +static int put_tree_ref(struct audit_context *ctx, struct audit_chunk *chunk) +{ + struct audit_tree_refs *p = ctx->trees; + int left = ctx->tree_count; + if (likely(left)) { + p->c[--left] = chunk; + ctx->tree_count = left; + return 1; + } + if (!p) + return 0; + p = p->next; + if (p) { + p->c[30] = chunk; + ctx->trees = p; + ctx->tree_count = 30; + return 1; + } + return 0; +} + +static int grow_tree_refs(struct audit_context *ctx) +{ + struct audit_tree_refs *p = ctx->trees; + ctx->trees = kzalloc(sizeof(struct audit_tree_refs), GFP_KERNEL); + if (!ctx->trees) { + ctx->trees = p; + return 0; + } + if (p) + p->next = ctx->trees; + else + ctx->first_trees = ctx->trees; + ctx->tree_count = 31; + return 1; +} +#endif + +static void unroll_tree_refs(struct audit_context *ctx, + struct audit_tree_refs *p, int count) +{ +#ifdef CONFIG_AUDIT_TREE + struct audit_tree_refs *q; + int n; + if (!p) { + /* we started with empty chain */ + p = ctx->first_trees; + count = 31; + /* if the very first allocation has failed, nothing to do */ + if (!p) + return; + } + n = count; + for (q = p; q != ctx->trees; q = q->next, n = 31) { + while (n--) { + audit_put_chunk(q->c[n]); + q->c[n] = NULL; + } + } + while (n-- > ctx->tree_count) { + audit_put_chunk(q->c[n]); + q->c[n] = NULL; + } + ctx->trees = p; + ctx->tree_count = count; +#endif +} + +static void free_tree_refs(struct audit_context *ctx) +{ + struct audit_tree_refs *p, *q; + for (p = ctx->first_trees; p; p = q) { + q = p->next; + kfree(p); + } +} + +static int match_tree_refs(struct audit_context *ctx, struct audit_tree *tree) +{ +#ifdef CONFIG_AUDIT_TREE + struct audit_tree_refs *p; + int n; + if (!tree) + return 0; + /* full ones */ + for (p = ctx->first_trees; p != ctx->trees; p = p->next) { + for (n = 0; n < 31; n++) + if (audit_tree_match(p->c[n], tree)) + return 1; + } + /* partial */ + if (p) { + for (n = ctx->tree_count; n < 31; n++) + if (audit_tree_match(p->c[n], tree)) + return 1; + } +#endif + return 0; +} + +static int audit_compare_uid(kuid_t uid, + struct audit_names *name, + struct audit_field *f, + struct audit_context *ctx) +{ + struct audit_names *n; + int rc; + + if (name) { + rc = audit_uid_comparator(uid, f->op, name->uid); + if (rc) + return rc; + } + + if (ctx) { + list_for_each_entry(n, &ctx->names_list, list) { + rc = audit_uid_comparator(uid, f->op, n->uid); + if (rc) + return rc; + } + } + return 0; +} + +static int audit_compare_gid(kgid_t gid, + struct audit_names *name, + struct audit_field *f, + struct audit_context *ctx) +{ + struct audit_names *n; + int rc; + + if (name) { + rc = audit_gid_comparator(gid, f->op, name->gid); + if (rc) + return rc; + } + + if (ctx) { + list_for_each_entry(n, &ctx->names_list, list) { + rc = audit_gid_comparator(gid, f->op, n->gid); + if (rc) + return rc; + } + } + return 0; +} + +static int audit_field_compare(struct task_struct *tsk, + const struct cred *cred, + struct audit_field *f, + struct audit_context *ctx, + struct audit_names *name) +{ + switch (f->val) { + /* process to file object comparisons */ + case AUDIT_COMPARE_UID_TO_OBJ_UID: + return audit_compare_uid(cred->uid, name, f, ctx); + case AUDIT_COMPARE_GID_TO_OBJ_GID: + return audit_compare_gid(cred->gid, name, f, ctx); + case AUDIT_COMPARE_EUID_TO_OBJ_UID: + return audit_compare_uid(cred->euid, name, f, ctx); + case AUDIT_COMPARE_EGID_TO_OBJ_GID: + return audit_compare_gid(cred->egid, name, f, ctx); + case AUDIT_COMPARE_AUID_TO_OBJ_UID: + return audit_compare_uid(tsk->loginuid, name, f, ctx); + case AUDIT_COMPARE_SUID_TO_OBJ_UID: + return audit_compare_uid(cred->suid, name, f, ctx); + case AUDIT_COMPARE_SGID_TO_OBJ_GID: + return audit_compare_gid(cred->sgid, name, f, ctx); + case AUDIT_COMPARE_FSUID_TO_OBJ_UID: + return audit_compare_uid(cred->fsuid, name, f, ctx); + case AUDIT_COMPARE_FSGID_TO_OBJ_GID: + return audit_compare_gid(cred->fsgid, name, f, ctx); + /* uid comparisons */ + case AUDIT_COMPARE_UID_TO_AUID: + return audit_uid_comparator(cred->uid, f->op, tsk->loginuid); + case AUDIT_COMPARE_UID_TO_EUID: + return audit_uid_comparator(cred->uid, f->op, cred->euid); + case AUDIT_COMPARE_UID_TO_SUID: + return audit_uid_comparator(cred->uid, f->op, cred->suid); + case AUDIT_COMPARE_UID_TO_FSUID: + return audit_uid_comparator(cred->uid, f->op, cred->fsuid); + /* auid comparisons */ + case AUDIT_COMPARE_AUID_TO_EUID: + return audit_uid_comparator(tsk->loginuid, f->op, cred->euid); + case AUDIT_COMPARE_AUID_TO_SUID: + return audit_uid_comparator(tsk->loginuid, f->op, cred->suid); + case AUDIT_COMPARE_AUID_TO_FSUID: + return audit_uid_comparator(tsk->loginuid, f->op, cred->fsuid); + /* euid comparisons */ + case AUDIT_COMPARE_EUID_TO_SUID: + return audit_uid_comparator(cred->euid, f->op, cred->suid); + case AUDIT_COMPARE_EUID_TO_FSUID: + return audit_uid_comparator(cred->euid, f->op, cred->fsuid); + /* suid comparisons */ + case AUDIT_COMPARE_SUID_TO_FSUID: + return audit_uid_comparator(cred->suid, f->op, cred->fsuid); + /* gid comparisons */ + case AUDIT_COMPARE_GID_TO_EGID: + return audit_gid_comparator(cred->gid, f->op, cred->egid); + case AUDIT_COMPARE_GID_TO_SGID: + return audit_gid_comparator(cred->gid, f->op, cred->sgid); + case AUDIT_COMPARE_GID_TO_FSGID: + return audit_gid_comparator(cred->gid, f->op, cred->fsgid); + /* egid comparisons */ + case AUDIT_COMPARE_EGID_TO_SGID: + return audit_gid_comparator(cred->egid, f->op, cred->sgid); + case AUDIT_COMPARE_EGID_TO_FSGID: + return audit_gid_comparator(cred->egid, f->op, cred->fsgid); + /* sgid comparison */ + case AUDIT_COMPARE_SGID_TO_FSGID: + return audit_gid_comparator(cred->sgid, f->op, cred->fsgid); + default: + WARN(1, "Missing AUDIT_COMPARE define. Report as a bug\n"); + return 0; + } + return 0; +} + +/* Determine if any context name data matches a rule's watch data */ +/* Compare a task_struct with an audit_rule. Return 1 on match, 0 + * otherwise. + * + * If task_creation is true, this is an explicit indication that we are + * filtering a task rule at task creation time. This and tsk == current are + * the only situations where tsk->cred may be accessed without an rcu read lock. + */ +static int audit_filter_rules(struct task_struct *tsk, + struct audit_krule *rule, + struct audit_context *ctx, + struct audit_names *name, + enum audit_state *state, + bool task_creation) +{ + const struct cred *cred; + int i, need_sid = 1; + u32 sid; + + cred = rcu_dereference_check(tsk->cred, tsk == current || task_creation); + + for (i = 0; i < rule->field_count; i++) { + struct audit_field *f = &rule->fields[i]; + struct audit_names *n; + int result = 0; + pid_t pid; + + switch (f->type) { + case AUDIT_PID: + pid = task_pid_nr(tsk); + result = audit_comparator(pid, f->op, f->val); + break; + case AUDIT_PPID: + if (ctx) { + if (!ctx->ppid) + ctx->ppid = task_ppid_nr(tsk); + result = audit_comparator(ctx->ppid, f->op, f->val); + } + break; + case AUDIT_UID: + result = audit_uid_comparator(cred->uid, f->op, f->uid); + break; + case AUDIT_EUID: + result = audit_uid_comparator(cred->euid, f->op, f->uid); + break; + case AUDIT_SUID: + result = audit_uid_comparator(cred->suid, f->op, f->uid); + break; + case AUDIT_FSUID: + result = audit_uid_comparator(cred->fsuid, f->op, f->uid); + break; + case AUDIT_GID: + result = audit_gid_comparator(cred->gid, f->op, f->gid); + if (f->op == Audit_equal) { + if (!result) + result = in_group_p(f->gid); + } else if (f->op == Audit_not_equal) { + if (result) + result = !in_group_p(f->gid); + } + break; + case AUDIT_EGID: + result = audit_gid_comparator(cred->egid, f->op, f->gid); + if (f->op == Audit_equal) { + if (!result) + result = in_egroup_p(f->gid); + } else if (f->op == Audit_not_equal) { + if (result) + result = !in_egroup_p(f->gid); + } + break; + case AUDIT_SGID: + result = audit_gid_comparator(cred->sgid, f->op, f->gid); + break; + case AUDIT_FSGID: + result = audit_gid_comparator(cred->fsgid, f->op, f->gid); + break; + case AUDIT_PERS: + result = audit_comparator(tsk->personality, f->op, f->val); + break; + case AUDIT_ARCH: + if (ctx) + result = audit_comparator(ctx->arch, f->op, f->val); + break; + + case AUDIT_EXIT: + if (ctx && ctx->return_valid) + result = audit_comparator(ctx->return_code, f->op, f->val); + break; + case AUDIT_SUCCESS: + if (ctx && ctx->return_valid) { + if (f->val) + result = audit_comparator(ctx->return_valid, f->op, AUDITSC_SUCCESS); + else + result = audit_comparator(ctx->return_valid, f->op, AUDITSC_FAILURE); + } + break; + case AUDIT_DEVMAJOR: + if (name) { + if (audit_comparator(MAJOR(name->dev), f->op, f->val) || + audit_comparator(MAJOR(name->rdev), f->op, f->val)) + ++result; + } else if (ctx) { + list_for_each_entry(n, &ctx->names_list, list) { + if (audit_comparator(MAJOR(n->dev), f->op, f->val) || + audit_comparator(MAJOR(n->rdev), f->op, f->val)) { + ++result; + break; + } + } + } + break; + case AUDIT_DEVMINOR: + if (name) { + if (audit_comparator(MINOR(name->dev), f->op, f->val) || + audit_comparator(MINOR(name->rdev), f->op, f->val)) + ++result; + } else if (ctx) { + list_for_each_entry(n, &ctx->names_list, list) { + if (audit_comparator(MINOR(n->dev), f->op, f->val) || + audit_comparator(MINOR(n->rdev), f->op, f->val)) { + ++result; + break; + } + } + } + break; + case AUDIT_INODE: + if (name) + result = audit_comparator(name->ino, f->op, f->val); + else if (ctx) { + list_for_each_entry(n, &ctx->names_list, list) { + if (audit_comparator(n->ino, f->op, f->val)) { + ++result; + break; + } + } + } + break; + case AUDIT_OBJ_UID: + if (name) { + result = audit_uid_comparator(name->uid, f->op, f->uid); + } else if (ctx) { + list_for_each_entry(n, &ctx->names_list, list) { + if (audit_uid_comparator(n->uid, f->op, f->uid)) { + ++result; + break; + } + } + } + break; + case AUDIT_OBJ_GID: + if (name) { + result = audit_gid_comparator(name->gid, f->op, f->gid); + } else if (ctx) { + list_for_each_entry(n, &ctx->names_list, list) { + if (audit_gid_comparator(n->gid, f->op, f->gid)) { + ++result; + break; + } + } + } + break; + case AUDIT_WATCH: + if (name) + result = audit_watch_compare(rule->watch, name->ino, name->dev); + break; + case AUDIT_DIR: + if (ctx) + result = match_tree_refs(ctx, rule->tree); + break; + case AUDIT_LOGINUID: + result = 0; + if (ctx) + result = audit_uid_comparator(tsk->loginuid, f->op, f->uid); + break; + case AUDIT_LOGINUID_SET: + result = audit_comparator(audit_loginuid_set(tsk), f->op, f->val); + break; + case AUDIT_SUBJ_USER: + case AUDIT_SUBJ_ROLE: + case AUDIT_SUBJ_TYPE: + case AUDIT_SUBJ_SEN: + case AUDIT_SUBJ_CLR: + /* NOTE: this may return negative values indicating + a temporary error. We simply treat this as a + match for now to avoid losing information that + may be wanted. An error message will also be + logged upon error */ + if (f->lsm_rule) { + if (need_sid) { + security_task_getsecid(tsk, &sid); + need_sid = 0; + } + result = security_audit_rule_match(sid, f->type, + f->op, + f->lsm_rule, + ctx); + } + break; + case AUDIT_OBJ_USER: + case AUDIT_OBJ_ROLE: + case AUDIT_OBJ_TYPE: + case AUDIT_OBJ_LEV_LOW: + case AUDIT_OBJ_LEV_HIGH: + /* The above note for AUDIT_SUBJ_USER...AUDIT_SUBJ_CLR + also applies here */ + if (f->lsm_rule) { + /* Find files that match */ + if (name) { + result = security_audit_rule_match( + name->osid, f->type, f->op, + f->lsm_rule, ctx); + } else if (ctx) { + list_for_each_entry(n, &ctx->names_list, list) { + if (security_audit_rule_match(n->osid, f->type, + f->op, f->lsm_rule, + ctx)) { + ++result; + break; + } + } + } + /* Find ipc objects that match */ + if (!ctx || ctx->type != AUDIT_IPC) + break; + if (security_audit_rule_match(ctx->ipc.osid, + f->type, f->op, + f->lsm_rule, ctx)) + ++result; + } + break; + case AUDIT_ARG0: + case AUDIT_ARG1: + case AUDIT_ARG2: + case AUDIT_ARG3: + if (ctx) + result = audit_comparator(ctx->argv[f->type-AUDIT_ARG0], f->op, f->val); + break; + case AUDIT_FILTERKEY: + /* ignore this field for filtering */ + result = 1; + break; + case AUDIT_PERM: + result = audit_match_perm(ctx, f->val); + break; + case AUDIT_FILETYPE: + result = audit_match_filetype(ctx, f->val); + break; + case AUDIT_FIELD_COMPARE: + result = audit_field_compare(tsk, cred, f, ctx, name); + break; + } + if (!result) + return 0; + } + + if (ctx) { + if (rule->prio <= ctx->prio) + return 0; + if (rule->filterkey) { + kfree(ctx->filterkey); + ctx->filterkey = kstrdup(rule->filterkey, GFP_ATOMIC); + } + ctx->prio = rule->prio; + } + switch (rule->action) { + case AUDIT_NEVER: *state = AUDIT_DISABLED; break; + case AUDIT_ALWAYS: *state = AUDIT_RECORD_CONTEXT; break; + } + return 1; +} + +/* At process creation time, we can determine if system-call auditing is + * completely disabled for this task. Since we only have the task + * structure at this point, we can only check uid and gid. + */ +static enum audit_state audit_filter_task(struct task_struct *tsk, char **key) +{ + struct audit_entry *e; + enum audit_state state; + + rcu_read_lock(); + list_for_each_entry_rcu(e, &audit_filter_list[AUDIT_FILTER_TASK], list) { + if (audit_filter_rules(tsk, &e->rule, NULL, NULL, + &state, true)) { + if (state == AUDIT_RECORD_CONTEXT) + *key = kstrdup(e->rule.filterkey, GFP_ATOMIC); + rcu_read_unlock(); + return state; + } + } + rcu_read_unlock(); + return AUDIT_BUILD_CONTEXT; +} + +static int audit_in_mask(const struct audit_krule *rule, unsigned long val) +{ + int word, bit; + + if (val > 0xffffffff) + return false; + + word = AUDIT_WORD(val); + if (word >= AUDIT_BITMASK_SIZE) + return false; + + bit = AUDIT_BIT(val); + + return rule->mask[word] & bit; +} + +/* At syscall entry and exit time, this filter is called if the + * audit_state is not low enough that auditing cannot take place, but is + * also not high enough that we already know we have to write an audit + * record (i.e., the state is AUDIT_SETUP_CONTEXT or AUDIT_BUILD_CONTEXT). + */ +static enum audit_state audit_filter_syscall(struct task_struct *tsk, + struct audit_context *ctx, + struct list_head *list) +{ + struct audit_entry *e; + enum audit_state state; + + if (audit_pid && tsk->tgid == audit_pid) + return AUDIT_DISABLED; + + rcu_read_lock(); + if (!list_empty(list)) { + list_for_each_entry_rcu(e, list, list) { + if (audit_in_mask(&e->rule, ctx->major) && + audit_filter_rules(tsk, &e->rule, ctx, NULL, + &state, false)) { + rcu_read_unlock(); + ctx->current_state = state; + return state; + } + } + } + rcu_read_unlock(); + return AUDIT_BUILD_CONTEXT; +} + +/* + * Given an audit_name check the inode hash table to see if they match. + * Called holding the rcu read lock to protect the use of audit_inode_hash + */ +static int audit_filter_inode_name(struct task_struct *tsk, + struct audit_names *n, + struct audit_context *ctx) { + int h = audit_hash_ino((u32)n->ino); + struct list_head *list = &audit_inode_hash[h]; + struct audit_entry *e; + enum audit_state state; + + if (list_empty(list)) + return 0; + + list_for_each_entry_rcu(e, list, list) { + if (audit_in_mask(&e->rule, ctx->major) && + audit_filter_rules(tsk, &e->rule, ctx, n, &state, false)) { + ctx->current_state = state; + return 1; + } + } + + return 0; +} + +/* At syscall exit time, this filter is called if any audit_names have been + * collected during syscall processing. We only check rules in sublists at hash + * buckets applicable to the inode numbers in audit_names. + * Regarding audit_state, same rules apply as for audit_filter_syscall(). + */ +void audit_filter_inodes(struct task_struct *tsk, struct audit_context *ctx) +{ + struct audit_names *n; + + if (audit_pid && tsk->tgid == audit_pid) + return; + + rcu_read_lock(); + + list_for_each_entry(n, &ctx->names_list, list) { + if (audit_filter_inode_name(tsk, n, ctx)) + break; + } + rcu_read_unlock(); +} + +/* Transfer the audit context pointer to the caller, clearing it in the tsk's struct */ +static inline struct audit_context *audit_take_context(struct task_struct *tsk, + int return_valid, + long return_code) +{ + struct audit_context *context = tsk->audit_context; + + if (!context) + return NULL; + context->return_valid = return_valid; + + /* + * we need to fix up the return code in the audit logs if the actual + * return codes are later going to be fixed up by the arch specific + * signal handlers + * + * This is actually a test for: + * (rc == ERESTARTSYS ) || (rc == ERESTARTNOINTR) || + * (rc == ERESTARTNOHAND) || (rc == ERESTART_RESTARTBLOCK) + * + * but is faster than a bunch of || + */ + if (unlikely(return_code <= -ERESTARTSYS) && + (return_code >= -ERESTART_RESTARTBLOCK) && + (return_code != -ENOIOCTLCMD)) + context->return_code = -EINTR; + else + context->return_code = return_code; + + if (context->in_syscall && !context->dummy) { + audit_filter_syscall(tsk, context, &audit_filter_list[AUDIT_FILTER_EXIT]); + audit_filter_inodes(tsk, context); + } + + tsk->audit_context = NULL; + return context; +} + +static inline void audit_proctitle_free(struct audit_context *context) +{ + kfree(context->proctitle.value); + context->proctitle.value = NULL; + context->proctitle.len = 0; +} + +static inline void audit_free_names(struct audit_context *context) +{ + struct audit_names *n, *next; + + list_for_each_entry_safe(n, next, &context->names_list, list) { + list_del(&n->list); + if (n->name) + putname(n->name); + if (n->should_free) + kfree(n); + } + context->name_count = 0; + path_put(&context->pwd); + context->pwd.dentry = NULL; + context->pwd.mnt = NULL; +} + +static inline void audit_free_aux(struct audit_context *context) +{ + struct audit_aux_data *aux; + + while ((aux = context->aux)) { + context->aux = aux->next; + kfree(aux); + } + while ((aux = context->aux_pids)) { + context->aux_pids = aux->next; + kfree(aux); + } +} + +static inline struct audit_context *audit_alloc_context(enum audit_state state) +{ + struct audit_context *context; + + context = kzalloc(sizeof(*context), GFP_KERNEL); + if (!context) + return NULL; + context->state = state; + context->prio = state == AUDIT_RECORD_CONTEXT ? ~0ULL : 0; + INIT_LIST_HEAD(&context->killed_trees); + INIT_LIST_HEAD(&context->names_list); + return context; +} + +/** + * audit_alloc - allocate an audit context block for a task + * @tsk: task + * + * Filter on the task information and allocate a per-task audit context + * if necessary. Doing so turns on system call auditing for the + * specified task. This is called from copy_process, so no lock is + * needed. + */ +int audit_alloc(struct task_struct *tsk) +{ + struct audit_context *context; + enum audit_state state; + char *key = NULL; + + if (likely(!audit_ever_enabled)) + return 0; /* Return if not auditing. */ + + state = audit_filter_task(tsk, &key); + if (state == AUDIT_DISABLED) { + clear_tsk_thread_flag(tsk, TIF_SYSCALL_AUDIT); + return 0; + } + + if (!(context = audit_alloc_context(state))) { + kfree(key); + audit_log_lost("out of memory in audit_alloc"); + return -ENOMEM; + } + context->filterkey = key; + + tsk->audit_context = context; + set_tsk_thread_flag(tsk, TIF_SYSCALL_AUDIT); + return 0; +} + +static inline void audit_free_context(struct audit_context *context) +{ + audit_free_names(context); + unroll_tree_refs(context, NULL, 0); + free_tree_refs(context); + audit_free_aux(context); + kfree(context->filterkey); + kfree(context->sockaddr); + audit_proctitle_free(context); + kfree(context); +} + +static int audit_log_pid_context(struct audit_context *context, pid_t pid, + kuid_t auid, kuid_t uid, unsigned int sessionid, + u32 sid, char *comm) +{ + struct audit_buffer *ab; + char *ctx = NULL; + u32 len; + int rc = 0; + + ab = audit_log_start(context, GFP_KERNEL, AUDIT_OBJ_PID); + if (!ab) + return rc; + + audit_log_format(ab, "opid=%d oauid=%d ouid=%d oses=%d", pid, + from_kuid(&init_user_ns, auid), + from_kuid(&init_user_ns, uid), sessionid); + if (sid) { + if (security_secid_to_secctx(sid, &ctx, &len)) { + audit_log_format(ab, " obj=(none)"); + rc = 1; + } else { + audit_log_format(ab, " obj=%s", ctx); + security_release_secctx(ctx, len); + } + } + audit_log_format(ab, " ocomm="); + audit_log_untrustedstring(ab, comm); + audit_log_end(ab); + + return rc; +} + +/* + * to_send and len_sent accounting are very loose estimates. We aren't + * really worried about a hard cap to MAX_EXECVE_AUDIT_LEN so much as being + * within about 500 bytes (next page boundary) + * + * why snprintf? an int is up to 12 digits long. if we just assumed when + * logging that a[%d]= was going to be 16 characters long we would be wasting + * space in every audit message. In one 7500 byte message we can log up to + * about 1000 min size arguments. That comes down to about 50% waste of space + * if we didn't do the snprintf to find out how long arg_num_len was. + */ +static int audit_log_single_execve_arg(struct audit_context *context, + struct audit_buffer **ab, + int arg_num, + size_t *len_sent, + const char __user *p, + char *buf) +{ + char arg_num_len_buf[12]; + const char __user *tmp_p = p; + /* how many digits are in arg_num? 5 is the length of ' a=""' */ + size_t arg_num_len = snprintf(arg_num_len_buf, 12, "%d", arg_num) + 5; + size_t len, len_left, to_send; + size_t max_execve_audit_len = MAX_EXECVE_AUDIT_LEN; + unsigned int i, has_cntl = 0, too_long = 0; + int ret; + + /* strnlen_user includes the null we don't want to send */ + len_left = len = strnlen_user(p, MAX_ARG_STRLEN) - 1; + + /* + * We just created this mm, if we can't find the strings + * we just copied into it something is _very_ wrong. Similar + * for strings that are too long, we should not have created + * any. + */ + if (unlikely((len == -1) || len > MAX_ARG_STRLEN - 1)) { + WARN_ON(1); + send_sig(SIGKILL, current, 0); + return -1; + } + + /* walk the whole argument looking for non-ascii chars */ + do { + if (len_left > MAX_EXECVE_AUDIT_LEN) + to_send = MAX_EXECVE_AUDIT_LEN; + else + to_send = len_left; + ret = copy_from_user(buf, tmp_p, to_send); + /* + * There is no reason for this copy to be short. We just + * copied them here, and the mm hasn't been exposed to user- + * space yet. + */ + if (ret) { + WARN_ON(1); + send_sig(SIGKILL, current, 0); + return -1; + } + buf[to_send] = '\0'; + has_cntl = audit_string_contains_control(buf, to_send); + if (has_cntl) { + /* + * hex messages get logged as 2 bytes, so we can only + * send half as much in each message + */ + max_execve_audit_len = MAX_EXECVE_AUDIT_LEN / 2; + break; + } + len_left -= to_send; + tmp_p += to_send; + } while (len_left > 0); + + len_left = len; + + if (len > max_execve_audit_len) + too_long = 1; + + /* rewalk the argument actually logging the message */ + for (i = 0; len_left > 0; i++) { + int room_left; + + if (len_left > max_execve_audit_len) + to_send = max_execve_audit_len; + else + to_send = len_left; + + /* do we have space left to send this argument in this ab? */ + room_left = MAX_EXECVE_AUDIT_LEN - arg_num_len - *len_sent; + if (has_cntl) + room_left -= (to_send * 2); + else + room_left -= to_send; + if (room_left < 0) { + *len_sent = 0; + audit_log_end(*ab); + *ab = audit_log_start(context, GFP_KERNEL, AUDIT_EXECVE); + if (!*ab) + return 0; + } + + /* + * first record needs to say how long the original string was + * so we can be sure nothing was lost. + */ + if ((i == 0) && (too_long)) + audit_log_format(*ab, " a%d_len=%zu", arg_num, + has_cntl ? 2*len : len); + + /* + * normally arguments are small enough to fit and we already + * filled buf above when we checked for control characters + * so don't bother with another copy_from_user + */ + if (len >= max_execve_audit_len) + ret = copy_from_user(buf, p, to_send); + else + ret = 0; + if (ret) { + WARN_ON(1); + send_sig(SIGKILL, current, 0); + return -1; + } + buf[to_send] = '\0'; + + /* actually log it */ + audit_log_format(*ab, " a%d", arg_num); + if (too_long) + audit_log_format(*ab, "[%d]", i); + audit_log_format(*ab, "="); + if (has_cntl) + audit_log_n_hex(*ab, buf, to_send); + else + audit_log_string(*ab, buf); + + p += to_send; + len_left -= to_send; + *len_sent += arg_num_len; + if (has_cntl) + *len_sent += to_send * 2; + else + *len_sent += to_send; + } + /* include the null we didn't log */ + return len + 1; +} + +static void audit_log_execve_info(struct audit_context *context, + struct audit_buffer **ab) +{ + int i, len; + size_t len_sent = 0; + const char __user *p; + char *buf; + + p = (const char __user *)current->mm->arg_start; + + audit_log_format(*ab, "argc=%d", context->execve.argc); + + /* + * we need some kernel buffer to hold the userspace args. Just + * allocate one big one rather than allocating one of the right size + * for every single argument inside audit_log_single_execve_arg() + * should be <8k allocation so should be pretty safe. + */ + buf = kmalloc(MAX_EXECVE_AUDIT_LEN + 1, GFP_KERNEL); + if (!buf) { + audit_panic("out of memory for argv string"); + return; + } + + for (i = 0; i < context->execve.argc; i++) { + len = audit_log_single_execve_arg(context, ab, i, + &len_sent, p, buf); + if (len <= 0) + break; + p += len; + } + kfree(buf); +} + +static void show_special(struct audit_context *context, int *call_panic) +{ + struct audit_buffer *ab; + int i; + + ab = audit_log_start(context, GFP_KERNEL, context->type); + if (!ab) + return; + + switch (context->type) { + case AUDIT_SOCKETCALL: { + int nargs = context->socketcall.nargs; + audit_log_format(ab, "nargs=%d", nargs); + for (i = 0; i < nargs; i++) + audit_log_format(ab, " a%d=%lx", i, + context->socketcall.args[i]); + break; } + case AUDIT_IPC: { + u32 osid = context->ipc.osid; + + audit_log_format(ab, "ouid=%u ogid=%u mode=%#ho", + from_kuid(&init_user_ns, context->ipc.uid), + from_kgid(&init_user_ns, context->ipc.gid), + context->ipc.mode); + if (osid) { + char *ctx = NULL; + u32 len; + if (security_secid_to_secctx(osid, &ctx, &len)) { + audit_log_format(ab, " osid=%u", osid); + *call_panic = 1; + } else { + audit_log_format(ab, " obj=%s", ctx); + security_release_secctx(ctx, len); + } + } + if (context->ipc.has_perm) { + audit_log_end(ab); + ab = audit_log_start(context, GFP_KERNEL, + AUDIT_IPC_SET_PERM); + if (unlikely(!ab)) + return; + audit_log_format(ab, + "qbytes=%lx ouid=%u ogid=%u mode=%#ho", + context->ipc.qbytes, + context->ipc.perm_uid, + context->ipc.perm_gid, + context->ipc.perm_mode); + } + break; } + case AUDIT_MQ_OPEN: { + audit_log_format(ab, + "oflag=0x%x mode=%#ho mq_flags=0x%lx mq_maxmsg=%ld " + "mq_msgsize=%ld mq_curmsgs=%ld", + context->mq_open.oflag, context->mq_open.mode, + context->mq_open.attr.mq_flags, + context->mq_open.attr.mq_maxmsg, + context->mq_open.attr.mq_msgsize, + context->mq_open.attr.mq_curmsgs); + break; } + case AUDIT_MQ_SENDRECV: { + audit_log_format(ab, + "mqdes=%d msg_len=%zd msg_prio=%u " + "abs_timeout_sec=%ld abs_timeout_nsec=%ld", + context->mq_sendrecv.mqdes, + context->mq_sendrecv.msg_len, + context->mq_sendrecv.msg_prio, + context->mq_sendrecv.abs_timeout.tv_sec, + context->mq_sendrecv.abs_timeout.tv_nsec); + break; } + case AUDIT_MQ_NOTIFY: { + audit_log_format(ab, "mqdes=%d sigev_signo=%d", + context->mq_notify.mqdes, + context->mq_notify.sigev_signo); + break; } + case AUDIT_MQ_GETSETATTR: { + struct mq_attr *attr = &context->mq_getsetattr.mqstat; + audit_log_format(ab, + "mqdes=%d mq_flags=0x%lx mq_maxmsg=%ld mq_msgsize=%ld " + "mq_curmsgs=%ld ", + context->mq_getsetattr.mqdes, + attr->mq_flags, attr->mq_maxmsg, + attr->mq_msgsize, attr->mq_curmsgs); + break; } + case AUDIT_CAPSET: { + audit_log_format(ab, "pid=%d", context->capset.pid); + audit_log_cap(ab, "cap_pi", &context->capset.cap.inheritable); + audit_log_cap(ab, "cap_pp", &context->capset.cap.permitted); + audit_log_cap(ab, "cap_pe", &context->capset.cap.effective); + break; } + case AUDIT_MMAP: { + audit_log_format(ab, "fd=%d flags=0x%x", context->mmap.fd, + context->mmap.flags); + break; } + case AUDIT_EXECVE: { + audit_log_execve_info(context, &ab); + break; } + } + audit_log_end(ab); +} + +static inline int audit_proctitle_rtrim(char *proctitle, int len) +{ + char *end = proctitle + len - 1; + while (end > proctitle && !isprint(*end)) + end--; + + /* catch the case where proctitle is only 1 non-print character */ + len = end - proctitle + 1; + len -= isprint(proctitle[len-1]) == 0; + return len; +} + +static void audit_log_proctitle(struct task_struct *tsk, + struct audit_context *context) +{ + int res; + char *buf; + char *msg = "(null)"; + int len = strlen(msg); + struct audit_buffer *ab; + + ab = audit_log_start(context, GFP_KERNEL, AUDIT_PROCTITLE); + if (!ab) + return; /* audit_panic or being filtered */ + + audit_log_format(ab, "proctitle="); + + /* Not cached */ + if (!context->proctitle.value) { + buf = kmalloc(MAX_PROCTITLE_AUDIT_LEN, GFP_KERNEL); + if (!buf) + goto out; + /* Historically called this from procfs naming */ + res = get_cmdline(tsk, buf, MAX_PROCTITLE_AUDIT_LEN); + if (res == 0) { + kfree(buf); + goto out; + } + res = audit_proctitle_rtrim(buf, res); + if (res == 0) { + kfree(buf); + goto out; + } + context->proctitle.value = buf; + context->proctitle.len = res; + } + msg = context->proctitle.value; + len = context->proctitle.len; +out: + audit_log_n_untrustedstring(ab, msg, len); + audit_log_end(ab); +} + +static void audit_log_exit(struct audit_context *context, struct task_struct *tsk) +{ + int i, call_panic = 0; + struct audit_buffer *ab; + struct audit_aux_data *aux; + struct audit_names *n; + + /* tsk == current */ + context->personality = tsk->personality; + + ab = audit_log_start(context, GFP_KERNEL, AUDIT_SYSCALL); + if (!ab) + return; /* audit_panic has been called */ + audit_log_format(ab, "arch=%x syscall=%d", + context->arch, context->major); + if (context->personality != PER_LINUX) + audit_log_format(ab, " per=%lx", context->personality); + if (context->return_valid) + audit_log_format(ab, " success=%s exit=%ld", + (context->return_valid==AUDITSC_SUCCESS)?"yes":"no", + context->return_code); + + audit_log_format(ab, + " a0=%lx a1=%lx a2=%lx a3=%lx items=%d", + context->argv[0], + context->argv[1], + context->argv[2], + context->argv[3], + context->name_count); + + audit_log_task_info(ab, tsk); + audit_log_key(ab, context->filterkey); + audit_log_end(ab); + + for (aux = context->aux; aux; aux = aux->next) { + + ab = audit_log_start(context, GFP_KERNEL, aux->type); + if (!ab) + continue; /* audit_panic has been called */ + + switch (aux->type) { + + case AUDIT_BPRM_FCAPS: { + struct audit_aux_data_bprm_fcaps *axs = (void *)aux; + audit_log_format(ab, "fver=%x", axs->fcap_ver); + audit_log_cap(ab, "fp", &axs->fcap.permitted); + audit_log_cap(ab, "fi", &axs->fcap.inheritable); + audit_log_format(ab, " fe=%d", axs->fcap.fE); + audit_log_cap(ab, "old_pp", &axs->old_pcap.permitted); + audit_log_cap(ab, "old_pi", &axs->old_pcap.inheritable); + audit_log_cap(ab, "old_pe", &axs->old_pcap.effective); + audit_log_cap(ab, "new_pp", &axs->new_pcap.permitted); + audit_log_cap(ab, "new_pi", &axs->new_pcap.inheritable); + audit_log_cap(ab, "new_pe", &axs->new_pcap.effective); + break; } + + } + audit_log_end(ab); + } + + if (context->type) + show_special(context, &call_panic); + + if (context->fds[0] >= 0) { + ab = audit_log_start(context, GFP_KERNEL, AUDIT_FD_PAIR); + if (ab) { + audit_log_format(ab, "fd0=%d fd1=%d", + context->fds[0], context->fds[1]); + audit_log_end(ab); + } + } + + if (context->sockaddr_len) { + ab = audit_log_start(context, GFP_KERNEL, AUDIT_SOCKADDR); + if (ab) { + audit_log_format(ab, "saddr="); + audit_log_n_hex(ab, (void *)context->sockaddr, + context->sockaddr_len); + audit_log_end(ab); + } + } + + for (aux = context->aux_pids; aux; aux = aux->next) { + struct audit_aux_data_pids *axs = (void *)aux; + + for (i = 0; i < axs->pid_count; i++) + if (audit_log_pid_context(context, axs->target_pid[i], + axs->target_auid[i], + axs->target_uid[i], + axs->target_sessionid[i], + axs->target_sid[i], + axs->target_comm[i])) + call_panic = 1; + } + + if (context->target_pid && + audit_log_pid_context(context, context->target_pid, + context->target_auid, context->target_uid, + context->target_sessionid, + context->target_sid, context->target_comm)) + call_panic = 1; + + if (context->pwd.dentry && context->pwd.mnt) { + ab = audit_log_start(context, GFP_KERNEL, AUDIT_CWD); + if (ab) { + audit_log_d_path(ab, " cwd=", &context->pwd); + audit_log_end(ab); + } + } + + i = 0; + list_for_each_entry(n, &context->names_list, list) { + if (n->hidden) + continue; + audit_log_name(context, n, NULL, i++, &call_panic); + } + + audit_log_proctitle(tsk, context); + + /* Send end of event record to help user space know we are finished */ + ab = audit_log_start(context, GFP_KERNEL, AUDIT_EOE); + if (ab) + audit_log_end(ab); + if (call_panic) + audit_panic("error converting sid to string"); +} + +/** + * audit_free - free a per-task audit context + * @tsk: task whose audit context block to free + * + * Called from copy_process and do_exit + */ +void __audit_free(struct task_struct *tsk) +{ + struct audit_context *context; + + context = audit_take_context(tsk, 0, 0); + if (!context) + return; + + /* Check for system calls that do not go through the exit + * function (e.g., exit_group), then free context block. + * We use GFP_ATOMIC here because we might be doing this + * in the context of the idle thread */ + /* that can happen only if we are called from do_exit() */ + if (context->in_syscall && context->current_state == AUDIT_RECORD_CONTEXT) + audit_log_exit(context, tsk); + if (!list_empty(&context->killed_trees)) + audit_kill_trees(&context->killed_trees); + + audit_free_context(context); +} + +/** + * audit_syscall_entry - fill in an audit record at syscall entry + * @major: major syscall type (function) + * @a1: additional syscall register 1 + * @a2: additional syscall register 2 + * @a3: additional syscall register 3 + * @a4: additional syscall register 4 + * + * Fill in audit context at syscall entry. This only happens if the + * audit context was created when the task was created and the state or + * filters demand the audit context be built. If the state from the + * per-task filter or from the per-syscall filter is AUDIT_RECORD_CONTEXT, + * then the record will be written at syscall exit time (otherwise, it + * will only be written if another part of the kernel requests that it + * be written). + */ +void __audit_syscall_entry(int major, unsigned long a1, unsigned long a2, + unsigned long a3, unsigned long a4) +{ + struct task_struct *tsk = current; + struct audit_context *context = tsk->audit_context; + enum audit_state state; + + if (!context) + return; + + BUG_ON(context->in_syscall || context->name_count); + + if (!audit_enabled) + return; + + context->arch = syscall_get_arch(); + context->major = major; + context->argv[0] = a1; + context->argv[1] = a2; + context->argv[2] = a3; + context->argv[3] = a4; + + state = context->state; + context->dummy = !audit_n_rules; + if (!context->dummy && state == AUDIT_BUILD_CONTEXT) { + context->prio = 0; + state = audit_filter_syscall(tsk, context, &audit_filter_list[AUDIT_FILTER_ENTRY]); + } + if (state == AUDIT_DISABLED) + return; + + context->serial = 0; + context->ctime = CURRENT_TIME; + context->in_syscall = 1; + context->current_state = state; + context->ppid = 0; +} + +/** + * audit_syscall_exit - deallocate audit context after a system call + * @success: success value of the syscall + * @return_code: return value of the syscall + * + * Tear down after system call. If the audit context has been marked as + * auditable (either because of the AUDIT_RECORD_CONTEXT state from + * filtering, or because some other part of the kernel wrote an audit + * message), then write out the syscall information. In call cases, + * free the names stored from getname(). + */ +void __audit_syscall_exit(int success, long return_code) +{ + struct task_struct *tsk = current; + struct audit_context *context; + + if (success) + success = AUDITSC_SUCCESS; + else + success = AUDITSC_FAILURE; + + context = audit_take_context(tsk, success, return_code); + if (!context) + return; + + if (context->in_syscall && context->current_state == AUDIT_RECORD_CONTEXT) + audit_log_exit(context, tsk); + + context->in_syscall = 0; + context->prio = context->state == AUDIT_RECORD_CONTEXT ? ~0ULL : 0; + + if (!list_empty(&context->killed_trees)) + audit_kill_trees(&context->killed_trees); + + audit_free_names(context); + unroll_tree_refs(context, NULL, 0); + audit_free_aux(context); + context->aux = NULL; + context->aux_pids = NULL; + context->target_pid = 0; + context->target_sid = 0; + context->sockaddr_len = 0; + context->type = 0; + context->fds[0] = -1; + if (context->state != AUDIT_RECORD_CONTEXT) { + kfree(context->filterkey); + context->filterkey = NULL; + } + tsk->audit_context = context; +} + +static inline void handle_one(const struct inode *inode) +{ +#ifdef CONFIG_AUDIT_TREE + struct audit_context *context; + struct audit_tree_refs *p; + struct audit_chunk *chunk; + int count; + if (likely(hlist_empty(&inode->i_fsnotify_marks))) + return; + context = current->audit_context; + p = context->trees; + count = context->tree_count; + rcu_read_lock(); + chunk = audit_tree_lookup(inode); + rcu_read_unlock(); + if (!chunk) + return; + if (likely(put_tree_ref(context, chunk))) + return; + if (unlikely(!grow_tree_refs(context))) { + pr_warn("out of memory, audit has lost a tree reference\n"); + audit_set_auditable(context); + audit_put_chunk(chunk); + unroll_tree_refs(context, p, count); + return; + } + put_tree_ref(context, chunk); +#endif +} + +static void handle_path(const struct dentry *dentry) +{ +#ifdef CONFIG_AUDIT_TREE + struct audit_context *context; + struct audit_tree_refs *p; + const struct dentry *d, *parent; + struct audit_chunk *drop; + unsigned long seq; + int count; + + context = current->audit_context; + p = context->trees; + count = context->tree_count; +retry: + drop = NULL; + d = dentry; + rcu_read_lock(); + seq = read_seqbegin(&rename_lock); + for(;;) { + struct inode *inode = d_backing_inode(d); + if (inode && unlikely(!hlist_empty(&inode->i_fsnotify_marks))) { + struct audit_chunk *chunk; + chunk = audit_tree_lookup(inode); + if (chunk) { + if (unlikely(!put_tree_ref(context, chunk))) { + drop = chunk; + break; + } + } + } + parent = d->d_parent; + if (parent == d) + break; + d = parent; + } + if (unlikely(read_seqretry(&rename_lock, seq) || drop)) { /* in this order */ + rcu_read_unlock(); + if (!drop) { + /* just a race with rename */ + unroll_tree_refs(context, p, count); + goto retry; + } + audit_put_chunk(drop); + if (grow_tree_refs(context)) { + /* OK, got more space */ + unroll_tree_refs(context, p, count); + goto retry; + } + /* too bad */ + pr_warn("out of memory, audit has lost a tree reference\n"); + unroll_tree_refs(context, p, count); + audit_set_auditable(context); + return; + } + rcu_read_unlock(); +#endif +} + +static struct audit_names *audit_alloc_name(struct audit_context *context, + unsigned char type) +{ + struct audit_names *aname; + + if (context->name_count < AUDIT_NAMES) { + aname = &context->preallocated_names[context->name_count]; + memset(aname, 0, sizeof(*aname)); + } else { + aname = kzalloc(sizeof(*aname), GFP_NOFS); + if (!aname) + return NULL; + aname->should_free = true; + } + + aname->ino = (unsigned long)-1; + aname->type = type; + list_add_tail(&aname->list, &context->names_list); + + context->name_count++; + return aname; +} + +/** + * audit_reusename - fill out filename with info from existing entry + * @uptr: userland ptr to pathname + * + * Search the audit_names list for the current audit context. If there is an + * existing entry with a matching "uptr" then return the filename + * associated with that audit_name. If not, return NULL. + */ +struct filename * +__audit_reusename(const __user char *uptr) +{ + struct audit_context *context = current->audit_context; + struct audit_names *n; + + list_for_each_entry(n, &context->names_list, list) { + if (!n->name) + continue; + if (n->name->uptr == uptr) { + n->name->refcnt++; + return n->name; + } + } + return NULL; +} + +/** + * audit_getname - add a name to the list + * @name: name to add + * + * Add a name to the list of audit names for this context. + * Called from fs/namei.c:getname(). + */ +void __audit_getname(struct filename *name) +{ + struct audit_context *context = current->audit_context; + struct audit_names *n; + + if (!context->in_syscall) + return; + + n = audit_alloc_name(context, AUDIT_TYPE_UNKNOWN); + if (!n) + return; + + n->name = name; + n->name_len = AUDIT_NAME_FULL; + name->aname = n; + name->refcnt++; + + if (!context->pwd.dentry) + get_fs_pwd(current->fs, &context->pwd); +} + +/** + * __audit_inode - store the inode and device from a lookup + * @name: name being audited + * @dentry: dentry being audited + * @flags: attributes for this particular entry + */ +void __audit_inode(struct filename *name, const struct dentry *dentry, + unsigned int flags) +{ + struct audit_context *context = current->audit_context; + const struct inode *inode = d_backing_inode(dentry); + struct audit_names *n; + bool parent = flags & AUDIT_INODE_PARENT; + + if (!context->in_syscall) + return; + + if (!name) + goto out_alloc; + + /* + * If we have a pointer to an audit_names entry already, then we can + * just use it directly if the type is correct. + */ + n = name->aname; + if (n) { + if (parent) { + if (n->type == AUDIT_TYPE_PARENT || + n->type == AUDIT_TYPE_UNKNOWN) + goto out; + } else { + if (n->type != AUDIT_TYPE_PARENT) + goto out; + } + } + + list_for_each_entry_reverse(n, &context->names_list, list) { + if (n->ino) { + /* valid inode number, use that for the comparison */ + if (n->ino != inode->i_ino || + n->dev != inode->i_sb->s_dev) + continue; + } else if (n->name) { + /* inode number has not been set, check the name */ + if (strcmp(n->name->name, name->name)) + continue; + } else + /* no inode and no name (?!) ... this is odd ... */ + continue; + + /* match the correct record type */ + if (parent) { + if (n->type == AUDIT_TYPE_PARENT || + n->type == AUDIT_TYPE_UNKNOWN) + goto out; + } else { + if (n->type != AUDIT_TYPE_PARENT) + goto out; + } + } + +out_alloc: + /* unable to find an entry with both a matching name and type */ + n = audit_alloc_name(context, AUDIT_TYPE_UNKNOWN); + if (!n) + return; + if (name) { + n->name = name; + name->refcnt++; + } + +out: + if (parent) { + n->name_len = n->name ? parent_len(n->name->name) : AUDIT_NAME_FULL; + n->type = AUDIT_TYPE_PARENT; + if (flags & AUDIT_INODE_HIDDEN) + n->hidden = true; + } else { + n->name_len = AUDIT_NAME_FULL; + n->type = AUDIT_TYPE_NORMAL; + } + handle_path(dentry); + audit_copy_inode(n, dentry, inode); +} + +void __audit_file(const struct file *file) +{ + __audit_inode(NULL, file->f_path.dentry, 0); +} + +/** + * __audit_inode_child - collect inode info for created/removed objects + * @parent: inode of dentry parent + * @dentry: dentry being audited + * @type: AUDIT_TYPE_* value that we're looking for + * + * For syscalls that create or remove filesystem objects, audit_inode + * can only collect information for the filesystem object's parent. + * This call updates the audit context with the child's information. + * Syscalls that create a new filesystem object must be hooked after + * the object is created. Syscalls that remove a filesystem object + * must be hooked prior, in order to capture the target inode during + * unsuccessful attempts. + */ +void __audit_inode_child(const struct inode *parent, + const struct dentry *dentry, + const unsigned char type) +{ + struct audit_context *context = current->audit_context; + const struct inode *inode = d_backing_inode(dentry); + const char *dname = dentry->d_name.name; + struct audit_names *n, *found_parent = NULL, *found_child = NULL; + + if (!context->in_syscall) + return; + + if (inode) + handle_one(inode); + + /* look for a parent entry first */ + list_for_each_entry(n, &context->names_list, list) { + if (!n->name || + (n->type != AUDIT_TYPE_PARENT && + n->type != AUDIT_TYPE_UNKNOWN)) + continue; + + if (n->ino == parent->i_ino && n->dev == parent->i_sb->s_dev && + !audit_compare_dname_path(dname, + n->name->name, n->name_len)) { + if (n->type == AUDIT_TYPE_UNKNOWN) + n->type = AUDIT_TYPE_PARENT; + found_parent = n; + break; + } + } + + /* is there a matching child entry? */ + list_for_each_entry(n, &context->names_list, list) { + /* can only match entries that have a name */ + if (!n->name || + (n->type != type && n->type != AUDIT_TYPE_UNKNOWN)) + continue; + + if (!strcmp(dname, n->name->name) || + !audit_compare_dname_path(dname, n->name->name, + found_parent ? + found_parent->name_len : + AUDIT_NAME_FULL)) { + if (n->type == AUDIT_TYPE_UNKNOWN) + n->type = type; + found_child = n; + break; + } + } + + if (!found_parent) { + /* create a new, "anonymous" parent record */ + n = audit_alloc_name(context, AUDIT_TYPE_PARENT); + if (!n) + return; + audit_copy_inode(n, NULL, parent); + } + + if (!found_child) { + found_child = audit_alloc_name(context, type); + if (!found_child) + return; + + /* Re-use the name belonging to the slot for a matching parent + * directory. All names for this context are relinquished in + * audit_free_names() */ + if (found_parent) { + found_child->name = found_parent->name; + found_child->name_len = AUDIT_NAME_FULL; + found_child->name->refcnt++; + } + } + + if (inode) + audit_copy_inode(found_child, dentry, inode); + else + found_child->ino = (unsigned long)-1; +} +EXPORT_SYMBOL_GPL(__audit_inode_child); + +/** + * auditsc_get_stamp - get local copies of audit_context values + * @ctx: audit_context for the task + * @t: timespec to store time recorded in the audit_context + * @serial: serial value that is recorded in the audit_context + * + * Also sets the context as auditable. + */ +int auditsc_get_stamp(struct audit_context *ctx, + struct timespec *t, unsigned int *serial) +{ + if (!ctx->in_syscall) + return 0; + if (!ctx->serial) + ctx->serial = audit_serial(); + t->tv_sec = ctx->ctime.tv_sec; + t->tv_nsec = ctx->ctime.tv_nsec; + *serial = ctx->serial; + if (!ctx->prio) { + ctx->prio = 1; + ctx->current_state = AUDIT_RECORD_CONTEXT; + } + return 1; +} + +/* global counter which is incremented every time something logs in */ +static atomic_t session_id = ATOMIC_INIT(0); + +static int audit_set_loginuid_perm(kuid_t loginuid) +{ + /* if we are unset, we don't need privs */ + if (!audit_loginuid_set(current)) + return 0; + /* if AUDIT_FEATURE_LOGINUID_IMMUTABLE means never ever allow a change*/ + if (is_audit_feature_set(AUDIT_FEATURE_LOGINUID_IMMUTABLE)) + return -EPERM; + /* it is set, you need permission */ + if (!capable(CAP_AUDIT_CONTROL)) + return -EPERM; + /* reject if this is not an unset and we don't allow that */ + if (is_audit_feature_set(AUDIT_FEATURE_ONLY_UNSET_LOGINUID) && uid_valid(loginuid)) + return -EPERM; + return 0; +} + +static void audit_log_set_loginuid(kuid_t koldloginuid, kuid_t kloginuid, + unsigned int oldsessionid, unsigned int sessionid, + int rc) +{ + struct audit_buffer *ab; + uid_t uid, oldloginuid, loginuid; + + if (!audit_enabled) + return; + + uid = from_kuid(&init_user_ns, task_uid(current)); + oldloginuid = from_kuid(&init_user_ns, koldloginuid); + loginuid = from_kuid(&init_user_ns, kloginuid), + + ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_LOGIN); + if (!ab) + return; + audit_log_format(ab, "pid=%d uid=%u", task_pid_nr(current), uid); + audit_log_task_context(ab); + audit_log_format(ab, " old-auid=%u auid=%u old-ses=%u ses=%u res=%d", + oldloginuid, loginuid, oldsessionid, sessionid, !rc); + audit_log_end(ab); +} + +/** + * audit_set_loginuid - set current task's audit_context loginuid + * @loginuid: loginuid value + * + * Returns 0. + * + * Called (set) from fs/proc/base.c::proc_loginuid_write(). + */ +int audit_set_loginuid(kuid_t loginuid) +{ + struct task_struct *task = current; + unsigned int oldsessionid, sessionid = (unsigned int)-1; + kuid_t oldloginuid; + int rc; + + oldloginuid = audit_get_loginuid(current); + oldsessionid = audit_get_sessionid(current); + + rc = audit_set_loginuid_perm(loginuid); + if (rc) + goto out; + + /* are we setting or clearing? */ + if (uid_valid(loginuid)) + sessionid = (unsigned int)atomic_inc_return(&session_id); + + task->sessionid = sessionid; + task->loginuid = loginuid; +out: + audit_log_set_loginuid(oldloginuid, loginuid, oldsessionid, sessionid, rc); + return rc; +} + +/** + * __audit_mq_open - record audit data for a POSIX MQ open + * @oflag: open flag + * @mode: mode bits + * @attr: queue attributes + * + */ +void __audit_mq_open(int oflag, umode_t mode, struct mq_attr *attr) +{ + struct audit_context *context = current->audit_context; + + if (attr) + memcpy(&context->mq_open.attr, attr, sizeof(struct mq_attr)); + else + memset(&context->mq_open.attr, 0, sizeof(struct mq_attr)); + + context->mq_open.oflag = oflag; + context->mq_open.mode = mode; + + context->type = AUDIT_MQ_OPEN; +} + +/** + * __audit_mq_sendrecv - record audit data for a POSIX MQ timed send/receive + * @mqdes: MQ descriptor + * @msg_len: Message length + * @msg_prio: Message priority + * @abs_timeout: Message timeout in absolute time + * + */ +void __audit_mq_sendrecv(mqd_t mqdes, size_t msg_len, unsigned int msg_prio, + const struct timespec *abs_timeout) +{ + struct audit_context *context = current->audit_context; + struct timespec *p = &context->mq_sendrecv.abs_timeout; + + if (abs_timeout) + memcpy(p, abs_timeout, sizeof(struct timespec)); + else + memset(p, 0, sizeof(struct timespec)); + + context->mq_sendrecv.mqdes = mqdes; + context->mq_sendrecv.msg_len = msg_len; + context->mq_sendrecv.msg_prio = msg_prio; + + context->type = AUDIT_MQ_SENDRECV; +} + +/** + * __audit_mq_notify - record audit data for a POSIX MQ notify + * @mqdes: MQ descriptor + * @notification: Notification event + * + */ + +void __audit_mq_notify(mqd_t mqdes, const struct sigevent *notification) +{ + struct audit_context *context = current->audit_context; + + if (notification) + context->mq_notify.sigev_signo = notification->sigev_signo; + else + context->mq_notify.sigev_signo = 0; + + context->mq_notify.mqdes = mqdes; + context->type = AUDIT_MQ_NOTIFY; +} + +/** + * __audit_mq_getsetattr - record audit data for a POSIX MQ get/set attribute + * @mqdes: MQ descriptor + * @mqstat: MQ flags + * + */ +void __audit_mq_getsetattr(mqd_t mqdes, struct mq_attr *mqstat) +{ + struct audit_context *context = current->audit_context; + context->mq_getsetattr.mqdes = mqdes; + context->mq_getsetattr.mqstat = *mqstat; + context->type = AUDIT_MQ_GETSETATTR; +} + +/** + * audit_ipc_obj - record audit data for ipc object + * @ipcp: ipc permissions + * + */ +void __audit_ipc_obj(struct kern_ipc_perm *ipcp) +{ + struct audit_context *context = current->audit_context; + context->ipc.uid = ipcp->uid; + context->ipc.gid = ipcp->gid; + context->ipc.mode = ipcp->mode; + context->ipc.has_perm = 0; + security_ipc_getsecid(ipcp, &context->ipc.osid); + context->type = AUDIT_IPC; +} + +/** + * audit_ipc_set_perm - record audit data for new ipc permissions + * @qbytes: msgq bytes + * @uid: msgq user id + * @gid: msgq group id + * @mode: msgq mode (permissions) + * + * Called only after audit_ipc_obj(). + */ +void __audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid, umode_t mode) +{ + struct audit_context *context = current->audit_context; + + context->ipc.qbytes = qbytes; + context->ipc.perm_uid = uid; + context->ipc.perm_gid = gid; + context->ipc.perm_mode = mode; + context->ipc.has_perm = 1; +} + +void __audit_bprm(struct linux_binprm *bprm) +{ + struct audit_context *context = current->audit_context; + + context->type = AUDIT_EXECVE; + context->execve.argc = bprm->argc; +} + + +/** + * audit_socketcall - record audit data for sys_socketcall + * @nargs: number of args, which should not be more than AUDITSC_ARGS. + * @args: args array + * + */ +int __audit_socketcall(int nargs, unsigned long *args) +{ + struct audit_context *context = current->audit_context; + + if (nargs <= 0 || nargs > AUDITSC_ARGS || !args) + return -EINVAL; + context->type = AUDIT_SOCKETCALL; + context->socketcall.nargs = nargs; + memcpy(context->socketcall.args, args, nargs * sizeof(unsigned long)); + return 0; +} + +/** + * __audit_fd_pair - record audit data for pipe and socketpair + * @fd1: the first file descriptor + * @fd2: the second file descriptor + * + */ +void __audit_fd_pair(int fd1, int fd2) +{ + struct audit_context *context = current->audit_context; + context->fds[0] = fd1; + context->fds[1] = fd2; +} + +/** + * audit_sockaddr - record audit data for sys_bind, sys_connect, sys_sendto + * @len: data length in user space + * @a: data address in kernel space + * + * Returns 0 for success or NULL context or < 0 on error. + */ +int __audit_sockaddr(int len, void *a) +{ + struct audit_context *context = current->audit_context; + + if (!context->sockaddr) { + void *p = kmalloc(sizeof(struct sockaddr_storage), GFP_KERNEL); + if (!p) + return -ENOMEM; + context->sockaddr = p; + } + + context->sockaddr_len = len; + memcpy(context->sockaddr, a, len); + return 0; +} + +void __audit_ptrace(struct task_struct *t) +{ + struct audit_context *context = current->audit_context; + + context->target_pid = task_pid_nr(t); + context->target_auid = audit_get_loginuid(t); + context->target_uid = task_uid(t); + context->target_sessionid = audit_get_sessionid(t); + security_task_getsecid(t, &context->target_sid); + memcpy(context->target_comm, t->comm, TASK_COMM_LEN); +} + +/** + * audit_signal_info - record signal info for shutting down audit subsystem + * @sig: signal value + * @t: task being signaled + * + * If the audit subsystem is being terminated, record the task (pid) + * and uid that is doing that. + */ +int __audit_signal_info(int sig, struct task_struct *t) +{ + struct audit_aux_data_pids *axp; + struct task_struct *tsk = current; + struct audit_context *ctx = tsk->audit_context; + kuid_t uid = current_uid(), t_uid = task_uid(t); + + if (audit_pid && t->tgid == audit_pid) { + if (sig == SIGTERM || sig == SIGHUP || sig == SIGUSR1 || sig == SIGUSR2) { + audit_sig_pid = task_pid_nr(tsk); + if (uid_valid(tsk->loginuid)) + audit_sig_uid = tsk->loginuid; + else + audit_sig_uid = uid; + security_task_getsecid(tsk, &audit_sig_sid); + } + if (!audit_signals || audit_dummy_context()) + return 0; + } + + /* optimize the common case by putting first signal recipient directly + * in audit_context */ + if (!ctx->target_pid) { + ctx->target_pid = task_tgid_nr(t); + ctx->target_auid = audit_get_loginuid(t); + ctx->target_uid = t_uid; + ctx->target_sessionid = audit_get_sessionid(t); + security_task_getsecid(t, &ctx->target_sid); + memcpy(ctx->target_comm, t->comm, TASK_COMM_LEN); + return 0; + } + + axp = (void *)ctx->aux_pids; + if (!axp || axp->pid_count == AUDIT_AUX_PIDS) { + axp = kzalloc(sizeof(*axp), GFP_ATOMIC); + if (!axp) + return -ENOMEM; + + axp->d.type = AUDIT_OBJ_PID; + axp->d.next = ctx->aux_pids; + ctx->aux_pids = (void *)axp; + } + BUG_ON(axp->pid_count >= AUDIT_AUX_PIDS); + + axp->target_pid[axp->pid_count] = task_tgid_nr(t); + axp->target_auid[axp->pid_count] = audit_get_loginuid(t); + axp->target_uid[axp->pid_count] = t_uid; + axp->target_sessionid[axp->pid_count] = audit_get_sessionid(t); + security_task_getsecid(t, &axp->target_sid[axp->pid_count]); + memcpy(axp->target_comm[axp->pid_count], t->comm, TASK_COMM_LEN); + axp->pid_count++; + + return 0; +} + +/** + * __audit_log_bprm_fcaps - store information about a loading bprm and relevant fcaps + * @bprm: pointer to the bprm being processed + * @new: the proposed new credentials + * @old: the old credentials + * + * Simply check if the proc already has the caps given by the file and if not + * store the priv escalation info for later auditing at the end of the syscall + * + * -Eric + */ +int __audit_log_bprm_fcaps(struct linux_binprm *bprm, + const struct cred *new, const struct cred *old) +{ + struct audit_aux_data_bprm_fcaps *ax; + struct audit_context *context = current->audit_context; + struct cpu_vfs_cap_data vcaps; + + ax = kmalloc(sizeof(*ax), GFP_KERNEL); + if (!ax) + return -ENOMEM; + + ax->d.type = AUDIT_BPRM_FCAPS; + ax->d.next = context->aux; + context->aux = (void *)ax; + + get_vfs_caps_from_disk(bprm->file->f_path.dentry, &vcaps); + + ax->fcap.permitted = vcaps.permitted; + ax->fcap.inheritable = vcaps.inheritable; + ax->fcap.fE = !!(vcaps.magic_etc & VFS_CAP_FLAGS_EFFECTIVE); + ax->fcap_ver = (vcaps.magic_etc & VFS_CAP_REVISION_MASK) >> VFS_CAP_REVISION_SHIFT; + + ax->old_pcap.permitted = old->cap_permitted; + ax->old_pcap.inheritable = old->cap_inheritable; + ax->old_pcap.effective = old->cap_effective; + + ax->new_pcap.permitted = new->cap_permitted; + ax->new_pcap.inheritable = new->cap_inheritable; + ax->new_pcap.effective = new->cap_effective; + return 0; +} + +/** + * __audit_log_capset - store information about the arguments to the capset syscall + * @new: the new credentials + * @old: the old (current) credentials + * + * Record the arguments userspace sent to sys_capset for later printing by the + * audit system if applicable + */ +void __audit_log_capset(const struct cred *new, const struct cred *old) +{ + struct audit_context *context = current->audit_context; + context->capset.pid = task_pid_nr(current); + context->capset.cap.effective = new->cap_effective; + context->capset.cap.inheritable = new->cap_effective; + context->capset.cap.permitted = new->cap_permitted; + context->type = AUDIT_CAPSET; +} + +void __audit_mmap_fd(int fd, int flags) +{ + struct audit_context *context = current->audit_context; + context->mmap.fd = fd; + context->mmap.flags = flags; + context->type = AUDIT_MMAP; +} + +static void audit_log_task(struct audit_buffer *ab) +{ + kuid_t auid, uid; + kgid_t gid; + unsigned int sessionid; + char comm[sizeof(current->comm)]; + + auid = audit_get_loginuid(current); + sessionid = audit_get_sessionid(current); + current_uid_gid(&uid, &gid); + + audit_log_format(ab, "auid=%u uid=%u gid=%u ses=%u", + from_kuid(&init_user_ns, auid), + from_kuid(&init_user_ns, uid), + from_kgid(&init_user_ns, gid), + sessionid); + audit_log_task_context(ab); + audit_log_format(ab, " pid=%d comm=", task_pid_nr(current)); + audit_log_untrustedstring(ab, get_task_comm(comm, current)); + audit_log_d_path_exe(ab, current->mm); +} + +/** + * audit_core_dumps - record information about processes that end abnormally + * @signr: signal value + * + * If a process ends with a core dump, something fishy is going on and we + * should record the event for investigation. + */ +void audit_core_dumps(long signr) +{ + struct audit_buffer *ab; + + if (!audit_enabled) + return; + + if (signr == SIGQUIT) /* don't care for those */ + return; + + ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_ANOM_ABEND); + if (unlikely(!ab)) + return; + audit_log_task(ab); + audit_log_format(ab, " sig=%ld", signr); + audit_log_end(ab); +} + +void __audit_seccomp(unsigned long syscall, long signr, int code) +{ + struct audit_buffer *ab; + + ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_SECCOMP); + if (unlikely(!ab)) + return; + audit_log_task(ab); + audit_log_format(ab, " sig=%ld arch=%x syscall=%ld compat=%d ip=0x%lx code=0x%x", + signr, syscall_get_arch(), syscall, is_compat_task(), + KSTK_EIP(current), code); + audit_log_end(ab); +} + +struct list_head *audit_killed_trees(void) +{ + struct audit_context *ctx = current->audit_context; + if (likely(!ctx || !ctx->in_syscall)) + return NULL; + return &ctx->killed_trees; +} diff --git a/kernel/kernel/backtracetest.c b/kernel/kernel/backtracetest.c new file mode 100644 index 000000000..1323360d9 --- /dev/null +++ b/kernel/kernel/backtracetest.c @@ -0,0 +1,91 @@ +/* + * Simple stack backtrace regression test module + * + * (C) Copyright 2008 Intel Corporation + * Author: Arjan van de Ven + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; version 2 + * of the License. + */ + +#include +#include +#include +#include +#include +#include + +static void backtrace_test_normal(void) +{ + pr_info("Testing a backtrace from process context.\n"); + pr_info("The following trace is a kernel self test and not a bug!\n"); + + dump_stack(); +} + +static DECLARE_COMPLETION(backtrace_work); + +static void backtrace_test_irq_callback(unsigned long data) +{ + dump_stack(); + complete(&backtrace_work); +} + +static DECLARE_TASKLET(backtrace_tasklet, &backtrace_test_irq_callback, 0); + +static void backtrace_test_irq(void) +{ + pr_info("Testing a backtrace from irq context.\n"); + pr_info("The following trace is a kernel self test and not a bug!\n"); + + init_completion(&backtrace_work); + tasklet_schedule(&backtrace_tasklet); + wait_for_completion(&backtrace_work); +} + +#ifdef CONFIG_STACKTRACE +static void backtrace_test_saved(void) +{ + struct stack_trace trace; + unsigned long entries[8]; + + pr_info("Testing a saved backtrace.\n"); + pr_info("The following trace is a kernel self test and not a bug!\n"); + + trace.nr_entries = 0; + trace.max_entries = ARRAY_SIZE(entries); + trace.entries = entries; + trace.skip = 0; + + save_stack_trace(&trace); + print_stack_trace(&trace, 0); +} +#else +static void backtrace_test_saved(void) +{ + pr_info("Saved backtrace test skipped.\n"); +} +#endif + +static int backtrace_regression_test(void) +{ + pr_info("====[ backtrace testing ]===========\n"); + + backtrace_test_normal(); + backtrace_test_irq(); + backtrace_test_saved(); + + pr_info("====[ end of backtrace testing ]====\n"); + return 0; +} + +static void exitf(void) +{ +} + +module_init(backtrace_regression_test); +module_exit(exitf); +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Arjan van de Ven "); diff --git a/kernel/kernel/bounds.c b/kernel/kernel/bounds.c new file mode 100644 index 000000000..e1d1d1952 --- /dev/null +++ b/kernel/kernel/bounds.c @@ -0,0 +1,25 @@ +/* + * Generate definitions needed by the preprocessor. + * This code generates raw asm output which is post-processed + * to extract and format the required data. + */ + +#define __GENERATING_BOUNDS_H +/* Include headers that define the enum constants of interest */ +#include +#include +#include +#include +#include + +void foo(void) +{ + /* The enum constants to put into include/generated/bounds.h */ + DEFINE(NR_PAGEFLAGS, __NR_PAGEFLAGS); + DEFINE(MAX_NR_ZONES, __MAX_NR_ZONES); +#ifdef CONFIG_SMP + DEFINE(NR_CPUS_BITS, ilog2(CONFIG_NR_CPUS)); +#endif + DEFINE(SPINLOCK_SIZE, sizeof(spinlock_t)); + /* End of constants */ +} diff --git a/kernel/kernel/bpf/Makefile b/kernel/kernel/bpf/Makefile new file mode 100644 index 000000000..e6983be12 --- /dev/null +++ b/kernel/kernel/bpf/Makefile @@ -0,0 +1,2 @@ +obj-y := core.o +obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o hashtab.o arraymap.o helpers.o diff --git a/kernel/kernel/bpf/arraymap.c b/kernel/kernel/bpf/arraymap.c new file mode 100644 index 000000000..8a6616583 --- /dev/null +++ b/kernel/kernel/bpf/arraymap.c @@ -0,0 +1,156 @@ +/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + */ +#include +#include +#include +#include +#include + +struct bpf_array { + struct bpf_map map; + u32 elem_size; + char value[0] __aligned(8); +}; + +/* Called from syscall */ +static struct bpf_map *array_map_alloc(union bpf_attr *attr) +{ + struct bpf_array *array; + u32 elem_size, array_size; + + /* check sanity of attributes */ + if (attr->max_entries == 0 || attr->key_size != 4 || + attr->value_size == 0) + return ERR_PTR(-EINVAL); + + elem_size = round_up(attr->value_size, 8); + + /* check round_up into zero and u32 overflow */ + if (elem_size == 0 || + attr->max_entries > (U32_MAX - sizeof(*array)) / elem_size) + return ERR_PTR(-ENOMEM); + + array_size = sizeof(*array) + attr->max_entries * elem_size; + + /* allocate all map elements and zero-initialize them */ + array = kzalloc(array_size, GFP_USER | __GFP_NOWARN); + if (!array) { + array = vzalloc(array_size); + if (!array) + return ERR_PTR(-ENOMEM); + } + + /* copy mandatory map attributes */ + array->map.key_size = attr->key_size; + array->map.value_size = attr->value_size; + array->map.max_entries = attr->max_entries; + + array->elem_size = elem_size; + + return &array->map; +} + +/* Called from syscall or from eBPF program */ +static void *array_map_lookup_elem(struct bpf_map *map, void *key) +{ + struct bpf_array *array = container_of(map, struct bpf_array, map); + u32 index = *(u32 *)key; + + if (index >= array->map.max_entries) + return NULL; + + return array->value + array->elem_size * index; +} + +/* Called from syscall */ +static int array_map_get_next_key(struct bpf_map *map, void *key, void *next_key) +{ + struct bpf_array *array = container_of(map, struct bpf_array, map); + u32 index = *(u32 *)key; + u32 *next = (u32 *)next_key; + + if (index >= array->map.max_entries) { + *next = 0; + return 0; + } + + if (index == array->map.max_entries - 1) + return -ENOENT; + + *next = index + 1; + return 0; +} + +/* Called from syscall or from eBPF program */ +static int array_map_update_elem(struct bpf_map *map, void *key, void *value, + u64 map_flags) +{ + struct bpf_array *array = container_of(map, struct bpf_array, map); + u32 index = *(u32 *)key; + + if (map_flags > BPF_EXIST) + /* unknown flags */ + return -EINVAL; + + if (index >= array->map.max_entries) + /* all elements were pre-allocated, cannot insert a new one */ + return -E2BIG; + + if (map_flags == BPF_NOEXIST) + /* all elements already exist */ + return -EEXIST; + + memcpy(array->value + array->elem_size * index, value, array->elem_size); + return 0; +} + +/* Called from syscall or from eBPF program */ +static int array_map_delete_elem(struct bpf_map *map, void *key) +{ + return -EINVAL; +} + +/* Called when map->refcnt goes to zero, either from workqueue or from syscall */ +static void array_map_free(struct bpf_map *map) +{ + struct bpf_array *array = container_of(map, struct bpf_array, map); + + /* at this point bpf_prog->aux->refcnt == 0 and this map->refcnt == 0, + * so the programs (can be more than one that used this map) were + * disconnected from events. Wait for outstanding programs to complete + * and free the array + */ + synchronize_rcu(); + + kvfree(array); +} + +static const struct bpf_map_ops array_ops = { + .map_alloc = array_map_alloc, + .map_free = array_map_free, + .map_get_next_key = array_map_get_next_key, + .map_lookup_elem = array_map_lookup_elem, + .map_update_elem = array_map_update_elem, + .map_delete_elem = array_map_delete_elem, +}; + +static struct bpf_map_type_list array_type __read_mostly = { + .ops = &array_ops, + .type = BPF_MAP_TYPE_ARRAY, +}; + +static int __init register_array_map(void) +{ + bpf_register_map_type(&array_type); + return 0; +} +late_initcall(register_array_map); diff --git a/kernel/kernel/bpf/core.c b/kernel/kernel/bpf/core.c new file mode 100644 index 000000000..54f0e7fcd --- /dev/null +++ b/kernel/kernel/bpf/core.c @@ -0,0 +1,674 @@ +/* + * Linux Socket Filter - Kernel level socket filtering + * + * Based on the design of the Berkeley Packet Filter. The new + * internal format has been designed by PLUMgrid: + * + * Copyright (c) 2011 - 2014 PLUMgrid, http://plumgrid.com + * + * Authors: + * + * Jay Schulist + * Alexei Starovoitov + * Daniel Borkmann + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + * Andi Kleen - Fix a few bad bugs and races. + * Kris Katterjohn - Added many additional checks in bpf_check_classic() + */ + +#include +#include +#include +#include +#include +#include +#include + +/* Registers */ +#define BPF_R0 regs[BPF_REG_0] +#define BPF_R1 regs[BPF_REG_1] +#define BPF_R2 regs[BPF_REG_2] +#define BPF_R3 regs[BPF_REG_3] +#define BPF_R4 regs[BPF_REG_4] +#define BPF_R5 regs[BPF_REG_5] +#define BPF_R6 regs[BPF_REG_6] +#define BPF_R7 regs[BPF_REG_7] +#define BPF_R8 regs[BPF_REG_8] +#define BPF_R9 regs[BPF_REG_9] +#define BPF_R10 regs[BPF_REG_10] + +/* Named registers */ +#define DST regs[insn->dst_reg] +#define SRC regs[insn->src_reg] +#define FP regs[BPF_REG_FP] +#define ARG1 regs[BPF_REG_ARG1] +#define CTX regs[BPF_REG_CTX] +#define IMM insn->imm + +/* No hurry in this branch + * + * Exported for the bpf jit load helper. + */ +void *bpf_internal_load_pointer_neg_helper(const struct sk_buff *skb, int k, unsigned int size) +{ + u8 *ptr = NULL; + + if (k >= SKF_NET_OFF) + ptr = skb_network_header(skb) + k - SKF_NET_OFF; + else if (k >= SKF_LL_OFF) + ptr = skb_mac_header(skb) + k - SKF_LL_OFF; + if (ptr >= skb->head && ptr + size <= skb_tail_pointer(skb)) + return ptr; + + return NULL; +} + +struct bpf_prog *bpf_prog_alloc(unsigned int size, gfp_t gfp_extra_flags) +{ + gfp_t gfp_flags = GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO | + gfp_extra_flags; + struct bpf_prog_aux *aux; + struct bpf_prog *fp; + + size = round_up(size, PAGE_SIZE); + fp = __vmalloc(size, gfp_flags, PAGE_KERNEL); + if (fp == NULL) + return NULL; + + aux = kzalloc(sizeof(*aux), GFP_KERNEL | gfp_extra_flags); + if (aux == NULL) { + vfree(fp); + return NULL; + } + + fp->pages = size / PAGE_SIZE; + fp->aux = aux; + + return fp; +} +EXPORT_SYMBOL_GPL(bpf_prog_alloc); + +struct bpf_prog *bpf_prog_realloc(struct bpf_prog *fp_old, unsigned int size, + gfp_t gfp_extra_flags) +{ + gfp_t gfp_flags = GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO | + gfp_extra_flags; + struct bpf_prog *fp; + + BUG_ON(fp_old == NULL); + + size = round_up(size, PAGE_SIZE); + if (size <= fp_old->pages * PAGE_SIZE) + return fp_old; + + fp = __vmalloc(size, gfp_flags, PAGE_KERNEL); + if (fp != NULL) { + memcpy(fp, fp_old, fp_old->pages * PAGE_SIZE); + fp->pages = size / PAGE_SIZE; + + /* We keep fp->aux from fp_old around in the new + * reallocated structure. + */ + fp_old->aux = NULL; + __bpf_prog_free(fp_old); + } + + return fp; +} +EXPORT_SYMBOL_GPL(bpf_prog_realloc); + +void __bpf_prog_free(struct bpf_prog *fp) +{ + kfree(fp->aux); + vfree(fp); +} +EXPORT_SYMBOL_GPL(__bpf_prog_free); + +#ifdef CONFIG_BPF_JIT +struct bpf_binary_header * +bpf_jit_binary_alloc(unsigned int proglen, u8 **image_ptr, + unsigned int alignment, + bpf_jit_fill_hole_t bpf_fill_ill_insns) +{ + struct bpf_binary_header *hdr; + unsigned int size, hole, start; + + /* Most of BPF filters are really small, but if some of them + * fill a page, allow at least 128 extra bytes to insert a + * random section of illegal instructions. + */ + size = round_up(proglen + sizeof(*hdr) + 128, PAGE_SIZE); + hdr = module_alloc(size); + if (hdr == NULL) + return NULL; + + /* Fill space with illegal/arch-dep instructions. */ + bpf_fill_ill_insns(hdr, size); + + hdr->pages = size / PAGE_SIZE; + hole = min_t(unsigned int, size - (proglen + sizeof(*hdr)), + PAGE_SIZE - sizeof(*hdr)); + start = (prandom_u32() % hole) & ~(alignment - 1); + + /* Leave a random number of instructions before BPF code. */ + *image_ptr = &hdr->image[start]; + + return hdr; +} + +void bpf_jit_binary_free(struct bpf_binary_header *hdr) +{ + module_memfree(hdr); +} +#endif /* CONFIG_BPF_JIT */ + +/* Base function for offset calculation. Needs to go into .text section, + * therefore keeping it non-static as well; will also be used by JITs + * anyway later on, so do not let the compiler omit it. + */ +noinline u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) +{ + return 0; +} + +/** + * __bpf_prog_run - run eBPF program on a given context + * @ctx: is the data we are operating on + * @insn: is the array of eBPF instructions + * + * Decode and execute eBPF instructions. + */ +static unsigned int __bpf_prog_run(void *ctx, const struct bpf_insn *insn) +{ + u64 stack[MAX_BPF_STACK / sizeof(u64)]; + u64 regs[MAX_BPF_REG], tmp; + static const void *jumptable[256] = { + [0 ... 255] = &&default_label, + /* Now overwrite non-defaults ... */ + /* 32 bit ALU operations */ + [BPF_ALU | BPF_ADD | BPF_X] = &&ALU_ADD_X, + [BPF_ALU | BPF_ADD | BPF_K] = &&ALU_ADD_K, + [BPF_ALU | BPF_SUB | BPF_X] = &&ALU_SUB_X, + [BPF_ALU | BPF_SUB | BPF_K] = &&ALU_SUB_K, + [BPF_ALU | BPF_AND | BPF_X] = &&ALU_AND_X, + [BPF_ALU | BPF_AND | BPF_K] = &&ALU_AND_K, + [BPF_ALU | BPF_OR | BPF_X] = &&ALU_OR_X, + [BPF_ALU | BPF_OR | BPF_K] = &&ALU_OR_K, + [BPF_ALU | BPF_LSH | BPF_X] = &&ALU_LSH_X, + [BPF_ALU | BPF_LSH | BPF_K] = &&ALU_LSH_K, + [BPF_ALU | BPF_RSH | BPF_X] = &&ALU_RSH_X, + [BPF_ALU | BPF_RSH | BPF_K] = &&ALU_RSH_K, + [BPF_ALU | BPF_XOR | BPF_X] = &&ALU_XOR_X, + [BPF_ALU | BPF_XOR | BPF_K] = &&ALU_XOR_K, + [BPF_ALU | BPF_MUL | BPF_X] = &&ALU_MUL_X, + [BPF_ALU | BPF_MUL | BPF_K] = &&ALU_MUL_K, + [BPF_ALU | BPF_MOV | BPF_X] = &&ALU_MOV_X, + [BPF_ALU | BPF_MOV | BPF_K] = &&ALU_MOV_K, + [BPF_ALU | BPF_DIV | BPF_X] = &&ALU_DIV_X, + [BPF_ALU | BPF_DIV | BPF_K] = &&ALU_DIV_K, + [BPF_ALU | BPF_MOD | BPF_X] = &&ALU_MOD_X, + [BPF_ALU | BPF_MOD | BPF_K] = &&ALU_MOD_K, + [BPF_ALU | BPF_NEG] = &&ALU_NEG, + [BPF_ALU | BPF_END | BPF_TO_BE] = &&ALU_END_TO_BE, + [BPF_ALU | BPF_END | BPF_TO_LE] = &&ALU_END_TO_LE, + /* 64 bit ALU operations */ + [BPF_ALU64 | BPF_ADD | BPF_X] = &&ALU64_ADD_X, + [BPF_ALU64 | BPF_ADD | BPF_K] = &&ALU64_ADD_K, + [BPF_ALU64 | BPF_SUB | BPF_X] = &&ALU64_SUB_X, + [BPF_ALU64 | BPF_SUB | BPF_K] = &&ALU64_SUB_K, + [BPF_ALU64 | BPF_AND | BPF_X] = &&ALU64_AND_X, + [BPF_ALU64 | BPF_AND | BPF_K] = &&ALU64_AND_K, + [BPF_ALU64 | BPF_OR | BPF_X] = &&ALU64_OR_X, + [BPF_ALU64 | BPF_OR | BPF_K] = &&ALU64_OR_K, + [BPF_ALU64 | BPF_LSH | BPF_X] = &&ALU64_LSH_X, + [BPF_ALU64 | BPF_LSH | BPF_K] = &&ALU64_LSH_K, + [BPF_ALU64 | BPF_RSH | BPF_X] = &&ALU64_RSH_X, + [BPF_ALU64 | BPF_RSH | BPF_K] = &&ALU64_RSH_K, + [BPF_ALU64 | BPF_XOR | BPF_X] = &&ALU64_XOR_X, + [BPF_ALU64 | BPF_XOR | BPF_K] = &&ALU64_XOR_K, + [BPF_ALU64 | BPF_MUL | BPF_X] = &&ALU64_MUL_X, + [BPF_ALU64 | BPF_MUL | BPF_K] = &&ALU64_MUL_K, + [BPF_ALU64 | BPF_MOV | BPF_X] = &&ALU64_MOV_X, + [BPF_ALU64 | BPF_MOV | BPF_K] = &&ALU64_MOV_K, + [BPF_ALU64 | BPF_ARSH | BPF_X] = &&ALU64_ARSH_X, + [BPF_ALU64 | BPF_ARSH | BPF_K] = &&ALU64_ARSH_K, + [BPF_ALU64 | BPF_DIV | BPF_X] = &&ALU64_DIV_X, + [BPF_ALU64 | BPF_DIV | BPF_K] = &&ALU64_DIV_K, + [BPF_ALU64 | BPF_MOD | BPF_X] = &&ALU64_MOD_X, + [BPF_ALU64 | BPF_MOD | BPF_K] = &&ALU64_MOD_K, + [BPF_ALU64 | BPF_NEG] = &&ALU64_NEG, + /* Call instruction */ + [BPF_JMP | BPF_CALL] = &&JMP_CALL, + /* Jumps */ + [BPF_JMP | BPF_JA] = &&JMP_JA, + [BPF_JMP | BPF_JEQ | BPF_X] = &&JMP_JEQ_X, + [BPF_JMP | BPF_JEQ | BPF_K] = &&JMP_JEQ_K, + [BPF_JMP | BPF_JNE | BPF_X] = &&JMP_JNE_X, + [BPF_JMP | BPF_JNE | BPF_K] = &&JMP_JNE_K, + [BPF_JMP | BPF_JGT | BPF_X] = &&JMP_JGT_X, + [BPF_JMP | BPF_JGT | BPF_K] = &&JMP_JGT_K, + [BPF_JMP | BPF_JGE | BPF_X] = &&JMP_JGE_X, + [BPF_JMP | BPF_JGE | BPF_K] = &&JMP_JGE_K, + [BPF_JMP | BPF_JSGT | BPF_X] = &&JMP_JSGT_X, + [BPF_JMP | BPF_JSGT | BPF_K] = &&JMP_JSGT_K, + [BPF_JMP | BPF_JSGE | BPF_X] = &&JMP_JSGE_X, + [BPF_JMP | BPF_JSGE | BPF_K] = &&JMP_JSGE_K, + [BPF_JMP | BPF_JSET | BPF_X] = &&JMP_JSET_X, + [BPF_JMP | BPF_JSET | BPF_K] = &&JMP_JSET_K, + /* Program return */ + [BPF_JMP | BPF_EXIT] = &&JMP_EXIT, + /* Store instructions */ + [BPF_STX | BPF_MEM | BPF_B] = &&STX_MEM_B, + [BPF_STX | BPF_MEM | BPF_H] = &&STX_MEM_H, + [BPF_STX | BPF_MEM | BPF_W] = &&STX_MEM_W, + [BPF_STX | BPF_MEM | BPF_DW] = &&STX_MEM_DW, + [BPF_STX | BPF_XADD | BPF_W] = &&STX_XADD_W, + [BPF_STX | BPF_XADD | BPF_DW] = &&STX_XADD_DW, + [BPF_ST | BPF_MEM | BPF_B] = &&ST_MEM_B, + [BPF_ST | BPF_MEM | BPF_H] = &&ST_MEM_H, + [BPF_ST | BPF_MEM | BPF_W] = &&ST_MEM_W, + [BPF_ST | BPF_MEM | BPF_DW] = &&ST_MEM_DW, + /* Load instructions */ + [BPF_LDX | BPF_MEM | BPF_B] = &&LDX_MEM_B, + [BPF_LDX | BPF_MEM | BPF_H] = &&LDX_MEM_H, + [BPF_LDX | BPF_MEM | BPF_W] = &&LDX_MEM_W, + [BPF_LDX | BPF_MEM | BPF_DW] = &&LDX_MEM_DW, + [BPF_LD | BPF_ABS | BPF_W] = &&LD_ABS_W, + [BPF_LD | BPF_ABS | BPF_H] = &&LD_ABS_H, + [BPF_LD | BPF_ABS | BPF_B] = &&LD_ABS_B, + [BPF_LD | BPF_IND | BPF_W] = &&LD_IND_W, + [BPF_LD | BPF_IND | BPF_H] = &&LD_IND_H, + [BPF_LD | BPF_IND | BPF_B] = &&LD_IND_B, + [BPF_LD | BPF_IMM | BPF_DW] = &&LD_IMM_DW, + }; + void *ptr; + int off; + +#define CONT ({ insn++; goto select_insn; }) +#define CONT_JMP ({ insn++; goto select_insn; }) + + FP = (u64) (unsigned long) &stack[ARRAY_SIZE(stack)]; + ARG1 = (u64) (unsigned long) ctx; + + /* Registers used in classic BPF programs need to be reset first. */ + regs[BPF_REG_A] = 0; + regs[BPF_REG_X] = 0; + +select_insn: + goto *jumptable[insn->code]; + + /* ALU */ +#define ALU(OPCODE, OP) \ + ALU64_##OPCODE##_X: \ + DST = DST OP SRC; \ + CONT; \ + ALU_##OPCODE##_X: \ + DST = (u32) DST OP (u32) SRC; \ + CONT; \ + ALU64_##OPCODE##_K: \ + DST = DST OP IMM; \ + CONT; \ + ALU_##OPCODE##_K: \ + DST = (u32) DST OP (u32) IMM; \ + CONT; + + ALU(ADD, +) + ALU(SUB, -) + ALU(AND, &) + ALU(OR, |) + ALU(LSH, <<) + ALU(RSH, >>) + ALU(XOR, ^) + ALU(MUL, *) +#undef ALU + ALU_NEG: + DST = (u32) -DST; + CONT; + ALU64_NEG: + DST = -DST; + CONT; + ALU_MOV_X: + DST = (u32) SRC; + CONT; + ALU_MOV_K: + DST = (u32) IMM; + CONT; + ALU64_MOV_X: + DST = SRC; + CONT; + ALU64_MOV_K: + DST = IMM; + CONT; + LD_IMM_DW: + DST = (u64) (u32) insn[0].imm | ((u64) (u32) insn[1].imm) << 32; + insn++; + CONT; + ALU64_ARSH_X: + (*(s64 *) &DST) >>= SRC; + CONT; + ALU64_ARSH_K: + (*(s64 *) &DST) >>= IMM; + CONT; + ALU64_MOD_X: + if (unlikely(SRC == 0)) + return 0; + div64_u64_rem(DST, SRC, &tmp); + DST = tmp; + CONT; + ALU_MOD_X: + if (unlikely(SRC == 0)) + return 0; + tmp = (u32) DST; + DST = do_div(tmp, (u32) SRC); + CONT; + ALU64_MOD_K: + div64_u64_rem(DST, IMM, &tmp); + DST = tmp; + CONT; + ALU_MOD_K: + tmp = (u32) DST; + DST = do_div(tmp, (u32) IMM); + CONT; + ALU64_DIV_X: + if (unlikely(SRC == 0)) + return 0; + DST = div64_u64(DST, SRC); + CONT; + ALU_DIV_X: + if (unlikely(SRC == 0)) + return 0; + tmp = (u32) DST; + do_div(tmp, (u32) SRC); + DST = (u32) tmp; + CONT; + ALU64_DIV_K: + DST = div64_u64(DST, IMM); + CONT; + ALU_DIV_K: + tmp = (u32) DST; + do_div(tmp, (u32) IMM); + DST = (u32) tmp; + CONT; + ALU_END_TO_BE: + switch (IMM) { + case 16: + DST = (__force u16) cpu_to_be16(DST); + break; + case 32: + DST = (__force u32) cpu_to_be32(DST); + break; + case 64: + DST = (__force u64) cpu_to_be64(DST); + break; + } + CONT; + ALU_END_TO_LE: + switch (IMM) { + case 16: + DST = (__force u16) cpu_to_le16(DST); + break; + case 32: + DST = (__force u32) cpu_to_le32(DST); + break; + case 64: + DST = (__force u64) cpu_to_le64(DST); + break; + } + CONT; + + /* CALL */ + JMP_CALL: + /* Function call scratches BPF_R1-BPF_R5 registers, + * preserves BPF_R6-BPF_R9, and stores return value + * into BPF_R0. + */ + BPF_R0 = (__bpf_call_base + insn->imm)(BPF_R1, BPF_R2, BPF_R3, + BPF_R4, BPF_R5); + CONT; + + /* JMP */ + JMP_JA: + insn += insn->off; + CONT; + JMP_JEQ_X: + if (DST == SRC) { + insn += insn->off; + CONT_JMP; + } + CONT; + JMP_JEQ_K: + if (DST == IMM) { + insn += insn->off; + CONT_JMP; + } + CONT; + JMP_JNE_X: + if (DST != SRC) { + insn += insn->off; + CONT_JMP; + } + CONT; + JMP_JNE_K: + if (DST != IMM) { + insn += insn->off; + CONT_JMP; + } + CONT; + JMP_JGT_X: + if (DST > SRC) { + insn += insn->off; + CONT_JMP; + } + CONT; + JMP_JGT_K: + if (DST > IMM) { + insn += insn->off; + CONT_JMP; + } + CONT; + JMP_JGE_X: + if (DST >= SRC) { + insn += insn->off; + CONT_JMP; + } + CONT; + JMP_JGE_K: + if (DST >= IMM) { + insn += insn->off; + CONT_JMP; + } + CONT; + JMP_JSGT_X: + if (((s64) DST) > ((s64) SRC)) { + insn += insn->off; + CONT_JMP; + } + CONT; + JMP_JSGT_K: + if (((s64) DST) > ((s64) IMM)) { + insn += insn->off; + CONT_JMP; + } + CONT; + JMP_JSGE_X: + if (((s64) DST) >= ((s64) SRC)) { + insn += insn->off; + CONT_JMP; + } + CONT; + JMP_JSGE_K: + if (((s64) DST) >= ((s64) IMM)) { + insn += insn->off; + CONT_JMP; + } + CONT; + JMP_JSET_X: + if (DST & SRC) { + insn += insn->off; + CONT_JMP; + } + CONT; + JMP_JSET_K: + if (DST & IMM) { + insn += insn->off; + CONT_JMP; + } + CONT; + JMP_EXIT: + return BPF_R0; + + /* STX and ST and LDX*/ +#define LDST(SIZEOP, SIZE) \ + STX_MEM_##SIZEOP: \ + *(SIZE *)(unsigned long) (DST + insn->off) = SRC; \ + CONT; \ + ST_MEM_##SIZEOP: \ + *(SIZE *)(unsigned long) (DST + insn->off) = IMM; \ + CONT; \ + LDX_MEM_##SIZEOP: \ + DST = *(SIZE *)(unsigned long) (SRC + insn->off); \ + CONT; + + LDST(B, u8) + LDST(H, u16) + LDST(W, u32) + LDST(DW, u64) +#undef LDST + STX_XADD_W: /* lock xadd *(u32 *)(dst_reg + off16) += src_reg */ + atomic_add((u32) SRC, (atomic_t *)(unsigned long) + (DST + insn->off)); + CONT; + STX_XADD_DW: /* lock xadd *(u64 *)(dst_reg + off16) += src_reg */ + atomic64_add((u64) SRC, (atomic64_t *)(unsigned long) + (DST + insn->off)); + CONT; + LD_ABS_W: /* BPF_R0 = ntohl(*(u32 *) (skb->data + imm32)) */ + off = IMM; +load_word: + /* BPF_LD + BPD_ABS and BPF_LD + BPF_IND insns are + * only appearing in the programs where ctx == + * skb. All programs keep 'ctx' in regs[BPF_REG_CTX] + * == BPF_R6, bpf_convert_filter() saves it in BPF_R6, + * internal BPF verifier will check that BPF_R6 == + * ctx. + * + * BPF_ABS and BPF_IND are wrappers of function calls, + * so they scratch BPF_R1-BPF_R5 registers, preserve + * BPF_R6-BPF_R9, and store return value into BPF_R0. + * + * Implicit input: + * ctx == skb == BPF_R6 == CTX + * + * Explicit input: + * SRC == any register + * IMM == 32-bit immediate + * + * Output: + * BPF_R0 - 8/16/32-bit skb data converted to cpu endianness + */ + + ptr = bpf_load_pointer((struct sk_buff *) (unsigned long) CTX, off, 4, &tmp); + if (likely(ptr != NULL)) { + BPF_R0 = get_unaligned_be32(ptr); + CONT; + } + + return 0; + LD_ABS_H: /* BPF_R0 = ntohs(*(u16 *) (skb->data + imm32)) */ + off = IMM; +load_half: + ptr = bpf_load_pointer((struct sk_buff *) (unsigned long) CTX, off, 2, &tmp); + if (likely(ptr != NULL)) { + BPF_R0 = get_unaligned_be16(ptr); + CONT; + } + + return 0; + LD_ABS_B: /* BPF_R0 = *(u8 *) (skb->data + imm32) */ + off = IMM; +load_byte: + ptr = bpf_load_pointer((struct sk_buff *) (unsigned long) CTX, off, 1, &tmp); + if (likely(ptr != NULL)) { + BPF_R0 = *(u8 *)ptr; + CONT; + } + + return 0; + LD_IND_W: /* BPF_R0 = ntohl(*(u32 *) (skb->data + src_reg + imm32)) */ + off = IMM + SRC; + goto load_word; + LD_IND_H: /* BPF_R0 = ntohs(*(u16 *) (skb->data + src_reg + imm32)) */ + off = IMM + SRC; + goto load_half; + LD_IND_B: /* BPF_R0 = *(u8 *) (skb->data + src_reg + imm32) */ + off = IMM + SRC; + goto load_byte; + + default_label: + /* If we ever reach this, we have a bug somewhere. */ + WARN_RATELIMIT(1, "unknown opcode %02x\n", insn->code); + return 0; +} + +void __weak bpf_int_jit_compile(struct bpf_prog *prog) +{ +} + +/** + * bpf_prog_select_runtime - select execution runtime for BPF program + * @fp: bpf_prog populated with internal BPF program + * + * try to JIT internal BPF program, if JIT is not available select interpreter + * BPF program will be executed via BPF_PROG_RUN() macro + */ +void bpf_prog_select_runtime(struct bpf_prog *fp) +{ + fp->bpf_func = (void *) __bpf_prog_run; + + /* Probe if internal BPF can be JITed */ + bpf_int_jit_compile(fp); + /* Lock whole bpf_prog as read-only */ + bpf_prog_lock_ro(fp); +} +EXPORT_SYMBOL_GPL(bpf_prog_select_runtime); + +static void bpf_prog_free_deferred(struct work_struct *work) +{ + struct bpf_prog_aux *aux; + + aux = container_of(work, struct bpf_prog_aux, work); + bpf_jit_free(aux->prog); +} + +/* Free internal BPF program */ +void bpf_prog_free(struct bpf_prog *fp) +{ + struct bpf_prog_aux *aux = fp->aux; + + INIT_WORK(&aux->work, bpf_prog_free_deferred); + aux->prog = fp; + schedule_work(&aux->work); +} +EXPORT_SYMBOL_GPL(bpf_prog_free); + +/* Weak definitions of helper functions in case we don't have bpf syscall. */ +const struct bpf_func_proto bpf_map_lookup_elem_proto __weak; +const struct bpf_func_proto bpf_map_update_elem_proto __weak; +const struct bpf_func_proto bpf_map_delete_elem_proto __weak; + +const struct bpf_func_proto bpf_get_prandom_u32_proto __weak; +const struct bpf_func_proto bpf_get_smp_processor_id_proto __weak; + +/* To execute LD_ABS/LD_IND instructions __bpf_prog_run() may call + * skb_copy_bits(), so provide a weak definition of it for NET-less config. + */ +int __weak skb_copy_bits(const struct sk_buff *skb, int offset, void *to, + int len) +{ + return -EFAULT; +} diff --git a/kernel/kernel/bpf/hashtab.c b/kernel/kernel/bpf/hashtab.c new file mode 100644 index 000000000..83c209d9b --- /dev/null +++ b/kernel/kernel/bpf/hashtab.c @@ -0,0 +1,367 @@ +/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + */ +#include +#include +#include +#include + +struct bpf_htab { + struct bpf_map map; + struct hlist_head *buckets; + spinlock_t lock; + u32 count; /* number of elements in this hashtable */ + u32 n_buckets; /* number of hash buckets */ + u32 elem_size; /* size of each element in bytes */ +}; + +/* each htab element is struct htab_elem + key + value */ +struct htab_elem { + struct hlist_node hash_node; + struct rcu_head rcu; + u32 hash; + char key[0] __aligned(8); +}; + +/* Called from syscall */ +static struct bpf_map *htab_map_alloc(union bpf_attr *attr) +{ + struct bpf_htab *htab; + int err, i; + + htab = kzalloc(sizeof(*htab), GFP_USER); + if (!htab) + return ERR_PTR(-ENOMEM); + + /* mandatory map attributes */ + htab->map.key_size = attr->key_size; + htab->map.value_size = attr->value_size; + htab->map.max_entries = attr->max_entries; + + /* check sanity of attributes. + * value_size == 0 may be allowed in the future to use map as a set + */ + err = -EINVAL; + if (htab->map.max_entries == 0 || htab->map.key_size == 0 || + htab->map.value_size == 0) + goto free_htab; + + /* hash table size must be power of 2 */ + htab->n_buckets = roundup_pow_of_two(htab->map.max_entries); + + err = -E2BIG; + if (htab->map.key_size > MAX_BPF_STACK) + /* eBPF programs initialize keys on stack, so they cannot be + * larger than max stack size + */ + goto free_htab; + + err = -ENOMEM; + /* prevent zero size kmalloc and check for u32 overflow */ + if (htab->n_buckets == 0 || + htab->n_buckets > U32_MAX / sizeof(struct hlist_head)) + goto free_htab; + + htab->buckets = kmalloc_array(htab->n_buckets, sizeof(struct hlist_head), + GFP_USER | __GFP_NOWARN); + + if (!htab->buckets) { + htab->buckets = vmalloc(htab->n_buckets * sizeof(struct hlist_head)); + if (!htab->buckets) + goto free_htab; + } + + for (i = 0; i < htab->n_buckets; i++) + INIT_HLIST_HEAD(&htab->buckets[i]); + + spin_lock_init(&htab->lock); + htab->count = 0; + + htab->elem_size = sizeof(struct htab_elem) + + round_up(htab->map.key_size, 8) + + htab->map.value_size; + return &htab->map; + +free_htab: + kfree(htab); + return ERR_PTR(err); +} + +static inline u32 htab_map_hash(const void *key, u32 key_len) +{ + return jhash(key, key_len, 0); +} + +static inline struct hlist_head *select_bucket(struct bpf_htab *htab, u32 hash) +{ + return &htab->buckets[hash & (htab->n_buckets - 1)]; +} + +static struct htab_elem *lookup_elem_raw(struct hlist_head *head, u32 hash, + void *key, u32 key_size) +{ + struct htab_elem *l; + + hlist_for_each_entry_rcu(l, head, hash_node) + if (l->hash == hash && !memcmp(&l->key, key, key_size)) + return l; + + return NULL; +} + +/* Called from syscall or from eBPF program */ +static void *htab_map_lookup_elem(struct bpf_map *map, void *key) +{ + struct bpf_htab *htab = container_of(map, struct bpf_htab, map); + struct hlist_head *head; + struct htab_elem *l; + u32 hash, key_size; + + /* Must be called with rcu_read_lock. */ + WARN_ON_ONCE(!rcu_read_lock_held()); + + key_size = map->key_size; + + hash = htab_map_hash(key, key_size); + + head = select_bucket(htab, hash); + + l = lookup_elem_raw(head, hash, key, key_size); + + if (l) + return l->key + round_up(map->key_size, 8); + + return NULL; +} + +/* Called from syscall */ +static int htab_map_get_next_key(struct bpf_map *map, void *key, void *next_key) +{ + struct bpf_htab *htab = container_of(map, struct bpf_htab, map); + struct hlist_head *head; + struct htab_elem *l, *next_l; + u32 hash, key_size; + int i; + + WARN_ON_ONCE(!rcu_read_lock_held()); + + key_size = map->key_size; + + hash = htab_map_hash(key, key_size); + + head = select_bucket(htab, hash); + + /* lookup the key */ + l = lookup_elem_raw(head, hash, key, key_size); + + if (!l) { + i = 0; + goto find_first_elem; + } + + /* key was found, get next key in the same bucket */ + next_l = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu(&l->hash_node)), + struct htab_elem, hash_node); + + if (next_l) { + /* if next elem in this hash list is non-zero, just return it */ + memcpy(next_key, next_l->key, key_size); + return 0; + } + + /* no more elements in this hash list, go to the next bucket */ + i = hash & (htab->n_buckets - 1); + i++; + +find_first_elem: + /* iterate over buckets */ + for (; i < htab->n_buckets; i++) { + head = select_bucket(htab, i); + + /* pick first element in the bucket */ + next_l = hlist_entry_safe(rcu_dereference_raw(hlist_first_rcu(head)), + struct htab_elem, hash_node); + if (next_l) { + /* if it's not empty, just return it */ + memcpy(next_key, next_l->key, key_size); + return 0; + } + } + + /* itereated over all buckets and all elements */ + return -ENOENT; +} + +/* Called from syscall or from eBPF program */ +static int htab_map_update_elem(struct bpf_map *map, void *key, void *value, + u64 map_flags) +{ + struct bpf_htab *htab = container_of(map, struct bpf_htab, map); + struct htab_elem *l_new, *l_old; + struct hlist_head *head; + unsigned long flags; + u32 key_size; + int ret; + + if (map_flags > BPF_EXIST) + /* unknown flags */ + return -EINVAL; + + WARN_ON_ONCE(!rcu_read_lock_held()); + + /* allocate new element outside of lock */ + l_new = kmalloc(htab->elem_size, GFP_ATOMIC); + if (!l_new) + return -ENOMEM; + + key_size = map->key_size; + + memcpy(l_new->key, key, key_size); + memcpy(l_new->key + round_up(key_size, 8), value, map->value_size); + + l_new->hash = htab_map_hash(l_new->key, key_size); + + /* bpf_map_update_elem() can be called in_irq() */ + spin_lock_irqsave(&htab->lock, flags); + + head = select_bucket(htab, l_new->hash); + + l_old = lookup_elem_raw(head, l_new->hash, key, key_size); + + if (!l_old && unlikely(htab->count >= map->max_entries)) { + /* if elem with this 'key' doesn't exist and we've reached + * max_entries limit, fail insertion of new elem + */ + ret = -E2BIG; + goto err; + } + + if (l_old && map_flags == BPF_NOEXIST) { + /* elem already exists */ + ret = -EEXIST; + goto err; + } + + if (!l_old && map_flags == BPF_EXIST) { + /* elem doesn't exist, cannot update it */ + ret = -ENOENT; + goto err; + } + + /* add new element to the head of the list, so that concurrent + * search will find it before old elem + */ + hlist_add_head_rcu(&l_new->hash_node, head); + if (l_old) { + hlist_del_rcu(&l_old->hash_node); + kfree_rcu(l_old, rcu); + } else { + htab->count++; + } + spin_unlock_irqrestore(&htab->lock, flags); + + return 0; +err: + spin_unlock_irqrestore(&htab->lock, flags); + kfree(l_new); + return ret; +} + +/* Called from syscall or from eBPF program */ +static int htab_map_delete_elem(struct bpf_map *map, void *key) +{ + struct bpf_htab *htab = container_of(map, struct bpf_htab, map); + struct hlist_head *head; + struct htab_elem *l; + unsigned long flags; + u32 hash, key_size; + int ret = -ENOENT; + + WARN_ON_ONCE(!rcu_read_lock_held()); + + key_size = map->key_size; + + hash = htab_map_hash(key, key_size); + + spin_lock_irqsave(&htab->lock, flags); + + head = select_bucket(htab, hash); + + l = lookup_elem_raw(head, hash, key, key_size); + + if (l) { + hlist_del_rcu(&l->hash_node); + htab->count--; + kfree_rcu(l, rcu); + ret = 0; + } + + spin_unlock_irqrestore(&htab->lock, flags); + return ret; +} + +static void delete_all_elements(struct bpf_htab *htab) +{ + int i; + + for (i = 0; i < htab->n_buckets; i++) { + struct hlist_head *head = select_bucket(htab, i); + struct hlist_node *n; + struct htab_elem *l; + + hlist_for_each_entry_safe(l, n, head, hash_node) { + hlist_del_rcu(&l->hash_node); + htab->count--; + kfree(l); + } + } +} + +/* Called when map->refcnt goes to zero, either from workqueue or from syscall */ +static void htab_map_free(struct bpf_map *map) +{ + struct bpf_htab *htab = container_of(map, struct bpf_htab, map); + + /* at this point bpf_prog->aux->refcnt == 0 and this map->refcnt == 0, + * so the programs (can be more than one that used this map) were + * disconnected from events. Wait for outstanding critical sections in + * these programs to complete + */ + synchronize_rcu(); + + /* some of kfree_rcu() callbacks for elements of this map may not have + * executed. It's ok. Proceed to free residual elements and map itself + */ + delete_all_elements(htab); + kvfree(htab->buckets); + kfree(htab); +} + +static const struct bpf_map_ops htab_ops = { + .map_alloc = htab_map_alloc, + .map_free = htab_map_free, + .map_get_next_key = htab_map_get_next_key, + .map_lookup_elem = htab_map_lookup_elem, + .map_update_elem = htab_map_update_elem, + .map_delete_elem = htab_map_delete_elem, +}; + +static struct bpf_map_type_list htab_type __read_mostly = { + .ops = &htab_ops, + .type = BPF_MAP_TYPE_HASH, +}; + +static int __init register_htab_map(void) +{ + bpf_register_map_type(&htab_type); + return 0; +} +late_initcall(register_htab_map); diff --git a/kernel/kernel/bpf/helpers.c b/kernel/kernel/bpf/helpers.c new file mode 100644 index 000000000..bd7f5988e --- /dev/null +++ b/kernel/kernel/bpf/helpers.c @@ -0,0 +1,113 @@ +/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + */ +#include +#include +#include +#include + +/* If kernel subsystem is allowing eBPF programs to call this function, + * inside its own verifier_ops->get_func_proto() callback it should return + * bpf_map_lookup_elem_proto, so that verifier can properly check the arguments + * + * Different map implementations will rely on rcu in map methods + * lookup/update/delete, therefore eBPF programs must run under rcu lock + * if program is allowed to access maps, so check rcu_read_lock_held in + * all three functions. + */ +static u64 bpf_map_lookup_elem(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) +{ + /* verifier checked that R1 contains a valid pointer to bpf_map + * and R2 points to a program stack and map->key_size bytes were + * initialized + */ + struct bpf_map *map = (struct bpf_map *) (unsigned long) r1; + void *key = (void *) (unsigned long) r2; + void *value; + + WARN_ON_ONCE(!rcu_read_lock_held()); + + value = map->ops->map_lookup_elem(map, key); + + /* lookup() returns either pointer to element value or NULL + * which is the meaning of PTR_TO_MAP_VALUE_OR_NULL type + */ + return (unsigned long) value; +} + +const struct bpf_func_proto bpf_map_lookup_elem_proto = { + .func = bpf_map_lookup_elem, + .gpl_only = false, + .ret_type = RET_PTR_TO_MAP_VALUE_OR_NULL, + .arg1_type = ARG_CONST_MAP_PTR, + .arg2_type = ARG_PTR_TO_MAP_KEY, +}; + +static u64 bpf_map_update_elem(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) +{ + struct bpf_map *map = (struct bpf_map *) (unsigned long) r1; + void *key = (void *) (unsigned long) r2; + void *value = (void *) (unsigned long) r3; + + WARN_ON_ONCE(!rcu_read_lock_held()); + + return map->ops->map_update_elem(map, key, value, r4); +} + +const struct bpf_func_proto bpf_map_update_elem_proto = { + .func = bpf_map_update_elem, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_CONST_MAP_PTR, + .arg2_type = ARG_PTR_TO_MAP_KEY, + .arg3_type = ARG_PTR_TO_MAP_VALUE, + .arg4_type = ARG_ANYTHING, +}; + +static u64 bpf_map_delete_elem(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) +{ + struct bpf_map *map = (struct bpf_map *) (unsigned long) r1; + void *key = (void *) (unsigned long) r2; + + WARN_ON_ONCE(!rcu_read_lock_held()); + + return map->ops->map_delete_elem(map, key); +} + +const struct bpf_func_proto bpf_map_delete_elem_proto = { + .func = bpf_map_delete_elem, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_CONST_MAP_PTR, + .arg2_type = ARG_PTR_TO_MAP_KEY, +}; + +static u64 bpf_get_prandom_u32(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) +{ + return prandom_u32(); +} + +const struct bpf_func_proto bpf_get_prandom_u32_proto = { + .func = bpf_get_prandom_u32, + .gpl_only = false, + .ret_type = RET_INTEGER, +}; + +static u64 bpf_get_smp_processor_id(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) +{ + return raw_smp_processor_id(); +} + +const struct bpf_func_proto bpf_get_smp_processor_id_proto = { + .func = bpf_get_smp_processor_id, + .gpl_only = false, + .ret_type = RET_INTEGER, +}; diff --git a/kernel/kernel/bpf/syscall.c b/kernel/kernel/bpf/syscall.c new file mode 100644 index 000000000..3bae6c591 --- /dev/null +++ b/kernel/kernel/bpf/syscall.c @@ -0,0 +1,621 @@ +/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + */ +#include +#include +#include +#include +#include +#include +#include +#include + +static LIST_HEAD(bpf_map_types); + +static struct bpf_map *find_and_alloc_map(union bpf_attr *attr) +{ + struct bpf_map_type_list *tl; + struct bpf_map *map; + + list_for_each_entry(tl, &bpf_map_types, list_node) { + if (tl->type == attr->map_type) { + map = tl->ops->map_alloc(attr); + if (IS_ERR(map)) + return map; + map->ops = tl->ops; + map->map_type = attr->map_type; + return map; + } + } + return ERR_PTR(-EINVAL); +} + +/* boot time registration of different map implementations */ +void bpf_register_map_type(struct bpf_map_type_list *tl) +{ + list_add(&tl->list_node, &bpf_map_types); +} + +/* called from workqueue */ +static void bpf_map_free_deferred(struct work_struct *work) +{ + struct bpf_map *map = container_of(work, struct bpf_map, work); + + /* implementation dependent freeing */ + map->ops->map_free(map); +} + +/* decrement map refcnt and schedule it for freeing via workqueue + * (unrelying map implementation ops->map_free() might sleep) + */ +void bpf_map_put(struct bpf_map *map) +{ + if (atomic_dec_and_test(&map->refcnt)) { + INIT_WORK(&map->work, bpf_map_free_deferred); + schedule_work(&map->work); + } +} + +static int bpf_map_release(struct inode *inode, struct file *filp) +{ + struct bpf_map *map = filp->private_data; + + bpf_map_put(map); + return 0; +} + +static const struct file_operations bpf_map_fops = { + .release = bpf_map_release, +}; + +/* helper macro to check that unused fields 'union bpf_attr' are zero */ +#define CHECK_ATTR(CMD) \ + memchr_inv((void *) &attr->CMD##_LAST_FIELD + \ + sizeof(attr->CMD##_LAST_FIELD), 0, \ + sizeof(*attr) - \ + offsetof(union bpf_attr, CMD##_LAST_FIELD) - \ + sizeof(attr->CMD##_LAST_FIELD)) != NULL + +#define BPF_MAP_CREATE_LAST_FIELD max_entries +/* called via syscall */ +static int map_create(union bpf_attr *attr) +{ + struct bpf_map *map; + int err; + + err = CHECK_ATTR(BPF_MAP_CREATE); + if (err) + return -EINVAL; + + /* find map type and init map: hashtable vs rbtree vs bloom vs ... */ + map = find_and_alloc_map(attr); + if (IS_ERR(map)) + return PTR_ERR(map); + + atomic_set(&map->refcnt, 1); + + err = anon_inode_getfd("bpf-map", &bpf_map_fops, map, O_RDWR | O_CLOEXEC); + + if (err < 0) + /* failed to allocate fd */ + goto free_map; + + return err; + +free_map: + map->ops->map_free(map); + return err; +} + +/* if error is returned, fd is released. + * On success caller should complete fd access with matching fdput() + */ +struct bpf_map *bpf_map_get(struct fd f) +{ + struct bpf_map *map; + + if (!f.file) + return ERR_PTR(-EBADF); + + if (f.file->f_op != &bpf_map_fops) { + fdput(f); + return ERR_PTR(-EINVAL); + } + + map = f.file->private_data; + + return map; +} + +/* helper to convert user pointers passed inside __aligned_u64 fields */ +static void __user *u64_to_ptr(__u64 val) +{ + return (void __user *) (unsigned long) val; +} + +/* last field in 'union bpf_attr' used by this command */ +#define BPF_MAP_LOOKUP_ELEM_LAST_FIELD value + +static int map_lookup_elem(union bpf_attr *attr) +{ + void __user *ukey = u64_to_ptr(attr->key); + void __user *uvalue = u64_to_ptr(attr->value); + int ufd = attr->map_fd; + struct fd f = fdget(ufd); + struct bpf_map *map; + void *key, *value, *ptr; + int err; + + if (CHECK_ATTR(BPF_MAP_LOOKUP_ELEM)) + return -EINVAL; + + map = bpf_map_get(f); + if (IS_ERR(map)) + return PTR_ERR(map); + + err = -ENOMEM; + key = kmalloc(map->key_size, GFP_USER); + if (!key) + goto err_put; + + err = -EFAULT; + if (copy_from_user(key, ukey, map->key_size) != 0) + goto free_key; + + err = -ENOMEM; + value = kmalloc(map->value_size, GFP_USER); + if (!value) + goto free_key; + + rcu_read_lock(); + ptr = map->ops->map_lookup_elem(map, key); + if (ptr) + memcpy(value, ptr, map->value_size); + rcu_read_unlock(); + + err = -ENOENT; + if (!ptr) + goto free_value; + + err = -EFAULT; + if (copy_to_user(uvalue, value, map->value_size) != 0) + goto free_value; + + err = 0; + +free_value: + kfree(value); +free_key: + kfree(key); +err_put: + fdput(f); + return err; +} + +#define BPF_MAP_UPDATE_ELEM_LAST_FIELD flags + +static int map_update_elem(union bpf_attr *attr) +{ + void __user *ukey = u64_to_ptr(attr->key); + void __user *uvalue = u64_to_ptr(attr->value); + int ufd = attr->map_fd; + struct fd f = fdget(ufd); + struct bpf_map *map; + void *key, *value; + int err; + + if (CHECK_ATTR(BPF_MAP_UPDATE_ELEM)) + return -EINVAL; + + map = bpf_map_get(f); + if (IS_ERR(map)) + return PTR_ERR(map); + + err = -ENOMEM; + key = kmalloc(map->key_size, GFP_USER); + if (!key) + goto err_put; + + err = -EFAULT; + if (copy_from_user(key, ukey, map->key_size) != 0) + goto free_key; + + err = -ENOMEM; + value = kmalloc(map->value_size, GFP_USER); + if (!value) + goto free_key; + + err = -EFAULT; + if (copy_from_user(value, uvalue, map->value_size) != 0) + goto free_value; + + /* eBPF program that use maps are running under rcu_read_lock(), + * therefore all map accessors rely on this fact, so do the same here + */ + rcu_read_lock(); + err = map->ops->map_update_elem(map, key, value, attr->flags); + rcu_read_unlock(); + +free_value: + kfree(value); +free_key: + kfree(key); +err_put: + fdput(f); + return err; +} + +#define BPF_MAP_DELETE_ELEM_LAST_FIELD key + +static int map_delete_elem(union bpf_attr *attr) +{ + void __user *ukey = u64_to_ptr(attr->key); + int ufd = attr->map_fd; + struct fd f = fdget(ufd); + struct bpf_map *map; + void *key; + int err; + + if (CHECK_ATTR(BPF_MAP_DELETE_ELEM)) + return -EINVAL; + + map = bpf_map_get(f); + if (IS_ERR(map)) + return PTR_ERR(map); + + err = -ENOMEM; + key = kmalloc(map->key_size, GFP_USER); + if (!key) + goto err_put; + + err = -EFAULT; + if (copy_from_user(key, ukey, map->key_size) != 0) + goto free_key; + + rcu_read_lock(); + err = map->ops->map_delete_elem(map, key); + rcu_read_unlock(); + +free_key: + kfree(key); +err_put: + fdput(f); + return err; +} + +/* last field in 'union bpf_attr' used by this command */ +#define BPF_MAP_GET_NEXT_KEY_LAST_FIELD next_key + +static int map_get_next_key(union bpf_attr *attr) +{ + void __user *ukey = u64_to_ptr(attr->key); + void __user *unext_key = u64_to_ptr(attr->next_key); + int ufd = attr->map_fd; + struct fd f = fdget(ufd); + struct bpf_map *map; + void *key, *next_key; + int err; + + if (CHECK_ATTR(BPF_MAP_GET_NEXT_KEY)) + return -EINVAL; + + map = bpf_map_get(f); + if (IS_ERR(map)) + return PTR_ERR(map); + + err = -ENOMEM; + key = kmalloc(map->key_size, GFP_USER); + if (!key) + goto err_put; + + err = -EFAULT; + if (copy_from_user(key, ukey, map->key_size) != 0) + goto free_key; + + err = -ENOMEM; + next_key = kmalloc(map->key_size, GFP_USER); + if (!next_key) + goto free_key; + + rcu_read_lock(); + err = map->ops->map_get_next_key(map, key, next_key); + rcu_read_unlock(); + if (err) + goto free_next_key; + + err = -EFAULT; + if (copy_to_user(unext_key, next_key, map->key_size) != 0) + goto free_next_key; + + err = 0; + +free_next_key: + kfree(next_key); +free_key: + kfree(key); +err_put: + fdput(f); + return err; +} + +static LIST_HEAD(bpf_prog_types); + +static int find_prog_type(enum bpf_prog_type type, struct bpf_prog *prog) +{ + struct bpf_prog_type_list *tl; + + list_for_each_entry(tl, &bpf_prog_types, list_node) { + if (tl->type == type) { + prog->aux->ops = tl->ops; + prog->type = type; + return 0; + } + } + + return -EINVAL; +} + +void bpf_register_prog_type(struct bpf_prog_type_list *tl) +{ + list_add(&tl->list_node, &bpf_prog_types); +} + +/* fixup insn->imm field of bpf_call instructions: + * if (insn->imm == BPF_FUNC_map_lookup_elem) + * insn->imm = bpf_map_lookup_elem - __bpf_call_base; + * else if (insn->imm == BPF_FUNC_map_update_elem) + * insn->imm = bpf_map_update_elem - __bpf_call_base; + * else ... + * + * this function is called after eBPF program passed verification + */ +static void fixup_bpf_calls(struct bpf_prog *prog) +{ + const struct bpf_func_proto *fn; + int i; + + for (i = 0; i < prog->len; i++) { + struct bpf_insn *insn = &prog->insnsi[i]; + + if (insn->code == (BPF_JMP | BPF_CALL)) { + /* we reach here when program has bpf_call instructions + * and it passed bpf_check(), means that + * ops->get_func_proto must have been supplied, check it + */ + BUG_ON(!prog->aux->ops->get_func_proto); + + fn = prog->aux->ops->get_func_proto(insn->imm); + /* all functions that have prototype and verifier allowed + * programs to call them, must be real in-kernel functions + */ + BUG_ON(!fn->func); + insn->imm = fn->func - __bpf_call_base; + } + } +} + +/* drop refcnt on maps used by eBPF program and free auxilary data */ +static void free_used_maps(struct bpf_prog_aux *aux) +{ + int i; + + for (i = 0; i < aux->used_map_cnt; i++) + bpf_map_put(aux->used_maps[i]); + + kfree(aux->used_maps); +} + +void bpf_prog_put(struct bpf_prog *prog) +{ + if (atomic_dec_and_test(&prog->aux->refcnt)) { + free_used_maps(prog->aux); + bpf_prog_free(prog); + } +} +EXPORT_SYMBOL_GPL(bpf_prog_put); + +static int bpf_prog_release(struct inode *inode, struct file *filp) +{ + struct bpf_prog *prog = filp->private_data; + + bpf_prog_put(prog); + return 0; +} + +static const struct file_operations bpf_prog_fops = { + .release = bpf_prog_release, +}; + +static struct bpf_prog *get_prog(struct fd f) +{ + struct bpf_prog *prog; + + if (!f.file) + return ERR_PTR(-EBADF); + + if (f.file->f_op != &bpf_prog_fops) { + fdput(f); + return ERR_PTR(-EINVAL); + } + + prog = f.file->private_data; + + return prog; +} + +/* called by sockets/tracing/seccomp before attaching program to an event + * pairs with bpf_prog_put() + */ +struct bpf_prog *bpf_prog_get(u32 ufd) +{ + struct fd f = fdget(ufd); + struct bpf_prog *prog; + + prog = get_prog(f); + + if (IS_ERR(prog)) + return prog; + + atomic_inc(&prog->aux->refcnt); + fdput(f); + return prog; +} +EXPORT_SYMBOL_GPL(bpf_prog_get); + +/* last field in 'union bpf_attr' used by this command */ +#define BPF_PROG_LOAD_LAST_FIELD kern_version + +static int bpf_prog_load(union bpf_attr *attr) +{ + enum bpf_prog_type type = attr->prog_type; + struct bpf_prog *prog; + int err; + char license[128]; + bool is_gpl; + + if (CHECK_ATTR(BPF_PROG_LOAD)) + return -EINVAL; + + /* copy eBPF program license from user space */ + if (strncpy_from_user(license, u64_to_ptr(attr->license), + sizeof(license) - 1) < 0) + return -EFAULT; + license[sizeof(license) - 1] = 0; + + /* eBPF programs must be GPL compatible to use GPL-ed functions */ + is_gpl = license_is_gpl_compatible(license); + + if (attr->insn_cnt >= BPF_MAXINSNS) + return -EINVAL; + + if (type == BPF_PROG_TYPE_KPROBE && + attr->kern_version != LINUX_VERSION_CODE) + return -EINVAL; + + /* plain bpf_prog allocation */ + prog = bpf_prog_alloc(bpf_prog_size(attr->insn_cnt), GFP_USER); + if (!prog) + return -ENOMEM; + + prog->len = attr->insn_cnt; + + err = -EFAULT; + if (copy_from_user(prog->insns, u64_to_ptr(attr->insns), + prog->len * sizeof(struct bpf_insn)) != 0) + goto free_prog; + + prog->orig_prog = NULL; + prog->jited = false; + + atomic_set(&prog->aux->refcnt, 1); + prog->gpl_compatible = is_gpl; + + /* find program type: socket_filter vs tracing_filter */ + err = find_prog_type(type, prog); + if (err < 0) + goto free_prog; + + /* run eBPF verifier */ + err = bpf_check(&prog, attr); + if (err < 0) + goto free_used_maps; + + /* fixup BPF_CALL->imm field */ + fixup_bpf_calls(prog); + + /* eBPF program is ready to be JITed */ + bpf_prog_select_runtime(prog); + + err = anon_inode_getfd("bpf-prog", &bpf_prog_fops, prog, O_RDWR | O_CLOEXEC); + if (err < 0) + /* failed to allocate fd */ + goto free_used_maps; + + return err; + +free_used_maps: + free_used_maps(prog->aux); +free_prog: + bpf_prog_free(prog); + return err; +} + +SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, size) +{ + union bpf_attr attr = {}; + int err; + + /* the syscall is limited to root temporarily. This restriction will be + * lifted when security audit is clean. Note that eBPF+tracing must have + * this restriction, since it may pass kernel data to user space + */ + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + if (!access_ok(VERIFY_READ, uattr, 1)) + return -EFAULT; + + if (size > PAGE_SIZE) /* silly large */ + return -E2BIG; + + /* If we're handed a bigger struct than we know of, + * ensure all the unknown bits are 0 - i.e. new + * user-space does not rely on any kernel feature + * extensions we dont know about yet. + */ + if (size > sizeof(attr)) { + unsigned char __user *addr; + unsigned char __user *end; + unsigned char val; + + addr = (void __user *)uattr + sizeof(attr); + end = (void __user *)uattr + size; + + for (; addr < end; addr++) { + err = get_user(val, addr); + if (err) + return err; + if (val) + return -E2BIG; + } + size = sizeof(attr); + } + + /* copy attributes from user space, may be less than sizeof(bpf_attr) */ + if (copy_from_user(&attr, uattr, size) != 0) + return -EFAULT; + + switch (cmd) { + case BPF_MAP_CREATE: + err = map_create(&attr); + break; + case BPF_MAP_LOOKUP_ELEM: + err = map_lookup_elem(&attr); + break; + case BPF_MAP_UPDATE_ELEM: + err = map_update_elem(&attr); + break; + case BPF_MAP_DELETE_ELEM: + err = map_delete_elem(&attr); + break; + case BPF_MAP_GET_NEXT_KEY: + err = map_get_next_key(&attr); + break; + case BPF_PROG_LOAD: + err = bpf_prog_load(&attr); + break; + default: + err = -EINVAL; + break; + } + + return err; +} diff --git a/kernel/kernel/bpf/verifier.c b/kernel/kernel/bpf/verifier.c new file mode 100644 index 000000000..47dcd3aa6 --- /dev/null +++ b/kernel/kernel/bpf/verifier.c @@ -0,0 +1,2146 @@ +/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + */ +#include +#include +#include +#include +#include +#include +#include +#include + +/* bpf_check() is a static code analyzer that walks eBPF program + * instruction by instruction and updates register/stack state. + * All paths of conditional branches are analyzed until 'bpf_exit' insn. + * + * The first pass is depth-first-search to check that the program is a DAG. + * It rejects the following programs: + * - larger than BPF_MAXINSNS insns + * - if loop is present (detected via back-edge) + * - unreachable insns exist (shouldn't be a forest. program = one function) + * - out of bounds or malformed jumps + * The second pass is all possible path descent from the 1st insn. + * Since it's analyzing all pathes through the program, the length of the + * analysis is limited to 32k insn, which may be hit even if total number of + * insn is less then 4K, but there are too many branches that change stack/regs. + * Number of 'branches to be analyzed' is limited to 1k + * + * On entry to each instruction, each register has a type, and the instruction + * changes the types of the registers depending on instruction semantics. + * If instruction is BPF_MOV64_REG(BPF_REG_1, BPF_REG_5), then type of R5 is + * copied to R1. + * + * All registers are 64-bit. + * R0 - return register + * R1-R5 argument passing registers + * R6-R9 callee saved registers + * R10 - frame pointer read-only + * + * At the start of BPF program the register R1 contains a pointer to bpf_context + * and has type PTR_TO_CTX. + * + * Verifier tracks arithmetic operations on pointers in case: + * BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + * BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -20), + * 1st insn copies R10 (which has FRAME_PTR) type into R1 + * and 2nd arithmetic instruction is pattern matched to recognize + * that it wants to construct a pointer to some element within stack. + * So after 2nd insn, the register R1 has type PTR_TO_STACK + * (and -20 constant is saved for further stack bounds checking). + * Meaning that this reg is a pointer to stack plus known immediate constant. + * + * Most of the time the registers have UNKNOWN_VALUE type, which + * means the register has some value, but it's not a valid pointer. + * (like pointer plus pointer becomes UNKNOWN_VALUE type) + * + * When verifier sees load or store instructions the type of base register + * can be: PTR_TO_MAP_VALUE, PTR_TO_CTX, FRAME_PTR. These are three pointer + * types recognized by check_mem_access() function. + * + * PTR_TO_MAP_VALUE means that this register is pointing to 'map element value' + * and the range of [ptr, ptr + map's value_size) is accessible. + * + * registers used to pass values to function calls are checked against + * function argument constraints. + * + * ARG_PTR_TO_MAP_KEY is one of such argument constraints. + * It means that the register type passed to this function must be + * PTR_TO_STACK and it will be used inside the function as + * 'pointer to map element key' + * + * For example the argument constraints for bpf_map_lookup_elem(): + * .ret_type = RET_PTR_TO_MAP_VALUE_OR_NULL, + * .arg1_type = ARG_CONST_MAP_PTR, + * .arg2_type = ARG_PTR_TO_MAP_KEY, + * + * ret_type says that this function returns 'pointer to map elem value or null' + * function expects 1st argument to be a const pointer to 'struct bpf_map' and + * 2nd argument should be a pointer to stack, which will be used inside + * the helper function as a pointer to map element key. + * + * On the kernel side the helper function looks like: + * u64 bpf_map_lookup_elem(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) + * { + * struct bpf_map *map = (struct bpf_map *) (unsigned long) r1; + * void *key = (void *) (unsigned long) r2; + * void *value; + * + * here kernel can access 'key' and 'map' pointers safely, knowing that + * [key, key + map->key_size) bytes are valid and were initialized on + * the stack of eBPF program. + * } + * + * Corresponding eBPF program may look like: + * BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), // after this insn R2 type is FRAME_PTR + * BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4), // after this insn R2 type is PTR_TO_STACK + * BPF_LD_MAP_FD(BPF_REG_1, map_fd), // after this insn R1 type is CONST_PTR_TO_MAP + * BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + * here verifier looks at prototype of map_lookup_elem() and sees: + * .arg1_type == ARG_CONST_MAP_PTR and R1->type == CONST_PTR_TO_MAP, which is ok, + * Now verifier knows that this map has key of R1->map_ptr->key_size bytes + * + * Then .arg2_type == ARG_PTR_TO_MAP_KEY and R2->type == PTR_TO_STACK, ok so far, + * Now verifier checks that [R2, R2 + map's key_size) are within stack limits + * and were initialized prior to this call. + * If it's ok, then verifier allows this BPF_CALL insn and looks at + * .ret_type which is RET_PTR_TO_MAP_VALUE_OR_NULL, so it sets + * R0->type = PTR_TO_MAP_VALUE_OR_NULL which means bpf_map_lookup_elem() function + * returns ether pointer to map value or NULL. + * + * When type PTR_TO_MAP_VALUE_OR_NULL passes through 'if (reg != 0) goto +off' + * insn, the register holding that pointer in the true branch changes state to + * PTR_TO_MAP_VALUE and the same register changes state to CONST_IMM in the false + * branch. See check_cond_jmp_op(). + * + * After the call R0 is set to return type of the function and registers R1-R5 + * are set to NOT_INIT to indicate that they are no longer readable. + */ + +/* types of values stored in eBPF registers */ +enum bpf_reg_type { + NOT_INIT = 0, /* nothing was written into register */ + UNKNOWN_VALUE, /* reg doesn't contain a valid pointer */ + PTR_TO_CTX, /* reg points to bpf_context */ + CONST_PTR_TO_MAP, /* reg points to struct bpf_map */ + PTR_TO_MAP_VALUE, /* reg points to map element value */ + PTR_TO_MAP_VALUE_OR_NULL,/* points to map elem value or NULL */ + FRAME_PTR, /* reg == frame_pointer */ + PTR_TO_STACK, /* reg == frame_pointer + imm */ + CONST_IMM, /* constant integer value */ +}; + +struct reg_state { + enum bpf_reg_type type; + union { + /* valid when type == CONST_IMM | PTR_TO_STACK */ + int imm; + + /* valid when type == CONST_PTR_TO_MAP | PTR_TO_MAP_VALUE | + * PTR_TO_MAP_VALUE_OR_NULL + */ + struct bpf_map *map_ptr; + }; +}; + +enum bpf_stack_slot_type { + STACK_INVALID, /* nothing was stored in this stack slot */ + STACK_SPILL, /* register spilled into stack */ + STACK_MISC /* BPF program wrote some data into this slot */ +}; + +#define BPF_REG_SIZE 8 /* size of eBPF register in bytes */ + +/* state of the program: + * type of all registers and stack info + */ +struct verifier_state { + struct reg_state regs[MAX_BPF_REG]; + u8 stack_slot_type[MAX_BPF_STACK]; + struct reg_state spilled_regs[MAX_BPF_STACK / BPF_REG_SIZE]; +}; + +/* linked list of verifier states used to prune search */ +struct verifier_state_list { + struct verifier_state state; + struct verifier_state_list *next; +}; + +/* verifier_state + insn_idx are pushed to stack when branch is encountered */ +struct verifier_stack_elem { + /* verifer state is 'st' + * before processing instruction 'insn_idx' + * and after processing instruction 'prev_insn_idx' + */ + struct verifier_state st; + int insn_idx; + int prev_insn_idx; + struct verifier_stack_elem *next; +}; + +#define MAX_USED_MAPS 64 /* max number of maps accessed by one eBPF program */ + +/* single container for all structs + * one verifier_env per bpf_check() call + */ +struct verifier_env { + struct bpf_prog *prog; /* eBPF program being verified */ + struct verifier_stack_elem *head; /* stack of verifier states to be processed */ + int stack_size; /* number of states to be processed */ + struct verifier_state cur_state; /* current verifier state */ + struct verifier_state_list **explored_states; /* search pruning optimization */ + struct bpf_map *used_maps[MAX_USED_MAPS]; /* array of map's used by eBPF program */ + u32 used_map_cnt; /* number of used maps */ +}; + +/* verbose verifier prints what it's seeing + * bpf_check() is called under lock, so no race to access these global vars + */ +static u32 log_level, log_size, log_len; +static char *log_buf; + +static DEFINE_MUTEX(bpf_verifier_lock); + +/* log_level controls verbosity level of eBPF verifier. + * verbose() is used to dump the verification trace to the log, so the user + * can figure out what's wrong with the program + */ +static void verbose(const char *fmt, ...) +{ + va_list args; + + if (log_level == 0 || log_len >= log_size - 1) + return; + + va_start(args, fmt); + log_len += vscnprintf(log_buf + log_len, log_size - log_len, fmt, args); + va_end(args); +} + +/* string representation of 'enum bpf_reg_type' */ +static const char * const reg_type_str[] = { + [NOT_INIT] = "?", + [UNKNOWN_VALUE] = "inv", + [PTR_TO_CTX] = "ctx", + [CONST_PTR_TO_MAP] = "map_ptr", + [PTR_TO_MAP_VALUE] = "map_value", + [PTR_TO_MAP_VALUE_OR_NULL] = "map_value_or_null", + [FRAME_PTR] = "fp", + [PTR_TO_STACK] = "fp", + [CONST_IMM] = "imm", +}; + +static void print_verifier_state(struct verifier_env *env) +{ + enum bpf_reg_type t; + int i; + + for (i = 0; i < MAX_BPF_REG; i++) { + t = env->cur_state.regs[i].type; + if (t == NOT_INIT) + continue; + verbose(" R%d=%s", i, reg_type_str[t]); + if (t == CONST_IMM || t == PTR_TO_STACK) + verbose("%d", env->cur_state.regs[i].imm); + else if (t == CONST_PTR_TO_MAP || t == PTR_TO_MAP_VALUE || + t == PTR_TO_MAP_VALUE_OR_NULL) + verbose("(ks=%d,vs=%d)", + env->cur_state.regs[i].map_ptr->key_size, + env->cur_state.regs[i].map_ptr->value_size); + } + for (i = 0; i < MAX_BPF_STACK; i += BPF_REG_SIZE) { + if (env->cur_state.stack_slot_type[i] == STACK_SPILL) + verbose(" fp%d=%s", -MAX_BPF_STACK + i, + reg_type_str[env->cur_state.spilled_regs[i / BPF_REG_SIZE].type]); + } + verbose("\n"); +} + +static const char *const bpf_class_string[] = { + [BPF_LD] = "ld", + [BPF_LDX] = "ldx", + [BPF_ST] = "st", + [BPF_STX] = "stx", + [BPF_ALU] = "alu", + [BPF_JMP] = "jmp", + [BPF_RET] = "BUG", + [BPF_ALU64] = "alu64", +}; + +static const char *const bpf_alu_string[] = { + [BPF_ADD >> 4] = "+=", + [BPF_SUB >> 4] = "-=", + [BPF_MUL >> 4] = "*=", + [BPF_DIV >> 4] = "/=", + [BPF_OR >> 4] = "|=", + [BPF_AND >> 4] = "&=", + [BPF_LSH >> 4] = "<<=", + [BPF_RSH >> 4] = ">>=", + [BPF_NEG >> 4] = "neg", + [BPF_MOD >> 4] = "%=", + [BPF_XOR >> 4] = "^=", + [BPF_MOV >> 4] = "=", + [BPF_ARSH >> 4] = "s>>=", + [BPF_END >> 4] = "endian", +}; + +static const char *const bpf_ldst_string[] = { + [BPF_W >> 3] = "u32", + [BPF_H >> 3] = "u16", + [BPF_B >> 3] = "u8", + [BPF_DW >> 3] = "u64", +}; + +static const char *const bpf_jmp_string[] = { + [BPF_JA >> 4] = "jmp", + [BPF_JEQ >> 4] = "==", + [BPF_JGT >> 4] = ">", + [BPF_JGE >> 4] = ">=", + [BPF_JSET >> 4] = "&", + [BPF_JNE >> 4] = "!=", + [BPF_JSGT >> 4] = "s>", + [BPF_JSGE >> 4] = "s>=", + [BPF_CALL >> 4] = "call", + [BPF_EXIT >> 4] = "exit", +}; + +static void print_bpf_insn(struct bpf_insn *insn) +{ + u8 class = BPF_CLASS(insn->code); + + if (class == BPF_ALU || class == BPF_ALU64) { + if (BPF_SRC(insn->code) == BPF_X) + verbose("(%02x) %sr%d %s %sr%d\n", + insn->code, class == BPF_ALU ? "(u32) " : "", + insn->dst_reg, + bpf_alu_string[BPF_OP(insn->code) >> 4], + class == BPF_ALU ? "(u32) " : "", + insn->src_reg); + else + verbose("(%02x) %sr%d %s %s%d\n", + insn->code, class == BPF_ALU ? "(u32) " : "", + insn->dst_reg, + bpf_alu_string[BPF_OP(insn->code) >> 4], + class == BPF_ALU ? "(u32) " : "", + insn->imm); + } else if (class == BPF_STX) { + if (BPF_MODE(insn->code) == BPF_MEM) + verbose("(%02x) *(%s *)(r%d %+d) = r%d\n", + insn->code, + bpf_ldst_string[BPF_SIZE(insn->code) >> 3], + insn->dst_reg, + insn->off, insn->src_reg); + else if (BPF_MODE(insn->code) == BPF_XADD) + verbose("(%02x) lock *(%s *)(r%d %+d) += r%d\n", + insn->code, + bpf_ldst_string[BPF_SIZE(insn->code) >> 3], + insn->dst_reg, insn->off, + insn->src_reg); + else + verbose("BUG_%02x\n", insn->code); + } else if (class == BPF_ST) { + if (BPF_MODE(insn->code) != BPF_MEM) { + verbose("BUG_st_%02x\n", insn->code); + return; + } + verbose("(%02x) *(%s *)(r%d %+d) = %d\n", + insn->code, + bpf_ldst_string[BPF_SIZE(insn->code) >> 3], + insn->dst_reg, + insn->off, insn->imm); + } else if (class == BPF_LDX) { + if (BPF_MODE(insn->code) != BPF_MEM) { + verbose("BUG_ldx_%02x\n", insn->code); + return; + } + verbose("(%02x) r%d = *(%s *)(r%d %+d)\n", + insn->code, insn->dst_reg, + bpf_ldst_string[BPF_SIZE(insn->code) >> 3], + insn->src_reg, insn->off); + } else if (class == BPF_LD) { + if (BPF_MODE(insn->code) == BPF_ABS) { + verbose("(%02x) r0 = *(%s *)skb[%d]\n", + insn->code, + bpf_ldst_string[BPF_SIZE(insn->code) >> 3], + insn->imm); + } else if (BPF_MODE(insn->code) == BPF_IND) { + verbose("(%02x) r0 = *(%s *)skb[r%d + %d]\n", + insn->code, + bpf_ldst_string[BPF_SIZE(insn->code) >> 3], + insn->src_reg, insn->imm); + } else if (BPF_MODE(insn->code) == BPF_IMM) { + verbose("(%02x) r%d = 0x%x\n", + insn->code, insn->dst_reg, insn->imm); + } else { + verbose("BUG_ld_%02x\n", insn->code); + return; + } + } else if (class == BPF_JMP) { + u8 opcode = BPF_OP(insn->code); + + if (opcode == BPF_CALL) { + verbose("(%02x) call %d\n", insn->code, insn->imm); + } else if (insn->code == (BPF_JMP | BPF_JA)) { + verbose("(%02x) goto pc%+d\n", + insn->code, insn->off); + } else if (insn->code == (BPF_JMP | BPF_EXIT)) { + verbose("(%02x) exit\n", insn->code); + } else if (BPF_SRC(insn->code) == BPF_X) { + verbose("(%02x) if r%d %s r%d goto pc%+d\n", + insn->code, insn->dst_reg, + bpf_jmp_string[BPF_OP(insn->code) >> 4], + insn->src_reg, insn->off); + } else { + verbose("(%02x) if r%d %s 0x%x goto pc%+d\n", + insn->code, insn->dst_reg, + bpf_jmp_string[BPF_OP(insn->code) >> 4], + insn->imm, insn->off); + } + } else { + verbose("(%02x) %s\n", insn->code, bpf_class_string[class]); + } +} + +static int pop_stack(struct verifier_env *env, int *prev_insn_idx) +{ + struct verifier_stack_elem *elem; + int insn_idx; + + if (env->head == NULL) + return -1; + + memcpy(&env->cur_state, &env->head->st, sizeof(env->cur_state)); + insn_idx = env->head->insn_idx; + if (prev_insn_idx) + *prev_insn_idx = env->head->prev_insn_idx; + elem = env->head->next; + kfree(env->head); + env->head = elem; + env->stack_size--; + return insn_idx; +} + +static struct verifier_state *push_stack(struct verifier_env *env, int insn_idx, + int prev_insn_idx) +{ + struct verifier_stack_elem *elem; + + elem = kmalloc(sizeof(struct verifier_stack_elem), GFP_KERNEL); + if (!elem) + goto err; + + memcpy(&elem->st, &env->cur_state, sizeof(env->cur_state)); + elem->insn_idx = insn_idx; + elem->prev_insn_idx = prev_insn_idx; + elem->next = env->head; + env->head = elem; + env->stack_size++; + if (env->stack_size > 1024) { + verbose("BPF program is too complex\n"); + goto err; + } + return &elem->st; +err: + /* pop all elements and return */ + while (pop_stack(env, NULL) >= 0); + return NULL; +} + +#define CALLER_SAVED_REGS 6 +static const int caller_saved[CALLER_SAVED_REGS] = { + BPF_REG_0, BPF_REG_1, BPF_REG_2, BPF_REG_3, BPF_REG_4, BPF_REG_5 +}; + +static void init_reg_state(struct reg_state *regs) +{ + int i; + + for (i = 0; i < MAX_BPF_REG; i++) { + regs[i].type = NOT_INIT; + regs[i].imm = 0; + regs[i].map_ptr = NULL; + } + + /* frame pointer */ + regs[BPF_REG_FP].type = FRAME_PTR; + + /* 1st arg to a function */ + regs[BPF_REG_1].type = PTR_TO_CTX; +} + +static void mark_reg_unknown_value(struct reg_state *regs, u32 regno) +{ + BUG_ON(regno >= MAX_BPF_REG); + regs[regno].type = UNKNOWN_VALUE; + regs[regno].imm = 0; + regs[regno].map_ptr = NULL; +} + +enum reg_arg_type { + SRC_OP, /* register is used as source operand */ + DST_OP, /* register is used as destination operand */ + DST_OP_NO_MARK /* same as above, check only, don't mark */ +}; + +static int check_reg_arg(struct reg_state *regs, u32 regno, + enum reg_arg_type t) +{ + if (regno >= MAX_BPF_REG) { + verbose("R%d is invalid\n", regno); + return -EINVAL; + } + + if (t == SRC_OP) { + /* check whether register used as source operand can be read */ + if (regs[regno].type == NOT_INIT) { + verbose("R%d !read_ok\n", regno); + return -EACCES; + } + } else { + /* check whether register used as dest operand can be written to */ + if (regno == BPF_REG_FP) { + verbose("frame pointer is read only\n"); + return -EACCES; + } + if (t == DST_OP) + mark_reg_unknown_value(regs, regno); + } + return 0; +} + +static int bpf_size_to_bytes(int bpf_size) +{ + if (bpf_size == BPF_W) + return 4; + else if (bpf_size == BPF_H) + return 2; + else if (bpf_size == BPF_B) + return 1; + else if (bpf_size == BPF_DW) + return 8; + else + return -EINVAL; +} + +/* check_stack_read/write functions track spill/fill of registers, + * stack boundary and alignment are checked in check_mem_access() + */ +static int check_stack_write(struct verifier_state *state, int off, int size, + int value_regno) +{ + int i; + /* caller checked that off % size == 0 and -MAX_BPF_STACK <= off < 0, + * so it's aligned access and [off, off + size) are within stack limits + */ + + if (value_regno >= 0 && + (state->regs[value_regno].type == PTR_TO_MAP_VALUE || + state->regs[value_regno].type == PTR_TO_STACK || + state->regs[value_regno].type == PTR_TO_CTX)) { + + /* register containing pointer is being spilled into stack */ + if (size != BPF_REG_SIZE) { + verbose("invalid size of register spill\n"); + return -EACCES; + } + + /* save register state */ + state->spilled_regs[(MAX_BPF_STACK + off) / BPF_REG_SIZE] = + state->regs[value_regno]; + + for (i = 0; i < BPF_REG_SIZE; i++) + state->stack_slot_type[MAX_BPF_STACK + off + i] = STACK_SPILL; + } else { + /* regular write of data into stack */ + state->spilled_regs[(MAX_BPF_STACK + off) / BPF_REG_SIZE] = + (struct reg_state) {}; + + for (i = 0; i < size; i++) + state->stack_slot_type[MAX_BPF_STACK + off + i] = STACK_MISC; + } + return 0; +} + +static int check_stack_read(struct verifier_state *state, int off, int size, + int value_regno) +{ + u8 *slot_type; + int i; + + slot_type = &state->stack_slot_type[MAX_BPF_STACK + off]; + + if (slot_type[0] == STACK_SPILL) { + if (size != BPF_REG_SIZE) { + verbose("invalid size of register spill\n"); + return -EACCES; + } + for (i = 1; i < BPF_REG_SIZE; i++) { + if (slot_type[i] != STACK_SPILL) { + verbose("corrupted spill memory\n"); + return -EACCES; + } + } + + if (value_regno >= 0) + /* restore register state from stack */ + state->regs[value_regno] = + state->spilled_regs[(MAX_BPF_STACK + off) / BPF_REG_SIZE]; + return 0; + } else { + for (i = 0; i < size; i++) { + if (slot_type[i] != STACK_MISC) { + verbose("invalid read from stack off %d+%d size %d\n", + off, i, size); + return -EACCES; + } + } + if (value_regno >= 0) + /* have read misc data from the stack */ + mark_reg_unknown_value(state->regs, value_regno); + return 0; + } +} + +/* check read/write into map element returned by bpf_map_lookup_elem() */ +static int check_map_access(struct verifier_env *env, u32 regno, int off, + int size) +{ + struct bpf_map *map = env->cur_state.regs[regno].map_ptr; + + if (off < 0 || off + size > map->value_size) { + verbose("invalid access to map value, value_size=%d off=%d size=%d\n", + map->value_size, off, size); + return -EACCES; + } + return 0; +} + +/* check access to 'struct bpf_context' fields */ +static int check_ctx_access(struct verifier_env *env, int off, int size, + enum bpf_access_type t) +{ + if (env->prog->aux->ops->is_valid_access && + env->prog->aux->ops->is_valid_access(off, size, t)) + return 0; + + verbose("invalid bpf_context access off=%d size=%d\n", off, size); + return -EACCES; +} + +/* check whether memory at (regno + off) is accessible for t = (read | write) + * if t==write, value_regno is a register which value is stored into memory + * if t==read, value_regno is a register which will receive the value from memory + * if t==write && value_regno==-1, some unknown value is stored into memory + * if t==read && value_regno==-1, don't care what we read from memory + */ +static int check_mem_access(struct verifier_env *env, u32 regno, int off, + int bpf_size, enum bpf_access_type t, + int value_regno) +{ + struct verifier_state *state = &env->cur_state; + int size, err = 0; + + size = bpf_size_to_bytes(bpf_size); + if (size < 0) + return size; + + if (off % size != 0) { + verbose("misaligned access off %d size %d\n", off, size); + return -EACCES; + } + + if (state->regs[regno].type == PTR_TO_MAP_VALUE) { + err = check_map_access(env, regno, off, size); + if (!err && t == BPF_READ && value_regno >= 0) + mark_reg_unknown_value(state->regs, value_regno); + + } else if (state->regs[regno].type == PTR_TO_CTX) { + err = check_ctx_access(env, off, size, t); + if (!err && t == BPF_READ && value_regno >= 0) + mark_reg_unknown_value(state->regs, value_regno); + + } else if (state->regs[regno].type == FRAME_PTR) { + if (off >= 0 || off < -MAX_BPF_STACK) { + verbose("invalid stack off=%d size=%d\n", off, size); + return -EACCES; + } + if (t == BPF_WRITE) + err = check_stack_write(state, off, size, value_regno); + else + err = check_stack_read(state, off, size, value_regno); + } else { + verbose("R%d invalid mem access '%s'\n", + regno, reg_type_str[state->regs[regno].type]); + return -EACCES; + } + return err; +} + +static int check_xadd(struct verifier_env *env, struct bpf_insn *insn) +{ + struct reg_state *regs = env->cur_state.regs; + int err; + + if ((BPF_SIZE(insn->code) != BPF_W && BPF_SIZE(insn->code) != BPF_DW) || + insn->imm != 0) { + verbose("BPF_XADD uses reserved fields\n"); + return -EINVAL; + } + + /* check src1 operand */ + err = check_reg_arg(regs, insn->src_reg, SRC_OP); + if (err) + return err; + + /* check src2 operand */ + err = check_reg_arg(regs, insn->dst_reg, SRC_OP); + if (err) + return err; + + /* check whether atomic_add can read the memory */ + err = check_mem_access(env, insn->dst_reg, insn->off, + BPF_SIZE(insn->code), BPF_READ, -1); + if (err) + return err; + + /* check whether atomic_add can write into the same memory */ + return check_mem_access(env, insn->dst_reg, insn->off, + BPF_SIZE(insn->code), BPF_WRITE, -1); +} + +/* when register 'regno' is passed into function that will read 'access_size' + * bytes from that pointer, make sure that it's within stack boundary + * and all elements of stack are initialized + */ +static int check_stack_boundary(struct verifier_env *env, + int regno, int access_size) +{ + struct verifier_state *state = &env->cur_state; + struct reg_state *regs = state->regs; + int off, i; + + if (regs[regno].type != PTR_TO_STACK) + return -EACCES; + + off = regs[regno].imm; + if (off >= 0 || off < -MAX_BPF_STACK || off + access_size > 0 || + access_size <= 0) { + verbose("invalid stack type R%d off=%d access_size=%d\n", + regno, off, access_size); + return -EACCES; + } + + for (i = 0; i < access_size; i++) { + if (state->stack_slot_type[MAX_BPF_STACK + off + i] != STACK_MISC) { + verbose("invalid indirect read from stack off %d+%d size %d\n", + off, i, access_size); + return -EACCES; + } + } + return 0; +} + +static int check_func_arg(struct verifier_env *env, u32 regno, + enum bpf_arg_type arg_type, struct bpf_map **mapp) +{ + struct reg_state *reg = env->cur_state.regs + regno; + enum bpf_reg_type expected_type; + int err = 0; + + if (arg_type == ARG_DONTCARE) + return 0; + + if (reg->type == NOT_INIT) { + verbose("R%d !read_ok\n", regno); + return -EACCES; + } + + if (arg_type == ARG_ANYTHING) + return 0; + + if (arg_type == ARG_PTR_TO_STACK || arg_type == ARG_PTR_TO_MAP_KEY || + arg_type == ARG_PTR_TO_MAP_VALUE) { + expected_type = PTR_TO_STACK; + } else if (arg_type == ARG_CONST_STACK_SIZE) { + expected_type = CONST_IMM; + } else if (arg_type == ARG_CONST_MAP_PTR) { + expected_type = CONST_PTR_TO_MAP; + } else if (arg_type == ARG_PTR_TO_CTX) { + expected_type = PTR_TO_CTX; + } else { + verbose("unsupported arg_type %d\n", arg_type); + return -EFAULT; + } + + if (reg->type != expected_type) { + verbose("R%d type=%s expected=%s\n", regno, + reg_type_str[reg->type], reg_type_str[expected_type]); + return -EACCES; + } + + if (arg_type == ARG_CONST_MAP_PTR) { + /* bpf_map_xxx(map_ptr) call: remember that map_ptr */ + *mapp = reg->map_ptr; + + } else if (arg_type == ARG_PTR_TO_MAP_KEY) { + /* bpf_map_xxx(..., map_ptr, ..., key) call: + * check that [key, key + map->key_size) are within + * stack limits and initialized + */ + if (!*mapp) { + /* in function declaration map_ptr must come before + * map_key, so that it's verified and known before + * we have to check map_key here. Otherwise it means + * that kernel subsystem misconfigured verifier + */ + verbose("invalid map_ptr to access map->key\n"); + return -EACCES; + } + err = check_stack_boundary(env, regno, (*mapp)->key_size); + + } else if (arg_type == ARG_PTR_TO_MAP_VALUE) { + /* bpf_map_xxx(..., map_ptr, ..., value) call: + * check [value, value + map->value_size) validity + */ + if (!*mapp) { + /* kernel subsystem misconfigured verifier */ + verbose("invalid map_ptr to access map->value\n"); + return -EACCES; + } + err = check_stack_boundary(env, regno, (*mapp)->value_size); + + } else if (arg_type == ARG_CONST_STACK_SIZE) { + /* bpf_xxx(..., buf, len) call will access 'len' bytes + * from stack pointer 'buf'. Check it + * note: regno == len, regno - 1 == buf + */ + if (regno == 0) { + /* kernel subsystem misconfigured verifier */ + verbose("ARG_CONST_STACK_SIZE cannot be first argument\n"); + return -EACCES; + } + err = check_stack_boundary(env, regno - 1, reg->imm); + } + + return err; +} + +static int check_call(struct verifier_env *env, int func_id) +{ + struct verifier_state *state = &env->cur_state; + const struct bpf_func_proto *fn = NULL; + struct reg_state *regs = state->regs; + struct bpf_map *map = NULL; + struct reg_state *reg; + int i, err; + + /* find function prototype */ + if (func_id < 0 || func_id >= __BPF_FUNC_MAX_ID) { + verbose("invalid func %d\n", func_id); + return -EINVAL; + } + + if (env->prog->aux->ops->get_func_proto) + fn = env->prog->aux->ops->get_func_proto(func_id); + + if (!fn) { + verbose("unknown func %d\n", func_id); + return -EINVAL; + } + + /* eBPF programs must be GPL compatible to use GPL-ed functions */ + if (!env->prog->gpl_compatible && fn->gpl_only) { + verbose("cannot call GPL only function from proprietary program\n"); + return -EINVAL; + } + + /* check args */ + err = check_func_arg(env, BPF_REG_1, fn->arg1_type, &map); + if (err) + return err; + err = check_func_arg(env, BPF_REG_2, fn->arg2_type, &map); + if (err) + return err; + err = check_func_arg(env, BPF_REG_3, fn->arg3_type, &map); + if (err) + return err; + err = check_func_arg(env, BPF_REG_4, fn->arg4_type, &map); + if (err) + return err; + err = check_func_arg(env, BPF_REG_5, fn->arg5_type, &map); + if (err) + return err; + + /* reset caller saved regs */ + for (i = 0; i < CALLER_SAVED_REGS; i++) { + reg = regs + caller_saved[i]; + reg->type = NOT_INIT; + reg->imm = 0; + } + + /* update return register */ + if (fn->ret_type == RET_INTEGER) { + regs[BPF_REG_0].type = UNKNOWN_VALUE; + } else if (fn->ret_type == RET_VOID) { + regs[BPF_REG_0].type = NOT_INIT; + } else if (fn->ret_type == RET_PTR_TO_MAP_VALUE_OR_NULL) { + regs[BPF_REG_0].type = PTR_TO_MAP_VALUE_OR_NULL; + /* remember map_ptr, so that check_map_access() + * can check 'value_size' boundary of memory access + * to map element returned from bpf_map_lookup_elem() + */ + if (map == NULL) { + verbose("kernel subsystem misconfigured verifier\n"); + return -EINVAL; + } + regs[BPF_REG_0].map_ptr = map; + } else { + verbose("unknown return type %d of func %d\n", + fn->ret_type, func_id); + return -EINVAL; + } + return 0; +} + +/* check validity of 32-bit and 64-bit arithmetic operations */ +static int check_alu_op(struct reg_state *regs, struct bpf_insn *insn) +{ + u8 opcode = BPF_OP(insn->code); + int err; + + if (opcode == BPF_END || opcode == BPF_NEG) { + if (opcode == BPF_NEG) { + if (BPF_SRC(insn->code) != 0 || + insn->src_reg != BPF_REG_0 || + insn->off != 0 || insn->imm != 0) { + verbose("BPF_NEG uses reserved fields\n"); + return -EINVAL; + } + } else { + if (insn->src_reg != BPF_REG_0 || insn->off != 0 || + (insn->imm != 16 && insn->imm != 32 && insn->imm != 64)) { + verbose("BPF_END uses reserved fields\n"); + return -EINVAL; + } + } + + /* check src operand */ + err = check_reg_arg(regs, insn->dst_reg, SRC_OP); + if (err) + return err; + + /* check dest operand */ + err = check_reg_arg(regs, insn->dst_reg, DST_OP); + if (err) + return err; + + } else if (opcode == BPF_MOV) { + + if (BPF_SRC(insn->code) == BPF_X) { + if (insn->imm != 0 || insn->off != 0) { + verbose("BPF_MOV uses reserved fields\n"); + return -EINVAL; + } + + /* check src operand */ + err = check_reg_arg(regs, insn->src_reg, SRC_OP); + if (err) + return err; + } else { + if (insn->src_reg != BPF_REG_0 || insn->off != 0) { + verbose("BPF_MOV uses reserved fields\n"); + return -EINVAL; + } + } + + /* check dest operand */ + err = check_reg_arg(regs, insn->dst_reg, DST_OP); + if (err) + return err; + + if (BPF_SRC(insn->code) == BPF_X) { + if (BPF_CLASS(insn->code) == BPF_ALU64) { + /* case: R1 = R2 + * copy register state to dest reg + */ + regs[insn->dst_reg] = regs[insn->src_reg]; + } else { + regs[insn->dst_reg].type = UNKNOWN_VALUE; + regs[insn->dst_reg].map_ptr = NULL; + } + } else { + /* case: R = imm + * remember the value we stored into this reg + */ + regs[insn->dst_reg].type = CONST_IMM; + regs[insn->dst_reg].imm = insn->imm; + } + + } else if (opcode > BPF_END) { + verbose("invalid BPF_ALU opcode %x\n", opcode); + return -EINVAL; + + } else { /* all other ALU ops: and, sub, xor, add, ... */ + + bool stack_relative = false; + + if (BPF_SRC(insn->code) == BPF_X) { + if (insn->imm != 0 || insn->off != 0) { + verbose("BPF_ALU uses reserved fields\n"); + return -EINVAL; + } + /* check src1 operand */ + err = check_reg_arg(regs, insn->src_reg, SRC_OP); + if (err) + return err; + } else { + if (insn->src_reg != BPF_REG_0 || insn->off != 0) { + verbose("BPF_ALU uses reserved fields\n"); + return -EINVAL; + } + } + + /* check src2 operand */ + err = check_reg_arg(regs, insn->dst_reg, SRC_OP); + if (err) + return err; + + if ((opcode == BPF_MOD || opcode == BPF_DIV) && + BPF_SRC(insn->code) == BPF_K && insn->imm == 0) { + verbose("div by zero\n"); + return -EINVAL; + } + + /* pattern match 'bpf_add Rx, imm' instruction */ + if (opcode == BPF_ADD && BPF_CLASS(insn->code) == BPF_ALU64 && + regs[insn->dst_reg].type == FRAME_PTR && + BPF_SRC(insn->code) == BPF_K) + stack_relative = true; + + /* check dest operand */ + err = check_reg_arg(regs, insn->dst_reg, DST_OP); + if (err) + return err; + + if (stack_relative) { + regs[insn->dst_reg].type = PTR_TO_STACK; + regs[insn->dst_reg].imm = insn->imm; + } + } + + return 0; +} + +static int check_cond_jmp_op(struct verifier_env *env, + struct bpf_insn *insn, int *insn_idx) +{ + struct reg_state *regs = env->cur_state.regs; + struct verifier_state *other_branch; + u8 opcode = BPF_OP(insn->code); + int err; + + if (opcode > BPF_EXIT) { + verbose("invalid BPF_JMP opcode %x\n", opcode); + return -EINVAL; + } + + if (BPF_SRC(insn->code) == BPF_X) { + if (insn->imm != 0) { + verbose("BPF_JMP uses reserved fields\n"); + return -EINVAL; + } + + /* check src1 operand */ + err = check_reg_arg(regs, insn->src_reg, SRC_OP); + if (err) + return err; + } else { + if (insn->src_reg != BPF_REG_0) { + verbose("BPF_JMP uses reserved fields\n"); + return -EINVAL; + } + } + + /* check src2 operand */ + err = check_reg_arg(regs, insn->dst_reg, SRC_OP); + if (err) + return err; + + /* detect if R == 0 where R was initialized to zero earlier */ + if (BPF_SRC(insn->code) == BPF_K && + (opcode == BPF_JEQ || opcode == BPF_JNE) && + regs[insn->dst_reg].type == CONST_IMM && + regs[insn->dst_reg].imm == insn->imm) { + if (opcode == BPF_JEQ) { + /* if (imm == imm) goto pc+off; + * only follow the goto, ignore fall-through + */ + *insn_idx += insn->off; + return 0; + } else { + /* if (imm != imm) goto pc+off; + * only follow fall-through branch, since + * that's where the program will go + */ + return 0; + } + } + + other_branch = push_stack(env, *insn_idx + insn->off + 1, *insn_idx); + if (!other_branch) + return -EFAULT; + + /* detect if R == 0 where R is returned value from bpf_map_lookup_elem() */ + if (BPF_SRC(insn->code) == BPF_K && + insn->imm == 0 && (opcode == BPF_JEQ || + opcode == BPF_JNE) && + regs[insn->dst_reg].type == PTR_TO_MAP_VALUE_OR_NULL) { + if (opcode == BPF_JEQ) { + /* next fallthrough insn can access memory via + * this register + */ + regs[insn->dst_reg].type = PTR_TO_MAP_VALUE; + /* branch targer cannot access it, since reg == 0 */ + other_branch->regs[insn->dst_reg].type = CONST_IMM; + other_branch->regs[insn->dst_reg].imm = 0; + } else { + other_branch->regs[insn->dst_reg].type = PTR_TO_MAP_VALUE; + regs[insn->dst_reg].type = CONST_IMM; + regs[insn->dst_reg].imm = 0; + } + } else if (BPF_SRC(insn->code) == BPF_K && + (opcode == BPF_JEQ || opcode == BPF_JNE)) { + + if (opcode == BPF_JEQ) { + /* detect if (R == imm) goto + * and in the target state recognize that R = imm + */ + other_branch->regs[insn->dst_reg].type = CONST_IMM; + other_branch->regs[insn->dst_reg].imm = insn->imm; + } else { + /* detect if (R != imm) goto + * and in the fall-through state recognize that R = imm + */ + regs[insn->dst_reg].type = CONST_IMM; + regs[insn->dst_reg].imm = insn->imm; + } + } + if (log_level) + print_verifier_state(env); + return 0; +} + +/* return the map pointer stored inside BPF_LD_IMM64 instruction */ +static struct bpf_map *ld_imm64_to_map_ptr(struct bpf_insn *insn) +{ + u64 imm64 = ((u64) (u32) insn[0].imm) | ((u64) (u32) insn[1].imm) << 32; + + return (struct bpf_map *) (unsigned long) imm64; +} + +/* verify BPF_LD_IMM64 instruction */ +static int check_ld_imm(struct verifier_env *env, struct bpf_insn *insn) +{ + struct reg_state *regs = env->cur_state.regs; + int err; + + if (BPF_SIZE(insn->code) != BPF_DW) { + verbose("invalid BPF_LD_IMM insn\n"); + return -EINVAL; + } + if (insn->off != 0) { + verbose("BPF_LD_IMM64 uses reserved fields\n"); + return -EINVAL; + } + + err = check_reg_arg(regs, insn->dst_reg, DST_OP); + if (err) + return err; + + if (insn->src_reg == 0) + /* generic move 64-bit immediate into a register */ + return 0; + + /* replace_map_fd_with_map_ptr() should have caught bad ld_imm64 */ + BUG_ON(insn->src_reg != BPF_PSEUDO_MAP_FD); + + regs[insn->dst_reg].type = CONST_PTR_TO_MAP; + regs[insn->dst_reg].map_ptr = ld_imm64_to_map_ptr(insn); + return 0; +} + +static bool may_access_skb(enum bpf_prog_type type) +{ + switch (type) { + case BPF_PROG_TYPE_SOCKET_FILTER: + case BPF_PROG_TYPE_SCHED_CLS: + case BPF_PROG_TYPE_SCHED_ACT: + return true; + default: + return false; + } +} + +/* verify safety of LD_ABS|LD_IND instructions: + * - they can only appear in the programs where ctx == skb + * - since they are wrappers of function calls, they scratch R1-R5 registers, + * preserve R6-R9, and store return value into R0 + * + * Implicit input: + * ctx == skb == R6 == CTX + * + * Explicit input: + * SRC == any register + * IMM == 32-bit immediate + * + * Output: + * R0 - 8/16/32-bit skb data converted to cpu endianness + */ +static int check_ld_abs(struct verifier_env *env, struct bpf_insn *insn) +{ + struct reg_state *regs = env->cur_state.regs; + u8 mode = BPF_MODE(insn->code); + struct reg_state *reg; + int i, err; + + if (!may_access_skb(env->prog->type)) { + verbose("BPF_LD_ABS|IND instructions not allowed for this program type\n"); + return -EINVAL; + } + + if (insn->dst_reg != BPF_REG_0 || insn->off != 0 || + (mode == BPF_ABS && insn->src_reg != BPF_REG_0)) { + verbose("BPF_LD_ABS uses reserved fields\n"); + return -EINVAL; + } + + /* check whether implicit source operand (register R6) is readable */ + err = check_reg_arg(regs, BPF_REG_6, SRC_OP); + if (err) + return err; + + if (regs[BPF_REG_6].type != PTR_TO_CTX) { + verbose("at the time of BPF_LD_ABS|IND R6 != pointer to skb\n"); + return -EINVAL; + } + + if (mode == BPF_IND) { + /* check explicit source operand */ + err = check_reg_arg(regs, insn->src_reg, SRC_OP); + if (err) + return err; + } + + /* reset caller saved regs to unreadable */ + for (i = 0; i < CALLER_SAVED_REGS; i++) { + reg = regs + caller_saved[i]; + reg->type = NOT_INIT; + reg->imm = 0; + } + + /* mark destination R0 register as readable, since it contains + * the value fetched from the packet + */ + regs[BPF_REG_0].type = UNKNOWN_VALUE; + return 0; +} + +/* non-recursive DFS pseudo code + * 1 procedure DFS-iterative(G,v): + * 2 label v as discovered + * 3 let S be a stack + * 4 S.push(v) + * 5 while S is not empty + * 6 t <- S.pop() + * 7 if t is what we're looking for: + * 8 return t + * 9 for all edges e in G.adjacentEdges(t) do + * 10 if edge e is already labelled + * 11 continue with the next edge + * 12 w <- G.adjacentVertex(t,e) + * 13 if vertex w is not discovered and not explored + * 14 label e as tree-edge + * 15 label w as discovered + * 16 S.push(w) + * 17 continue at 5 + * 18 else if vertex w is discovered + * 19 label e as back-edge + * 20 else + * 21 // vertex w is explored + * 22 label e as forward- or cross-edge + * 23 label t as explored + * 24 S.pop() + * + * convention: + * 0x10 - discovered + * 0x11 - discovered and fall-through edge labelled + * 0x12 - discovered and fall-through and branch edges labelled + * 0x20 - explored + */ + +enum { + DISCOVERED = 0x10, + EXPLORED = 0x20, + FALLTHROUGH = 1, + BRANCH = 2, +}; + +#define STATE_LIST_MARK ((struct verifier_state_list *) -1L) + +static int *insn_stack; /* stack of insns to process */ +static int cur_stack; /* current stack index */ +static int *insn_state; + +/* t, w, e - match pseudo-code above: + * t - index of current instruction + * w - next instruction + * e - edge + */ +static int push_insn(int t, int w, int e, struct verifier_env *env) +{ + if (e == FALLTHROUGH && insn_state[t] >= (DISCOVERED | FALLTHROUGH)) + return 0; + + if (e == BRANCH && insn_state[t] >= (DISCOVERED | BRANCH)) + return 0; + + if (w < 0 || w >= env->prog->len) { + verbose("jump out of range from insn %d to %d\n", t, w); + return -EINVAL; + } + + if (e == BRANCH) + /* mark branch target for state pruning */ + env->explored_states[w] = STATE_LIST_MARK; + + if (insn_state[w] == 0) { + /* tree-edge */ + insn_state[t] = DISCOVERED | e; + insn_state[w] = DISCOVERED; + if (cur_stack >= env->prog->len) + return -E2BIG; + insn_stack[cur_stack++] = w; + return 1; + } else if ((insn_state[w] & 0xF0) == DISCOVERED) { + verbose("back-edge from insn %d to %d\n", t, w); + return -EINVAL; + } else if (insn_state[w] == EXPLORED) { + /* forward- or cross-edge */ + insn_state[t] = DISCOVERED | e; + } else { + verbose("insn state internal bug\n"); + return -EFAULT; + } + return 0; +} + +/* non-recursive depth-first-search to detect loops in BPF program + * loop == back-edge in directed graph + */ +static int check_cfg(struct verifier_env *env) +{ + struct bpf_insn *insns = env->prog->insnsi; + int insn_cnt = env->prog->len; + int ret = 0; + int i, t; + + insn_state = kcalloc(insn_cnt, sizeof(int), GFP_KERNEL); + if (!insn_state) + return -ENOMEM; + + insn_stack = kcalloc(insn_cnt, sizeof(int), GFP_KERNEL); + if (!insn_stack) { + kfree(insn_state); + return -ENOMEM; + } + + insn_state[0] = DISCOVERED; /* mark 1st insn as discovered */ + insn_stack[0] = 0; /* 0 is the first instruction */ + cur_stack = 1; + +peek_stack: + if (cur_stack == 0) + goto check_state; + t = insn_stack[cur_stack - 1]; + + if (BPF_CLASS(insns[t].code) == BPF_JMP) { + u8 opcode = BPF_OP(insns[t].code); + + if (opcode == BPF_EXIT) { + goto mark_explored; + } else if (opcode == BPF_CALL) { + ret = push_insn(t, t + 1, FALLTHROUGH, env); + if (ret == 1) + goto peek_stack; + else if (ret < 0) + goto err_free; + } else if (opcode == BPF_JA) { + if (BPF_SRC(insns[t].code) != BPF_K) { + ret = -EINVAL; + goto err_free; + } + /* unconditional jump with single edge */ + ret = push_insn(t, t + insns[t].off + 1, + FALLTHROUGH, env); + if (ret == 1) + goto peek_stack; + else if (ret < 0) + goto err_free; + /* tell verifier to check for equivalent states + * after every call and jump + */ + if (t + 1 < insn_cnt) + env->explored_states[t + 1] = STATE_LIST_MARK; + } else { + /* conditional jump with two edges */ + ret = push_insn(t, t + 1, FALLTHROUGH, env); + if (ret == 1) + goto peek_stack; + else if (ret < 0) + goto err_free; + + ret = push_insn(t, t + insns[t].off + 1, BRANCH, env); + if (ret == 1) + goto peek_stack; + else if (ret < 0) + goto err_free; + } + } else { + /* all other non-branch instructions with single + * fall-through edge + */ + ret = push_insn(t, t + 1, FALLTHROUGH, env); + if (ret == 1) + goto peek_stack; + else if (ret < 0) + goto err_free; + } + +mark_explored: + insn_state[t] = EXPLORED; + if (cur_stack-- <= 0) { + verbose("pop stack internal bug\n"); + ret = -EFAULT; + goto err_free; + } + goto peek_stack; + +check_state: + for (i = 0; i < insn_cnt; i++) { + if (insn_state[i] != EXPLORED) { + verbose("unreachable insn %d\n", i); + ret = -EINVAL; + goto err_free; + } + } + ret = 0; /* cfg looks good */ + +err_free: + kfree(insn_state); + kfree(insn_stack); + return ret; +} + +/* compare two verifier states + * + * all states stored in state_list are known to be valid, since + * verifier reached 'bpf_exit' instruction through them + * + * this function is called when verifier exploring different branches of + * execution popped from the state stack. If it sees an old state that has + * more strict register state and more strict stack state then this execution + * branch doesn't need to be explored further, since verifier already + * concluded that more strict state leads to valid finish. + * + * Therefore two states are equivalent if register state is more conservative + * and explored stack state is more conservative than the current one. + * Example: + * explored current + * (slot1=INV slot2=MISC) == (slot1=MISC slot2=MISC) + * (slot1=MISC slot2=MISC) != (slot1=INV slot2=MISC) + * + * In other words if current stack state (one being explored) has more + * valid slots than old one that already passed validation, it means + * the verifier can stop exploring and conclude that current state is valid too + * + * Similarly with registers. If explored state has register type as invalid + * whereas register type in current state is meaningful, it means that + * the current state will reach 'bpf_exit' instruction safely + */ +static bool states_equal(struct verifier_state *old, struct verifier_state *cur) +{ + int i; + + for (i = 0; i < MAX_BPF_REG; i++) { + if (memcmp(&old->regs[i], &cur->regs[i], + sizeof(old->regs[0])) != 0) { + if (old->regs[i].type == NOT_INIT || + (old->regs[i].type == UNKNOWN_VALUE && + cur->regs[i].type != NOT_INIT)) + continue; + return false; + } + } + + for (i = 0; i < MAX_BPF_STACK; i++) { + if (old->stack_slot_type[i] == STACK_INVALID) + continue; + if (old->stack_slot_type[i] != cur->stack_slot_type[i]) + /* Ex: old explored (safe) state has STACK_SPILL in + * this stack slot, but current has has STACK_MISC -> + * this verifier states are not equivalent, + * return false to continue verification of this path + */ + return false; + if (i % BPF_REG_SIZE) + continue; + if (memcmp(&old->spilled_regs[i / BPF_REG_SIZE], + &cur->spilled_regs[i / BPF_REG_SIZE], + sizeof(old->spilled_regs[0]))) + /* when explored and current stack slot types are + * the same, check that stored pointers types + * are the same as well. + * Ex: explored safe path could have stored + * (struct reg_state) {.type = PTR_TO_STACK, .imm = -8} + * but current path has stored: + * (struct reg_state) {.type = PTR_TO_STACK, .imm = -16} + * such verifier states are not equivalent. + * return false to continue verification of this path + */ + return false; + else + continue; + } + return true; +} + +static int is_state_visited(struct verifier_env *env, int insn_idx) +{ + struct verifier_state_list *new_sl; + struct verifier_state_list *sl; + + sl = env->explored_states[insn_idx]; + if (!sl) + /* this 'insn_idx' instruction wasn't marked, so we will not + * be doing state search here + */ + return 0; + + while (sl != STATE_LIST_MARK) { + if (states_equal(&sl->state, &env->cur_state)) + /* reached equivalent register/stack state, + * prune the search + */ + return 1; + sl = sl->next; + } + + /* there were no equivalent states, remember current one. + * technically the current state is not proven to be safe yet, + * but it will either reach bpf_exit (which means it's safe) or + * it will be rejected. Since there are no loops, we won't be + * seeing this 'insn_idx' instruction again on the way to bpf_exit + */ + new_sl = kmalloc(sizeof(struct verifier_state_list), GFP_USER); + if (!new_sl) + return -ENOMEM; + + /* add new state to the head of linked list */ + memcpy(&new_sl->state, &env->cur_state, sizeof(env->cur_state)); + new_sl->next = env->explored_states[insn_idx]; + env->explored_states[insn_idx] = new_sl; + return 0; +} + +static int do_check(struct verifier_env *env) +{ + struct verifier_state *state = &env->cur_state; + struct bpf_insn *insns = env->prog->insnsi; + struct reg_state *regs = state->regs; + int insn_cnt = env->prog->len; + int insn_idx, prev_insn_idx = 0; + int insn_processed = 0; + bool do_print_state = false; + + init_reg_state(regs); + insn_idx = 0; + for (;;) { + struct bpf_insn *insn; + u8 class; + int err; + + if (insn_idx >= insn_cnt) { + verbose("invalid insn idx %d insn_cnt %d\n", + insn_idx, insn_cnt); + return -EFAULT; + } + + insn = &insns[insn_idx]; + class = BPF_CLASS(insn->code); + + if (++insn_processed > 32768) { + verbose("BPF program is too large. Proccessed %d insn\n", + insn_processed); + return -E2BIG; + } + + err = is_state_visited(env, insn_idx); + if (err < 0) + return err; + if (err == 1) { + /* found equivalent state, can prune the search */ + if (log_level) { + if (do_print_state) + verbose("\nfrom %d to %d: safe\n", + prev_insn_idx, insn_idx); + else + verbose("%d: safe\n", insn_idx); + } + goto process_bpf_exit; + } + + if (log_level && do_print_state) { + verbose("\nfrom %d to %d:", prev_insn_idx, insn_idx); + print_verifier_state(env); + do_print_state = false; + } + + if (log_level) { + verbose("%d: ", insn_idx); + print_bpf_insn(insn); + } + + if (class == BPF_ALU || class == BPF_ALU64) { + err = check_alu_op(regs, insn); + if (err) + return err; + + } else if (class == BPF_LDX) { + enum bpf_reg_type src_reg_type; + + /* check for reserved fields is already done */ + + /* check src operand */ + err = check_reg_arg(regs, insn->src_reg, SRC_OP); + if (err) + return err; + + err = check_reg_arg(regs, insn->dst_reg, DST_OP_NO_MARK); + if (err) + return err; + + src_reg_type = regs[insn->src_reg].type; + + /* check that memory (src_reg + off) is readable, + * the state of dst_reg will be updated by this func + */ + err = check_mem_access(env, insn->src_reg, insn->off, + BPF_SIZE(insn->code), BPF_READ, + insn->dst_reg); + if (err) + return err; + + if (BPF_SIZE(insn->code) != BPF_W) { + insn_idx++; + continue; + } + + if (insn->imm == 0) { + /* saw a valid insn + * dst_reg = *(u32 *)(src_reg + off) + * use reserved 'imm' field to mark this insn + */ + insn->imm = src_reg_type; + + } else if (src_reg_type != insn->imm && + (src_reg_type == PTR_TO_CTX || + insn->imm == PTR_TO_CTX)) { + /* ABuser program is trying to use the same insn + * dst_reg = *(u32*) (src_reg + off) + * with different pointer types: + * src_reg == ctx in one branch and + * src_reg == stack|map in some other branch. + * Reject it. + */ + verbose("same insn cannot be used with different pointers\n"); + return -EINVAL; + } + + } else if (class == BPF_STX) { + if (BPF_MODE(insn->code) == BPF_XADD) { + err = check_xadd(env, insn); + if (err) + return err; + insn_idx++; + continue; + } + + if (BPF_MODE(insn->code) != BPF_MEM || + insn->imm != 0) { + verbose("BPF_STX uses reserved fields\n"); + return -EINVAL; + } + /* check src1 operand */ + err = check_reg_arg(regs, insn->src_reg, SRC_OP); + if (err) + return err; + /* check src2 operand */ + err = check_reg_arg(regs, insn->dst_reg, SRC_OP); + if (err) + return err; + + /* check that memory (dst_reg + off) is writeable */ + err = check_mem_access(env, insn->dst_reg, insn->off, + BPF_SIZE(insn->code), BPF_WRITE, + insn->src_reg); + if (err) + return err; + + } else if (class == BPF_ST) { + if (BPF_MODE(insn->code) != BPF_MEM || + insn->src_reg != BPF_REG_0) { + verbose("BPF_ST uses reserved fields\n"); + return -EINVAL; + } + /* check src operand */ + err = check_reg_arg(regs, insn->dst_reg, SRC_OP); + if (err) + return err; + + /* check that memory (dst_reg + off) is writeable */ + err = check_mem_access(env, insn->dst_reg, insn->off, + BPF_SIZE(insn->code), BPF_WRITE, + -1); + if (err) + return err; + + } else if (class == BPF_JMP) { + u8 opcode = BPF_OP(insn->code); + + if (opcode == BPF_CALL) { + if (BPF_SRC(insn->code) != BPF_K || + insn->off != 0 || + insn->src_reg != BPF_REG_0 || + insn->dst_reg != BPF_REG_0) { + verbose("BPF_CALL uses reserved fields\n"); + return -EINVAL; + } + + err = check_call(env, insn->imm); + if (err) + return err; + + } else if (opcode == BPF_JA) { + if (BPF_SRC(insn->code) != BPF_K || + insn->imm != 0 || + insn->src_reg != BPF_REG_0 || + insn->dst_reg != BPF_REG_0) { + verbose("BPF_JA uses reserved fields\n"); + return -EINVAL; + } + + insn_idx += insn->off + 1; + continue; + + } else if (opcode == BPF_EXIT) { + if (BPF_SRC(insn->code) != BPF_K || + insn->imm != 0 || + insn->src_reg != BPF_REG_0 || + insn->dst_reg != BPF_REG_0) { + verbose("BPF_EXIT uses reserved fields\n"); + return -EINVAL; + } + + /* eBPF calling convetion is such that R0 is used + * to return the value from eBPF program. + * Make sure that it's readable at this time + * of bpf_exit, which means that program wrote + * something into it earlier + */ + err = check_reg_arg(regs, BPF_REG_0, SRC_OP); + if (err) + return err; + +process_bpf_exit: + insn_idx = pop_stack(env, &prev_insn_idx); + if (insn_idx < 0) { + break; + } else { + do_print_state = true; + continue; + } + } else { + err = check_cond_jmp_op(env, insn, &insn_idx); + if (err) + return err; + } + } else if (class == BPF_LD) { + u8 mode = BPF_MODE(insn->code); + + if (mode == BPF_ABS || mode == BPF_IND) { + err = check_ld_abs(env, insn); + if (err) + return err; + + } else if (mode == BPF_IMM) { + err = check_ld_imm(env, insn); + if (err) + return err; + + insn_idx++; + } else { + verbose("invalid BPF_LD mode\n"); + return -EINVAL; + } + } else { + verbose("unknown insn class %d\n", class); + return -EINVAL; + } + + insn_idx++; + } + + return 0; +} + +/* look for pseudo eBPF instructions that access map FDs and + * replace them with actual map pointers + */ +static int replace_map_fd_with_map_ptr(struct verifier_env *env) +{ + struct bpf_insn *insn = env->prog->insnsi; + int insn_cnt = env->prog->len; + int i, j; + + for (i = 0; i < insn_cnt; i++, insn++) { + if (BPF_CLASS(insn->code) == BPF_LDX && + (BPF_MODE(insn->code) != BPF_MEM || + insn->imm != 0)) { + verbose("BPF_LDX uses reserved fields\n"); + return -EINVAL; + } + + if (insn[0].code == (BPF_LD | BPF_IMM | BPF_DW)) { + struct bpf_map *map; + struct fd f; + + if (i == insn_cnt - 1 || insn[1].code != 0 || + insn[1].dst_reg != 0 || insn[1].src_reg != 0 || + insn[1].off != 0) { + verbose("invalid bpf_ld_imm64 insn\n"); + return -EINVAL; + } + + if (insn->src_reg == 0) + /* valid generic load 64-bit imm */ + goto next_insn; + + if (insn->src_reg != BPF_PSEUDO_MAP_FD) { + verbose("unrecognized bpf_ld_imm64 insn\n"); + return -EINVAL; + } + + f = fdget(insn->imm); + + map = bpf_map_get(f); + if (IS_ERR(map)) { + verbose("fd %d is not pointing to valid bpf_map\n", + insn->imm); + fdput(f); + return PTR_ERR(map); + } + + /* store map pointer inside BPF_LD_IMM64 instruction */ + insn[0].imm = (u32) (unsigned long) map; + insn[1].imm = ((u64) (unsigned long) map) >> 32; + + /* check whether we recorded this map already */ + for (j = 0; j < env->used_map_cnt; j++) + if (env->used_maps[j] == map) { + fdput(f); + goto next_insn; + } + + if (env->used_map_cnt >= MAX_USED_MAPS) { + fdput(f); + return -E2BIG; + } + + /* remember this map */ + env->used_maps[env->used_map_cnt++] = map; + + /* hold the map. If the program is rejected by verifier, + * the map will be released by release_maps() or it + * will be used by the valid program until it's unloaded + * and all maps are released in free_bpf_prog_info() + */ + atomic_inc(&map->refcnt); + + fdput(f); +next_insn: + insn++; + i++; + } + } + + /* now all pseudo BPF_LD_IMM64 instructions load valid + * 'struct bpf_map *' into a register instead of user map_fd. + * These pointers will be used later by verifier to validate map access. + */ + return 0; +} + +/* drop refcnt of maps used by the rejected program */ +static void release_maps(struct verifier_env *env) +{ + int i; + + for (i = 0; i < env->used_map_cnt; i++) + bpf_map_put(env->used_maps[i]); +} + +/* convert pseudo BPF_LD_IMM64 into generic BPF_LD_IMM64 */ +static void convert_pseudo_ld_imm64(struct verifier_env *env) +{ + struct bpf_insn *insn = env->prog->insnsi; + int insn_cnt = env->prog->len; + int i; + + for (i = 0; i < insn_cnt; i++, insn++) + if (insn->code == (BPF_LD | BPF_IMM | BPF_DW)) + insn->src_reg = 0; +} + +static void adjust_branches(struct bpf_prog *prog, int pos, int delta) +{ + struct bpf_insn *insn = prog->insnsi; + int insn_cnt = prog->len; + int i; + + for (i = 0; i < insn_cnt; i++, insn++) { + if (BPF_CLASS(insn->code) != BPF_JMP || + BPF_OP(insn->code) == BPF_CALL || + BPF_OP(insn->code) == BPF_EXIT) + continue; + + /* adjust offset of jmps if necessary */ + if (i < pos && i + insn->off + 1 > pos) + insn->off += delta; + else if (i > pos && i + insn->off + 1 < pos) + insn->off -= delta; + } +} + +/* convert load instructions that access fields of 'struct __sk_buff' + * into sequence of instructions that access fields of 'struct sk_buff' + */ +static int convert_ctx_accesses(struct verifier_env *env) +{ + struct bpf_insn *insn = env->prog->insnsi; + int insn_cnt = env->prog->len; + struct bpf_insn insn_buf[16]; + struct bpf_prog *new_prog; + u32 cnt; + int i; + + if (!env->prog->aux->ops->convert_ctx_access) + return 0; + + for (i = 0; i < insn_cnt; i++, insn++) { + if (insn->code != (BPF_LDX | BPF_MEM | BPF_W)) + continue; + + if (insn->imm != PTR_TO_CTX) { + /* clear internal mark */ + insn->imm = 0; + continue; + } + + cnt = env->prog->aux->ops-> + convert_ctx_access(insn->dst_reg, insn->src_reg, + insn->off, insn_buf); + if (cnt == 0 || cnt >= ARRAY_SIZE(insn_buf)) { + verbose("bpf verifier is misconfigured\n"); + return -EINVAL; + } + + if (cnt == 1) { + memcpy(insn, insn_buf, sizeof(*insn)); + continue; + } + + /* several new insns need to be inserted. Make room for them */ + insn_cnt += cnt - 1; + new_prog = bpf_prog_realloc(env->prog, + bpf_prog_size(insn_cnt), + GFP_USER); + if (!new_prog) + return -ENOMEM; + + new_prog->len = insn_cnt; + + memmove(new_prog->insnsi + i + cnt, new_prog->insns + i + 1, + sizeof(*insn) * (insn_cnt - i - cnt)); + + /* copy substitute insns in place of load instruction */ + memcpy(new_prog->insnsi + i, insn_buf, sizeof(*insn) * cnt); + + /* adjust branches in the whole program */ + adjust_branches(new_prog, i, cnt - 1); + + /* keep walking new program and skip insns we just inserted */ + env->prog = new_prog; + insn = new_prog->insnsi + i + cnt - 1; + i += cnt - 1; + } + + return 0; +} + +static void free_states(struct verifier_env *env) +{ + struct verifier_state_list *sl, *sln; + int i; + + if (!env->explored_states) + return; + + for (i = 0; i < env->prog->len; i++) { + sl = env->explored_states[i]; + + if (sl) + while (sl != STATE_LIST_MARK) { + sln = sl->next; + kfree(sl); + sl = sln; + } + } + + kfree(env->explored_states); +} + +int bpf_check(struct bpf_prog **prog, union bpf_attr *attr) +{ + char __user *log_ubuf = NULL; + struct verifier_env *env; + int ret = -EINVAL; + + if ((*prog)->len <= 0 || (*prog)->len > BPF_MAXINSNS) + return -E2BIG; + + /* 'struct verifier_env' can be global, but since it's not small, + * allocate/free it every time bpf_check() is called + */ + env = kzalloc(sizeof(struct verifier_env), GFP_KERNEL); + if (!env) + return -ENOMEM; + + env->prog = *prog; + + /* grab the mutex to protect few globals used by verifier */ + mutex_lock(&bpf_verifier_lock); + + if (attr->log_level || attr->log_buf || attr->log_size) { + /* user requested verbose verifier output + * and supplied buffer to store the verification trace + */ + log_level = attr->log_level; + log_ubuf = (char __user *) (unsigned long) attr->log_buf; + log_size = attr->log_size; + log_len = 0; + + ret = -EINVAL; + /* log_* values have to be sane */ + if (log_size < 128 || log_size > UINT_MAX >> 8 || + log_level == 0 || log_ubuf == NULL) + goto free_env; + + ret = -ENOMEM; + log_buf = vmalloc(log_size); + if (!log_buf) + goto free_env; + } else { + log_level = 0; + } + + ret = replace_map_fd_with_map_ptr(env); + if (ret < 0) + goto skip_full_check; + + env->explored_states = kcalloc(env->prog->len, + sizeof(struct verifier_state_list *), + GFP_USER); + ret = -ENOMEM; + if (!env->explored_states) + goto skip_full_check; + + ret = check_cfg(env); + if (ret < 0) + goto skip_full_check; + + ret = do_check(env); + +skip_full_check: + while (pop_stack(env, NULL) >= 0); + free_states(env); + + if (ret == 0) + /* program is valid, convert *(u32*)(ctx + off) accesses */ + ret = convert_ctx_accesses(env); + + if (log_level && log_len >= log_size - 1) { + BUG_ON(log_len >= log_size); + /* verifier log exceeded user supplied buffer */ + ret = -ENOSPC; + /* fall through to return what was recorded */ + } + + /* copy verifier log back to user space including trailing zero */ + if (log_level && copy_to_user(log_ubuf, log_buf, log_len + 1) != 0) { + ret = -EFAULT; + goto free_log_buf; + } + + if (ret == 0 && env->used_map_cnt) { + /* if program passed verifier, update used_maps in bpf_prog_info */ + env->prog->aux->used_maps = kmalloc_array(env->used_map_cnt, + sizeof(env->used_maps[0]), + GFP_KERNEL); + + if (!env->prog->aux->used_maps) { + ret = -ENOMEM; + goto free_log_buf; + } + + memcpy(env->prog->aux->used_maps, env->used_maps, + sizeof(env->used_maps[0]) * env->used_map_cnt); + env->prog->aux->used_map_cnt = env->used_map_cnt; + + /* program is valid. Convert pseudo bpf_ld_imm64 into generic + * bpf_ld_imm64 instructions + */ + convert_pseudo_ld_imm64(env); + } + +free_log_buf: + if (log_level) + vfree(log_buf); +free_env: + if (!env->prog->aux->used_maps) + /* if we didn't copy map pointers into bpf_prog_info, release + * them now. Otherwise free_bpf_prog_info() will release them. + */ + release_maps(env); + *prog = env->prog; + kfree(env); + mutex_unlock(&bpf_verifier_lock); + return ret; +} diff --git a/kernel/kernel/capability.c b/kernel/kernel/capability.c new file mode 100644 index 000000000..45432b54d --- /dev/null +++ b/kernel/kernel/capability.c @@ -0,0 +1,449 @@ +/* + * linux/kernel/capability.c + * + * Copyright (C) 1997 Andrew Main + * + * Integrated into 2.1.97+, Andrew G. Morgan + * 30 May 2002: Cleanup, Robert M. Love + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +/* + * Leveraged for setting/resetting capabilities + */ + +const kernel_cap_t __cap_empty_set = CAP_EMPTY_SET; +EXPORT_SYMBOL(__cap_empty_set); + +int file_caps_enabled = 1; + +static int __init file_caps_disable(char *str) +{ + file_caps_enabled = 0; + return 1; +} +__setup("no_file_caps", file_caps_disable); + +#ifdef CONFIG_MULTIUSER +/* + * More recent versions of libcap are available from: + * + * http://www.kernel.org/pub/linux/libs/security/linux-privs/ + */ + +static void warn_legacy_capability_use(void) +{ + char name[sizeof(current->comm)]; + + pr_info_once("warning: `%s' uses 32-bit capabilities (legacy support in use)\n", + get_task_comm(name, current)); +} + +/* + * Version 2 capabilities worked fine, but the linux/capability.h file + * that accompanied their introduction encouraged their use without + * the necessary user-space source code changes. As such, we have + * created a version 3 with equivalent functionality to version 2, but + * with a header change to protect legacy source code from using + * version 2 when it wanted to use version 1. If your system has code + * that trips the following warning, it is using version 2 specific + * capabilities and may be doing so insecurely. + * + * The remedy is to either upgrade your version of libcap (to 2.10+, + * if the application is linked against it), or recompile your + * application with modern kernel headers and this warning will go + * away. + */ + +static void warn_deprecated_v2(void) +{ + char name[sizeof(current->comm)]; + + pr_info_once("warning: `%s' uses deprecated v2 capabilities in a way that may be insecure\n", + get_task_comm(name, current)); +} + +/* + * Version check. Return the number of u32s in each capability flag + * array, or a negative value on error. + */ +static int cap_validate_magic(cap_user_header_t header, unsigned *tocopy) +{ + __u32 version; + + if (get_user(version, &header->version)) + return -EFAULT; + + switch (version) { + case _LINUX_CAPABILITY_VERSION_1: + warn_legacy_capability_use(); + *tocopy = _LINUX_CAPABILITY_U32S_1; + break; + case _LINUX_CAPABILITY_VERSION_2: + warn_deprecated_v2(); + /* + * fall through - v3 is otherwise equivalent to v2. + */ + case _LINUX_CAPABILITY_VERSION_3: + *tocopy = _LINUX_CAPABILITY_U32S_3; + break; + default: + if (put_user((u32)_KERNEL_CAPABILITY_VERSION, &header->version)) + return -EFAULT; + return -EINVAL; + } + + return 0; +} + +/* + * The only thing that can change the capabilities of the current + * process is the current process. As such, we can't be in this code + * at the same time as we are in the process of setting capabilities + * in this process. The net result is that we can limit our use of + * locks to when we are reading the caps of another process. + */ +static inline int cap_get_target_pid(pid_t pid, kernel_cap_t *pEp, + kernel_cap_t *pIp, kernel_cap_t *pPp) +{ + int ret; + + if (pid && (pid != task_pid_vnr(current))) { + struct task_struct *target; + + rcu_read_lock(); + + target = find_task_by_vpid(pid); + if (!target) + ret = -ESRCH; + else + ret = security_capget(target, pEp, pIp, pPp); + + rcu_read_unlock(); + } else + ret = security_capget(current, pEp, pIp, pPp); + + return ret; +} + +/** + * sys_capget - get the capabilities of a given process. + * @header: pointer to struct that contains capability version and + * target pid data + * @dataptr: pointer to struct that contains the effective, permitted, + * and inheritable capabilities that are returned + * + * Returns 0 on success and < 0 on error. + */ +SYSCALL_DEFINE2(capget, cap_user_header_t, header, cap_user_data_t, dataptr) +{ + int ret = 0; + pid_t pid; + unsigned tocopy; + kernel_cap_t pE, pI, pP; + + ret = cap_validate_magic(header, &tocopy); + if ((dataptr == NULL) || (ret != 0)) + return ((dataptr == NULL) && (ret == -EINVAL)) ? 0 : ret; + + if (get_user(pid, &header->pid)) + return -EFAULT; + + if (pid < 0) + return -EINVAL; + + ret = cap_get_target_pid(pid, &pE, &pI, &pP); + if (!ret) { + struct __user_cap_data_struct kdata[_KERNEL_CAPABILITY_U32S]; + unsigned i; + + for (i = 0; i < tocopy; i++) { + kdata[i].effective = pE.cap[i]; + kdata[i].permitted = pP.cap[i]; + kdata[i].inheritable = pI.cap[i]; + } + + /* + * Note, in the case, tocopy < _KERNEL_CAPABILITY_U32S, + * we silently drop the upper capabilities here. This + * has the effect of making older libcap + * implementations implicitly drop upper capability + * bits when they perform a: capget/modify/capset + * sequence. + * + * This behavior is considered fail-safe + * behavior. Upgrading the application to a newer + * version of libcap will enable access to the newer + * capabilities. + * + * An alternative would be to return an error here + * (-ERANGE), but that causes legacy applications to + * unexpectedly fail; the capget/modify/capset aborts + * before modification is attempted and the application + * fails. + */ + if (copy_to_user(dataptr, kdata, tocopy + * sizeof(struct __user_cap_data_struct))) { + return -EFAULT; + } + } + + return ret; +} + +/** + * sys_capset - set capabilities for a process or (*) a group of processes + * @header: pointer to struct that contains capability version and + * target pid data + * @data: pointer to struct that contains the effective, permitted, + * and inheritable capabilities + * + * Set capabilities for the current process only. The ability to any other + * process(es) has been deprecated and removed. + * + * The restrictions on setting capabilities are specified as: + * + * I: any raised capabilities must be a subset of the old permitted + * P: any raised capabilities must be a subset of the old permitted + * E: must be set to a subset of new permitted + * + * Returns 0 on success and < 0 on error. + */ +SYSCALL_DEFINE2(capset, cap_user_header_t, header, const cap_user_data_t, data) +{ + struct __user_cap_data_struct kdata[_KERNEL_CAPABILITY_U32S]; + unsigned i, tocopy, copybytes; + kernel_cap_t inheritable, permitted, effective; + struct cred *new; + int ret; + pid_t pid; + + ret = cap_validate_magic(header, &tocopy); + if (ret != 0) + return ret; + + if (get_user(pid, &header->pid)) + return -EFAULT; + + /* may only affect current now */ + if (pid != 0 && pid != task_pid_vnr(current)) + return -EPERM; + + copybytes = tocopy * sizeof(struct __user_cap_data_struct); + if (copybytes > sizeof(kdata)) + return -EFAULT; + + if (copy_from_user(&kdata, data, copybytes)) + return -EFAULT; + + for (i = 0; i < tocopy; i++) { + effective.cap[i] = kdata[i].effective; + permitted.cap[i] = kdata[i].permitted; + inheritable.cap[i] = kdata[i].inheritable; + } + while (i < _KERNEL_CAPABILITY_U32S) { + effective.cap[i] = 0; + permitted.cap[i] = 0; + inheritable.cap[i] = 0; + i++; + } + + effective.cap[CAP_LAST_U32] &= CAP_LAST_U32_VALID_MASK; + permitted.cap[CAP_LAST_U32] &= CAP_LAST_U32_VALID_MASK; + inheritable.cap[CAP_LAST_U32] &= CAP_LAST_U32_VALID_MASK; + + new = prepare_creds(); + if (!new) + return -ENOMEM; + + ret = security_capset(new, current_cred(), + &effective, &inheritable, &permitted); + if (ret < 0) + goto error; + + audit_log_capset(new, current_cred()); + + return commit_creds(new); + +error: + abort_creds(new); + return ret; +} + +/** + * has_ns_capability - Does a task have a capability in a specific user ns + * @t: The task in question + * @ns: target user namespace + * @cap: The capability to be tested for + * + * Return true if the specified task has the given superior capability + * currently in effect to the specified user namespace, false if not. + * + * Note that this does not set PF_SUPERPRIV on the task. + */ +bool has_ns_capability(struct task_struct *t, + struct user_namespace *ns, int cap) +{ + int ret; + + rcu_read_lock(); + ret = security_capable(__task_cred(t), ns, cap); + rcu_read_unlock(); + + return (ret == 0); +} + +/** + * has_capability - Does a task have a capability in init_user_ns + * @t: The task in question + * @cap: The capability to be tested for + * + * Return true if the specified task has the given superior capability + * currently in effect to the initial user namespace, false if not. + * + * Note that this does not set PF_SUPERPRIV on the task. + */ +bool has_capability(struct task_struct *t, int cap) +{ + return has_ns_capability(t, &init_user_ns, cap); +} + +/** + * has_ns_capability_noaudit - Does a task have a capability (unaudited) + * in a specific user ns. + * @t: The task in question + * @ns: target user namespace + * @cap: The capability to be tested for + * + * Return true if the specified task has the given superior capability + * currently in effect to the specified user namespace, false if not. + * Do not write an audit message for the check. + * + * Note that this does not set PF_SUPERPRIV on the task. + */ +bool has_ns_capability_noaudit(struct task_struct *t, + struct user_namespace *ns, int cap) +{ + int ret; + + rcu_read_lock(); + ret = security_capable_noaudit(__task_cred(t), ns, cap); + rcu_read_unlock(); + + return (ret == 0); +} + +/** + * has_capability_noaudit - Does a task have a capability (unaudited) in the + * initial user ns + * @t: The task in question + * @cap: The capability to be tested for + * + * Return true if the specified task has the given superior capability + * currently in effect to init_user_ns, false if not. Don't write an + * audit message for the check. + * + * Note that this does not set PF_SUPERPRIV on the task. + */ +bool has_capability_noaudit(struct task_struct *t, int cap) +{ + return has_ns_capability_noaudit(t, &init_user_ns, cap); +} + +/** + * ns_capable - Determine if the current task has a superior capability in effect + * @ns: The usernamespace we want the capability in + * @cap: The capability to be tested for + * + * Return true if the current task has the given superior capability currently + * available for use, false if not. + * + * This sets PF_SUPERPRIV on the task if the capability is available on the + * assumption that it's about to be used. + */ +bool ns_capable(struct user_namespace *ns, int cap) +{ + if (unlikely(!cap_valid(cap))) { + pr_crit("capable() called with invalid cap=%u\n", cap); + BUG(); + } + + if (security_capable(current_cred(), ns, cap) == 0) { + current->flags |= PF_SUPERPRIV; + return true; + } + return false; +} +EXPORT_SYMBOL(ns_capable); + + +/** + * capable - Determine if the current task has a superior capability in effect + * @cap: The capability to be tested for + * + * Return true if the current task has the given superior capability currently + * available for use, false if not. + * + * This sets PF_SUPERPRIV on the task if the capability is available on the + * assumption that it's about to be used. + */ +bool capable(int cap) +{ + return ns_capable(&init_user_ns, cap); +} +EXPORT_SYMBOL(capable); +#endif /* CONFIG_MULTIUSER */ + +/** + * file_ns_capable - Determine if the file's opener had a capability in effect + * @file: The file we want to check + * @ns: The usernamespace we want the capability in + * @cap: The capability to be tested for + * + * Return true if task that opened the file had a capability in effect + * when the file was opened. + * + * This does not set PF_SUPERPRIV because the caller may not + * actually be privileged. + */ +bool file_ns_capable(const struct file *file, struct user_namespace *ns, + int cap) +{ + if (WARN_ON_ONCE(!cap_valid(cap))) + return false; + + if (security_capable(file->f_cred, ns, cap) == 0) + return true; + + return false; +} +EXPORT_SYMBOL(file_ns_capable); + +/** + * capable_wrt_inode_uidgid - Check nsown_capable and uid and gid mapped + * @inode: The inode in question + * @cap: The capability in question + * + * Return true if the current task has the given capability targeted at + * its own user namespace and that the given inode's uid and gid are + * mapped into the current user namespace. + */ +bool capable_wrt_inode_uidgid(const struct inode *inode, int cap) +{ + struct user_namespace *ns = current_user_ns(); + + return ns_capable(ns, cap) && kuid_has_mapping(ns, inode->i_uid) && + kgid_has_mapping(ns, inode->i_gid); +} +EXPORT_SYMBOL(capable_wrt_inode_uidgid); diff --git a/kernel/kernel/cgroup.c b/kernel/kernel/cgroup.c new file mode 100644 index 000000000..2a7a0fe19 --- /dev/null +++ b/kernel/kernel/cgroup.c @@ -0,0 +1,5602 @@ +/* + * Generic process-grouping system. + * + * Based originally on the cpuset system, extracted by Paul Menage + * Copyright (C) 2006 Google, Inc + * + * Notifications support + * Copyright (C) 2009 Nokia Corporation + * Author: Kirill A. Shutemov + * + * Copyright notices from the original cpuset code: + * -------------------------------------------------- + * Copyright (C) 2003 BULL SA. + * Copyright (C) 2004-2006 Silicon Graphics, Inc. + * + * Portions derived from Patrick Mochel's sysfs code. + * sysfs is Copyright (c) 2001-3 Patrick Mochel + * + * 2003-10-10 Written by Simon Derr. + * 2003-10-22 Updates by Stephen Hemminger. + * 2004 May-July Rework by Paul Jackson. + * --------------------------------------------------- + * + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file COPYING in the main directory of the Linux + * distribution for more details. + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include /* TODO: replace with more sophisticated array */ +#include +#include + +#include + +/* + * pidlists linger the following amount before being destroyed. The goal + * is avoiding frequent destruction in the middle of consecutive read calls + * Expiring in the middle is a performance problem not a correctness one. + * 1 sec should be enough. + */ +#define CGROUP_PIDLIST_DESTROY_DELAY HZ + +#define CGROUP_FILE_NAME_MAX (MAX_CGROUP_TYPE_NAMELEN + \ + MAX_CFTYPE_NAME + 2) + +/* + * cgroup_mutex is the master lock. Any modification to cgroup or its + * hierarchy must be performed while holding it. + * + * css_set_rwsem protects task->cgroups pointer, the list of css_set + * objects, and the chain of tasks off each css_set. + * + * These locks are exported if CONFIG_PROVE_RCU so that accessors in + * cgroup.h can use them for lockdep annotations. + */ +#ifdef CONFIG_PROVE_RCU +DEFINE_MUTEX(cgroup_mutex); +DECLARE_RWSEM(css_set_rwsem); +EXPORT_SYMBOL_GPL(cgroup_mutex); +EXPORT_SYMBOL_GPL(css_set_rwsem); +#else +static DEFINE_MUTEX(cgroup_mutex); +static DECLARE_RWSEM(css_set_rwsem); +#endif + +/* + * Protects cgroup_idr and css_idr so that IDs can be released without + * grabbing cgroup_mutex. + */ +static DEFINE_SPINLOCK(cgroup_idr_lock); + +/* + * Protects cgroup_subsys->release_agent_path. Modifying it also requires + * cgroup_mutex. Reading requires either cgroup_mutex or this spinlock. + */ +static DEFINE_SPINLOCK(release_agent_path_lock); + +#define cgroup_assert_mutex_or_rcu_locked() \ + rcu_lockdep_assert(rcu_read_lock_held() || \ + lockdep_is_held(&cgroup_mutex), \ + "cgroup_mutex or RCU read lock required"); + +/* + * cgroup destruction makes heavy use of work items and there can be a lot + * of concurrent destructions. Use a separate workqueue so that cgroup + * destruction work items don't end up filling up max_active of system_wq + * which may lead to deadlock. + */ +static struct workqueue_struct *cgroup_destroy_wq; + +/* + * pidlist destructions need to be flushed on cgroup destruction. Use a + * separate workqueue as flush domain. + */ +static struct workqueue_struct *cgroup_pidlist_destroy_wq; + +/* generate an array of cgroup subsystem pointers */ +#define SUBSYS(_x) [_x ## _cgrp_id] = &_x ## _cgrp_subsys, +static struct cgroup_subsys *cgroup_subsys[] = { +#include +}; +#undef SUBSYS + +/* array of cgroup subsystem names */ +#define SUBSYS(_x) [_x ## _cgrp_id] = #_x, +static const char *cgroup_subsys_name[] = { +#include +}; +#undef SUBSYS + +/* + * The default hierarchy, reserved for the subsystems that are otherwise + * unattached - it never has more than a single cgroup, and all tasks are + * part of that cgroup. + */ +struct cgroup_root cgrp_dfl_root; + +/* + * The default hierarchy always exists but is hidden until mounted for the + * first time. This is for backward compatibility. + */ +static bool cgrp_dfl_root_visible; + +/* + * Set by the boot param of the same name and makes subsystems with NULL + * ->dfl_files to use ->legacy_files on the default hierarchy. + */ +static bool cgroup_legacy_files_on_dfl; + +/* some controllers are not supported in the default hierarchy */ +static unsigned int cgrp_dfl_root_inhibit_ss_mask; + +/* The list of hierarchy roots */ + +static LIST_HEAD(cgroup_roots); +static int cgroup_root_count; + +/* hierarchy ID allocation and mapping, protected by cgroup_mutex */ +static DEFINE_IDR(cgroup_hierarchy_idr); + +/* + * Assign a monotonically increasing serial number to csses. It guarantees + * cgroups with bigger numbers are newer than those with smaller numbers. + * Also, as csses are always appended to the parent's ->children list, it + * guarantees that sibling csses are always sorted in the ascending serial + * number order on the list. Protected by cgroup_mutex. + */ +static u64 css_serial_nr_next = 1; + +/* This flag indicates whether tasks in the fork and exit paths should + * check for fork/exit handlers to call. This avoids us having to do + * extra work in the fork/exit path if none of the subsystems need to + * be called. + */ +static int need_forkexit_callback __read_mostly; + +static struct cftype cgroup_dfl_base_files[]; +static struct cftype cgroup_legacy_base_files[]; + +static int rebind_subsystems(struct cgroup_root *dst_root, + unsigned int ss_mask); +static int cgroup_destroy_locked(struct cgroup *cgrp); +static int create_css(struct cgroup *cgrp, struct cgroup_subsys *ss, + bool visible); +static void css_release(struct percpu_ref *ref); +static void kill_css(struct cgroup_subsys_state *css); +static int cgroup_addrm_files(struct cgroup *cgrp, struct cftype cfts[], + bool is_add); + +/* IDR wrappers which synchronize using cgroup_idr_lock */ +static int cgroup_idr_alloc(struct idr *idr, void *ptr, int start, int end, + gfp_t gfp_mask) +{ + int ret; + + idr_preload(gfp_mask); + spin_lock_bh(&cgroup_idr_lock); + ret = idr_alloc(idr, ptr, start, end, gfp_mask); + spin_unlock_bh(&cgroup_idr_lock); + idr_preload_end(); + return ret; +} + +static void *cgroup_idr_replace(struct idr *idr, void *ptr, int id) +{ + void *ret; + + spin_lock_bh(&cgroup_idr_lock); + ret = idr_replace(idr, ptr, id); + spin_unlock_bh(&cgroup_idr_lock); + return ret; +} + +static void cgroup_idr_remove(struct idr *idr, int id) +{ + spin_lock_bh(&cgroup_idr_lock); + idr_remove(idr, id); + spin_unlock_bh(&cgroup_idr_lock); +} + +static struct cgroup *cgroup_parent(struct cgroup *cgrp) +{ + struct cgroup_subsys_state *parent_css = cgrp->self.parent; + + if (parent_css) + return container_of(parent_css, struct cgroup, self); + return NULL; +} + +/** + * cgroup_css - obtain a cgroup's css for the specified subsystem + * @cgrp: the cgroup of interest + * @ss: the subsystem of interest (%NULL returns @cgrp->self) + * + * Return @cgrp's css (cgroup_subsys_state) associated with @ss. This + * function must be called either under cgroup_mutex or rcu_read_lock() and + * the caller is responsible for pinning the returned css if it wants to + * keep accessing it outside the said locks. This function may return + * %NULL if @cgrp doesn't have @subsys_id enabled. + */ +static struct cgroup_subsys_state *cgroup_css(struct cgroup *cgrp, + struct cgroup_subsys *ss) +{ + if (ss) + return rcu_dereference_check(cgrp->subsys[ss->id], + lockdep_is_held(&cgroup_mutex)); + else + return &cgrp->self; +} + +/** + * cgroup_e_css - obtain a cgroup's effective css for the specified subsystem + * @cgrp: the cgroup of interest + * @ss: the subsystem of interest (%NULL returns @cgrp->self) + * + * Similar to cgroup_css() but returns the effctive css, which is defined + * as the matching css of the nearest ancestor including self which has @ss + * enabled. If @ss is associated with the hierarchy @cgrp is on, this + * function is guaranteed to return non-NULL css. + */ +static struct cgroup_subsys_state *cgroup_e_css(struct cgroup *cgrp, + struct cgroup_subsys *ss) +{ + lockdep_assert_held(&cgroup_mutex); + + if (!ss) + return &cgrp->self; + + if (!(cgrp->root->subsys_mask & (1 << ss->id))) + return NULL; + + /* + * This function is used while updating css associations and thus + * can't test the csses directly. Use ->child_subsys_mask. + */ + while (cgroup_parent(cgrp) && + !(cgroup_parent(cgrp)->child_subsys_mask & (1 << ss->id))) + cgrp = cgroup_parent(cgrp); + + return cgroup_css(cgrp, ss); +} + +/** + * cgroup_get_e_css - get a cgroup's effective css for the specified subsystem + * @cgrp: the cgroup of interest + * @ss: the subsystem of interest + * + * Find and get the effective css of @cgrp for @ss. The effective css is + * defined as the matching css of the nearest ancestor including self which + * has @ss enabled. If @ss is not mounted on the hierarchy @cgrp is on, + * the root css is returned, so this function always returns a valid css. + * The returned css must be put using css_put(). + */ +struct cgroup_subsys_state *cgroup_get_e_css(struct cgroup *cgrp, + struct cgroup_subsys *ss) +{ + struct cgroup_subsys_state *css; + + rcu_read_lock(); + + do { + css = cgroup_css(cgrp, ss); + + if (css && css_tryget_online(css)) + goto out_unlock; + cgrp = cgroup_parent(cgrp); + } while (cgrp); + + css = init_css_set.subsys[ss->id]; + css_get(css); +out_unlock: + rcu_read_unlock(); + return css; +} + +/* convenient tests for these bits */ +static inline bool cgroup_is_dead(const struct cgroup *cgrp) +{ + return !(cgrp->self.flags & CSS_ONLINE); +} + +struct cgroup_subsys_state *of_css(struct kernfs_open_file *of) +{ + struct cgroup *cgrp = of->kn->parent->priv; + struct cftype *cft = of_cft(of); + + /* + * This is open and unprotected implementation of cgroup_css(). + * seq_css() is only called from a kernfs file operation which has + * an active reference on the file. Because all the subsystem + * files are drained before a css is disassociated with a cgroup, + * the matching css from the cgroup's subsys table is guaranteed to + * be and stay valid until the enclosing operation is complete. + */ + if (cft->ss) + return rcu_dereference_raw(cgrp->subsys[cft->ss->id]); + else + return &cgrp->self; +} +EXPORT_SYMBOL_GPL(of_css); + +/** + * cgroup_is_descendant - test ancestry + * @cgrp: the cgroup to be tested + * @ancestor: possible ancestor of @cgrp + * + * Test whether @cgrp is a descendant of @ancestor. It also returns %true + * if @cgrp == @ancestor. This function is safe to call as long as @cgrp + * and @ancestor are accessible. + */ +bool cgroup_is_descendant(struct cgroup *cgrp, struct cgroup *ancestor) +{ + while (cgrp) { + if (cgrp == ancestor) + return true; + cgrp = cgroup_parent(cgrp); + } + return false; +} + +static int notify_on_release(const struct cgroup *cgrp) +{ + return test_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags); +} + +/** + * for_each_css - iterate all css's of a cgroup + * @css: the iteration cursor + * @ssid: the index of the subsystem, CGROUP_SUBSYS_COUNT after reaching the end + * @cgrp: the target cgroup to iterate css's of + * + * Should be called under cgroup_[tree_]mutex. + */ +#define for_each_css(css, ssid, cgrp) \ + for ((ssid) = 0; (ssid) < CGROUP_SUBSYS_COUNT; (ssid)++) \ + if (!((css) = rcu_dereference_check( \ + (cgrp)->subsys[(ssid)], \ + lockdep_is_held(&cgroup_mutex)))) { } \ + else + +/** + * for_each_e_css - iterate all effective css's of a cgroup + * @css: the iteration cursor + * @ssid: the index of the subsystem, CGROUP_SUBSYS_COUNT after reaching the end + * @cgrp: the target cgroup to iterate css's of + * + * Should be called under cgroup_[tree_]mutex. + */ +#define for_each_e_css(css, ssid, cgrp) \ + for ((ssid) = 0; (ssid) < CGROUP_SUBSYS_COUNT; (ssid)++) \ + if (!((css) = cgroup_e_css(cgrp, cgroup_subsys[(ssid)]))) \ + ; \ + else + +/** + * for_each_subsys - iterate all enabled cgroup subsystems + * @ss: the iteration cursor + * @ssid: the index of @ss, CGROUP_SUBSYS_COUNT after reaching the end + */ +#define for_each_subsys(ss, ssid) \ + for ((ssid) = 0; (ssid) < CGROUP_SUBSYS_COUNT && \ + (((ss) = cgroup_subsys[ssid]) || true); (ssid)++) + +/* iterate across the hierarchies */ +#define for_each_root(root) \ + list_for_each_entry((root), &cgroup_roots, root_list) + +/* iterate over child cgrps, lock should be held throughout iteration */ +#define cgroup_for_each_live_child(child, cgrp) \ + list_for_each_entry((child), &(cgrp)->self.children, self.sibling) \ + if (({ lockdep_assert_held(&cgroup_mutex); \ + cgroup_is_dead(child); })) \ + ; \ + else + +static void cgroup_release_agent(struct work_struct *work); +static void check_for_release(struct cgroup *cgrp); + +/* + * A cgroup can be associated with multiple css_sets as different tasks may + * belong to different cgroups on different hierarchies. In the other + * direction, a css_set is naturally associated with multiple cgroups. + * This M:N relationship is represented by the following link structure + * which exists for each association and allows traversing the associations + * from both sides. + */ +struct cgrp_cset_link { + /* the cgroup and css_set this link associates */ + struct cgroup *cgrp; + struct css_set *cset; + + /* list of cgrp_cset_links anchored at cgrp->cset_links */ + struct list_head cset_link; + + /* list of cgrp_cset_links anchored at css_set->cgrp_links */ + struct list_head cgrp_link; +}; + +/* + * The default css_set - used by init and its children prior to any + * hierarchies being mounted. It contains a pointer to the root state + * for each subsystem. Also used to anchor the list of css_sets. Not + * reference-counted, to improve performance when child cgroups + * haven't been created. + */ +struct css_set init_css_set = { + .refcount = ATOMIC_INIT(1), + .cgrp_links = LIST_HEAD_INIT(init_css_set.cgrp_links), + .tasks = LIST_HEAD_INIT(init_css_set.tasks), + .mg_tasks = LIST_HEAD_INIT(init_css_set.mg_tasks), + .mg_preload_node = LIST_HEAD_INIT(init_css_set.mg_preload_node), + .mg_node = LIST_HEAD_INIT(init_css_set.mg_node), +}; + +static int css_set_count = 1; /* 1 for init_css_set */ + +/** + * cgroup_update_populated - updated populated count of a cgroup + * @cgrp: the target cgroup + * @populated: inc or dec populated count + * + * @cgrp is either getting the first task (css_set) or losing the last. + * Update @cgrp->populated_cnt accordingly. The count is propagated + * towards root so that a given cgroup's populated_cnt is zero iff the + * cgroup and all its descendants are empty. + * + * @cgrp's interface file "cgroup.populated" is zero if + * @cgrp->populated_cnt is zero and 1 otherwise. When @cgrp->populated_cnt + * changes from or to zero, userland is notified that the content of the + * interface file has changed. This can be used to detect when @cgrp and + * its descendants become populated or empty. + */ +static void cgroup_update_populated(struct cgroup *cgrp, bool populated) +{ + lockdep_assert_held(&css_set_rwsem); + + do { + bool trigger; + + if (populated) + trigger = !cgrp->populated_cnt++; + else + trigger = !--cgrp->populated_cnt; + + if (!trigger) + break; + + if (cgrp->populated_kn) + kernfs_notify(cgrp->populated_kn); + cgrp = cgroup_parent(cgrp); + } while (cgrp); +} + +/* + * hash table for cgroup groups. This improves the performance to find + * an existing css_set. This hash doesn't (currently) take into + * account cgroups in empty hierarchies. + */ +#define CSS_SET_HASH_BITS 7 +static DEFINE_HASHTABLE(css_set_table, CSS_SET_HASH_BITS); + +static unsigned long css_set_hash(struct cgroup_subsys_state *css[]) +{ + unsigned long key = 0UL; + struct cgroup_subsys *ss; + int i; + + for_each_subsys(ss, i) + key += (unsigned long)css[i]; + key = (key >> 16) ^ key; + + return key; +} + +static void put_css_set_locked(struct css_set *cset) +{ + struct cgrp_cset_link *link, *tmp_link; + struct cgroup_subsys *ss; + int ssid; + + lockdep_assert_held(&css_set_rwsem); + + if (!atomic_dec_and_test(&cset->refcount)) + return; + + /* This css_set is dead. unlink it and release cgroup refcounts */ + for_each_subsys(ss, ssid) + list_del(&cset->e_cset_node[ssid]); + hash_del(&cset->hlist); + css_set_count--; + + list_for_each_entry_safe(link, tmp_link, &cset->cgrp_links, cgrp_link) { + struct cgroup *cgrp = link->cgrp; + + list_del(&link->cset_link); + list_del(&link->cgrp_link); + + /* @cgrp can't go away while we're holding css_set_rwsem */ + if (list_empty(&cgrp->cset_links)) { + cgroup_update_populated(cgrp, false); + check_for_release(cgrp); + } + + kfree(link); + } + + kfree_rcu(cset, rcu_head); +} + +static void put_css_set(struct css_set *cset) +{ + /* + * Ensure that the refcount doesn't hit zero while any readers + * can see it. Similar to atomic_dec_and_lock(), but for an + * rwlock + */ + if (atomic_add_unless(&cset->refcount, -1, 1)) + return; + + down_write(&css_set_rwsem); + put_css_set_locked(cset); + up_write(&css_set_rwsem); +} + +/* + * refcounted get/put for css_set objects + */ +static inline void get_css_set(struct css_set *cset) +{ + atomic_inc(&cset->refcount); +} + +/** + * compare_css_sets - helper function for find_existing_css_set(). + * @cset: candidate css_set being tested + * @old_cset: existing css_set for a task + * @new_cgrp: cgroup that's being entered by the task + * @template: desired set of css pointers in css_set (pre-calculated) + * + * Returns true if "cset" matches "old_cset" except for the hierarchy + * which "new_cgrp" belongs to, for which it should match "new_cgrp". + */ +static bool compare_css_sets(struct css_set *cset, + struct css_set *old_cset, + struct cgroup *new_cgrp, + struct cgroup_subsys_state *template[]) +{ + struct list_head *l1, *l2; + + /* + * On the default hierarchy, there can be csets which are + * associated with the same set of cgroups but different csses. + * Let's first ensure that csses match. + */ + if (memcmp(template, cset->subsys, sizeof(cset->subsys))) + return false; + + /* + * Compare cgroup pointers in order to distinguish between + * different cgroups in hierarchies. As different cgroups may + * share the same effective css, this comparison is always + * necessary. + */ + l1 = &cset->cgrp_links; + l2 = &old_cset->cgrp_links; + while (1) { + struct cgrp_cset_link *link1, *link2; + struct cgroup *cgrp1, *cgrp2; + + l1 = l1->next; + l2 = l2->next; + /* See if we reached the end - both lists are equal length. */ + if (l1 == &cset->cgrp_links) { + BUG_ON(l2 != &old_cset->cgrp_links); + break; + } else { + BUG_ON(l2 == &old_cset->cgrp_links); + } + /* Locate the cgroups associated with these links. */ + link1 = list_entry(l1, struct cgrp_cset_link, cgrp_link); + link2 = list_entry(l2, struct cgrp_cset_link, cgrp_link); + cgrp1 = link1->cgrp; + cgrp2 = link2->cgrp; + /* Hierarchies should be linked in the same order. */ + BUG_ON(cgrp1->root != cgrp2->root); + + /* + * If this hierarchy is the hierarchy of the cgroup + * that's changing, then we need to check that this + * css_set points to the new cgroup; if it's any other + * hierarchy, then this css_set should point to the + * same cgroup as the old css_set. + */ + if (cgrp1->root == new_cgrp->root) { + if (cgrp1 != new_cgrp) + return false; + } else { + if (cgrp1 != cgrp2) + return false; + } + } + return true; +} + +/** + * find_existing_css_set - init css array and find the matching css_set + * @old_cset: the css_set that we're using before the cgroup transition + * @cgrp: the cgroup that we're moving into + * @template: out param for the new set of csses, should be clear on entry + */ +static struct css_set *find_existing_css_set(struct css_set *old_cset, + struct cgroup *cgrp, + struct cgroup_subsys_state *template[]) +{ + struct cgroup_root *root = cgrp->root; + struct cgroup_subsys *ss; + struct css_set *cset; + unsigned long key; + int i; + + /* + * Build the set of subsystem state objects that we want to see in the + * new css_set. while subsystems can change globally, the entries here + * won't change, so no need for locking. + */ + for_each_subsys(ss, i) { + if (root->subsys_mask & (1UL << i)) { + /* + * @ss is in this hierarchy, so we want the + * effective css from @cgrp. + */ + template[i] = cgroup_e_css(cgrp, ss); + } else { + /* + * @ss is not in this hierarchy, so we don't want + * to change the css. + */ + template[i] = old_cset->subsys[i]; + } + } + + key = css_set_hash(template); + hash_for_each_possible(css_set_table, cset, hlist, key) { + if (!compare_css_sets(cset, old_cset, cgrp, template)) + continue; + + /* This css_set matches what we need */ + return cset; + } + + /* No existing cgroup group matched */ + return NULL; +} + +static void free_cgrp_cset_links(struct list_head *links_to_free) +{ + struct cgrp_cset_link *link, *tmp_link; + + list_for_each_entry_safe(link, tmp_link, links_to_free, cset_link) { + list_del(&link->cset_link); + kfree(link); + } +} + +/** + * allocate_cgrp_cset_links - allocate cgrp_cset_links + * @count: the number of links to allocate + * @tmp_links: list_head the allocated links are put on + * + * Allocate @count cgrp_cset_link structures and chain them on @tmp_links + * through ->cset_link. Returns 0 on success or -errno. + */ +static int allocate_cgrp_cset_links(int count, struct list_head *tmp_links) +{ + struct cgrp_cset_link *link; + int i; + + INIT_LIST_HEAD(tmp_links); + + for (i = 0; i < count; i++) { + link = kzalloc(sizeof(*link), GFP_KERNEL); + if (!link) { + free_cgrp_cset_links(tmp_links); + return -ENOMEM; + } + list_add(&link->cset_link, tmp_links); + } + return 0; +} + +/** + * link_css_set - a helper function to link a css_set to a cgroup + * @tmp_links: cgrp_cset_link objects allocated by allocate_cgrp_cset_links() + * @cset: the css_set to be linked + * @cgrp: the destination cgroup + */ +static void link_css_set(struct list_head *tmp_links, struct css_set *cset, + struct cgroup *cgrp) +{ + struct cgrp_cset_link *link; + + BUG_ON(list_empty(tmp_links)); + + if (cgroup_on_dfl(cgrp)) + cset->dfl_cgrp = cgrp; + + link = list_first_entry(tmp_links, struct cgrp_cset_link, cset_link); + link->cset = cset; + link->cgrp = cgrp; + + if (list_empty(&cgrp->cset_links)) + cgroup_update_populated(cgrp, true); + list_move(&link->cset_link, &cgrp->cset_links); + + /* + * Always add links to the tail of the list so that the list + * is sorted by order of hierarchy creation + */ + list_add_tail(&link->cgrp_link, &cset->cgrp_links); +} + +/** + * find_css_set - return a new css_set with one cgroup updated + * @old_cset: the baseline css_set + * @cgrp: the cgroup to be updated + * + * Return a new css_set that's equivalent to @old_cset, but with @cgrp + * substituted into the appropriate hierarchy. + */ +static struct css_set *find_css_set(struct css_set *old_cset, + struct cgroup *cgrp) +{ + struct cgroup_subsys_state *template[CGROUP_SUBSYS_COUNT] = { }; + struct css_set *cset; + struct list_head tmp_links; + struct cgrp_cset_link *link; + struct cgroup_subsys *ss; + unsigned long key; + int ssid; + + lockdep_assert_held(&cgroup_mutex); + + /* First see if we already have a cgroup group that matches + * the desired set */ + down_read(&css_set_rwsem); + cset = find_existing_css_set(old_cset, cgrp, template); + if (cset) + get_css_set(cset); + up_read(&css_set_rwsem); + + if (cset) + return cset; + + cset = kzalloc(sizeof(*cset), GFP_KERNEL); + if (!cset) + return NULL; + + /* Allocate all the cgrp_cset_link objects that we'll need */ + if (allocate_cgrp_cset_links(cgroup_root_count, &tmp_links) < 0) { + kfree(cset); + return NULL; + } + + atomic_set(&cset->refcount, 1); + INIT_LIST_HEAD(&cset->cgrp_links); + INIT_LIST_HEAD(&cset->tasks); + INIT_LIST_HEAD(&cset->mg_tasks); + INIT_LIST_HEAD(&cset->mg_preload_node); + INIT_LIST_HEAD(&cset->mg_node); + INIT_HLIST_NODE(&cset->hlist); + + /* Copy the set of subsystem state objects generated in + * find_existing_css_set() */ + memcpy(cset->subsys, template, sizeof(cset->subsys)); + + down_write(&css_set_rwsem); + /* Add reference counts and links from the new css_set. */ + list_for_each_entry(link, &old_cset->cgrp_links, cgrp_link) { + struct cgroup *c = link->cgrp; + + if (c->root == cgrp->root) + c = cgrp; + link_css_set(&tmp_links, cset, c); + } + + BUG_ON(!list_empty(&tmp_links)); + + css_set_count++; + + /* Add @cset to the hash table */ + key = css_set_hash(cset->subsys); + hash_add(css_set_table, &cset->hlist, key); + + for_each_subsys(ss, ssid) + list_add_tail(&cset->e_cset_node[ssid], + &cset->subsys[ssid]->cgroup->e_csets[ssid]); + + up_write(&css_set_rwsem); + + return cset; +} + +static struct cgroup_root *cgroup_root_from_kf(struct kernfs_root *kf_root) +{ + struct cgroup *root_cgrp = kf_root->kn->priv; + + return root_cgrp->root; +} + +static int cgroup_init_root_id(struct cgroup_root *root) +{ + int id; + + lockdep_assert_held(&cgroup_mutex); + + id = idr_alloc_cyclic(&cgroup_hierarchy_idr, root, 0, 0, GFP_KERNEL); + if (id < 0) + return id; + + root->hierarchy_id = id; + return 0; +} + +static void cgroup_exit_root_id(struct cgroup_root *root) +{ + lockdep_assert_held(&cgroup_mutex); + + if (root->hierarchy_id) { + idr_remove(&cgroup_hierarchy_idr, root->hierarchy_id); + root->hierarchy_id = 0; + } +} + +static void cgroup_free_root(struct cgroup_root *root) +{ + if (root) { + /* hierarhcy ID shoulid already have been released */ + WARN_ON_ONCE(root->hierarchy_id); + + idr_destroy(&root->cgroup_idr); + kfree(root); + } +} + +static void cgroup_destroy_root(struct cgroup_root *root) +{ + struct cgroup *cgrp = &root->cgrp; + struct cgrp_cset_link *link, *tmp_link; + + mutex_lock(&cgroup_mutex); + + BUG_ON(atomic_read(&root->nr_cgrps)); + BUG_ON(!list_empty(&cgrp->self.children)); + + /* Rebind all subsystems back to the default hierarchy */ + rebind_subsystems(&cgrp_dfl_root, root->subsys_mask); + + /* + * Release all the links from cset_links to this hierarchy's + * root cgroup + */ + down_write(&css_set_rwsem); + + list_for_each_entry_safe(link, tmp_link, &cgrp->cset_links, cset_link) { + list_del(&link->cset_link); + list_del(&link->cgrp_link); + kfree(link); + } + up_write(&css_set_rwsem); + + if (!list_empty(&root->root_list)) { + list_del(&root->root_list); + cgroup_root_count--; + } + + cgroup_exit_root_id(root); + + mutex_unlock(&cgroup_mutex); + + kernfs_destroy_root(root->kf_root); + cgroup_free_root(root); +} + +/* look up cgroup associated with given css_set on the specified hierarchy */ +static struct cgroup *cset_cgroup_from_root(struct css_set *cset, + struct cgroup_root *root) +{ + struct cgroup *res = NULL; + + lockdep_assert_held(&cgroup_mutex); + lockdep_assert_held(&css_set_rwsem); + + if (cset == &init_css_set) { + res = &root->cgrp; + } else { + struct cgrp_cset_link *link; + + list_for_each_entry(link, &cset->cgrp_links, cgrp_link) { + struct cgroup *c = link->cgrp; + + if (c->root == root) { + res = c; + break; + } + } + } + + BUG_ON(!res); + return res; +} + +/* + * Return the cgroup for "task" from the given hierarchy. Must be + * called with cgroup_mutex and css_set_rwsem held. + */ +static struct cgroup *task_cgroup_from_root(struct task_struct *task, + struct cgroup_root *root) +{ + /* + * No need to lock the task - since we hold cgroup_mutex the + * task can't change groups, so the only thing that can happen + * is that it exits and its css is set back to init_css_set. + */ + return cset_cgroup_from_root(task_css_set(task), root); +} + +/* + * A task must hold cgroup_mutex to modify cgroups. + * + * Any task can increment and decrement the count field without lock. + * So in general, code holding cgroup_mutex can't rely on the count + * field not changing. However, if the count goes to zero, then only + * cgroup_attach_task() can increment it again. Because a count of zero + * means that no tasks are currently attached, therefore there is no + * way a task attached to that cgroup can fork (the other way to + * increment the count). So code holding cgroup_mutex can safely + * assume that if the count is zero, it will stay zero. Similarly, if + * a task holds cgroup_mutex on a cgroup with zero count, it + * knows that the cgroup won't be removed, as cgroup_rmdir() + * needs that mutex. + * + * A cgroup can only be deleted if both its 'count' of using tasks + * is zero, and its list of 'children' cgroups is empty. Since all + * tasks in the system use _some_ cgroup, and since there is always at + * least one task in the system (init, pid == 1), therefore, root cgroup + * always has either children cgroups and/or using tasks. So we don't + * need a special hack to ensure that root cgroup cannot be deleted. + * + * P.S. One more locking exception. RCU is used to guard the + * update of a tasks cgroup pointer by cgroup_attach_task() + */ + +static int cgroup_populate_dir(struct cgroup *cgrp, unsigned int subsys_mask); +static struct kernfs_syscall_ops cgroup_kf_syscall_ops; +static const struct file_operations proc_cgroupstats_operations; + +static char *cgroup_file_name(struct cgroup *cgrp, const struct cftype *cft, + char *buf) +{ + if (cft->ss && !(cft->flags & CFTYPE_NO_PREFIX) && + !(cgrp->root->flags & CGRP_ROOT_NOPREFIX)) + snprintf(buf, CGROUP_FILE_NAME_MAX, "%s.%s", + cft->ss->name, cft->name); + else + strncpy(buf, cft->name, CGROUP_FILE_NAME_MAX); + return buf; +} + +/** + * cgroup_file_mode - deduce file mode of a control file + * @cft: the control file in question + * + * returns cft->mode if ->mode is not 0 + * returns S_IRUGO|S_IWUSR if it has both a read and a write handler + * returns S_IRUGO if it has only a read handler + * returns S_IWUSR if it has only a write hander + */ +static umode_t cgroup_file_mode(const struct cftype *cft) +{ + umode_t mode = 0; + + if (cft->mode) + return cft->mode; + + if (cft->read_u64 || cft->read_s64 || cft->seq_show) + mode |= S_IRUGO; + + if (cft->write_u64 || cft->write_s64 || cft->write) + mode |= S_IWUSR; + + return mode; +} + +static void cgroup_get(struct cgroup *cgrp) +{ + WARN_ON_ONCE(cgroup_is_dead(cgrp)); + css_get(&cgrp->self); +} + +static bool cgroup_tryget(struct cgroup *cgrp) +{ + return css_tryget(&cgrp->self); +} + +static void cgroup_put(struct cgroup *cgrp) +{ + css_put(&cgrp->self); +} + +/** + * cgroup_calc_child_subsys_mask - calculate child_subsys_mask + * @cgrp: the target cgroup + * @subtree_control: the new subtree_control mask to consider + * + * On the default hierarchy, a subsystem may request other subsystems to be + * enabled together through its ->depends_on mask. In such cases, more + * subsystems than specified in "cgroup.subtree_control" may be enabled. + * + * This function calculates which subsystems need to be enabled if + * @subtree_control is to be applied to @cgrp. The returned mask is always + * a superset of @subtree_control and follows the usual hierarchy rules. + */ +static unsigned int cgroup_calc_child_subsys_mask(struct cgroup *cgrp, + unsigned int subtree_control) +{ + struct cgroup *parent = cgroup_parent(cgrp); + unsigned int cur_ss_mask = subtree_control; + struct cgroup_subsys *ss; + int ssid; + + lockdep_assert_held(&cgroup_mutex); + + if (!cgroup_on_dfl(cgrp)) + return cur_ss_mask; + + while (true) { + unsigned int new_ss_mask = cur_ss_mask; + + for_each_subsys(ss, ssid) + if (cur_ss_mask & (1 << ssid)) + new_ss_mask |= ss->depends_on; + + /* + * Mask out subsystems which aren't available. This can + * happen only if some depended-upon subsystems were bound + * to non-default hierarchies. + */ + if (parent) + new_ss_mask &= parent->child_subsys_mask; + else + new_ss_mask &= cgrp->root->subsys_mask; + + if (new_ss_mask == cur_ss_mask) + break; + cur_ss_mask = new_ss_mask; + } + + return cur_ss_mask; +} + +/** + * cgroup_refresh_child_subsys_mask - update child_subsys_mask + * @cgrp: the target cgroup + * + * Update @cgrp->child_subsys_mask according to the current + * @cgrp->subtree_control using cgroup_calc_child_subsys_mask(). + */ +static void cgroup_refresh_child_subsys_mask(struct cgroup *cgrp) +{ + cgrp->child_subsys_mask = + cgroup_calc_child_subsys_mask(cgrp, cgrp->subtree_control); +} + +/** + * cgroup_kn_unlock - unlocking helper for cgroup kernfs methods + * @kn: the kernfs_node being serviced + * + * This helper undoes cgroup_kn_lock_live() and should be invoked before + * the method finishes if locking succeeded. Note that once this function + * returns the cgroup returned by cgroup_kn_lock_live() may become + * inaccessible any time. If the caller intends to continue to access the + * cgroup, it should pin it before invoking this function. + */ +static void cgroup_kn_unlock(struct kernfs_node *kn) +{ + struct cgroup *cgrp; + + if (kernfs_type(kn) == KERNFS_DIR) + cgrp = kn->priv; + else + cgrp = kn->parent->priv; + + mutex_unlock(&cgroup_mutex); + + kernfs_unbreak_active_protection(kn); + cgroup_put(cgrp); +} + +/** + * cgroup_kn_lock_live - locking helper for cgroup kernfs methods + * @kn: the kernfs_node being serviced + * + * This helper is to be used by a cgroup kernfs method currently servicing + * @kn. It breaks the active protection, performs cgroup locking and + * verifies that the associated cgroup is alive. Returns the cgroup if + * alive; otherwise, %NULL. A successful return should be undone by a + * matching cgroup_kn_unlock() invocation. + * + * Any cgroup kernfs method implementation which requires locking the + * associated cgroup should use this helper. It avoids nesting cgroup + * locking under kernfs active protection and allows all kernfs operations + * including self-removal. + */ +static struct cgroup *cgroup_kn_lock_live(struct kernfs_node *kn) +{ + struct cgroup *cgrp; + + if (kernfs_type(kn) == KERNFS_DIR) + cgrp = kn->priv; + else + cgrp = kn->parent->priv; + + /* + * We're gonna grab cgroup_mutex which nests outside kernfs + * active_ref. cgroup liveliness check alone provides enough + * protection against removal. Ensure @cgrp stays accessible and + * break the active_ref protection. + */ + if (!cgroup_tryget(cgrp)) + return NULL; + kernfs_break_active_protection(kn); + + mutex_lock(&cgroup_mutex); + + if (!cgroup_is_dead(cgrp)) + return cgrp; + + cgroup_kn_unlock(kn); + return NULL; +} + +static void cgroup_rm_file(struct cgroup *cgrp, const struct cftype *cft) +{ + char name[CGROUP_FILE_NAME_MAX]; + + lockdep_assert_held(&cgroup_mutex); + kernfs_remove_by_name(cgrp->kn, cgroup_file_name(cgrp, cft, name)); +} + +/** + * cgroup_clear_dir - remove subsys files in a cgroup directory + * @cgrp: target cgroup + * @subsys_mask: mask of the subsystem ids whose files should be removed + */ +static void cgroup_clear_dir(struct cgroup *cgrp, unsigned int subsys_mask) +{ + struct cgroup_subsys *ss; + int i; + + for_each_subsys(ss, i) { + struct cftype *cfts; + + if (!(subsys_mask & (1 << i))) + continue; + list_for_each_entry(cfts, &ss->cfts, node) + cgroup_addrm_files(cgrp, cfts, false); + } +} + +static int rebind_subsystems(struct cgroup_root *dst_root, unsigned int ss_mask) +{ + struct cgroup_subsys *ss; + unsigned int tmp_ss_mask; + int ssid, i, ret; + + lockdep_assert_held(&cgroup_mutex); + + for_each_subsys(ss, ssid) { + if (!(ss_mask & (1 << ssid))) + continue; + + /* if @ss has non-root csses attached to it, can't move */ + if (css_next_child(NULL, cgroup_css(&ss->root->cgrp, ss))) + return -EBUSY; + + /* can't move between two non-dummy roots either */ + if (ss->root != &cgrp_dfl_root && dst_root != &cgrp_dfl_root) + return -EBUSY; + } + + /* skip creating root files on dfl_root for inhibited subsystems */ + tmp_ss_mask = ss_mask; + if (dst_root == &cgrp_dfl_root) + tmp_ss_mask &= ~cgrp_dfl_root_inhibit_ss_mask; + + ret = cgroup_populate_dir(&dst_root->cgrp, tmp_ss_mask); + if (ret) { + if (dst_root != &cgrp_dfl_root) + return ret; + + /* + * Rebinding back to the default root is not allowed to + * fail. Using both default and non-default roots should + * be rare. Moving subsystems back and forth even more so. + * Just warn about it and continue. + */ + if (cgrp_dfl_root_visible) { + pr_warn("failed to create files (%d) while rebinding 0x%x to default root\n", + ret, ss_mask); + pr_warn("you may retry by moving them to a different hierarchy and unbinding\n"); + } + } + + /* + * Nothing can fail from this point on. Remove files for the + * removed subsystems and rebind each subsystem. + */ + for_each_subsys(ss, ssid) + if (ss_mask & (1 << ssid)) + cgroup_clear_dir(&ss->root->cgrp, 1 << ssid); + + for_each_subsys(ss, ssid) { + struct cgroup_root *src_root; + struct cgroup_subsys_state *css; + struct css_set *cset; + + if (!(ss_mask & (1 << ssid))) + continue; + + src_root = ss->root; + css = cgroup_css(&src_root->cgrp, ss); + + WARN_ON(!css || cgroup_css(&dst_root->cgrp, ss)); + + RCU_INIT_POINTER(src_root->cgrp.subsys[ssid], NULL); + rcu_assign_pointer(dst_root->cgrp.subsys[ssid], css); + ss->root = dst_root; + css->cgroup = &dst_root->cgrp; + + down_write(&css_set_rwsem); + hash_for_each(css_set_table, i, cset, hlist) + list_move_tail(&cset->e_cset_node[ss->id], + &dst_root->cgrp.e_csets[ss->id]); + up_write(&css_set_rwsem); + + src_root->subsys_mask &= ~(1 << ssid); + src_root->cgrp.subtree_control &= ~(1 << ssid); + cgroup_refresh_child_subsys_mask(&src_root->cgrp); + + /* default hierarchy doesn't enable controllers by default */ + dst_root->subsys_mask |= 1 << ssid; + if (dst_root != &cgrp_dfl_root) { + dst_root->cgrp.subtree_control |= 1 << ssid; + cgroup_refresh_child_subsys_mask(&dst_root->cgrp); + } + + if (ss->bind) + ss->bind(css); + } + + kernfs_activate(dst_root->cgrp.kn); + return 0; +} + +static int cgroup_show_options(struct seq_file *seq, + struct kernfs_root *kf_root) +{ + struct cgroup_root *root = cgroup_root_from_kf(kf_root); + struct cgroup_subsys *ss; + int ssid; + + for_each_subsys(ss, ssid) + if (root->subsys_mask & (1 << ssid)) + seq_printf(seq, ",%s", ss->name); + if (root->flags & CGRP_ROOT_NOPREFIX) + seq_puts(seq, ",noprefix"); + if (root->flags & CGRP_ROOT_XATTR) + seq_puts(seq, ",xattr"); + + spin_lock(&release_agent_path_lock); + if (strlen(root->release_agent_path)) + seq_printf(seq, ",release_agent=%s", root->release_agent_path); + spin_unlock(&release_agent_path_lock); + + if (test_bit(CGRP_CPUSET_CLONE_CHILDREN, &root->cgrp.flags)) + seq_puts(seq, ",clone_children"); + if (strlen(root->name)) + seq_printf(seq, ",name=%s", root->name); + return 0; +} + +struct cgroup_sb_opts { + unsigned int subsys_mask; + unsigned int flags; + char *release_agent; + bool cpuset_clone_children; + char *name; + /* User explicitly requested empty subsystem */ + bool none; +}; + +static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts) +{ + char *token, *o = data; + bool all_ss = false, one_ss = false; + unsigned int mask = -1U; + struct cgroup_subsys *ss; + int nr_opts = 0; + int i; + +#ifdef CONFIG_CPUSETS + mask = ~(1U << cpuset_cgrp_id); +#endif + + memset(opts, 0, sizeof(*opts)); + + while ((token = strsep(&o, ",")) != NULL) { + nr_opts++; + + if (!*token) + return -EINVAL; + if (!strcmp(token, "none")) { + /* Explicitly have no subsystems */ + opts->none = true; + continue; + } + if (!strcmp(token, "all")) { + /* Mutually exclusive option 'all' + subsystem name */ + if (one_ss) + return -EINVAL; + all_ss = true; + continue; + } + if (!strcmp(token, "__DEVEL__sane_behavior")) { + opts->flags |= CGRP_ROOT_SANE_BEHAVIOR; + continue; + } + if (!strcmp(token, "noprefix")) { + opts->flags |= CGRP_ROOT_NOPREFIX; + continue; + } + if (!strcmp(token, "clone_children")) { + opts->cpuset_clone_children = true; + continue; + } + if (!strcmp(token, "xattr")) { + opts->flags |= CGRP_ROOT_XATTR; + continue; + } + if (!strncmp(token, "release_agent=", 14)) { + /* Specifying two release agents is forbidden */ + if (opts->release_agent) + return -EINVAL; + opts->release_agent = + kstrndup(token + 14, PATH_MAX - 1, GFP_KERNEL); + if (!opts->release_agent) + return -ENOMEM; + continue; + } + if (!strncmp(token, "name=", 5)) { + const char *name = token + 5; + /* Can't specify an empty name */ + if (!strlen(name)) + return -EINVAL; + /* Must match [\w.-]+ */ + for (i = 0; i < strlen(name); i++) { + char c = name[i]; + if (isalnum(c)) + continue; + if ((c == '.') || (c == '-') || (c == '_')) + continue; + return -EINVAL; + } + /* Specifying two names is forbidden */ + if (opts->name) + return -EINVAL; + opts->name = kstrndup(name, + MAX_CGROUP_ROOT_NAMELEN - 1, + GFP_KERNEL); + if (!opts->name) + return -ENOMEM; + + continue; + } + + for_each_subsys(ss, i) { + if (strcmp(token, ss->name)) + continue; + if (ss->disabled) + continue; + + /* Mutually exclusive option 'all' + subsystem name */ + if (all_ss) + return -EINVAL; + opts->subsys_mask |= (1 << i); + one_ss = true; + + break; + } + if (i == CGROUP_SUBSYS_COUNT) + return -ENOENT; + } + + if (opts->flags & CGRP_ROOT_SANE_BEHAVIOR) { + pr_warn("sane_behavior: this is still under development and its behaviors will change, proceed at your own risk\n"); + if (nr_opts != 1) { + pr_err("sane_behavior: no other mount options allowed\n"); + return -EINVAL; + } + return 0; + } + + /* + * If the 'all' option was specified select all the subsystems, + * otherwise if 'none', 'name=' and a subsystem name options were + * not specified, let's default to 'all' + */ + if (all_ss || (!one_ss && !opts->none && !opts->name)) + for_each_subsys(ss, i) + if (!ss->disabled) + opts->subsys_mask |= (1 << i); + + /* + * We either have to specify by name or by subsystems. (So all + * empty hierarchies must have a name). + */ + if (!opts->subsys_mask && !opts->name) + return -EINVAL; + + /* + * Option noprefix was introduced just for backward compatibility + * with the old cpuset, so we allow noprefix only if mounting just + * the cpuset subsystem. + */ + if ((opts->flags & CGRP_ROOT_NOPREFIX) && (opts->subsys_mask & mask)) + return -EINVAL; + + /* Can't specify "none" and some subsystems */ + if (opts->subsys_mask && opts->none) + return -EINVAL; + + return 0; +} + +static int cgroup_remount(struct kernfs_root *kf_root, int *flags, char *data) +{ + int ret = 0; + struct cgroup_root *root = cgroup_root_from_kf(kf_root); + struct cgroup_sb_opts opts; + unsigned int added_mask, removed_mask; + + if (root == &cgrp_dfl_root) { + pr_err("remount is not allowed\n"); + return -EINVAL; + } + + mutex_lock(&cgroup_mutex); + + /* See what subsystems are wanted */ + ret = parse_cgroupfs_options(data, &opts); + if (ret) + goto out_unlock; + + if (opts.subsys_mask != root->subsys_mask || opts.release_agent) + pr_warn("option changes via remount are deprecated (pid=%d comm=%s)\n", + task_tgid_nr(current), current->comm); + + added_mask = opts.subsys_mask & ~root->subsys_mask; + removed_mask = root->subsys_mask & ~opts.subsys_mask; + + /* Don't allow flags or name to change at remount */ + if ((opts.flags ^ root->flags) || + (opts.name && strcmp(opts.name, root->name))) { + pr_err("option or name mismatch, new: 0x%x \"%s\", old: 0x%x \"%s\"\n", + opts.flags, opts.name ?: "", root->flags, root->name); + ret = -EINVAL; + goto out_unlock; + } + + /* remounting is not allowed for populated hierarchies */ + if (!list_empty(&root->cgrp.self.children)) { + ret = -EBUSY; + goto out_unlock; + } + + ret = rebind_subsystems(root, added_mask); + if (ret) + goto out_unlock; + + rebind_subsystems(&cgrp_dfl_root, removed_mask); + + if (opts.release_agent) { + spin_lock(&release_agent_path_lock); + strcpy(root->release_agent_path, opts.release_agent); + spin_unlock(&release_agent_path_lock); + } + out_unlock: + kfree(opts.release_agent); + kfree(opts.name); + mutex_unlock(&cgroup_mutex); + return ret; +} + +/* + * To reduce the fork() overhead for systems that are not actually using + * their cgroups capability, we don't maintain the lists running through + * each css_set to its tasks until we see the list actually used - in other + * words after the first mount. + */ +static bool use_task_css_set_links __read_mostly; + +static void cgroup_enable_task_cg_lists(void) +{ + struct task_struct *p, *g; + + down_write(&css_set_rwsem); + + if (use_task_css_set_links) + goto out_unlock; + + use_task_css_set_links = true; + + /* + * We need tasklist_lock because RCU is not safe against + * while_each_thread(). Besides, a forking task that has passed + * cgroup_post_fork() without seeing use_task_css_set_links = 1 + * is not guaranteed to have its child immediately visible in the + * tasklist if we walk through it with RCU. + */ + read_lock(&tasklist_lock); + do_each_thread(g, p) { + WARN_ON_ONCE(!list_empty(&p->cg_list) || + task_css_set(p) != &init_css_set); + + /* + * We should check if the process is exiting, otherwise + * it will race with cgroup_exit() in that the list + * entry won't be deleted though the process has exited. + * Do it while holding siglock so that we don't end up + * racing against cgroup_exit(). + */ + spin_lock_irq(&p->sighand->siglock); + if (!(p->flags & PF_EXITING)) { + struct css_set *cset = task_css_set(p); + + list_add(&p->cg_list, &cset->tasks); + get_css_set(cset); + } + spin_unlock_irq(&p->sighand->siglock); + } while_each_thread(g, p); + read_unlock(&tasklist_lock); +out_unlock: + up_write(&css_set_rwsem); +} + +static void init_cgroup_housekeeping(struct cgroup *cgrp) +{ + struct cgroup_subsys *ss; + int ssid; + + INIT_LIST_HEAD(&cgrp->self.sibling); + INIT_LIST_HEAD(&cgrp->self.children); + INIT_LIST_HEAD(&cgrp->cset_links); + INIT_LIST_HEAD(&cgrp->pidlists); + mutex_init(&cgrp->pidlist_mutex); + cgrp->self.cgroup = cgrp; + cgrp->self.flags |= CSS_ONLINE; + + for_each_subsys(ss, ssid) + INIT_LIST_HEAD(&cgrp->e_csets[ssid]); + + init_waitqueue_head(&cgrp->offline_waitq); + INIT_WORK(&cgrp->release_agent_work, cgroup_release_agent); +} + +static void init_cgroup_root(struct cgroup_root *root, + struct cgroup_sb_opts *opts) +{ + struct cgroup *cgrp = &root->cgrp; + + INIT_LIST_HEAD(&root->root_list); + atomic_set(&root->nr_cgrps, 1); + cgrp->root = root; + init_cgroup_housekeeping(cgrp); + idr_init(&root->cgroup_idr); + + root->flags = opts->flags; + if (opts->release_agent) + strcpy(root->release_agent_path, opts->release_agent); + if (opts->name) + strcpy(root->name, opts->name); + if (opts->cpuset_clone_children) + set_bit(CGRP_CPUSET_CLONE_CHILDREN, &root->cgrp.flags); +} + +static int cgroup_setup_root(struct cgroup_root *root, unsigned int ss_mask) +{ + LIST_HEAD(tmp_links); + struct cgroup *root_cgrp = &root->cgrp; + struct cftype *base_files; + struct css_set *cset; + int i, ret; + + lockdep_assert_held(&cgroup_mutex); + + ret = cgroup_idr_alloc(&root->cgroup_idr, root_cgrp, 1, 2, GFP_NOWAIT); + if (ret < 0) + goto out; + root_cgrp->id = ret; + + ret = percpu_ref_init(&root_cgrp->self.refcnt, css_release, 0, + GFP_KERNEL); + if (ret) + goto out; + + /* + * We're accessing css_set_count without locking css_set_rwsem here, + * but that's OK - it can only be increased by someone holding + * cgroup_lock, and that's us. The worst that can happen is that we + * have some link structures left over + */ + ret = allocate_cgrp_cset_links(css_set_count, &tmp_links); + if (ret) + goto cancel_ref; + + ret = cgroup_init_root_id(root); + if (ret) + goto cancel_ref; + + root->kf_root = kernfs_create_root(&cgroup_kf_syscall_ops, + KERNFS_ROOT_CREATE_DEACTIVATED, + root_cgrp); + if (IS_ERR(root->kf_root)) { + ret = PTR_ERR(root->kf_root); + goto exit_root_id; + } + root_cgrp->kn = root->kf_root->kn; + + if (root == &cgrp_dfl_root) + base_files = cgroup_dfl_base_files; + else + base_files = cgroup_legacy_base_files; + + ret = cgroup_addrm_files(root_cgrp, base_files, true); + if (ret) + goto destroy_root; + + ret = rebind_subsystems(root, ss_mask); + if (ret) + goto destroy_root; + + /* + * There must be no failure case after here, since rebinding takes + * care of subsystems' refcounts, which are explicitly dropped in + * the failure exit path. + */ + list_add(&root->root_list, &cgroup_roots); + cgroup_root_count++; + + /* + * Link the root cgroup in this hierarchy into all the css_set + * objects. + */ + down_write(&css_set_rwsem); + hash_for_each(css_set_table, i, cset, hlist) + link_css_set(&tmp_links, cset, root_cgrp); + up_write(&css_set_rwsem); + + BUG_ON(!list_empty(&root_cgrp->self.children)); + BUG_ON(atomic_read(&root->nr_cgrps) != 1); + + kernfs_activate(root_cgrp->kn); + ret = 0; + goto out; + +destroy_root: + kernfs_destroy_root(root->kf_root); + root->kf_root = NULL; +exit_root_id: + cgroup_exit_root_id(root); +cancel_ref: + percpu_ref_exit(&root_cgrp->self.refcnt); +out: + free_cgrp_cset_links(&tmp_links); + return ret; +} + +static struct dentry *cgroup_mount(struct file_system_type *fs_type, + int flags, const char *unused_dev_name, + void *data) +{ + struct super_block *pinned_sb = NULL; + struct cgroup_subsys *ss; + struct cgroup_root *root; + struct cgroup_sb_opts opts; + struct dentry *dentry; + int ret; + int i; + bool new_sb; + + /* + * The first time anyone tries to mount a cgroup, enable the list + * linking each css_set to its tasks and fix up all existing tasks. + */ + if (!use_task_css_set_links) + cgroup_enable_task_cg_lists(); + + mutex_lock(&cgroup_mutex); + + /* First find the desired set of subsystems */ + ret = parse_cgroupfs_options(data, &opts); + if (ret) + goto out_unlock; + + /* look for a matching existing root */ + if (opts.flags & CGRP_ROOT_SANE_BEHAVIOR) { + cgrp_dfl_root_visible = true; + root = &cgrp_dfl_root; + cgroup_get(&root->cgrp); + ret = 0; + goto out_unlock; + } + + /* + * Destruction of cgroup root is asynchronous, so subsystems may + * still be dying after the previous unmount. Let's drain the + * dying subsystems. We just need to ensure that the ones + * unmounted previously finish dying and don't care about new ones + * starting. Testing ref liveliness is good enough. + */ + for_each_subsys(ss, i) { + if (!(opts.subsys_mask & (1 << i)) || + ss->root == &cgrp_dfl_root) + continue; + + if (!percpu_ref_tryget_live(&ss->root->cgrp.self.refcnt)) { + mutex_unlock(&cgroup_mutex); + msleep(10); + ret = restart_syscall(); + goto out_free; + } + cgroup_put(&ss->root->cgrp); + } + + for_each_root(root) { + bool name_match = false; + + if (root == &cgrp_dfl_root) + continue; + + /* + * If we asked for a name then it must match. Also, if + * name matches but sybsys_mask doesn't, we should fail. + * Remember whether name matched. + */ + if (opts.name) { + if (strcmp(opts.name, root->name)) + continue; + name_match = true; + } + + /* + * If we asked for subsystems (or explicitly for no + * subsystems) then they must match. + */ + if ((opts.subsys_mask || opts.none) && + (opts.subsys_mask != root->subsys_mask)) { + if (!name_match) + continue; + ret = -EBUSY; + goto out_unlock; + } + + if (root->flags ^ opts.flags) + pr_warn("new mount options do not match the existing superblock, will be ignored\n"); + + /* + * We want to reuse @root whose lifetime is governed by its + * ->cgrp. Let's check whether @root is alive and keep it + * that way. As cgroup_kill_sb() can happen anytime, we + * want to block it by pinning the sb so that @root doesn't + * get killed before mount is complete. + * + * With the sb pinned, tryget_live can reliably indicate + * whether @root can be reused. If it's being killed, + * drain it. We can use wait_queue for the wait but this + * path is super cold. Let's just sleep a bit and retry. + */ + pinned_sb = kernfs_pin_sb(root->kf_root, NULL); + if (IS_ERR(pinned_sb) || + !percpu_ref_tryget_live(&root->cgrp.self.refcnt)) { + mutex_unlock(&cgroup_mutex); + if (!IS_ERR_OR_NULL(pinned_sb)) + deactivate_super(pinned_sb); + msleep(10); + ret = restart_syscall(); + goto out_free; + } + + ret = 0; + goto out_unlock; + } + + /* + * No such thing, create a new one. name= matching without subsys + * specification is allowed for already existing hierarchies but we + * can't create new one without subsys specification. + */ + if (!opts.subsys_mask && !opts.none) { + ret = -EINVAL; + goto out_unlock; + } + + root = kzalloc(sizeof(*root), GFP_KERNEL); + if (!root) { + ret = -ENOMEM; + goto out_unlock; + } + + init_cgroup_root(root, &opts); + + ret = cgroup_setup_root(root, opts.subsys_mask); + if (ret) + cgroup_free_root(root); + +out_unlock: + mutex_unlock(&cgroup_mutex); +out_free: + kfree(opts.release_agent); + kfree(opts.name); + + if (ret) + return ERR_PTR(ret); + + dentry = kernfs_mount(fs_type, flags, root->kf_root, + CGROUP_SUPER_MAGIC, &new_sb); + if (IS_ERR(dentry) || !new_sb) + cgroup_put(&root->cgrp); + + /* + * If @pinned_sb, we're reusing an existing root and holding an + * extra ref on its sb. Mount is complete. Put the extra ref. + */ + if (pinned_sb) { + WARN_ON(new_sb); + deactivate_super(pinned_sb); + } + + return dentry; +} + +static void cgroup_kill_sb(struct super_block *sb) +{ + struct kernfs_root *kf_root = kernfs_root_from_sb(sb); + struct cgroup_root *root = cgroup_root_from_kf(kf_root); + + /* + * If @root doesn't have any mounts or children, start killing it. + * This prevents new mounts by disabling percpu_ref_tryget_live(). + * cgroup_mount() may wait for @root's release. + * + * And don't kill the default root. + */ + if (!list_empty(&root->cgrp.self.children) || + root == &cgrp_dfl_root) + cgroup_put(&root->cgrp); + else + percpu_ref_kill(&root->cgrp.self.refcnt); + + kernfs_kill_sb(sb); +} + +static struct file_system_type cgroup_fs_type = { + .name = "cgroup", + .mount = cgroup_mount, + .kill_sb = cgroup_kill_sb, +}; + +/** + * task_cgroup_path - cgroup path of a task in the first cgroup hierarchy + * @task: target task + * @buf: the buffer to write the path into + * @buflen: the length of the buffer + * + * Determine @task's cgroup on the first (the one with the lowest non-zero + * hierarchy_id) cgroup hierarchy and copy its path into @buf. This + * function grabs cgroup_mutex and shouldn't be used inside locks used by + * cgroup controller callbacks. + * + * Return value is the same as kernfs_path(). + */ +char *task_cgroup_path(struct task_struct *task, char *buf, size_t buflen) +{ + struct cgroup_root *root; + struct cgroup *cgrp; + int hierarchy_id = 1; + char *path = NULL; + + mutex_lock(&cgroup_mutex); + down_read(&css_set_rwsem); + + root = idr_get_next(&cgroup_hierarchy_idr, &hierarchy_id); + + if (root) { + cgrp = task_cgroup_from_root(task, root); + path = cgroup_path(cgrp, buf, buflen); + } else { + /* if no hierarchy exists, everyone is in "/" */ + if (strlcpy(buf, "/", buflen) < buflen) + path = buf; + } + + up_read(&css_set_rwsem); + mutex_unlock(&cgroup_mutex); + return path; +} +EXPORT_SYMBOL_GPL(task_cgroup_path); + +/* used to track tasks and other necessary states during migration */ +struct cgroup_taskset { + /* the src and dst cset list running through cset->mg_node */ + struct list_head src_csets; + struct list_head dst_csets; + + /* + * Fields for cgroup_taskset_*() iteration. + * + * Before migration is committed, the target migration tasks are on + * ->mg_tasks of the csets on ->src_csets. After, on ->mg_tasks of + * the csets on ->dst_csets. ->csets point to either ->src_csets + * or ->dst_csets depending on whether migration is committed. + * + * ->cur_csets and ->cur_task point to the current task position + * during iteration. + */ + struct list_head *csets; + struct css_set *cur_cset; + struct task_struct *cur_task; +}; + +/** + * cgroup_taskset_first - reset taskset and return the first task + * @tset: taskset of interest + * + * @tset iteration is initialized and the first task is returned. + */ +struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset) +{ + tset->cur_cset = list_first_entry(tset->csets, struct css_set, mg_node); + tset->cur_task = NULL; + + return cgroup_taskset_next(tset); +} + +/** + * cgroup_taskset_next - iterate to the next task in taskset + * @tset: taskset of interest + * + * Return the next task in @tset. Iteration must have been initialized + * with cgroup_taskset_first(). + */ +struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset) +{ + struct css_set *cset = tset->cur_cset; + struct task_struct *task = tset->cur_task; + + while (&cset->mg_node != tset->csets) { + if (!task) + task = list_first_entry(&cset->mg_tasks, + struct task_struct, cg_list); + else + task = list_next_entry(task, cg_list); + + if (&task->cg_list != &cset->mg_tasks) { + tset->cur_cset = cset; + tset->cur_task = task; + return task; + } + + cset = list_next_entry(cset, mg_node); + task = NULL; + } + + return NULL; +} + +/** + * cgroup_task_migrate - move a task from one cgroup to another. + * @old_cgrp: the cgroup @tsk is being migrated from + * @tsk: the task being migrated + * @new_cset: the new css_set @tsk is being attached to + * + * Must be called with cgroup_mutex, threadgroup and css_set_rwsem locked. + */ +static void cgroup_task_migrate(struct cgroup *old_cgrp, + struct task_struct *tsk, + struct css_set *new_cset) +{ + struct css_set *old_cset; + + lockdep_assert_held(&cgroup_mutex); + lockdep_assert_held(&css_set_rwsem); + + /* + * We are synchronized through threadgroup_lock() against PF_EXITING + * setting such that we can't race against cgroup_exit() changing the + * css_set to init_css_set and dropping the old one. + */ + WARN_ON_ONCE(tsk->flags & PF_EXITING); + old_cset = task_css_set(tsk); + + get_css_set(new_cset); + rcu_assign_pointer(tsk->cgroups, new_cset); + + /* + * Use move_tail so that cgroup_taskset_first() still returns the + * leader after migration. This works because cgroup_migrate() + * ensures that the dst_cset of the leader is the first on the + * tset's dst_csets list. + */ + list_move_tail(&tsk->cg_list, &new_cset->mg_tasks); + + /* + * We just gained a reference on old_cset by taking it from the + * task. As trading it for new_cset is protected by cgroup_mutex, + * we're safe to drop it here; it will be freed under RCU. + */ + put_css_set_locked(old_cset); +} + +/** + * cgroup_migrate_finish - cleanup after attach + * @preloaded_csets: list of preloaded css_sets + * + * Undo cgroup_migrate_add_src() and cgroup_migrate_prepare_dst(). See + * those functions for details. + */ +static void cgroup_migrate_finish(struct list_head *preloaded_csets) +{ + struct css_set *cset, *tmp_cset; + + lockdep_assert_held(&cgroup_mutex); + + down_write(&css_set_rwsem); + list_for_each_entry_safe(cset, tmp_cset, preloaded_csets, mg_preload_node) { + cset->mg_src_cgrp = NULL; + cset->mg_dst_cset = NULL; + list_del_init(&cset->mg_preload_node); + put_css_set_locked(cset); + } + up_write(&css_set_rwsem); +} + +/** + * cgroup_migrate_add_src - add a migration source css_set + * @src_cset: the source css_set to add + * @dst_cgrp: the destination cgroup + * @preloaded_csets: list of preloaded css_sets + * + * Tasks belonging to @src_cset are about to be migrated to @dst_cgrp. Pin + * @src_cset and add it to @preloaded_csets, which should later be cleaned + * up by cgroup_migrate_finish(). + * + * This function may be called without holding threadgroup_lock even if the + * target is a process. Threads may be created and destroyed but as long + * as cgroup_mutex is not dropped, no new css_set can be put into play and + * the preloaded css_sets are guaranteed to cover all migrations. + */ +static void cgroup_migrate_add_src(struct css_set *src_cset, + struct cgroup *dst_cgrp, + struct list_head *preloaded_csets) +{ + struct cgroup *src_cgrp; + + lockdep_assert_held(&cgroup_mutex); + lockdep_assert_held(&css_set_rwsem); + + src_cgrp = cset_cgroup_from_root(src_cset, dst_cgrp->root); + + if (!list_empty(&src_cset->mg_preload_node)) + return; + + WARN_ON(src_cset->mg_src_cgrp); + WARN_ON(!list_empty(&src_cset->mg_tasks)); + WARN_ON(!list_empty(&src_cset->mg_node)); + + src_cset->mg_src_cgrp = src_cgrp; + get_css_set(src_cset); + list_add(&src_cset->mg_preload_node, preloaded_csets); +} + +/** + * cgroup_migrate_prepare_dst - prepare destination css_sets for migration + * @dst_cgrp: the destination cgroup (may be %NULL) + * @preloaded_csets: list of preloaded source css_sets + * + * Tasks are about to be moved to @dst_cgrp and all the source css_sets + * have been preloaded to @preloaded_csets. This function looks up and + * pins all destination css_sets, links each to its source, and append them + * to @preloaded_csets. If @dst_cgrp is %NULL, the destination of each + * source css_set is assumed to be its cgroup on the default hierarchy. + * + * This function must be called after cgroup_migrate_add_src() has been + * called on each migration source css_set. After migration is performed + * using cgroup_migrate(), cgroup_migrate_finish() must be called on + * @preloaded_csets. + */ +static int cgroup_migrate_prepare_dst(struct cgroup *dst_cgrp, + struct list_head *preloaded_csets) +{ + LIST_HEAD(csets); + struct css_set *src_cset, *tmp_cset; + + lockdep_assert_held(&cgroup_mutex); + + /* + * Except for the root, child_subsys_mask must be zero for a cgroup + * with tasks so that child cgroups don't compete against tasks. + */ + if (dst_cgrp && cgroup_on_dfl(dst_cgrp) && cgroup_parent(dst_cgrp) && + dst_cgrp->child_subsys_mask) + return -EBUSY; + + /* look up the dst cset for each src cset and link it to src */ + list_for_each_entry_safe(src_cset, tmp_cset, preloaded_csets, mg_preload_node) { + struct css_set *dst_cset; + + dst_cset = find_css_set(src_cset, + dst_cgrp ?: src_cset->dfl_cgrp); + if (!dst_cset) + goto err; + + WARN_ON_ONCE(src_cset->mg_dst_cset || dst_cset->mg_dst_cset); + + /* + * If src cset equals dst, it's noop. Drop the src. + * cgroup_migrate() will skip the cset too. Note that we + * can't handle src == dst as some nodes are used by both. + */ + if (src_cset == dst_cset) { + src_cset->mg_src_cgrp = NULL; + list_del_init(&src_cset->mg_preload_node); + put_css_set(src_cset); + put_css_set(dst_cset); + continue; + } + + src_cset->mg_dst_cset = dst_cset; + + if (list_empty(&dst_cset->mg_preload_node)) + list_add(&dst_cset->mg_preload_node, &csets); + else + put_css_set(dst_cset); + } + + list_splice_tail(&csets, preloaded_csets); + return 0; +err: + cgroup_migrate_finish(&csets); + return -ENOMEM; +} + +/** + * cgroup_migrate - migrate a process or task to a cgroup + * @cgrp: the destination cgroup + * @leader: the leader of the process or the task to migrate + * @threadgroup: whether @leader points to the whole process or a single task + * + * Migrate a process or task denoted by @leader to @cgrp. If migrating a + * process, the caller must be holding threadgroup_lock of @leader. The + * caller is also responsible for invoking cgroup_migrate_add_src() and + * cgroup_migrate_prepare_dst() on the targets before invoking this + * function and following up with cgroup_migrate_finish(). + * + * As long as a controller's ->can_attach() doesn't fail, this function is + * guaranteed to succeed. This means that, excluding ->can_attach() + * failure, when migrating multiple targets, the success or failure can be + * decided for all targets by invoking group_migrate_prepare_dst() before + * actually starting migrating. + */ +static int cgroup_migrate(struct cgroup *cgrp, struct task_struct *leader, + bool threadgroup) +{ + struct cgroup_taskset tset = { + .src_csets = LIST_HEAD_INIT(tset.src_csets), + .dst_csets = LIST_HEAD_INIT(tset.dst_csets), + .csets = &tset.src_csets, + }; + struct cgroup_subsys_state *css, *failed_css = NULL; + struct css_set *cset, *tmp_cset; + struct task_struct *task, *tmp_task; + int i, ret; + + /* + * Prevent freeing of tasks while we take a snapshot. Tasks that are + * already PF_EXITING could be freed from underneath us unless we + * take an rcu_read_lock. + */ + down_write(&css_set_rwsem); + rcu_read_lock(); + task = leader; + do { + /* @task either already exited or can't exit until the end */ + if (task->flags & PF_EXITING) + goto next; + + /* leave @task alone if post_fork() hasn't linked it yet */ + if (list_empty(&task->cg_list)) + goto next; + + cset = task_css_set(task); + if (!cset->mg_src_cgrp) + goto next; + + /* + * cgroup_taskset_first() must always return the leader. + * Take care to avoid disturbing the ordering. + */ + list_move_tail(&task->cg_list, &cset->mg_tasks); + if (list_empty(&cset->mg_node)) + list_add_tail(&cset->mg_node, &tset.src_csets); + if (list_empty(&cset->mg_dst_cset->mg_node)) + list_move_tail(&cset->mg_dst_cset->mg_node, + &tset.dst_csets); + next: + if (!threadgroup) + break; + } while_each_thread(leader, task); + rcu_read_unlock(); + up_write(&css_set_rwsem); + + /* methods shouldn't be called if no task is actually migrating */ + if (list_empty(&tset.src_csets)) + return 0; + + /* check that we can legitimately attach to the cgroup */ + for_each_e_css(css, i, cgrp) { + if (css->ss->can_attach) { + ret = css->ss->can_attach(css, &tset); + if (ret) { + failed_css = css; + goto out_cancel_attach; + } + } + } + + /* + * Now that we're guaranteed success, proceed to move all tasks to + * the new cgroup. There are no failure cases after here, so this + * is the commit point. + */ + down_write(&css_set_rwsem); + list_for_each_entry(cset, &tset.src_csets, mg_node) { + list_for_each_entry_safe(task, tmp_task, &cset->mg_tasks, cg_list) + cgroup_task_migrate(cset->mg_src_cgrp, task, + cset->mg_dst_cset); + } + up_write(&css_set_rwsem); + + /* + * Migration is committed, all target tasks are now on dst_csets. + * Nothing is sensitive to fork() after this point. Notify + * controllers that migration is complete. + */ + tset.csets = &tset.dst_csets; + + for_each_e_css(css, i, cgrp) + if (css->ss->attach) + css->ss->attach(css, &tset); + + ret = 0; + goto out_release_tset; + +out_cancel_attach: + for_each_e_css(css, i, cgrp) { + if (css == failed_css) + break; + if (css->ss->cancel_attach) + css->ss->cancel_attach(css, &tset); + } +out_release_tset: + down_write(&css_set_rwsem); + list_splice_init(&tset.dst_csets, &tset.src_csets); + list_for_each_entry_safe(cset, tmp_cset, &tset.src_csets, mg_node) { + list_splice_tail_init(&cset->mg_tasks, &cset->tasks); + list_del_init(&cset->mg_node); + } + up_write(&css_set_rwsem); + return ret; +} + +/** + * cgroup_attach_task - attach a task or a whole threadgroup to a cgroup + * @dst_cgrp: the cgroup to attach to + * @leader: the task or the leader of the threadgroup to be attached + * @threadgroup: attach the whole threadgroup? + * + * Call holding cgroup_mutex and threadgroup_lock of @leader. + */ +static int cgroup_attach_task(struct cgroup *dst_cgrp, + struct task_struct *leader, bool threadgroup) +{ + LIST_HEAD(preloaded_csets); + struct task_struct *task; + int ret; + + /* look up all src csets */ + down_read(&css_set_rwsem); + rcu_read_lock(); + task = leader; + do { + cgroup_migrate_add_src(task_css_set(task), dst_cgrp, + &preloaded_csets); + if (!threadgroup) + break; + } while_each_thread(leader, task); + rcu_read_unlock(); + up_read(&css_set_rwsem); + + /* prepare dst csets and commit */ + ret = cgroup_migrate_prepare_dst(dst_cgrp, &preloaded_csets); + if (!ret) + ret = cgroup_migrate(dst_cgrp, leader, threadgroup); + + cgroup_migrate_finish(&preloaded_csets); + return ret; +} + +/* + * Find the task_struct of the task to attach by vpid and pass it along to the + * function to attach either it or all tasks in its threadgroup. Will lock + * cgroup_mutex and threadgroup. + */ +static ssize_t __cgroup_procs_write(struct kernfs_open_file *of, char *buf, + size_t nbytes, loff_t off, bool threadgroup) +{ + struct task_struct *tsk; + const struct cred *cred = current_cred(), *tcred; + struct cgroup *cgrp; + pid_t pid; + int ret; + + if (kstrtoint(strstrip(buf), 0, &pid) || pid < 0) + return -EINVAL; + + cgrp = cgroup_kn_lock_live(of->kn); + if (!cgrp) + return -ENODEV; + +retry_find_task: + rcu_read_lock(); + if (pid) { + tsk = find_task_by_vpid(pid); + if (!tsk) { + rcu_read_unlock(); + ret = -ESRCH; + goto out_unlock_cgroup; + } + /* + * even if we're attaching all tasks in the thread group, we + * only need to check permissions on one of them. + */ + tcred = __task_cred(tsk); + if (!uid_eq(cred->euid, GLOBAL_ROOT_UID) && + !uid_eq(cred->euid, tcred->uid) && + !uid_eq(cred->euid, tcred->suid)) { + rcu_read_unlock(); + ret = -EACCES; + goto out_unlock_cgroup; + } + } else + tsk = current; + + if (threadgroup) + tsk = tsk->group_leader; + + /* + * Workqueue threads may acquire PF_NO_SETAFFINITY and become + * trapped in a cpuset, or RT worker may be born in a cgroup + * with no rt_runtime allocated. Just say no. + */ + if (tsk == kthreadd_task || (tsk->flags & PF_NO_SETAFFINITY)) { + ret = -EINVAL; + rcu_read_unlock(); + goto out_unlock_cgroup; + } + + get_task_struct(tsk); + rcu_read_unlock(); + + threadgroup_lock(tsk); + if (threadgroup) { + if (!thread_group_leader(tsk)) { + /* + * a race with de_thread from another thread's exec() + * may strip us of our leadership, if this happens, + * there is no choice but to throw this task away and + * try again; this is + * "double-double-toil-and-trouble-check locking". + */ + threadgroup_unlock(tsk); + put_task_struct(tsk); + goto retry_find_task; + } + } + + ret = cgroup_attach_task(cgrp, tsk, threadgroup); + + threadgroup_unlock(tsk); + + put_task_struct(tsk); +out_unlock_cgroup: + cgroup_kn_unlock(of->kn); + return ret ?: nbytes; +} + +/** + * cgroup_attach_task_all - attach task 'tsk' to all cgroups of task 'from' + * @from: attach to all cgroups of a given task + * @tsk: the task to be attached + */ +int cgroup_attach_task_all(struct task_struct *from, struct task_struct *tsk) +{ + struct cgroup_root *root; + int retval = 0; + + mutex_lock(&cgroup_mutex); + for_each_root(root) { + struct cgroup *from_cgrp; + + if (root == &cgrp_dfl_root) + continue; + + down_read(&css_set_rwsem); + from_cgrp = task_cgroup_from_root(from, root); + up_read(&css_set_rwsem); + + retval = cgroup_attach_task(from_cgrp, tsk, false); + if (retval) + break; + } + mutex_unlock(&cgroup_mutex); + + return retval; +} +EXPORT_SYMBOL_GPL(cgroup_attach_task_all); + +static ssize_t cgroup_tasks_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) +{ + return __cgroup_procs_write(of, buf, nbytes, off, false); +} + +static ssize_t cgroup_procs_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) +{ + return __cgroup_procs_write(of, buf, nbytes, off, true); +} + +static ssize_t cgroup_release_agent_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) +{ + struct cgroup *cgrp; + + BUILD_BUG_ON(sizeof(cgrp->root->release_agent_path) < PATH_MAX); + + cgrp = cgroup_kn_lock_live(of->kn); + if (!cgrp) + return -ENODEV; + spin_lock(&release_agent_path_lock); + strlcpy(cgrp->root->release_agent_path, strstrip(buf), + sizeof(cgrp->root->release_agent_path)); + spin_unlock(&release_agent_path_lock); + cgroup_kn_unlock(of->kn); + return nbytes; +} + +static int cgroup_release_agent_show(struct seq_file *seq, void *v) +{ + struct cgroup *cgrp = seq_css(seq)->cgroup; + + spin_lock(&release_agent_path_lock); + seq_puts(seq, cgrp->root->release_agent_path); + spin_unlock(&release_agent_path_lock); + seq_putc(seq, '\n'); + return 0; +} + +static int cgroup_sane_behavior_show(struct seq_file *seq, void *v) +{ + seq_puts(seq, "0\n"); + return 0; +} + +static void cgroup_print_ss_mask(struct seq_file *seq, unsigned int ss_mask) +{ + struct cgroup_subsys *ss; + bool printed = false; + int ssid; + + for_each_subsys(ss, ssid) { + if (ss_mask & (1 << ssid)) { + if (printed) + seq_putc(seq, ' '); + seq_printf(seq, "%s", ss->name); + printed = true; + } + } + if (printed) + seq_putc(seq, '\n'); +} + +/* show controllers which are currently attached to the default hierarchy */ +static int cgroup_root_controllers_show(struct seq_file *seq, void *v) +{ + struct cgroup *cgrp = seq_css(seq)->cgroup; + + cgroup_print_ss_mask(seq, cgrp->root->subsys_mask & + ~cgrp_dfl_root_inhibit_ss_mask); + return 0; +} + +/* show controllers which are enabled from the parent */ +static int cgroup_controllers_show(struct seq_file *seq, void *v) +{ + struct cgroup *cgrp = seq_css(seq)->cgroup; + + cgroup_print_ss_mask(seq, cgroup_parent(cgrp)->subtree_control); + return 0; +} + +/* show controllers which are enabled for a given cgroup's children */ +static int cgroup_subtree_control_show(struct seq_file *seq, void *v) +{ + struct cgroup *cgrp = seq_css(seq)->cgroup; + + cgroup_print_ss_mask(seq, cgrp->subtree_control); + return 0; +} + +/** + * cgroup_update_dfl_csses - update css assoc of a subtree in default hierarchy + * @cgrp: root of the subtree to update csses for + * + * @cgrp's child_subsys_mask has changed and its subtree's (self excluded) + * css associations need to be updated accordingly. This function looks up + * all css_sets which are attached to the subtree, creates the matching + * updated css_sets and migrates the tasks to the new ones. + */ +static int cgroup_update_dfl_csses(struct cgroup *cgrp) +{ + LIST_HEAD(preloaded_csets); + struct cgroup_subsys_state *css; + struct css_set *src_cset; + int ret; + + lockdep_assert_held(&cgroup_mutex); + + /* look up all csses currently attached to @cgrp's subtree */ + down_read(&css_set_rwsem); + css_for_each_descendant_pre(css, cgroup_css(cgrp, NULL)) { + struct cgrp_cset_link *link; + + /* self is not affected by child_subsys_mask change */ + if (css->cgroup == cgrp) + continue; + + list_for_each_entry(link, &css->cgroup->cset_links, cset_link) + cgroup_migrate_add_src(link->cset, cgrp, + &preloaded_csets); + } + up_read(&css_set_rwsem); + + /* NULL dst indicates self on default hierarchy */ + ret = cgroup_migrate_prepare_dst(NULL, &preloaded_csets); + if (ret) + goto out_finish; + + list_for_each_entry(src_cset, &preloaded_csets, mg_preload_node) { + struct task_struct *last_task = NULL, *task; + + /* src_csets precede dst_csets, break on the first dst_cset */ + if (!src_cset->mg_src_cgrp) + break; + + /* + * All tasks in src_cset need to be migrated to the + * matching dst_cset. Empty it process by process. We + * walk tasks but migrate processes. The leader might even + * belong to a different cset but such src_cset would also + * be among the target src_csets because the default + * hierarchy enforces per-process membership. + */ + while (true) { + down_read(&css_set_rwsem); + task = list_first_entry_or_null(&src_cset->tasks, + struct task_struct, cg_list); + if (task) { + task = task->group_leader; + WARN_ON_ONCE(!task_css_set(task)->mg_src_cgrp); + get_task_struct(task); + } + up_read(&css_set_rwsem); + + if (!task) + break; + + /* guard against possible infinite loop */ + if (WARN(last_task == task, + "cgroup: update_dfl_csses failed to make progress, aborting in inconsistent state\n")) + goto out_finish; + last_task = task; + + threadgroup_lock(task); + /* raced against de_thread() from another thread? */ + if (!thread_group_leader(task)) { + threadgroup_unlock(task); + put_task_struct(task); + continue; + } + + ret = cgroup_migrate(src_cset->dfl_cgrp, task, true); + + threadgroup_unlock(task); + put_task_struct(task); + + if (WARN(ret, "cgroup: failed to update controllers for the default hierarchy (%d), further operations may crash or hang\n", ret)) + goto out_finish; + } + } + +out_finish: + cgroup_migrate_finish(&preloaded_csets); + return ret; +} + +/* change the enabled child controllers for a cgroup in the default hierarchy */ +static ssize_t cgroup_subtree_control_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, + loff_t off) +{ + unsigned int enable = 0, disable = 0; + unsigned int css_enable, css_disable, old_sc, new_sc, old_ss, new_ss; + struct cgroup *cgrp, *child; + struct cgroup_subsys *ss; + char *tok; + int ssid, ret; + + /* + * Parse input - space separated list of subsystem names prefixed + * with either + or -. + */ + buf = strstrip(buf); + while ((tok = strsep(&buf, " "))) { + if (tok[0] == '\0') + continue; + for_each_subsys(ss, ssid) { + if (ss->disabled || strcmp(tok + 1, ss->name) || + ((1 << ss->id) & cgrp_dfl_root_inhibit_ss_mask)) + continue; + + if (*tok == '+') { + enable |= 1 << ssid; + disable &= ~(1 << ssid); + } else if (*tok == '-') { + disable |= 1 << ssid; + enable &= ~(1 << ssid); + } else { + return -EINVAL; + } + break; + } + if (ssid == CGROUP_SUBSYS_COUNT) + return -EINVAL; + } + + cgrp = cgroup_kn_lock_live(of->kn); + if (!cgrp) + return -ENODEV; + + for_each_subsys(ss, ssid) { + if (enable & (1 << ssid)) { + if (cgrp->subtree_control & (1 << ssid)) { + enable &= ~(1 << ssid); + continue; + } + + /* unavailable or not enabled on the parent? */ + if (!(cgrp_dfl_root.subsys_mask & (1 << ssid)) || + (cgroup_parent(cgrp) && + !(cgroup_parent(cgrp)->subtree_control & (1 << ssid)))) { + ret = -ENOENT; + goto out_unlock; + } + } else if (disable & (1 << ssid)) { + if (!(cgrp->subtree_control & (1 << ssid))) { + disable &= ~(1 << ssid); + continue; + } + + /* a child has it enabled? */ + cgroup_for_each_live_child(child, cgrp) { + if (child->subtree_control & (1 << ssid)) { + ret = -EBUSY; + goto out_unlock; + } + } + } + } + + if (!enable && !disable) { + ret = 0; + goto out_unlock; + } + + /* + * Except for the root, subtree_control must be zero for a cgroup + * with tasks so that child cgroups don't compete against tasks. + */ + if (enable && cgroup_parent(cgrp) && !list_empty(&cgrp->cset_links)) { + ret = -EBUSY; + goto out_unlock; + } + + /* + * Update subsys masks and calculate what needs to be done. More + * subsystems than specified may need to be enabled or disabled + * depending on subsystem dependencies. + */ + old_sc = cgrp->subtree_control; + old_ss = cgrp->child_subsys_mask; + new_sc = (old_sc | enable) & ~disable; + new_ss = cgroup_calc_child_subsys_mask(cgrp, new_sc); + + css_enable = ~old_ss & new_ss; + css_disable = old_ss & ~new_ss; + enable |= css_enable; + disable |= css_disable; + + /* + * Because css offlining is asynchronous, userland might try to + * re-enable the same controller while the previous instance is + * still around. In such cases, wait till it's gone using + * offline_waitq. + */ + for_each_subsys(ss, ssid) { + if (!(css_enable & (1 << ssid))) + continue; + + cgroup_for_each_live_child(child, cgrp) { + DEFINE_WAIT(wait); + + if (!cgroup_css(child, ss)) + continue; + + cgroup_get(child); + prepare_to_wait(&child->offline_waitq, &wait, + TASK_UNINTERRUPTIBLE); + cgroup_kn_unlock(of->kn); + schedule(); + finish_wait(&child->offline_waitq, &wait); + cgroup_put(child); + + return restart_syscall(); + } + } + + cgrp->subtree_control = new_sc; + cgrp->child_subsys_mask = new_ss; + + /* + * Create new csses or make the existing ones visible. A css is + * created invisible if it's being implicitly enabled through + * dependency. An invisible css is made visible when the userland + * explicitly enables it. + */ + for_each_subsys(ss, ssid) { + if (!(enable & (1 << ssid))) + continue; + + cgroup_for_each_live_child(child, cgrp) { + if (css_enable & (1 << ssid)) + ret = create_css(child, ss, + cgrp->subtree_control & (1 << ssid)); + else + ret = cgroup_populate_dir(child, 1 << ssid); + if (ret) + goto err_undo_css; + } + } + + /* + * At this point, cgroup_e_css() results reflect the new csses + * making the following cgroup_update_dfl_csses() properly update + * css associations of all tasks in the subtree. + */ + ret = cgroup_update_dfl_csses(cgrp); + if (ret) + goto err_undo_css; + + /* + * All tasks are migrated out of disabled csses. Kill or hide + * them. A css is hidden when the userland requests it to be + * disabled while other subsystems are still depending on it. The + * css must not actively control resources and be in the vanilla + * state if it's made visible again later. Controllers which may + * be depended upon should provide ->css_reset() for this purpose. + */ + for_each_subsys(ss, ssid) { + if (!(disable & (1 << ssid))) + continue; + + cgroup_for_each_live_child(child, cgrp) { + struct cgroup_subsys_state *css = cgroup_css(child, ss); + + if (css_disable & (1 << ssid)) { + kill_css(css); + } else { + cgroup_clear_dir(child, 1 << ssid); + if (ss->css_reset) + ss->css_reset(css); + } + } + } + + /* + * The effective csses of all the descendants (excluding @cgrp) may + * have changed. Subsystems can optionally subscribe to this event + * by implementing ->css_e_css_changed() which is invoked if any of + * the effective csses seen from the css's cgroup may have changed. + */ + for_each_subsys(ss, ssid) { + struct cgroup_subsys_state *this_css = cgroup_css(cgrp, ss); + struct cgroup_subsys_state *css; + + if (!ss->css_e_css_changed || !this_css) + continue; + + css_for_each_descendant_pre(css, this_css) + if (css != this_css) + ss->css_e_css_changed(css); + } + + kernfs_activate(cgrp->kn); + ret = 0; +out_unlock: + cgroup_kn_unlock(of->kn); + return ret ?: nbytes; + +err_undo_css: + cgrp->subtree_control = old_sc; + cgrp->child_subsys_mask = old_ss; + + for_each_subsys(ss, ssid) { + if (!(enable & (1 << ssid))) + continue; + + cgroup_for_each_live_child(child, cgrp) { + struct cgroup_subsys_state *css = cgroup_css(child, ss); + + if (!css) + continue; + + if (css_enable & (1 << ssid)) + kill_css(css); + else + cgroup_clear_dir(child, 1 << ssid); + } + } + goto out_unlock; +} + +static int cgroup_populated_show(struct seq_file *seq, void *v) +{ + seq_printf(seq, "%d\n", (bool)seq_css(seq)->cgroup->populated_cnt); + return 0; +} + +static ssize_t cgroup_file_write(struct kernfs_open_file *of, char *buf, + size_t nbytes, loff_t off) +{ + struct cgroup *cgrp = of->kn->parent->priv; + struct cftype *cft = of->kn->priv; + struct cgroup_subsys_state *css; + int ret; + + if (cft->write) + return cft->write(of, buf, nbytes, off); + + /* + * kernfs guarantees that a file isn't deleted with operations in + * flight, which means that the matching css is and stays alive and + * doesn't need to be pinned. The RCU locking is not necessary + * either. It's just for the convenience of using cgroup_css(). + */ + rcu_read_lock(); + css = cgroup_css(cgrp, cft->ss); + rcu_read_unlock(); + + if (cft->write_u64) { + unsigned long long v; + ret = kstrtoull(buf, 0, &v); + if (!ret) + ret = cft->write_u64(css, cft, v); + } else if (cft->write_s64) { + long long v; + ret = kstrtoll(buf, 0, &v); + if (!ret) + ret = cft->write_s64(css, cft, v); + } else { + ret = -EINVAL; + } + + return ret ?: nbytes; +} + +static void *cgroup_seqfile_start(struct seq_file *seq, loff_t *ppos) +{ + return seq_cft(seq)->seq_start(seq, ppos); +} + +static void *cgroup_seqfile_next(struct seq_file *seq, void *v, loff_t *ppos) +{ + return seq_cft(seq)->seq_next(seq, v, ppos); +} + +static void cgroup_seqfile_stop(struct seq_file *seq, void *v) +{ + seq_cft(seq)->seq_stop(seq, v); +} + +static int cgroup_seqfile_show(struct seq_file *m, void *arg) +{ + struct cftype *cft = seq_cft(m); + struct cgroup_subsys_state *css = seq_css(m); + + if (cft->seq_show) + return cft->seq_show(m, arg); + + if (cft->read_u64) + seq_printf(m, "%llu\n", cft->read_u64(css, cft)); + else if (cft->read_s64) + seq_printf(m, "%lld\n", cft->read_s64(css, cft)); + else + return -EINVAL; + return 0; +} + +static struct kernfs_ops cgroup_kf_single_ops = { + .atomic_write_len = PAGE_SIZE, + .write = cgroup_file_write, + .seq_show = cgroup_seqfile_show, +}; + +static struct kernfs_ops cgroup_kf_ops = { + .atomic_write_len = PAGE_SIZE, + .write = cgroup_file_write, + .seq_start = cgroup_seqfile_start, + .seq_next = cgroup_seqfile_next, + .seq_stop = cgroup_seqfile_stop, + .seq_show = cgroup_seqfile_show, +}; + +/* + * cgroup_rename - Only allow simple rename of directories in place. + */ +static int cgroup_rename(struct kernfs_node *kn, struct kernfs_node *new_parent, + const char *new_name_str) +{ + struct cgroup *cgrp = kn->priv; + int ret; + + if (kernfs_type(kn) != KERNFS_DIR) + return -ENOTDIR; + if (kn->parent != new_parent) + return -EIO; + + /* + * This isn't a proper migration and its usefulness is very + * limited. Disallow on the default hierarchy. + */ + if (cgroup_on_dfl(cgrp)) + return -EPERM; + + /* + * We're gonna grab cgroup_mutex which nests outside kernfs + * active_ref. kernfs_rename() doesn't require active_ref + * protection. Break them before grabbing cgroup_mutex. + */ + kernfs_break_active_protection(new_parent); + kernfs_break_active_protection(kn); + + mutex_lock(&cgroup_mutex); + + ret = kernfs_rename(kn, new_parent, new_name_str); + + mutex_unlock(&cgroup_mutex); + + kernfs_unbreak_active_protection(kn); + kernfs_unbreak_active_protection(new_parent); + return ret; +} + +/* set uid and gid of cgroup dirs and files to that of the creator */ +static int cgroup_kn_set_ugid(struct kernfs_node *kn) +{ + struct iattr iattr = { .ia_valid = ATTR_UID | ATTR_GID, + .ia_uid = current_fsuid(), + .ia_gid = current_fsgid(), }; + + if (uid_eq(iattr.ia_uid, GLOBAL_ROOT_UID) && + gid_eq(iattr.ia_gid, GLOBAL_ROOT_GID)) + return 0; + + return kernfs_setattr(kn, &iattr); +} + +static int cgroup_add_file(struct cgroup *cgrp, struct cftype *cft) +{ + char name[CGROUP_FILE_NAME_MAX]; + struct kernfs_node *kn; + struct lock_class_key *key = NULL; + int ret; + +#ifdef CONFIG_DEBUG_LOCK_ALLOC + key = &cft->lockdep_key; +#endif + kn = __kernfs_create_file(cgrp->kn, cgroup_file_name(cgrp, cft, name), + cgroup_file_mode(cft), 0, cft->kf_ops, cft, + NULL, key); + if (IS_ERR(kn)) + return PTR_ERR(kn); + + ret = cgroup_kn_set_ugid(kn); + if (ret) { + kernfs_remove(kn); + return ret; + } + + if (cft->seq_show == cgroup_populated_show) + cgrp->populated_kn = kn; + return 0; +} + +/** + * cgroup_addrm_files - add or remove files to a cgroup directory + * @cgrp: the target cgroup + * @cfts: array of cftypes to be added + * @is_add: whether to add or remove + * + * Depending on @is_add, add or remove files defined by @cfts on @cgrp. + * For removals, this function never fails. If addition fails, this + * function doesn't remove files already added. The caller is responsible + * for cleaning up. + */ +static int cgroup_addrm_files(struct cgroup *cgrp, struct cftype cfts[], + bool is_add) +{ + struct cftype *cft; + int ret; + + lockdep_assert_held(&cgroup_mutex); + + for (cft = cfts; cft->name[0] != '\0'; cft++) { + /* does cft->flags tell us to skip this file on @cgrp? */ + if ((cft->flags & __CFTYPE_ONLY_ON_DFL) && !cgroup_on_dfl(cgrp)) + continue; + if ((cft->flags & __CFTYPE_NOT_ON_DFL) && cgroup_on_dfl(cgrp)) + continue; + if ((cft->flags & CFTYPE_NOT_ON_ROOT) && !cgroup_parent(cgrp)) + continue; + if ((cft->flags & CFTYPE_ONLY_ON_ROOT) && cgroup_parent(cgrp)) + continue; + + if (is_add) { + ret = cgroup_add_file(cgrp, cft); + if (ret) { + pr_warn("%s: failed to add %s, err=%d\n", + __func__, cft->name, ret); + return ret; + } + } else { + cgroup_rm_file(cgrp, cft); + } + } + return 0; +} + +static int cgroup_apply_cftypes(struct cftype *cfts, bool is_add) +{ + LIST_HEAD(pending); + struct cgroup_subsys *ss = cfts[0].ss; + struct cgroup *root = &ss->root->cgrp; + struct cgroup_subsys_state *css; + int ret = 0; + + lockdep_assert_held(&cgroup_mutex); + + /* add/rm files for all cgroups created before */ + css_for_each_descendant_pre(css, cgroup_css(root, ss)) { + struct cgroup *cgrp = css->cgroup; + + if (cgroup_is_dead(cgrp)) + continue; + + ret = cgroup_addrm_files(cgrp, cfts, is_add); + if (ret) + break; + } + + if (is_add && !ret) + kernfs_activate(root->kn); + return ret; +} + +static void cgroup_exit_cftypes(struct cftype *cfts) +{ + struct cftype *cft; + + for (cft = cfts; cft->name[0] != '\0'; cft++) { + /* free copy for custom atomic_write_len, see init_cftypes() */ + if (cft->max_write_len && cft->max_write_len != PAGE_SIZE) + kfree(cft->kf_ops); + cft->kf_ops = NULL; + cft->ss = NULL; + + /* revert flags set by cgroup core while adding @cfts */ + cft->flags &= ~(__CFTYPE_ONLY_ON_DFL | __CFTYPE_NOT_ON_DFL); + } +} + +static int cgroup_init_cftypes(struct cgroup_subsys *ss, struct cftype *cfts) +{ + struct cftype *cft; + + for (cft = cfts; cft->name[0] != '\0'; cft++) { + struct kernfs_ops *kf_ops; + + WARN_ON(cft->ss || cft->kf_ops); + + if (cft->seq_start) + kf_ops = &cgroup_kf_ops; + else + kf_ops = &cgroup_kf_single_ops; + + /* + * Ugh... if @cft wants a custom max_write_len, we need to + * make a copy of kf_ops to set its atomic_write_len. + */ + if (cft->max_write_len && cft->max_write_len != PAGE_SIZE) { + kf_ops = kmemdup(kf_ops, sizeof(*kf_ops), GFP_KERNEL); + if (!kf_ops) { + cgroup_exit_cftypes(cfts); + return -ENOMEM; + } + kf_ops->atomic_write_len = cft->max_write_len; + } + + cft->kf_ops = kf_ops; + cft->ss = ss; + } + + return 0; +} + +static int cgroup_rm_cftypes_locked(struct cftype *cfts) +{ + lockdep_assert_held(&cgroup_mutex); + + if (!cfts || !cfts[0].ss) + return -ENOENT; + + list_del(&cfts->node); + cgroup_apply_cftypes(cfts, false); + cgroup_exit_cftypes(cfts); + return 0; +} + +/** + * cgroup_rm_cftypes - remove an array of cftypes from a subsystem + * @cfts: zero-length name terminated array of cftypes + * + * Unregister @cfts. Files described by @cfts are removed from all + * existing cgroups and all future cgroups won't have them either. This + * function can be called anytime whether @cfts' subsys is attached or not. + * + * Returns 0 on successful unregistration, -ENOENT if @cfts is not + * registered. + */ +int cgroup_rm_cftypes(struct cftype *cfts) +{ + int ret; + + mutex_lock(&cgroup_mutex); + ret = cgroup_rm_cftypes_locked(cfts); + mutex_unlock(&cgroup_mutex); + return ret; +} + +/** + * cgroup_add_cftypes - add an array of cftypes to a subsystem + * @ss: target cgroup subsystem + * @cfts: zero-length name terminated array of cftypes + * + * Register @cfts to @ss. Files described by @cfts are created for all + * existing cgroups to which @ss is attached and all future cgroups will + * have them too. This function can be called anytime whether @ss is + * attached or not. + * + * Returns 0 on successful registration, -errno on failure. Note that this + * function currently returns 0 as long as @cfts registration is successful + * even if some file creation attempts on existing cgroups fail. + */ +static int cgroup_add_cftypes(struct cgroup_subsys *ss, struct cftype *cfts) +{ + int ret; + + if (ss->disabled) + return 0; + + if (!cfts || cfts[0].name[0] == '\0') + return 0; + + ret = cgroup_init_cftypes(ss, cfts); + if (ret) + return ret; + + mutex_lock(&cgroup_mutex); + + list_add_tail(&cfts->node, &ss->cfts); + ret = cgroup_apply_cftypes(cfts, true); + if (ret) + cgroup_rm_cftypes_locked(cfts); + + mutex_unlock(&cgroup_mutex); + return ret; +} + +/** + * cgroup_add_dfl_cftypes - add an array of cftypes for default hierarchy + * @ss: target cgroup subsystem + * @cfts: zero-length name terminated array of cftypes + * + * Similar to cgroup_add_cftypes() but the added files are only used for + * the default hierarchy. + */ +int cgroup_add_dfl_cftypes(struct cgroup_subsys *ss, struct cftype *cfts) +{ + struct cftype *cft; + + for (cft = cfts; cft && cft->name[0] != '\0'; cft++) + cft->flags |= __CFTYPE_ONLY_ON_DFL; + return cgroup_add_cftypes(ss, cfts); +} + +/** + * cgroup_add_legacy_cftypes - add an array of cftypes for legacy hierarchies + * @ss: target cgroup subsystem + * @cfts: zero-length name terminated array of cftypes + * + * Similar to cgroup_add_cftypes() but the added files are only used for + * the legacy hierarchies. + */ +int cgroup_add_legacy_cftypes(struct cgroup_subsys *ss, struct cftype *cfts) +{ + struct cftype *cft; + + /* + * If legacy_flies_on_dfl, we want to show the legacy files on the + * dfl hierarchy but iff the target subsystem hasn't been updated + * for the dfl hierarchy yet. + */ + if (!cgroup_legacy_files_on_dfl || + ss->dfl_cftypes != ss->legacy_cftypes) { + for (cft = cfts; cft && cft->name[0] != '\0'; cft++) + cft->flags |= __CFTYPE_NOT_ON_DFL; + } + + return cgroup_add_cftypes(ss, cfts); +} + +/** + * cgroup_task_count - count the number of tasks in a cgroup. + * @cgrp: the cgroup in question + * + * Return the number of tasks in the cgroup. + */ +static int cgroup_task_count(const struct cgroup *cgrp) +{ + int count = 0; + struct cgrp_cset_link *link; + + down_read(&css_set_rwsem); + list_for_each_entry(link, &cgrp->cset_links, cset_link) + count += atomic_read(&link->cset->refcount); + up_read(&css_set_rwsem); + return count; +} + +/** + * css_next_child - find the next child of a given css + * @pos: the current position (%NULL to initiate traversal) + * @parent: css whose children to walk + * + * This function returns the next child of @parent and should be called + * under either cgroup_mutex or RCU read lock. The only requirement is + * that @parent and @pos are accessible. The next sibling is guaranteed to + * be returned regardless of their states. + * + * If a subsystem synchronizes ->css_online() and the start of iteration, a + * css which finished ->css_online() is guaranteed to be visible in the + * future iterations and will stay visible until the last reference is put. + * A css which hasn't finished ->css_online() or already finished + * ->css_offline() may show up during traversal. It's each subsystem's + * responsibility to synchronize against on/offlining. + */ +struct cgroup_subsys_state *css_next_child(struct cgroup_subsys_state *pos, + struct cgroup_subsys_state *parent) +{ + struct cgroup_subsys_state *next; + + cgroup_assert_mutex_or_rcu_locked(); + + /* + * @pos could already have been unlinked from the sibling list. + * Once a cgroup is removed, its ->sibling.next is no longer + * updated when its next sibling changes. CSS_RELEASED is set when + * @pos is taken off list, at which time its next pointer is valid, + * and, as releases are serialized, the one pointed to by the next + * pointer is guaranteed to not have started release yet. This + * implies that if we observe !CSS_RELEASED on @pos in this RCU + * critical section, the one pointed to by its next pointer is + * guaranteed to not have finished its RCU grace period even if we + * have dropped rcu_read_lock() inbetween iterations. + * + * If @pos has CSS_RELEASED set, its next pointer can't be + * dereferenced; however, as each css is given a monotonically + * increasing unique serial number and always appended to the + * sibling list, the next one can be found by walking the parent's + * children until the first css with higher serial number than + * @pos's. While this path can be slower, it happens iff iteration + * races against release and the race window is very small. + */ + if (!pos) { + next = list_entry_rcu(parent->children.next, struct cgroup_subsys_state, sibling); + } else if (likely(!(pos->flags & CSS_RELEASED))) { + next = list_entry_rcu(pos->sibling.next, struct cgroup_subsys_state, sibling); + } else { + list_for_each_entry_rcu(next, &parent->children, sibling) + if (next->serial_nr > pos->serial_nr) + break; + } + + /* + * @next, if not pointing to the head, can be dereferenced and is + * the next sibling. + */ + if (&next->sibling != &parent->children) + return next; + return NULL; +} + +/** + * css_next_descendant_pre - find the next descendant for pre-order walk + * @pos: the current position (%NULL to initiate traversal) + * @root: css whose descendants to walk + * + * To be used by css_for_each_descendant_pre(). Find the next descendant + * to visit for pre-order traversal of @root's descendants. @root is + * included in the iteration and the first node to be visited. + * + * While this function requires cgroup_mutex or RCU read locking, it + * doesn't require the whole traversal to be contained in a single critical + * section. This function will return the correct next descendant as long + * as both @pos and @root are accessible and @pos is a descendant of @root. + * + * If a subsystem synchronizes ->css_online() and the start of iteration, a + * css which finished ->css_online() is guaranteed to be visible in the + * future iterations and will stay visible until the last reference is put. + * A css which hasn't finished ->css_online() or already finished + * ->css_offline() may show up during traversal. It's each subsystem's + * responsibility to synchronize against on/offlining. + */ +struct cgroup_subsys_state * +css_next_descendant_pre(struct cgroup_subsys_state *pos, + struct cgroup_subsys_state *root) +{ + struct cgroup_subsys_state *next; + + cgroup_assert_mutex_or_rcu_locked(); + + /* if first iteration, visit @root */ + if (!pos) + return root; + + /* visit the first child if exists */ + next = css_next_child(NULL, pos); + if (next) + return next; + + /* no child, visit my or the closest ancestor's next sibling */ + while (pos != root) { + next = css_next_child(pos, pos->parent); + if (next) + return next; + pos = pos->parent; + } + + return NULL; +} + +/** + * css_rightmost_descendant - return the rightmost descendant of a css + * @pos: css of interest + * + * Return the rightmost descendant of @pos. If there's no descendant, @pos + * is returned. This can be used during pre-order traversal to skip + * subtree of @pos. + * + * While this function requires cgroup_mutex or RCU read locking, it + * doesn't require the whole traversal to be contained in a single critical + * section. This function will return the correct rightmost descendant as + * long as @pos is accessible. + */ +struct cgroup_subsys_state * +css_rightmost_descendant(struct cgroup_subsys_state *pos) +{ + struct cgroup_subsys_state *last, *tmp; + + cgroup_assert_mutex_or_rcu_locked(); + + do { + last = pos; + /* ->prev isn't RCU safe, walk ->next till the end */ + pos = NULL; + css_for_each_child(tmp, last) + pos = tmp; + } while (pos); + + return last; +} + +static struct cgroup_subsys_state * +css_leftmost_descendant(struct cgroup_subsys_state *pos) +{ + struct cgroup_subsys_state *last; + + do { + last = pos; + pos = css_next_child(NULL, pos); + } while (pos); + + return last; +} + +/** + * css_next_descendant_post - find the next descendant for post-order walk + * @pos: the current position (%NULL to initiate traversal) + * @root: css whose descendants to walk + * + * To be used by css_for_each_descendant_post(). Find the next descendant + * to visit for post-order traversal of @root's descendants. @root is + * included in the iteration and the last node to be visited. + * + * While this function requires cgroup_mutex or RCU read locking, it + * doesn't require the whole traversal to be contained in a single critical + * section. This function will return the correct next descendant as long + * as both @pos and @cgroup are accessible and @pos is a descendant of + * @cgroup. + * + * If a subsystem synchronizes ->css_online() and the start of iteration, a + * css which finished ->css_online() is guaranteed to be visible in the + * future iterations and will stay visible until the last reference is put. + * A css which hasn't finished ->css_online() or already finished + * ->css_offline() may show up during traversal. It's each subsystem's + * responsibility to synchronize against on/offlining. + */ +struct cgroup_subsys_state * +css_next_descendant_post(struct cgroup_subsys_state *pos, + struct cgroup_subsys_state *root) +{ + struct cgroup_subsys_state *next; + + cgroup_assert_mutex_or_rcu_locked(); + + /* if first iteration, visit leftmost descendant which may be @root */ + if (!pos) + return css_leftmost_descendant(root); + + /* if we visited @root, we're done */ + if (pos == root) + return NULL; + + /* if there's an unvisited sibling, visit its leftmost descendant */ + next = css_next_child(pos, pos->parent); + if (next) + return css_leftmost_descendant(next); + + /* no sibling left, visit parent */ + return pos->parent; +} + +/** + * css_has_online_children - does a css have online children + * @css: the target css + * + * Returns %true if @css has any online children; otherwise, %false. This + * function can be called from any context but the caller is responsible + * for synchronizing against on/offlining as necessary. + */ +bool css_has_online_children(struct cgroup_subsys_state *css) +{ + struct cgroup_subsys_state *child; + bool ret = false; + + rcu_read_lock(); + css_for_each_child(child, css) { + if (child->flags & CSS_ONLINE) { + ret = true; + break; + } + } + rcu_read_unlock(); + return ret; +} + +/** + * css_advance_task_iter - advance a task itererator to the next css_set + * @it: the iterator to advance + * + * Advance @it to the next css_set to walk. + */ +static void css_advance_task_iter(struct css_task_iter *it) +{ + struct list_head *l = it->cset_pos; + struct cgrp_cset_link *link; + struct css_set *cset; + + /* Advance to the next non-empty css_set */ + do { + l = l->next; + if (l == it->cset_head) { + it->cset_pos = NULL; + return; + } + + if (it->ss) { + cset = container_of(l, struct css_set, + e_cset_node[it->ss->id]); + } else { + link = list_entry(l, struct cgrp_cset_link, cset_link); + cset = link->cset; + } + } while (list_empty(&cset->tasks) && list_empty(&cset->mg_tasks)); + + it->cset_pos = l; + + if (!list_empty(&cset->tasks)) + it->task_pos = cset->tasks.next; + else + it->task_pos = cset->mg_tasks.next; + + it->tasks_head = &cset->tasks; + it->mg_tasks_head = &cset->mg_tasks; +} + +/** + * css_task_iter_start - initiate task iteration + * @css: the css to walk tasks of + * @it: the task iterator to use + * + * Initiate iteration through the tasks of @css. The caller can call + * css_task_iter_next() to walk through the tasks until the function + * returns NULL. On completion of iteration, css_task_iter_end() must be + * called. + * + * Note that this function acquires a lock which is released when the + * iteration finishes. The caller can't sleep while iteration is in + * progress. + */ +void css_task_iter_start(struct cgroup_subsys_state *css, + struct css_task_iter *it) + __acquires(css_set_rwsem) +{ + /* no one should try to iterate before mounting cgroups */ + WARN_ON_ONCE(!use_task_css_set_links); + + down_read(&css_set_rwsem); + + it->ss = css->ss; + + if (it->ss) + it->cset_pos = &css->cgroup->e_csets[css->ss->id]; + else + it->cset_pos = &css->cgroup->cset_links; + + it->cset_head = it->cset_pos; + + css_advance_task_iter(it); +} + +/** + * css_task_iter_next - return the next task for the iterator + * @it: the task iterator being iterated + * + * The "next" function for task iteration. @it should have been + * initialized via css_task_iter_start(). Returns NULL when the iteration + * reaches the end. + */ +struct task_struct *css_task_iter_next(struct css_task_iter *it) +{ + struct task_struct *res; + struct list_head *l = it->task_pos; + + /* If the iterator cg is NULL, we have no tasks */ + if (!it->cset_pos) + return NULL; + res = list_entry(l, struct task_struct, cg_list); + + /* + * Advance iterator to find next entry. cset->tasks is consumed + * first and then ->mg_tasks. After ->mg_tasks, we move onto the + * next cset. + */ + l = l->next; + + if (l == it->tasks_head) + l = it->mg_tasks_head->next; + + if (l == it->mg_tasks_head) + css_advance_task_iter(it); + else + it->task_pos = l; + + return res; +} + +/** + * css_task_iter_end - finish task iteration + * @it: the task iterator to finish + * + * Finish task iteration started by css_task_iter_start(). + */ +void css_task_iter_end(struct css_task_iter *it) + __releases(css_set_rwsem) +{ + up_read(&css_set_rwsem); +} + +/** + * cgroup_trasnsfer_tasks - move tasks from one cgroup to another + * @to: cgroup to which the tasks will be moved + * @from: cgroup in which the tasks currently reside + * + * Locking rules between cgroup_post_fork() and the migration path + * guarantee that, if a task is forking while being migrated, the new child + * is guaranteed to be either visible in the source cgroup after the + * parent's migration is complete or put into the target cgroup. No task + * can slip out of migration through forking. + */ +int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from) +{ + LIST_HEAD(preloaded_csets); + struct cgrp_cset_link *link; + struct css_task_iter it; + struct task_struct *task; + int ret; + + mutex_lock(&cgroup_mutex); + + /* all tasks in @from are being moved, all csets are source */ + down_read(&css_set_rwsem); + list_for_each_entry(link, &from->cset_links, cset_link) + cgroup_migrate_add_src(link->cset, to, &preloaded_csets); + up_read(&css_set_rwsem); + + ret = cgroup_migrate_prepare_dst(to, &preloaded_csets); + if (ret) + goto out_err; + + /* + * Migrate tasks one-by-one until @form is empty. This fails iff + * ->can_attach() fails. + */ + do { + css_task_iter_start(&from->self, &it); + task = css_task_iter_next(&it); + if (task) + get_task_struct(task); + css_task_iter_end(&it); + + if (task) { + ret = cgroup_migrate(to, task, false); + put_task_struct(task); + } + } while (task && !ret); +out_err: + cgroup_migrate_finish(&preloaded_csets); + mutex_unlock(&cgroup_mutex); + return ret; +} + +/* + * Stuff for reading the 'tasks'/'procs' files. + * + * Reading this file can return large amounts of data if a cgroup has + * *lots* of attached tasks. So it may need several calls to read(), + * but we cannot guarantee that the information we produce is correct + * unless we produce it entirely atomically. + * + */ + +/* which pidlist file are we talking about? */ +enum cgroup_filetype { + CGROUP_FILE_PROCS, + CGROUP_FILE_TASKS, +}; + +/* + * A pidlist is a list of pids that virtually represents the contents of one + * of the cgroup files ("procs" or "tasks"). We keep a list of such pidlists, + * a pair (one each for procs, tasks) for each pid namespace that's relevant + * to the cgroup. + */ +struct cgroup_pidlist { + /* + * used to find which pidlist is wanted. doesn't change as long as + * this particular list stays in the list. + */ + struct { enum cgroup_filetype type; struct pid_namespace *ns; } key; + /* array of xids */ + pid_t *list; + /* how many elements the above list has */ + int length; + /* each of these stored in a list by its cgroup */ + struct list_head links; + /* pointer to the cgroup we belong to, for list removal purposes */ + struct cgroup *owner; + /* for delayed destruction */ + struct delayed_work destroy_dwork; +}; + +/* + * The following two functions "fix" the issue where there are more pids + * than kmalloc will give memory for; in such cases, we use vmalloc/vfree. + * TODO: replace with a kernel-wide solution to this problem + */ +#define PIDLIST_TOO_LARGE(c) ((c) * sizeof(pid_t) > (PAGE_SIZE * 2)) +static void *pidlist_allocate(int count) +{ + if (PIDLIST_TOO_LARGE(count)) + return vmalloc(count * sizeof(pid_t)); + else + return kmalloc(count * sizeof(pid_t), GFP_KERNEL); +} + +static void pidlist_free(void *p) +{ + kvfree(p); +} + +/* + * Used to destroy all pidlists lingering waiting for destroy timer. None + * should be left afterwards. + */ +static void cgroup_pidlist_destroy_all(struct cgroup *cgrp) +{ + struct cgroup_pidlist *l, *tmp_l; + + mutex_lock(&cgrp->pidlist_mutex); + list_for_each_entry_safe(l, tmp_l, &cgrp->pidlists, links) + mod_delayed_work(cgroup_pidlist_destroy_wq, &l->destroy_dwork, 0); + mutex_unlock(&cgrp->pidlist_mutex); + + flush_workqueue(cgroup_pidlist_destroy_wq); + BUG_ON(!list_empty(&cgrp->pidlists)); +} + +static void cgroup_pidlist_destroy_work_fn(struct work_struct *work) +{ + struct delayed_work *dwork = to_delayed_work(work); + struct cgroup_pidlist *l = container_of(dwork, struct cgroup_pidlist, + destroy_dwork); + struct cgroup_pidlist *tofree = NULL; + + mutex_lock(&l->owner->pidlist_mutex); + + /* + * Destroy iff we didn't get queued again. The state won't change + * as destroy_dwork can only be queued while locked. + */ + if (!delayed_work_pending(dwork)) { + list_del(&l->links); + pidlist_free(l->list); + put_pid_ns(l->key.ns); + tofree = l; + } + + mutex_unlock(&l->owner->pidlist_mutex); + kfree(tofree); +} + +/* + * pidlist_uniq - given a kmalloc()ed list, strip out all duplicate entries + * Returns the number of unique elements. + */ +static int pidlist_uniq(pid_t *list, int length) +{ + int src, dest = 1; + + /* + * we presume the 0th element is unique, so i starts at 1. trivial + * edge cases first; no work needs to be done for either + */ + if (length == 0 || length == 1) + return length; + /* src and dest walk down the list; dest counts unique elements */ + for (src = 1; src < length; src++) { + /* find next unique element */ + while (list[src] == list[src-1]) { + src++; + if (src == length) + goto after; + } + /* dest always points to where the next unique element goes */ + list[dest] = list[src]; + dest++; + } +after: + return dest; +} + +/* + * The two pid files - task and cgroup.procs - guaranteed that the result + * is sorted, which forced this whole pidlist fiasco. As pid order is + * different per namespace, each namespace needs differently sorted list, + * making it impossible to use, for example, single rbtree of member tasks + * sorted by task pointer. As pidlists can be fairly large, allocating one + * per open file is dangerous, so cgroup had to implement shared pool of + * pidlists keyed by cgroup and namespace. + * + * All this extra complexity was caused by the original implementation + * committing to an entirely unnecessary property. In the long term, we + * want to do away with it. Explicitly scramble sort order if on the + * default hierarchy so that no such expectation exists in the new + * interface. + * + * Scrambling is done by swapping every two consecutive bits, which is + * non-identity one-to-one mapping which disturbs sort order sufficiently. + */ +static pid_t pid_fry(pid_t pid) +{ + unsigned a = pid & 0x55555555; + unsigned b = pid & 0xAAAAAAAA; + + return (a << 1) | (b >> 1); +} + +static pid_t cgroup_pid_fry(struct cgroup *cgrp, pid_t pid) +{ + if (cgroup_on_dfl(cgrp)) + return pid_fry(pid); + else + return pid; +} + +static int cmppid(const void *a, const void *b) +{ + return *(pid_t *)a - *(pid_t *)b; +} + +static int fried_cmppid(const void *a, const void *b) +{ + return pid_fry(*(pid_t *)a) - pid_fry(*(pid_t *)b); +} + +static struct cgroup_pidlist *cgroup_pidlist_find(struct cgroup *cgrp, + enum cgroup_filetype type) +{ + struct cgroup_pidlist *l; + /* don't need task_nsproxy() if we're looking at ourself */ + struct pid_namespace *ns = task_active_pid_ns(current); + + lockdep_assert_held(&cgrp->pidlist_mutex); + + list_for_each_entry(l, &cgrp->pidlists, links) + if (l->key.type == type && l->key.ns == ns) + return l; + return NULL; +} + +/* + * find the appropriate pidlist for our purpose (given procs vs tasks) + * returns with the lock on that pidlist already held, and takes care + * of the use count, or returns NULL with no locks held if we're out of + * memory. + */ +static struct cgroup_pidlist *cgroup_pidlist_find_create(struct cgroup *cgrp, + enum cgroup_filetype type) +{ + struct cgroup_pidlist *l; + + lockdep_assert_held(&cgrp->pidlist_mutex); + + l = cgroup_pidlist_find(cgrp, type); + if (l) + return l; + + /* entry not found; create a new one */ + l = kzalloc(sizeof(struct cgroup_pidlist), GFP_KERNEL); + if (!l) + return l; + + INIT_DELAYED_WORK(&l->destroy_dwork, cgroup_pidlist_destroy_work_fn); + l->key.type = type; + /* don't need task_nsproxy() if we're looking at ourself */ + l->key.ns = get_pid_ns(task_active_pid_ns(current)); + l->owner = cgrp; + list_add(&l->links, &cgrp->pidlists); + return l; +} + +/* + * Load a cgroup's pidarray with either procs' tgids or tasks' pids + */ +static int pidlist_array_load(struct cgroup *cgrp, enum cgroup_filetype type, + struct cgroup_pidlist **lp) +{ + pid_t *array; + int length; + int pid, n = 0; /* used for populating the array */ + struct css_task_iter it; + struct task_struct *tsk; + struct cgroup_pidlist *l; + + lockdep_assert_held(&cgrp->pidlist_mutex); + + /* + * If cgroup gets more users after we read count, we won't have + * enough space - tough. This race is indistinguishable to the + * caller from the case that the additional cgroup users didn't + * show up until sometime later on. + */ + length = cgroup_task_count(cgrp); + array = pidlist_allocate(length); + if (!array) + return -ENOMEM; + /* now, populate the array */ + css_task_iter_start(&cgrp->self, &it); + while ((tsk = css_task_iter_next(&it))) { + if (unlikely(n == length)) + break; + /* get tgid or pid for procs or tasks file respectively */ + if (type == CGROUP_FILE_PROCS) + pid = task_tgid_vnr(tsk); + else + pid = task_pid_vnr(tsk); + if (pid > 0) /* make sure to only use valid results */ + array[n++] = pid; + } + css_task_iter_end(&it); + length = n; + /* now sort & (if procs) strip out duplicates */ + if (cgroup_on_dfl(cgrp)) + sort(array, length, sizeof(pid_t), fried_cmppid, NULL); + else + sort(array, length, sizeof(pid_t), cmppid, NULL); + if (type == CGROUP_FILE_PROCS) + length = pidlist_uniq(array, length); + + l = cgroup_pidlist_find_create(cgrp, type); + if (!l) { + pidlist_free(array); + return -ENOMEM; + } + + /* store array, freeing old if necessary */ + pidlist_free(l->list); + l->list = array; + l->length = length; + *lp = l; + return 0; +} + +/** + * cgroupstats_build - build and fill cgroupstats + * @stats: cgroupstats to fill information into + * @dentry: A dentry entry belonging to the cgroup for which stats have + * been requested. + * + * Build and fill cgroupstats so that taskstats can export it to user + * space. + */ +int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry) +{ + struct kernfs_node *kn = kernfs_node_from_dentry(dentry); + struct cgroup *cgrp; + struct css_task_iter it; + struct task_struct *tsk; + + /* it should be kernfs_node belonging to cgroupfs and is a directory */ + if (dentry->d_sb->s_type != &cgroup_fs_type || !kn || + kernfs_type(kn) != KERNFS_DIR) + return -EINVAL; + + mutex_lock(&cgroup_mutex); + + /* + * We aren't being called from kernfs and there's no guarantee on + * @kn->priv's validity. For this and css_tryget_online_from_dir(), + * @kn->priv is RCU safe. Let's do the RCU dancing. + */ + rcu_read_lock(); + cgrp = rcu_dereference(kn->priv); + if (!cgrp || cgroup_is_dead(cgrp)) { + rcu_read_unlock(); + mutex_unlock(&cgroup_mutex); + return -ENOENT; + } + rcu_read_unlock(); + + css_task_iter_start(&cgrp->self, &it); + while ((tsk = css_task_iter_next(&it))) { + switch (tsk->state) { + case TASK_RUNNING: + stats->nr_running++; + break; + case TASK_INTERRUPTIBLE: + stats->nr_sleeping++; + break; + case TASK_UNINTERRUPTIBLE: + stats->nr_uninterruptible++; + break; + case TASK_STOPPED: + stats->nr_stopped++; + break; + default: + if (delayacct_is_task_waiting_on_io(tsk)) + stats->nr_io_wait++; + break; + } + } + css_task_iter_end(&it); + + mutex_unlock(&cgroup_mutex); + return 0; +} + + +/* + * seq_file methods for the tasks/procs files. The seq_file position is the + * next pid to display; the seq_file iterator is a pointer to the pid + * in the cgroup->l->list array. + */ + +static void *cgroup_pidlist_start(struct seq_file *s, loff_t *pos) +{ + /* + * Initially we receive a position value that corresponds to + * one more than the last pid shown (or 0 on the first call or + * after a seek to the start). Use a binary-search to find the + * next pid to display, if any + */ + struct kernfs_open_file *of = s->private; + struct cgroup *cgrp = seq_css(s)->cgroup; + struct cgroup_pidlist *l; + enum cgroup_filetype type = seq_cft(s)->private; + int index = 0, pid = *pos; + int *iter, ret; + + mutex_lock(&cgrp->pidlist_mutex); + + /* + * !NULL @of->priv indicates that this isn't the first start() + * after open. If the matching pidlist is around, we can use that. + * Look for it. Note that @of->priv can't be used directly. It + * could already have been destroyed. + */ + if (of->priv) + of->priv = cgroup_pidlist_find(cgrp, type); + + /* + * Either this is the first start() after open or the matching + * pidlist has been destroyed inbetween. Create a new one. + */ + if (!of->priv) { + ret = pidlist_array_load(cgrp, type, + (struct cgroup_pidlist **)&of->priv); + if (ret) + return ERR_PTR(ret); + } + l = of->priv; + + if (pid) { + int end = l->length; + + while (index < end) { + int mid = (index + end) / 2; + if (cgroup_pid_fry(cgrp, l->list[mid]) == pid) { + index = mid; + break; + } else if (cgroup_pid_fry(cgrp, l->list[mid]) <= pid) + index = mid + 1; + else + end = mid; + } + } + /* If we're off the end of the array, we're done */ + if (index >= l->length) + return NULL; + /* Update the abstract position to be the actual pid that we found */ + iter = l->list + index; + *pos = cgroup_pid_fry(cgrp, *iter); + return iter; +} + +static void cgroup_pidlist_stop(struct seq_file *s, void *v) +{ + struct kernfs_open_file *of = s->private; + struct cgroup_pidlist *l = of->priv; + + if (l) + mod_delayed_work(cgroup_pidlist_destroy_wq, &l->destroy_dwork, + CGROUP_PIDLIST_DESTROY_DELAY); + mutex_unlock(&seq_css(s)->cgroup->pidlist_mutex); +} + +static void *cgroup_pidlist_next(struct seq_file *s, void *v, loff_t *pos) +{ + struct kernfs_open_file *of = s->private; + struct cgroup_pidlist *l = of->priv; + pid_t *p = v; + pid_t *end = l->list + l->length; + /* + * Advance to the next pid in the array. If this goes off the + * end, we're done + */ + p++; + if (p >= end) { + return NULL; + } else { + *pos = cgroup_pid_fry(seq_css(s)->cgroup, *p); + return p; + } +} + +static int cgroup_pidlist_show(struct seq_file *s, void *v) +{ + seq_printf(s, "%d\n", *(int *)v); + + return 0; +} + +static u64 cgroup_read_notify_on_release(struct cgroup_subsys_state *css, + struct cftype *cft) +{ + return notify_on_release(css->cgroup); +} + +static int cgroup_write_notify_on_release(struct cgroup_subsys_state *css, + struct cftype *cft, u64 val) +{ + if (val) + set_bit(CGRP_NOTIFY_ON_RELEASE, &css->cgroup->flags); + else + clear_bit(CGRP_NOTIFY_ON_RELEASE, &css->cgroup->flags); + return 0; +} + +static u64 cgroup_clone_children_read(struct cgroup_subsys_state *css, + struct cftype *cft) +{ + return test_bit(CGRP_CPUSET_CLONE_CHILDREN, &css->cgroup->flags); +} + +static int cgroup_clone_children_write(struct cgroup_subsys_state *css, + struct cftype *cft, u64 val) +{ + if (val) + set_bit(CGRP_CPUSET_CLONE_CHILDREN, &css->cgroup->flags); + else + clear_bit(CGRP_CPUSET_CLONE_CHILDREN, &css->cgroup->flags); + return 0; +} + +/* cgroup core interface files for the default hierarchy */ +static struct cftype cgroup_dfl_base_files[] = { + { + .name = "cgroup.procs", + .seq_start = cgroup_pidlist_start, + .seq_next = cgroup_pidlist_next, + .seq_stop = cgroup_pidlist_stop, + .seq_show = cgroup_pidlist_show, + .private = CGROUP_FILE_PROCS, + .write = cgroup_procs_write, + .mode = S_IRUGO | S_IWUSR, + }, + { + .name = "cgroup.controllers", + .flags = CFTYPE_ONLY_ON_ROOT, + .seq_show = cgroup_root_controllers_show, + }, + { + .name = "cgroup.controllers", + .flags = CFTYPE_NOT_ON_ROOT, + .seq_show = cgroup_controllers_show, + }, + { + .name = "cgroup.subtree_control", + .seq_show = cgroup_subtree_control_show, + .write = cgroup_subtree_control_write, + }, + { + .name = "cgroup.populated", + .flags = CFTYPE_NOT_ON_ROOT, + .seq_show = cgroup_populated_show, + }, + { } /* terminate */ +}; + +/* cgroup core interface files for the legacy hierarchies */ +static struct cftype cgroup_legacy_base_files[] = { + { + .name = "cgroup.procs", + .seq_start = cgroup_pidlist_start, + .seq_next = cgroup_pidlist_next, + .seq_stop = cgroup_pidlist_stop, + .seq_show = cgroup_pidlist_show, + .private = CGROUP_FILE_PROCS, + .write = cgroup_procs_write, + .mode = S_IRUGO | S_IWUSR, + }, + { + .name = "cgroup.clone_children", + .read_u64 = cgroup_clone_children_read, + .write_u64 = cgroup_clone_children_write, + }, + { + .name = "cgroup.sane_behavior", + .flags = CFTYPE_ONLY_ON_ROOT, + .seq_show = cgroup_sane_behavior_show, + }, + { + .name = "tasks", + .seq_start = cgroup_pidlist_start, + .seq_next = cgroup_pidlist_next, + .seq_stop = cgroup_pidlist_stop, + .seq_show = cgroup_pidlist_show, + .private = CGROUP_FILE_TASKS, + .write = cgroup_tasks_write, + .mode = S_IRUGO | S_IWUSR, + }, + { + .name = "notify_on_release", + .read_u64 = cgroup_read_notify_on_release, + .write_u64 = cgroup_write_notify_on_release, + }, + { + .name = "release_agent", + .flags = CFTYPE_ONLY_ON_ROOT, + .seq_show = cgroup_release_agent_show, + .write = cgroup_release_agent_write, + .max_write_len = PATH_MAX - 1, + }, + { } /* terminate */ +}; + +/** + * cgroup_populate_dir - create subsys files in a cgroup directory + * @cgrp: target cgroup + * @subsys_mask: mask of the subsystem ids whose files should be added + * + * On failure, no file is added. + */ +static int cgroup_populate_dir(struct cgroup *cgrp, unsigned int subsys_mask) +{ + struct cgroup_subsys *ss; + int i, ret = 0; + + /* process cftsets of each subsystem */ + for_each_subsys(ss, i) { + struct cftype *cfts; + + if (!(subsys_mask & (1 << i))) + continue; + + list_for_each_entry(cfts, &ss->cfts, node) { + ret = cgroup_addrm_files(cgrp, cfts, true); + if (ret < 0) + goto err; + } + } + return 0; +err: + cgroup_clear_dir(cgrp, subsys_mask); + return ret; +} + +/* + * css destruction is four-stage process. + * + * 1. Destruction starts. Killing of the percpu_ref is initiated. + * Implemented in kill_css(). + * + * 2. When the percpu_ref is confirmed to be visible as killed on all CPUs + * and thus css_tryget_online() is guaranteed to fail, the css can be + * offlined by invoking offline_css(). After offlining, the base ref is + * put. Implemented in css_killed_work_fn(). + * + * 3. When the percpu_ref reaches zero, the only possible remaining + * accessors are inside RCU read sections. css_release() schedules the + * RCU callback. + * + * 4. After the grace period, the css can be freed. Implemented in + * css_free_work_fn(). + * + * It is actually hairier because both step 2 and 4 require process context + * and thus involve punting to css->destroy_work adding two additional + * steps to the already complex sequence. + */ +static void css_free_work_fn(struct work_struct *work) +{ + struct cgroup_subsys_state *css = + container_of(work, struct cgroup_subsys_state, destroy_work); + struct cgroup_subsys *ss = css->ss; + struct cgroup *cgrp = css->cgroup; + + percpu_ref_exit(&css->refcnt); + + if (ss) { + /* css free path */ + int id = css->id; + + if (css->parent) + css_put(css->parent); + + ss->css_free(css); + cgroup_idr_remove(&ss->css_idr, id); + cgroup_put(cgrp); + } else { + /* cgroup free path */ + atomic_dec(&cgrp->root->nr_cgrps); + cgroup_pidlist_destroy_all(cgrp); + cancel_work_sync(&cgrp->release_agent_work); + + if (cgroup_parent(cgrp)) { + /* + * We get a ref to the parent, and put the ref when + * this cgroup is being freed, so it's guaranteed + * that the parent won't be destroyed before its + * children. + */ + cgroup_put(cgroup_parent(cgrp)); + kernfs_put(cgrp->kn); + kfree(cgrp); + } else { + /* + * This is root cgroup's refcnt reaching zero, + * which indicates that the root should be + * released. + */ + cgroup_destroy_root(cgrp->root); + } + } +} + +static void css_free_rcu_fn(struct rcu_head *rcu_head) +{ + struct cgroup_subsys_state *css = + container_of(rcu_head, struct cgroup_subsys_state, rcu_head); + + INIT_WORK(&css->destroy_work, css_free_work_fn); + queue_work(cgroup_destroy_wq, &css->destroy_work); +} + +static void css_release_work_fn(struct swork_event *sev) +{ + struct cgroup_subsys_state *css = + container_of(sev, struct cgroup_subsys_state, destroy_swork); + struct cgroup_subsys *ss = css->ss; + struct cgroup *cgrp = css->cgroup; + + mutex_lock(&cgroup_mutex); + + css->flags |= CSS_RELEASED; + list_del_rcu(&css->sibling); + + if (ss) { + /* css release path */ + cgroup_idr_replace(&ss->css_idr, NULL, css->id); + if (ss->css_released) + ss->css_released(css); + } else { + /* cgroup release path */ + cgroup_idr_remove(&cgrp->root->cgroup_idr, cgrp->id); + cgrp->id = -1; + + /* + * There are two control paths which try to determine + * cgroup from dentry without going through kernfs - + * cgroupstats_build() and css_tryget_online_from_dir(). + * Those are supported by RCU protecting clearing of + * cgrp->kn->priv backpointer. + */ + RCU_INIT_POINTER(*(void __rcu __force **)&cgrp->kn->priv, NULL); + } + + mutex_unlock(&cgroup_mutex); + + call_rcu(&css->rcu_head, css_free_rcu_fn); +} + +static void css_release(struct percpu_ref *ref) +{ + struct cgroup_subsys_state *css = + container_of(ref, struct cgroup_subsys_state, refcnt); + + INIT_SWORK(&css->destroy_swork, css_release_work_fn); + swork_queue(&css->destroy_swork); +} + +static void init_and_link_css(struct cgroup_subsys_state *css, + struct cgroup_subsys *ss, struct cgroup *cgrp) +{ + lockdep_assert_held(&cgroup_mutex); + + cgroup_get(cgrp); + + memset(css, 0, sizeof(*css)); + css->cgroup = cgrp; + css->ss = ss; + INIT_LIST_HEAD(&css->sibling); + INIT_LIST_HEAD(&css->children); + css->serial_nr = css_serial_nr_next++; + + if (cgroup_parent(cgrp)) { + css->parent = cgroup_css(cgroup_parent(cgrp), ss); + css_get(css->parent); + } + + BUG_ON(cgroup_css(cgrp, ss)); +} + +/* invoke ->css_online() on a new CSS and mark it online if successful */ +static int online_css(struct cgroup_subsys_state *css) +{ + struct cgroup_subsys *ss = css->ss; + int ret = 0; + + lockdep_assert_held(&cgroup_mutex); + + if (ss->css_online) + ret = ss->css_online(css); + if (!ret) { + css->flags |= CSS_ONLINE; + rcu_assign_pointer(css->cgroup->subsys[ss->id], css); + } + return ret; +} + +/* if the CSS is online, invoke ->css_offline() on it and mark it offline */ +static void offline_css(struct cgroup_subsys_state *css) +{ + struct cgroup_subsys *ss = css->ss; + + lockdep_assert_held(&cgroup_mutex); + + if (!(css->flags & CSS_ONLINE)) + return; + + if (ss->css_offline) + ss->css_offline(css); + + css->flags &= ~CSS_ONLINE; + RCU_INIT_POINTER(css->cgroup->subsys[ss->id], NULL); + + wake_up_all(&css->cgroup->offline_waitq); +} + +/** + * create_css - create a cgroup_subsys_state + * @cgrp: the cgroup new css will be associated with + * @ss: the subsys of new css + * @visible: whether to create control knobs for the new css or not + * + * Create a new css associated with @cgrp - @ss pair. On success, the new + * css is online and installed in @cgrp with all interface files created if + * @visible. Returns 0 on success, -errno on failure. + */ +static int create_css(struct cgroup *cgrp, struct cgroup_subsys *ss, + bool visible) +{ + struct cgroup *parent = cgroup_parent(cgrp); + struct cgroup_subsys_state *parent_css = cgroup_css(parent, ss); + struct cgroup_subsys_state *css; + int err; + + lockdep_assert_held(&cgroup_mutex); + + css = ss->css_alloc(parent_css); + if (IS_ERR(css)) + return PTR_ERR(css); + + init_and_link_css(css, ss, cgrp); + + err = percpu_ref_init(&css->refcnt, css_release, 0, GFP_KERNEL); + if (err) + goto err_free_css; + + err = cgroup_idr_alloc(&ss->css_idr, NULL, 2, 0, GFP_NOWAIT); + if (err < 0) + goto err_free_percpu_ref; + css->id = err; + + if (visible) { + err = cgroup_populate_dir(cgrp, 1 << ss->id); + if (err) + goto err_free_id; + } + + /* @css is ready to be brought online now, make it visible */ + list_add_tail_rcu(&css->sibling, &parent_css->children); + cgroup_idr_replace(&ss->css_idr, css, css->id); + + err = online_css(css); + if (err) + goto err_list_del; + + if (ss->broken_hierarchy && !ss->warned_broken_hierarchy && + cgroup_parent(parent)) { + pr_warn("%s (%d) created nested cgroup for controller \"%s\" which has incomplete hierarchy support. Nested cgroups may change behavior in the future.\n", + current->comm, current->pid, ss->name); + if (!strcmp(ss->name, "memory")) + pr_warn("\"memory\" requires setting use_hierarchy to 1 on the root\n"); + ss->warned_broken_hierarchy = true; + } + + return 0; + +err_list_del: + list_del_rcu(&css->sibling); + cgroup_clear_dir(css->cgroup, 1 << css->ss->id); +err_free_id: + cgroup_idr_remove(&ss->css_idr, css->id); +err_free_percpu_ref: + percpu_ref_exit(&css->refcnt); +err_free_css: + call_rcu(&css->rcu_head, css_free_rcu_fn); + return err; +} + +static int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name, + umode_t mode) +{ + struct cgroup *parent, *cgrp; + struct cgroup_root *root; + struct cgroup_subsys *ss; + struct kernfs_node *kn; + struct cftype *base_files; + int ssid, ret; + + /* Do not accept '\n' to prevent making /proc//cgroup unparsable. + */ + if (strchr(name, '\n')) + return -EINVAL; + + parent = cgroup_kn_lock_live(parent_kn); + if (!parent) + return -ENODEV; + root = parent->root; + + /* allocate the cgroup and its ID, 0 is reserved for the root */ + cgrp = kzalloc(sizeof(*cgrp), GFP_KERNEL); + if (!cgrp) { + ret = -ENOMEM; + goto out_unlock; + } + + ret = percpu_ref_init(&cgrp->self.refcnt, css_release, 0, GFP_KERNEL); + if (ret) + goto out_free_cgrp; + + /* + * Temporarily set the pointer to NULL, so idr_find() won't return + * a half-baked cgroup. + */ + cgrp->id = cgroup_idr_alloc(&root->cgroup_idr, NULL, 2, 0, GFP_NOWAIT); + if (cgrp->id < 0) { + ret = -ENOMEM; + goto out_cancel_ref; + } + + init_cgroup_housekeeping(cgrp); + + cgrp->self.parent = &parent->self; + cgrp->root = root; + + if (notify_on_release(parent)) + set_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags); + + if (test_bit(CGRP_CPUSET_CLONE_CHILDREN, &parent->flags)) + set_bit(CGRP_CPUSET_CLONE_CHILDREN, &cgrp->flags); + + /* create the directory */ + kn = kernfs_create_dir(parent->kn, name, mode, cgrp); + if (IS_ERR(kn)) { + ret = PTR_ERR(kn); + goto out_free_id; + } + cgrp->kn = kn; + + /* + * This extra ref will be put in cgroup_free_fn() and guarantees + * that @cgrp->kn is always accessible. + */ + kernfs_get(kn); + + cgrp->self.serial_nr = css_serial_nr_next++; + + /* allocation complete, commit to creation */ + list_add_tail_rcu(&cgrp->self.sibling, &cgroup_parent(cgrp)->self.children); + atomic_inc(&root->nr_cgrps); + cgroup_get(parent); + + /* + * @cgrp is now fully operational. If something fails after this + * point, it'll be released via the normal destruction path. + */ + cgroup_idr_replace(&root->cgroup_idr, cgrp, cgrp->id); + + ret = cgroup_kn_set_ugid(kn); + if (ret) + goto out_destroy; + + if (cgroup_on_dfl(cgrp)) + base_files = cgroup_dfl_base_files; + else + base_files = cgroup_legacy_base_files; + + ret = cgroup_addrm_files(cgrp, base_files, true); + if (ret) + goto out_destroy; + + /* let's create and online css's */ + for_each_subsys(ss, ssid) { + if (parent->child_subsys_mask & (1 << ssid)) { + ret = create_css(cgrp, ss, + parent->subtree_control & (1 << ssid)); + if (ret) + goto out_destroy; + } + } + + /* + * On the default hierarchy, a child doesn't automatically inherit + * subtree_control from the parent. Each is configured manually. + */ + if (!cgroup_on_dfl(cgrp)) { + cgrp->subtree_control = parent->subtree_control; + cgroup_refresh_child_subsys_mask(cgrp); + } + + kernfs_activate(kn); + + ret = 0; + goto out_unlock; + +out_free_id: + cgroup_idr_remove(&root->cgroup_idr, cgrp->id); +out_cancel_ref: + percpu_ref_exit(&cgrp->self.refcnt); +out_free_cgrp: + kfree(cgrp); +out_unlock: + cgroup_kn_unlock(parent_kn); + return ret; + +out_destroy: + cgroup_destroy_locked(cgrp); + goto out_unlock; +} + +/* + * This is called when the refcnt of a css is confirmed to be killed. + * css_tryget_online() is now guaranteed to fail. Tell the subsystem to + * initate destruction and put the css ref from kill_css(). + */ +static void css_killed_work_fn(struct work_struct *work) +{ + struct cgroup_subsys_state *css = + container_of(work, struct cgroup_subsys_state, destroy_work); + + mutex_lock(&cgroup_mutex); + offline_css(css); + mutex_unlock(&cgroup_mutex); + + css_put(css); +} + +/* css kill confirmation processing requires process context, bounce */ +static void css_killed_ref_fn(struct percpu_ref *ref) +{ + struct cgroup_subsys_state *css = + container_of(ref, struct cgroup_subsys_state, refcnt); + + INIT_WORK(&css->destroy_work, css_killed_work_fn); + queue_work(cgroup_destroy_wq, &css->destroy_work); +} + +/** + * kill_css - destroy a css + * @css: css to destroy + * + * This function initiates destruction of @css by removing cgroup interface + * files and putting its base reference. ->css_offline() will be invoked + * asynchronously once css_tryget_online() is guaranteed to fail and when + * the reference count reaches zero, @css will be released. + */ +static void kill_css(struct cgroup_subsys_state *css) +{ + lockdep_assert_held(&cgroup_mutex); + + /* + * This must happen before css is disassociated with its cgroup. + * See seq_css() for details. + */ + cgroup_clear_dir(css->cgroup, 1 << css->ss->id); + + /* + * Killing would put the base ref, but we need to keep it alive + * until after ->css_offline(). + */ + css_get(css); + + /* + * cgroup core guarantees that, by the time ->css_offline() is + * invoked, no new css reference will be given out via + * css_tryget_online(). We can't simply call percpu_ref_kill() and + * proceed to offlining css's because percpu_ref_kill() doesn't + * guarantee that the ref is seen as killed on all CPUs on return. + * + * Use percpu_ref_kill_and_confirm() to get notifications as each + * css is confirmed to be seen as killed on all CPUs. + */ + percpu_ref_kill_and_confirm(&css->refcnt, css_killed_ref_fn); +} + +/** + * cgroup_destroy_locked - the first stage of cgroup destruction + * @cgrp: cgroup to be destroyed + * + * css's make use of percpu refcnts whose killing latency shouldn't be + * exposed to userland and are RCU protected. Also, cgroup core needs to + * guarantee that css_tryget_online() won't succeed by the time + * ->css_offline() is invoked. To satisfy all the requirements, + * destruction is implemented in the following two steps. + * + * s1. Verify @cgrp can be destroyed and mark it dying. Remove all + * userland visible parts and start killing the percpu refcnts of + * css's. Set up so that the next stage will be kicked off once all + * the percpu refcnts are confirmed to be killed. + * + * s2. Invoke ->css_offline(), mark the cgroup dead and proceed with the + * rest of destruction. Once all cgroup references are gone, the + * cgroup is RCU-freed. + * + * This function implements s1. After this step, @cgrp is gone as far as + * the userland is concerned and a new cgroup with the same name may be + * created. As cgroup doesn't care about the names internally, this + * doesn't cause any problem. + */ +static int cgroup_destroy_locked(struct cgroup *cgrp) + __releases(&cgroup_mutex) __acquires(&cgroup_mutex) +{ + struct cgroup_subsys_state *css; + bool empty; + int ssid; + + lockdep_assert_held(&cgroup_mutex); + + /* + * css_set_rwsem synchronizes access to ->cset_links and prevents + * @cgrp from being removed while put_css_set() is in progress. + */ + down_read(&css_set_rwsem); + empty = list_empty(&cgrp->cset_links); + up_read(&css_set_rwsem); + if (!empty) + return -EBUSY; + + /* + * Make sure there's no live children. We can't test emptiness of + * ->self.children as dead children linger on it while being + * drained; otherwise, "rmdir parent/child parent" may fail. + */ + if (css_has_online_children(&cgrp->self)) + return -EBUSY; + + /* + * Mark @cgrp dead. This prevents further task migration and child + * creation by disabling cgroup_lock_live_group(). + */ + cgrp->self.flags &= ~CSS_ONLINE; + + /* initiate massacre of all css's */ + for_each_css(css, ssid, cgrp) + kill_css(css); + + /* + * Remove @cgrp directory along with the base files. @cgrp has an + * extra ref on its kn. + */ + kernfs_remove(cgrp->kn); + + check_for_release(cgroup_parent(cgrp)); + + /* put the base reference */ + percpu_ref_kill(&cgrp->self.refcnt); + + return 0; +}; + +static int cgroup_rmdir(struct kernfs_node *kn) +{ + struct cgroup *cgrp; + int ret = 0; + + cgrp = cgroup_kn_lock_live(kn); + if (!cgrp) + return 0; + + ret = cgroup_destroy_locked(cgrp); + + cgroup_kn_unlock(kn); + return ret; +} + +static struct kernfs_syscall_ops cgroup_kf_syscall_ops = { + .remount_fs = cgroup_remount, + .show_options = cgroup_show_options, + .mkdir = cgroup_mkdir, + .rmdir = cgroup_rmdir, + .rename = cgroup_rename, +}; + +static void __init cgroup_init_subsys(struct cgroup_subsys *ss, bool early) +{ + struct cgroup_subsys_state *css; + + printk(KERN_INFO "Initializing cgroup subsys %s\n", ss->name); + + mutex_lock(&cgroup_mutex); + + idr_init(&ss->css_idr); + INIT_LIST_HEAD(&ss->cfts); + + /* Create the root cgroup state for this subsystem */ + ss->root = &cgrp_dfl_root; + css = ss->css_alloc(cgroup_css(&cgrp_dfl_root.cgrp, ss)); + /* We don't handle early failures gracefully */ + BUG_ON(IS_ERR(css)); + init_and_link_css(css, ss, &cgrp_dfl_root.cgrp); + + /* + * Root csses are never destroyed and we can't initialize + * percpu_ref during early init. Disable refcnting. + */ + css->flags |= CSS_NO_REF; + + if (early) { + /* allocation can't be done safely during early init */ + css->id = 1; + } else { + css->id = cgroup_idr_alloc(&ss->css_idr, css, 1, 2, GFP_KERNEL); + BUG_ON(css->id < 0); + } + + /* Update the init_css_set to contain a subsys + * pointer to this state - since the subsystem is + * newly registered, all tasks and hence the + * init_css_set is in the subsystem's root cgroup. */ + init_css_set.subsys[ss->id] = css; + + need_forkexit_callback |= ss->fork || ss->exit; + + /* At system boot, before all subsystems have been + * registered, no tasks have been forked, so we don't + * need to invoke fork callbacks here. */ + BUG_ON(!list_empty(&init_task.tasks)); + + BUG_ON(online_css(css)); + + mutex_unlock(&cgroup_mutex); +} + +/** + * cgroup_init_early - cgroup initialization at system boot + * + * Initialize cgroups at system boot, and initialize any + * subsystems that request early init. + */ +int __init cgroup_init_early(void) +{ + static struct cgroup_sb_opts __initdata opts; + struct cgroup_subsys *ss; + int i; + + init_cgroup_root(&cgrp_dfl_root, &opts); + cgrp_dfl_root.cgrp.self.flags |= CSS_NO_REF; + + RCU_INIT_POINTER(init_task.cgroups, &init_css_set); + + for_each_subsys(ss, i) { + WARN(!ss->css_alloc || !ss->css_free || ss->name || ss->id, + "invalid cgroup_subsys %d:%s css_alloc=%p css_free=%p name:id=%d:%s\n", + i, cgroup_subsys_name[i], ss->css_alloc, ss->css_free, + ss->id, ss->name); + WARN(strlen(cgroup_subsys_name[i]) > MAX_CGROUP_TYPE_NAMELEN, + "cgroup_subsys_name %s too long\n", cgroup_subsys_name[i]); + + ss->id = i; + ss->name = cgroup_subsys_name[i]; + + if (ss->early_init) + cgroup_init_subsys(ss, true); + } + return 0; +} + +/** + * cgroup_init - cgroup initialization + * + * Register cgroup filesystem and /proc file, and initialize + * any subsystems that didn't request early init. + */ +int __init cgroup_init(void) +{ + struct cgroup_subsys *ss; + unsigned long key; + int ssid, err; + + BUG_ON(cgroup_init_cftypes(NULL, cgroup_dfl_base_files)); + BUG_ON(cgroup_init_cftypes(NULL, cgroup_legacy_base_files)); + + mutex_lock(&cgroup_mutex); + + /* Add init_css_set to the hash table */ + key = css_set_hash(init_css_set.subsys); + hash_add(css_set_table, &init_css_set.hlist, key); + + BUG_ON(cgroup_setup_root(&cgrp_dfl_root, 0)); + + mutex_unlock(&cgroup_mutex); + + for_each_subsys(ss, ssid) { + if (ss->early_init) { + struct cgroup_subsys_state *css = + init_css_set.subsys[ss->id]; + + css->id = cgroup_idr_alloc(&ss->css_idr, css, 1, 2, + GFP_KERNEL); + BUG_ON(css->id < 0); + } else { + cgroup_init_subsys(ss, false); + } + + list_add_tail(&init_css_set.e_cset_node[ssid], + &cgrp_dfl_root.cgrp.e_csets[ssid]); + + /* + * Setting dfl_root subsys_mask needs to consider the + * disabled flag and cftype registration needs kmalloc, + * both of which aren't available during early_init. + */ + if (ss->disabled) + continue; + + cgrp_dfl_root.subsys_mask |= 1 << ss->id; + + if (cgroup_legacy_files_on_dfl && !ss->dfl_cftypes) + ss->dfl_cftypes = ss->legacy_cftypes; + + if (!ss->dfl_cftypes) + cgrp_dfl_root_inhibit_ss_mask |= 1 << ss->id; + + if (ss->dfl_cftypes == ss->legacy_cftypes) { + WARN_ON(cgroup_add_cftypes(ss, ss->dfl_cftypes)); + } else { + WARN_ON(cgroup_add_dfl_cftypes(ss, ss->dfl_cftypes)); + WARN_ON(cgroup_add_legacy_cftypes(ss, ss->legacy_cftypes)); + } + + if (ss->bind) + ss->bind(init_css_set.subsys[ssid]); + } + + err = sysfs_create_mount_point(fs_kobj, "cgroup"); + if (err) + return err; + + err = register_filesystem(&cgroup_fs_type); + if (err < 0) { + sysfs_remove_mount_point(fs_kobj, "cgroup"); + return err; + } + + proc_create("cgroups", 0, NULL, &proc_cgroupstats_operations); + return 0; +} + +static int __init cgroup_wq_init(void) +{ + /* + * There isn't much point in executing destruction path in + * parallel. Good chunk is serialized with cgroup_mutex anyway. + * Use 1 for @max_active. + * + * We would prefer to do this in cgroup_init() above, but that + * is called before init_workqueues(): so leave this until after. + */ + cgroup_destroy_wq = alloc_workqueue("cgroup_destroy", 0, 1); + BUG_ON(!cgroup_destroy_wq); + BUG_ON(swork_get()); + + /* + * Used to destroy pidlists and separate to serve as flush domain. + * Cap @max_active to 1 too. + */ + cgroup_pidlist_destroy_wq = alloc_workqueue("cgroup_pidlist_destroy", + 0, 1); + BUG_ON(!cgroup_pidlist_destroy_wq); + + return 0; +} +core_initcall(cgroup_wq_init); + +/* + * proc_cgroup_show() + * - Print task's cgroup paths into seq_file, one line for each hierarchy + * - Used for /proc//cgroup. + */ +int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns, + struct pid *pid, struct task_struct *tsk) +{ + char *buf, *path; + int retval; + struct cgroup_root *root; + + retval = -ENOMEM; + buf = kmalloc(PATH_MAX, GFP_KERNEL); + if (!buf) + goto out; + + mutex_lock(&cgroup_mutex); + down_read(&css_set_rwsem); + + for_each_root(root) { + struct cgroup_subsys *ss; + struct cgroup *cgrp; + int ssid, count = 0; + + if (root == &cgrp_dfl_root && !cgrp_dfl_root_visible) + continue; + + seq_printf(m, "%d:", root->hierarchy_id); + for_each_subsys(ss, ssid) + if (root->subsys_mask & (1 << ssid)) + seq_printf(m, "%s%s", count++ ? "," : "", ss->name); + if (strlen(root->name)) + seq_printf(m, "%sname=%s", count ? "," : "", + root->name); + seq_putc(m, ':'); + cgrp = task_cgroup_from_root(tsk, root); + path = cgroup_path(cgrp, buf, PATH_MAX); + if (!path) { + retval = -ENAMETOOLONG; + goto out_unlock; + } + seq_puts(m, path); + seq_putc(m, '\n'); + } + + retval = 0; +out_unlock: + up_read(&css_set_rwsem); + mutex_unlock(&cgroup_mutex); + kfree(buf); +out: + return retval; +} + +/* Display information about each subsystem and each hierarchy */ +static int proc_cgroupstats_show(struct seq_file *m, void *v) +{ + struct cgroup_subsys *ss; + int i; + + seq_puts(m, "#subsys_name\thierarchy\tnum_cgroups\tenabled\n"); + /* + * ideally we don't want subsystems moving around while we do this. + * cgroup_mutex is also necessary to guarantee an atomic snapshot of + * subsys/hierarchy state. + */ + mutex_lock(&cgroup_mutex); + + for_each_subsys(ss, i) + seq_printf(m, "%s\t%d\t%d\t%d\n", + ss->name, ss->root->hierarchy_id, + atomic_read(&ss->root->nr_cgrps), !ss->disabled); + + mutex_unlock(&cgroup_mutex); + return 0; +} + +static int cgroupstats_open(struct inode *inode, struct file *file) +{ + return single_open(file, proc_cgroupstats_show, NULL); +} + +static const struct file_operations proc_cgroupstats_operations = { + .open = cgroupstats_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +/** + * cgroup_fork - initialize cgroup related fields during copy_process() + * @child: pointer to task_struct of forking parent process. + * + * A task is associated with the init_css_set until cgroup_post_fork() + * attaches it to the parent's css_set. Empty cg_list indicates that + * @child isn't holding reference to its css_set. + */ +void cgroup_fork(struct task_struct *child) +{ + RCU_INIT_POINTER(child->cgroups, &init_css_set); + INIT_LIST_HEAD(&child->cg_list); +} + +/** + * cgroup_post_fork - called on a new task after adding it to the task list + * @child: the task in question + * + * Adds the task to the list running through its css_set if necessary and + * call the subsystem fork() callbacks. Has to be after the task is + * visible on the task list in case we race with the first call to + * cgroup_task_iter_start() - to guarantee that the new task ends up on its + * list. + */ +void cgroup_post_fork(struct task_struct *child) +{ + struct cgroup_subsys *ss; + int i; + + /* + * This may race against cgroup_enable_task_cg_lists(). As that + * function sets use_task_css_set_links before grabbing + * tasklist_lock and we just went through tasklist_lock to add + * @child, it's guaranteed that either we see the set + * use_task_css_set_links or cgroup_enable_task_cg_lists() sees + * @child during its iteration. + * + * If we won the race, @child is associated with %current's + * css_set. Grabbing css_set_rwsem guarantees both that the + * association is stable, and, on completion of the parent's + * migration, @child is visible in the source of migration or + * already in the destination cgroup. This guarantee is necessary + * when implementing operations which need to migrate all tasks of + * a cgroup to another. + * + * Note that if we lose to cgroup_enable_task_cg_lists(), @child + * will remain in init_css_set. This is safe because all tasks are + * in the init_css_set before cg_links is enabled and there's no + * operation which transfers all tasks out of init_css_set. + */ + if (use_task_css_set_links) { + struct css_set *cset; + + down_write(&css_set_rwsem); + cset = task_css_set(current); + if (list_empty(&child->cg_list)) { + rcu_assign_pointer(child->cgroups, cset); + list_add(&child->cg_list, &cset->tasks); + get_css_set(cset); + } + up_write(&css_set_rwsem); + } + + /* + * Call ss->fork(). This must happen after @child is linked on + * css_set; otherwise, @child might change state between ->fork() + * and addition to css_set. + */ + if (need_forkexit_callback) { + for_each_subsys(ss, i) + if (ss->fork) + ss->fork(child); + } +} + +/** + * cgroup_exit - detach cgroup from exiting task + * @tsk: pointer to task_struct of exiting process + * + * Description: Detach cgroup from @tsk and release it. + * + * Note that cgroups marked notify_on_release force every task in + * them to take the global cgroup_mutex mutex when exiting. + * This could impact scaling on very large systems. Be reluctant to + * use notify_on_release cgroups where very high task exit scaling + * is required on large systems. + * + * We set the exiting tasks cgroup to the root cgroup (top_cgroup). We + * call cgroup_exit() while the task is still competent to handle + * notify_on_release(), then leave the task attached to the root cgroup in + * each hierarchy for the remainder of its exit. No need to bother with + * init_css_set refcnting. init_css_set never goes away and we can't race + * with migration path - PF_EXITING is visible to migration path. + */ +void cgroup_exit(struct task_struct *tsk) +{ + struct cgroup_subsys *ss; + struct css_set *cset; + bool put_cset = false; + int i; + + /* + * Unlink from @tsk from its css_set. As migration path can't race + * with us, we can check cg_list without grabbing css_set_rwsem. + */ + if (!list_empty(&tsk->cg_list)) { + down_write(&css_set_rwsem); + list_del_init(&tsk->cg_list); + up_write(&css_set_rwsem); + put_cset = true; + } + + /* Reassign the task to the init_css_set. */ + cset = task_css_set(tsk); + RCU_INIT_POINTER(tsk->cgroups, &init_css_set); + + if (need_forkexit_callback) { + /* see cgroup_post_fork() for details */ + for_each_subsys(ss, i) { + if (ss->exit) { + struct cgroup_subsys_state *old_css = cset->subsys[i]; + struct cgroup_subsys_state *css = task_css(tsk, i); + + ss->exit(css, old_css, tsk); + } + } + } + + if (put_cset) + put_css_set(cset); +} + +static void check_for_release(struct cgroup *cgrp) +{ + if (notify_on_release(cgrp) && !cgroup_has_tasks(cgrp) && + !css_has_online_children(&cgrp->self) && !cgroup_is_dead(cgrp)) + schedule_work(&cgrp->release_agent_work); +} + +/* + * Notify userspace when a cgroup is released, by running the + * configured release agent with the name of the cgroup (path + * relative to the root of cgroup file system) as the argument. + * + * Most likely, this user command will try to rmdir this cgroup. + * + * This races with the possibility that some other task will be + * attached to this cgroup before it is removed, or that some other + * user task will 'mkdir' a child cgroup of this cgroup. That's ok. + * The presumed 'rmdir' will fail quietly if this cgroup is no longer + * unused, and this cgroup will be reprieved from its death sentence, + * to continue to serve a useful existence. Next time it's released, + * we will get notified again, if it still has 'notify_on_release' set. + * + * The final arg to call_usermodehelper() is UMH_WAIT_EXEC, which + * means only wait until the task is successfully execve()'d. The + * separate release agent task is forked by call_usermodehelper(), + * then control in this thread returns here, without waiting for the + * release agent task. We don't bother to wait because the caller of + * this routine has no use for the exit status of the release agent + * task, so no sense holding our caller up for that. + */ +static void cgroup_release_agent(struct work_struct *work) +{ + struct cgroup *cgrp = + container_of(work, struct cgroup, release_agent_work); + char *pathbuf = NULL, *agentbuf = NULL, *path; + char *argv[3], *envp[3]; + + mutex_lock(&cgroup_mutex); + + pathbuf = kmalloc(PATH_MAX, GFP_KERNEL); + agentbuf = kstrdup(cgrp->root->release_agent_path, GFP_KERNEL); + if (!pathbuf || !agentbuf) + goto out; + + path = cgroup_path(cgrp, pathbuf, PATH_MAX); + if (!path) + goto out; + + argv[0] = agentbuf; + argv[1] = path; + argv[2] = NULL; + + /* minimal command environment */ + envp[0] = "HOME=/"; + envp[1] = "PATH=/sbin:/bin:/usr/sbin:/usr/bin"; + envp[2] = NULL; + + mutex_unlock(&cgroup_mutex); + call_usermodehelper(argv[0], argv, envp, UMH_WAIT_EXEC); + goto out_free; +out: + mutex_unlock(&cgroup_mutex); +out_free: + kfree(agentbuf); + kfree(pathbuf); +} + +static int __init cgroup_disable(char *str) +{ + struct cgroup_subsys *ss; + char *token; + int i; + + while ((token = strsep(&str, ",")) != NULL) { + if (!*token) + continue; + + for_each_subsys(ss, i) { + if (!strcmp(token, ss->name)) { + ss->disabled = 1; + printk(KERN_INFO "Disabling %s control group" + " subsystem\n", ss->name); + break; + } + } + } + return 1; +} +__setup("cgroup_disable=", cgroup_disable); + +static int __init cgroup_set_legacy_files_on_dfl(char *str) +{ + printk("cgroup: using legacy files on the default hierarchy\n"); + cgroup_legacy_files_on_dfl = true; + return 0; +} +__setup("cgroup__DEVEL__legacy_files_on_dfl", cgroup_set_legacy_files_on_dfl); + +/** + * css_tryget_online_from_dir - get corresponding css from a cgroup dentry + * @dentry: directory dentry of interest + * @ss: subsystem of interest + * + * If @dentry is a directory for a cgroup which has @ss enabled on it, try + * to get the corresponding css and return it. If such css doesn't exist + * or can't be pinned, an ERR_PTR value is returned. + */ +struct cgroup_subsys_state *css_tryget_online_from_dir(struct dentry *dentry, + struct cgroup_subsys *ss) +{ + struct kernfs_node *kn = kernfs_node_from_dentry(dentry); + struct cgroup_subsys_state *css = NULL; + struct cgroup *cgrp; + + /* is @dentry a cgroup dir? */ + if (dentry->d_sb->s_type != &cgroup_fs_type || !kn || + kernfs_type(kn) != KERNFS_DIR) + return ERR_PTR(-EBADF); + + rcu_read_lock(); + + /* + * This path doesn't originate from kernfs and @kn could already + * have been or be removed at any point. @kn->priv is RCU + * protected for this access. See css_release_work_fn() for details. + */ + cgrp = rcu_dereference(kn->priv); + if (cgrp) + css = cgroup_css(cgrp, ss); + + if (!css || !css_tryget_online(css)) + css = ERR_PTR(-ENOENT); + + rcu_read_unlock(); + return css; +} + +/** + * css_from_id - lookup css by id + * @id: the cgroup id + * @ss: cgroup subsys to be looked into + * + * Returns the css if there's valid one with @id, otherwise returns NULL. + * Should be called under rcu_read_lock(). + */ +struct cgroup_subsys_state *css_from_id(int id, struct cgroup_subsys *ss) +{ + WARN_ON_ONCE(!rcu_read_lock_held()); + return id > 0 ? idr_find(&ss->css_idr, id) : NULL; +} + +#ifdef CONFIG_CGROUP_DEBUG +static struct cgroup_subsys_state * +debug_css_alloc(struct cgroup_subsys_state *parent_css) +{ + struct cgroup_subsys_state *css = kzalloc(sizeof(*css), GFP_KERNEL); + + if (!css) + return ERR_PTR(-ENOMEM); + + return css; +} + +static void debug_css_free(struct cgroup_subsys_state *css) +{ + kfree(css); +} + +static u64 debug_taskcount_read(struct cgroup_subsys_state *css, + struct cftype *cft) +{ + return cgroup_task_count(css->cgroup); +} + +static u64 current_css_set_read(struct cgroup_subsys_state *css, + struct cftype *cft) +{ + return (u64)(unsigned long)current->cgroups; +} + +static u64 current_css_set_refcount_read(struct cgroup_subsys_state *css, + struct cftype *cft) +{ + u64 count; + + rcu_read_lock(); + count = atomic_read(&task_css_set(current)->refcount); + rcu_read_unlock(); + return count; +} + +static int current_css_set_cg_links_read(struct seq_file *seq, void *v) +{ + struct cgrp_cset_link *link; + struct css_set *cset; + char *name_buf; + + name_buf = kmalloc(NAME_MAX + 1, GFP_KERNEL); + if (!name_buf) + return -ENOMEM; + + down_read(&css_set_rwsem); + rcu_read_lock(); + cset = rcu_dereference(current->cgroups); + list_for_each_entry(link, &cset->cgrp_links, cgrp_link) { + struct cgroup *c = link->cgrp; + + cgroup_name(c, name_buf, NAME_MAX + 1); + seq_printf(seq, "Root %d group %s\n", + c->root->hierarchy_id, name_buf); + } + rcu_read_unlock(); + up_read(&css_set_rwsem); + kfree(name_buf); + return 0; +} + +#define MAX_TASKS_SHOWN_PER_CSS 25 +static int cgroup_css_links_read(struct seq_file *seq, void *v) +{ + struct cgroup_subsys_state *css = seq_css(seq); + struct cgrp_cset_link *link; + + down_read(&css_set_rwsem); + list_for_each_entry(link, &css->cgroup->cset_links, cset_link) { + struct css_set *cset = link->cset; + struct task_struct *task; + int count = 0; + + seq_printf(seq, "css_set %p\n", cset); + + list_for_each_entry(task, &cset->tasks, cg_list) { + if (count++ > MAX_TASKS_SHOWN_PER_CSS) + goto overflow; + seq_printf(seq, " task %d\n", task_pid_vnr(task)); + } + + list_for_each_entry(task, &cset->mg_tasks, cg_list) { + if (count++ > MAX_TASKS_SHOWN_PER_CSS) + goto overflow; + seq_printf(seq, " task %d\n", task_pid_vnr(task)); + } + continue; + overflow: + seq_puts(seq, " ...\n"); + } + up_read(&css_set_rwsem); + return 0; +} + +static u64 releasable_read(struct cgroup_subsys_state *css, struct cftype *cft) +{ + return (!cgroup_has_tasks(css->cgroup) && + !css_has_online_children(&css->cgroup->self)); +} + +static struct cftype debug_files[] = { + { + .name = "taskcount", + .read_u64 = debug_taskcount_read, + }, + + { + .name = "current_css_set", + .read_u64 = current_css_set_read, + }, + + { + .name = "current_css_set_refcount", + .read_u64 = current_css_set_refcount_read, + }, + + { + .name = "current_css_set_cg_links", + .seq_show = current_css_set_cg_links_read, + }, + + { + .name = "cgroup_css_links", + .seq_show = cgroup_css_links_read, + }, + + { + .name = "releasable", + .read_u64 = releasable_read, + }, + + { } /* terminate */ +}; + +struct cgroup_subsys debug_cgrp_subsys = { + .css_alloc = debug_css_alloc, + .css_free = debug_css_free, + .legacy_cftypes = debug_files, +}; +#endif /* CONFIG_CGROUP_DEBUG */ diff --git a/kernel/kernel/cgroup_freezer.c b/kernel/kernel/cgroup_freezer.c new file mode 100644 index 000000000..92b98cc0e --- /dev/null +++ b/kernel/kernel/cgroup_freezer.c @@ -0,0 +1,484 @@ +/* + * cgroup_freezer.c - control group freezer subsystem + * + * Copyright IBM Corporation, 2007 + * + * Author : Cedric Le Goater + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of version 2.1 of the GNU Lesser General Public License + * as published by the Free Software Foundation. + * + * This program is distributed in the hope that it would be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + */ + +#include +#include +#include +#include +#include +#include +#include +#include + +/* + * A cgroup is freezing if any FREEZING flags are set. FREEZING_SELF is + * set if "FROZEN" is written to freezer.state cgroupfs file, and cleared + * for "THAWED". FREEZING_PARENT is set if the parent freezer is FREEZING + * for whatever reason. IOW, a cgroup has FREEZING_PARENT set if one of + * its ancestors has FREEZING_SELF set. + */ +enum freezer_state_flags { + CGROUP_FREEZER_ONLINE = (1 << 0), /* freezer is fully online */ + CGROUP_FREEZING_SELF = (1 << 1), /* this freezer is freezing */ + CGROUP_FREEZING_PARENT = (1 << 2), /* the parent freezer is freezing */ + CGROUP_FROZEN = (1 << 3), /* this and its descendants frozen */ + + /* mask for all FREEZING flags */ + CGROUP_FREEZING = CGROUP_FREEZING_SELF | CGROUP_FREEZING_PARENT, +}; + +struct freezer { + struct cgroup_subsys_state css; + unsigned int state; +}; + +static DEFINE_MUTEX(freezer_mutex); + +static inline struct freezer *css_freezer(struct cgroup_subsys_state *css) +{ + return css ? container_of(css, struct freezer, css) : NULL; +} + +static inline struct freezer *task_freezer(struct task_struct *task) +{ + return css_freezer(task_css(task, freezer_cgrp_id)); +} + +static struct freezer *parent_freezer(struct freezer *freezer) +{ + return css_freezer(freezer->css.parent); +} + +bool cgroup_freezing(struct task_struct *task) +{ + bool ret; + + rcu_read_lock(); + ret = task_freezer(task)->state & CGROUP_FREEZING; + rcu_read_unlock(); + + return ret; +} + +static const char *freezer_state_strs(unsigned int state) +{ + if (state & CGROUP_FROZEN) + return "FROZEN"; + if (state & CGROUP_FREEZING) + return "FREEZING"; + return "THAWED"; +}; + +static struct cgroup_subsys_state * +freezer_css_alloc(struct cgroup_subsys_state *parent_css) +{ + struct freezer *freezer; + + freezer = kzalloc(sizeof(struct freezer), GFP_KERNEL); + if (!freezer) + return ERR_PTR(-ENOMEM); + + return &freezer->css; +} + +/** + * freezer_css_online - commit creation of a freezer css + * @css: css being created + * + * We're committing to creation of @css. Mark it online and inherit + * parent's freezing state while holding both parent's and our + * freezer->lock. + */ +static int freezer_css_online(struct cgroup_subsys_state *css) +{ + struct freezer *freezer = css_freezer(css); + struct freezer *parent = parent_freezer(freezer); + + mutex_lock(&freezer_mutex); + + freezer->state |= CGROUP_FREEZER_ONLINE; + + if (parent && (parent->state & CGROUP_FREEZING)) { + freezer->state |= CGROUP_FREEZING_PARENT | CGROUP_FROZEN; + atomic_inc(&system_freezing_cnt); + } + + mutex_unlock(&freezer_mutex); + return 0; +} + +/** + * freezer_css_offline - initiate destruction of a freezer css + * @css: css being destroyed + * + * @css is going away. Mark it dead and decrement system_freezing_count if + * it was holding one. + */ +static void freezer_css_offline(struct cgroup_subsys_state *css) +{ + struct freezer *freezer = css_freezer(css); + + mutex_lock(&freezer_mutex); + + if (freezer->state & CGROUP_FREEZING) + atomic_dec(&system_freezing_cnt); + + freezer->state = 0; + + mutex_unlock(&freezer_mutex); +} + +static void freezer_css_free(struct cgroup_subsys_state *css) +{ + kfree(css_freezer(css)); +} + +/* + * Tasks can be migrated into a different freezer anytime regardless of its + * current state. freezer_attach() is responsible for making new tasks + * conform to the current state. + * + * Freezer state changes and task migration are synchronized via + * @freezer->lock. freezer_attach() makes the new tasks conform to the + * current state and all following state changes can see the new tasks. + */ +static void freezer_attach(struct cgroup_subsys_state *new_css, + struct cgroup_taskset *tset) +{ + struct freezer *freezer = css_freezer(new_css); + struct task_struct *task; + bool clear_frozen = false; + + mutex_lock(&freezer_mutex); + + /* + * Make the new tasks conform to the current state of @new_css. + * For simplicity, when migrating any task to a FROZEN cgroup, we + * revert it to FREEZING and let update_if_frozen() determine the + * correct state later. + * + * Tasks in @tset are on @new_css but may not conform to its + * current state before executing the following - !frozen tasks may + * be visible in a FROZEN cgroup and frozen tasks in a THAWED one. + */ + cgroup_taskset_for_each(task, tset) { + if (!(freezer->state & CGROUP_FREEZING)) { + __thaw_task(task); + } else { + freeze_task(task); + freezer->state &= ~CGROUP_FROZEN; + clear_frozen = true; + } + } + + /* propagate FROZEN clearing upwards */ + while (clear_frozen && (freezer = parent_freezer(freezer))) { + freezer->state &= ~CGROUP_FROZEN; + clear_frozen = freezer->state & CGROUP_FREEZING; + } + + mutex_unlock(&freezer_mutex); +} + +/** + * freezer_fork - cgroup post fork callback + * @task: a task which has just been forked + * + * @task has just been created and should conform to the current state of + * the cgroup_freezer it belongs to. This function may race against + * freezer_attach(). Losing to freezer_attach() means that we don't have + * to do anything as freezer_attach() will put @task into the appropriate + * state. + */ +static void freezer_fork(struct task_struct *task) +{ + struct freezer *freezer; + + /* + * The root cgroup is non-freezable, so we can skip locking the + * freezer. This is safe regardless of race with task migration. + * If we didn't race or won, skipping is obviously the right thing + * to do. If we lost and root is the new cgroup, noop is still the + * right thing to do. + */ + if (task_css_is_root(task, freezer_cgrp_id)) + return; + + mutex_lock(&freezer_mutex); + rcu_read_lock(); + + freezer = task_freezer(task); + if (freezer->state & CGROUP_FREEZING) + freeze_task(task); + + rcu_read_unlock(); + mutex_unlock(&freezer_mutex); +} + +/** + * update_if_frozen - update whether a cgroup finished freezing + * @css: css of interest + * + * Once FREEZING is initiated, transition to FROZEN is lazily updated by + * calling this function. If the current state is FREEZING but not FROZEN, + * this function checks whether all tasks of this cgroup and the descendant + * cgroups finished freezing and, if so, sets FROZEN. + * + * The caller is responsible for grabbing RCU read lock and calling + * update_if_frozen() on all descendants prior to invoking this function. + * + * Task states and freezer state might disagree while tasks are being + * migrated into or out of @css, so we can't verify task states against + * @freezer state here. See freezer_attach() for details. + */ +static void update_if_frozen(struct cgroup_subsys_state *css) +{ + struct freezer *freezer = css_freezer(css); + struct cgroup_subsys_state *pos; + struct css_task_iter it; + struct task_struct *task; + + lockdep_assert_held(&freezer_mutex); + + if (!(freezer->state & CGROUP_FREEZING) || + (freezer->state & CGROUP_FROZEN)) + return; + + /* are all (live) children frozen? */ + rcu_read_lock(); + css_for_each_child(pos, css) { + struct freezer *child = css_freezer(pos); + + if ((child->state & CGROUP_FREEZER_ONLINE) && + !(child->state & CGROUP_FROZEN)) { + rcu_read_unlock(); + return; + } + } + rcu_read_unlock(); + + /* are all tasks frozen? */ + css_task_iter_start(css, &it); + + while ((task = css_task_iter_next(&it))) { + if (freezing(task)) { + /* + * freezer_should_skip() indicates that the task + * should be skipped when determining freezing + * completion. Consider it frozen in addition to + * the usual frozen condition. + */ + if (!frozen(task) && !freezer_should_skip(task)) + goto out_iter_end; + } + } + + freezer->state |= CGROUP_FROZEN; +out_iter_end: + css_task_iter_end(&it); +} + +static int freezer_read(struct seq_file *m, void *v) +{ + struct cgroup_subsys_state *css = seq_css(m), *pos; + + mutex_lock(&freezer_mutex); + rcu_read_lock(); + + /* update states bottom-up */ + css_for_each_descendant_post(pos, css) { + if (!css_tryget_online(pos)) + continue; + rcu_read_unlock(); + + update_if_frozen(pos); + + rcu_read_lock(); + css_put(pos); + } + + rcu_read_unlock(); + mutex_unlock(&freezer_mutex); + + seq_puts(m, freezer_state_strs(css_freezer(css)->state)); + seq_putc(m, '\n'); + return 0; +} + +static void freeze_cgroup(struct freezer *freezer) +{ + struct css_task_iter it; + struct task_struct *task; + + css_task_iter_start(&freezer->css, &it); + while ((task = css_task_iter_next(&it))) + freeze_task(task); + css_task_iter_end(&it); +} + +static void unfreeze_cgroup(struct freezer *freezer) +{ + struct css_task_iter it; + struct task_struct *task; + + css_task_iter_start(&freezer->css, &it); + while ((task = css_task_iter_next(&it))) + __thaw_task(task); + css_task_iter_end(&it); +} + +/** + * freezer_apply_state - apply state change to a single cgroup_freezer + * @freezer: freezer to apply state change to + * @freeze: whether to freeze or unfreeze + * @state: CGROUP_FREEZING_* flag to set or clear + * + * Set or clear @state on @cgroup according to @freeze, and perform + * freezing or thawing as necessary. + */ +static void freezer_apply_state(struct freezer *freezer, bool freeze, + unsigned int state) +{ + /* also synchronizes against task migration, see freezer_attach() */ + lockdep_assert_held(&freezer_mutex); + + if (!(freezer->state & CGROUP_FREEZER_ONLINE)) + return; + + if (freeze) { + if (!(freezer->state & CGROUP_FREEZING)) + atomic_inc(&system_freezing_cnt); + freezer->state |= state; + freeze_cgroup(freezer); + } else { + bool was_freezing = freezer->state & CGROUP_FREEZING; + + freezer->state &= ~state; + + if (!(freezer->state & CGROUP_FREEZING)) { + if (was_freezing) + atomic_dec(&system_freezing_cnt); + freezer->state &= ~CGROUP_FROZEN; + unfreeze_cgroup(freezer); + } + } +} + +/** + * freezer_change_state - change the freezing state of a cgroup_freezer + * @freezer: freezer of interest + * @freeze: whether to freeze or thaw + * + * Freeze or thaw @freezer according to @freeze. The operations are + * recursive - all descendants of @freezer will be affected. + */ +static void freezer_change_state(struct freezer *freezer, bool freeze) +{ + struct cgroup_subsys_state *pos; + + /* + * Update all its descendants in pre-order traversal. Each + * descendant will try to inherit its parent's FREEZING state as + * CGROUP_FREEZING_PARENT. + */ + mutex_lock(&freezer_mutex); + rcu_read_lock(); + css_for_each_descendant_pre(pos, &freezer->css) { + struct freezer *pos_f = css_freezer(pos); + struct freezer *parent = parent_freezer(pos_f); + + if (!css_tryget_online(pos)) + continue; + rcu_read_unlock(); + + if (pos_f == freezer) + freezer_apply_state(pos_f, freeze, + CGROUP_FREEZING_SELF); + else + freezer_apply_state(pos_f, + parent->state & CGROUP_FREEZING, + CGROUP_FREEZING_PARENT); + + rcu_read_lock(); + css_put(pos); + } + rcu_read_unlock(); + mutex_unlock(&freezer_mutex); +} + +static ssize_t freezer_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) +{ + bool freeze; + + buf = strstrip(buf); + + if (strcmp(buf, freezer_state_strs(0)) == 0) + freeze = false; + else if (strcmp(buf, freezer_state_strs(CGROUP_FROZEN)) == 0) + freeze = true; + else + return -EINVAL; + + freezer_change_state(css_freezer(of_css(of)), freeze); + return nbytes; +} + +static u64 freezer_self_freezing_read(struct cgroup_subsys_state *css, + struct cftype *cft) +{ + struct freezer *freezer = css_freezer(css); + + return (bool)(freezer->state & CGROUP_FREEZING_SELF); +} + +static u64 freezer_parent_freezing_read(struct cgroup_subsys_state *css, + struct cftype *cft) +{ + struct freezer *freezer = css_freezer(css); + + return (bool)(freezer->state & CGROUP_FREEZING_PARENT); +} + +static struct cftype files[] = { + { + .name = "state", + .flags = CFTYPE_NOT_ON_ROOT, + .seq_show = freezer_read, + .write = freezer_write, + }, + { + .name = "self_freezing", + .flags = CFTYPE_NOT_ON_ROOT, + .read_u64 = freezer_self_freezing_read, + }, + { + .name = "parent_freezing", + .flags = CFTYPE_NOT_ON_ROOT, + .read_u64 = freezer_parent_freezing_read, + }, + { } /* terminate */ +}; + +struct cgroup_subsys freezer_cgrp_subsys = { + .css_alloc = freezer_css_alloc, + .css_online = freezer_css_online, + .css_offline = freezer_css_offline, + .css_free = freezer_css_free, + .attach = freezer_attach, + .fork = freezer_fork, + .legacy_cftypes = files, +}; diff --git a/kernel/kernel/compat.c b/kernel/kernel/compat.c new file mode 100644 index 000000000..333d364be --- /dev/null +++ b/kernel/kernel/compat.c @@ -0,0 +1,1176 @@ +/* + * linux/kernel/compat.c + * + * Kernel compatibililty routines for e.g. 32 bit syscall support + * on 64 bit kernels. + * + * Copyright (C) 2002-2003 Stephen Rothwell, IBM Corporation + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include +#include +#include +#include +#include +#include /* for MAX_SCHEDULE_TIMEOUT */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +static int compat_get_timex(struct timex *txc, struct compat_timex __user *utp) +{ + memset(txc, 0, sizeof(struct timex)); + + if (!access_ok(VERIFY_READ, utp, sizeof(struct compat_timex)) || + __get_user(txc->modes, &utp->modes) || + __get_user(txc->offset, &utp->offset) || + __get_user(txc->freq, &utp->freq) || + __get_user(txc->maxerror, &utp->maxerror) || + __get_user(txc->esterror, &utp->esterror) || + __get_user(txc->status, &utp->status) || + __get_user(txc->constant, &utp->constant) || + __get_user(txc->precision, &utp->precision) || + __get_user(txc->tolerance, &utp->tolerance) || + __get_user(txc->time.tv_sec, &utp->time.tv_sec) || + __get_user(txc->time.tv_usec, &utp->time.tv_usec) || + __get_user(txc->tick, &utp->tick) || + __get_user(txc->ppsfreq, &utp->ppsfreq) || + __get_user(txc->jitter, &utp->jitter) || + __get_user(txc->shift, &utp->shift) || + __get_user(txc->stabil, &utp->stabil) || + __get_user(txc->jitcnt, &utp->jitcnt) || + __get_user(txc->calcnt, &utp->calcnt) || + __get_user(txc->errcnt, &utp->errcnt) || + __get_user(txc->stbcnt, &utp->stbcnt)) + return -EFAULT; + + return 0; +} + +static int compat_put_timex(struct compat_timex __user *utp, struct timex *txc) +{ + if (!access_ok(VERIFY_WRITE, utp, sizeof(struct compat_timex)) || + __put_user(txc->modes, &utp->modes) || + __put_user(txc->offset, &utp->offset) || + __put_user(txc->freq, &utp->freq) || + __put_user(txc->maxerror, &utp->maxerror) || + __put_user(txc->esterror, &utp->esterror) || + __put_user(txc->status, &utp->status) || + __put_user(txc->constant, &utp->constant) || + __put_user(txc->precision, &utp->precision) || + __put_user(txc->tolerance, &utp->tolerance) || + __put_user(txc->time.tv_sec, &utp->time.tv_sec) || + __put_user(txc->time.tv_usec, &utp->time.tv_usec) || + __put_user(txc->tick, &utp->tick) || + __put_user(txc->ppsfreq, &utp->ppsfreq) || + __put_user(txc->jitter, &utp->jitter) || + __put_user(txc->shift, &utp->shift) || + __put_user(txc->stabil, &utp->stabil) || + __put_user(txc->jitcnt, &utp->jitcnt) || + __put_user(txc->calcnt, &utp->calcnt) || + __put_user(txc->errcnt, &utp->errcnt) || + __put_user(txc->stbcnt, &utp->stbcnt) || + __put_user(txc->tai, &utp->tai)) + return -EFAULT; + return 0; +} + +COMPAT_SYSCALL_DEFINE2(gettimeofday, struct compat_timeval __user *, tv, + struct timezone __user *, tz) +{ + if (tv) { + struct timeval ktv; + do_gettimeofday(&ktv); + if (compat_put_timeval(&ktv, tv)) + return -EFAULT; + } + if (tz) { + if (copy_to_user(tz, &sys_tz, sizeof(sys_tz))) + return -EFAULT; + } + + return 0; +} + +COMPAT_SYSCALL_DEFINE2(settimeofday, struct compat_timeval __user *, tv, + struct timezone __user *, tz) +{ + struct timeval user_tv; + struct timespec new_ts; + struct timezone new_tz; + + if (tv) { + if (compat_get_timeval(&user_tv, tv)) + return -EFAULT; + new_ts.tv_sec = user_tv.tv_sec; + new_ts.tv_nsec = user_tv.tv_usec * NSEC_PER_USEC; + } + if (tz) { + if (copy_from_user(&new_tz, tz, sizeof(*tz))) + return -EFAULT; + } + + return do_sys_settimeofday(tv ? &new_ts : NULL, tz ? &new_tz : NULL); +} + +static int __compat_get_timeval(struct timeval *tv, const struct compat_timeval __user *ctv) +{ + return (!access_ok(VERIFY_READ, ctv, sizeof(*ctv)) || + __get_user(tv->tv_sec, &ctv->tv_sec) || + __get_user(tv->tv_usec, &ctv->tv_usec)) ? -EFAULT : 0; +} + +static int __compat_put_timeval(const struct timeval *tv, struct compat_timeval __user *ctv) +{ + return (!access_ok(VERIFY_WRITE, ctv, sizeof(*ctv)) || + __put_user(tv->tv_sec, &ctv->tv_sec) || + __put_user(tv->tv_usec, &ctv->tv_usec)) ? -EFAULT : 0; +} + +static int __compat_get_timespec(struct timespec *ts, const struct compat_timespec __user *cts) +{ + return (!access_ok(VERIFY_READ, cts, sizeof(*cts)) || + __get_user(ts->tv_sec, &cts->tv_sec) || + __get_user(ts->tv_nsec, &cts->tv_nsec)) ? -EFAULT : 0; +} + +static int __compat_put_timespec(const struct timespec *ts, struct compat_timespec __user *cts) +{ + return (!access_ok(VERIFY_WRITE, cts, sizeof(*cts)) || + __put_user(ts->tv_sec, &cts->tv_sec) || + __put_user(ts->tv_nsec, &cts->tv_nsec)) ? -EFAULT : 0; +} + +int compat_get_timeval(struct timeval *tv, const void __user *utv) +{ + if (COMPAT_USE_64BIT_TIME) + return copy_from_user(tv, utv, sizeof(*tv)) ? -EFAULT : 0; + else + return __compat_get_timeval(tv, utv); +} +EXPORT_SYMBOL_GPL(compat_get_timeval); + +int compat_put_timeval(const struct timeval *tv, void __user *utv) +{ + if (COMPAT_USE_64BIT_TIME) + return copy_to_user(utv, tv, sizeof(*tv)) ? -EFAULT : 0; + else + return __compat_put_timeval(tv, utv); +} +EXPORT_SYMBOL_GPL(compat_put_timeval); + +int compat_get_timespec(struct timespec *ts, const void __user *uts) +{ + if (COMPAT_USE_64BIT_TIME) + return copy_from_user(ts, uts, sizeof(*ts)) ? -EFAULT : 0; + else + return __compat_get_timespec(ts, uts); +} +EXPORT_SYMBOL_GPL(compat_get_timespec); + +int compat_put_timespec(const struct timespec *ts, void __user *uts) +{ + if (COMPAT_USE_64BIT_TIME) + return copy_to_user(uts, ts, sizeof(*ts)) ? -EFAULT : 0; + else + return __compat_put_timespec(ts, uts); +} +EXPORT_SYMBOL_GPL(compat_put_timespec); + +int compat_convert_timespec(struct timespec __user **kts, + const void __user *cts) +{ + struct timespec ts; + struct timespec __user *uts; + + if (!cts || COMPAT_USE_64BIT_TIME) { + *kts = (struct timespec __user *)cts; + return 0; + } + + uts = compat_alloc_user_space(sizeof(ts)); + if (!uts) + return -EFAULT; + if (compat_get_timespec(&ts, cts)) + return -EFAULT; + if (copy_to_user(uts, &ts, sizeof(ts))) + return -EFAULT; + + *kts = uts; + return 0; +} + +static long compat_nanosleep_restart(struct restart_block *restart) +{ + struct compat_timespec __user *rmtp; + struct timespec rmt; + mm_segment_t oldfs; + long ret; + + restart->nanosleep.rmtp = (struct timespec __user *) &rmt; + oldfs = get_fs(); + set_fs(KERNEL_DS); + ret = hrtimer_nanosleep_restart(restart); + set_fs(oldfs); + + if (ret == -ERESTART_RESTARTBLOCK) { + rmtp = restart->nanosleep.compat_rmtp; + + if (rmtp && compat_put_timespec(&rmt, rmtp)) + return -EFAULT; + } + + return ret; +} + +COMPAT_SYSCALL_DEFINE2(nanosleep, struct compat_timespec __user *, rqtp, + struct compat_timespec __user *, rmtp) +{ + struct timespec tu, rmt; + mm_segment_t oldfs; + long ret; + + if (compat_get_timespec(&tu, rqtp)) + return -EFAULT; + + if (!timespec_valid(&tu)) + return -EINVAL; + + oldfs = get_fs(); + set_fs(KERNEL_DS); + ret = hrtimer_nanosleep(&tu, + rmtp ? (struct timespec __user *)&rmt : NULL, + HRTIMER_MODE_REL, CLOCK_MONOTONIC); + set_fs(oldfs); + + /* + * hrtimer_nanosleep() can only return 0 or + * -ERESTART_RESTARTBLOCK here because: + * + * - we call it with HRTIMER_MODE_REL and therefor exclude the + * -ERESTARTNOHAND return path. + * + * - we supply the rmtp argument from the task stack (due to + * the necessary compat conversion. So the update cannot + * fail, which excludes the -EFAULT return path as well. If + * it fails nevertheless we have a bigger problem and wont + * reach this place anymore. + * + * - if the return value is 0, we do not have to update rmtp + * because there is no remaining time. + * + * We check for -ERESTART_RESTARTBLOCK nevertheless if the + * core implementation decides to return random nonsense. + */ + if (ret == -ERESTART_RESTARTBLOCK) { + struct restart_block *restart = ¤t->restart_block; + + restart->fn = compat_nanosleep_restart; + restart->nanosleep.compat_rmtp = rmtp; + + if (rmtp && compat_put_timespec(&rmt, rmtp)) + return -EFAULT; + } + return ret; +} + +static inline long get_compat_itimerval(struct itimerval *o, + struct compat_itimerval __user *i) +{ + return (!access_ok(VERIFY_READ, i, sizeof(*i)) || + (__get_user(o->it_interval.tv_sec, &i->it_interval.tv_sec) | + __get_user(o->it_interval.tv_usec, &i->it_interval.tv_usec) | + __get_user(o->it_value.tv_sec, &i->it_value.tv_sec) | + __get_user(o->it_value.tv_usec, &i->it_value.tv_usec))); +} + +static inline long put_compat_itimerval(struct compat_itimerval __user *o, + struct itimerval *i) +{ + return (!access_ok(VERIFY_WRITE, o, sizeof(*o)) || + (__put_user(i->it_interval.tv_sec, &o->it_interval.tv_sec) | + __put_user(i->it_interval.tv_usec, &o->it_interval.tv_usec) | + __put_user(i->it_value.tv_sec, &o->it_value.tv_sec) | + __put_user(i->it_value.tv_usec, &o->it_value.tv_usec))); +} + +COMPAT_SYSCALL_DEFINE2(getitimer, int, which, + struct compat_itimerval __user *, it) +{ + struct itimerval kit; + int error; + + error = do_getitimer(which, &kit); + if (!error && put_compat_itimerval(it, &kit)) + error = -EFAULT; + return error; +} + +COMPAT_SYSCALL_DEFINE3(setitimer, int, which, + struct compat_itimerval __user *, in, + struct compat_itimerval __user *, out) +{ + struct itimerval kin, kout; + int error; + + if (in) { + if (get_compat_itimerval(&kin, in)) + return -EFAULT; + } else + memset(&kin, 0, sizeof(kin)); + + error = do_setitimer(which, &kin, out ? &kout : NULL); + if (error || !out) + return error; + if (put_compat_itimerval(out, &kout)) + return -EFAULT; + return 0; +} + +static compat_clock_t clock_t_to_compat_clock_t(clock_t x) +{ + return compat_jiffies_to_clock_t(clock_t_to_jiffies(x)); +} + +COMPAT_SYSCALL_DEFINE1(times, struct compat_tms __user *, tbuf) +{ + if (tbuf) { + struct tms tms; + struct compat_tms tmp; + + do_sys_times(&tms); + /* Convert our struct tms to the compat version. */ + tmp.tms_utime = clock_t_to_compat_clock_t(tms.tms_utime); + tmp.tms_stime = clock_t_to_compat_clock_t(tms.tms_stime); + tmp.tms_cutime = clock_t_to_compat_clock_t(tms.tms_cutime); + tmp.tms_cstime = clock_t_to_compat_clock_t(tms.tms_cstime); + if (copy_to_user(tbuf, &tmp, sizeof(tmp))) + return -EFAULT; + } + force_successful_syscall_return(); + return compat_jiffies_to_clock_t(jiffies); +} + +#ifdef __ARCH_WANT_SYS_SIGPENDING + +/* + * Assumption: old_sigset_t and compat_old_sigset_t are both + * types that can be passed to put_user()/get_user(). + */ + +COMPAT_SYSCALL_DEFINE1(sigpending, compat_old_sigset_t __user *, set) +{ + old_sigset_t s; + long ret; + mm_segment_t old_fs = get_fs(); + + set_fs(KERNEL_DS); + ret = sys_sigpending((old_sigset_t __user *) &s); + set_fs(old_fs); + if (ret == 0) + ret = put_user(s, set); + return ret; +} + +#endif + +#ifdef __ARCH_WANT_SYS_SIGPROCMASK + +/* + * sys_sigprocmask SIG_SETMASK sets the first (compat) word of the + * blocked set of signals to the supplied signal set + */ +static inline void compat_sig_setmask(sigset_t *blocked, compat_sigset_word set) +{ + memcpy(blocked->sig, &set, sizeof(set)); +} + +COMPAT_SYSCALL_DEFINE3(sigprocmask, int, how, + compat_old_sigset_t __user *, nset, + compat_old_sigset_t __user *, oset) +{ + old_sigset_t old_set, new_set; + sigset_t new_blocked; + + old_set = current->blocked.sig[0]; + + if (nset) { + if (get_user(new_set, nset)) + return -EFAULT; + new_set &= ~(sigmask(SIGKILL) | sigmask(SIGSTOP)); + + new_blocked = current->blocked; + + switch (how) { + case SIG_BLOCK: + sigaddsetmask(&new_blocked, new_set); + break; + case SIG_UNBLOCK: + sigdelsetmask(&new_blocked, new_set); + break; + case SIG_SETMASK: + compat_sig_setmask(&new_blocked, new_set); + break; + default: + return -EINVAL; + } + + set_current_blocked(&new_blocked); + } + + if (oset) { + if (put_user(old_set, oset)) + return -EFAULT; + } + + return 0; +} + +#endif + +COMPAT_SYSCALL_DEFINE2(setrlimit, unsigned int, resource, + struct compat_rlimit __user *, rlim) +{ + struct rlimit r; + + if (!access_ok(VERIFY_READ, rlim, sizeof(*rlim)) || + __get_user(r.rlim_cur, &rlim->rlim_cur) || + __get_user(r.rlim_max, &rlim->rlim_max)) + return -EFAULT; + + if (r.rlim_cur == COMPAT_RLIM_INFINITY) + r.rlim_cur = RLIM_INFINITY; + if (r.rlim_max == COMPAT_RLIM_INFINITY) + r.rlim_max = RLIM_INFINITY; + return do_prlimit(current, resource, &r, NULL); +} + +#ifdef COMPAT_RLIM_OLD_INFINITY + +COMPAT_SYSCALL_DEFINE2(old_getrlimit, unsigned int, resource, + struct compat_rlimit __user *, rlim) +{ + struct rlimit r; + int ret; + mm_segment_t old_fs = get_fs(); + + set_fs(KERNEL_DS); + ret = sys_old_getrlimit(resource, (struct rlimit __user *)&r); + set_fs(old_fs); + + if (!ret) { + if (r.rlim_cur > COMPAT_RLIM_OLD_INFINITY) + r.rlim_cur = COMPAT_RLIM_INFINITY; + if (r.rlim_max > COMPAT_RLIM_OLD_INFINITY) + r.rlim_max = COMPAT_RLIM_INFINITY; + + if (!access_ok(VERIFY_WRITE, rlim, sizeof(*rlim)) || + __put_user(r.rlim_cur, &rlim->rlim_cur) || + __put_user(r.rlim_max, &rlim->rlim_max)) + return -EFAULT; + } + return ret; +} + +#endif + +COMPAT_SYSCALL_DEFINE2(getrlimit, unsigned int, resource, + struct compat_rlimit __user *, rlim) +{ + struct rlimit r; + int ret; + + ret = do_prlimit(current, resource, NULL, &r); + if (!ret) { + if (r.rlim_cur > COMPAT_RLIM_INFINITY) + r.rlim_cur = COMPAT_RLIM_INFINITY; + if (r.rlim_max > COMPAT_RLIM_INFINITY) + r.rlim_max = COMPAT_RLIM_INFINITY; + + if (!access_ok(VERIFY_WRITE, rlim, sizeof(*rlim)) || + __put_user(r.rlim_cur, &rlim->rlim_cur) || + __put_user(r.rlim_max, &rlim->rlim_max)) + return -EFAULT; + } + return ret; +} + +int put_compat_rusage(const struct rusage *r, struct compat_rusage __user *ru) +{ + if (!access_ok(VERIFY_WRITE, ru, sizeof(*ru)) || + __put_user(r->ru_utime.tv_sec, &ru->ru_utime.tv_sec) || + __put_user(r->ru_utime.tv_usec, &ru->ru_utime.tv_usec) || + __put_user(r->ru_stime.tv_sec, &ru->ru_stime.tv_sec) || + __put_user(r->ru_stime.tv_usec, &ru->ru_stime.tv_usec) || + __put_user(r->ru_maxrss, &ru->ru_maxrss) || + __put_user(r->ru_ixrss, &ru->ru_ixrss) || + __put_user(r->ru_idrss, &ru->ru_idrss) || + __put_user(r->ru_isrss, &ru->ru_isrss) || + __put_user(r->ru_minflt, &ru->ru_minflt) || + __put_user(r->ru_majflt, &ru->ru_majflt) || + __put_user(r->ru_nswap, &ru->ru_nswap) || + __put_user(r->ru_inblock, &ru->ru_inblock) || + __put_user(r->ru_oublock, &ru->ru_oublock) || + __put_user(r->ru_msgsnd, &ru->ru_msgsnd) || + __put_user(r->ru_msgrcv, &ru->ru_msgrcv) || + __put_user(r->ru_nsignals, &ru->ru_nsignals) || + __put_user(r->ru_nvcsw, &ru->ru_nvcsw) || + __put_user(r->ru_nivcsw, &ru->ru_nivcsw)) + return -EFAULT; + return 0; +} + +COMPAT_SYSCALL_DEFINE4(wait4, + compat_pid_t, pid, + compat_uint_t __user *, stat_addr, + int, options, + struct compat_rusage __user *, ru) +{ + if (!ru) { + return sys_wait4(pid, stat_addr, options, NULL); + } else { + struct rusage r; + int ret; + unsigned int status; + mm_segment_t old_fs = get_fs(); + + set_fs (KERNEL_DS); + ret = sys_wait4(pid, + (stat_addr ? + (unsigned int __user *) &status : NULL), + options, (struct rusage __user *) &r); + set_fs (old_fs); + + if (ret > 0) { + if (put_compat_rusage(&r, ru)) + return -EFAULT; + if (stat_addr && put_user(status, stat_addr)) + return -EFAULT; + } + return ret; + } +} + +COMPAT_SYSCALL_DEFINE5(waitid, + int, which, compat_pid_t, pid, + struct compat_siginfo __user *, uinfo, int, options, + struct compat_rusage __user *, uru) +{ + siginfo_t info; + struct rusage ru; + long ret; + mm_segment_t old_fs = get_fs(); + + memset(&info, 0, sizeof(info)); + + set_fs(KERNEL_DS); + ret = sys_waitid(which, pid, (siginfo_t __user *)&info, options, + uru ? (struct rusage __user *)&ru : NULL); + set_fs(old_fs); + + if ((ret < 0) || (info.si_signo == 0)) + return ret; + + if (uru) { + /* sys_waitid() overwrites everything in ru */ + if (COMPAT_USE_64BIT_TIME) + ret = copy_to_user(uru, &ru, sizeof(ru)); + else + ret = put_compat_rusage(&ru, uru); + if (ret) + return -EFAULT; + } + + BUG_ON(info.si_code & __SI_MASK); + info.si_code |= __SI_CHLD; + return copy_siginfo_to_user32(uinfo, &info); +} + +static int compat_get_user_cpu_mask(compat_ulong_t __user *user_mask_ptr, + unsigned len, struct cpumask *new_mask) +{ + unsigned long *k; + + if (len < cpumask_size()) + memset(new_mask, 0, cpumask_size()); + else if (len > cpumask_size()) + len = cpumask_size(); + + k = cpumask_bits(new_mask); + return compat_get_bitmap(k, user_mask_ptr, len * 8); +} + +COMPAT_SYSCALL_DEFINE3(sched_setaffinity, compat_pid_t, pid, + unsigned int, len, + compat_ulong_t __user *, user_mask_ptr) +{ + cpumask_var_t new_mask; + int retval; + + if (!alloc_cpumask_var(&new_mask, GFP_KERNEL)) + return -ENOMEM; + + retval = compat_get_user_cpu_mask(user_mask_ptr, len, new_mask); + if (retval) + goto out; + + retval = sched_setaffinity(pid, new_mask); +out: + free_cpumask_var(new_mask); + return retval; +} + +COMPAT_SYSCALL_DEFINE3(sched_getaffinity, compat_pid_t, pid, unsigned int, len, + compat_ulong_t __user *, user_mask_ptr) +{ + int ret; + cpumask_var_t mask; + + if ((len * BITS_PER_BYTE) < nr_cpu_ids) + return -EINVAL; + if (len & (sizeof(compat_ulong_t)-1)) + return -EINVAL; + + if (!alloc_cpumask_var(&mask, GFP_KERNEL)) + return -ENOMEM; + + ret = sched_getaffinity(pid, mask); + if (ret == 0) { + size_t retlen = min_t(size_t, len, cpumask_size()); + + if (compat_put_bitmap(user_mask_ptr, cpumask_bits(mask), retlen * 8)) + ret = -EFAULT; + else + ret = retlen; + } + free_cpumask_var(mask); + + return ret; +} + +int get_compat_itimerspec(struct itimerspec *dst, + const struct compat_itimerspec __user *src) +{ + if (__compat_get_timespec(&dst->it_interval, &src->it_interval) || + __compat_get_timespec(&dst->it_value, &src->it_value)) + return -EFAULT; + return 0; +} + +int put_compat_itimerspec(struct compat_itimerspec __user *dst, + const struct itimerspec *src) +{ + if (__compat_put_timespec(&src->it_interval, &dst->it_interval) || + __compat_put_timespec(&src->it_value, &dst->it_value)) + return -EFAULT; + return 0; +} + +COMPAT_SYSCALL_DEFINE3(timer_create, clockid_t, which_clock, + struct compat_sigevent __user *, timer_event_spec, + timer_t __user *, created_timer_id) +{ + struct sigevent __user *event = NULL; + + if (timer_event_spec) { + struct sigevent kevent; + + event = compat_alloc_user_space(sizeof(*event)); + if (get_compat_sigevent(&kevent, timer_event_spec) || + copy_to_user(event, &kevent, sizeof(*event))) + return -EFAULT; + } + + return sys_timer_create(which_clock, event, created_timer_id); +} + +COMPAT_SYSCALL_DEFINE4(timer_settime, timer_t, timer_id, int, flags, + struct compat_itimerspec __user *, new, + struct compat_itimerspec __user *, old) +{ + long err; + mm_segment_t oldfs; + struct itimerspec newts, oldts; + + if (!new) + return -EINVAL; + if (get_compat_itimerspec(&newts, new)) + return -EFAULT; + oldfs = get_fs(); + set_fs(KERNEL_DS); + err = sys_timer_settime(timer_id, flags, + (struct itimerspec __user *) &newts, + (struct itimerspec __user *) &oldts); + set_fs(oldfs); + if (!err && old && put_compat_itimerspec(old, &oldts)) + return -EFAULT; + return err; +} + +COMPAT_SYSCALL_DEFINE2(timer_gettime, timer_t, timer_id, + struct compat_itimerspec __user *, setting) +{ + long err; + mm_segment_t oldfs; + struct itimerspec ts; + + oldfs = get_fs(); + set_fs(KERNEL_DS); + err = sys_timer_gettime(timer_id, + (struct itimerspec __user *) &ts); + set_fs(oldfs); + if (!err && put_compat_itimerspec(setting, &ts)) + return -EFAULT; + return err; +} + +COMPAT_SYSCALL_DEFINE2(clock_settime, clockid_t, which_clock, + struct compat_timespec __user *, tp) +{ + long err; + mm_segment_t oldfs; + struct timespec ts; + + if (compat_get_timespec(&ts, tp)) + return -EFAULT; + oldfs = get_fs(); + set_fs(KERNEL_DS); + err = sys_clock_settime(which_clock, + (struct timespec __user *) &ts); + set_fs(oldfs); + return err; +} + +COMPAT_SYSCALL_DEFINE2(clock_gettime, clockid_t, which_clock, + struct compat_timespec __user *, tp) +{ + long err; + mm_segment_t oldfs; + struct timespec ts; + + oldfs = get_fs(); + set_fs(KERNEL_DS); + err = sys_clock_gettime(which_clock, + (struct timespec __user *) &ts); + set_fs(oldfs); + if (!err && compat_put_timespec(&ts, tp)) + return -EFAULT; + return err; +} + +COMPAT_SYSCALL_DEFINE2(clock_adjtime, clockid_t, which_clock, + struct compat_timex __user *, utp) +{ + struct timex txc; + mm_segment_t oldfs; + int err, ret; + + err = compat_get_timex(&txc, utp); + if (err) + return err; + + oldfs = get_fs(); + set_fs(KERNEL_DS); + ret = sys_clock_adjtime(which_clock, (struct timex __user *) &txc); + set_fs(oldfs); + + err = compat_put_timex(utp, &txc); + if (err) + return err; + + return ret; +} + +COMPAT_SYSCALL_DEFINE2(clock_getres, clockid_t, which_clock, + struct compat_timespec __user *, tp) +{ + long err; + mm_segment_t oldfs; + struct timespec ts; + + oldfs = get_fs(); + set_fs(KERNEL_DS); + err = sys_clock_getres(which_clock, + (struct timespec __user *) &ts); + set_fs(oldfs); + if (!err && tp && compat_put_timespec(&ts, tp)) + return -EFAULT; + return err; +} + +static long compat_clock_nanosleep_restart(struct restart_block *restart) +{ + long err; + mm_segment_t oldfs; + struct timespec tu; + struct compat_timespec __user *rmtp = restart->nanosleep.compat_rmtp; + + restart->nanosleep.rmtp = (struct timespec __user *) &tu; + oldfs = get_fs(); + set_fs(KERNEL_DS); + err = clock_nanosleep_restart(restart); + set_fs(oldfs); + + if ((err == -ERESTART_RESTARTBLOCK) && rmtp && + compat_put_timespec(&tu, rmtp)) + return -EFAULT; + + if (err == -ERESTART_RESTARTBLOCK) { + restart->fn = compat_clock_nanosleep_restart; + restart->nanosleep.compat_rmtp = rmtp; + } + return err; +} + +COMPAT_SYSCALL_DEFINE4(clock_nanosleep, clockid_t, which_clock, int, flags, + struct compat_timespec __user *, rqtp, + struct compat_timespec __user *, rmtp) +{ + long err; + mm_segment_t oldfs; + struct timespec in, out; + struct restart_block *restart; + + if (compat_get_timespec(&in, rqtp)) + return -EFAULT; + + oldfs = get_fs(); + set_fs(KERNEL_DS); + err = sys_clock_nanosleep(which_clock, flags, + (struct timespec __user *) &in, + (struct timespec __user *) &out); + set_fs(oldfs); + + if ((err == -ERESTART_RESTARTBLOCK) && rmtp && + compat_put_timespec(&out, rmtp)) + return -EFAULT; + + if (err == -ERESTART_RESTARTBLOCK) { + restart = ¤t->restart_block; + restart->fn = compat_clock_nanosleep_restart; + restart->nanosleep.compat_rmtp = rmtp; + } + return err; +} + +/* + * We currently only need the following fields from the sigevent + * structure: sigev_value, sigev_signo, sig_notify and (sometimes + * sigev_notify_thread_id). The others are handled in user mode. + * We also assume that copying sigev_value.sival_int is sufficient + * to keep all the bits of sigev_value.sival_ptr intact. + */ +int get_compat_sigevent(struct sigevent *event, + const struct compat_sigevent __user *u_event) +{ + memset(event, 0, sizeof(*event)); + return (!access_ok(VERIFY_READ, u_event, sizeof(*u_event)) || + __get_user(event->sigev_value.sival_int, + &u_event->sigev_value.sival_int) || + __get_user(event->sigev_signo, &u_event->sigev_signo) || + __get_user(event->sigev_notify, &u_event->sigev_notify) || + __get_user(event->sigev_notify_thread_id, + &u_event->sigev_notify_thread_id)) + ? -EFAULT : 0; +} + +long compat_get_bitmap(unsigned long *mask, const compat_ulong_t __user *umask, + unsigned long bitmap_size) +{ + int i, j; + unsigned long m; + compat_ulong_t um; + unsigned long nr_compat_longs; + + /* align bitmap up to nearest compat_long_t boundary */ + bitmap_size = ALIGN(bitmap_size, BITS_PER_COMPAT_LONG); + + if (!access_ok(VERIFY_READ, umask, bitmap_size / 8)) + return -EFAULT; + + nr_compat_longs = BITS_TO_COMPAT_LONGS(bitmap_size); + + for (i = 0; i < BITS_TO_LONGS(bitmap_size); i++) { + m = 0; + + for (j = 0; j < sizeof(m)/sizeof(um); j++) { + /* + * We dont want to read past the end of the userspace + * bitmap. We must however ensure the end of the + * kernel bitmap is zeroed. + */ + if (nr_compat_longs) { + nr_compat_longs--; + if (__get_user(um, umask)) + return -EFAULT; + } else { + um = 0; + } + + umask++; + m |= (long)um << (j * BITS_PER_COMPAT_LONG); + } + *mask++ = m; + } + + return 0; +} + +long compat_put_bitmap(compat_ulong_t __user *umask, unsigned long *mask, + unsigned long bitmap_size) +{ + int i, j; + unsigned long m; + compat_ulong_t um; + unsigned long nr_compat_longs; + + /* align bitmap up to nearest compat_long_t boundary */ + bitmap_size = ALIGN(bitmap_size, BITS_PER_COMPAT_LONG); + + if (!access_ok(VERIFY_WRITE, umask, bitmap_size / 8)) + return -EFAULT; + + nr_compat_longs = BITS_TO_COMPAT_LONGS(bitmap_size); + + for (i = 0; i < BITS_TO_LONGS(bitmap_size); i++) { + m = *mask++; + + for (j = 0; j < sizeof(m)/sizeof(um); j++) { + um = m; + + /* + * We dont want to write past the end of the userspace + * bitmap. + */ + if (nr_compat_longs) { + nr_compat_longs--; + if (__put_user(um, umask)) + return -EFAULT; + } + + umask++; + m >>= 4*sizeof(um); + m >>= 4*sizeof(um); + } + } + + return 0; +} + +void +sigset_from_compat(sigset_t *set, const compat_sigset_t *compat) +{ + switch (_NSIG_WORDS) { + case 4: set->sig[3] = compat->sig[6] | (((long)compat->sig[7]) << 32 ); + case 3: set->sig[2] = compat->sig[4] | (((long)compat->sig[5]) << 32 ); + case 2: set->sig[1] = compat->sig[2] | (((long)compat->sig[3]) << 32 ); + case 1: set->sig[0] = compat->sig[0] | (((long)compat->sig[1]) << 32 ); + } +} +EXPORT_SYMBOL_GPL(sigset_from_compat); + +void +sigset_to_compat(compat_sigset_t *compat, const sigset_t *set) +{ + switch (_NSIG_WORDS) { + case 4: compat->sig[7] = (set->sig[3] >> 32); compat->sig[6] = set->sig[3]; + case 3: compat->sig[5] = (set->sig[2] >> 32); compat->sig[4] = set->sig[2]; + case 2: compat->sig[3] = (set->sig[1] >> 32); compat->sig[2] = set->sig[1]; + case 1: compat->sig[1] = (set->sig[0] >> 32); compat->sig[0] = set->sig[0]; + } +} + +COMPAT_SYSCALL_DEFINE4(rt_sigtimedwait, compat_sigset_t __user *, uthese, + struct compat_siginfo __user *, uinfo, + struct compat_timespec __user *, uts, compat_size_t, sigsetsize) +{ + compat_sigset_t s32; + sigset_t s; + struct timespec t; + siginfo_t info; + long ret; + + if (sigsetsize != sizeof(sigset_t)) + return -EINVAL; + + if (copy_from_user(&s32, uthese, sizeof(compat_sigset_t))) + return -EFAULT; + sigset_from_compat(&s, &s32); + + if (uts) { + if (compat_get_timespec(&t, uts)) + return -EFAULT; + } + + ret = do_sigtimedwait(&s, &info, uts ? &t : NULL); + + if (ret > 0 && uinfo) { + if (copy_siginfo_to_user32(uinfo, &info)) + ret = -EFAULT; + } + + return ret; +} + +#ifdef __ARCH_WANT_COMPAT_SYS_TIME + +/* compat_time_t is a 32 bit "long" and needs to get converted. */ + +COMPAT_SYSCALL_DEFINE1(time, compat_time_t __user *, tloc) +{ + compat_time_t i; + struct timeval tv; + + do_gettimeofday(&tv); + i = tv.tv_sec; + + if (tloc) { + if (put_user(i,tloc)) + return -EFAULT; + } + force_successful_syscall_return(); + return i; +} + +COMPAT_SYSCALL_DEFINE1(stime, compat_time_t __user *, tptr) +{ + struct timespec tv; + int err; + + if (get_user(tv.tv_sec, tptr)) + return -EFAULT; + + tv.tv_nsec = 0; + + err = security_settime(&tv, NULL); + if (err) + return err; + + do_settimeofday(&tv); + return 0; +} + +#endif /* __ARCH_WANT_COMPAT_SYS_TIME */ + +COMPAT_SYSCALL_DEFINE1(adjtimex, struct compat_timex __user *, utp) +{ + struct timex txc; + int err, ret; + + err = compat_get_timex(&txc, utp); + if (err) + return err; + + ret = do_adjtimex(&txc); + + err = compat_put_timex(utp, &txc); + if (err) + return err; + + return ret; +} + +#ifdef CONFIG_NUMA +COMPAT_SYSCALL_DEFINE6(move_pages, pid_t, pid, compat_ulong_t, nr_pages, + compat_uptr_t __user *, pages32, + const int __user *, nodes, + int __user *, status, + int, flags) +{ + const void __user * __user *pages; + int i; + + pages = compat_alloc_user_space(nr_pages * sizeof(void *)); + for (i = 0; i < nr_pages; i++) { + compat_uptr_t p; + + if (get_user(p, pages32 + i) || + put_user(compat_ptr(p), pages + i)) + return -EFAULT; + } + return sys_move_pages(pid, nr_pages, pages, nodes, status, flags); +} + +COMPAT_SYSCALL_DEFINE4(migrate_pages, compat_pid_t, pid, + compat_ulong_t, maxnode, + const compat_ulong_t __user *, old_nodes, + const compat_ulong_t __user *, new_nodes) +{ + unsigned long __user *old = NULL; + unsigned long __user *new = NULL; + nodemask_t tmp_mask; + unsigned long nr_bits; + unsigned long size; + + nr_bits = min_t(unsigned long, maxnode - 1, MAX_NUMNODES); + size = ALIGN(nr_bits, BITS_PER_LONG) / 8; + if (old_nodes) { + if (compat_get_bitmap(nodes_addr(tmp_mask), old_nodes, nr_bits)) + return -EFAULT; + old = compat_alloc_user_space(new_nodes ? size * 2 : size); + if (new_nodes) + new = old + size / sizeof(unsigned long); + if (copy_to_user(old, nodes_addr(tmp_mask), size)) + return -EFAULT; + } + if (new_nodes) { + if (compat_get_bitmap(nodes_addr(tmp_mask), new_nodes, nr_bits)) + return -EFAULT; + if (new == NULL) + new = compat_alloc_user_space(size); + if (copy_to_user(new, nodes_addr(tmp_mask), size)) + return -EFAULT; + } + return sys_migrate_pages(pid, nr_bits + 1, old, new); +} +#endif + +COMPAT_SYSCALL_DEFINE2(sched_rr_get_interval, + compat_pid_t, pid, + struct compat_timespec __user *, interval) +{ + struct timespec t; + int ret; + mm_segment_t old_fs = get_fs(); + + set_fs(KERNEL_DS); + ret = sys_sched_rr_get_interval(pid, (struct timespec __user *)&t); + set_fs(old_fs); + if (compat_put_timespec(&t, interval)) + return -EFAULT; + return ret; +} + +/* + * Allocate user-space memory for the duration of a single system call, + * in order to marshall parameters inside a compat thunk. + */ +void __user *compat_alloc_user_space(unsigned long len) +{ + void __user *ptr; + + /* If len would occupy more than half of the entire compat space... */ + if (unlikely(len > (((compat_uptr_t)~0) >> 1))) + return NULL; + + ptr = arch_compat_alloc_user_space(len); + + if (unlikely(!access_ok(VERIFY_WRITE, ptr, len))) + return NULL; + + return ptr; +} +EXPORT_SYMBOL_GPL(compat_alloc_user_space); diff --git a/kernel/kernel/configs.c b/kernel/kernel/configs.c new file mode 100644 index 000000000..c18b1f1ae --- /dev/null +++ b/kernel/kernel/configs.c @@ -0,0 +1,99 @@ +/* + * kernel/configs.c + * Echo the kernel .config file used to build the kernel + * + * Copyright (C) 2002 Khalid Aziz + * Copyright (C) 2002 Randy Dunlap + * Copyright (C) 2002 Al Stone + * Copyright (C) 2002 Hewlett-Packard Company + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or (at + * your option) any later version. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or + * NON INFRINGEMENT. See the GNU General Public License for more + * details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. + */ + +#include +#include +#include +#include +#include +#include + +/**************************************************/ +/* the actual current config file */ + +/* + * Define kernel_config_data and kernel_config_data_size, which contains the + * wrapped and compressed configuration file. The file is first compressed + * with gzip and then bounded by two eight byte magic numbers to allow + * extraction from a binary kernel image: + * + * IKCFG_ST + * + * IKCFG_ED + */ +#define MAGIC_START "IKCFG_ST" +#define MAGIC_END "IKCFG_ED" +#include "config_data.h" + + +#define MAGIC_SIZE (sizeof(MAGIC_START) - 1) +#define kernel_config_data_size \ + (sizeof(kernel_config_data) - 1 - MAGIC_SIZE * 2) + +#ifdef CONFIG_IKCONFIG_PROC + +static ssize_t +ikconfig_read_current(struct file *file, char __user *buf, + size_t len, loff_t * offset) +{ + return simple_read_from_buffer(buf, len, offset, + kernel_config_data + MAGIC_SIZE, + kernel_config_data_size); +} + +static const struct file_operations ikconfig_file_ops = { + .owner = THIS_MODULE, + .read = ikconfig_read_current, + .llseek = default_llseek, +}; + +static int __init ikconfig_init(void) +{ + struct proc_dir_entry *entry; + + /* create the current config file */ + entry = proc_create("config.gz", S_IFREG | S_IRUGO, NULL, + &ikconfig_file_ops); + if (!entry) + return -ENOMEM; + + proc_set_size(entry, kernel_config_data_size); + + return 0; +} + +static void __exit ikconfig_cleanup(void) +{ + remove_proc_entry("config.gz", NULL); +} + +module_init(ikconfig_init); +module_exit(ikconfig_cleanup); + +#endif /* CONFIG_IKCONFIG_PROC */ + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Randy Dunlap"); +MODULE_DESCRIPTION("Echo the kernel .config file used to build the kernel"); diff --git a/kernel/kernel/configs/tiny.config b/kernel/kernel/configs/tiny.config new file mode 100644 index 000000000..c2de56ab0 --- /dev/null +++ b/kernel/kernel/configs/tiny.config @@ -0,0 +1,4 @@ +CONFIG_CC_OPTIMIZE_FOR_SIZE=y +CONFIG_KERNEL_XZ=y +CONFIG_OPTIMIZE_INLINING=y +CONFIG_SLOB=y diff --git a/kernel/kernel/context_tracking.c b/kernel/kernel/context_tracking.c new file mode 100644 index 000000000..72d59a1a6 --- /dev/null +++ b/kernel/kernel/context_tracking.c @@ -0,0 +1,195 @@ +/* + * Context tracking: Probe on high level context boundaries such as kernel + * and userspace. This includes syscalls and exceptions entry/exit. + * + * This is used by RCU to remove its dependency on the timer tick while a CPU + * runs in userspace. + * + * Started by Frederic Weisbecker: + * + * Copyright (C) 2012 Red Hat, Inc., Frederic Weisbecker + * + * Many thanks to Gilad Ben-Yossef, Paul McKenney, Ingo Molnar, Andrew Morton, + * Steven Rostedt, Peter Zijlstra for suggestions and improvements. + * + */ + +#include +#include +#include +#include +#include +#include + +#define CREATE_TRACE_POINTS +#include + +struct static_key context_tracking_enabled = STATIC_KEY_INIT_FALSE; +EXPORT_SYMBOL_GPL(context_tracking_enabled); + +DEFINE_PER_CPU(struct context_tracking, context_tracking); +EXPORT_SYMBOL_GPL(context_tracking); + +void context_tracking_cpu_set(int cpu) +{ + if (!per_cpu(context_tracking.active, cpu)) { + per_cpu(context_tracking.active, cpu) = true; + static_key_slow_inc(&context_tracking_enabled); + } +} + +/** + * context_tracking_enter - Inform the context tracking that the CPU is going + * enter user or guest space mode. + * + * This function must be called right before we switch from the kernel + * to user or guest space, when it's guaranteed the remaining kernel + * instructions to execute won't use any RCU read side critical section + * because this function sets RCU in extended quiescent state. + */ +void context_tracking_enter(enum ctx_state state) +{ + unsigned long flags; + + /* + * Repeat the user_enter() check here because some archs may be calling + * this from asm and if no CPU needs context tracking, they shouldn't + * go further. Repeat the check here until they support the inline static + * key check. + */ + if (!context_tracking_is_enabled()) + return; + + /* + * Some contexts may involve an exception occuring in an irq, + * leading to that nesting: + * rcu_irq_enter() rcu_user_exit() rcu_user_exit() rcu_irq_exit() + * This would mess up the dyntick_nesting count though. And rcu_irq_*() + * helpers are enough to protect RCU uses inside the exception. So + * just return immediately if we detect we are in an IRQ. + */ + if (in_interrupt()) + return; + + /* Kernel threads aren't supposed to go to userspace */ + WARN_ON_ONCE(!current->mm); + + local_irq_save(flags); + if ( __this_cpu_read(context_tracking.state) != state) { + if (__this_cpu_read(context_tracking.active)) { + /* + * At this stage, only low level arch entry code remains and + * then we'll run in userspace. We can assume there won't be + * any RCU read-side critical section until the next call to + * user_exit() or rcu_irq_enter(). Let's remove RCU's dependency + * on the tick. + */ + if (state == CONTEXT_USER) { + trace_user_enter(0); + vtime_user_enter(current); + } + rcu_user_enter(); + } + /* + * Even if context tracking is disabled on this CPU, because it's outside + * the full dynticks mask for example, we still have to keep track of the + * context transitions and states to prevent inconsistency on those of + * other CPUs. + * If a task triggers an exception in userspace, sleep on the exception + * handler and then migrate to another CPU, that new CPU must know where + * the exception returns by the time we call exception_exit(). + * This information can only be provided by the previous CPU when it called + * exception_enter(). + * OTOH we can spare the calls to vtime and RCU when context_tracking.active + * is false because we know that CPU is not tickless. + */ + __this_cpu_write(context_tracking.state, state); + } + local_irq_restore(flags); +} +NOKPROBE_SYMBOL(context_tracking_enter); +EXPORT_SYMBOL_GPL(context_tracking_enter); + +void context_tracking_user_enter(void) +{ + context_tracking_enter(CONTEXT_USER); +} +NOKPROBE_SYMBOL(context_tracking_user_enter); + +/** + * context_tracking_exit - Inform the context tracking that the CPU is + * exiting user or guest mode and entering the kernel. + * + * This function must be called after we entered the kernel from user or + * guest space before any use of RCU read side critical section. This + * potentially include any high level kernel code like syscalls, exceptions, + * signal handling, etc... + * + * This call supports re-entrancy. This way it can be called from any exception + * handler without needing to know if we came from userspace or not. + */ +void context_tracking_exit(enum ctx_state state) +{ + unsigned long flags; + + if (!context_tracking_is_enabled()) + return; + + if (in_interrupt()) + return; + + local_irq_save(flags); + if (__this_cpu_read(context_tracking.state) == state) { + if (__this_cpu_read(context_tracking.active)) { + /* + * We are going to run code that may use RCU. Inform + * RCU core about that (ie: we may need the tick again). + */ + rcu_user_exit(); + if (state == CONTEXT_USER) { + vtime_user_exit(current); + trace_user_exit(0); + } + } + __this_cpu_write(context_tracking.state, CONTEXT_KERNEL); + } + local_irq_restore(flags); +} +NOKPROBE_SYMBOL(context_tracking_exit); +EXPORT_SYMBOL_GPL(context_tracking_exit); + +void context_tracking_user_exit(void) +{ + context_tracking_exit(CONTEXT_USER); +} +NOKPROBE_SYMBOL(context_tracking_user_exit); + +/** + * __context_tracking_task_switch - context switch the syscall callbacks + * @prev: the task that is being switched out + * @next: the task that is being switched in + * + * The context tracking uses the syscall slow path to implement its user-kernel + * boundaries probes on syscalls. This way it doesn't impact the syscall fast + * path on CPUs that don't do context tracking. + * + * But we need to clear the flag on the previous task because it may later + * migrate to some CPU that doesn't do the context tracking. As such the TIF + * flag may not be desired there. + */ +void __context_tracking_task_switch(struct task_struct *prev, + struct task_struct *next) +{ + clear_tsk_thread_flag(prev, TIF_NOHZ); + set_tsk_thread_flag(next, TIF_NOHZ); +} + +#ifdef CONFIG_CONTEXT_TRACKING_FORCE +void __init context_tracking_init(void) +{ + int cpu; + + for_each_possible_cpu(cpu) + context_tracking_cpu_set(cpu); +} +#endif diff --git a/kernel/kernel/cpu.c b/kernel/kernel/cpu.c new file mode 100644 index 000000000..0351ac422 --- /dev/null +++ b/kernel/kernel/cpu.c @@ -0,0 +1,1146 @@ +/* CPU control. + * (C) 2001, 2002, 2003, 2004 Rusty Russell + * + * This code is licenced under the GPL. + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "smpboot.h" + +#ifdef CONFIG_SMP +/* Serializes the updates to cpu_online_mask, cpu_present_mask */ +static DEFINE_MUTEX(cpu_add_remove_lock); + +/* + * The following two APIs (cpu_maps_update_begin/done) must be used when + * attempting to serialize the updates to cpu_online_mask & cpu_present_mask. + * The APIs cpu_notifier_register_begin/done() must be used to protect CPU + * hotplug callback (un)registration performed using __register_cpu_notifier() + * or __unregister_cpu_notifier(). + */ +void cpu_maps_update_begin(void) +{ + mutex_lock(&cpu_add_remove_lock); +} +EXPORT_SYMBOL(cpu_notifier_register_begin); + +void cpu_maps_update_done(void) +{ + mutex_unlock(&cpu_add_remove_lock); +} +EXPORT_SYMBOL(cpu_notifier_register_done); + +static RAW_NOTIFIER_HEAD(cpu_chain); + +/* If set, cpu_up and cpu_down will return -EBUSY and do nothing. + * Should always be manipulated under cpu_add_remove_lock + */ +static int cpu_hotplug_disabled; + +#ifdef CONFIG_HOTPLUG_CPU + +static struct { + struct task_struct *active_writer; + /* wait queue to wake up the active_writer */ + wait_queue_head_t wq; + /* verifies that no writer will get active while readers are active */ + struct mutex lock; + /* + * Also blocks the new readers during + * an ongoing cpu hotplug operation. + */ + atomic_t refcount; + +#ifdef CONFIG_DEBUG_LOCK_ALLOC + struct lockdep_map dep_map; +#endif +} cpu_hotplug = { + .active_writer = NULL, + .lock = __MUTEX_INITIALIZER(cpu_hotplug.lock), + .wq = __WAIT_QUEUE_HEAD_INITIALIZER(cpu_hotplug.wq), +#ifdef CONFIG_DEBUG_LOCK_ALLOC + .dep_map = {.name = "cpu_hotplug.lock" }, +#endif +}; + +/* Lockdep annotations for get/put_online_cpus() and cpu_hotplug_begin/end() */ +#define cpuhp_lock_acquire_read() lock_map_acquire_read(&cpu_hotplug.dep_map) +#define cpuhp_lock_acquire_tryread() \ + lock_map_acquire_tryread(&cpu_hotplug.dep_map) +#define cpuhp_lock_acquire() lock_map_acquire(&cpu_hotplug.dep_map) +#define cpuhp_lock_release() lock_map_release(&cpu_hotplug.dep_map) + +/** + * hotplug_pcp - per cpu hotplug descriptor + * @unplug: set when pin_current_cpu() needs to sync tasks + * @sync_tsk: the task that waits for tasks to finish pinned sections + * @refcount: counter of tasks in pinned sections + * @grab_lock: set when the tasks entering pinned sections should wait + * @synced: notifier for @sync_tsk to tell cpu_down it's finished + * @mutex: the mutex to make tasks wait (used when @grab_lock is true) + * @mutex_init: zero if the mutex hasn't been initialized yet. + * + * Although @unplug and @sync_tsk may point to the same task, the @unplug + * is used as a flag and still exists after @sync_tsk has exited and + * @sync_tsk set to NULL. + */ +struct hotplug_pcp { + struct task_struct *unplug; + struct task_struct *sync_tsk; + int refcount; + int grab_lock; + struct completion synced; + struct completion unplug_wait; +#ifdef CONFIG_PREEMPT_RT_FULL + /* + * Note, on PREEMPT_RT, the hotplug lock must save the state of + * the task, otherwise the mutex will cause the task to fail + * to sleep when required. (Because it's called from migrate_disable()) + * + * The spinlock_t on PREEMPT_RT is a mutex that saves the task's + * state. + */ + spinlock_t lock; +#else + struct mutex mutex; +#endif + int mutex_init; +}; + +#ifdef CONFIG_PREEMPT_RT_FULL +# define hotplug_lock(hp) rt_spin_lock(&(hp)->lock) +# define hotplug_unlock(hp) rt_spin_unlock(&(hp)->lock) +#else +# define hotplug_lock(hp) mutex_lock(&(hp)->mutex) +# define hotplug_unlock(hp) mutex_unlock(&(hp)->mutex) +#endif + +static DEFINE_PER_CPU(struct hotplug_pcp, hotplug_pcp); + +/** + * pin_current_cpu - Prevent the current cpu from being unplugged + * + * Lightweight version of get_online_cpus() to prevent cpu from being + * unplugged when code runs in a migration disabled region. + * + * Must be called with preemption disabled (preempt_count = 1)! + */ +void pin_current_cpu(void) +{ + struct hotplug_pcp *hp; + int force = 0; + +retry: + hp = this_cpu_ptr(&hotplug_pcp); + + if (!hp->unplug || hp->refcount || force || preempt_count() > 1 || + hp->unplug == current) { + hp->refcount++; + return; + } + if (hp->grab_lock) { + preempt_enable(); + hotplug_lock(hp); + hotplug_unlock(hp); + } else { + preempt_enable(); + /* + * Try to push this task off of this CPU. + */ + if (!migrate_me()) { + preempt_disable(); + hp = this_cpu_ptr(&hotplug_pcp); + if (!hp->grab_lock) { + /* + * Just let it continue it's already pinned + * or about to sleep. + */ + force = 1; + goto retry; + } + preempt_enable(); + } + } + preempt_disable(); + goto retry; +} + +/** + * unpin_current_cpu - Allow unplug of current cpu + * + * Must be called with preemption or interrupts disabled! + */ +void unpin_current_cpu(void) +{ + struct hotplug_pcp *hp = this_cpu_ptr(&hotplug_pcp); + + WARN_ON(hp->refcount <= 0); + + /* This is safe. sync_unplug_thread is pinned to this cpu */ + if (!--hp->refcount && hp->unplug && hp->unplug != current) + wake_up_process(hp->unplug); +} + +static void wait_for_pinned_cpus(struct hotplug_pcp *hp) +{ + set_current_state(TASK_UNINTERRUPTIBLE); + while (hp->refcount) { + schedule_preempt_disabled(); + set_current_state(TASK_UNINTERRUPTIBLE); + } +} + +static int sync_unplug_thread(void *data) +{ + struct hotplug_pcp *hp = data; + + wait_for_completion(&hp->unplug_wait); + preempt_disable(); + hp->unplug = current; + wait_for_pinned_cpus(hp); + + /* + * This thread will synchronize the cpu_down() with threads + * that have pinned the CPU. When the pinned CPU count reaches + * zero, we inform the cpu_down code to continue to the next step. + */ + set_current_state(TASK_UNINTERRUPTIBLE); + preempt_enable(); + complete(&hp->synced); + + /* + * If all succeeds, the next step will need tasks to wait till + * the CPU is offline before continuing. To do this, the grab_lock + * is set and tasks going into pin_current_cpu() will block on the + * mutex. But we still need to wait for those that are already in + * pinned CPU sections. If the cpu_down() failed, the kthread_should_stop() + * will kick this thread out. + */ + while (!hp->grab_lock && !kthread_should_stop()) { + schedule(); + set_current_state(TASK_UNINTERRUPTIBLE); + } + + /* Make sure grab_lock is seen before we see a stale completion */ + smp_mb(); + + /* + * Now just before cpu_down() enters stop machine, we need to make + * sure all tasks that are in pinned CPU sections are out, and new + * tasks will now grab the lock, keeping them from entering pinned + * CPU sections. + */ + if (!kthread_should_stop()) { + preempt_disable(); + wait_for_pinned_cpus(hp); + preempt_enable(); + complete(&hp->synced); + } + + set_current_state(TASK_UNINTERRUPTIBLE); + while (!kthread_should_stop()) { + schedule(); + set_current_state(TASK_UNINTERRUPTIBLE); + } + set_current_state(TASK_RUNNING); + + /* + * Force this thread off this CPU as it's going down and + * we don't want any more work on this CPU. + */ + current->flags &= ~PF_NO_SETAFFINITY; + set_cpus_allowed_ptr(current, cpu_present_mask); + migrate_me(); + return 0; +} + +static void __cpu_unplug_sync(struct hotplug_pcp *hp) +{ + wake_up_process(hp->sync_tsk); + wait_for_completion(&hp->synced); +} + +static void __cpu_unplug_wait(unsigned int cpu) +{ + struct hotplug_pcp *hp = &per_cpu(hotplug_pcp, cpu); + + complete(&hp->unplug_wait); + wait_for_completion(&hp->synced); +} + +/* + * Start the sync_unplug_thread on the target cpu and wait for it to + * complete. + */ +static int cpu_unplug_begin(unsigned int cpu) +{ + struct hotplug_pcp *hp = &per_cpu(hotplug_pcp, cpu); + int err; + + /* Protected by cpu_hotplug.lock */ + if (!hp->mutex_init) { +#ifdef CONFIG_PREEMPT_RT_FULL + spin_lock_init(&hp->lock); +#else + mutex_init(&hp->mutex); +#endif + hp->mutex_init = 1; + } + + /* Inform the scheduler to migrate tasks off this CPU */ + tell_sched_cpu_down_begin(cpu); + + init_completion(&hp->synced); + init_completion(&hp->unplug_wait); + + hp->sync_tsk = kthread_create(sync_unplug_thread, hp, "sync_unplug/%d", cpu); + if (IS_ERR(hp->sync_tsk)) { + err = PTR_ERR(hp->sync_tsk); + hp->sync_tsk = NULL; + return err; + } + kthread_bind(hp->sync_tsk, cpu); + + /* + * Wait for tasks to get out of the pinned sections, + * it's still OK if new tasks enter. Some CPU notifiers will + * wait for tasks that are going to enter these sections and + * we must not have them block. + */ + wake_up_process(hp->sync_tsk); + return 0; +} + +static void cpu_unplug_sync(unsigned int cpu) +{ + struct hotplug_pcp *hp = &per_cpu(hotplug_pcp, cpu); + + init_completion(&hp->synced); + /* The completion needs to be initialzied before setting grab_lock */ + smp_wmb(); + + /* Grab the mutex before setting grab_lock */ + hotplug_lock(hp); + hp->grab_lock = 1; + + /* + * The CPU notifiers have been completed. + * Wait for tasks to get out of pinned CPU sections and have new + * tasks block until the CPU is completely down. + */ + __cpu_unplug_sync(hp); + + /* All done with the sync thread */ + kthread_stop(hp->sync_tsk); + hp->sync_tsk = NULL; +} + +static void cpu_unplug_done(unsigned int cpu) +{ + struct hotplug_pcp *hp = &per_cpu(hotplug_pcp, cpu); + + hp->unplug = NULL; + /* Let all tasks know cpu unplug is finished before cleaning up */ + smp_wmb(); + + if (hp->sync_tsk) + kthread_stop(hp->sync_tsk); + + if (hp->grab_lock) { + hotplug_unlock(hp); + /* protected by cpu_hotplug.lock */ + hp->grab_lock = 0; + } + tell_sched_cpu_down_done(cpu); +} + +void get_online_cpus(void) +{ + might_sleep(); + if (cpu_hotplug.active_writer == current) + return; + cpuhp_lock_acquire_read(); + mutex_lock(&cpu_hotplug.lock); + atomic_inc(&cpu_hotplug.refcount); + mutex_unlock(&cpu_hotplug.lock); +} +EXPORT_SYMBOL_GPL(get_online_cpus); + +bool try_get_online_cpus(void) +{ + if (cpu_hotplug.active_writer == current) + return true; + if (!mutex_trylock(&cpu_hotplug.lock)) + return false; + cpuhp_lock_acquire_tryread(); + atomic_inc(&cpu_hotplug.refcount); + mutex_unlock(&cpu_hotplug.lock); + return true; +} +EXPORT_SYMBOL_GPL(try_get_online_cpus); + +void put_online_cpus(void) +{ + int refcount; + + if (cpu_hotplug.active_writer == current) + return; + + refcount = atomic_dec_return(&cpu_hotplug.refcount); + if (WARN_ON(refcount < 0)) /* try to fix things up */ + atomic_inc(&cpu_hotplug.refcount); + + if (refcount <= 0 && waitqueue_active(&cpu_hotplug.wq)) + wake_up(&cpu_hotplug.wq); + + cpuhp_lock_release(); + +} +EXPORT_SYMBOL_GPL(put_online_cpus); + +/* + * This ensures that the hotplug operation can begin only when the + * refcount goes to zero. + * + * Note that during a cpu-hotplug operation, the new readers, if any, + * will be blocked by the cpu_hotplug.lock + * + * Since cpu_hotplug_begin() is always called after invoking + * cpu_maps_update_begin(), we can be sure that only one writer is active. + * + * Note that theoretically, there is a possibility of a livelock: + * - Refcount goes to zero, last reader wakes up the sleeping + * writer. + * - Last reader unlocks the cpu_hotplug.lock. + * - A new reader arrives at this moment, bumps up the refcount. + * - The writer acquires the cpu_hotplug.lock finds the refcount + * non zero and goes to sleep again. + * + * However, this is very difficult to achieve in practice since + * get_online_cpus() not an api which is called all that often. + * + */ +void cpu_hotplug_begin(void) +{ + DEFINE_WAIT(wait); + + cpu_hotplug.active_writer = current; + cpuhp_lock_acquire(); + + for (;;) { + mutex_lock(&cpu_hotplug.lock); + prepare_to_wait(&cpu_hotplug.wq, &wait, TASK_UNINTERRUPTIBLE); + if (likely(!atomic_read(&cpu_hotplug.refcount))) + break; + mutex_unlock(&cpu_hotplug.lock); + schedule(); + } + finish_wait(&cpu_hotplug.wq, &wait); +} + +void cpu_hotplug_done(void) +{ + cpu_hotplug.active_writer = NULL; + mutex_unlock(&cpu_hotplug.lock); + cpuhp_lock_release(); +} + +/* + * Wait for currently running CPU hotplug operations to complete (if any) and + * disable future CPU hotplug (from sysfs). The 'cpu_add_remove_lock' protects + * the 'cpu_hotplug_disabled' flag. The same lock is also acquired by the + * hotplug path before performing hotplug operations. So acquiring that lock + * guarantees mutual exclusion from any currently running hotplug operations. + */ +void cpu_hotplug_disable(void) +{ + cpu_maps_update_begin(); + cpu_hotplug_disabled = 1; + cpu_maps_update_done(); +} + +void cpu_hotplug_enable(void) +{ + cpu_maps_update_begin(); + cpu_hotplug_disabled = 0; + cpu_maps_update_done(); +} + +#endif /* CONFIG_HOTPLUG_CPU */ + +/* Need to know about CPUs going up/down? */ +int __ref register_cpu_notifier(struct notifier_block *nb) +{ + int ret; + cpu_maps_update_begin(); + ret = raw_notifier_chain_register(&cpu_chain, nb); + cpu_maps_update_done(); + return ret; +} + +int __ref __register_cpu_notifier(struct notifier_block *nb) +{ + return raw_notifier_chain_register(&cpu_chain, nb); +} + +static int __cpu_notify(unsigned long val, void *v, int nr_to_call, + int *nr_calls) +{ + int ret; + + ret = __raw_notifier_call_chain(&cpu_chain, val, v, nr_to_call, + nr_calls); + + return notifier_to_errno(ret); +} + +static int cpu_notify(unsigned long val, void *v) +{ + return __cpu_notify(val, v, -1, NULL); +} + +#ifdef CONFIG_HOTPLUG_CPU + +static void cpu_notify_nofail(unsigned long val, void *v) +{ + BUG_ON(cpu_notify(val, v)); +} +EXPORT_SYMBOL(register_cpu_notifier); +EXPORT_SYMBOL(__register_cpu_notifier); + +void __ref unregister_cpu_notifier(struct notifier_block *nb) +{ + cpu_maps_update_begin(); + raw_notifier_chain_unregister(&cpu_chain, nb); + cpu_maps_update_done(); +} +EXPORT_SYMBOL(unregister_cpu_notifier); + +void __ref __unregister_cpu_notifier(struct notifier_block *nb) +{ + raw_notifier_chain_unregister(&cpu_chain, nb); +} +EXPORT_SYMBOL(__unregister_cpu_notifier); + +/** + * clear_tasks_mm_cpumask - Safely clear tasks' mm_cpumask for a CPU + * @cpu: a CPU id + * + * This function walks all processes, finds a valid mm struct for each one and + * then clears a corresponding bit in mm's cpumask. While this all sounds + * trivial, there are various non-obvious corner cases, which this function + * tries to solve in a safe manner. + * + * Also note that the function uses a somewhat relaxed locking scheme, so it may + * be called only for an already offlined CPU. + */ +void clear_tasks_mm_cpumask(int cpu) +{ + struct task_struct *p; + + /* + * This function is called after the cpu is taken down and marked + * offline, so its not like new tasks will ever get this cpu set in + * their mm mask. -- Peter Zijlstra + * Thus, we may use rcu_read_lock() here, instead of grabbing + * full-fledged tasklist_lock. + */ + WARN_ON(cpu_online(cpu)); + rcu_read_lock(); + for_each_process(p) { + struct task_struct *t; + + /* + * Main thread might exit, but other threads may still have + * a valid mm. Find one. + */ + t = find_lock_task_mm(p); + if (!t) + continue; + cpumask_clear_cpu(cpu, mm_cpumask(t->mm)); + task_unlock(t); + } + rcu_read_unlock(); +} + +static inline void check_for_tasks(int dead_cpu) +{ + struct task_struct *g, *p; + + read_lock_irq(&tasklist_lock); + do_each_thread(g, p) { + if (!p->on_rq) + continue; + /* + * We do the check with unlocked task_rq(p)->lock. + * Order the reading to do not warn about a task, + * which was running on this cpu in the past, and + * it's just been woken on another cpu. + */ + rmb(); + if (task_cpu(p) != dead_cpu) + continue; + + pr_warn("Task %s (pid=%d) is on cpu %d (state=%ld, flags=%x)\n", + p->comm, task_pid_nr(p), dead_cpu, p->state, p->flags); + } while_each_thread(g, p); + read_unlock_irq(&tasklist_lock); +} + +struct take_cpu_down_param { + unsigned long mod; + void *hcpu; +}; + +/* Take this CPU down. */ +static int __ref take_cpu_down(void *_param) +{ + struct take_cpu_down_param *param = _param; + int err; + + /* Ensure this CPU doesn't handle any more interrupts. */ + err = __cpu_disable(); + if (err < 0) + return err; + + cpu_notify(CPU_DYING | param->mod, param->hcpu); + /* Give up timekeeping duties */ + tick_handover_do_timer(); + /* Park the stopper thread */ + kthread_park(current); + return 0; +} + +/* Requires cpu_add_remove_lock to be held */ +static int __ref _cpu_down(unsigned int cpu, int tasks_frozen) +{ + int mycpu, err, nr_calls = 0; + void *hcpu = (void *)(long)cpu; + unsigned long mod = tasks_frozen ? CPU_TASKS_FROZEN : 0; + struct take_cpu_down_param tcd_param = { + .mod = mod, + .hcpu = hcpu, + }; + cpumask_var_t cpumask; + cpumask_var_t cpumask_org; + + if (num_online_cpus() == 1) + return -EBUSY; + + if (!cpu_online(cpu)) + return -EINVAL; + + /* Move the downtaker off the unplug cpu */ + if (!alloc_cpumask_var(&cpumask, GFP_KERNEL)) + return -ENOMEM; + if (!alloc_cpumask_var(&cpumask_org, GFP_KERNEL)) { + free_cpumask_var(cpumask); + return -ENOMEM; + } + + cpumask_copy(cpumask_org, tsk_cpus_allowed(current)); + cpumask_andnot(cpumask, cpu_online_mask, cpumask_of(cpu)); + set_cpus_allowed_ptr(current, cpumask); + free_cpumask_var(cpumask); + migrate_disable(); + mycpu = smp_processor_id(); + if (mycpu == cpu) { + printk(KERN_ERR "Yuck! Still on unplug CPU\n!"); + migrate_enable(); + err = -EBUSY; + goto restore_cpus; + } + migrate_enable(); + + cpu_hotplug_begin(); + err = cpu_unplug_begin(cpu); + if (err) { + printk("cpu_unplug_begin(%d) failed\n", cpu); + goto out_cancel; + } + + err = __cpu_notify(CPU_DOWN_PREPARE | mod, hcpu, -1, &nr_calls); + if (err) { + nr_calls--; + __cpu_notify(CPU_DOWN_FAILED | mod, hcpu, nr_calls, NULL); + pr_warn("%s: attempt to take down CPU %u failed\n", + __func__, cpu); + goto out_release; + } + + /* + * By now we've cleared cpu_active_mask, wait for all preempt-disabled + * and RCU users of this state to go away such that all new such users + * will observe it. + * + * For CONFIG_PREEMPT we have preemptible RCU and its sync_rcu() might + * not imply sync_sched(), so explicitly call both. + * + * Do sync before park smpboot threads to take care the rcu boost case. + */ +#ifdef CONFIG_PREEMPT + synchronize_sched(); +#endif + synchronize_rcu(); + + __cpu_unplug_wait(cpu); + smpboot_park_threads(cpu); + + /* Notifiers are done. Don't let any more tasks pin this CPU. */ + cpu_unplug_sync(cpu); + + /* + * So now all preempt/rcu users must observe !cpu_active(). + */ + + err = __stop_machine(take_cpu_down, &tcd_param, cpumask_of(cpu)); + if (err) { + /* CPU didn't die: tell everyone. Can't complain. */ + smpboot_unpark_threads(cpu); + cpu_notify_nofail(CPU_DOWN_FAILED | mod, hcpu); + goto out_release; + } + BUG_ON(cpu_online(cpu)); + + /* + * The migration_call() CPU_DYING callback will have removed all + * runnable tasks from the cpu, there's only the idle task left now + * that the migration thread is done doing the stop_machine thing. + * + * Wait for the stop thread to go away. + */ + while (!per_cpu(cpu_dead_idle, cpu)) + cpu_relax(); + smp_mb(); /* Read from cpu_dead_idle before __cpu_die(). */ + per_cpu(cpu_dead_idle, cpu) = false; + + hotplug_cpu__broadcast_tick_pull(cpu); + /* This actually kills the CPU. */ + __cpu_die(cpu); + + /* CPU is completely dead: tell everyone. Too late to complain. */ + tick_cleanup_dead_cpu(cpu); + cpu_notify_nofail(CPU_DEAD | mod, hcpu); + + check_for_tasks(cpu); + +out_release: + cpu_unplug_done(cpu); +out_cancel: + cpu_hotplug_done(); + if (!err) + cpu_notify_nofail(CPU_POST_DEAD | mod, hcpu); +restore_cpus: + set_cpus_allowed_ptr(current, cpumask_org); + free_cpumask_var(cpumask_org); + return err; +} + +int __ref cpu_down(unsigned int cpu) +{ + int err; + + cpu_maps_update_begin(); + + if (cpu_hotplug_disabled) { + err = -EBUSY; + goto out; + } + + err = _cpu_down(cpu, 0); + +out: + cpu_maps_update_done(); + return err; +} +EXPORT_SYMBOL(cpu_down); +#endif /*CONFIG_HOTPLUG_CPU*/ + +/* + * Unpark per-CPU smpboot kthreads at CPU-online time. + */ +static int smpboot_thread_call(struct notifier_block *nfb, + unsigned long action, void *hcpu) +{ + int cpu = (long)hcpu; + + switch (action & ~CPU_TASKS_FROZEN) { + + case CPU_ONLINE: + smpboot_unpark_threads(cpu); + break; + + default: + break; + } + + return NOTIFY_OK; +} + +static struct notifier_block smpboot_thread_notifier = { + .notifier_call = smpboot_thread_call, + .priority = CPU_PRI_SMPBOOT, +}; + +void __cpuinit smpboot_thread_init(void) +{ + register_cpu_notifier(&smpboot_thread_notifier); +} + +/* Requires cpu_add_remove_lock to be held */ +static int _cpu_up(unsigned int cpu, int tasks_frozen) +{ + int ret, nr_calls = 0; + void *hcpu = (void *)(long)cpu; + unsigned long mod = tasks_frozen ? CPU_TASKS_FROZEN : 0; + struct task_struct *idle; + + cpu_hotplug_begin(); + + if (cpu_online(cpu) || !cpu_present(cpu)) { + ret = -EINVAL; + goto out; + } + + idle = idle_thread_get(cpu); + if (IS_ERR(idle)) { + ret = PTR_ERR(idle); + goto out; + } + + ret = smpboot_create_threads(cpu); + if (ret) + goto out; + + ret = __cpu_notify(CPU_UP_PREPARE | mod, hcpu, -1, &nr_calls); + if (ret) { + nr_calls--; + pr_warn("%s: attempt to bring up CPU %u failed\n", + __func__, cpu); + goto out_notify; + } + + /* Arch-specific enabling code. */ + ret = __cpu_up(cpu, idle); + if (ret != 0) + goto out_notify; + BUG_ON(!cpu_online(cpu)); + + /* Now call notifier in preparation. */ + cpu_notify(CPU_ONLINE | mod, hcpu); + +out_notify: + if (ret != 0) + __cpu_notify(CPU_UP_CANCELED | mod, hcpu, nr_calls, NULL); +out: + cpu_hotplug_done(); + + return ret; +} + +int cpu_up(unsigned int cpu) +{ + int err = 0; + + if (!cpu_possible(cpu)) { + pr_err("can't online cpu %d because it is not configured as may-hotadd at boot time\n", + cpu); +#if defined(CONFIG_IA64) + pr_err("please check additional_cpus= boot parameter\n"); +#endif + return -EINVAL; + } + + err = try_online_node(cpu_to_node(cpu)); + if (err) + return err; + + cpu_maps_update_begin(); + + if (cpu_hotplug_disabled) { + err = -EBUSY; + goto out; + } + + err = _cpu_up(cpu, 0); + +out: + cpu_maps_update_done(); + return err; +} +EXPORT_SYMBOL_GPL(cpu_up); + +#ifdef CONFIG_PM_SLEEP_SMP +static cpumask_var_t frozen_cpus; + +int disable_nonboot_cpus(void) +{ + int cpu, first_cpu, error = 0; + + cpu_maps_update_begin(); + first_cpu = cpumask_first(cpu_online_mask); + /* + * We take down all of the non-boot CPUs in one shot to avoid races + * with the userspace trying to use the CPU hotplug at the same time + */ + cpumask_clear(frozen_cpus); + + pr_info("Disabling non-boot CPUs ...\n"); + for_each_online_cpu(cpu) { + if (cpu == first_cpu) + continue; + trace_suspend_resume(TPS("CPU_OFF"), cpu, true); + error = _cpu_down(cpu, 1); + trace_suspend_resume(TPS("CPU_OFF"), cpu, false); + if (!error) + cpumask_set_cpu(cpu, frozen_cpus); + else { + pr_err("Error taking CPU%d down: %d\n", cpu, error); + break; + } + } + + if (!error) { + BUG_ON(num_online_cpus() > 1); + /* Make sure the CPUs won't be enabled by someone else */ + cpu_hotplug_disabled = 1; + } else { + pr_err("Non-boot CPUs are not disabled\n"); + } + cpu_maps_update_done(); + return error; +} + +void __weak arch_enable_nonboot_cpus_begin(void) +{ +} + +void __weak arch_enable_nonboot_cpus_end(void) +{ +} + +void __ref enable_nonboot_cpus(void) +{ + int cpu, error; + + /* Allow everyone to use the CPU hotplug again */ + cpu_maps_update_begin(); + cpu_hotplug_disabled = 0; + if (cpumask_empty(frozen_cpus)) + goto out; + + pr_info("Enabling non-boot CPUs ...\n"); + + arch_enable_nonboot_cpus_begin(); + + for_each_cpu(cpu, frozen_cpus) { + trace_suspend_resume(TPS("CPU_ON"), cpu, true); + error = _cpu_up(cpu, 1); + trace_suspend_resume(TPS("CPU_ON"), cpu, false); + if (!error) { + pr_info("CPU%d is up\n", cpu); + continue; + } + pr_warn("Error taking CPU%d up: %d\n", cpu, error); + } + + arch_enable_nonboot_cpus_end(); + + cpumask_clear(frozen_cpus); +out: + cpu_maps_update_done(); +} + +static int __init alloc_frozen_cpus(void) +{ + if (!alloc_cpumask_var(&frozen_cpus, GFP_KERNEL|__GFP_ZERO)) + return -ENOMEM; + return 0; +} +core_initcall(alloc_frozen_cpus); + +/* + * When callbacks for CPU hotplug notifications are being executed, we must + * ensure that the state of the system with respect to the tasks being frozen + * or not, as reported by the notification, remains unchanged *throughout the + * duration* of the execution of the callbacks. + * Hence we need to prevent the freezer from racing with regular CPU hotplug. + * + * This synchronization is implemented by mutually excluding regular CPU + * hotplug and Suspend/Hibernate call paths by hooking onto the Suspend/ + * Hibernate notifications. + */ +static int +cpu_hotplug_pm_callback(struct notifier_block *nb, + unsigned long action, void *ptr) +{ + switch (action) { + + case PM_SUSPEND_PREPARE: + case PM_HIBERNATION_PREPARE: + cpu_hotplug_disable(); + break; + + case PM_POST_SUSPEND: + case PM_POST_HIBERNATION: + cpu_hotplug_enable(); + break; + + default: + return NOTIFY_DONE; + } + + return NOTIFY_OK; +} + + +static int __init cpu_hotplug_pm_sync_init(void) +{ + /* + * cpu_hotplug_pm_callback has higher priority than x86 + * bsp_pm_callback which depends on cpu_hotplug_pm_callback + * to disable cpu hotplug to avoid cpu hotplug race. + */ + pm_notifier(cpu_hotplug_pm_callback, 0); + return 0; +} +core_initcall(cpu_hotplug_pm_sync_init); + +#endif /* CONFIG_PM_SLEEP_SMP */ + +/** + * notify_cpu_starting(cpu) - call the CPU_STARTING notifiers + * @cpu: cpu that just started + * + * This function calls the cpu_chain notifiers with CPU_STARTING. + * It must be called by the arch code on the new cpu, before the new cpu + * enables interrupts and before the "boot" cpu returns from __cpu_up(). + */ +void notify_cpu_starting(unsigned int cpu) +{ + unsigned long val = CPU_STARTING; + +#ifdef CONFIG_PM_SLEEP_SMP + if (frozen_cpus != NULL && cpumask_test_cpu(cpu, frozen_cpus)) + val = CPU_STARTING_FROZEN; +#endif /* CONFIG_PM_SLEEP_SMP */ + cpu_notify(val, (void *)(long)cpu); +} + +#endif /* CONFIG_SMP */ + +/* + * cpu_bit_bitmap[] is a special, "compressed" data structure that + * represents all NR_CPUS bits binary values of 1< 32 + MASK_DECLARE_8(32), MASK_DECLARE_8(40), + MASK_DECLARE_8(48), MASK_DECLARE_8(56), +#endif +}; +EXPORT_SYMBOL_GPL(cpu_bit_bitmap); + +const DECLARE_BITMAP(cpu_all_bits, NR_CPUS) = CPU_BITS_ALL; +EXPORT_SYMBOL(cpu_all_bits); + +#ifdef CONFIG_INIT_ALL_POSSIBLE +static DECLARE_BITMAP(cpu_possible_bits, CONFIG_NR_CPUS) __read_mostly + = CPU_BITS_ALL; +#else +static DECLARE_BITMAP(cpu_possible_bits, CONFIG_NR_CPUS) __read_mostly; +#endif +const struct cpumask *const cpu_possible_mask = to_cpumask(cpu_possible_bits); +EXPORT_SYMBOL(cpu_possible_mask); + +static DECLARE_BITMAP(cpu_online_bits, CONFIG_NR_CPUS) __read_mostly; +const struct cpumask *const cpu_online_mask = to_cpumask(cpu_online_bits); +EXPORT_SYMBOL(cpu_online_mask); + +static DECLARE_BITMAP(cpu_present_bits, CONFIG_NR_CPUS) __read_mostly; +const struct cpumask *const cpu_present_mask = to_cpumask(cpu_present_bits); +EXPORT_SYMBOL(cpu_present_mask); + +static DECLARE_BITMAP(cpu_active_bits, CONFIG_NR_CPUS) __read_mostly; +const struct cpumask *const cpu_active_mask = to_cpumask(cpu_active_bits); +EXPORT_SYMBOL(cpu_active_mask); + +void set_cpu_possible(unsigned int cpu, bool possible) +{ + if (possible) + cpumask_set_cpu(cpu, to_cpumask(cpu_possible_bits)); + else + cpumask_clear_cpu(cpu, to_cpumask(cpu_possible_bits)); +} + +void set_cpu_present(unsigned int cpu, bool present) +{ + if (present) + cpumask_set_cpu(cpu, to_cpumask(cpu_present_bits)); + else + cpumask_clear_cpu(cpu, to_cpumask(cpu_present_bits)); +} + +void set_cpu_online(unsigned int cpu, bool online) +{ + if (online) { + cpumask_set_cpu(cpu, to_cpumask(cpu_online_bits)); + cpumask_set_cpu(cpu, to_cpumask(cpu_active_bits)); + } else { + cpumask_clear_cpu(cpu, to_cpumask(cpu_online_bits)); + } +} + +void set_cpu_active(unsigned int cpu, bool active) +{ + if (active) + cpumask_set_cpu(cpu, to_cpumask(cpu_active_bits)); + else + cpumask_clear_cpu(cpu, to_cpumask(cpu_active_bits)); +} + +void init_cpu_present(const struct cpumask *src) +{ + cpumask_copy(to_cpumask(cpu_present_bits), src); +} + +void init_cpu_possible(const struct cpumask *src) +{ + cpumask_copy(to_cpumask(cpu_possible_bits), src); +} + +void init_cpu_online(const struct cpumask *src) +{ + cpumask_copy(to_cpumask(cpu_online_bits), src); +} diff --git a/kernel/kernel/cpu_pm.c b/kernel/kernel/cpu_pm.c new file mode 100644 index 000000000..9656a3c36 --- /dev/null +++ b/kernel/kernel/cpu_pm.c @@ -0,0 +1,233 @@ +/* + * Copyright (C) 2011 Google, Inc. + * + * Author: + * Colin Cross + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + */ + +#include +#include +#include +#include +#include +#include + +static DEFINE_RWLOCK(cpu_pm_notifier_lock); +static RAW_NOTIFIER_HEAD(cpu_pm_notifier_chain); + +static int cpu_pm_notify(enum cpu_pm_event event, int nr_to_call, int *nr_calls) +{ + int ret; + + ret = __raw_notifier_call_chain(&cpu_pm_notifier_chain, event, NULL, + nr_to_call, nr_calls); + + return notifier_to_errno(ret); +} + +/** + * cpu_pm_register_notifier - register a driver with cpu_pm + * @nb: notifier block to register + * + * Add a driver to a list of drivers that are notified about + * CPU and CPU cluster low power entry and exit. + * + * This function may sleep, and has the same return conditions as + * raw_notifier_chain_register. + */ +int cpu_pm_register_notifier(struct notifier_block *nb) +{ + unsigned long flags; + int ret; + + write_lock_irqsave(&cpu_pm_notifier_lock, flags); + ret = raw_notifier_chain_register(&cpu_pm_notifier_chain, nb); + write_unlock_irqrestore(&cpu_pm_notifier_lock, flags); + + return ret; +} +EXPORT_SYMBOL_GPL(cpu_pm_register_notifier); + +/** + * cpu_pm_unregister_notifier - unregister a driver with cpu_pm + * @nb: notifier block to be unregistered + * + * Remove a driver from the CPU PM notifier list. + * + * This function may sleep, and has the same return conditions as + * raw_notifier_chain_unregister. + */ +int cpu_pm_unregister_notifier(struct notifier_block *nb) +{ + unsigned long flags; + int ret; + + write_lock_irqsave(&cpu_pm_notifier_lock, flags); + ret = raw_notifier_chain_unregister(&cpu_pm_notifier_chain, nb); + write_unlock_irqrestore(&cpu_pm_notifier_lock, flags); + + return ret; +} +EXPORT_SYMBOL_GPL(cpu_pm_unregister_notifier); + +/** + * cpu_pm_enter - CPU low power entry notifier + * + * Notifies listeners that a single CPU is entering a low power state that may + * cause some blocks in the same power domain as the cpu to reset. + * + * Must be called on the affected CPU with interrupts disabled. Platform is + * responsible for ensuring that cpu_pm_enter is not called twice on the same + * CPU before cpu_pm_exit is called. Notified drivers can include VFP + * co-processor, interrupt controller and its PM extensions, local CPU + * timers context save/restore which shouldn't be interrupted. Hence it + * must be called with interrupts disabled. + * + * Return conditions are same as __raw_notifier_call_chain. + */ +int cpu_pm_enter(void) +{ + int nr_calls; + int ret = 0; + + read_lock(&cpu_pm_notifier_lock); + ret = cpu_pm_notify(CPU_PM_ENTER, -1, &nr_calls); + if (ret) + /* + * Inform listeners (nr_calls - 1) about failure of CPU PM + * PM entry who are notified earlier to prepare for it. + */ + cpu_pm_notify(CPU_PM_ENTER_FAILED, nr_calls - 1, NULL); + read_unlock(&cpu_pm_notifier_lock); + + return ret; +} +EXPORT_SYMBOL_GPL(cpu_pm_enter); + +/** + * cpu_pm_exit - CPU low power exit notifier + * + * Notifies listeners that a single CPU is exiting a low power state that may + * have caused some blocks in the same power domain as the cpu to reset. + * + * Notified drivers can include VFP co-processor, interrupt controller + * and its PM extensions, local CPU timers context save/restore which + * shouldn't be interrupted. Hence it must be called with interrupts disabled. + * + * Return conditions are same as __raw_notifier_call_chain. + */ +int cpu_pm_exit(void) +{ + int ret; + + read_lock(&cpu_pm_notifier_lock); + ret = cpu_pm_notify(CPU_PM_EXIT, -1, NULL); + read_unlock(&cpu_pm_notifier_lock); + + return ret; +} +EXPORT_SYMBOL_GPL(cpu_pm_exit); + +/** + * cpu_cluster_pm_enter - CPU cluster low power entry notifier + * + * Notifies listeners that all cpus in a power domain are entering a low power + * state that may cause some blocks in the same power domain to reset. + * + * Must be called after cpu_pm_enter has been called on all cpus in the power + * domain, and before cpu_pm_exit has been called on any cpu in the power + * domain. Notified drivers can include VFP co-processor, interrupt controller + * and its PM extensions, local CPU timers context save/restore which + * shouldn't be interrupted. Hence it must be called with interrupts disabled. + * + * Must be called with interrupts disabled. + * + * Return conditions are same as __raw_notifier_call_chain. + */ +int cpu_cluster_pm_enter(void) +{ + int nr_calls; + int ret = 0; + + read_lock(&cpu_pm_notifier_lock); + ret = cpu_pm_notify(CPU_CLUSTER_PM_ENTER, -1, &nr_calls); + if (ret) + /* + * Inform listeners (nr_calls - 1) about failure of CPU cluster + * PM entry who are notified earlier to prepare for it. + */ + cpu_pm_notify(CPU_CLUSTER_PM_ENTER_FAILED, nr_calls - 1, NULL); + read_unlock(&cpu_pm_notifier_lock); + + return ret; +} +EXPORT_SYMBOL_GPL(cpu_cluster_pm_enter); + +/** + * cpu_cluster_pm_exit - CPU cluster low power exit notifier + * + * Notifies listeners that all cpus in a power domain are exiting form a + * low power state that may have caused some blocks in the same power domain + * to reset. + * + * Must be called after cpu_pm_exit has been called on all cpus in the power + * domain, and before cpu_pm_exit has been called on any cpu in the power + * domain. Notified drivers can include VFP co-processor, interrupt controller + * and its PM extensions, local CPU timers context save/restore which + * shouldn't be interrupted. Hence it must be called with interrupts disabled. + * + * Return conditions are same as __raw_notifier_call_chain. + */ +int cpu_cluster_pm_exit(void) +{ + int ret; + + read_lock(&cpu_pm_notifier_lock); + ret = cpu_pm_notify(CPU_CLUSTER_PM_EXIT, -1, NULL); + read_unlock(&cpu_pm_notifier_lock); + + return ret; +} +EXPORT_SYMBOL_GPL(cpu_cluster_pm_exit); + +#ifdef CONFIG_PM +static int cpu_pm_suspend(void) +{ + int ret; + + ret = cpu_pm_enter(); + if (ret) + return ret; + + ret = cpu_cluster_pm_enter(); + return ret; +} + +static void cpu_pm_resume(void) +{ + cpu_cluster_pm_exit(); + cpu_pm_exit(); +} + +static struct syscore_ops cpu_pm_syscore_ops = { + .suspend = cpu_pm_suspend, + .resume = cpu_pm_resume, +}; + +static int cpu_pm_init(void) +{ + register_syscore_ops(&cpu_pm_syscore_ops); + return 0; +} +core_initcall(cpu_pm_init); +#endif diff --git a/kernel/kernel/cpuset.c b/kernel/kernel/cpuset.c new file mode 100644 index 000000000..ee14e3a35 --- /dev/null +++ b/kernel/kernel/cpuset.c @@ -0,0 +1,2700 @@ +/* + * kernel/cpuset.c + * + * Processor and Memory placement constraints for sets of tasks. + * + * Copyright (C) 2003 BULL SA. + * Copyright (C) 2004-2007 Silicon Graphics, Inc. + * Copyright (C) 2006 Google, Inc + * + * Portions derived from Patrick Mochel's sysfs code. + * sysfs is Copyright (c) 2001-3 Patrick Mochel + * + * 2003-10-10 Written by Simon Derr. + * 2003-10-22 Updates by Stephen Hemminger. + * 2004 May-July Rework by Paul Jackson. + * 2006 Rework by Paul Menage to use generic cgroups + * 2008 Rework of the scheduler domains and CPU hotplug handling + * by Max Krasnyansky + * + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file COPYING in the main directory of the Linux + * distribution for more details. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include +#include + +struct static_key cpusets_enabled_key __read_mostly = STATIC_KEY_INIT_FALSE; + +/* See "Frequency meter" comments, below. */ + +struct fmeter { + int cnt; /* unprocessed events count */ + int val; /* most recent output value */ + time_t time; /* clock (secs) when val computed */ + spinlock_t lock; /* guards read or write of above */ +}; + +struct cpuset { + struct cgroup_subsys_state css; + + unsigned long flags; /* "unsigned long" so bitops work */ + + /* + * On default hierarchy: + * + * The user-configured masks can only be changed by writing to + * cpuset.cpus and cpuset.mems, and won't be limited by the + * parent masks. + * + * The effective masks is the real masks that apply to the tasks + * in the cpuset. They may be changed if the configured masks are + * changed or hotplug happens. + * + * effective_mask == configured_mask & parent's effective_mask, + * and if it ends up empty, it will inherit the parent's mask. + * + * + * On legacy hierachy: + * + * The user-configured masks are always the same with effective masks. + */ + + /* user-configured CPUs and Memory Nodes allow to tasks */ + cpumask_var_t cpus_allowed; + nodemask_t mems_allowed; + + /* effective CPUs and Memory Nodes allow to tasks */ + cpumask_var_t effective_cpus; + nodemask_t effective_mems; + + /* + * This is old Memory Nodes tasks took on. + * + * - top_cpuset.old_mems_allowed is initialized to mems_allowed. + * - A new cpuset's old_mems_allowed is initialized when some + * task is moved into it. + * - old_mems_allowed is used in cpuset_migrate_mm() when we change + * cpuset.mems_allowed and have tasks' nodemask updated, and + * then old_mems_allowed is updated to mems_allowed. + */ + nodemask_t old_mems_allowed; + + struct fmeter fmeter; /* memory_pressure filter */ + + /* + * Tasks are being attached to this cpuset. Used to prevent + * zeroing cpus/mems_allowed between ->can_attach() and ->attach(). + */ + int attach_in_progress; + + /* partition number for rebuild_sched_domains() */ + int pn; + + /* for custom sched domain */ + int relax_domain_level; +}; + +static inline struct cpuset *css_cs(struct cgroup_subsys_state *css) +{ + return css ? container_of(css, struct cpuset, css) : NULL; +} + +/* Retrieve the cpuset for a task */ +static inline struct cpuset *task_cs(struct task_struct *task) +{ + return css_cs(task_css(task, cpuset_cgrp_id)); +} + +static inline struct cpuset *parent_cs(struct cpuset *cs) +{ + return css_cs(cs->css.parent); +} + +#ifdef CONFIG_NUMA +static inline bool task_has_mempolicy(struct task_struct *task) +{ + return task->mempolicy; +} +#else +static inline bool task_has_mempolicy(struct task_struct *task) +{ + return false; +} +#endif + + +/* bits in struct cpuset flags field */ +typedef enum { + CS_ONLINE, + CS_CPU_EXCLUSIVE, + CS_MEM_EXCLUSIVE, + CS_MEM_HARDWALL, + CS_MEMORY_MIGRATE, + CS_SCHED_LOAD_BALANCE, + CS_SPREAD_PAGE, + CS_SPREAD_SLAB, +} cpuset_flagbits_t; + +/* convenient tests for these bits */ +static inline bool is_cpuset_online(const struct cpuset *cs) +{ + return test_bit(CS_ONLINE, &cs->flags); +} + +static inline int is_cpu_exclusive(const struct cpuset *cs) +{ + return test_bit(CS_CPU_EXCLUSIVE, &cs->flags); +} + +static inline int is_mem_exclusive(const struct cpuset *cs) +{ + return test_bit(CS_MEM_EXCLUSIVE, &cs->flags); +} + +static inline int is_mem_hardwall(const struct cpuset *cs) +{ + return test_bit(CS_MEM_HARDWALL, &cs->flags); +} + +static inline int is_sched_load_balance(const struct cpuset *cs) +{ + return test_bit(CS_SCHED_LOAD_BALANCE, &cs->flags); +} + +static inline int is_memory_migrate(const struct cpuset *cs) +{ + return test_bit(CS_MEMORY_MIGRATE, &cs->flags); +} + +static inline int is_spread_page(const struct cpuset *cs) +{ + return test_bit(CS_SPREAD_PAGE, &cs->flags); +} + +static inline int is_spread_slab(const struct cpuset *cs) +{ + return test_bit(CS_SPREAD_SLAB, &cs->flags); +} + +static struct cpuset top_cpuset = { + .flags = ((1 << CS_ONLINE) | (1 << CS_CPU_EXCLUSIVE) | + (1 << CS_MEM_EXCLUSIVE)), +}; + +/** + * cpuset_for_each_child - traverse online children of a cpuset + * @child_cs: loop cursor pointing to the current child + * @pos_css: used for iteration + * @parent_cs: target cpuset to walk children of + * + * Walk @child_cs through the online children of @parent_cs. Must be used + * with RCU read locked. + */ +#define cpuset_for_each_child(child_cs, pos_css, parent_cs) \ + css_for_each_child((pos_css), &(parent_cs)->css) \ + if (is_cpuset_online(((child_cs) = css_cs((pos_css))))) + +/** + * cpuset_for_each_descendant_pre - pre-order walk of a cpuset's descendants + * @des_cs: loop cursor pointing to the current descendant + * @pos_css: used for iteration + * @root_cs: target cpuset to walk ancestor of + * + * Walk @des_cs through the online descendants of @root_cs. Must be used + * with RCU read locked. The caller may modify @pos_css by calling + * css_rightmost_descendant() to skip subtree. @root_cs is included in the + * iteration and the first node to be visited. + */ +#define cpuset_for_each_descendant_pre(des_cs, pos_css, root_cs) \ + css_for_each_descendant_pre((pos_css), &(root_cs)->css) \ + if (is_cpuset_online(((des_cs) = css_cs((pos_css))))) + +/* + * There are two global locks guarding cpuset structures - cpuset_mutex and + * callback_lock. We also require taking task_lock() when dereferencing a + * task's cpuset pointer. See "The task_lock() exception", at the end of this + * comment. + * + * A task must hold both locks to modify cpusets. If a task holds + * cpuset_mutex, then it blocks others wanting that mutex, ensuring that it + * is the only task able to also acquire callback_lock and be able to + * modify cpusets. It can perform various checks on the cpuset structure + * first, knowing nothing will change. It can also allocate memory while + * just holding cpuset_mutex. While it is performing these checks, various + * callback routines can briefly acquire callback_lock to query cpusets. + * Once it is ready to make the changes, it takes callback_lock, blocking + * everyone else. + * + * Calls to the kernel memory allocator can not be made while holding + * callback_lock, as that would risk double tripping on callback_lock + * from one of the callbacks into the cpuset code from within + * __alloc_pages(). + * + * If a task is only holding callback_lock, then it has read-only + * access to cpusets. + * + * Now, the task_struct fields mems_allowed and mempolicy may be changed + * by other task, we use alloc_lock in the task_struct fields to protect + * them. + * + * The cpuset_common_file_read() handlers only hold callback_lock across + * small pieces of code, such as when reading out possibly multi-word + * cpumasks and nodemasks. + * + * Accessing a task's cpuset should be done in accordance with the + * guidelines for accessing subsystem state in kernel/cgroup.c + */ + +static DEFINE_MUTEX(cpuset_mutex); +static DEFINE_SPINLOCK(callback_lock); + +/* + * CPU / memory hotplug is handled asynchronously. + */ +static void cpuset_hotplug_workfn(struct work_struct *work); +static DECLARE_WORK(cpuset_hotplug_work, cpuset_hotplug_workfn); + +static DECLARE_WAIT_QUEUE_HEAD(cpuset_attach_wq); + +/* + * This is ugly, but preserves the userspace API for existing cpuset + * users. If someone tries to mount the "cpuset" filesystem, we + * silently switch it to mount "cgroup" instead + */ +static struct dentry *cpuset_mount(struct file_system_type *fs_type, + int flags, const char *unused_dev_name, void *data) +{ + struct file_system_type *cgroup_fs = get_fs_type("cgroup"); + struct dentry *ret = ERR_PTR(-ENODEV); + if (cgroup_fs) { + char mountopts[] = + "cpuset,noprefix," + "release_agent=/sbin/cpuset_release_agent"; + ret = cgroup_fs->mount(cgroup_fs, flags, + unused_dev_name, mountopts); + put_filesystem(cgroup_fs); + } + return ret; +} + +static struct file_system_type cpuset_fs_type = { + .name = "cpuset", + .mount = cpuset_mount, +}; + +/* + * Return in pmask the portion of a cpusets's cpus_allowed that + * are online. If none are online, walk up the cpuset hierarchy + * until we find one that does have some online cpus. The top + * cpuset always has some cpus online. + * + * One way or another, we guarantee to return some non-empty subset + * of cpu_online_mask. + * + * Call with callback_lock or cpuset_mutex held. + */ +static void guarantee_online_cpus(struct cpuset *cs, struct cpumask *pmask) +{ + while (!cpumask_intersects(cs->effective_cpus, cpu_online_mask)) + cs = parent_cs(cs); + cpumask_and(pmask, cs->effective_cpus, cpu_online_mask); +} + +/* + * Return in *pmask the portion of a cpusets's mems_allowed that + * are online, with memory. If none are online with memory, walk + * up the cpuset hierarchy until we find one that does have some + * online mems. The top cpuset always has some mems online. + * + * One way or another, we guarantee to return some non-empty subset + * of node_states[N_MEMORY]. + * + * Call with callback_lock or cpuset_mutex held. + */ +static void guarantee_online_mems(struct cpuset *cs, nodemask_t *pmask) +{ + while (!nodes_intersects(cs->effective_mems, node_states[N_MEMORY])) + cs = parent_cs(cs); + nodes_and(*pmask, cs->effective_mems, node_states[N_MEMORY]); +} + +/* + * update task's spread flag if cpuset's page/slab spread flag is set + * + * Call with callback_lock or cpuset_mutex held. + */ +static void cpuset_update_task_spread_flag(struct cpuset *cs, + struct task_struct *tsk) +{ + if (is_spread_page(cs)) + task_set_spread_page(tsk); + else + task_clear_spread_page(tsk); + + if (is_spread_slab(cs)) + task_set_spread_slab(tsk); + else + task_clear_spread_slab(tsk); +} + +/* + * is_cpuset_subset(p, q) - Is cpuset p a subset of cpuset q? + * + * One cpuset is a subset of another if all its allowed CPUs and + * Memory Nodes are a subset of the other, and its exclusive flags + * are only set if the other's are set. Call holding cpuset_mutex. + */ + +static int is_cpuset_subset(const struct cpuset *p, const struct cpuset *q) +{ + return cpumask_subset(p->cpus_allowed, q->cpus_allowed) && + nodes_subset(p->mems_allowed, q->mems_allowed) && + is_cpu_exclusive(p) <= is_cpu_exclusive(q) && + is_mem_exclusive(p) <= is_mem_exclusive(q); +} + +/** + * alloc_trial_cpuset - allocate a trial cpuset + * @cs: the cpuset that the trial cpuset duplicates + */ +static struct cpuset *alloc_trial_cpuset(struct cpuset *cs) +{ + struct cpuset *trial; + + trial = kmemdup(cs, sizeof(*cs), GFP_KERNEL); + if (!trial) + return NULL; + + if (!alloc_cpumask_var(&trial->cpus_allowed, GFP_KERNEL)) + goto free_cs; + if (!alloc_cpumask_var(&trial->effective_cpus, GFP_KERNEL)) + goto free_cpus; + + cpumask_copy(trial->cpus_allowed, cs->cpus_allowed); + cpumask_copy(trial->effective_cpus, cs->effective_cpus); + return trial; + +free_cpus: + free_cpumask_var(trial->cpus_allowed); +free_cs: + kfree(trial); + return NULL; +} + +/** + * free_trial_cpuset - free the trial cpuset + * @trial: the trial cpuset to be freed + */ +static void free_trial_cpuset(struct cpuset *trial) +{ + free_cpumask_var(trial->effective_cpus); + free_cpumask_var(trial->cpus_allowed); + kfree(trial); +} + +/* + * validate_change() - Used to validate that any proposed cpuset change + * follows the structural rules for cpusets. + * + * If we replaced the flag and mask values of the current cpuset + * (cur) with those values in the trial cpuset (trial), would + * our various subset and exclusive rules still be valid? Presumes + * cpuset_mutex held. + * + * 'cur' is the address of an actual, in-use cpuset. Operations + * such as list traversal that depend on the actual address of the + * cpuset in the list must use cur below, not trial. + * + * 'trial' is the address of bulk structure copy of cur, with + * perhaps one or more of the fields cpus_allowed, mems_allowed, + * or flags changed to new, trial values. + * + * Return 0 if valid, -errno if not. + */ + +static int validate_change(struct cpuset *cur, struct cpuset *trial) +{ + struct cgroup_subsys_state *css; + struct cpuset *c, *par; + int ret; + + rcu_read_lock(); + + /* Each of our child cpusets must be a subset of us */ + ret = -EBUSY; + cpuset_for_each_child(c, css, cur) + if (!is_cpuset_subset(c, trial)) + goto out; + + /* Remaining checks don't apply to root cpuset */ + ret = 0; + if (cur == &top_cpuset) + goto out; + + par = parent_cs(cur); + + /* On legacy hiearchy, we must be a subset of our parent cpuset. */ + ret = -EACCES; + if (!cgroup_on_dfl(cur->css.cgroup) && !is_cpuset_subset(trial, par)) + goto out; + + /* + * If either I or some sibling (!= me) is exclusive, we can't + * overlap + */ + ret = -EINVAL; + cpuset_for_each_child(c, css, par) { + if ((is_cpu_exclusive(trial) || is_cpu_exclusive(c)) && + c != cur && + cpumask_intersects(trial->cpus_allowed, c->cpus_allowed)) + goto out; + if ((is_mem_exclusive(trial) || is_mem_exclusive(c)) && + c != cur && + nodes_intersects(trial->mems_allowed, c->mems_allowed)) + goto out; + } + + /* + * Cpusets with tasks - existing or newly being attached - can't + * be changed to have empty cpus_allowed or mems_allowed. + */ + ret = -ENOSPC; + if ((cgroup_has_tasks(cur->css.cgroup) || cur->attach_in_progress)) { + if (!cpumask_empty(cur->cpus_allowed) && + cpumask_empty(trial->cpus_allowed)) + goto out; + if (!nodes_empty(cur->mems_allowed) && + nodes_empty(trial->mems_allowed)) + goto out; + } + + /* + * We can't shrink if we won't have enough room for SCHED_DEADLINE + * tasks. + */ + ret = -EBUSY; + if (is_cpu_exclusive(cur) && + !cpuset_cpumask_can_shrink(cur->cpus_allowed, + trial->cpus_allowed)) + goto out; + + ret = 0; +out: + rcu_read_unlock(); + return ret; +} + +#ifdef CONFIG_SMP +/* + * Helper routine for generate_sched_domains(). + * Do cpusets a, b have overlapping effective cpus_allowed masks? + */ +static int cpusets_overlap(struct cpuset *a, struct cpuset *b) +{ + return cpumask_intersects(a->effective_cpus, b->effective_cpus); +} + +static void +update_domain_attr(struct sched_domain_attr *dattr, struct cpuset *c) +{ + if (dattr->relax_domain_level < c->relax_domain_level) + dattr->relax_domain_level = c->relax_domain_level; + return; +} + +static void update_domain_attr_tree(struct sched_domain_attr *dattr, + struct cpuset *root_cs) +{ + struct cpuset *cp; + struct cgroup_subsys_state *pos_css; + + rcu_read_lock(); + cpuset_for_each_descendant_pre(cp, pos_css, root_cs) { + /* skip the whole subtree if @cp doesn't have any CPU */ + if (cpumask_empty(cp->cpus_allowed)) { + pos_css = css_rightmost_descendant(pos_css); + continue; + } + + if (is_sched_load_balance(cp)) + update_domain_attr(dattr, cp); + } + rcu_read_unlock(); +} + +/* + * generate_sched_domains() + * + * This function builds a partial partition of the systems CPUs + * A 'partial partition' is a set of non-overlapping subsets whose + * union is a subset of that set. + * The output of this function needs to be passed to kernel/sched/core.c + * partition_sched_domains() routine, which will rebuild the scheduler's + * load balancing domains (sched domains) as specified by that partial + * partition. + * + * See "What is sched_load_balance" in Documentation/cgroups/cpusets.txt + * for a background explanation of this. + * + * Does not return errors, on the theory that the callers of this + * routine would rather not worry about failures to rebuild sched + * domains when operating in the severe memory shortage situations + * that could cause allocation failures below. + * + * Must be called with cpuset_mutex held. + * + * The three key local variables below are: + * q - a linked-list queue of cpuset pointers, used to implement a + * top-down scan of all cpusets. This scan loads a pointer + * to each cpuset marked is_sched_load_balance into the + * array 'csa'. For our purposes, rebuilding the schedulers + * sched domains, we can ignore !is_sched_load_balance cpusets. + * csa - (for CpuSet Array) Array of pointers to all the cpusets + * that need to be load balanced, for convenient iterative + * access by the subsequent code that finds the best partition, + * i.e the set of domains (subsets) of CPUs such that the + * cpus_allowed of every cpuset marked is_sched_load_balance + * is a subset of one of these domains, while there are as + * many such domains as possible, each as small as possible. + * doms - Conversion of 'csa' to an array of cpumasks, for passing to + * the kernel/sched/core.c routine partition_sched_domains() in a + * convenient format, that can be easily compared to the prior + * value to determine what partition elements (sched domains) + * were changed (added or removed.) + * + * Finding the best partition (set of domains): + * The triple nested loops below over i, j, k scan over the + * load balanced cpusets (using the array of cpuset pointers in + * csa[]) looking for pairs of cpusets that have overlapping + * cpus_allowed, but which don't have the same 'pn' partition + * number and gives them in the same partition number. It keeps + * looping on the 'restart' label until it can no longer find + * any such pairs. + * + * The union of the cpus_allowed masks from the set of + * all cpusets having the same 'pn' value then form the one + * element of the partition (one sched domain) to be passed to + * partition_sched_domains(). + */ +static int generate_sched_domains(cpumask_var_t **domains, + struct sched_domain_attr **attributes) +{ + struct cpuset *cp; /* scans q */ + struct cpuset **csa; /* array of all cpuset ptrs */ + int csn; /* how many cpuset ptrs in csa so far */ + int i, j, k; /* indices for partition finding loops */ + cpumask_var_t *doms; /* resulting partition; i.e. sched domains */ + cpumask_var_t non_isolated_cpus; /* load balanced CPUs */ + struct sched_domain_attr *dattr; /* attributes for custom domains */ + int ndoms = 0; /* number of sched domains in result */ + int nslot; /* next empty doms[] struct cpumask slot */ + struct cgroup_subsys_state *pos_css; + + doms = NULL; + dattr = NULL; + csa = NULL; + + if (!alloc_cpumask_var(&non_isolated_cpus, GFP_KERNEL)) + goto done; + cpumask_andnot(non_isolated_cpus, cpu_possible_mask, cpu_isolated_map); + + /* Special case for the 99% of systems with one, full, sched domain */ + if (is_sched_load_balance(&top_cpuset)) { + ndoms = 1; + doms = alloc_sched_domains(ndoms); + if (!doms) + goto done; + + dattr = kmalloc(sizeof(struct sched_domain_attr), GFP_KERNEL); + if (dattr) { + *dattr = SD_ATTR_INIT; + update_domain_attr_tree(dattr, &top_cpuset); + } + cpumask_and(doms[0], top_cpuset.effective_cpus, + non_isolated_cpus); + + goto done; + } + + csa = kmalloc(nr_cpusets() * sizeof(cp), GFP_KERNEL); + if (!csa) + goto done; + csn = 0; + + rcu_read_lock(); + cpuset_for_each_descendant_pre(cp, pos_css, &top_cpuset) { + if (cp == &top_cpuset) + continue; + /* + * Continue traversing beyond @cp iff @cp has some CPUs and + * isn't load balancing. The former is obvious. The + * latter: All child cpusets contain a subset of the + * parent's cpus, so just skip them, and then we call + * update_domain_attr_tree() to calc relax_domain_level of + * the corresponding sched domain. + */ + if (!cpumask_empty(cp->cpus_allowed) && + !(is_sched_load_balance(cp) && + cpumask_intersects(cp->cpus_allowed, non_isolated_cpus))) + continue; + + if (is_sched_load_balance(cp)) + csa[csn++] = cp; + + /* skip @cp's subtree */ + pos_css = css_rightmost_descendant(pos_css); + } + rcu_read_unlock(); + + for (i = 0; i < csn; i++) + csa[i]->pn = i; + ndoms = csn; + +restart: + /* Find the best partition (set of sched domains) */ + for (i = 0; i < csn; i++) { + struct cpuset *a = csa[i]; + int apn = a->pn; + + for (j = 0; j < csn; j++) { + struct cpuset *b = csa[j]; + int bpn = b->pn; + + if (apn != bpn && cpusets_overlap(a, b)) { + for (k = 0; k < csn; k++) { + struct cpuset *c = csa[k]; + + if (c->pn == bpn) + c->pn = apn; + } + ndoms--; /* one less element */ + goto restart; + } + } + } + + /* + * Now we know how many domains to create. + * Convert to and populate cpu masks. + */ + doms = alloc_sched_domains(ndoms); + if (!doms) + goto done; + + /* + * The rest of the code, including the scheduler, can deal with + * dattr==NULL case. No need to abort if alloc fails. + */ + dattr = kmalloc(ndoms * sizeof(struct sched_domain_attr), GFP_KERNEL); + + for (nslot = 0, i = 0; i < csn; i++) { + struct cpuset *a = csa[i]; + struct cpumask *dp; + int apn = a->pn; + + if (apn < 0) { + /* Skip completed partitions */ + continue; + } + + dp = doms[nslot]; + + if (nslot == ndoms) { + static int warnings = 10; + if (warnings) { + pr_warn("rebuild_sched_domains confused: nslot %d, ndoms %d, csn %d, i %d, apn %d\n", + nslot, ndoms, csn, i, apn); + warnings--; + } + continue; + } + + cpumask_clear(dp); + if (dattr) + *(dattr + nslot) = SD_ATTR_INIT; + for (j = i; j < csn; j++) { + struct cpuset *b = csa[j]; + + if (apn == b->pn) { + cpumask_or(dp, dp, b->effective_cpus); + cpumask_and(dp, dp, non_isolated_cpus); + if (dattr) + update_domain_attr_tree(dattr + nslot, b); + + /* Done with this partition */ + b->pn = -1; + } + } + nslot++; + } + BUG_ON(nslot != ndoms); + +done: + free_cpumask_var(non_isolated_cpus); + kfree(csa); + + /* + * Fallback to the default domain if kmalloc() failed. + * See comments in partition_sched_domains(). + */ + if (doms == NULL) + ndoms = 1; + + *domains = doms; + *attributes = dattr; + return ndoms; +} + +/* + * Rebuild scheduler domains. + * + * If the flag 'sched_load_balance' of any cpuset with non-empty + * 'cpus' changes, or if the 'cpus' allowed changes in any cpuset + * which has that flag enabled, or if any cpuset with a non-empty + * 'cpus' is removed, then call this routine to rebuild the + * scheduler's dynamic sched domains. + * + * Call with cpuset_mutex held. Takes get_online_cpus(). + */ +static void rebuild_sched_domains_locked(void) +{ + struct sched_domain_attr *attr; + cpumask_var_t *doms; + int ndoms; + + lockdep_assert_held(&cpuset_mutex); + get_online_cpus(); + + /* + * We have raced with CPU hotplug. Don't do anything to avoid + * passing doms with offlined cpu to partition_sched_domains(). + * Anyways, hotplug work item will rebuild sched domains. + */ + if (!cpumask_equal(top_cpuset.effective_cpus, cpu_active_mask)) + goto out; + + /* Generate domain masks and attrs */ + ndoms = generate_sched_domains(&doms, &attr); + + /* Have scheduler rebuild the domains */ + partition_sched_domains(ndoms, doms, attr); +out: + put_online_cpus(); +} +#else /* !CONFIG_SMP */ +static void rebuild_sched_domains_locked(void) +{ +} +#endif /* CONFIG_SMP */ + +void rebuild_sched_domains(void) +{ + mutex_lock(&cpuset_mutex); + rebuild_sched_domains_locked(); + mutex_unlock(&cpuset_mutex); +} + +/** + * update_tasks_cpumask - Update the cpumasks of tasks in the cpuset. + * @cs: the cpuset in which each task's cpus_allowed mask needs to be changed + * + * Iterate through each task of @cs updating its cpus_allowed to the + * effective cpuset's. As this function is called with cpuset_mutex held, + * cpuset membership stays stable. + */ +static void update_tasks_cpumask(struct cpuset *cs) +{ + struct css_task_iter it; + struct task_struct *task; + + css_task_iter_start(&cs->css, &it); + while ((task = css_task_iter_next(&it))) + set_cpus_allowed_ptr(task, cs->effective_cpus); + css_task_iter_end(&it); +} + +/* + * update_cpumasks_hier - Update effective cpumasks and tasks in the subtree + * @cs: the cpuset to consider + * @new_cpus: temp variable for calculating new effective_cpus + * + * When congifured cpumask is changed, the effective cpumasks of this cpuset + * and all its descendants need to be updated. + * + * On legacy hierachy, effective_cpus will be the same with cpu_allowed. + * + * Called with cpuset_mutex held + */ +static void update_cpumasks_hier(struct cpuset *cs, struct cpumask *new_cpus) +{ + struct cpuset *cp; + struct cgroup_subsys_state *pos_css; + bool need_rebuild_sched_domains = false; + + rcu_read_lock(); + cpuset_for_each_descendant_pre(cp, pos_css, cs) { + struct cpuset *parent = parent_cs(cp); + + cpumask_and(new_cpus, cp->cpus_allowed, parent->effective_cpus); + + /* + * If it becomes empty, inherit the effective mask of the + * parent, which is guaranteed to have some CPUs. + */ + if (cgroup_on_dfl(cp->css.cgroup) && cpumask_empty(new_cpus)) + cpumask_copy(new_cpus, parent->effective_cpus); + + /* Skip the whole subtree if the cpumask remains the same. */ + if (cpumask_equal(new_cpus, cp->effective_cpus)) { + pos_css = css_rightmost_descendant(pos_css); + continue; + } + + if (!css_tryget_online(&cp->css)) + continue; + rcu_read_unlock(); + + spin_lock_irq(&callback_lock); + cpumask_copy(cp->effective_cpus, new_cpus); + spin_unlock_irq(&callback_lock); + + WARN_ON(!cgroup_on_dfl(cp->css.cgroup) && + !cpumask_equal(cp->cpus_allowed, cp->effective_cpus)); + + update_tasks_cpumask(cp); + + /* + * If the effective cpumask of any non-empty cpuset is changed, + * we need to rebuild sched domains. + */ + if (!cpumask_empty(cp->cpus_allowed) && + is_sched_load_balance(cp)) + need_rebuild_sched_domains = true; + + rcu_read_lock(); + css_put(&cp->css); + } + rcu_read_unlock(); + + if (need_rebuild_sched_domains) + rebuild_sched_domains_locked(); +} + +/** + * update_cpumask - update the cpus_allowed mask of a cpuset and all tasks in it + * @cs: the cpuset to consider + * @trialcs: trial cpuset + * @buf: buffer of cpu numbers written to this cpuset + */ +static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs, + const char *buf) +{ + int retval; + + /* top_cpuset.cpus_allowed tracks cpu_online_mask; it's read-only */ + if (cs == &top_cpuset) + return -EACCES; + + /* + * An empty cpus_allowed is ok only if the cpuset has no tasks. + * Since cpulist_parse() fails on an empty mask, we special case + * that parsing. The validate_change() call ensures that cpusets + * with tasks have cpus. + */ + if (!*buf) { + cpumask_clear(trialcs->cpus_allowed); + } else { + retval = cpulist_parse(buf, trialcs->cpus_allowed); + if (retval < 0) + return retval; + + if (!cpumask_subset(trialcs->cpus_allowed, + top_cpuset.cpus_allowed)) + return -EINVAL; + } + + /* Nothing to do if the cpus didn't change */ + if (cpumask_equal(cs->cpus_allowed, trialcs->cpus_allowed)) + return 0; + + retval = validate_change(cs, trialcs); + if (retval < 0) + return retval; + + spin_lock_irq(&callback_lock); + cpumask_copy(cs->cpus_allowed, trialcs->cpus_allowed); + spin_unlock_irq(&callback_lock); + + /* use trialcs->cpus_allowed as a temp variable */ + update_cpumasks_hier(cs, trialcs->cpus_allowed); + return 0; +} + +/* + * cpuset_migrate_mm + * + * Migrate memory region from one set of nodes to another. + * + * Temporarilly set tasks mems_allowed to target nodes of migration, + * so that the migration code can allocate pages on these nodes. + * + * While the mm_struct we are migrating is typically from some + * other task, the task_struct mems_allowed that we are hacking + * is for our current task, which must allocate new pages for that + * migrating memory region. + */ + +static void cpuset_migrate_mm(struct mm_struct *mm, const nodemask_t *from, + const nodemask_t *to) +{ + struct task_struct *tsk = current; + + tsk->mems_allowed = *to; + + do_migrate_pages(mm, from, to, MPOL_MF_MOVE_ALL); + + rcu_read_lock(); + guarantee_online_mems(task_cs(tsk), &tsk->mems_allowed); + rcu_read_unlock(); +} + +/* + * cpuset_change_task_nodemask - change task's mems_allowed and mempolicy + * @tsk: the task to change + * @newmems: new nodes that the task will be set + * + * In order to avoid seeing no nodes if the old and new nodes are disjoint, + * we structure updates as setting all new allowed nodes, then clearing newly + * disallowed ones. + */ +static void cpuset_change_task_nodemask(struct task_struct *tsk, + nodemask_t *newmems) +{ + bool need_loop; + + /* + * Allow tasks that have access to memory reserves because they have + * been OOM killed to get memory anywhere. + */ + if (unlikely(test_thread_flag(TIF_MEMDIE))) + return; + if (current->flags & PF_EXITING) /* Let dying task have memory */ + return; + + task_lock(tsk); + /* + * Determine if a loop is necessary if another thread is doing + * read_mems_allowed_begin(). If at least one node remains unchanged and + * tsk does not have a mempolicy, then an empty nodemask will not be + * possible when mems_allowed is larger than a word. + */ + need_loop = task_has_mempolicy(tsk) || + !nodes_intersects(*newmems, tsk->mems_allowed); + + if (need_loop) { + local_irq_disable(); + write_seqcount_begin(&tsk->mems_allowed_seq); + } + + nodes_or(tsk->mems_allowed, tsk->mems_allowed, *newmems); + mpol_rebind_task(tsk, newmems, MPOL_REBIND_STEP1); + + mpol_rebind_task(tsk, newmems, MPOL_REBIND_STEP2); + tsk->mems_allowed = *newmems; + + if (need_loop) { + write_seqcount_end(&tsk->mems_allowed_seq); + local_irq_enable(); + } + + task_unlock(tsk); +} + +static void *cpuset_being_rebound; + +/** + * update_tasks_nodemask - Update the nodemasks of tasks in the cpuset. + * @cs: the cpuset in which each task's mems_allowed mask needs to be changed + * + * Iterate through each task of @cs updating its mems_allowed to the + * effective cpuset's. As this function is called with cpuset_mutex held, + * cpuset membership stays stable. + */ +static void update_tasks_nodemask(struct cpuset *cs) +{ + static nodemask_t newmems; /* protected by cpuset_mutex */ + struct css_task_iter it; + struct task_struct *task; + + cpuset_being_rebound = cs; /* causes mpol_dup() rebind */ + + guarantee_online_mems(cs, &newmems); + + /* + * The mpol_rebind_mm() call takes mmap_sem, which we couldn't + * take while holding tasklist_lock. Forks can happen - the + * mpol_dup() cpuset_being_rebound check will catch such forks, + * and rebind their vma mempolicies too. Because we still hold + * the global cpuset_mutex, we know that no other rebind effort + * will be contending for the global variable cpuset_being_rebound. + * It's ok if we rebind the same mm twice; mpol_rebind_mm() + * is idempotent. Also migrate pages in each mm to new nodes. + */ + css_task_iter_start(&cs->css, &it); + while ((task = css_task_iter_next(&it))) { + struct mm_struct *mm; + bool migrate; + + cpuset_change_task_nodemask(task, &newmems); + + mm = get_task_mm(task); + if (!mm) + continue; + + migrate = is_memory_migrate(cs); + + mpol_rebind_mm(mm, &cs->mems_allowed); + if (migrate) + cpuset_migrate_mm(mm, &cs->old_mems_allowed, &newmems); + mmput(mm); + } + css_task_iter_end(&it); + + /* + * All the tasks' nodemasks have been updated, update + * cs->old_mems_allowed. + */ + cs->old_mems_allowed = newmems; + + /* We're done rebinding vmas to this cpuset's new mems_allowed. */ + cpuset_being_rebound = NULL; +} + +/* + * update_nodemasks_hier - Update effective nodemasks and tasks in the subtree + * @cs: the cpuset to consider + * @new_mems: a temp variable for calculating new effective_mems + * + * When configured nodemask is changed, the effective nodemasks of this cpuset + * and all its descendants need to be updated. + * + * On legacy hiearchy, effective_mems will be the same with mems_allowed. + * + * Called with cpuset_mutex held + */ +static void update_nodemasks_hier(struct cpuset *cs, nodemask_t *new_mems) +{ + struct cpuset *cp; + struct cgroup_subsys_state *pos_css; + + rcu_read_lock(); + cpuset_for_each_descendant_pre(cp, pos_css, cs) { + struct cpuset *parent = parent_cs(cp); + + nodes_and(*new_mems, cp->mems_allowed, parent->effective_mems); + + /* + * If it becomes empty, inherit the effective mask of the + * parent, which is guaranteed to have some MEMs. + */ + if (cgroup_on_dfl(cp->css.cgroup) && nodes_empty(*new_mems)) + *new_mems = parent->effective_mems; + + /* Skip the whole subtree if the nodemask remains the same. */ + if (nodes_equal(*new_mems, cp->effective_mems)) { + pos_css = css_rightmost_descendant(pos_css); + continue; + } + + if (!css_tryget_online(&cp->css)) + continue; + rcu_read_unlock(); + + spin_lock_irq(&callback_lock); + cp->effective_mems = *new_mems; + spin_unlock_irq(&callback_lock); + + WARN_ON(!cgroup_on_dfl(cp->css.cgroup) && + !nodes_equal(cp->mems_allowed, cp->effective_mems)); + + update_tasks_nodemask(cp); + + rcu_read_lock(); + css_put(&cp->css); + } + rcu_read_unlock(); +} + +/* + * Handle user request to change the 'mems' memory placement + * of a cpuset. Needs to validate the request, update the + * cpusets mems_allowed, and for each task in the cpuset, + * update mems_allowed and rebind task's mempolicy and any vma + * mempolicies and if the cpuset is marked 'memory_migrate', + * migrate the tasks pages to the new memory. + * + * Call with cpuset_mutex held. May take callback_lock during call. + * Will take tasklist_lock, scan tasklist for tasks in cpuset cs, + * lock each such tasks mm->mmap_sem, scan its vma's and rebind + * their mempolicies to the cpusets new mems_allowed. + */ +static int update_nodemask(struct cpuset *cs, struct cpuset *trialcs, + const char *buf) +{ + int retval; + + /* + * top_cpuset.mems_allowed tracks node_stats[N_MEMORY]; + * it's read-only + */ + if (cs == &top_cpuset) { + retval = -EACCES; + goto done; + } + + /* + * An empty mems_allowed is ok iff there are no tasks in the cpuset. + * Since nodelist_parse() fails on an empty mask, we special case + * that parsing. The validate_change() call ensures that cpusets + * with tasks have memory. + */ + if (!*buf) { + nodes_clear(trialcs->mems_allowed); + } else { + retval = nodelist_parse(buf, trialcs->mems_allowed); + if (retval < 0) + goto done; + + if (!nodes_subset(trialcs->mems_allowed, + top_cpuset.mems_allowed)) { + retval = -EINVAL; + goto done; + } + } + + if (nodes_equal(cs->mems_allowed, trialcs->mems_allowed)) { + retval = 0; /* Too easy - nothing to do */ + goto done; + } + retval = validate_change(cs, trialcs); + if (retval < 0) + goto done; + + spin_lock_irq(&callback_lock); + cs->mems_allowed = trialcs->mems_allowed; + spin_unlock_irq(&callback_lock); + + /* use trialcs->mems_allowed as a temp variable */ + update_nodemasks_hier(cs, &cs->mems_allowed); +done: + return retval; +} + +int current_cpuset_is_being_rebound(void) +{ + int ret; + + rcu_read_lock(); + ret = task_cs(current) == cpuset_being_rebound; + rcu_read_unlock(); + + return ret; +} + +static int update_relax_domain_level(struct cpuset *cs, s64 val) +{ +#ifdef CONFIG_SMP + if (val < -1 || val >= sched_domain_level_max) + return -EINVAL; +#endif + + if (val != cs->relax_domain_level) { + cs->relax_domain_level = val; + if (!cpumask_empty(cs->cpus_allowed) && + is_sched_load_balance(cs)) + rebuild_sched_domains_locked(); + } + + return 0; +} + +/** + * update_tasks_flags - update the spread flags of tasks in the cpuset. + * @cs: the cpuset in which each task's spread flags needs to be changed + * + * Iterate through each task of @cs updating its spread flags. As this + * function is called with cpuset_mutex held, cpuset membership stays + * stable. + */ +static void update_tasks_flags(struct cpuset *cs) +{ + struct css_task_iter it; + struct task_struct *task; + + css_task_iter_start(&cs->css, &it); + while ((task = css_task_iter_next(&it))) + cpuset_update_task_spread_flag(cs, task); + css_task_iter_end(&it); +} + +/* + * update_flag - read a 0 or a 1 in a file and update associated flag + * bit: the bit to update (see cpuset_flagbits_t) + * cs: the cpuset to update + * turning_on: whether the flag is being set or cleared + * + * Call with cpuset_mutex held. + */ + +static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs, + int turning_on) +{ + struct cpuset *trialcs; + int balance_flag_changed; + int spread_flag_changed; + int err; + + trialcs = alloc_trial_cpuset(cs); + if (!trialcs) + return -ENOMEM; + + if (turning_on) + set_bit(bit, &trialcs->flags); + else + clear_bit(bit, &trialcs->flags); + + err = validate_change(cs, trialcs); + if (err < 0) + goto out; + + balance_flag_changed = (is_sched_load_balance(cs) != + is_sched_load_balance(trialcs)); + + spread_flag_changed = ((is_spread_slab(cs) != is_spread_slab(trialcs)) + || (is_spread_page(cs) != is_spread_page(trialcs))); + + spin_lock_irq(&callback_lock); + cs->flags = trialcs->flags; + spin_unlock_irq(&callback_lock); + + if (!cpumask_empty(trialcs->cpus_allowed) && balance_flag_changed) + rebuild_sched_domains_locked(); + + if (spread_flag_changed) + update_tasks_flags(cs); +out: + free_trial_cpuset(trialcs); + return err; +} + +/* + * Frequency meter - How fast is some event occurring? + * + * These routines manage a digitally filtered, constant time based, + * event frequency meter. There are four routines: + * fmeter_init() - initialize a frequency meter. + * fmeter_markevent() - called each time the event happens. + * fmeter_getrate() - returns the recent rate of such events. + * fmeter_update() - internal routine used to update fmeter. + * + * A common data structure is passed to each of these routines, + * which is used to keep track of the state required to manage the + * frequency meter and its digital filter. + * + * The filter works on the number of events marked per unit time. + * The filter is single-pole low-pass recursive (IIR). The time unit + * is 1 second. Arithmetic is done using 32-bit integers scaled to + * simulate 3 decimal digits of precision (multiplied by 1000). + * + * With an FM_COEF of 933, and a time base of 1 second, the filter + * has a half-life of 10 seconds, meaning that if the events quit + * happening, then the rate returned from the fmeter_getrate() + * will be cut in half each 10 seconds, until it converges to zero. + * + * It is not worth doing a real infinitely recursive filter. If more + * than FM_MAXTICKS ticks have elapsed since the last filter event, + * just compute FM_MAXTICKS ticks worth, by which point the level + * will be stable. + * + * Limit the count of unprocessed events to FM_MAXCNT, so as to avoid + * arithmetic overflow in the fmeter_update() routine. + * + * Given the simple 32 bit integer arithmetic used, this meter works + * best for reporting rates between one per millisecond (msec) and + * one per 32 (approx) seconds. At constant rates faster than one + * per msec it maxes out at values just under 1,000,000. At constant + * rates between one per msec, and one per second it will stabilize + * to a value N*1000, where N is the rate of events per second. + * At constant rates between one per second and one per 32 seconds, + * it will be choppy, moving up on the seconds that have an event, + * and then decaying until the next event. At rates slower than + * about one in 32 seconds, it decays all the way back to zero between + * each event. + */ + +#define FM_COEF 933 /* coefficient for half-life of 10 secs */ +#define FM_MAXTICKS ((time_t)99) /* useless computing more ticks than this */ +#define FM_MAXCNT 1000000 /* limit cnt to avoid overflow */ +#define FM_SCALE 1000 /* faux fixed point scale */ + +/* Initialize a frequency meter */ +static void fmeter_init(struct fmeter *fmp) +{ + fmp->cnt = 0; + fmp->val = 0; + fmp->time = 0; + spin_lock_init(&fmp->lock); +} + +/* Internal meter update - process cnt events and update value */ +static void fmeter_update(struct fmeter *fmp) +{ + time_t now = get_seconds(); + time_t ticks = now - fmp->time; + + if (ticks == 0) + return; + + ticks = min(FM_MAXTICKS, ticks); + while (ticks-- > 0) + fmp->val = (FM_COEF * fmp->val) / FM_SCALE; + fmp->time = now; + + fmp->val += ((FM_SCALE - FM_COEF) * fmp->cnt) / FM_SCALE; + fmp->cnt = 0; +} + +/* Process any previous ticks, then bump cnt by one (times scale). */ +static void fmeter_markevent(struct fmeter *fmp) +{ + spin_lock(&fmp->lock); + fmeter_update(fmp); + fmp->cnt = min(FM_MAXCNT, fmp->cnt + FM_SCALE); + spin_unlock(&fmp->lock); +} + +/* Process any previous ticks, then return current value. */ +static int fmeter_getrate(struct fmeter *fmp) +{ + int val; + + spin_lock(&fmp->lock); + fmeter_update(fmp); + val = fmp->val; + spin_unlock(&fmp->lock); + return val; +} + +static struct cpuset *cpuset_attach_old_cs; + +/* Called by cgroups to determine if a cpuset is usable; cpuset_mutex held */ +static int cpuset_can_attach(struct cgroup_subsys_state *css, + struct cgroup_taskset *tset) +{ + struct cpuset *cs = css_cs(css); + struct task_struct *task; + int ret; + + /* used later by cpuset_attach() */ + cpuset_attach_old_cs = task_cs(cgroup_taskset_first(tset)); + + mutex_lock(&cpuset_mutex); + + /* allow moving tasks into an empty cpuset if on default hierarchy */ + ret = -ENOSPC; + if (!cgroup_on_dfl(css->cgroup) && + (cpumask_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed))) + goto out_unlock; + + cgroup_taskset_for_each(task, tset) { + ret = task_can_attach(task, cs->cpus_allowed); + if (ret) + goto out_unlock; + ret = security_task_setscheduler(task); + if (ret) + goto out_unlock; + } + + /* + * Mark attach is in progress. This makes validate_change() fail + * changes which zero cpus/mems_allowed. + */ + cs->attach_in_progress++; + ret = 0; +out_unlock: + mutex_unlock(&cpuset_mutex); + return ret; +} + +static void cpuset_cancel_attach(struct cgroup_subsys_state *css, + struct cgroup_taskset *tset) +{ + mutex_lock(&cpuset_mutex); + css_cs(css)->attach_in_progress--; + mutex_unlock(&cpuset_mutex); +} + +/* + * Protected by cpuset_mutex. cpus_attach is used only by cpuset_attach() + * but we can't allocate it dynamically there. Define it global and + * allocate from cpuset_init(). + */ +static cpumask_var_t cpus_attach; + +static void cpuset_attach(struct cgroup_subsys_state *css, + struct cgroup_taskset *tset) +{ + /* static buf protected by cpuset_mutex */ + static nodemask_t cpuset_attach_nodemask_to; + struct mm_struct *mm; + struct task_struct *task; + struct task_struct *leader = cgroup_taskset_first(tset); + struct cpuset *cs = css_cs(css); + struct cpuset *oldcs = cpuset_attach_old_cs; + + mutex_lock(&cpuset_mutex); + + /* prepare for attach */ + if (cs == &top_cpuset) + cpumask_copy(cpus_attach, cpu_possible_mask); + else + guarantee_online_cpus(cs, cpus_attach); + + guarantee_online_mems(cs, &cpuset_attach_nodemask_to); + + cgroup_taskset_for_each(task, tset) { + /* + * can_attach beforehand should guarantee that this doesn't + * fail. TODO: have a better way to handle failure here + */ + WARN_ON_ONCE(set_cpus_allowed_ptr(task, cpus_attach)); + + cpuset_change_task_nodemask(task, &cpuset_attach_nodemask_to); + cpuset_update_task_spread_flag(cs, task); + } + + /* + * Change mm, possibly for multiple threads in a threadgroup. This is + * expensive and may sleep. + */ + cpuset_attach_nodemask_to = cs->effective_mems; + mm = get_task_mm(leader); + if (mm) { + mpol_rebind_mm(mm, &cpuset_attach_nodemask_to); + + /* + * old_mems_allowed is the same with mems_allowed here, except + * if this task is being moved automatically due to hotplug. + * In that case @mems_allowed has been updated and is empty, + * so @old_mems_allowed is the right nodesets that we migrate + * mm from. + */ + if (is_memory_migrate(cs)) { + cpuset_migrate_mm(mm, &oldcs->old_mems_allowed, + &cpuset_attach_nodemask_to); + } + mmput(mm); + } + + cs->old_mems_allowed = cpuset_attach_nodemask_to; + + cs->attach_in_progress--; + if (!cs->attach_in_progress) + wake_up(&cpuset_attach_wq); + + mutex_unlock(&cpuset_mutex); +} + +/* The various types of files and directories in a cpuset file system */ + +typedef enum { + FILE_MEMORY_MIGRATE, + FILE_CPULIST, + FILE_MEMLIST, + FILE_EFFECTIVE_CPULIST, + FILE_EFFECTIVE_MEMLIST, + FILE_CPU_EXCLUSIVE, + FILE_MEM_EXCLUSIVE, + FILE_MEM_HARDWALL, + FILE_SCHED_LOAD_BALANCE, + FILE_SCHED_RELAX_DOMAIN_LEVEL, + FILE_MEMORY_PRESSURE_ENABLED, + FILE_MEMORY_PRESSURE, + FILE_SPREAD_PAGE, + FILE_SPREAD_SLAB, +} cpuset_filetype_t; + +static int cpuset_write_u64(struct cgroup_subsys_state *css, struct cftype *cft, + u64 val) +{ + struct cpuset *cs = css_cs(css); + cpuset_filetype_t type = cft->private; + int retval = 0; + + mutex_lock(&cpuset_mutex); + if (!is_cpuset_online(cs)) { + retval = -ENODEV; + goto out_unlock; + } + + switch (type) { + case FILE_CPU_EXCLUSIVE: + retval = update_flag(CS_CPU_EXCLUSIVE, cs, val); + break; + case FILE_MEM_EXCLUSIVE: + retval = update_flag(CS_MEM_EXCLUSIVE, cs, val); + break; + case FILE_MEM_HARDWALL: + retval = update_flag(CS_MEM_HARDWALL, cs, val); + break; + case FILE_SCHED_LOAD_BALANCE: + retval = update_flag(CS_SCHED_LOAD_BALANCE, cs, val); + break; + case FILE_MEMORY_MIGRATE: + retval = update_flag(CS_MEMORY_MIGRATE, cs, val); + break; + case FILE_MEMORY_PRESSURE_ENABLED: + cpuset_memory_pressure_enabled = !!val; + break; + case FILE_MEMORY_PRESSURE: + retval = -EACCES; + break; + case FILE_SPREAD_PAGE: + retval = update_flag(CS_SPREAD_PAGE, cs, val); + break; + case FILE_SPREAD_SLAB: + retval = update_flag(CS_SPREAD_SLAB, cs, val); + break; + default: + retval = -EINVAL; + break; + } +out_unlock: + mutex_unlock(&cpuset_mutex); + return retval; +} + +static int cpuset_write_s64(struct cgroup_subsys_state *css, struct cftype *cft, + s64 val) +{ + struct cpuset *cs = css_cs(css); + cpuset_filetype_t type = cft->private; + int retval = -ENODEV; + + mutex_lock(&cpuset_mutex); + if (!is_cpuset_online(cs)) + goto out_unlock; + + switch (type) { + case FILE_SCHED_RELAX_DOMAIN_LEVEL: + retval = update_relax_domain_level(cs, val); + break; + default: + retval = -EINVAL; + break; + } +out_unlock: + mutex_unlock(&cpuset_mutex); + return retval; +} + +/* + * Common handling for a write to a "cpus" or "mems" file. + */ +static ssize_t cpuset_write_resmask(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) +{ + struct cpuset *cs = css_cs(of_css(of)); + struct cpuset *trialcs; + int retval = -ENODEV; + + buf = strstrip(buf); + + /* + * CPU or memory hotunplug may leave @cs w/o any execution + * resources, in which case the hotplug code asynchronously updates + * configuration and transfers all tasks to the nearest ancestor + * which can execute. + * + * As writes to "cpus" or "mems" may restore @cs's execution + * resources, wait for the previously scheduled operations before + * proceeding, so that we don't end up keep removing tasks added + * after execution capability is restored. + * + * cpuset_hotplug_work calls back into cgroup core via + * cgroup_transfer_tasks() and waiting for it from a cgroupfs + * operation like this one can lead to a deadlock through kernfs + * active_ref protection. Let's break the protection. Losing the + * protection is okay as we check whether @cs is online after + * grabbing cpuset_mutex anyway. This only happens on the legacy + * hierarchies. + */ + css_get(&cs->css); + kernfs_break_active_protection(of->kn); + flush_work(&cpuset_hotplug_work); + + mutex_lock(&cpuset_mutex); + if (!is_cpuset_online(cs)) + goto out_unlock; + + trialcs = alloc_trial_cpuset(cs); + if (!trialcs) { + retval = -ENOMEM; + goto out_unlock; + } + + switch (of_cft(of)->private) { + case FILE_CPULIST: + retval = update_cpumask(cs, trialcs, buf); + break; + case FILE_MEMLIST: + retval = update_nodemask(cs, trialcs, buf); + break; + default: + retval = -EINVAL; + break; + } + + free_trial_cpuset(trialcs); +out_unlock: + mutex_unlock(&cpuset_mutex); + kernfs_unbreak_active_protection(of->kn); + css_put(&cs->css); + return retval ?: nbytes; +} + +/* + * These ascii lists should be read in a single call, by using a user + * buffer large enough to hold the entire map. If read in smaller + * chunks, there is no guarantee of atomicity. Since the display format + * used, list of ranges of sequential numbers, is variable length, + * and since these maps can change value dynamically, one could read + * gibberish by doing partial reads while a list was changing. + */ +static int cpuset_common_seq_show(struct seq_file *sf, void *v) +{ + struct cpuset *cs = css_cs(seq_css(sf)); + cpuset_filetype_t type = seq_cft(sf)->private; + int ret = 0; + + spin_lock_irq(&callback_lock); + + switch (type) { + case FILE_CPULIST: + seq_printf(sf, "%*pbl\n", cpumask_pr_args(cs->cpus_allowed)); + break; + case FILE_MEMLIST: + seq_printf(sf, "%*pbl\n", nodemask_pr_args(&cs->mems_allowed)); + break; + case FILE_EFFECTIVE_CPULIST: + seq_printf(sf, "%*pbl\n", cpumask_pr_args(cs->effective_cpus)); + break; + case FILE_EFFECTIVE_MEMLIST: + seq_printf(sf, "%*pbl\n", nodemask_pr_args(&cs->effective_mems)); + break; + default: + ret = -EINVAL; + } + + spin_unlock_irq(&callback_lock); + return ret; +} + +static u64 cpuset_read_u64(struct cgroup_subsys_state *css, struct cftype *cft) +{ + struct cpuset *cs = css_cs(css); + cpuset_filetype_t type = cft->private; + switch (type) { + case FILE_CPU_EXCLUSIVE: + return is_cpu_exclusive(cs); + case FILE_MEM_EXCLUSIVE: + return is_mem_exclusive(cs); + case FILE_MEM_HARDWALL: + return is_mem_hardwall(cs); + case FILE_SCHED_LOAD_BALANCE: + return is_sched_load_balance(cs); + case FILE_MEMORY_MIGRATE: + return is_memory_migrate(cs); + case FILE_MEMORY_PRESSURE_ENABLED: + return cpuset_memory_pressure_enabled; + case FILE_MEMORY_PRESSURE: + return fmeter_getrate(&cs->fmeter); + case FILE_SPREAD_PAGE: + return is_spread_page(cs); + case FILE_SPREAD_SLAB: + return is_spread_slab(cs); + default: + BUG(); + } + + /* Unreachable but makes gcc happy */ + return 0; +} + +static s64 cpuset_read_s64(struct cgroup_subsys_state *css, struct cftype *cft) +{ + struct cpuset *cs = css_cs(css); + cpuset_filetype_t type = cft->private; + switch (type) { + case FILE_SCHED_RELAX_DOMAIN_LEVEL: + return cs->relax_domain_level; + default: + BUG(); + } + + /* Unrechable but makes gcc happy */ + return 0; +} + + +/* + * for the common functions, 'private' gives the type of file + */ + +static struct cftype files[] = { + { + .name = "cpus", + .seq_show = cpuset_common_seq_show, + .write = cpuset_write_resmask, + .max_write_len = (100U + 6 * NR_CPUS), + .private = FILE_CPULIST, + }, + + { + .name = "mems", + .seq_show = cpuset_common_seq_show, + .write = cpuset_write_resmask, + .max_write_len = (100U + 6 * MAX_NUMNODES), + .private = FILE_MEMLIST, + }, + + { + .name = "effective_cpus", + .seq_show = cpuset_common_seq_show, + .private = FILE_EFFECTIVE_CPULIST, + }, + + { + .name = "effective_mems", + .seq_show = cpuset_common_seq_show, + .private = FILE_EFFECTIVE_MEMLIST, + }, + + { + .name = "cpu_exclusive", + .read_u64 = cpuset_read_u64, + .write_u64 = cpuset_write_u64, + .private = FILE_CPU_EXCLUSIVE, + }, + + { + .name = "mem_exclusive", + .read_u64 = cpuset_read_u64, + .write_u64 = cpuset_write_u64, + .private = FILE_MEM_EXCLUSIVE, + }, + + { + .name = "mem_hardwall", + .read_u64 = cpuset_read_u64, + .write_u64 = cpuset_write_u64, + .private = FILE_MEM_HARDWALL, + }, + + { + .name = "sched_load_balance", + .read_u64 = cpuset_read_u64, + .write_u64 = cpuset_write_u64, + .private = FILE_SCHED_LOAD_BALANCE, + }, + + { + .name = "sched_relax_domain_level", + .read_s64 = cpuset_read_s64, + .write_s64 = cpuset_write_s64, + .private = FILE_SCHED_RELAX_DOMAIN_LEVEL, + }, + + { + .name = "memory_migrate", + .read_u64 = cpuset_read_u64, + .write_u64 = cpuset_write_u64, + .private = FILE_MEMORY_MIGRATE, + }, + + { + .name = "memory_pressure", + .read_u64 = cpuset_read_u64, + .write_u64 = cpuset_write_u64, + .private = FILE_MEMORY_PRESSURE, + .mode = S_IRUGO, + }, + + { + .name = "memory_spread_page", + .read_u64 = cpuset_read_u64, + .write_u64 = cpuset_write_u64, + .private = FILE_SPREAD_PAGE, + }, + + { + .name = "memory_spread_slab", + .read_u64 = cpuset_read_u64, + .write_u64 = cpuset_write_u64, + .private = FILE_SPREAD_SLAB, + }, + + { + .name = "memory_pressure_enabled", + .flags = CFTYPE_ONLY_ON_ROOT, + .read_u64 = cpuset_read_u64, + .write_u64 = cpuset_write_u64, + .private = FILE_MEMORY_PRESSURE_ENABLED, + }, + + { } /* terminate */ +}; + +/* + * cpuset_css_alloc - allocate a cpuset css + * cgrp: control group that the new cpuset will be part of + */ + +static struct cgroup_subsys_state * +cpuset_css_alloc(struct cgroup_subsys_state *parent_css) +{ + struct cpuset *cs; + + if (!parent_css) + return &top_cpuset.css; + + cs = kzalloc(sizeof(*cs), GFP_KERNEL); + if (!cs) + return ERR_PTR(-ENOMEM); + if (!alloc_cpumask_var(&cs->cpus_allowed, GFP_KERNEL)) + goto free_cs; + if (!alloc_cpumask_var(&cs->effective_cpus, GFP_KERNEL)) + goto free_cpus; + + set_bit(CS_SCHED_LOAD_BALANCE, &cs->flags); + cpumask_clear(cs->cpus_allowed); + nodes_clear(cs->mems_allowed); + cpumask_clear(cs->effective_cpus); + nodes_clear(cs->effective_mems); + fmeter_init(&cs->fmeter); + cs->relax_domain_level = -1; + + return &cs->css; + +free_cpus: + free_cpumask_var(cs->cpus_allowed); +free_cs: + kfree(cs); + return ERR_PTR(-ENOMEM); +} + +static int cpuset_css_online(struct cgroup_subsys_state *css) +{ + struct cpuset *cs = css_cs(css); + struct cpuset *parent = parent_cs(cs); + struct cpuset *tmp_cs; + struct cgroup_subsys_state *pos_css; + + if (!parent) + return 0; + + mutex_lock(&cpuset_mutex); + + set_bit(CS_ONLINE, &cs->flags); + if (is_spread_page(parent)) + set_bit(CS_SPREAD_PAGE, &cs->flags); + if (is_spread_slab(parent)) + set_bit(CS_SPREAD_SLAB, &cs->flags); + + cpuset_inc(); + + spin_lock_irq(&callback_lock); + if (cgroup_on_dfl(cs->css.cgroup)) { + cpumask_copy(cs->effective_cpus, parent->effective_cpus); + cs->effective_mems = parent->effective_mems; + } + spin_unlock_irq(&callback_lock); + + if (!test_bit(CGRP_CPUSET_CLONE_CHILDREN, &css->cgroup->flags)) + goto out_unlock; + + /* + * Clone @parent's configuration if CGRP_CPUSET_CLONE_CHILDREN is + * set. This flag handling is implemented in cgroup core for + * histrical reasons - the flag may be specified during mount. + * + * Currently, if any sibling cpusets have exclusive cpus or mem, we + * refuse to clone the configuration - thereby refusing the task to + * be entered, and as a result refusing the sys_unshare() or + * clone() which initiated it. If this becomes a problem for some + * users who wish to allow that scenario, then this could be + * changed to grant parent->cpus_allowed-sibling_cpus_exclusive + * (and likewise for mems) to the new cgroup. + */ + rcu_read_lock(); + cpuset_for_each_child(tmp_cs, pos_css, parent) { + if (is_mem_exclusive(tmp_cs) || is_cpu_exclusive(tmp_cs)) { + rcu_read_unlock(); + goto out_unlock; + } + } + rcu_read_unlock(); + + spin_lock_irq(&callback_lock); + cs->mems_allowed = parent->mems_allowed; + cs->effective_mems = parent->mems_allowed; + cpumask_copy(cs->cpus_allowed, parent->cpus_allowed); + cpumask_copy(cs->effective_cpus, parent->cpus_allowed); + spin_unlock_irq(&callback_lock); +out_unlock: + mutex_unlock(&cpuset_mutex); + return 0; +} + +/* + * If the cpuset being removed has its flag 'sched_load_balance' + * enabled, then simulate turning sched_load_balance off, which + * will call rebuild_sched_domains_locked(). + */ + +static void cpuset_css_offline(struct cgroup_subsys_state *css) +{ + struct cpuset *cs = css_cs(css); + + mutex_lock(&cpuset_mutex); + + if (is_sched_load_balance(cs)) + update_flag(CS_SCHED_LOAD_BALANCE, cs, 0); + + cpuset_dec(); + clear_bit(CS_ONLINE, &cs->flags); + + mutex_unlock(&cpuset_mutex); +} + +static void cpuset_css_free(struct cgroup_subsys_state *css) +{ + struct cpuset *cs = css_cs(css); + + free_cpumask_var(cs->effective_cpus); + free_cpumask_var(cs->cpus_allowed); + kfree(cs); +} + +static void cpuset_bind(struct cgroup_subsys_state *root_css) +{ + mutex_lock(&cpuset_mutex); + spin_lock_irq(&callback_lock); + + if (cgroup_on_dfl(root_css->cgroup)) { + cpumask_copy(top_cpuset.cpus_allowed, cpu_possible_mask); + top_cpuset.mems_allowed = node_possible_map; + } else { + cpumask_copy(top_cpuset.cpus_allowed, + top_cpuset.effective_cpus); + top_cpuset.mems_allowed = top_cpuset.effective_mems; + } + + spin_unlock_irq(&callback_lock); + mutex_unlock(&cpuset_mutex); +} + +struct cgroup_subsys cpuset_cgrp_subsys = { + .css_alloc = cpuset_css_alloc, + .css_online = cpuset_css_online, + .css_offline = cpuset_css_offline, + .css_free = cpuset_css_free, + .can_attach = cpuset_can_attach, + .cancel_attach = cpuset_cancel_attach, + .attach = cpuset_attach, + .bind = cpuset_bind, + .legacy_cftypes = files, + .early_init = 1, +}; + +/** + * cpuset_init - initialize cpusets at system boot + * + * Description: Initialize top_cpuset and the cpuset internal file system, + **/ + +int __init cpuset_init(void) +{ + int err = 0; + + if (!alloc_cpumask_var(&top_cpuset.cpus_allowed, GFP_KERNEL)) + BUG(); + if (!alloc_cpumask_var(&top_cpuset.effective_cpus, GFP_KERNEL)) + BUG(); + + cpumask_setall(top_cpuset.cpus_allowed); + nodes_setall(top_cpuset.mems_allowed); + cpumask_setall(top_cpuset.effective_cpus); + nodes_setall(top_cpuset.effective_mems); + + fmeter_init(&top_cpuset.fmeter); + set_bit(CS_SCHED_LOAD_BALANCE, &top_cpuset.flags); + top_cpuset.relax_domain_level = -1; + + err = register_filesystem(&cpuset_fs_type); + if (err < 0) + return err; + + if (!alloc_cpumask_var(&cpus_attach, GFP_KERNEL)) + BUG(); + + return 0; +} + +/* + * If CPU and/or memory hotplug handlers, below, unplug any CPUs + * or memory nodes, we need to walk over the cpuset hierarchy, + * removing that CPU or node from all cpusets. If this removes the + * last CPU or node from a cpuset, then move the tasks in the empty + * cpuset to its next-highest non-empty parent. + */ +static void remove_tasks_in_empty_cpuset(struct cpuset *cs) +{ + struct cpuset *parent; + + /* + * Find its next-highest non-empty parent, (top cpuset + * has online cpus, so can't be empty). + */ + parent = parent_cs(cs); + while (cpumask_empty(parent->cpus_allowed) || + nodes_empty(parent->mems_allowed)) + parent = parent_cs(parent); + + if (cgroup_transfer_tasks(parent->css.cgroup, cs->css.cgroup)) { + pr_err("cpuset: failed to transfer tasks out of empty cpuset "); + pr_cont_cgroup_name(cs->css.cgroup); + pr_cont("\n"); + } +} + +static void +hotplug_update_tasks_legacy(struct cpuset *cs, + struct cpumask *new_cpus, nodemask_t *new_mems, + bool cpus_updated, bool mems_updated) +{ + bool is_empty; + + spin_lock_irq(&callback_lock); + cpumask_copy(cs->cpus_allowed, new_cpus); + cpumask_copy(cs->effective_cpus, new_cpus); + cs->mems_allowed = *new_mems; + cs->effective_mems = *new_mems; + spin_unlock_irq(&callback_lock); + + /* + * Don't call update_tasks_cpumask() if the cpuset becomes empty, + * as the tasks will be migratecd to an ancestor. + */ + if (cpus_updated && !cpumask_empty(cs->cpus_allowed)) + update_tasks_cpumask(cs); + if (mems_updated && !nodes_empty(cs->mems_allowed)) + update_tasks_nodemask(cs); + + is_empty = cpumask_empty(cs->cpus_allowed) || + nodes_empty(cs->mems_allowed); + + mutex_unlock(&cpuset_mutex); + + /* + * Move tasks to the nearest ancestor with execution resources, + * This is full cgroup operation which will also call back into + * cpuset. Should be done outside any lock. + */ + if (is_empty) + remove_tasks_in_empty_cpuset(cs); + + mutex_lock(&cpuset_mutex); +} + +static void +hotplug_update_tasks(struct cpuset *cs, + struct cpumask *new_cpus, nodemask_t *new_mems, + bool cpus_updated, bool mems_updated) +{ + if (cpumask_empty(new_cpus)) + cpumask_copy(new_cpus, parent_cs(cs)->effective_cpus); + if (nodes_empty(*new_mems)) + *new_mems = parent_cs(cs)->effective_mems; + + spin_lock_irq(&callback_lock); + cpumask_copy(cs->effective_cpus, new_cpus); + cs->effective_mems = *new_mems; + spin_unlock_irq(&callback_lock); + + if (cpus_updated) + update_tasks_cpumask(cs); + if (mems_updated) + update_tasks_nodemask(cs); +} + +/** + * cpuset_hotplug_update_tasks - update tasks in a cpuset for hotunplug + * @cs: cpuset in interest + * + * Compare @cs's cpu and mem masks against top_cpuset and if some have gone + * offline, update @cs accordingly. If @cs ends up with no CPU or memory, + * all its tasks are moved to the nearest ancestor with both resources. + */ +static void cpuset_hotplug_update_tasks(struct cpuset *cs) +{ + static cpumask_t new_cpus; + static nodemask_t new_mems; + bool cpus_updated; + bool mems_updated; +retry: + wait_event(cpuset_attach_wq, cs->attach_in_progress == 0); + + mutex_lock(&cpuset_mutex); + + /* + * We have raced with task attaching. We wait until attaching + * is finished, so we won't attach a task to an empty cpuset. + */ + if (cs->attach_in_progress) { + mutex_unlock(&cpuset_mutex); + goto retry; + } + + cpumask_and(&new_cpus, cs->cpus_allowed, parent_cs(cs)->effective_cpus); + nodes_and(new_mems, cs->mems_allowed, parent_cs(cs)->effective_mems); + + cpus_updated = !cpumask_equal(&new_cpus, cs->effective_cpus); + mems_updated = !nodes_equal(new_mems, cs->effective_mems); + + if (cgroup_on_dfl(cs->css.cgroup)) + hotplug_update_tasks(cs, &new_cpus, &new_mems, + cpus_updated, mems_updated); + else + hotplug_update_tasks_legacy(cs, &new_cpus, &new_mems, + cpus_updated, mems_updated); + + mutex_unlock(&cpuset_mutex); +} + +/** + * cpuset_hotplug_workfn - handle CPU/memory hotunplug for a cpuset + * + * This function is called after either CPU or memory configuration has + * changed and updates cpuset accordingly. The top_cpuset is always + * synchronized to cpu_active_mask and N_MEMORY, which is necessary in + * order to make cpusets transparent (of no affect) on systems that are + * actively using CPU hotplug but making no active use of cpusets. + * + * Non-root cpusets are only affected by offlining. If any CPUs or memory + * nodes have been taken down, cpuset_hotplug_update_tasks() is invoked on + * all descendants. + * + * Note that CPU offlining during suspend is ignored. We don't modify + * cpusets across suspend/resume cycles at all. + */ +static void cpuset_hotplug_workfn(struct work_struct *work) +{ + static cpumask_t new_cpus; + static nodemask_t new_mems; + bool cpus_updated, mems_updated; + bool on_dfl = cgroup_on_dfl(top_cpuset.css.cgroup); + + mutex_lock(&cpuset_mutex); + + /* fetch the available cpus/mems and find out which changed how */ + cpumask_copy(&new_cpus, cpu_active_mask); + new_mems = node_states[N_MEMORY]; + + cpus_updated = !cpumask_equal(top_cpuset.effective_cpus, &new_cpus); + mems_updated = !nodes_equal(top_cpuset.effective_mems, new_mems); + + /* synchronize cpus_allowed to cpu_active_mask */ + if (cpus_updated) { + spin_lock_irq(&callback_lock); + if (!on_dfl) + cpumask_copy(top_cpuset.cpus_allowed, &new_cpus); + cpumask_copy(top_cpuset.effective_cpus, &new_cpus); + spin_unlock_irq(&callback_lock); + /* we don't mess with cpumasks of tasks in top_cpuset */ + } + + /* synchronize mems_allowed to N_MEMORY */ + if (mems_updated) { + spin_lock_irq(&callback_lock); + if (!on_dfl) + top_cpuset.mems_allowed = new_mems; + top_cpuset.effective_mems = new_mems; + spin_unlock_irq(&callback_lock); + update_tasks_nodemask(&top_cpuset); + } + + mutex_unlock(&cpuset_mutex); + + /* if cpus or mems changed, we need to propagate to descendants */ + if (cpus_updated || mems_updated) { + struct cpuset *cs; + struct cgroup_subsys_state *pos_css; + + rcu_read_lock(); + cpuset_for_each_descendant_pre(cs, pos_css, &top_cpuset) { + if (cs == &top_cpuset || !css_tryget_online(&cs->css)) + continue; + rcu_read_unlock(); + + cpuset_hotplug_update_tasks(cs); + + rcu_read_lock(); + css_put(&cs->css); + } + rcu_read_unlock(); + } + + /* rebuild sched domains if cpus_allowed has changed */ + if (cpus_updated) + rebuild_sched_domains(); +} + +void cpuset_update_active_cpus(bool cpu_online) +{ + /* + * We're inside cpu hotplug critical region which usually nests + * inside cgroup synchronization. Bounce actual hotplug processing + * to a work item to avoid reverse locking order. + * + * We still need to do partition_sched_domains() synchronously; + * otherwise, the scheduler will get confused and put tasks to the + * dead CPU. Fall back to the default single domain. + * cpuset_hotplug_workfn() will rebuild it as necessary. + */ + partition_sched_domains(1, NULL, NULL); + schedule_work(&cpuset_hotplug_work); +} + +/* + * Keep top_cpuset.mems_allowed tracking node_states[N_MEMORY]. + * Call this routine anytime after node_states[N_MEMORY] changes. + * See cpuset_update_active_cpus() for CPU hotplug handling. + */ +static int cpuset_track_online_nodes(struct notifier_block *self, + unsigned long action, void *arg) +{ + schedule_work(&cpuset_hotplug_work); + return NOTIFY_OK; +} + +static struct notifier_block cpuset_track_online_nodes_nb = { + .notifier_call = cpuset_track_online_nodes, + .priority = 10, /* ??! */ +}; + +/** + * cpuset_init_smp - initialize cpus_allowed + * + * Description: Finish top cpuset after cpu, node maps are initialized + */ +void __init cpuset_init_smp(void) +{ + cpumask_copy(top_cpuset.cpus_allowed, cpu_active_mask); + top_cpuset.mems_allowed = node_states[N_MEMORY]; + top_cpuset.old_mems_allowed = top_cpuset.mems_allowed; + + cpumask_copy(top_cpuset.effective_cpus, cpu_active_mask); + top_cpuset.effective_mems = node_states[N_MEMORY]; + + register_hotmemory_notifier(&cpuset_track_online_nodes_nb); +} + +/** + * cpuset_cpus_allowed - return cpus_allowed mask from a tasks cpuset. + * @tsk: pointer to task_struct from which to obtain cpuset->cpus_allowed. + * @pmask: pointer to struct cpumask variable to receive cpus_allowed set. + * + * Description: Returns the cpumask_var_t cpus_allowed of the cpuset + * attached to the specified @tsk. Guaranteed to return some non-empty + * subset of cpu_online_mask, even if this means going outside the + * tasks cpuset. + **/ + +void cpuset_cpus_allowed(struct task_struct *tsk, struct cpumask *pmask) +{ + unsigned long flags; + + spin_lock_irqsave(&callback_lock, flags); + rcu_read_lock(); + guarantee_online_cpus(task_cs(tsk), pmask); + rcu_read_unlock(); + spin_unlock_irqrestore(&callback_lock, flags); +} + +void cpuset_cpus_allowed_fallback(struct task_struct *tsk) +{ + rcu_read_lock(); + do_set_cpus_allowed(tsk, task_cs(tsk)->effective_cpus); + rcu_read_unlock(); + + /* + * We own tsk->cpus_allowed, nobody can change it under us. + * + * But we used cs && cs->cpus_allowed lockless and thus can + * race with cgroup_attach_task() or update_cpumask() and get + * the wrong tsk->cpus_allowed. However, both cases imply the + * subsequent cpuset_change_cpumask()->set_cpus_allowed_ptr() + * which takes task_rq_lock(). + * + * If we are called after it dropped the lock we must see all + * changes in tsk_cs()->cpus_allowed. Otherwise we can temporary + * set any mask even if it is not right from task_cs() pov, + * the pending set_cpus_allowed_ptr() will fix things. + * + * select_fallback_rq() will fix things ups and set cpu_possible_mask + * if required. + */ +} + +void __init cpuset_init_current_mems_allowed(void) +{ + nodes_setall(current->mems_allowed); +} + +/** + * cpuset_mems_allowed - return mems_allowed mask from a tasks cpuset. + * @tsk: pointer to task_struct from which to obtain cpuset->mems_allowed. + * + * Description: Returns the nodemask_t mems_allowed of the cpuset + * attached to the specified @tsk. Guaranteed to return some non-empty + * subset of node_states[N_MEMORY], even if this means going outside the + * tasks cpuset. + **/ + +nodemask_t cpuset_mems_allowed(struct task_struct *tsk) +{ + nodemask_t mask; + unsigned long flags; + + spin_lock_irqsave(&callback_lock, flags); + rcu_read_lock(); + guarantee_online_mems(task_cs(tsk), &mask); + rcu_read_unlock(); + spin_unlock_irqrestore(&callback_lock, flags); + + return mask; +} + +/** + * cpuset_nodemask_valid_mems_allowed - check nodemask vs. curremt mems_allowed + * @nodemask: the nodemask to be checked + * + * Are any of the nodes in the nodemask allowed in current->mems_allowed? + */ +int cpuset_nodemask_valid_mems_allowed(nodemask_t *nodemask) +{ + return nodes_intersects(*nodemask, current->mems_allowed); +} + +/* + * nearest_hardwall_ancestor() - Returns the nearest mem_exclusive or + * mem_hardwall ancestor to the specified cpuset. Call holding + * callback_lock. If no ancestor is mem_exclusive or mem_hardwall + * (an unusual configuration), then returns the root cpuset. + */ +static struct cpuset *nearest_hardwall_ancestor(struct cpuset *cs) +{ + while (!(is_mem_exclusive(cs) || is_mem_hardwall(cs)) && parent_cs(cs)) + cs = parent_cs(cs); + return cs; +} + +/** + * cpuset_node_allowed - Can we allocate on a memory node? + * @node: is this an allowed node? + * @gfp_mask: memory allocation flags + * + * If we're in interrupt, yes, we can always allocate. If @node is set in + * current's mems_allowed, yes. If it's not a __GFP_HARDWALL request and this + * node is set in the nearest hardwalled cpuset ancestor to current's cpuset, + * yes. If current has access to memory reserves due to TIF_MEMDIE, yes. + * Otherwise, no. + * + * GFP_USER allocations are marked with the __GFP_HARDWALL bit, + * and do not allow allocations outside the current tasks cpuset + * unless the task has been OOM killed as is marked TIF_MEMDIE. + * GFP_KERNEL allocations are not so marked, so can escape to the + * nearest enclosing hardwalled ancestor cpuset. + * + * Scanning up parent cpusets requires callback_lock. The + * __alloc_pages() routine only calls here with __GFP_HARDWALL bit + * _not_ set if it's a GFP_KERNEL allocation, and all nodes in the + * current tasks mems_allowed came up empty on the first pass over + * the zonelist. So only GFP_KERNEL allocations, if all nodes in the + * cpuset are short of memory, might require taking the callback_lock. + * + * The first call here from mm/page_alloc:get_page_from_freelist() + * has __GFP_HARDWALL set in gfp_mask, enforcing hardwall cpusets, + * so no allocation on a node outside the cpuset is allowed (unless + * in interrupt, of course). + * + * The second pass through get_page_from_freelist() doesn't even call + * here for GFP_ATOMIC calls. For those calls, the __alloc_pages() + * variable 'wait' is not set, and the bit ALLOC_CPUSET is not set + * in alloc_flags. That logic and the checks below have the combined + * affect that: + * in_interrupt - any node ok (current task context irrelevant) + * GFP_ATOMIC - any node ok + * TIF_MEMDIE - any node ok + * GFP_KERNEL - any node in enclosing hardwalled cpuset ok + * GFP_USER - only nodes in current tasks mems allowed ok. + */ +int __cpuset_node_allowed(int node, gfp_t gfp_mask) +{ + struct cpuset *cs; /* current cpuset ancestors */ + int allowed; /* is allocation in zone z allowed? */ + unsigned long flags; + + if (in_interrupt()) + return 1; + if (node_isset(node, current->mems_allowed)) + return 1; + /* + * Allow tasks that have access to memory reserves because they have + * been OOM killed to get memory anywhere. + */ + if (unlikely(test_thread_flag(TIF_MEMDIE))) + return 1; + if (gfp_mask & __GFP_HARDWALL) /* If hardwall request, stop here */ + return 0; + + if (current->flags & PF_EXITING) /* Let dying task have memory */ + return 1; + + /* Not hardwall and node outside mems_allowed: scan up cpusets */ + spin_lock_irqsave(&callback_lock, flags); + + rcu_read_lock(); + cs = nearest_hardwall_ancestor(task_cs(current)); + allowed = node_isset(node, cs->mems_allowed); + rcu_read_unlock(); + + spin_unlock_irqrestore(&callback_lock, flags); + return allowed; +} + +/** + * cpuset_mem_spread_node() - On which node to begin search for a file page + * cpuset_slab_spread_node() - On which node to begin search for a slab page + * + * If a task is marked PF_SPREAD_PAGE or PF_SPREAD_SLAB (as for + * tasks in a cpuset with is_spread_page or is_spread_slab set), + * and if the memory allocation used cpuset_mem_spread_node() + * to determine on which node to start looking, as it will for + * certain page cache or slab cache pages such as used for file + * system buffers and inode caches, then instead of starting on the + * local node to look for a free page, rather spread the starting + * node around the tasks mems_allowed nodes. + * + * We don't have to worry about the returned node being offline + * because "it can't happen", and even if it did, it would be ok. + * + * The routines calling guarantee_online_mems() are careful to + * only set nodes in task->mems_allowed that are online. So it + * should not be possible for the following code to return an + * offline node. But if it did, that would be ok, as this routine + * is not returning the node where the allocation must be, only + * the node where the search should start. The zonelist passed to + * __alloc_pages() will include all nodes. If the slab allocator + * is passed an offline node, it will fall back to the local node. + * See kmem_cache_alloc_node(). + */ + +static int cpuset_spread_node(int *rotor) +{ + int node; + + node = next_node(*rotor, current->mems_allowed); + if (node == MAX_NUMNODES) + node = first_node(current->mems_allowed); + *rotor = node; + return node; +} + +int cpuset_mem_spread_node(void) +{ + if (current->cpuset_mem_spread_rotor == NUMA_NO_NODE) + current->cpuset_mem_spread_rotor = + node_random(¤t->mems_allowed); + + return cpuset_spread_node(¤t->cpuset_mem_spread_rotor); +} + +int cpuset_slab_spread_node(void) +{ + if (current->cpuset_slab_spread_rotor == NUMA_NO_NODE) + current->cpuset_slab_spread_rotor = + node_random(¤t->mems_allowed); + + return cpuset_spread_node(¤t->cpuset_slab_spread_rotor); +} + +EXPORT_SYMBOL_GPL(cpuset_mem_spread_node); + +/** + * cpuset_mems_allowed_intersects - Does @tsk1's mems_allowed intersect @tsk2's? + * @tsk1: pointer to task_struct of some task. + * @tsk2: pointer to task_struct of some other task. + * + * Description: Return true if @tsk1's mems_allowed intersects the + * mems_allowed of @tsk2. Used by the OOM killer to determine if + * one of the task's memory usage might impact the memory available + * to the other. + **/ + +int cpuset_mems_allowed_intersects(const struct task_struct *tsk1, + const struct task_struct *tsk2) +{ + return nodes_intersects(tsk1->mems_allowed, tsk2->mems_allowed); +} + +/** + * cpuset_print_task_mems_allowed - prints task's cpuset and mems_allowed + * @tsk: pointer to task_struct of some task. + * + * Description: Prints @task's name, cpuset name, and cached copy of its + * mems_allowed to the kernel log. + */ +void cpuset_print_task_mems_allowed(struct task_struct *tsk) +{ + struct cgroup *cgrp; + + rcu_read_lock(); + + cgrp = task_cs(tsk)->css.cgroup; + pr_info("%s cpuset=", tsk->comm); + pr_cont_cgroup_name(cgrp); + pr_cont(" mems_allowed=%*pbl\n", nodemask_pr_args(&tsk->mems_allowed)); + + rcu_read_unlock(); +} + +/* + * Collection of memory_pressure is suppressed unless + * this flag is enabled by writing "1" to the special + * cpuset file 'memory_pressure_enabled' in the root cpuset. + */ + +int cpuset_memory_pressure_enabled __read_mostly; + +/** + * cpuset_memory_pressure_bump - keep stats of per-cpuset reclaims. + * + * Keep a running average of the rate of synchronous (direct) + * page reclaim efforts initiated by tasks in each cpuset. + * + * This represents the rate at which some task in the cpuset + * ran low on memory on all nodes it was allowed to use, and + * had to enter the kernels page reclaim code in an effort to + * create more free memory by tossing clean pages or swapping + * or writing dirty pages. + * + * Display to user space in the per-cpuset read-only file + * "memory_pressure". Value displayed is an integer + * representing the recent rate of entry into the synchronous + * (direct) page reclaim by any task attached to the cpuset. + **/ + +void __cpuset_memory_pressure_bump(void) +{ + rcu_read_lock(); + fmeter_markevent(&task_cs(current)->fmeter); + rcu_read_unlock(); +} + +#ifdef CONFIG_PROC_PID_CPUSET +/* + * proc_cpuset_show() + * - Print tasks cpuset path into seq_file. + * - Used for /proc//cpuset. + * - No need to task_lock(tsk) on this tsk->cpuset reference, as it + * doesn't really matter if tsk->cpuset changes after we read it, + * and we take cpuset_mutex, keeping cpuset_attach() from changing it + * anyway. + */ +int proc_cpuset_show(struct seq_file *m, struct pid_namespace *ns, + struct pid *pid, struct task_struct *tsk) +{ + char *buf, *p; + struct cgroup_subsys_state *css; + int retval; + + retval = -ENOMEM; + buf = kmalloc(PATH_MAX, GFP_KERNEL); + if (!buf) + goto out; + + retval = -ENAMETOOLONG; + rcu_read_lock(); + css = task_css(tsk, cpuset_cgrp_id); + p = cgroup_path(css->cgroup, buf, PATH_MAX); + rcu_read_unlock(); + if (!p) + goto out_free; + seq_puts(m, p); + seq_putc(m, '\n'); + retval = 0; +out_free: + kfree(buf); +out: + return retval; +} +#endif /* CONFIG_PROC_PID_CPUSET */ + +/* Display task mems_allowed in /proc//status file. */ +void cpuset_task_status_allowed(struct seq_file *m, struct task_struct *task) +{ + seq_printf(m, "Mems_allowed:\t%*pb\n", + nodemask_pr_args(&task->mems_allowed)); + seq_printf(m, "Mems_allowed_list:\t%*pbl\n", + nodemask_pr_args(&task->mems_allowed)); +} diff --git a/kernel/kernel/crash_dump.c b/kernel/kernel/crash_dump.c new file mode 100644 index 000000000..b64e238b5 --- /dev/null +++ b/kernel/kernel/crash_dump.c @@ -0,0 +1,46 @@ +#include +#include +#include +#include +#include + +/* + * If we have booted due to a crash, max_pfn will be a very low value. We need + * to know the amount of memory that the previous kernel used. + */ +unsigned long saved_max_pfn; + +/* + * stores the physical address of elf header of crash image + * + * Note: elfcorehdr_addr is not just limited to vmcore. It is also used by + * is_kdump_kernel() to determine if we are booting after a panic. Hence put + * it under CONFIG_CRASH_DUMP and not CONFIG_PROC_VMCORE. + */ +unsigned long long elfcorehdr_addr = ELFCORE_ADDR_MAX; +EXPORT_SYMBOL_GPL(elfcorehdr_addr); + +/* + * stores the size of elf header of crash image + */ +unsigned long long elfcorehdr_size; + +/* + * elfcorehdr= specifies the location of elf core header stored by the crashed + * kernel. This option will be passed by kexec loader to the capture kernel. + * + * Syntax: elfcorehdr=[size[KMG]@]offset[KMG] + */ +static int __init setup_elfcorehdr(char *arg) +{ + char *end; + if (!arg) + return -EINVAL; + elfcorehdr_addr = memparse(arg, &end); + if (*end == '@') { + elfcorehdr_size = elfcorehdr_addr; + elfcorehdr_addr = memparse(end + 1, &end); + } + return end > arg ? 0 : -EINVAL; +} +early_param("elfcorehdr", setup_elfcorehdr); diff --git a/kernel/kernel/cred.c b/kernel/kernel/cred.c new file mode 100644 index 000000000..ec1c07667 --- /dev/null +++ b/kernel/kernel/cred.c @@ -0,0 +1,810 @@ +/* Task credentials management - see Documentation/security/credentials.txt + * + * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public Licence + * as published by the Free Software Foundation; either version + * 2 of the Licence, or (at your option) any later version. + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#if 0 +#define kdebug(FMT, ...) \ + printk("[%-5.5s%5u] "FMT"\n", current->comm, current->pid ,##__VA_ARGS__) +#else +#define kdebug(FMT, ...) \ + no_printk("[%-5.5s%5u] "FMT"\n", current->comm, current->pid ,##__VA_ARGS__) +#endif + +static struct kmem_cache *cred_jar; + +/* init to 2 - one for init_task, one to ensure it is never freed */ +struct group_info init_groups = { .usage = ATOMIC_INIT(2) }; + +/* + * The initial credentials for the initial task + */ +struct cred init_cred = { + .usage = ATOMIC_INIT(4), +#ifdef CONFIG_DEBUG_CREDENTIALS + .subscribers = ATOMIC_INIT(2), + .magic = CRED_MAGIC, +#endif + .uid = GLOBAL_ROOT_UID, + .gid = GLOBAL_ROOT_GID, + .suid = GLOBAL_ROOT_UID, + .sgid = GLOBAL_ROOT_GID, + .euid = GLOBAL_ROOT_UID, + .egid = GLOBAL_ROOT_GID, + .fsuid = GLOBAL_ROOT_UID, + .fsgid = GLOBAL_ROOT_GID, + .securebits = SECUREBITS_DEFAULT, + .cap_inheritable = CAP_EMPTY_SET, + .cap_permitted = CAP_FULL_SET, + .cap_effective = CAP_FULL_SET, + .cap_bset = CAP_FULL_SET, + .user = INIT_USER, + .user_ns = &init_user_ns, + .group_info = &init_groups, +}; + +static inline void set_cred_subscribers(struct cred *cred, int n) +{ +#ifdef CONFIG_DEBUG_CREDENTIALS + atomic_set(&cred->subscribers, n); +#endif +} + +static inline int read_cred_subscribers(const struct cred *cred) +{ +#ifdef CONFIG_DEBUG_CREDENTIALS + return atomic_read(&cred->subscribers); +#else + return 0; +#endif +} + +static inline void alter_cred_subscribers(const struct cred *_cred, int n) +{ +#ifdef CONFIG_DEBUG_CREDENTIALS + struct cred *cred = (struct cred *) _cred; + + atomic_add(n, &cred->subscribers); +#endif +} + +/* + * The RCU callback to actually dispose of a set of credentials + */ +static void put_cred_rcu(struct rcu_head *rcu) +{ + struct cred *cred = container_of(rcu, struct cred, rcu); + + kdebug("put_cred_rcu(%p)", cred); + +#ifdef CONFIG_DEBUG_CREDENTIALS + if (cred->magic != CRED_MAGIC_DEAD || + atomic_read(&cred->usage) != 0 || + read_cred_subscribers(cred) != 0) + panic("CRED: put_cred_rcu() sees %p with" + " mag %x, put %p, usage %d, subscr %d\n", + cred, cred->magic, cred->put_addr, + atomic_read(&cred->usage), + read_cred_subscribers(cred)); +#else + if (atomic_read(&cred->usage) != 0) + panic("CRED: put_cred_rcu() sees %p with usage %d\n", + cred, atomic_read(&cred->usage)); +#endif + + security_cred_free(cred); + key_put(cred->session_keyring); + key_put(cred->process_keyring); + key_put(cred->thread_keyring); + key_put(cred->request_key_auth); + if (cred->group_info) + put_group_info(cred->group_info); + free_uid(cred->user); + put_user_ns(cred->user_ns); + kmem_cache_free(cred_jar, cred); +} + +/** + * __put_cred - Destroy a set of credentials + * @cred: The record to release + * + * Destroy a set of credentials on which no references remain. + */ +void __put_cred(struct cred *cred) +{ + kdebug("__put_cred(%p{%d,%d})", cred, + atomic_read(&cred->usage), + read_cred_subscribers(cred)); + + BUG_ON(atomic_read(&cred->usage) != 0); +#ifdef CONFIG_DEBUG_CREDENTIALS + BUG_ON(read_cred_subscribers(cred) != 0); + cred->magic = CRED_MAGIC_DEAD; + cred->put_addr = __builtin_return_address(0); +#endif + BUG_ON(cred == current->cred); + BUG_ON(cred == current->real_cred); + + call_rcu(&cred->rcu, put_cred_rcu); +} +EXPORT_SYMBOL(__put_cred); + +/* + * Clean up a task's credentials when it exits + */ +void exit_creds(struct task_struct *tsk) +{ + struct cred *cred; + + kdebug("exit_creds(%u,%p,%p,{%d,%d})", tsk->pid, tsk->real_cred, tsk->cred, + atomic_read(&tsk->cred->usage), + read_cred_subscribers(tsk->cred)); + + cred = (struct cred *) tsk->real_cred; + tsk->real_cred = NULL; + validate_creds(cred); + alter_cred_subscribers(cred, -1); + put_cred(cred); + + cred = (struct cred *) tsk->cred; + tsk->cred = NULL; + validate_creds(cred); + alter_cred_subscribers(cred, -1); + put_cred(cred); +} + +/** + * get_task_cred - Get another task's objective credentials + * @task: The task to query + * + * Get the objective credentials of a task, pinning them so that they can't go + * away. Accessing a task's credentials directly is not permitted. + * + * The caller must also make sure task doesn't get deleted, either by holding a + * ref on task or by holding tasklist_lock to prevent it from being unlinked. + */ +const struct cred *get_task_cred(struct task_struct *task) +{ + const struct cred *cred; + + rcu_read_lock(); + + do { + cred = __task_cred((task)); + BUG_ON(!cred); + } while (!atomic_inc_not_zero(&((struct cred *)cred)->usage)); + + rcu_read_unlock(); + return cred; +} + +/* + * Allocate blank credentials, such that the credentials can be filled in at a + * later date without risk of ENOMEM. + */ +struct cred *cred_alloc_blank(void) +{ + struct cred *new; + + new = kmem_cache_zalloc(cred_jar, GFP_KERNEL); + if (!new) + return NULL; + + atomic_set(&new->usage, 1); +#ifdef CONFIG_DEBUG_CREDENTIALS + new->magic = CRED_MAGIC; +#endif + + if (security_cred_alloc_blank(new, GFP_KERNEL) < 0) + goto error; + + return new; + +error: + abort_creds(new); + return NULL; +} + +/** + * prepare_creds - Prepare a new set of credentials for modification + * + * Prepare a new set of task credentials for modification. A task's creds + * shouldn't generally be modified directly, therefore this function is used to + * prepare a new copy, which the caller then modifies and then commits by + * calling commit_creds(). + * + * Preparation involves making a copy of the objective creds for modification. + * + * Returns a pointer to the new creds-to-be if successful, NULL otherwise. + * + * Call commit_creds() or abort_creds() to clean up. + */ +struct cred *prepare_creds(void) +{ + struct task_struct *task = current; + const struct cred *old; + struct cred *new; + + validate_process_creds(); + + new = kmem_cache_alloc(cred_jar, GFP_KERNEL); + if (!new) + return NULL; + + kdebug("prepare_creds() alloc %p", new); + + old = task->cred; + memcpy(new, old, sizeof(struct cred)); + + atomic_set(&new->usage, 1); + set_cred_subscribers(new, 0); + get_group_info(new->group_info); + get_uid(new->user); + get_user_ns(new->user_ns); + +#ifdef CONFIG_KEYS + key_get(new->session_keyring); + key_get(new->process_keyring); + key_get(new->thread_keyring); + key_get(new->request_key_auth); +#endif + +#ifdef CONFIG_SECURITY + new->security = NULL; +#endif + + if (security_prepare_creds(new, old, GFP_KERNEL) < 0) + goto error; + validate_creds(new); + return new; + +error: + abort_creds(new); + return NULL; +} +EXPORT_SYMBOL(prepare_creds); + +/* + * Prepare credentials for current to perform an execve() + * - The caller must hold ->cred_guard_mutex + */ +struct cred *prepare_exec_creds(void) +{ + struct cred *new; + + new = prepare_creds(); + if (!new) + return new; + +#ifdef CONFIG_KEYS + /* newly exec'd tasks don't get a thread keyring */ + key_put(new->thread_keyring); + new->thread_keyring = NULL; + + /* inherit the session keyring; new process keyring */ + key_put(new->process_keyring); + new->process_keyring = NULL; +#endif + + return new; +} + +/* + * Copy credentials for the new process created by fork() + * + * We share if we can, but under some circumstances we have to generate a new + * set. + * + * The new process gets the current process's subjective credentials as its + * objective and subjective credentials + */ +int copy_creds(struct task_struct *p, unsigned long clone_flags) +{ + struct cred *new; + int ret; + + if ( +#ifdef CONFIG_KEYS + !p->cred->thread_keyring && +#endif + clone_flags & CLONE_THREAD + ) { + p->real_cred = get_cred(p->cred); + get_cred(p->cred); + alter_cred_subscribers(p->cred, 2); + kdebug("share_creds(%p{%d,%d})", + p->cred, atomic_read(&p->cred->usage), + read_cred_subscribers(p->cred)); + atomic_inc(&p->cred->user->processes); + return 0; + } + + new = prepare_creds(); + if (!new) + return -ENOMEM; + + if (clone_flags & CLONE_NEWUSER) { + ret = create_user_ns(new); + if (ret < 0) + goto error_put; + } + +#ifdef CONFIG_KEYS + /* new threads get their own thread keyrings if their parent already + * had one */ + if (new->thread_keyring) { + key_put(new->thread_keyring); + new->thread_keyring = NULL; + if (clone_flags & CLONE_THREAD) + install_thread_keyring_to_cred(new); + } + + /* The process keyring is only shared between the threads in a process; + * anything outside of those threads doesn't inherit. + */ + if (!(clone_flags & CLONE_THREAD)) { + key_put(new->process_keyring); + new->process_keyring = NULL; + } +#endif + + atomic_inc(&new->user->processes); + p->cred = p->real_cred = get_cred(new); + alter_cred_subscribers(new, 2); + validate_creds(new); + return 0; + +error_put: + put_cred(new); + return ret; +} + +static bool cred_cap_issubset(const struct cred *set, const struct cred *subset) +{ + const struct user_namespace *set_ns = set->user_ns; + const struct user_namespace *subset_ns = subset->user_ns; + + /* If the two credentials are in the same user namespace see if + * the capabilities of subset are a subset of set. + */ + if (set_ns == subset_ns) + return cap_issubset(subset->cap_permitted, set->cap_permitted); + + /* The credentials are in a different user namespaces + * therefore one is a subset of the other only if a set is an + * ancestor of subset and set->euid is owner of subset or one + * of subsets ancestors. + */ + for (;subset_ns != &init_user_ns; subset_ns = subset_ns->parent) { + if ((set_ns == subset_ns->parent) && + uid_eq(subset_ns->owner, set->euid)) + return true; + } + + return false; +} + +/** + * commit_creds - Install new credentials upon the current task + * @new: The credentials to be assigned + * + * Install a new set of credentials to the current task, using RCU to replace + * the old set. Both the objective and the subjective credentials pointers are + * updated. This function may not be called if the subjective credentials are + * in an overridden state. + * + * This function eats the caller's reference to the new credentials. + * + * Always returns 0 thus allowing this function to be tail-called at the end + * of, say, sys_setgid(). + */ +int commit_creds(struct cred *new) +{ + struct task_struct *task = current; + const struct cred *old = task->real_cred; + + kdebug("commit_creds(%p{%d,%d})", new, + atomic_read(&new->usage), + read_cred_subscribers(new)); + + BUG_ON(task->cred != old); +#ifdef CONFIG_DEBUG_CREDENTIALS + BUG_ON(read_cred_subscribers(old) < 2); + validate_creds(old); + validate_creds(new); +#endif + BUG_ON(atomic_read(&new->usage) < 1); + + get_cred(new); /* we will require a ref for the subj creds too */ + + /* dumpability changes */ + if (!uid_eq(old->euid, new->euid) || + !gid_eq(old->egid, new->egid) || + !uid_eq(old->fsuid, new->fsuid) || + !gid_eq(old->fsgid, new->fsgid) || + !cred_cap_issubset(old, new)) { + if (task->mm) + set_dumpable(task->mm, suid_dumpable); + task->pdeath_signal = 0; + smp_wmb(); + } + + /* alter the thread keyring */ + if (!uid_eq(new->fsuid, old->fsuid)) + key_fsuid_changed(task); + if (!gid_eq(new->fsgid, old->fsgid)) + key_fsgid_changed(task); + + /* do it + * RLIMIT_NPROC limits on user->processes have already been checked + * in set_user(). + */ + alter_cred_subscribers(new, 2); + if (new->user != old->user) + atomic_inc(&new->user->processes); + rcu_assign_pointer(task->real_cred, new); + rcu_assign_pointer(task->cred, new); + if (new->user != old->user) + atomic_dec(&old->user->processes); + alter_cred_subscribers(old, -2); + + /* send notifications */ + if (!uid_eq(new->uid, old->uid) || + !uid_eq(new->euid, old->euid) || + !uid_eq(new->suid, old->suid) || + !uid_eq(new->fsuid, old->fsuid)) + proc_id_connector(task, PROC_EVENT_UID); + + if (!gid_eq(new->gid, old->gid) || + !gid_eq(new->egid, old->egid) || + !gid_eq(new->sgid, old->sgid) || + !gid_eq(new->fsgid, old->fsgid)) + proc_id_connector(task, PROC_EVENT_GID); + + /* release the old obj and subj refs both */ + put_cred(old); + put_cred(old); + return 0; +} +EXPORT_SYMBOL(commit_creds); + +/** + * abort_creds - Discard a set of credentials and unlock the current task + * @new: The credentials that were going to be applied + * + * Discard a set of credentials that were under construction and unlock the + * current task. + */ +void abort_creds(struct cred *new) +{ + kdebug("abort_creds(%p{%d,%d})", new, + atomic_read(&new->usage), + read_cred_subscribers(new)); + +#ifdef CONFIG_DEBUG_CREDENTIALS + BUG_ON(read_cred_subscribers(new) != 0); +#endif + BUG_ON(atomic_read(&new->usage) < 1); + put_cred(new); +} +EXPORT_SYMBOL(abort_creds); + +/** + * override_creds - Override the current process's subjective credentials + * @new: The credentials to be assigned + * + * Install a set of temporary override subjective credentials on the current + * process, returning the old set for later reversion. + */ +const struct cred *override_creds(const struct cred *new) +{ + const struct cred *old = current->cred; + + kdebug("override_creds(%p{%d,%d})", new, + atomic_read(&new->usage), + read_cred_subscribers(new)); + + validate_creds(old); + validate_creds(new); + get_cred(new); + alter_cred_subscribers(new, 1); + rcu_assign_pointer(current->cred, new); + alter_cred_subscribers(old, -1); + + kdebug("override_creds() = %p{%d,%d}", old, + atomic_read(&old->usage), + read_cred_subscribers(old)); + return old; +} +EXPORT_SYMBOL(override_creds); + +/** + * revert_creds - Revert a temporary subjective credentials override + * @old: The credentials to be restored + * + * Revert a temporary set of override subjective credentials to an old set, + * discarding the override set. + */ +void revert_creds(const struct cred *old) +{ + const struct cred *override = current->cred; + + kdebug("revert_creds(%p{%d,%d})", old, + atomic_read(&old->usage), + read_cred_subscribers(old)); + + validate_creds(old); + validate_creds(override); + alter_cred_subscribers(old, 1); + rcu_assign_pointer(current->cred, old); + alter_cred_subscribers(override, -1); + put_cred(override); +} +EXPORT_SYMBOL(revert_creds); + +/* + * initialise the credentials stuff + */ +void __init cred_init(void) +{ + /* allocate a slab in which we can store credentials */ + cred_jar = kmem_cache_create("cred_jar", sizeof(struct cred), + 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL); +} + +/** + * prepare_kernel_cred - Prepare a set of credentials for a kernel service + * @daemon: A userspace daemon to be used as a reference + * + * Prepare a set of credentials for a kernel service. This can then be used to + * override a task's own credentials so that work can be done on behalf of that + * task that requires a different subjective context. + * + * @daemon is used to provide a base for the security record, but can be NULL. + * If @daemon is supplied, then the security data will be derived from that; + * otherwise they'll be set to 0 and no groups, full capabilities and no keys. + * + * The caller may change these controls afterwards if desired. + * + * Returns the new credentials or NULL if out of memory. + * + * Does not take, and does not return holding current->cred_replace_mutex. + */ +struct cred *prepare_kernel_cred(struct task_struct *daemon) +{ + const struct cred *old; + struct cred *new; + + new = kmem_cache_alloc(cred_jar, GFP_KERNEL); + if (!new) + return NULL; + + kdebug("prepare_kernel_cred() alloc %p", new); + + if (daemon) + old = get_task_cred(daemon); + else + old = get_cred(&init_cred); + + validate_creds(old); + + *new = *old; + atomic_set(&new->usage, 1); + set_cred_subscribers(new, 0); + get_uid(new->user); + get_user_ns(new->user_ns); + get_group_info(new->group_info); + +#ifdef CONFIG_KEYS + new->session_keyring = NULL; + new->process_keyring = NULL; + new->thread_keyring = NULL; + new->request_key_auth = NULL; + new->jit_keyring = KEY_REQKEY_DEFL_THREAD_KEYRING; +#endif + +#ifdef CONFIG_SECURITY + new->security = NULL; +#endif + if (security_prepare_creds(new, old, GFP_KERNEL) < 0) + goto error; + + put_cred(old); + validate_creds(new); + return new; + +error: + put_cred(new); + put_cred(old); + return NULL; +} +EXPORT_SYMBOL(prepare_kernel_cred); + +/** + * set_security_override - Set the security ID in a set of credentials + * @new: The credentials to alter + * @secid: The LSM security ID to set + * + * Set the LSM security ID in a set of credentials so that the subjective + * security is overridden when an alternative set of credentials is used. + */ +int set_security_override(struct cred *new, u32 secid) +{ + return security_kernel_act_as(new, secid); +} +EXPORT_SYMBOL(set_security_override); + +/** + * set_security_override_from_ctx - Set the security ID in a set of credentials + * @new: The credentials to alter + * @secctx: The LSM security context to generate the security ID from. + * + * Set the LSM security ID in a set of credentials so that the subjective + * security is overridden when an alternative set of credentials is used. The + * security ID is specified in string form as a security context to be + * interpreted by the LSM. + */ +int set_security_override_from_ctx(struct cred *new, const char *secctx) +{ + u32 secid; + int ret; + + ret = security_secctx_to_secid(secctx, strlen(secctx), &secid); + if (ret < 0) + return ret; + + return set_security_override(new, secid); +} +EXPORT_SYMBOL(set_security_override_from_ctx); + +/** + * set_create_files_as - Set the LSM file create context in a set of credentials + * @new: The credentials to alter + * @inode: The inode to take the context from + * + * Change the LSM file creation context in a set of credentials to be the same + * as the object context of the specified inode, so that the new inodes have + * the same MAC context as that inode. + */ +int set_create_files_as(struct cred *new, struct inode *inode) +{ + new->fsuid = inode->i_uid; + new->fsgid = inode->i_gid; + return security_kernel_create_files_as(new, inode); +} +EXPORT_SYMBOL(set_create_files_as); + +#ifdef CONFIG_DEBUG_CREDENTIALS + +bool creds_are_invalid(const struct cred *cred) +{ + if (cred->magic != CRED_MAGIC) + return true; +#ifdef CONFIG_SECURITY_SELINUX + /* + * cred->security == NULL if security_cred_alloc_blank() or + * security_prepare_creds() returned an error. + */ + if (selinux_is_enabled() && cred->security) { + if ((unsigned long) cred->security < PAGE_SIZE) + return true; + if ((*(u32 *)cred->security & 0xffffff00) == + (POISON_FREE << 24 | POISON_FREE << 16 | POISON_FREE << 8)) + return true; + } +#endif + return false; +} +EXPORT_SYMBOL(creds_are_invalid); + +/* + * dump invalid credentials + */ +static void dump_invalid_creds(const struct cred *cred, const char *label, + const struct task_struct *tsk) +{ + printk(KERN_ERR "CRED: %s credentials: %p %s%s%s\n", + label, cred, + cred == &init_cred ? "[init]" : "", + cred == tsk->real_cred ? "[real]" : "", + cred == tsk->cred ? "[eff]" : ""); + printk(KERN_ERR "CRED: ->magic=%x, put_addr=%p\n", + cred->magic, cred->put_addr); + printk(KERN_ERR "CRED: ->usage=%d, subscr=%d\n", + atomic_read(&cred->usage), + read_cred_subscribers(cred)); + printk(KERN_ERR "CRED: ->*uid = { %d,%d,%d,%d }\n", + from_kuid_munged(&init_user_ns, cred->uid), + from_kuid_munged(&init_user_ns, cred->euid), + from_kuid_munged(&init_user_ns, cred->suid), + from_kuid_munged(&init_user_ns, cred->fsuid)); + printk(KERN_ERR "CRED: ->*gid = { %d,%d,%d,%d }\n", + from_kgid_munged(&init_user_ns, cred->gid), + from_kgid_munged(&init_user_ns, cred->egid), + from_kgid_munged(&init_user_ns, cred->sgid), + from_kgid_munged(&init_user_ns, cred->fsgid)); +#ifdef CONFIG_SECURITY + printk(KERN_ERR "CRED: ->security is %p\n", cred->security); + if ((unsigned long) cred->security >= PAGE_SIZE && + (((unsigned long) cred->security & 0xffffff00) != + (POISON_FREE << 24 | POISON_FREE << 16 | POISON_FREE << 8))) + printk(KERN_ERR "CRED: ->security {%x, %x}\n", + ((u32*)cred->security)[0], + ((u32*)cred->security)[1]); +#endif +} + +/* + * report use of invalid credentials + */ +void __invalid_creds(const struct cred *cred, const char *file, unsigned line) +{ + printk(KERN_ERR "CRED: Invalid credentials\n"); + printk(KERN_ERR "CRED: At %s:%u\n", file, line); + dump_invalid_creds(cred, "Specified", current); + BUG(); +} +EXPORT_SYMBOL(__invalid_creds); + +/* + * check the credentials on a process + */ +void __validate_process_creds(struct task_struct *tsk, + const char *file, unsigned line) +{ + if (tsk->cred == tsk->real_cred) { + if (unlikely(read_cred_subscribers(tsk->cred) < 2 || + creds_are_invalid(tsk->cred))) + goto invalid_creds; + } else { + if (unlikely(read_cred_subscribers(tsk->real_cred) < 1 || + read_cred_subscribers(tsk->cred) < 1 || + creds_are_invalid(tsk->real_cred) || + creds_are_invalid(tsk->cred))) + goto invalid_creds; + } + return; + +invalid_creds: + printk(KERN_ERR "CRED: Invalid process credentials\n"); + printk(KERN_ERR "CRED: At %s:%u\n", file, line); + + dump_invalid_creds(tsk->real_cred, "Real", tsk); + if (tsk->cred != tsk->real_cred) + dump_invalid_creds(tsk->cred, "Effective", tsk); + else + printk(KERN_ERR "CRED: Effective creds == Real creds\n"); + BUG(); +} +EXPORT_SYMBOL(__validate_process_creds); + +/* + * check creds for do_exit() + */ +void validate_creds_for_do_exit(struct task_struct *tsk) +{ + kdebug("validate_creds_for_do_exit(%p,%p{%d,%d})", + tsk->real_cred, tsk->cred, + atomic_read(&tsk->cred->usage), + read_cred_subscribers(tsk->cred)); + + __validate_process_creds(tsk, __FILE__, __LINE__); +} + +#endif /* CONFIG_DEBUG_CREDENTIALS */ diff --git a/kernel/kernel/debug/Makefile b/kernel/kernel/debug/Makefile new file mode 100644 index 000000000..a85edc339 --- /dev/null +++ b/kernel/kernel/debug/Makefile @@ -0,0 +1,6 @@ +# +# Makefile for the linux kernel debugger +# + +obj-$(CONFIG_KGDB) += debug_core.o gdbstub.o +obj-$(CONFIG_KGDB_KDB) += kdb/ diff --git a/kernel/kernel/debug/debug_core.c b/kernel/kernel/debug/debug_core.c new file mode 100644 index 000000000..0874e2edd --- /dev/null +++ b/kernel/kernel/debug/debug_core.c @@ -0,0 +1,1088 @@ +/* + * Kernel Debug Core + * + * Maintainer: Jason Wessel + * + * Copyright (C) 2000-2001 VERITAS Software Corporation. + * Copyright (C) 2002-2004 Timesys Corporation + * Copyright (C) 2003-2004 Amit S. Kale + * Copyright (C) 2004 Pavel Machek + * Copyright (C) 2004-2006 Tom Rini + * Copyright (C) 2004-2006 LinSysSoft Technologies Pvt. Ltd. + * Copyright (C) 2005-2009 Wind River Systems, Inc. + * Copyright (C) 2007 MontaVista Software, Inc. + * Copyright (C) 2008 Red Hat, Inc., Ingo Molnar + * + * Contributors at various stages not listed above: + * Jason Wessel ( jason.wessel@windriver.com ) + * George Anzinger + * Anurekh Saxena (anurekh.saxena@timesys.com) + * Lake Stevens Instrument Division (Glenn Engel) + * Jim Kingdon, Cygnus Support. + * + * Original KGDB stub: David Grothe , + * Tigran Aivazian + * + * This file is licensed under the terms of the GNU General Public License + * version 2. This program is licensed "as is" without any warranty of any + * kind, whether express or implied. + */ + +#define pr_fmt(fmt) "KGDB: " fmt + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include + +#include "debug_core.h" + +static int kgdb_break_asap; + +struct debuggerinfo_struct kgdb_info[NR_CPUS]; + +/** + * kgdb_connected - Is a host GDB connected to us? + */ +int kgdb_connected; +EXPORT_SYMBOL_GPL(kgdb_connected); + +/* All the KGDB handlers are installed */ +int kgdb_io_module_registered; + +/* Guard for recursive entry */ +static int exception_level; + +struct kgdb_io *dbg_io_ops; +static DEFINE_SPINLOCK(kgdb_registration_lock); + +/* Action for the reboot notifiter, a global allow kdb to change it */ +static int kgdbreboot; +/* kgdb console driver is loaded */ +static int kgdb_con_registered; +/* determine if kgdb console output should be used */ +static int kgdb_use_con; +/* Flag for alternate operations for early debugging */ +bool dbg_is_early = true; +/* Next cpu to become the master debug core */ +int dbg_switch_cpu; + +/* Use kdb or gdbserver mode */ +int dbg_kdb_mode = 1; + +static int __init opt_kgdb_con(char *str) +{ + kgdb_use_con = 1; + return 0; +} + +early_param("kgdbcon", opt_kgdb_con); + +module_param(kgdb_use_con, int, 0644); +module_param(kgdbreboot, int, 0644); + +/* + * Holds information about breakpoints in a kernel. These breakpoints are + * added and removed by gdb. + */ +static struct kgdb_bkpt kgdb_break[KGDB_MAX_BREAKPOINTS] = { + [0 ... KGDB_MAX_BREAKPOINTS-1] = { .state = BP_UNDEFINED } +}; + +/* + * The CPU# of the active CPU, or -1 if none: + */ +atomic_t kgdb_active = ATOMIC_INIT(-1); +EXPORT_SYMBOL_GPL(kgdb_active); +static DEFINE_RAW_SPINLOCK(dbg_master_lock); +static DEFINE_RAW_SPINLOCK(dbg_slave_lock); + +/* + * We use NR_CPUs not PERCPU, in case kgdb is used to debug early + * bootup code (which might not have percpu set up yet): + */ +static atomic_t masters_in_kgdb; +static atomic_t slaves_in_kgdb; +static atomic_t kgdb_break_tasklet_var; +atomic_t kgdb_setting_breakpoint; + +struct task_struct *kgdb_usethread; +struct task_struct *kgdb_contthread; + +int kgdb_single_step; +static pid_t kgdb_sstep_pid; + +/* to keep track of the CPU which is doing the single stepping*/ +atomic_t kgdb_cpu_doing_single_step = ATOMIC_INIT(-1); + +/* + * If you are debugging a problem where roundup (the collection of + * all other CPUs) is a problem [this should be extremely rare], + * then use the nokgdbroundup option to avoid roundup. In that case + * the other CPUs might interfere with your debugging context, so + * use this with care: + */ +static int kgdb_do_roundup = 1; + +static int __init opt_nokgdbroundup(char *str) +{ + kgdb_do_roundup = 0; + + return 0; +} + +early_param("nokgdbroundup", opt_nokgdbroundup); + +/* + * Finally, some KGDB code :-) + */ + +/* + * Weak aliases for breakpoint management, + * can be overriden by architectures when needed: + */ +int __weak kgdb_arch_set_breakpoint(struct kgdb_bkpt *bpt) +{ + int err; + + err = probe_kernel_read(bpt->saved_instr, (char *)bpt->bpt_addr, + BREAK_INSTR_SIZE); + if (err) + return err; + err = probe_kernel_write((char *)bpt->bpt_addr, + arch_kgdb_ops.gdb_bpt_instr, BREAK_INSTR_SIZE); + return err; +} + +int __weak kgdb_arch_remove_breakpoint(struct kgdb_bkpt *bpt) +{ + return probe_kernel_write((char *)bpt->bpt_addr, + (char *)bpt->saved_instr, BREAK_INSTR_SIZE); +} + +int __weak kgdb_validate_break_address(unsigned long addr) +{ + struct kgdb_bkpt tmp; + int err; + /* Validate setting the breakpoint and then removing it. If the + * remove fails, the kernel needs to emit a bad message because we + * are deep trouble not being able to put things back the way we + * found them. + */ + tmp.bpt_addr = addr; + err = kgdb_arch_set_breakpoint(&tmp); + if (err) + return err; + err = kgdb_arch_remove_breakpoint(&tmp); + if (err) + pr_err("Critical breakpoint error, kernel memory destroyed at: %lx\n", + addr); + return err; +} + +unsigned long __weak kgdb_arch_pc(int exception, struct pt_regs *regs) +{ + return instruction_pointer(regs); +} + +int __weak kgdb_arch_init(void) +{ + return 0; +} + +int __weak kgdb_skipexception(int exception, struct pt_regs *regs) +{ + return 0; +} + +/* + * Some architectures need cache flushes when we set/clear a + * breakpoint: + */ +static void kgdb_flush_swbreak_addr(unsigned long addr) +{ + if (!CACHE_FLUSH_IS_SAFE) + return; + + if (current->mm) { + int i; + + for (i = 0; i < VMACACHE_SIZE; i++) { + if (!current->vmacache[i]) + continue; + flush_cache_range(current->vmacache[i], + addr, addr + BREAK_INSTR_SIZE); + } + } + + /* Force flush instruction cache if it was outside the mm */ + flush_icache_range(addr, addr + BREAK_INSTR_SIZE); +} + +/* + * SW breakpoint management: + */ +int dbg_activate_sw_breakpoints(void) +{ + int error; + int ret = 0; + int i; + + for (i = 0; i < KGDB_MAX_BREAKPOINTS; i++) { + if (kgdb_break[i].state != BP_SET) + continue; + + error = kgdb_arch_set_breakpoint(&kgdb_break[i]); + if (error) { + ret = error; + pr_info("BP install failed: %lx\n", + kgdb_break[i].bpt_addr); + continue; + } + + kgdb_flush_swbreak_addr(kgdb_break[i].bpt_addr); + kgdb_break[i].state = BP_ACTIVE; + } + return ret; +} + +int dbg_set_sw_break(unsigned long addr) +{ + int err = kgdb_validate_break_address(addr); + int breakno = -1; + int i; + + if (err) + return err; + + for (i = 0; i < KGDB_MAX_BREAKPOINTS; i++) { + if ((kgdb_break[i].state == BP_SET) && + (kgdb_break[i].bpt_addr == addr)) + return -EEXIST; + } + for (i = 0; i < KGDB_MAX_BREAKPOINTS; i++) { + if (kgdb_break[i].state == BP_REMOVED && + kgdb_break[i].bpt_addr == addr) { + breakno = i; + break; + } + } + + if (breakno == -1) { + for (i = 0; i < KGDB_MAX_BREAKPOINTS; i++) { + if (kgdb_break[i].state == BP_UNDEFINED) { + breakno = i; + break; + } + } + } + + if (breakno == -1) + return -E2BIG; + + kgdb_break[breakno].state = BP_SET; + kgdb_break[breakno].type = BP_BREAKPOINT; + kgdb_break[breakno].bpt_addr = addr; + + return 0; +} + +int dbg_deactivate_sw_breakpoints(void) +{ + int error; + int ret = 0; + int i; + + for (i = 0; i < KGDB_MAX_BREAKPOINTS; i++) { + if (kgdb_break[i].state != BP_ACTIVE) + continue; + error = kgdb_arch_remove_breakpoint(&kgdb_break[i]); + if (error) { + pr_info("BP remove failed: %lx\n", + kgdb_break[i].bpt_addr); + ret = error; + } + + kgdb_flush_swbreak_addr(kgdb_break[i].bpt_addr); + kgdb_break[i].state = BP_SET; + } + return ret; +} + +int dbg_remove_sw_break(unsigned long addr) +{ + int i; + + for (i = 0; i < KGDB_MAX_BREAKPOINTS; i++) { + if ((kgdb_break[i].state == BP_SET) && + (kgdb_break[i].bpt_addr == addr)) { + kgdb_break[i].state = BP_REMOVED; + return 0; + } + } + return -ENOENT; +} + +int kgdb_isremovedbreak(unsigned long addr) +{ + int i; + + for (i = 0; i < KGDB_MAX_BREAKPOINTS; i++) { + if ((kgdb_break[i].state == BP_REMOVED) && + (kgdb_break[i].bpt_addr == addr)) + return 1; + } + return 0; +} + +int dbg_remove_all_break(void) +{ + int error; + int i; + + /* Clear memory breakpoints. */ + for (i = 0; i < KGDB_MAX_BREAKPOINTS; i++) { + if (kgdb_break[i].state != BP_ACTIVE) + goto setundefined; + error = kgdb_arch_remove_breakpoint(&kgdb_break[i]); + if (error) + pr_err("breakpoint remove failed: %lx\n", + kgdb_break[i].bpt_addr); +setundefined: + kgdb_break[i].state = BP_UNDEFINED; + } + + /* Clear hardware breakpoints. */ + if (arch_kgdb_ops.remove_all_hw_break) + arch_kgdb_ops.remove_all_hw_break(); + + return 0; +} + +/* + * Return true if there is a valid kgdb I/O module. Also if no + * debugger is attached a message can be printed to the console about + * waiting for the debugger to attach. + * + * The print_wait argument is only to be true when called from inside + * the core kgdb_handle_exception, because it will wait for the + * debugger to attach. + */ +static int kgdb_io_ready(int print_wait) +{ + if (!dbg_io_ops) + return 0; + if (kgdb_connected) + return 1; + if (atomic_read(&kgdb_setting_breakpoint)) + return 1; + if (print_wait) { +#ifdef CONFIG_KGDB_KDB + if (!dbg_kdb_mode) + pr_crit("waiting... or $3#33 for KDB\n"); +#else + pr_crit("Waiting for remote debugger\n"); +#endif + } + return 1; +} + +static int kgdb_reenter_check(struct kgdb_state *ks) +{ + unsigned long addr; + + if (atomic_read(&kgdb_active) != raw_smp_processor_id()) + return 0; + + /* Panic on recursive debugger calls: */ + exception_level++; + addr = kgdb_arch_pc(ks->ex_vector, ks->linux_regs); + dbg_deactivate_sw_breakpoints(); + + /* + * If the break point removed ok at the place exception + * occurred, try to recover and print a warning to the end + * user because the user planted a breakpoint in a place that + * KGDB needs in order to function. + */ + if (dbg_remove_sw_break(addr) == 0) { + exception_level = 0; + kgdb_skipexception(ks->ex_vector, ks->linux_regs); + dbg_activate_sw_breakpoints(); + pr_crit("re-enter error: breakpoint removed %lx\n", addr); + WARN_ON_ONCE(1); + + return 1; + } + dbg_remove_all_break(); + kgdb_skipexception(ks->ex_vector, ks->linux_regs); + + if (exception_level > 1) { + dump_stack(); + panic("Recursive entry to debugger"); + } + + pr_crit("re-enter exception: ALL breakpoints killed\n"); +#ifdef CONFIG_KGDB_KDB + /* Allow kdb to debug itself one level */ + return 0; +#endif + dump_stack(); + panic("Recursive entry to debugger"); + + return 1; +} + +static void dbg_touch_watchdogs(void) +{ + touch_softlockup_watchdog_sync(); + clocksource_touch_watchdog(); + rcu_cpu_stall_reset(); +} + +static int kgdb_cpu_enter(struct kgdb_state *ks, struct pt_regs *regs, + int exception_state) +{ + unsigned long flags; + int sstep_tries = 100; + int error; + int cpu; + int trace_on = 0; + int online_cpus = num_online_cpus(); + u64 time_left; + + kgdb_info[ks->cpu].enter_kgdb++; + kgdb_info[ks->cpu].exception_state |= exception_state; + + if (exception_state == DCPU_WANT_MASTER) + atomic_inc(&masters_in_kgdb); + else + atomic_inc(&slaves_in_kgdb); + + if (arch_kgdb_ops.disable_hw_break) + arch_kgdb_ops.disable_hw_break(regs); + +acquirelock: + /* + * Interrupts will be restored by the 'trap return' code, except when + * single stepping. + */ + local_irq_save(flags); + + cpu = ks->cpu; + kgdb_info[cpu].debuggerinfo = regs; + kgdb_info[cpu].task = current; + kgdb_info[cpu].ret_state = 0; + kgdb_info[cpu].irq_depth = hardirq_count() >> HARDIRQ_SHIFT; + + /* Make sure the above info reaches the primary CPU */ + smp_mb(); + + if (exception_level == 1) { + if (raw_spin_trylock(&dbg_master_lock)) + atomic_xchg(&kgdb_active, cpu); + goto cpu_master_loop; + } + + /* + * CPU will loop if it is a slave or request to become a kgdb + * master cpu and acquire the kgdb_active lock: + */ + while (1) { +cpu_loop: + if (kgdb_info[cpu].exception_state & DCPU_NEXT_MASTER) { + kgdb_info[cpu].exception_state &= ~DCPU_NEXT_MASTER; + goto cpu_master_loop; + } else if (kgdb_info[cpu].exception_state & DCPU_WANT_MASTER) { + if (raw_spin_trylock(&dbg_master_lock)) { + atomic_xchg(&kgdb_active, cpu); + break; + } + } else if (kgdb_info[cpu].exception_state & DCPU_IS_SLAVE) { + if (!raw_spin_is_locked(&dbg_slave_lock)) + goto return_normal; + } else { +return_normal: + /* Return to normal operation by executing any + * hw breakpoint fixup. + */ + if (arch_kgdb_ops.correct_hw_break) + arch_kgdb_ops.correct_hw_break(); + if (trace_on) + tracing_on(); + kgdb_info[cpu].exception_state &= + ~(DCPU_WANT_MASTER | DCPU_IS_SLAVE); + kgdb_info[cpu].enter_kgdb--; + smp_mb__before_atomic(); + atomic_dec(&slaves_in_kgdb); + dbg_touch_watchdogs(); + local_irq_restore(flags); + return 0; + } + cpu_relax(); + } + + /* + * For single stepping, try to only enter on the processor + * that was single stepping. To guard against a deadlock, the + * kernel will only try for the value of sstep_tries before + * giving up and continuing on. + */ + if (atomic_read(&kgdb_cpu_doing_single_step) != -1 && + (kgdb_info[cpu].task && + kgdb_info[cpu].task->pid != kgdb_sstep_pid) && --sstep_tries) { + atomic_set(&kgdb_active, -1); + raw_spin_unlock(&dbg_master_lock); + dbg_touch_watchdogs(); + local_irq_restore(flags); + + goto acquirelock; + } + + if (!kgdb_io_ready(1)) { + kgdb_info[cpu].ret_state = 1; + goto kgdb_restore; /* No I/O connection, resume the system */ + } + + /* + * Don't enter if we have hit a removed breakpoint. + */ + if (kgdb_skipexception(ks->ex_vector, ks->linux_regs)) + goto kgdb_restore; + + /* Call the I/O driver's pre_exception routine */ + if (dbg_io_ops->pre_exception) + dbg_io_ops->pre_exception(); + + /* + * Get the passive CPU lock which will hold all the non-primary + * CPU in a spin state while the debugger is active + */ + if (!kgdb_single_step) + raw_spin_lock(&dbg_slave_lock); + +#ifdef CONFIG_SMP + /* If send_ready set, slaves are already waiting */ + if (ks->send_ready) + atomic_set(ks->send_ready, 1); + + /* Signal the other CPUs to enter kgdb_wait() */ + else if ((!kgdb_single_step) && kgdb_do_roundup) + kgdb_roundup_cpus(flags); +#endif + + /* + * Wait for the other CPUs to be notified and be waiting for us: + */ + time_left = loops_per_jiffy * HZ; + while (kgdb_do_roundup && --time_left && + (atomic_read(&masters_in_kgdb) + atomic_read(&slaves_in_kgdb)) != + online_cpus) + cpu_relax(); + if (!time_left) + pr_crit("Timed out waiting for secondary CPUs.\n"); + + /* + * At this point the primary processor is completely + * in the debugger and all secondary CPUs are quiescent + */ + dbg_deactivate_sw_breakpoints(); + kgdb_single_step = 0; + kgdb_contthread = current; + exception_level = 0; + trace_on = tracing_is_on(); + if (trace_on) + tracing_off(); + + while (1) { +cpu_master_loop: + if (dbg_kdb_mode) { + kgdb_connected = 1; + error = kdb_stub(ks); + if (error == -1) + continue; + kgdb_connected = 0; + } else { + error = gdb_serial_stub(ks); + } + + if (error == DBG_PASS_EVENT) { + dbg_kdb_mode = !dbg_kdb_mode; + } else if (error == DBG_SWITCH_CPU_EVENT) { + kgdb_info[dbg_switch_cpu].exception_state |= + DCPU_NEXT_MASTER; + goto cpu_loop; + } else { + kgdb_info[cpu].ret_state = error; + break; + } + } + + /* Call the I/O driver's post_exception routine */ + if (dbg_io_ops->post_exception) + dbg_io_ops->post_exception(); + + if (!kgdb_single_step) { + raw_spin_unlock(&dbg_slave_lock); + /* Wait till all the CPUs have quit from the debugger. */ + while (kgdb_do_roundup && atomic_read(&slaves_in_kgdb)) + cpu_relax(); + } + +kgdb_restore: + if (atomic_read(&kgdb_cpu_doing_single_step) != -1) { + int sstep_cpu = atomic_read(&kgdb_cpu_doing_single_step); + if (kgdb_info[sstep_cpu].task) + kgdb_sstep_pid = kgdb_info[sstep_cpu].task->pid; + else + kgdb_sstep_pid = 0; + } + if (arch_kgdb_ops.correct_hw_break) + arch_kgdb_ops.correct_hw_break(); + if (trace_on) + tracing_on(); + + kgdb_info[cpu].exception_state &= + ~(DCPU_WANT_MASTER | DCPU_IS_SLAVE); + kgdb_info[cpu].enter_kgdb--; + smp_mb__before_atomic(); + atomic_dec(&masters_in_kgdb); + /* Free kgdb_active */ + atomic_set(&kgdb_active, -1); + raw_spin_unlock(&dbg_master_lock); + dbg_touch_watchdogs(); + local_irq_restore(flags); + + return kgdb_info[cpu].ret_state; +} + +/* + * kgdb_handle_exception() - main entry point from a kernel exception + * + * Locking hierarchy: + * interface locks, if any (begin_session) + * kgdb lock (kgdb_active) + */ +int +kgdb_handle_exception(int evector, int signo, int ecode, struct pt_regs *regs) +{ + struct kgdb_state kgdb_var; + struct kgdb_state *ks = &kgdb_var; + int ret = 0; + + if (arch_kgdb_ops.enable_nmi) + arch_kgdb_ops.enable_nmi(0); + /* + * Avoid entering the debugger if we were triggered due to an oops + * but panic_timeout indicates the system should automatically + * reboot on panic. We don't want to get stuck waiting for input + * on such systems, especially if its "just" an oops. + */ + if (signo != SIGTRAP && panic_timeout) + return 1; + + memset(ks, 0, sizeof(struct kgdb_state)); + ks->cpu = raw_smp_processor_id(); + ks->ex_vector = evector; + ks->signo = signo; + ks->err_code = ecode; + ks->linux_regs = regs; + + if (kgdb_reenter_check(ks)) + goto out; /* Ouch, double exception ! */ + if (kgdb_info[ks->cpu].enter_kgdb != 0) + goto out; + + ret = kgdb_cpu_enter(ks, regs, DCPU_WANT_MASTER); +out: + if (arch_kgdb_ops.enable_nmi) + arch_kgdb_ops.enable_nmi(1); + return ret; +} + +/* + * GDB places a breakpoint at this function to know dynamically + * loaded objects. It's not defined static so that only one instance with this + * name exists in the kernel. + */ + +static int module_event(struct notifier_block *self, unsigned long val, + void *data) +{ + return 0; +} + +static struct notifier_block dbg_module_load_nb = { + .notifier_call = module_event, +}; + +int kgdb_nmicallback(int cpu, void *regs) +{ +#ifdef CONFIG_SMP + struct kgdb_state kgdb_var; + struct kgdb_state *ks = &kgdb_var; + + memset(ks, 0, sizeof(struct kgdb_state)); + ks->cpu = cpu; + ks->linux_regs = regs; + + if (kgdb_info[ks->cpu].enter_kgdb == 0 && + raw_spin_is_locked(&dbg_master_lock)) { + kgdb_cpu_enter(ks, regs, DCPU_IS_SLAVE); + return 0; + } +#endif + return 1; +} + +int kgdb_nmicallin(int cpu, int trapnr, void *regs, int err_code, + atomic_t *send_ready) +{ +#ifdef CONFIG_SMP + if (!kgdb_io_ready(0) || !send_ready) + return 1; + + if (kgdb_info[cpu].enter_kgdb == 0) { + struct kgdb_state kgdb_var; + struct kgdb_state *ks = &kgdb_var; + + memset(ks, 0, sizeof(struct kgdb_state)); + ks->cpu = cpu; + ks->ex_vector = trapnr; + ks->signo = SIGTRAP; + ks->err_code = err_code; + ks->linux_regs = regs; + ks->send_ready = send_ready; + kgdb_cpu_enter(ks, regs, DCPU_WANT_MASTER); + return 0; + } +#endif + return 1; +} + +static void kgdb_console_write(struct console *co, const char *s, + unsigned count) +{ + unsigned long flags; + + /* If we're debugging, or KGDB has not connected, don't try + * and print. */ + if (!kgdb_connected || atomic_read(&kgdb_active) != -1 || dbg_kdb_mode) + return; + + local_irq_save(flags); + gdbstub_msg_write(s, count); + local_irq_restore(flags); +} + +static struct console kgdbcons = { + .name = "kgdb", + .write = kgdb_console_write, + .flags = CON_PRINTBUFFER | CON_ENABLED, + .index = -1, +}; + +#ifdef CONFIG_MAGIC_SYSRQ +static void sysrq_handle_dbg(int key) +{ + if (!dbg_io_ops) { + pr_crit("ERROR: No KGDB I/O module available\n"); + return; + } + if (!kgdb_connected) { +#ifdef CONFIG_KGDB_KDB + if (!dbg_kdb_mode) + pr_crit("KGDB or $3#33 for KDB\n"); +#else + pr_crit("Entering KGDB\n"); +#endif + } + + kgdb_breakpoint(); +} + +static struct sysrq_key_op sysrq_dbg_op = { + .handler = sysrq_handle_dbg, + .help_msg = "debug(g)", + .action_msg = "DEBUG", +}; +#endif + +static int kgdb_panic_event(struct notifier_block *self, + unsigned long val, + void *data) +{ + /* + * Avoid entering the debugger if we were triggered due to a panic + * We don't want to get stuck waiting for input from user in such case. + * panic_timeout indicates the system should automatically + * reboot on panic. + */ + if (panic_timeout) + return NOTIFY_DONE; + + if (dbg_kdb_mode) + kdb_printf("PANIC: %s\n", (char *)data); + kgdb_breakpoint(); + return NOTIFY_DONE; +} + +static struct notifier_block kgdb_panic_event_nb = { + .notifier_call = kgdb_panic_event, + .priority = INT_MAX, +}; + +void __weak kgdb_arch_late(void) +{ +} + +void __init dbg_late_init(void) +{ + dbg_is_early = false; + if (kgdb_io_module_registered) + kgdb_arch_late(); + kdb_init(KDB_INIT_FULL); +} + +static int +dbg_notify_reboot(struct notifier_block *this, unsigned long code, void *x) +{ + /* + * Take the following action on reboot notify depending on value: + * 1 == Enter debugger + * 0 == [the default] detatch debug client + * -1 == Do nothing... and use this until the board resets + */ + switch (kgdbreboot) { + case 1: + kgdb_breakpoint(); + case -1: + goto done; + } + if (!dbg_kdb_mode) + gdbstub_exit(code); +done: + return NOTIFY_DONE; +} + +static struct notifier_block dbg_reboot_notifier = { + .notifier_call = dbg_notify_reboot, + .next = NULL, + .priority = INT_MAX, +}; + +static void kgdb_register_callbacks(void) +{ + if (!kgdb_io_module_registered) { + kgdb_io_module_registered = 1; + kgdb_arch_init(); + if (!dbg_is_early) + kgdb_arch_late(); + register_module_notifier(&dbg_module_load_nb); + register_reboot_notifier(&dbg_reboot_notifier); + atomic_notifier_chain_register(&panic_notifier_list, + &kgdb_panic_event_nb); +#ifdef CONFIG_MAGIC_SYSRQ + register_sysrq_key('g', &sysrq_dbg_op); +#endif + if (kgdb_use_con && !kgdb_con_registered) { + register_console(&kgdbcons); + kgdb_con_registered = 1; + } + } +} + +static void kgdb_unregister_callbacks(void) +{ + /* + * When this routine is called KGDB should unregister from the + * panic handler and clean up, making sure it is not handling any + * break exceptions at the time. + */ + if (kgdb_io_module_registered) { + kgdb_io_module_registered = 0; + unregister_reboot_notifier(&dbg_reboot_notifier); + unregister_module_notifier(&dbg_module_load_nb); + atomic_notifier_chain_unregister(&panic_notifier_list, + &kgdb_panic_event_nb); + kgdb_arch_exit(); +#ifdef CONFIG_MAGIC_SYSRQ + unregister_sysrq_key('g', &sysrq_dbg_op); +#endif + if (kgdb_con_registered) { + unregister_console(&kgdbcons); + kgdb_con_registered = 0; + } + } +} + +/* + * There are times a tasklet needs to be used vs a compiled in + * break point so as to cause an exception outside a kgdb I/O module, + * such as is the case with kgdboe, where calling a breakpoint in the + * I/O driver itself would be fatal. + */ +static void kgdb_tasklet_bpt(unsigned long ing) +{ + kgdb_breakpoint(); + atomic_set(&kgdb_break_tasklet_var, 0); +} + +static DECLARE_TASKLET(kgdb_tasklet_breakpoint, kgdb_tasklet_bpt, 0); + +void kgdb_schedule_breakpoint(void) +{ + if (atomic_read(&kgdb_break_tasklet_var) || + atomic_read(&kgdb_active) != -1 || + atomic_read(&kgdb_setting_breakpoint)) + return; + atomic_inc(&kgdb_break_tasklet_var); + tasklet_schedule(&kgdb_tasklet_breakpoint); +} +EXPORT_SYMBOL_GPL(kgdb_schedule_breakpoint); + +static void kgdb_initial_breakpoint(void) +{ + kgdb_break_asap = 0; + + pr_crit("Waiting for connection from remote gdb...\n"); + kgdb_breakpoint(); +} + +/** + * kgdb_register_io_module - register KGDB IO module + * @new_dbg_io_ops: the io ops vector + * + * Register it with the KGDB core. + */ +int kgdb_register_io_module(struct kgdb_io *new_dbg_io_ops) +{ + int err; + + spin_lock(&kgdb_registration_lock); + + if (dbg_io_ops) { + spin_unlock(&kgdb_registration_lock); + + pr_err("Another I/O driver is already registered with KGDB\n"); + return -EBUSY; + } + + if (new_dbg_io_ops->init) { + err = new_dbg_io_ops->init(); + if (err) { + spin_unlock(&kgdb_registration_lock); + return err; + } + } + + dbg_io_ops = new_dbg_io_ops; + + spin_unlock(&kgdb_registration_lock); + + pr_info("Registered I/O driver %s\n", new_dbg_io_ops->name); + + /* Arm KGDB now. */ + kgdb_register_callbacks(); + + if (kgdb_break_asap) + kgdb_initial_breakpoint(); + + return 0; +} +EXPORT_SYMBOL_GPL(kgdb_register_io_module); + +/** + * kkgdb_unregister_io_module - unregister KGDB IO module + * @old_dbg_io_ops: the io ops vector + * + * Unregister it with the KGDB core. + */ +void kgdb_unregister_io_module(struct kgdb_io *old_dbg_io_ops) +{ + BUG_ON(kgdb_connected); + + /* + * KGDB is no longer able to communicate out, so + * unregister our callbacks and reset state. + */ + kgdb_unregister_callbacks(); + + spin_lock(&kgdb_registration_lock); + + WARN_ON_ONCE(dbg_io_ops != old_dbg_io_ops); + dbg_io_ops = NULL; + + spin_unlock(&kgdb_registration_lock); + + pr_info("Unregistered I/O driver %s, debugger disabled\n", + old_dbg_io_ops->name); +} +EXPORT_SYMBOL_GPL(kgdb_unregister_io_module); + +int dbg_io_get_char(void) +{ + int ret = dbg_io_ops->read_char(); + if (ret == NO_POLL_CHAR) + return -1; + if (!dbg_kdb_mode) + return ret; + if (ret == 127) + return 8; + return ret; +} + +/** + * kgdb_breakpoint - generate breakpoint exception + * + * This function will generate a breakpoint exception. It is used at the + * beginning of a program to sync up with a debugger and can be used + * otherwise as a quick means to stop program execution and "break" into + * the debugger. + */ +noinline void kgdb_breakpoint(void) +{ + atomic_inc(&kgdb_setting_breakpoint); + wmb(); /* Sync point before breakpoint */ + arch_kgdb_breakpoint(); + wmb(); /* Sync point after breakpoint */ + atomic_dec(&kgdb_setting_breakpoint); +} +EXPORT_SYMBOL_GPL(kgdb_breakpoint); + +static int __init opt_kgdb_wait(char *str) +{ + kgdb_break_asap = 1; + + kdb_init(KDB_INIT_EARLY); + if (kgdb_io_module_registered) + kgdb_initial_breakpoint(); + + return 0; +} + +early_param("kgdbwait", opt_kgdb_wait); diff --git a/kernel/kernel/debug/debug_core.h b/kernel/kernel/debug/debug_core.h new file mode 100644 index 000000000..127d9bc49 --- /dev/null +++ b/kernel/kernel/debug/debug_core.h @@ -0,0 +1,85 @@ +/* + * Created by: Jason Wessel + * + * Copyright (c) 2009 Wind River Systems, Inc. All Rights Reserved. + * + * This file is licensed under the terms of the GNU General Public + * License version 2. This program is licensed "as is" without any + * warranty of any kind, whether express or implied. + */ + +#ifndef _DEBUG_CORE_H_ +#define _DEBUG_CORE_H_ +/* + * These are the private implementation headers between the kernel + * debugger core and the debugger front end code. + */ + +/* kernel debug core data structures */ +struct kgdb_state { + int ex_vector; + int signo; + int err_code; + int cpu; + int pass_exception; + unsigned long thr_query; + unsigned long threadid; + long kgdb_usethreadid; + struct pt_regs *linux_regs; + atomic_t *send_ready; +}; + +/* Exception state values */ +#define DCPU_WANT_MASTER 0x1 /* Waiting to become a master kgdb cpu */ +#define DCPU_NEXT_MASTER 0x2 /* Transition from one master cpu to another */ +#define DCPU_IS_SLAVE 0x4 /* Slave cpu enter exception */ +#define DCPU_SSTEP 0x8 /* CPU is single stepping */ + +struct debuggerinfo_struct { + void *debuggerinfo; + struct task_struct *task; + int exception_state; + int ret_state; + int irq_depth; + int enter_kgdb; +}; + +extern struct debuggerinfo_struct kgdb_info[]; + +/* kernel debug core break point routines */ +extern int dbg_remove_all_break(void); +extern int dbg_set_sw_break(unsigned long addr); +extern int dbg_remove_sw_break(unsigned long addr); +extern int dbg_activate_sw_breakpoints(void); +extern int dbg_deactivate_sw_breakpoints(void); + +/* polled character access to i/o module */ +extern int dbg_io_get_char(void); + +/* stub return value for switching between the gdbstub and kdb */ +#define DBG_PASS_EVENT -12345 +/* Switch from one cpu to another */ +#define DBG_SWITCH_CPU_EVENT -123456 +extern int dbg_switch_cpu; + +/* gdbstub interface functions */ +extern int gdb_serial_stub(struct kgdb_state *ks); +extern void gdbstub_msg_write(const char *s, int len); + +/* gdbstub functions used for kdb <-> gdbstub transition */ +extern int gdbstub_state(struct kgdb_state *ks, char *cmd); +extern int dbg_kdb_mode; + +#ifdef CONFIG_KGDB_KDB +extern int kdb_stub(struct kgdb_state *ks); +extern int kdb_parse(const char *cmdstr); +extern int kdb_common_init_state(struct kgdb_state *ks); +extern int kdb_common_deinit_state(void); +#else /* ! CONFIG_KGDB_KDB */ +static inline int kdb_stub(struct kgdb_state *ks) +{ + return DBG_PASS_EVENT; +} +#endif /* CONFIG_KGDB_KDB */ + +#endif /* _DEBUG_CORE_H_ */ diff --git a/kernel/kernel/debug/gdbstub.c b/kernel/kernel/debug/gdbstub.c new file mode 100644 index 000000000..19d9a578c --- /dev/null +++ b/kernel/kernel/debug/gdbstub.c @@ -0,0 +1,1145 @@ +/* + * Kernel Debug Core + * + * Maintainer: Jason Wessel + * + * Copyright (C) 2000-2001 VERITAS Software Corporation. + * Copyright (C) 2002-2004 Timesys Corporation + * Copyright (C) 2003-2004 Amit S. Kale + * Copyright (C) 2004 Pavel Machek + * Copyright (C) 2004-2006 Tom Rini + * Copyright (C) 2004-2006 LinSysSoft Technologies Pvt. Ltd. + * Copyright (C) 2005-2009 Wind River Systems, Inc. + * Copyright (C) 2007 MontaVista Software, Inc. + * Copyright (C) 2008 Red Hat, Inc., Ingo Molnar + * + * Contributors at various stages not listed above: + * Jason Wessel ( jason.wessel@windriver.com ) + * George Anzinger + * Anurekh Saxena (anurekh.saxena@timesys.com) + * Lake Stevens Instrument Division (Glenn Engel) + * Jim Kingdon, Cygnus Support. + * + * Original KGDB stub: David Grothe , + * Tigran Aivazian + * + * This file is licensed under the terms of the GNU General Public License + * version 2. This program is licensed "as is" without any warranty of any + * kind, whether express or implied. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include "debug_core.h" + +#define KGDB_MAX_THREAD_QUERY 17 + +/* Our I/O buffers. */ +static char remcom_in_buffer[BUFMAX]; +static char remcom_out_buffer[BUFMAX]; +static int gdbstub_use_prev_in_buf; +static int gdbstub_prev_in_buf_pos; + +/* Storage for the registers, in GDB format. */ +static unsigned long gdb_regs[(NUMREGBYTES + + sizeof(unsigned long) - 1) / + sizeof(unsigned long)]; + +/* + * GDB remote protocol parser: + */ + +#ifdef CONFIG_KGDB_KDB +static int gdbstub_read_wait(void) +{ + int ret = -1; + int i; + + if (unlikely(gdbstub_use_prev_in_buf)) { + if (gdbstub_prev_in_buf_pos < gdbstub_use_prev_in_buf) + return remcom_in_buffer[gdbstub_prev_in_buf_pos++]; + else + gdbstub_use_prev_in_buf = 0; + } + + /* poll any additional I/O interfaces that are defined */ + while (ret < 0) + for (i = 0; kdb_poll_funcs[i] != NULL; i++) { + ret = kdb_poll_funcs[i](); + if (ret > 0) + break; + } + return ret; +} +#else +static int gdbstub_read_wait(void) +{ + int ret = dbg_io_ops->read_char(); + while (ret == NO_POLL_CHAR) + ret = dbg_io_ops->read_char(); + return ret; +} +#endif +/* scan for the sequence $# */ +static void get_packet(char *buffer) +{ + unsigned char checksum; + unsigned char xmitcsum; + int count; + char ch; + + do { + /* + * Spin and wait around for the start character, ignore all + * other characters: + */ + while ((ch = (gdbstub_read_wait())) != '$') + /* nothing */; + + kgdb_connected = 1; + checksum = 0; + xmitcsum = -1; + + count = 0; + + /* + * now, read until a # or end of buffer is found: + */ + while (count < (BUFMAX - 1)) { + ch = gdbstub_read_wait(); + if (ch == '#') + break; + checksum = checksum + ch; + buffer[count] = ch; + count = count + 1; + } + + if (ch == '#') { + xmitcsum = hex_to_bin(gdbstub_read_wait()) << 4; + xmitcsum += hex_to_bin(gdbstub_read_wait()); + + if (checksum != xmitcsum) + /* failed checksum */ + dbg_io_ops->write_char('-'); + else + /* successful transfer */ + dbg_io_ops->write_char('+'); + if (dbg_io_ops->flush) + dbg_io_ops->flush(); + } + buffer[count] = 0; + } while (checksum != xmitcsum); +} + +/* + * Send the packet in buffer. + * Check for gdb connection if asked for. + */ +static void put_packet(char *buffer) +{ + unsigned char checksum; + int count; + char ch; + + /* + * $#. + */ + while (1) { + dbg_io_ops->write_char('$'); + checksum = 0; + count = 0; + + while ((ch = buffer[count])) { + dbg_io_ops->write_char(ch); + checksum += ch; + count++; + } + + dbg_io_ops->write_char('#'); + dbg_io_ops->write_char(hex_asc_hi(checksum)); + dbg_io_ops->write_char(hex_asc_lo(checksum)); + if (dbg_io_ops->flush) + dbg_io_ops->flush(); + + /* Now see what we get in reply. */ + ch = gdbstub_read_wait(); + + if (ch == 3) + ch = gdbstub_read_wait(); + + /* If we get an ACK, we are done. */ + if (ch == '+') + return; + + /* + * If we get the start of another packet, this means + * that GDB is attempting to reconnect. We will NAK + * the packet being sent, and stop trying to send this + * packet. + */ + if (ch == '$') { + dbg_io_ops->write_char('-'); + if (dbg_io_ops->flush) + dbg_io_ops->flush(); + return; + } + } +} + +static char gdbmsgbuf[BUFMAX + 1]; + +void gdbstub_msg_write(const char *s, int len) +{ + char *bufptr; + int wcount; + int i; + + if (len == 0) + len = strlen(s); + + /* 'O'utput */ + gdbmsgbuf[0] = 'O'; + + /* Fill and send buffers... */ + while (len > 0) { + bufptr = gdbmsgbuf + 1; + + /* Calculate how many this time */ + if ((len << 1) > (BUFMAX - 2)) + wcount = (BUFMAX - 2) >> 1; + else + wcount = len; + + /* Pack in hex chars */ + for (i = 0; i < wcount; i++) + bufptr = hex_byte_pack(bufptr, s[i]); + *bufptr = '\0'; + + /* Move up */ + s += wcount; + len -= wcount; + + /* Write packet */ + put_packet(gdbmsgbuf); + } +} + +/* + * Convert the memory pointed to by mem into hex, placing result in + * buf. Return a pointer to the last char put in buf (null). May + * return an error. + */ +char *kgdb_mem2hex(char *mem, char *buf, int count) +{ + char *tmp; + int err; + + /* + * We use the upper half of buf as an intermediate buffer for the + * raw memory copy. Hex conversion will work against this one. + */ + tmp = buf + count; + + err = probe_kernel_read(tmp, mem, count); + if (err) + return NULL; + while (count > 0) { + buf = hex_byte_pack(buf, *tmp); + tmp++; + count--; + } + *buf = 0; + + return buf; +} + +/* + * Convert the hex array pointed to by buf into binary to be placed in + * mem. Return a pointer to the character AFTER the last byte + * written. May return an error. + */ +int kgdb_hex2mem(char *buf, char *mem, int count) +{ + char *tmp_raw; + char *tmp_hex; + + /* + * We use the upper half of buf as an intermediate buffer for the + * raw memory that is converted from hex. + */ + tmp_raw = buf + count * 2; + + tmp_hex = tmp_raw - 1; + while (tmp_hex >= buf) { + tmp_raw--; + *tmp_raw = hex_to_bin(*tmp_hex--); + *tmp_raw |= hex_to_bin(*tmp_hex--) << 4; + } + + return probe_kernel_write(mem, tmp_raw, count); +} + +/* + * While we find nice hex chars, build a long_val. + * Return number of chars processed. + */ +int kgdb_hex2long(char **ptr, unsigned long *long_val) +{ + int hex_val; + int num = 0; + int negate = 0; + + *long_val = 0; + + if (**ptr == '-') { + negate = 1; + (*ptr)++; + } + while (**ptr) { + hex_val = hex_to_bin(**ptr); + if (hex_val < 0) + break; + + *long_val = (*long_val << 4) | hex_val; + num++; + (*ptr)++; + } + + if (negate) + *long_val = -*long_val; + + return num; +} + +/* + * Copy the binary array pointed to by buf into mem. Fix $, #, and + * 0x7d escaped with 0x7d. Return -EFAULT on failure or 0 on success. + * The input buf is overwitten with the result to write to mem. + */ +static int kgdb_ebin2mem(char *buf, char *mem, int count) +{ + int size = 0; + char *c = buf; + + while (count-- > 0) { + c[size] = *buf++; + if (c[size] == 0x7d) + c[size] = *buf++ ^ 0x20; + size++; + } + + return probe_kernel_write(mem, c, size); +} + +#if DBG_MAX_REG_NUM > 0 +void pt_regs_to_gdb_regs(unsigned long *gdb_regs, struct pt_regs *regs) +{ + int i; + int idx = 0; + char *ptr = (char *)gdb_regs; + + for (i = 0; i < DBG_MAX_REG_NUM; i++) { + dbg_get_reg(i, ptr + idx, regs); + idx += dbg_reg_def[i].size; + } +} + +void gdb_regs_to_pt_regs(unsigned long *gdb_regs, struct pt_regs *regs) +{ + int i; + int idx = 0; + char *ptr = (char *)gdb_regs; + + for (i = 0; i < DBG_MAX_REG_NUM; i++) { + dbg_set_reg(i, ptr + idx, regs); + idx += dbg_reg_def[i].size; + } +} +#endif /* DBG_MAX_REG_NUM > 0 */ + +/* Write memory due to an 'M' or 'X' packet. */ +static int write_mem_msg(int binary) +{ + char *ptr = &remcom_in_buffer[1]; + unsigned long addr; + unsigned long length; + int err; + + if (kgdb_hex2long(&ptr, &addr) > 0 && *(ptr++) == ',' && + kgdb_hex2long(&ptr, &length) > 0 && *(ptr++) == ':') { + if (binary) + err = kgdb_ebin2mem(ptr, (char *)addr, length); + else + err = kgdb_hex2mem(ptr, (char *)addr, length); + if (err) + return err; + if (CACHE_FLUSH_IS_SAFE) + flush_icache_range(addr, addr + length); + return 0; + } + + return -EINVAL; +} + +static void error_packet(char *pkt, int error) +{ + error = -error; + pkt[0] = 'E'; + pkt[1] = hex_asc[(error / 10)]; + pkt[2] = hex_asc[(error % 10)]; + pkt[3] = '\0'; +} + +/* + * Thread ID accessors. We represent a flat TID space to GDB, where + * the per CPU idle threads (which under Linux all have PID 0) are + * remapped to negative TIDs. + */ + +#define BUF_THREAD_ID_SIZE 8 + +static char *pack_threadid(char *pkt, unsigned char *id) +{ + unsigned char *limit; + int lzero = 1; + + limit = id + (BUF_THREAD_ID_SIZE / 2); + while (id < limit) { + if (!lzero || *id != 0) { + pkt = hex_byte_pack(pkt, *id); + lzero = 0; + } + id++; + } + + if (lzero) + pkt = hex_byte_pack(pkt, 0); + + return pkt; +} + +static void int_to_threadref(unsigned char *id, int value) +{ + put_unaligned_be32(value, id); +} + +static struct task_struct *getthread(struct pt_regs *regs, int tid) +{ + /* + * Non-positive TIDs are remapped to the cpu shadow information + */ + if (tid == 0 || tid == -1) + tid = -atomic_read(&kgdb_active) - 2; + if (tid < -1 && tid > -NR_CPUS - 2) { + if (kgdb_info[-tid - 2].task) + return kgdb_info[-tid - 2].task; + else + return idle_task(-tid - 2); + } + if (tid <= 0) { + printk(KERN_ERR "KGDB: Internal thread select error\n"); + dump_stack(); + return NULL; + } + + /* + * find_task_by_pid_ns() does not take the tasklist lock anymore + * but is nicely RCU locked - hence is a pretty resilient + * thing to use: + */ + return find_task_by_pid_ns(tid, &init_pid_ns); +} + + +/* + * Remap normal tasks to their real PID, + * CPU shadow threads are mapped to -CPU - 2 + */ +static inline int shadow_pid(int realpid) +{ + if (realpid) + return realpid; + + return -raw_smp_processor_id() - 2; +} + +/* + * All the functions that start with gdb_cmd are the various + * operations to implement the handlers for the gdbserial protocol + * where KGDB is communicating with an external debugger + */ + +/* Handle the '?' status packets */ +static void gdb_cmd_status(struct kgdb_state *ks) +{ + /* + * We know that this packet is only sent + * during initial connect. So to be safe, + * we clear out our breakpoints now in case + * GDB is reconnecting. + */ + dbg_remove_all_break(); + + remcom_out_buffer[0] = 'S'; + hex_byte_pack(&remcom_out_buffer[1], ks->signo); +} + +static void gdb_get_regs_helper(struct kgdb_state *ks) +{ + struct task_struct *thread; + void *local_debuggerinfo; + int i; + + thread = kgdb_usethread; + if (!thread) { + thread = kgdb_info[ks->cpu].task; + local_debuggerinfo = kgdb_info[ks->cpu].debuggerinfo; + } else { + local_debuggerinfo = NULL; + for_each_online_cpu(i) { + /* + * Try to find the task on some other + * or possibly this node if we do not + * find the matching task then we try + * to approximate the results. + */ + if (thread == kgdb_info[i].task) + local_debuggerinfo = kgdb_info[i].debuggerinfo; + } + } + + /* + * All threads that don't have debuggerinfo should be + * in schedule() sleeping, since all other CPUs + * are in kgdb_wait, and thus have debuggerinfo. + */ + if (local_debuggerinfo) { + pt_regs_to_gdb_regs(gdb_regs, local_debuggerinfo); + } else { + /* + * Pull stuff saved during switch_to; nothing + * else is accessible (or even particularly + * relevant). + * + * This should be enough for a stack trace. + */ + sleeping_thread_to_gdb_regs(gdb_regs, thread); + } +} + +/* Handle the 'g' get registers request */ +static void gdb_cmd_getregs(struct kgdb_state *ks) +{ + gdb_get_regs_helper(ks); + kgdb_mem2hex((char *)gdb_regs, remcom_out_buffer, NUMREGBYTES); +} + +/* Handle the 'G' set registers request */ +static void gdb_cmd_setregs(struct kgdb_state *ks) +{ + kgdb_hex2mem(&remcom_in_buffer[1], (char *)gdb_regs, NUMREGBYTES); + + if (kgdb_usethread && kgdb_usethread != current) { + error_packet(remcom_out_buffer, -EINVAL); + } else { + gdb_regs_to_pt_regs(gdb_regs, ks->linux_regs); + strcpy(remcom_out_buffer, "OK"); + } +} + +/* Handle the 'm' memory read bytes */ +static void gdb_cmd_memread(struct kgdb_state *ks) +{ + char *ptr = &remcom_in_buffer[1]; + unsigned long length; + unsigned long addr; + char *err; + + if (kgdb_hex2long(&ptr, &addr) > 0 && *ptr++ == ',' && + kgdb_hex2long(&ptr, &length) > 0) { + err = kgdb_mem2hex((char *)addr, remcom_out_buffer, length); + if (!err) + error_packet(remcom_out_buffer, -EINVAL); + } else { + error_packet(remcom_out_buffer, -EINVAL); + } +} + +/* Handle the 'M' memory write bytes */ +static void gdb_cmd_memwrite(struct kgdb_state *ks) +{ + int err = write_mem_msg(0); + + if (err) + error_packet(remcom_out_buffer, err); + else + strcpy(remcom_out_buffer, "OK"); +} + +#if DBG_MAX_REG_NUM > 0 +static char *gdb_hex_reg_helper(int regnum, char *out) +{ + int i; + int offset = 0; + + for (i = 0; i < regnum; i++) + offset += dbg_reg_def[i].size; + return kgdb_mem2hex((char *)gdb_regs + offset, out, + dbg_reg_def[i].size); +} + +/* Handle the 'p' individual regster get */ +static void gdb_cmd_reg_get(struct kgdb_state *ks) +{ + unsigned long regnum; + char *ptr = &remcom_in_buffer[1]; + + kgdb_hex2long(&ptr, ®num); + if (regnum >= DBG_MAX_REG_NUM) { + error_packet(remcom_out_buffer, -EINVAL); + return; + } + gdb_get_regs_helper(ks); + gdb_hex_reg_helper(regnum, remcom_out_buffer); +} + +/* Handle the 'P' individual regster set */ +static void gdb_cmd_reg_set(struct kgdb_state *ks) +{ + unsigned long regnum; + char *ptr = &remcom_in_buffer[1]; + int i = 0; + + kgdb_hex2long(&ptr, ®num); + if (*ptr++ != '=' || + !(!kgdb_usethread || kgdb_usethread == current) || + !dbg_get_reg(regnum, gdb_regs, ks->linux_regs)) { + error_packet(remcom_out_buffer, -EINVAL); + return; + } + memset(gdb_regs, 0, sizeof(gdb_regs)); + while (i < sizeof(gdb_regs) * 2) + if (hex_to_bin(ptr[i]) >= 0) + i++; + else + break; + i = i / 2; + kgdb_hex2mem(ptr, (char *)gdb_regs, i); + dbg_set_reg(regnum, gdb_regs, ks->linux_regs); + strcpy(remcom_out_buffer, "OK"); +} +#endif /* DBG_MAX_REG_NUM > 0 */ + +/* Handle the 'X' memory binary write bytes */ +static void gdb_cmd_binwrite(struct kgdb_state *ks) +{ + int err = write_mem_msg(1); + + if (err) + error_packet(remcom_out_buffer, err); + else + strcpy(remcom_out_buffer, "OK"); +} + +/* Handle the 'D' or 'k', detach or kill packets */ +static void gdb_cmd_detachkill(struct kgdb_state *ks) +{ + int error; + + /* The detach case */ + if (remcom_in_buffer[0] == 'D') { + error = dbg_remove_all_break(); + if (error < 0) { + error_packet(remcom_out_buffer, error); + } else { + strcpy(remcom_out_buffer, "OK"); + kgdb_connected = 0; + } + put_packet(remcom_out_buffer); + } else { + /* + * Assume the kill case, with no exit code checking, + * trying to force detach the debugger: + */ + dbg_remove_all_break(); + kgdb_connected = 0; + } +} + +/* Handle the 'R' reboot packets */ +static int gdb_cmd_reboot(struct kgdb_state *ks) +{ + /* For now, only honor R0 */ + if (strcmp(remcom_in_buffer, "R0") == 0) { + printk(KERN_CRIT "Executing emergency reboot\n"); + strcpy(remcom_out_buffer, "OK"); + put_packet(remcom_out_buffer); + + /* + * Execution should not return from + * machine_emergency_restart() + */ + machine_emergency_restart(); + kgdb_connected = 0; + + return 1; + } + return 0; +} + +/* Handle the 'q' query packets */ +static void gdb_cmd_query(struct kgdb_state *ks) +{ + struct task_struct *g; + struct task_struct *p; + unsigned char thref[BUF_THREAD_ID_SIZE]; + char *ptr; + int i; + int cpu; + int finished = 0; + + switch (remcom_in_buffer[1]) { + case 's': + case 'f': + if (memcmp(remcom_in_buffer + 2, "ThreadInfo", 10)) + break; + + i = 0; + remcom_out_buffer[0] = 'm'; + ptr = remcom_out_buffer + 1; + if (remcom_in_buffer[1] == 'f') { + /* Each cpu is a shadow thread */ + for_each_online_cpu(cpu) { + ks->thr_query = 0; + int_to_threadref(thref, -cpu - 2); + ptr = pack_threadid(ptr, thref); + *(ptr++) = ','; + i++; + } + } + + do_each_thread(g, p) { + if (i >= ks->thr_query && !finished) { + int_to_threadref(thref, p->pid); + ptr = pack_threadid(ptr, thref); + *(ptr++) = ','; + ks->thr_query++; + if (ks->thr_query % KGDB_MAX_THREAD_QUERY == 0) + finished = 1; + } + i++; + } while_each_thread(g, p); + + *(--ptr) = '\0'; + break; + + case 'C': + /* Current thread id */ + strcpy(remcom_out_buffer, "QC"); + ks->threadid = shadow_pid(current->pid); + int_to_threadref(thref, ks->threadid); + pack_threadid(remcom_out_buffer + 2, thref); + break; + case 'T': + if (memcmp(remcom_in_buffer + 1, "ThreadExtraInfo,", 16)) + break; + + ks->threadid = 0; + ptr = remcom_in_buffer + 17; + kgdb_hex2long(&ptr, &ks->threadid); + if (!getthread(ks->linux_regs, ks->threadid)) { + error_packet(remcom_out_buffer, -EINVAL); + break; + } + if ((int)ks->threadid > 0) { + kgdb_mem2hex(getthread(ks->linux_regs, + ks->threadid)->comm, + remcom_out_buffer, 16); + } else { + static char tmpstr[23 + BUF_THREAD_ID_SIZE]; + + sprintf(tmpstr, "shadowCPU%d", + (int)(-ks->threadid - 2)); + kgdb_mem2hex(tmpstr, remcom_out_buffer, strlen(tmpstr)); + } + break; +#ifdef CONFIG_KGDB_KDB + case 'R': + if (strncmp(remcom_in_buffer, "qRcmd,", 6) == 0) { + int len = strlen(remcom_in_buffer + 6); + + if ((len % 2) != 0) { + strcpy(remcom_out_buffer, "E01"); + break; + } + kgdb_hex2mem(remcom_in_buffer + 6, + remcom_out_buffer, len); + len = len / 2; + remcom_out_buffer[len++] = 0; + + kdb_common_init_state(ks); + kdb_parse(remcom_out_buffer); + kdb_common_deinit_state(); + + strcpy(remcom_out_buffer, "OK"); + } + break; +#endif + } +} + +/* Handle the 'H' task query packets */ +static void gdb_cmd_task(struct kgdb_state *ks) +{ + struct task_struct *thread; + char *ptr; + + switch (remcom_in_buffer[1]) { + case 'g': + ptr = &remcom_in_buffer[2]; + kgdb_hex2long(&ptr, &ks->threadid); + thread = getthread(ks->linux_regs, ks->threadid); + if (!thread && ks->threadid > 0) { + error_packet(remcom_out_buffer, -EINVAL); + break; + } + kgdb_usethread = thread; + ks->kgdb_usethreadid = ks->threadid; + strcpy(remcom_out_buffer, "OK"); + break; + case 'c': + ptr = &remcom_in_buffer[2]; + kgdb_hex2long(&ptr, &ks->threadid); + if (!ks->threadid) { + kgdb_contthread = NULL; + } else { + thread = getthread(ks->linux_regs, ks->threadid); + if (!thread && ks->threadid > 0) { + error_packet(remcom_out_buffer, -EINVAL); + break; + } + kgdb_contthread = thread; + } + strcpy(remcom_out_buffer, "OK"); + break; + } +} + +/* Handle the 'T' thread query packets */ +static void gdb_cmd_thread(struct kgdb_state *ks) +{ + char *ptr = &remcom_in_buffer[1]; + struct task_struct *thread; + + kgdb_hex2long(&ptr, &ks->threadid); + thread = getthread(ks->linux_regs, ks->threadid); + if (thread) + strcpy(remcom_out_buffer, "OK"); + else + error_packet(remcom_out_buffer, -EINVAL); +} + +/* Handle the 'z' or 'Z' breakpoint remove or set packets */ +static void gdb_cmd_break(struct kgdb_state *ks) +{ + /* + * Since GDB-5.3, it's been drafted that '0' is a software + * breakpoint, '1' is a hardware breakpoint, so let's do that. + */ + char *bpt_type = &remcom_in_buffer[1]; + char *ptr = &remcom_in_buffer[2]; + unsigned long addr; + unsigned long length; + int error = 0; + + if (arch_kgdb_ops.set_hw_breakpoint && *bpt_type >= '1') { + /* Unsupported */ + if (*bpt_type > '4') + return; + } else { + if (*bpt_type != '0' && *bpt_type != '1') + /* Unsupported. */ + return; + } + + /* + * Test if this is a hardware breakpoint, and + * if we support it: + */ + if (*bpt_type == '1' && !(arch_kgdb_ops.flags & KGDB_HW_BREAKPOINT)) + /* Unsupported. */ + return; + + if (*(ptr++) != ',') { + error_packet(remcom_out_buffer, -EINVAL); + return; + } + if (!kgdb_hex2long(&ptr, &addr)) { + error_packet(remcom_out_buffer, -EINVAL); + return; + } + if (*(ptr++) != ',' || + !kgdb_hex2long(&ptr, &length)) { + error_packet(remcom_out_buffer, -EINVAL); + return; + } + + if (remcom_in_buffer[0] == 'Z' && *bpt_type == '0') + error = dbg_set_sw_break(addr); + else if (remcom_in_buffer[0] == 'z' && *bpt_type == '0') + error = dbg_remove_sw_break(addr); + else if (remcom_in_buffer[0] == 'Z') + error = arch_kgdb_ops.set_hw_breakpoint(addr, + (int)length, *bpt_type - '0'); + else if (remcom_in_buffer[0] == 'z') + error = arch_kgdb_ops.remove_hw_breakpoint(addr, + (int) length, *bpt_type - '0'); + + if (error == 0) + strcpy(remcom_out_buffer, "OK"); + else + error_packet(remcom_out_buffer, error); +} + +/* Handle the 'C' signal / exception passing packets */ +static int gdb_cmd_exception_pass(struct kgdb_state *ks) +{ + /* C09 == pass exception + * C15 == detach kgdb, pass exception + */ + if (remcom_in_buffer[1] == '0' && remcom_in_buffer[2] == '9') { + + ks->pass_exception = 1; + remcom_in_buffer[0] = 'c'; + + } else if (remcom_in_buffer[1] == '1' && remcom_in_buffer[2] == '5') { + + ks->pass_exception = 1; + remcom_in_buffer[0] = 'D'; + dbg_remove_all_break(); + kgdb_connected = 0; + return 1; + + } else { + gdbstub_msg_write("KGDB only knows signal 9 (pass)" + " and 15 (pass and disconnect)\n" + "Executing a continue without signal passing\n", 0); + remcom_in_buffer[0] = 'c'; + } + + /* Indicate fall through */ + return -1; +} + +/* + * This function performs all gdbserial command procesing + */ +int gdb_serial_stub(struct kgdb_state *ks) +{ + int error = 0; + int tmp; + + /* Initialize comm buffer and globals. */ + memset(remcom_out_buffer, 0, sizeof(remcom_out_buffer)); + kgdb_usethread = kgdb_info[ks->cpu].task; + ks->kgdb_usethreadid = shadow_pid(kgdb_info[ks->cpu].task->pid); + ks->pass_exception = 0; + + if (kgdb_connected) { + unsigned char thref[BUF_THREAD_ID_SIZE]; + char *ptr; + + /* Reply to host that an exception has occurred */ + ptr = remcom_out_buffer; + *ptr++ = 'T'; + ptr = hex_byte_pack(ptr, ks->signo); + ptr += strlen(strcpy(ptr, "thread:")); + int_to_threadref(thref, shadow_pid(current->pid)); + ptr = pack_threadid(ptr, thref); + *ptr++ = ';'; + put_packet(remcom_out_buffer); + } + + while (1) { + error = 0; + + /* Clear the out buffer. */ + memset(remcom_out_buffer, 0, sizeof(remcom_out_buffer)); + + get_packet(remcom_in_buffer); + + switch (remcom_in_buffer[0]) { + case '?': /* gdbserial status */ + gdb_cmd_status(ks); + break; + case 'g': /* return the value of the CPU registers */ + gdb_cmd_getregs(ks); + break; + case 'G': /* set the value of the CPU registers - return OK */ + gdb_cmd_setregs(ks); + break; + case 'm': /* mAA..AA,LLLL Read LLLL bytes at address AA..AA */ + gdb_cmd_memread(ks); + break; + case 'M': /* MAA..AA,LLLL: Write LLLL bytes at address AA..AA */ + gdb_cmd_memwrite(ks); + break; +#if DBG_MAX_REG_NUM > 0 + case 'p': /* pXX Return gdb register XX (in hex) */ + gdb_cmd_reg_get(ks); + break; + case 'P': /* PXX=aaaa Set gdb register XX to aaaa (in hex) */ + gdb_cmd_reg_set(ks); + break; +#endif /* DBG_MAX_REG_NUM > 0 */ + case 'X': /* XAA..AA,LLLL: Write LLLL bytes at address AA..AA */ + gdb_cmd_binwrite(ks); + break; + /* kill or detach. KGDB should treat this like a + * continue. + */ + case 'D': /* Debugger detach */ + case 'k': /* Debugger detach via kill */ + gdb_cmd_detachkill(ks); + goto default_handle; + case 'R': /* Reboot */ + if (gdb_cmd_reboot(ks)) + goto default_handle; + break; + case 'q': /* query command */ + gdb_cmd_query(ks); + break; + case 'H': /* task related */ + gdb_cmd_task(ks); + break; + case 'T': /* Query thread status */ + gdb_cmd_thread(ks); + break; + case 'z': /* Break point remove */ + case 'Z': /* Break point set */ + gdb_cmd_break(ks); + break; +#ifdef CONFIG_KGDB_KDB + case '3': /* Escape into back into kdb */ + if (remcom_in_buffer[1] == '\0') { + gdb_cmd_detachkill(ks); + return DBG_PASS_EVENT; + } +#endif + case 'C': /* Exception passing */ + tmp = gdb_cmd_exception_pass(ks); + if (tmp > 0) + goto default_handle; + if (tmp == 0) + break; + /* Fall through on tmp < 0 */ + case 'c': /* Continue packet */ + case 's': /* Single step packet */ + if (kgdb_contthread && kgdb_contthread != current) { + /* Can't switch threads in kgdb */ + error_packet(remcom_out_buffer, -EINVAL); + break; + } + dbg_activate_sw_breakpoints(); + /* Fall through to default processing */ + default: +default_handle: + error = kgdb_arch_handle_exception(ks->ex_vector, + ks->signo, + ks->err_code, + remcom_in_buffer, + remcom_out_buffer, + ks->linux_regs); + /* + * Leave cmd processing on error, detach, + * kill, continue, or single step. + */ + if (error >= 0 || remcom_in_buffer[0] == 'D' || + remcom_in_buffer[0] == 'k') { + error = 0; + goto kgdb_exit; + } + + } + + /* reply to the request */ + put_packet(remcom_out_buffer); + } + +kgdb_exit: + if (ks->pass_exception) + error = 1; + return error; +} + +int gdbstub_state(struct kgdb_state *ks, char *cmd) +{ + int error; + + switch (cmd[0]) { + case 'e': + error = kgdb_arch_handle_exception(ks->ex_vector, + ks->signo, + ks->err_code, + remcom_in_buffer, + remcom_out_buffer, + ks->linux_regs); + return error; + case 's': + case 'c': + strcpy(remcom_in_buffer, cmd); + return 0; + case '$': + strcpy(remcom_in_buffer, cmd); + gdbstub_use_prev_in_buf = strlen(remcom_in_buffer); + gdbstub_prev_in_buf_pos = 0; + return 0; + } + dbg_io_ops->write_char('+'); + put_packet(remcom_out_buffer); + return 0; +} + +/** + * gdbstub_exit - Send an exit message to GDB + * @status: The exit code to report. + */ +void gdbstub_exit(int status) +{ + unsigned char checksum, ch, buffer[3]; + int loop; + + if (!kgdb_connected) + return; + kgdb_connected = 0; + + if (!dbg_io_ops || dbg_kdb_mode) + return; + + buffer[0] = 'W'; + buffer[1] = hex_asc_hi(status); + buffer[2] = hex_asc_lo(status); + + dbg_io_ops->write_char('$'); + checksum = 0; + + for (loop = 0; loop < 3; loop++) { + ch = buffer[loop]; + checksum += ch; + dbg_io_ops->write_char(ch); + } + + dbg_io_ops->write_char('#'); + dbg_io_ops->write_char(hex_asc_hi(checksum)); + dbg_io_ops->write_char(hex_asc_lo(checksum)); + + /* make sure the output is flushed, lest the bootloader clobber it */ + if (dbg_io_ops->flush) + dbg_io_ops->flush(); +} diff --git a/kernel/kernel/debug/kdb/.gitignore b/kernel/kernel/debug/kdb/.gitignore new file mode 100644 index 000000000..396d12eda --- /dev/null +++ b/kernel/kernel/debug/kdb/.gitignore @@ -0,0 +1 @@ +gen-kdb_cmds.c diff --git a/kernel/kernel/debug/kdb/Makefile b/kernel/kernel/debug/kdb/Makefile new file mode 100644 index 000000000..d4fc58f4b --- /dev/null +++ b/kernel/kernel/debug/kdb/Makefile @@ -0,0 +1,25 @@ +# This file is subject to the terms and conditions of the GNU General Public +# License. See the file "COPYING" in the main directory of this archive +# for more details. +# +# Copyright (c) 1999-2004 Silicon Graphics, Inc. All Rights Reserved. +# Copyright (c) 2009 Wind River Systems, Inc. All Rights Reserved. +# + +CCVERSION := $(shell $(CC) -v 2>&1 | sed -ne '$$p') +obj-y := kdb_io.o kdb_main.o kdb_support.o kdb_bt.o gen-kdb_cmds.o kdb_bp.o kdb_debugger.o +obj-$(CONFIG_KDB_KEYBOARD) += kdb_keyboard.o + +clean-files := gen-kdb_cmds.c + +quiet_cmd_gen-kdb = GENKDB $@ + cmd_gen-kdb = $(AWK) 'BEGIN {print "\#include "; print "\#include "} \ + /^\#/{next} \ + /^[ \t]*$$/{next} \ + {gsub(/"/, "\\\"", $$0); \ + print "static __initdata char kdb_cmd" cmds++ "[] = \"" $$0 "\\n\";"} \ + END {print "extern char *kdb_cmds[]; char __initdata *kdb_cmds[] = {"; for (i = 0; i < cmds; ++i) {print " kdb_cmd" i ","}; print(" NULL\n};");}' \ + $(filter-out %/Makefile,$^) > $@# + +$(obj)/gen-kdb_cmds.c: $(src)/kdb_cmds $(src)/Makefile + $(call cmd,gen-kdb) diff --git a/kernel/kernel/debug/kdb/kdb_bp.c b/kernel/kernel/debug/kdb/kdb_bp.c new file mode 100644 index 000000000..e1dbf4a2c --- /dev/null +++ b/kernel/kernel/debug/kdb/kdb_bp.c @@ -0,0 +1,560 @@ +/* + * Kernel Debugger Architecture Independent Breakpoint Handler + * + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file "COPYING" in the main directory of this archive + * for more details. + * + * Copyright (c) 1999-2004 Silicon Graphics, Inc. All Rights Reserved. + * Copyright (c) 2009 Wind River Systems, Inc. All Rights Reserved. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include "kdb_private.h" + +/* + * Table of kdb_breakpoints + */ +kdb_bp_t kdb_breakpoints[KDB_MAXBPT]; + +static void kdb_setsinglestep(struct pt_regs *regs) +{ + KDB_STATE_SET(DOING_SS); +} + +static char *kdb_rwtypes[] = { + "Instruction(i)", + "Instruction(Register)", + "Data Write", + "I/O", + "Data Access" +}; + +static char *kdb_bptype(kdb_bp_t *bp) +{ + if (bp->bp_type < 0 || bp->bp_type > 4) + return ""; + + return kdb_rwtypes[bp->bp_type]; +} + +static int kdb_parsebp(int argc, const char **argv, int *nextargp, kdb_bp_t *bp) +{ + int nextarg = *nextargp; + int diag; + + bp->bph_length = 1; + if ((argc + 1) != nextarg) { + if (strncasecmp(argv[nextarg], "datar", sizeof("datar")) == 0) + bp->bp_type = BP_ACCESS_WATCHPOINT; + else if (strncasecmp(argv[nextarg], "dataw", sizeof("dataw")) == 0) + bp->bp_type = BP_WRITE_WATCHPOINT; + else if (strncasecmp(argv[nextarg], "inst", sizeof("inst")) == 0) + bp->bp_type = BP_HARDWARE_BREAKPOINT; + else + return KDB_ARGCOUNT; + + bp->bph_length = 1; + + nextarg++; + + if ((argc + 1) != nextarg) { + unsigned long len; + + diag = kdbgetularg((char *)argv[nextarg], + &len); + if (diag) + return diag; + + + if (len > 8) + return KDB_BADLENGTH; + + bp->bph_length = len; + nextarg++; + } + + if ((argc + 1) != nextarg) + return KDB_ARGCOUNT; + } + + *nextargp = nextarg; + return 0; +} + +static int _kdb_bp_remove(kdb_bp_t *bp) +{ + int ret = 1; + if (!bp->bp_installed) + return ret; + if (!bp->bp_type) + ret = dbg_remove_sw_break(bp->bp_addr); + else + ret = arch_kgdb_ops.remove_hw_breakpoint(bp->bp_addr, + bp->bph_length, + bp->bp_type); + if (ret == 0) + bp->bp_installed = 0; + return ret; +} + +static void kdb_handle_bp(struct pt_regs *regs, kdb_bp_t *bp) +{ + if (KDB_DEBUG(BP)) + kdb_printf("regs->ip = 0x%lx\n", instruction_pointer(regs)); + + /* + * Setup single step + */ + kdb_setsinglestep(regs); + + /* + * Reset delay attribute + */ + bp->bp_delay = 0; + bp->bp_delayed = 1; +} + +static int _kdb_bp_install(struct pt_regs *regs, kdb_bp_t *bp) +{ + int ret; + /* + * Install the breakpoint, if it is not already installed. + */ + + if (KDB_DEBUG(BP)) + kdb_printf("%s: bp_installed %d\n", + __func__, bp->bp_installed); + if (!KDB_STATE(SSBPT)) + bp->bp_delay = 0; + if (bp->bp_installed) + return 1; + if (bp->bp_delay || (bp->bp_delayed && KDB_STATE(DOING_SS))) { + if (KDB_DEBUG(BP)) + kdb_printf("%s: delayed bp\n", __func__); + kdb_handle_bp(regs, bp); + return 0; + } + if (!bp->bp_type) + ret = dbg_set_sw_break(bp->bp_addr); + else + ret = arch_kgdb_ops.set_hw_breakpoint(bp->bp_addr, + bp->bph_length, + bp->bp_type); + if (ret == 0) { + bp->bp_installed = 1; + } else { + kdb_printf("%s: failed to set breakpoint at 0x%lx\n", + __func__, bp->bp_addr); +#ifdef CONFIG_DEBUG_RODATA + if (!bp->bp_type) { + kdb_printf("Software breakpoints are unavailable.\n" + " Change the kernel CONFIG_DEBUG_RODATA=n\n" + " OR use hw breaks: help bph\n"); + } +#endif + return 1; + } + return 0; +} + +/* + * kdb_bp_install + * + * Install kdb_breakpoints prior to returning from the + * kernel debugger. This allows the kdb_breakpoints to be set + * upon functions that are used internally by kdb, such as + * printk(). This function is only called once per kdb session. + */ +void kdb_bp_install(struct pt_regs *regs) +{ + int i; + + for (i = 0; i < KDB_MAXBPT; i++) { + kdb_bp_t *bp = &kdb_breakpoints[i]; + + if (KDB_DEBUG(BP)) { + kdb_printf("%s: bp %d bp_enabled %d\n", + __func__, i, bp->bp_enabled); + } + if (bp->bp_enabled) + _kdb_bp_install(regs, bp); + } +} + +/* + * kdb_bp_remove + * + * Remove kdb_breakpoints upon entry to the kernel debugger. + * + * Parameters: + * None. + * Outputs: + * None. + * Returns: + * None. + * Locking: + * None. + * Remarks: + */ +void kdb_bp_remove(void) +{ + int i; + + for (i = KDB_MAXBPT - 1; i >= 0; i--) { + kdb_bp_t *bp = &kdb_breakpoints[i]; + + if (KDB_DEBUG(BP)) { + kdb_printf("%s: bp %d bp_enabled %d\n", + __func__, i, bp->bp_enabled); + } + if (bp->bp_enabled) + _kdb_bp_remove(bp); + } +} + + +/* + * kdb_printbp + * + * Internal function to format and print a breakpoint entry. + * + * Parameters: + * None. + * Outputs: + * None. + * Returns: + * None. + * Locking: + * None. + * Remarks: + */ + +static void kdb_printbp(kdb_bp_t *bp, int i) +{ + kdb_printf("%s ", kdb_bptype(bp)); + kdb_printf("BP #%d at ", i); + kdb_symbol_print(bp->bp_addr, NULL, KDB_SP_DEFAULT); + + if (bp->bp_enabled) + kdb_printf("\n is enabled"); + else + kdb_printf("\n is disabled"); + + kdb_printf("\taddr at %016lx, hardtype=%d installed=%d\n", + bp->bp_addr, bp->bp_type, bp->bp_installed); + + kdb_printf("\n"); +} + +/* + * kdb_bp + * + * Handle the bp commands. + * + * [bp|bph] [DATAR|DATAW] + * + * Parameters: + * argc Count of arguments in argv + * argv Space delimited command line arguments + * Outputs: + * None. + * Returns: + * Zero for success, a kdb diagnostic if failure. + * Locking: + * None. + * Remarks: + * + * bp Set breakpoint on all cpus. Only use hardware assist if need. + * bph Set breakpoint on all cpus. Force hardware register + */ + +static int kdb_bp(int argc, const char **argv) +{ + int i, bpno; + kdb_bp_t *bp, *bp_check; + int diag; + char *symname = NULL; + long offset = 0ul; + int nextarg; + kdb_bp_t template = {0}; + + if (argc == 0) { + /* + * Display breakpoint table + */ + for (bpno = 0, bp = kdb_breakpoints; bpno < KDB_MAXBPT; + bpno++, bp++) { + if (bp->bp_free) + continue; + kdb_printbp(bp, bpno); + } + + return 0; + } + + nextarg = 1; + diag = kdbgetaddrarg(argc, argv, &nextarg, &template.bp_addr, + &offset, &symname); + if (diag) + return diag; + if (!template.bp_addr) + return KDB_BADINT; + + /* + * Find an empty bp structure to allocate + */ + for (bpno = 0, bp = kdb_breakpoints; bpno < KDB_MAXBPT; bpno++, bp++) { + if (bp->bp_free) + break; + } + + if (bpno == KDB_MAXBPT) + return KDB_TOOMANYBPT; + + if (strcmp(argv[0], "bph") == 0) { + template.bp_type = BP_HARDWARE_BREAKPOINT; + diag = kdb_parsebp(argc, argv, &nextarg, &template); + if (diag) + return diag; + } else { + template.bp_type = BP_BREAKPOINT; + } + + /* + * Check for clashing breakpoints. + * + * Note, in this design we can't have hardware breakpoints + * enabled for both read and write on the same address. + */ + for (i = 0, bp_check = kdb_breakpoints; i < KDB_MAXBPT; + i++, bp_check++) { + if (!bp_check->bp_free && + bp_check->bp_addr == template.bp_addr) { + kdb_printf("You already have a breakpoint at " + kdb_bfd_vma_fmt0 "\n", template.bp_addr); + return KDB_DUPBPT; + } + } + + template.bp_enabled = 1; + + /* + * Actually allocate the breakpoint found earlier + */ + *bp = template; + bp->bp_free = 0; + + kdb_printbp(bp, bpno); + + return 0; +} + +/* + * kdb_bc + * + * Handles the 'bc', 'be', and 'bd' commands + * + * [bd|bc|be] + * [bd|bc|be] * + * + * Parameters: + * argc Count of arguments in argv + * argv Space delimited command line arguments + * Outputs: + * None. + * Returns: + * Zero for success, a kdb diagnostic for failure + * Locking: + * None. + * Remarks: + */ +static int kdb_bc(int argc, const char **argv) +{ + unsigned long addr; + kdb_bp_t *bp = NULL; + int lowbp = KDB_MAXBPT; + int highbp = 0; + int done = 0; + int i; + int diag = 0; + + int cmd; /* KDBCMD_B? */ +#define KDBCMD_BC 0 +#define KDBCMD_BE 1 +#define KDBCMD_BD 2 + + if (strcmp(argv[0], "be") == 0) + cmd = KDBCMD_BE; + else if (strcmp(argv[0], "bd") == 0) + cmd = KDBCMD_BD; + else + cmd = KDBCMD_BC; + + if (argc != 1) + return KDB_ARGCOUNT; + + if (strcmp(argv[1], "*") == 0) { + lowbp = 0; + highbp = KDB_MAXBPT; + } else { + diag = kdbgetularg(argv[1], &addr); + if (diag) + return diag; + + /* + * For addresses less than the maximum breakpoint number, + * assume that the breakpoint number is desired. + */ + if (addr < KDB_MAXBPT) { + bp = &kdb_breakpoints[addr]; + lowbp = highbp = addr; + highbp++; + } else { + for (i = 0, bp = kdb_breakpoints; i < KDB_MAXBPT; + i++, bp++) { + if (bp->bp_addr == addr) { + lowbp = highbp = i; + highbp++; + break; + } + } + } + } + + /* + * Now operate on the set of breakpoints matching the input + * criteria (either '*' for all, or an individual breakpoint). + */ + for (bp = &kdb_breakpoints[lowbp], i = lowbp; + i < highbp; + i++, bp++) { + if (bp->bp_free) + continue; + + done++; + + switch (cmd) { + case KDBCMD_BC: + bp->bp_enabled = 0; + + kdb_printf("Breakpoint %d at " + kdb_bfd_vma_fmt " cleared\n", + i, bp->bp_addr); + + bp->bp_addr = 0; + bp->bp_free = 1; + + break; + case KDBCMD_BE: + bp->bp_enabled = 1; + + kdb_printf("Breakpoint %d at " + kdb_bfd_vma_fmt " enabled", + i, bp->bp_addr); + + kdb_printf("\n"); + break; + case KDBCMD_BD: + if (!bp->bp_enabled) + break; + + bp->bp_enabled = 0; + + kdb_printf("Breakpoint %d at " + kdb_bfd_vma_fmt " disabled\n", + i, bp->bp_addr); + + break; + } + if (bp->bp_delay && (cmd == KDBCMD_BC || cmd == KDBCMD_BD)) { + bp->bp_delay = 0; + KDB_STATE_CLEAR(SSBPT); + } + } + + return (!done) ? KDB_BPTNOTFOUND : 0; +} + +/* + * kdb_ss + * + * Process the 'ss' (Single Step) command. + * + * ss + * + * Parameters: + * argc Argument count + * argv Argument vector + * Outputs: + * None. + * Returns: + * KDB_CMD_SS for success, a kdb error if failure. + * Locking: + * None. + * Remarks: + * + * Set the arch specific option to trigger a debug trap after the next + * instruction. + */ + +static int kdb_ss(int argc, const char **argv) +{ + if (argc != 0) + return KDB_ARGCOUNT; + /* + * Set trace flag and go. + */ + KDB_STATE_SET(DOING_SS); + return KDB_CMD_SS; +} + +/* Initialize the breakpoint table and register breakpoint commands. */ + +void __init kdb_initbptab(void) +{ + int i; + kdb_bp_t *bp; + + /* + * First time initialization. + */ + memset(&kdb_breakpoints, '\0', sizeof(kdb_breakpoints)); + + for (i = 0, bp = kdb_breakpoints; i < KDB_MAXBPT; i++, bp++) + bp->bp_free = 1; + + kdb_register_flags("bp", kdb_bp, "[]", + "Set/Display breakpoints", 0, + KDB_ENABLE_FLOW_CTRL | KDB_REPEAT_NO_ARGS); + kdb_register_flags("bl", kdb_bp, "[]", + "Display breakpoints", 0, + KDB_ENABLE_FLOW_CTRL | KDB_REPEAT_NO_ARGS); + if (arch_kgdb_ops.flags & KGDB_HW_BREAKPOINT) + kdb_register_flags("bph", kdb_bp, "[]", + "[datar [length]|dataw [length]] Set hw brk", 0, + KDB_ENABLE_FLOW_CTRL | KDB_REPEAT_NO_ARGS); + kdb_register_flags("bc", kdb_bc, "", + "Clear Breakpoint", 0, + KDB_ENABLE_FLOW_CTRL); + kdb_register_flags("be", kdb_bc, "", + "Enable Breakpoint", 0, + KDB_ENABLE_FLOW_CTRL); + kdb_register_flags("bd", kdb_bc, "", + "Disable Breakpoint", 0, + KDB_ENABLE_FLOW_CTRL); + + kdb_register_flags("ss", kdb_ss, "", + "Single Step", 1, + KDB_ENABLE_FLOW_CTRL | KDB_REPEAT_NO_ARGS); + /* + * Architecture dependent initialization. + */ +} diff --git a/kernel/kernel/debug/kdb/kdb_bt.c b/kernel/kernel/debug/kdb/kdb_bt.c new file mode 100644 index 000000000..fe15fff5d --- /dev/null +++ b/kernel/kernel/debug/kdb/kdb_bt.c @@ -0,0 +1,210 @@ +/* + * Kernel Debugger Architecture Independent Stack Traceback + * + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file "COPYING" in the main directory of this archive + * for more details. + * + * Copyright (c) 1999-2004 Silicon Graphics, Inc. All Rights Reserved. + * Copyright (c) 2009 Wind River Systems, Inc. All Rights Reserved. + */ + +#include +#include +#include +#include +#include +#include +#include "kdb_private.h" + + +static void kdb_show_stack(struct task_struct *p, void *addr) +{ + int old_lvl = console_loglevel; + console_loglevel = CONSOLE_LOGLEVEL_MOTORMOUTH; + kdb_trap_printk++; + kdb_set_current_task(p); + if (addr) { + show_stack((struct task_struct *)p, addr); + } else if (kdb_current_regs) { +#ifdef CONFIG_X86 + show_stack(p, &kdb_current_regs->sp); +#else + show_stack(p, NULL); +#endif + } else { + show_stack(p, NULL); + } + console_loglevel = old_lvl; + kdb_trap_printk--; +} + +/* + * kdb_bt + * + * This function implements the 'bt' command. Print a stack + * traceback. + * + * bt [] (addr-exp is for alternate stacks) + * btp Kernel stack for + * btt Kernel stack for task structure at + * + * bta [DRSTCZEUIMA] All useful processes, optionally + * filtered by state + * btc [] The current process on one cpu, + * default is all cpus + * + * bt refers to a address on the stack, that location + * is assumed to contain a return address. + * + * btt refers to the address of a struct task. + * + * Inputs: + * argc argument count + * argv argument vector + * Outputs: + * None. + * Returns: + * zero for success, a kdb diagnostic if error + * Locking: + * none. + * Remarks: + * Backtrack works best when the code uses frame pointers. But even + * without frame pointers we should get a reasonable trace. + * + * mds comes in handy when examining the stack to do a manual traceback or + * to get a starting point for bt . + */ + +static int +kdb_bt1(struct task_struct *p, unsigned long mask, + int argcount, int btaprompt) +{ + char buffer[2]; + if (kdb_getarea(buffer[0], (unsigned long)p) || + kdb_getarea(buffer[0], (unsigned long)(p+1)-1)) + return KDB_BADADDR; + if (!kdb_task_state(p, mask)) + return 0; + kdb_printf("Stack traceback for pid %d\n", p->pid); + kdb_ps1(p); + kdb_show_stack(p, NULL); + if (btaprompt) { + kdb_getstr(buffer, sizeof(buffer), + "Enter to end, to continue:"); + if (buffer[0] == 'q') { + kdb_printf("\n"); + return 1; + } + } + touch_nmi_watchdog(); + return 0; +} + +int +kdb_bt(int argc, const char **argv) +{ + int diag; + int argcount = 5; + int btaprompt = 1; + int nextarg; + unsigned long addr; + long offset; + + /* Prompt after each proc in bta */ + kdbgetintenv("BTAPROMPT", &btaprompt); + + if (strcmp(argv[0], "bta") == 0) { + struct task_struct *g, *p; + unsigned long cpu; + unsigned long mask = kdb_task_state_string(argc ? argv[1] : + NULL); + if (argc == 0) + kdb_ps_suppressed(); + /* Run the active tasks first */ + for_each_online_cpu(cpu) { + p = kdb_curr_task(cpu); + if (kdb_bt1(p, mask, argcount, btaprompt)) + return 0; + } + /* Now the inactive tasks */ + kdb_do_each_thread(g, p) { + if (KDB_FLAG(CMD_INTERRUPT)) + return 0; + if (task_curr(p)) + continue; + if (kdb_bt1(p, mask, argcount, btaprompt)) + return 0; + } kdb_while_each_thread(g, p); + } else if (strcmp(argv[0], "btp") == 0) { + struct task_struct *p; + unsigned long pid; + if (argc != 1) + return KDB_ARGCOUNT; + diag = kdbgetularg((char *)argv[1], &pid); + if (diag) + return diag; + p = find_task_by_pid_ns(pid, &init_pid_ns); + if (p) { + kdb_set_current_task(p); + return kdb_bt1(p, ~0UL, argcount, 0); + } + kdb_printf("No process with pid == %ld found\n", pid); + return 0; + } else if (strcmp(argv[0], "btt") == 0) { + if (argc != 1) + return KDB_ARGCOUNT; + diag = kdbgetularg((char *)argv[1], &addr); + if (diag) + return diag; + kdb_set_current_task((struct task_struct *)addr); + return kdb_bt1((struct task_struct *)addr, ~0UL, argcount, 0); + } else if (strcmp(argv[0], "btc") == 0) { + unsigned long cpu = ~0; + struct task_struct *save_current_task = kdb_current_task; + char buf[80]; + if (argc > 1) + return KDB_ARGCOUNT; + if (argc == 1) { + diag = kdbgetularg((char *)argv[1], &cpu); + if (diag) + return diag; + } + /* Recursive use of kdb_parse, do not use argv after + * this point */ + argv = NULL; + if (cpu != ~0) { + if (cpu >= num_possible_cpus() || !cpu_online(cpu)) { + kdb_printf("no process for cpu %ld\n", cpu); + return 0; + } + sprintf(buf, "btt 0x%p\n", KDB_TSK(cpu)); + kdb_parse(buf); + return 0; + } + kdb_printf("btc: cpu status: "); + kdb_parse("cpu\n"); + for_each_online_cpu(cpu) { + sprintf(buf, "btt 0x%p\n", KDB_TSK(cpu)); + kdb_parse(buf); + touch_nmi_watchdog(); + } + kdb_set_current_task(save_current_task); + return 0; + } else { + if (argc) { + nextarg = 1; + diag = kdbgetaddrarg(argc, argv, &nextarg, &addr, + &offset, NULL); + if (diag) + return diag; + kdb_show_stack(kdb_current_task, (void *)addr); + return 0; + } else { + return kdb_bt1(kdb_current_task, ~0UL, argcount, 0); + } + } + + /* NOTREACHED */ + return 0; +} diff --git a/kernel/kernel/debug/kdb/kdb_cmds b/kernel/kernel/debug/kdb/kdb_cmds new file mode 100644 index 000000000..9834ad303 --- /dev/null +++ b/kernel/kernel/debug/kdb/kdb_cmds @@ -0,0 +1,31 @@ +# Initial commands for kdb, alter to suit your needs. +# These commands are executed in kdb_init() context, no SMP, no +# processes. Commands that require process data (including stack or +# registers) are not reliable this early. set and bp commands should +# be safe. Global breakpoint commands affect each cpu as it is booted. + +# Standard debugging information for first level support, just type archkdb +# or archkdbcpu or archkdbshort at the kdb prompt. + +defcmd dumpcommon "" "Common kdb debugging" + set BTAPROMPT 0 + set LINES 10000 + -summary + -cpu + -ps + -dmesg 600 + -bt +endefcmd + +defcmd dumpall "" "First line debugging" + pid R + -dumpcommon + -bta +endefcmd + +defcmd dumpcpu "" "Same as dumpall but only tasks on cpus" + pid R + -dumpcommon + -btc +endefcmd + diff --git a/kernel/kernel/debug/kdb/kdb_debugger.c b/kernel/kernel/debug/kdb/kdb_debugger.c new file mode 100644 index 000000000..15e1a7af5 --- /dev/null +++ b/kernel/kernel/debug/kdb/kdb_debugger.c @@ -0,0 +1,186 @@ +/* + * Created by: Jason Wessel + * + * Copyright (c) 2009 Wind River Systems, Inc. All Rights Reserved. + * + * This file is licensed under the terms of the GNU General Public + * License version 2. This program is licensed "as is" without any + * warranty of any kind, whether express or implied. + */ + +#include +#include +#include +#include +#include +#include "kdb_private.h" +#include "../debug_core.h" + +/* + * KDB interface to KGDB internals + */ +get_char_func kdb_poll_funcs[] = { + dbg_io_get_char, + NULL, + NULL, + NULL, + NULL, + NULL, +}; +EXPORT_SYMBOL_GPL(kdb_poll_funcs); + +int kdb_poll_idx = 1; +EXPORT_SYMBOL_GPL(kdb_poll_idx); + +static struct kgdb_state *kdb_ks; + +int kdb_common_init_state(struct kgdb_state *ks) +{ + kdb_initial_cpu = atomic_read(&kgdb_active); + kdb_current_task = kgdb_info[ks->cpu].task; + kdb_current_regs = kgdb_info[ks->cpu].debuggerinfo; + return 0; +} + +int kdb_common_deinit_state(void) +{ + kdb_initial_cpu = -1; + kdb_current_task = NULL; + kdb_current_regs = NULL; + return 0; +} + +int kdb_stub(struct kgdb_state *ks) +{ + int error = 0; + kdb_bp_t *bp; + unsigned long addr = kgdb_arch_pc(ks->ex_vector, ks->linux_regs); + kdb_reason_t reason = KDB_REASON_OOPS; + kdb_dbtrap_t db_result = KDB_DB_NOBPT; + int i; + + kdb_ks = ks; + if (KDB_STATE(REENTRY)) { + reason = KDB_REASON_SWITCH; + KDB_STATE_CLEAR(REENTRY); + addr = instruction_pointer(ks->linux_regs); + } + ks->pass_exception = 0; + if (atomic_read(&kgdb_setting_breakpoint)) + reason = KDB_REASON_KEYBOARD; + + if (ks->err_code == KDB_REASON_SYSTEM_NMI && ks->signo == SIGTRAP) + reason = KDB_REASON_SYSTEM_NMI; + + else if (in_nmi()) + reason = KDB_REASON_NMI; + + for (i = 0, bp = kdb_breakpoints; i < KDB_MAXBPT; i++, bp++) { + if ((bp->bp_enabled) && (bp->bp_addr == addr)) { + reason = KDB_REASON_BREAK; + db_result = KDB_DB_BPT; + if (addr != instruction_pointer(ks->linux_regs)) + kgdb_arch_set_pc(ks->linux_regs, addr); + break; + } + } + if (reason == KDB_REASON_BREAK || reason == KDB_REASON_SWITCH) { + for (i = 0, bp = kdb_breakpoints; i < KDB_MAXBPT; i++, bp++) { + if (bp->bp_free) + continue; + if (bp->bp_addr == addr) { + bp->bp_delay = 1; + bp->bp_delayed = 1; + /* + * SSBPT is set when the kernel debugger must single step a + * task in order to re-establish an instruction breakpoint + * which uses the instruction replacement mechanism. It is + * cleared by any action that removes the need to single-step + * the breakpoint. + */ + reason = KDB_REASON_BREAK; + db_result = KDB_DB_BPT; + KDB_STATE_SET(SSBPT); + break; + } + } + } + + if (reason != KDB_REASON_BREAK && ks->ex_vector == 0 && + ks->signo == SIGTRAP) { + reason = KDB_REASON_SSTEP; + db_result = KDB_DB_BPT; + } + /* Set initial kdb state variables */ + KDB_STATE_CLEAR(KGDB_TRANS); + kdb_common_init_state(ks); + /* Remove any breakpoints as needed by kdb and clear single step */ + kdb_bp_remove(); + KDB_STATE_CLEAR(DOING_SS); + KDB_STATE_SET(PAGER); + /* zero out any offline cpu data */ + for_each_present_cpu(i) { + if (!cpu_online(i)) { + kgdb_info[i].debuggerinfo = NULL; + kgdb_info[i].task = NULL; + } + } + if (ks->err_code == DIE_OOPS || reason == KDB_REASON_OOPS) { + ks->pass_exception = 1; + KDB_FLAG_SET(CATASTROPHIC); + } + /* set CATASTROPHIC if the system contains unresponsive processors */ + for_each_online_cpu(i) + if (!kgdb_info[i].enter_kgdb) + KDB_FLAG_SET(CATASTROPHIC); + if (KDB_STATE(SSBPT) && reason == KDB_REASON_SSTEP) { + KDB_STATE_CLEAR(SSBPT); + KDB_STATE_CLEAR(DOING_SS); + } else { + /* Start kdb main loop */ + error = kdb_main_loop(KDB_REASON_ENTER, reason, + ks->err_code, db_result, ks->linux_regs); + } + /* + * Upon exit from the kdb main loop setup break points and restart + * the system based on the requested continue state + */ + kdb_common_deinit_state(); + KDB_STATE_CLEAR(PAGER); + kdbnearsym_cleanup(); + if (error == KDB_CMD_KGDB) { + if (KDB_STATE(DOING_KGDB)) + KDB_STATE_CLEAR(DOING_KGDB); + return DBG_PASS_EVENT; + } + kdb_bp_install(ks->linux_regs); + dbg_activate_sw_breakpoints(); + /* Set the exit state to a single step or a continue */ + if (KDB_STATE(DOING_SS)) + gdbstub_state(ks, "s"); + else + gdbstub_state(ks, "c"); + + KDB_FLAG_CLEAR(CATASTROPHIC); + + /* Invoke arch specific exception handling prior to system resume */ + kgdb_info[ks->cpu].ret_state = gdbstub_state(ks, "e"); + if (ks->pass_exception) + kgdb_info[ks->cpu].ret_state = 1; + if (error == KDB_CMD_CPU) { + KDB_STATE_SET(REENTRY); + /* + * Force clear the single step bit because kdb emulates this + * differently vs the gdbstub + */ + kgdb_single_step = 0; + dbg_deactivate_sw_breakpoints(); + return DBG_SWITCH_CPU_EVENT; + } + return kgdb_info[ks->cpu].ret_state; +} + +void kdb_gdb_state_pass(char *buf) +{ + gdbstub_state(kdb_ks, buf); +} diff --git a/kernel/kernel/debug/kdb/kdb_io.c b/kernel/kernel/debug/kdb/kdb_io.c new file mode 100644 index 000000000..83c666537 --- /dev/null +++ b/kernel/kernel/debug/kdb/kdb_io.c @@ -0,0 +1,872 @@ +/* + * Kernel Debugger Architecture Independent Console I/O handler + * + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file "COPYING" in the main directory of this archive + * for more details. + * + * Copyright (c) 1999-2006 Silicon Graphics, Inc. All Rights Reserved. + * Copyright (c) 2009 Wind River Systems, Inc. All Rights Reserved. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include "kdb_private.h" + +#define CMD_BUFLEN 256 +char kdb_prompt_str[CMD_BUFLEN]; + +int kdb_trap_printk; + +static int kgdb_transition_check(char *buffer) +{ + if (buffer[0] != '+' && buffer[0] != '$') { + KDB_STATE_SET(KGDB_TRANS); + kdb_printf("%s", buffer); + } else { + int slen = strlen(buffer); + if (slen > 3 && buffer[slen - 3] == '#') { + kdb_gdb_state_pass(buffer); + strcpy(buffer, "kgdb"); + KDB_STATE_SET(DOING_KGDB); + return 1; + } + } + return 0; +} + +static int kdb_read_get_key(char *buffer, size_t bufsize) +{ +#define ESCAPE_UDELAY 1000 +#define ESCAPE_DELAY (2*1000000/ESCAPE_UDELAY) /* 2 seconds worth of udelays */ + char escape_data[5]; /* longest vt100 escape sequence is 4 bytes */ + char *ped = escape_data; + int escape_delay = 0; + get_char_func *f, *f_escape = NULL; + int key; + + for (f = &kdb_poll_funcs[0]; ; ++f) { + if (*f == NULL) { + /* Reset NMI watchdog once per poll loop */ + touch_nmi_watchdog(); + f = &kdb_poll_funcs[0]; + } + if (escape_delay == 2) { + *ped = '\0'; + ped = escape_data; + --escape_delay; + } + if (escape_delay == 1) { + key = *ped++; + if (!*ped) + --escape_delay; + break; + } + key = (*f)(); + if (key == -1) { + if (escape_delay) { + udelay(ESCAPE_UDELAY); + --escape_delay; + } + continue; + } + if (bufsize <= 2) { + if (key == '\r') + key = '\n'; + *buffer++ = key; + *buffer = '\0'; + return -1; + } + if (escape_delay == 0 && key == '\e') { + escape_delay = ESCAPE_DELAY; + ped = escape_data; + f_escape = f; + } + if (escape_delay) { + *ped++ = key; + if (f_escape != f) { + escape_delay = 2; + continue; + } + if (ped - escape_data == 1) { + /* \e */ + continue; + } else if (ped - escape_data == 2) { + /* \e */ + if (key != '[') + escape_delay = 2; + continue; + } else if (ped - escape_data == 3) { + /* \e[ */ + int mapkey = 0; + switch (key) { + case 'A': /* \e[A, up arrow */ + mapkey = 16; + break; + case 'B': /* \e[B, down arrow */ + mapkey = 14; + break; + case 'C': /* \e[C, right arrow */ + mapkey = 6; + break; + case 'D': /* \e[D, left arrow */ + mapkey = 2; + break; + case '1': /* dropthrough */ + case '3': /* dropthrough */ + /* \e[<1,3,4>], may be home, del, end */ + case '4': + mapkey = -1; + break; + } + if (mapkey != -1) { + if (mapkey > 0) { + escape_data[0] = mapkey; + escape_data[1] = '\0'; + } + escape_delay = 2; + } + continue; + } else if (ped - escape_data == 4) { + /* \e[<1,3,4> */ + int mapkey = 0; + if (key == '~') { + switch (escape_data[2]) { + case '1': /* \e[1~, home */ + mapkey = 1; + break; + case '3': /* \e[3~, del */ + mapkey = 4; + break; + case '4': /* \e[4~, end */ + mapkey = 5; + break; + } + } + if (mapkey > 0) { + escape_data[0] = mapkey; + escape_data[1] = '\0'; + } + escape_delay = 2; + continue; + } + } + break; /* A key to process */ + } + return key; +} + +/* + * kdb_read + * + * This function reads a string of characters, terminated by + * a newline, or by reaching the end of the supplied buffer, + * from the current kernel debugger console device. + * Parameters: + * buffer - Address of character buffer to receive input characters. + * bufsize - size, in bytes, of the character buffer + * Returns: + * Returns a pointer to the buffer containing the received + * character string. This string will be terminated by a + * newline character. + * Locking: + * No locks are required to be held upon entry to this + * function. It is not reentrant - it relies on the fact + * that while kdb is running on only one "master debug" cpu. + * Remarks: + * + * The buffer size must be >= 2. A buffer size of 2 means that the caller only + * wants a single key. + * + * An escape key could be the start of a vt100 control sequence such as \e[D + * (left arrow) or it could be a character in its own right. The standard + * method for detecting the difference is to wait for 2 seconds to see if there + * are any other characters. kdb is complicated by the lack of a timer service + * (interrupts are off), by multiple input sources and by the need to sometimes + * return after just one key. Escape sequence processing has to be done as + * states in the polling loop. + */ + +static char *kdb_read(char *buffer, size_t bufsize) +{ + char *cp = buffer; + char *bufend = buffer+bufsize-2; /* Reserve space for newline + * and null byte */ + char *lastchar; + char *p_tmp; + char tmp; + static char tmpbuffer[CMD_BUFLEN]; + int len = strlen(buffer); + int len_tmp; + int tab = 0; + int count; + int i; + int diag, dtab_count; + int key; + + + diag = kdbgetintenv("DTABCOUNT", &dtab_count); + if (diag) + dtab_count = 30; + + if (len > 0) { + cp += len; + if (*(buffer+len-1) == '\n') + cp--; + } + + lastchar = cp; + *cp = '\0'; + kdb_printf("%s", buffer); +poll_again: + key = kdb_read_get_key(buffer, bufsize); + if (key == -1) + return buffer; + if (key != 9) + tab = 0; + switch (key) { + case 8: /* backspace */ + if (cp > buffer) { + if (cp < lastchar) { + memcpy(tmpbuffer, cp, lastchar - cp); + memcpy(cp-1, tmpbuffer, lastchar - cp); + } + *(--lastchar) = '\0'; + --cp; + kdb_printf("\b%s \r", cp); + tmp = *cp; + *cp = '\0'; + kdb_printf(kdb_prompt_str); + kdb_printf("%s", buffer); + *cp = tmp; + } + break; + case 13: /* enter */ + *lastchar++ = '\n'; + *lastchar++ = '\0'; + if (!KDB_STATE(KGDB_TRANS)) { + KDB_STATE_SET(KGDB_TRANS); + kdb_printf("%s", buffer); + } + kdb_printf("\n"); + return buffer; + case 4: /* Del */ + if (cp < lastchar) { + memcpy(tmpbuffer, cp+1, lastchar - cp - 1); + memcpy(cp, tmpbuffer, lastchar - cp - 1); + *(--lastchar) = '\0'; + kdb_printf("%s \r", cp); + tmp = *cp; + *cp = '\0'; + kdb_printf(kdb_prompt_str); + kdb_printf("%s", buffer); + *cp = tmp; + } + break; + case 1: /* Home */ + if (cp > buffer) { + kdb_printf("\r"); + kdb_printf(kdb_prompt_str); + cp = buffer; + } + break; + case 5: /* End */ + if (cp < lastchar) { + kdb_printf("%s", cp); + cp = lastchar; + } + break; + case 2: /* Left */ + if (cp > buffer) { + kdb_printf("\b"); + --cp; + } + break; + case 14: /* Down */ + memset(tmpbuffer, ' ', + strlen(kdb_prompt_str) + (lastchar-buffer)); + *(tmpbuffer+strlen(kdb_prompt_str) + + (lastchar-buffer)) = '\0'; + kdb_printf("\r%s\r", tmpbuffer); + *lastchar = (char)key; + *(lastchar+1) = '\0'; + return lastchar; + case 6: /* Right */ + if (cp < lastchar) { + kdb_printf("%c", *cp); + ++cp; + } + break; + case 16: /* Up */ + memset(tmpbuffer, ' ', + strlen(kdb_prompt_str) + (lastchar-buffer)); + *(tmpbuffer+strlen(kdb_prompt_str) + + (lastchar-buffer)) = '\0'; + kdb_printf("\r%s\r", tmpbuffer); + *lastchar = (char)key; + *(lastchar+1) = '\0'; + return lastchar; + case 9: /* Tab */ + if (tab < 2) + ++tab; + p_tmp = buffer; + while (*p_tmp == ' ') + p_tmp++; + if (p_tmp > cp) + break; + memcpy(tmpbuffer, p_tmp, cp-p_tmp); + *(tmpbuffer + (cp-p_tmp)) = '\0'; + p_tmp = strrchr(tmpbuffer, ' '); + if (p_tmp) + ++p_tmp; + else + p_tmp = tmpbuffer; + len = strlen(p_tmp); + count = kallsyms_symbol_complete(p_tmp, + sizeof(tmpbuffer) - + (p_tmp - tmpbuffer)); + if (tab == 2 && count > 0) { + kdb_printf("\n%d symbols are found.", count); + if (count > dtab_count) { + count = dtab_count; + kdb_printf(" But only first %d symbols will" + " be printed.\nYou can change the" + " environment variable DTABCOUNT.", + count); + } + kdb_printf("\n"); + for (i = 0; i < count; i++) { + if (kallsyms_symbol_next(p_tmp, i) < 0) + break; + kdb_printf("%s ", p_tmp); + *(p_tmp + len) = '\0'; + } + if (i >= dtab_count) + kdb_printf("..."); + kdb_printf("\n"); + kdb_printf(kdb_prompt_str); + kdb_printf("%s", buffer); + } else if (tab != 2 && count > 0) { + len_tmp = strlen(p_tmp); + strncpy(p_tmp+len_tmp, cp, lastchar-cp+1); + len_tmp = strlen(p_tmp); + strncpy(cp, p_tmp+len, len_tmp-len + 1); + len = len_tmp - len; + kdb_printf("%s", cp); + cp += len; + lastchar += len; + } + kdb_nextline = 1; /* reset output line number */ + break; + default: + if (key >= 32 && lastchar < bufend) { + if (cp < lastchar) { + memcpy(tmpbuffer, cp, lastchar - cp); + memcpy(cp+1, tmpbuffer, lastchar - cp); + *++lastchar = '\0'; + *cp = key; + kdb_printf("%s\r", cp); + ++cp; + tmp = *cp; + *cp = '\0'; + kdb_printf(kdb_prompt_str); + kdb_printf("%s", buffer); + *cp = tmp; + } else { + *++lastchar = '\0'; + *cp++ = key; + /* The kgdb transition check will hide + * printed characters if we think that + * kgdb is connecting, until the check + * fails */ + if (!KDB_STATE(KGDB_TRANS)) { + if (kgdb_transition_check(buffer)) + return buffer; + } else { + kdb_printf("%c", key); + } + } + /* Special escape to kgdb */ + if (lastchar - buffer >= 5 && + strcmp(lastchar - 5, "$?#3f") == 0) { + kdb_gdb_state_pass(lastchar - 5); + strcpy(buffer, "kgdb"); + KDB_STATE_SET(DOING_KGDB); + return buffer; + } + if (lastchar - buffer >= 11 && + strcmp(lastchar - 11, "$qSupported") == 0) { + kdb_gdb_state_pass(lastchar - 11); + strcpy(buffer, "kgdb"); + KDB_STATE_SET(DOING_KGDB); + return buffer; + } + } + break; + } + goto poll_again; +} + +/* + * kdb_getstr + * + * Print the prompt string and read a command from the + * input device. + * + * Parameters: + * buffer Address of buffer to receive command + * bufsize Size of buffer in bytes + * prompt Pointer to string to use as prompt string + * Returns: + * Pointer to command buffer. + * Locking: + * None. + * Remarks: + * For SMP kernels, the processor number will be + * substituted for %d, %x or %o in the prompt. + */ + +char *kdb_getstr(char *buffer, size_t bufsize, const char *prompt) +{ + if (prompt && kdb_prompt_str != prompt) + strncpy(kdb_prompt_str, prompt, CMD_BUFLEN); + kdb_printf(kdb_prompt_str); + kdb_nextline = 1; /* Prompt and input resets line number */ + return kdb_read(buffer, bufsize); +} + +/* + * kdb_input_flush + * + * Get rid of any buffered console input. + * + * Parameters: + * none + * Returns: + * nothing + * Locking: + * none + * Remarks: + * Call this function whenever you want to flush input. If there is any + * outstanding input, it ignores all characters until there has been no + * data for approximately 1ms. + */ + +static void kdb_input_flush(void) +{ + get_char_func *f; + int res; + int flush_delay = 1; + while (flush_delay) { + flush_delay--; +empty: + touch_nmi_watchdog(); + for (f = &kdb_poll_funcs[0]; *f; ++f) { + res = (*f)(); + if (res != -1) { + flush_delay = 1; + goto empty; + } + } + if (flush_delay) + mdelay(1); + } +} + +/* + * kdb_printf + * + * Print a string to the output device(s). + * + * Parameters: + * printf-like format and optional args. + * Returns: + * 0 + * Locking: + * None. + * Remarks: + * use 'kdbcons->write()' to avoid polluting 'log_buf' with + * kdb output. + * + * If the user is doing a cmd args | grep srch + * then kdb_grepping_flag is set. + * In that case we need to accumulate full lines (ending in \n) before + * searching for the pattern. + */ + +static char kdb_buffer[256]; /* A bit too big to go on stack */ +static char *next_avail = kdb_buffer; +static int size_avail; +static int suspend_grep; + +/* + * search arg1 to see if it contains arg2 + * (kdmain.c provides flags for ^pat and pat$) + * + * return 1 for found, 0 for not found + */ +static int kdb_search_string(char *searched, char *searchfor) +{ + char firstchar, *cp; + int len1, len2; + + /* not counting the newline at the end of "searched" */ + len1 = strlen(searched)-1; + len2 = strlen(searchfor); + if (len1 < len2) + return 0; + if (kdb_grep_leading && kdb_grep_trailing && len1 != len2) + return 0; + if (kdb_grep_leading) { + if (!strncmp(searched, searchfor, len2)) + return 1; + } else if (kdb_grep_trailing) { + if (!strncmp(searched+len1-len2, searchfor, len2)) + return 1; + } else { + firstchar = *searchfor; + cp = searched; + while ((cp = strchr(cp, firstchar))) { + if (!strncmp(cp, searchfor, len2)) + return 1; + cp++; + } + } + return 0; +} + +int vkdb_printf(enum kdb_msgsrc src, const char *fmt, va_list ap) +{ + int diag; + int linecount; + int colcount; + int logging, saved_loglevel = 0; + int got_printf_lock = 0; + int retlen = 0; + int fnd, len; + char *cp, *cp2, *cphold = NULL, replaced_byte = ' '; + char *moreprompt = "more> "; + struct console *c = console_drivers; + static DEFINE_SPINLOCK(kdb_printf_lock); + unsigned long uninitialized_var(flags); + + preempt_disable(); + + /* Serialize kdb_printf if multiple cpus try to write at once. + * But if any cpu goes recursive in kdb, just print the output, + * even if it is interleaved with any other text. + */ + if (!KDB_STATE(PRINTF_LOCK)) { + KDB_STATE_SET(PRINTF_LOCK); + spin_lock_irqsave(&kdb_printf_lock, flags); + got_printf_lock = 1; + atomic_inc(&kdb_event); + } else { + __acquire(kdb_printf_lock); + } + + diag = kdbgetintenv("LINES", &linecount); + if (diag || linecount <= 1) + linecount = 24; + + diag = kdbgetintenv("COLUMNS", &colcount); + if (diag || colcount <= 1) + colcount = 80; + + diag = kdbgetintenv("LOGGING", &logging); + if (diag) + logging = 0; + + if (!kdb_grepping_flag || suspend_grep) { + /* normally, every vsnprintf starts a new buffer */ + next_avail = kdb_buffer; + size_avail = sizeof(kdb_buffer); + } + vsnprintf(next_avail, size_avail, fmt, ap); + + /* + * If kdb_parse() found that the command was cmd xxx | grep yyy + * then kdb_grepping_flag is set, and kdb_grep_string contains yyy + * + * Accumulate the print data up to a newline before searching it. + * (vsnprintf does null-terminate the string that it generates) + */ + + /* skip the search if prints are temporarily unconditional */ + if (!suspend_grep && kdb_grepping_flag) { + cp = strchr(kdb_buffer, '\n'); + if (!cp) { + /* + * Special cases that don't end with newlines + * but should be written without one: + * The "[nn]kdb> " prompt should + * appear at the front of the buffer. + * + * The "[nn]more " prompt should also be + * (MOREPROMPT -> moreprompt) + * written * but we print that ourselves, + * we set the suspend_grep flag to make + * it unconditional. + * + */ + if (next_avail == kdb_buffer) { + /* + * these should occur after a newline, + * so they will be at the front of the + * buffer + */ + cp2 = kdb_buffer; + len = strlen(kdb_prompt_str); + if (!strncmp(cp2, kdb_prompt_str, len)) { + /* + * We're about to start a new + * command, so we can go back + * to normal mode. + */ + kdb_grepping_flag = 0; + goto kdb_printit; + } + } + /* no newline; don't search/write the buffer + until one is there */ + len = strlen(kdb_buffer); + next_avail = kdb_buffer + len; + size_avail = sizeof(kdb_buffer) - len; + goto kdb_print_out; + } + + /* + * The newline is present; print through it or discard + * it, depending on the results of the search. + */ + cp++; /* to byte after the newline */ + replaced_byte = *cp; /* remember what/where it was */ + cphold = cp; + *cp = '\0'; /* end the string for our search */ + + /* + * We now have a newline at the end of the string + * Only continue with this output if it contains the + * search string. + */ + fnd = kdb_search_string(kdb_buffer, kdb_grep_string); + if (!fnd) { + /* + * At this point the complete line at the start + * of kdb_buffer can be discarded, as it does + * not contain what the user is looking for. + * Shift the buffer left. + */ + *cphold = replaced_byte; + strcpy(kdb_buffer, cphold); + len = strlen(kdb_buffer); + next_avail = kdb_buffer + len; + size_avail = sizeof(kdb_buffer) - len; + goto kdb_print_out; + } + if (kdb_grepping_flag >= KDB_GREPPING_FLAG_SEARCH) + /* + * This was a interactive search (using '/' at more + * prompt) and it has completed. Clear the flag. + */ + kdb_grepping_flag = 0; + /* + * at this point the string is a full line and + * should be printed, up to the null. + */ + } +kdb_printit: + + /* + * Write to all consoles. + */ + retlen = strlen(kdb_buffer); + cp = (char *) printk_skip_level(kdb_buffer); + if (!dbg_kdb_mode && kgdb_connected) { + gdbstub_msg_write(cp, retlen - (cp - kdb_buffer)); + } else { + if (dbg_io_ops && !dbg_io_ops->is_console) { + len = retlen - (cp - kdb_buffer); + cp2 = cp; + while (len--) { + dbg_io_ops->write_char(*cp2); + cp2++; + } + } + while (c) { + c->write(c, cp, retlen - (cp - kdb_buffer)); + touch_nmi_watchdog(); + c = c->next; + } + } + if (logging) { + saved_loglevel = console_loglevel; + console_loglevel = CONSOLE_LOGLEVEL_SILENT; + if (printk_get_level(kdb_buffer) || src == KDB_MSGSRC_PRINTK) + printk("%s", kdb_buffer); + else + pr_info("%s", kdb_buffer); + } + + if (KDB_STATE(PAGER)) { + /* + * Check printed string to decide how to bump the + * kdb_nextline to control when the more prompt should + * show up. + */ + int got = 0; + len = retlen; + while (len--) { + if (kdb_buffer[len] == '\n') { + kdb_nextline++; + got = 0; + } else if (kdb_buffer[len] == '\r') { + got = 0; + } else { + got++; + } + } + kdb_nextline += got / (colcount + 1); + } + + /* check for having reached the LINES number of printed lines */ + if (kdb_nextline >= linecount) { + char buf1[16] = ""; + + /* Watch out for recursion here. Any routine that calls + * kdb_printf will come back through here. And kdb_read + * uses kdb_printf to echo on serial consoles ... + */ + kdb_nextline = 1; /* In case of recursion */ + + /* + * Pause until cr. + */ + moreprompt = kdbgetenv("MOREPROMPT"); + if (moreprompt == NULL) + moreprompt = "more> "; + + kdb_input_flush(); + c = console_drivers; + + if (dbg_io_ops && !dbg_io_ops->is_console) { + len = strlen(moreprompt); + cp = moreprompt; + while (len--) { + dbg_io_ops->write_char(*cp); + cp++; + } + } + while (c) { + c->write(c, moreprompt, strlen(moreprompt)); + touch_nmi_watchdog(); + c = c->next; + } + + if (logging) + printk("%s", moreprompt); + + kdb_read(buf1, 2); /* '2' indicates to return + * immediately after getting one key. */ + kdb_nextline = 1; /* Really set output line 1 */ + + /* empty and reset the buffer: */ + kdb_buffer[0] = '\0'; + next_avail = kdb_buffer; + size_avail = sizeof(kdb_buffer); + if ((buf1[0] == 'q') || (buf1[0] == 'Q')) { + /* user hit q or Q */ + KDB_FLAG_SET(CMD_INTERRUPT); /* command interrupted */ + KDB_STATE_CLEAR(PAGER); + /* end of command output; back to normal mode */ + kdb_grepping_flag = 0; + kdb_printf("\n"); + } else if (buf1[0] == ' ') { + kdb_printf("\r"); + suspend_grep = 1; /* for this recursion */ + } else if (buf1[0] == '\n') { + kdb_nextline = linecount - 1; + kdb_printf("\r"); + suspend_grep = 1; /* for this recursion */ + } else if (buf1[0] == '/' && !kdb_grepping_flag) { + kdb_printf("\r"); + kdb_getstr(kdb_grep_string, KDB_GREP_STRLEN, + kdbgetenv("SEARCHPROMPT") ?: "search> "); + *strchrnul(kdb_grep_string, '\n') = '\0'; + kdb_grepping_flag += KDB_GREPPING_FLAG_SEARCH; + suspend_grep = 1; /* for this recursion */ + } else if (buf1[0] && buf1[0] != '\n') { + /* user hit something other than enter */ + suspend_grep = 1; /* for this recursion */ + if (buf1[0] != '/') + kdb_printf( + "\nOnly 'q', 'Q' or '/' are processed at " + "more prompt, input ignored\n"); + else + kdb_printf("\n'/' cannot be used during | " + "grep filtering, input ignored\n"); + } else if (kdb_grepping_flag) { + /* user hit enter */ + suspend_grep = 1; /* for this recursion */ + kdb_printf("\n"); + } + kdb_input_flush(); + } + + /* + * For grep searches, shift the printed string left. + * replaced_byte contains the character that was overwritten with + * the terminating null, and cphold points to the null. + * Then adjust the notion of available space in the buffer. + */ + if (kdb_grepping_flag && !suspend_grep) { + *cphold = replaced_byte; + strcpy(kdb_buffer, cphold); + len = strlen(kdb_buffer); + next_avail = kdb_buffer + len; + size_avail = sizeof(kdb_buffer) - len; + } + +kdb_print_out: + suspend_grep = 0; /* end of what may have been a recursive call */ + if (logging) + console_loglevel = saved_loglevel; + if (KDB_STATE(PRINTF_LOCK) && got_printf_lock) { + got_printf_lock = 0; + spin_unlock_irqrestore(&kdb_printf_lock, flags); + KDB_STATE_CLEAR(PRINTF_LOCK); + atomic_dec(&kdb_event); + } else { + __release(kdb_printf_lock); + } + preempt_enable(); + return retlen; +} + +int kdb_printf(const char *fmt, ...) +{ + va_list ap; + int r; + + kdb_trap_printk++; + va_start(ap, fmt); + r = vkdb_printf(KDB_MSGSRC_INTERNAL, fmt, ap); + va_end(ap); + kdb_trap_printk--; + + return r; +} +EXPORT_SYMBOL_GPL(kdb_printf); diff --git a/kernel/kernel/debug/kdb/kdb_keyboard.c b/kernel/kernel/debug/kdb/kdb_keyboard.c new file mode 100644 index 000000000..118527aa6 --- /dev/null +++ b/kernel/kernel/debug/kdb/kdb_keyboard.c @@ -0,0 +1,263 @@ +/* + * Kernel Debugger Architecture Dependent Console I/O handler + * + * This file is subject to the terms and conditions of the GNU General Public + * License. + * + * Copyright (c) 1999-2006 Silicon Graphics, Inc. All Rights Reserved. + * Copyright (c) 2009 Wind River Systems, Inc. All Rights Reserved. + */ + +#include +#include +#include +#include +#include + +/* Keyboard Controller Registers on normal PCs. */ + +#define KBD_STATUS_REG 0x64 /* Status register (R) */ +#define KBD_DATA_REG 0x60 /* Keyboard data register (R/W) */ + +/* Status Register Bits */ + +#define KBD_STAT_OBF 0x01 /* Keyboard output buffer full */ +#define KBD_STAT_MOUSE_OBF 0x20 /* Mouse output buffer full */ + +static int kbd_exists; +static int kbd_last_ret; + +/* + * Check if the keyboard controller has a keypress for us. + * Some parts (Enter Release, LED change) are still blocking polled here, + * but hopefully they are all short. + */ +int kdb_get_kbd_char(void) +{ + int scancode, scanstatus; + static int shift_lock; /* CAPS LOCK state (0-off, 1-on) */ + static int shift_key; /* Shift next keypress */ + static int ctrl_key; + u_short keychar; + + if (KDB_FLAG(NO_I8042) || KDB_FLAG(NO_VT_CONSOLE) || + (inb(KBD_STATUS_REG) == 0xff && inb(KBD_DATA_REG) == 0xff)) { + kbd_exists = 0; + return -1; + } + kbd_exists = 1; + + if ((inb(KBD_STATUS_REG) & KBD_STAT_OBF) == 0) + return -1; + + /* + * Fetch the scancode + */ + scancode = inb(KBD_DATA_REG); + scanstatus = inb(KBD_STATUS_REG); + + /* + * Ignore mouse events. + */ + if (scanstatus & KBD_STAT_MOUSE_OBF) + return -1; + + /* + * Ignore release, trigger on make + * (except for shift keys, where we want to + * keep the shift state so long as the key is + * held down). + */ + + if (((scancode&0x7f) == 0x2a) || ((scancode&0x7f) == 0x36)) { + /* + * Next key may use shift table + */ + if ((scancode & 0x80) == 0) + shift_key = 1; + else + shift_key = 0; + return -1; + } + + if ((scancode&0x7f) == 0x1d) { + /* + * Left ctrl key + */ + if ((scancode & 0x80) == 0) + ctrl_key = 1; + else + ctrl_key = 0; + return -1; + } + + if ((scancode & 0x80) != 0) { + if (scancode == 0x9c) + kbd_last_ret = 0; + return -1; + } + + scancode &= 0x7f; + + /* + * Translate scancode + */ + + if (scancode == 0x3a) { + /* + * Toggle caps lock + */ + shift_lock ^= 1; + +#ifdef KDB_BLINK_LED + kdb_toggleled(0x4); +#endif + return -1; + } + + if (scancode == 0x0e) { + /* + * Backspace + */ + return 8; + } + + /* Special Key */ + switch (scancode) { + case 0xF: /* Tab */ + return 9; + case 0x53: /* Del */ + return 4; + case 0x47: /* Home */ + return 1; + case 0x4F: /* End */ + return 5; + case 0x4B: /* Left */ + return 2; + case 0x48: /* Up */ + return 16; + case 0x50: /* Down */ + return 14; + case 0x4D: /* Right */ + return 6; + } + + if (scancode == 0xe0) + return -1; + + /* + * For Japanese 86/106 keyboards + * See comment in drivers/char/pc_keyb.c. + * - Masahiro Adegawa + */ + if (scancode == 0x73) + scancode = 0x59; + else if (scancode == 0x7d) + scancode = 0x7c; + + if (!shift_lock && !shift_key && !ctrl_key) { + keychar = plain_map[scancode]; + } else if ((shift_lock || shift_key) && key_maps[1]) { + keychar = key_maps[1][scancode]; + } else if (ctrl_key && key_maps[4]) { + keychar = key_maps[4][scancode]; + } else { + keychar = 0x0020; + kdb_printf("Unknown state/scancode (%d)\n", scancode); + } + keychar &= 0x0fff; + if (keychar == '\t') + keychar = ' '; + switch (KTYP(keychar)) { + case KT_LETTER: + case KT_LATIN: + if (isprint(keychar)) + break; /* printable characters */ + /* drop through */ + case KT_SPEC: + if (keychar == K_ENTER) + break; + /* drop through */ + default: + return -1; /* ignore unprintables */ + } + + if (scancode == 0x1c) { + kbd_last_ret = 1; + return 13; + } + + return keychar & 0xff; +} +EXPORT_SYMBOL_GPL(kdb_get_kbd_char); + +/* + * Best effort cleanup of ENTER break codes on leaving KDB. Called on + * exiting KDB, when we know we processed an ENTER or KP ENTER scan + * code. + */ +void kdb_kbd_cleanup_state(void) +{ + int scancode, scanstatus; + + /* + * Nothing to clean up, since either + * ENTER was never pressed, or has already + * gotten cleaned up. + */ + if (!kbd_last_ret) + return; + + kbd_last_ret = 0; + /* + * Enter key. Need to absorb the break code here, lest it gets + * leaked out if we exit KDB as the result of processing 'g'. + * + * This has several interesting implications: + * + Need to handle KP ENTER, which has break code 0xe0 0x9c. + * + Need to handle repeat ENTER and repeat KP ENTER. Repeats + * only get a break code at the end of the repeated + * sequence. This means we can't propagate the repeated key + * press, and must swallow it away. + * + Need to handle possible PS/2 mouse input. + * + Need to handle mashed keys. + */ + + while (1) { + while ((inb(KBD_STATUS_REG) & KBD_STAT_OBF) == 0) + cpu_relax(); + + /* + * Fetch the scancode. + */ + scancode = inb(KBD_DATA_REG); + scanstatus = inb(KBD_STATUS_REG); + + /* + * Skip mouse input. + */ + if (scanstatus & KBD_STAT_MOUSE_OBF) + continue; + + /* + * If we see 0xe0, this is either a break code for KP + * ENTER, or a repeat make for KP ENTER. Either way, + * since the second byte is equivalent to an ENTER, + * skip the 0xe0 and try again. + * + * If we see 0x1c, this must be a repeat ENTER or KP + * ENTER (and we swallowed 0xe0 before). Try again. + * + * We can also see make and break codes for other keys + * mashed before or after pressing ENTER. Thus, if we + * see anything other than 0x9c, we have to try again. + * + * Note, if you held some key as ENTER was depressed, + * that break code would get leaked out. + */ + if (scancode != 0x9c) + continue; + + return; + } +} diff --git a/kernel/kernel/debug/kdb/kdb_main.c b/kernel/kernel/debug/kdb/kdb_main.c new file mode 100644 index 000000000..412134549 --- /dev/null +++ b/kernel/kernel/debug/kdb/kdb_main.c @@ -0,0 +1,2954 @@ +/* + * Kernel Debugger Architecture Independent Main Code + * + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file "COPYING" in the main directory of this archive + * for more details. + * + * Copyright (C) 1999-2004 Silicon Graphics, Inc. All Rights Reserved. + * Copyright (C) 2000 Stephane Eranian + * Xscale (R) modifications copyright (C) 2003 Intel Corporation. + * Copyright (c) 2009 Wind River Systems, Inc. All Rights Reserved. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include "kdb_private.h" + +#undef MODULE_PARAM_PREFIX +#define MODULE_PARAM_PREFIX "kdb." + +static int kdb_cmd_enabled = CONFIG_KDB_DEFAULT_ENABLE; +module_param_named(cmd_enable, kdb_cmd_enabled, int, 0600); + +char kdb_grep_string[KDB_GREP_STRLEN]; +int kdb_grepping_flag; +EXPORT_SYMBOL(kdb_grepping_flag); +int kdb_grep_leading; +int kdb_grep_trailing; + +/* + * Kernel debugger state flags + */ +int kdb_flags; +atomic_t kdb_event; + +/* + * kdb_lock protects updates to kdb_initial_cpu. Used to + * single thread processors through the kernel debugger. + */ +int kdb_initial_cpu = -1; /* cpu number that owns kdb */ +int kdb_nextline = 1; +int kdb_state; /* General KDB state */ + +struct task_struct *kdb_current_task; +EXPORT_SYMBOL(kdb_current_task); +struct pt_regs *kdb_current_regs; + +const char *kdb_diemsg; +static int kdb_go_count; +#ifdef CONFIG_KDB_CONTINUE_CATASTROPHIC +static unsigned int kdb_continue_catastrophic = + CONFIG_KDB_CONTINUE_CATASTROPHIC; +#else +static unsigned int kdb_continue_catastrophic; +#endif + +/* kdb_commands describes the available commands. */ +static kdbtab_t *kdb_commands; +#define KDB_BASE_CMD_MAX 50 +static int kdb_max_commands = KDB_BASE_CMD_MAX; +static kdbtab_t kdb_base_commands[KDB_BASE_CMD_MAX]; +#define for_each_kdbcmd(cmd, num) \ + for ((cmd) = kdb_base_commands, (num) = 0; \ + num < kdb_max_commands; \ + num++, num == KDB_BASE_CMD_MAX ? cmd = kdb_commands : cmd++) + +typedef struct _kdbmsg { + int km_diag; /* kdb diagnostic */ + char *km_msg; /* Corresponding message text */ +} kdbmsg_t; + +#define KDBMSG(msgnum, text) \ + { KDB_##msgnum, text } + +static kdbmsg_t kdbmsgs[] = { + KDBMSG(NOTFOUND, "Command Not Found"), + KDBMSG(ARGCOUNT, "Improper argument count, see usage."), + KDBMSG(BADWIDTH, "Illegal value for BYTESPERWORD use 1, 2, 4 or 8, " + "8 is only allowed on 64 bit systems"), + KDBMSG(BADRADIX, "Illegal value for RADIX use 8, 10 or 16"), + KDBMSG(NOTENV, "Cannot find environment variable"), + KDBMSG(NOENVVALUE, "Environment variable should have value"), + KDBMSG(NOTIMP, "Command not implemented"), + KDBMSG(ENVFULL, "Environment full"), + KDBMSG(ENVBUFFULL, "Environment buffer full"), + KDBMSG(TOOMANYBPT, "Too many breakpoints defined"), +#ifdef CONFIG_CPU_XSCALE + KDBMSG(TOOMANYDBREGS, "More breakpoints than ibcr registers defined"), +#else + KDBMSG(TOOMANYDBREGS, "More breakpoints than db registers defined"), +#endif + KDBMSG(DUPBPT, "Duplicate breakpoint address"), + KDBMSG(BPTNOTFOUND, "Breakpoint not found"), + KDBMSG(BADMODE, "Invalid IDMODE"), + KDBMSG(BADINT, "Illegal numeric value"), + KDBMSG(INVADDRFMT, "Invalid symbolic address format"), + KDBMSG(BADREG, "Invalid register name"), + KDBMSG(BADCPUNUM, "Invalid cpu number"), + KDBMSG(BADLENGTH, "Invalid length field"), + KDBMSG(NOBP, "No Breakpoint exists"), + KDBMSG(BADADDR, "Invalid address"), + KDBMSG(NOPERM, "Permission denied"), +}; +#undef KDBMSG + +static const int __nkdb_err = ARRAY_SIZE(kdbmsgs); + + +/* + * Initial environment. This is all kept static and local to + * this file. We don't want to rely on the memory allocation + * mechanisms in the kernel, so we use a very limited allocate-only + * heap for new and altered environment variables. The entire + * environment is limited to a fixed number of entries (add more + * to __env[] if required) and a fixed amount of heap (add more to + * KDB_ENVBUFSIZE if required). + */ + +static char *__env[] = { +#if defined(CONFIG_SMP) + "PROMPT=[%d]kdb> ", +#else + "PROMPT=kdb> ", +#endif + "MOREPROMPT=more> ", + "RADIX=16", + "MDCOUNT=8", /* lines of md output */ + KDB_PLATFORM_ENV, + "DTABCOUNT=30", + "NOSECT=1", + (char *)0, + (char *)0, + (char *)0, + (char *)0, + (char *)0, + (char *)0, + (char *)0, + (char *)0, + (char *)0, + (char *)0, + (char *)0, + (char *)0, + (char *)0, + (char *)0, + (char *)0, + (char *)0, + (char *)0, + (char *)0, + (char *)0, + (char *)0, + (char *)0, + (char *)0, + (char *)0, + (char *)0, +}; + +static const int __nenv = ARRAY_SIZE(__env); + +struct task_struct *kdb_curr_task(int cpu) +{ + struct task_struct *p = curr_task(cpu); +#ifdef _TIF_MCA_INIT + if ((task_thread_info(p)->flags & _TIF_MCA_INIT) && KDB_TSK(cpu)) + p = krp->p; +#endif + return p; +} + +/* + * Check whether the flags of the current command and the permissions + * of the kdb console has allow a command to be run. + */ +static inline bool kdb_check_flags(kdb_cmdflags_t flags, int permissions, + bool no_args) +{ + /* permissions comes from userspace so needs massaging slightly */ + permissions &= KDB_ENABLE_MASK; + permissions |= KDB_ENABLE_ALWAYS_SAFE; + + /* some commands change group when launched with no arguments */ + if (no_args) + permissions |= permissions << KDB_ENABLE_NO_ARGS_SHIFT; + + flags |= KDB_ENABLE_ALL; + + return permissions & flags; +} + +/* + * kdbgetenv - This function will return the character string value of + * an environment variable. + * Parameters: + * match A character string representing an environment variable. + * Returns: + * NULL No environment variable matches 'match' + * char* Pointer to string value of environment variable. + */ +char *kdbgetenv(const char *match) +{ + char **ep = __env; + int matchlen = strlen(match); + int i; + + for (i = 0; i < __nenv; i++) { + char *e = *ep++; + + if (!e) + continue; + + if ((strncmp(match, e, matchlen) == 0) + && ((e[matchlen] == '\0') + || (e[matchlen] == '='))) { + char *cp = strchr(e, '='); + return cp ? ++cp : ""; + } + } + return NULL; +} + +/* + * kdballocenv - This function is used to allocate bytes for + * environment entries. + * Parameters: + * match A character string representing a numeric value + * Outputs: + * *value the unsigned long representation of the env variable 'match' + * Returns: + * Zero on success, a kdb diagnostic on failure. + * Remarks: + * We use a static environment buffer (envbuffer) to hold the values + * of dynamically generated environment variables (see kdb_set). Buffer + * space once allocated is never free'd, so over time, the amount of space + * (currently 512 bytes) will be exhausted if env variables are changed + * frequently. + */ +static char *kdballocenv(size_t bytes) +{ +#define KDB_ENVBUFSIZE 512 + static char envbuffer[KDB_ENVBUFSIZE]; + static int envbufsize; + char *ep = NULL; + + if ((KDB_ENVBUFSIZE - envbufsize) >= bytes) { + ep = &envbuffer[envbufsize]; + envbufsize += bytes; + } + return ep; +} + +/* + * kdbgetulenv - This function will return the value of an unsigned + * long-valued environment variable. + * Parameters: + * match A character string representing a numeric value + * Outputs: + * *value the unsigned long represntation of the env variable 'match' + * Returns: + * Zero on success, a kdb diagnostic on failure. + */ +static int kdbgetulenv(const char *match, unsigned long *value) +{ + char *ep; + + ep = kdbgetenv(match); + if (!ep) + return KDB_NOTENV; + if (strlen(ep) == 0) + return KDB_NOENVVALUE; + + *value = simple_strtoul(ep, NULL, 0); + + return 0; +} + +/* + * kdbgetintenv - This function will return the value of an + * integer-valued environment variable. + * Parameters: + * match A character string representing an integer-valued env variable + * Outputs: + * *value the integer representation of the environment variable 'match' + * Returns: + * Zero on success, a kdb diagnostic on failure. + */ +int kdbgetintenv(const char *match, int *value) +{ + unsigned long val; + int diag; + + diag = kdbgetulenv(match, &val); + if (!diag) + *value = (int) val; + return diag; +} + +/* + * kdbgetularg - This function will convert a numeric string into an + * unsigned long value. + * Parameters: + * arg A character string representing a numeric value + * Outputs: + * *value the unsigned long represntation of arg. + * Returns: + * Zero on success, a kdb diagnostic on failure. + */ +int kdbgetularg(const char *arg, unsigned long *value) +{ + char *endp; + unsigned long val; + + val = simple_strtoul(arg, &endp, 0); + + if (endp == arg) { + /* + * Also try base 16, for us folks too lazy to type the + * leading 0x... + */ + val = simple_strtoul(arg, &endp, 16); + if (endp == arg) + return KDB_BADINT; + } + + *value = val; + + return 0; +} + +int kdbgetu64arg(const char *arg, u64 *value) +{ + char *endp; + u64 val; + + val = simple_strtoull(arg, &endp, 0); + + if (endp == arg) { + + val = simple_strtoull(arg, &endp, 16); + if (endp == arg) + return KDB_BADINT; + } + + *value = val; + + return 0; +} + +/* + * kdb_set - This function implements the 'set' command. Alter an + * existing environment variable or create a new one. + */ +int kdb_set(int argc, const char **argv) +{ + int i; + char *ep; + size_t varlen, vallen; + + /* + * we can be invoked two ways: + * set var=value argv[1]="var", argv[2]="value" + * set var = value argv[1]="var", argv[2]="=", argv[3]="value" + * - if the latter, shift 'em down. + */ + if (argc == 3) { + argv[2] = argv[3]; + argc--; + } + + if (argc != 2) + return KDB_ARGCOUNT; + + /* + * Check for internal variables + */ + if (strcmp(argv[1], "KDBDEBUG") == 0) { + unsigned int debugflags; + char *cp; + + debugflags = simple_strtoul(argv[2], &cp, 0); + if (cp == argv[2] || debugflags & ~KDB_DEBUG_FLAG_MASK) { + kdb_printf("kdb: illegal debug flags '%s'\n", + argv[2]); + return 0; + } + kdb_flags = (kdb_flags & + ~(KDB_DEBUG_FLAG_MASK << KDB_DEBUG_FLAG_SHIFT)) + | (debugflags << KDB_DEBUG_FLAG_SHIFT); + + return 0; + } + + /* + * Tokenizer squashed the '=' sign. argv[1] is variable + * name, argv[2] = value. + */ + varlen = strlen(argv[1]); + vallen = strlen(argv[2]); + ep = kdballocenv(varlen + vallen + 2); + if (ep == (char *)0) + return KDB_ENVBUFFULL; + + sprintf(ep, "%s=%s", argv[1], argv[2]); + + ep[varlen+vallen+1] = '\0'; + + for (i = 0; i < __nenv; i++) { + if (__env[i] + && ((strncmp(__env[i], argv[1], varlen) == 0) + && ((__env[i][varlen] == '\0') + || (__env[i][varlen] == '=')))) { + __env[i] = ep; + return 0; + } + } + + /* + * Wasn't existing variable. Fit into slot. + */ + for (i = 0; i < __nenv-1; i++) { + if (__env[i] == (char *)0) { + __env[i] = ep; + return 0; + } + } + + return KDB_ENVFULL; +} + +static int kdb_check_regs(void) +{ + if (!kdb_current_regs) { + kdb_printf("No current kdb registers." + " You may need to select another task\n"); + return KDB_BADREG; + } + return 0; +} + +/* + * kdbgetaddrarg - This function is responsible for parsing an + * address-expression and returning the value of the expression, + * symbol name, and offset to the caller. + * + * The argument may consist of a numeric value (decimal or + * hexidecimal), a symbol name, a register name (preceded by the + * percent sign), an environment variable with a numeric value + * (preceded by a dollar sign) or a simple arithmetic expression + * consisting of a symbol name, +/-, and a numeric constant value + * (offset). + * Parameters: + * argc - count of arguments in argv + * argv - argument vector + * *nextarg - index to next unparsed argument in argv[] + * regs - Register state at time of KDB entry + * Outputs: + * *value - receives the value of the address-expression + * *offset - receives the offset specified, if any + * *name - receives the symbol name, if any + * *nextarg - index to next unparsed argument in argv[] + * Returns: + * zero is returned on success, a kdb diagnostic code is + * returned on error. + */ +int kdbgetaddrarg(int argc, const char **argv, int *nextarg, + unsigned long *value, long *offset, + char **name) +{ + unsigned long addr; + unsigned long off = 0; + int positive; + int diag; + int found = 0; + char *symname; + char symbol = '\0'; + char *cp; + kdb_symtab_t symtab; + + /* + * If the enable flags prohibit both arbitrary memory access + * and flow control then there are no reasonable grounds to + * provide symbol lookup. + */ + if (!kdb_check_flags(KDB_ENABLE_MEM_READ | KDB_ENABLE_FLOW_CTRL, + kdb_cmd_enabled, false)) + return KDB_NOPERM; + + /* + * Process arguments which follow the following syntax: + * + * symbol | numeric-address [+/- numeric-offset] + * %register + * $environment-variable + */ + + if (*nextarg > argc) + return KDB_ARGCOUNT; + + symname = (char *)argv[*nextarg]; + + /* + * If there is no whitespace between the symbol + * or address and the '+' or '-' symbols, we + * remember the character and replace it with a + * null so the symbol/value can be properly parsed + */ + cp = strpbrk(symname, "+-"); + if (cp != NULL) { + symbol = *cp; + *cp++ = '\0'; + } + + if (symname[0] == '$') { + diag = kdbgetulenv(&symname[1], &addr); + if (diag) + return diag; + } else if (symname[0] == '%') { + diag = kdb_check_regs(); + if (diag) + return diag; + /* Implement register values with % at a later time as it is + * arch optional. + */ + return KDB_NOTIMP; + } else { + found = kdbgetsymval(symname, &symtab); + if (found) { + addr = symtab.sym_start; + } else { + diag = kdbgetularg(argv[*nextarg], &addr); + if (diag) + return diag; + } + } + + if (!found) + found = kdbnearsym(addr, &symtab); + + (*nextarg)++; + + if (name) + *name = symname; + if (value) + *value = addr; + if (offset && name && *name) + *offset = addr - symtab.sym_start; + + if ((*nextarg > argc) + && (symbol == '\0')) + return 0; + + /* + * check for +/- and offset + */ + + if (symbol == '\0') { + if ((argv[*nextarg][0] != '+') + && (argv[*nextarg][0] != '-')) { + /* + * Not our argument. Return. + */ + return 0; + } else { + positive = (argv[*nextarg][0] == '+'); + (*nextarg)++; + } + } else + positive = (symbol == '+'); + + /* + * Now there must be an offset! + */ + if ((*nextarg > argc) + && (symbol == '\0')) { + return KDB_INVADDRFMT; + } + + if (!symbol) { + cp = (char *)argv[*nextarg]; + (*nextarg)++; + } + + diag = kdbgetularg(cp, &off); + if (diag) + return diag; + + if (!positive) + off = -off; + + if (offset) + *offset += off; + + if (value) + *value += off; + + return 0; +} + +static void kdb_cmderror(int diag) +{ + int i; + + if (diag >= 0) { + kdb_printf("no error detected (diagnostic is %d)\n", diag); + return; + } + + for (i = 0; i < __nkdb_err; i++) { + if (kdbmsgs[i].km_diag == diag) { + kdb_printf("diag: %d: %s\n", diag, kdbmsgs[i].km_msg); + return; + } + } + + kdb_printf("Unknown diag %d\n", -diag); +} + +/* + * kdb_defcmd, kdb_defcmd2 - This function implements the 'defcmd' + * command which defines one command as a set of other commands, + * terminated by endefcmd. kdb_defcmd processes the initial + * 'defcmd' command, kdb_defcmd2 is invoked from kdb_parse for + * the following commands until 'endefcmd'. + * Inputs: + * argc argument count + * argv argument vector + * Returns: + * zero for success, a kdb diagnostic if error + */ +struct defcmd_set { + int count; + int usable; + char *name; + char *usage; + char *help; + char **command; +}; +static struct defcmd_set *defcmd_set; +static int defcmd_set_count; +static int defcmd_in_progress; + +/* Forward references */ +static int kdb_exec_defcmd(int argc, const char **argv); + +static int kdb_defcmd2(const char *cmdstr, const char *argv0) +{ + struct defcmd_set *s = defcmd_set + defcmd_set_count - 1; + char **save_command = s->command; + if (strcmp(argv0, "endefcmd") == 0) { + defcmd_in_progress = 0; + if (!s->count) + s->usable = 0; + if (s->usable) + /* macros are always safe because when executed each + * internal command re-enters kdb_parse() and is + * safety checked individually. + */ + kdb_register_flags(s->name, kdb_exec_defcmd, s->usage, + s->help, 0, + KDB_ENABLE_ALWAYS_SAFE); + return 0; + } + if (!s->usable) + return KDB_NOTIMP; + s->command = kzalloc((s->count + 1) * sizeof(*(s->command)), GFP_KDB); + if (!s->command) { + kdb_printf("Could not allocate new kdb_defcmd table for %s\n", + cmdstr); + s->usable = 0; + return KDB_NOTIMP; + } + memcpy(s->command, save_command, s->count * sizeof(*(s->command))); + s->command[s->count++] = kdb_strdup(cmdstr, GFP_KDB); + kfree(save_command); + return 0; +} + +static int kdb_defcmd(int argc, const char **argv) +{ + struct defcmd_set *save_defcmd_set = defcmd_set, *s; + if (defcmd_in_progress) { + kdb_printf("kdb: nested defcmd detected, assuming missing " + "endefcmd\n"); + kdb_defcmd2("endefcmd", "endefcmd"); + } + if (argc == 0) { + int i; + for (s = defcmd_set; s < defcmd_set + defcmd_set_count; ++s) { + kdb_printf("defcmd %s \"%s\" \"%s\"\n", s->name, + s->usage, s->help); + for (i = 0; i < s->count; ++i) + kdb_printf("%s", s->command[i]); + kdb_printf("endefcmd\n"); + } + return 0; + } + if (argc != 3) + return KDB_ARGCOUNT; + if (in_dbg_master()) { + kdb_printf("Command only available during kdb_init()\n"); + return KDB_NOTIMP; + } + defcmd_set = kmalloc((defcmd_set_count + 1) * sizeof(*defcmd_set), + GFP_KDB); + if (!defcmd_set) + goto fail_defcmd; + memcpy(defcmd_set, save_defcmd_set, + defcmd_set_count * sizeof(*defcmd_set)); + s = defcmd_set + defcmd_set_count; + memset(s, 0, sizeof(*s)); + s->usable = 1; + s->name = kdb_strdup(argv[1], GFP_KDB); + if (!s->name) + goto fail_name; + s->usage = kdb_strdup(argv[2], GFP_KDB); + if (!s->usage) + goto fail_usage; + s->help = kdb_strdup(argv[3], GFP_KDB); + if (!s->help) + goto fail_help; + if (s->usage[0] == '"') { + strcpy(s->usage, argv[2]+1); + s->usage[strlen(s->usage)-1] = '\0'; + } + if (s->help[0] == '"') { + strcpy(s->help, argv[3]+1); + s->help[strlen(s->help)-1] = '\0'; + } + ++defcmd_set_count; + defcmd_in_progress = 1; + kfree(save_defcmd_set); + return 0; +fail_help: + kfree(s->usage); +fail_usage: + kfree(s->name); +fail_name: + kfree(defcmd_set); +fail_defcmd: + kdb_printf("Could not allocate new defcmd_set entry for %s\n", argv[1]); + defcmd_set = save_defcmd_set; + return KDB_NOTIMP; +} + +/* + * kdb_exec_defcmd - Execute the set of commands associated with this + * defcmd name. + * Inputs: + * argc argument count + * argv argument vector + * Returns: + * zero for success, a kdb diagnostic if error + */ +static int kdb_exec_defcmd(int argc, const char **argv) +{ + int i, ret; + struct defcmd_set *s; + if (argc != 0) + return KDB_ARGCOUNT; + for (s = defcmd_set, i = 0; i < defcmd_set_count; ++i, ++s) { + if (strcmp(s->name, argv[0]) == 0) + break; + } + if (i == defcmd_set_count) { + kdb_printf("kdb_exec_defcmd: could not find commands for %s\n", + argv[0]); + return KDB_NOTIMP; + } + for (i = 0; i < s->count; ++i) { + /* Recursive use of kdb_parse, do not use argv after + * this point */ + argv = NULL; + kdb_printf("[%s]kdb> %s\n", s->name, s->command[i]); + ret = kdb_parse(s->command[i]); + if (ret) + return ret; + } + return 0; +} + +/* Command history */ +#define KDB_CMD_HISTORY_COUNT 32 +#define CMD_BUFLEN 200 /* kdb_printf: max printline + * size == 256 */ +static unsigned int cmd_head, cmd_tail; +static unsigned int cmdptr; +static char cmd_hist[KDB_CMD_HISTORY_COUNT][CMD_BUFLEN]; +static char cmd_cur[CMD_BUFLEN]; + +/* + * The "str" argument may point to something like | grep xyz + */ +static void parse_grep(const char *str) +{ + int len; + char *cp = (char *)str, *cp2; + + /* sanity check: we should have been called with the \ first */ + if (*cp != '|') + return; + cp++; + while (isspace(*cp)) + cp++; + if (strncmp(cp, "grep ", 5)) { + kdb_printf("invalid 'pipe', see grephelp\n"); + return; + } + cp += 5; + while (isspace(*cp)) + cp++; + cp2 = strchr(cp, '\n'); + if (cp2) + *cp2 = '\0'; /* remove the trailing newline */ + len = strlen(cp); + if (len == 0) { + kdb_printf("invalid 'pipe', see grephelp\n"); + return; + } + /* now cp points to a nonzero length search string */ + if (*cp == '"') { + /* allow it be "x y z" by removing the "'s - there must + be two of them */ + cp++; + cp2 = strchr(cp, '"'); + if (!cp2) { + kdb_printf("invalid quoted string, see grephelp\n"); + return; + } + *cp2 = '\0'; /* end the string where the 2nd " was */ + } + kdb_grep_leading = 0; + if (*cp == '^') { + kdb_grep_leading = 1; + cp++; + } + len = strlen(cp); + kdb_grep_trailing = 0; + if (*(cp+len-1) == '$') { + kdb_grep_trailing = 1; + *(cp+len-1) = '\0'; + } + len = strlen(cp); + if (!len) + return; + if (len >= KDB_GREP_STRLEN) { + kdb_printf("search string too long\n"); + return; + } + strcpy(kdb_grep_string, cp); + kdb_grepping_flag++; + return; +} + +/* + * kdb_parse - Parse the command line, search the command table for a + * matching command and invoke the command function. This + * function may be called recursively, if it is, the second call + * will overwrite argv and cbuf. It is the caller's + * responsibility to save their argv if they recursively call + * kdb_parse(). + * Parameters: + * cmdstr The input command line to be parsed. + * regs The registers at the time kdb was entered. + * Returns: + * Zero for success, a kdb diagnostic if failure. + * Remarks: + * Limited to 20 tokens. + * + * Real rudimentary tokenization. Basically only whitespace + * is considered a token delimeter (but special consideration + * is taken of the '=' sign as used by the 'set' command). + * + * The algorithm used to tokenize the input string relies on + * there being at least one whitespace (or otherwise useless) + * character between tokens as the character immediately following + * the token is altered in-place to a null-byte to terminate the + * token string. + */ + +#define MAXARGC 20 + +int kdb_parse(const char *cmdstr) +{ + static char *argv[MAXARGC]; + static int argc; + static char cbuf[CMD_BUFLEN+2]; + char *cp; + char *cpp, quoted; + kdbtab_t *tp; + int i, escaped, ignore_errors = 0, check_grep = 0; + + /* + * First tokenize the command string. + */ + cp = (char *)cmdstr; + + if (KDB_FLAG(CMD_INTERRUPT)) { + /* Previous command was interrupted, newline must not + * repeat the command */ + KDB_FLAG_CLEAR(CMD_INTERRUPT); + KDB_STATE_SET(PAGER); + argc = 0; /* no repeat */ + } + + if (*cp != '\n' && *cp != '\0') { + argc = 0; + cpp = cbuf; + while (*cp) { + /* skip whitespace */ + while (isspace(*cp)) + cp++; + if ((*cp == '\0') || (*cp == '\n') || + (*cp == '#' && !defcmd_in_progress)) + break; + /* special case: check for | grep pattern */ + if (*cp == '|') { + check_grep++; + break; + } + if (cpp >= cbuf + CMD_BUFLEN) { + kdb_printf("kdb_parse: command buffer " + "overflow, command ignored\n%s\n", + cmdstr); + return KDB_NOTFOUND; + } + if (argc >= MAXARGC - 1) { + kdb_printf("kdb_parse: too many arguments, " + "command ignored\n%s\n", cmdstr); + return KDB_NOTFOUND; + } + argv[argc++] = cpp; + escaped = 0; + quoted = '\0'; + /* Copy to next unquoted and unescaped + * whitespace or '=' */ + while (*cp && *cp != '\n' && + (escaped || quoted || !isspace(*cp))) { + if (cpp >= cbuf + CMD_BUFLEN) + break; + if (escaped) { + escaped = 0; + *cpp++ = *cp++; + continue; + } + if (*cp == '\\') { + escaped = 1; + ++cp; + continue; + } + if (*cp == quoted) + quoted = '\0'; + else if (*cp == '\'' || *cp == '"') + quoted = *cp; + *cpp = *cp++; + if (*cpp == '=' && !quoted) + break; + ++cpp; + } + *cpp++ = '\0'; /* Squash a ws or '=' character */ + } + } + if (!argc) + return 0; + if (check_grep) + parse_grep(cp); + if (defcmd_in_progress) { + int result = kdb_defcmd2(cmdstr, argv[0]); + if (!defcmd_in_progress) { + argc = 0; /* avoid repeat on endefcmd */ + *(argv[0]) = '\0'; + } + return result; + } + if (argv[0][0] == '-' && argv[0][1] && + (argv[0][1] < '0' || argv[0][1] > '9')) { + ignore_errors = 1; + ++argv[0]; + } + + for_each_kdbcmd(tp, i) { + if (tp->cmd_name) { + /* + * If this command is allowed to be abbreviated, + * check to see if this is it. + */ + + if (tp->cmd_minlen + && (strlen(argv[0]) <= tp->cmd_minlen)) { + if (strncmp(argv[0], + tp->cmd_name, + tp->cmd_minlen) == 0) { + break; + } + } + + if (strcmp(argv[0], tp->cmd_name) == 0) + break; + } + } + + /* + * If we don't find a command by this name, see if the first + * few characters of this match any of the known commands. + * e.g., md1c20 should match md. + */ + if (i == kdb_max_commands) { + for_each_kdbcmd(tp, i) { + if (tp->cmd_name) { + if (strncmp(argv[0], + tp->cmd_name, + strlen(tp->cmd_name)) == 0) { + break; + } + } + } + } + + if (i < kdb_max_commands) { + int result; + + if (!kdb_check_flags(tp->cmd_flags, kdb_cmd_enabled, argc <= 1)) + return KDB_NOPERM; + + KDB_STATE_SET(CMD); + result = (*tp->cmd_func)(argc-1, (const char **)argv); + if (result && ignore_errors && result > KDB_CMD_GO) + result = 0; + KDB_STATE_CLEAR(CMD); + + if (tp->cmd_flags & KDB_REPEAT_WITH_ARGS) + return result; + + argc = tp->cmd_flags & KDB_REPEAT_NO_ARGS ? 1 : 0; + if (argv[argc]) + *(argv[argc]) = '\0'; + return result; + } + + /* + * If the input with which we were presented does not + * map to an existing command, attempt to parse it as an + * address argument and display the result. Useful for + * obtaining the address of a variable, or the nearest symbol + * to an address contained in a register. + */ + { + unsigned long value; + char *name = NULL; + long offset; + int nextarg = 0; + + if (kdbgetaddrarg(0, (const char **)argv, &nextarg, + &value, &offset, &name)) { + return KDB_NOTFOUND; + } + + kdb_printf("%s = ", argv[0]); + kdb_symbol_print(value, NULL, KDB_SP_DEFAULT); + kdb_printf("\n"); + return 0; + } +} + + +static int handle_ctrl_cmd(char *cmd) +{ +#define CTRL_P 16 +#define CTRL_N 14 + + /* initial situation */ + if (cmd_head == cmd_tail) + return 0; + switch (*cmd) { + case CTRL_P: + if (cmdptr != cmd_tail) + cmdptr = (cmdptr-1) % KDB_CMD_HISTORY_COUNT; + strncpy(cmd_cur, cmd_hist[cmdptr], CMD_BUFLEN); + return 1; + case CTRL_N: + if (cmdptr != cmd_head) + cmdptr = (cmdptr+1) % KDB_CMD_HISTORY_COUNT; + strncpy(cmd_cur, cmd_hist[cmdptr], CMD_BUFLEN); + return 1; + } + return 0; +} + +/* + * kdb_reboot - This function implements the 'reboot' command. Reboot + * the system immediately, or loop for ever on failure. + */ +static int kdb_reboot(int argc, const char **argv) +{ + emergency_restart(); + kdb_printf("Hmm, kdb_reboot did not reboot, spinning here\n"); + while (1) + cpu_relax(); + /* NOTREACHED */ + return 0; +} + +static void kdb_dumpregs(struct pt_regs *regs) +{ + int old_lvl = console_loglevel; + console_loglevel = CONSOLE_LOGLEVEL_MOTORMOUTH; + kdb_trap_printk++; + show_regs(regs); + kdb_trap_printk--; + kdb_printf("\n"); + console_loglevel = old_lvl; +} + +void kdb_set_current_task(struct task_struct *p) +{ + kdb_current_task = p; + + if (kdb_task_has_cpu(p)) { + kdb_current_regs = KDB_TSKREGS(kdb_process_cpu(p)); + return; + } + kdb_current_regs = NULL; +} + +/* + * kdb_local - The main code for kdb. This routine is invoked on a + * specific processor, it is not global. The main kdb() routine + * ensures that only one processor at a time is in this routine. + * This code is called with the real reason code on the first + * entry to a kdb session, thereafter it is called with reason + * SWITCH, even if the user goes back to the original cpu. + * Inputs: + * reason The reason KDB was invoked + * error The hardware-defined error code + * regs The exception frame at time of fault/breakpoint. + * db_result Result code from the break or debug point. + * Returns: + * 0 KDB was invoked for an event which it wasn't responsible + * 1 KDB handled the event for which it was invoked. + * KDB_CMD_GO User typed 'go'. + * KDB_CMD_CPU User switched to another cpu. + * KDB_CMD_SS Single step. + */ +static int kdb_local(kdb_reason_t reason, int error, struct pt_regs *regs, + kdb_dbtrap_t db_result) +{ + char *cmdbuf; + int diag; + struct task_struct *kdb_current = + kdb_curr_task(raw_smp_processor_id()); + + KDB_DEBUG_STATE("kdb_local 1", reason); + kdb_go_count = 0; + if (reason == KDB_REASON_DEBUG) { + /* special case below */ + } else { + kdb_printf("\nEntering kdb (current=0x%p, pid %d) ", + kdb_current, kdb_current ? kdb_current->pid : 0); +#if defined(CONFIG_SMP) + kdb_printf("on processor %d ", raw_smp_processor_id()); +#endif + } + + switch (reason) { + case KDB_REASON_DEBUG: + { + /* + * If re-entering kdb after a single step + * command, don't print the message. + */ + switch (db_result) { + case KDB_DB_BPT: + kdb_printf("\nEntering kdb (0x%p, pid %d) ", + kdb_current, kdb_current->pid); +#if defined(CONFIG_SMP) + kdb_printf("on processor %d ", raw_smp_processor_id()); +#endif + kdb_printf("due to Debug @ " kdb_machreg_fmt "\n", + instruction_pointer(regs)); + break; + case KDB_DB_SS: + break; + case KDB_DB_SSBPT: + KDB_DEBUG_STATE("kdb_local 4", reason); + return 1; /* kdba_db_trap did the work */ + default: + kdb_printf("kdb: Bad result from kdba_db_trap: %d\n", + db_result); + break; + } + + } + break; + case KDB_REASON_ENTER: + if (KDB_STATE(KEYBOARD)) + kdb_printf("due to Keyboard Entry\n"); + else + kdb_printf("due to KDB_ENTER()\n"); + break; + case KDB_REASON_KEYBOARD: + KDB_STATE_SET(KEYBOARD); + kdb_printf("due to Keyboard Entry\n"); + break; + case KDB_REASON_ENTER_SLAVE: + /* drop through, slaves only get released via cpu switch */ + case KDB_REASON_SWITCH: + kdb_printf("due to cpu switch\n"); + break; + case KDB_REASON_OOPS: + kdb_printf("Oops: %s\n", kdb_diemsg); + kdb_printf("due to oops @ " kdb_machreg_fmt "\n", + instruction_pointer(regs)); + kdb_dumpregs(regs); + break; + case KDB_REASON_SYSTEM_NMI: + kdb_printf("due to System NonMaskable Interrupt\n"); + break; + case KDB_REASON_NMI: + kdb_printf("due to NonMaskable Interrupt @ " + kdb_machreg_fmt "\n", + instruction_pointer(regs)); + break; + case KDB_REASON_SSTEP: + case KDB_REASON_BREAK: + kdb_printf("due to %s @ " kdb_machreg_fmt "\n", + reason == KDB_REASON_BREAK ? + "Breakpoint" : "SS trap", instruction_pointer(regs)); + /* + * Determine if this breakpoint is one that we + * are interested in. + */ + if (db_result != KDB_DB_BPT) { + kdb_printf("kdb: error return from kdba_bp_trap: %d\n", + db_result); + KDB_DEBUG_STATE("kdb_local 6", reason); + return 0; /* Not for us, dismiss it */ + } + break; + case KDB_REASON_RECURSE: + kdb_printf("due to Recursion @ " kdb_machreg_fmt "\n", + instruction_pointer(regs)); + break; + default: + kdb_printf("kdb: unexpected reason code: %d\n", reason); + KDB_DEBUG_STATE("kdb_local 8", reason); + return 0; /* Not for us, dismiss it */ + } + + while (1) { + /* + * Initialize pager context. + */ + kdb_nextline = 1; + KDB_STATE_CLEAR(SUPPRESS); + kdb_grepping_flag = 0; + /* ensure the old search does not leak into '/' commands */ + kdb_grep_string[0] = '\0'; + + cmdbuf = cmd_cur; + *cmdbuf = '\0'; + *(cmd_hist[cmd_head]) = '\0'; + +do_full_getstr: +#if defined(CONFIG_SMP) + snprintf(kdb_prompt_str, CMD_BUFLEN, kdbgetenv("PROMPT"), + raw_smp_processor_id()); +#else + snprintf(kdb_prompt_str, CMD_BUFLEN, kdbgetenv("PROMPT")); +#endif + if (defcmd_in_progress) + strncat(kdb_prompt_str, "[defcmd]", CMD_BUFLEN); + + /* + * Fetch command from keyboard + */ + cmdbuf = kdb_getstr(cmdbuf, CMD_BUFLEN, kdb_prompt_str); + if (*cmdbuf != '\n') { + if (*cmdbuf < 32) { + if (cmdptr == cmd_head) { + strncpy(cmd_hist[cmd_head], cmd_cur, + CMD_BUFLEN); + *(cmd_hist[cmd_head] + + strlen(cmd_hist[cmd_head])-1) = '\0'; + } + if (!handle_ctrl_cmd(cmdbuf)) + *(cmd_cur+strlen(cmd_cur)-1) = '\0'; + cmdbuf = cmd_cur; + goto do_full_getstr; + } else { + strncpy(cmd_hist[cmd_head], cmd_cur, + CMD_BUFLEN); + } + + cmd_head = (cmd_head+1) % KDB_CMD_HISTORY_COUNT; + if (cmd_head == cmd_tail) + cmd_tail = (cmd_tail+1) % KDB_CMD_HISTORY_COUNT; + } + + cmdptr = cmd_head; + diag = kdb_parse(cmdbuf); + if (diag == KDB_NOTFOUND) { + kdb_printf("Unknown kdb command: '%s'\n", cmdbuf); + diag = 0; + } + if (diag == KDB_CMD_GO + || diag == KDB_CMD_CPU + || diag == KDB_CMD_SS + || diag == KDB_CMD_KGDB) + break; + + if (diag) + kdb_cmderror(diag); + } + KDB_DEBUG_STATE("kdb_local 9", diag); + return diag; +} + + +/* + * kdb_print_state - Print the state data for the current processor + * for debugging. + * Inputs: + * text Identifies the debug point + * value Any integer value to be printed, e.g. reason code. + */ +void kdb_print_state(const char *text, int value) +{ + kdb_printf("state: %s cpu %d value %d initial %d state %x\n", + text, raw_smp_processor_id(), value, kdb_initial_cpu, + kdb_state); +} + +/* + * kdb_main_loop - After initial setup and assignment of the + * controlling cpu, all cpus are in this loop. One cpu is in + * control and will issue the kdb prompt, the others will spin + * until 'go' or cpu switch. + * + * To get a consistent view of the kernel stacks for all + * processes, this routine is invoked from the main kdb code via + * an architecture specific routine. kdba_main_loop is + * responsible for making the kernel stacks consistent for all + * processes, there should be no difference between a blocked + * process and a running process as far as kdb is concerned. + * Inputs: + * reason The reason KDB was invoked + * error The hardware-defined error code + * reason2 kdb's current reason code. + * Initially error but can change + * according to kdb state. + * db_result Result code from break or debug point. + * regs The exception frame at time of fault/breakpoint. + * should always be valid. + * Returns: + * 0 KDB was invoked for an event which it wasn't responsible + * 1 KDB handled the event for which it was invoked. + */ +int kdb_main_loop(kdb_reason_t reason, kdb_reason_t reason2, int error, + kdb_dbtrap_t db_result, struct pt_regs *regs) +{ + int result = 1; + /* Stay in kdb() until 'go', 'ss[b]' or an error */ + while (1) { + /* + * All processors except the one that is in control + * will spin here. + */ + KDB_DEBUG_STATE("kdb_main_loop 1", reason); + while (KDB_STATE(HOLD_CPU)) { + /* state KDB is turned off by kdb_cpu to see if the + * other cpus are still live, each cpu in this loop + * turns it back on. + */ + if (!KDB_STATE(KDB)) + KDB_STATE_SET(KDB); + } + + KDB_STATE_CLEAR(SUPPRESS); + KDB_DEBUG_STATE("kdb_main_loop 2", reason); + if (KDB_STATE(LEAVING)) + break; /* Another cpu said 'go' */ + /* Still using kdb, this processor is in control */ + result = kdb_local(reason2, error, regs, db_result); + KDB_DEBUG_STATE("kdb_main_loop 3", result); + + if (result == KDB_CMD_CPU) + break; + + if (result == KDB_CMD_SS) { + KDB_STATE_SET(DOING_SS); + break; + } + + if (result == KDB_CMD_KGDB) { + if (!KDB_STATE(DOING_KGDB)) + kdb_printf("Entering please attach debugger " + "or use $D#44+ or $3#33\n"); + break; + } + if (result && result != 1 && result != KDB_CMD_GO) + kdb_printf("\nUnexpected kdb_local return code %d\n", + result); + KDB_DEBUG_STATE("kdb_main_loop 4", reason); + break; + } + if (KDB_STATE(DOING_SS)) + KDB_STATE_CLEAR(SSBPT); + + /* Clean up any keyboard devices before leaving */ + kdb_kbd_cleanup_state(); + + return result; +} + +/* + * kdb_mdr - This function implements the guts of the 'mdr', memory + * read command. + * mdr , + * Inputs: + * addr Start address + * count Number of bytes + * Returns: + * Always 0. Any errors are detected and printed by kdb_getarea. + */ +static int kdb_mdr(unsigned long addr, unsigned int count) +{ + unsigned char c; + while (count--) { + if (kdb_getarea(c, addr)) + return 0; + kdb_printf("%02x", c); + addr++; + } + kdb_printf("\n"); + return 0; +} + +/* + * kdb_md - This function implements the 'md', 'md1', 'md2', 'md4', + * 'md8' 'mdr' and 'mds' commands. + * + * md|mds [ [ []]] + * mdWcN [ [ []]] + * where W = is the width (1, 2, 4 or 8) and N is the count. + * for eg., md1c20 reads 20 bytes, 1 at a time. + * mdr , + */ +static void kdb_md_line(const char *fmtstr, unsigned long addr, + int symbolic, int nosect, int bytesperword, + int num, int repeat, int phys) +{ + /* print just one line of data */ + kdb_symtab_t symtab; + char cbuf[32]; + char *c = cbuf; + int i; + unsigned long word; + + memset(cbuf, '\0', sizeof(cbuf)); + if (phys) + kdb_printf("phys " kdb_machreg_fmt0 " ", addr); + else + kdb_printf(kdb_machreg_fmt0 " ", addr); + + for (i = 0; i < num && repeat--; i++) { + if (phys) { + if (kdb_getphysword(&word, addr, bytesperword)) + break; + } else if (kdb_getword(&word, addr, bytesperword)) + break; + kdb_printf(fmtstr, word); + if (symbolic) + kdbnearsym(word, &symtab); + else + memset(&symtab, 0, sizeof(symtab)); + if (symtab.sym_name) { + kdb_symbol_print(word, &symtab, 0); + if (!nosect) { + kdb_printf("\n"); + kdb_printf(" %s %s " + kdb_machreg_fmt " " + kdb_machreg_fmt " " + kdb_machreg_fmt, symtab.mod_name, + symtab.sec_name, symtab.sec_start, + symtab.sym_start, symtab.sym_end); + } + addr += bytesperword; + } else { + union { + u64 word; + unsigned char c[8]; + } wc; + unsigned char *cp; +#ifdef __BIG_ENDIAN + cp = wc.c + 8 - bytesperword; +#else + cp = wc.c; +#endif + wc.word = word; +#define printable_char(c) \ + ({unsigned char __c = c; isascii(__c) && isprint(__c) ? __c : '.'; }) + switch (bytesperword) { + case 8: + *c++ = printable_char(*cp++); + *c++ = printable_char(*cp++); + *c++ = printable_char(*cp++); + *c++ = printable_char(*cp++); + addr += 4; + case 4: + *c++ = printable_char(*cp++); + *c++ = printable_char(*cp++); + addr += 2; + case 2: + *c++ = printable_char(*cp++); + addr++; + case 1: + *c++ = printable_char(*cp++); + addr++; + break; + } +#undef printable_char + } + } + kdb_printf("%*s %s\n", (int)((num-i)*(2*bytesperword + 1)+1), + " ", cbuf); +} + +static int kdb_md(int argc, const char **argv) +{ + static unsigned long last_addr; + static int last_radix, last_bytesperword, last_repeat; + int radix = 16, mdcount = 8, bytesperword = KDB_WORD_SIZE, repeat; + int nosect = 0; + char fmtchar, fmtstr[64]; + unsigned long addr; + unsigned long word; + long offset = 0; + int symbolic = 0; + int valid = 0; + int phys = 0; + + kdbgetintenv("MDCOUNT", &mdcount); + kdbgetintenv("RADIX", &radix); + kdbgetintenv("BYTESPERWORD", &bytesperword); + + /* Assume 'md ' and start with environment values */ + repeat = mdcount * 16 / bytesperword; + + if (strcmp(argv[0], "mdr") == 0) { + if (argc != 2) + return KDB_ARGCOUNT; + valid = 1; + } else if (isdigit(argv[0][2])) { + bytesperword = (int)(argv[0][2] - '0'); + if (bytesperword == 0) { + bytesperword = last_bytesperword; + if (bytesperword == 0) + bytesperword = 4; + } + last_bytesperword = bytesperword; + repeat = mdcount * 16 / bytesperword; + if (!argv[0][3]) + valid = 1; + else if (argv[0][3] == 'c' && argv[0][4]) { + char *p; + repeat = simple_strtoul(argv[0] + 4, &p, 10); + mdcount = ((repeat * bytesperword) + 15) / 16; + valid = !*p; + } + last_repeat = repeat; + } else if (strcmp(argv[0], "md") == 0) + valid = 1; + else if (strcmp(argv[0], "mds") == 0) + valid = 1; + else if (strcmp(argv[0], "mdp") == 0) { + phys = valid = 1; + } + if (!valid) + return KDB_NOTFOUND; + + if (argc == 0) { + if (last_addr == 0) + return KDB_ARGCOUNT; + addr = last_addr; + radix = last_radix; + bytesperword = last_bytesperword; + repeat = last_repeat; + mdcount = ((repeat * bytesperword) + 15) / 16; + } + + if (argc) { + unsigned long val; + int diag, nextarg = 1; + diag = kdbgetaddrarg(argc, argv, &nextarg, &addr, + &offset, NULL); + if (diag) + return diag; + if (argc > nextarg+2) + return KDB_ARGCOUNT; + + if (argc >= nextarg) { + diag = kdbgetularg(argv[nextarg], &val); + if (!diag) { + mdcount = (int) val; + repeat = mdcount * 16 / bytesperword; + } + } + if (argc >= nextarg+1) { + diag = kdbgetularg(argv[nextarg+1], &val); + if (!diag) + radix = (int) val; + } + } + + if (strcmp(argv[0], "mdr") == 0) + return kdb_mdr(addr, mdcount); + + switch (radix) { + case 10: + fmtchar = 'd'; + break; + case 16: + fmtchar = 'x'; + break; + case 8: + fmtchar = 'o'; + break; + default: + return KDB_BADRADIX; + } + + last_radix = radix; + + if (bytesperword > KDB_WORD_SIZE) + return KDB_BADWIDTH; + + switch (bytesperword) { + case 8: + sprintf(fmtstr, "%%16.16l%c ", fmtchar); + break; + case 4: + sprintf(fmtstr, "%%8.8l%c ", fmtchar); + break; + case 2: + sprintf(fmtstr, "%%4.4l%c ", fmtchar); + break; + case 1: + sprintf(fmtstr, "%%2.2l%c ", fmtchar); + break; + default: + return KDB_BADWIDTH; + } + + last_repeat = repeat; + last_bytesperword = bytesperword; + + if (strcmp(argv[0], "mds") == 0) { + symbolic = 1; + /* Do not save these changes as last_*, they are temporary mds + * overrides. + */ + bytesperword = KDB_WORD_SIZE; + repeat = mdcount; + kdbgetintenv("NOSECT", &nosect); + } + + /* Round address down modulo BYTESPERWORD */ + + addr &= ~(bytesperword-1); + + while (repeat > 0) { + unsigned long a; + int n, z, num = (symbolic ? 1 : (16 / bytesperword)); + + if (KDB_FLAG(CMD_INTERRUPT)) + return 0; + for (a = addr, z = 0; z < repeat; a += bytesperword, ++z) { + if (phys) { + if (kdb_getphysword(&word, a, bytesperword) + || word) + break; + } else if (kdb_getword(&word, a, bytesperword) || word) + break; + } + n = min(num, repeat); + kdb_md_line(fmtstr, addr, symbolic, nosect, bytesperword, + num, repeat, phys); + addr += bytesperword * n; + repeat -= n; + z = (z + num - 1) / num; + if (z > 2) { + int s = num * (z-2); + kdb_printf(kdb_machreg_fmt0 "-" kdb_machreg_fmt0 + " zero suppressed\n", + addr, addr + bytesperword * s - 1); + addr += bytesperword * s; + repeat -= s; + } + } + last_addr = addr; + + return 0; +} + +/* + * kdb_mm - This function implements the 'mm' command. + * mm address-expression new-value + * Remarks: + * mm works on machine words, mmW works on bytes. + */ +static int kdb_mm(int argc, const char **argv) +{ + int diag; + unsigned long addr; + long offset = 0; + unsigned long contents; + int nextarg; + int width; + + if (argv[0][2] && !isdigit(argv[0][2])) + return KDB_NOTFOUND; + + if (argc < 2) + return KDB_ARGCOUNT; + + nextarg = 1; + diag = kdbgetaddrarg(argc, argv, &nextarg, &addr, &offset, NULL); + if (diag) + return diag; + + if (nextarg > argc) + return KDB_ARGCOUNT; + diag = kdbgetaddrarg(argc, argv, &nextarg, &contents, NULL, NULL); + if (diag) + return diag; + + if (nextarg != argc + 1) + return KDB_ARGCOUNT; + + width = argv[0][2] ? (argv[0][2] - '0') : (KDB_WORD_SIZE); + diag = kdb_putword(addr, contents, width); + if (diag) + return diag; + + kdb_printf(kdb_machreg_fmt " = " kdb_machreg_fmt "\n", addr, contents); + + return 0; +} + +/* + * kdb_go - This function implements the 'go' command. + * go [address-expression] + */ +static int kdb_go(int argc, const char **argv) +{ + unsigned long addr; + int diag; + int nextarg; + long offset; + + if (raw_smp_processor_id() != kdb_initial_cpu) { + kdb_printf("go must execute on the entry cpu, " + "please use \"cpu %d\" and then execute go\n", + kdb_initial_cpu); + return KDB_BADCPUNUM; + } + if (argc == 1) { + nextarg = 1; + diag = kdbgetaddrarg(argc, argv, &nextarg, + &addr, &offset, NULL); + if (diag) + return diag; + } else if (argc) { + return KDB_ARGCOUNT; + } + + diag = KDB_CMD_GO; + if (KDB_FLAG(CATASTROPHIC)) { + kdb_printf("Catastrophic error detected\n"); + kdb_printf("kdb_continue_catastrophic=%d, ", + kdb_continue_catastrophic); + if (kdb_continue_catastrophic == 0 && kdb_go_count++ == 0) { + kdb_printf("type go a second time if you really want " + "to continue\n"); + return 0; + } + if (kdb_continue_catastrophic == 2) { + kdb_printf("forcing reboot\n"); + kdb_reboot(0, NULL); + } + kdb_printf("attempting to continue\n"); + } + return diag; +} + +/* + * kdb_rd - This function implements the 'rd' command. + */ +static int kdb_rd(int argc, const char **argv) +{ + int len = kdb_check_regs(); +#if DBG_MAX_REG_NUM > 0 + int i; + char *rname; + int rsize; + u64 reg64; + u32 reg32; + u16 reg16; + u8 reg8; + + if (len) + return len; + + for (i = 0; i < DBG_MAX_REG_NUM; i++) { + rsize = dbg_reg_def[i].size * 2; + if (rsize > 16) + rsize = 2; + if (len + strlen(dbg_reg_def[i].name) + 4 + rsize > 80) { + len = 0; + kdb_printf("\n"); + } + if (len) + len += kdb_printf(" "); + switch(dbg_reg_def[i].size * 8) { + case 8: + rname = dbg_get_reg(i, ®8, kdb_current_regs); + if (!rname) + break; + len += kdb_printf("%s: %02x", rname, reg8); + break; + case 16: + rname = dbg_get_reg(i, ®16, kdb_current_regs); + if (!rname) + break; + len += kdb_printf("%s: %04x", rname, reg16); + break; + case 32: + rname = dbg_get_reg(i, ®32, kdb_current_regs); + if (!rname) + break; + len += kdb_printf("%s: %08x", rname, reg32); + break; + case 64: + rname = dbg_get_reg(i, ®64, kdb_current_regs); + if (!rname) + break; + len += kdb_printf("%s: %016llx", rname, reg64); + break; + default: + len += kdb_printf("%s: ??", dbg_reg_def[i].name); + } + } + kdb_printf("\n"); +#else + if (len) + return len; + + kdb_dumpregs(kdb_current_regs); +#endif + return 0; +} + +/* + * kdb_rm - This function implements the 'rm' (register modify) command. + * rm register-name new-contents + * Remarks: + * Allows register modification with the same restrictions as gdb + */ +static int kdb_rm(int argc, const char **argv) +{ +#if DBG_MAX_REG_NUM > 0 + int diag; + const char *rname; + int i; + u64 reg64; + u32 reg32; + u16 reg16; + u8 reg8; + + if (argc != 2) + return KDB_ARGCOUNT; + /* + * Allow presence or absence of leading '%' symbol. + */ + rname = argv[1]; + if (*rname == '%') + rname++; + + diag = kdbgetu64arg(argv[2], ®64); + if (diag) + return diag; + + diag = kdb_check_regs(); + if (diag) + return diag; + + diag = KDB_BADREG; + for (i = 0; i < DBG_MAX_REG_NUM; i++) { + if (strcmp(rname, dbg_reg_def[i].name) == 0) { + diag = 0; + break; + } + } + if (!diag) { + switch(dbg_reg_def[i].size * 8) { + case 8: + reg8 = reg64; + dbg_set_reg(i, ®8, kdb_current_regs); + break; + case 16: + reg16 = reg64; + dbg_set_reg(i, ®16, kdb_current_regs); + break; + case 32: + reg32 = reg64; + dbg_set_reg(i, ®32, kdb_current_regs); + break; + case 64: + dbg_set_reg(i, ®64, kdb_current_regs); + break; + } + } + return diag; +#else + kdb_printf("ERROR: Register set currently not implemented\n"); + return 0; +#endif +} + +#if defined(CONFIG_MAGIC_SYSRQ) +/* + * kdb_sr - This function implements the 'sr' (SYSRQ key) command + * which interfaces to the soi-disant MAGIC SYSRQ functionality. + * sr + */ +static int kdb_sr(int argc, const char **argv) +{ + bool check_mask = + !kdb_check_flags(KDB_ENABLE_ALL, kdb_cmd_enabled, false); + + if (argc != 1) + return KDB_ARGCOUNT; + + kdb_trap_printk++; + __handle_sysrq(*argv[1], check_mask); + kdb_trap_printk--; + + return 0; +} +#endif /* CONFIG_MAGIC_SYSRQ */ + +/* + * kdb_ef - This function implements the 'regs' (display exception + * frame) command. This command takes an address and expects to + * find an exception frame at that address, formats and prints + * it. + * regs address-expression + * Remarks: + * Not done yet. + */ +static int kdb_ef(int argc, const char **argv) +{ + int diag; + unsigned long addr; + long offset; + int nextarg; + + if (argc != 1) + return KDB_ARGCOUNT; + + nextarg = 1; + diag = kdbgetaddrarg(argc, argv, &nextarg, &addr, &offset, NULL); + if (diag) + return diag; + show_regs((struct pt_regs *)addr); + return 0; +} + +#if defined(CONFIG_MODULES) +/* + * kdb_lsmod - This function implements the 'lsmod' command. Lists + * currently loaded kernel modules. + * Mostly taken from userland lsmod. + */ +static int kdb_lsmod(int argc, const char **argv) +{ + struct module *mod; + + if (argc != 0) + return KDB_ARGCOUNT; + + kdb_printf("Module Size modstruct Used by\n"); + list_for_each_entry(mod, kdb_modules, list) { + if (mod->state == MODULE_STATE_UNFORMED) + continue; + + kdb_printf("%-20s%8u 0x%p ", mod->name, + mod->core_size, (void *)mod); +#ifdef CONFIG_MODULE_UNLOAD + kdb_printf("%4d ", module_refcount(mod)); +#endif + if (mod->state == MODULE_STATE_GOING) + kdb_printf(" (Unloading)"); + else if (mod->state == MODULE_STATE_COMING) + kdb_printf(" (Loading)"); + else + kdb_printf(" (Live)"); + kdb_printf(" 0x%p", mod->module_core); + +#ifdef CONFIG_MODULE_UNLOAD + { + struct module_use *use; + kdb_printf(" [ "); + list_for_each_entry(use, &mod->source_list, + source_list) + kdb_printf("%s ", use->target->name); + kdb_printf("]\n"); + } +#endif + } + + return 0; +} + +#endif /* CONFIG_MODULES */ + +/* + * kdb_env - This function implements the 'env' command. Display the + * current environment variables. + */ + +static int kdb_env(int argc, const char **argv) +{ + int i; + + for (i = 0; i < __nenv; i++) { + if (__env[i]) + kdb_printf("%s\n", __env[i]); + } + + if (KDB_DEBUG(MASK)) + kdb_printf("KDBFLAGS=0x%x\n", kdb_flags); + + return 0; +} + +#ifdef CONFIG_PRINTK +/* + * kdb_dmesg - This function implements the 'dmesg' command to display + * the contents of the syslog buffer. + * dmesg [lines] [adjust] + */ +static int kdb_dmesg(int argc, const char **argv) +{ + int diag; + int logging; + int lines = 0; + int adjust = 0; + int n = 0; + int skip = 0; + struct kmsg_dumper dumper = { .active = 1 }; + size_t len; + char buf[201]; + + if (argc > 2) + return KDB_ARGCOUNT; + if (argc) { + char *cp; + lines = simple_strtol(argv[1], &cp, 0); + if (*cp) + lines = 0; + if (argc > 1) { + adjust = simple_strtoul(argv[2], &cp, 0); + if (*cp || adjust < 0) + adjust = 0; + } + } + + /* disable LOGGING if set */ + diag = kdbgetintenv("LOGGING", &logging); + if (!diag && logging) { + const char *setargs[] = { "set", "LOGGING", "0" }; + kdb_set(2, setargs); + } + + kmsg_dump_rewind_nolock(&dumper); + while (kmsg_dump_get_line_nolock(&dumper, 1, NULL, 0, NULL)) + n++; + + if (lines < 0) { + if (adjust >= n) + kdb_printf("buffer only contains %d lines, nothing " + "printed\n", n); + else if (adjust - lines >= n) + kdb_printf("buffer only contains %d lines, last %d " + "lines printed\n", n, n - adjust); + skip = adjust; + lines = abs(lines); + } else if (lines > 0) { + skip = n - lines - adjust; + lines = abs(lines); + if (adjust >= n) { + kdb_printf("buffer only contains %d lines, " + "nothing printed\n", n); + skip = n; + } else if (skip < 0) { + lines += skip; + skip = 0; + kdb_printf("buffer only contains %d lines, first " + "%d lines printed\n", n, lines); + } + } else { + lines = n; + } + + if (skip >= n || skip < 0) + return 0; + + kmsg_dump_rewind_nolock(&dumper); + while (kmsg_dump_get_line_nolock(&dumper, 1, buf, sizeof(buf), &len)) { + if (skip) { + skip--; + continue; + } + if (!lines--) + break; + if (KDB_FLAG(CMD_INTERRUPT)) + return 0; + + kdb_printf("%.*s\n", (int)len - 1, buf); + } + + return 0; +} +#endif /* CONFIG_PRINTK */ + +/* Make sure we balance enable/disable calls, must disable first. */ +static atomic_t kdb_nmi_disabled; + +static int kdb_disable_nmi(int argc, const char *argv[]) +{ + if (atomic_read(&kdb_nmi_disabled)) + return 0; + atomic_set(&kdb_nmi_disabled, 1); + arch_kgdb_ops.enable_nmi(0); + return 0; +} + +static int kdb_param_enable_nmi(const char *val, const struct kernel_param *kp) +{ + if (!atomic_add_unless(&kdb_nmi_disabled, -1, 0)) + return -EINVAL; + arch_kgdb_ops.enable_nmi(1); + return 0; +} + +static const struct kernel_param_ops kdb_param_ops_enable_nmi = { + .set = kdb_param_enable_nmi, +}; +module_param_cb(enable_nmi, &kdb_param_ops_enable_nmi, NULL, 0600); + +/* + * kdb_cpu - This function implements the 'cpu' command. + * cpu [] + * Returns: + * KDB_CMD_CPU for success, a kdb diagnostic if error + */ +static void kdb_cpu_status(void) +{ + int i, start_cpu, first_print = 1; + char state, prev_state = '?'; + + kdb_printf("Currently on cpu %d\n", raw_smp_processor_id()); + kdb_printf("Available cpus: "); + for (start_cpu = -1, i = 0; i < NR_CPUS; i++) { + if (!cpu_online(i)) { + state = 'F'; /* cpu is offline */ + } else if (!kgdb_info[i].enter_kgdb) { + state = 'D'; /* cpu is online but unresponsive */ + } else { + state = ' '; /* cpu is responding to kdb */ + if (kdb_task_state_char(KDB_TSK(i)) == 'I') + state = 'I'; /* idle task */ + } + if (state != prev_state) { + if (prev_state != '?') { + if (!first_print) + kdb_printf(", "); + first_print = 0; + kdb_printf("%d", start_cpu); + if (start_cpu < i-1) + kdb_printf("-%d", i-1); + if (prev_state != ' ') + kdb_printf("(%c)", prev_state); + } + prev_state = state; + start_cpu = i; + } + } + /* print the trailing cpus, ignoring them if they are all offline */ + if (prev_state != 'F') { + if (!first_print) + kdb_printf(", "); + kdb_printf("%d", start_cpu); + if (start_cpu < i-1) + kdb_printf("-%d", i-1); + if (prev_state != ' ') + kdb_printf("(%c)", prev_state); + } + kdb_printf("\n"); +} + +static int kdb_cpu(int argc, const char **argv) +{ + unsigned long cpunum; + int diag; + + if (argc == 0) { + kdb_cpu_status(); + return 0; + } + + if (argc != 1) + return KDB_ARGCOUNT; + + diag = kdbgetularg(argv[1], &cpunum); + if (diag) + return diag; + + /* + * Validate cpunum + */ + if ((cpunum >= CONFIG_NR_CPUS) || !kgdb_info[cpunum].enter_kgdb) + return KDB_BADCPUNUM; + + dbg_switch_cpu = cpunum; + + /* + * Switch to other cpu + */ + return KDB_CMD_CPU; +} + +/* The user may not realize that ps/bta with no parameters does not print idle + * or sleeping system daemon processes, so tell them how many were suppressed. + */ +void kdb_ps_suppressed(void) +{ + int idle = 0, daemon = 0; + unsigned long mask_I = kdb_task_state_string("I"), + mask_M = kdb_task_state_string("M"); + unsigned long cpu; + const struct task_struct *p, *g; + for_each_online_cpu(cpu) { + p = kdb_curr_task(cpu); + if (kdb_task_state(p, mask_I)) + ++idle; + } + kdb_do_each_thread(g, p) { + if (kdb_task_state(p, mask_M)) + ++daemon; + } kdb_while_each_thread(g, p); + if (idle || daemon) { + if (idle) + kdb_printf("%d idle process%s (state I)%s\n", + idle, idle == 1 ? "" : "es", + daemon ? " and " : ""); + if (daemon) + kdb_printf("%d sleeping system daemon (state M) " + "process%s", daemon, + daemon == 1 ? "" : "es"); + kdb_printf(" suppressed,\nuse 'ps A' to see all.\n"); + } +} + +/* + * kdb_ps - This function implements the 'ps' command which shows a + * list of the active processes. + * ps [DRSTCZEUIMA] All processes, optionally filtered by state + */ +void kdb_ps1(const struct task_struct *p) +{ + int cpu; + unsigned long tmp; + + if (!p || probe_kernel_read(&tmp, (char *)p, sizeof(unsigned long))) + return; + + cpu = kdb_process_cpu(p); + kdb_printf("0x%p %8d %8d %d %4d %c 0x%p %c%s\n", + (void *)p, p->pid, p->parent->pid, + kdb_task_has_cpu(p), kdb_process_cpu(p), + kdb_task_state_char(p), + (void *)(&p->thread), + p == kdb_curr_task(raw_smp_processor_id()) ? '*' : ' ', + p->comm); + if (kdb_task_has_cpu(p)) { + if (!KDB_TSK(cpu)) { + kdb_printf(" Error: no saved data for this cpu\n"); + } else { + if (KDB_TSK(cpu) != p) + kdb_printf(" Error: does not match running " + "process table (0x%p)\n", KDB_TSK(cpu)); + } + } +} + +static int kdb_ps(int argc, const char **argv) +{ + struct task_struct *g, *p; + unsigned long mask, cpu; + + if (argc == 0) + kdb_ps_suppressed(); + kdb_printf("%-*s Pid Parent [*] cpu State %-*s Command\n", + (int)(2*sizeof(void *))+2, "Task Addr", + (int)(2*sizeof(void *))+2, "Thread"); + mask = kdb_task_state_string(argc ? argv[1] : NULL); + /* Run the active tasks first */ + for_each_online_cpu(cpu) { + if (KDB_FLAG(CMD_INTERRUPT)) + return 0; + p = kdb_curr_task(cpu); + if (kdb_task_state(p, mask)) + kdb_ps1(p); + } + kdb_printf("\n"); + /* Now the real tasks */ + kdb_do_each_thread(g, p) { + if (KDB_FLAG(CMD_INTERRUPT)) + return 0; + if (kdb_task_state(p, mask)) + kdb_ps1(p); + } kdb_while_each_thread(g, p); + + return 0; +} + +/* + * kdb_pid - This function implements the 'pid' command which switches + * the currently active process. + * pid [ | R] + */ +static int kdb_pid(int argc, const char **argv) +{ + struct task_struct *p; + unsigned long val; + int diag; + + if (argc > 1) + return KDB_ARGCOUNT; + + if (argc) { + if (strcmp(argv[1], "R") == 0) { + p = KDB_TSK(kdb_initial_cpu); + } else { + diag = kdbgetularg(argv[1], &val); + if (diag) + return KDB_BADINT; + + p = find_task_by_pid_ns((pid_t)val, &init_pid_ns); + if (!p) { + kdb_printf("No task with pid=%d\n", (pid_t)val); + return 0; + } + } + kdb_set_current_task(p); + } + kdb_printf("KDB current process is %s(pid=%d)\n", + kdb_current_task->comm, + kdb_current_task->pid); + + return 0; +} + +static int kdb_kgdb(int argc, const char **argv) +{ + return KDB_CMD_KGDB; +} + +/* + * kdb_help - This function implements the 'help' and '?' commands. + */ +static int kdb_help(int argc, const char **argv) +{ + kdbtab_t *kt; + int i; + + kdb_printf("%-15.15s %-20.20s %s\n", "Command", "Usage", "Description"); + kdb_printf("-----------------------------" + "-----------------------------\n"); + for_each_kdbcmd(kt, i) { + char *space = ""; + if (KDB_FLAG(CMD_INTERRUPT)) + return 0; + if (!kt->cmd_name) + continue; + if (!kdb_check_flags(kt->cmd_flags, kdb_cmd_enabled, true)) + continue; + if (strlen(kt->cmd_usage) > 20) + space = "\n "; + kdb_printf("%-15.15s %-20s%s%s\n", kt->cmd_name, + kt->cmd_usage, space, kt->cmd_help); + } + return 0; +} + +/* + * kdb_kill - This function implements the 'kill' commands. + */ +static int kdb_kill(int argc, const char **argv) +{ + long sig, pid; + char *endp; + struct task_struct *p; + struct siginfo info; + + if (argc != 2) + return KDB_ARGCOUNT; + + sig = simple_strtol(argv[1], &endp, 0); + if (*endp) + return KDB_BADINT; + if (sig >= 0) { + kdb_printf("Invalid signal parameter.<-signal>\n"); + return 0; + } + sig = -sig; + + pid = simple_strtol(argv[2], &endp, 0); + if (*endp) + return KDB_BADINT; + if (pid <= 0) { + kdb_printf("Process ID must be large than 0.\n"); + return 0; + } + + /* Find the process. */ + p = find_task_by_pid_ns(pid, &init_pid_ns); + if (!p) { + kdb_printf("The specified process isn't found.\n"); + return 0; + } + p = p->group_leader; + info.si_signo = sig; + info.si_errno = 0; + info.si_code = SI_USER; + info.si_pid = pid; /* same capabilities as process being signalled */ + info.si_uid = 0; /* kdb has root authority */ + kdb_send_sig_info(p, &info); + return 0; +} + +struct kdb_tm { + int tm_sec; /* seconds */ + int tm_min; /* minutes */ + int tm_hour; /* hours */ + int tm_mday; /* day of the month */ + int tm_mon; /* month */ + int tm_year; /* year */ +}; + +static void kdb_gmtime(struct timespec *tv, struct kdb_tm *tm) +{ + /* This will work from 1970-2099, 2100 is not a leap year */ + static int mon_day[] = { 31, 29, 31, 30, 31, 30, 31, + 31, 30, 31, 30, 31 }; + memset(tm, 0, sizeof(*tm)); + tm->tm_sec = tv->tv_sec % (24 * 60 * 60); + tm->tm_mday = tv->tv_sec / (24 * 60 * 60) + + (2 * 365 + 1); /* shift base from 1970 to 1968 */ + tm->tm_min = tm->tm_sec / 60 % 60; + tm->tm_hour = tm->tm_sec / 60 / 60; + tm->tm_sec = tm->tm_sec % 60; + tm->tm_year = 68 + 4*(tm->tm_mday / (4*365+1)); + tm->tm_mday %= (4*365+1); + mon_day[1] = 29; + while (tm->tm_mday >= mon_day[tm->tm_mon]) { + tm->tm_mday -= mon_day[tm->tm_mon]; + if (++tm->tm_mon == 12) { + tm->tm_mon = 0; + ++tm->tm_year; + mon_day[1] = 28; + } + } + ++tm->tm_mday; +} + +/* + * Most of this code has been lifted from kernel/timer.c::sys_sysinfo(). + * I cannot call that code directly from kdb, it has an unconditional + * cli()/sti() and calls routines that take locks which can stop the debugger. + */ +static void kdb_sysinfo(struct sysinfo *val) +{ + struct timespec uptime; + ktime_get_ts(&uptime); + memset(val, 0, sizeof(*val)); + val->uptime = uptime.tv_sec; + val->loads[0] = avenrun[0]; + val->loads[1] = avenrun[1]; + val->loads[2] = avenrun[2]; + val->procs = nr_threads-1; + si_meminfo(val); + + return; +} + +/* + * kdb_summary - This function implements the 'summary' command. + */ +static int kdb_summary(int argc, const char **argv) +{ + struct timespec now; + struct kdb_tm tm; + struct sysinfo val; + + if (argc) + return KDB_ARGCOUNT; + + kdb_printf("sysname %s\n", init_uts_ns.name.sysname); + kdb_printf("release %s\n", init_uts_ns.name.release); + kdb_printf("version %s\n", init_uts_ns.name.version); + kdb_printf("machine %s\n", init_uts_ns.name.machine); + kdb_printf("nodename %s\n", init_uts_ns.name.nodename); + kdb_printf("domainname %s\n", init_uts_ns.name.domainname); + kdb_printf("ccversion %s\n", __stringify(CCVERSION)); + + now = __current_kernel_time(); + kdb_gmtime(&now, &tm); + kdb_printf("date %04d-%02d-%02d %02d:%02d:%02d " + "tz_minuteswest %d\n", + 1900+tm.tm_year, tm.tm_mon+1, tm.tm_mday, + tm.tm_hour, tm.tm_min, tm.tm_sec, + sys_tz.tz_minuteswest); + + kdb_sysinfo(&val); + kdb_printf("uptime "); + if (val.uptime > (24*60*60)) { + int days = val.uptime / (24*60*60); + val.uptime %= (24*60*60); + kdb_printf("%d day%s ", days, days == 1 ? "" : "s"); + } + kdb_printf("%02ld:%02ld\n", val.uptime/(60*60), (val.uptime/60)%60); + + /* lifted from fs/proc/proc_misc.c::loadavg_read_proc() */ + +#define LOAD_INT(x) ((x) >> FSHIFT) +#define LOAD_FRAC(x) LOAD_INT(((x) & (FIXED_1-1)) * 100) + kdb_printf("load avg %ld.%02ld %ld.%02ld %ld.%02ld\n", + LOAD_INT(val.loads[0]), LOAD_FRAC(val.loads[0]), + LOAD_INT(val.loads[1]), LOAD_FRAC(val.loads[1]), + LOAD_INT(val.loads[2]), LOAD_FRAC(val.loads[2])); +#undef LOAD_INT +#undef LOAD_FRAC + /* Display in kilobytes */ +#define K(x) ((x) << (PAGE_SHIFT - 10)) + kdb_printf("\nMemTotal: %8lu kB\nMemFree: %8lu kB\n" + "Buffers: %8lu kB\n", + K(val.totalram), K(val.freeram), K(val.bufferram)); + return 0; +} + +/* + * kdb_per_cpu - This function implements the 'per_cpu' command. + */ +static int kdb_per_cpu(int argc, const char **argv) +{ + char fmtstr[64]; + int cpu, diag, nextarg = 1; + unsigned long addr, symaddr, val, bytesperword = 0, whichcpu = ~0UL; + + if (argc < 1 || argc > 3) + return KDB_ARGCOUNT; + + diag = kdbgetaddrarg(argc, argv, &nextarg, &symaddr, NULL, NULL); + if (diag) + return diag; + + if (argc >= 2) { + diag = kdbgetularg(argv[2], &bytesperword); + if (diag) + return diag; + } + if (!bytesperword) + bytesperword = KDB_WORD_SIZE; + else if (bytesperword > KDB_WORD_SIZE) + return KDB_BADWIDTH; + sprintf(fmtstr, "%%0%dlx ", (int)(2*bytesperword)); + if (argc >= 3) { + diag = kdbgetularg(argv[3], &whichcpu); + if (diag) + return diag; + if (!cpu_online(whichcpu)) { + kdb_printf("cpu %ld is not online\n", whichcpu); + return KDB_BADCPUNUM; + } + } + + /* Most architectures use __per_cpu_offset[cpu], some use + * __per_cpu_offset(cpu), smp has no __per_cpu_offset. + */ +#ifdef __per_cpu_offset +#define KDB_PCU(cpu) __per_cpu_offset(cpu) +#else +#ifdef CONFIG_SMP +#define KDB_PCU(cpu) __per_cpu_offset[cpu] +#else +#define KDB_PCU(cpu) 0 +#endif +#endif + for_each_online_cpu(cpu) { + if (KDB_FLAG(CMD_INTERRUPT)) + return 0; + + if (whichcpu != ~0UL && whichcpu != cpu) + continue; + addr = symaddr + KDB_PCU(cpu); + diag = kdb_getword(&val, addr, bytesperword); + if (diag) { + kdb_printf("%5d " kdb_bfd_vma_fmt0 " - unable to " + "read, diag=%d\n", cpu, addr, diag); + continue; + } + kdb_printf("%5d ", cpu); + kdb_md_line(fmtstr, addr, + bytesperword == KDB_WORD_SIZE, + 1, bytesperword, 1, 1, 0); + } +#undef KDB_PCU + return 0; +} + +/* + * display help for the use of cmd | grep pattern + */ +static int kdb_grep_help(int argc, const char **argv) +{ + kdb_printf("Usage of cmd args | grep pattern:\n"); + kdb_printf(" Any command's output may be filtered through an "); + kdb_printf("emulated 'pipe'.\n"); + kdb_printf(" 'grep' is just a key word.\n"); + kdb_printf(" The pattern may include a very limited set of " + "metacharacters:\n"); + kdb_printf(" pattern or ^pattern or pattern$ or ^pattern$\n"); + kdb_printf(" And if there are spaces in the pattern, you may " + "quote it:\n"); + kdb_printf(" \"pat tern\" or \"^pat tern\" or \"pat tern$\"" + " or \"^pat tern$\"\n"); + return 0; +} + +/* + * kdb_register_flags - This function is used to register a kernel + * debugger command. + * Inputs: + * cmd Command name + * func Function to execute the command + * usage A simple usage string showing arguments + * help A simple help string describing command + * repeat Does the command auto repeat on enter? + * Returns: + * zero for success, one if a duplicate command. + */ +#define kdb_command_extend 50 /* arbitrary */ +int kdb_register_flags(char *cmd, + kdb_func_t func, + char *usage, + char *help, + short minlen, + kdb_cmdflags_t flags) +{ + int i; + kdbtab_t *kp; + + /* + * Brute force method to determine duplicates + */ + for_each_kdbcmd(kp, i) { + if (kp->cmd_name && (strcmp(kp->cmd_name, cmd) == 0)) { + kdb_printf("Duplicate kdb command registered: " + "%s, func %p help %s\n", cmd, func, help); + return 1; + } + } + + /* + * Insert command into first available location in table + */ + for_each_kdbcmd(kp, i) { + if (kp->cmd_name == NULL) + break; + } + + if (i >= kdb_max_commands) { + kdbtab_t *new = kmalloc((kdb_max_commands - KDB_BASE_CMD_MAX + + kdb_command_extend) * sizeof(*new), GFP_KDB); + if (!new) { + kdb_printf("Could not allocate new kdb_command " + "table\n"); + return 1; + } + if (kdb_commands) { + memcpy(new, kdb_commands, + (kdb_max_commands - KDB_BASE_CMD_MAX) * sizeof(*new)); + kfree(kdb_commands); + } + memset(new + kdb_max_commands - KDB_BASE_CMD_MAX, 0, + kdb_command_extend * sizeof(*new)); + kdb_commands = new; + kp = kdb_commands + kdb_max_commands - KDB_BASE_CMD_MAX; + kdb_max_commands += kdb_command_extend; + } + + kp->cmd_name = cmd; + kp->cmd_func = func; + kp->cmd_usage = usage; + kp->cmd_help = help; + kp->cmd_minlen = minlen; + kp->cmd_flags = flags; + + return 0; +} +EXPORT_SYMBOL_GPL(kdb_register_flags); + + +/* + * kdb_register - Compatibility register function for commands that do + * not need to specify a repeat state. Equivalent to + * kdb_register_flags with flags set to 0. + * Inputs: + * cmd Command name + * func Function to execute the command + * usage A simple usage string showing arguments + * help A simple help string describing command + * Returns: + * zero for success, one if a duplicate command. + */ +int kdb_register(char *cmd, + kdb_func_t func, + char *usage, + char *help, + short minlen) +{ + return kdb_register_flags(cmd, func, usage, help, minlen, 0); +} +EXPORT_SYMBOL_GPL(kdb_register); + +/* + * kdb_unregister - This function is used to unregister a kernel + * debugger command. It is generally called when a module which + * implements kdb commands is unloaded. + * Inputs: + * cmd Command name + * Returns: + * zero for success, one command not registered. + */ +int kdb_unregister(char *cmd) +{ + int i; + kdbtab_t *kp; + + /* + * find the command. + */ + for_each_kdbcmd(kp, i) { + if (kp->cmd_name && (strcmp(kp->cmd_name, cmd) == 0)) { + kp->cmd_name = NULL; + return 0; + } + } + + /* Couldn't find it. */ + return 1; +} +EXPORT_SYMBOL_GPL(kdb_unregister); + +/* Initialize the kdb command table. */ +static void __init kdb_inittab(void) +{ + int i; + kdbtab_t *kp; + + for_each_kdbcmd(kp, i) + kp->cmd_name = NULL; + + kdb_register_flags("md", kdb_md, "", + "Display Memory Contents, also mdWcN, e.g. md8c1", 1, + KDB_ENABLE_MEM_READ | KDB_REPEAT_NO_ARGS); + kdb_register_flags("mdr", kdb_md, " ", + "Display Raw Memory", 0, + KDB_ENABLE_MEM_READ | KDB_REPEAT_NO_ARGS); + kdb_register_flags("mdp", kdb_md, " ", + "Display Physical Memory", 0, + KDB_ENABLE_MEM_READ | KDB_REPEAT_NO_ARGS); + kdb_register_flags("mds", kdb_md, "", + "Display Memory Symbolically", 0, + KDB_ENABLE_MEM_READ | KDB_REPEAT_NO_ARGS); + kdb_register_flags("mm", kdb_mm, " ", + "Modify Memory Contents", 0, + KDB_ENABLE_MEM_WRITE | KDB_REPEAT_NO_ARGS); + kdb_register_flags("go", kdb_go, "[]", + "Continue Execution", 1, + KDB_ENABLE_REG_WRITE | KDB_ENABLE_ALWAYS_SAFE_NO_ARGS); + kdb_register_flags("rd", kdb_rd, "", + "Display Registers", 0, + KDB_ENABLE_REG_READ); + kdb_register_flags("rm", kdb_rm, " ", + "Modify Registers", 0, + KDB_ENABLE_REG_WRITE); + kdb_register_flags("ef", kdb_ef, "", + "Display exception frame", 0, + KDB_ENABLE_MEM_READ); + kdb_register_flags("bt", kdb_bt, "[]", + "Stack traceback", 1, + KDB_ENABLE_MEM_READ | KDB_ENABLE_INSPECT_NO_ARGS); + kdb_register_flags("btp", kdb_bt, "", + "Display stack for process ", 0, + KDB_ENABLE_INSPECT); + kdb_register_flags("bta", kdb_bt, "[D|R|S|T|C|Z|E|U|I|M|A]", + "Backtrace all processes matching state flag", 0, + KDB_ENABLE_INSPECT); + kdb_register_flags("btc", kdb_bt, "", + "Backtrace current process on each cpu", 0, + KDB_ENABLE_INSPECT); + kdb_register_flags("btt", kdb_bt, "", + "Backtrace process given its struct task address", 0, + KDB_ENABLE_MEM_READ | KDB_ENABLE_INSPECT_NO_ARGS); + kdb_register_flags("env", kdb_env, "", + "Show environment variables", 0, + KDB_ENABLE_ALWAYS_SAFE); + kdb_register_flags("set", kdb_set, "", + "Set environment variables", 0, + KDB_ENABLE_ALWAYS_SAFE); + kdb_register_flags("help", kdb_help, "", + "Display Help Message", 1, + KDB_ENABLE_ALWAYS_SAFE); + kdb_register_flags("?", kdb_help, "", + "Display Help Message", 0, + KDB_ENABLE_ALWAYS_SAFE); + kdb_register_flags("cpu", kdb_cpu, "", + "Switch to new cpu", 0, + KDB_ENABLE_ALWAYS_SAFE_NO_ARGS); + kdb_register_flags("kgdb", kdb_kgdb, "", + "Enter kgdb mode", 0, 0); + kdb_register_flags("ps", kdb_ps, "[|A]", + "Display active task list", 0, + KDB_ENABLE_INSPECT); + kdb_register_flags("pid", kdb_pid, "", + "Switch to another task", 0, + KDB_ENABLE_INSPECT); + kdb_register_flags("reboot", kdb_reboot, "", + "Reboot the machine immediately", 0, + KDB_ENABLE_REBOOT); +#if defined(CONFIG_MODULES) + kdb_register_flags("lsmod", kdb_lsmod, "", + "List loaded kernel modules", 0, + KDB_ENABLE_INSPECT); +#endif +#if defined(CONFIG_MAGIC_SYSRQ) + kdb_register_flags("sr", kdb_sr, "", + "Magic SysRq key", 0, + KDB_ENABLE_ALWAYS_SAFE); +#endif +#if defined(CONFIG_PRINTK) + kdb_register_flags("dmesg", kdb_dmesg, "[lines]", + "Display syslog buffer", 0, + KDB_ENABLE_ALWAYS_SAFE); +#endif + if (arch_kgdb_ops.enable_nmi) { + kdb_register_flags("disable_nmi", kdb_disable_nmi, "", + "Disable NMI entry to KDB", 0, + KDB_ENABLE_ALWAYS_SAFE); + } + kdb_register_flags("defcmd", kdb_defcmd, "name \"usage\" \"help\"", + "Define a set of commands, down to endefcmd", 0, + KDB_ENABLE_ALWAYS_SAFE); + kdb_register_flags("kill", kdb_kill, "<-signal> ", + "Send a signal to a process", 0, + KDB_ENABLE_SIGNAL); + kdb_register_flags("summary", kdb_summary, "", + "Summarize the system", 4, + KDB_ENABLE_ALWAYS_SAFE); + kdb_register_flags("per_cpu", kdb_per_cpu, " [] []", + "Display per_cpu variables", 3, + KDB_ENABLE_MEM_READ); + kdb_register_flags("grephelp", kdb_grep_help, "", + "Display help on | grep", 0, + KDB_ENABLE_ALWAYS_SAFE); +} + +/* Execute any commands defined in kdb_cmds. */ +static void __init kdb_cmd_init(void) +{ + int i, diag; + for (i = 0; kdb_cmds[i]; ++i) { + diag = kdb_parse(kdb_cmds[i]); + if (diag) + kdb_printf("kdb command %s failed, kdb diag %d\n", + kdb_cmds[i], diag); + } + if (defcmd_in_progress) { + kdb_printf("Incomplete 'defcmd' set, forcing endefcmd\n"); + kdb_parse("endefcmd"); + } +} + +/* Initialize kdb_printf, breakpoint tables and kdb state */ +void __init kdb_init(int lvl) +{ + static int kdb_init_lvl = KDB_NOT_INITIALIZED; + int i; + + if (kdb_init_lvl == KDB_INIT_FULL || lvl <= kdb_init_lvl) + return; + for (i = kdb_init_lvl; i < lvl; i++) { + switch (i) { + case KDB_NOT_INITIALIZED: + kdb_inittab(); /* Initialize Command Table */ + kdb_initbptab(); /* Initialize Breakpoints */ + break; + case KDB_INIT_EARLY: + kdb_cmd_init(); /* Build kdb_cmds tables */ + break; + } + } + kdb_init_lvl = lvl; +} diff --git a/kernel/kernel/debug/kdb/kdb_private.h b/kernel/kernel/debug/kdb/kdb_private.h new file mode 100644 index 000000000..75014d7f4 --- /dev/null +++ b/kernel/kernel/debug/kdb/kdb_private.h @@ -0,0 +1,261 @@ +#ifndef _KDBPRIVATE_H +#define _KDBPRIVATE_H + +/* + * Kernel Debugger Architecture Independent Private Headers + * + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file "COPYING" in the main directory of this archive + * for more details. + * + * Copyright (c) 2000-2004 Silicon Graphics, Inc. All Rights Reserved. + * Copyright (c) 2009 Wind River Systems, Inc. All Rights Reserved. + */ + +#include +#include "../debug_core.h" + +/* Kernel Debugger Command codes. Must not overlap with error codes. */ +#define KDB_CMD_GO (-1001) +#define KDB_CMD_CPU (-1002) +#define KDB_CMD_SS (-1003) +#define KDB_CMD_KGDB (-1005) + +/* Internal debug flags */ +#define KDB_DEBUG_FLAG_BP 0x0002 /* Breakpoint subsystem debug */ +#define KDB_DEBUG_FLAG_BB_SUMM 0x0004 /* Basic block analysis, summary only */ +#define KDB_DEBUG_FLAG_AR 0x0008 /* Activation record, generic */ +#define KDB_DEBUG_FLAG_ARA 0x0010 /* Activation record, arch specific */ +#define KDB_DEBUG_FLAG_BB 0x0020 /* All basic block analysis */ +#define KDB_DEBUG_FLAG_STATE 0x0040 /* State flags */ +#define KDB_DEBUG_FLAG_MASK 0xffff /* All debug flags */ +#define KDB_DEBUG_FLAG_SHIFT 16 /* Shift factor for dbflags */ + +#define KDB_DEBUG(flag) (kdb_flags & \ + (KDB_DEBUG_FLAG_##flag << KDB_DEBUG_FLAG_SHIFT)) +#define KDB_DEBUG_STATE(text, value) if (KDB_DEBUG(STATE)) \ + kdb_print_state(text, value) + +#if BITS_PER_LONG == 32 + +#define KDB_PLATFORM_ENV "BYTESPERWORD=4" + +#define kdb_machreg_fmt "0x%lx" +#define kdb_machreg_fmt0 "0x%08lx" +#define kdb_bfd_vma_fmt "0x%lx" +#define kdb_bfd_vma_fmt0 "0x%08lx" +#define kdb_elfw_addr_fmt "0x%x" +#define kdb_elfw_addr_fmt0 "0x%08x" +#define kdb_f_count_fmt "%d" + +#elif BITS_PER_LONG == 64 + +#define KDB_PLATFORM_ENV "BYTESPERWORD=8" + +#define kdb_machreg_fmt "0x%lx" +#define kdb_machreg_fmt0 "0x%016lx" +#define kdb_bfd_vma_fmt "0x%lx" +#define kdb_bfd_vma_fmt0 "0x%016lx" +#define kdb_elfw_addr_fmt "0x%x" +#define kdb_elfw_addr_fmt0 "0x%016x" +#define kdb_f_count_fmt "%ld" + +#endif + +/* + * KDB_MAXBPT describes the total number of breakpoints + * supported by this architecure. + */ +#define KDB_MAXBPT 16 + +/* Symbol table format returned by kallsyms. */ +typedef struct __ksymtab { + unsigned long value; /* Address of symbol */ + const char *mod_name; /* Module containing symbol or + * "kernel" */ + unsigned long mod_start; + unsigned long mod_end; + const char *sec_name; /* Section containing symbol */ + unsigned long sec_start; + unsigned long sec_end; + const char *sym_name; /* Full symbol name, including + * any version */ + unsigned long sym_start; + unsigned long sym_end; + } kdb_symtab_t; +extern int kallsyms_symbol_next(char *prefix_name, int flag); +extern int kallsyms_symbol_complete(char *prefix_name, int max_len); + +/* Exported Symbols for kernel loadable modules to use. */ +extern int kdb_getarea_size(void *, unsigned long, size_t); +extern int kdb_putarea_size(unsigned long, void *, size_t); + +/* + * Like get_user and put_user, kdb_getarea and kdb_putarea take variable + * names, not pointers. The underlying *_size functions take pointers. + */ +#define kdb_getarea(x, addr) kdb_getarea_size(&(x), addr, sizeof((x))) +#define kdb_putarea(addr, x) kdb_putarea_size(addr, &(x), sizeof((x))) + +extern int kdb_getphysword(unsigned long *word, + unsigned long addr, size_t size); +extern int kdb_getword(unsigned long *, unsigned long, size_t); +extern int kdb_putword(unsigned long, unsigned long, size_t); + +extern int kdbgetularg(const char *, unsigned long *); +extern int kdbgetu64arg(const char *, u64 *); +extern char *kdbgetenv(const char *); +extern int kdbgetaddrarg(int, const char **, int*, unsigned long *, + long *, char **); +extern int kdbgetsymval(const char *, kdb_symtab_t *); +extern int kdbnearsym(unsigned long, kdb_symtab_t *); +extern void kdbnearsym_cleanup(void); +extern char *kdb_strdup(const char *str, gfp_t type); +extern void kdb_symbol_print(unsigned long, const kdb_symtab_t *, unsigned int); + +/* Routine for debugging the debugger state. */ +extern void kdb_print_state(const char *, int); + +extern int kdb_state; +#define KDB_STATE_KDB 0x00000001 /* Cpu is inside kdb */ +#define KDB_STATE_LEAVING 0x00000002 /* Cpu is leaving kdb */ +#define KDB_STATE_CMD 0x00000004 /* Running a kdb command */ +#define KDB_STATE_KDB_CONTROL 0x00000008 /* This cpu is under + * kdb control */ +#define KDB_STATE_HOLD_CPU 0x00000010 /* Hold this cpu inside kdb */ +#define KDB_STATE_DOING_SS 0x00000020 /* Doing ss command */ +#define KDB_STATE_SSBPT 0x00000080 /* Install breakpoint + * after one ss, independent of + * DOING_SS */ +#define KDB_STATE_REENTRY 0x00000100 /* Valid re-entry into kdb */ +#define KDB_STATE_SUPPRESS 0x00000200 /* Suppress error messages */ +#define KDB_STATE_PAGER 0x00000400 /* pager is available */ +#define KDB_STATE_GO_SWITCH 0x00000800 /* go is switching + * back to initial cpu */ +#define KDB_STATE_PRINTF_LOCK 0x00001000 /* Holds kdb_printf lock */ +#define KDB_STATE_WAIT_IPI 0x00002000 /* Waiting for kdb_ipi() NMI */ +#define KDB_STATE_RECURSE 0x00004000 /* Recursive entry to kdb */ +#define KDB_STATE_IP_ADJUSTED 0x00008000 /* Restart IP has been + * adjusted */ +#define KDB_STATE_GO1 0x00010000 /* go only releases one cpu */ +#define KDB_STATE_KEYBOARD 0x00020000 /* kdb entered via + * keyboard on this cpu */ +#define KDB_STATE_KEXEC 0x00040000 /* kexec issued */ +#define KDB_STATE_DOING_KGDB 0x00080000 /* kgdb enter now issued */ +#define KDB_STATE_KGDB_TRANS 0x00200000 /* Transition to kgdb */ +#define KDB_STATE_ARCH 0xff000000 /* Reserved for arch + * specific use */ + +#define KDB_STATE(flag) (kdb_state & KDB_STATE_##flag) +#define KDB_STATE_SET(flag) ((void)(kdb_state |= KDB_STATE_##flag)) +#define KDB_STATE_CLEAR(flag) ((void)(kdb_state &= ~KDB_STATE_##flag)) + +extern int kdb_nextline; /* Current number of lines displayed */ + +typedef struct _kdb_bp { + unsigned long bp_addr; /* Address breakpoint is present at */ + unsigned int bp_free:1; /* This entry is available */ + unsigned int bp_enabled:1; /* Breakpoint is active in register */ + unsigned int bp_type:4; /* Uses hardware register */ + unsigned int bp_installed:1; /* Breakpoint is installed */ + unsigned int bp_delay:1; /* Do delayed bp handling */ + unsigned int bp_delayed:1; /* Delayed breakpoint */ + unsigned int bph_length; /* HW break length */ +} kdb_bp_t; + +#ifdef CONFIG_KGDB_KDB +extern kdb_bp_t kdb_breakpoints[/* KDB_MAXBPT */]; + +/* The KDB shell command table */ +typedef struct _kdbtab { + char *cmd_name; /* Command name */ + kdb_func_t cmd_func; /* Function to execute command */ + char *cmd_usage; /* Usage String for this command */ + char *cmd_help; /* Help message for this command */ + short cmd_minlen; /* Minimum legal # command + * chars required */ + kdb_cmdflags_t cmd_flags; /* Command behaviour flags */ +} kdbtab_t; + +extern int kdb_bt(int, const char **); /* KDB display back trace */ + +/* KDB breakpoint management functions */ +extern void kdb_initbptab(void); +extern void kdb_bp_install(struct pt_regs *); +extern void kdb_bp_remove(void); + +typedef enum { + KDB_DB_BPT, /* Breakpoint */ + KDB_DB_SS, /* Single-step trap */ + KDB_DB_SSBPT, /* Single step over breakpoint */ + KDB_DB_NOBPT /* Spurious breakpoint */ +} kdb_dbtrap_t; + +extern int kdb_main_loop(kdb_reason_t, kdb_reason_t, + int, kdb_dbtrap_t, struct pt_regs *); + +/* Miscellaneous functions and data areas */ +extern int kdb_grepping_flag; +#define KDB_GREPPING_FLAG_SEARCH 0x8000 +extern char kdb_grep_string[]; +#define KDB_GREP_STRLEN 256 +extern int kdb_grep_leading; +extern int kdb_grep_trailing; +extern char *kdb_cmds[]; +extern unsigned long kdb_task_state_string(const char *); +extern char kdb_task_state_char (const struct task_struct *); +extern unsigned long kdb_task_state(const struct task_struct *p, + unsigned long mask); +extern void kdb_ps_suppressed(void); +extern void kdb_ps1(const struct task_struct *p); +extern void kdb_print_nameval(const char *name, unsigned long val); +extern void kdb_send_sig_info(struct task_struct *p, struct siginfo *info); +extern void kdb_meminfo_proc_show(void); +extern char *kdb_getstr(char *, size_t, const char *); +extern void kdb_gdb_state_pass(char *buf); + +/* Defines for kdb_symbol_print */ +#define KDB_SP_SPACEB 0x0001 /* Space before string */ +#define KDB_SP_SPACEA 0x0002 /* Space after string */ +#define KDB_SP_PAREN 0x0004 /* Parenthesis around string */ +#define KDB_SP_VALUE 0x0008 /* Print the value of the address */ +#define KDB_SP_SYMSIZE 0x0010 /* Print the size of the symbol */ +#define KDB_SP_NEWLINE 0x0020 /* Newline after string */ +#define KDB_SP_DEFAULT (KDB_SP_VALUE|KDB_SP_PAREN) + +#define KDB_TSK(cpu) kgdb_info[cpu].task +#define KDB_TSKREGS(cpu) kgdb_info[cpu].debuggerinfo + +extern struct task_struct *kdb_curr_task(int); + +#define kdb_task_has_cpu(p) (task_curr(p)) + +/* Simplify coexistence with NPTL */ +#define kdb_do_each_thread(g, p) do_each_thread(g, p) +#define kdb_while_each_thread(g, p) while_each_thread(g, p) + +#define GFP_KDB (in_interrupt() ? GFP_ATOMIC : GFP_KERNEL) + +extern void *debug_kmalloc(size_t size, gfp_t flags); +extern void debug_kfree(void *); +extern void debug_kusage(void); + +extern void kdb_set_current_task(struct task_struct *); +extern struct task_struct *kdb_current_task; + +#ifdef CONFIG_KDB_KEYBOARD +extern void kdb_kbd_cleanup_state(void); +#else /* ! CONFIG_KDB_KEYBOARD */ +#define kdb_kbd_cleanup_state() +#endif /* ! CONFIG_KDB_KEYBOARD */ + +#ifdef CONFIG_MODULES +extern struct list_head *kdb_modules; +#endif /* CONFIG_MODULES */ + +extern char kdb_prompt_str[]; + +#define KDB_WORD_SIZE ((int)sizeof(unsigned long)) + +#endif /* CONFIG_KGDB_KDB */ +#endif /* !_KDBPRIVATE_H */ diff --git a/kernel/kernel/debug/kdb/kdb_support.c b/kernel/kernel/debug/kdb/kdb_support.c new file mode 100644 index 000000000..d35cc2d3a --- /dev/null +++ b/kernel/kernel/debug/kdb/kdb_support.c @@ -0,0 +1,927 @@ +/* + * Kernel Debugger Architecture Independent Support Functions + * + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file "COPYING" in the main directory of this archive + * for more details. + * + * Copyright (c) 1999-2004 Silicon Graphics, Inc. All Rights Reserved. + * Copyright (c) 2009 Wind River Systems, Inc. All Rights Reserved. + * 03/02/13 added new 2.5 kallsyms + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include "kdb_private.h" + +/* + * kdbgetsymval - Return the address of the given symbol. + * + * Parameters: + * symname Character string containing symbol name + * symtab Structure to receive results + * Returns: + * 0 Symbol not found, symtab zero filled + * 1 Symbol mapped to module/symbol/section, data in symtab + */ +int kdbgetsymval(const char *symname, kdb_symtab_t *symtab) +{ + if (KDB_DEBUG(AR)) + kdb_printf("kdbgetsymval: symname=%s, symtab=%p\n", symname, + symtab); + memset(symtab, 0, sizeof(*symtab)); + symtab->sym_start = kallsyms_lookup_name(symname); + if (symtab->sym_start) { + if (KDB_DEBUG(AR)) + kdb_printf("kdbgetsymval: returns 1, " + "symtab->sym_start=0x%lx\n", + symtab->sym_start); + return 1; + } + if (KDB_DEBUG(AR)) + kdb_printf("kdbgetsymval: returns 0\n"); + return 0; +} +EXPORT_SYMBOL(kdbgetsymval); + +static char *kdb_name_table[100]; /* arbitrary size */ + +/* + * kdbnearsym - Return the name of the symbol with the nearest address + * less than 'addr'. + * + * Parameters: + * addr Address to check for symbol near + * symtab Structure to receive results + * Returns: + * 0 No sections contain this address, symtab zero filled + * 1 Address mapped to module/symbol/section, data in symtab + * Remarks: + * 2.6 kallsyms has a "feature" where it unpacks the name into a + * string. If that string is reused before the caller expects it + * then the caller sees its string change without warning. To + * avoid cluttering up the main kdb code with lots of kdb_strdup, + * tests and kfree calls, kdbnearsym maintains an LRU list of the + * last few unique strings. The list is sized large enough to + * hold active strings, no kdb caller of kdbnearsym makes more + * than ~20 later calls before using a saved value. + */ +int kdbnearsym(unsigned long addr, kdb_symtab_t *symtab) +{ + int ret = 0; + unsigned long symbolsize = 0; + unsigned long offset = 0; +#define knt1_size 128 /* must be >= kallsyms table size */ + char *knt1 = NULL; + + if (KDB_DEBUG(AR)) + kdb_printf("kdbnearsym: addr=0x%lx, symtab=%p\n", addr, symtab); + memset(symtab, 0, sizeof(*symtab)); + + if (addr < 4096) + goto out; + knt1 = debug_kmalloc(knt1_size, GFP_ATOMIC); + if (!knt1) { + kdb_printf("kdbnearsym: addr=0x%lx cannot kmalloc knt1\n", + addr); + goto out; + } + symtab->sym_name = kallsyms_lookup(addr, &symbolsize , &offset, + (char **)(&symtab->mod_name), knt1); + if (offset > 8*1024*1024) { + symtab->sym_name = NULL; + addr = offset = symbolsize = 0; + } + symtab->sym_start = addr - offset; + symtab->sym_end = symtab->sym_start + symbolsize; + ret = symtab->sym_name != NULL && *(symtab->sym_name) != '\0'; + + if (ret) { + int i; + /* Another 2.6 kallsyms "feature". Sometimes the sym_name is + * set but the buffer passed into kallsyms_lookup is not used, + * so it contains garbage. The caller has to work out which + * buffer needs to be saved. + * + * What was Rusty smoking when he wrote that code? + */ + if (symtab->sym_name != knt1) { + strncpy(knt1, symtab->sym_name, knt1_size); + knt1[knt1_size-1] = '\0'; + } + for (i = 0; i < ARRAY_SIZE(kdb_name_table); ++i) { + if (kdb_name_table[i] && + strcmp(kdb_name_table[i], knt1) == 0) + break; + } + if (i >= ARRAY_SIZE(kdb_name_table)) { + debug_kfree(kdb_name_table[0]); + memcpy(kdb_name_table, kdb_name_table+1, + sizeof(kdb_name_table[0]) * + (ARRAY_SIZE(kdb_name_table)-1)); + } else { + debug_kfree(knt1); + knt1 = kdb_name_table[i]; + memcpy(kdb_name_table+i, kdb_name_table+i+1, + sizeof(kdb_name_table[0]) * + (ARRAY_SIZE(kdb_name_table)-i-1)); + } + i = ARRAY_SIZE(kdb_name_table) - 1; + kdb_name_table[i] = knt1; + symtab->sym_name = kdb_name_table[i]; + knt1 = NULL; + } + + if (symtab->mod_name == NULL) + symtab->mod_name = "kernel"; + if (KDB_DEBUG(AR)) + kdb_printf("kdbnearsym: returns %d symtab->sym_start=0x%lx, " + "symtab->mod_name=%p, symtab->sym_name=%p (%s)\n", ret, + symtab->sym_start, symtab->mod_name, symtab->sym_name, + symtab->sym_name); + +out: + debug_kfree(knt1); + return ret; +} + +void kdbnearsym_cleanup(void) +{ + int i; + for (i = 0; i < ARRAY_SIZE(kdb_name_table); ++i) { + if (kdb_name_table[i]) { + debug_kfree(kdb_name_table[i]); + kdb_name_table[i] = NULL; + } + } +} + +static char ks_namebuf[KSYM_NAME_LEN+1], ks_namebuf_prev[KSYM_NAME_LEN+1]; + +/* + * kallsyms_symbol_complete + * + * Parameters: + * prefix_name prefix of a symbol name to lookup + * max_len maximum length that can be returned + * Returns: + * Number of symbols which match the given prefix. + * Notes: + * prefix_name is changed to contain the longest unique prefix that + * starts with this prefix (tab completion). + */ +int kallsyms_symbol_complete(char *prefix_name, int max_len) +{ + loff_t pos = 0; + int prefix_len = strlen(prefix_name), prev_len = 0; + int i, number = 0; + const char *name; + + while ((name = kdb_walk_kallsyms(&pos))) { + if (strncmp(name, prefix_name, prefix_len) == 0) { + strcpy(ks_namebuf, name); + /* Work out the longest name that matches the prefix */ + if (++number == 1) { + prev_len = min_t(int, max_len-1, + strlen(ks_namebuf)); + memcpy(ks_namebuf_prev, ks_namebuf, prev_len); + ks_namebuf_prev[prev_len] = '\0'; + continue; + } + for (i = 0; i < prev_len; i++) { + if (ks_namebuf[i] != ks_namebuf_prev[i]) { + prev_len = i; + ks_namebuf_prev[i] = '\0'; + break; + } + } + } + } + if (prev_len > prefix_len) + memcpy(prefix_name, ks_namebuf_prev, prev_len+1); + return number; +} + +/* + * kallsyms_symbol_next + * + * Parameters: + * prefix_name prefix of a symbol name to lookup + * flag 0 means search from the head, 1 means continue search. + * Returns: + * 1 if a symbol matches the given prefix. + * 0 if no string found + */ +int kallsyms_symbol_next(char *prefix_name, int flag) +{ + int prefix_len = strlen(prefix_name); + static loff_t pos; + const char *name; + + if (!flag) + pos = 0; + + while ((name = kdb_walk_kallsyms(&pos))) { + if (strncmp(name, prefix_name, prefix_len) == 0) { + strncpy(prefix_name, name, strlen(name)+1); + return 1; + } + } + return 0; +} + +/* + * kdb_symbol_print - Standard method for printing a symbol name and offset. + * Inputs: + * addr Address to be printed. + * symtab Address of symbol data, if NULL this routine does its + * own lookup. + * punc Punctuation for string, bit field. + * Remarks: + * The string and its punctuation is only printed if the address + * is inside the kernel, except that the value is always printed + * when requested. + */ +void kdb_symbol_print(unsigned long addr, const kdb_symtab_t *symtab_p, + unsigned int punc) +{ + kdb_symtab_t symtab, *symtab_p2; + if (symtab_p) { + symtab_p2 = (kdb_symtab_t *)symtab_p; + } else { + symtab_p2 = &symtab; + kdbnearsym(addr, symtab_p2); + } + if (!(symtab_p2->sym_name || (punc & KDB_SP_VALUE))) + return; + if (punc & KDB_SP_SPACEB) + kdb_printf(" "); + if (punc & KDB_SP_VALUE) + kdb_printf(kdb_machreg_fmt0, addr); + if (symtab_p2->sym_name) { + if (punc & KDB_SP_VALUE) + kdb_printf(" "); + if (punc & KDB_SP_PAREN) + kdb_printf("("); + if (strcmp(symtab_p2->mod_name, "kernel")) + kdb_printf("[%s]", symtab_p2->mod_name); + kdb_printf("%s", symtab_p2->sym_name); + if (addr != symtab_p2->sym_start) + kdb_printf("+0x%lx", addr - symtab_p2->sym_start); + if (punc & KDB_SP_SYMSIZE) + kdb_printf("/0x%lx", + symtab_p2->sym_end - symtab_p2->sym_start); + if (punc & KDB_SP_PAREN) + kdb_printf(")"); + } + if (punc & KDB_SP_SPACEA) + kdb_printf(" "); + if (punc & KDB_SP_NEWLINE) + kdb_printf("\n"); +} + +/* + * kdb_strdup - kdb equivalent of strdup, for disasm code. + * Inputs: + * str The string to duplicate. + * type Flags to kmalloc for the new string. + * Returns: + * Address of the new string, NULL if storage could not be allocated. + * Remarks: + * This is not in lib/string.c because it uses kmalloc which is not + * available when string.o is used in boot loaders. + */ +char *kdb_strdup(const char *str, gfp_t type) +{ + int n = strlen(str)+1; + char *s = kmalloc(n, type); + if (!s) + return NULL; + return strcpy(s, str); +} + +/* + * kdb_getarea_size - Read an area of data. The kdb equivalent of + * copy_from_user, with kdb messages for invalid addresses. + * Inputs: + * res Pointer to the area to receive the result. + * addr Address of the area to copy. + * size Size of the area. + * Returns: + * 0 for success, < 0 for error. + */ +int kdb_getarea_size(void *res, unsigned long addr, size_t size) +{ + int ret = probe_kernel_read((char *)res, (char *)addr, size); + if (ret) { + if (!KDB_STATE(SUPPRESS)) { + kdb_printf("kdb_getarea: Bad address 0x%lx\n", addr); + KDB_STATE_SET(SUPPRESS); + } + ret = KDB_BADADDR; + } else { + KDB_STATE_CLEAR(SUPPRESS); + } + return ret; +} + +/* + * kdb_putarea_size - Write an area of data. The kdb equivalent of + * copy_to_user, with kdb messages for invalid addresses. + * Inputs: + * addr Address of the area to write to. + * res Pointer to the area holding the data. + * size Size of the area. + * Returns: + * 0 for success, < 0 for error. + */ +int kdb_putarea_size(unsigned long addr, void *res, size_t size) +{ + int ret = probe_kernel_read((char *)addr, (char *)res, size); + if (ret) { + if (!KDB_STATE(SUPPRESS)) { + kdb_printf("kdb_putarea: Bad address 0x%lx\n", addr); + KDB_STATE_SET(SUPPRESS); + } + ret = KDB_BADADDR; + } else { + KDB_STATE_CLEAR(SUPPRESS); + } + return ret; +} + +/* + * kdb_getphys - Read data from a physical address. Validate the + * address is in range, use kmap_atomic() to get data + * similar to kdb_getarea() - but for phys addresses + * Inputs: + * res Pointer to the word to receive the result + * addr Physical address of the area to copy + * size Size of the area + * Returns: + * 0 for success, < 0 for error. + */ +static int kdb_getphys(void *res, unsigned long addr, size_t size) +{ + unsigned long pfn; + void *vaddr; + struct page *page; + + pfn = (addr >> PAGE_SHIFT); + if (!pfn_valid(pfn)) + return 1; + page = pfn_to_page(pfn); + vaddr = kmap_atomic(page); + memcpy(res, vaddr + (addr & (PAGE_SIZE - 1)), size); + kunmap_atomic(vaddr); + + return 0; +} + +/* + * kdb_getphysword + * Inputs: + * word Pointer to the word to receive the result. + * addr Address of the area to copy. + * size Size of the area. + * Returns: + * 0 for success, < 0 for error. + */ +int kdb_getphysword(unsigned long *word, unsigned long addr, size_t size) +{ + int diag; + __u8 w1; + __u16 w2; + __u32 w4; + __u64 w8; + *word = 0; /* Default value if addr or size is invalid */ + + switch (size) { + case 1: + diag = kdb_getphys(&w1, addr, sizeof(w1)); + if (!diag) + *word = w1; + break; + case 2: + diag = kdb_getphys(&w2, addr, sizeof(w2)); + if (!diag) + *word = w2; + break; + case 4: + diag = kdb_getphys(&w4, addr, sizeof(w4)); + if (!diag) + *word = w4; + break; + case 8: + if (size <= sizeof(*word)) { + diag = kdb_getphys(&w8, addr, sizeof(w8)); + if (!diag) + *word = w8; + break; + } + /* drop through */ + default: + diag = KDB_BADWIDTH; + kdb_printf("kdb_getphysword: bad width %ld\n", (long) size); + } + return diag; +} + +/* + * kdb_getword - Read a binary value. Unlike kdb_getarea, this treats + * data as numbers. + * Inputs: + * word Pointer to the word to receive the result. + * addr Address of the area to copy. + * size Size of the area. + * Returns: + * 0 for success, < 0 for error. + */ +int kdb_getword(unsigned long *word, unsigned long addr, size_t size) +{ + int diag; + __u8 w1; + __u16 w2; + __u32 w4; + __u64 w8; + *word = 0; /* Default value if addr or size is invalid */ + switch (size) { + case 1: + diag = kdb_getarea(w1, addr); + if (!diag) + *word = w1; + break; + case 2: + diag = kdb_getarea(w2, addr); + if (!diag) + *word = w2; + break; + case 4: + diag = kdb_getarea(w4, addr); + if (!diag) + *word = w4; + break; + case 8: + if (size <= sizeof(*word)) { + diag = kdb_getarea(w8, addr); + if (!diag) + *word = w8; + break; + } + /* drop through */ + default: + diag = KDB_BADWIDTH; + kdb_printf("kdb_getword: bad width %ld\n", (long) size); + } + return diag; +} + +/* + * kdb_putword - Write a binary value. Unlike kdb_putarea, this + * treats data as numbers. + * Inputs: + * addr Address of the area to write to.. + * word The value to set. + * size Size of the area. + * Returns: + * 0 for success, < 0 for error. + */ +int kdb_putword(unsigned long addr, unsigned long word, size_t size) +{ + int diag; + __u8 w1; + __u16 w2; + __u32 w4; + __u64 w8; + switch (size) { + case 1: + w1 = word; + diag = kdb_putarea(addr, w1); + break; + case 2: + w2 = word; + diag = kdb_putarea(addr, w2); + break; + case 4: + w4 = word; + diag = kdb_putarea(addr, w4); + break; + case 8: + if (size <= sizeof(word)) { + w8 = word; + diag = kdb_putarea(addr, w8); + break; + } + /* drop through */ + default: + diag = KDB_BADWIDTH; + kdb_printf("kdb_putword: bad width %ld\n", (long) size); + } + return diag; +} + +/* + * kdb_task_state_string - Convert a string containing any of the + * letters DRSTCZEUIMA to a mask for the process state field and + * return the value. If no argument is supplied, return the mask + * that corresponds to environment variable PS, DRSTCZEU by + * default. + * Inputs: + * s String to convert + * Returns: + * Mask for process state. + * Notes: + * The mask folds data from several sources into a single long value, so + * be careful not to overlap the bits. TASK_* bits are in the LSB, + * special cases like UNRUNNABLE are in the MSB. As of 2.6.10-rc1 there + * is no overlap between TASK_* and EXIT_* but that may not always be + * true, so EXIT_* bits are shifted left 16 bits before being stored in + * the mask. + */ + +/* unrunnable is < 0 */ +#define UNRUNNABLE (1UL << (8*sizeof(unsigned long) - 1)) +#define RUNNING (1UL << (8*sizeof(unsigned long) - 2)) +#define IDLE (1UL << (8*sizeof(unsigned long) - 3)) +#define DAEMON (1UL << (8*sizeof(unsigned long) - 4)) + +unsigned long kdb_task_state_string(const char *s) +{ + long res = 0; + if (!s) { + s = kdbgetenv("PS"); + if (!s) + s = "DRSTCZEU"; /* default value for ps */ + } + while (*s) { + switch (*s) { + case 'D': + res |= TASK_UNINTERRUPTIBLE; + break; + case 'R': + res |= RUNNING; + break; + case 'S': + res |= TASK_INTERRUPTIBLE; + break; + case 'T': + res |= TASK_STOPPED; + break; + case 'C': + res |= TASK_TRACED; + break; + case 'Z': + res |= EXIT_ZOMBIE << 16; + break; + case 'E': + res |= EXIT_DEAD << 16; + break; + case 'U': + res |= UNRUNNABLE; + break; + case 'I': + res |= IDLE; + break; + case 'M': + res |= DAEMON; + break; + case 'A': + res = ~0UL; + break; + default: + kdb_printf("%s: unknown flag '%c' ignored\n", + __func__, *s); + break; + } + ++s; + } + return res; +} + +/* + * kdb_task_state_char - Return the character that represents the task state. + * Inputs: + * p struct task for the process + * Returns: + * One character to represent the task state. + */ +char kdb_task_state_char (const struct task_struct *p) +{ + int cpu; + char state; + unsigned long tmp; + + if (!p || probe_kernel_read(&tmp, (char *)p, sizeof(unsigned long))) + return 'E'; + + cpu = kdb_process_cpu(p); + state = (p->state == 0) ? 'R' : + (p->state < 0) ? 'U' : + (p->state & TASK_UNINTERRUPTIBLE) ? 'D' : + (p->state & TASK_STOPPED) ? 'T' : + (p->state & TASK_TRACED) ? 'C' : + (p->exit_state & EXIT_ZOMBIE) ? 'Z' : + (p->exit_state & EXIT_DEAD) ? 'E' : + (p->state & TASK_INTERRUPTIBLE) ? 'S' : '?'; + if (is_idle_task(p)) { + /* Idle task. Is it really idle, apart from the kdb + * interrupt? */ + if (!kdb_task_has_cpu(p) || kgdb_info[cpu].irq_depth == 1) { + if (cpu != kdb_initial_cpu) + state = 'I'; /* idle task */ + } + } else if (!p->mm && state == 'S') { + state = 'M'; /* sleeping system daemon */ + } + return state; +} + +/* + * kdb_task_state - Return true if a process has the desired state + * given by the mask. + * Inputs: + * p struct task for the process + * mask mask from kdb_task_state_string to select processes + * Returns: + * True if the process matches at least one criteria defined by the mask. + */ +unsigned long kdb_task_state(const struct task_struct *p, unsigned long mask) +{ + char state[] = { kdb_task_state_char(p), '\0' }; + return (mask & kdb_task_state_string(state)) != 0; +} + +/* + * kdb_print_nameval - Print a name and its value, converting the + * value to a symbol lookup if possible. + * Inputs: + * name field name to print + * val value of field + */ +void kdb_print_nameval(const char *name, unsigned long val) +{ + kdb_symtab_t symtab; + kdb_printf(" %-11.11s ", name); + if (kdbnearsym(val, &symtab)) + kdb_symbol_print(val, &symtab, + KDB_SP_VALUE|KDB_SP_SYMSIZE|KDB_SP_NEWLINE); + else + kdb_printf("0x%lx\n", val); +} + +/* Last ditch allocator for debugging, so we can still debug even when + * the GFP_ATOMIC pool has been exhausted. The algorithms are tuned + * for space usage, not for speed. One smallish memory pool, the free + * chain is always in ascending address order to allow coalescing, + * allocations are done in brute force best fit. + */ + +struct debug_alloc_header { + u32 next; /* offset of next header from start of pool */ + u32 size; + void *caller; +}; + +/* The memory returned by this allocator must be aligned, which means + * so must the header size. Do not assume that sizeof(struct + * debug_alloc_header) is a multiple of the alignment, explicitly + * calculate the overhead of this header, including the alignment. + * The rest of this code must not use sizeof() on any header or + * pointer to a header. + */ +#define dah_align 8 +#define dah_overhead ALIGN(sizeof(struct debug_alloc_header), dah_align) + +static u64 debug_alloc_pool_aligned[256*1024/dah_align]; /* 256K pool */ +static char *debug_alloc_pool = (char *)debug_alloc_pool_aligned; +static u32 dah_first, dah_first_call = 1, dah_used, dah_used_max; + +/* Locking is awkward. The debug code is called from all contexts, + * including non maskable interrupts. A normal spinlock is not safe + * in NMI context. Try to get the debug allocator lock, if it cannot + * be obtained after a second then give up. If the lock could not be + * previously obtained on this cpu then only try once. + * + * sparse has no annotation for "this function _sometimes_ acquires a + * lock", so fudge the acquire/release notation. + */ +static DEFINE_SPINLOCK(dap_lock); +static int get_dap_lock(void) + __acquires(dap_lock) +{ + static int dap_locked = -1; + int count; + if (dap_locked == smp_processor_id()) + count = 1; + else + count = 1000; + while (1) { + if (spin_trylock(&dap_lock)) { + dap_locked = -1; + return 1; + } + if (!count--) + break; + udelay(1000); + } + dap_locked = smp_processor_id(); + __acquire(dap_lock); + return 0; +} + +void *debug_kmalloc(size_t size, gfp_t flags) +{ + unsigned int rem, h_offset; + struct debug_alloc_header *best, *bestprev, *prev, *h; + void *p = NULL; + if (!get_dap_lock()) { + __release(dap_lock); /* we never actually got it */ + return NULL; + } + h = (struct debug_alloc_header *)(debug_alloc_pool + dah_first); + if (dah_first_call) { + h->size = sizeof(debug_alloc_pool_aligned) - dah_overhead; + dah_first_call = 0; + } + size = ALIGN(size, dah_align); + prev = best = bestprev = NULL; + while (1) { + if (h->size >= size && (!best || h->size < best->size)) { + best = h; + bestprev = prev; + if (h->size == size) + break; + } + if (!h->next) + break; + prev = h; + h = (struct debug_alloc_header *)(debug_alloc_pool + h->next); + } + if (!best) + goto out; + rem = best->size - size; + /* The pool must always contain at least one header */ + if (best->next == 0 && bestprev == NULL && rem < dah_overhead) + goto out; + if (rem >= dah_overhead) { + best->size = size; + h_offset = ((char *)best - debug_alloc_pool) + + dah_overhead + best->size; + h = (struct debug_alloc_header *)(debug_alloc_pool + h_offset); + h->size = rem - dah_overhead; + h->next = best->next; + } else + h_offset = best->next; + best->caller = __builtin_return_address(0); + dah_used += best->size; + dah_used_max = max(dah_used, dah_used_max); + if (bestprev) + bestprev->next = h_offset; + else + dah_first = h_offset; + p = (char *)best + dah_overhead; + memset(p, POISON_INUSE, best->size - 1); + *((char *)p + best->size - 1) = POISON_END; +out: + spin_unlock(&dap_lock); + return p; +} + +void debug_kfree(void *p) +{ + struct debug_alloc_header *h; + unsigned int h_offset; + if (!p) + return; + if ((char *)p < debug_alloc_pool || + (char *)p >= debug_alloc_pool + sizeof(debug_alloc_pool_aligned)) { + kfree(p); + return; + } + if (!get_dap_lock()) { + __release(dap_lock); /* we never actually got it */ + return; /* memory leak, cannot be helped */ + } + h = (struct debug_alloc_header *)((char *)p - dah_overhead); + memset(p, POISON_FREE, h->size - 1); + *((char *)p + h->size - 1) = POISON_END; + h->caller = NULL; + dah_used -= h->size; + h_offset = (char *)h - debug_alloc_pool; + if (h_offset < dah_first) { + h->next = dah_first; + dah_first = h_offset; + } else { + struct debug_alloc_header *prev; + unsigned int prev_offset; + prev = (struct debug_alloc_header *)(debug_alloc_pool + + dah_first); + while (1) { + if (!prev->next || prev->next > h_offset) + break; + prev = (struct debug_alloc_header *) + (debug_alloc_pool + prev->next); + } + prev_offset = (char *)prev - debug_alloc_pool; + if (prev_offset + dah_overhead + prev->size == h_offset) { + prev->size += dah_overhead + h->size; + memset(h, POISON_FREE, dah_overhead - 1); + *((char *)h + dah_overhead - 1) = POISON_END; + h = prev; + h_offset = prev_offset; + } else { + h->next = prev->next; + prev->next = h_offset; + } + } + if (h_offset + dah_overhead + h->size == h->next) { + struct debug_alloc_header *next; + next = (struct debug_alloc_header *) + (debug_alloc_pool + h->next); + h->size += dah_overhead + next->size; + h->next = next->next; + memset(next, POISON_FREE, dah_overhead - 1); + *((char *)next + dah_overhead - 1) = POISON_END; + } + spin_unlock(&dap_lock); +} + +void debug_kusage(void) +{ + struct debug_alloc_header *h_free, *h_used; +#ifdef CONFIG_IA64 + /* FIXME: using dah for ia64 unwind always results in a memory leak. + * Fix that memory leak first, then set debug_kusage_one_time = 1 for + * all architectures. + */ + static int debug_kusage_one_time; +#else + static int debug_kusage_one_time = 1; +#endif + if (!get_dap_lock()) { + __release(dap_lock); /* we never actually got it */ + return; + } + h_free = (struct debug_alloc_header *)(debug_alloc_pool + dah_first); + if (dah_first == 0 && + (h_free->size == sizeof(debug_alloc_pool_aligned) - dah_overhead || + dah_first_call)) + goto out; + if (!debug_kusage_one_time) + goto out; + debug_kusage_one_time = 0; + kdb_printf("%s: debug_kmalloc memory leak dah_first %d\n", + __func__, dah_first); + if (dah_first) { + h_used = (struct debug_alloc_header *)debug_alloc_pool; + kdb_printf("%s: h_used %p size %d\n", __func__, h_used, + h_used->size); + } + do { + h_used = (struct debug_alloc_header *) + ((char *)h_free + dah_overhead + h_free->size); + kdb_printf("%s: h_used %p size %d caller %p\n", + __func__, h_used, h_used->size, h_used->caller); + h_free = (struct debug_alloc_header *) + (debug_alloc_pool + h_free->next); + } while (h_free->next); + h_used = (struct debug_alloc_header *) + ((char *)h_free + dah_overhead + h_free->size); + if ((char *)h_used - debug_alloc_pool != + sizeof(debug_alloc_pool_aligned)) + kdb_printf("%s: h_used %p size %d caller %p\n", + __func__, h_used, h_used->size, h_used->caller); +out: + spin_unlock(&dap_lock); +} + +/* Maintain a small stack of kdb_flags to allow recursion without disturbing + * the global kdb state. + */ + +static int kdb_flags_stack[4], kdb_flags_index; + +void kdb_save_flags(void) +{ + BUG_ON(kdb_flags_index >= ARRAY_SIZE(kdb_flags_stack)); + kdb_flags_stack[kdb_flags_index++] = kdb_flags; +} + +void kdb_restore_flags(void) +{ + BUG_ON(kdb_flags_index <= 0); + kdb_flags = kdb_flags_stack[--kdb_flags_index]; +} diff --git a/kernel/kernel/delayacct.c b/kernel/kernel/delayacct.c new file mode 100644 index 000000000..ef90b04d7 --- /dev/null +++ b/kernel/kernel/delayacct.c @@ -0,0 +1,158 @@ +/* delayacct.c - per-task delay accounting + * + * Copyright (C) Shailabh Nagar, IBM Corp. 2006 + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it would be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See + * the GNU General Public License for more details. + */ + +#include +#include +#include +#include +#include +#include +#include + +int delayacct_on __read_mostly = 1; /* Delay accounting turned on/off */ +EXPORT_SYMBOL_GPL(delayacct_on); +struct kmem_cache *delayacct_cache; + +static int __init delayacct_setup_disable(char *str) +{ + delayacct_on = 0; + return 1; +} +__setup("nodelayacct", delayacct_setup_disable); + +void delayacct_init(void) +{ + delayacct_cache = KMEM_CACHE(task_delay_info, SLAB_PANIC); + delayacct_tsk_init(&init_task); +} + +void __delayacct_tsk_init(struct task_struct *tsk) +{ + tsk->delays = kmem_cache_zalloc(delayacct_cache, GFP_KERNEL); + if (tsk->delays) + spin_lock_init(&tsk->delays->lock); +} + +/* + * Finish delay accounting for a statistic using its timestamps (@start), + * accumalator (@total) and @count + */ +static void delayacct_end(u64 *start, u64 *total, u32 *count) +{ + s64 ns = ktime_get_ns() - *start; + unsigned long flags; + + if (ns > 0) { + spin_lock_irqsave(¤t->delays->lock, flags); + *total += ns; + (*count)++; + spin_unlock_irqrestore(¤t->delays->lock, flags); + } +} + +void __delayacct_blkio_start(void) +{ + current->delays->blkio_start = ktime_get_ns(); +} + +void __delayacct_blkio_end(void) +{ + if (current->delays->flags & DELAYACCT_PF_SWAPIN) + /* Swapin block I/O */ + delayacct_end(¤t->delays->blkio_start, + ¤t->delays->swapin_delay, + ¤t->delays->swapin_count); + else /* Other block I/O */ + delayacct_end(¤t->delays->blkio_start, + ¤t->delays->blkio_delay, + ¤t->delays->blkio_count); +} + +int __delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk) +{ + cputime_t utime, stime, stimescaled, utimescaled; + unsigned long long t2, t3; + unsigned long flags, t1; + s64 tmp; + + task_cputime(tsk, &utime, &stime); + tmp = (s64)d->cpu_run_real_total; + tmp += cputime_to_nsecs(utime + stime); + d->cpu_run_real_total = (tmp < (s64)d->cpu_run_real_total) ? 0 : tmp; + + task_cputime_scaled(tsk, &utimescaled, &stimescaled); + tmp = (s64)d->cpu_scaled_run_real_total; + tmp += cputime_to_nsecs(utimescaled + stimescaled); + d->cpu_scaled_run_real_total = + (tmp < (s64)d->cpu_scaled_run_real_total) ? 0 : tmp; + + /* + * No locking available for sched_info (and too expensive to add one) + * Mitigate by taking snapshot of values + */ + t1 = tsk->sched_info.pcount; + t2 = tsk->sched_info.run_delay; + t3 = tsk->se.sum_exec_runtime; + + d->cpu_count += t1; + + tmp = (s64)d->cpu_delay_total + t2; + d->cpu_delay_total = (tmp < (s64)d->cpu_delay_total) ? 0 : tmp; + + tmp = (s64)d->cpu_run_virtual_total + t3; + d->cpu_run_virtual_total = + (tmp < (s64)d->cpu_run_virtual_total) ? 0 : tmp; + + /* zero XXX_total, non-zero XXX_count implies XXX stat overflowed */ + + spin_lock_irqsave(&tsk->delays->lock, flags); + tmp = d->blkio_delay_total + tsk->delays->blkio_delay; + d->blkio_delay_total = (tmp < d->blkio_delay_total) ? 0 : tmp; + tmp = d->swapin_delay_total + tsk->delays->swapin_delay; + d->swapin_delay_total = (tmp < d->swapin_delay_total) ? 0 : tmp; + tmp = d->freepages_delay_total + tsk->delays->freepages_delay; + d->freepages_delay_total = (tmp < d->freepages_delay_total) ? 0 : tmp; + d->blkio_count += tsk->delays->blkio_count; + d->swapin_count += tsk->delays->swapin_count; + d->freepages_count += tsk->delays->freepages_count; + spin_unlock_irqrestore(&tsk->delays->lock, flags); + + return 0; +} + +__u64 __delayacct_blkio_ticks(struct task_struct *tsk) +{ + __u64 ret; + unsigned long flags; + + spin_lock_irqsave(&tsk->delays->lock, flags); + ret = nsec_to_clock_t(tsk->delays->blkio_delay + + tsk->delays->swapin_delay); + spin_unlock_irqrestore(&tsk->delays->lock, flags); + return ret; +} + +void __delayacct_freepages_start(void) +{ + current->delays->freepages_start = ktime_get_ns(); +} + +void __delayacct_freepages_end(void) +{ + delayacct_end(¤t->delays->freepages_start, + ¤t->delays->freepages_delay, + ¤t->delays->freepages_count); +} + diff --git a/kernel/kernel/dma.c b/kernel/kernel/dma.c new file mode 100644 index 000000000..6c6262f86 --- /dev/null +++ b/kernel/kernel/dma.c @@ -0,0 +1,160 @@ +/* + * linux/kernel/dma.c: A DMA channel allocator. Inspired by linux/kernel/irq.c. + * + * Written by Hennus Bergman, 1992. + * + * 1994/12/26: Changes by Alex Nash to fix a minor bug in /proc/dma. + * In the previous version the reported device could end up being wrong, + * if a device requested a DMA channel that was already in use. + * [It also happened to remove the sizeof(char *) == sizeof(int) + * assumption introduced because of those /proc/dma patches. -- Hennus] + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include + + + +/* A note on resource allocation: + * + * All drivers needing DMA channels, should allocate and release them + * through the public routines `request_dma()' and `free_dma()'. + * + * In order to avoid problems, all processes should allocate resources in + * the same sequence and release them in the reverse order. + * + * So, when allocating DMAs and IRQs, first allocate the IRQ, then the DMA. + * When releasing them, first release the DMA, then release the IRQ. + * If you don't, you may cause allocation requests to fail unnecessarily. + * This doesn't really matter now, but it will once we get real semaphores + * in the kernel. + */ + + +DEFINE_SPINLOCK(dma_spin_lock); + +/* + * If our port doesn't define this it has no PC like DMA + */ + +#ifdef MAX_DMA_CHANNELS + + +/* Channel n is busy iff dma_chan_busy[n].lock != 0. + * DMA0 used to be reserved for DRAM refresh, but apparently not any more... + * DMA4 is reserved for cascading. + */ + +struct dma_chan { + int lock; + const char *device_id; +}; + +static struct dma_chan dma_chan_busy[MAX_DMA_CHANNELS] = { + [4] = { 1, "cascade" }, +}; + + +/** + * request_dma - request and reserve a system DMA channel + * @dmanr: DMA channel number + * @device_id: reserving device ID string, used in /proc/dma + */ +int request_dma(unsigned int dmanr, const char * device_id) +{ + if (dmanr >= MAX_DMA_CHANNELS) + return -EINVAL; + + if (xchg(&dma_chan_busy[dmanr].lock, 1) != 0) + return -EBUSY; + + dma_chan_busy[dmanr].device_id = device_id; + + /* old flag was 0, now contains 1 to indicate busy */ + return 0; +} /* request_dma */ + +/** + * free_dma - free a reserved system DMA channel + * @dmanr: DMA channel number + */ +void free_dma(unsigned int dmanr) +{ + if (dmanr >= MAX_DMA_CHANNELS) { + printk(KERN_WARNING "Trying to free DMA%d\n", dmanr); + return; + } + + if (xchg(&dma_chan_busy[dmanr].lock, 0) == 0) { + printk(KERN_WARNING "Trying to free free DMA%d\n", dmanr); + return; + } + +} /* free_dma */ + +#else + +int request_dma(unsigned int dmanr, const char *device_id) +{ + return -EINVAL; +} + +void free_dma(unsigned int dmanr) +{ +} + +#endif + +#ifdef CONFIG_PROC_FS + +#ifdef MAX_DMA_CHANNELS +static int proc_dma_show(struct seq_file *m, void *v) +{ + int i; + + for (i = 0 ; i < MAX_DMA_CHANNELS ; i++) { + if (dma_chan_busy[i].lock) { + seq_printf(m, "%2d: %s\n", i, + dma_chan_busy[i].device_id); + } + } + return 0; +} +#else +static int proc_dma_show(struct seq_file *m, void *v) +{ + seq_puts(m, "No DMA\n"); + return 0; +} +#endif /* MAX_DMA_CHANNELS */ + +static int proc_dma_open(struct inode *inode, struct file *file) +{ + return single_open(file, proc_dma_show, NULL); +} + +static const struct file_operations proc_dma_operations = { + .open = proc_dma_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static int __init proc_dma_init(void) +{ + proc_create("dma", 0, NULL, &proc_dma_operations); + return 0; +} + +__initcall(proc_dma_init); +#endif + +EXPORT_SYMBOL(request_dma); +EXPORT_SYMBOL(free_dma); +EXPORT_SYMBOL(dma_spin_lock); diff --git a/kernel/kernel/elfcore.c b/kernel/kernel/elfcore.c new file mode 100644 index 000000000..e556751d1 --- /dev/null +++ b/kernel/kernel/elfcore.c @@ -0,0 +1,24 @@ +#include +#include +#include +#include + +Elf_Half __weak elf_core_extra_phdrs(void) +{ + return 0; +} + +int __weak elf_core_write_extra_phdrs(struct coredump_params *cprm, loff_t offset) +{ + return 1; +} + +int __weak elf_core_write_extra_data(struct coredump_params *cprm) +{ + return 1; +} + +size_t __weak elf_core_extra_data_size(void) +{ + return 0; +} diff --git a/kernel/kernel/events/Makefile b/kernel/kernel/events/Makefile new file mode 100644 index 000000000..2925188f5 --- /dev/null +++ b/kernel/kernel/events/Makefile @@ -0,0 +1,9 @@ +ifdef CONFIG_FUNCTION_TRACER +CFLAGS_REMOVE_core.o = $(CC_FLAGS_FTRACE) +endif + +obj-y := core.o ring_buffer.o callchain.o + +obj-$(CONFIG_HAVE_HW_BREAKPOINT) += hw_breakpoint.o +obj-$(CONFIG_UPROBES) += uprobes.o + diff --git a/kernel/kernel/events/callchain.c b/kernel/kernel/events/callchain.c new file mode 100644 index 000000000..d65948725 --- /dev/null +++ b/kernel/kernel/events/callchain.c @@ -0,0 +1,209 @@ +/* + * Performance events callchain code, extracted from core.c: + * + * Copyright (C) 2008 Thomas Gleixner + * Copyright (C) 2008-2011 Red Hat, Inc., Ingo Molnar + * Copyright (C) 2008-2011 Red Hat, Inc., Peter Zijlstra + * Copyright © 2009 Paul Mackerras, IBM Corp. + * + * For licensing details see kernel-base/COPYING + */ + +#include +#include +#include "internal.h" + +struct callchain_cpus_entries { + struct rcu_head rcu_head; + struct perf_callchain_entry *cpu_entries[0]; +}; + +static DEFINE_PER_CPU(int, callchain_recursion[PERF_NR_CONTEXTS]); +static atomic_t nr_callchain_events; +static DEFINE_MUTEX(callchain_mutex); +static struct callchain_cpus_entries *callchain_cpus_entries; + + +__weak void perf_callchain_kernel(struct perf_callchain_entry *entry, + struct pt_regs *regs) +{ +} + +__weak void perf_callchain_user(struct perf_callchain_entry *entry, + struct pt_regs *regs) +{ +} + +static void release_callchain_buffers_rcu(struct rcu_head *head) +{ + struct callchain_cpus_entries *entries; + int cpu; + + entries = container_of(head, struct callchain_cpus_entries, rcu_head); + + for_each_possible_cpu(cpu) + kfree(entries->cpu_entries[cpu]); + + kfree(entries); +} + +static void release_callchain_buffers(void) +{ + struct callchain_cpus_entries *entries; + + entries = callchain_cpus_entries; + RCU_INIT_POINTER(callchain_cpus_entries, NULL); + call_rcu(&entries->rcu_head, release_callchain_buffers_rcu); +} + +static int alloc_callchain_buffers(void) +{ + int cpu; + int size; + struct callchain_cpus_entries *entries; + + /* + * We can't use the percpu allocation API for data that can be + * accessed from NMI. Use a temporary manual per cpu allocation + * until that gets sorted out. + */ + size = offsetof(struct callchain_cpus_entries, cpu_entries[nr_cpu_ids]); + + entries = kzalloc(size, GFP_KERNEL); + if (!entries) + return -ENOMEM; + + size = sizeof(struct perf_callchain_entry) * PERF_NR_CONTEXTS; + + for_each_possible_cpu(cpu) { + entries->cpu_entries[cpu] = kmalloc_node(size, GFP_KERNEL, + cpu_to_node(cpu)); + if (!entries->cpu_entries[cpu]) + goto fail; + } + + rcu_assign_pointer(callchain_cpus_entries, entries); + + return 0; + +fail: + for_each_possible_cpu(cpu) + kfree(entries->cpu_entries[cpu]); + kfree(entries); + + return -ENOMEM; +} + +int get_callchain_buffers(void) +{ + int err = 0; + int count; + + mutex_lock(&callchain_mutex); + + count = atomic_inc_return(&nr_callchain_events); + if (WARN_ON_ONCE(count < 1)) { + err = -EINVAL; + goto exit; + } + + if (count > 1) { + /* If the allocation failed, give up */ + if (!callchain_cpus_entries) + err = -ENOMEM; + goto exit; + } + + err = alloc_callchain_buffers(); +exit: + if (err) + atomic_dec(&nr_callchain_events); + + mutex_unlock(&callchain_mutex); + + return err; +} + +void put_callchain_buffers(void) +{ + if (atomic_dec_and_mutex_lock(&nr_callchain_events, &callchain_mutex)) { + release_callchain_buffers(); + mutex_unlock(&callchain_mutex); + } +} + +static struct perf_callchain_entry *get_callchain_entry(int *rctx) +{ + int cpu; + struct callchain_cpus_entries *entries; + + *rctx = get_recursion_context(this_cpu_ptr(callchain_recursion)); + if (*rctx == -1) + return NULL; + + entries = rcu_dereference(callchain_cpus_entries); + if (!entries) + return NULL; + + cpu = smp_processor_id(); + + return &entries->cpu_entries[cpu][*rctx]; +} + +static void +put_callchain_entry(int rctx) +{ + put_recursion_context(this_cpu_ptr(callchain_recursion), rctx); +} + +struct perf_callchain_entry * +perf_callchain(struct perf_event *event, struct pt_regs *regs) +{ + int rctx; + struct perf_callchain_entry *entry; + + int kernel = !event->attr.exclude_callchain_kernel; + int user = !event->attr.exclude_callchain_user; + + if (!kernel && !user) + return NULL; + + entry = get_callchain_entry(&rctx); + if (rctx == -1) + return NULL; + + if (!entry) + goto exit_put; + + entry->nr = 0; + + if (kernel && !user_mode(regs)) { + perf_callchain_store(entry, PERF_CONTEXT_KERNEL); + perf_callchain_kernel(entry, regs); + } + + if (user) { + if (!user_mode(regs)) { + if (current->mm) + regs = task_pt_regs(current); + else + regs = NULL; + } + + if (regs) { + /* + * Disallow cross-task user callchains. + */ + if (event->ctx->task && event->ctx->task != current) + goto exit_put; + + perf_callchain_store(entry, PERF_CONTEXT_USER); + perf_callchain_user(entry, regs); + } + } + +exit_put: + put_callchain_entry(rctx); + + return entry; +} diff --git a/kernel/kernel/events/core.c b/kernel/kernel/events/core.c new file mode 100644 index 000000000..e05d1dd7d --- /dev/null +++ b/kernel/kernel/events/core.c @@ -0,0 +1,9084 @@ +/* + * Performance events core code: + * + * Copyright (C) 2008 Thomas Gleixner + * Copyright (C) 2008-2011 Red Hat, Inc., Ingo Molnar + * Copyright (C) 2008-2011 Red Hat, Inc., Peter Zijlstra + * Copyright © 2009 Paul Mackerras, IBM Corp. + * + * For licensing details see kernel-base/COPYING + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "internal.h" + +#include + +static struct workqueue_struct *perf_wq; + +struct remote_function_call { + struct task_struct *p; + int (*func)(void *info); + void *info; + int ret; +}; + +static void remote_function(void *data) +{ + struct remote_function_call *tfc = data; + struct task_struct *p = tfc->p; + + if (p) { + tfc->ret = -EAGAIN; + if (task_cpu(p) != smp_processor_id() || !task_curr(p)) + return; + } + + tfc->ret = tfc->func(tfc->info); +} + +/** + * task_function_call - call a function on the cpu on which a task runs + * @p: the task to evaluate + * @func: the function to be called + * @info: the function call argument + * + * Calls the function @func when the task is currently running. This might + * be on the current CPU, which just calls the function directly + * + * returns: @func return value, or + * -ESRCH - when the process isn't running + * -EAGAIN - when the process moved away + */ +static int +task_function_call(struct task_struct *p, int (*func) (void *info), void *info) +{ + struct remote_function_call data = { + .p = p, + .func = func, + .info = info, + .ret = -ESRCH, /* No such (running) process */ + }; + + if (task_curr(p)) + smp_call_function_single(task_cpu(p), remote_function, &data, 1); + + return data.ret; +} + +/** + * cpu_function_call - call a function on the cpu + * @func: the function to be called + * @info: the function call argument + * + * Calls the function @func on the remote cpu. + * + * returns: @func return value or -ENXIO when the cpu is offline + */ +static int cpu_function_call(int cpu, int (*func) (void *info), void *info) +{ + struct remote_function_call data = { + .p = NULL, + .func = func, + .info = info, + .ret = -ENXIO, /* No such CPU */ + }; + + smp_call_function_single(cpu, remote_function, &data, 1); + + return data.ret; +} + +#define EVENT_OWNER_KERNEL ((void *) -1) + +static bool is_kernel_event(struct perf_event *event) +{ + return event->owner == EVENT_OWNER_KERNEL; +} + +#define PERF_FLAG_ALL (PERF_FLAG_FD_NO_GROUP |\ + PERF_FLAG_FD_OUTPUT |\ + PERF_FLAG_PID_CGROUP |\ + PERF_FLAG_FD_CLOEXEC) + +/* + * branch priv levels that need permission checks + */ +#define PERF_SAMPLE_BRANCH_PERM_PLM \ + (PERF_SAMPLE_BRANCH_KERNEL |\ + PERF_SAMPLE_BRANCH_HV) + +enum event_type_t { + EVENT_FLEXIBLE = 0x1, + EVENT_PINNED = 0x2, + EVENT_ALL = EVENT_FLEXIBLE | EVENT_PINNED, +}; + +/* + * perf_sched_events : >0 events exist + * perf_cgroup_events: >0 per-cpu cgroup events exist on this cpu + */ +struct static_key_deferred perf_sched_events __read_mostly; +static DEFINE_PER_CPU(atomic_t, perf_cgroup_events); +static DEFINE_PER_CPU(int, perf_sched_cb_usages); + +static atomic_t nr_mmap_events __read_mostly; +static atomic_t nr_comm_events __read_mostly; +static atomic_t nr_task_events __read_mostly; +static atomic_t nr_freq_events __read_mostly; + +static LIST_HEAD(pmus); +static DEFINE_MUTEX(pmus_lock); +static struct srcu_struct pmus_srcu; + +/* + * perf event paranoia level: + * -1 - not paranoid at all + * 0 - disallow raw tracepoint access for unpriv + * 1 - disallow cpu events for unpriv + * 2 - disallow kernel profiling for unpriv + */ +int sysctl_perf_event_paranoid __read_mostly = 1; + +/* Minimum for 512 kiB + 1 user control page */ +int sysctl_perf_event_mlock __read_mostly = 512 + (PAGE_SIZE / 1024); /* 'free' kiB per user */ + +/* + * max perf event sample rate + */ +#define DEFAULT_MAX_SAMPLE_RATE 100000 +#define DEFAULT_SAMPLE_PERIOD_NS (NSEC_PER_SEC / DEFAULT_MAX_SAMPLE_RATE) +#define DEFAULT_CPU_TIME_MAX_PERCENT 25 + +int sysctl_perf_event_sample_rate __read_mostly = DEFAULT_MAX_SAMPLE_RATE; + +static int max_samples_per_tick __read_mostly = DIV_ROUND_UP(DEFAULT_MAX_SAMPLE_RATE, HZ); +static int perf_sample_period_ns __read_mostly = DEFAULT_SAMPLE_PERIOD_NS; + +static int perf_sample_allowed_ns __read_mostly = + DEFAULT_SAMPLE_PERIOD_NS * DEFAULT_CPU_TIME_MAX_PERCENT / 100; + +void update_perf_cpu_limits(void) +{ + u64 tmp = perf_sample_period_ns; + + tmp *= sysctl_perf_cpu_time_max_percent; + do_div(tmp, 100); + ACCESS_ONCE(perf_sample_allowed_ns) = tmp; +} + +static int perf_rotate_context(struct perf_cpu_context *cpuctx); + +int perf_proc_update_handler(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos) +{ + int ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); + + if (ret || !write) + return ret; + + max_samples_per_tick = DIV_ROUND_UP(sysctl_perf_event_sample_rate, HZ); + perf_sample_period_ns = NSEC_PER_SEC / sysctl_perf_event_sample_rate; + update_perf_cpu_limits(); + + return 0; +} + +int sysctl_perf_cpu_time_max_percent __read_mostly = DEFAULT_CPU_TIME_MAX_PERCENT; + +int perf_cpu_time_max_percent_handler(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos) +{ + int ret = proc_dointvec(table, write, buffer, lenp, ppos); + + if (ret || !write) + return ret; + + update_perf_cpu_limits(); + + return 0; +} + +/* + * perf samples are done in some very critical code paths (NMIs). + * If they take too much CPU time, the system can lock up and not + * get any real work done. This will drop the sample rate when + * we detect that events are taking too long. + */ +#define NR_ACCUMULATED_SAMPLES 128 +static DEFINE_PER_CPU(u64, running_sample_length); + +static void perf_duration_warn(struct irq_work *w) +{ + u64 allowed_ns = ACCESS_ONCE(perf_sample_allowed_ns); + u64 avg_local_sample_len; + u64 local_samples_len; + + local_samples_len = __this_cpu_read(running_sample_length); + avg_local_sample_len = local_samples_len/NR_ACCUMULATED_SAMPLES; + + printk_ratelimited(KERN_WARNING + "perf interrupt took too long (%lld > %lld), lowering " + "kernel.perf_event_max_sample_rate to %d\n", + avg_local_sample_len, allowed_ns >> 1, + sysctl_perf_event_sample_rate); +} + +static DEFINE_IRQ_WORK(perf_duration_work, perf_duration_warn); + +void perf_sample_event_took(u64 sample_len_ns) +{ + u64 allowed_ns = ACCESS_ONCE(perf_sample_allowed_ns); + u64 avg_local_sample_len; + u64 local_samples_len; + + if (allowed_ns == 0) + return; + + /* decay the counter by 1 average sample */ + local_samples_len = __this_cpu_read(running_sample_length); + local_samples_len -= local_samples_len/NR_ACCUMULATED_SAMPLES; + local_samples_len += sample_len_ns; + __this_cpu_write(running_sample_length, local_samples_len); + + /* + * note: this will be biased artifically low until we have + * seen NR_ACCUMULATED_SAMPLES. Doing it this way keeps us + * from having to maintain a count. + */ + avg_local_sample_len = local_samples_len/NR_ACCUMULATED_SAMPLES; + + if (avg_local_sample_len <= allowed_ns) + return; + + if (max_samples_per_tick <= 1) + return; + + max_samples_per_tick = DIV_ROUND_UP(max_samples_per_tick, 2); + sysctl_perf_event_sample_rate = max_samples_per_tick * HZ; + perf_sample_period_ns = NSEC_PER_SEC / sysctl_perf_event_sample_rate; + + update_perf_cpu_limits(); + + if (!irq_work_queue(&perf_duration_work)) { + early_printk("perf interrupt took too long (%lld > %lld), lowering " + "kernel.perf_event_max_sample_rate to %d\n", + avg_local_sample_len, allowed_ns >> 1, + sysctl_perf_event_sample_rate); + } +} + +static atomic64_t perf_event_id; + +static void cpu_ctx_sched_out(struct perf_cpu_context *cpuctx, + enum event_type_t event_type); + +static void cpu_ctx_sched_in(struct perf_cpu_context *cpuctx, + enum event_type_t event_type, + struct task_struct *task); + +static void update_context_time(struct perf_event_context *ctx); +static u64 perf_event_time(struct perf_event *event); + +void __weak perf_event_print_debug(void) { } + +extern __weak const char *perf_pmu_name(void) +{ + return "pmu"; +} + +static inline u64 perf_clock(void) +{ + return local_clock(); +} + +static inline u64 perf_event_clock(struct perf_event *event) +{ + return event->clock(); +} + +static inline struct perf_cpu_context * +__get_cpu_context(struct perf_event_context *ctx) +{ + return this_cpu_ptr(ctx->pmu->pmu_cpu_context); +} + +static void perf_ctx_lock(struct perf_cpu_context *cpuctx, + struct perf_event_context *ctx) +{ + raw_spin_lock(&cpuctx->ctx.lock); + if (ctx) + raw_spin_lock(&ctx->lock); +} + +static void perf_ctx_unlock(struct perf_cpu_context *cpuctx, + struct perf_event_context *ctx) +{ + if (ctx) + raw_spin_unlock(&ctx->lock); + raw_spin_unlock(&cpuctx->ctx.lock); +} + +#ifdef CONFIG_CGROUP_PERF + +static inline bool +perf_cgroup_match(struct perf_event *event) +{ + struct perf_event_context *ctx = event->ctx; + struct perf_cpu_context *cpuctx = __get_cpu_context(ctx); + + /* @event doesn't care about cgroup */ + if (!event->cgrp) + return true; + + /* wants specific cgroup scope but @cpuctx isn't associated with any */ + if (!cpuctx->cgrp) + return false; + + /* + * Cgroup scoping is recursive. An event enabled for a cgroup is + * also enabled for all its descendant cgroups. If @cpuctx's + * cgroup is a descendant of @event's (the test covers identity + * case), it's a match. + */ + return cgroup_is_descendant(cpuctx->cgrp->css.cgroup, + event->cgrp->css.cgroup); +} + +static inline void perf_detach_cgroup(struct perf_event *event) +{ + css_put(&event->cgrp->css); + event->cgrp = NULL; +} + +static inline int is_cgroup_event(struct perf_event *event) +{ + return event->cgrp != NULL; +} + +static inline u64 perf_cgroup_event_time(struct perf_event *event) +{ + struct perf_cgroup_info *t; + + t = per_cpu_ptr(event->cgrp->info, event->cpu); + return t->time; +} + +static inline void __update_cgrp_time(struct perf_cgroup *cgrp) +{ + struct perf_cgroup_info *info; + u64 now; + + now = perf_clock(); + + info = this_cpu_ptr(cgrp->info); + + info->time += now - info->timestamp; + info->timestamp = now; +} + +static inline void update_cgrp_time_from_cpuctx(struct perf_cpu_context *cpuctx) +{ + struct perf_cgroup *cgrp_out = cpuctx->cgrp; + if (cgrp_out) + __update_cgrp_time(cgrp_out); +} + +static inline void update_cgrp_time_from_event(struct perf_event *event) +{ + struct perf_cgroup *cgrp; + + /* + * ensure we access cgroup data only when needed and + * when we know the cgroup is pinned (css_get) + */ + if (!is_cgroup_event(event)) + return; + + cgrp = perf_cgroup_from_task(current); + /* + * Do not update time when cgroup is not active + */ + if (cgrp == event->cgrp) + __update_cgrp_time(event->cgrp); +} + +static inline void +perf_cgroup_set_timestamp(struct task_struct *task, + struct perf_event_context *ctx) +{ + struct perf_cgroup *cgrp; + struct perf_cgroup_info *info; + + /* + * ctx->lock held by caller + * ensure we do not access cgroup data + * unless we have the cgroup pinned (css_get) + */ + if (!task || !ctx->nr_cgroups) + return; + + cgrp = perf_cgroup_from_task(task); + info = this_cpu_ptr(cgrp->info); + info->timestamp = ctx->timestamp; +} + +#define PERF_CGROUP_SWOUT 0x1 /* cgroup switch out every event */ +#define PERF_CGROUP_SWIN 0x2 /* cgroup switch in events based on task */ + +/* + * reschedule events based on the cgroup constraint of task. + * + * mode SWOUT : schedule out everything + * mode SWIN : schedule in based on cgroup for next + */ +void perf_cgroup_switch(struct task_struct *task, int mode) +{ + struct perf_cpu_context *cpuctx; + struct pmu *pmu; + unsigned long flags; + + /* + * disable interrupts to avoid geting nr_cgroup + * changes via __perf_event_disable(). Also + * avoids preemption. + */ + local_irq_save(flags); + + /* + * we reschedule only in the presence of cgroup + * constrained events. + */ + rcu_read_lock(); + + list_for_each_entry_rcu(pmu, &pmus, entry) { + cpuctx = this_cpu_ptr(pmu->pmu_cpu_context); + if (cpuctx->unique_pmu != pmu) + continue; /* ensure we process each cpuctx once */ + + /* + * perf_cgroup_events says at least one + * context on this CPU has cgroup events. + * + * ctx->nr_cgroups reports the number of cgroup + * events for a context. + */ + if (cpuctx->ctx.nr_cgroups > 0) { + perf_ctx_lock(cpuctx, cpuctx->task_ctx); + perf_pmu_disable(cpuctx->ctx.pmu); + + if (mode & PERF_CGROUP_SWOUT) { + cpu_ctx_sched_out(cpuctx, EVENT_ALL); + /* + * must not be done before ctxswout due + * to event_filter_match() in event_sched_out() + */ + cpuctx->cgrp = NULL; + } + + if (mode & PERF_CGROUP_SWIN) { + WARN_ON_ONCE(cpuctx->cgrp); + /* + * set cgrp before ctxsw in to allow + * event_filter_match() to not have to pass + * task around + */ + cpuctx->cgrp = perf_cgroup_from_task(task); + cpu_ctx_sched_in(cpuctx, EVENT_ALL, task); + } + perf_pmu_enable(cpuctx->ctx.pmu); + perf_ctx_unlock(cpuctx, cpuctx->task_ctx); + } + } + + rcu_read_unlock(); + + local_irq_restore(flags); +} + +static inline void perf_cgroup_sched_out(struct task_struct *task, + struct task_struct *next) +{ + struct perf_cgroup *cgrp1; + struct perf_cgroup *cgrp2 = NULL; + + /* + * we come here when we know perf_cgroup_events > 0 + */ + cgrp1 = perf_cgroup_from_task(task); + + /* + * next is NULL when called from perf_event_enable_on_exec() + * that will systematically cause a cgroup_switch() + */ + if (next) + cgrp2 = perf_cgroup_from_task(next); + + /* + * only schedule out current cgroup events if we know + * that we are switching to a different cgroup. Otherwise, + * do no touch the cgroup events. + */ + if (cgrp1 != cgrp2) + perf_cgroup_switch(task, PERF_CGROUP_SWOUT); +} + +static inline void perf_cgroup_sched_in(struct task_struct *prev, + struct task_struct *task) +{ + struct perf_cgroup *cgrp1; + struct perf_cgroup *cgrp2 = NULL; + + /* + * we come here when we know perf_cgroup_events > 0 + */ + cgrp1 = perf_cgroup_from_task(task); + + /* prev can never be NULL */ + cgrp2 = perf_cgroup_from_task(prev); + + /* + * only need to schedule in cgroup events if we are changing + * cgroup during ctxsw. Cgroup events were not scheduled + * out of ctxsw out if that was not the case. + */ + if (cgrp1 != cgrp2) + perf_cgroup_switch(task, PERF_CGROUP_SWIN); +} + +static inline int perf_cgroup_connect(int fd, struct perf_event *event, + struct perf_event_attr *attr, + struct perf_event *group_leader) +{ + struct perf_cgroup *cgrp; + struct cgroup_subsys_state *css; + struct fd f = fdget(fd); + int ret = 0; + + if (!f.file) + return -EBADF; + + css = css_tryget_online_from_dir(f.file->f_path.dentry, + &perf_event_cgrp_subsys); + if (IS_ERR(css)) { + ret = PTR_ERR(css); + goto out; + } + + cgrp = container_of(css, struct perf_cgroup, css); + event->cgrp = cgrp; + + /* + * all events in a group must monitor + * the same cgroup because a task belongs + * to only one perf cgroup at a time + */ + if (group_leader && group_leader->cgrp != cgrp) { + perf_detach_cgroup(event); + ret = -EINVAL; + } +out: + fdput(f); + return ret; +} + +static inline void +perf_cgroup_set_shadow_time(struct perf_event *event, u64 now) +{ + struct perf_cgroup_info *t; + t = per_cpu_ptr(event->cgrp->info, event->cpu); + event->shadow_ctx_time = now - t->timestamp; +} + +static inline void +perf_cgroup_defer_enabled(struct perf_event *event) +{ + /* + * when the current task's perf cgroup does not match + * the event's, we need to remember to call the + * perf_mark_enable() function the first time a task with + * a matching perf cgroup is scheduled in. + */ + if (is_cgroup_event(event) && !perf_cgroup_match(event)) + event->cgrp_defer_enabled = 1; +} + +static inline void +perf_cgroup_mark_enabled(struct perf_event *event, + struct perf_event_context *ctx) +{ + struct perf_event *sub; + u64 tstamp = perf_event_time(event); + + if (!event->cgrp_defer_enabled) + return; + + event->cgrp_defer_enabled = 0; + + event->tstamp_enabled = tstamp - event->total_time_enabled; + list_for_each_entry(sub, &event->sibling_list, group_entry) { + if (sub->state >= PERF_EVENT_STATE_INACTIVE) { + sub->tstamp_enabled = tstamp - sub->total_time_enabled; + sub->cgrp_defer_enabled = 0; + } + } +} +#else /* !CONFIG_CGROUP_PERF */ + +static inline bool +perf_cgroup_match(struct perf_event *event) +{ + return true; +} + +static inline void perf_detach_cgroup(struct perf_event *event) +{} + +static inline int is_cgroup_event(struct perf_event *event) +{ + return 0; +} + +static inline u64 perf_cgroup_event_cgrp_time(struct perf_event *event) +{ + return 0; +} + +static inline void update_cgrp_time_from_event(struct perf_event *event) +{ +} + +static inline void update_cgrp_time_from_cpuctx(struct perf_cpu_context *cpuctx) +{ +} + +static inline void perf_cgroup_sched_out(struct task_struct *task, + struct task_struct *next) +{ +} + +static inline void perf_cgroup_sched_in(struct task_struct *prev, + struct task_struct *task) +{ +} + +static inline int perf_cgroup_connect(pid_t pid, struct perf_event *event, + struct perf_event_attr *attr, + struct perf_event *group_leader) +{ + return -EINVAL; +} + +static inline void +perf_cgroup_set_timestamp(struct task_struct *task, + struct perf_event_context *ctx) +{ +} + +void +perf_cgroup_switch(struct task_struct *task, struct task_struct *next) +{ +} + +static inline void +perf_cgroup_set_shadow_time(struct perf_event *event, u64 now) +{ +} + +static inline u64 perf_cgroup_event_time(struct perf_event *event) +{ + return 0; +} + +static inline void +perf_cgroup_defer_enabled(struct perf_event *event) +{ +} + +static inline void +perf_cgroup_mark_enabled(struct perf_event *event, + struct perf_event_context *ctx) +{ +} +#endif + +/* + * set default to be dependent on timer tick just + * like original code + */ +#define PERF_CPU_HRTIMER (1000 / HZ) +/* + * function must be called with interrupts disbled + */ +static enum hrtimer_restart perf_cpu_hrtimer_handler(struct hrtimer *hr) +{ + struct perf_cpu_context *cpuctx; + enum hrtimer_restart ret = HRTIMER_NORESTART; + int rotations = 0; + + WARN_ON(!irqs_disabled()); + + cpuctx = container_of(hr, struct perf_cpu_context, hrtimer); + + rotations = perf_rotate_context(cpuctx); + + /* + * arm timer if needed + */ + if (rotations) { + hrtimer_forward_now(hr, cpuctx->hrtimer_interval); + ret = HRTIMER_RESTART; + } + + return ret; +} + +/* CPU is going down */ +void perf_cpu_hrtimer_cancel(int cpu) +{ + struct perf_cpu_context *cpuctx; + struct pmu *pmu; + unsigned long flags; + + if (WARN_ON(cpu != smp_processor_id())) + return; + + local_irq_save(flags); + + rcu_read_lock(); + + list_for_each_entry_rcu(pmu, &pmus, entry) { + cpuctx = this_cpu_ptr(pmu->pmu_cpu_context); + + if (pmu->task_ctx_nr == perf_sw_context) + continue; + + hrtimer_cancel(&cpuctx->hrtimer); + } + + rcu_read_unlock(); + + local_irq_restore(flags); +} + +static void __perf_cpu_hrtimer_init(struct perf_cpu_context *cpuctx, int cpu) +{ + struct hrtimer *hr = &cpuctx->hrtimer; + struct pmu *pmu = cpuctx->ctx.pmu; + int timer; + + /* no multiplexing needed for SW PMU */ + if (pmu->task_ctx_nr == perf_sw_context) + return; + + /* + * check default is sane, if not set then force to + * default interval (1/tick) + */ + timer = pmu->hrtimer_interval_ms; + if (timer < 1) + timer = pmu->hrtimer_interval_ms = PERF_CPU_HRTIMER; + + cpuctx->hrtimer_interval = ns_to_ktime(NSEC_PER_MSEC * timer); + + hrtimer_init(hr, CLOCK_MONOTONIC, HRTIMER_MODE_REL_PINNED); + hr->function = perf_cpu_hrtimer_handler; +} + +static void perf_cpu_hrtimer_restart(struct perf_cpu_context *cpuctx) +{ + struct hrtimer *hr = &cpuctx->hrtimer; + struct pmu *pmu = cpuctx->ctx.pmu; + + /* not for SW PMU */ + if (pmu->task_ctx_nr == perf_sw_context) + return; + + if (hrtimer_active(hr)) + return; + + if (!hrtimer_callback_running(hr)) + __hrtimer_start_range_ns(hr, cpuctx->hrtimer_interval, + 0, HRTIMER_MODE_REL_PINNED, 0); +} + +void perf_pmu_disable(struct pmu *pmu) +{ + int *count = this_cpu_ptr(pmu->pmu_disable_count); + if (!(*count)++) + pmu->pmu_disable(pmu); +} + +void perf_pmu_enable(struct pmu *pmu) +{ + int *count = this_cpu_ptr(pmu->pmu_disable_count); + if (!--(*count)) + pmu->pmu_enable(pmu); +} + +static DEFINE_PER_CPU(struct list_head, active_ctx_list); + +/* + * perf_event_ctx_activate(), perf_event_ctx_deactivate(), and + * perf_event_task_tick() are fully serialized because they're strictly cpu + * affine and perf_event_ctx{activate,deactivate} are called with IRQs + * disabled, while perf_event_task_tick is called from IRQ context. + */ +static void perf_event_ctx_activate(struct perf_event_context *ctx) +{ + struct list_head *head = this_cpu_ptr(&active_ctx_list); + + WARN_ON(!irqs_disabled()); + + WARN_ON(!list_empty(&ctx->active_ctx_list)); + + list_add(&ctx->active_ctx_list, head); +} + +static void perf_event_ctx_deactivate(struct perf_event_context *ctx) +{ + WARN_ON(!irqs_disabled()); + + WARN_ON(list_empty(&ctx->active_ctx_list)); + + list_del_init(&ctx->active_ctx_list); +} + +static void get_ctx(struct perf_event_context *ctx) +{ + WARN_ON(!atomic_inc_not_zero(&ctx->refcount)); +} + +static void free_ctx(struct rcu_head *head) +{ + struct perf_event_context *ctx; + + ctx = container_of(head, struct perf_event_context, rcu_head); + kfree(ctx->task_ctx_data); + kfree(ctx); +} + +static void put_ctx(struct perf_event_context *ctx) +{ + if (atomic_dec_and_test(&ctx->refcount)) { + if (ctx->parent_ctx) + put_ctx(ctx->parent_ctx); + if (ctx->task) + put_task_struct(ctx->task); + call_rcu(&ctx->rcu_head, free_ctx); + } +} + +/* + * Because of perf_event::ctx migration in sys_perf_event_open::move_group and + * perf_pmu_migrate_context() we need some magic. + * + * Those places that change perf_event::ctx will hold both + * perf_event_ctx::mutex of the 'old' and 'new' ctx value. + * + * Lock ordering is by mutex address. There are two other sites where + * perf_event_context::mutex nests and those are: + * + * - perf_event_exit_task_context() [ child , 0 ] + * __perf_event_exit_task() + * sync_child_event() + * put_event() [ parent, 1 ] + * + * - perf_event_init_context() [ parent, 0 ] + * inherit_task_group() + * inherit_group() + * inherit_event() + * perf_event_alloc() + * perf_init_event() + * perf_try_init_event() [ child , 1 ] + * + * While it appears there is an obvious deadlock here -- the parent and child + * nesting levels are inverted between the two. This is in fact safe because + * life-time rules separate them. That is an exiting task cannot fork, and a + * spawning task cannot (yet) exit. + * + * But remember that that these are parent<->child context relations, and + * migration does not affect children, therefore these two orderings should not + * interact. + * + * The change in perf_event::ctx does not affect children (as claimed above) + * because the sys_perf_event_open() case will install a new event and break + * the ctx parent<->child relation, and perf_pmu_migrate_context() is only + * concerned with cpuctx and that doesn't have children. + * + * The places that change perf_event::ctx will issue: + * + * perf_remove_from_context(); + * synchronize_rcu(); + * perf_install_in_context(); + * + * to affect the change. The remove_from_context() + synchronize_rcu() should + * quiesce the event, after which we can install it in the new location. This + * means that only external vectors (perf_fops, prctl) can perturb the event + * while in transit. Therefore all such accessors should also acquire + * perf_event_context::mutex to serialize against this. + * + * However; because event->ctx can change while we're waiting to acquire + * ctx->mutex we must be careful and use the below perf_event_ctx_lock() + * function. + * + * Lock order: + * task_struct::perf_event_mutex + * perf_event_context::mutex + * perf_event_context::lock + * perf_event::child_mutex; + * perf_event::mmap_mutex + * mmap_sem + */ +static struct perf_event_context * +perf_event_ctx_lock_nested(struct perf_event *event, int nesting) +{ + struct perf_event_context *ctx; + +again: + rcu_read_lock(); + ctx = ACCESS_ONCE(event->ctx); + if (!atomic_inc_not_zero(&ctx->refcount)) { + rcu_read_unlock(); + goto again; + } + rcu_read_unlock(); + + mutex_lock_nested(&ctx->mutex, nesting); + if (event->ctx != ctx) { + mutex_unlock(&ctx->mutex); + put_ctx(ctx); + goto again; + } + + return ctx; +} + +static inline struct perf_event_context * +perf_event_ctx_lock(struct perf_event *event) +{ + return perf_event_ctx_lock_nested(event, 0); +} + +static void perf_event_ctx_unlock(struct perf_event *event, + struct perf_event_context *ctx) +{ + mutex_unlock(&ctx->mutex); + put_ctx(ctx); +} + +/* + * This must be done under the ctx->lock, such as to serialize against + * context_equiv(), therefore we cannot call put_ctx() since that might end up + * calling scheduler related locks and ctx->lock nests inside those. + */ +static __must_check struct perf_event_context * +unclone_ctx(struct perf_event_context *ctx) +{ + struct perf_event_context *parent_ctx = ctx->parent_ctx; + + lockdep_assert_held(&ctx->lock); + + if (parent_ctx) + ctx->parent_ctx = NULL; + ctx->generation++; + + return parent_ctx; +} + +static u32 perf_event_pid(struct perf_event *event, struct task_struct *p) +{ + /* + * only top level events have the pid namespace they were created in + */ + if (event->parent) + event = event->parent; + + return task_tgid_nr_ns(p, event->ns); +} + +static u32 perf_event_tid(struct perf_event *event, struct task_struct *p) +{ + /* + * only top level events have the pid namespace they were created in + */ + if (event->parent) + event = event->parent; + + return task_pid_nr_ns(p, event->ns); +} + +/* + * If we inherit events we want to return the parent event id + * to userspace. + */ +static u64 primary_event_id(struct perf_event *event) +{ + u64 id = event->id; + + if (event->parent) + id = event->parent->id; + + return id; +} + +/* + * Get the perf_event_context for a task and lock it. + * This has to cope with with the fact that until it is locked, + * the context could get moved to another task. + */ +static struct perf_event_context * +perf_lock_task_context(struct task_struct *task, int ctxn, unsigned long *flags) +{ + struct perf_event_context *ctx; + +retry: + /* + * One of the few rules of preemptible RCU is that one cannot do + * rcu_read_unlock() while holding a scheduler (or nested) lock when + * part of the read side critical section was preemptible -- see + * rcu_read_unlock_special(). + * + * Since ctx->lock nests under rq->lock we must ensure the entire read + * side critical section is non-preemptible. + */ + preempt_disable(); + rcu_read_lock(); + ctx = rcu_dereference(task->perf_event_ctxp[ctxn]); + if (ctx) { + /* + * If this context is a clone of another, it might + * get swapped for another underneath us by + * perf_event_task_sched_out, though the + * rcu_read_lock() protects us from any context + * getting freed. Lock the context and check if it + * got swapped before we could get the lock, and retry + * if so. If we locked the right context, then it + * can't get swapped on us any more. + */ + raw_spin_lock_irqsave(&ctx->lock, *flags); + if (ctx != rcu_dereference(task->perf_event_ctxp[ctxn])) { + raw_spin_unlock_irqrestore(&ctx->lock, *flags); + rcu_read_unlock(); + preempt_enable(); + goto retry; + } + + if (!atomic_inc_not_zero(&ctx->refcount)) { + raw_spin_unlock_irqrestore(&ctx->lock, *flags); + ctx = NULL; + } + } + rcu_read_unlock(); + preempt_enable(); + return ctx; +} + +/* + * Get the context for a task and increment its pin_count so it + * can't get swapped to another task. This also increments its + * reference count so that the context can't get freed. + */ +static struct perf_event_context * +perf_pin_task_context(struct task_struct *task, int ctxn) +{ + struct perf_event_context *ctx; + unsigned long flags; + + ctx = perf_lock_task_context(task, ctxn, &flags); + if (ctx) { + ++ctx->pin_count; + raw_spin_unlock_irqrestore(&ctx->lock, flags); + } + return ctx; +} + +static void perf_unpin_context(struct perf_event_context *ctx) +{ + unsigned long flags; + + raw_spin_lock_irqsave(&ctx->lock, flags); + --ctx->pin_count; + raw_spin_unlock_irqrestore(&ctx->lock, flags); +} + +/* + * Update the record of the current time in a context. + */ +static void update_context_time(struct perf_event_context *ctx) +{ + u64 now = perf_clock(); + + ctx->time += now - ctx->timestamp; + ctx->timestamp = now; +} + +static u64 perf_event_time(struct perf_event *event) +{ + struct perf_event_context *ctx = event->ctx; + + if (is_cgroup_event(event)) + return perf_cgroup_event_time(event); + + return ctx ? ctx->time : 0; +} + +/* + * Update the total_time_enabled and total_time_running fields for a event. + * The caller of this function needs to hold the ctx->lock. + */ +static void update_event_times(struct perf_event *event) +{ + struct perf_event_context *ctx = event->ctx; + u64 run_end; + + if (event->state < PERF_EVENT_STATE_INACTIVE || + event->group_leader->state < PERF_EVENT_STATE_INACTIVE) + return; + /* + * in cgroup mode, time_enabled represents + * the time the event was enabled AND active + * tasks were in the monitored cgroup. This is + * independent of the activity of the context as + * there may be a mix of cgroup and non-cgroup events. + * + * That is why we treat cgroup events differently + * here. + */ + if (is_cgroup_event(event)) + run_end = perf_cgroup_event_time(event); + else if (ctx->is_active) + run_end = ctx->time; + else + run_end = event->tstamp_stopped; + + event->total_time_enabled = run_end - event->tstamp_enabled; + + if (event->state == PERF_EVENT_STATE_INACTIVE) + run_end = event->tstamp_stopped; + else + run_end = perf_event_time(event); + + event->total_time_running = run_end - event->tstamp_running; + +} + +/* + * Update total_time_enabled and total_time_running for all events in a group. + */ +static void update_group_times(struct perf_event *leader) +{ + struct perf_event *event; + + update_event_times(leader); + list_for_each_entry(event, &leader->sibling_list, group_entry) + update_event_times(event); +} + +static struct list_head * +ctx_group_list(struct perf_event *event, struct perf_event_context *ctx) +{ + if (event->attr.pinned) + return &ctx->pinned_groups; + else + return &ctx->flexible_groups; +} + +/* + * Add a event from the lists for its context. + * Must be called with ctx->mutex and ctx->lock held. + */ +static void +list_add_event(struct perf_event *event, struct perf_event_context *ctx) +{ + WARN_ON_ONCE(event->attach_state & PERF_ATTACH_CONTEXT); + event->attach_state |= PERF_ATTACH_CONTEXT; + + /* + * If we're a stand alone event or group leader, we go to the context + * list, group events are kept attached to the group so that + * perf_group_detach can, at all times, locate all siblings. + */ + if (event->group_leader == event) { + struct list_head *list; + + if (is_software_event(event)) + event->group_flags |= PERF_GROUP_SOFTWARE; + + list = ctx_group_list(event, ctx); + list_add_tail(&event->group_entry, list); + } + + if (is_cgroup_event(event)) + ctx->nr_cgroups++; + + list_add_rcu(&event->event_entry, &ctx->event_list); + ctx->nr_events++; + if (event->attr.inherit_stat) + ctx->nr_stat++; + + ctx->generation++; +} + +/* + * Initialize event state based on the perf_event_attr::disabled. + */ +static inline void perf_event__state_init(struct perf_event *event) +{ + event->state = event->attr.disabled ? PERF_EVENT_STATE_OFF : + PERF_EVENT_STATE_INACTIVE; +} + +/* + * Called at perf_event creation and when events are attached/detached from a + * group. + */ +static void perf_event__read_size(struct perf_event *event) +{ + int entry = sizeof(u64); /* value */ + int size = 0; + int nr = 1; + + if (event->attr.read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) + size += sizeof(u64); + + if (event->attr.read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) + size += sizeof(u64); + + if (event->attr.read_format & PERF_FORMAT_ID) + entry += sizeof(u64); + + if (event->attr.read_format & PERF_FORMAT_GROUP) { + nr += event->group_leader->nr_siblings; + size += sizeof(u64); + } + + size += entry * nr; + event->read_size = size; +} + +static void perf_event__header_size(struct perf_event *event) +{ + struct perf_sample_data *data; + u64 sample_type = event->attr.sample_type; + u16 size = 0; + + perf_event__read_size(event); + + if (sample_type & PERF_SAMPLE_IP) + size += sizeof(data->ip); + + if (sample_type & PERF_SAMPLE_ADDR) + size += sizeof(data->addr); + + if (sample_type & PERF_SAMPLE_PERIOD) + size += sizeof(data->period); + + if (sample_type & PERF_SAMPLE_WEIGHT) + size += sizeof(data->weight); + + if (sample_type & PERF_SAMPLE_READ) + size += event->read_size; + + if (sample_type & PERF_SAMPLE_DATA_SRC) + size += sizeof(data->data_src.val); + + if (sample_type & PERF_SAMPLE_TRANSACTION) + size += sizeof(data->txn); + + event->header_size = size; +} + +static void perf_event__id_header_size(struct perf_event *event) +{ + struct perf_sample_data *data; + u64 sample_type = event->attr.sample_type; + u16 size = 0; + + if (sample_type & PERF_SAMPLE_TID) + size += sizeof(data->tid_entry); + + if (sample_type & PERF_SAMPLE_TIME) + size += sizeof(data->time); + + if (sample_type & PERF_SAMPLE_IDENTIFIER) + size += sizeof(data->id); + + if (sample_type & PERF_SAMPLE_ID) + size += sizeof(data->id); + + if (sample_type & PERF_SAMPLE_STREAM_ID) + size += sizeof(data->stream_id); + + if (sample_type & PERF_SAMPLE_CPU) + size += sizeof(data->cpu_entry); + + event->id_header_size = size; +} + +static void perf_group_attach(struct perf_event *event) +{ + struct perf_event *group_leader = event->group_leader, *pos; + + /* + * We can have double attach due to group movement in perf_event_open. + */ + if (event->attach_state & PERF_ATTACH_GROUP) + return; + + event->attach_state |= PERF_ATTACH_GROUP; + + if (group_leader == event) + return; + + WARN_ON_ONCE(group_leader->ctx != event->ctx); + + if (group_leader->group_flags & PERF_GROUP_SOFTWARE && + !is_software_event(event)) + group_leader->group_flags &= ~PERF_GROUP_SOFTWARE; + + list_add_tail(&event->group_entry, &group_leader->sibling_list); + group_leader->nr_siblings++; + + perf_event__header_size(group_leader); + + list_for_each_entry(pos, &group_leader->sibling_list, group_entry) + perf_event__header_size(pos); +} + +/* + * Remove a event from the lists for its context. + * Must be called with ctx->mutex and ctx->lock held. + */ +static void +list_del_event(struct perf_event *event, struct perf_event_context *ctx) +{ + struct perf_cpu_context *cpuctx; + + WARN_ON_ONCE(event->ctx != ctx); + lockdep_assert_held(&ctx->lock); + + /* + * We can have double detach due to exit/hot-unplug + close. + */ + if (!(event->attach_state & PERF_ATTACH_CONTEXT)) + return; + + event->attach_state &= ~PERF_ATTACH_CONTEXT; + + if (is_cgroup_event(event)) { + ctx->nr_cgroups--; + cpuctx = __get_cpu_context(ctx); + /* + * if there are no more cgroup events + * then cler cgrp to avoid stale pointer + * in update_cgrp_time_from_cpuctx() + */ + if (!ctx->nr_cgroups) + cpuctx->cgrp = NULL; + } + + ctx->nr_events--; + if (event->attr.inherit_stat) + ctx->nr_stat--; + + list_del_rcu(&event->event_entry); + + if (event->group_leader == event) + list_del_init(&event->group_entry); + + update_group_times(event); + + /* + * If event was in error state, then keep it + * that way, otherwise bogus counts will be + * returned on read(). The only way to get out + * of error state is by explicit re-enabling + * of the event + */ + if (event->state > PERF_EVENT_STATE_OFF) + event->state = PERF_EVENT_STATE_OFF; + + ctx->generation++; +} + +static void perf_group_detach(struct perf_event *event) +{ + struct perf_event *sibling, *tmp; + struct list_head *list = NULL; + + /* + * We can have double detach due to exit/hot-unplug + close. + */ + if (!(event->attach_state & PERF_ATTACH_GROUP)) + return; + + event->attach_state &= ~PERF_ATTACH_GROUP; + + /* + * If this is a sibling, remove it from its group. + */ + if (event->group_leader != event) { + list_del_init(&event->group_entry); + event->group_leader->nr_siblings--; + goto out; + } + + if (!list_empty(&event->group_entry)) + list = &event->group_entry; + + /* + * If this was a group event with sibling events then + * upgrade the siblings to singleton events by adding them + * to whatever list we are on. + */ + list_for_each_entry_safe(sibling, tmp, &event->sibling_list, group_entry) { + if (list) + list_move_tail(&sibling->group_entry, list); + sibling->group_leader = sibling; + + /* Inherit group flags from the previous leader */ + sibling->group_flags = event->group_flags; + + WARN_ON_ONCE(sibling->ctx != event->ctx); + } + +out: + perf_event__header_size(event->group_leader); + + list_for_each_entry(tmp, &event->group_leader->sibling_list, group_entry) + perf_event__header_size(tmp); +} + +/* + * User event without the task. + */ +static bool is_orphaned_event(struct perf_event *event) +{ + return event && !is_kernel_event(event) && !event->owner; +} + +/* + * Event has a parent but parent's task finished and it's + * alive only because of children holding refference. + */ +static bool is_orphaned_child(struct perf_event *event) +{ + return is_orphaned_event(event->parent); +} + +static void orphans_remove_work(struct work_struct *work); + +static void schedule_orphans_remove(struct perf_event_context *ctx) +{ + if (!ctx->task || ctx->orphans_remove_sched || !perf_wq) + return; + + if (queue_delayed_work(perf_wq, &ctx->orphans_remove, 1)) { + get_ctx(ctx); + ctx->orphans_remove_sched = true; + } +} + +static int __init perf_workqueue_init(void) +{ + perf_wq = create_singlethread_workqueue("perf"); + WARN(!perf_wq, "failed to create perf workqueue\n"); + return perf_wq ? 0 : -1; +} + +core_initcall(perf_workqueue_init); + +static inline int +event_filter_match(struct perf_event *event) +{ + return (event->cpu == -1 || event->cpu == smp_processor_id()) + && perf_cgroup_match(event); +} + +static void +event_sched_out(struct perf_event *event, + struct perf_cpu_context *cpuctx, + struct perf_event_context *ctx) +{ + u64 tstamp = perf_event_time(event); + u64 delta; + + WARN_ON_ONCE(event->ctx != ctx); + lockdep_assert_held(&ctx->lock); + + /* + * An event which could not be activated because of + * filter mismatch still needs to have its timings + * maintained, otherwise bogus information is return + * via read() for time_enabled, time_running: + */ + if (event->state == PERF_EVENT_STATE_INACTIVE + && !event_filter_match(event)) { + delta = tstamp - event->tstamp_stopped; + event->tstamp_running += delta; + event->tstamp_stopped = tstamp; + } + + if (event->state != PERF_EVENT_STATE_ACTIVE) + return; + + perf_pmu_disable(event->pmu); + + event->state = PERF_EVENT_STATE_INACTIVE; + if (event->pending_disable) { + event->pending_disable = 0; + event->state = PERF_EVENT_STATE_OFF; + } + event->tstamp_stopped = tstamp; + event->pmu->del(event, 0); + event->oncpu = -1; + + if (!is_software_event(event)) + cpuctx->active_oncpu--; + if (!--ctx->nr_active) + perf_event_ctx_deactivate(ctx); + if (event->attr.freq && event->attr.sample_freq) + ctx->nr_freq--; + if (event->attr.exclusive || !cpuctx->active_oncpu) + cpuctx->exclusive = 0; + + if (is_orphaned_child(event)) + schedule_orphans_remove(ctx); + + perf_pmu_enable(event->pmu); +} + +static void +group_sched_out(struct perf_event *group_event, + struct perf_cpu_context *cpuctx, + struct perf_event_context *ctx) +{ + struct perf_event *event; + int state = group_event->state; + + event_sched_out(group_event, cpuctx, ctx); + + /* + * Schedule out siblings (if any): + */ + list_for_each_entry(event, &group_event->sibling_list, group_entry) + event_sched_out(event, cpuctx, ctx); + + if (state == PERF_EVENT_STATE_ACTIVE && group_event->attr.exclusive) + cpuctx->exclusive = 0; +} + +struct remove_event { + struct perf_event *event; + bool detach_group; +}; + +/* + * Cross CPU call to remove a performance event + * + * We disable the event on the hardware level first. After that we + * remove it from the context list. + */ +static int __perf_remove_from_context(void *info) +{ + struct remove_event *re = info; + struct perf_event *event = re->event; + struct perf_event_context *ctx = event->ctx; + struct perf_cpu_context *cpuctx = __get_cpu_context(ctx); + + raw_spin_lock(&ctx->lock); + event_sched_out(event, cpuctx, ctx); + if (re->detach_group) + perf_group_detach(event); + list_del_event(event, ctx); + if (!ctx->nr_events && cpuctx->task_ctx == ctx) { + ctx->is_active = 0; + cpuctx->task_ctx = NULL; + } + raw_spin_unlock(&ctx->lock); + + return 0; +} + + +/* + * Remove the event from a task's (or a CPU's) list of events. + * + * CPU events are removed with a smp call. For task events we only + * call when the task is on a CPU. + * + * If event->ctx is a cloned context, callers must make sure that + * every task struct that event->ctx->task could possibly point to + * remains valid. This is OK when called from perf_release since + * that only calls us on the top-level context, which can't be a clone. + * When called from perf_event_exit_task, it's OK because the + * context has been detached from its task. + */ +static void perf_remove_from_context(struct perf_event *event, bool detach_group) +{ + struct perf_event_context *ctx = event->ctx; + struct task_struct *task = ctx->task; + struct remove_event re = { + .event = event, + .detach_group = detach_group, + }; + + lockdep_assert_held(&ctx->mutex); + + if (!task) { + /* + * Per cpu events are removed via an smp call. The removal can + * fail if the CPU is currently offline, but in that case we + * already called __perf_remove_from_context from + * perf_event_exit_cpu. + */ + cpu_function_call(event->cpu, __perf_remove_from_context, &re); + return; + } + +retry: + if (!task_function_call(task, __perf_remove_from_context, &re)) + return; + + raw_spin_lock_irq(&ctx->lock); + /* + * If we failed to find a running task, but find the context active now + * that we've acquired the ctx->lock, retry. + */ + if (ctx->is_active) { + raw_spin_unlock_irq(&ctx->lock); + /* + * Reload the task pointer, it might have been changed by + * a concurrent perf_event_context_sched_out(). + */ + task = ctx->task; + goto retry; + } + + /* + * Since the task isn't running, its safe to remove the event, us + * holding the ctx->lock ensures the task won't get scheduled in. + */ + if (detach_group) + perf_group_detach(event); + list_del_event(event, ctx); + raw_spin_unlock_irq(&ctx->lock); +} + +/* + * Cross CPU call to disable a performance event + */ +int __perf_event_disable(void *info) +{ + struct perf_event *event = info; + struct perf_event_context *ctx = event->ctx; + struct perf_cpu_context *cpuctx = __get_cpu_context(ctx); + + /* + * If this is a per-task event, need to check whether this + * event's task is the current task on this cpu. + * + * Can trigger due to concurrent perf_event_context_sched_out() + * flipping contexts around. + */ + if (ctx->task && cpuctx->task_ctx != ctx) + return -EINVAL; + + raw_spin_lock(&ctx->lock); + + /* + * If the event is on, turn it off. + * If it is in error state, leave it in error state. + */ + if (event->state >= PERF_EVENT_STATE_INACTIVE) { + update_context_time(ctx); + update_cgrp_time_from_event(event); + update_group_times(event); + if (event == event->group_leader) + group_sched_out(event, cpuctx, ctx); + else + event_sched_out(event, cpuctx, ctx); + event->state = PERF_EVENT_STATE_OFF; + } + + raw_spin_unlock(&ctx->lock); + + return 0; +} + +/* + * Disable a event. + * + * If event->ctx is a cloned context, callers must make sure that + * every task struct that event->ctx->task could possibly point to + * remains valid. This condition is satisifed when called through + * perf_event_for_each_child or perf_event_for_each because they + * hold the top-level event's child_mutex, so any descendant that + * goes to exit will block in sync_child_event. + * When called from perf_pending_event it's OK because event->ctx + * is the current context on this CPU and preemption is disabled, + * hence we can't get into perf_event_task_sched_out for this context. + */ +static void _perf_event_disable(struct perf_event *event) +{ + struct perf_event_context *ctx = event->ctx; + struct task_struct *task = ctx->task; + + if (!task) { + /* + * Disable the event on the cpu that it's on + */ + cpu_function_call(event->cpu, __perf_event_disable, event); + return; + } + +retry: + if (!task_function_call(task, __perf_event_disable, event)) + return; + + raw_spin_lock_irq(&ctx->lock); + /* + * If the event is still active, we need to retry the cross-call. + */ + if (event->state == PERF_EVENT_STATE_ACTIVE) { + raw_spin_unlock_irq(&ctx->lock); + /* + * Reload the task pointer, it might have been changed by + * a concurrent perf_event_context_sched_out(). + */ + task = ctx->task; + goto retry; + } + + /* + * Since we have the lock this context can't be scheduled + * in, so we can change the state safely. + */ + if (event->state == PERF_EVENT_STATE_INACTIVE) { + update_group_times(event); + event->state = PERF_EVENT_STATE_OFF; + } + raw_spin_unlock_irq(&ctx->lock); +} + +/* + * Strictly speaking kernel users cannot create groups and therefore this + * interface does not need the perf_event_ctx_lock() magic. + */ +void perf_event_disable(struct perf_event *event) +{ + struct perf_event_context *ctx; + + ctx = perf_event_ctx_lock(event); + _perf_event_disable(event); + perf_event_ctx_unlock(event, ctx); +} +EXPORT_SYMBOL_GPL(perf_event_disable); + +static void perf_set_shadow_time(struct perf_event *event, + struct perf_event_context *ctx, + u64 tstamp) +{ + /* + * use the correct time source for the time snapshot + * + * We could get by without this by leveraging the + * fact that to get to this function, the caller + * has most likely already called update_context_time() + * and update_cgrp_time_xx() and thus both timestamp + * are identical (or very close). Given that tstamp is, + * already adjusted for cgroup, we could say that: + * tstamp - ctx->timestamp + * is equivalent to + * tstamp - cgrp->timestamp. + * + * Then, in perf_output_read(), the calculation would + * work with no changes because: + * - event is guaranteed scheduled in + * - no scheduled out in between + * - thus the timestamp would be the same + * + * But this is a bit hairy. + * + * So instead, we have an explicit cgroup call to remain + * within the time time source all along. We believe it + * is cleaner and simpler to understand. + */ + if (is_cgroup_event(event)) + perf_cgroup_set_shadow_time(event, tstamp); + else + event->shadow_ctx_time = tstamp - ctx->timestamp; +} + +#define MAX_INTERRUPTS (~0ULL) + +static void perf_log_throttle(struct perf_event *event, int enable); +static void perf_log_itrace_start(struct perf_event *event); + +static int +event_sched_in(struct perf_event *event, + struct perf_cpu_context *cpuctx, + struct perf_event_context *ctx) +{ + u64 tstamp = perf_event_time(event); + int ret = 0; + + lockdep_assert_held(&ctx->lock); + + if (event->state <= PERF_EVENT_STATE_OFF) + return 0; + + event->state = PERF_EVENT_STATE_ACTIVE; + event->oncpu = smp_processor_id(); + + /* + * Unthrottle events, since we scheduled we might have missed several + * ticks already, also for a heavily scheduling task there is little + * guarantee it'll get a tick in a timely manner. + */ + if (unlikely(event->hw.interrupts == MAX_INTERRUPTS)) { + perf_log_throttle(event, 1); + event->hw.interrupts = 0; + } + + /* + * The new state must be visible before we turn it on in the hardware: + */ + smp_wmb(); + + perf_pmu_disable(event->pmu); + + event->tstamp_running += tstamp - event->tstamp_stopped; + + perf_set_shadow_time(event, ctx, tstamp); + + perf_log_itrace_start(event); + + if (event->pmu->add(event, PERF_EF_START)) { + event->state = PERF_EVENT_STATE_INACTIVE; + event->oncpu = -1; + ret = -EAGAIN; + goto out; + } + + if (!is_software_event(event)) + cpuctx->active_oncpu++; + if (!ctx->nr_active++) + perf_event_ctx_activate(ctx); + if (event->attr.freq && event->attr.sample_freq) + ctx->nr_freq++; + + if (event->attr.exclusive) + cpuctx->exclusive = 1; + + if (is_orphaned_child(event)) + schedule_orphans_remove(ctx); + +out: + perf_pmu_enable(event->pmu); + + return ret; +} + +static int +group_sched_in(struct perf_event *group_event, + struct perf_cpu_context *cpuctx, + struct perf_event_context *ctx) +{ + struct perf_event *event, *partial_group = NULL; + struct pmu *pmu = ctx->pmu; + u64 now = ctx->time; + bool simulate = false; + + if (group_event->state == PERF_EVENT_STATE_OFF) + return 0; + + pmu->start_txn(pmu); + + if (event_sched_in(group_event, cpuctx, ctx)) { + pmu->cancel_txn(pmu); + perf_cpu_hrtimer_restart(cpuctx); + return -EAGAIN; + } + + /* + * Schedule in siblings as one group (if any): + */ + list_for_each_entry(event, &group_event->sibling_list, group_entry) { + if (event_sched_in(event, cpuctx, ctx)) { + partial_group = event; + goto group_error; + } + } + + if (!pmu->commit_txn(pmu)) + return 0; + +group_error: + /* + * Groups can be scheduled in as one unit only, so undo any + * partial group before returning: + * The events up to the failed event are scheduled out normally, + * tstamp_stopped will be updated. + * + * The failed events and the remaining siblings need to have + * their timings updated as if they had gone thru event_sched_in() + * and event_sched_out(). This is required to get consistent timings + * across the group. This also takes care of the case where the group + * could never be scheduled by ensuring tstamp_stopped is set to mark + * the time the event was actually stopped, such that time delta + * calculation in update_event_times() is correct. + */ + list_for_each_entry(event, &group_event->sibling_list, group_entry) { + if (event == partial_group) + simulate = true; + + if (simulate) { + event->tstamp_running += now - event->tstamp_stopped; + event->tstamp_stopped = now; + } else { + event_sched_out(event, cpuctx, ctx); + } + } + event_sched_out(group_event, cpuctx, ctx); + + pmu->cancel_txn(pmu); + + perf_cpu_hrtimer_restart(cpuctx); + + return -EAGAIN; +} + +/* + * Work out whether we can put this event group on the CPU now. + */ +static int group_can_go_on(struct perf_event *event, + struct perf_cpu_context *cpuctx, + int can_add_hw) +{ + /* + * Groups consisting entirely of software events can always go on. + */ + if (event->group_flags & PERF_GROUP_SOFTWARE) + return 1; + /* + * If an exclusive group is already on, no other hardware + * events can go on. + */ + if (cpuctx->exclusive) + return 0; + /* + * If this group is exclusive and there are already + * events on the CPU, it can't go on. + */ + if (event->attr.exclusive && cpuctx->active_oncpu) + return 0; + /* + * Otherwise, try to add it if all previous groups were able + * to go on. + */ + return can_add_hw; +} + +static void add_event_to_ctx(struct perf_event *event, + struct perf_event_context *ctx) +{ + u64 tstamp = perf_event_time(event); + + list_add_event(event, ctx); + perf_group_attach(event); + event->tstamp_enabled = tstamp; + event->tstamp_running = tstamp; + event->tstamp_stopped = tstamp; +} + +static void task_ctx_sched_out(struct perf_event_context *ctx); +static void +ctx_sched_in(struct perf_event_context *ctx, + struct perf_cpu_context *cpuctx, + enum event_type_t event_type, + struct task_struct *task); + +static void perf_event_sched_in(struct perf_cpu_context *cpuctx, + struct perf_event_context *ctx, + struct task_struct *task) +{ + cpu_ctx_sched_in(cpuctx, EVENT_PINNED, task); + if (ctx) + ctx_sched_in(ctx, cpuctx, EVENT_PINNED, task); + cpu_ctx_sched_in(cpuctx, EVENT_FLEXIBLE, task); + if (ctx) + ctx_sched_in(ctx, cpuctx, EVENT_FLEXIBLE, task); +} + +/* + * Cross CPU call to install and enable a performance event + * + * Must be called with ctx->mutex held + */ +static int __perf_install_in_context(void *info) +{ + struct perf_event *event = info; + struct perf_event_context *ctx = event->ctx; + struct perf_cpu_context *cpuctx = __get_cpu_context(ctx); + struct perf_event_context *task_ctx = cpuctx->task_ctx; + struct task_struct *task = current; + + perf_ctx_lock(cpuctx, task_ctx); + perf_pmu_disable(cpuctx->ctx.pmu); + + /* + * If there was an active task_ctx schedule it out. + */ + if (task_ctx) + task_ctx_sched_out(task_ctx); + + /* + * If the context we're installing events in is not the + * active task_ctx, flip them. + */ + if (ctx->task && task_ctx != ctx) { + if (task_ctx) + raw_spin_unlock(&task_ctx->lock); + raw_spin_lock(&ctx->lock); + task_ctx = ctx; + } + + if (task_ctx) { + cpuctx->task_ctx = task_ctx; + task = task_ctx->task; + } + + cpu_ctx_sched_out(cpuctx, EVENT_ALL); + + update_context_time(ctx); + /* + * update cgrp time only if current cgrp + * matches event->cgrp. Must be done before + * calling add_event_to_ctx() + */ + update_cgrp_time_from_event(event); + + add_event_to_ctx(event, ctx); + + /* + * Schedule everything back in + */ + perf_event_sched_in(cpuctx, task_ctx, task); + + perf_pmu_enable(cpuctx->ctx.pmu); + perf_ctx_unlock(cpuctx, task_ctx); + + return 0; +} + +/* + * Attach a performance event to a context + * + * First we add the event to the list with the hardware enable bit + * in event->hw_config cleared. + * + * If the event is attached to a task which is on a CPU we use a smp + * call to enable it in the task context. The task might have been + * scheduled away, but we check this in the smp call again. + */ +static void +perf_install_in_context(struct perf_event_context *ctx, + struct perf_event *event, + int cpu) +{ + struct task_struct *task = ctx->task; + + lockdep_assert_held(&ctx->mutex); + + event->ctx = ctx; + if (event->cpu != -1) + event->cpu = cpu; + + if (!task) { + /* + * Per cpu events are installed via an smp call and + * the install is always successful. + */ + cpu_function_call(cpu, __perf_install_in_context, event); + return; + } + +retry: + if (!task_function_call(task, __perf_install_in_context, event)) + return; + + raw_spin_lock_irq(&ctx->lock); + /* + * If we failed to find a running task, but find the context active now + * that we've acquired the ctx->lock, retry. + */ + if (ctx->is_active) { + raw_spin_unlock_irq(&ctx->lock); + /* + * Reload the task pointer, it might have been changed by + * a concurrent perf_event_context_sched_out(). + */ + task = ctx->task; + goto retry; + } + + /* + * Since the task isn't running, its safe to add the event, us holding + * the ctx->lock ensures the task won't get scheduled in. + */ + add_event_to_ctx(event, ctx); + raw_spin_unlock_irq(&ctx->lock); +} + +/* + * Put a event into inactive state and update time fields. + * Enabling the leader of a group effectively enables all + * the group members that aren't explicitly disabled, so we + * have to update their ->tstamp_enabled also. + * Note: this works for group members as well as group leaders + * since the non-leader members' sibling_lists will be empty. + */ +static void __perf_event_mark_enabled(struct perf_event *event) +{ + struct perf_event *sub; + u64 tstamp = perf_event_time(event); + + event->state = PERF_EVENT_STATE_INACTIVE; + event->tstamp_enabled = tstamp - event->total_time_enabled; + list_for_each_entry(sub, &event->sibling_list, group_entry) { + if (sub->state >= PERF_EVENT_STATE_INACTIVE) + sub->tstamp_enabled = tstamp - sub->total_time_enabled; + } +} + +/* + * Cross CPU call to enable a performance event + */ +static int __perf_event_enable(void *info) +{ + struct perf_event *event = info; + struct perf_event_context *ctx = event->ctx; + struct perf_event *leader = event->group_leader; + struct perf_cpu_context *cpuctx = __get_cpu_context(ctx); + int err; + + /* + * There's a time window between 'ctx->is_active' check + * in perf_event_enable function and this place having: + * - IRQs on + * - ctx->lock unlocked + * + * where the task could be killed and 'ctx' deactivated + * by perf_event_exit_task. + */ + if (!ctx->is_active) + return -EINVAL; + + raw_spin_lock(&ctx->lock); + update_context_time(ctx); + + if (event->state >= PERF_EVENT_STATE_INACTIVE) + goto unlock; + + /* + * set current task's cgroup time reference point + */ + perf_cgroup_set_timestamp(current, ctx); + + __perf_event_mark_enabled(event); + + if (!event_filter_match(event)) { + if (is_cgroup_event(event)) + perf_cgroup_defer_enabled(event); + goto unlock; + } + + /* + * If the event is in a group and isn't the group leader, + * then don't put it on unless the group is on. + */ + if (leader != event && leader->state != PERF_EVENT_STATE_ACTIVE) + goto unlock; + + if (!group_can_go_on(event, cpuctx, 1)) { + err = -EEXIST; + } else { + if (event == leader) + err = group_sched_in(event, cpuctx, ctx); + else + err = event_sched_in(event, cpuctx, ctx); + } + + if (err) { + /* + * If this event can't go on and it's part of a + * group, then the whole group has to come off. + */ + if (leader != event) { + group_sched_out(leader, cpuctx, ctx); + perf_cpu_hrtimer_restart(cpuctx); + } + if (leader->attr.pinned) { + update_group_times(leader); + leader->state = PERF_EVENT_STATE_ERROR; + } + } + +unlock: + raw_spin_unlock(&ctx->lock); + + return 0; +} + +/* + * Enable a event. + * + * If event->ctx is a cloned context, callers must make sure that + * every task struct that event->ctx->task could possibly point to + * remains valid. This condition is satisfied when called through + * perf_event_for_each_child or perf_event_for_each as described + * for perf_event_disable. + */ +static void _perf_event_enable(struct perf_event *event) +{ + struct perf_event_context *ctx = event->ctx; + struct task_struct *task = ctx->task; + + if (!task) { + /* + * Enable the event on the cpu that it's on + */ + cpu_function_call(event->cpu, __perf_event_enable, event); + return; + } + + raw_spin_lock_irq(&ctx->lock); + if (event->state >= PERF_EVENT_STATE_INACTIVE) + goto out; + + /* + * If the event is in error state, clear that first. + * That way, if we see the event in error state below, we + * know that it has gone back into error state, as distinct + * from the task having been scheduled away before the + * cross-call arrived. + */ + if (event->state == PERF_EVENT_STATE_ERROR) + event->state = PERF_EVENT_STATE_OFF; + +retry: + if (!ctx->is_active) { + __perf_event_mark_enabled(event); + goto out; + } + + raw_spin_unlock_irq(&ctx->lock); + + if (!task_function_call(task, __perf_event_enable, event)) + return; + + raw_spin_lock_irq(&ctx->lock); + + /* + * If the context is active and the event is still off, + * we need to retry the cross-call. + */ + if (ctx->is_active && event->state == PERF_EVENT_STATE_OFF) { + /* + * task could have been flipped by a concurrent + * perf_event_context_sched_out() + */ + task = ctx->task; + goto retry; + } + +out: + raw_spin_unlock_irq(&ctx->lock); +} + +/* + * See perf_event_disable(); + */ +void perf_event_enable(struct perf_event *event) +{ + struct perf_event_context *ctx; + + ctx = perf_event_ctx_lock(event); + _perf_event_enable(event); + perf_event_ctx_unlock(event, ctx); +} +EXPORT_SYMBOL_GPL(perf_event_enable); + +static int _perf_event_refresh(struct perf_event *event, int refresh) +{ + /* + * not supported on inherited events + */ + if (event->attr.inherit || !is_sampling_event(event)) + return -EINVAL; + + atomic_add(refresh, &event->event_limit); + _perf_event_enable(event); + + return 0; +} + +/* + * See perf_event_disable() + */ +int perf_event_refresh(struct perf_event *event, int refresh) +{ + struct perf_event_context *ctx; + int ret; + + ctx = perf_event_ctx_lock(event); + ret = _perf_event_refresh(event, refresh); + perf_event_ctx_unlock(event, ctx); + + return ret; +} +EXPORT_SYMBOL_GPL(perf_event_refresh); + +static void ctx_sched_out(struct perf_event_context *ctx, + struct perf_cpu_context *cpuctx, + enum event_type_t event_type) +{ + struct perf_event *event; + int is_active = ctx->is_active; + + ctx->is_active &= ~event_type; + if (likely(!ctx->nr_events)) + return; + + update_context_time(ctx); + update_cgrp_time_from_cpuctx(cpuctx); + if (!ctx->nr_active) + return; + + perf_pmu_disable(ctx->pmu); + if ((is_active & EVENT_PINNED) && (event_type & EVENT_PINNED)) { + list_for_each_entry(event, &ctx->pinned_groups, group_entry) + group_sched_out(event, cpuctx, ctx); + } + + if ((is_active & EVENT_FLEXIBLE) && (event_type & EVENT_FLEXIBLE)) { + list_for_each_entry(event, &ctx->flexible_groups, group_entry) + group_sched_out(event, cpuctx, ctx); + } + perf_pmu_enable(ctx->pmu); +} + +/* + * Test whether two contexts are equivalent, i.e. whether they have both been + * cloned from the same version of the same context. + * + * Equivalence is measured using a generation number in the context that is + * incremented on each modification to it; see unclone_ctx(), list_add_event() + * and list_del_event(). + */ +static int context_equiv(struct perf_event_context *ctx1, + struct perf_event_context *ctx2) +{ + lockdep_assert_held(&ctx1->lock); + lockdep_assert_held(&ctx2->lock); + + /* Pinning disables the swap optimization */ + if (ctx1->pin_count || ctx2->pin_count) + return 0; + + /* If ctx1 is the parent of ctx2 */ + if (ctx1 == ctx2->parent_ctx && ctx1->generation == ctx2->parent_gen) + return 1; + + /* If ctx2 is the parent of ctx1 */ + if (ctx1->parent_ctx == ctx2 && ctx1->parent_gen == ctx2->generation) + return 1; + + /* + * If ctx1 and ctx2 have the same parent; we flatten the parent + * hierarchy, see perf_event_init_context(). + */ + if (ctx1->parent_ctx && ctx1->parent_ctx == ctx2->parent_ctx && + ctx1->parent_gen == ctx2->parent_gen) + return 1; + + /* Unmatched */ + return 0; +} + +static void __perf_event_sync_stat(struct perf_event *event, + struct perf_event *next_event) +{ + u64 value; + + if (!event->attr.inherit_stat) + return; + + /* + * Update the event value, we cannot use perf_event_read() + * because we're in the middle of a context switch and have IRQs + * disabled, which upsets smp_call_function_single(), however + * we know the event must be on the current CPU, therefore we + * don't need to use it. + */ + switch (event->state) { + case PERF_EVENT_STATE_ACTIVE: + event->pmu->read(event); + /* fall-through */ + + case PERF_EVENT_STATE_INACTIVE: + update_event_times(event); + break; + + default: + break; + } + + /* + * In order to keep per-task stats reliable we need to flip the event + * values when we flip the contexts. + */ + value = local64_read(&next_event->count); + value = local64_xchg(&event->count, value); + local64_set(&next_event->count, value); + + swap(event->total_time_enabled, next_event->total_time_enabled); + swap(event->total_time_running, next_event->total_time_running); + + /* + * Since we swizzled the values, update the user visible data too. + */ + perf_event_update_userpage(event); + perf_event_update_userpage(next_event); +} + +static void perf_event_sync_stat(struct perf_event_context *ctx, + struct perf_event_context *next_ctx) +{ + struct perf_event *event, *next_event; + + if (!ctx->nr_stat) + return; + + update_context_time(ctx); + + event = list_first_entry(&ctx->event_list, + struct perf_event, event_entry); + + next_event = list_first_entry(&next_ctx->event_list, + struct perf_event, event_entry); + + while (&event->event_entry != &ctx->event_list && + &next_event->event_entry != &next_ctx->event_list) { + + __perf_event_sync_stat(event, next_event); + + event = list_next_entry(event, event_entry); + next_event = list_next_entry(next_event, event_entry); + } +} + +static void perf_event_context_sched_out(struct task_struct *task, int ctxn, + struct task_struct *next) +{ + struct perf_event_context *ctx = task->perf_event_ctxp[ctxn]; + struct perf_event_context *next_ctx; + struct perf_event_context *parent, *next_parent; + struct perf_cpu_context *cpuctx; + int do_switch = 1; + + if (likely(!ctx)) + return; + + cpuctx = __get_cpu_context(ctx); + if (!cpuctx->task_ctx) + return; + + rcu_read_lock(); + next_ctx = next->perf_event_ctxp[ctxn]; + if (!next_ctx) + goto unlock; + + parent = rcu_dereference(ctx->parent_ctx); + next_parent = rcu_dereference(next_ctx->parent_ctx); + + /* If neither context have a parent context; they cannot be clones. */ + if (!parent && !next_parent) + goto unlock; + + if (next_parent == ctx || next_ctx == parent || next_parent == parent) { + /* + * Looks like the two contexts are clones, so we might be + * able to optimize the context switch. We lock both + * contexts and check that they are clones under the + * lock (including re-checking that neither has been + * uncloned in the meantime). It doesn't matter which + * order we take the locks because no other cpu could + * be trying to lock both of these tasks. + */ + raw_spin_lock(&ctx->lock); + raw_spin_lock_nested(&next_ctx->lock, SINGLE_DEPTH_NESTING); + if (context_equiv(ctx, next_ctx)) { + /* + * XXX do we need a memory barrier of sorts + * wrt to rcu_dereference() of perf_event_ctxp + */ + task->perf_event_ctxp[ctxn] = next_ctx; + next->perf_event_ctxp[ctxn] = ctx; + ctx->task = next; + next_ctx->task = task; + + swap(ctx->task_ctx_data, next_ctx->task_ctx_data); + + do_switch = 0; + + perf_event_sync_stat(ctx, next_ctx); + } + raw_spin_unlock(&next_ctx->lock); + raw_spin_unlock(&ctx->lock); + } +unlock: + rcu_read_unlock(); + + if (do_switch) { + raw_spin_lock(&ctx->lock); + ctx_sched_out(ctx, cpuctx, EVENT_ALL); + cpuctx->task_ctx = NULL; + raw_spin_unlock(&ctx->lock); + } +} + +void perf_sched_cb_dec(struct pmu *pmu) +{ + this_cpu_dec(perf_sched_cb_usages); +} + +void perf_sched_cb_inc(struct pmu *pmu) +{ + this_cpu_inc(perf_sched_cb_usages); +} + +/* + * This function provides the context switch callback to the lower code + * layer. It is invoked ONLY when the context switch callback is enabled. + */ +static void perf_pmu_sched_task(struct task_struct *prev, + struct task_struct *next, + bool sched_in) +{ + struct perf_cpu_context *cpuctx; + struct pmu *pmu; + unsigned long flags; + + if (prev == next) + return; + + local_irq_save(flags); + + rcu_read_lock(); + + list_for_each_entry_rcu(pmu, &pmus, entry) { + if (pmu->sched_task) { + cpuctx = this_cpu_ptr(pmu->pmu_cpu_context); + + perf_ctx_lock(cpuctx, cpuctx->task_ctx); + + perf_pmu_disable(pmu); + + pmu->sched_task(cpuctx->task_ctx, sched_in); + + perf_pmu_enable(pmu); + + perf_ctx_unlock(cpuctx, cpuctx->task_ctx); + } + } + + rcu_read_unlock(); + + local_irq_restore(flags); +} + +#define for_each_task_context_nr(ctxn) \ + for ((ctxn) = 0; (ctxn) < perf_nr_task_contexts; (ctxn)++) + +/* + * Called from scheduler to remove the events of the current task, + * with interrupts disabled. + * + * We stop each event and update the event value in event->count. + * + * This does not protect us against NMI, but disable() + * sets the disabled bit in the control field of event _before_ + * accessing the event control register. If a NMI hits, then it will + * not restart the event. + */ +void __perf_event_task_sched_out(struct task_struct *task, + struct task_struct *next) +{ + int ctxn; + + if (__this_cpu_read(perf_sched_cb_usages)) + perf_pmu_sched_task(task, next, false); + + for_each_task_context_nr(ctxn) + perf_event_context_sched_out(task, ctxn, next); + + /* + * if cgroup events exist on this CPU, then we need + * to check if we have to switch out PMU state. + * cgroup event are system-wide mode only + */ + if (atomic_read(this_cpu_ptr(&perf_cgroup_events))) + perf_cgroup_sched_out(task, next); +} + +static void task_ctx_sched_out(struct perf_event_context *ctx) +{ + struct perf_cpu_context *cpuctx = __get_cpu_context(ctx); + + if (!cpuctx->task_ctx) + return; + + if (WARN_ON_ONCE(ctx != cpuctx->task_ctx)) + return; + + ctx_sched_out(ctx, cpuctx, EVENT_ALL); + cpuctx->task_ctx = NULL; +} + +/* + * Called with IRQs disabled + */ +static void cpu_ctx_sched_out(struct perf_cpu_context *cpuctx, + enum event_type_t event_type) +{ + ctx_sched_out(&cpuctx->ctx, cpuctx, event_type); +} + +static void +ctx_pinned_sched_in(struct perf_event_context *ctx, + struct perf_cpu_context *cpuctx) +{ + struct perf_event *event; + + list_for_each_entry(event, &ctx->pinned_groups, group_entry) { + if (event->state <= PERF_EVENT_STATE_OFF) + continue; + if (!event_filter_match(event)) + continue; + + /* may need to reset tstamp_enabled */ + if (is_cgroup_event(event)) + perf_cgroup_mark_enabled(event, ctx); + + if (group_can_go_on(event, cpuctx, 1)) + group_sched_in(event, cpuctx, ctx); + + /* + * If this pinned group hasn't been scheduled, + * put it in error state. + */ + if (event->state == PERF_EVENT_STATE_INACTIVE) { + update_group_times(event); + event->state = PERF_EVENT_STATE_ERROR; + } + } +} + +static void +ctx_flexible_sched_in(struct perf_event_context *ctx, + struct perf_cpu_context *cpuctx) +{ + struct perf_event *event; + int can_add_hw = 1; + + list_for_each_entry(event, &ctx->flexible_groups, group_entry) { + /* Ignore events in OFF or ERROR state */ + if (event->state <= PERF_EVENT_STATE_OFF) + continue; + /* + * Listen to the 'cpu' scheduling filter constraint + * of events: + */ + if (!event_filter_match(event)) + continue; + + /* may need to reset tstamp_enabled */ + if (is_cgroup_event(event)) + perf_cgroup_mark_enabled(event, ctx); + + if (group_can_go_on(event, cpuctx, can_add_hw)) { + if (group_sched_in(event, cpuctx, ctx)) + can_add_hw = 0; + } + } +} + +static void +ctx_sched_in(struct perf_event_context *ctx, + struct perf_cpu_context *cpuctx, + enum event_type_t event_type, + struct task_struct *task) +{ + u64 now; + int is_active = ctx->is_active; + + ctx->is_active |= event_type; + if (likely(!ctx->nr_events)) + return; + + now = perf_clock(); + ctx->timestamp = now; + perf_cgroup_set_timestamp(task, ctx); + /* + * First go through the list and put on any pinned groups + * in order to give them the best chance of going on. + */ + if (!(is_active & EVENT_PINNED) && (event_type & EVENT_PINNED)) + ctx_pinned_sched_in(ctx, cpuctx); + + /* Then walk through the lower prio flexible groups */ + if (!(is_active & EVENT_FLEXIBLE) && (event_type & EVENT_FLEXIBLE)) + ctx_flexible_sched_in(ctx, cpuctx); +} + +static void cpu_ctx_sched_in(struct perf_cpu_context *cpuctx, + enum event_type_t event_type, + struct task_struct *task) +{ + struct perf_event_context *ctx = &cpuctx->ctx; + + ctx_sched_in(ctx, cpuctx, event_type, task); +} + +static void perf_event_context_sched_in(struct perf_event_context *ctx, + struct task_struct *task) +{ + struct perf_cpu_context *cpuctx; + + cpuctx = __get_cpu_context(ctx); + if (cpuctx->task_ctx == ctx) + return; + + perf_ctx_lock(cpuctx, ctx); + perf_pmu_disable(ctx->pmu); + /* + * We want to keep the following priority order: + * cpu pinned (that don't need to move), task pinned, + * cpu flexible, task flexible. + */ + cpu_ctx_sched_out(cpuctx, EVENT_FLEXIBLE); + + if (ctx->nr_events) + cpuctx->task_ctx = ctx; + + perf_event_sched_in(cpuctx, cpuctx->task_ctx, task); + + perf_pmu_enable(ctx->pmu); + perf_ctx_unlock(cpuctx, ctx); +} + +/* + * Called from scheduler to add the events of the current task + * with interrupts disabled. + * + * We restore the event value and then enable it. + * + * This does not protect us against NMI, but enable() + * sets the enabled bit in the control field of event _before_ + * accessing the event control register. If a NMI hits, then it will + * keep the event running. + */ +void __perf_event_task_sched_in(struct task_struct *prev, + struct task_struct *task) +{ + struct perf_event_context *ctx; + int ctxn; + + for_each_task_context_nr(ctxn) { + ctx = task->perf_event_ctxp[ctxn]; + if (likely(!ctx)) + continue; + + perf_event_context_sched_in(ctx, task); + } + /* + * if cgroup events exist on this CPU, then we need + * to check if we have to switch in PMU state. + * cgroup event are system-wide mode only + */ + if (atomic_read(this_cpu_ptr(&perf_cgroup_events))) + perf_cgroup_sched_in(prev, task); + + if (__this_cpu_read(perf_sched_cb_usages)) + perf_pmu_sched_task(prev, task, true); +} + +static u64 perf_calculate_period(struct perf_event *event, u64 nsec, u64 count) +{ + u64 frequency = event->attr.sample_freq; + u64 sec = NSEC_PER_SEC; + u64 divisor, dividend; + + int count_fls, nsec_fls, frequency_fls, sec_fls; + + count_fls = fls64(count); + nsec_fls = fls64(nsec); + frequency_fls = fls64(frequency); + sec_fls = 30; + + /* + * We got @count in @nsec, with a target of sample_freq HZ + * the target period becomes: + * + * @count * 10^9 + * period = ------------------- + * @nsec * sample_freq + * + */ + + /* + * Reduce accuracy by one bit such that @a and @b converge + * to a similar magnitude. + */ +#define REDUCE_FLS(a, b) \ +do { \ + if (a##_fls > b##_fls) { \ + a >>= 1; \ + a##_fls--; \ + } else { \ + b >>= 1; \ + b##_fls--; \ + } \ +} while (0) + + /* + * Reduce accuracy until either term fits in a u64, then proceed with + * the other, so that finally we can do a u64/u64 division. + */ + while (count_fls + sec_fls > 64 && nsec_fls + frequency_fls > 64) { + REDUCE_FLS(nsec, frequency); + REDUCE_FLS(sec, count); + } + + if (count_fls + sec_fls > 64) { + divisor = nsec * frequency; + + while (count_fls + sec_fls > 64) { + REDUCE_FLS(count, sec); + divisor >>= 1; + } + + dividend = count * sec; + } else { + dividend = count * sec; + + while (nsec_fls + frequency_fls > 64) { + REDUCE_FLS(nsec, frequency); + dividend >>= 1; + } + + divisor = nsec * frequency; + } + + if (!divisor) + return dividend; + + return div64_u64(dividend, divisor); +} + +static DEFINE_PER_CPU(int, perf_throttled_count); +static DEFINE_PER_CPU(u64, perf_throttled_seq); + +static void perf_adjust_period(struct perf_event *event, u64 nsec, u64 count, bool disable) +{ + struct hw_perf_event *hwc = &event->hw; + s64 period, sample_period; + s64 delta; + + period = perf_calculate_period(event, nsec, count); + + delta = (s64)(period - hwc->sample_period); + delta = (delta + 7) / 8; /* low pass filter */ + + sample_period = hwc->sample_period + delta; + + if (!sample_period) + sample_period = 1; + + hwc->sample_period = sample_period; + + if (local64_read(&hwc->period_left) > 8*sample_period) { + if (disable) + event->pmu->stop(event, PERF_EF_UPDATE); + + local64_set(&hwc->period_left, 0); + + if (disable) + event->pmu->start(event, PERF_EF_RELOAD); + } +} + +/* + * combine freq adjustment with unthrottling to avoid two passes over the + * events. At the same time, make sure, having freq events does not change + * the rate of unthrottling as that would introduce bias. + */ +static void perf_adjust_freq_unthr_context(struct perf_event_context *ctx, + int needs_unthr) +{ + struct perf_event *event; + struct hw_perf_event *hwc; + u64 now, period = TICK_NSEC; + s64 delta; + + /* + * only need to iterate over all events iff: + * - context have events in frequency mode (needs freq adjust) + * - there are events to unthrottle on this cpu + */ + if (!(ctx->nr_freq || needs_unthr)) + return; + + raw_spin_lock(&ctx->lock); + perf_pmu_disable(ctx->pmu); + + list_for_each_entry_rcu(event, &ctx->event_list, event_entry) { + if (event->state != PERF_EVENT_STATE_ACTIVE) + continue; + + if (!event_filter_match(event)) + continue; + + perf_pmu_disable(event->pmu); + + hwc = &event->hw; + + if (hwc->interrupts == MAX_INTERRUPTS) { + hwc->interrupts = 0; + perf_log_throttle(event, 1); + event->pmu->start(event, 0); + } + + if (!event->attr.freq || !event->attr.sample_freq) + goto next; + + /* + * stop the event and update event->count + */ + event->pmu->stop(event, PERF_EF_UPDATE); + + now = local64_read(&event->count); + delta = now - hwc->freq_count_stamp; + hwc->freq_count_stamp = now; + + /* + * restart the event + * reload only if value has changed + * we have stopped the event so tell that + * to perf_adjust_period() to avoid stopping it + * twice. + */ + if (delta > 0) + perf_adjust_period(event, period, delta, false); + + event->pmu->start(event, delta > 0 ? PERF_EF_RELOAD : 0); + next: + perf_pmu_enable(event->pmu); + } + + perf_pmu_enable(ctx->pmu); + raw_spin_unlock(&ctx->lock); +} + +/* + * Round-robin a context's events: + */ +static void rotate_ctx(struct perf_event_context *ctx) +{ + /* + * Rotate the first entry last of non-pinned groups. Rotation might be + * disabled by the inheritance code. + */ + if (!ctx->rotate_disable) + list_rotate_left(&ctx->flexible_groups); +} + +static int perf_rotate_context(struct perf_cpu_context *cpuctx) +{ + struct perf_event_context *ctx = NULL; + int rotate = 0; + + if (cpuctx->ctx.nr_events) { + if (cpuctx->ctx.nr_events != cpuctx->ctx.nr_active) + rotate = 1; + } + + ctx = cpuctx->task_ctx; + if (ctx && ctx->nr_events) { + if (ctx->nr_events != ctx->nr_active) + rotate = 1; + } + + if (!rotate) + goto done; + + perf_ctx_lock(cpuctx, cpuctx->task_ctx); + perf_pmu_disable(cpuctx->ctx.pmu); + + cpu_ctx_sched_out(cpuctx, EVENT_FLEXIBLE); + if (ctx) + ctx_sched_out(ctx, cpuctx, EVENT_FLEXIBLE); + + rotate_ctx(&cpuctx->ctx); + if (ctx) + rotate_ctx(ctx); + + perf_event_sched_in(cpuctx, ctx, current); + + perf_pmu_enable(cpuctx->ctx.pmu); + perf_ctx_unlock(cpuctx, cpuctx->task_ctx); +done: + + return rotate; +} + +#ifdef CONFIG_NO_HZ_FULL +bool perf_event_can_stop_tick(void) +{ + if (atomic_read(&nr_freq_events) || + __this_cpu_read(perf_throttled_count)) + return false; + else + return true; +} +#endif + +void perf_event_task_tick(void) +{ + struct list_head *head = this_cpu_ptr(&active_ctx_list); + struct perf_event_context *ctx, *tmp; + int throttled; + + WARN_ON(!irqs_disabled()); + + __this_cpu_inc(perf_throttled_seq); + throttled = __this_cpu_xchg(perf_throttled_count, 0); + + list_for_each_entry_safe(ctx, tmp, head, active_ctx_list) + perf_adjust_freq_unthr_context(ctx, throttled); +} + +static int event_enable_on_exec(struct perf_event *event, + struct perf_event_context *ctx) +{ + if (!event->attr.enable_on_exec) + return 0; + + event->attr.enable_on_exec = 0; + if (event->state >= PERF_EVENT_STATE_INACTIVE) + return 0; + + __perf_event_mark_enabled(event); + + return 1; +} + +/* + * Enable all of a task's events that have been marked enable-on-exec. + * This expects task == current. + */ +static void perf_event_enable_on_exec(struct perf_event_context *ctx) +{ + struct perf_event_context *clone_ctx = NULL; + struct perf_event *event; + unsigned long flags; + int enabled = 0; + int ret; + + local_irq_save(flags); + if (!ctx || !ctx->nr_events) + goto out; + + /* + * We must ctxsw out cgroup events to avoid conflict + * when invoking perf_task_event_sched_in() later on + * in this function. Otherwise we end up trying to + * ctxswin cgroup events which are already scheduled + * in. + */ + perf_cgroup_sched_out(current, NULL); + + raw_spin_lock(&ctx->lock); + task_ctx_sched_out(ctx); + + list_for_each_entry(event, &ctx->event_list, event_entry) { + ret = event_enable_on_exec(event, ctx); + if (ret) + enabled = 1; + } + + /* + * Unclone this context if we enabled any event. + */ + if (enabled) + clone_ctx = unclone_ctx(ctx); + + raw_spin_unlock(&ctx->lock); + + /* + * Also calls ctxswin for cgroup events, if any: + */ + perf_event_context_sched_in(ctx, ctx->task); +out: + local_irq_restore(flags); + + if (clone_ctx) + put_ctx(clone_ctx); +} + +void perf_event_exec(void) +{ + struct perf_event_context *ctx; + int ctxn; + + rcu_read_lock(); + for_each_task_context_nr(ctxn) { + ctx = current->perf_event_ctxp[ctxn]; + if (!ctx) + continue; + + perf_event_enable_on_exec(ctx); + } + rcu_read_unlock(); +} + +/* + * Cross CPU call to read the hardware event + */ +static void __perf_event_read(void *info) +{ + struct perf_event *event = info; + struct perf_event_context *ctx = event->ctx; + struct perf_cpu_context *cpuctx = __get_cpu_context(ctx); + + /* + * If this is a task context, we need to check whether it is + * the current task context of this cpu. If not it has been + * scheduled out before the smp call arrived. In that case + * event->count would have been updated to a recent sample + * when the event was scheduled out. + */ + if (ctx->task && cpuctx->task_ctx != ctx) + return; + + raw_spin_lock(&ctx->lock); + if (ctx->is_active) { + update_context_time(ctx); + update_cgrp_time_from_event(event); + } + update_event_times(event); + if (event->state == PERF_EVENT_STATE_ACTIVE) + event->pmu->read(event); + raw_spin_unlock(&ctx->lock); +} + +static inline u64 perf_event_count(struct perf_event *event) +{ + if (event->pmu->count) + return event->pmu->count(event); + + return __perf_event_count(event); +} + +static u64 perf_event_read(struct perf_event *event) +{ + /* + * If event is enabled and currently active on a CPU, update the + * value in the event structure: + */ + if (event->state == PERF_EVENT_STATE_ACTIVE) { + smp_call_function_single(event->oncpu, + __perf_event_read, event, 1); + } else if (event->state == PERF_EVENT_STATE_INACTIVE) { + struct perf_event_context *ctx = event->ctx; + unsigned long flags; + + raw_spin_lock_irqsave(&ctx->lock, flags); + /* + * may read while context is not active + * (e.g., thread is blocked), in that case + * we cannot update context time + */ + if (ctx->is_active) { + update_context_time(ctx); + update_cgrp_time_from_event(event); + } + update_event_times(event); + raw_spin_unlock_irqrestore(&ctx->lock, flags); + } + + return perf_event_count(event); +} + +/* + * Initialize the perf_event context in a task_struct: + */ +static void __perf_event_init_context(struct perf_event_context *ctx) +{ + raw_spin_lock_init(&ctx->lock); + mutex_init(&ctx->mutex); + INIT_LIST_HEAD(&ctx->active_ctx_list); + INIT_LIST_HEAD(&ctx->pinned_groups); + INIT_LIST_HEAD(&ctx->flexible_groups); + INIT_LIST_HEAD(&ctx->event_list); + atomic_set(&ctx->refcount, 1); + INIT_DELAYED_WORK(&ctx->orphans_remove, orphans_remove_work); +} + +static struct perf_event_context * +alloc_perf_context(struct pmu *pmu, struct task_struct *task) +{ + struct perf_event_context *ctx; + + ctx = kzalloc(sizeof(struct perf_event_context), GFP_KERNEL); + if (!ctx) + return NULL; + + __perf_event_init_context(ctx); + if (task) { + ctx->task = task; + get_task_struct(task); + } + ctx->pmu = pmu; + + return ctx; +} + +static struct task_struct * +find_lively_task_by_vpid(pid_t vpid) +{ + struct task_struct *task; + int err; + + rcu_read_lock(); + if (!vpid) + task = current; + else + task = find_task_by_vpid(vpid); + if (task) + get_task_struct(task); + rcu_read_unlock(); + + if (!task) + return ERR_PTR(-ESRCH); + + /* Reuse ptrace permission checks for now. */ + err = -EACCES; + if (!ptrace_may_access(task, PTRACE_MODE_READ)) + goto errout; + + return task; +errout: + put_task_struct(task); + return ERR_PTR(err); + +} + +/* + * Returns a matching context with refcount and pincount. + */ +static struct perf_event_context * +find_get_context(struct pmu *pmu, struct task_struct *task, + struct perf_event *event) +{ + struct perf_event_context *ctx, *clone_ctx = NULL; + struct perf_cpu_context *cpuctx; + void *task_ctx_data = NULL; + unsigned long flags; + int ctxn, err; + int cpu = event->cpu; + + if (!task) { + /* Must be root to operate on a CPU event: */ + if (perf_paranoid_cpu() && !capable(CAP_SYS_ADMIN)) + return ERR_PTR(-EACCES); + + /* + * We could be clever and allow to attach a event to an + * offline CPU and activate it when the CPU comes up, but + * that's for later. + */ + if (!cpu_online(cpu)) + return ERR_PTR(-ENODEV); + + cpuctx = per_cpu_ptr(pmu->pmu_cpu_context, cpu); + ctx = &cpuctx->ctx; + get_ctx(ctx); + ++ctx->pin_count; + + return ctx; + } + + err = -EINVAL; + ctxn = pmu->task_ctx_nr; + if (ctxn < 0) + goto errout; + + if (event->attach_state & PERF_ATTACH_TASK_DATA) { + task_ctx_data = kzalloc(pmu->task_ctx_size, GFP_KERNEL); + if (!task_ctx_data) { + err = -ENOMEM; + goto errout; + } + } + +retry: + ctx = perf_lock_task_context(task, ctxn, &flags); + if (ctx) { + clone_ctx = unclone_ctx(ctx); + ++ctx->pin_count; + + if (task_ctx_data && !ctx->task_ctx_data) { + ctx->task_ctx_data = task_ctx_data; + task_ctx_data = NULL; + } + raw_spin_unlock_irqrestore(&ctx->lock, flags); + + if (clone_ctx) + put_ctx(clone_ctx); + } else { + ctx = alloc_perf_context(pmu, task); + err = -ENOMEM; + if (!ctx) + goto errout; + + if (task_ctx_data) { + ctx->task_ctx_data = task_ctx_data; + task_ctx_data = NULL; + } + + err = 0; + mutex_lock(&task->perf_event_mutex); + /* + * If it has already passed perf_event_exit_task(). + * we must see PF_EXITING, it takes this mutex too. + */ + if (task->flags & PF_EXITING) + err = -ESRCH; + else if (task->perf_event_ctxp[ctxn]) + err = -EAGAIN; + else { + get_ctx(ctx); + ++ctx->pin_count; + rcu_assign_pointer(task->perf_event_ctxp[ctxn], ctx); + } + mutex_unlock(&task->perf_event_mutex); + + if (unlikely(err)) { + put_ctx(ctx); + + if (err == -EAGAIN) + goto retry; + goto errout; + } + } + + kfree(task_ctx_data); + return ctx; + +errout: + kfree(task_ctx_data); + return ERR_PTR(err); +} + +static void perf_event_free_filter(struct perf_event *event); +static void perf_event_free_bpf_prog(struct perf_event *event); + +static void free_event_rcu(struct rcu_head *head) +{ + struct perf_event *event; + + event = container_of(head, struct perf_event, rcu_head); + if (event->ns) + put_pid_ns(event->ns); + perf_event_free_filter(event); + kfree(event); +} + +static void ring_buffer_attach(struct perf_event *event, + struct ring_buffer *rb); + +static void unaccount_event_cpu(struct perf_event *event, int cpu) +{ + if (event->parent) + return; + + if (is_cgroup_event(event)) + atomic_dec(&per_cpu(perf_cgroup_events, cpu)); +} + +static void unaccount_event(struct perf_event *event) +{ + if (event->parent) + return; + + if (event->attach_state & PERF_ATTACH_TASK) + static_key_slow_dec_deferred(&perf_sched_events); + if (event->attr.mmap || event->attr.mmap_data) + atomic_dec(&nr_mmap_events); + if (event->attr.comm) + atomic_dec(&nr_comm_events); + if (event->attr.task) + atomic_dec(&nr_task_events); + if (event->attr.freq) + atomic_dec(&nr_freq_events); + if (is_cgroup_event(event)) + static_key_slow_dec_deferred(&perf_sched_events); + if (has_branch_stack(event)) + static_key_slow_dec_deferred(&perf_sched_events); + + unaccount_event_cpu(event, event->cpu); +} + +/* + * The following implement mutual exclusion of events on "exclusive" pmus + * (PERF_PMU_CAP_EXCLUSIVE). Such pmus can only have one event scheduled + * at a time, so we disallow creating events that might conflict, namely: + * + * 1) cpu-wide events in the presence of per-task events, + * 2) per-task events in the presence of cpu-wide events, + * 3) two matching events on the same context. + * + * The former two cases are handled in the allocation path (perf_event_alloc(), + * __free_event()), the latter -- before the first perf_install_in_context(). + */ +static int exclusive_event_init(struct perf_event *event) +{ + struct pmu *pmu = event->pmu; + + if (!(pmu->capabilities & PERF_PMU_CAP_EXCLUSIVE)) + return 0; + + /* + * Prevent co-existence of per-task and cpu-wide events on the + * same exclusive pmu. + * + * Negative pmu::exclusive_cnt means there are cpu-wide + * events on this "exclusive" pmu, positive means there are + * per-task events. + * + * Since this is called in perf_event_alloc() path, event::ctx + * doesn't exist yet; it is, however, safe to use PERF_ATTACH_TASK + * to mean "per-task event", because unlike other attach states it + * never gets cleared. + */ + if (event->attach_state & PERF_ATTACH_TASK) { + if (!atomic_inc_unless_negative(&pmu->exclusive_cnt)) + return -EBUSY; + } else { + if (!atomic_dec_unless_positive(&pmu->exclusive_cnt)) + return -EBUSY; + } + + return 0; +} + +static void exclusive_event_destroy(struct perf_event *event) +{ + struct pmu *pmu = event->pmu; + + if (!(pmu->capabilities & PERF_PMU_CAP_EXCLUSIVE)) + return; + + /* see comment in exclusive_event_init() */ + if (event->attach_state & PERF_ATTACH_TASK) + atomic_dec(&pmu->exclusive_cnt); + else + atomic_inc(&pmu->exclusive_cnt); +} + +static bool exclusive_event_match(struct perf_event *e1, struct perf_event *e2) +{ + if ((e1->pmu->capabilities & PERF_PMU_CAP_EXCLUSIVE) && + (e1->cpu == e2->cpu || + e1->cpu == -1 || + e2->cpu == -1)) + return true; + return false; +} + +/* Called under the same ctx::mutex as perf_install_in_context() */ +static bool exclusive_event_installable(struct perf_event *event, + struct perf_event_context *ctx) +{ + struct perf_event *iter_event; + struct pmu *pmu = event->pmu; + + if (!(pmu->capabilities & PERF_PMU_CAP_EXCLUSIVE)) + return true; + + list_for_each_entry(iter_event, &ctx->event_list, event_entry) { + if (exclusive_event_match(iter_event, event)) + return false; + } + + return true; +} + +static void __free_event(struct perf_event *event) +{ + if (!event->parent) { + if (event->attr.sample_type & PERF_SAMPLE_CALLCHAIN) + put_callchain_buffers(); + } + + perf_event_free_bpf_prog(event); + + if (event->destroy) + event->destroy(event); + + if (event->ctx) + put_ctx(event->ctx); + + if (event->pmu) { + exclusive_event_destroy(event); + module_put(event->pmu->module); + } + + call_rcu(&event->rcu_head, free_event_rcu); +} + +static void _free_event(struct perf_event *event) +{ + irq_work_sync(&event->pending); + + unaccount_event(event); + + if (event->rb) { + /* + * Can happen when we close an event with re-directed output. + * + * Since we have a 0 refcount, perf_mmap_close() will skip + * over us; possibly making our ring_buffer_put() the last. + */ + mutex_lock(&event->mmap_mutex); + ring_buffer_attach(event, NULL); + mutex_unlock(&event->mmap_mutex); + } + + if (is_cgroup_event(event)) + perf_detach_cgroup(event); + + __free_event(event); +} + +/* + * Used to free events which have a known refcount of 1, such as in error paths + * where the event isn't exposed yet and inherited events. + */ +static void free_event(struct perf_event *event) +{ + if (WARN(atomic_long_cmpxchg(&event->refcount, 1, 0) != 1, + "unexpected event refcount: %ld; ptr=%p\n", + atomic_long_read(&event->refcount), event)) { + /* leak to avoid use-after-free */ + return; + } + + _free_event(event); +} + +/* + * Remove user event from the owner task. + */ +static void perf_remove_from_owner(struct perf_event *event) +{ + struct task_struct *owner; + + rcu_read_lock(); + owner = ACCESS_ONCE(event->owner); + /* + * Matches the smp_wmb() in perf_event_exit_task(). If we observe + * !owner it means the list deletion is complete and we can indeed + * free this event, otherwise we need to serialize on + * owner->perf_event_mutex. + */ + smp_read_barrier_depends(); + if (owner) { + /* + * Since delayed_put_task_struct() also drops the last + * task reference we can safely take a new reference + * while holding the rcu_read_lock(). + */ + get_task_struct(owner); + } + rcu_read_unlock(); + + if (owner) { + /* + * If we're here through perf_event_exit_task() we're already + * holding ctx->mutex which would be an inversion wrt. the + * normal lock order. + * + * However we can safely take this lock because its the child + * ctx->mutex. + */ + mutex_lock_nested(&owner->perf_event_mutex, SINGLE_DEPTH_NESTING); + + /* + * We have to re-check the event->owner field, if it is cleared + * we raced with perf_event_exit_task(), acquiring the mutex + * ensured they're done, and we can proceed with freeing the + * event. + */ + if (event->owner) + list_del_init(&event->owner_entry); + mutex_unlock(&owner->perf_event_mutex); + put_task_struct(owner); + } +} + +static void put_event(struct perf_event *event) +{ + struct perf_event_context *ctx; + + if (!atomic_long_dec_and_test(&event->refcount)) + return; + + if (!is_kernel_event(event)) + perf_remove_from_owner(event); + + /* + * There are two ways this annotation is useful: + * + * 1) there is a lock recursion from perf_event_exit_task + * see the comment there. + * + * 2) there is a lock-inversion with mmap_sem through + * perf_event_read_group(), which takes faults while + * holding ctx->mutex, however this is called after + * the last filedesc died, so there is no possibility + * to trigger the AB-BA case. + */ + ctx = perf_event_ctx_lock_nested(event, SINGLE_DEPTH_NESTING); + WARN_ON_ONCE(ctx->parent_ctx); + perf_remove_from_context(event, true); + perf_event_ctx_unlock(event, ctx); + + _free_event(event); +} + +int perf_event_release_kernel(struct perf_event *event) +{ + put_event(event); + return 0; +} +EXPORT_SYMBOL_GPL(perf_event_release_kernel); + +/* + * Called when the last reference to the file is gone. + */ +static int perf_release(struct inode *inode, struct file *file) +{ + put_event(file->private_data); + return 0; +} + +/* + * Remove all orphanes events from the context. + */ +static void orphans_remove_work(struct work_struct *work) +{ + struct perf_event_context *ctx; + struct perf_event *event, *tmp; + + ctx = container_of(work, struct perf_event_context, + orphans_remove.work); + + mutex_lock(&ctx->mutex); + list_for_each_entry_safe(event, tmp, &ctx->event_list, event_entry) { + struct perf_event *parent_event = event->parent; + + if (!is_orphaned_child(event)) + continue; + + perf_remove_from_context(event, true); + + mutex_lock(&parent_event->child_mutex); + list_del_init(&event->child_list); + mutex_unlock(&parent_event->child_mutex); + + free_event(event); + put_event(parent_event); + } + + raw_spin_lock_irq(&ctx->lock); + ctx->orphans_remove_sched = false; + raw_spin_unlock_irq(&ctx->lock); + mutex_unlock(&ctx->mutex); + + put_ctx(ctx); +} + +u64 perf_event_read_value(struct perf_event *event, u64 *enabled, u64 *running) +{ + struct perf_event *child; + u64 total = 0; + + *enabled = 0; + *running = 0; + + mutex_lock(&event->child_mutex); + total += perf_event_read(event); + *enabled += event->total_time_enabled + + atomic64_read(&event->child_total_time_enabled); + *running += event->total_time_running + + atomic64_read(&event->child_total_time_running); + + list_for_each_entry(child, &event->child_list, child_list) { + total += perf_event_read(child); + *enabled += child->total_time_enabled; + *running += child->total_time_running; + } + mutex_unlock(&event->child_mutex); + + return total; +} +EXPORT_SYMBOL_GPL(perf_event_read_value); + +static int perf_event_read_group(struct perf_event *event, + u64 read_format, char __user *buf) +{ + struct perf_event *leader = event->group_leader, *sub; + struct perf_event_context *ctx = leader->ctx; + int n = 0, size = 0, ret; + u64 count, enabled, running; + u64 values[5]; + + lockdep_assert_held(&ctx->mutex); + + count = perf_event_read_value(leader, &enabled, &running); + + values[n++] = 1 + leader->nr_siblings; + if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) + values[n++] = enabled; + if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) + values[n++] = running; + values[n++] = count; + if (read_format & PERF_FORMAT_ID) + values[n++] = primary_event_id(leader); + + size = n * sizeof(u64); + + if (copy_to_user(buf, values, size)) + return -EFAULT; + + ret = size; + + list_for_each_entry(sub, &leader->sibling_list, group_entry) { + n = 0; + + values[n++] = perf_event_read_value(sub, &enabled, &running); + if (read_format & PERF_FORMAT_ID) + values[n++] = primary_event_id(sub); + + size = n * sizeof(u64); + + if (copy_to_user(buf + ret, values, size)) { + return -EFAULT; + } + + ret += size; + } + + return ret; +} + +static int perf_event_read_one(struct perf_event *event, + u64 read_format, char __user *buf) +{ + u64 enabled, running; + u64 values[4]; + int n = 0; + + values[n++] = perf_event_read_value(event, &enabled, &running); + if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) + values[n++] = enabled; + if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) + values[n++] = running; + if (read_format & PERF_FORMAT_ID) + values[n++] = primary_event_id(event); + + if (copy_to_user(buf, values, n * sizeof(u64))) + return -EFAULT; + + return n * sizeof(u64); +} + +static bool is_event_hup(struct perf_event *event) +{ + bool no_children; + + if (event->state != PERF_EVENT_STATE_EXIT) + return false; + + mutex_lock(&event->child_mutex); + no_children = list_empty(&event->child_list); + mutex_unlock(&event->child_mutex); + return no_children; +} + +/* + * Read the performance event - simple non blocking version for now + */ +static ssize_t +perf_read_hw(struct perf_event *event, char __user *buf, size_t count) +{ + u64 read_format = event->attr.read_format; + int ret; + + /* + * Return end-of-file for a read on a event that is in + * error state (i.e. because it was pinned but it couldn't be + * scheduled on to the CPU at some point). + */ + if (event->state == PERF_EVENT_STATE_ERROR) + return 0; + + if (count < event->read_size) + return -ENOSPC; + + WARN_ON_ONCE(event->ctx->parent_ctx); + if (read_format & PERF_FORMAT_GROUP) + ret = perf_event_read_group(event, read_format, buf); + else + ret = perf_event_read_one(event, read_format, buf); + + return ret; +} + +static ssize_t +perf_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) +{ + struct perf_event *event = file->private_data; + struct perf_event_context *ctx; + int ret; + + ctx = perf_event_ctx_lock(event); + ret = perf_read_hw(event, buf, count); + perf_event_ctx_unlock(event, ctx); + + return ret; +} + +static unsigned int perf_poll(struct file *file, poll_table *wait) +{ + struct perf_event *event = file->private_data; + struct ring_buffer *rb; + unsigned int events = POLLHUP; + + poll_wait(file, &event->waitq, wait); + + if (is_event_hup(event)) + return events; + + /* + * Pin the event->rb by taking event->mmap_mutex; otherwise + * perf_event_set_output() can swizzle our rb and make us miss wakeups. + */ + mutex_lock(&event->mmap_mutex); + rb = event->rb; + if (rb) + events = atomic_xchg(&rb->poll, 0); + mutex_unlock(&event->mmap_mutex); + return events; +} + +static void _perf_event_reset(struct perf_event *event) +{ + (void)perf_event_read(event); + local64_set(&event->count, 0); + perf_event_update_userpage(event); +} + +/* + * Holding the top-level event's child_mutex means that any + * descendant process that has inherited this event will block + * in sync_child_event if it goes to exit, thus satisfying the + * task existence requirements of perf_event_enable/disable. + */ +static void perf_event_for_each_child(struct perf_event *event, + void (*func)(struct perf_event *)) +{ + struct perf_event *child; + + WARN_ON_ONCE(event->ctx->parent_ctx); + + mutex_lock(&event->child_mutex); + func(event); + list_for_each_entry(child, &event->child_list, child_list) + func(child); + mutex_unlock(&event->child_mutex); +} + +static void perf_event_for_each(struct perf_event *event, + void (*func)(struct perf_event *)) +{ + struct perf_event_context *ctx = event->ctx; + struct perf_event *sibling; + + lockdep_assert_held(&ctx->mutex); + + event = event->group_leader; + + perf_event_for_each_child(event, func); + list_for_each_entry(sibling, &event->sibling_list, group_entry) + perf_event_for_each_child(sibling, func); +} + +static int perf_event_period(struct perf_event *event, u64 __user *arg) +{ + struct perf_event_context *ctx = event->ctx; + int ret = 0, active; + u64 value; + + if (!is_sampling_event(event)) + return -EINVAL; + + if (copy_from_user(&value, arg, sizeof(value))) + return -EFAULT; + + if (!value) + return -EINVAL; + + raw_spin_lock_irq(&ctx->lock); + if (event->attr.freq) { + if (value > sysctl_perf_event_sample_rate) { + ret = -EINVAL; + goto unlock; + } + + event->attr.sample_freq = value; + } else { + event->attr.sample_period = value; + event->hw.sample_period = value; + } + + active = (event->state == PERF_EVENT_STATE_ACTIVE); + if (active) { + perf_pmu_disable(ctx->pmu); + event->pmu->stop(event, PERF_EF_UPDATE); + } + + local64_set(&event->hw.period_left, 0); + + if (active) { + event->pmu->start(event, PERF_EF_RELOAD); + perf_pmu_enable(ctx->pmu); + } + +unlock: + raw_spin_unlock_irq(&ctx->lock); + + return ret; +} + +static const struct file_operations perf_fops; + +static inline int perf_fget_light(int fd, struct fd *p) +{ + struct fd f = fdget(fd); + if (!f.file) + return -EBADF; + + if (f.file->f_op != &perf_fops) { + fdput(f); + return -EBADF; + } + *p = f; + return 0; +} + +static int perf_event_set_output(struct perf_event *event, + struct perf_event *output_event); +static int perf_event_set_filter(struct perf_event *event, void __user *arg); +static int perf_event_set_bpf_prog(struct perf_event *event, u32 prog_fd); + +static long _perf_ioctl(struct perf_event *event, unsigned int cmd, unsigned long arg) +{ + void (*func)(struct perf_event *); + u32 flags = arg; + + switch (cmd) { + case PERF_EVENT_IOC_ENABLE: + func = _perf_event_enable; + break; + case PERF_EVENT_IOC_DISABLE: + func = _perf_event_disable; + break; + case PERF_EVENT_IOC_RESET: + func = _perf_event_reset; + break; + + case PERF_EVENT_IOC_REFRESH: + return _perf_event_refresh(event, arg); + + case PERF_EVENT_IOC_PERIOD: + return perf_event_period(event, (u64 __user *)arg); + + case PERF_EVENT_IOC_ID: + { + u64 id = primary_event_id(event); + + if (copy_to_user((void __user *)arg, &id, sizeof(id))) + return -EFAULT; + return 0; + } + + case PERF_EVENT_IOC_SET_OUTPUT: + { + int ret; + if (arg != -1) { + struct perf_event *output_event; + struct fd output; + ret = perf_fget_light(arg, &output); + if (ret) + return ret; + output_event = output.file->private_data; + ret = perf_event_set_output(event, output_event); + fdput(output); + } else { + ret = perf_event_set_output(event, NULL); + } + return ret; + } + + case PERF_EVENT_IOC_SET_FILTER: + return perf_event_set_filter(event, (void __user *)arg); + + case PERF_EVENT_IOC_SET_BPF: + return perf_event_set_bpf_prog(event, arg); + + default: + return -ENOTTY; + } + + if (flags & PERF_IOC_FLAG_GROUP) + perf_event_for_each(event, func); + else + perf_event_for_each_child(event, func); + + return 0; +} + +static long perf_ioctl(struct file *file, unsigned int cmd, unsigned long arg) +{ + struct perf_event *event = file->private_data; + struct perf_event_context *ctx; + long ret; + + ctx = perf_event_ctx_lock(event); + ret = _perf_ioctl(event, cmd, arg); + perf_event_ctx_unlock(event, ctx); + + return ret; +} + +#ifdef CONFIG_COMPAT +static long perf_compat_ioctl(struct file *file, unsigned int cmd, + unsigned long arg) +{ + switch (_IOC_NR(cmd)) { + case _IOC_NR(PERF_EVENT_IOC_SET_FILTER): + case _IOC_NR(PERF_EVENT_IOC_ID): + /* Fix up pointer size (usually 4 -> 8 in 32-on-64-bit case */ + if (_IOC_SIZE(cmd) == sizeof(compat_uptr_t)) { + cmd &= ~IOCSIZE_MASK; + cmd |= sizeof(void *) << IOCSIZE_SHIFT; + } + break; + } + return perf_ioctl(file, cmd, arg); +} +#else +# define perf_compat_ioctl NULL +#endif + +int perf_event_task_enable(void) +{ + struct perf_event_context *ctx; + struct perf_event *event; + + mutex_lock(¤t->perf_event_mutex); + list_for_each_entry(event, ¤t->perf_event_list, owner_entry) { + ctx = perf_event_ctx_lock(event); + perf_event_for_each_child(event, _perf_event_enable); + perf_event_ctx_unlock(event, ctx); + } + mutex_unlock(¤t->perf_event_mutex); + + return 0; +} + +int perf_event_task_disable(void) +{ + struct perf_event_context *ctx; + struct perf_event *event; + + mutex_lock(¤t->perf_event_mutex); + list_for_each_entry(event, ¤t->perf_event_list, owner_entry) { + ctx = perf_event_ctx_lock(event); + perf_event_for_each_child(event, _perf_event_disable); + perf_event_ctx_unlock(event, ctx); + } + mutex_unlock(¤t->perf_event_mutex); + + return 0; +} + +static int perf_event_index(struct perf_event *event) +{ + if (event->hw.state & PERF_HES_STOPPED) + return 0; + + if (event->state != PERF_EVENT_STATE_ACTIVE) + return 0; + + return event->pmu->event_idx(event); +} + +static void calc_timer_values(struct perf_event *event, + u64 *now, + u64 *enabled, + u64 *running) +{ + u64 ctx_time; + + *now = perf_clock(); + ctx_time = event->shadow_ctx_time + *now; + *enabled = ctx_time - event->tstamp_enabled; + *running = ctx_time - event->tstamp_running; +} + +static void perf_event_init_userpage(struct perf_event *event) +{ + struct perf_event_mmap_page *userpg; + struct ring_buffer *rb; + + rcu_read_lock(); + rb = rcu_dereference(event->rb); + if (!rb) + goto unlock; + + userpg = rb->user_page; + + /* Allow new userspace to detect that bit 0 is deprecated */ + userpg->cap_bit0_is_deprecated = 1; + userpg->size = offsetof(struct perf_event_mmap_page, __reserved); + userpg->data_offset = PAGE_SIZE; + userpg->data_size = perf_data_size(rb); + +unlock: + rcu_read_unlock(); +} + +void __weak arch_perf_update_userpage( + struct perf_event *event, struct perf_event_mmap_page *userpg, u64 now) +{ +} + +/* + * Callers need to ensure there can be no nesting of this function, otherwise + * the seqlock logic goes bad. We can not serialize this because the arch + * code calls this from NMI context. + */ +void perf_event_update_userpage(struct perf_event *event) +{ + struct perf_event_mmap_page *userpg; + struct ring_buffer *rb; + u64 enabled, running, now; + + rcu_read_lock(); + rb = rcu_dereference(event->rb); + if (!rb) + goto unlock; + + /* + * compute total_time_enabled, total_time_running + * based on snapshot values taken when the event + * was last scheduled in. + * + * we cannot simply called update_context_time() + * because of locking issue as we can be called in + * NMI context + */ + calc_timer_values(event, &now, &enabled, &running); + + userpg = rb->user_page; + /* + * Disable preemption so as to not let the corresponding user-space + * spin too long if we get preempted. + */ + preempt_disable(); + ++userpg->lock; + barrier(); + userpg->index = perf_event_index(event); + userpg->offset = perf_event_count(event); + if (userpg->index) + userpg->offset -= local64_read(&event->hw.prev_count); + + userpg->time_enabled = enabled + + atomic64_read(&event->child_total_time_enabled); + + userpg->time_running = running + + atomic64_read(&event->child_total_time_running); + + arch_perf_update_userpage(event, userpg, now); + + barrier(); + ++userpg->lock; + preempt_enable(); +unlock: + rcu_read_unlock(); +} + +static int perf_mmap_fault(struct vm_area_struct *vma, struct vm_fault *vmf) +{ + struct perf_event *event = vma->vm_file->private_data; + struct ring_buffer *rb; + int ret = VM_FAULT_SIGBUS; + + if (vmf->flags & FAULT_FLAG_MKWRITE) { + if (vmf->pgoff == 0) + ret = 0; + return ret; + } + + rcu_read_lock(); + rb = rcu_dereference(event->rb); + if (!rb) + goto unlock; + + if (vmf->pgoff && (vmf->flags & FAULT_FLAG_WRITE)) + goto unlock; + + vmf->page = perf_mmap_to_page(rb, vmf->pgoff); + if (!vmf->page) + goto unlock; + + get_page(vmf->page); + vmf->page->mapping = vma->vm_file->f_mapping; + vmf->page->index = vmf->pgoff; + + ret = 0; +unlock: + rcu_read_unlock(); + + return ret; +} + +static void ring_buffer_attach(struct perf_event *event, + struct ring_buffer *rb) +{ + struct ring_buffer *old_rb = NULL; + unsigned long flags; + + if (event->rb) { + /* + * Should be impossible, we set this when removing + * event->rb_entry and wait/clear when adding event->rb_entry. + */ + WARN_ON_ONCE(event->rcu_pending); + + old_rb = event->rb; + spin_lock_irqsave(&old_rb->event_lock, flags); + list_del_rcu(&event->rb_entry); + spin_unlock_irqrestore(&old_rb->event_lock, flags); + + event->rcu_batches = get_state_synchronize_rcu(); + event->rcu_pending = 1; + } + + if (rb) { + if (event->rcu_pending) { + cond_synchronize_rcu(event->rcu_batches); + event->rcu_pending = 0; + } + + spin_lock_irqsave(&rb->event_lock, flags); + list_add_rcu(&event->rb_entry, &rb->event_list); + spin_unlock_irqrestore(&rb->event_lock, flags); + } + + rcu_assign_pointer(event->rb, rb); + + if (old_rb) { + ring_buffer_put(old_rb); + /* + * Since we detached before setting the new rb, so that we + * could attach the new rb, we could have missed a wakeup. + * Provide it now. + */ + wake_up_all(&event->waitq); + } +} + +static void ring_buffer_wakeup(struct perf_event *event) +{ + struct ring_buffer *rb; + + rcu_read_lock(); + rb = rcu_dereference(event->rb); + if (rb) { + list_for_each_entry_rcu(event, &rb->event_list, rb_entry) + wake_up_all(&event->waitq); + } + rcu_read_unlock(); +} + +static void rb_free_rcu(struct rcu_head *rcu_head) +{ + struct ring_buffer *rb; + + rb = container_of(rcu_head, struct ring_buffer, rcu_head); + rb_free(rb); +} + +struct ring_buffer *ring_buffer_get(struct perf_event *event) +{ + struct ring_buffer *rb; + + rcu_read_lock(); + rb = rcu_dereference(event->rb); + if (rb) { + if (!atomic_inc_not_zero(&rb->refcount)) + rb = NULL; + } + rcu_read_unlock(); + + return rb; +} + +void ring_buffer_put(struct ring_buffer *rb) +{ + if (!atomic_dec_and_test(&rb->refcount)) + return; + + WARN_ON_ONCE(!list_empty(&rb->event_list)); + + call_rcu(&rb->rcu_head, rb_free_rcu); +} + +static void perf_mmap_open(struct vm_area_struct *vma) +{ + struct perf_event *event = vma->vm_file->private_data; + + atomic_inc(&event->mmap_count); + atomic_inc(&event->rb->mmap_count); + + if (vma->vm_pgoff) + atomic_inc(&event->rb->aux_mmap_count); + + if (event->pmu->event_mapped) + event->pmu->event_mapped(event); +} + +/* + * A buffer can be mmap()ed multiple times; either directly through the same + * event, or through other events by use of perf_event_set_output(). + * + * In order to undo the VM accounting done by perf_mmap() we need to destroy + * the buffer here, where we still have a VM context. This means we need + * to detach all events redirecting to us. + */ +static void perf_mmap_close(struct vm_area_struct *vma) +{ + struct perf_event *event = vma->vm_file->private_data; + + struct ring_buffer *rb = ring_buffer_get(event); + struct user_struct *mmap_user = rb->mmap_user; + int mmap_locked = rb->mmap_locked; + unsigned long size = perf_data_size(rb); + + if (event->pmu->event_unmapped) + event->pmu->event_unmapped(event); + + /* + * rb->aux_mmap_count will always drop before rb->mmap_count and + * event->mmap_count, so it is ok to use event->mmap_mutex to + * serialize with perf_mmap here. + */ + if (rb_has_aux(rb) && vma->vm_pgoff == rb->aux_pgoff && + atomic_dec_and_mutex_lock(&rb->aux_mmap_count, &event->mmap_mutex)) { + atomic_long_sub(rb->aux_nr_pages, &mmap_user->locked_vm); + vma->vm_mm->pinned_vm -= rb->aux_mmap_locked; + + rb_free_aux(rb); + mutex_unlock(&event->mmap_mutex); + } + + atomic_dec(&rb->mmap_count); + + if (!atomic_dec_and_mutex_lock(&event->mmap_count, &event->mmap_mutex)) + goto out_put; + + ring_buffer_attach(event, NULL); + mutex_unlock(&event->mmap_mutex); + + /* If there's still other mmap()s of this buffer, we're done. */ + if (atomic_read(&rb->mmap_count)) + goto out_put; + + /* + * No other mmap()s, detach from all other events that might redirect + * into the now unreachable buffer. Somewhat complicated by the + * fact that rb::event_lock otherwise nests inside mmap_mutex. + */ +again: + rcu_read_lock(); + list_for_each_entry_rcu(event, &rb->event_list, rb_entry) { + if (!atomic_long_inc_not_zero(&event->refcount)) { + /* + * This event is en-route to free_event() which will + * detach it and remove it from the list. + */ + continue; + } + rcu_read_unlock(); + + mutex_lock(&event->mmap_mutex); + /* + * Check we didn't race with perf_event_set_output() which can + * swizzle the rb from under us while we were waiting to + * acquire mmap_mutex. + * + * If we find a different rb; ignore this event, a next + * iteration will no longer find it on the list. We have to + * still restart the iteration to make sure we're not now + * iterating the wrong list. + */ + if (event->rb == rb) + ring_buffer_attach(event, NULL); + + mutex_unlock(&event->mmap_mutex); + put_event(event); + + /* + * Restart the iteration; either we're on the wrong list or + * destroyed its integrity by doing a deletion. + */ + goto again; + } + rcu_read_unlock(); + + /* + * It could be there's still a few 0-ref events on the list; they'll + * get cleaned up by free_event() -- they'll also still have their + * ref on the rb and will free it whenever they are done with it. + * + * Aside from that, this buffer is 'fully' detached and unmapped, + * undo the VM accounting. + */ + + atomic_long_sub((size >> PAGE_SHIFT) + 1, &mmap_user->locked_vm); + vma->vm_mm->pinned_vm -= mmap_locked; + free_uid(mmap_user); + +out_put: + ring_buffer_put(rb); /* could be last */ +} + +static const struct vm_operations_struct perf_mmap_vmops = { + .open = perf_mmap_open, + .close = perf_mmap_close, /* non mergable */ + .fault = perf_mmap_fault, + .page_mkwrite = perf_mmap_fault, +}; + +static int perf_mmap(struct file *file, struct vm_area_struct *vma) +{ + struct perf_event *event = file->private_data; + unsigned long user_locked, user_lock_limit; + struct user_struct *user = current_user(); + unsigned long locked, lock_limit; + struct ring_buffer *rb = NULL; + unsigned long vma_size; + unsigned long nr_pages; + long user_extra = 0, extra = 0; + int ret = 0, flags = 0; + + /* + * Don't allow mmap() of inherited per-task counters. This would + * create a performance issue due to all children writing to the + * same rb. + */ + if (event->cpu == -1 && event->attr.inherit) + return -EINVAL; + + if (!(vma->vm_flags & VM_SHARED)) + return -EINVAL; + + vma_size = vma->vm_end - vma->vm_start; + + if (vma->vm_pgoff == 0) { + nr_pages = (vma_size / PAGE_SIZE) - 1; + } else { + /* + * AUX area mapping: if rb->aux_nr_pages != 0, it's already + * mapped, all subsequent mappings should have the same size + * and offset. Must be above the normal perf buffer. + */ + u64 aux_offset, aux_size; + + if (!event->rb) + return -EINVAL; + + nr_pages = vma_size / PAGE_SIZE; + + mutex_lock(&event->mmap_mutex); + ret = -EINVAL; + + rb = event->rb; + if (!rb) + goto aux_unlock; + + aux_offset = ACCESS_ONCE(rb->user_page->aux_offset); + aux_size = ACCESS_ONCE(rb->user_page->aux_size); + + if (aux_offset < perf_data_size(rb) + PAGE_SIZE) + goto aux_unlock; + + if (aux_offset != vma->vm_pgoff << PAGE_SHIFT) + goto aux_unlock; + + /* already mapped with a different offset */ + if (rb_has_aux(rb) && rb->aux_pgoff != vma->vm_pgoff) + goto aux_unlock; + + if (aux_size != vma_size || aux_size != nr_pages * PAGE_SIZE) + goto aux_unlock; + + /* already mapped with a different size */ + if (rb_has_aux(rb) && rb->aux_nr_pages != nr_pages) + goto aux_unlock; + + if (!is_power_of_2(nr_pages)) + goto aux_unlock; + + if (!atomic_inc_not_zero(&rb->mmap_count)) + goto aux_unlock; + + if (rb_has_aux(rb)) { + atomic_inc(&rb->aux_mmap_count); + ret = 0; + goto unlock; + } + + atomic_set(&rb->aux_mmap_count, 1); + user_extra = nr_pages; + + goto accounting; + } + + /* + * If we have rb pages ensure they're a power-of-two number, so we + * can do bitmasks instead of modulo. + */ + if (nr_pages != 0 && !is_power_of_2(nr_pages)) + return -EINVAL; + + if (vma_size != PAGE_SIZE * (1 + nr_pages)) + return -EINVAL; + + WARN_ON_ONCE(event->ctx->parent_ctx); +again: + mutex_lock(&event->mmap_mutex); + if (event->rb) { + if (event->rb->nr_pages != nr_pages) { + ret = -EINVAL; + goto unlock; + } + + if (!atomic_inc_not_zero(&event->rb->mmap_count)) { + /* + * Raced against perf_mmap_close() through + * perf_event_set_output(). Try again, hope for better + * luck. + */ + mutex_unlock(&event->mmap_mutex); + goto again; + } + + goto unlock; + } + + user_extra = nr_pages + 1; + +accounting: + user_lock_limit = sysctl_perf_event_mlock >> (PAGE_SHIFT - 10); + + /* + * Increase the limit linearly with more CPUs: + */ + user_lock_limit *= num_online_cpus(); + + user_locked = atomic_long_read(&user->locked_vm) + user_extra; + + if (user_locked > user_lock_limit) + extra = user_locked - user_lock_limit; + + lock_limit = rlimit(RLIMIT_MEMLOCK); + lock_limit >>= PAGE_SHIFT; + locked = vma->vm_mm->pinned_vm + extra; + + if ((locked > lock_limit) && perf_paranoid_tracepoint_raw() && + !capable(CAP_IPC_LOCK)) { + ret = -EPERM; + goto unlock; + } + + WARN_ON(!rb && event->rb); + + if (vma->vm_flags & VM_WRITE) + flags |= RING_BUFFER_WRITABLE; + + if (!rb) { + rb = rb_alloc(nr_pages, + event->attr.watermark ? event->attr.wakeup_watermark : 0, + event->cpu, flags); + + if (!rb) { + ret = -ENOMEM; + goto unlock; + } + + atomic_set(&rb->mmap_count, 1); + rb->mmap_user = get_current_user(); + rb->mmap_locked = extra; + + ring_buffer_attach(event, rb); + + perf_event_init_userpage(event); + perf_event_update_userpage(event); + } else { + ret = rb_alloc_aux(rb, event, vma->vm_pgoff, nr_pages, + event->attr.aux_watermark, flags); + if (!ret) + rb->aux_mmap_locked = extra; + } + +unlock: + if (!ret) { + atomic_long_add(user_extra, &user->locked_vm); + vma->vm_mm->pinned_vm += extra; + + atomic_inc(&event->mmap_count); + } else if (rb) { + atomic_dec(&rb->mmap_count); + } +aux_unlock: + mutex_unlock(&event->mmap_mutex); + + /* + * Since pinned accounting is per vm we cannot allow fork() to copy our + * vma. + */ + vma->vm_flags |= VM_DONTCOPY | VM_DONTEXPAND | VM_DONTDUMP; + vma->vm_ops = &perf_mmap_vmops; + + if (event->pmu->event_mapped) + event->pmu->event_mapped(event); + + return ret; +} + +static int perf_fasync(int fd, struct file *filp, int on) +{ + struct inode *inode = file_inode(filp); + struct perf_event *event = filp->private_data; + int retval; + + mutex_lock(&inode->i_mutex); + retval = fasync_helper(fd, filp, on, &event->fasync); + mutex_unlock(&inode->i_mutex); + + if (retval < 0) + return retval; + + return 0; +} + +static const struct file_operations perf_fops = { + .llseek = no_llseek, + .release = perf_release, + .read = perf_read, + .poll = perf_poll, + .unlocked_ioctl = perf_ioctl, + .compat_ioctl = perf_compat_ioctl, + .mmap = perf_mmap, + .fasync = perf_fasync, +}; + +/* + * Perf event wakeup + * + * If there's data, ensure we set the poll() state and publish everything + * to user-space before waking everybody up. + */ + +void perf_event_wakeup(struct perf_event *event) +{ + ring_buffer_wakeup(event); + + if (event->pending_kill) { + kill_fasync(&event->fasync, SIGIO, event->pending_kill); + event->pending_kill = 0; + } +} + +static void perf_pending_event(struct irq_work *entry) +{ + struct perf_event *event = container_of(entry, + struct perf_event, pending); + int rctx; + + rctx = perf_swevent_get_recursion_context(); + /* + * If we 'fail' here, that's OK, it means recursion is already disabled + * and we won't recurse 'further'. + */ + + if (event->pending_disable) { + event->pending_disable = 0; + __perf_event_disable(event); + } + + if (event->pending_wakeup) { + event->pending_wakeup = 0; + perf_event_wakeup(event); + } + + if (rctx >= 0) + perf_swevent_put_recursion_context(rctx); +} + +/* + * We assume there is only KVM supporting the callbacks. + * Later on, we might change it to a list if there is + * another virtualization implementation supporting the callbacks. + */ +struct perf_guest_info_callbacks *perf_guest_cbs; + +int perf_register_guest_info_callbacks(struct perf_guest_info_callbacks *cbs) +{ + perf_guest_cbs = cbs; + return 0; +} +EXPORT_SYMBOL_GPL(perf_register_guest_info_callbacks); + +int perf_unregister_guest_info_callbacks(struct perf_guest_info_callbacks *cbs) +{ + perf_guest_cbs = NULL; + return 0; +} +EXPORT_SYMBOL_GPL(perf_unregister_guest_info_callbacks); + +static void +perf_output_sample_regs(struct perf_output_handle *handle, + struct pt_regs *regs, u64 mask) +{ + int bit; + + for_each_set_bit(bit, (const unsigned long *) &mask, + sizeof(mask) * BITS_PER_BYTE) { + u64 val; + + val = perf_reg_value(regs, bit); + perf_output_put(handle, val); + } +} + +static void perf_sample_regs_user(struct perf_regs *regs_user, + struct pt_regs *regs, + struct pt_regs *regs_user_copy) +{ + if (user_mode(regs)) { + regs_user->abi = perf_reg_abi(current); + regs_user->regs = regs; + } else if (current->mm) { + perf_get_regs_user(regs_user, regs, regs_user_copy); + } else { + regs_user->abi = PERF_SAMPLE_REGS_ABI_NONE; + regs_user->regs = NULL; + } +} + +static void perf_sample_regs_intr(struct perf_regs *regs_intr, + struct pt_regs *regs) +{ + regs_intr->regs = regs; + regs_intr->abi = perf_reg_abi(current); +} + + +/* + * Get remaining task size from user stack pointer. + * + * It'd be better to take stack vma map and limit this more + * precisly, but there's no way to get it safely under interrupt, + * so using TASK_SIZE as limit. + */ +static u64 perf_ustack_task_size(struct pt_regs *regs) +{ + unsigned long addr = perf_user_stack_pointer(regs); + + if (!addr || addr >= TASK_SIZE) + return 0; + + return TASK_SIZE - addr; +} + +static u16 +perf_sample_ustack_size(u16 stack_size, u16 header_size, + struct pt_regs *regs) +{ + u64 task_size; + + /* No regs, no stack pointer, no dump. */ + if (!regs) + return 0; + + /* + * Check if we fit in with the requested stack size into the: + * - TASK_SIZE + * If we don't, we limit the size to the TASK_SIZE. + * + * - remaining sample size + * If we don't, we customize the stack size to + * fit in to the remaining sample size. + */ + + task_size = min((u64) USHRT_MAX, perf_ustack_task_size(regs)); + stack_size = min(stack_size, (u16) task_size); + + /* Current header size plus static size and dynamic size. */ + header_size += 2 * sizeof(u64); + + /* Do we fit in with the current stack dump size? */ + if ((u16) (header_size + stack_size) < header_size) { + /* + * If we overflow the maximum size for the sample, + * we customize the stack dump size to fit in. + */ + stack_size = USHRT_MAX - header_size - sizeof(u64); + stack_size = round_up(stack_size, sizeof(u64)); + } + + return stack_size; +} + +static void +perf_output_sample_ustack(struct perf_output_handle *handle, u64 dump_size, + struct pt_regs *regs) +{ + /* Case of a kernel thread, nothing to dump */ + if (!regs) { + u64 size = 0; + perf_output_put(handle, size); + } else { + unsigned long sp; + unsigned int rem; + u64 dyn_size; + + /* + * We dump: + * static size + * - the size requested by user or the best one we can fit + * in to the sample max size + * data + * - user stack dump data + * dynamic size + * - the actual dumped size + */ + + /* Static size. */ + perf_output_put(handle, dump_size); + + /* Data. */ + sp = perf_user_stack_pointer(regs); + rem = __output_copy_user(handle, (void *) sp, dump_size); + dyn_size = dump_size - rem; + + perf_output_skip(handle, rem); + + /* Dynamic size. */ + perf_output_put(handle, dyn_size); + } +} + +static void __perf_event_header__init_id(struct perf_event_header *header, + struct perf_sample_data *data, + struct perf_event *event) +{ + u64 sample_type = event->attr.sample_type; + + data->type = sample_type; + header->size += event->id_header_size; + + if (sample_type & PERF_SAMPLE_TID) { + /* namespace issues */ + data->tid_entry.pid = perf_event_pid(event, current); + data->tid_entry.tid = perf_event_tid(event, current); + } + + if (sample_type & PERF_SAMPLE_TIME) + data->time = perf_event_clock(event); + + if (sample_type & (PERF_SAMPLE_ID | PERF_SAMPLE_IDENTIFIER)) + data->id = primary_event_id(event); + + if (sample_type & PERF_SAMPLE_STREAM_ID) + data->stream_id = event->id; + + if (sample_type & PERF_SAMPLE_CPU) { + data->cpu_entry.cpu = raw_smp_processor_id(); + data->cpu_entry.reserved = 0; + } +} + +void perf_event_header__init_id(struct perf_event_header *header, + struct perf_sample_data *data, + struct perf_event *event) +{ + if (event->attr.sample_id_all) + __perf_event_header__init_id(header, data, event); +} + +static void __perf_event__output_id_sample(struct perf_output_handle *handle, + struct perf_sample_data *data) +{ + u64 sample_type = data->type; + + if (sample_type & PERF_SAMPLE_TID) + perf_output_put(handle, data->tid_entry); + + if (sample_type & PERF_SAMPLE_TIME) + perf_output_put(handle, data->time); + + if (sample_type & PERF_SAMPLE_ID) + perf_output_put(handle, data->id); + + if (sample_type & PERF_SAMPLE_STREAM_ID) + perf_output_put(handle, data->stream_id); + + if (sample_type & PERF_SAMPLE_CPU) + perf_output_put(handle, data->cpu_entry); + + if (sample_type & PERF_SAMPLE_IDENTIFIER) + perf_output_put(handle, data->id); +} + +void perf_event__output_id_sample(struct perf_event *event, + struct perf_output_handle *handle, + struct perf_sample_data *sample) +{ + if (event->attr.sample_id_all) + __perf_event__output_id_sample(handle, sample); +} + +static void perf_output_read_one(struct perf_output_handle *handle, + struct perf_event *event, + u64 enabled, u64 running) +{ + u64 read_format = event->attr.read_format; + u64 values[4]; + int n = 0; + + values[n++] = perf_event_count(event); + if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) { + values[n++] = enabled + + atomic64_read(&event->child_total_time_enabled); + } + if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) { + values[n++] = running + + atomic64_read(&event->child_total_time_running); + } + if (read_format & PERF_FORMAT_ID) + values[n++] = primary_event_id(event); + + __output_copy(handle, values, n * sizeof(u64)); +} + +/* + * XXX PERF_FORMAT_GROUP vs inherited events seems difficult. + */ +static void perf_output_read_group(struct perf_output_handle *handle, + struct perf_event *event, + u64 enabled, u64 running) +{ + struct perf_event *leader = event->group_leader, *sub; + u64 read_format = event->attr.read_format; + u64 values[5]; + int n = 0; + + values[n++] = 1 + leader->nr_siblings; + + if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) + values[n++] = enabled; + + if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) + values[n++] = running; + + if (leader != event) + leader->pmu->read(leader); + + values[n++] = perf_event_count(leader); + if (read_format & PERF_FORMAT_ID) + values[n++] = primary_event_id(leader); + + __output_copy(handle, values, n * sizeof(u64)); + + list_for_each_entry(sub, &leader->sibling_list, group_entry) { + n = 0; + + if ((sub != event) && + (sub->state == PERF_EVENT_STATE_ACTIVE)) + sub->pmu->read(sub); + + values[n++] = perf_event_count(sub); + if (read_format & PERF_FORMAT_ID) + values[n++] = primary_event_id(sub); + + __output_copy(handle, values, n * sizeof(u64)); + } +} + +#define PERF_FORMAT_TOTAL_TIMES (PERF_FORMAT_TOTAL_TIME_ENABLED|\ + PERF_FORMAT_TOTAL_TIME_RUNNING) + +static void perf_output_read(struct perf_output_handle *handle, + struct perf_event *event) +{ + u64 enabled = 0, running = 0, now; + u64 read_format = event->attr.read_format; + + /* + * compute total_time_enabled, total_time_running + * based on snapshot values taken when the event + * was last scheduled in. + * + * we cannot simply called update_context_time() + * because of locking issue as we are called in + * NMI context + */ + if (read_format & PERF_FORMAT_TOTAL_TIMES) + calc_timer_values(event, &now, &enabled, &running); + + if (event->attr.read_format & PERF_FORMAT_GROUP) + perf_output_read_group(handle, event, enabled, running); + else + perf_output_read_one(handle, event, enabled, running); +} + +void perf_output_sample(struct perf_output_handle *handle, + struct perf_event_header *header, + struct perf_sample_data *data, + struct perf_event *event) +{ + u64 sample_type = data->type; + + perf_output_put(handle, *header); + + if (sample_type & PERF_SAMPLE_IDENTIFIER) + perf_output_put(handle, data->id); + + if (sample_type & PERF_SAMPLE_IP) + perf_output_put(handle, data->ip); + + if (sample_type & PERF_SAMPLE_TID) + perf_output_put(handle, data->tid_entry); + + if (sample_type & PERF_SAMPLE_TIME) + perf_output_put(handle, data->time); + + if (sample_type & PERF_SAMPLE_ADDR) + perf_output_put(handle, data->addr); + + if (sample_type & PERF_SAMPLE_ID) + perf_output_put(handle, data->id); + + if (sample_type & PERF_SAMPLE_STREAM_ID) + perf_output_put(handle, data->stream_id); + + if (sample_type & PERF_SAMPLE_CPU) + perf_output_put(handle, data->cpu_entry); + + if (sample_type & PERF_SAMPLE_PERIOD) + perf_output_put(handle, data->period); + + if (sample_type & PERF_SAMPLE_READ) + perf_output_read(handle, event); + + if (sample_type & PERF_SAMPLE_CALLCHAIN) { + if (data->callchain) { + int size = 1; + + if (data->callchain) + size += data->callchain->nr; + + size *= sizeof(u64); + + __output_copy(handle, data->callchain, size); + } else { + u64 nr = 0; + perf_output_put(handle, nr); + } + } + + if (sample_type & PERF_SAMPLE_RAW) { + if (data->raw) { + perf_output_put(handle, data->raw->size); + __output_copy(handle, data->raw->data, + data->raw->size); + } else { + struct { + u32 size; + u32 data; + } raw = { + .size = sizeof(u32), + .data = 0, + }; + perf_output_put(handle, raw); + } + } + + if (sample_type & PERF_SAMPLE_BRANCH_STACK) { + if (data->br_stack) { + size_t size; + + size = data->br_stack->nr + * sizeof(struct perf_branch_entry); + + perf_output_put(handle, data->br_stack->nr); + perf_output_copy(handle, data->br_stack->entries, size); + } else { + /* + * we always store at least the value of nr + */ + u64 nr = 0; + perf_output_put(handle, nr); + } + } + + if (sample_type & PERF_SAMPLE_REGS_USER) { + u64 abi = data->regs_user.abi; + + /* + * If there are no regs to dump, notice it through + * first u64 being zero (PERF_SAMPLE_REGS_ABI_NONE). + */ + perf_output_put(handle, abi); + + if (abi) { + u64 mask = event->attr.sample_regs_user; + perf_output_sample_regs(handle, + data->regs_user.regs, + mask); + } + } + + if (sample_type & PERF_SAMPLE_STACK_USER) { + perf_output_sample_ustack(handle, + data->stack_user_size, + data->regs_user.regs); + } + + if (sample_type & PERF_SAMPLE_WEIGHT) + perf_output_put(handle, data->weight); + + if (sample_type & PERF_SAMPLE_DATA_SRC) + perf_output_put(handle, data->data_src.val); + + if (sample_type & PERF_SAMPLE_TRANSACTION) + perf_output_put(handle, data->txn); + + if (sample_type & PERF_SAMPLE_REGS_INTR) { + u64 abi = data->regs_intr.abi; + /* + * If there are no regs to dump, notice it through + * first u64 being zero (PERF_SAMPLE_REGS_ABI_NONE). + */ + perf_output_put(handle, abi); + + if (abi) { + u64 mask = event->attr.sample_regs_intr; + + perf_output_sample_regs(handle, + data->regs_intr.regs, + mask); + } + } + + if (!event->attr.watermark) { + int wakeup_events = event->attr.wakeup_events; + + if (wakeup_events) { + struct ring_buffer *rb = handle->rb; + int events = local_inc_return(&rb->events); + + if (events >= wakeup_events) { + local_sub(wakeup_events, &rb->events); + local_inc(&rb->wakeup); + } + } + } +} + +void perf_prepare_sample(struct perf_event_header *header, + struct perf_sample_data *data, + struct perf_event *event, + struct pt_regs *regs) +{ + u64 sample_type = event->attr.sample_type; + + header->type = PERF_RECORD_SAMPLE; + header->size = sizeof(*header) + event->header_size; + + header->misc = 0; + header->misc |= perf_misc_flags(regs); + + __perf_event_header__init_id(header, data, event); + + if (sample_type & PERF_SAMPLE_IP) + data->ip = perf_instruction_pointer(regs); + + if (sample_type & PERF_SAMPLE_CALLCHAIN) { + int size = 1; + + data->callchain = perf_callchain(event, regs); + + if (data->callchain) + size += data->callchain->nr; + + header->size += size * sizeof(u64); + } + + if (sample_type & PERF_SAMPLE_RAW) { + int size = sizeof(u32); + + if (data->raw) + size += data->raw->size; + else + size += sizeof(u32); + + WARN_ON_ONCE(size & (sizeof(u64)-1)); + header->size += size; + } + + if (sample_type & PERF_SAMPLE_BRANCH_STACK) { + int size = sizeof(u64); /* nr */ + if (data->br_stack) { + size += data->br_stack->nr + * sizeof(struct perf_branch_entry); + } + header->size += size; + } + + if (sample_type & (PERF_SAMPLE_REGS_USER | PERF_SAMPLE_STACK_USER)) + perf_sample_regs_user(&data->regs_user, regs, + &data->regs_user_copy); + + if (sample_type & PERF_SAMPLE_REGS_USER) { + /* regs dump ABI info */ + int size = sizeof(u64); + + if (data->regs_user.regs) { + u64 mask = event->attr.sample_regs_user; + size += hweight64(mask) * sizeof(u64); + } + + header->size += size; + } + + if (sample_type & PERF_SAMPLE_STACK_USER) { + /* + * Either we need PERF_SAMPLE_STACK_USER bit to be allways + * processed as the last one or have additional check added + * in case new sample type is added, because we could eat + * up the rest of the sample size. + */ + u16 stack_size = event->attr.sample_stack_user; + u16 size = sizeof(u64); + + stack_size = perf_sample_ustack_size(stack_size, header->size, + data->regs_user.regs); + + /* + * If there is something to dump, add space for the dump + * itself and for the field that tells the dynamic size, + * which is how many have been actually dumped. + */ + if (stack_size) + size += sizeof(u64) + stack_size; + + data->stack_user_size = stack_size; + header->size += size; + } + + if (sample_type & PERF_SAMPLE_REGS_INTR) { + /* regs dump ABI info */ + int size = sizeof(u64); + + perf_sample_regs_intr(&data->regs_intr, regs); + + if (data->regs_intr.regs) { + u64 mask = event->attr.sample_regs_intr; + + size += hweight64(mask) * sizeof(u64); + } + + header->size += size; + } +} + +static void perf_event_output(struct perf_event *event, + struct perf_sample_data *data, + struct pt_regs *regs) +{ + struct perf_output_handle handle; + struct perf_event_header header; + + /* protect the callchain buffers */ + rcu_read_lock(); + + perf_prepare_sample(&header, data, event, regs); + + if (perf_output_begin(&handle, event, header.size)) + goto exit; + + perf_output_sample(&handle, &header, data, event); + + perf_output_end(&handle); + +exit: + rcu_read_unlock(); +} + +/* + * read event_id + */ + +struct perf_read_event { + struct perf_event_header header; + + u32 pid; + u32 tid; +}; + +static void +perf_event_read_event(struct perf_event *event, + struct task_struct *task) +{ + struct perf_output_handle handle; + struct perf_sample_data sample; + struct perf_read_event read_event = { + .header = { + .type = PERF_RECORD_READ, + .misc = 0, + .size = sizeof(read_event) + event->read_size, + }, + .pid = perf_event_pid(event, task), + .tid = perf_event_tid(event, task), + }; + int ret; + + perf_event_header__init_id(&read_event.header, &sample, event); + ret = perf_output_begin(&handle, event, read_event.header.size); + if (ret) + return; + + perf_output_put(&handle, read_event); + perf_output_read(&handle, event); + perf_event__output_id_sample(event, &handle, &sample); + + perf_output_end(&handle); +} + +typedef void (perf_event_aux_output_cb)(struct perf_event *event, void *data); + +static void +perf_event_aux_ctx(struct perf_event_context *ctx, + perf_event_aux_output_cb output, + void *data) +{ + struct perf_event *event; + + list_for_each_entry_rcu(event, &ctx->event_list, event_entry) { + if (event->state < PERF_EVENT_STATE_INACTIVE) + continue; + if (!event_filter_match(event)) + continue; + output(event, data); + } +} + +static void +perf_event_aux(perf_event_aux_output_cb output, void *data, + struct perf_event_context *task_ctx) +{ + struct perf_cpu_context *cpuctx; + struct perf_event_context *ctx; + struct pmu *pmu; + int ctxn; + + rcu_read_lock(); + list_for_each_entry_rcu(pmu, &pmus, entry) { + cpuctx = get_cpu_ptr(pmu->pmu_cpu_context); + if (cpuctx->unique_pmu != pmu) + goto next; + perf_event_aux_ctx(&cpuctx->ctx, output, data); + if (task_ctx) + goto next; + ctxn = pmu->task_ctx_nr; + if (ctxn < 0) + goto next; + ctx = rcu_dereference(current->perf_event_ctxp[ctxn]); + if (ctx) + perf_event_aux_ctx(ctx, output, data); +next: + put_cpu_ptr(pmu->pmu_cpu_context); + } + + if (task_ctx) { + preempt_disable(); + perf_event_aux_ctx(task_ctx, output, data); + preempt_enable(); + } + rcu_read_unlock(); +} + +/* + * task tracking -- fork/exit + * + * enabled by: attr.comm | attr.mmap | attr.mmap2 | attr.mmap_data | attr.task + */ + +struct perf_task_event { + struct task_struct *task; + struct perf_event_context *task_ctx; + + struct { + struct perf_event_header header; + + u32 pid; + u32 ppid; + u32 tid; + u32 ptid; + u64 time; + } event_id; +}; + +static int perf_event_task_match(struct perf_event *event) +{ + return event->attr.comm || event->attr.mmap || + event->attr.mmap2 || event->attr.mmap_data || + event->attr.task; +} + +static void perf_event_task_output(struct perf_event *event, + void *data) +{ + struct perf_task_event *task_event = data; + struct perf_output_handle handle; + struct perf_sample_data sample; + struct task_struct *task = task_event->task; + int ret, size = task_event->event_id.header.size; + + if (!perf_event_task_match(event)) + return; + + perf_event_header__init_id(&task_event->event_id.header, &sample, event); + + ret = perf_output_begin(&handle, event, + task_event->event_id.header.size); + if (ret) + goto out; + + task_event->event_id.pid = perf_event_pid(event, task); + task_event->event_id.ppid = perf_event_pid(event, current); + + task_event->event_id.tid = perf_event_tid(event, task); + task_event->event_id.ptid = perf_event_tid(event, current); + + task_event->event_id.time = perf_event_clock(event); + + perf_output_put(&handle, task_event->event_id); + + perf_event__output_id_sample(event, &handle, &sample); + + perf_output_end(&handle); +out: + task_event->event_id.header.size = size; +} + +static void perf_event_task(struct task_struct *task, + struct perf_event_context *task_ctx, + int new) +{ + struct perf_task_event task_event; + + if (!atomic_read(&nr_comm_events) && + !atomic_read(&nr_mmap_events) && + !atomic_read(&nr_task_events)) + return; + + task_event = (struct perf_task_event){ + .task = task, + .task_ctx = task_ctx, + .event_id = { + .header = { + .type = new ? PERF_RECORD_FORK : PERF_RECORD_EXIT, + .misc = 0, + .size = sizeof(task_event.event_id), + }, + /* .pid */ + /* .ppid */ + /* .tid */ + /* .ptid */ + /* .time */ + }, + }; + + perf_event_aux(perf_event_task_output, + &task_event, + task_ctx); +} + +void perf_event_fork(struct task_struct *task) +{ + perf_event_task(task, NULL, 1); +} + +/* + * comm tracking + */ + +struct perf_comm_event { + struct task_struct *task; + char *comm; + int comm_size; + + struct { + struct perf_event_header header; + + u32 pid; + u32 tid; + } event_id; +}; + +static int perf_event_comm_match(struct perf_event *event) +{ + return event->attr.comm; +} + +static void perf_event_comm_output(struct perf_event *event, + void *data) +{ + struct perf_comm_event *comm_event = data; + struct perf_output_handle handle; + struct perf_sample_data sample; + int size = comm_event->event_id.header.size; + int ret; + + if (!perf_event_comm_match(event)) + return; + + perf_event_header__init_id(&comm_event->event_id.header, &sample, event); + ret = perf_output_begin(&handle, event, + comm_event->event_id.header.size); + + if (ret) + goto out; + + comm_event->event_id.pid = perf_event_pid(event, comm_event->task); + comm_event->event_id.tid = perf_event_tid(event, comm_event->task); + + perf_output_put(&handle, comm_event->event_id); + __output_copy(&handle, comm_event->comm, + comm_event->comm_size); + + perf_event__output_id_sample(event, &handle, &sample); + + perf_output_end(&handle); +out: + comm_event->event_id.header.size = size; +} + +static void perf_event_comm_event(struct perf_comm_event *comm_event) +{ + char comm[TASK_COMM_LEN]; + unsigned int size; + + memset(comm, 0, sizeof(comm)); + strlcpy(comm, comm_event->task->comm, sizeof(comm)); + size = ALIGN(strlen(comm)+1, sizeof(u64)); + + comm_event->comm = comm; + comm_event->comm_size = size; + + comm_event->event_id.header.size = sizeof(comm_event->event_id) + size; + + perf_event_aux(perf_event_comm_output, + comm_event, + NULL); +} + +void perf_event_comm(struct task_struct *task, bool exec) +{ + struct perf_comm_event comm_event; + + if (!atomic_read(&nr_comm_events)) + return; + + comm_event = (struct perf_comm_event){ + .task = task, + /* .comm */ + /* .comm_size */ + .event_id = { + .header = { + .type = PERF_RECORD_COMM, + .misc = exec ? PERF_RECORD_MISC_COMM_EXEC : 0, + /* .size */ + }, + /* .pid */ + /* .tid */ + }, + }; + + perf_event_comm_event(&comm_event); +} + +/* + * mmap tracking + */ + +struct perf_mmap_event { + struct vm_area_struct *vma; + + const char *file_name; + int file_size; + int maj, min; + u64 ino; + u64 ino_generation; + u32 prot, flags; + + struct { + struct perf_event_header header; + + u32 pid; + u32 tid; + u64 start; + u64 len; + u64 pgoff; + } event_id; +}; + +static int perf_event_mmap_match(struct perf_event *event, + void *data) +{ + struct perf_mmap_event *mmap_event = data; + struct vm_area_struct *vma = mmap_event->vma; + int executable = vma->vm_flags & VM_EXEC; + + return (!executable && event->attr.mmap_data) || + (executable && (event->attr.mmap || event->attr.mmap2)); +} + +static void perf_event_mmap_output(struct perf_event *event, + void *data) +{ + struct perf_mmap_event *mmap_event = data; + struct perf_output_handle handle; + struct perf_sample_data sample; + int size = mmap_event->event_id.header.size; + int ret; + + if (!perf_event_mmap_match(event, data)) + return; + + if (event->attr.mmap2) { + mmap_event->event_id.header.type = PERF_RECORD_MMAP2; + mmap_event->event_id.header.size += sizeof(mmap_event->maj); + mmap_event->event_id.header.size += sizeof(mmap_event->min); + mmap_event->event_id.header.size += sizeof(mmap_event->ino); + mmap_event->event_id.header.size += sizeof(mmap_event->ino_generation); + mmap_event->event_id.header.size += sizeof(mmap_event->prot); + mmap_event->event_id.header.size += sizeof(mmap_event->flags); + } + + perf_event_header__init_id(&mmap_event->event_id.header, &sample, event); + ret = perf_output_begin(&handle, event, + mmap_event->event_id.header.size); + if (ret) + goto out; + + mmap_event->event_id.pid = perf_event_pid(event, current); + mmap_event->event_id.tid = perf_event_tid(event, current); + + perf_output_put(&handle, mmap_event->event_id); + + if (event->attr.mmap2) { + perf_output_put(&handle, mmap_event->maj); + perf_output_put(&handle, mmap_event->min); + perf_output_put(&handle, mmap_event->ino); + perf_output_put(&handle, mmap_event->ino_generation); + perf_output_put(&handle, mmap_event->prot); + perf_output_put(&handle, mmap_event->flags); + } + + __output_copy(&handle, mmap_event->file_name, + mmap_event->file_size); + + perf_event__output_id_sample(event, &handle, &sample); + + perf_output_end(&handle); +out: + mmap_event->event_id.header.size = size; +} + +static void perf_event_mmap_event(struct perf_mmap_event *mmap_event) +{ + struct vm_area_struct *vma = mmap_event->vma; + struct file *file = vma->vm_file; + int maj = 0, min = 0; + u64 ino = 0, gen = 0; + u32 prot = 0, flags = 0; + unsigned int size; + char tmp[16]; + char *buf = NULL; + char *name; + + if (file) { + struct inode *inode; + dev_t dev; + + buf = kmalloc(PATH_MAX, GFP_KERNEL); + if (!buf) { + name = "//enomem"; + goto cpy_name; + } + /* + * d_path() works from the end of the rb backwards, so we + * need to add enough zero bytes after the string to handle + * the 64bit alignment we do later. + */ + name = d_path(&file->f_path, buf, PATH_MAX - sizeof(u64)); + if (IS_ERR(name)) { + name = "//toolong"; + goto cpy_name; + } + inode = file_inode(vma->vm_file); + dev = inode->i_sb->s_dev; + ino = inode->i_ino; + gen = inode->i_generation; + maj = MAJOR(dev); + min = MINOR(dev); + + if (vma->vm_flags & VM_READ) + prot |= PROT_READ; + if (vma->vm_flags & VM_WRITE) + prot |= PROT_WRITE; + if (vma->vm_flags & VM_EXEC) + prot |= PROT_EXEC; + + if (vma->vm_flags & VM_MAYSHARE) + flags = MAP_SHARED; + else + flags = MAP_PRIVATE; + + if (vma->vm_flags & VM_DENYWRITE) + flags |= MAP_DENYWRITE; + if (vma->vm_flags & VM_MAYEXEC) + flags |= MAP_EXECUTABLE; + if (vma->vm_flags & VM_LOCKED) + flags |= MAP_LOCKED; + if (vma->vm_flags & VM_HUGETLB) + flags |= MAP_HUGETLB; + + goto got_name; + } else { + if (vma->vm_ops && vma->vm_ops->name) { + name = (char *) vma->vm_ops->name(vma); + if (name) + goto cpy_name; + } + + name = (char *)arch_vma_name(vma); + if (name) + goto cpy_name; + + if (vma->vm_start <= vma->vm_mm->start_brk && + vma->vm_end >= vma->vm_mm->brk) { + name = "[heap]"; + goto cpy_name; + } + if (vma->vm_start <= vma->vm_mm->start_stack && + vma->vm_end >= vma->vm_mm->start_stack) { + name = "[stack]"; + goto cpy_name; + } + + name = "//anon"; + goto cpy_name; + } + +cpy_name: + strlcpy(tmp, name, sizeof(tmp)); + name = tmp; +got_name: + /* + * Since our buffer works in 8 byte units we need to align our string + * size to a multiple of 8. However, we must guarantee the tail end is + * zero'd out to avoid leaking random bits to userspace. + */ + size = strlen(name)+1; + while (!IS_ALIGNED(size, sizeof(u64))) + name[size++] = '\0'; + + mmap_event->file_name = name; + mmap_event->file_size = size; + mmap_event->maj = maj; + mmap_event->min = min; + mmap_event->ino = ino; + mmap_event->ino_generation = gen; + mmap_event->prot = prot; + mmap_event->flags = flags; + + if (!(vma->vm_flags & VM_EXEC)) + mmap_event->event_id.header.misc |= PERF_RECORD_MISC_MMAP_DATA; + + mmap_event->event_id.header.size = sizeof(mmap_event->event_id) + size; + + perf_event_aux(perf_event_mmap_output, + mmap_event, + NULL); + + kfree(buf); +} + +void perf_event_mmap(struct vm_area_struct *vma) +{ + struct perf_mmap_event mmap_event; + + if (!atomic_read(&nr_mmap_events)) + return; + + mmap_event = (struct perf_mmap_event){ + .vma = vma, + /* .file_name */ + /* .file_size */ + .event_id = { + .header = { + .type = PERF_RECORD_MMAP, + .misc = PERF_RECORD_MISC_USER, + /* .size */ + }, + /* .pid */ + /* .tid */ + .start = vma->vm_start, + .len = vma->vm_end - vma->vm_start, + .pgoff = (u64)vma->vm_pgoff << PAGE_SHIFT, + }, + /* .maj (attr_mmap2 only) */ + /* .min (attr_mmap2 only) */ + /* .ino (attr_mmap2 only) */ + /* .ino_generation (attr_mmap2 only) */ + /* .prot (attr_mmap2 only) */ + /* .flags (attr_mmap2 only) */ + }; + + perf_event_mmap_event(&mmap_event); +} + +void perf_event_aux_event(struct perf_event *event, unsigned long head, + unsigned long size, u64 flags) +{ + struct perf_output_handle handle; + struct perf_sample_data sample; + struct perf_aux_event { + struct perf_event_header header; + u64 offset; + u64 size; + u64 flags; + } rec = { + .header = { + .type = PERF_RECORD_AUX, + .misc = 0, + .size = sizeof(rec), + }, + .offset = head, + .size = size, + .flags = flags, + }; + int ret; + + perf_event_header__init_id(&rec.header, &sample, event); + ret = perf_output_begin(&handle, event, rec.header.size); + + if (ret) + return; + + perf_output_put(&handle, rec); + perf_event__output_id_sample(event, &handle, &sample); + + perf_output_end(&handle); +} + +/* + * IRQ throttle logging + */ + +static void perf_log_throttle(struct perf_event *event, int enable) +{ + struct perf_output_handle handle; + struct perf_sample_data sample; + int ret; + + struct { + struct perf_event_header header; + u64 time; + u64 id; + u64 stream_id; + } throttle_event = { + .header = { + .type = PERF_RECORD_THROTTLE, + .misc = 0, + .size = sizeof(throttle_event), + }, + .time = perf_event_clock(event), + .id = primary_event_id(event), + .stream_id = event->id, + }; + + if (enable) + throttle_event.header.type = PERF_RECORD_UNTHROTTLE; + + perf_event_header__init_id(&throttle_event.header, &sample, event); + + ret = perf_output_begin(&handle, event, + throttle_event.header.size); + if (ret) + return; + + perf_output_put(&handle, throttle_event); + perf_event__output_id_sample(event, &handle, &sample); + perf_output_end(&handle); +} + +static void perf_log_itrace_start(struct perf_event *event) +{ + struct perf_output_handle handle; + struct perf_sample_data sample; + struct perf_aux_event { + struct perf_event_header header; + u32 pid; + u32 tid; + } rec; + int ret; + + if (event->parent) + event = event->parent; + + if (!(event->pmu->capabilities & PERF_PMU_CAP_ITRACE) || + event->hw.itrace_started) + return; + + event->hw.itrace_started = 1; + + rec.header.type = PERF_RECORD_ITRACE_START; + rec.header.misc = 0; + rec.header.size = sizeof(rec); + rec.pid = perf_event_pid(event, current); + rec.tid = perf_event_tid(event, current); + + perf_event_header__init_id(&rec.header, &sample, event); + ret = perf_output_begin(&handle, event, rec.header.size); + + if (ret) + return; + + perf_output_put(&handle, rec); + perf_event__output_id_sample(event, &handle, &sample); + + perf_output_end(&handle); +} + +/* + * Generic event overflow handling, sampling. + */ + +static int __perf_event_overflow(struct perf_event *event, + int throttle, struct perf_sample_data *data, + struct pt_regs *regs) +{ + int events = atomic_read(&event->event_limit); + struct hw_perf_event *hwc = &event->hw; + u64 seq; + int ret = 0; + + /* + * Non-sampling counters might still use the PMI to fold short + * hardware counters, ignore those. + */ + if (unlikely(!is_sampling_event(event))) + return 0; + + seq = __this_cpu_read(perf_throttled_seq); + if (seq != hwc->interrupts_seq) { + hwc->interrupts_seq = seq; + hwc->interrupts = 1; + } else { + hwc->interrupts++; + if (unlikely(throttle + && hwc->interrupts >= max_samples_per_tick)) { + __this_cpu_inc(perf_throttled_count); + hwc->interrupts = MAX_INTERRUPTS; + perf_log_throttle(event, 0); + tick_nohz_full_kick(); + ret = 1; + } + } + + if (event->attr.freq) { + u64 now = perf_clock(); + s64 delta = now - hwc->freq_time_stamp; + + hwc->freq_time_stamp = now; + + if (delta > 0 && delta < 2*TICK_NSEC) + perf_adjust_period(event, delta, hwc->last_period, true); + } + + /* + * XXX event_limit might not quite work as expected on inherited + * events + */ + + event->pending_kill = POLL_IN; + if (events && atomic_dec_and_test(&event->event_limit)) { + ret = 1; + event->pending_kill = POLL_HUP; + event->pending_disable = 1; + irq_work_queue(&event->pending); + } + + if (event->overflow_handler) + event->overflow_handler(event, data, regs); + else + perf_event_output(event, data, regs); + + if (event->fasync && event->pending_kill) { + event->pending_wakeup = 1; + irq_work_queue(&event->pending); + } + + return ret; +} + +int perf_event_overflow(struct perf_event *event, + struct perf_sample_data *data, + struct pt_regs *regs) +{ + return __perf_event_overflow(event, 1, data, regs); +} + +/* + * Generic software event infrastructure + */ + +struct swevent_htable { + struct swevent_hlist *swevent_hlist; + struct mutex hlist_mutex; + int hlist_refcount; + + /* Recursion avoidance in each contexts */ + int recursion[PERF_NR_CONTEXTS]; + + /* Keeps track of cpu being initialized/exited */ + bool online; +}; + +static DEFINE_PER_CPU(struct swevent_htable, swevent_htable); + +/* + * We directly increment event->count and keep a second value in + * event->hw.period_left to count intervals. This period event + * is kept in the range [-sample_period, 0] so that we can use the + * sign as trigger. + */ + +u64 perf_swevent_set_period(struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + u64 period = hwc->last_period; + u64 nr, offset; + s64 old, val; + + hwc->last_period = hwc->sample_period; + +again: + old = val = local64_read(&hwc->period_left); + if (val < 0) + return 0; + + nr = div64_u64(period + val, period); + offset = nr * period; + val -= offset; + if (local64_cmpxchg(&hwc->period_left, old, val) != old) + goto again; + + return nr; +} + +static void perf_swevent_overflow(struct perf_event *event, u64 overflow, + struct perf_sample_data *data, + struct pt_regs *regs) +{ + struct hw_perf_event *hwc = &event->hw; + int throttle = 0; + + if (!overflow) + overflow = perf_swevent_set_period(event); + + if (hwc->interrupts == MAX_INTERRUPTS) + return; + + for (; overflow; overflow--) { + if (__perf_event_overflow(event, throttle, + data, regs)) { + /* + * We inhibit the overflow from happening when + * hwc->interrupts == MAX_INTERRUPTS. + */ + break; + } + throttle = 1; + } +} + +static void perf_swevent_event(struct perf_event *event, u64 nr, + struct perf_sample_data *data, + struct pt_regs *regs) +{ + struct hw_perf_event *hwc = &event->hw; + + local64_add(nr, &event->count); + + if (!regs) + return; + + if (!is_sampling_event(event)) + return; + + if ((event->attr.sample_type & PERF_SAMPLE_PERIOD) && !event->attr.freq) { + data->period = nr; + return perf_swevent_overflow(event, 1, data, regs); + } else + data->period = event->hw.last_period; + + if (nr == 1 && hwc->sample_period == 1 && !event->attr.freq) + return perf_swevent_overflow(event, 1, data, regs); + + if (local64_add_negative(nr, &hwc->period_left)) + return; + + perf_swevent_overflow(event, 0, data, regs); +} + +static int perf_exclude_event(struct perf_event *event, + struct pt_regs *regs) +{ + if (event->hw.state & PERF_HES_STOPPED) + return 1; + + if (regs) { + if (event->attr.exclude_user && user_mode(regs)) + return 1; + + if (event->attr.exclude_kernel && !user_mode(regs)) + return 1; + } + + return 0; +} + +static int perf_swevent_match(struct perf_event *event, + enum perf_type_id type, + u32 event_id, + struct perf_sample_data *data, + struct pt_regs *regs) +{ + if (event->attr.type != type) + return 0; + + if (event->attr.config != event_id) + return 0; + + if (perf_exclude_event(event, regs)) + return 0; + + return 1; +} + +static inline u64 swevent_hash(u64 type, u32 event_id) +{ + u64 val = event_id | (type << 32); + + return hash_64(val, SWEVENT_HLIST_BITS); +} + +static inline struct hlist_head * +__find_swevent_head(struct swevent_hlist *hlist, u64 type, u32 event_id) +{ + u64 hash = swevent_hash(type, event_id); + + return &hlist->heads[hash]; +} + +/* For the read side: events when they trigger */ +static inline struct hlist_head * +find_swevent_head_rcu(struct swevent_htable *swhash, u64 type, u32 event_id) +{ + struct swevent_hlist *hlist; + + hlist = rcu_dereference(swhash->swevent_hlist); + if (!hlist) + return NULL; + + return __find_swevent_head(hlist, type, event_id); +} + +/* For the event head insertion and removal in the hlist */ +static inline struct hlist_head * +find_swevent_head(struct swevent_htable *swhash, struct perf_event *event) +{ + struct swevent_hlist *hlist; + u32 event_id = event->attr.config; + u64 type = event->attr.type; + + /* + * Event scheduling is always serialized against hlist allocation + * and release. Which makes the protected version suitable here. + * The context lock guarantees that. + */ + hlist = rcu_dereference_protected(swhash->swevent_hlist, + lockdep_is_held(&event->ctx->lock)); + if (!hlist) + return NULL; + + return __find_swevent_head(hlist, type, event_id); +} + +static void do_perf_sw_event(enum perf_type_id type, u32 event_id, + u64 nr, + struct perf_sample_data *data, + struct pt_regs *regs) +{ + struct swevent_htable *swhash = this_cpu_ptr(&swevent_htable); + struct perf_event *event; + struct hlist_head *head; + + rcu_read_lock(); + head = find_swevent_head_rcu(swhash, type, event_id); + if (!head) + goto end; + + hlist_for_each_entry_rcu(event, head, hlist_entry) { + if (perf_swevent_match(event, type, event_id, data, regs)) + perf_swevent_event(event, nr, data, regs); + } +end: + rcu_read_unlock(); +} + +DEFINE_PER_CPU(struct pt_regs, __perf_regs[4]); + +int perf_swevent_get_recursion_context(void) +{ + struct swevent_htable *swhash = this_cpu_ptr(&swevent_htable); + + return get_recursion_context(swhash->recursion); +} +EXPORT_SYMBOL_GPL(perf_swevent_get_recursion_context); + +inline void perf_swevent_put_recursion_context(int rctx) +{ + struct swevent_htable *swhash = this_cpu_ptr(&swevent_htable); + + put_recursion_context(swhash->recursion, rctx); +} + +void ___perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr) +{ + struct perf_sample_data data; + + if (WARN_ON_ONCE(!regs)) + return; + + perf_sample_data_init(&data, addr, 0); + do_perf_sw_event(PERF_TYPE_SOFTWARE, event_id, nr, &data, regs); +} + +void __perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr) +{ + int rctx; + + preempt_disable_notrace(); + rctx = perf_swevent_get_recursion_context(); + if (unlikely(rctx < 0)) + goto fail; + + ___perf_sw_event(event_id, nr, regs, addr); + + perf_swevent_put_recursion_context(rctx); +fail: + preempt_enable_notrace(); +} + +static void perf_swevent_read(struct perf_event *event) +{ +} + +static int perf_swevent_add(struct perf_event *event, int flags) +{ + struct swevent_htable *swhash = this_cpu_ptr(&swevent_htable); + struct hw_perf_event *hwc = &event->hw; + struct hlist_head *head; + + if (is_sampling_event(event)) { + hwc->last_period = hwc->sample_period; + perf_swevent_set_period(event); + } + + hwc->state = !(flags & PERF_EF_START); + + head = find_swevent_head(swhash, event); + if (!head) { + /* + * We can race with cpu hotplug code. Do not + * WARN if the cpu just got unplugged. + */ + WARN_ON_ONCE(swhash->online); + return -EINVAL; + } + + hlist_add_head_rcu(&event->hlist_entry, head); + perf_event_update_userpage(event); + + return 0; +} + +static void perf_swevent_del(struct perf_event *event, int flags) +{ + hlist_del_rcu(&event->hlist_entry); +} + +static void perf_swevent_start(struct perf_event *event, int flags) +{ + event->hw.state = 0; +} + +static void perf_swevent_stop(struct perf_event *event, int flags) +{ + event->hw.state = PERF_HES_STOPPED; +} + +/* Deref the hlist from the update side */ +static inline struct swevent_hlist * +swevent_hlist_deref(struct swevent_htable *swhash) +{ + return rcu_dereference_protected(swhash->swevent_hlist, + lockdep_is_held(&swhash->hlist_mutex)); +} + +static void swevent_hlist_release(struct swevent_htable *swhash) +{ + struct swevent_hlist *hlist = swevent_hlist_deref(swhash); + + if (!hlist) + return; + + RCU_INIT_POINTER(swhash->swevent_hlist, NULL); + kfree_rcu(hlist, rcu_head); +} + +static void swevent_hlist_put_cpu(struct perf_event *event, int cpu) +{ + struct swevent_htable *swhash = &per_cpu(swevent_htable, cpu); + + mutex_lock(&swhash->hlist_mutex); + + if (!--swhash->hlist_refcount) + swevent_hlist_release(swhash); + + mutex_unlock(&swhash->hlist_mutex); +} + +static void swevent_hlist_put(struct perf_event *event) +{ + int cpu; + + for_each_possible_cpu(cpu) + swevent_hlist_put_cpu(event, cpu); +} + +static int swevent_hlist_get_cpu(struct perf_event *event, int cpu) +{ + struct swevent_htable *swhash = &per_cpu(swevent_htable, cpu); + int err = 0; + + mutex_lock(&swhash->hlist_mutex); + + if (!swevent_hlist_deref(swhash) && cpu_online(cpu)) { + struct swevent_hlist *hlist; + + hlist = kzalloc(sizeof(*hlist), GFP_KERNEL); + if (!hlist) { + err = -ENOMEM; + goto exit; + } + rcu_assign_pointer(swhash->swevent_hlist, hlist); + } + swhash->hlist_refcount++; +exit: + mutex_unlock(&swhash->hlist_mutex); + + return err; +} + +static int swevent_hlist_get(struct perf_event *event) +{ + int err; + int cpu, failed_cpu; + + get_online_cpus(); + for_each_possible_cpu(cpu) { + err = swevent_hlist_get_cpu(event, cpu); + if (err) { + failed_cpu = cpu; + goto fail; + } + } + put_online_cpus(); + + return 0; +fail: + for_each_possible_cpu(cpu) { + if (cpu == failed_cpu) + break; + swevent_hlist_put_cpu(event, cpu); + } + + put_online_cpus(); + return err; +} + +struct static_key perf_swevent_enabled[PERF_COUNT_SW_MAX]; + +static void sw_perf_event_destroy(struct perf_event *event) +{ + u64 event_id = event->attr.config; + + WARN_ON(event->parent); + + static_key_slow_dec(&perf_swevent_enabled[event_id]); + swevent_hlist_put(event); +} + +static int perf_swevent_init(struct perf_event *event) +{ + u64 event_id = event->attr.config; + + if (event->attr.type != PERF_TYPE_SOFTWARE) + return -ENOENT; + + /* + * no branch sampling for software events + */ + if (has_branch_stack(event)) + return -EOPNOTSUPP; + + switch (event_id) { + case PERF_COUNT_SW_CPU_CLOCK: + case PERF_COUNT_SW_TASK_CLOCK: + return -ENOENT; + + default: + break; + } + + if (event_id >= PERF_COUNT_SW_MAX) + return -ENOENT; + + if (!event->parent) { + int err; + + err = swevent_hlist_get(event); + if (err) + return err; + + static_key_slow_inc(&perf_swevent_enabled[event_id]); + event->destroy = sw_perf_event_destroy; + } + + return 0; +} + +static struct pmu perf_swevent = { + .task_ctx_nr = perf_sw_context, + + .capabilities = PERF_PMU_CAP_NO_NMI, + + .event_init = perf_swevent_init, + .add = perf_swevent_add, + .del = perf_swevent_del, + .start = perf_swevent_start, + .stop = perf_swevent_stop, + .read = perf_swevent_read, +}; + +#ifdef CONFIG_EVENT_TRACING + +static int perf_tp_filter_match(struct perf_event *event, + struct perf_sample_data *data) +{ + void *record = data->raw->data; + + if (likely(!event->filter) || filter_match_preds(event->filter, record)) + return 1; + return 0; +} + +static int perf_tp_event_match(struct perf_event *event, + struct perf_sample_data *data, + struct pt_regs *regs) +{ + if (event->hw.state & PERF_HES_STOPPED) + return 0; + /* + * All tracepoints are from kernel-space. + */ + if (event->attr.exclude_kernel) + return 0; + + if (!perf_tp_filter_match(event, data)) + return 0; + + return 1; +} + +void perf_tp_event(u64 addr, u64 count, void *record, int entry_size, + struct pt_regs *regs, struct hlist_head *head, int rctx, + struct task_struct *task) +{ + struct perf_sample_data data; + struct perf_event *event; + + struct perf_raw_record raw = { + .size = entry_size, + .data = record, + }; + + perf_sample_data_init(&data, addr, 0); + data.raw = &raw; + + hlist_for_each_entry_rcu(event, head, hlist_entry) { + if (perf_tp_event_match(event, &data, regs)) + perf_swevent_event(event, count, &data, regs); + } + + /* + * If we got specified a target task, also iterate its context and + * deliver this event there too. + */ + if (task && task != current) { + struct perf_event_context *ctx; + struct trace_entry *entry = record; + + rcu_read_lock(); + ctx = rcu_dereference(task->perf_event_ctxp[perf_sw_context]); + if (!ctx) + goto unlock; + + list_for_each_entry_rcu(event, &ctx->event_list, event_entry) { + if (event->attr.type != PERF_TYPE_TRACEPOINT) + continue; + if (event->attr.config != entry->type) + continue; + if (perf_tp_event_match(event, &data, regs)) + perf_swevent_event(event, count, &data, regs); + } +unlock: + rcu_read_unlock(); + } + + perf_swevent_put_recursion_context(rctx); +} +EXPORT_SYMBOL_GPL(perf_tp_event); + +static void tp_perf_event_destroy(struct perf_event *event) +{ + perf_trace_destroy(event); +} + +static int perf_tp_event_init(struct perf_event *event) +{ + int err; + + if (event->attr.type != PERF_TYPE_TRACEPOINT) + return -ENOENT; + + /* + * no branch sampling for tracepoint events + */ + if (has_branch_stack(event)) + return -EOPNOTSUPP; + + err = perf_trace_init(event); + if (err) + return err; + + event->destroy = tp_perf_event_destroy; + + return 0; +} + +static struct pmu perf_tracepoint = { + .task_ctx_nr = perf_sw_context, + + .event_init = perf_tp_event_init, + .add = perf_trace_add, + .del = perf_trace_del, + .start = perf_swevent_start, + .stop = perf_swevent_stop, + .read = perf_swevent_read, +}; + +static inline void perf_tp_register(void) +{ + perf_pmu_register(&perf_tracepoint, "tracepoint", PERF_TYPE_TRACEPOINT); +} + +static int perf_event_set_filter(struct perf_event *event, void __user *arg) +{ + char *filter_str; + int ret; + + if (event->attr.type != PERF_TYPE_TRACEPOINT) + return -EINVAL; + + filter_str = strndup_user(arg, PAGE_SIZE); + if (IS_ERR(filter_str)) + return PTR_ERR(filter_str); + + ret = ftrace_profile_set_filter(event, event->attr.config, filter_str); + + kfree(filter_str); + return ret; +} + +static void perf_event_free_filter(struct perf_event *event) +{ + ftrace_profile_free_filter(event); +} + +static int perf_event_set_bpf_prog(struct perf_event *event, u32 prog_fd) +{ + struct bpf_prog *prog; + + if (event->attr.type != PERF_TYPE_TRACEPOINT) + return -EINVAL; + + if (event->tp_event->prog) + return -EEXIST; + + if (!(event->tp_event->flags & TRACE_EVENT_FL_KPROBE)) + /* bpf programs can only be attached to kprobes */ + return -EINVAL; + + prog = bpf_prog_get(prog_fd); + if (IS_ERR(prog)) + return PTR_ERR(prog); + + if (prog->type != BPF_PROG_TYPE_KPROBE) { + /* valid fd, but invalid bpf program type */ + bpf_prog_put(prog); + return -EINVAL; + } + + event->tp_event->prog = prog; + + return 0; +} + +static void perf_event_free_bpf_prog(struct perf_event *event) +{ + struct bpf_prog *prog; + + if (!event->tp_event) + return; + + prog = event->tp_event->prog; + if (prog) { + event->tp_event->prog = NULL; + bpf_prog_put(prog); + } +} + +#else + +static inline void perf_tp_register(void) +{ +} + +static int perf_event_set_filter(struct perf_event *event, void __user *arg) +{ + return -ENOENT; +} + +static void perf_event_free_filter(struct perf_event *event) +{ +} + +static int perf_event_set_bpf_prog(struct perf_event *event, u32 prog_fd) +{ + return -ENOENT; +} + +static void perf_event_free_bpf_prog(struct perf_event *event) +{ +} +#endif /* CONFIG_EVENT_TRACING */ + +#ifdef CONFIG_HAVE_HW_BREAKPOINT +void perf_bp_event(struct perf_event *bp, void *data) +{ + struct perf_sample_data sample; + struct pt_regs *regs = data; + + perf_sample_data_init(&sample, bp->attr.bp_addr, 0); + + if (!bp->hw.state && !perf_exclude_event(bp, regs)) + perf_swevent_event(bp, 1, &sample, regs); +} +#endif + +/* + * hrtimer based swevent callback + */ + +static enum hrtimer_restart perf_swevent_hrtimer(struct hrtimer *hrtimer) +{ + enum hrtimer_restart ret = HRTIMER_RESTART; + struct perf_sample_data data; + struct pt_regs *regs; + struct perf_event *event; + u64 period; + + event = container_of(hrtimer, struct perf_event, hw.hrtimer); + + if (event->state != PERF_EVENT_STATE_ACTIVE) + return HRTIMER_NORESTART; + + event->pmu->read(event); + + perf_sample_data_init(&data, 0, event->hw.last_period); + regs = get_irq_regs(); + + if (regs && !perf_exclude_event(event, regs)) { + if (!(event->attr.exclude_idle && is_idle_task(current))) + if (__perf_event_overflow(event, 1, &data, regs)) + ret = HRTIMER_NORESTART; + } + + period = max_t(u64, 10000, event->hw.sample_period); + hrtimer_forward_now(hrtimer, ns_to_ktime(period)); + + return ret; +} + +static void perf_swevent_start_hrtimer(struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + s64 period; + + if (!is_sampling_event(event)) + return; + + period = local64_read(&hwc->period_left); + if (period) { + if (period < 0) + period = 10000; + + local64_set(&hwc->period_left, 0); + } else { + period = max_t(u64, 10000, hwc->sample_period); + } + __hrtimer_start_range_ns(&hwc->hrtimer, + ns_to_ktime(period), 0, + HRTIMER_MODE_REL_PINNED, 0); +} + +static void perf_swevent_cancel_hrtimer(struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + + if (is_sampling_event(event)) { + ktime_t remaining = hrtimer_get_remaining(&hwc->hrtimer); + local64_set(&hwc->period_left, ktime_to_ns(remaining)); + + hrtimer_cancel(&hwc->hrtimer); + } +} + +static void perf_swevent_init_hrtimer(struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + + if (!is_sampling_event(event)) + return; + + hrtimer_init(&hwc->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + hwc->hrtimer.function = perf_swevent_hrtimer; + hwc->hrtimer.irqsafe = 1; + + /* + * Since hrtimers have a fixed rate, we can do a static freq->period + * mapping and avoid the whole period adjust feedback stuff. + */ + if (event->attr.freq) { + long freq = event->attr.sample_freq; + + event->attr.sample_period = NSEC_PER_SEC / freq; + hwc->sample_period = event->attr.sample_period; + local64_set(&hwc->period_left, hwc->sample_period); + hwc->last_period = hwc->sample_period; + event->attr.freq = 0; + } +} + +/* + * Software event: cpu wall time clock + */ + +static void cpu_clock_event_update(struct perf_event *event) +{ + s64 prev; + u64 now; + + now = local_clock(); + prev = local64_xchg(&event->hw.prev_count, now); + local64_add(now - prev, &event->count); +} + +static void cpu_clock_event_start(struct perf_event *event, int flags) +{ + local64_set(&event->hw.prev_count, local_clock()); + perf_swevent_start_hrtimer(event); +} + +static void cpu_clock_event_stop(struct perf_event *event, int flags) +{ + perf_swevent_cancel_hrtimer(event); + cpu_clock_event_update(event); +} + +static int cpu_clock_event_add(struct perf_event *event, int flags) +{ + if (flags & PERF_EF_START) + cpu_clock_event_start(event, flags); + perf_event_update_userpage(event); + + return 0; +} + +static void cpu_clock_event_del(struct perf_event *event, int flags) +{ + cpu_clock_event_stop(event, flags); +} + +static void cpu_clock_event_read(struct perf_event *event) +{ + cpu_clock_event_update(event); +} + +static int cpu_clock_event_init(struct perf_event *event) +{ + if (event->attr.type != PERF_TYPE_SOFTWARE) + return -ENOENT; + + if (event->attr.config != PERF_COUNT_SW_CPU_CLOCK) + return -ENOENT; + + /* + * no branch sampling for software events + */ + if (has_branch_stack(event)) + return -EOPNOTSUPP; + + perf_swevent_init_hrtimer(event); + + return 0; +} + +static struct pmu perf_cpu_clock = { + .task_ctx_nr = perf_sw_context, + + .capabilities = PERF_PMU_CAP_NO_NMI, + + .event_init = cpu_clock_event_init, + .add = cpu_clock_event_add, + .del = cpu_clock_event_del, + .start = cpu_clock_event_start, + .stop = cpu_clock_event_stop, + .read = cpu_clock_event_read, +}; + +/* + * Software event: task time clock + */ + +static void task_clock_event_update(struct perf_event *event, u64 now) +{ + u64 prev; + s64 delta; + + prev = local64_xchg(&event->hw.prev_count, now); + delta = now - prev; + local64_add(delta, &event->count); +} + +static void task_clock_event_start(struct perf_event *event, int flags) +{ + local64_set(&event->hw.prev_count, event->ctx->time); + perf_swevent_start_hrtimer(event); +} + +static void task_clock_event_stop(struct perf_event *event, int flags) +{ + perf_swevent_cancel_hrtimer(event); + task_clock_event_update(event, event->ctx->time); +} + +static int task_clock_event_add(struct perf_event *event, int flags) +{ + if (flags & PERF_EF_START) + task_clock_event_start(event, flags); + perf_event_update_userpage(event); + + return 0; +} + +static void task_clock_event_del(struct perf_event *event, int flags) +{ + task_clock_event_stop(event, PERF_EF_UPDATE); +} + +static void task_clock_event_read(struct perf_event *event) +{ + u64 now = perf_clock(); + u64 delta = now - event->ctx->timestamp; + u64 time = event->ctx->time + delta; + + task_clock_event_update(event, time); +} + +static int task_clock_event_init(struct perf_event *event) +{ + if (event->attr.type != PERF_TYPE_SOFTWARE) + return -ENOENT; + + if (event->attr.config != PERF_COUNT_SW_TASK_CLOCK) + return -ENOENT; + + /* + * no branch sampling for software events + */ + if (has_branch_stack(event)) + return -EOPNOTSUPP; + + perf_swevent_init_hrtimer(event); + + return 0; +} + +static struct pmu perf_task_clock = { + .task_ctx_nr = perf_sw_context, + + .capabilities = PERF_PMU_CAP_NO_NMI, + + .event_init = task_clock_event_init, + .add = task_clock_event_add, + .del = task_clock_event_del, + .start = task_clock_event_start, + .stop = task_clock_event_stop, + .read = task_clock_event_read, +}; + +static void perf_pmu_nop_void(struct pmu *pmu) +{ +} + +static int perf_pmu_nop_int(struct pmu *pmu) +{ + return 0; +} + +static void perf_pmu_start_txn(struct pmu *pmu) +{ + perf_pmu_disable(pmu); +} + +static int perf_pmu_commit_txn(struct pmu *pmu) +{ + perf_pmu_enable(pmu); + return 0; +} + +static void perf_pmu_cancel_txn(struct pmu *pmu) +{ + perf_pmu_enable(pmu); +} + +static int perf_event_idx_default(struct perf_event *event) +{ + return 0; +} + +/* + * Ensures all contexts with the same task_ctx_nr have the same + * pmu_cpu_context too. + */ +static struct perf_cpu_context __percpu *find_pmu_context(int ctxn) +{ + struct pmu *pmu; + + if (ctxn < 0) + return NULL; + + list_for_each_entry(pmu, &pmus, entry) { + if (pmu->task_ctx_nr == ctxn) + return pmu->pmu_cpu_context; + } + + return NULL; +} + +static void update_pmu_context(struct pmu *pmu, struct pmu *old_pmu) +{ + int cpu; + + for_each_possible_cpu(cpu) { + struct perf_cpu_context *cpuctx; + + cpuctx = per_cpu_ptr(pmu->pmu_cpu_context, cpu); + + if (cpuctx->unique_pmu == old_pmu) + cpuctx->unique_pmu = pmu; + } +} + +static void free_pmu_context(struct pmu *pmu) +{ + struct pmu *i; + + mutex_lock(&pmus_lock); + /* + * Like a real lame refcount. + */ + list_for_each_entry(i, &pmus, entry) { + if (i->pmu_cpu_context == pmu->pmu_cpu_context) { + update_pmu_context(i, pmu); + goto out; + } + } + + free_percpu(pmu->pmu_cpu_context); +out: + mutex_unlock(&pmus_lock); +} +static struct idr pmu_idr; + +static ssize_t +type_show(struct device *dev, struct device_attribute *attr, char *page) +{ + struct pmu *pmu = dev_get_drvdata(dev); + + return snprintf(page, PAGE_SIZE-1, "%d\n", pmu->type); +} +static DEVICE_ATTR_RO(type); + +static ssize_t +perf_event_mux_interval_ms_show(struct device *dev, + struct device_attribute *attr, + char *page) +{ + struct pmu *pmu = dev_get_drvdata(dev); + + return snprintf(page, PAGE_SIZE-1, "%d\n", pmu->hrtimer_interval_ms); +} + +static ssize_t +perf_event_mux_interval_ms_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct pmu *pmu = dev_get_drvdata(dev); + int timer, cpu, ret; + + ret = kstrtoint(buf, 0, &timer); + if (ret) + return ret; + + if (timer < 1) + return -EINVAL; + + /* same value, noting to do */ + if (timer == pmu->hrtimer_interval_ms) + return count; + + pmu->hrtimer_interval_ms = timer; + + /* update all cpuctx for this PMU */ + for_each_possible_cpu(cpu) { + struct perf_cpu_context *cpuctx; + cpuctx = per_cpu_ptr(pmu->pmu_cpu_context, cpu); + cpuctx->hrtimer_interval = ns_to_ktime(NSEC_PER_MSEC * timer); + + if (hrtimer_active(&cpuctx->hrtimer)) + hrtimer_forward_now(&cpuctx->hrtimer, cpuctx->hrtimer_interval); + } + + return count; +} +static DEVICE_ATTR_RW(perf_event_mux_interval_ms); + +static struct attribute *pmu_dev_attrs[] = { + &dev_attr_type.attr, + &dev_attr_perf_event_mux_interval_ms.attr, + NULL, +}; +ATTRIBUTE_GROUPS(pmu_dev); + +static int pmu_bus_running; +static struct bus_type pmu_bus = { + .name = "event_source", + .dev_groups = pmu_dev_groups, +}; + +static void pmu_dev_release(struct device *dev) +{ + kfree(dev); +} + +static int pmu_dev_alloc(struct pmu *pmu) +{ + int ret = -ENOMEM; + + pmu->dev = kzalloc(sizeof(struct device), GFP_KERNEL); + if (!pmu->dev) + goto out; + + pmu->dev->groups = pmu->attr_groups; + device_initialize(pmu->dev); + ret = dev_set_name(pmu->dev, "%s", pmu->name); + if (ret) + goto free_dev; + + dev_set_drvdata(pmu->dev, pmu); + pmu->dev->bus = &pmu_bus; + pmu->dev->release = pmu_dev_release; + ret = device_add(pmu->dev); + if (ret) + goto free_dev; + +out: + return ret; + +free_dev: + put_device(pmu->dev); + goto out; +} + +static struct lock_class_key cpuctx_mutex; +static struct lock_class_key cpuctx_lock; + +int perf_pmu_register(struct pmu *pmu, const char *name, int type) +{ + int cpu, ret; + + mutex_lock(&pmus_lock); + ret = -ENOMEM; + pmu->pmu_disable_count = alloc_percpu(int); + if (!pmu->pmu_disable_count) + goto unlock; + + pmu->type = -1; + if (!name) + goto skip_type; + pmu->name = name; + + if (type < 0) { + type = idr_alloc(&pmu_idr, pmu, PERF_TYPE_MAX, 0, GFP_KERNEL); + if (type < 0) { + ret = type; + goto free_pdc; + } + } + pmu->type = type; + + if (pmu_bus_running) { + ret = pmu_dev_alloc(pmu); + if (ret) + goto free_idr; + } + +skip_type: + pmu->pmu_cpu_context = find_pmu_context(pmu->task_ctx_nr); + if (pmu->pmu_cpu_context) + goto got_cpu_context; + + ret = -ENOMEM; + pmu->pmu_cpu_context = alloc_percpu(struct perf_cpu_context); + if (!pmu->pmu_cpu_context) + goto free_dev; + + for_each_possible_cpu(cpu) { + struct perf_cpu_context *cpuctx; + + cpuctx = per_cpu_ptr(pmu->pmu_cpu_context, cpu); + __perf_event_init_context(&cpuctx->ctx); + lockdep_set_class(&cpuctx->ctx.mutex, &cpuctx_mutex); + lockdep_set_class(&cpuctx->ctx.lock, &cpuctx_lock); + cpuctx->ctx.pmu = pmu; + + __perf_cpu_hrtimer_init(cpuctx, cpu); + + cpuctx->unique_pmu = pmu; + } + +got_cpu_context: + if (!pmu->start_txn) { + if (pmu->pmu_enable) { + /* + * If we have pmu_enable/pmu_disable calls, install + * transaction stubs that use that to try and batch + * hardware accesses. + */ + pmu->start_txn = perf_pmu_start_txn; + pmu->commit_txn = perf_pmu_commit_txn; + pmu->cancel_txn = perf_pmu_cancel_txn; + } else { + pmu->start_txn = perf_pmu_nop_void; + pmu->commit_txn = perf_pmu_nop_int; + pmu->cancel_txn = perf_pmu_nop_void; + } + } + + if (!pmu->pmu_enable) { + pmu->pmu_enable = perf_pmu_nop_void; + pmu->pmu_disable = perf_pmu_nop_void; + } + + if (!pmu->event_idx) + pmu->event_idx = perf_event_idx_default; + + list_add_rcu(&pmu->entry, &pmus); + atomic_set(&pmu->exclusive_cnt, 0); + ret = 0; +unlock: + mutex_unlock(&pmus_lock); + + return ret; + +free_dev: + device_del(pmu->dev); + put_device(pmu->dev); + +free_idr: + if (pmu->type >= PERF_TYPE_MAX) + idr_remove(&pmu_idr, pmu->type); + +free_pdc: + free_percpu(pmu->pmu_disable_count); + goto unlock; +} +EXPORT_SYMBOL_GPL(perf_pmu_register); + +void perf_pmu_unregister(struct pmu *pmu) +{ + mutex_lock(&pmus_lock); + list_del_rcu(&pmu->entry); + mutex_unlock(&pmus_lock); + + /* + * We dereference the pmu list under both SRCU and regular RCU, so + * synchronize against both of those. + */ + synchronize_srcu(&pmus_srcu); + synchronize_rcu(); + + free_percpu(pmu->pmu_disable_count); + if (pmu->type >= PERF_TYPE_MAX) + idr_remove(&pmu_idr, pmu->type); + device_del(pmu->dev); + put_device(pmu->dev); + free_pmu_context(pmu); +} +EXPORT_SYMBOL_GPL(perf_pmu_unregister); + +static int perf_try_init_event(struct pmu *pmu, struct perf_event *event) +{ + struct perf_event_context *ctx = NULL; + int ret; + + if (!try_module_get(pmu->module)) + return -ENODEV; + + if (event->group_leader != event) { + /* + * This ctx->mutex can nest when we're called through + * inheritance. See the perf_event_ctx_lock_nested() comment. + */ + ctx = perf_event_ctx_lock_nested(event->group_leader, + SINGLE_DEPTH_NESTING); + BUG_ON(!ctx); + } + + event->pmu = pmu; + ret = pmu->event_init(event); + + if (ctx) + perf_event_ctx_unlock(event->group_leader, ctx); + + if (ret) + module_put(pmu->module); + + return ret; +} + +struct pmu *perf_init_event(struct perf_event *event) +{ + struct pmu *pmu = NULL; + int idx; + int ret; + + idx = srcu_read_lock(&pmus_srcu); + + rcu_read_lock(); + pmu = idr_find(&pmu_idr, event->attr.type); + rcu_read_unlock(); + if (pmu) { + ret = perf_try_init_event(pmu, event); + if (ret) + pmu = ERR_PTR(ret); + goto unlock; + } + + list_for_each_entry_rcu(pmu, &pmus, entry) { + ret = perf_try_init_event(pmu, event); + if (!ret) + goto unlock; + + if (ret != -ENOENT) { + pmu = ERR_PTR(ret); + goto unlock; + } + } + pmu = ERR_PTR(-ENOENT); +unlock: + srcu_read_unlock(&pmus_srcu, idx); + + return pmu; +} + +static void account_event_cpu(struct perf_event *event, int cpu) +{ + if (event->parent) + return; + + if (is_cgroup_event(event)) + atomic_inc(&per_cpu(perf_cgroup_events, cpu)); +} + +static void account_event(struct perf_event *event) +{ + if (event->parent) + return; + + if (event->attach_state & PERF_ATTACH_TASK) + static_key_slow_inc(&perf_sched_events.key); + if (event->attr.mmap || event->attr.mmap_data) + atomic_inc(&nr_mmap_events); + if (event->attr.comm) + atomic_inc(&nr_comm_events); + if (event->attr.task) + atomic_inc(&nr_task_events); + if (event->attr.freq) { + if (atomic_inc_return(&nr_freq_events) == 1) + tick_nohz_full_kick_all(); + } + if (has_branch_stack(event)) + static_key_slow_inc(&perf_sched_events.key); + if (is_cgroup_event(event)) + static_key_slow_inc(&perf_sched_events.key); + + account_event_cpu(event, event->cpu); +} + +/* + * Allocate and initialize a event structure + */ +static struct perf_event * +perf_event_alloc(struct perf_event_attr *attr, int cpu, + struct task_struct *task, + struct perf_event *group_leader, + struct perf_event *parent_event, + perf_overflow_handler_t overflow_handler, + void *context, int cgroup_fd) +{ + struct pmu *pmu; + struct perf_event *event; + struct hw_perf_event *hwc; + long err = -EINVAL; + + if ((unsigned)cpu >= nr_cpu_ids) { + if (!task || cpu != -1) + return ERR_PTR(-EINVAL); + } + + event = kzalloc(sizeof(*event), GFP_KERNEL); + if (!event) + return ERR_PTR(-ENOMEM); + + /* + * Single events are their own group leaders, with an + * empty sibling list: + */ + if (!group_leader) + group_leader = event; + + mutex_init(&event->child_mutex); + INIT_LIST_HEAD(&event->child_list); + + INIT_LIST_HEAD(&event->group_entry); + INIT_LIST_HEAD(&event->event_entry); + INIT_LIST_HEAD(&event->sibling_list); + INIT_LIST_HEAD(&event->rb_entry); + INIT_LIST_HEAD(&event->active_entry); + INIT_HLIST_NODE(&event->hlist_entry); + + + init_waitqueue_head(&event->waitq); + init_irq_work(&event->pending, perf_pending_event); + + mutex_init(&event->mmap_mutex); + + atomic_long_set(&event->refcount, 1); + event->cpu = cpu; + event->attr = *attr; + event->group_leader = group_leader; + event->pmu = NULL; + event->oncpu = -1; + + event->parent = parent_event; + + event->ns = get_pid_ns(task_active_pid_ns(current)); + event->id = atomic64_inc_return(&perf_event_id); + + event->state = PERF_EVENT_STATE_INACTIVE; + + if (task) { + event->attach_state = PERF_ATTACH_TASK; + /* + * XXX pmu::event_init needs to know what task to account to + * and we cannot use the ctx information because we need the + * pmu before we get a ctx. + */ + event->hw.target = task; + } + + event->clock = &local_clock; + if (parent_event) + event->clock = parent_event->clock; + + if (!overflow_handler && parent_event) { + overflow_handler = parent_event->overflow_handler; + context = parent_event->overflow_handler_context; + } + + event->overflow_handler = overflow_handler; + event->overflow_handler_context = context; + + perf_event__state_init(event); + + pmu = NULL; + + hwc = &event->hw; + hwc->sample_period = attr->sample_period; + if (attr->freq && attr->sample_freq) + hwc->sample_period = 1; + hwc->last_period = hwc->sample_period; + + local64_set(&hwc->period_left, hwc->sample_period); + + /* + * we currently do not support PERF_FORMAT_GROUP on inherited events + */ + if (attr->inherit && (attr->read_format & PERF_FORMAT_GROUP)) + goto err_ns; + + if (!has_branch_stack(event)) + event->attr.branch_sample_type = 0; + + if (cgroup_fd != -1) { + err = perf_cgroup_connect(cgroup_fd, event, attr, group_leader); + if (err) + goto err_ns; + } + + pmu = perf_init_event(event); + if (!pmu) + goto err_ns; + else if (IS_ERR(pmu)) { + err = PTR_ERR(pmu); + goto err_ns; + } + + err = exclusive_event_init(event); + if (err) + goto err_pmu; + + if (!event->parent) { + if (event->attr.sample_type & PERF_SAMPLE_CALLCHAIN) { + err = get_callchain_buffers(); + if (err) + goto err_per_task; + } + } + + return event; + +err_per_task: + exclusive_event_destroy(event); + +err_pmu: + if (event->destroy) + event->destroy(event); + module_put(pmu->module); +err_ns: + if (is_cgroup_event(event)) + perf_detach_cgroup(event); + if (event->ns) + put_pid_ns(event->ns); + kfree(event); + + return ERR_PTR(err); +} + +static int perf_copy_attr(struct perf_event_attr __user *uattr, + struct perf_event_attr *attr) +{ + u32 size; + int ret; + + if (!access_ok(VERIFY_WRITE, uattr, PERF_ATTR_SIZE_VER0)) + return -EFAULT; + + /* + * zero the full structure, so that a short copy will be nice. + */ + memset(attr, 0, sizeof(*attr)); + + ret = get_user(size, &uattr->size); + if (ret) + return ret; + + if (size > PAGE_SIZE) /* silly large */ + goto err_size; + + if (!size) /* abi compat */ + size = PERF_ATTR_SIZE_VER0; + + if (size < PERF_ATTR_SIZE_VER0) + goto err_size; + + /* + * If we're handed a bigger struct than we know of, + * ensure all the unknown bits are 0 - i.e. new + * user-space does not rely on any kernel feature + * extensions we dont know about yet. + */ + if (size > sizeof(*attr)) { + unsigned char __user *addr; + unsigned char __user *end; + unsigned char val; + + addr = (void __user *)uattr + sizeof(*attr); + end = (void __user *)uattr + size; + + for (; addr < end; addr++) { + ret = get_user(val, addr); + if (ret) + return ret; + if (val) + goto err_size; + } + size = sizeof(*attr); + } + + ret = copy_from_user(attr, uattr, size); + if (ret) + return -EFAULT; + + if (attr->__reserved_1) + return -EINVAL; + + if (attr->sample_type & ~(PERF_SAMPLE_MAX-1)) + return -EINVAL; + + if (attr->read_format & ~(PERF_FORMAT_MAX-1)) + return -EINVAL; + + if (attr->sample_type & PERF_SAMPLE_BRANCH_STACK) { + u64 mask = attr->branch_sample_type; + + /* only using defined bits */ + if (mask & ~(PERF_SAMPLE_BRANCH_MAX-1)) + return -EINVAL; + + /* at least one branch bit must be set */ + if (!(mask & ~PERF_SAMPLE_BRANCH_PLM_ALL)) + return -EINVAL; + + /* propagate priv level, when not set for branch */ + if (!(mask & PERF_SAMPLE_BRANCH_PLM_ALL)) { + + /* exclude_kernel checked on syscall entry */ + if (!attr->exclude_kernel) + mask |= PERF_SAMPLE_BRANCH_KERNEL; + + if (!attr->exclude_user) + mask |= PERF_SAMPLE_BRANCH_USER; + + if (!attr->exclude_hv) + mask |= PERF_SAMPLE_BRANCH_HV; + /* + * adjust user setting (for HW filter setup) + */ + attr->branch_sample_type = mask; + } + /* privileged levels capture (kernel, hv): check permissions */ + if ((mask & PERF_SAMPLE_BRANCH_PERM_PLM) + && perf_paranoid_kernel() && !capable(CAP_SYS_ADMIN)) + return -EACCES; + } + + if (attr->sample_type & PERF_SAMPLE_REGS_USER) { + ret = perf_reg_validate(attr->sample_regs_user); + if (ret) + return ret; + } + + if (attr->sample_type & PERF_SAMPLE_STACK_USER) { + if (!arch_perf_have_user_stack_dump()) + return -ENOSYS; + + /* + * We have __u32 type for the size, but so far + * we can only use __u16 as maximum due to the + * __u16 sample size limit. + */ + if (attr->sample_stack_user >= USHRT_MAX) + ret = -EINVAL; + else if (!IS_ALIGNED(attr->sample_stack_user, sizeof(u64))) + ret = -EINVAL; + } + + if (attr->sample_type & PERF_SAMPLE_REGS_INTR) + ret = perf_reg_validate(attr->sample_regs_intr); +out: + return ret; + +err_size: + put_user(sizeof(*attr), &uattr->size); + ret = -E2BIG; + goto out; +} + +static int +perf_event_set_output(struct perf_event *event, struct perf_event *output_event) +{ + struct ring_buffer *rb = NULL; + int ret = -EINVAL; + + if (!output_event) + goto set; + + /* don't allow circular references */ + if (event == output_event) + goto out; + + /* + * Don't allow cross-cpu buffers + */ + if (output_event->cpu != event->cpu) + goto out; + + /* + * If its not a per-cpu rb, it must be the same task. + */ + if (output_event->cpu == -1 && output_event->ctx != event->ctx) + goto out; + + /* + * Mixing clocks in the same buffer is trouble you don't need. + */ + if (output_event->clock != event->clock) + goto out; + + /* + * If both events generate aux data, they must be on the same PMU + */ + if (has_aux(event) && has_aux(output_event) && + event->pmu != output_event->pmu) + goto out; + +set: + mutex_lock(&event->mmap_mutex); + /* Can't redirect output if we've got an active mmap() */ + if (atomic_read(&event->mmap_count)) + goto unlock; + + if (output_event) { + /* get the rb we want to redirect to */ + rb = ring_buffer_get(output_event); + if (!rb) + goto unlock; + } + + ring_buffer_attach(event, rb); + + ret = 0; +unlock: + mutex_unlock(&event->mmap_mutex); + +out: + return ret; +} + +static void mutex_lock_double(struct mutex *a, struct mutex *b) +{ + if (b < a) + swap(a, b); + + mutex_lock(a); + mutex_lock_nested(b, SINGLE_DEPTH_NESTING); +} + +static int perf_event_set_clock(struct perf_event *event, clockid_t clk_id) +{ + bool nmi_safe = false; + + switch (clk_id) { + case CLOCK_MONOTONIC: + event->clock = &ktime_get_mono_fast_ns; + nmi_safe = true; + break; + + case CLOCK_MONOTONIC_RAW: + event->clock = &ktime_get_raw_fast_ns; + nmi_safe = true; + break; + + case CLOCK_REALTIME: + event->clock = &ktime_get_real_ns; + break; + + case CLOCK_BOOTTIME: + event->clock = &ktime_get_boot_ns; + break; + + case CLOCK_TAI: + event->clock = &ktime_get_tai_ns; + break; + + default: + return -EINVAL; + } + + if (!nmi_safe && !(event->pmu->capabilities & PERF_PMU_CAP_NO_NMI)) + return -EINVAL; + + return 0; +} + +/** + * sys_perf_event_open - open a performance event, associate it to a task/cpu + * + * @attr_uptr: event_id type attributes for monitoring/sampling + * @pid: target pid + * @cpu: target cpu + * @group_fd: group leader event fd + */ +SYSCALL_DEFINE5(perf_event_open, + struct perf_event_attr __user *, attr_uptr, + pid_t, pid, int, cpu, int, group_fd, unsigned long, flags) +{ + struct perf_event *group_leader = NULL, *output_event = NULL; + struct perf_event *event, *sibling; + struct perf_event_attr attr; + struct perf_event_context *ctx, *uninitialized_var(gctx); + struct file *event_file = NULL; + struct fd group = {NULL, 0}; + struct task_struct *task = NULL; + struct pmu *pmu; + int event_fd; + int move_group = 0; + int err; + int f_flags = O_RDWR; + int cgroup_fd = -1; + + /* for future expandability... */ + if (flags & ~PERF_FLAG_ALL) + return -EINVAL; + + err = perf_copy_attr(attr_uptr, &attr); + if (err) + return err; + + if (!attr.exclude_kernel) { + if (perf_paranoid_kernel() && !capable(CAP_SYS_ADMIN)) + return -EACCES; + } + + if (attr.freq) { + if (attr.sample_freq > sysctl_perf_event_sample_rate) + return -EINVAL; + } else { + if (attr.sample_period & (1ULL << 63)) + return -EINVAL; + } + + /* + * In cgroup mode, the pid argument is used to pass the fd + * opened to the cgroup directory in cgroupfs. The cpu argument + * designates the cpu on which to monitor threads from that + * cgroup. + */ + if ((flags & PERF_FLAG_PID_CGROUP) && (pid == -1 || cpu == -1)) + return -EINVAL; + + if (flags & PERF_FLAG_FD_CLOEXEC) + f_flags |= O_CLOEXEC; + + event_fd = get_unused_fd_flags(f_flags); + if (event_fd < 0) + return event_fd; + + if (group_fd != -1) { + err = perf_fget_light(group_fd, &group); + if (err) + goto err_fd; + group_leader = group.file->private_data; + if (flags & PERF_FLAG_FD_OUTPUT) + output_event = group_leader; + if (flags & PERF_FLAG_FD_NO_GROUP) + group_leader = NULL; + } + + if (pid != -1 && !(flags & PERF_FLAG_PID_CGROUP)) { + task = find_lively_task_by_vpid(pid); + if (IS_ERR(task)) { + err = PTR_ERR(task); + goto err_group_fd; + } + } + + if (task && group_leader && + group_leader->attr.inherit != attr.inherit) { + err = -EINVAL; + goto err_task; + } + + get_online_cpus(); + + if (flags & PERF_FLAG_PID_CGROUP) + cgroup_fd = pid; + + event = perf_event_alloc(&attr, cpu, task, group_leader, NULL, + NULL, NULL, cgroup_fd); + if (IS_ERR(event)) { + err = PTR_ERR(event); + goto err_cpus; + } + + if (is_sampling_event(event)) { + if (event->pmu->capabilities & PERF_PMU_CAP_NO_INTERRUPT) { + err = -ENOTSUPP; + goto err_alloc; + } + } + + account_event(event); + + /* + * Special case software events and allow them to be part of + * any hardware group. + */ + pmu = event->pmu; + + if (attr.use_clockid) { + err = perf_event_set_clock(event, attr.clockid); + if (err) + goto err_alloc; + } + + if (group_leader && + (is_software_event(event) != is_software_event(group_leader))) { + if (is_software_event(event)) { + /* + * If event and group_leader are not both a software + * event, and event is, then group leader is not. + * + * Allow the addition of software events to !software + * groups, this is safe because software events never + * fail to schedule. + */ + pmu = group_leader->pmu; + } else if (is_software_event(group_leader) && + (group_leader->group_flags & PERF_GROUP_SOFTWARE)) { + /* + * In case the group is a pure software group, and we + * try to add a hardware event, move the whole group to + * the hardware context. + */ + move_group = 1; + } + } + + /* + * Get the target context (task or percpu): + */ + ctx = find_get_context(pmu, task, event); + if (IS_ERR(ctx)) { + err = PTR_ERR(ctx); + goto err_alloc; + } + + if ((pmu->capabilities & PERF_PMU_CAP_EXCLUSIVE) && group_leader) { + err = -EBUSY; + goto err_context; + } + + if (task) { + put_task_struct(task); + task = NULL; + } + + /* + * Look up the group leader (we will attach this event to it): + */ + if (group_leader) { + err = -EINVAL; + + /* + * Do not allow a recursive hierarchy (this new sibling + * becoming part of another group-sibling): + */ + if (group_leader->group_leader != group_leader) + goto err_context; + + /* All events in a group should have the same clock */ + if (group_leader->clock != event->clock) + goto err_context; + + /* + * Do not allow to attach to a group in a different + * task or CPU context: + */ + if (move_group) { + /* + * Make sure we're both on the same task, or both + * per-cpu events. + */ + if (group_leader->ctx->task != ctx->task) + goto err_context; + + /* + * Make sure we're both events for the same CPU; + * grouping events for different CPUs is broken; since + * you can never concurrently schedule them anyhow. + */ + if (group_leader->cpu != event->cpu) + goto err_context; + } else { + if (group_leader->ctx != ctx) + goto err_context; + } + + /* + * Only a group leader can be exclusive or pinned + */ + if (attr.exclusive || attr.pinned) + goto err_context; + } + + if (output_event) { + err = perf_event_set_output(event, output_event); + if (err) + goto err_context; + } + + event_file = anon_inode_getfile("[perf_event]", &perf_fops, event, + f_flags); + if (IS_ERR(event_file)) { + err = PTR_ERR(event_file); + goto err_context; + } + + if (move_group) { + gctx = group_leader->ctx; + + /* + * See perf_event_ctx_lock() for comments on the details + * of swizzling perf_event::ctx. + */ + mutex_lock_double(&gctx->mutex, &ctx->mutex); + + perf_remove_from_context(group_leader, false); + + list_for_each_entry(sibling, &group_leader->sibling_list, + group_entry) { + perf_remove_from_context(sibling, false); + put_ctx(gctx); + } + } else { + mutex_lock(&ctx->mutex); + } + + WARN_ON_ONCE(ctx->parent_ctx); + + if (move_group) { + /* + * Wait for everybody to stop referencing the events through + * the old lists, before installing it on new lists. + */ + synchronize_rcu(); + + /* + * Install the group siblings before the group leader. + * + * Because a group leader will try and install the entire group + * (through the sibling list, which is still in-tact), we can + * end up with siblings installed in the wrong context. + * + * By installing siblings first we NO-OP because they're not + * reachable through the group lists. + */ + list_for_each_entry(sibling, &group_leader->sibling_list, + group_entry) { + perf_event__state_init(sibling); + perf_install_in_context(ctx, sibling, sibling->cpu); + get_ctx(ctx); + } + + /* + * Removing from the context ends up with disabled + * event. What we want here is event in the initial + * startup state, ready to be add into new context. + */ + perf_event__state_init(group_leader); + perf_install_in_context(ctx, group_leader, group_leader->cpu); + get_ctx(ctx); + } + + if (!exclusive_event_installable(event, ctx)) { + err = -EBUSY; + mutex_unlock(&ctx->mutex); + fput(event_file); + goto err_context; + } + + perf_install_in_context(ctx, event, event->cpu); + perf_unpin_context(ctx); + + if (move_group) { + mutex_unlock(&gctx->mutex); + put_ctx(gctx); + } + mutex_unlock(&ctx->mutex); + + put_online_cpus(); + + event->owner = current; + + mutex_lock(¤t->perf_event_mutex); + list_add_tail(&event->owner_entry, ¤t->perf_event_list); + mutex_unlock(¤t->perf_event_mutex); + + /* + * Precalculate sample_data sizes + */ + perf_event__header_size(event); + perf_event__id_header_size(event); + + /* + * Drop the reference on the group_event after placing the + * new event on the sibling_list. This ensures destruction + * of the group leader will find the pointer to itself in + * perf_group_detach(). + */ + fdput(group); + fd_install(event_fd, event_file); + return event_fd; + +err_context: + perf_unpin_context(ctx); + put_ctx(ctx); +err_alloc: + free_event(event); +err_cpus: + put_online_cpus(); +err_task: + if (task) + put_task_struct(task); +err_group_fd: + fdput(group); +err_fd: + put_unused_fd(event_fd); + return err; +} + +/** + * perf_event_create_kernel_counter + * + * @attr: attributes of the counter to create + * @cpu: cpu in which the counter is bound + * @task: task to profile (NULL for percpu) + */ +struct perf_event * +perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu, + struct task_struct *task, + perf_overflow_handler_t overflow_handler, + void *context) +{ + struct perf_event_context *ctx; + struct perf_event *event; + int err; + + /* + * Get the target context (task or percpu): + */ + + event = perf_event_alloc(attr, cpu, task, NULL, NULL, + overflow_handler, context, -1); + if (IS_ERR(event)) { + err = PTR_ERR(event); + goto err; + } + + /* Mark owner so we could distinguish it from user events. */ + event->owner = EVENT_OWNER_KERNEL; + + account_event(event); + + ctx = find_get_context(event->pmu, task, event); + if (IS_ERR(ctx)) { + err = PTR_ERR(ctx); + goto err_free; + } + + WARN_ON_ONCE(ctx->parent_ctx); + mutex_lock(&ctx->mutex); + if (!exclusive_event_installable(event, ctx)) { + mutex_unlock(&ctx->mutex); + perf_unpin_context(ctx); + put_ctx(ctx); + err = -EBUSY; + goto err_free; + } + + perf_install_in_context(ctx, event, cpu); + perf_unpin_context(ctx); + mutex_unlock(&ctx->mutex); + + return event; + +err_free: + free_event(event); +err: + return ERR_PTR(err); +} +EXPORT_SYMBOL_GPL(perf_event_create_kernel_counter); + +void perf_pmu_migrate_context(struct pmu *pmu, int src_cpu, int dst_cpu) +{ + struct perf_event_context *src_ctx; + struct perf_event_context *dst_ctx; + struct perf_event *event, *tmp; + LIST_HEAD(events); + + src_ctx = &per_cpu_ptr(pmu->pmu_cpu_context, src_cpu)->ctx; + dst_ctx = &per_cpu_ptr(pmu->pmu_cpu_context, dst_cpu)->ctx; + + /* + * See perf_event_ctx_lock() for comments on the details + * of swizzling perf_event::ctx. + */ + mutex_lock_double(&src_ctx->mutex, &dst_ctx->mutex); + list_for_each_entry_safe(event, tmp, &src_ctx->event_list, + event_entry) { + perf_remove_from_context(event, false); + unaccount_event_cpu(event, src_cpu); + put_ctx(src_ctx); + list_add(&event->migrate_entry, &events); + } + + /* + * Wait for the events to quiesce before re-instating them. + */ + synchronize_rcu(); + + /* + * Re-instate events in 2 passes. + * + * Skip over group leaders and only install siblings on this first + * pass, siblings will not get enabled without a leader, however a + * leader will enable its siblings, even if those are still on the old + * context. + */ + list_for_each_entry_safe(event, tmp, &events, migrate_entry) { + if (event->group_leader == event) + continue; + + list_del(&event->migrate_entry); + if (event->state >= PERF_EVENT_STATE_OFF) + event->state = PERF_EVENT_STATE_INACTIVE; + account_event_cpu(event, dst_cpu); + perf_install_in_context(dst_ctx, event, dst_cpu); + get_ctx(dst_ctx); + } + + /* + * Once all the siblings are setup properly, install the group leaders + * to make it go. + */ + list_for_each_entry_safe(event, tmp, &events, migrate_entry) { + list_del(&event->migrate_entry); + if (event->state >= PERF_EVENT_STATE_OFF) + event->state = PERF_EVENT_STATE_INACTIVE; + account_event_cpu(event, dst_cpu); + perf_install_in_context(dst_ctx, event, dst_cpu); + get_ctx(dst_ctx); + } + mutex_unlock(&dst_ctx->mutex); + mutex_unlock(&src_ctx->mutex); +} +EXPORT_SYMBOL_GPL(perf_pmu_migrate_context); + +static void sync_child_event(struct perf_event *child_event, + struct task_struct *child) +{ + struct perf_event *parent_event = child_event->parent; + u64 child_val; + + if (child_event->attr.inherit_stat) + perf_event_read_event(child_event, child); + + child_val = perf_event_count(child_event); + + /* + * Add back the child's count to the parent's count: + */ + atomic64_add(child_val, &parent_event->child_count); + atomic64_add(child_event->total_time_enabled, + &parent_event->child_total_time_enabled); + atomic64_add(child_event->total_time_running, + &parent_event->child_total_time_running); + + /* + * Remove this event from the parent's list + */ + WARN_ON_ONCE(parent_event->ctx->parent_ctx); + mutex_lock(&parent_event->child_mutex); + list_del_init(&child_event->child_list); + mutex_unlock(&parent_event->child_mutex); + + /* + * Make sure user/parent get notified, that we just + * lost one event. + */ + perf_event_wakeup(parent_event); + + /* + * Release the parent event, if this was the last + * reference to it. + */ + put_event(parent_event); +} + +static void +__perf_event_exit_task(struct perf_event *child_event, + struct perf_event_context *child_ctx, + struct task_struct *child) +{ + /* + * Do not destroy the 'original' grouping; because of the context + * switch optimization the original events could've ended up in a + * random child task. + * + * If we were to destroy the original group, all group related + * operations would cease to function properly after this random + * child dies. + * + * Do destroy all inherited groups, we don't care about those + * and being thorough is better. + */ + perf_remove_from_context(child_event, !!child_event->parent); + + /* + * It can happen that the parent exits first, and has events + * that are still around due to the child reference. These + * events need to be zapped. + */ + if (child_event->parent) { + sync_child_event(child_event, child); + free_event(child_event); + } else { + child_event->state = PERF_EVENT_STATE_EXIT; + perf_event_wakeup(child_event); + } +} + +static void perf_event_exit_task_context(struct task_struct *child, int ctxn) +{ + struct perf_event *child_event, *next; + struct perf_event_context *child_ctx, *clone_ctx = NULL; + unsigned long flags; + + if (likely(!child->perf_event_ctxp[ctxn])) { + perf_event_task(child, NULL, 0); + return; + } + + local_irq_save(flags); + /* + * We can't reschedule here because interrupts are disabled, + * and either child is current or it is a task that can't be + * scheduled, so we are now safe from rescheduling changing + * our context. + */ + child_ctx = rcu_dereference_raw(child->perf_event_ctxp[ctxn]); + + /* + * Take the context lock here so that if find_get_context is + * reading child->perf_event_ctxp, we wait until it has + * incremented the context's refcount before we do put_ctx below. + */ + raw_spin_lock(&child_ctx->lock); + task_ctx_sched_out(child_ctx); + child->perf_event_ctxp[ctxn] = NULL; + + /* + * If this context is a clone; unclone it so it can't get + * swapped to another process while we're removing all + * the events from it. + */ + clone_ctx = unclone_ctx(child_ctx); + update_context_time(child_ctx); + raw_spin_unlock_irqrestore(&child_ctx->lock, flags); + + if (clone_ctx) + put_ctx(clone_ctx); + + /* + * Report the task dead after unscheduling the events so that we + * won't get any samples after PERF_RECORD_EXIT. We can however still + * get a few PERF_RECORD_READ events. + */ + perf_event_task(child, child_ctx, 0); + + /* + * We can recurse on the same lock type through: + * + * __perf_event_exit_task() + * sync_child_event() + * put_event() + * mutex_lock(&ctx->mutex) + * + * But since its the parent context it won't be the same instance. + */ + mutex_lock(&child_ctx->mutex); + + list_for_each_entry_safe(child_event, next, &child_ctx->event_list, event_entry) + __perf_event_exit_task(child_event, child_ctx, child); + + mutex_unlock(&child_ctx->mutex); + + put_ctx(child_ctx); +} + +/* + * When a child task exits, feed back event values to parent events. + */ +void perf_event_exit_task(struct task_struct *child) +{ + struct perf_event *event, *tmp; + int ctxn; + + mutex_lock(&child->perf_event_mutex); + list_for_each_entry_safe(event, tmp, &child->perf_event_list, + owner_entry) { + list_del_init(&event->owner_entry); + + /* + * Ensure the list deletion is visible before we clear + * the owner, closes a race against perf_release() where + * we need to serialize on the owner->perf_event_mutex. + */ + smp_wmb(); + event->owner = NULL; + } + mutex_unlock(&child->perf_event_mutex); + + for_each_task_context_nr(ctxn) + perf_event_exit_task_context(child, ctxn); +} + +static void perf_free_event(struct perf_event *event, + struct perf_event_context *ctx) +{ + struct perf_event *parent = event->parent; + + if (WARN_ON_ONCE(!parent)) + return; + + mutex_lock(&parent->child_mutex); + list_del_init(&event->child_list); + mutex_unlock(&parent->child_mutex); + + put_event(parent); + + raw_spin_lock_irq(&ctx->lock); + perf_group_detach(event); + list_del_event(event, ctx); + raw_spin_unlock_irq(&ctx->lock); + free_event(event); +} + +/* + * Free an unexposed, unused context as created by inheritance by + * perf_event_init_task below, used by fork() in case of fail. + * + * Not all locks are strictly required, but take them anyway to be nice and + * help out with the lockdep assertions. + */ +void perf_event_free_task(struct task_struct *task) +{ + struct perf_event_context *ctx; + struct perf_event *event, *tmp; + int ctxn; + + for_each_task_context_nr(ctxn) { + ctx = task->perf_event_ctxp[ctxn]; + if (!ctx) + continue; + + mutex_lock(&ctx->mutex); +again: + list_for_each_entry_safe(event, tmp, &ctx->pinned_groups, + group_entry) + perf_free_event(event, ctx); + + list_for_each_entry_safe(event, tmp, &ctx->flexible_groups, + group_entry) + perf_free_event(event, ctx); + + if (!list_empty(&ctx->pinned_groups) || + !list_empty(&ctx->flexible_groups)) + goto again; + + mutex_unlock(&ctx->mutex); + + put_ctx(ctx); + } +} + +void perf_event_delayed_put(struct task_struct *task) +{ + int ctxn; + + for_each_task_context_nr(ctxn) + WARN_ON_ONCE(task->perf_event_ctxp[ctxn]); +} + +/* + * inherit a event from parent task to child task: + */ +static struct perf_event * +inherit_event(struct perf_event *parent_event, + struct task_struct *parent, + struct perf_event_context *parent_ctx, + struct task_struct *child, + struct perf_event *group_leader, + struct perf_event_context *child_ctx) +{ + enum perf_event_active_state parent_state = parent_event->state; + struct perf_event *child_event; + unsigned long flags; + + /* + * Instead of creating recursive hierarchies of events, + * we link inherited events back to the original parent, + * which has a filp for sure, which we use as the reference + * count: + */ + if (parent_event->parent) + parent_event = parent_event->parent; + + child_event = perf_event_alloc(&parent_event->attr, + parent_event->cpu, + child, + group_leader, parent_event, + NULL, NULL, -1); + if (IS_ERR(child_event)) + return child_event; + + if (is_orphaned_event(parent_event) || + !atomic_long_inc_not_zero(&parent_event->refcount)) { + free_event(child_event); + return NULL; + } + + get_ctx(child_ctx); + + /* + * Make the child state follow the state of the parent event, + * not its attr.disabled bit. We hold the parent's mutex, + * so we won't race with perf_event_{en, dis}able_family. + */ + if (parent_state >= PERF_EVENT_STATE_INACTIVE) + child_event->state = PERF_EVENT_STATE_INACTIVE; + else + child_event->state = PERF_EVENT_STATE_OFF; + + if (parent_event->attr.freq) { + u64 sample_period = parent_event->hw.sample_period; + struct hw_perf_event *hwc = &child_event->hw; + + hwc->sample_period = sample_period; + hwc->last_period = sample_period; + + local64_set(&hwc->period_left, sample_period); + } + + child_event->ctx = child_ctx; + child_event->overflow_handler = parent_event->overflow_handler; + child_event->overflow_handler_context + = parent_event->overflow_handler_context; + + /* + * Precalculate sample_data sizes + */ + perf_event__header_size(child_event); + perf_event__id_header_size(child_event); + + /* + * Link it up in the child's context: + */ + raw_spin_lock_irqsave(&child_ctx->lock, flags); + add_event_to_ctx(child_event, child_ctx); + raw_spin_unlock_irqrestore(&child_ctx->lock, flags); + + /* + * Link this into the parent event's child list + */ + WARN_ON_ONCE(parent_event->ctx->parent_ctx); + mutex_lock(&parent_event->child_mutex); + list_add_tail(&child_event->child_list, &parent_event->child_list); + mutex_unlock(&parent_event->child_mutex); + + return child_event; +} + +static int inherit_group(struct perf_event *parent_event, + struct task_struct *parent, + struct perf_event_context *parent_ctx, + struct task_struct *child, + struct perf_event_context *child_ctx) +{ + struct perf_event *leader; + struct perf_event *sub; + struct perf_event *child_ctr; + + leader = inherit_event(parent_event, parent, parent_ctx, + child, NULL, child_ctx); + if (IS_ERR(leader)) + return PTR_ERR(leader); + list_for_each_entry(sub, &parent_event->sibling_list, group_entry) { + child_ctr = inherit_event(sub, parent, parent_ctx, + child, leader, child_ctx); + if (IS_ERR(child_ctr)) + return PTR_ERR(child_ctr); + } + return 0; +} + +static int +inherit_task_group(struct perf_event *event, struct task_struct *parent, + struct perf_event_context *parent_ctx, + struct task_struct *child, int ctxn, + int *inherited_all) +{ + int ret; + struct perf_event_context *child_ctx; + + if (!event->attr.inherit) { + *inherited_all = 0; + return 0; + } + + child_ctx = child->perf_event_ctxp[ctxn]; + if (!child_ctx) { + /* + * This is executed from the parent task context, so + * inherit events that have been marked for cloning. + * First allocate and initialize a context for the + * child. + */ + + child_ctx = alloc_perf_context(parent_ctx->pmu, child); + if (!child_ctx) + return -ENOMEM; + + child->perf_event_ctxp[ctxn] = child_ctx; + } + + ret = inherit_group(event, parent, parent_ctx, + child, child_ctx); + + if (ret) + *inherited_all = 0; + + return ret; +} + +/* + * Initialize the perf_event context in task_struct + */ +static int perf_event_init_context(struct task_struct *child, int ctxn) +{ + struct perf_event_context *child_ctx, *parent_ctx; + struct perf_event_context *cloned_ctx; + struct perf_event *event; + struct task_struct *parent = current; + int inherited_all = 1; + unsigned long flags; + int ret = 0; + + if (likely(!parent->perf_event_ctxp[ctxn])) + return 0; + + /* + * If the parent's context is a clone, pin it so it won't get + * swapped under us. + */ + parent_ctx = perf_pin_task_context(parent, ctxn); + if (!parent_ctx) + return 0; + + /* + * No need to check if parent_ctx != NULL here; since we saw + * it non-NULL earlier, the only reason for it to become NULL + * is if we exit, and since we're currently in the middle of + * a fork we can't be exiting at the same time. + */ + + /* + * Lock the parent list. No need to lock the child - not PID + * hashed yet and not running, so nobody can access it. + */ + mutex_lock(&parent_ctx->mutex); + + /* + * We dont have to disable NMIs - we are only looking at + * the list, not manipulating it: + */ + list_for_each_entry(event, &parent_ctx->pinned_groups, group_entry) { + ret = inherit_task_group(event, parent, parent_ctx, + child, ctxn, &inherited_all); + if (ret) + break; + } + + /* + * We can't hold ctx->lock when iterating the ->flexible_group list due + * to allocations, but we need to prevent rotation because + * rotate_ctx() will change the list from interrupt context. + */ + raw_spin_lock_irqsave(&parent_ctx->lock, flags); + parent_ctx->rotate_disable = 1; + raw_spin_unlock_irqrestore(&parent_ctx->lock, flags); + + list_for_each_entry(event, &parent_ctx->flexible_groups, group_entry) { + ret = inherit_task_group(event, parent, parent_ctx, + child, ctxn, &inherited_all); + if (ret) + break; + } + + raw_spin_lock_irqsave(&parent_ctx->lock, flags); + parent_ctx->rotate_disable = 0; + + child_ctx = child->perf_event_ctxp[ctxn]; + + if (child_ctx && inherited_all) { + /* + * Mark the child context as a clone of the parent + * context, or of whatever the parent is a clone of. + * + * Note that if the parent is a clone, the holding of + * parent_ctx->lock avoids it from being uncloned. + */ + cloned_ctx = parent_ctx->parent_ctx; + if (cloned_ctx) { + child_ctx->parent_ctx = cloned_ctx; + child_ctx->parent_gen = parent_ctx->parent_gen; + } else { + child_ctx->parent_ctx = parent_ctx; + child_ctx->parent_gen = parent_ctx->generation; + } + get_ctx(child_ctx->parent_ctx); + } + + raw_spin_unlock_irqrestore(&parent_ctx->lock, flags); + mutex_unlock(&parent_ctx->mutex); + + perf_unpin_context(parent_ctx); + put_ctx(parent_ctx); + + return ret; +} + +/* + * Initialize the perf_event context in task_struct + */ +int perf_event_init_task(struct task_struct *child) +{ + int ctxn, ret; + + memset(child->perf_event_ctxp, 0, sizeof(child->perf_event_ctxp)); + mutex_init(&child->perf_event_mutex); + INIT_LIST_HEAD(&child->perf_event_list); + + for_each_task_context_nr(ctxn) { + ret = perf_event_init_context(child, ctxn); + if (ret) { + perf_event_free_task(child); + return ret; + } + } + + return 0; +} + +static void __init perf_event_init_all_cpus(void) +{ + struct swevent_htable *swhash; + int cpu; + + for_each_possible_cpu(cpu) { + swhash = &per_cpu(swevent_htable, cpu); + mutex_init(&swhash->hlist_mutex); + INIT_LIST_HEAD(&per_cpu(active_ctx_list, cpu)); + } +} + +static void perf_event_init_cpu(int cpu) +{ + struct swevent_htable *swhash = &per_cpu(swevent_htable, cpu); + + mutex_lock(&swhash->hlist_mutex); + swhash->online = true; + if (swhash->hlist_refcount > 0) { + struct swevent_hlist *hlist; + + hlist = kzalloc_node(sizeof(*hlist), GFP_KERNEL, cpu_to_node(cpu)); + WARN_ON(!hlist); + rcu_assign_pointer(swhash->swevent_hlist, hlist); + } + mutex_unlock(&swhash->hlist_mutex); +} + +#if defined CONFIG_HOTPLUG_CPU || defined CONFIG_KEXEC +static void __perf_event_exit_context(void *__info) +{ + struct remove_event re = { .detach_group = true }; + struct perf_event_context *ctx = __info; + + rcu_read_lock(); + list_for_each_entry_rcu(re.event, &ctx->event_list, event_entry) + __perf_remove_from_context(&re); + rcu_read_unlock(); +} + +static void perf_event_exit_cpu_context(int cpu) +{ + struct perf_event_context *ctx; + struct pmu *pmu; + int idx; + + idx = srcu_read_lock(&pmus_srcu); + list_for_each_entry_rcu(pmu, &pmus, entry) { + ctx = &per_cpu_ptr(pmu->pmu_cpu_context, cpu)->ctx; + + mutex_lock(&ctx->mutex); + smp_call_function_single(cpu, __perf_event_exit_context, ctx, 1); + mutex_unlock(&ctx->mutex); + } + srcu_read_unlock(&pmus_srcu, idx); +} + +static void perf_event_exit_cpu(int cpu) +{ + struct swevent_htable *swhash = &per_cpu(swevent_htable, cpu); + + perf_event_exit_cpu_context(cpu); + + mutex_lock(&swhash->hlist_mutex); + swhash->online = false; + swevent_hlist_release(swhash); + mutex_unlock(&swhash->hlist_mutex); +} +#else +static inline void perf_event_exit_cpu(int cpu) { } +#endif + +static int +perf_reboot(struct notifier_block *notifier, unsigned long val, void *v) +{ + int cpu; + + for_each_online_cpu(cpu) + perf_event_exit_cpu(cpu); + + return NOTIFY_OK; +} + +/* + * Run the perf reboot notifier at the very last possible moment so that + * the generic watchdog code runs as long as possible. + */ +static struct notifier_block perf_reboot_notifier = { + .notifier_call = perf_reboot, + .priority = INT_MIN, +}; + +static int +perf_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu) +{ + unsigned int cpu = (long)hcpu; + + switch (action & ~CPU_TASKS_FROZEN) { + + case CPU_UP_PREPARE: + case CPU_DOWN_FAILED: + perf_event_init_cpu(cpu); + break; + + case CPU_UP_CANCELED: + case CPU_DOWN_PREPARE: + perf_event_exit_cpu(cpu); + break; + default: + break; + } + + return NOTIFY_OK; +} + +void __init perf_event_init(void) +{ + int ret; + + idr_init(&pmu_idr); + + perf_event_init_all_cpus(); + init_srcu_struct(&pmus_srcu); + perf_pmu_register(&perf_swevent, "software", PERF_TYPE_SOFTWARE); + perf_pmu_register(&perf_cpu_clock, NULL, -1); + perf_pmu_register(&perf_task_clock, NULL, -1); + perf_tp_register(); + perf_cpu_notifier(perf_cpu_notify); + register_reboot_notifier(&perf_reboot_notifier); + + ret = init_hw_breakpoint(); + WARN(ret, "hw_breakpoint initialization failed with: %d", ret); + + /* do not patch jump label more than once per second */ + jump_label_rate_limit(&perf_sched_events, HZ); + + /* + * Build time assertion that we keep the data_head at the intended + * location. IOW, validation we got the __reserved[] size right. + */ + BUILD_BUG_ON((offsetof(struct perf_event_mmap_page, data_head)) + != 1024); +} + +ssize_t perf_event_sysfs_show(struct device *dev, struct device_attribute *attr, + char *page) +{ + struct perf_pmu_events_attr *pmu_attr = + container_of(attr, struct perf_pmu_events_attr, attr); + + if (pmu_attr->event_str) + return sprintf(page, "%s\n", pmu_attr->event_str); + + return 0; +} + +static int __init perf_event_sysfs_init(void) +{ + struct pmu *pmu; + int ret; + + mutex_lock(&pmus_lock); + + ret = bus_register(&pmu_bus); + if (ret) + goto unlock; + + list_for_each_entry(pmu, &pmus, entry) { + if (!pmu->name || pmu->type < 0) + continue; + + ret = pmu_dev_alloc(pmu); + WARN(ret, "Failed to register pmu: %s, reason %d\n", pmu->name, ret); + } + pmu_bus_running = 1; + ret = 0; + +unlock: + mutex_unlock(&pmus_lock); + + return ret; +} +device_initcall(perf_event_sysfs_init); + +#ifdef CONFIG_CGROUP_PERF +static struct cgroup_subsys_state * +perf_cgroup_css_alloc(struct cgroup_subsys_state *parent_css) +{ + struct perf_cgroup *jc; + + jc = kzalloc(sizeof(*jc), GFP_KERNEL); + if (!jc) + return ERR_PTR(-ENOMEM); + + jc->info = alloc_percpu(struct perf_cgroup_info); + if (!jc->info) { + kfree(jc); + return ERR_PTR(-ENOMEM); + } + + return &jc->css; +} + +static void perf_cgroup_css_free(struct cgroup_subsys_state *css) +{ + struct perf_cgroup *jc = container_of(css, struct perf_cgroup, css); + + free_percpu(jc->info); + kfree(jc); +} + +static int __perf_cgroup_move(void *info) +{ + struct task_struct *task = info; + perf_cgroup_switch(task, PERF_CGROUP_SWOUT | PERF_CGROUP_SWIN); + return 0; +} + +static void perf_cgroup_attach(struct cgroup_subsys_state *css, + struct cgroup_taskset *tset) +{ + struct task_struct *task; + + cgroup_taskset_for_each(task, tset) + task_function_call(task, __perf_cgroup_move, task); +} + +static void perf_cgroup_exit(struct cgroup_subsys_state *css, + struct cgroup_subsys_state *old_css, + struct task_struct *task) +{ + /* + * cgroup_exit() is called in the copy_process() failure path. + * Ignore this case since the task hasn't ran yet, this avoids + * trying to poke a half freed task state from generic code. + */ + if (!(task->flags & PF_EXITING)) + return; + + task_function_call(task, __perf_cgroup_move, task); +} + +struct cgroup_subsys perf_event_cgrp_subsys = { + .css_alloc = perf_cgroup_css_alloc, + .css_free = perf_cgroup_css_free, + .exit = perf_cgroup_exit, + .attach = perf_cgroup_attach, +}; +#endif /* CONFIG_CGROUP_PERF */ diff --git a/kernel/kernel/events/hw_breakpoint.c b/kernel/kernel/events/hw_breakpoint.c new file mode 100644 index 000000000..92ce5f4cc --- /dev/null +++ b/kernel/kernel/events/hw_breakpoint.c @@ -0,0 +1,655 @@ +/* + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * + * Copyright (C) 2007 Alan Stern + * Copyright (C) IBM Corporation, 2009 + * Copyright (C) 2009, Frederic Weisbecker + * + * Thanks to Ingo Molnar for his many suggestions. + * + * Authors: Alan Stern + * K.Prasad + * Frederic Weisbecker + */ + +/* + * HW_breakpoint: a unified kernel/user-space hardware breakpoint facility, + * using the CPU's debug registers. + * This file contains the arch-independent routines. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +/* + * Constraints data + */ +struct bp_cpuinfo { + /* Number of pinned cpu breakpoints in a cpu */ + unsigned int cpu_pinned; + /* tsk_pinned[n] is the number of tasks having n+1 breakpoints */ + unsigned int *tsk_pinned; + /* Number of non-pinned cpu/task breakpoints in a cpu */ + unsigned int flexible; /* XXX: placeholder, see fetch_this_slot() */ +}; + +static DEFINE_PER_CPU(struct bp_cpuinfo, bp_cpuinfo[TYPE_MAX]); +static int nr_slots[TYPE_MAX]; + +static struct bp_cpuinfo *get_bp_info(int cpu, enum bp_type_idx type) +{ + return per_cpu_ptr(bp_cpuinfo + type, cpu); +} + +/* Keep track of the breakpoints attached to tasks */ +static LIST_HEAD(bp_task_head); + +static int constraints_initialized; + +/* Gather the number of total pinned and un-pinned bp in a cpuset */ +struct bp_busy_slots { + unsigned int pinned; + unsigned int flexible; +}; + +/* Serialize accesses to the above constraints */ +static DEFINE_MUTEX(nr_bp_mutex); + +__weak int hw_breakpoint_weight(struct perf_event *bp) +{ + return 1; +} + +static inline enum bp_type_idx find_slot_idx(struct perf_event *bp) +{ + if (bp->attr.bp_type & HW_BREAKPOINT_RW) + return TYPE_DATA; + + return TYPE_INST; +} + +/* + * Report the maximum number of pinned breakpoints a task + * have in this cpu + */ +static unsigned int max_task_bp_pinned(int cpu, enum bp_type_idx type) +{ + unsigned int *tsk_pinned = get_bp_info(cpu, type)->tsk_pinned; + int i; + + for (i = nr_slots[type] - 1; i >= 0; i--) { + if (tsk_pinned[i] > 0) + return i + 1; + } + + return 0; +} + +/* + * Count the number of breakpoints of the same type and same task. + * The given event must be not on the list. + */ +static int task_bp_pinned(int cpu, struct perf_event *bp, enum bp_type_idx type) +{ + struct task_struct *tsk = bp->hw.target; + struct perf_event *iter; + int count = 0; + + list_for_each_entry(iter, &bp_task_head, hw.bp_list) { + if (iter->hw.target == tsk && + find_slot_idx(iter) == type && + (iter->cpu < 0 || cpu == iter->cpu)) + count += hw_breakpoint_weight(iter); + } + + return count; +} + +static const struct cpumask *cpumask_of_bp(struct perf_event *bp) +{ + if (bp->cpu >= 0) + return cpumask_of(bp->cpu); + return cpu_possible_mask; +} + +/* + * Report the number of pinned/un-pinned breakpoints we have in + * a given cpu (cpu > -1) or in all of them (cpu = -1). + */ +static void +fetch_bp_busy_slots(struct bp_busy_slots *slots, struct perf_event *bp, + enum bp_type_idx type) +{ + const struct cpumask *cpumask = cpumask_of_bp(bp); + int cpu; + + for_each_cpu(cpu, cpumask) { + struct bp_cpuinfo *info = get_bp_info(cpu, type); + int nr; + + nr = info->cpu_pinned; + if (!bp->hw.target) + nr += max_task_bp_pinned(cpu, type); + else + nr += task_bp_pinned(cpu, bp, type); + + if (nr > slots->pinned) + slots->pinned = nr; + + nr = info->flexible; + if (nr > slots->flexible) + slots->flexible = nr; + } +} + +/* + * For now, continue to consider flexible as pinned, until we can + * ensure no flexible event can ever be scheduled before a pinned event + * in a same cpu. + */ +static void +fetch_this_slot(struct bp_busy_slots *slots, int weight) +{ + slots->pinned += weight; +} + +/* + * Add a pinned breakpoint for the given task in our constraint table + */ +static void toggle_bp_task_slot(struct perf_event *bp, int cpu, + enum bp_type_idx type, int weight) +{ + unsigned int *tsk_pinned = get_bp_info(cpu, type)->tsk_pinned; + int old_idx, new_idx; + + old_idx = task_bp_pinned(cpu, bp, type) - 1; + new_idx = old_idx + weight; + + if (old_idx >= 0) + tsk_pinned[old_idx]--; + if (new_idx >= 0) + tsk_pinned[new_idx]++; +} + +/* + * Add/remove the given breakpoint in our constraint table + */ +static void +toggle_bp_slot(struct perf_event *bp, bool enable, enum bp_type_idx type, + int weight) +{ + const struct cpumask *cpumask = cpumask_of_bp(bp); + int cpu; + + if (!enable) + weight = -weight; + + /* Pinned counter cpu profiling */ + if (!bp->hw.target) { + get_bp_info(bp->cpu, type)->cpu_pinned += weight; + return; + } + + /* Pinned counter task profiling */ + for_each_cpu(cpu, cpumask) + toggle_bp_task_slot(bp, cpu, type, weight); + + if (enable) + list_add_tail(&bp->hw.bp_list, &bp_task_head); + else + list_del(&bp->hw.bp_list); +} + +/* + * Function to perform processor-specific cleanup during unregistration + */ +__weak void arch_unregister_hw_breakpoint(struct perf_event *bp) +{ + /* + * A weak stub function here for those archs that don't define + * it inside arch/.../kernel/hw_breakpoint.c + */ +} + +/* + * Contraints to check before allowing this new breakpoint counter: + * + * == Non-pinned counter == (Considered as pinned for now) + * + * - If attached to a single cpu, check: + * + * (per_cpu(info->flexible, cpu) || (per_cpu(info->cpu_pinned, cpu) + * + max(per_cpu(info->tsk_pinned, cpu)))) < HBP_NUM + * + * -> If there are already non-pinned counters in this cpu, it means + * there is already a free slot for them. + * Otherwise, we check that the maximum number of per task + * breakpoints (for this cpu) plus the number of per cpu breakpoint + * (for this cpu) doesn't cover every registers. + * + * - If attached to every cpus, check: + * + * (per_cpu(info->flexible, *) || (max(per_cpu(info->cpu_pinned, *)) + * + max(per_cpu(info->tsk_pinned, *)))) < HBP_NUM + * + * -> This is roughly the same, except we check the number of per cpu + * bp for every cpu and we keep the max one. Same for the per tasks + * breakpoints. + * + * + * == Pinned counter == + * + * - If attached to a single cpu, check: + * + * ((per_cpu(info->flexible, cpu) > 1) + per_cpu(info->cpu_pinned, cpu) + * + max(per_cpu(info->tsk_pinned, cpu))) < HBP_NUM + * + * -> Same checks as before. But now the info->flexible, if any, must keep + * one register at least (or they will never be fed). + * + * - If attached to every cpus, check: + * + * ((per_cpu(info->flexible, *) > 1) + max(per_cpu(info->cpu_pinned, *)) + * + max(per_cpu(info->tsk_pinned, *))) < HBP_NUM + */ +static int __reserve_bp_slot(struct perf_event *bp) +{ + struct bp_busy_slots slots = {0}; + enum bp_type_idx type; + int weight; + + /* We couldn't initialize breakpoint constraints on boot */ + if (!constraints_initialized) + return -ENOMEM; + + /* Basic checks */ + if (bp->attr.bp_type == HW_BREAKPOINT_EMPTY || + bp->attr.bp_type == HW_BREAKPOINT_INVALID) + return -EINVAL; + + type = find_slot_idx(bp); + weight = hw_breakpoint_weight(bp); + + fetch_bp_busy_slots(&slots, bp, type); + /* + * Simulate the addition of this breakpoint to the constraints + * and see the result. + */ + fetch_this_slot(&slots, weight); + + /* Flexible counters need to keep at least one slot */ + if (slots.pinned + (!!slots.flexible) > nr_slots[type]) + return -ENOSPC; + + toggle_bp_slot(bp, true, type, weight); + + return 0; +} + +int reserve_bp_slot(struct perf_event *bp) +{ + int ret; + + mutex_lock(&nr_bp_mutex); + + ret = __reserve_bp_slot(bp); + + mutex_unlock(&nr_bp_mutex); + + return ret; +} + +static void __release_bp_slot(struct perf_event *bp) +{ + enum bp_type_idx type; + int weight; + + type = find_slot_idx(bp); + weight = hw_breakpoint_weight(bp); + toggle_bp_slot(bp, false, type, weight); +} + +void release_bp_slot(struct perf_event *bp) +{ + mutex_lock(&nr_bp_mutex); + + arch_unregister_hw_breakpoint(bp); + __release_bp_slot(bp); + + mutex_unlock(&nr_bp_mutex); +} + +/* + * Allow the kernel debugger to reserve breakpoint slots without + * taking a lock using the dbg_* variant of for the reserve and + * release breakpoint slots. + */ +int dbg_reserve_bp_slot(struct perf_event *bp) +{ + if (mutex_is_locked(&nr_bp_mutex)) + return -1; + + return __reserve_bp_slot(bp); +} + +int dbg_release_bp_slot(struct perf_event *bp) +{ + if (mutex_is_locked(&nr_bp_mutex)) + return -1; + + __release_bp_slot(bp); + + return 0; +} + +static int validate_hw_breakpoint(struct perf_event *bp) +{ + int ret; + + ret = arch_validate_hwbkpt_settings(bp); + if (ret) + return ret; + + if (arch_check_bp_in_kernelspace(bp)) { + if (bp->attr.exclude_kernel) + return -EINVAL; + /* + * Don't let unprivileged users set a breakpoint in the trap + * path to avoid trap recursion attacks. + */ + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + } + + return 0; +} + +int register_perf_hw_breakpoint(struct perf_event *bp) +{ + int ret; + + ret = reserve_bp_slot(bp); + if (ret) + return ret; + + ret = validate_hw_breakpoint(bp); + + /* if arch_validate_hwbkpt_settings() fails then release bp slot */ + if (ret) + release_bp_slot(bp); + + return ret; +} + +/** + * register_user_hw_breakpoint - register a hardware breakpoint for user space + * @attr: breakpoint attributes + * @triggered: callback to trigger when we hit the breakpoint + * @tsk: pointer to 'task_struct' of the process to which the address belongs + */ +struct perf_event * +register_user_hw_breakpoint(struct perf_event_attr *attr, + perf_overflow_handler_t triggered, + void *context, + struct task_struct *tsk) +{ + return perf_event_create_kernel_counter(attr, -1, tsk, triggered, + context); +} +EXPORT_SYMBOL_GPL(register_user_hw_breakpoint); + +/** + * modify_user_hw_breakpoint - modify a user-space hardware breakpoint + * @bp: the breakpoint structure to modify + * @attr: new breakpoint attributes + * @triggered: callback to trigger when we hit the breakpoint + * @tsk: pointer to 'task_struct' of the process to which the address belongs + */ +int modify_user_hw_breakpoint(struct perf_event *bp, struct perf_event_attr *attr) +{ + u64 old_addr = bp->attr.bp_addr; + u64 old_len = bp->attr.bp_len; + int old_type = bp->attr.bp_type; + int err = 0; + + /* + * modify_user_hw_breakpoint can be invoked with IRQs disabled and hence it + * will not be possible to raise IPIs that invoke __perf_event_disable. + * So call the function directly after making sure we are targeting the + * current task. + */ + if (irqs_disabled() && bp->ctx && bp->ctx->task == current) + __perf_event_disable(bp); + else + perf_event_disable(bp); + + bp->attr.bp_addr = attr->bp_addr; + bp->attr.bp_type = attr->bp_type; + bp->attr.bp_len = attr->bp_len; + + if (attr->disabled) + goto end; + + err = validate_hw_breakpoint(bp); + if (!err) + perf_event_enable(bp); + + if (err) { + bp->attr.bp_addr = old_addr; + bp->attr.bp_type = old_type; + bp->attr.bp_len = old_len; + if (!bp->attr.disabled) + perf_event_enable(bp); + + return err; + } + +end: + bp->attr.disabled = attr->disabled; + + return 0; +} +EXPORT_SYMBOL_GPL(modify_user_hw_breakpoint); + +/** + * unregister_hw_breakpoint - unregister a user-space hardware breakpoint + * @bp: the breakpoint structure to unregister + */ +void unregister_hw_breakpoint(struct perf_event *bp) +{ + if (!bp) + return; + perf_event_release_kernel(bp); +} +EXPORT_SYMBOL_GPL(unregister_hw_breakpoint); + +/** + * register_wide_hw_breakpoint - register a wide breakpoint in the kernel + * @attr: breakpoint attributes + * @triggered: callback to trigger when we hit the breakpoint + * + * @return a set of per_cpu pointers to perf events + */ +struct perf_event * __percpu * +register_wide_hw_breakpoint(struct perf_event_attr *attr, + perf_overflow_handler_t triggered, + void *context) +{ + struct perf_event * __percpu *cpu_events, *bp; + long err = 0; + int cpu; + + cpu_events = alloc_percpu(typeof(*cpu_events)); + if (!cpu_events) + return (void __percpu __force *)ERR_PTR(-ENOMEM); + + get_online_cpus(); + for_each_online_cpu(cpu) { + bp = perf_event_create_kernel_counter(attr, cpu, NULL, + triggered, context); + if (IS_ERR(bp)) { + err = PTR_ERR(bp); + break; + } + + per_cpu(*cpu_events, cpu) = bp; + } + put_online_cpus(); + + if (likely(!err)) + return cpu_events; + + unregister_wide_hw_breakpoint(cpu_events); + return (void __percpu __force *)ERR_PTR(err); +} +EXPORT_SYMBOL_GPL(register_wide_hw_breakpoint); + +/** + * unregister_wide_hw_breakpoint - unregister a wide breakpoint in the kernel + * @cpu_events: the per cpu set of events to unregister + */ +void unregister_wide_hw_breakpoint(struct perf_event * __percpu *cpu_events) +{ + int cpu; + + for_each_possible_cpu(cpu) + unregister_hw_breakpoint(per_cpu(*cpu_events, cpu)); + + free_percpu(cpu_events); +} +EXPORT_SYMBOL_GPL(unregister_wide_hw_breakpoint); + +static struct notifier_block hw_breakpoint_exceptions_nb = { + .notifier_call = hw_breakpoint_exceptions_notify, + /* we need to be notified first */ + .priority = 0x7fffffff +}; + +static void bp_perf_event_destroy(struct perf_event *event) +{ + release_bp_slot(event); +} + +static int hw_breakpoint_event_init(struct perf_event *bp) +{ + int err; + + if (bp->attr.type != PERF_TYPE_BREAKPOINT) + return -ENOENT; + + /* + * no branch sampling for breakpoint events + */ + if (has_branch_stack(bp)) + return -EOPNOTSUPP; + + err = register_perf_hw_breakpoint(bp); + if (err) + return err; + + bp->destroy = bp_perf_event_destroy; + + return 0; +} + +static int hw_breakpoint_add(struct perf_event *bp, int flags) +{ + if (!(flags & PERF_EF_START)) + bp->hw.state = PERF_HES_STOPPED; + + if (is_sampling_event(bp)) { + bp->hw.last_period = bp->hw.sample_period; + perf_swevent_set_period(bp); + } + + return arch_install_hw_breakpoint(bp); +} + +static void hw_breakpoint_del(struct perf_event *bp, int flags) +{ + arch_uninstall_hw_breakpoint(bp); +} + +static void hw_breakpoint_start(struct perf_event *bp, int flags) +{ + bp->hw.state = 0; +} + +static void hw_breakpoint_stop(struct perf_event *bp, int flags) +{ + bp->hw.state = PERF_HES_STOPPED; +} + +static struct pmu perf_breakpoint = { + .task_ctx_nr = perf_sw_context, /* could eventually get its own */ + + .event_init = hw_breakpoint_event_init, + .add = hw_breakpoint_add, + .del = hw_breakpoint_del, + .start = hw_breakpoint_start, + .stop = hw_breakpoint_stop, + .read = hw_breakpoint_pmu_read, +}; + +int __init init_hw_breakpoint(void) +{ + int cpu, err_cpu; + int i; + + for (i = 0; i < TYPE_MAX; i++) + nr_slots[i] = hw_breakpoint_slots(i); + + for_each_possible_cpu(cpu) { + for (i = 0; i < TYPE_MAX; i++) { + struct bp_cpuinfo *info = get_bp_info(cpu, i); + + info->tsk_pinned = kcalloc(nr_slots[i], sizeof(int), + GFP_KERNEL); + if (!info->tsk_pinned) + goto err_alloc; + } + } + + constraints_initialized = 1; + + perf_pmu_register(&perf_breakpoint, "breakpoint", PERF_TYPE_BREAKPOINT); + + return register_die_notifier(&hw_breakpoint_exceptions_nb); + + err_alloc: + for_each_possible_cpu(err_cpu) { + for (i = 0; i < TYPE_MAX; i++) + kfree(get_bp_info(err_cpu, i)->tsk_pinned); + if (err_cpu == cpu) + break; + } + + return -ENOMEM; +} + + diff --git a/kernel/kernel/events/internal.h b/kernel/kernel/events/internal.h new file mode 100644 index 000000000..9f6ce9ba4 --- /dev/null +++ b/kernel/kernel/events/internal.h @@ -0,0 +1,231 @@ +#ifndef _KERNEL_EVENTS_INTERNAL_H +#define _KERNEL_EVENTS_INTERNAL_H + +#include +#include + +/* Buffer handling */ + +#define RING_BUFFER_WRITABLE 0x01 + +struct ring_buffer { + atomic_t refcount; + struct rcu_head rcu_head; +#ifdef CONFIG_PERF_USE_VMALLOC + struct work_struct work; + int page_order; /* allocation order */ +#endif + int nr_pages; /* nr of data pages */ + int overwrite; /* can overwrite itself */ + + atomic_t poll; /* POLL_ for wakeups */ + + local_t head; /* write position */ + local_t nest; /* nested writers */ + local_t events; /* event limit */ + local_t wakeup; /* wakeup stamp */ + local_t lost; /* nr records lost */ + + long watermark; /* wakeup watermark */ + long aux_watermark; + /* poll crap */ + spinlock_t event_lock; + struct list_head event_list; + + atomic_t mmap_count; + unsigned long mmap_locked; + struct user_struct *mmap_user; + + /* AUX area */ + local_t aux_head; + local_t aux_nest; + local_t aux_wakeup; + unsigned long aux_pgoff; + int aux_nr_pages; + int aux_overwrite; + atomic_t aux_mmap_count; + unsigned long aux_mmap_locked; + void (*free_aux)(void *); + atomic_t aux_refcount; + void **aux_pages; + void *aux_priv; + + struct perf_event_mmap_page *user_page; + void *data_pages[0]; +}; + +extern void rb_free(struct ring_buffer *rb); +extern struct ring_buffer * +rb_alloc(int nr_pages, long watermark, int cpu, int flags); +extern void perf_event_wakeup(struct perf_event *event); +extern int rb_alloc_aux(struct ring_buffer *rb, struct perf_event *event, + pgoff_t pgoff, int nr_pages, long watermark, int flags); +extern void rb_free_aux(struct ring_buffer *rb); +extern struct ring_buffer *ring_buffer_get(struct perf_event *event); +extern void ring_buffer_put(struct ring_buffer *rb); + +static inline bool rb_has_aux(struct ring_buffer *rb) +{ + return !!rb->aux_nr_pages; +} + +void perf_event_aux_event(struct perf_event *event, unsigned long head, + unsigned long size, u64 flags); + +extern void +perf_event_header__init_id(struct perf_event_header *header, + struct perf_sample_data *data, + struct perf_event *event); +extern void +perf_event__output_id_sample(struct perf_event *event, + struct perf_output_handle *handle, + struct perf_sample_data *sample); + +extern struct page * +perf_mmap_to_page(struct ring_buffer *rb, unsigned long pgoff); + +#ifdef CONFIG_PERF_USE_VMALLOC +/* + * Back perf_mmap() with vmalloc memory. + * + * Required for architectures that have d-cache aliasing issues. + */ + +static inline int page_order(struct ring_buffer *rb) +{ + return rb->page_order; +} + +#else + +static inline int page_order(struct ring_buffer *rb) +{ + return 0; +} +#endif + +static inline unsigned long perf_data_size(struct ring_buffer *rb) +{ + return rb->nr_pages << (PAGE_SHIFT + page_order(rb)); +} + +static inline unsigned long perf_aux_size(struct ring_buffer *rb) +{ + return rb->aux_nr_pages << PAGE_SHIFT; +} + +#define DEFINE_OUTPUT_COPY(func_name, memcpy_func) \ +static inline unsigned long \ +func_name(struct perf_output_handle *handle, \ + const void *buf, unsigned long len) \ +{ \ + unsigned long size, written; \ + \ + do { \ + size = min(handle->size, len); \ + written = memcpy_func(handle->addr, buf, size); \ + written = size - written; \ + \ + len -= written; \ + handle->addr += written; \ + buf += written; \ + handle->size -= written; \ + if (!handle->size) { \ + struct ring_buffer *rb = handle->rb; \ + \ + handle->page++; \ + handle->page &= rb->nr_pages - 1; \ + handle->addr = rb->data_pages[handle->page]; \ + handle->size = PAGE_SIZE << page_order(rb); \ + } \ + } while (len && written == size); \ + \ + return len; \ +} + +static inline unsigned long +memcpy_common(void *dst, const void *src, unsigned long n) +{ + memcpy(dst, src, n); + return 0; +} + +DEFINE_OUTPUT_COPY(__output_copy, memcpy_common) + +static inline unsigned long +memcpy_skip(void *dst, const void *src, unsigned long n) +{ + return 0; +} + +DEFINE_OUTPUT_COPY(__output_skip, memcpy_skip) + +#ifndef arch_perf_out_copy_user +#define arch_perf_out_copy_user arch_perf_out_copy_user + +static inline unsigned long +arch_perf_out_copy_user(void *dst, const void *src, unsigned long n) +{ + unsigned long ret; + + pagefault_disable(); + ret = __copy_from_user_inatomic(dst, src, n); + pagefault_enable(); + + return ret; +} +#endif + +DEFINE_OUTPUT_COPY(__output_copy_user, arch_perf_out_copy_user) + +/* Callchain handling */ +extern struct perf_callchain_entry * +perf_callchain(struct perf_event *event, struct pt_regs *regs); +extern int get_callchain_buffers(void); +extern void put_callchain_buffers(void); + +static inline int get_recursion_context(int *recursion) +{ + int rctx; + + if (in_nmi()) + rctx = 3; + else if (in_irq()) + rctx = 2; + else if (in_softirq()) + rctx = 1; + else + rctx = 0; + + if (recursion[rctx]) + return -1; + + recursion[rctx]++; + barrier(); + + return rctx; +} + +static inline void put_recursion_context(int *recursion, int rctx) +{ + barrier(); + recursion[rctx]--; +} + +#ifdef CONFIG_HAVE_PERF_USER_STACK_DUMP +static inline bool arch_perf_have_user_stack_dump(void) +{ + return true; +} + +#define perf_user_stack_pointer(regs) user_stack_pointer(regs) +#else +static inline bool arch_perf_have_user_stack_dump(void) +{ + return false; +} + +#define perf_user_stack_pointer(regs) 0 +#endif /* CONFIG_HAVE_PERF_USER_STACK_DUMP */ + +#endif /* _KERNEL_EVENTS_INTERNAL_H */ diff --git a/kernel/kernel/events/ring_buffer.c b/kernel/kernel/events/ring_buffer.c new file mode 100644 index 000000000..725c41608 --- /dev/null +++ b/kernel/kernel/events/ring_buffer.c @@ -0,0 +1,751 @@ +/* + * Performance events ring-buffer code: + * + * Copyright (C) 2008 Thomas Gleixner + * Copyright (C) 2008-2011 Red Hat, Inc., Ingo Molnar + * Copyright (C) 2008-2011 Red Hat, Inc., Peter Zijlstra + * Copyright © 2009 Paul Mackerras, IBM Corp. + * + * For licensing details see kernel-base/COPYING + */ + +#include +#include +#include +#include +#include + +#include "internal.h" + +static void perf_output_wakeup(struct perf_output_handle *handle) +{ + atomic_set(&handle->rb->poll, POLLIN); + + handle->event->pending_wakeup = 1; + irq_work_queue(&handle->event->pending); +} + +/* + * We need to ensure a later event_id doesn't publish a head when a former + * event isn't done writing. However since we need to deal with NMIs we + * cannot fully serialize things. + * + * We only publish the head (and generate a wakeup) when the outer-most + * event completes. + */ +static void perf_output_get_handle(struct perf_output_handle *handle) +{ + struct ring_buffer *rb = handle->rb; + + preempt_disable(); + local_inc(&rb->nest); + handle->wakeup = local_read(&rb->wakeup); +} + +static void perf_output_put_handle(struct perf_output_handle *handle) +{ + struct ring_buffer *rb = handle->rb; + unsigned long head; + +again: + head = local_read(&rb->head); + + /* + * IRQ/NMI can happen here, which means we can miss a head update. + */ + + if (!local_dec_and_test(&rb->nest)) + goto out; + + /* + * Since the mmap() consumer (userspace) can run on a different CPU: + * + * kernel user + * + * if (LOAD ->data_tail) { LOAD ->data_head + * (A) smp_rmb() (C) + * STORE $data LOAD $data + * smp_wmb() (B) smp_mb() (D) + * STORE ->data_head STORE ->data_tail + * } + * + * Where A pairs with D, and B pairs with C. + * + * In our case (A) is a control dependency that separates the load of + * the ->data_tail and the stores of $data. In case ->data_tail + * indicates there is no room in the buffer to store $data we do not. + * + * D needs to be a full barrier since it separates the data READ + * from the tail WRITE. + * + * For B a WMB is sufficient since it separates two WRITEs, and for C + * an RMB is sufficient since it separates two READs. + * + * See perf_output_begin(). + */ + smp_wmb(); /* B, matches C */ + rb->user_page->data_head = head; + + /* + * Now check if we missed an update -- rely on previous implied + * compiler barriers to force a re-read. + */ + if (unlikely(head != local_read(&rb->head))) { + local_inc(&rb->nest); + goto again; + } + + if (handle->wakeup != local_read(&rb->wakeup)) + perf_output_wakeup(handle); + +out: + preempt_enable(); +} + +int perf_output_begin(struct perf_output_handle *handle, + struct perf_event *event, unsigned int size) +{ + struct ring_buffer *rb; + unsigned long tail, offset, head; + int have_lost, page_shift; + struct { + struct perf_event_header header; + u64 id; + u64 lost; + } lost_event; + + rcu_read_lock(); + /* + * For inherited events we send all the output towards the parent. + */ + if (event->parent) + event = event->parent; + + rb = rcu_dereference(event->rb); + if (unlikely(!rb)) + goto out; + + if (unlikely(!rb->nr_pages)) + goto out; + + handle->rb = rb; + handle->event = event; + + have_lost = local_read(&rb->lost); + if (unlikely(have_lost)) { + size += sizeof(lost_event); + if (event->attr.sample_id_all) + size += event->id_header_size; + } + + perf_output_get_handle(handle); + + do { + tail = ACCESS_ONCE(rb->user_page->data_tail); + offset = head = local_read(&rb->head); + if (!rb->overwrite && + unlikely(CIRC_SPACE(head, tail, perf_data_size(rb)) < size)) + goto fail; + + /* + * The above forms a control dependency barrier separating the + * @tail load above from the data stores below. Since the @tail + * load is required to compute the branch to fail below. + * + * A, matches D; the full memory barrier userspace SHOULD issue + * after reading the data and before storing the new tail + * position. + * + * See perf_output_put_handle(). + */ + + head += size; + } while (local_cmpxchg(&rb->head, offset, head) != offset); + + /* + * We rely on the implied barrier() by local_cmpxchg() to ensure + * none of the data stores below can be lifted up by the compiler. + */ + + if (unlikely(head - local_read(&rb->wakeup) > rb->watermark)) + local_add(rb->watermark, &rb->wakeup); + + page_shift = PAGE_SHIFT + page_order(rb); + + handle->page = (offset >> page_shift) & (rb->nr_pages - 1); + offset &= (1UL << page_shift) - 1; + handle->addr = rb->data_pages[handle->page] + offset; + handle->size = (1UL << page_shift) - offset; + + if (unlikely(have_lost)) { + struct perf_sample_data sample_data; + + lost_event.header.size = sizeof(lost_event); + lost_event.header.type = PERF_RECORD_LOST; + lost_event.header.misc = 0; + lost_event.id = event->id; + lost_event.lost = local_xchg(&rb->lost, 0); + + perf_event_header__init_id(&lost_event.header, + &sample_data, event); + perf_output_put(handle, lost_event); + perf_event__output_id_sample(event, handle, &sample_data); + } + + return 0; + +fail: + local_inc(&rb->lost); + perf_output_put_handle(handle); +out: + rcu_read_unlock(); + + return -ENOSPC; +} + +unsigned int perf_output_copy(struct perf_output_handle *handle, + const void *buf, unsigned int len) +{ + return __output_copy(handle, buf, len); +} + +unsigned int perf_output_skip(struct perf_output_handle *handle, + unsigned int len) +{ + return __output_skip(handle, NULL, len); +} + +void perf_output_end(struct perf_output_handle *handle) +{ + perf_output_put_handle(handle); + rcu_read_unlock(); +} + +static void +ring_buffer_init(struct ring_buffer *rb, long watermark, int flags) +{ + long max_size = perf_data_size(rb); + + if (watermark) + rb->watermark = min(max_size, watermark); + + if (!rb->watermark) + rb->watermark = max_size / 2; + + if (flags & RING_BUFFER_WRITABLE) + rb->overwrite = 0; + else + rb->overwrite = 1; + + atomic_set(&rb->refcount, 1); + + INIT_LIST_HEAD(&rb->event_list); + spin_lock_init(&rb->event_lock); +} + +/* + * This is called before hardware starts writing to the AUX area to + * obtain an output handle and make sure there's room in the buffer. + * When the capture completes, call perf_aux_output_end() to commit + * the recorded data to the buffer. + * + * The ordering is similar to that of perf_output_{begin,end}, with + * the exception of (B), which should be taken care of by the pmu + * driver, since ordering rules will differ depending on hardware. + */ +void *perf_aux_output_begin(struct perf_output_handle *handle, + struct perf_event *event) +{ + struct perf_event *output_event = event; + unsigned long aux_head, aux_tail; + struct ring_buffer *rb; + + if (output_event->parent) + output_event = output_event->parent; + + /* + * Since this will typically be open across pmu::add/pmu::del, we + * grab ring_buffer's refcount instead of holding rcu read lock + * to make sure it doesn't disappear under us. + */ + rb = ring_buffer_get(output_event); + if (!rb) + return NULL; + + if (!rb_has_aux(rb) || !atomic_inc_not_zero(&rb->aux_refcount)) + goto err; + + /* + * Nesting is not supported for AUX area, make sure nested + * writers are caught early + */ + if (WARN_ON_ONCE(local_xchg(&rb->aux_nest, 1))) + goto err_put; + + aux_head = local_read(&rb->aux_head); + + handle->rb = rb; + handle->event = event; + handle->head = aux_head; + handle->size = 0; + + /* + * In overwrite mode, AUX data stores do not depend on aux_tail, + * therefore (A) control dependency barrier does not exist. The + * (B) <-> (C) ordering is still observed by the pmu driver. + */ + if (!rb->aux_overwrite) { + aux_tail = ACCESS_ONCE(rb->user_page->aux_tail); + handle->wakeup = local_read(&rb->aux_wakeup) + rb->aux_watermark; + if (aux_head - aux_tail < perf_aux_size(rb)) + handle->size = CIRC_SPACE(aux_head, aux_tail, perf_aux_size(rb)); + + /* + * handle->size computation depends on aux_tail load; this forms a + * control dependency barrier separating aux_tail load from aux data + * store that will be enabled on successful return + */ + if (!handle->size) { /* A, matches D */ + event->pending_disable = 1; + perf_output_wakeup(handle); + local_set(&rb->aux_nest, 0); + goto err_put; + } + } + + return handle->rb->aux_priv; + +err_put: + rb_free_aux(rb); + +err: + ring_buffer_put(rb); + handle->event = NULL; + + return NULL; +} + +/* + * Commit the data written by hardware into the ring buffer by adjusting + * aux_head and posting a PERF_RECORD_AUX into the perf buffer. It is the + * pmu driver's responsibility to observe ordering rules of the hardware, + * so that all the data is externally visible before this is called. + */ +void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size, + bool truncated) +{ + struct ring_buffer *rb = handle->rb; + unsigned long aux_head; + u64 flags = 0; + + if (truncated) + flags |= PERF_AUX_FLAG_TRUNCATED; + + /* in overwrite mode, driver provides aux_head via handle */ + if (rb->aux_overwrite) { + flags |= PERF_AUX_FLAG_OVERWRITE; + + aux_head = handle->head; + local_set(&rb->aux_head, aux_head); + } else { + aux_head = local_read(&rb->aux_head); + local_add(size, &rb->aux_head); + } + + if (size || flags) { + /* + * Only send RECORD_AUX if we have something useful to communicate + */ + + perf_event_aux_event(handle->event, aux_head, size, flags); + } + + aux_head = rb->user_page->aux_head = local_read(&rb->aux_head); + + if (aux_head - local_read(&rb->aux_wakeup) >= rb->aux_watermark) { + perf_output_wakeup(handle); + local_add(rb->aux_watermark, &rb->aux_wakeup); + } + handle->event = NULL; + + local_set(&rb->aux_nest, 0); + rb_free_aux(rb); + ring_buffer_put(rb); +} + +/* + * Skip over a given number of bytes in the AUX buffer, due to, for example, + * hardware's alignment constraints. + */ +int perf_aux_output_skip(struct perf_output_handle *handle, unsigned long size) +{ + struct ring_buffer *rb = handle->rb; + unsigned long aux_head; + + if (size > handle->size) + return -ENOSPC; + + local_add(size, &rb->aux_head); + + aux_head = rb->user_page->aux_head = local_read(&rb->aux_head); + if (aux_head - local_read(&rb->aux_wakeup) >= rb->aux_watermark) { + perf_output_wakeup(handle); + local_add(rb->aux_watermark, &rb->aux_wakeup); + handle->wakeup = local_read(&rb->aux_wakeup) + + rb->aux_watermark; + } + + handle->head = aux_head; + handle->size -= size; + + return 0; +} + +void *perf_get_aux(struct perf_output_handle *handle) +{ + /* this is only valid between perf_aux_output_begin and *_end */ + if (!handle->event) + return NULL; + + return handle->rb->aux_priv; +} + +#define PERF_AUX_GFP (GFP_KERNEL | __GFP_ZERO | __GFP_NOWARN | __GFP_NORETRY) + +static struct page *rb_alloc_aux_page(int node, int order) +{ + struct page *page; + + if (order > MAX_ORDER) + order = MAX_ORDER; + + do { + page = alloc_pages_node(node, PERF_AUX_GFP, order); + } while (!page && order--); + + if (page && order) { + /* + * Communicate the allocation size to the driver + */ + split_page(page, order); + SetPagePrivate(page); + set_page_private(page, order); + } + + return page; +} + +static void rb_free_aux_page(struct ring_buffer *rb, int idx) +{ + struct page *page = virt_to_page(rb->aux_pages[idx]); + + ClearPagePrivate(page); + page->mapping = NULL; + __free_page(page); +} + +int rb_alloc_aux(struct ring_buffer *rb, struct perf_event *event, + pgoff_t pgoff, int nr_pages, long watermark, int flags) +{ + bool overwrite = !(flags & RING_BUFFER_WRITABLE); + int node = (event->cpu == -1) ? -1 : cpu_to_node(event->cpu); + int ret = -ENOMEM, max_order = 0; + + if (!has_aux(event)) + return -ENOTSUPP; + + if (event->pmu->capabilities & PERF_PMU_CAP_AUX_NO_SG) { + /* + * We need to start with the max_order that fits in nr_pages, + * not the other way around, hence ilog2() and not get_order. + */ + max_order = ilog2(nr_pages); + + /* + * PMU requests more than one contiguous chunks of memory + * for SW double buffering + */ + if ((event->pmu->capabilities & PERF_PMU_CAP_AUX_SW_DOUBLEBUF) && + !overwrite) { + if (!max_order) + return -EINVAL; + + max_order--; + } + } + + rb->aux_pages = kzalloc_node(nr_pages * sizeof(void *), GFP_KERNEL, node); + if (!rb->aux_pages) + return -ENOMEM; + + rb->free_aux = event->pmu->free_aux; + for (rb->aux_nr_pages = 0; rb->aux_nr_pages < nr_pages;) { + struct page *page; + int last, order; + + order = min(max_order, ilog2(nr_pages - rb->aux_nr_pages)); + page = rb_alloc_aux_page(node, order); + if (!page) + goto out; + + for (last = rb->aux_nr_pages + (1 << page_private(page)); + last > rb->aux_nr_pages; rb->aux_nr_pages++) + rb->aux_pages[rb->aux_nr_pages] = page_address(page++); + } + + /* + * In overwrite mode, PMUs that don't support SG may not handle more + * than one contiguous allocation, since they rely on PMI to do double + * buffering. In this case, the entire buffer has to be one contiguous + * chunk. + */ + if ((event->pmu->capabilities & PERF_PMU_CAP_AUX_NO_SG) && + overwrite) { + struct page *page = virt_to_page(rb->aux_pages[0]); + + if (page_private(page) != max_order) + goto out; + } + + rb->aux_priv = event->pmu->setup_aux(event->cpu, rb->aux_pages, nr_pages, + overwrite); + if (!rb->aux_priv) + goto out; + + ret = 0; + + /* + * aux_pages (and pmu driver's private data, aux_priv) will be + * referenced in both producer's and consumer's contexts, thus + * we keep a refcount here to make sure either of the two can + * reference them safely. + */ + atomic_set(&rb->aux_refcount, 1); + + rb->aux_overwrite = overwrite; + rb->aux_watermark = watermark; + + if (!rb->aux_watermark && !rb->aux_overwrite) + rb->aux_watermark = nr_pages << (PAGE_SHIFT - 1); + +out: + if (!ret) + rb->aux_pgoff = pgoff; + else + rb_free_aux(rb); + + return ret; +} + +static void __rb_free_aux(struct ring_buffer *rb) +{ + int pg; + + if (rb->aux_priv) { + rb->free_aux(rb->aux_priv); + rb->free_aux = NULL; + rb->aux_priv = NULL; + } + + for (pg = 0; pg < rb->aux_nr_pages; pg++) + rb_free_aux_page(rb, pg); + + kfree(rb->aux_pages); + rb->aux_nr_pages = 0; +} + +void rb_free_aux(struct ring_buffer *rb) +{ + if (atomic_dec_and_test(&rb->aux_refcount)) + __rb_free_aux(rb); +} + +#ifndef CONFIG_PERF_USE_VMALLOC + +/* + * Back perf_mmap() with regular GFP_KERNEL-0 pages. + */ + +static struct page * +__perf_mmap_to_page(struct ring_buffer *rb, unsigned long pgoff) +{ + if (pgoff > rb->nr_pages) + return NULL; + + if (pgoff == 0) + return virt_to_page(rb->user_page); + + return virt_to_page(rb->data_pages[pgoff - 1]); +} + +static void *perf_mmap_alloc_page(int cpu) +{ + struct page *page; + int node; + + node = (cpu == -1) ? cpu : cpu_to_node(cpu); + page = alloc_pages_node(node, GFP_KERNEL | __GFP_ZERO, 0); + if (!page) + return NULL; + + return page_address(page); +} + +struct ring_buffer *rb_alloc(int nr_pages, long watermark, int cpu, int flags) +{ + struct ring_buffer *rb; + unsigned long size; + int i; + + size = sizeof(struct ring_buffer); + size += nr_pages * sizeof(void *); + + rb = kzalloc(size, GFP_KERNEL); + if (!rb) + goto fail; + + rb->user_page = perf_mmap_alloc_page(cpu); + if (!rb->user_page) + goto fail_user_page; + + for (i = 0; i < nr_pages; i++) { + rb->data_pages[i] = perf_mmap_alloc_page(cpu); + if (!rb->data_pages[i]) + goto fail_data_pages; + } + + rb->nr_pages = nr_pages; + + ring_buffer_init(rb, watermark, flags); + + return rb; + +fail_data_pages: + for (i--; i >= 0; i--) + free_page((unsigned long)rb->data_pages[i]); + + free_page((unsigned long)rb->user_page); + +fail_user_page: + kfree(rb); + +fail: + return NULL; +} + +static void perf_mmap_free_page(unsigned long addr) +{ + struct page *page = virt_to_page((void *)addr); + + page->mapping = NULL; + __free_page(page); +} + +void rb_free(struct ring_buffer *rb) +{ + int i; + + perf_mmap_free_page((unsigned long)rb->user_page); + for (i = 0; i < rb->nr_pages; i++) + perf_mmap_free_page((unsigned long)rb->data_pages[i]); + kfree(rb); +} + +#else +static int data_page_nr(struct ring_buffer *rb) +{ + return rb->nr_pages << page_order(rb); +} + +static struct page * +__perf_mmap_to_page(struct ring_buffer *rb, unsigned long pgoff) +{ + /* The '>' counts in the user page. */ + if (pgoff > data_page_nr(rb)) + return NULL; + + return vmalloc_to_page((void *)rb->user_page + pgoff * PAGE_SIZE); +} + +static void perf_mmap_unmark_page(void *addr) +{ + struct page *page = vmalloc_to_page(addr); + + page->mapping = NULL; +} + +static void rb_free_work(struct work_struct *work) +{ + struct ring_buffer *rb; + void *base; + int i, nr; + + rb = container_of(work, struct ring_buffer, work); + nr = data_page_nr(rb); + + base = rb->user_page; + /* The '<=' counts in the user page. */ + for (i = 0; i <= nr; i++) + perf_mmap_unmark_page(base + (i * PAGE_SIZE)); + + vfree(base); + kfree(rb); +} + +void rb_free(struct ring_buffer *rb) +{ + schedule_work(&rb->work); +} + +struct ring_buffer *rb_alloc(int nr_pages, long watermark, int cpu, int flags) +{ + struct ring_buffer *rb; + unsigned long size; + void *all_buf; + + size = sizeof(struct ring_buffer); + size += sizeof(void *); + + rb = kzalloc(size, GFP_KERNEL); + if (!rb) + goto fail; + + INIT_WORK(&rb->work, rb_free_work); + + all_buf = vmalloc_user((nr_pages + 1) * PAGE_SIZE); + if (!all_buf) + goto fail_all_buf; + + rb->user_page = all_buf; + rb->data_pages[0] = all_buf + PAGE_SIZE; + rb->page_order = ilog2(nr_pages); + rb->nr_pages = !!nr_pages; + + ring_buffer_init(rb, watermark, flags); + + return rb; + +fail_all_buf: + kfree(rb); + +fail: + return NULL; +} + +#endif + +struct page * +perf_mmap_to_page(struct ring_buffer *rb, unsigned long pgoff) +{ + if (rb->aux_nr_pages) { + /* above AUX space */ + if (pgoff > rb->aux_pgoff + rb->aux_nr_pages) + return NULL; + + /* AUX space */ + if (pgoff >= rb->aux_pgoff) + return virt_to_page(rb->aux_pages[pgoff - rb->aux_pgoff]); + } + + return __perf_mmap_to_page(rb, pgoff); +} diff --git a/kernel/kernel/events/uprobes.c b/kernel/kernel/events/uprobes.c new file mode 100644 index 000000000..cb346f26a --- /dev/null +++ b/kernel/kernel/events/uprobes.c @@ -0,0 +1,1993 @@ +/* + * User-space Probes (UProbes) + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * + * Copyright (C) IBM Corporation, 2008-2012 + * Authors: + * Srikar Dronamraju + * Jim Keniston + * Copyright (C) 2011-2012 Red Hat, Inc., Peter Zijlstra + */ + +#include +#include +#include /* read_mapping_page */ +#include +#include +#include +#include /* anon_vma_prepare */ +#include /* set_pte_at_notify */ +#include /* try_to_free_swap */ +#include /* user_enable_single_step */ +#include /* notifier mechanism */ +#include "../../mm/internal.h" /* munlock_vma_page */ +#include +#include +#include + +#include + +#define UINSNS_PER_PAGE (PAGE_SIZE/UPROBE_XOL_SLOT_BYTES) +#define MAX_UPROBE_XOL_SLOTS UINSNS_PER_PAGE + +static struct rb_root uprobes_tree = RB_ROOT; +/* + * allows us to skip the uprobe_mmap if there are no uprobe events active + * at this time. Probably a fine grained per inode count is better? + */ +#define no_uprobe_events() RB_EMPTY_ROOT(&uprobes_tree) + +static DEFINE_SPINLOCK(uprobes_treelock); /* serialize rbtree access */ + +#define UPROBES_HASH_SZ 13 +/* serialize uprobe->pending_list */ +static struct mutex uprobes_mmap_mutex[UPROBES_HASH_SZ]; +#define uprobes_mmap_hash(v) (&uprobes_mmap_mutex[((unsigned long)(v)) % UPROBES_HASH_SZ]) + +static struct percpu_rw_semaphore dup_mmap_sem; + +/* Have a copy of original instruction */ +#define UPROBE_COPY_INSN 0 + +struct uprobe { + struct rb_node rb_node; /* node in the rb tree */ + atomic_t ref; + struct rw_semaphore register_rwsem; + struct rw_semaphore consumer_rwsem; + struct list_head pending_list; + struct uprobe_consumer *consumers; + struct inode *inode; /* Also hold a ref to inode */ + loff_t offset; + unsigned long flags; + + /* + * The generic code assumes that it has two members of unknown type + * owned by the arch-specific code: + * + * insn - copy_insn() saves the original instruction here for + * arch_uprobe_analyze_insn(). + * + * ixol - potentially modified instruction to execute out of + * line, copied to xol_area by xol_get_insn_slot(). + */ + struct arch_uprobe arch; +}; + +struct return_instance { + struct uprobe *uprobe; + unsigned long func; + unsigned long orig_ret_vaddr; /* original return address */ + bool chained; /* true, if instance is nested */ + + struct return_instance *next; /* keep as stack */ +}; + +/* + * Execute out of line area: anonymous executable mapping installed + * by the probed task to execute the copy of the original instruction + * mangled by set_swbp(). + * + * On a breakpoint hit, thread contests for a slot. It frees the + * slot after singlestep. Currently a fixed number of slots are + * allocated. + */ +struct xol_area { + wait_queue_head_t wq; /* if all slots are busy */ + atomic_t slot_count; /* number of in-use slots */ + unsigned long *bitmap; /* 0 = free slot */ + struct page *page; + + /* + * We keep the vma's vm_start rather than a pointer to the vma + * itself. The probed process or a naughty kernel module could make + * the vma go away, and we must handle that reasonably gracefully. + */ + unsigned long vaddr; /* Page(s) of instruction slots */ +}; + +/* + * valid_vma: Verify if the specified vma is an executable vma + * Relax restrictions while unregistering: vm_flags might have + * changed after breakpoint was inserted. + * - is_register: indicates if we are in register context. + * - Return 1 if the specified virtual address is in an + * executable vma. + */ +static bool valid_vma(struct vm_area_struct *vma, bool is_register) +{ + vm_flags_t flags = VM_HUGETLB | VM_MAYEXEC | VM_MAYSHARE; + + if (is_register) + flags |= VM_WRITE; + + return vma->vm_file && (vma->vm_flags & flags) == VM_MAYEXEC; +} + +static unsigned long offset_to_vaddr(struct vm_area_struct *vma, loff_t offset) +{ + return vma->vm_start + offset - ((loff_t)vma->vm_pgoff << PAGE_SHIFT); +} + +static loff_t vaddr_to_offset(struct vm_area_struct *vma, unsigned long vaddr) +{ + return ((loff_t)vma->vm_pgoff << PAGE_SHIFT) + (vaddr - vma->vm_start); +} + +/** + * __replace_page - replace page in vma by new page. + * based on replace_page in mm/ksm.c + * + * @vma: vma that holds the pte pointing to page + * @addr: address the old @page is mapped at + * @page: the cowed page we are replacing by kpage + * @kpage: the modified page we replace page by + * + * Returns 0 on success, -EFAULT on failure. + */ +static int __replace_page(struct vm_area_struct *vma, unsigned long addr, + struct page *page, struct page *kpage) +{ + struct mm_struct *mm = vma->vm_mm; + spinlock_t *ptl; + pte_t *ptep; + int err; + /* For mmu_notifiers */ + const unsigned long mmun_start = addr; + const unsigned long mmun_end = addr + PAGE_SIZE; + struct mem_cgroup *memcg; + + err = mem_cgroup_try_charge(kpage, vma->vm_mm, GFP_KERNEL, &memcg); + if (err) + return err; + + /* For try_to_free_swap() and munlock_vma_page() below */ + lock_page(page); + + mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end); + err = -EAGAIN; + ptep = page_check_address(page, mm, addr, &ptl, 0); + if (!ptep) + goto unlock; + + get_page(kpage); + page_add_new_anon_rmap(kpage, vma, addr); + mem_cgroup_commit_charge(kpage, memcg, false); + lru_cache_add_active_or_unevictable(kpage, vma); + + if (!PageAnon(page)) { + dec_mm_counter(mm, MM_FILEPAGES); + inc_mm_counter(mm, MM_ANONPAGES); + } + + flush_cache_page(vma, addr, pte_pfn(*ptep)); + ptep_clear_flush_notify(vma, addr, ptep); + set_pte_at_notify(mm, addr, ptep, mk_pte(kpage, vma->vm_page_prot)); + + page_remove_rmap(page); + if (!page_mapped(page)) + try_to_free_swap(page); + pte_unmap_unlock(ptep, ptl); + + if (vma->vm_flags & VM_LOCKED) + munlock_vma_page(page); + put_page(page); + + err = 0; + unlock: + mem_cgroup_cancel_charge(kpage, memcg); + mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); + unlock_page(page); + return err; +} + +/** + * is_swbp_insn - check if instruction is breakpoint instruction. + * @insn: instruction to be checked. + * Default implementation of is_swbp_insn + * Returns true if @insn is a breakpoint instruction. + */ +bool __weak is_swbp_insn(uprobe_opcode_t *insn) +{ + return *insn == UPROBE_SWBP_INSN; +} + +/** + * is_trap_insn - check if instruction is breakpoint instruction. + * @insn: instruction to be checked. + * Default implementation of is_trap_insn + * Returns true if @insn is a breakpoint instruction. + * + * This function is needed for the case where an architecture has multiple + * trap instructions (like powerpc). + */ +bool __weak is_trap_insn(uprobe_opcode_t *insn) +{ + return is_swbp_insn(insn); +} + +static void copy_from_page(struct page *page, unsigned long vaddr, void *dst, int len) +{ + void *kaddr = kmap_atomic(page); + memcpy(dst, kaddr + (vaddr & ~PAGE_MASK), len); + kunmap_atomic(kaddr); +} + +static void copy_to_page(struct page *page, unsigned long vaddr, const void *src, int len) +{ + void *kaddr = kmap_atomic(page); + memcpy(kaddr + (vaddr & ~PAGE_MASK), src, len); + kunmap_atomic(kaddr); +} + +static int verify_opcode(struct page *page, unsigned long vaddr, uprobe_opcode_t *new_opcode) +{ + uprobe_opcode_t old_opcode; + bool is_swbp; + + /* + * Note: We only check if the old_opcode is UPROBE_SWBP_INSN here. + * We do not check if it is any other 'trap variant' which could + * be conditional trap instruction such as the one powerpc supports. + * + * The logic is that we do not care if the underlying instruction + * is a trap variant; uprobes always wins over any other (gdb) + * breakpoint. + */ + copy_from_page(page, vaddr, &old_opcode, UPROBE_SWBP_INSN_SIZE); + is_swbp = is_swbp_insn(&old_opcode); + + if (is_swbp_insn(new_opcode)) { + if (is_swbp) /* register: already installed? */ + return 0; + } else { + if (!is_swbp) /* unregister: was it changed by us? */ + return 0; + } + + return 1; +} + +/* + * NOTE: + * Expect the breakpoint instruction to be the smallest size instruction for + * the architecture. If an arch has variable length instruction and the + * breakpoint instruction is not of the smallest length instruction + * supported by that architecture then we need to modify is_trap_at_addr and + * uprobe_write_opcode accordingly. This would never be a problem for archs + * that have fixed length instructions. + * + * uprobe_write_opcode - write the opcode at a given virtual address. + * @mm: the probed process address space. + * @vaddr: the virtual address to store the opcode. + * @opcode: opcode to be written at @vaddr. + * + * Called with mm->mmap_sem held for write. + * Return 0 (success) or a negative errno. + */ +int uprobe_write_opcode(struct mm_struct *mm, unsigned long vaddr, + uprobe_opcode_t opcode) +{ + struct page *old_page, *new_page; + struct vm_area_struct *vma; + int ret; + +retry: + /* Read the page with vaddr into memory */ + ret = get_user_pages(NULL, mm, vaddr, 1, 0, 1, &old_page, &vma); + if (ret <= 0) + return ret; + + ret = verify_opcode(old_page, vaddr, &opcode); + if (ret <= 0) + goto put_old; + + ret = anon_vma_prepare(vma); + if (ret) + goto put_old; + + ret = -ENOMEM; + new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, vaddr); + if (!new_page) + goto put_old; + + __SetPageUptodate(new_page); + copy_highpage(new_page, old_page); + copy_to_page(new_page, vaddr, &opcode, UPROBE_SWBP_INSN_SIZE); + + ret = __replace_page(vma, vaddr, old_page, new_page); + page_cache_release(new_page); +put_old: + put_page(old_page); + + if (unlikely(ret == -EAGAIN)) + goto retry; + return ret; +} + +/** + * set_swbp - store breakpoint at a given address. + * @auprobe: arch specific probepoint information. + * @mm: the probed process address space. + * @vaddr: the virtual address to insert the opcode. + * + * For mm @mm, store the breakpoint instruction at @vaddr. + * Return 0 (success) or a negative errno. + */ +int __weak set_swbp(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr) +{ + return uprobe_write_opcode(mm, vaddr, UPROBE_SWBP_INSN); +} + +/** + * set_orig_insn - Restore the original instruction. + * @mm: the probed process address space. + * @auprobe: arch specific probepoint information. + * @vaddr: the virtual address to insert the opcode. + * + * For mm @mm, restore the original opcode (opcode) at @vaddr. + * Return 0 (success) or a negative errno. + */ +int __weak +set_orig_insn(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr) +{ + return uprobe_write_opcode(mm, vaddr, *(uprobe_opcode_t *)&auprobe->insn); +} + +static int match_uprobe(struct uprobe *l, struct uprobe *r) +{ + if (l->inode < r->inode) + return -1; + + if (l->inode > r->inode) + return 1; + + if (l->offset < r->offset) + return -1; + + if (l->offset > r->offset) + return 1; + + return 0; +} + +static struct uprobe *__find_uprobe(struct inode *inode, loff_t offset) +{ + struct uprobe u = { .inode = inode, .offset = offset }; + struct rb_node *n = uprobes_tree.rb_node; + struct uprobe *uprobe; + int match; + + while (n) { + uprobe = rb_entry(n, struct uprobe, rb_node); + match = match_uprobe(&u, uprobe); + if (!match) { + atomic_inc(&uprobe->ref); + return uprobe; + } + + if (match < 0) + n = n->rb_left; + else + n = n->rb_right; + } + return NULL; +} + +/* + * Find a uprobe corresponding to a given inode:offset + * Acquires uprobes_treelock + */ +static struct uprobe *find_uprobe(struct inode *inode, loff_t offset) +{ + struct uprobe *uprobe; + + spin_lock(&uprobes_treelock); + uprobe = __find_uprobe(inode, offset); + spin_unlock(&uprobes_treelock); + + return uprobe; +} + +static struct uprobe *__insert_uprobe(struct uprobe *uprobe) +{ + struct rb_node **p = &uprobes_tree.rb_node; + struct rb_node *parent = NULL; + struct uprobe *u; + int match; + + while (*p) { + parent = *p; + u = rb_entry(parent, struct uprobe, rb_node); + match = match_uprobe(uprobe, u); + if (!match) { + atomic_inc(&u->ref); + return u; + } + + if (match < 0) + p = &parent->rb_left; + else + p = &parent->rb_right; + + } + + u = NULL; + rb_link_node(&uprobe->rb_node, parent, p); + rb_insert_color(&uprobe->rb_node, &uprobes_tree); + /* get access + creation ref */ + atomic_set(&uprobe->ref, 2); + + return u; +} + +/* + * Acquire uprobes_treelock. + * Matching uprobe already exists in rbtree; + * increment (access refcount) and return the matching uprobe. + * + * No matching uprobe; insert the uprobe in rb_tree; + * get a double refcount (access + creation) and return NULL. + */ +static struct uprobe *insert_uprobe(struct uprobe *uprobe) +{ + struct uprobe *u; + + spin_lock(&uprobes_treelock); + u = __insert_uprobe(uprobe); + spin_unlock(&uprobes_treelock); + + return u; +} + +static void put_uprobe(struct uprobe *uprobe) +{ + if (atomic_dec_and_test(&uprobe->ref)) + kfree(uprobe); +} + +static struct uprobe *alloc_uprobe(struct inode *inode, loff_t offset) +{ + struct uprobe *uprobe, *cur_uprobe; + + uprobe = kzalloc(sizeof(struct uprobe), GFP_KERNEL); + if (!uprobe) + return NULL; + + uprobe->inode = igrab(inode); + uprobe->offset = offset; + init_rwsem(&uprobe->register_rwsem); + init_rwsem(&uprobe->consumer_rwsem); + + /* add to uprobes_tree, sorted on inode:offset */ + cur_uprobe = insert_uprobe(uprobe); + /* a uprobe exists for this inode:offset combination */ + if (cur_uprobe) { + kfree(uprobe); + uprobe = cur_uprobe; + iput(inode); + } + + return uprobe; +} + +static void consumer_add(struct uprobe *uprobe, struct uprobe_consumer *uc) +{ + down_write(&uprobe->consumer_rwsem); + uc->next = uprobe->consumers; + uprobe->consumers = uc; + up_write(&uprobe->consumer_rwsem); +} + +/* + * For uprobe @uprobe, delete the consumer @uc. + * Return true if the @uc is deleted successfully + * or return false. + */ +static bool consumer_del(struct uprobe *uprobe, struct uprobe_consumer *uc) +{ + struct uprobe_consumer **con; + bool ret = false; + + down_write(&uprobe->consumer_rwsem); + for (con = &uprobe->consumers; *con; con = &(*con)->next) { + if (*con == uc) { + *con = uc->next; + ret = true; + break; + } + } + up_write(&uprobe->consumer_rwsem); + + return ret; +} + +static int __copy_insn(struct address_space *mapping, struct file *filp, + void *insn, int nbytes, loff_t offset) +{ + struct page *page; + /* + * Ensure that the page that has the original instruction is populated + * and in page-cache. If ->readpage == NULL it must be shmem_mapping(), + * see uprobe_register(). + */ + if (mapping->a_ops->readpage) + page = read_mapping_page(mapping, offset >> PAGE_CACHE_SHIFT, filp); + else + page = shmem_read_mapping_page(mapping, offset >> PAGE_CACHE_SHIFT); + if (IS_ERR(page)) + return PTR_ERR(page); + + copy_from_page(page, offset, insn, nbytes); + page_cache_release(page); + + return 0; +} + +static int copy_insn(struct uprobe *uprobe, struct file *filp) +{ + struct address_space *mapping = uprobe->inode->i_mapping; + loff_t offs = uprobe->offset; + void *insn = &uprobe->arch.insn; + int size = sizeof(uprobe->arch.insn); + int len, err = -EIO; + + /* Copy only available bytes, -EIO if nothing was read */ + do { + if (offs >= i_size_read(uprobe->inode)) + break; + + len = min_t(int, size, PAGE_SIZE - (offs & ~PAGE_MASK)); + err = __copy_insn(mapping, filp, insn, len, offs); + if (err) + break; + + insn += len; + offs += len; + size -= len; + } while (size); + + return err; +} + +static int prepare_uprobe(struct uprobe *uprobe, struct file *file, + struct mm_struct *mm, unsigned long vaddr) +{ + int ret = 0; + + if (test_bit(UPROBE_COPY_INSN, &uprobe->flags)) + return ret; + + /* TODO: move this into _register, until then we abuse this sem. */ + down_write(&uprobe->consumer_rwsem); + if (test_bit(UPROBE_COPY_INSN, &uprobe->flags)) + goto out; + + ret = copy_insn(uprobe, file); + if (ret) + goto out; + + ret = -ENOTSUPP; + if (is_trap_insn((uprobe_opcode_t *)&uprobe->arch.insn)) + goto out; + + ret = arch_uprobe_analyze_insn(&uprobe->arch, mm, vaddr); + if (ret) + goto out; + + /* uprobe_write_opcode() assumes we don't cross page boundary */ + BUG_ON((uprobe->offset & ~PAGE_MASK) + + UPROBE_SWBP_INSN_SIZE > PAGE_SIZE); + + smp_wmb(); /* pairs with rmb() in find_active_uprobe() */ + set_bit(UPROBE_COPY_INSN, &uprobe->flags); + + out: + up_write(&uprobe->consumer_rwsem); + + return ret; +} + +static inline bool consumer_filter(struct uprobe_consumer *uc, + enum uprobe_filter_ctx ctx, struct mm_struct *mm) +{ + return !uc->filter || uc->filter(uc, ctx, mm); +} + +static bool filter_chain(struct uprobe *uprobe, + enum uprobe_filter_ctx ctx, struct mm_struct *mm) +{ + struct uprobe_consumer *uc; + bool ret = false; + + down_read(&uprobe->consumer_rwsem); + for (uc = uprobe->consumers; uc; uc = uc->next) { + ret = consumer_filter(uc, ctx, mm); + if (ret) + break; + } + up_read(&uprobe->consumer_rwsem); + + return ret; +} + +static int +install_breakpoint(struct uprobe *uprobe, struct mm_struct *mm, + struct vm_area_struct *vma, unsigned long vaddr) +{ + bool first_uprobe; + int ret; + + ret = prepare_uprobe(uprobe, vma->vm_file, mm, vaddr); + if (ret) + return ret; + + /* + * set MMF_HAS_UPROBES in advance for uprobe_pre_sstep_notifier(), + * the task can hit this breakpoint right after __replace_page(). + */ + first_uprobe = !test_bit(MMF_HAS_UPROBES, &mm->flags); + if (first_uprobe) + set_bit(MMF_HAS_UPROBES, &mm->flags); + + ret = set_swbp(&uprobe->arch, mm, vaddr); + if (!ret) + clear_bit(MMF_RECALC_UPROBES, &mm->flags); + else if (first_uprobe) + clear_bit(MMF_HAS_UPROBES, &mm->flags); + + return ret; +} + +static int +remove_breakpoint(struct uprobe *uprobe, struct mm_struct *mm, unsigned long vaddr) +{ + set_bit(MMF_RECALC_UPROBES, &mm->flags); + return set_orig_insn(&uprobe->arch, mm, vaddr); +} + +static inline bool uprobe_is_active(struct uprobe *uprobe) +{ + return !RB_EMPTY_NODE(&uprobe->rb_node); +} +/* + * There could be threads that have already hit the breakpoint. They + * will recheck the current insn and restart if find_uprobe() fails. + * See find_active_uprobe(). + */ +static void delete_uprobe(struct uprobe *uprobe) +{ + if (WARN_ON(!uprobe_is_active(uprobe))) + return; + + spin_lock(&uprobes_treelock); + rb_erase(&uprobe->rb_node, &uprobes_tree); + spin_unlock(&uprobes_treelock); + RB_CLEAR_NODE(&uprobe->rb_node); /* for uprobe_is_active() */ + iput(uprobe->inode); + put_uprobe(uprobe); +} + +struct map_info { + struct map_info *next; + struct mm_struct *mm; + unsigned long vaddr; +}; + +static inline struct map_info *free_map_info(struct map_info *info) +{ + struct map_info *next = info->next; + kfree(info); + return next; +} + +static struct map_info * +build_map_info(struct address_space *mapping, loff_t offset, bool is_register) +{ + unsigned long pgoff = offset >> PAGE_SHIFT; + struct vm_area_struct *vma; + struct map_info *curr = NULL; + struct map_info *prev = NULL; + struct map_info *info; + int more = 0; + + again: + i_mmap_lock_read(mapping); + vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff, pgoff) { + if (!valid_vma(vma, is_register)) + continue; + + if (!prev && !more) { + /* + * Needs GFP_NOWAIT to avoid i_mmap_rwsem recursion through + * reclaim. This is optimistic, no harm done if it fails. + */ + prev = kmalloc(sizeof(struct map_info), + GFP_NOWAIT | __GFP_NOMEMALLOC | __GFP_NOWARN); + if (prev) + prev->next = NULL; + } + if (!prev) { + more++; + continue; + } + + if (!atomic_inc_not_zero(&vma->vm_mm->mm_users)) + continue; + + info = prev; + prev = prev->next; + info->next = curr; + curr = info; + + info->mm = vma->vm_mm; + info->vaddr = offset_to_vaddr(vma, offset); + } + i_mmap_unlock_read(mapping); + + if (!more) + goto out; + + prev = curr; + while (curr) { + mmput(curr->mm); + curr = curr->next; + } + + do { + info = kmalloc(sizeof(struct map_info), GFP_KERNEL); + if (!info) { + curr = ERR_PTR(-ENOMEM); + goto out; + } + info->next = prev; + prev = info; + } while (--more); + + goto again; + out: + while (prev) + prev = free_map_info(prev); + return curr; +} + +static int +register_for_each_vma(struct uprobe *uprobe, struct uprobe_consumer *new) +{ + bool is_register = !!new; + struct map_info *info; + int err = 0; + + percpu_down_write(&dup_mmap_sem); + info = build_map_info(uprobe->inode->i_mapping, + uprobe->offset, is_register); + if (IS_ERR(info)) { + err = PTR_ERR(info); + goto out; + } + + while (info) { + struct mm_struct *mm = info->mm; + struct vm_area_struct *vma; + + if (err && is_register) + goto free; + + down_write(&mm->mmap_sem); + vma = find_vma(mm, info->vaddr); + if (!vma || !valid_vma(vma, is_register) || + file_inode(vma->vm_file) != uprobe->inode) + goto unlock; + + if (vma->vm_start > info->vaddr || + vaddr_to_offset(vma, info->vaddr) != uprobe->offset) + goto unlock; + + if (is_register) { + /* consult only the "caller", new consumer. */ + if (consumer_filter(new, + UPROBE_FILTER_REGISTER, mm)) + err = install_breakpoint(uprobe, mm, vma, info->vaddr); + } else if (test_bit(MMF_HAS_UPROBES, &mm->flags)) { + if (!filter_chain(uprobe, + UPROBE_FILTER_UNREGISTER, mm)) + err |= remove_breakpoint(uprobe, mm, info->vaddr); + } + + unlock: + up_write(&mm->mmap_sem); + free: + mmput(mm); + info = free_map_info(info); + } + out: + percpu_up_write(&dup_mmap_sem); + return err; +} + +static int __uprobe_register(struct uprobe *uprobe, struct uprobe_consumer *uc) +{ + consumer_add(uprobe, uc); + return register_for_each_vma(uprobe, uc); +} + +static void __uprobe_unregister(struct uprobe *uprobe, struct uprobe_consumer *uc) +{ + int err; + + if (WARN_ON(!consumer_del(uprobe, uc))) + return; + + err = register_for_each_vma(uprobe, NULL); + /* TODO : cant unregister? schedule a worker thread */ + if (!uprobe->consumers && !err) + delete_uprobe(uprobe); +} + +/* + * uprobe_register - register a probe + * @inode: the file in which the probe has to be placed. + * @offset: offset from the start of the file. + * @uc: information on howto handle the probe.. + * + * Apart from the access refcount, uprobe_register() takes a creation + * refcount (thro alloc_uprobe) if and only if this @uprobe is getting + * inserted into the rbtree (i.e first consumer for a @inode:@offset + * tuple). Creation refcount stops uprobe_unregister from freeing the + * @uprobe even before the register operation is complete. Creation + * refcount is released when the last @uc for the @uprobe + * unregisters. + * + * Return errno if it cannot successully install probes + * else return 0 (success) + */ +int uprobe_register(struct inode *inode, loff_t offset, struct uprobe_consumer *uc) +{ + struct uprobe *uprobe; + int ret; + + /* Uprobe must have at least one set consumer */ + if (!uc->handler && !uc->ret_handler) + return -EINVAL; + + /* copy_insn() uses read_mapping_page() or shmem_read_mapping_page() */ + if (!inode->i_mapping->a_ops->readpage && !shmem_mapping(inode->i_mapping)) + return -EIO; + /* Racy, just to catch the obvious mistakes */ + if (offset > i_size_read(inode)) + return -EINVAL; + + retry: + uprobe = alloc_uprobe(inode, offset); + if (!uprobe) + return -ENOMEM; + /* + * We can race with uprobe_unregister()->delete_uprobe(). + * Check uprobe_is_active() and retry if it is false. + */ + down_write(&uprobe->register_rwsem); + ret = -EAGAIN; + if (likely(uprobe_is_active(uprobe))) { + ret = __uprobe_register(uprobe, uc); + if (ret) + __uprobe_unregister(uprobe, uc); + } + up_write(&uprobe->register_rwsem); + put_uprobe(uprobe); + + if (unlikely(ret == -EAGAIN)) + goto retry; + return ret; +} +EXPORT_SYMBOL_GPL(uprobe_register); + +/* + * uprobe_apply - unregister a already registered probe. + * @inode: the file in which the probe has to be removed. + * @offset: offset from the start of the file. + * @uc: consumer which wants to add more or remove some breakpoints + * @add: add or remove the breakpoints + */ +int uprobe_apply(struct inode *inode, loff_t offset, + struct uprobe_consumer *uc, bool add) +{ + struct uprobe *uprobe; + struct uprobe_consumer *con; + int ret = -ENOENT; + + uprobe = find_uprobe(inode, offset); + if (WARN_ON(!uprobe)) + return ret; + + down_write(&uprobe->register_rwsem); + for (con = uprobe->consumers; con && con != uc ; con = con->next) + ; + if (con) + ret = register_for_each_vma(uprobe, add ? uc : NULL); + up_write(&uprobe->register_rwsem); + put_uprobe(uprobe); + + return ret; +} + +/* + * uprobe_unregister - unregister a already registered probe. + * @inode: the file in which the probe has to be removed. + * @offset: offset from the start of the file. + * @uc: identify which probe if multiple probes are colocated. + */ +void uprobe_unregister(struct inode *inode, loff_t offset, struct uprobe_consumer *uc) +{ + struct uprobe *uprobe; + + uprobe = find_uprobe(inode, offset); + if (WARN_ON(!uprobe)) + return; + + down_write(&uprobe->register_rwsem); + __uprobe_unregister(uprobe, uc); + up_write(&uprobe->register_rwsem); + put_uprobe(uprobe); +} +EXPORT_SYMBOL_GPL(uprobe_unregister); + +static int unapply_uprobe(struct uprobe *uprobe, struct mm_struct *mm) +{ + struct vm_area_struct *vma; + int err = 0; + + down_read(&mm->mmap_sem); + for (vma = mm->mmap; vma; vma = vma->vm_next) { + unsigned long vaddr; + loff_t offset; + + if (!valid_vma(vma, false) || + file_inode(vma->vm_file) != uprobe->inode) + continue; + + offset = (loff_t)vma->vm_pgoff << PAGE_SHIFT; + if (uprobe->offset < offset || + uprobe->offset >= offset + vma->vm_end - vma->vm_start) + continue; + + vaddr = offset_to_vaddr(vma, uprobe->offset); + err |= remove_breakpoint(uprobe, mm, vaddr); + } + up_read(&mm->mmap_sem); + + return err; +} + +static struct rb_node * +find_node_in_range(struct inode *inode, loff_t min, loff_t max) +{ + struct rb_node *n = uprobes_tree.rb_node; + + while (n) { + struct uprobe *u = rb_entry(n, struct uprobe, rb_node); + + if (inode < u->inode) { + n = n->rb_left; + } else if (inode > u->inode) { + n = n->rb_right; + } else { + if (max < u->offset) + n = n->rb_left; + else if (min > u->offset) + n = n->rb_right; + else + break; + } + } + + return n; +} + +/* + * For a given range in vma, build a list of probes that need to be inserted. + */ +static void build_probe_list(struct inode *inode, + struct vm_area_struct *vma, + unsigned long start, unsigned long end, + struct list_head *head) +{ + loff_t min, max; + struct rb_node *n, *t; + struct uprobe *u; + + INIT_LIST_HEAD(head); + min = vaddr_to_offset(vma, start); + max = min + (end - start) - 1; + + spin_lock(&uprobes_treelock); + n = find_node_in_range(inode, min, max); + if (n) { + for (t = n; t; t = rb_prev(t)) { + u = rb_entry(t, struct uprobe, rb_node); + if (u->inode != inode || u->offset < min) + break; + list_add(&u->pending_list, head); + atomic_inc(&u->ref); + } + for (t = n; (t = rb_next(t)); ) { + u = rb_entry(t, struct uprobe, rb_node); + if (u->inode != inode || u->offset > max) + break; + list_add(&u->pending_list, head); + atomic_inc(&u->ref); + } + } + spin_unlock(&uprobes_treelock); +} + +/* + * Called from mmap_region/vma_adjust with mm->mmap_sem acquired. + * + * Currently we ignore all errors and always return 0, the callers + * can't handle the failure anyway. + */ +int uprobe_mmap(struct vm_area_struct *vma) +{ + struct list_head tmp_list; + struct uprobe *uprobe, *u; + struct inode *inode; + + if (no_uprobe_events() || !valid_vma(vma, true)) + return 0; + + inode = file_inode(vma->vm_file); + if (!inode) + return 0; + + mutex_lock(uprobes_mmap_hash(inode)); + build_probe_list(inode, vma, vma->vm_start, vma->vm_end, &tmp_list); + /* + * We can race with uprobe_unregister(), this uprobe can be already + * removed. But in this case filter_chain() must return false, all + * consumers have gone away. + */ + list_for_each_entry_safe(uprobe, u, &tmp_list, pending_list) { + if (!fatal_signal_pending(current) && + filter_chain(uprobe, UPROBE_FILTER_MMAP, vma->vm_mm)) { + unsigned long vaddr = offset_to_vaddr(vma, uprobe->offset); + install_breakpoint(uprobe, vma->vm_mm, vma, vaddr); + } + put_uprobe(uprobe); + } + mutex_unlock(uprobes_mmap_hash(inode)); + + return 0; +} + +static bool +vma_has_uprobes(struct vm_area_struct *vma, unsigned long start, unsigned long end) +{ + loff_t min, max; + struct inode *inode; + struct rb_node *n; + + inode = file_inode(vma->vm_file); + + min = vaddr_to_offset(vma, start); + max = min + (end - start) - 1; + + spin_lock(&uprobes_treelock); + n = find_node_in_range(inode, min, max); + spin_unlock(&uprobes_treelock); + + return !!n; +} + +/* + * Called in context of a munmap of a vma. + */ +void uprobe_munmap(struct vm_area_struct *vma, unsigned long start, unsigned long end) +{ + if (no_uprobe_events() || !valid_vma(vma, false)) + return; + + if (!atomic_read(&vma->vm_mm->mm_users)) /* called by mmput() ? */ + return; + + if (!test_bit(MMF_HAS_UPROBES, &vma->vm_mm->flags) || + test_bit(MMF_RECALC_UPROBES, &vma->vm_mm->flags)) + return; + + if (vma_has_uprobes(vma, start, end)) + set_bit(MMF_RECALC_UPROBES, &vma->vm_mm->flags); +} + +/* Slot allocation for XOL */ +static int xol_add_vma(struct mm_struct *mm, struct xol_area *area) +{ + int ret = -EALREADY; + + down_write(&mm->mmap_sem); + if (mm->uprobes_state.xol_area) + goto fail; + + if (!area->vaddr) { + /* Try to map as high as possible, this is only a hint. */ + area->vaddr = get_unmapped_area(NULL, TASK_SIZE - PAGE_SIZE, + PAGE_SIZE, 0, 0); + if (area->vaddr & ~PAGE_MASK) { + ret = area->vaddr; + goto fail; + } + } + + ret = install_special_mapping(mm, area->vaddr, PAGE_SIZE, + VM_EXEC|VM_MAYEXEC|VM_DONTCOPY|VM_IO, &area->page); + if (ret) + goto fail; + + smp_wmb(); /* pairs with get_xol_area() */ + mm->uprobes_state.xol_area = area; + fail: + up_write(&mm->mmap_sem); + + return ret; +} + +static struct xol_area *__create_xol_area(unsigned long vaddr) +{ + struct mm_struct *mm = current->mm; + uprobe_opcode_t insn = UPROBE_SWBP_INSN; + struct xol_area *area; + + area = kmalloc(sizeof(*area), GFP_KERNEL); + if (unlikely(!area)) + goto out; + + area->bitmap = kzalloc(BITS_TO_LONGS(UINSNS_PER_PAGE) * sizeof(long), GFP_KERNEL); + if (!area->bitmap) + goto free_area; + + area->page = alloc_page(GFP_HIGHUSER); + if (!area->page) + goto free_bitmap; + + area->vaddr = vaddr; + init_waitqueue_head(&area->wq); + /* Reserve the 1st slot for get_trampoline_vaddr() */ + set_bit(0, area->bitmap); + atomic_set(&area->slot_count, 1); + copy_to_page(area->page, 0, &insn, UPROBE_SWBP_INSN_SIZE); + + if (!xol_add_vma(mm, area)) + return area; + + __free_page(area->page); + free_bitmap: + kfree(area->bitmap); + free_area: + kfree(area); + out: + return NULL; +} + +/* + * get_xol_area - Allocate process's xol_area if necessary. + * This area will be used for storing instructions for execution out of line. + * + * Returns the allocated area or NULL. + */ +static struct xol_area *get_xol_area(void) +{ + struct mm_struct *mm = current->mm; + struct xol_area *area; + + if (!mm->uprobes_state.xol_area) + __create_xol_area(0); + + area = mm->uprobes_state.xol_area; + smp_read_barrier_depends(); /* pairs with wmb in xol_add_vma() */ + return area; +} + +/* + * uprobe_clear_state - Free the area allocated for slots. + */ +void uprobe_clear_state(struct mm_struct *mm) +{ + struct xol_area *area = mm->uprobes_state.xol_area; + + if (!area) + return; + + put_page(area->page); + kfree(area->bitmap); + kfree(area); +} + +void uprobe_start_dup_mmap(void) +{ + percpu_down_read(&dup_mmap_sem); +} + +void uprobe_end_dup_mmap(void) +{ + percpu_up_read(&dup_mmap_sem); +} + +void uprobe_dup_mmap(struct mm_struct *oldmm, struct mm_struct *newmm) +{ + newmm->uprobes_state.xol_area = NULL; + + if (test_bit(MMF_HAS_UPROBES, &oldmm->flags)) { + set_bit(MMF_HAS_UPROBES, &newmm->flags); + /* unconditionally, dup_mmap() skips VM_DONTCOPY vmas */ + set_bit(MMF_RECALC_UPROBES, &newmm->flags); + } +} + +/* + * - search for a free slot. + */ +static unsigned long xol_take_insn_slot(struct xol_area *area) +{ + unsigned long slot_addr; + int slot_nr; + + do { + slot_nr = find_first_zero_bit(area->bitmap, UINSNS_PER_PAGE); + if (slot_nr < UINSNS_PER_PAGE) { + if (!test_and_set_bit(slot_nr, area->bitmap)) + break; + + slot_nr = UINSNS_PER_PAGE; + continue; + } + wait_event(area->wq, (atomic_read(&area->slot_count) < UINSNS_PER_PAGE)); + } while (slot_nr >= UINSNS_PER_PAGE); + + slot_addr = area->vaddr + (slot_nr * UPROBE_XOL_SLOT_BYTES); + atomic_inc(&area->slot_count); + + return slot_addr; +} + +/* + * xol_get_insn_slot - allocate a slot for xol. + * Returns the allocated slot address or 0. + */ +static unsigned long xol_get_insn_slot(struct uprobe *uprobe) +{ + struct xol_area *area; + unsigned long xol_vaddr; + + area = get_xol_area(); + if (!area) + return 0; + + xol_vaddr = xol_take_insn_slot(area); + if (unlikely(!xol_vaddr)) + return 0; + + arch_uprobe_copy_ixol(area->page, xol_vaddr, + &uprobe->arch.ixol, sizeof(uprobe->arch.ixol)); + + return xol_vaddr; +} + +/* + * xol_free_insn_slot - If slot was earlier allocated by + * @xol_get_insn_slot(), make the slot available for + * subsequent requests. + */ +static void xol_free_insn_slot(struct task_struct *tsk) +{ + struct xol_area *area; + unsigned long vma_end; + unsigned long slot_addr; + + if (!tsk->mm || !tsk->mm->uprobes_state.xol_area || !tsk->utask) + return; + + slot_addr = tsk->utask->xol_vaddr; + if (unlikely(!slot_addr)) + return; + + area = tsk->mm->uprobes_state.xol_area; + vma_end = area->vaddr + PAGE_SIZE; + if (area->vaddr <= slot_addr && slot_addr < vma_end) { + unsigned long offset; + int slot_nr; + + offset = slot_addr - area->vaddr; + slot_nr = offset / UPROBE_XOL_SLOT_BYTES; + if (slot_nr >= UINSNS_PER_PAGE) + return; + + clear_bit(slot_nr, area->bitmap); + atomic_dec(&area->slot_count); + if (waitqueue_active(&area->wq)) + wake_up(&area->wq); + + tsk->utask->xol_vaddr = 0; + } +} + +void __weak arch_uprobe_copy_ixol(struct page *page, unsigned long vaddr, + void *src, unsigned long len) +{ + /* Initialize the slot */ + copy_to_page(page, vaddr, src, len); + + /* + * We probably need flush_icache_user_range() but it needs vma. + * This should work on most of architectures by default. If + * architecture needs to do something different it can define + * its own version of the function. + */ + flush_dcache_page(page); +} + +/** + * uprobe_get_swbp_addr - compute address of swbp given post-swbp regs + * @regs: Reflects the saved state of the task after it has hit a breakpoint + * instruction. + * Return the address of the breakpoint instruction. + */ +unsigned long __weak uprobe_get_swbp_addr(struct pt_regs *regs) +{ + return instruction_pointer(regs) - UPROBE_SWBP_INSN_SIZE; +} + +unsigned long uprobe_get_trap_addr(struct pt_regs *regs) +{ + struct uprobe_task *utask = current->utask; + + if (unlikely(utask && utask->active_uprobe)) + return utask->vaddr; + + return instruction_pointer(regs); +} + +/* + * Called with no locks held. + * Called in context of a exiting or a exec-ing thread. + */ +void uprobe_free_utask(struct task_struct *t) +{ + struct uprobe_task *utask = t->utask; + struct return_instance *ri, *tmp; + + if (!utask) + return; + + if (utask->active_uprobe) + put_uprobe(utask->active_uprobe); + + ri = utask->return_instances; + while (ri) { + tmp = ri; + ri = ri->next; + + put_uprobe(tmp->uprobe); + kfree(tmp); + } + + xol_free_insn_slot(t); + kfree(utask); + t->utask = NULL; +} + +/* + * Allocate a uprobe_task object for the task if if necessary. + * Called when the thread hits a breakpoint. + * + * Returns: + * - pointer to new uprobe_task on success + * - NULL otherwise + */ +static struct uprobe_task *get_utask(void) +{ + if (!current->utask) + current->utask = kzalloc(sizeof(struct uprobe_task), GFP_KERNEL); + return current->utask; +} + +static int dup_utask(struct task_struct *t, struct uprobe_task *o_utask) +{ + struct uprobe_task *n_utask; + struct return_instance **p, *o, *n; + + n_utask = kzalloc(sizeof(struct uprobe_task), GFP_KERNEL); + if (!n_utask) + return -ENOMEM; + t->utask = n_utask; + + p = &n_utask->return_instances; + for (o = o_utask->return_instances; o; o = o->next) { + n = kmalloc(sizeof(struct return_instance), GFP_KERNEL); + if (!n) + return -ENOMEM; + + *n = *o; + atomic_inc(&n->uprobe->ref); + n->next = NULL; + + *p = n; + p = &n->next; + n_utask->depth++; + } + + return 0; +} + +static void uprobe_warn(struct task_struct *t, const char *msg) +{ + pr_warn("uprobe: %s:%d failed to %s\n", + current->comm, current->pid, msg); +} + +static void dup_xol_work(struct callback_head *work) +{ + if (current->flags & PF_EXITING) + return; + + if (!__create_xol_area(current->utask->dup_xol_addr)) + uprobe_warn(current, "dup xol area"); +} + +/* + * Called in context of a new clone/fork from copy_process. + */ +void uprobe_copy_process(struct task_struct *t, unsigned long flags) +{ + struct uprobe_task *utask = current->utask; + struct mm_struct *mm = current->mm; + struct xol_area *area; + + t->utask = NULL; + + if (!utask || !utask->return_instances) + return; + + if (mm == t->mm && !(flags & CLONE_VFORK)) + return; + + if (dup_utask(t, utask)) + return uprobe_warn(t, "dup ret instances"); + + /* The task can fork() after dup_xol_work() fails */ + area = mm->uprobes_state.xol_area; + if (!area) + return uprobe_warn(t, "dup xol area"); + + if (mm == t->mm) + return; + + t->utask->dup_xol_addr = area->vaddr; + init_task_work(&t->utask->dup_xol_work, dup_xol_work); + task_work_add(t, &t->utask->dup_xol_work, true); +} + +/* + * Current area->vaddr notion assume the trampoline address is always + * equal area->vaddr. + * + * Returns -1 in case the xol_area is not allocated. + */ +static unsigned long get_trampoline_vaddr(void) +{ + struct xol_area *area; + unsigned long trampoline_vaddr = -1; + + area = current->mm->uprobes_state.xol_area; + smp_read_barrier_depends(); + if (area) + trampoline_vaddr = area->vaddr; + + return trampoline_vaddr; +} + +static void prepare_uretprobe(struct uprobe *uprobe, struct pt_regs *regs) +{ + struct return_instance *ri; + struct uprobe_task *utask; + unsigned long orig_ret_vaddr, trampoline_vaddr; + bool chained = false; + + if (!get_xol_area()) + return; + + utask = get_utask(); + if (!utask) + return; + + if (utask->depth >= MAX_URETPROBE_DEPTH) { + printk_ratelimited(KERN_INFO "uprobe: omit uretprobe due to" + " nestedness limit pid/tgid=%d/%d\n", + current->pid, current->tgid); + return; + } + + ri = kzalloc(sizeof(struct return_instance), GFP_KERNEL); + if (!ri) + goto fail; + + trampoline_vaddr = get_trampoline_vaddr(); + orig_ret_vaddr = arch_uretprobe_hijack_return_addr(trampoline_vaddr, regs); + if (orig_ret_vaddr == -1) + goto fail; + + /* + * We don't want to keep trampoline address in stack, rather keep the + * original return address of first caller thru all the consequent + * instances. This also makes breakpoint unwrapping easier. + */ + if (orig_ret_vaddr == trampoline_vaddr) { + if (!utask->return_instances) { + /* + * This situation is not possible. Likely we have an + * attack from user-space. + */ + pr_warn("uprobe: unable to set uretprobe pid/tgid=%d/%d\n", + current->pid, current->tgid); + goto fail; + } + + chained = true; + orig_ret_vaddr = utask->return_instances->orig_ret_vaddr; + } + + atomic_inc(&uprobe->ref); + ri->uprobe = uprobe; + ri->func = instruction_pointer(regs); + ri->orig_ret_vaddr = orig_ret_vaddr; + ri->chained = chained; + + utask->depth++; + + /* add instance to the stack */ + ri->next = utask->return_instances; + utask->return_instances = ri; + + return; + + fail: + kfree(ri); +} + +/* Prepare to single-step probed instruction out of line. */ +static int +pre_ssout(struct uprobe *uprobe, struct pt_regs *regs, unsigned long bp_vaddr) +{ + struct uprobe_task *utask; + unsigned long xol_vaddr; + int err; + + utask = get_utask(); + if (!utask) + return -ENOMEM; + + xol_vaddr = xol_get_insn_slot(uprobe); + if (!xol_vaddr) + return -ENOMEM; + + utask->xol_vaddr = xol_vaddr; + utask->vaddr = bp_vaddr; + + err = arch_uprobe_pre_xol(&uprobe->arch, regs); + if (unlikely(err)) { + xol_free_insn_slot(current); + return err; + } + + utask->active_uprobe = uprobe; + utask->state = UTASK_SSTEP; + return 0; +} + +/* + * If we are singlestepping, then ensure this thread is not connected to + * non-fatal signals until completion of singlestep. When xol insn itself + * triggers the signal, restart the original insn even if the task is + * already SIGKILL'ed (since coredump should report the correct ip). This + * is even more important if the task has a handler for SIGSEGV/etc, The + * _same_ instruction should be repeated again after return from the signal + * handler, and SSTEP can never finish in this case. + */ +bool uprobe_deny_signal(void) +{ + struct task_struct *t = current; + struct uprobe_task *utask = t->utask; + + if (likely(!utask || !utask->active_uprobe)) + return false; + + WARN_ON_ONCE(utask->state != UTASK_SSTEP); + + if (signal_pending(t)) { + spin_lock_irq(&t->sighand->siglock); + clear_tsk_thread_flag(t, TIF_SIGPENDING); + spin_unlock_irq(&t->sighand->siglock); + + if (__fatal_signal_pending(t) || arch_uprobe_xol_was_trapped(t)) { + utask->state = UTASK_SSTEP_TRAPPED; + set_tsk_thread_flag(t, TIF_UPROBE); + } + } + + return true; +} + +static void mmf_recalc_uprobes(struct mm_struct *mm) +{ + struct vm_area_struct *vma; + + for (vma = mm->mmap; vma; vma = vma->vm_next) { + if (!valid_vma(vma, false)) + continue; + /* + * This is not strictly accurate, we can race with + * uprobe_unregister() and see the already removed + * uprobe if delete_uprobe() was not yet called. + * Or this uprobe can be filtered out. + */ + if (vma_has_uprobes(vma, vma->vm_start, vma->vm_end)) + return; + } + + clear_bit(MMF_HAS_UPROBES, &mm->flags); +} + +static int is_trap_at_addr(struct mm_struct *mm, unsigned long vaddr) +{ + struct page *page; + uprobe_opcode_t opcode; + int result; + + pagefault_disable(); + result = __copy_from_user_inatomic(&opcode, (void __user*)vaddr, + sizeof(opcode)); + pagefault_enable(); + + if (likely(result == 0)) + goto out; + + result = get_user_pages(NULL, mm, vaddr, 1, 0, 1, &page, NULL); + if (result < 0) + return result; + + copy_from_page(page, vaddr, &opcode, UPROBE_SWBP_INSN_SIZE); + put_page(page); + out: + /* This needs to return true for any variant of the trap insn */ + return is_trap_insn(&opcode); +} + +static struct uprobe *find_active_uprobe(unsigned long bp_vaddr, int *is_swbp) +{ + struct mm_struct *mm = current->mm; + struct uprobe *uprobe = NULL; + struct vm_area_struct *vma; + + down_read(&mm->mmap_sem); + vma = find_vma(mm, bp_vaddr); + if (vma && vma->vm_start <= bp_vaddr) { + if (valid_vma(vma, false)) { + struct inode *inode = file_inode(vma->vm_file); + loff_t offset = vaddr_to_offset(vma, bp_vaddr); + + uprobe = find_uprobe(inode, offset); + } + + if (!uprobe) + *is_swbp = is_trap_at_addr(mm, bp_vaddr); + } else { + *is_swbp = -EFAULT; + } + + if (!uprobe && test_and_clear_bit(MMF_RECALC_UPROBES, &mm->flags)) + mmf_recalc_uprobes(mm); + up_read(&mm->mmap_sem); + + return uprobe; +} + +static void handler_chain(struct uprobe *uprobe, struct pt_regs *regs) +{ + struct uprobe_consumer *uc; + int remove = UPROBE_HANDLER_REMOVE; + bool need_prep = false; /* prepare return uprobe, when needed */ + + down_read(&uprobe->register_rwsem); + for (uc = uprobe->consumers; uc; uc = uc->next) { + int rc = 0; + + if (uc->handler) { + rc = uc->handler(uc, regs); + WARN(rc & ~UPROBE_HANDLER_MASK, + "bad rc=0x%x from %pf()\n", rc, uc->handler); + } + + if (uc->ret_handler) + need_prep = true; + + remove &= rc; + } + + if (need_prep && !remove) + prepare_uretprobe(uprobe, regs); /* put bp at return */ + + if (remove && uprobe->consumers) { + WARN_ON(!uprobe_is_active(uprobe)); + unapply_uprobe(uprobe, current->mm); + } + up_read(&uprobe->register_rwsem); +} + +static void +handle_uretprobe_chain(struct return_instance *ri, struct pt_regs *regs) +{ + struct uprobe *uprobe = ri->uprobe; + struct uprobe_consumer *uc; + + down_read(&uprobe->register_rwsem); + for (uc = uprobe->consumers; uc; uc = uc->next) { + if (uc->ret_handler) + uc->ret_handler(uc, ri->func, regs); + } + up_read(&uprobe->register_rwsem); +} + +static bool handle_trampoline(struct pt_regs *regs) +{ + struct uprobe_task *utask; + struct return_instance *ri, *tmp; + bool chained; + + utask = current->utask; + if (!utask) + return false; + + ri = utask->return_instances; + if (!ri) + return false; + + /* + * TODO: we should throw out return_instance's invalidated by + * longjmp(), currently we assume that the probed function always + * returns. + */ + instruction_pointer_set(regs, ri->orig_ret_vaddr); + + for (;;) { + handle_uretprobe_chain(ri, regs); + + chained = ri->chained; + put_uprobe(ri->uprobe); + + tmp = ri; + ri = ri->next; + kfree(tmp); + utask->depth--; + + if (!chained) + break; + BUG_ON(!ri); + } + + utask->return_instances = ri; + + return true; +} + +bool __weak arch_uprobe_ignore(struct arch_uprobe *aup, struct pt_regs *regs) +{ + return false; +} + +/* + * Run handler and ask thread to singlestep. + * Ensure all non-fatal signals cannot interrupt thread while it singlesteps. + */ +static void handle_swbp(struct pt_regs *regs) +{ + struct uprobe *uprobe; + unsigned long bp_vaddr; + int uninitialized_var(is_swbp); + + bp_vaddr = uprobe_get_swbp_addr(regs); + if (bp_vaddr == get_trampoline_vaddr()) { + if (handle_trampoline(regs)) + return; + + pr_warn("uprobe: unable to handle uretprobe pid/tgid=%d/%d\n", + current->pid, current->tgid); + } + + uprobe = find_active_uprobe(bp_vaddr, &is_swbp); + if (!uprobe) { + if (is_swbp > 0) { + /* No matching uprobe; signal SIGTRAP. */ + send_sig(SIGTRAP, current, 0); + } else { + /* + * Either we raced with uprobe_unregister() or we can't + * access this memory. The latter is only possible if + * another thread plays with our ->mm. In both cases + * we can simply restart. If this vma was unmapped we + * can pretend this insn was not executed yet and get + * the (correct) SIGSEGV after restart. + */ + instruction_pointer_set(regs, bp_vaddr); + } + return; + } + + /* change it in advance for ->handler() and restart */ + instruction_pointer_set(regs, bp_vaddr); + + /* + * TODO: move copy_insn/etc into _register and remove this hack. + * After we hit the bp, _unregister + _register can install the + * new and not-yet-analyzed uprobe at the same address, restart. + */ + smp_rmb(); /* pairs with wmb() in install_breakpoint() */ + if (unlikely(!test_bit(UPROBE_COPY_INSN, &uprobe->flags))) + goto out; + + /* Tracing handlers use ->utask to communicate with fetch methods */ + if (!get_utask()) + goto out; + + if (arch_uprobe_ignore(&uprobe->arch, regs)) + goto out; + + handler_chain(uprobe, regs); + + if (arch_uprobe_skip_sstep(&uprobe->arch, regs)) + goto out; + + if (!pre_ssout(uprobe, regs, bp_vaddr)) + return; + + /* arch_uprobe_skip_sstep() succeeded, or restart if can't singlestep */ +out: + put_uprobe(uprobe); +} + +/* + * Perform required fix-ups and disable singlestep. + * Allow pending signals to take effect. + */ +static void handle_singlestep(struct uprobe_task *utask, struct pt_regs *regs) +{ + struct uprobe *uprobe; + int err = 0; + + uprobe = utask->active_uprobe; + if (utask->state == UTASK_SSTEP_ACK) + err = arch_uprobe_post_xol(&uprobe->arch, regs); + else if (utask->state == UTASK_SSTEP_TRAPPED) + arch_uprobe_abort_xol(&uprobe->arch, regs); + else + WARN_ON_ONCE(1); + + put_uprobe(uprobe); + utask->active_uprobe = NULL; + utask->state = UTASK_RUNNING; + xol_free_insn_slot(current); + + spin_lock_irq(¤t->sighand->siglock); + recalc_sigpending(); /* see uprobe_deny_signal() */ + spin_unlock_irq(¤t->sighand->siglock); + + if (unlikely(err)) { + uprobe_warn(current, "execute the probed insn, sending SIGILL."); + force_sig_info(SIGILL, SEND_SIG_FORCED, current); + } +} + +/* + * On breakpoint hit, breakpoint notifier sets the TIF_UPROBE flag and + * allows the thread to return from interrupt. After that handle_swbp() + * sets utask->active_uprobe. + * + * On singlestep exception, singlestep notifier sets the TIF_UPROBE flag + * and allows the thread to return from interrupt. + * + * While returning to userspace, thread notices the TIF_UPROBE flag and calls + * uprobe_notify_resume(). + */ +void uprobe_notify_resume(struct pt_regs *regs) +{ + struct uprobe_task *utask; + + clear_thread_flag(TIF_UPROBE); + + utask = current->utask; + if (utask && utask->active_uprobe) + handle_singlestep(utask, regs); + else + handle_swbp(regs); +} + +/* + * uprobe_pre_sstep_notifier gets called from interrupt context as part of + * notifier mechanism. Set TIF_UPROBE flag and indicate breakpoint hit. + */ +int uprobe_pre_sstep_notifier(struct pt_regs *regs) +{ + if (!current->mm) + return 0; + + if (!test_bit(MMF_HAS_UPROBES, ¤t->mm->flags) && + (!current->utask || !current->utask->return_instances)) + return 0; + + set_thread_flag(TIF_UPROBE); + return 1; +} + +/* + * uprobe_post_sstep_notifier gets called in interrupt context as part of notifier + * mechanism. Set TIF_UPROBE flag and indicate completion of singlestep. + */ +int uprobe_post_sstep_notifier(struct pt_regs *regs) +{ + struct uprobe_task *utask = current->utask; + + if (!current->mm || !utask || !utask->active_uprobe) + /* task is currently not uprobed */ + return 0; + + utask->state = UTASK_SSTEP_ACK; + set_thread_flag(TIF_UPROBE); + return 1; +} + +static struct notifier_block uprobe_exception_nb = { + .notifier_call = arch_uprobe_exception_notify, + .priority = INT_MAX-1, /* notified after kprobes, kgdb */ +}; + +static int __init init_uprobes(void) +{ + int i; + + for (i = 0; i < UPROBES_HASH_SZ; i++) + mutex_init(&uprobes_mmap_mutex[i]); + + if (percpu_init_rwsem(&dup_mmap_sem)) + return -ENOMEM; + + return register_die_notifier(&uprobe_exception_nb); +} +__initcall(init_uprobes); diff --git a/kernel/kernel/exec_domain.c b/kernel/kernel/exec_domain.c new file mode 100644 index 000000000..6873bb3e6 --- /dev/null +++ b/kernel/kernel/exec_domain.c @@ -0,0 +1,58 @@ +/* + * Handling of different ABIs (personalities). + * + * We group personalities into execution domains which have their + * own handlers for kernel entry points, signal mapping, etc... + * + * 2001-05-06 Complete rewrite, Christoph Hellwig (hch@infradead.org) + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#ifdef CONFIG_PROC_FS +static int execdomains_proc_show(struct seq_file *m, void *v) +{ + seq_puts(m, "0-0\tLinux \t[kernel]\n"); + return 0; +} + +static int execdomains_proc_open(struct inode *inode, struct file *file) +{ + return single_open(file, execdomains_proc_show, NULL); +} + +static const struct file_operations execdomains_proc_fops = { + .open = execdomains_proc_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static int __init proc_execdomains_init(void) +{ + proc_create("execdomains", 0, NULL, &execdomains_proc_fops); + return 0; +} +module_init(proc_execdomains_init); +#endif + +SYSCALL_DEFINE1(personality, unsigned int, personality) +{ + unsigned int old = current->personality; + + if (personality != 0xffffffff) + set_personality(personality); + + return old; +} diff --git a/kernel/kernel/exit.c b/kernel/kernel/exit.c new file mode 100644 index 000000000..a0cf72b37 --- /dev/null +++ b/kernel/kernel/exit.c @@ -0,0 +1,1632 @@ +/* + * linux/kernel/exit.c + * + * Copyright (C) 1991, 1992 Linus Torvalds + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include /* for audit_free() */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include + +static void exit_mm(struct task_struct *tsk); + +static void __unhash_process(struct task_struct *p, bool group_dead) +{ + nr_threads--; + detach_pid(p, PIDTYPE_PID); + if (group_dead) { + detach_pid(p, PIDTYPE_PGID); + detach_pid(p, PIDTYPE_SID); + + list_del_rcu(&p->tasks); + list_del_init(&p->sibling); + __this_cpu_dec(process_counts); + } + list_del_rcu(&p->thread_group); + list_del_rcu(&p->thread_node); +} + +/* + * This function expects the tasklist_lock write-locked. + */ +static void __exit_signal(struct task_struct *tsk) +{ + struct signal_struct *sig = tsk->signal; + bool group_dead = thread_group_leader(tsk); + struct sighand_struct *sighand; + struct tty_struct *uninitialized_var(tty); + cputime_t utime, stime; + + sighand = rcu_dereference_check(tsk->sighand, + lockdep_tasklist_lock_is_held()); + spin_lock(&sighand->siglock); + + posix_cpu_timers_exit(tsk); + if (group_dead) { + posix_cpu_timers_exit_group(tsk); + tty = sig->tty; + sig->tty = NULL; + } else { + /* + * This can only happen if the caller is de_thread(). + * FIXME: this is the temporary hack, we should teach + * posix-cpu-timers to handle this case correctly. + */ + if (unlikely(has_group_leader_pid(tsk))) + posix_cpu_timers_exit_group(tsk); + + /* + * If there is any task waiting for the group exit + * then notify it: + */ + if (sig->notify_count > 0 && !--sig->notify_count) + wake_up_process(sig->group_exit_task); + + if (tsk == sig->curr_target) + sig->curr_target = next_thread(tsk); + } + + /* + * Accumulate here the counters for all threads as they die. We could + * skip the group leader because it is the last user of signal_struct, + * but we want to avoid the race with thread_group_cputime() which can + * see the empty ->thread_head list. + */ + task_cputime(tsk, &utime, &stime); + write_seqlock(&sig->stats_lock); + sig->utime += utime; + sig->stime += stime; + sig->gtime += task_gtime(tsk); + sig->min_flt += tsk->min_flt; + sig->maj_flt += tsk->maj_flt; + sig->nvcsw += tsk->nvcsw; + sig->nivcsw += tsk->nivcsw; + sig->inblock += task_io_get_inblock(tsk); + sig->oublock += task_io_get_oublock(tsk); + task_io_accounting_add(&sig->ioac, &tsk->ioac); + sig->sum_sched_runtime += tsk->se.sum_exec_runtime; + sig->nr_threads--; + __unhash_process(tsk, group_dead); + write_sequnlock(&sig->stats_lock); + + /* + * Do this under ->siglock, we can race with another thread + * doing sigqueue_free() if we have SIGQUEUE_PREALLOC signals. + */ + flush_task_sigqueue(tsk); + tsk->sighand = NULL; + spin_unlock(&sighand->siglock); + + __cleanup_sighand(sighand); + clear_tsk_thread_flag(tsk, TIF_SIGPENDING); + if (group_dead) { + flush_sigqueue(&sig->shared_pending); + tty_kref_put(tty); + } +} + +static void delayed_put_task_struct(struct rcu_head *rhp) +{ + struct task_struct *tsk = container_of(rhp, struct task_struct, rcu); + + perf_event_delayed_put(tsk); + trace_sched_process_free(tsk); + put_task_struct(tsk); +} + + +void release_task(struct task_struct *p) +{ + struct task_struct *leader; + int zap_leader; +repeat: + /* don't need to get the RCU readlock here - the process is dead and + * can't be modifying its own credentials. But shut RCU-lockdep up */ + rcu_read_lock(); + atomic_dec(&__task_cred(p)->user->processes); + rcu_read_unlock(); + + proc_flush_task(p); + + write_lock_irq(&tasklist_lock); + ptrace_release_task(p); + __exit_signal(p); + + /* + * If we are the last non-leader member of the thread + * group, and the leader is zombie, then notify the + * group leader's parent process. (if it wants notification.) + */ + zap_leader = 0; + leader = p->group_leader; + if (leader != p && thread_group_empty(leader) + && leader->exit_state == EXIT_ZOMBIE) { + /* + * If we were the last child thread and the leader has + * exited already, and the leader's parent ignores SIGCHLD, + * then we are the one who should release the leader. + */ + zap_leader = do_notify_parent(leader, leader->exit_signal); + if (zap_leader) + leader->exit_state = EXIT_DEAD; + } + + write_unlock_irq(&tasklist_lock); + release_thread(p); + call_rcu(&p->rcu, delayed_put_task_struct); + + p = leader; + if (unlikely(zap_leader)) + goto repeat; +} + +/* + * Determine if a process group is "orphaned", according to the POSIX + * definition in 2.2.2.52. Orphaned process groups are not to be affected + * by terminal-generated stop signals. Newly orphaned process groups are + * to receive a SIGHUP and a SIGCONT. + * + * "I ask you, have you ever known what it is to be an orphan?" + */ +static int will_become_orphaned_pgrp(struct pid *pgrp, + struct task_struct *ignored_task) +{ + struct task_struct *p; + + do_each_pid_task(pgrp, PIDTYPE_PGID, p) { + if ((p == ignored_task) || + (p->exit_state && thread_group_empty(p)) || + is_global_init(p->real_parent)) + continue; + + if (task_pgrp(p->real_parent) != pgrp && + task_session(p->real_parent) == task_session(p)) + return 0; + } while_each_pid_task(pgrp, PIDTYPE_PGID, p); + + return 1; +} + +int is_current_pgrp_orphaned(void) +{ + int retval; + + read_lock(&tasklist_lock); + retval = will_become_orphaned_pgrp(task_pgrp(current), NULL); + read_unlock(&tasklist_lock); + + return retval; +} + +static bool has_stopped_jobs(struct pid *pgrp) +{ + struct task_struct *p; + + do_each_pid_task(pgrp, PIDTYPE_PGID, p) { + if (p->signal->flags & SIGNAL_STOP_STOPPED) + return true; + } while_each_pid_task(pgrp, PIDTYPE_PGID, p); + + return false; +} + +/* + * Check to see if any process groups have become orphaned as + * a result of our exiting, and if they have any stopped jobs, + * send them a SIGHUP and then a SIGCONT. (POSIX 3.2.2.2) + */ +static void +kill_orphaned_pgrp(struct task_struct *tsk, struct task_struct *parent) +{ + struct pid *pgrp = task_pgrp(tsk); + struct task_struct *ignored_task = tsk; + + if (!parent) + /* exit: our father is in a different pgrp than + * we are and we were the only connection outside. + */ + parent = tsk->real_parent; + else + /* reparent: our child is in a different pgrp than + * we are, and it was the only connection outside. + */ + ignored_task = NULL; + + if (task_pgrp(parent) != pgrp && + task_session(parent) == task_session(tsk) && + will_become_orphaned_pgrp(pgrp, ignored_task) && + has_stopped_jobs(pgrp)) { + __kill_pgrp_info(SIGHUP, SEND_SIG_PRIV, pgrp); + __kill_pgrp_info(SIGCONT, SEND_SIG_PRIV, pgrp); + } +} + +#ifdef CONFIG_MEMCG +/* + * A task is exiting. If it owned this mm, find a new owner for the mm. + */ +void mm_update_next_owner(struct mm_struct *mm) +{ + struct task_struct *c, *g, *p = current; + +retry: + /* + * If the exiting or execing task is not the owner, it's + * someone else's problem. + */ + if (mm->owner != p) + return; + /* + * The current owner is exiting/execing and there are no other + * candidates. Do not leave the mm pointing to a possibly + * freed task structure. + */ + if (atomic_read(&mm->mm_users) <= 1) { + mm->owner = NULL; + return; + } + + read_lock(&tasklist_lock); + /* + * Search in the children + */ + list_for_each_entry(c, &p->children, sibling) { + if (c->mm == mm) + goto assign_new_owner; + } + + /* + * Search in the siblings + */ + list_for_each_entry(c, &p->real_parent->children, sibling) { + if (c->mm == mm) + goto assign_new_owner; + } + + /* + * Search through everything else, we should not get here often. + */ + for_each_process(g) { + if (g->flags & PF_KTHREAD) + continue; + for_each_thread(g, c) { + if (c->mm == mm) + goto assign_new_owner; + if (c->mm) + break; + } + } + read_unlock(&tasklist_lock); + /* + * We found no owner yet mm_users > 1: this implies that we are + * most likely racing with swapoff (try_to_unuse()) or /proc or + * ptrace or page migration (get_task_mm()). Mark owner as NULL. + */ + mm->owner = NULL; + return; + +assign_new_owner: + BUG_ON(c == p); + get_task_struct(c); + /* + * The task_lock protects c->mm from changing. + * We always want mm->owner->mm == mm + */ + task_lock(c); + /* + * Delay read_unlock() till we have the task_lock() + * to ensure that c does not slip away underneath us + */ + read_unlock(&tasklist_lock); + if (c->mm != mm) { + task_unlock(c); + put_task_struct(c); + goto retry; + } + mm->owner = c; + task_unlock(c); + put_task_struct(c); +} +#endif /* CONFIG_MEMCG */ + +/* + * Turn us into a lazy TLB process if we + * aren't already.. + */ +static void exit_mm(struct task_struct *tsk) +{ + struct mm_struct *mm = tsk->mm; + struct core_state *core_state; + + mm_release(tsk, mm); + if (!mm) + return; + sync_mm_rss(mm); + /* + * Serialize with any possible pending coredump. + * We must hold mmap_sem around checking core_state + * and clearing tsk->mm. The core-inducing thread + * will increment ->nr_threads for each thread in the + * group with ->mm != NULL. + */ + down_read(&mm->mmap_sem); + core_state = mm->core_state; + if (core_state) { + struct core_thread self; + + up_read(&mm->mmap_sem); + + self.task = tsk; + self.next = xchg(&core_state->dumper.next, &self); + /* + * Implies mb(), the result of xchg() must be visible + * to core_state->dumper. + */ + if (atomic_dec_and_test(&core_state->nr_threads)) + complete(&core_state->startup); + + for (;;) { + set_task_state(tsk, TASK_UNINTERRUPTIBLE); + if (!self.task) /* see coredump_finish() */ + break; + freezable_schedule(); + } + __set_task_state(tsk, TASK_RUNNING); + down_read(&mm->mmap_sem); + } + atomic_inc(&mm->mm_count); + BUG_ON(mm != tsk->active_mm); + /* more a memory barrier than a real lock */ + task_lock(tsk); + tsk->mm = NULL; + up_read(&mm->mmap_sem); + enter_lazy_tlb(mm, current); + task_unlock(tsk); + mm_update_next_owner(mm); + mmput(mm); + if (test_thread_flag(TIF_MEMDIE)) + unmark_oom_victim(); +} + +static struct task_struct *find_alive_thread(struct task_struct *p) +{ + struct task_struct *t; + + for_each_thread(p, t) { + if (!(t->flags & PF_EXITING)) + return t; + } + return NULL; +} + +static struct task_struct *find_child_reaper(struct task_struct *father) + __releases(&tasklist_lock) + __acquires(&tasklist_lock) +{ + struct pid_namespace *pid_ns = task_active_pid_ns(father); + struct task_struct *reaper = pid_ns->child_reaper; + + if (likely(reaper != father)) + return reaper; + + reaper = find_alive_thread(father); + if (reaper) { + pid_ns->child_reaper = reaper; + return reaper; + } + + write_unlock_irq(&tasklist_lock); + if (unlikely(pid_ns == &init_pid_ns)) { + panic("Attempted to kill init! exitcode=0x%08x\n", + father->signal->group_exit_code ?: father->exit_code); + } + zap_pid_ns_processes(pid_ns); + write_lock_irq(&tasklist_lock); + + return father; +} + +/* + * When we die, we re-parent all our children, and try to: + * 1. give them to another thread in our thread group, if such a member exists + * 2. give it to the first ancestor process which prctl'd itself as a + * child_subreaper for its children (like a service manager) + * 3. give it to the init process (PID 1) in our pid namespace + */ +static struct task_struct *find_new_reaper(struct task_struct *father, + struct task_struct *child_reaper) +{ + struct task_struct *thread, *reaper; + + thread = find_alive_thread(father); + if (thread) + return thread; + + if (father->signal->has_child_subreaper) { + /* + * Find the first ->is_child_subreaper ancestor in our pid_ns. + * We start from father to ensure we can not look into another + * namespace, this is safe because all its threads are dead. + */ + for (reaper = father; + !same_thread_group(reaper, child_reaper); + reaper = reaper->real_parent) { + /* call_usermodehelper() descendants need this check */ + if (reaper == &init_task) + break; + if (!reaper->signal->is_child_subreaper) + continue; + thread = find_alive_thread(reaper); + if (thread) + return thread; + } + } + + return child_reaper; +} + +/* +* Any that need to be release_task'd are put on the @dead list. + */ +static void reparent_leader(struct task_struct *father, struct task_struct *p, + struct list_head *dead) +{ + if (unlikely(p->exit_state == EXIT_DEAD)) + return; + + /* We don't want people slaying init. */ + p->exit_signal = SIGCHLD; + + /* If it has exited notify the new parent about this child's death. */ + if (!p->ptrace && + p->exit_state == EXIT_ZOMBIE && thread_group_empty(p)) { + if (do_notify_parent(p, p->exit_signal)) { + p->exit_state = EXIT_DEAD; + list_add(&p->ptrace_entry, dead); + } + } + + kill_orphaned_pgrp(p, father); +} + +/* + * This does two things: + * + * A. Make init inherit all the child processes + * B. Check to see if any process groups have become orphaned + * as a result of our exiting, and if they have any stopped + * jobs, send them a SIGHUP and then a SIGCONT. (POSIX 3.2.2.2) + */ +static void forget_original_parent(struct task_struct *father, + struct list_head *dead) +{ + struct task_struct *p, *t, *reaper; + + if (unlikely(!list_empty(&father->ptraced))) + exit_ptrace(father, dead); + + /* Can drop and reacquire tasklist_lock */ + reaper = find_child_reaper(father); + if (list_empty(&father->children)) + return; + + reaper = find_new_reaper(father, reaper); + list_for_each_entry(p, &father->children, sibling) { + for_each_thread(p, t) { + t->real_parent = reaper; + BUG_ON((!t->ptrace) != (t->parent == father)); + if (likely(!t->ptrace)) + t->parent = t->real_parent; + if (t->pdeath_signal) + group_send_sig_info(t->pdeath_signal, + SEND_SIG_NOINFO, t); + } + /* + * If this is a threaded reparent there is no need to + * notify anyone anything has happened. + */ + if (!same_thread_group(reaper, father)) + reparent_leader(father, p, dead); + } + list_splice_tail_init(&father->children, &reaper->children); +} + +/* + * Send signals to all our closest relatives so that they know + * to properly mourn us.. + */ +static void exit_notify(struct task_struct *tsk, int group_dead) +{ + bool autoreap; + struct task_struct *p, *n; + LIST_HEAD(dead); + + write_lock_irq(&tasklist_lock); + forget_original_parent(tsk, &dead); + + if (group_dead) + kill_orphaned_pgrp(tsk->group_leader, NULL); + + if (unlikely(tsk->ptrace)) { + int sig = thread_group_leader(tsk) && + thread_group_empty(tsk) && + !ptrace_reparented(tsk) ? + tsk->exit_signal : SIGCHLD; + autoreap = do_notify_parent(tsk, sig); + } else if (thread_group_leader(tsk)) { + autoreap = thread_group_empty(tsk) && + do_notify_parent(tsk, tsk->exit_signal); + } else { + autoreap = true; + } + + tsk->exit_state = autoreap ? EXIT_DEAD : EXIT_ZOMBIE; + if (tsk->exit_state == EXIT_DEAD) + list_add(&tsk->ptrace_entry, &dead); + + /* mt-exec, de_thread() is waiting for group leader */ + if (unlikely(tsk->signal->notify_count < 0)) + wake_up_process(tsk->signal->group_exit_task); + write_unlock_irq(&tasklist_lock); + + list_for_each_entry_safe(p, n, &dead, ptrace_entry) { + list_del_init(&p->ptrace_entry); + release_task(p); + } +} + +#ifdef CONFIG_DEBUG_STACK_USAGE +static void check_stack_usage(void) +{ + static DEFINE_SPINLOCK(low_water_lock); + static int lowest_to_date = THREAD_SIZE; + unsigned long free; + + free = stack_not_used(current); + + if (free >= lowest_to_date) + return; + + spin_lock(&low_water_lock); + if (free < lowest_to_date) { + pr_warn("%s (%d) used greatest stack depth: %lu bytes left\n", + current->comm, task_pid_nr(current), free); + lowest_to_date = free; + } + spin_unlock(&low_water_lock); +} +#else +static inline void check_stack_usage(void) {} +#endif + +void do_exit(long code) +{ + struct task_struct *tsk = current; + int group_dead; + TASKS_RCU(int tasks_rcu_i); + + profile_task_exit(tsk); + + WARN_ON(blk_needs_flush_plug(tsk)); + + if (unlikely(in_interrupt())) + panic("Aiee, killing interrupt handler!"); + if (unlikely(!tsk->pid)) + panic("Attempted to kill the idle task!"); + + /* + * If do_exit is called because this processes oopsed, it's possible + * that get_fs() was left as KERNEL_DS, so reset it to USER_DS before + * continuing. Amongst other possible reasons, this is to prevent + * mm_release()->clear_child_tid() from writing to a user-controlled + * kernel address. + */ + set_fs(USER_DS); + + ptrace_event(PTRACE_EVENT_EXIT, code); + + validate_creds_for_do_exit(tsk); + + /* + * We're taking recursive faults here in do_exit. Safest is to just + * leave this task alone and wait for reboot. + */ + if (unlikely(tsk->flags & PF_EXITING)) { + pr_alert("Fixing recursive fault but reboot is needed!\n"); + /* + * We can do this unlocked here. The futex code uses + * this flag just to verify whether the pi state + * cleanup has been done or not. In the worst case it + * loops once more. We pretend that the cleanup was + * done as there is no way to return. Either the + * OWNER_DIED bit is set by now or we push the blocked + * task into the wait for ever nirwana as well. + */ + tsk->flags |= PF_EXITPIDONE; + set_current_state(TASK_UNINTERRUPTIBLE); + schedule(); + } + + exit_signals(tsk); /* sets PF_EXITING */ + /* + * tsk->flags are checked in the futex code to protect against + * an exiting task cleaning up the robust pi futexes. + */ + smp_mb(); + raw_spin_unlock_wait(&tsk->pi_lock); + + if (unlikely(in_atomic())) + pr_info("note: %s[%d] exited with preempt_count %d\n", + current->comm, task_pid_nr(current), + preempt_count()); + + acct_update_integrals(tsk); + /* sync mm's RSS info before statistics gathering */ + if (tsk->mm) + sync_mm_rss(tsk->mm); + group_dead = atomic_dec_and_test(&tsk->signal->live); + if (group_dead) { + hrtimer_cancel(&tsk->signal->real_timer); + exit_itimers(tsk->signal); + if (tsk->mm) + setmax_mm_hiwater_rss(&tsk->signal->maxrss, tsk->mm); + } + acct_collect(code, group_dead); + if (group_dead) + tty_audit_exit(); + audit_free(tsk); + + tsk->exit_code = code; + taskstats_exit(tsk, group_dead); + + exit_mm(tsk); + + if (group_dead) + acct_process(); + trace_sched_process_exit(tsk); + + exit_sem(tsk); + exit_shm(tsk); + exit_files(tsk); + exit_fs(tsk); + if (group_dead) + disassociate_ctty(1); + exit_task_namespaces(tsk); + exit_task_work(tsk); + exit_thread(); + + /* + * Flush inherited counters to the parent - before the parent + * gets woken up by child-exit notifications. + * + * because of cgroup mode, must be called before cgroup_exit() + */ + perf_event_exit_task(tsk); + + cgroup_exit(tsk); + + /* + * FIXME: do that only when needed, using sched_exit tracepoint + */ + flush_ptrace_hw_breakpoint(tsk); + + TASKS_RCU(tasks_rcu_i = __srcu_read_lock(&tasks_rcu_exit_srcu)); + exit_notify(tsk, group_dead); + proc_exit_connector(tsk); +#ifdef CONFIG_NUMA + task_lock(tsk); + mpol_put(tsk->mempolicy); + tsk->mempolicy = NULL; + task_unlock(tsk); +#endif +#ifdef CONFIG_FUTEX + if (unlikely(current->pi_state_cache)) + kfree(current->pi_state_cache); +#endif + /* + * Make sure we are holding no locks: + */ + debug_check_no_locks_held(); + /* + * We can do this unlocked here. The futex code uses this flag + * just to verify whether the pi state cleanup has been done + * or not. In the worst case it loops once more. + */ + tsk->flags |= PF_EXITPIDONE; + + if (tsk->io_context) + exit_io_context(tsk); + + if (tsk->splice_pipe) + free_pipe_info(tsk->splice_pipe); + + if (tsk->task_frag.page) + put_page(tsk->task_frag.page); + + validate_creds_for_do_exit(tsk); + + check_stack_usage(); + preempt_disable(); + if (tsk->nr_dirtied) + __this_cpu_add(dirty_throttle_leaks, tsk->nr_dirtied); + exit_rcu(); + TASKS_RCU(__srcu_read_unlock(&tasks_rcu_exit_srcu, tasks_rcu_i)); + + /* + * The setting of TASK_RUNNING by try_to_wake_up() may be delayed + * when the following two conditions become true. + * - There is race condition of mmap_sem (It is acquired by + * exit_mm()), and + * - SMI occurs before setting TASK_RUNINNG. + * (or hypervisor of virtual machine switches to other guest) + * As a result, we may become TASK_RUNNING after becoming TASK_DEAD + * + * To avoid it, we have to wait for releasing tsk->pi_lock which + * is held by try_to_wake_up() + */ + smp_mb(); + raw_spin_unlock_wait(&tsk->pi_lock); + + /* causes final put_task_struct in finish_task_switch(). */ + tsk->state = TASK_DEAD; + tsk->flags |= PF_NOFREEZE; /* tell freezer to ignore us */ + schedule(); + BUG(); + /* Avoid "noreturn function does return". */ + for (;;) + cpu_relax(); /* For when BUG is null */ +} +EXPORT_SYMBOL_GPL(do_exit); + +void complete_and_exit(struct completion *comp, long code) +{ + if (comp) + complete(comp); + + do_exit(code); +} +EXPORT_SYMBOL(complete_and_exit); + +SYSCALL_DEFINE1(exit, int, error_code) +{ + do_exit((error_code&0xff)<<8); +} + +/* + * Take down every thread in the group. This is called by fatal signals + * as well as by sys_exit_group (below). + */ +void +do_group_exit(int exit_code) +{ + struct signal_struct *sig = current->signal; + + BUG_ON(exit_code & 0x80); /* core dumps don't get here */ + + if (signal_group_exit(sig)) + exit_code = sig->group_exit_code; + else if (!thread_group_empty(current)) { + struct sighand_struct *const sighand = current->sighand; + + spin_lock_irq(&sighand->siglock); + if (signal_group_exit(sig)) + /* Another thread got here before we took the lock. */ + exit_code = sig->group_exit_code; + else { + sig->group_exit_code = exit_code; + sig->flags = SIGNAL_GROUP_EXIT; + zap_other_threads(current); + } + spin_unlock_irq(&sighand->siglock); + } + + do_exit(exit_code); + /* NOTREACHED */ +} + +/* + * this kills every thread in the thread group. Note that any externally + * wait4()-ing process will get the correct exit code - even if this + * thread is not the thread group leader. + */ +SYSCALL_DEFINE1(exit_group, int, error_code) +{ + do_group_exit((error_code & 0xff) << 8); + /* NOTREACHED */ + return 0; +} + +struct wait_opts { + enum pid_type wo_type; + int wo_flags; + struct pid *wo_pid; + + struct siginfo __user *wo_info; + int __user *wo_stat; + struct rusage __user *wo_rusage; + + wait_queue_t child_wait; + int notask_error; +}; + +static inline +struct pid *task_pid_type(struct task_struct *task, enum pid_type type) +{ + if (type != PIDTYPE_PID) + task = task->group_leader; + return task->pids[type].pid; +} + +static int eligible_pid(struct wait_opts *wo, struct task_struct *p) +{ + return wo->wo_type == PIDTYPE_MAX || + task_pid_type(p, wo->wo_type) == wo->wo_pid; +} + +static int eligible_child(struct wait_opts *wo, struct task_struct *p) +{ + if (!eligible_pid(wo, p)) + return 0; + /* Wait for all children (clone and not) if __WALL is set; + * otherwise, wait for clone children *only* if __WCLONE is + * set; otherwise, wait for non-clone children *only*. (Note: + * A "clone" child here is one that reports to its parent + * using a signal other than SIGCHLD.) */ + if (((p->exit_signal != SIGCHLD) ^ !!(wo->wo_flags & __WCLONE)) + && !(wo->wo_flags & __WALL)) + return 0; + + return 1; +} + +static int wait_noreap_copyout(struct wait_opts *wo, struct task_struct *p, + pid_t pid, uid_t uid, int why, int status) +{ + struct siginfo __user *infop; + int retval = wo->wo_rusage + ? getrusage(p, RUSAGE_BOTH, wo->wo_rusage) : 0; + + put_task_struct(p); + infop = wo->wo_info; + if (infop) { + if (!retval) + retval = put_user(SIGCHLD, &infop->si_signo); + if (!retval) + retval = put_user(0, &infop->si_errno); + if (!retval) + retval = put_user((short)why, &infop->si_code); + if (!retval) + retval = put_user(pid, &infop->si_pid); + if (!retval) + retval = put_user(uid, &infop->si_uid); + if (!retval) + retval = put_user(status, &infop->si_status); + } + if (!retval) + retval = pid; + return retval; +} + +/* + * Handle sys_wait4 work for one task in state EXIT_ZOMBIE. We hold + * read_lock(&tasklist_lock) on entry. If we return zero, we still hold + * the lock and this task is uninteresting. If we return nonzero, we have + * released the lock and the system call should return. + */ +static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p) +{ + int state, retval, status; + pid_t pid = task_pid_vnr(p); + uid_t uid = from_kuid_munged(current_user_ns(), task_uid(p)); + struct siginfo __user *infop; + + if (!likely(wo->wo_flags & WEXITED)) + return 0; + + if (unlikely(wo->wo_flags & WNOWAIT)) { + int exit_code = p->exit_code; + int why; + + get_task_struct(p); + read_unlock(&tasklist_lock); + sched_annotate_sleep(); + + if ((exit_code & 0x7f) == 0) { + why = CLD_EXITED; + status = exit_code >> 8; + } else { + why = (exit_code & 0x80) ? CLD_DUMPED : CLD_KILLED; + status = exit_code & 0x7f; + } + return wait_noreap_copyout(wo, p, pid, uid, why, status); + } + /* + * Move the task's state to DEAD/TRACE, only one thread can do this. + */ + state = (ptrace_reparented(p) && thread_group_leader(p)) ? + EXIT_TRACE : EXIT_DEAD; + if (cmpxchg(&p->exit_state, EXIT_ZOMBIE, state) != EXIT_ZOMBIE) + return 0; + /* + * We own this thread, nobody else can reap it. + */ + read_unlock(&tasklist_lock); + sched_annotate_sleep(); + + /* + * Check thread_group_leader() to exclude the traced sub-threads. + */ + if (state == EXIT_DEAD && thread_group_leader(p)) { + struct signal_struct *sig = p->signal; + struct signal_struct *psig = current->signal; + unsigned long maxrss; + cputime_t tgutime, tgstime; + + /* + * The resource counters for the group leader are in its + * own task_struct. Those for dead threads in the group + * are in its signal_struct, as are those for the child + * processes it has previously reaped. All these + * accumulate in the parent's signal_struct c* fields. + * + * We don't bother to take a lock here to protect these + * p->signal fields because the whole thread group is dead + * and nobody can change them. + * + * psig->stats_lock also protects us from our sub-theads + * which can reap other children at the same time. Until + * we change k_getrusage()-like users to rely on this lock + * we have to take ->siglock as well. + * + * We use thread_group_cputime_adjusted() to get times for + * the thread group, which consolidates times for all threads + * in the group including the group leader. + */ + thread_group_cputime_adjusted(p, &tgutime, &tgstime); + spin_lock_irq(¤t->sighand->siglock); + write_seqlock(&psig->stats_lock); + psig->cutime += tgutime + sig->cutime; + psig->cstime += tgstime + sig->cstime; + psig->cgtime += task_gtime(p) + sig->gtime + sig->cgtime; + psig->cmin_flt += + p->min_flt + sig->min_flt + sig->cmin_flt; + psig->cmaj_flt += + p->maj_flt + sig->maj_flt + sig->cmaj_flt; + psig->cnvcsw += + p->nvcsw + sig->nvcsw + sig->cnvcsw; + psig->cnivcsw += + p->nivcsw + sig->nivcsw + sig->cnivcsw; + psig->cinblock += + task_io_get_inblock(p) + + sig->inblock + sig->cinblock; + psig->coublock += + task_io_get_oublock(p) + + sig->oublock + sig->coublock; + maxrss = max(sig->maxrss, sig->cmaxrss); + if (psig->cmaxrss < maxrss) + psig->cmaxrss = maxrss; + task_io_accounting_add(&psig->ioac, &p->ioac); + task_io_accounting_add(&psig->ioac, &sig->ioac); + write_sequnlock(&psig->stats_lock); + spin_unlock_irq(¤t->sighand->siglock); + } + + retval = wo->wo_rusage + ? getrusage(p, RUSAGE_BOTH, wo->wo_rusage) : 0; + status = (p->signal->flags & SIGNAL_GROUP_EXIT) + ? p->signal->group_exit_code : p->exit_code; + if (!retval && wo->wo_stat) + retval = put_user(status, wo->wo_stat); + + infop = wo->wo_info; + if (!retval && infop) + retval = put_user(SIGCHLD, &infop->si_signo); + if (!retval && infop) + retval = put_user(0, &infop->si_errno); + if (!retval && infop) { + int why; + + if ((status & 0x7f) == 0) { + why = CLD_EXITED; + status >>= 8; + } else { + why = (status & 0x80) ? CLD_DUMPED : CLD_KILLED; + status &= 0x7f; + } + retval = put_user((short)why, &infop->si_code); + if (!retval) + retval = put_user(status, &infop->si_status); + } + if (!retval && infop) + retval = put_user(pid, &infop->si_pid); + if (!retval && infop) + retval = put_user(uid, &infop->si_uid); + if (!retval) + retval = pid; + + if (state == EXIT_TRACE) { + write_lock_irq(&tasklist_lock); + /* We dropped tasklist, ptracer could die and untrace */ + ptrace_unlink(p); + + /* If parent wants a zombie, don't release it now */ + state = EXIT_ZOMBIE; + if (do_notify_parent(p, p->exit_signal)) + state = EXIT_DEAD; + p->exit_state = state; + write_unlock_irq(&tasklist_lock); + } + if (state == EXIT_DEAD) + release_task(p); + + return retval; +} + +static int *task_stopped_code(struct task_struct *p, bool ptrace) +{ + if (ptrace) { + if (task_is_stopped_or_traced(p) && + !(p->jobctl & JOBCTL_LISTENING)) + return &p->exit_code; + } else { + if (p->signal->flags & SIGNAL_STOP_STOPPED) + return &p->signal->group_exit_code; + } + return NULL; +} + +/** + * wait_task_stopped - Wait for %TASK_STOPPED or %TASK_TRACED + * @wo: wait options + * @ptrace: is the wait for ptrace + * @p: task to wait for + * + * Handle sys_wait4() work for %p in state %TASK_STOPPED or %TASK_TRACED. + * + * CONTEXT: + * read_lock(&tasklist_lock), which is released if return value is + * non-zero. Also, grabs and releases @p->sighand->siglock. + * + * RETURNS: + * 0 if wait condition didn't exist and search for other wait conditions + * should continue. Non-zero return, -errno on failure and @p's pid on + * success, implies that tasklist_lock is released and wait condition + * search should terminate. + */ +static int wait_task_stopped(struct wait_opts *wo, + int ptrace, struct task_struct *p) +{ + struct siginfo __user *infop; + int retval, exit_code, *p_code, why; + uid_t uid = 0; /* unneeded, required by compiler */ + pid_t pid; + + /* + * Traditionally we see ptrace'd stopped tasks regardless of options. + */ + if (!ptrace && !(wo->wo_flags & WUNTRACED)) + return 0; + + if (!task_stopped_code(p, ptrace)) + return 0; + + exit_code = 0; + spin_lock_irq(&p->sighand->siglock); + + p_code = task_stopped_code(p, ptrace); + if (unlikely(!p_code)) + goto unlock_sig; + + exit_code = *p_code; + if (!exit_code) + goto unlock_sig; + + if (!unlikely(wo->wo_flags & WNOWAIT)) + *p_code = 0; + + uid = from_kuid_munged(current_user_ns(), task_uid(p)); +unlock_sig: + spin_unlock_irq(&p->sighand->siglock); + if (!exit_code) + return 0; + + /* + * Now we are pretty sure this task is interesting. + * Make sure it doesn't get reaped out from under us while we + * give up the lock and then examine it below. We don't want to + * keep holding onto the tasklist_lock while we call getrusage and + * possibly take page faults for user memory. + */ + get_task_struct(p); + pid = task_pid_vnr(p); + why = ptrace ? CLD_TRAPPED : CLD_STOPPED; + read_unlock(&tasklist_lock); + sched_annotate_sleep(); + + if (unlikely(wo->wo_flags & WNOWAIT)) + return wait_noreap_copyout(wo, p, pid, uid, why, exit_code); + + retval = wo->wo_rusage + ? getrusage(p, RUSAGE_BOTH, wo->wo_rusage) : 0; + if (!retval && wo->wo_stat) + retval = put_user((exit_code << 8) | 0x7f, wo->wo_stat); + + infop = wo->wo_info; + if (!retval && infop) + retval = put_user(SIGCHLD, &infop->si_signo); + if (!retval && infop) + retval = put_user(0, &infop->si_errno); + if (!retval && infop) + retval = put_user((short)why, &infop->si_code); + if (!retval && infop) + retval = put_user(exit_code, &infop->si_status); + if (!retval && infop) + retval = put_user(pid, &infop->si_pid); + if (!retval && infop) + retval = put_user(uid, &infop->si_uid); + if (!retval) + retval = pid; + put_task_struct(p); + + BUG_ON(!retval); + return retval; +} + +/* + * Handle do_wait work for one task in a live, non-stopped state. + * read_lock(&tasklist_lock) on entry. If we return zero, we still hold + * the lock and this task is uninteresting. If we return nonzero, we have + * released the lock and the system call should return. + */ +static int wait_task_continued(struct wait_opts *wo, struct task_struct *p) +{ + int retval; + pid_t pid; + uid_t uid; + + if (!unlikely(wo->wo_flags & WCONTINUED)) + return 0; + + if (!(p->signal->flags & SIGNAL_STOP_CONTINUED)) + return 0; + + spin_lock_irq(&p->sighand->siglock); + /* Re-check with the lock held. */ + if (!(p->signal->flags & SIGNAL_STOP_CONTINUED)) { + spin_unlock_irq(&p->sighand->siglock); + return 0; + } + if (!unlikely(wo->wo_flags & WNOWAIT)) + p->signal->flags &= ~SIGNAL_STOP_CONTINUED; + uid = from_kuid_munged(current_user_ns(), task_uid(p)); + spin_unlock_irq(&p->sighand->siglock); + + pid = task_pid_vnr(p); + get_task_struct(p); + read_unlock(&tasklist_lock); + sched_annotate_sleep(); + + if (!wo->wo_info) { + retval = wo->wo_rusage + ? getrusage(p, RUSAGE_BOTH, wo->wo_rusage) : 0; + put_task_struct(p); + if (!retval && wo->wo_stat) + retval = put_user(0xffff, wo->wo_stat); + if (!retval) + retval = pid; + } else { + retval = wait_noreap_copyout(wo, p, pid, uid, + CLD_CONTINUED, SIGCONT); + BUG_ON(retval == 0); + } + + return retval; +} + +/* + * Consider @p for a wait by @parent. + * + * -ECHILD should be in ->notask_error before the first call. + * Returns nonzero for a final return, when we have unlocked tasklist_lock. + * Returns zero if the search for a child should continue; + * then ->notask_error is 0 if @p is an eligible child, + * or another error from security_task_wait(), or still -ECHILD. + */ +static int wait_consider_task(struct wait_opts *wo, int ptrace, + struct task_struct *p) +{ + /* + * We can race with wait_task_zombie() from another thread. + * Ensure that EXIT_ZOMBIE -> EXIT_DEAD/EXIT_TRACE transition + * can't confuse the checks below. + */ + int exit_state = ACCESS_ONCE(p->exit_state); + int ret; + + if (unlikely(exit_state == EXIT_DEAD)) + return 0; + + ret = eligible_child(wo, p); + if (!ret) + return ret; + + ret = security_task_wait(p); + if (unlikely(ret < 0)) { + /* + * If we have not yet seen any eligible child, + * then let this error code replace -ECHILD. + * A permission error will give the user a clue + * to look for security policy problems, rather + * than for mysterious wait bugs. + */ + if (wo->notask_error) + wo->notask_error = ret; + return 0; + } + + if (unlikely(exit_state == EXIT_TRACE)) { + /* + * ptrace == 0 means we are the natural parent. In this case + * we should clear notask_error, debugger will notify us. + */ + if (likely(!ptrace)) + wo->notask_error = 0; + return 0; + } + + if (likely(!ptrace) && unlikely(p->ptrace)) { + /* + * If it is traced by its real parent's group, just pretend + * the caller is ptrace_do_wait() and reap this child if it + * is zombie. + * + * This also hides group stop state from real parent; otherwise + * a single stop can be reported twice as group and ptrace stop. + * If a ptracer wants to distinguish these two events for its + * own children it should create a separate process which takes + * the role of real parent. + */ + if (!ptrace_reparented(p)) + ptrace = 1; + } + + /* slay zombie? */ + if (exit_state == EXIT_ZOMBIE) { + /* we don't reap group leaders with subthreads */ + if (!delay_group_leader(p)) { + /* + * A zombie ptracee is only visible to its ptracer. + * Notification and reaping will be cascaded to the + * real parent when the ptracer detaches. + */ + if (unlikely(ptrace) || likely(!p->ptrace)) + return wait_task_zombie(wo, p); + } + + /* + * Allow access to stopped/continued state via zombie by + * falling through. Clearing of notask_error is complex. + * + * When !@ptrace: + * + * If WEXITED is set, notask_error should naturally be + * cleared. If not, subset of WSTOPPED|WCONTINUED is set, + * so, if there are live subthreads, there are events to + * wait for. If all subthreads are dead, it's still safe + * to clear - this function will be called again in finite + * amount time once all the subthreads are released and + * will then return without clearing. + * + * When @ptrace: + * + * Stopped state is per-task and thus can't change once the + * target task dies. Only continued and exited can happen. + * Clear notask_error if WCONTINUED | WEXITED. + */ + if (likely(!ptrace) || (wo->wo_flags & (WCONTINUED | WEXITED))) + wo->notask_error = 0; + } else { + /* + * @p is alive and it's gonna stop, continue or exit, so + * there always is something to wait for. + */ + wo->notask_error = 0; + } + + /* + * Wait for stopped. Depending on @ptrace, different stopped state + * is used and the two don't interact with each other. + */ + ret = wait_task_stopped(wo, ptrace, p); + if (ret) + return ret; + + /* + * Wait for continued. There's only one continued state and the + * ptracer can consume it which can confuse the real parent. Don't + * use WCONTINUED from ptracer. You don't need or want it. + */ + return wait_task_continued(wo, p); +} + +/* + * Do the work of do_wait() for one thread in the group, @tsk. + * + * -ECHILD should be in ->notask_error before the first call. + * Returns nonzero for a final return, when we have unlocked tasklist_lock. + * Returns zero if the search for a child should continue; then + * ->notask_error is 0 if there were any eligible children, + * or another error from security_task_wait(), or still -ECHILD. + */ +static int do_wait_thread(struct wait_opts *wo, struct task_struct *tsk) +{ + struct task_struct *p; + + list_for_each_entry(p, &tsk->children, sibling) { + int ret = wait_consider_task(wo, 0, p); + + if (ret) + return ret; + } + + return 0; +} + +static int ptrace_do_wait(struct wait_opts *wo, struct task_struct *tsk) +{ + struct task_struct *p; + + list_for_each_entry(p, &tsk->ptraced, ptrace_entry) { + int ret = wait_consider_task(wo, 1, p); + + if (ret) + return ret; + } + + return 0; +} + +static int child_wait_callback(wait_queue_t *wait, unsigned mode, + int sync, void *key) +{ + struct wait_opts *wo = container_of(wait, struct wait_opts, + child_wait); + struct task_struct *p = key; + + if (!eligible_pid(wo, p)) + return 0; + + if ((wo->wo_flags & __WNOTHREAD) && wait->private != p->parent) + return 0; + + return default_wake_function(wait, mode, sync, key); +} + +void __wake_up_parent(struct task_struct *p, struct task_struct *parent) +{ + __wake_up_sync_key(&parent->signal->wait_chldexit, + TASK_INTERRUPTIBLE, 1, p); +} + +static long do_wait(struct wait_opts *wo) +{ + struct task_struct *tsk; + int retval; + + trace_sched_process_wait(wo->wo_pid); + + init_waitqueue_func_entry(&wo->child_wait, child_wait_callback); + wo->child_wait.private = current; + add_wait_queue(¤t->signal->wait_chldexit, &wo->child_wait); +repeat: + /* + * If there is nothing that can match our critiera just get out. + * We will clear ->notask_error to zero if we see any child that + * might later match our criteria, even if we are not able to reap + * it yet. + */ + wo->notask_error = -ECHILD; + if ((wo->wo_type < PIDTYPE_MAX) && + (!wo->wo_pid || hlist_empty(&wo->wo_pid->tasks[wo->wo_type]))) + goto notask; + + set_current_state(TASK_INTERRUPTIBLE); + read_lock(&tasklist_lock); + tsk = current; + do { + retval = do_wait_thread(wo, tsk); + if (retval) + goto end; + + retval = ptrace_do_wait(wo, tsk); + if (retval) + goto end; + + if (wo->wo_flags & __WNOTHREAD) + break; + } while_each_thread(current, tsk); + read_unlock(&tasklist_lock); + +notask: + retval = wo->notask_error; + if (!retval && !(wo->wo_flags & WNOHANG)) { + retval = -ERESTARTSYS; + if (!signal_pending(current)) { + schedule(); + goto repeat; + } + } +end: + __set_current_state(TASK_RUNNING); + remove_wait_queue(¤t->signal->wait_chldexit, &wo->child_wait); + return retval; +} + +SYSCALL_DEFINE5(waitid, int, which, pid_t, upid, struct siginfo __user *, + infop, int, options, struct rusage __user *, ru) +{ + struct wait_opts wo; + struct pid *pid = NULL; + enum pid_type type; + long ret; + + if (options & ~(WNOHANG|WNOWAIT|WEXITED|WSTOPPED|WCONTINUED)) + return -EINVAL; + if (!(options & (WEXITED|WSTOPPED|WCONTINUED))) + return -EINVAL; + + switch (which) { + case P_ALL: + type = PIDTYPE_MAX; + break; + case P_PID: + type = PIDTYPE_PID; + if (upid <= 0) + return -EINVAL; + break; + case P_PGID: + type = PIDTYPE_PGID; + if (upid <= 0) + return -EINVAL; + break; + default: + return -EINVAL; + } + + if (type < PIDTYPE_MAX) + pid = find_get_pid(upid); + + wo.wo_type = type; + wo.wo_pid = pid; + wo.wo_flags = options; + wo.wo_info = infop; + wo.wo_stat = NULL; + wo.wo_rusage = ru; + ret = do_wait(&wo); + + if (ret > 0) { + ret = 0; + } else if (infop) { + /* + * For a WNOHANG return, clear out all the fields + * we would set so the user can easily tell the + * difference. + */ + if (!ret) + ret = put_user(0, &infop->si_signo); + if (!ret) + ret = put_user(0, &infop->si_errno); + if (!ret) + ret = put_user(0, &infop->si_code); + if (!ret) + ret = put_user(0, &infop->si_pid); + if (!ret) + ret = put_user(0, &infop->si_uid); + if (!ret) + ret = put_user(0, &infop->si_status); + } + + put_pid(pid); + return ret; +} + +SYSCALL_DEFINE4(wait4, pid_t, upid, int __user *, stat_addr, + int, options, struct rusage __user *, ru) +{ + struct wait_opts wo; + struct pid *pid = NULL; + enum pid_type type; + long ret; + + if (options & ~(WNOHANG|WUNTRACED|WCONTINUED| + __WNOTHREAD|__WCLONE|__WALL)) + return -EINVAL; + + if (upid == -1) + type = PIDTYPE_MAX; + else if (upid < 0) { + type = PIDTYPE_PGID; + pid = find_get_pid(-upid); + } else if (upid == 0) { + type = PIDTYPE_PGID; + pid = get_task_pid(current, PIDTYPE_PGID); + } else /* upid > 0 */ { + type = PIDTYPE_PID; + pid = find_get_pid(upid); + } + + wo.wo_type = type; + wo.wo_pid = pid; + wo.wo_flags = options | WEXITED; + wo.wo_info = NULL; + wo.wo_stat = stat_addr; + wo.wo_rusage = ru; + ret = do_wait(&wo); + put_pid(pid); + + return ret; +} + +#ifdef __ARCH_WANT_SYS_WAITPID + +/* + * sys_waitpid() remains for compatibility. waitpid() should be + * implemented by calling sys_wait4() from libc.a. + */ +SYSCALL_DEFINE3(waitpid, pid_t, pid, int __user *, stat_addr, int, options) +{ + return sys_wait4(pid, stat_addr, options, NULL); +} + +#endif diff --git a/kernel/kernel/extable.c b/kernel/kernel/extable.c new file mode 100644 index 000000000..c98f92627 --- /dev/null +++ b/kernel/kernel/extable.c @@ -0,0 +1,144 @@ +/* Rewritten by Rusty Russell, on the backs of many others... + Copyright (C) 2001 Rusty Russell, 2002 Rusty Russell IBM. + + This program is free software; you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation; either version 2 of the License, or + (at your option) any later version. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU General Public License for more details. + + You should have received a copy of the GNU General Public License + along with this program; if not, write to the Free Software + Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA +*/ +#include +#include +#include +#include +#include +#include + +#include +#include + +/* + * mutex protecting text section modification (dynamic code patching). + * some users need to sleep (allocating memory...) while they hold this lock. + * + * NOT exported to modules - patching kernel text is a really delicate matter. + */ +DEFINE_MUTEX(text_mutex); + +extern struct exception_table_entry __start___ex_table[]; +extern struct exception_table_entry __stop___ex_table[]; + +/* Cleared by build time tools if the table is already sorted. */ +u32 __initdata __visible main_extable_sort_needed = 1; + +/* Sort the kernel's built-in exception table */ +void __init sort_main_extable(void) +{ + if (main_extable_sort_needed && __stop___ex_table > __start___ex_table) { + pr_notice("Sorting __ex_table...\n"); + sort_extable(__start___ex_table, __stop___ex_table); + } +} + +/* Given an address, look for it in the exception tables. */ +const struct exception_table_entry *search_exception_tables(unsigned long addr) +{ + const struct exception_table_entry *e; + + e = search_extable(__start___ex_table, __stop___ex_table-1, addr); + if (!e) + e = search_module_extables(addr); + return e; +} + +static inline int init_kernel_text(unsigned long addr) +{ + if (addr >= (unsigned long)_sinittext && + addr < (unsigned long)_einittext) + return 1; + return 0; +} + +int core_kernel_text(unsigned long addr) +{ + if (addr >= (unsigned long)_stext && + addr < (unsigned long)_etext) + return 1; + + if (system_state == SYSTEM_BOOTING && + init_kernel_text(addr)) + return 1; + return 0; +} + +/** + * core_kernel_data - tell if addr points to kernel data + * @addr: address to test + * + * Returns true if @addr passed in is from the core kernel data + * section. + * + * Note: On some archs it may return true for core RODATA, and false + * for others. But will always be true for core RW data. + */ +int core_kernel_data(unsigned long addr) +{ + if (addr >= (unsigned long)_sdata && + addr < (unsigned long)_edata) + return 1; + return 0; +} + +int __kernel_text_address(unsigned long addr) +{ + if (core_kernel_text(addr)) + return 1; + if (is_module_text_address(addr)) + return 1; + if (is_ftrace_trampoline(addr)) + return 1; + /* + * There might be init symbols in saved stacktraces. + * Give those symbols a chance to be printed in + * backtraces (such as lockdep traces). + * + * Since we are after the module-symbols check, there's + * no danger of address overlap: + */ + if (init_kernel_text(addr)) + return 1; + return 0; +} + +int kernel_text_address(unsigned long addr) +{ + if (core_kernel_text(addr)) + return 1; + if (is_module_text_address(addr)) + return 1; + return is_ftrace_trampoline(addr); +} + +/* + * On some architectures (PPC64, IA64) function pointers + * are actually only tokens to some data that then holds the + * real function address. As a result, to find if a function + * pointer is part of the kernel text, we need to do some + * special dereferencing first. + */ +int func_ptr_is_kernel_text(void *ptr) +{ + unsigned long addr; + addr = (unsigned long) dereference_function_descriptor(ptr); + if (core_kernel_text(addr)) + return 1; + return is_module_text_address(addr); +} diff --git a/kernel/kernel/fork.c b/kernel/kernel/fork.c new file mode 100644 index 000000000..dd407cea0 --- /dev/null +++ b/kernel/kernel/fork.c @@ -0,0 +1,2109 @@ +/* + * linux/kernel/fork.c + * + * Copyright (C) 1991, 1992 Linus Torvalds + */ + +/* + * 'fork.c' contains the help-routines for the 'fork' system call + * (see also entry.S and others). + * Fork is rather simple, once you get the hang of it, but the memory + * management can be a bitch. See 'mm/memory.c': 'copy_page_range()' + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include +#include + +#include + +#define CREATE_TRACE_POINTS +#include + +/* + * Minimum number of threads to boot the kernel + */ +#define MIN_THREADS 20 + +/* + * Maximum number of threads + */ +#define MAX_THREADS FUTEX_TID_MASK + +/* + * Protected counters by write_lock_irq(&tasklist_lock) + */ +unsigned long total_forks; /* Handle normal Linux uptimes. */ +int nr_threads; /* The idle threads do not count.. */ + +int max_threads; /* tunable limit on nr_threads */ + +DEFINE_PER_CPU(unsigned long, process_counts) = 0; + +DEFINE_RWLOCK(tasklist_lock); /* outer */ + +#ifdef CONFIG_PROVE_RCU +int lockdep_tasklist_lock_is_held(void) +{ + return lockdep_is_held(&tasklist_lock); +} +EXPORT_SYMBOL_GPL(lockdep_tasklist_lock_is_held); +#endif /* #ifdef CONFIG_PROVE_RCU */ + +int nr_processes(void) +{ + int cpu; + int total = 0; + + for_each_possible_cpu(cpu) + total += per_cpu(process_counts, cpu); + + return total; +} + +void __weak arch_release_task_struct(struct task_struct *tsk) +{ +} + +#ifndef CONFIG_ARCH_TASK_STRUCT_ALLOCATOR +static struct kmem_cache *task_struct_cachep; + +static inline struct task_struct *alloc_task_struct_node(int node) +{ + return kmem_cache_alloc_node(task_struct_cachep, GFP_KERNEL, node); +} + +static inline void free_task_struct(struct task_struct *tsk) +{ + kmem_cache_free(task_struct_cachep, tsk); +} +#endif + +void __weak arch_release_thread_info(struct thread_info *ti) +{ +} + +#ifndef CONFIG_ARCH_THREAD_INFO_ALLOCATOR + +/* + * Allocate pages if THREAD_SIZE is >= PAGE_SIZE, otherwise use a + * kmemcache based allocator. + */ +# if THREAD_SIZE >= PAGE_SIZE +static struct thread_info *alloc_thread_info_node(struct task_struct *tsk, + int node) +{ + struct page *page = alloc_kmem_pages_node(node, THREADINFO_GFP, + THREAD_SIZE_ORDER); + + return page ? page_address(page) : NULL; +} + +static inline void free_thread_info(struct thread_info *ti) +{ + free_kmem_pages((unsigned long)ti, THREAD_SIZE_ORDER); +} +# else +static struct kmem_cache *thread_info_cache; + +static struct thread_info *alloc_thread_info_node(struct task_struct *tsk, + int node) +{ + return kmem_cache_alloc_node(thread_info_cache, THREADINFO_GFP, node); +} + +static void free_thread_info(struct thread_info *ti) +{ + kmem_cache_free(thread_info_cache, ti); +} + +void thread_info_cache_init(void) +{ + thread_info_cache = kmem_cache_create("thread_info", THREAD_SIZE, + THREAD_SIZE, 0, NULL); + BUG_ON(thread_info_cache == NULL); +} +# endif +#endif + +/* SLAB cache for signal_struct structures (tsk->signal) */ +static struct kmem_cache *signal_cachep; + +/* SLAB cache for sighand_struct structures (tsk->sighand) */ +struct kmem_cache *sighand_cachep; + +/* SLAB cache for files_struct structures (tsk->files) */ +struct kmem_cache *files_cachep; + +/* SLAB cache for fs_struct structures (tsk->fs) */ +struct kmem_cache *fs_cachep; + +/* SLAB cache for vm_area_struct structures */ +struct kmem_cache *vm_area_cachep; + +/* SLAB cache for mm_struct structures (tsk->mm) */ +static struct kmem_cache *mm_cachep; + +static void account_kernel_stack(struct thread_info *ti, int account) +{ + struct zone *zone = page_zone(virt_to_page(ti)); + + mod_zone_page_state(zone, NR_KERNEL_STACK, account); +} + +void free_task(struct task_struct *tsk) +{ + account_kernel_stack(tsk->stack, -1); + arch_release_thread_info(tsk->stack); + free_thread_info(tsk->stack); + rt_mutex_debug_task_free(tsk); + ftrace_graph_exit_task(tsk); + put_seccomp_filter(tsk); + arch_release_task_struct(tsk); + free_task_struct(tsk); +} +EXPORT_SYMBOL(free_task); + +static inline void free_signal_struct(struct signal_struct *sig) +{ + taskstats_tgid_free(sig); + sched_autogroup_exit(sig); + kmem_cache_free(signal_cachep, sig); +} + +static inline void put_signal_struct(struct signal_struct *sig) +{ + if (atomic_dec_and_test(&sig->sigcnt)) + free_signal_struct(sig); +} +#ifdef CONFIG_PREEMPT_RT_BASE +static +#endif +void __put_task_struct(struct task_struct *tsk) +{ + WARN_ON(!tsk->exit_state); + WARN_ON(atomic_read(&tsk->usage)); + WARN_ON(tsk == current); + + task_numa_free(tsk); + security_task_free(tsk); + exit_creds(tsk); + delayacct_tsk_free(tsk); + put_signal_struct(tsk->signal); + + if (!profile_handoff_task(tsk)) + free_task(tsk); +} +#ifndef CONFIG_PREEMPT_RT_BASE +EXPORT_SYMBOL_GPL(__put_task_struct); +#else +void __put_task_struct_cb(struct rcu_head *rhp) +{ + struct task_struct *tsk = container_of(rhp, struct task_struct, put_rcu); + + __put_task_struct(tsk); + +} +EXPORT_SYMBOL_GPL(__put_task_struct_cb); +#endif + +void __init __weak arch_task_cache_init(void) { } + +/* + * set_max_threads + */ +static void set_max_threads(unsigned int max_threads_suggested) +{ + u64 threads; + + /* + * The number of threads shall be limited such that the thread + * structures may only consume a small part of the available memory. + */ + if (fls64(totalram_pages) + fls64(PAGE_SIZE) > 64) + threads = MAX_THREADS; + else + threads = div64_u64((u64) totalram_pages * (u64) PAGE_SIZE, + (u64) THREAD_SIZE * 8UL); + + if (threads > max_threads_suggested) + threads = max_threads_suggested; + + max_threads = clamp_t(u64, threads, MIN_THREADS, MAX_THREADS); +} + +void __init fork_init(void) +{ +#ifndef CONFIG_ARCH_TASK_STRUCT_ALLOCATOR +#ifndef ARCH_MIN_TASKALIGN +#define ARCH_MIN_TASKALIGN L1_CACHE_BYTES +#endif + /* create a slab on which task_structs can be allocated */ + task_struct_cachep = + kmem_cache_create("task_struct", sizeof(struct task_struct), + ARCH_MIN_TASKALIGN, SLAB_PANIC | SLAB_NOTRACK, NULL); +#endif + + /* do the arch specific task caches init */ + arch_task_cache_init(); + + set_max_threads(MAX_THREADS); + + init_task.signal->rlim[RLIMIT_NPROC].rlim_cur = max_threads/2; + init_task.signal->rlim[RLIMIT_NPROC].rlim_max = max_threads/2; + init_task.signal->rlim[RLIMIT_SIGPENDING] = + init_task.signal->rlim[RLIMIT_NPROC]; +} + +int __weak arch_dup_task_struct(struct task_struct *dst, + struct task_struct *src) +{ + *dst = *src; + return 0; +} + +void set_task_stack_end_magic(struct task_struct *tsk) +{ + unsigned long *stackend; + + stackend = end_of_stack(tsk); + *stackend = STACK_END_MAGIC; /* for overflow detection */ +} + +static struct task_struct *dup_task_struct(struct task_struct *orig) +{ + struct task_struct *tsk; + struct thread_info *ti; + int node = tsk_fork_get_node(orig); + int err; + + tsk = alloc_task_struct_node(node); + if (!tsk) + return NULL; + + ti = alloc_thread_info_node(tsk, node); + if (!ti) + goto free_tsk; + + err = arch_dup_task_struct(tsk, orig); + if (err) + goto free_ti; + + tsk->stack = ti; +#ifdef CONFIG_SECCOMP + /* + * We must handle setting up seccomp filters once we're under + * the sighand lock in case orig has changed between now and + * then. Until then, filter must be NULL to avoid messing up + * the usage counts on the error path calling free_task. + */ + tsk->seccomp.filter = NULL; +#endif + + setup_thread_stack(tsk, orig); + clear_user_return_notifier(tsk); + clear_tsk_need_resched(tsk); + set_task_stack_end_magic(tsk); + +#ifdef CONFIG_CC_STACKPROTECTOR + tsk->stack_canary = get_random_int(); +#endif + + /* + * One for us, one for whoever does the "release_task()" (usually + * parent) + */ + atomic_set(&tsk->usage, 2); +#ifdef CONFIG_BLK_DEV_IO_TRACE + tsk->btrace_seq = 0; +#endif + tsk->splice_pipe = NULL; + tsk->task_frag.page = NULL; + + account_kernel_stack(ti, 1); + + return tsk; + +free_ti: + free_thread_info(ti); +free_tsk: + free_task_struct(tsk); + return NULL; +} + +#ifdef CONFIG_MMU +static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm) +{ + struct vm_area_struct *mpnt, *tmp, *prev, **pprev; + struct rb_node **rb_link, *rb_parent; + int retval; + unsigned long charge; + + uprobe_start_dup_mmap(); + down_write(&oldmm->mmap_sem); + flush_cache_dup_mm(oldmm); + uprobe_dup_mmap(oldmm, mm); + /* + * Not linked in yet - no deadlock potential: + */ + down_write_nested(&mm->mmap_sem, SINGLE_DEPTH_NESTING); + + /* No ordering required: file already has been exposed. */ + RCU_INIT_POINTER(mm->exe_file, get_mm_exe_file(oldmm)); + + mm->total_vm = oldmm->total_vm; + mm->shared_vm = oldmm->shared_vm; + mm->exec_vm = oldmm->exec_vm; + mm->stack_vm = oldmm->stack_vm; + + rb_link = &mm->mm_rb.rb_node; + rb_parent = NULL; + pprev = &mm->mmap; + retval = ksm_fork(mm, oldmm); + if (retval) + goto out; + retval = khugepaged_fork(mm, oldmm); + if (retval) + goto out; + + prev = NULL; + for (mpnt = oldmm->mmap; mpnt; mpnt = mpnt->vm_next) { + struct file *file; + + if (mpnt->vm_flags & VM_DONTCOPY) { + vm_stat_account(mm, mpnt->vm_flags, mpnt->vm_file, + -vma_pages(mpnt)); + continue; + } + charge = 0; + if (mpnt->vm_flags & VM_ACCOUNT) { + unsigned long len = vma_pages(mpnt); + + if (security_vm_enough_memory_mm(oldmm, len)) /* sic */ + goto fail_nomem; + charge = len; + } + tmp = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL); + if (!tmp) + goto fail_nomem; + *tmp = *mpnt; + INIT_LIST_HEAD(&tmp->anon_vma_chain); + retval = vma_dup_policy(mpnt, tmp); + if (retval) + goto fail_nomem_policy; + tmp->vm_mm = mm; + if (anon_vma_fork(tmp, mpnt)) + goto fail_nomem_anon_vma_fork; + tmp->vm_flags &= ~VM_LOCKED; + tmp->vm_next = tmp->vm_prev = NULL; + file = tmp->vm_file; + if (file) { + struct inode *inode = file_inode(file); + struct address_space *mapping = file->f_mapping; + + get_file(file); + if (tmp->vm_flags & VM_DENYWRITE) + atomic_dec(&inode->i_writecount); + i_mmap_lock_write(mapping); + if (tmp->vm_flags & VM_SHARED) + atomic_inc(&mapping->i_mmap_writable); + flush_dcache_mmap_lock(mapping); + /* insert tmp into the share list, just after mpnt */ + vma_interval_tree_insert_after(tmp, mpnt, + &mapping->i_mmap); + flush_dcache_mmap_unlock(mapping); + i_mmap_unlock_write(mapping); + } + + /* + * Clear hugetlb-related page reserves for children. This only + * affects MAP_PRIVATE mappings. Faults generated by the child + * are not guaranteed to succeed, even if read-only + */ + if (is_vm_hugetlb_page(tmp)) + reset_vma_resv_huge_pages(tmp); + + /* + * Link in the new vma and copy the page table entries. + */ + *pprev = tmp; + pprev = &tmp->vm_next; + tmp->vm_prev = prev; + prev = tmp; + + __vma_link_rb(mm, tmp, rb_link, rb_parent); + rb_link = &tmp->vm_rb.rb_right; + rb_parent = &tmp->vm_rb; + + mm->map_count++; + retval = copy_page_range(mm, oldmm, mpnt); + + if (tmp->vm_ops && tmp->vm_ops->open) + tmp->vm_ops->open(tmp); + + if (retval) + goto out; + } + /* a new mm has just been created */ + arch_dup_mmap(oldmm, mm); + retval = 0; +out: + up_write(&mm->mmap_sem); + flush_tlb_mm(oldmm); + up_write(&oldmm->mmap_sem); + uprobe_end_dup_mmap(); + return retval; +fail_nomem_anon_vma_fork: + mpol_put(vma_policy(tmp)); +fail_nomem_policy: + kmem_cache_free(vm_area_cachep, tmp); +fail_nomem: + retval = -ENOMEM; + vm_unacct_memory(charge); + goto out; +} + +static inline int mm_alloc_pgd(struct mm_struct *mm) +{ + mm->pgd = pgd_alloc(mm); + if (unlikely(!mm->pgd)) + return -ENOMEM; + return 0; +} + +static inline void mm_free_pgd(struct mm_struct *mm) +{ + pgd_free(mm, mm->pgd); +} +#else +static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm) +{ + down_write(&oldmm->mmap_sem); + RCU_INIT_POINTER(mm->exe_file, get_mm_exe_file(oldmm)); + up_write(&oldmm->mmap_sem); + return 0; +} +#define mm_alloc_pgd(mm) (0) +#define mm_free_pgd(mm) +#endif /* CONFIG_MMU */ + +__cacheline_aligned_in_smp DEFINE_SPINLOCK(mmlist_lock); + +#define allocate_mm() (kmem_cache_alloc(mm_cachep, GFP_KERNEL)) +#define free_mm(mm) (kmem_cache_free(mm_cachep, (mm))) + +static unsigned long default_dump_filter = MMF_DUMP_FILTER_DEFAULT; + +static int __init coredump_filter_setup(char *s) +{ + default_dump_filter = + (simple_strtoul(s, NULL, 0) << MMF_DUMP_FILTER_SHIFT) & + MMF_DUMP_FILTER_MASK; + return 1; +} + +__setup("coredump_filter=", coredump_filter_setup); + +#include + +static void mm_init_aio(struct mm_struct *mm) +{ +#ifdef CONFIG_AIO + spin_lock_init(&mm->ioctx_lock); + mm->ioctx_table = NULL; +#endif +} + +static void mm_init_owner(struct mm_struct *mm, struct task_struct *p) +{ +#ifdef CONFIG_MEMCG + mm->owner = p; +#endif +} + +static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p) +{ + mm->mmap = NULL; + mm->mm_rb = RB_ROOT; + mm->vmacache_seqnum = 0; + atomic_set(&mm->mm_users, 1); + atomic_set(&mm->mm_count, 1); + init_rwsem(&mm->mmap_sem); + INIT_LIST_HEAD(&mm->mmlist); + mm->core_state = NULL; + atomic_long_set(&mm->nr_ptes, 0); + mm_nr_pmds_init(mm); + mm->map_count = 0; + mm->locked_vm = 0; + mm->pinned_vm = 0; + memset(&mm->rss_stat, 0, sizeof(mm->rss_stat)); + spin_lock_init(&mm->page_table_lock); + mm_init_cpumask(mm); + mm_init_aio(mm); + mm_init_owner(mm, p); + mmu_notifier_mm_init(mm); + clear_tlb_flush_pending(mm); +#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS + mm->pmd_huge_pte = NULL; +#endif + + if (current->mm) { + mm->flags = current->mm->flags & MMF_INIT_MASK; + mm->def_flags = current->mm->def_flags & VM_INIT_DEF_MASK; + } else { + mm->flags = default_dump_filter; + mm->def_flags = 0; + } + + if (mm_alloc_pgd(mm)) + goto fail_nopgd; + + if (init_new_context(p, mm)) + goto fail_nocontext; + + return mm; + +fail_nocontext: + mm_free_pgd(mm); +fail_nopgd: + free_mm(mm); + return NULL; +} + +static void check_mm(struct mm_struct *mm) +{ + int i; + + for (i = 0; i < NR_MM_COUNTERS; i++) { + long x = atomic_long_read(&mm->rss_stat.count[i]); + + if (unlikely(x)) + printk(KERN_ALERT "BUG: Bad rss-counter state " + "mm:%p idx:%d val:%ld\n", mm, i, x); + } + + if (atomic_long_read(&mm->nr_ptes)) + pr_alert("BUG: non-zero nr_ptes on freeing mm: %ld\n", + atomic_long_read(&mm->nr_ptes)); + if (mm_nr_pmds(mm)) + pr_alert("BUG: non-zero nr_pmds on freeing mm: %ld\n", + mm_nr_pmds(mm)); + +#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS + VM_BUG_ON_MM(mm->pmd_huge_pte, mm); +#endif +} + +/* + * Allocate and initialize an mm_struct. + */ +struct mm_struct *mm_alloc(void) +{ + struct mm_struct *mm; + + mm = allocate_mm(); + if (!mm) + return NULL; + + memset(mm, 0, sizeof(*mm)); + return mm_init(mm, current); +} + +/* + * Called when the last reference to the mm + * is dropped: either by a lazy thread or by + * mmput. Free the page directory and the mm. + */ +void __mmdrop(struct mm_struct *mm) +{ + BUG_ON(mm == &init_mm); + mm_free_pgd(mm); + destroy_context(mm); + mmu_notifier_mm_destroy(mm); + check_mm(mm); + free_mm(mm); +} +EXPORT_SYMBOL_GPL(__mmdrop); + +#ifdef CONFIG_PREEMPT_RT_BASE +/* + * RCU callback for delayed mm drop. Not strictly rcu, but we don't + * want another facility to make this work. + */ +void __mmdrop_delayed(struct rcu_head *rhp) +{ + struct mm_struct *mm = container_of(rhp, struct mm_struct, delayed_drop); + + __mmdrop(mm); +} +#endif + +/* + * Decrement the use count and release all resources for an mm. + */ +void mmput(struct mm_struct *mm) +{ + might_sleep(); + + if (atomic_dec_and_test(&mm->mm_users)) { + uprobe_clear_state(mm); + exit_aio(mm); + ksm_exit(mm); + khugepaged_exit(mm); /* must run before exit_mmap */ + exit_mmap(mm); + set_mm_exe_file(mm, NULL); + if (!list_empty(&mm->mmlist)) { + spin_lock(&mmlist_lock); + list_del(&mm->mmlist); + spin_unlock(&mmlist_lock); + } + if (mm->binfmt) + module_put(mm->binfmt->module); + mmdrop(mm); + } +} +EXPORT_SYMBOL_GPL(mmput); + +/** + * set_mm_exe_file - change a reference to the mm's executable file + * + * This changes mm's executable file (shown as symlink /proc/[pid]/exe). + * + * Main users are mmput() and sys_execve(). Callers prevent concurrent + * invocations: in mmput() nobody alive left, in execve task is single + * threaded. sys_prctl(PR_SET_MM_MAP/EXE_FILE) also needs to set the + * mm->exe_file, but does so without using set_mm_exe_file() in order + * to do avoid the need for any locks. + */ +void set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file) +{ + struct file *old_exe_file; + + /* + * It is safe to dereference the exe_file without RCU as + * this function is only called if nobody else can access + * this mm -- see comment above for justification. + */ + old_exe_file = rcu_dereference_raw(mm->exe_file); + + if (new_exe_file) + get_file(new_exe_file); + rcu_assign_pointer(mm->exe_file, new_exe_file); + if (old_exe_file) + fput(old_exe_file); +} + +/** + * get_mm_exe_file - acquire a reference to the mm's executable file + * + * Returns %NULL if mm has no associated executable file. + * User must release file via fput(). + */ +struct file *get_mm_exe_file(struct mm_struct *mm) +{ + struct file *exe_file; + + rcu_read_lock(); + exe_file = rcu_dereference(mm->exe_file); + if (exe_file && !get_file_rcu(exe_file)) + exe_file = NULL; + rcu_read_unlock(); + return exe_file; +} +EXPORT_SYMBOL(get_mm_exe_file); + +/** + * get_task_mm - acquire a reference to the task's mm + * + * Returns %NULL if the task has no mm. Checks PF_KTHREAD (meaning + * this kernel workthread has transiently adopted a user mm with use_mm, + * to do its AIO) is not set and if so returns a reference to it, after + * bumping up the use count. User must release the mm via mmput() + * after use. Typically used by /proc and ptrace. + */ +struct mm_struct *get_task_mm(struct task_struct *task) +{ + struct mm_struct *mm; + + task_lock(task); + mm = task->mm; + if (mm) { + if (task->flags & PF_KTHREAD) + mm = NULL; + else + atomic_inc(&mm->mm_users); + } + task_unlock(task); + return mm; +} +EXPORT_SYMBOL_GPL(get_task_mm); + +struct mm_struct *mm_access(struct task_struct *task, unsigned int mode) +{ + struct mm_struct *mm; + int err; + + err = mutex_lock_killable(&task->signal->cred_guard_mutex); + if (err) + return ERR_PTR(err); + + mm = get_task_mm(task); + if (mm && mm != current->mm && + !ptrace_may_access(task, mode)) { + mmput(mm); + mm = ERR_PTR(-EACCES); + } + mutex_unlock(&task->signal->cred_guard_mutex); + + return mm; +} + +static void complete_vfork_done(struct task_struct *tsk) +{ + struct completion *vfork; + + task_lock(tsk); + vfork = tsk->vfork_done; + if (likely(vfork)) { + tsk->vfork_done = NULL; + complete(vfork); + } + task_unlock(tsk); +} + +static int wait_for_vfork_done(struct task_struct *child, + struct completion *vfork) +{ + int killed; + + freezer_do_not_count(); + killed = wait_for_completion_killable(vfork); + freezer_count(); + + if (killed) { + task_lock(child); + child->vfork_done = NULL; + task_unlock(child); + } + + put_task_struct(child); + return killed; +} + +/* Please note the differences between mmput and mm_release. + * mmput is called whenever we stop holding onto a mm_struct, + * error success whatever. + * + * mm_release is called after a mm_struct has been removed + * from the current process. + * + * This difference is important for error handling, when we + * only half set up a mm_struct for a new process and need to restore + * the old one. Because we mmput the new mm_struct before + * restoring the old one. . . + * Eric Biederman 10 January 1998 + */ +void mm_release(struct task_struct *tsk, struct mm_struct *mm) +{ + /* Get rid of any futexes when releasing the mm */ +#ifdef CONFIG_FUTEX + if (unlikely(tsk->robust_list)) { + exit_robust_list(tsk); + tsk->robust_list = NULL; + } +#ifdef CONFIG_COMPAT + if (unlikely(tsk->compat_robust_list)) { + compat_exit_robust_list(tsk); + tsk->compat_robust_list = NULL; + } +#endif + if (unlikely(!list_empty(&tsk->pi_state_list))) + exit_pi_state_list(tsk); +#endif + + uprobe_free_utask(tsk); + + /* Get rid of any cached register state */ + deactivate_mm(tsk, mm); + + /* + * If we're exiting normally, clear a user-space tid field if + * requested. We leave this alone when dying by signal, to leave + * the value intact in a core dump, and to save the unnecessary + * trouble, say, a killed vfork parent shouldn't touch this mm. + * Userland only wants this done for a sys_exit. + */ + if (tsk->clear_child_tid) { + if (!(tsk->flags & PF_SIGNALED) && + atomic_read(&mm->mm_users) > 1) { + /* + * We don't check the error code - if userspace has + * not set up a proper pointer then tough luck. + */ + put_user(0, tsk->clear_child_tid); + sys_futex(tsk->clear_child_tid, FUTEX_WAKE, + 1, NULL, NULL, 0); + } + tsk->clear_child_tid = NULL; + } + + /* + * All done, finally we can wake up parent and return this mm to him. + * Also kthread_stop() uses this completion for synchronization. + */ + if (tsk->vfork_done) + complete_vfork_done(tsk); +} + +/* + * Allocate a new mm structure and copy contents from the + * mm structure of the passed in task structure. + */ +static struct mm_struct *dup_mm(struct task_struct *tsk) +{ + struct mm_struct *mm, *oldmm = current->mm; + int err; + + mm = allocate_mm(); + if (!mm) + goto fail_nomem; + + memcpy(mm, oldmm, sizeof(*mm)); + + if (!mm_init(mm, tsk)) + goto fail_nomem; + + err = dup_mmap(mm, oldmm); + if (err) + goto free_pt; + + mm->hiwater_rss = get_mm_rss(mm); + mm->hiwater_vm = mm->total_vm; + + if (mm->binfmt && !try_module_get(mm->binfmt->module)) + goto free_pt; + + return mm; + +free_pt: + /* don't put binfmt in mmput, we haven't got module yet */ + mm->binfmt = NULL; + mmput(mm); + +fail_nomem: + return NULL; +} + +static int copy_mm(unsigned long clone_flags, struct task_struct *tsk) +{ + struct mm_struct *mm, *oldmm; + int retval; + + tsk->min_flt = tsk->maj_flt = 0; + tsk->nvcsw = tsk->nivcsw = 0; +#ifdef CONFIG_DETECT_HUNG_TASK + tsk->last_switch_count = tsk->nvcsw + tsk->nivcsw; +#endif + + tsk->mm = NULL; + tsk->active_mm = NULL; + + /* + * Are we cloning a kernel thread? + * + * We need to steal a active VM for that.. + */ + oldmm = current->mm; + if (!oldmm) + return 0; + + /* initialize the new vmacache entries */ + vmacache_flush(tsk); + + if (clone_flags & CLONE_VM) { + atomic_inc(&oldmm->mm_users); + mm = oldmm; + goto good_mm; + } + + retval = -ENOMEM; + mm = dup_mm(tsk); + if (!mm) + goto fail_nomem; + +good_mm: + tsk->mm = mm; + tsk->active_mm = mm; + return 0; + +fail_nomem: + return retval; +} + +static int copy_fs(unsigned long clone_flags, struct task_struct *tsk) +{ + struct fs_struct *fs = current->fs; + if (clone_flags & CLONE_FS) { + /* tsk->fs is already what we want */ + spin_lock(&fs->lock); + if (fs->in_exec) { + spin_unlock(&fs->lock); + return -EAGAIN; + } + fs->users++; + spin_unlock(&fs->lock); + return 0; + } + tsk->fs = copy_fs_struct(fs); + if (!tsk->fs) + return -ENOMEM; + return 0; +} + +static int copy_files(unsigned long clone_flags, struct task_struct *tsk) +{ + struct files_struct *oldf, *newf; + int error = 0; + + /* + * A background process may not have any files ... + */ + oldf = current->files; + if (!oldf) + goto out; + + if (clone_flags & CLONE_FILES) { + atomic_inc(&oldf->count); + goto out; + } + + newf = dup_fd(oldf, &error); + if (!newf) + goto out; + + tsk->files = newf; + error = 0; +out: + return error; +} + +static int copy_io(unsigned long clone_flags, struct task_struct *tsk) +{ +#ifdef CONFIG_BLOCK + struct io_context *ioc = current->io_context; + struct io_context *new_ioc; + + if (!ioc) + return 0; + /* + * Share io context with parent, if CLONE_IO is set + */ + if (clone_flags & CLONE_IO) { + ioc_task_link(ioc); + tsk->io_context = ioc; + } else if (ioprio_valid(ioc->ioprio)) { + new_ioc = get_task_io_context(tsk, GFP_KERNEL, NUMA_NO_NODE); + if (unlikely(!new_ioc)) + return -ENOMEM; + + new_ioc->ioprio = ioc->ioprio; + put_io_context(new_ioc); + } +#endif + return 0; +} + +static int copy_sighand(unsigned long clone_flags, struct task_struct *tsk) +{ + struct sighand_struct *sig; + + if (clone_flags & CLONE_SIGHAND) { + atomic_inc(¤t->sighand->count); + return 0; + } + sig = kmem_cache_alloc(sighand_cachep, GFP_KERNEL); + rcu_assign_pointer(tsk->sighand, sig); + if (!sig) + return -ENOMEM; + atomic_set(&sig->count, 1); + memcpy(sig->action, current->sighand->action, sizeof(sig->action)); + return 0; +} + +void __cleanup_sighand(struct sighand_struct *sighand) +{ + if (atomic_dec_and_test(&sighand->count)) { + signalfd_cleanup(sighand); + /* + * sighand_cachep is SLAB_DESTROY_BY_RCU so we can free it + * without an RCU grace period, see __lock_task_sighand(). + */ + kmem_cache_free(sighand_cachep, sighand); + } +} + +/* + * Initialize POSIX timer handling for a thread group. + */ +static void posix_cpu_timers_init_group(struct signal_struct *sig) +{ + unsigned long cpu_limit; + + /* Thread group counters. */ + thread_group_cputime_init(sig); + + cpu_limit = ACCESS_ONCE(sig->rlim[RLIMIT_CPU].rlim_cur); + if (cpu_limit != RLIM_INFINITY) { + sig->cputime_expires.prof_exp = secs_to_cputime(cpu_limit); + sig->cputimer.running = 1; + } + + /* The timer lists. */ + INIT_LIST_HEAD(&sig->cpu_timers[0]); + INIT_LIST_HEAD(&sig->cpu_timers[1]); + INIT_LIST_HEAD(&sig->cpu_timers[2]); +} + +static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) +{ + struct signal_struct *sig; + + if (clone_flags & CLONE_THREAD) + return 0; + + sig = kmem_cache_zalloc(signal_cachep, GFP_KERNEL); + tsk->signal = sig; + if (!sig) + return -ENOMEM; + + sig->nr_threads = 1; + atomic_set(&sig->live, 1); + atomic_set(&sig->sigcnt, 1); + + /* list_add(thread_node, thread_head) without INIT_LIST_HEAD() */ + sig->thread_head = (struct list_head)LIST_HEAD_INIT(tsk->thread_node); + tsk->thread_node = (struct list_head)LIST_HEAD_INIT(sig->thread_head); + + init_waitqueue_head(&sig->wait_chldexit); + sig->curr_target = tsk; + init_sigpending(&sig->shared_pending); + INIT_LIST_HEAD(&sig->posix_timers); + seqlock_init(&sig->stats_lock); + + hrtimer_init(&sig->real_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + sig->real_timer.function = it_real_fn; + + task_lock(current->group_leader); + memcpy(sig->rlim, current->signal->rlim, sizeof sig->rlim); + task_unlock(current->group_leader); + + posix_cpu_timers_init_group(sig); + + tty_audit_fork(sig); + sched_autogroup_fork(sig); + +#ifdef CONFIG_CGROUPS + init_rwsem(&sig->group_rwsem); +#endif + + sig->oom_score_adj = current->signal->oom_score_adj; + sig->oom_score_adj_min = current->signal->oom_score_adj_min; + + sig->has_child_subreaper = current->signal->has_child_subreaper || + current->signal->is_child_subreaper; + + mutex_init(&sig->cred_guard_mutex); + + return 0; +} + +static void copy_seccomp(struct task_struct *p) +{ +#ifdef CONFIG_SECCOMP + /* + * Must be called with sighand->lock held, which is common to + * all threads in the group. Holding cred_guard_mutex is not + * needed because this new task is not yet running and cannot + * be racing exec. + */ + assert_spin_locked(¤t->sighand->siglock); + + /* Ref-count the new filter user, and assign it. */ + get_seccomp_filter(current); + p->seccomp = current->seccomp; + + /* + * Explicitly enable no_new_privs here in case it got set + * between the task_struct being duplicated and holding the + * sighand lock. The seccomp state and nnp must be in sync. + */ + if (task_no_new_privs(current)) + task_set_no_new_privs(p); + + /* + * If the parent gained a seccomp mode after copying thread + * flags and between before we held the sighand lock, we have + * to manually enable the seccomp thread flag here. + */ + if (p->seccomp.mode != SECCOMP_MODE_DISABLED) + set_tsk_thread_flag(p, TIF_SECCOMP); +#endif +} + +SYSCALL_DEFINE1(set_tid_address, int __user *, tidptr) +{ + current->clear_child_tid = tidptr; + + return task_pid_vnr(current); +} + +static void rt_mutex_init_task(struct task_struct *p) +{ + raw_spin_lock_init(&p->pi_lock); +#ifdef CONFIG_RT_MUTEXES + p->pi_waiters = RB_ROOT; + p->pi_waiters_leftmost = NULL; + p->pi_blocked_on = NULL; +#endif +} + +/* + * Initialize POSIX timer handling for a single task. + */ +static void posix_cpu_timers_init(struct task_struct *tsk) +{ +#ifdef CONFIG_PREEMPT_RT_BASE + tsk->posix_timer_list = NULL; +#endif + tsk->cputime_expires.prof_exp = 0; + tsk->cputime_expires.virt_exp = 0; + tsk->cputime_expires.sched_exp = 0; + INIT_LIST_HEAD(&tsk->cpu_timers[0]); + INIT_LIST_HEAD(&tsk->cpu_timers[1]); + INIT_LIST_HEAD(&tsk->cpu_timers[2]); +} + +static inline void +init_task_pid(struct task_struct *task, enum pid_type type, struct pid *pid) +{ + task->pids[type].pid = pid; +} + +/* + * This creates a new process as a copy of the old one, + * but does not actually start it yet. + * + * It copies the registers, and all the appropriate + * parts of the process environment (as per the clone + * flags). The actual kick-off is left to the caller. + */ +static struct task_struct *copy_process(unsigned long clone_flags, + unsigned long stack_start, + unsigned long stack_size, + int __user *child_tidptr, + struct pid *pid, + int trace) +{ + int retval; + struct task_struct *p; + + if ((clone_flags & (CLONE_NEWNS|CLONE_FS)) == (CLONE_NEWNS|CLONE_FS)) + return ERR_PTR(-EINVAL); + + if ((clone_flags & (CLONE_NEWUSER|CLONE_FS)) == (CLONE_NEWUSER|CLONE_FS)) + return ERR_PTR(-EINVAL); + + /* + * Thread groups must share signals as well, and detached threads + * can only be started up within the thread group. + */ + if ((clone_flags & CLONE_THREAD) && !(clone_flags & CLONE_SIGHAND)) + return ERR_PTR(-EINVAL); + + /* + * Shared signal handlers imply shared VM. By way of the above, + * thread groups also imply shared VM. Blocking this case allows + * for various simplifications in other code. + */ + if ((clone_flags & CLONE_SIGHAND) && !(clone_flags & CLONE_VM)) + return ERR_PTR(-EINVAL); + + /* + * Siblings of global init remain as zombies on exit since they are + * not reaped by their parent (swapper). To solve this and to avoid + * multi-rooted process trees, prevent global and container-inits + * from creating siblings. + */ + if ((clone_flags & CLONE_PARENT) && + current->signal->flags & SIGNAL_UNKILLABLE) + return ERR_PTR(-EINVAL); + + /* + * If the new process will be in a different pid or user namespace + * do not allow it to share a thread group or signal handlers or + * parent with the forking task. + */ + if (clone_flags & CLONE_SIGHAND) { + if ((clone_flags & (CLONE_NEWUSER | CLONE_NEWPID)) || + (task_active_pid_ns(current) != + current->nsproxy->pid_ns_for_children)) + return ERR_PTR(-EINVAL); + } + + retval = security_task_create(clone_flags); + if (retval) + goto fork_out; + + retval = -ENOMEM; + p = dup_task_struct(current); + if (!p) + goto fork_out; + + ftrace_graph_init_task(p); + + rt_mutex_init_task(p); + +#ifdef CONFIG_PROVE_LOCKING + DEBUG_LOCKS_WARN_ON(!p->hardirqs_enabled); + DEBUG_LOCKS_WARN_ON(!p->softirqs_enabled); +#endif + retval = -EAGAIN; + if (atomic_read(&p->real_cred->user->processes) >= + task_rlimit(p, RLIMIT_NPROC)) { + if (p->real_cred->user != INIT_USER && + !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN)) + goto bad_fork_free; + } + current->flags &= ~PF_NPROC_EXCEEDED; + + retval = copy_creds(p, clone_flags); + if (retval < 0) + goto bad_fork_free; + + /* + * If multiple threads are within copy_process(), then this check + * triggers too late. This doesn't hurt, the check is only there + * to stop root fork bombs. + */ + retval = -EAGAIN; + if (nr_threads >= max_threads) + goto bad_fork_cleanup_count; + + delayacct_tsk_init(p); /* Must remain after dup_task_struct() */ + p->flags &= ~(PF_SUPERPRIV | PF_WQ_WORKER); + p->flags |= PF_FORKNOEXEC; + INIT_LIST_HEAD(&p->children); + INIT_LIST_HEAD(&p->sibling); + rcu_copy_process(p); + p->vfork_done = NULL; + spin_lock_init(&p->alloc_lock); + + init_sigpending(&p->pending); + p->sigqueue_cache = NULL; + + p->utime = p->stime = p->gtime = 0; + p->utimescaled = p->stimescaled = 0; +#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE + p->prev_cputime.utime = p->prev_cputime.stime = 0; +#endif +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN + raw_spin_lock_init(&p->vtime_lock); + seqcount_init(&p->vtime_seq); + p->vtime_snap = 0; + p->vtime_snap_whence = VTIME_SLEEPING; +#endif + +#if defined(SPLIT_RSS_COUNTING) + memset(&p->rss_stat, 0, sizeof(p->rss_stat)); +#endif + + p->default_timer_slack_ns = current->timer_slack_ns; + + task_io_accounting_init(&p->ioac); + acct_clear_integrals(p); + + posix_cpu_timers_init(p); + + p->start_time = ktime_get_ns(); + p->real_start_time = ktime_get_boot_ns(); + p->io_context = NULL; + p->audit_context = NULL; + if (clone_flags & CLONE_THREAD) + threadgroup_change_begin(current); + cgroup_fork(p); +#ifdef CONFIG_NUMA + p->mempolicy = mpol_dup(p->mempolicy); + if (IS_ERR(p->mempolicy)) { + retval = PTR_ERR(p->mempolicy); + p->mempolicy = NULL; + goto bad_fork_cleanup_threadgroup_lock; + } +#endif +#ifdef CONFIG_CPUSETS + p->cpuset_mem_spread_rotor = NUMA_NO_NODE; + p->cpuset_slab_spread_rotor = NUMA_NO_NODE; + seqcount_init(&p->mems_allowed_seq); +#endif +#ifdef CONFIG_TRACE_IRQFLAGS + p->irq_events = 0; + p->hardirqs_enabled = 0; + p->hardirq_enable_ip = 0; + p->hardirq_enable_event = 0; + p->hardirq_disable_ip = _THIS_IP_; + p->hardirq_disable_event = 0; + p->softirqs_enabled = 1; + p->softirq_enable_ip = _THIS_IP_; + p->softirq_enable_event = 0; + p->softirq_disable_ip = 0; + p->softirq_disable_event = 0; + p->hardirq_context = 0; + p->softirq_context = 0; +#endif + + p->pagefault_disabled = 0; + +#ifdef CONFIG_LOCKDEP + p->lockdep_depth = 0; /* no locks held yet */ + p->curr_chain_key = 0; + p->lockdep_recursion = 0; +#endif + +#ifdef CONFIG_DEBUG_MUTEXES + p->blocked_on = NULL; /* not blocked yet */ +#endif +#ifdef CONFIG_BCACHE + p->sequential_io = 0; + p->sequential_io_avg = 0; +#endif + + /* Perform scheduler related setup. Assign this task to a CPU. */ + retval = sched_fork(clone_flags, p); + if (retval) + goto bad_fork_cleanup_policy; + + retval = perf_event_init_task(p); + if (retval) + goto bad_fork_cleanup_policy; + retval = audit_alloc(p); + if (retval) + goto bad_fork_cleanup_perf; + /* copy all the process information */ + shm_init_task(p); + retval = copy_semundo(clone_flags, p); + if (retval) + goto bad_fork_cleanup_audit; + retval = copy_files(clone_flags, p); + if (retval) + goto bad_fork_cleanup_semundo; + retval = copy_fs(clone_flags, p); + if (retval) + goto bad_fork_cleanup_files; + retval = copy_sighand(clone_flags, p); + if (retval) + goto bad_fork_cleanup_fs; + retval = copy_signal(clone_flags, p); + if (retval) + goto bad_fork_cleanup_sighand; + retval = copy_mm(clone_flags, p); + if (retval) + goto bad_fork_cleanup_signal; + retval = copy_namespaces(clone_flags, p); + if (retval) + goto bad_fork_cleanup_mm; + retval = copy_io(clone_flags, p); + if (retval) + goto bad_fork_cleanup_namespaces; + retval = copy_thread(clone_flags, stack_start, stack_size, p); + if (retval) + goto bad_fork_cleanup_io; + + if (pid != &init_struct_pid) { + pid = alloc_pid(p->nsproxy->pid_ns_for_children); + if (IS_ERR(pid)) { + retval = PTR_ERR(pid); + goto bad_fork_cleanup_io; + } + } + + p->set_child_tid = (clone_flags & CLONE_CHILD_SETTID) ? child_tidptr : NULL; + /* + * Clear TID on mm_release()? + */ + p->clear_child_tid = (clone_flags & CLONE_CHILD_CLEARTID) ? child_tidptr : NULL; +#ifdef CONFIG_BLOCK + p->plug = NULL; +#endif +#ifdef CONFIG_FUTEX + p->robust_list = NULL; +#ifdef CONFIG_COMPAT + p->compat_robust_list = NULL; +#endif + INIT_LIST_HEAD(&p->pi_state_list); + p->pi_state_cache = NULL; +#endif + /* + * sigaltstack should be cleared when sharing the same VM + */ + if ((clone_flags & (CLONE_VM|CLONE_VFORK)) == CLONE_VM) + p->sas_ss_sp = p->sas_ss_size = 0; + + /* + * Syscall tracing and stepping should be turned off in the + * child regardless of CLONE_PTRACE. + */ + user_disable_single_step(p); + clear_tsk_thread_flag(p, TIF_SYSCALL_TRACE); +#ifdef TIF_SYSCALL_EMU + clear_tsk_thread_flag(p, TIF_SYSCALL_EMU); +#endif + clear_all_latency_tracing(p); + + /* ok, now we should be set up.. */ + p->pid = pid_nr(pid); + if (clone_flags & CLONE_THREAD) { + p->exit_signal = -1; + p->group_leader = current->group_leader; + p->tgid = current->tgid; + } else { + if (clone_flags & CLONE_PARENT) + p->exit_signal = current->group_leader->exit_signal; + else + p->exit_signal = (clone_flags & CSIGNAL); + p->group_leader = p; + p->tgid = p->pid; + } + + p->nr_dirtied = 0; + p->nr_dirtied_pause = 128 >> (PAGE_SHIFT - 10); + p->dirty_paused_when = 0; + + p->pdeath_signal = 0; + INIT_LIST_HEAD(&p->thread_group); + p->task_works = NULL; + + /* + * Make it visible to the rest of the system, but dont wake it up yet. + * Need tasklist lock for parent etc handling! + */ + write_lock_irq(&tasklist_lock); + + /* CLONE_PARENT re-uses the old parent */ + if (clone_flags & (CLONE_PARENT|CLONE_THREAD)) { + p->real_parent = current->real_parent; + p->parent_exec_id = current->parent_exec_id; + } else { + p->real_parent = current; + p->parent_exec_id = current->self_exec_id; + } + + spin_lock(¤t->sighand->siglock); + + /* + * Copy seccomp details explicitly here, in case they were changed + * before holding sighand lock. + */ + copy_seccomp(p); + + /* + * Process group and session signals need to be delivered to just the + * parent before the fork or both the parent and the child after the + * fork. Restart if a signal comes in before we add the new process to + * it's process group. + * A fatal signal pending means that current will exit, so the new + * thread can't slip out of an OOM kill (or normal SIGKILL). + */ + recalc_sigpending(); + if (signal_pending(current)) { + spin_unlock(¤t->sighand->siglock); + write_unlock_irq(&tasklist_lock); + retval = -ERESTARTNOINTR; + goto bad_fork_free_pid; + } + + if (likely(p->pid)) { + ptrace_init_task(p, (clone_flags & CLONE_PTRACE) || trace); + + init_task_pid(p, PIDTYPE_PID, pid); + if (thread_group_leader(p)) { + init_task_pid(p, PIDTYPE_PGID, task_pgrp(current)); + init_task_pid(p, PIDTYPE_SID, task_session(current)); + + if (is_child_reaper(pid)) { + ns_of_pid(pid)->child_reaper = p; + p->signal->flags |= SIGNAL_UNKILLABLE; + } + + p->signal->leader_pid = pid; + p->signal->tty = tty_kref_get(current->signal->tty); + list_add_tail(&p->sibling, &p->real_parent->children); + list_add_tail_rcu(&p->tasks, &init_task.tasks); + attach_pid(p, PIDTYPE_PGID); + attach_pid(p, PIDTYPE_SID); + __this_cpu_inc(process_counts); + } else { + current->signal->nr_threads++; + atomic_inc(¤t->signal->live); + atomic_inc(¤t->signal->sigcnt); + list_add_tail_rcu(&p->thread_group, + &p->group_leader->thread_group); + list_add_tail_rcu(&p->thread_node, + &p->signal->thread_head); + } + attach_pid(p, PIDTYPE_PID); + nr_threads++; + } + + total_forks++; + spin_unlock(¤t->sighand->siglock); + syscall_tracepoint_update(p); + write_unlock_irq(&tasklist_lock); + + proc_fork_connector(p); + cgroup_post_fork(p); + if (clone_flags & CLONE_THREAD) + threadgroup_change_end(current); + perf_event_fork(p); + + trace_task_newtask(p, clone_flags); + uprobe_copy_process(p, clone_flags); + + return p; + +bad_fork_free_pid: + if (pid != &init_struct_pid) + free_pid(pid); +bad_fork_cleanup_io: + if (p->io_context) + exit_io_context(p); +bad_fork_cleanup_namespaces: + exit_task_namespaces(p); +bad_fork_cleanup_mm: + if (p->mm) + mmput(p->mm); +bad_fork_cleanup_signal: + if (!(clone_flags & CLONE_THREAD)) + free_signal_struct(p->signal); +bad_fork_cleanup_sighand: + __cleanup_sighand(p->sighand); +bad_fork_cleanup_fs: + exit_fs(p); /* blocking */ +bad_fork_cleanup_files: + exit_files(p); /* blocking */ +bad_fork_cleanup_semundo: + exit_sem(p); +bad_fork_cleanup_audit: + audit_free(p); +bad_fork_cleanup_perf: + perf_event_free_task(p); +bad_fork_cleanup_policy: +#ifdef CONFIG_NUMA + mpol_put(p->mempolicy); +bad_fork_cleanup_threadgroup_lock: +#endif + if (clone_flags & CLONE_THREAD) + threadgroup_change_end(current); + delayacct_tsk_free(p); +bad_fork_cleanup_count: + atomic_dec(&p->cred->user->processes); + exit_creds(p); +bad_fork_free: + free_task(p); +fork_out: + return ERR_PTR(retval); +} + +static inline void init_idle_pids(struct pid_link *links) +{ + enum pid_type type; + + for (type = PIDTYPE_PID; type < PIDTYPE_MAX; ++type) { + INIT_HLIST_NODE(&links[type].node); /* not really needed */ + links[type].pid = &init_struct_pid; + } +} + +struct task_struct *fork_idle(int cpu) +{ + struct task_struct *task; + task = copy_process(CLONE_VM, 0, 0, NULL, &init_struct_pid, 0); + if (!IS_ERR(task)) { + init_idle_pids(task->pids); + init_idle(task, cpu); + } + + return task; +} + +/* + * Ok, this is the main fork-routine. + * + * It copies the process, and if successful kick-starts + * it and waits for it to finish using the VM if required. + */ +long do_fork(unsigned long clone_flags, + unsigned long stack_start, + unsigned long stack_size, + int __user *parent_tidptr, + int __user *child_tidptr) +{ + struct task_struct *p; + int trace = 0; + long nr; + + /* + * Determine whether and which event to report to ptracer. When + * called from kernel_thread or CLONE_UNTRACED is explicitly + * requested, no event is reported; otherwise, report if the event + * for the type of forking is enabled. + */ + if (!(clone_flags & CLONE_UNTRACED)) { + if (clone_flags & CLONE_VFORK) + trace = PTRACE_EVENT_VFORK; + else if ((clone_flags & CSIGNAL) != SIGCHLD) + trace = PTRACE_EVENT_CLONE; + else + trace = PTRACE_EVENT_FORK; + + if (likely(!ptrace_event_enabled(current, trace))) + trace = 0; + } + + p = copy_process(clone_flags, stack_start, stack_size, + child_tidptr, NULL, trace); + /* + * Do this prior waking up the new thread - the thread pointer + * might get invalid after that point, if the thread exits quickly. + */ + if (!IS_ERR(p)) { + struct completion vfork; + struct pid *pid; + + trace_sched_process_fork(current, p); + + pid = get_task_pid(p, PIDTYPE_PID); + nr = pid_vnr(pid); + + if (clone_flags & CLONE_PARENT_SETTID) + put_user(nr, parent_tidptr); + + if (clone_flags & CLONE_VFORK) { + p->vfork_done = &vfork; + init_completion(&vfork); + get_task_struct(p); + } + + wake_up_new_task(p); + + /* forking complete and child started to run, tell ptracer */ + if (unlikely(trace)) + ptrace_event_pid(trace, pid); + + if (clone_flags & CLONE_VFORK) { + if (!wait_for_vfork_done(p, &vfork)) + ptrace_event_pid(PTRACE_EVENT_VFORK_DONE, pid); + } + + put_pid(pid); + } else { + nr = PTR_ERR(p); + } + return nr; +} + +/* + * Create a kernel thread. + */ +pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags) +{ + return do_fork(flags|CLONE_VM|CLONE_UNTRACED, (unsigned long)fn, + (unsigned long)arg, NULL, NULL); +} + +#ifdef __ARCH_WANT_SYS_FORK +SYSCALL_DEFINE0(fork) +{ +#ifdef CONFIG_MMU + return do_fork(SIGCHLD, 0, 0, NULL, NULL); +#else + /* can not support in nommu mode */ + return -EINVAL; +#endif +} +#endif + +#ifdef __ARCH_WANT_SYS_VFORK +SYSCALL_DEFINE0(vfork) +{ + return do_fork(CLONE_VFORK | CLONE_VM | SIGCHLD, 0, + 0, NULL, NULL); +} +#endif + +#ifdef __ARCH_WANT_SYS_CLONE +#ifdef CONFIG_CLONE_BACKWARDS +SYSCALL_DEFINE5(clone, unsigned long, clone_flags, unsigned long, newsp, + int __user *, parent_tidptr, + int, tls_val, + int __user *, child_tidptr) +#elif defined(CONFIG_CLONE_BACKWARDS2) +SYSCALL_DEFINE5(clone, unsigned long, newsp, unsigned long, clone_flags, + int __user *, parent_tidptr, + int __user *, child_tidptr, + int, tls_val) +#elif defined(CONFIG_CLONE_BACKWARDS3) +SYSCALL_DEFINE6(clone, unsigned long, clone_flags, unsigned long, newsp, + int, stack_size, + int __user *, parent_tidptr, + int __user *, child_tidptr, + int, tls_val) +#else +SYSCALL_DEFINE5(clone, unsigned long, clone_flags, unsigned long, newsp, + int __user *, parent_tidptr, + int __user *, child_tidptr, + int, tls_val) +#endif +{ + return do_fork(clone_flags, newsp, 0, parent_tidptr, child_tidptr); +} +#endif + +#ifndef ARCH_MIN_MMSTRUCT_ALIGN +#define ARCH_MIN_MMSTRUCT_ALIGN 0 +#endif + +static void sighand_ctor(void *data) +{ + struct sighand_struct *sighand = data; + + spin_lock_init(&sighand->siglock); + init_waitqueue_head(&sighand->signalfd_wqh); +} + +void __init proc_caches_init(void) +{ + sighand_cachep = kmem_cache_create("sighand_cache", + sizeof(struct sighand_struct), 0, + SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_DESTROY_BY_RCU| + SLAB_NOTRACK, sighand_ctor); + signal_cachep = kmem_cache_create("signal_cache", + sizeof(struct signal_struct), 0, + SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_NOTRACK, NULL); + files_cachep = kmem_cache_create("files_cache", + sizeof(struct files_struct), 0, + SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_NOTRACK, NULL); + fs_cachep = kmem_cache_create("fs_cache", + sizeof(struct fs_struct), 0, + SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_NOTRACK, NULL); + /* + * FIXME! The "sizeof(struct mm_struct)" currently includes the + * whole struct cpumask for the OFFSTACK case. We could change + * this to *only* allocate as much of it as required by the + * maximum number of CPU's we can ever have. The cpumask_allocation + * is at the end of the structure, exactly for that reason. + */ + mm_cachep = kmem_cache_create("mm_struct", + sizeof(struct mm_struct), ARCH_MIN_MMSTRUCT_ALIGN, + SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_NOTRACK, NULL); + vm_area_cachep = KMEM_CACHE(vm_area_struct, SLAB_PANIC); + mmap_init(); + nsproxy_cache_init(); +} + +/* + * Check constraints on flags passed to the unshare system call. + */ +static int check_unshare_flags(unsigned long unshare_flags) +{ + if (unshare_flags & ~(CLONE_THREAD|CLONE_FS|CLONE_NEWNS|CLONE_SIGHAND| + CLONE_VM|CLONE_FILES|CLONE_SYSVSEM| + CLONE_NEWUTS|CLONE_NEWIPC|CLONE_NEWNET| + CLONE_NEWUSER|CLONE_NEWPID)) + return -EINVAL; + /* + * Not implemented, but pretend it works if there is nothing to + * unshare. Note that unsharing CLONE_THREAD or CLONE_SIGHAND + * needs to unshare vm. + */ + if (unshare_flags & (CLONE_THREAD | CLONE_SIGHAND | CLONE_VM)) { + /* FIXME: get_task_mm() increments ->mm_users */ + if (atomic_read(¤t->mm->mm_users) > 1) + return -EINVAL; + } + + return 0; +} + +/* + * Unshare the filesystem structure if it is being shared + */ +static int unshare_fs(unsigned long unshare_flags, struct fs_struct **new_fsp) +{ + struct fs_struct *fs = current->fs; + + if (!(unshare_flags & CLONE_FS) || !fs) + return 0; + + /* don't need lock here; in the worst case we'll do useless copy */ + if (fs->users == 1) + return 0; + + *new_fsp = copy_fs_struct(fs); + if (!*new_fsp) + return -ENOMEM; + + return 0; +} + +/* + * Unshare file descriptor table if it is being shared + */ +static int unshare_fd(unsigned long unshare_flags, struct files_struct **new_fdp) +{ + struct files_struct *fd = current->files; + int error = 0; + + if ((unshare_flags & CLONE_FILES) && + (fd && atomic_read(&fd->count) > 1)) { + *new_fdp = dup_fd(fd, &error); + if (!*new_fdp) + return error; + } + + return 0; +} + +/* + * unshare allows a process to 'unshare' part of the process + * context which was originally shared using clone. copy_* + * functions used by do_fork() cannot be used here directly + * because they modify an inactive task_struct that is being + * constructed. Here we are modifying the current, active, + * task_struct. + */ +SYSCALL_DEFINE1(unshare, unsigned long, unshare_flags) +{ + struct fs_struct *fs, *new_fs = NULL; + struct files_struct *fd, *new_fd = NULL; + struct cred *new_cred = NULL; + struct nsproxy *new_nsproxy = NULL; + int do_sysvsem = 0; + int err; + + /* + * If unsharing a user namespace must also unshare the thread. + */ + if (unshare_flags & CLONE_NEWUSER) + unshare_flags |= CLONE_THREAD | CLONE_FS; + /* + * If unsharing a thread from a thread group, must also unshare vm. + */ + if (unshare_flags & CLONE_THREAD) + unshare_flags |= CLONE_VM; + /* + * If unsharing vm, must also unshare signal handlers. + */ + if (unshare_flags & CLONE_VM) + unshare_flags |= CLONE_SIGHAND; + /* + * If unsharing namespace, must also unshare filesystem information. + */ + if (unshare_flags & CLONE_NEWNS) + unshare_flags |= CLONE_FS; + + err = check_unshare_flags(unshare_flags); + if (err) + goto bad_unshare_out; + /* + * CLONE_NEWIPC must also detach from the undolist: after switching + * to a new ipc namespace, the semaphore arrays from the old + * namespace are unreachable. + */ + if (unshare_flags & (CLONE_NEWIPC|CLONE_SYSVSEM)) + do_sysvsem = 1; + err = unshare_fs(unshare_flags, &new_fs); + if (err) + goto bad_unshare_out; + err = unshare_fd(unshare_flags, &new_fd); + if (err) + goto bad_unshare_cleanup_fs; + err = unshare_userns(unshare_flags, &new_cred); + if (err) + goto bad_unshare_cleanup_fd; + err = unshare_nsproxy_namespaces(unshare_flags, &new_nsproxy, + new_cred, new_fs); + if (err) + goto bad_unshare_cleanup_cred; + + if (new_fs || new_fd || do_sysvsem || new_cred || new_nsproxy) { + if (do_sysvsem) { + /* + * CLONE_SYSVSEM is equivalent to sys_exit(). + */ + exit_sem(current); + } + if (unshare_flags & CLONE_NEWIPC) { + /* Orphan segments in old ns (see sem above). */ + exit_shm(current); + shm_init_task(current); + } + + if (new_nsproxy) + switch_task_namespaces(current, new_nsproxy); + + task_lock(current); + + if (new_fs) { + fs = current->fs; + spin_lock(&fs->lock); + current->fs = new_fs; + if (--fs->users) + new_fs = NULL; + else + new_fs = fs; + spin_unlock(&fs->lock); + } + + if (new_fd) { + fd = current->files; + current->files = new_fd; + new_fd = fd; + } + + task_unlock(current); + + if (new_cred) { + /* Install the new user namespace */ + commit_creds(new_cred); + new_cred = NULL; + } + } + +bad_unshare_cleanup_cred: + if (new_cred) + put_cred(new_cred); +bad_unshare_cleanup_fd: + if (new_fd) + put_files_struct(new_fd); + +bad_unshare_cleanup_fs: + if (new_fs) + free_fs_struct(new_fs); + +bad_unshare_out: + return err; +} + +/* + * Helper to unshare the files of the current task. + * We don't want to expose copy_files internals to + * the exec layer of the kernel. + */ + +int unshare_files(struct files_struct **displaced) +{ + struct task_struct *task = current; + struct files_struct *copy = NULL; + int error; + + error = unshare_fd(CLONE_FILES, ©); + if (error || !copy) { + *displaced = NULL; + return error; + } + *displaced = task->files; + task_lock(task); + task->files = copy; + task_unlock(task); + return 0; +} + +int sysctl_max_threads(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + struct ctl_table t; + int ret; + int threads = max_threads; + int min = MIN_THREADS; + int max = MAX_THREADS; + + t = *table; + t.data = &threads; + t.extra1 = &min; + t.extra2 = &max; + + ret = proc_dointvec_minmax(&t, write, buffer, lenp, ppos); + if (ret || !write) + return ret; + + set_max_threads(threads); + + return 0; +} diff --git a/kernel/kernel/freezer.c b/kernel/kernel/freezer.c new file mode 100644 index 000000000..a8900a3bc --- /dev/null +++ b/kernel/kernel/freezer.c @@ -0,0 +1,179 @@ +/* + * kernel/freezer.c - Function to freeze a process + * + * Originally from kernel/power/process.c + */ + +#include +#include +#include +#include +#include +#include + +/* total number of freezing conditions in effect */ +atomic_t system_freezing_cnt = ATOMIC_INIT(0); +EXPORT_SYMBOL(system_freezing_cnt); + +/* indicate whether PM freezing is in effect, protected by pm_mutex */ +bool pm_freezing; +bool pm_nosig_freezing; + +/* + * Temporary export for the deadlock workaround in ata_scsi_hotplug(). + * Remove once the hack becomes unnecessary. + */ +EXPORT_SYMBOL_GPL(pm_freezing); + +/* protects freezing and frozen transitions */ +static DEFINE_SPINLOCK(freezer_lock); + +/** + * freezing_slow_path - slow path for testing whether a task needs to be frozen + * @p: task to be tested + * + * This function is called by freezing() if system_freezing_cnt isn't zero + * and tests whether @p needs to enter and stay in frozen state. Can be + * called under any context. The freezers are responsible for ensuring the + * target tasks see the updated state. + */ +bool freezing_slow_path(struct task_struct *p) +{ + if (p->flags & (PF_NOFREEZE | PF_SUSPEND_TASK)) + return false; + + if (test_thread_flag(TIF_MEMDIE)) + return false; + + if (pm_nosig_freezing || cgroup_freezing(p)) + return true; + + if (pm_freezing && !(p->flags & PF_KTHREAD)) + return true; + + return false; +} +EXPORT_SYMBOL(freezing_slow_path); + +/* Refrigerator is place where frozen processes are stored :-). */ +bool __refrigerator(bool check_kthr_stop) +{ + /* Hmm, should we be allowed to suspend when there are realtime + processes around? */ + bool was_frozen = false; + long save = current->state; + + pr_debug("%s entered refrigerator\n", current->comm); + + for (;;) { + set_current_state(TASK_UNINTERRUPTIBLE); + + spin_lock_irq(&freezer_lock); + current->flags |= PF_FROZEN; + if (!freezing(current) || + (check_kthr_stop && kthread_should_stop())) + current->flags &= ~PF_FROZEN; + spin_unlock_irq(&freezer_lock); + + if (!(current->flags & PF_FROZEN)) + break; + was_frozen = true; + schedule(); + } + + pr_debug("%s left refrigerator\n", current->comm); + + /* + * Restore saved task state before returning. The mb'd version + * needs to be used; otherwise, it might silently break + * synchronization which depends on ordered task state change. + */ + set_current_state(save); + + return was_frozen; +} +EXPORT_SYMBOL(__refrigerator); + +static void fake_signal_wake_up(struct task_struct *p) +{ + unsigned long flags; + + if (lock_task_sighand(p, &flags)) { + signal_wake_up(p, 0); + unlock_task_sighand(p, &flags); + } +} + +/** + * freeze_task - send a freeze request to given task + * @p: task to send the request to + * + * If @p is freezing, the freeze request is sent either by sending a fake + * signal (if it's not a kernel thread) or waking it up (if it's a kernel + * thread). + * + * RETURNS: + * %false, if @p is not freezing or already frozen; %true, otherwise + */ +bool freeze_task(struct task_struct *p) +{ + unsigned long flags; + + /* + * This check can race with freezer_do_not_count, but worst case that + * will result in an extra wakeup being sent to the task. It does not + * race with freezer_count(), the barriers in freezer_count() and + * freezer_should_skip() ensure that either freezer_count() sees + * freezing == true in try_to_freeze() and freezes, or + * freezer_should_skip() sees !PF_FREEZE_SKIP and freezes the task + * normally. + */ + if (freezer_should_skip(p)) + return false; + + spin_lock_irqsave(&freezer_lock, flags); + if (!freezing(p) || frozen(p)) { + spin_unlock_irqrestore(&freezer_lock, flags); + return false; + } + + if (!(p->flags & PF_KTHREAD)) + fake_signal_wake_up(p); + else + wake_up_state(p, TASK_INTERRUPTIBLE); + + spin_unlock_irqrestore(&freezer_lock, flags); + return true; +} + +void __thaw_task(struct task_struct *p) +{ + unsigned long flags; + + spin_lock_irqsave(&freezer_lock, flags); + if (frozen(p)) + wake_up_process(p); + spin_unlock_irqrestore(&freezer_lock, flags); +} + +/** + * set_freezable - make %current freezable + * + * Mark %current freezable and enter refrigerator if necessary. + */ +bool set_freezable(void) +{ + might_sleep(); + + /* + * Modify flags while holding freezer_lock. This ensures the + * freezer notices that we aren't frozen yet or the freezing + * condition is visible to try_to_freeze() below. + */ + spin_lock_irq(&freezer_lock); + current->flags &= ~PF_NOFREEZE; + spin_unlock_irq(&freezer_lock); + + return try_to_freeze(); +} +EXPORT_SYMBOL(set_freezable); diff --git a/kernel/kernel/futex.c b/kernel/kernel/futex.c new file mode 100644 index 000000000..bf20e0ad0 --- /dev/null +++ b/kernel/kernel/futex.c @@ -0,0 +1,3126 @@ +/* + * Fast Userspace Mutexes (which I call "Futexes!"). + * (C) Rusty Russell, IBM 2002 + * + * Generalized futexes, futex requeueing, misc fixes by Ingo Molnar + * (C) Copyright 2003 Red Hat Inc, All Rights Reserved + * + * Removed page pinning, fix privately mapped COW pages and other cleanups + * (C) Copyright 2003, 2004 Jamie Lokier + * + * Robust futex support started by Ingo Molnar + * (C) Copyright 2006 Red Hat Inc, All Rights Reserved + * Thanks to Thomas Gleixner for suggestions, analysis and fixes. + * + * PI-futex support started by Ingo Molnar and Thomas Gleixner + * Copyright (C) 2006 Red Hat, Inc., Ingo Molnar + * Copyright (C) 2006 Timesys Corp., Thomas Gleixner + * + * PRIVATE futexes by Eric Dumazet + * Copyright (C) 2007 Eric Dumazet + * + * Requeue-PI support by Darren Hart + * Copyright (C) IBM Corporation, 2009 + * Thanks to Thomas Gleixner for conceptual design and careful reviews. + * + * Thanks to Ben LaHaise for yelling "hashed waitqueues" loudly + * enough at me, Linus for the original (flawed) idea, Matthew + * Kirkwood for proof-of-concept implementation. + * + * "The futexes are also cursed." + * "But they come in a choice of three flavours!" + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +#include "locking/rtmutex_common.h" + +/* + * READ this before attempting to hack on futexes! + * + * Basic futex operation and ordering guarantees + * ============================================= + * + * The waiter reads the futex value in user space and calls + * futex_wait(). This function computes the hash bucket and acquires + * the hash bucket lock. After that it reads the futex user space value + * again and verifies that the data has not changed. If it has not changed + * it enqueues itself into the hash bucket, releases the hash bucket lock + * and schedules. + * + * The waker side modifies the user space value of the futex and calls + * futex_wake(). This function computes the hash bucket and acquires the + * hash bucket lock. Then it looks for waiters on that futex in the hash + * bucket and wakes them. + * + * In futex wake up scenarios where no tasks are blocked on a futex, taking + * the hb spinlock can be avoided and simply return. In order for this + * optimization to work, ordering guarantees must exist so that the waiter + * being added to the list is acknowledged when the list is concurrently being + * checked by the waker, avoiding scenarios like the following: + * + * CPU 0 CPU 1 + * val = *futex; + * sys_futex(WAIT, futex, val); + * futex_wait(futex, val); + * uval = *futex; + * *futex = newval; + * sys_futex(WAKE, futex); + * futex_wake(futex); + * if (queue_empty()) + * return; + * if (uval == val) + * lock(hash_bucket(futex)); + * queue(); + * unlock(hash_bucket(futex)); + * schedule(); + * + * This would cause the waiter on CPU 0 to wait forever because it + * missed the transition of the user space value from val to newval + * and the waker did not find the waiter in the hash bucket queue. + * + * The correct serialization ensures that a waiter either observes + * the changed user space value before blocking or is woken by a + * concurrent waker: + * + * CPU 0 CPU 1 + * val = *futex; + * sys_futex(WAIT, futex, val); + * futex_wait(futex, val); + * + * waiters++; (a) + * mb(); (A) <-- paired with -. + * | + * lock(hash_bucket(futex)); | + * | + * uval = *futex; | + * | *futex = newval; + * | sys_futex(WAKE, futex); + * | futex_wake(futex); + * | + * `-------> mb(); (B) + * if (uval == val) + * queue(); + * unlock(hash_bucket(futex)); + * schedule(); if (waiters) + * lock(hash_bucket(futex)); + * else wake_waiters(futex); + * waiters--; (b) unlock(hash_bucket(futex)); + * + * Where (A) orders the waiters increment and the futex value read through + * atomic operations (see hb_waiters_inc) and where (B) orders the write + * to futex and the waiters read -- this is done by the barriers for both + * shared and private futexes in get_futex_key_refs(). + * + * This yields the following case (where X:=waiters, Y:=futex): + * + * X = Y = 0 + * + * w[X]=1 w[Y]=1 + * MB MB + * r[Y]=y r[X]=x + * + * Which guarantees that x==0 && y==0 is impossible; which translates back into + * the guarantee that we cannot both miss the futex variable change and the + * enqueue. + * + * Note that a new waiter is accounted for in (a) even when it is possible that + * the wait call can return error, in which case we backtrack from it in (b). + * Refer to the comment in queue_lock(). + * + * Similarly, in order to account for waiters being requeued on another + * address we always increment the waiters for the destination bucket before + * acquiring the lock. It then decrements them again after releasing it - + * the code that actually moves the futex(es) between hash buckets (requeue_futex) + * will do the additional required waiter count housekeeping. This is done for + * double_lock_hb() and double_unlock_hb(), respectively. + */ + +#ifndef CONFIG_HAVE_FUTEX_CMPXCHG +int __read_mostly futex_cmpxchg_enabled; +#endif + +/* + * Futex flags used to encode options to functions and preserve them across + * restarts. + */ +#define FLAGS_SHARED 0x01 +#define FLAGS_CLOCKRT 0x02 +#define FLAGS_HAS_TIMEOUT 0x04 + +/* + * Priority Inheritance state: + */ +struct futex_pi_state { + /* + * list of 'owned' pi_state instances - these have to be + * cleaned up in do_exit() if the task exits prematurely: + */ + struct list_head list; + + /* + * The PI object: + */ + struct rt_mutex pi_mutex; + + struct task_struct *owner; + atomic_t refcount; + + union futex_key key; +}; + +/** + * struct futex_q - The hashed futex queue entry, one per waiting task + * @list: priority-sorted list of tasks waiting on this futex + * @task: the task waiting on the futex + * @lock_ptr: the hash bucket lock + * @key: the key the futex is hashed on + * @pi_state: optional priority inheritance state + * @rt_waiter: rt_waiter storage for use with requeue_pi + * @requeue_pi_key: the requeue_pi target futex key + * @bitset: bitset for the optional bitmasked wakeup + * + * We use this hashed waitqueue, instead of a normal wait_queue_t, so + * we can wake only the relevant ones (hashed queues may be shared). + * + * A futex_q has a woken state, just like tasks have TASK_RUNNING. + * It is considered woken when plist_node_empty(&q->list) || q->lock_ptr == 0. + * The order of wakeup is always to make the first condition true, then + * the second. + * + * PI futexes are typically woken before they are removed from the hash list via + * the rt_mutex code. See unqueue_me_pi(). + */ +struct futex_q { + struct plist_node list; + + struct task_struct *task; + spinlock_t *lock_ptr; + union futex_key key; + struct futex_pi_state *pi_state; + struct rt_mutex_waiter *rt_waiter; + union futex_key *requeue_pi_key; + u32 bitset; +}; + +static const struct futex_q futex_q_init = { + /* list gets initialized in queue_me()*/ + .key = FUTEX_KEY_INIT, + .bitset = FUTEX_BITSET_MATCH_ANY +}; + +/* + * Hash buckets are shared by all the futex_keys that hash to the same + * location. Each key may have multiple futex_q structures, one for each task + * waiting on a futex. + */ +struct futex_hash_bucket { + atomic_t waiters; + spinlock_t lock; + struct plist_head chain; +} ____cacheline_aligned_in_smp; + +static unsigned long __read_mostly futex_hashsize; + +static struct futex_hash_bucket *futex_queues; + +static inline void futex_get_mm(union futex_key *key) +{ + atomic_inc(&key->private.mm->mm_count); + /* + * Ensure futex_get_mm() implies a full barrier such that + * get_futex_key() implies a full barrier. This is relied upon + * as full barrier (B), see the ordering comment above. + */ + smp_mb__after_atomic(); +} + +/* + * Reflects a new waiter being added to the waitqueue. + */ +static inline void hb_waiters_inc(struct futex_hash_bucket *hb) +{ +#ifdef CONFIG_SMP + atomic_inc(&hb->waiters); + /* + * Full barrier (A), see the ordering comment above. + */ + smp_mb__after_atomic(); +#endif +} + +/* + * Reflects a waiter being removed from the waitqueue by wakeup + * paths. + */ +static inline void hb_waiters_dec(struct futex_hash_bucket *hb) +{ +#ifdef CONFIG_SMP + atomic_dec(&hb->waiters); +#endif +} + +static inline int hb_waiters_pending(struct futex_hash_bucket *hb) +{ +#ifdef CONFIG_SMP + return atomic_read(&hb->waiters); +#else + return 1; +#endif +} + +/* + * We hash on the keys returned from get_futex_key (see below). + */ +static struct futex_hash_bucket *hash_futex(union futex_key *key) +{ + u32 hash = jhash2((u32*)&key->both.word, + (sizeof(key->both.word)+sizeof(key->both.ptr))/4, + key->both.offset); + return &futex_queues[hash & (futex_hashsize - 1)]; +} + +/* + * Return 1 if two futex_keys are equal, 0 otherwise. + */ +static inline int match_futex(union futex_key *key1, union futex_key *key2) +{ + return (key1 && key2 + && key1->both.word == key2->both.word + && key1->both.ptr == key2->both.ptr + && key1->both.offset == key2->both.offset); +} + +/* + * Take a reference to the resource addressed by a key. + * Can be called while holding spinlocks. + * + */ +static void get_futex_key_refs(union futex_key *key) +{ + if (!key->both.ptr) + return; + + switch (key->both.offset & (FUT_OFF_INODE|FUT_OFF_MMSHARED)) { + case FUT_OFF_INODE: + ihold(key->shared.inode); /* implies MB (B) */ + break; + case FUT_OFF_MMSHARED: + futex_get_mm(key); /* implies MB (B) */ + break; + default: + /* + * Private futexes do not hold reference on an inode or + * mm, therefore the only purpose of calling get_futex_key_refs + * is because we need the barrier for the lockless waiter check. + */ + smp_mb(); /* explicit MB (B) */ + } +} + +/* + * Drop a reference to the resource addressed by a key. + * The hash bucket spinlock must not be held. This is + * a no-op for private futexes, see comment in the get + * counterpart. + */ +static void drop_futex_key_refs(union futex_key *key) +{ + if (!key->both.ptr) { + /* If we're here then we tried to put a key we failed to get */ + WARN_ON_ONCE(1); + return; + } + + switch (key->both.offset & (FUT_OFF_INODE|FUT_OFF_MMSHARED)) { + case FUT_OFF_INODE: + iput(key->shared.inode); + break; + case FUT_OFF_MMSHARED: + mmdrop(key->private.mm); + break; + } +} + +/** + * get_futex_key() - Get parameters which are the keys for a futex + * @uaddr: virtual address of the futex + * @fshared: 0 for a PROCESS_PRIVATE futex, 1 for PROCESS_SHARED + * @key: address where result is stored. + * @rw: mapping needs to be read/write (values: VERIFY_READ, + * VERIFY_WRITE) + * + * Return: a negative error code or 0 + * + * The key words are stored in *key on success. + * + * For shared mappings, it's (page->index, file_inode(vma->vm_file), + * offset_within_page). For private mappings, it's (uaddr, current->mm). + * We can usually work out the index without swapping in the page. + * + * lock_page() might sleep, the caller should not hold a spinlock. + */ +static int +get_futex_key(u32 __user *uaddr, int fshared, union futex_key *key, int rw) +{ + unsigned long address = (unsigned long)uaddr; + struct mm_struct *mm = current->mm; + struct page *page, *page_head; + int err, ro = 0; + + /* + * The futex address must be "naturally" aligned. + */ + key->both.offset = address % PAGE_SIZE; + if (unlikely((address % sizeof(u32)) != 0)) + return -EINVAL; + address -= key->both.offset; + + if (unlikely(!access_ok(rw, uaddr, sizeof(u32)))) + return -EFAULT; + + /* + * PROCESS_PRIVATE futexes are fast. + * As the mm cannot disappear under us and the 'key' only needs + * virtual address, we dont even have to find the underlying vma. + * Note : We do have to check 'uaddr' is a valid user address, + * but access_ok() should be faster than find_vma() + */ + if (!fshared) { + key->private.mm = mm; + key->private.address = address; + get_futex_key_refs(key); /* implies MB (B) */ + return 0; + } + +again: + err = get_user_pages_fast(address, 1, 1, &page); + /* + * If write access is not required (eg. FUTEX_WAIT), try + * and get read-only access. + */ + if (err == -EFAULT && rw == VERIFY_READ) { + err = get_user_pages_fast(address, 1, 0, &page); + ro = 1; + } + if (err < 0) + return err; + else + err = 0; + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + page_head = page; + if (unlikely(PageTail(page))) { + put_page(page); + /* serialize against __split_huge_page_splitting() */ + local_irq_disable(); + if (likely(__get_user_pages_fast(address, 1, !ro, &page) == 1)) { + page_head = compound_head(page); + /* + * page_head is valid pointer but we must pin + * it before taking the PG_lock and/or + * PG_compound_lock. The moment we re-enable + * irqs __split_huge_page_splitting() can + * return and the head page can be freed from + * under us. We can't take the PG_lock and/or + * PG_compound_lock on a page that could be + * freed from under us. + */ + if (page != page_head) { + get_page(page_head); + put_page(page); + } + local_irq_enable(); + } else { + local_irq_enable(); + goto again; + } + } +#else + page_head = compound_head(page); + if (page != page_head) { + get_page(page_head); + put_page(page); + } +#endif + + lock_page(page_head); + + /* + * If page_head->mapping is NULL, then it cannot be a PageAnon + * page; but it might be the ZERO_PAGE or in the gate area or + * in a special mapping (all cases which we are happy to fail); + * or it may have been a good file page when get_user_pages_fast + * found it, but truncated or holepunched or subjected to + * invalidate_complete_page2 before we got the page lock (also + * cases which we are happy to fail). And we hold a reference, + * so refcount care in invalidate_complete_page's remove_mapping + * prevents drop_caches from setting mapping to NULL beneath us. + * + * The case we do have to guard against is when memory pressure made + * shmem_writepage move it from filecache to swapcache beneath us: + * an unlikely race, but we do need to retry for page_head->mapping. + */ + if (!page_head->mapping) { + int shmem_swizzled = PageSwapCache(page_head); + unlock_page(page_head); + put_page(page_head); + if (shmem_swizzled) + goto again; + return -EFAULT; + } + + /* + * Private mappings are handled in a simple way. + * + * NOTE: When userspace waits on a MAP_SHARED mapping, even if + * it's a read-only handle, it's expected that futexes attach to + * the object not the particular process. + */ + if (PageAnon(page_head)) { + /* + * A RO anonymous page will never change and thus doesn't make + * sense for futex operations. + */ + if (ro) { + err = -EFAULT; + goto out; + } + + key->both.offset |= FUT_OFF_MMSHARED; /* ref taken on mm */ + key->private.mm = mm; + key->private.address = address; + } else { + key->both.offset |= FUT_OFF_INODE; /* inode-based key */ + key->shared.inode = page_head->mapping->host; + key->shared.pgoff = basepage_index(page); + } + + get_futex_key_refs(key); /* implies MB (B) */ + +out: + unlock_page(page_head); + put_page(page_head); + return err; +} + +static inline void put_futex_key(union futex_key *key) +{ + drop_futex_key_refs(key); +} + +/** + * fault_in_user_writeable() - Fault in user address and verify RW access + * @uaddr: pointer to faulting user space address + * + * Slow path to fixup the fault we just took in the atomic write + * access to @uaddr. + * + * We have no generic implementation of a non-destructive write to the + * user address. We know that we faulted in the atomic pagefault + * disabled section so we can as well avoid the #PF overhead by + * calling get_user_pages() right away. + */ +static int fault_in_user_writeable(u32 __user *uaddr) +{ + struct mm_struct *mm = current->mm; + int ret; + + down_read(&mm->mmap_sem); + ret = fixup_user_fault(current, mm, (unsigned long)uaddr, + FAULT_FLAG_WRITE); + up_read(&mm->mmap_sem); + + return ret < 0 ? ret : 0; +} + +/** + * futex_top_waiter() - Return the highest priority waiter on a futex + * @hb: the hash bucket the futex_q's reside in + * @key: the futex key (to distinguish it from other futex futex_q's) + * + * Must be called with the hb lock held. + */ +static struct futex_q *futex_top_waiter(struct futex_hash_bucket *hb, + union futex_key *key) +{ + struct futex_q *this; + + plist_for_each_entry(this, &hb->chain, list) { + if (match_futex(&this->key, key)) + return this; + } + return NULL; +} + +static int cmpxchg_futex_value_locked(u32 *curval, u32 __user *uaddr, + u32 uval, u32 newval) +{ + int ret; + + pagefault_disable(); + ret = futex_atomic_cmpxchg_inatomic(curval, uaddr, uval, newval); + pagefault_enable(); + + return ret; +} + +static int get_futex_value_locked(u32 *dest, u32 __user *from) +{ + int ret; + + pagefault_disable(); + ret = __copy_from_user_inatomic(dest, from, sizeof(u32)); + pagefault_enable(); + + return ret ? -EFAULT : 0; +} + + +/* + * PI code: + */ +static int refill_pi_state_cache(void) +{ + struct futex_pi_state *pi_state; + + if (likely(current->pi_state_cache)) + return 0; + + pi_state = kzalloc(sizeof(*pi_state), GFP_KERNEL); + + if (!pi_state) + return -ENOMEM; + + INIT_LIST_HEAD(&pi_state->list); + /* pi_mutex gets initialized later */ + pi_state->owner = NULL; + atomic_set(&pi_state->refcount, 1); + pi_state->key = FUTEX_KEY_INIT; + + current->pi_state_cache = pi_state; + + return 0; +} + +static struct futex_pi_state * alloc_pi_state(void) +{ + struct futex_pi_state *pi_state = current->pi_state_cache; + + WARN_ON(!pi_state); + current->pi_state_cache = NULL; + + return pi_state; +} + +/* + * Must be called with the hb lock held. + */ +static void free_pi_state(struct futex_pi_state *pi_state) +{ + if (!pi_state) + return; + + if (!atomic_dec_and_test(&pi_state->refcount)) + return; + + /* + * If pi_state->owner is NULL, the owner is most probably dying + * and has cleaned up the pi_state already + */ + if (pi_state->owner) { + raw_spin_lock_irq(&pi_state->owner->pi_lock); + list_del_init(&pi_state->list); + raw_spin_unlock_irq(&pi_state->owner->pi_lock); + + rt_mutex_proxy_unlock(&pi_state->pi_mutex, pi_state->owner); + } + + if (current->pi_state_cache) + kfree(pi_state); + else { + /* + * pi_state->list is already empty. + * clear pi_state->owner. + * refcount is at 0 - put it back to 1. + */ + pi_state->owner = NULL; + atomic_set(&pi_state->refcount, 1); + current->pi_state_cache = pi_state; + } +} + +/* + * Look up the task based on what TID userspace gave us. + * We dont trust it. + */ +static struct task_struct * futex_find_get_task(pid_t pid) +{ + struct task_struct *p; + + rcu_read_lock(); + p = find_task_by_vpid(pid); + if (p) + get_task_struct(p); + + rcu_read_unlock(); + + return p; +} + +/* + * This task is holding PI mutexes at exit time => bad. + * Kernel cleans up PI-state, but userspace is likely hosed. + * (Robust-futex cleanup is separate and might save the day for userspace.) + */ +void exit_pi_state_list(struct task_struct *curr) +{ + struct list_head *next, *head = &curr->pi_state_list; + struct futex_pi_state *pi_state; + struct futex_hash_bucket *hb; + union futex_key key = FUTEX_KEY_INIT; + + if (!futex_cmpxchg_enabled) + return; + /* + * We are a ZOMBIE and nobody can enqueue itself on + * pi_state_list anymore, but we have to be careful + * versus waiters unqueueing themselves: + */ + raw_spin_lock_irq(&curr->pi_lock); + while (!list_empty(head)) { + + next = head->next; + pi_state = list_entry(next, struct futex_pi_state, list); + key = pi_state->key; + hb = hash_futex(&key); + raw_spin_unlock_irq(&curr->pi_lock); + + spin_lock(&hb->lock); + + raw_spin_lock_irq(&curr->pi_lock); + /* + * We dropped the pi-lock, so re-check whether this + * task still owns the PI-state: + */ + if (head->next != next) { + raw_spin_unlock_irq(&curr->pi_lock); + spin_unlock(&hb->lock); + raw_spin_lock_irq(&curr->pi_lock); + continue; + } + + WARN_ON(pi_state->owner != curr); + WARN_ON(list_empty(&pi_state->list)); + list_del_init(&pi_state->list); + pi_state->owner = NULL; + raw_spin_unlock_irq(&curr->pi_lock); + + rt_mutex_unlock(&pi_state->pi_mutex); + + spin_unlock(&hb->lock); + + raw_spin_lock_irq(&curr->pi_lock); + } + raw_spin_unlock_irq(&curr->pi_lock); +} + +/* + * We need to check the following states: + * + * Waiter | pi_state | pi->owner | uTID | uODIED | ? + * + * [1] NULL | --- | --- | 0 | 0/1 | Valid + * [2] NULL | --- | --- | >0 | 0/1 | Valid + * + * [3] Found | NULL | -- | Any | 0/1 | Invalid + * + * [4] Found | Found | NULL | 0 | 1 | Valid + * [5] Found | Found | NULL | >0 | 1 | Invalid + * + * [6] Found | Found | task | 0 | 1 | Valid + * + * [7] Found | Found | NULL | Any | 0 | Invalid + * + * [8] Found | Found | task | ==taskTID | 0/1 | Valid + * [9] Found | Found | task | 0 | 0 | Invalid + * [10] Found | Found | task | !=taskTID | 0/1 | Invalid + * + * [1] Indicates that the kernel can acquire the futex atomically. We + * came came here due to a stale FUTEX_WAITERS/FUTEX_OWNER_DIED bit. + * + * [2] Valid, if TID does not belong to a kernel thread. If no matching + * thread is found then it indicates that the owner TID has died. + * + * [3] Invalid. The waiter is queued on a non PI futex + * + * [4] Valid state after exit_robust_list(), which sets the user space + * value to FUTEX_WAITERS | FUTEX_OWNER_DIED. + * + * [5] The user space value got manipulated between exit_robust_list() + * and exit_pi_state_list() + * + * [6] Valid state after exit_pi_state_list() which sets the new owner in + * the pi_state but cannot access the user space value. + * + * [7] pi_state->owner can only be NULL when the OWNER_DIED bit is set. + * + * [8] Owner and user space value match + * + * [9] There is no transient state which sets the user space TID to 0 + * except exit_robust_list(), but this is indicated by the + * FUTEX_OWNER_DIED bit. See [4] + * + * [10] There is no transient state which leaves owner and user space + * TID out of sync. + */ + +/* + * Validate that the existing waiter has a pi_state and sanity check + * the pi_state against the user space value. If correct, attach to + * it. + */ +static int attach_to_pi_state(u32 uval, struct futex_pi_state *pi_state, + struct futex_pi_state **ps) +{ + pid_t pid = uval & FUTEX_TID_MASK; + + /* + * Userspace might have messed up non-PI and PI futexes [3] + */ + if (unlikely(!pi_state)) + return -EINVAL; + + WARN_ON(!atomic_read(&pi_state->refcount)); + + /* + * Handle the owner died case: + */ + if (uval & FUTEX_OWNER_DIED) { + /* + * exit_pi_state_list sets owner to NULL and wakes the + * topmost waiter. The task which acquires the + * pi_state->rt_mutex will fixup owner. + */ + if (!pi_state->owner) { + /* + * No pi state owner, but the user space TID + * is not 0. Inconsistent state. [5] + */ + if (pid) + return -EINVAL; + /* + * Take a ref on the state and return success. [4] + */ + goto out_state; + } + + /* + * If TID is 0, then either the dying owner has not + * yet executed exit_pi_state_list() or some waiter + * acquired the rtmutex in the pi state, but did not + * yet fixup the TID in user space. + * + * Take a ref on the state and return success. [6] + */ + if (!pid) + goto out_state; + } else { + /* + * If the owner died bit is not set, then the pi_state + * must have an owner. [7] + */ + if (!pi_state->owner) + return -EINVAL; + } + + /* + * Bail out if user space manipulated the futex value. If pi + * state exists then the owner TID must be the same as the + * user space TID. [9/10] + */ + if (pid != task_pid_vnr(pi_state->owner)) + return -EINVAL; +out_state: + atomic_inc(&pi_state->refcount); + *ps = pi_state; + return 0; +} + +/* + * Lookup the task for the TID provided from user space and attach to + * it after doing proper sanity checks. + */ +static int attach_to_pi_owner(u32 uval, union futex_key *key, + struct futex_pi_state **ps) +{ + pid_t pid = uval & FUTEX_TID_MASK; + struct futex_pi_state *pi_state; + struct task_struct *p; + + /* + * We are the first waiter - try to look up the real owner and attach + * the new pi_state to it, but bail out when TID = 0 [1] + */ + if (!pid) + return -ESRCH; + p = futex_find_get_task(pid); + if (!p) + return -ESRCH; + + if (unlikely(p->flags & PF_KTHREAD)) { + put_task_struct(p); + return -EPERM; + } + + /* + * We need to look at the task state flags to figure out, + * whether the task is exiting. To protect against the do_exit + * change of the task flags, we do this protected by + * p->pi_lock: + */ + raw_spin_lock_irq(&p->pi_lock); + if (unlikely(p->flags & PF_EXITING)) { + /* + * The task is on the way out. When PF_EXITPIDONE is + * set, we know that the task has finished the + * cleanup: + */ + int ret = (p->flags & PF_EXITPIDONE) ? -ESRCH : -EAGAIN; + + raw_spin_unlock_irq(&p->pi_lock); + put_task_struct(p); + return ret; + } + + /* + * No existing pi state. First waiter. [2] + */ + pi_state = alloc_pi_state(); + + /* + * Initialize the pi_mutex in locked state and make @p + * the owner of it: + */ + rt_mutex_init_proxy_locked(&pi_state->pi_mutex, p); + + /* Store the key for possible exit cleanups: */ + pi_state->key = *key; + + WARN_ON(!list_empty(&pi_state->list)); + list_add(&pi_state->list, &p->pi_state_list); + pi_state->owner = p; + raw_spin_unlock_irq(&p->pi_lock); + + put_task_struct(p); + + *ps = pi_state; + + return 0; +} + +static int lookup_pi_state(u32 uval, struct futex_hash_bucket *hb, + union futex_key *key, struct futex_pi_state **ps) +{ + struct futex_q *match = futex_top_waiter(hb, key); + + /* + * If there is a waiter on that futex, validate it and + * attach to the pi_state when the validation succeeds. + */ + if (match) + return attach_to_pi_state(uval, match->pi_state, ps); + + /* + * We are the first waiter - try to look up the owner based on + * @uval and attach to it. + */ + return attach_to_pi_owner(uval, key, ps); +} + +static int lock_pi_update_atomic(u32 __user *uaddr, u32 uval, u32 newval) +{ + u32 uninitialized_var(curval); + + if (unlikely(cmpxchg_futex_value_locked(&curval, uaddr, uval, newval))) + return -EFAULT; + + /*If user space value changed, let the caller retry */ + return curval != uval ? -EAGAIN : 0; +} + +/** + * futex_lock_pi_atomic() - Atomic work required to acquire a pi aware futex + * @uaddr: the pi futex user address + * @hb: the pi futex hash bucket + * @key: the futex key associated with uaddr and hb + * @ps: the pi_state pointer where we store the result of the + * lookup + * @task: the task to perform the atomic lock work for. This will + * be "current" except in the case of requeue pi. + * @set_waiters: force setting the FUTEX_WAITERS bit (1) or not (0) + * + * Return: + * 0 - ready to wait; + * 1 - acquired the lock; + * <0 - error + * + * The hb->lock and futex_key refs shall be held by the caller. + */ +static int futex_lock_pi_atomic(u32 __user *uaddr, struct futex_hash_bucket *hb, + union futex_key *key, + struct futex_pi_state **ps, + struct task_struct *task, int set_waiters) +{ + u32 uval, newval, vpid = task_pid_vnr(task); + struct futex_q *match; + int ret; + + /* + * Read the user space value first so we can validate a few + * things before proceeding further. + */ + if (get_futex_value_locked(&uval, uaddr)) + return -EFAULT; + + /* + * Detect deadlocks. + */ + if ((unlikely((uval & FUTEX_TID_MASK) == vpid))) + return -EDEADLK; + + /* + * Lookup existing state first. If it exists, try to attach to + * its pi_state. + */ + match = futex_top_waiter(hb, key); + if (match) + return attach_to_pi_state(uval, match->pi_state, ps); + + /* + * No waiter and user TID is 0. We are here because the + * waiters or the owner died bit is set or called from + * requeue_cmp_pi or for whatever reason something took the + * syscall. + */ + if (!(uval & FUTEX_TID_MASK)) { + /* + * We take over the futex. No other waiters and the user space + * TID is 0. We preserve the owner died bit. + */ + newval = uval & FUTEX_OWNER_DIED; + newval |= vpid; + + /* The futex requeue_pi code can enforce the waiters bit */ + if (set_waiters) + newval |= FUTEX_WAITERS; + + ret = lock_pi_update_atomic(uaddr, uval, newval); + /* If the take over worked, return 1 */ + return ret < 0 ? ret : 1; + } + + /* + * First waiter. Set the waiters bit before attaching ourself to + * the owner. If owner tries to unlock, it will be forced into + * the kernel and blocked on hb->lock. + */ + newval = uval | FUTEX_WAITERS; + ret = lock_pi_update_atomic(uaddr, uval, newval); + if (ret) + return ret; + /* + * If the update of the user space value succeeded, we try to + * attach to the owner. If that fails, no harm done, we only + * set the FUTEX_WAITERS bit in the user space variable. + */ + return attach_to_pi_owner(uval, key, ps); +} + +/** + * __unqueue_futex() - Remove the futex_q from its futex_hash_bucket + * @q: The futex_q to unqueue + * + * The q->lock_ptr must not be NULL and must be held by the caller. + */ +static void __unqueue_futex(struct futex_q *q) +{ + struct futex_hash_bucket *hb; + + if (WARN_ON_SMP(!q->lock_ptr || !spin_is_locked(q->lock_ptr)) + || WARN_ON(plist_node_empty(&q->list))) + return; + + hb = container_of(q->lock_ptr, struct futex_hash_bucket, lock); + plist_del(&q->list, &hb->chain); + hb_waiters_dec(hb); +} + +/* + * The hash bucket lock must be held when this is called. + * Afterwards, the futex_q must not be accessed. Callers + * must ensure to later call wake_up_q() for the actual + * wakeups to occur. + */ +static void mark_wake_futex(struct wake_q_head *wake_q, struct futex_q *q) +{ + struct task_struct *p = q->task; + + if (WARN(q->pi_state || q->rt_waiter, "refusing to wake PI futex\n")) + return; + + /* + * Queue the task for later wakeup for after we've released + * the hb->lock. wake_q_add() grabs reference to p. + */ + wake_q_add(wake_q, p); + __unqueue_futex(q); + /* + * The waiting task can free the futex_q as soon as + * q->lock_ptr = NULL is written, without taking any locks. A + * memory barrier is required here to prevent the following + * store to lock_ptr from getting ahead of the plist_del. + */ + smp_wmb(); + q->lock_ptr = NULL; +} + +static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *this, + struct futex_hash_bucket *hb) +{ + struct task_struct *new_owner; + struct futex_pi_state *pi_state = this->pi_state; + u32 uninitialized_var(curval), newval; + bool deboost; + int ret = 0; + + if (!pi_state) + return -EINVAL; + + /* + * If current does not own the pi_state then the futex is + * inconsistent and user space fiddled with the futex value. + */ + if (pi_state->owner != current) + return -EINVAL; + + raw_spin_lock(&pi_state->pi_mutex.wait_lock); + new_owner = rt_mutex_next_owner(&pi_state->pi_mutex); + + /* + * It is possible that the next waiter (the one that brought + * this owner to the kernel) timed out and is no longer + * waiting on the lock. + */ + if (!new_owner) + new_owner = this->task; + + /* + * We pass it to the next owner. The WAITERS bit is always + * kept enabled while there is PI state around. We cleanup the + * owner died bit, because we are the owner. + */ + newval = FUTEX_WAITERS | task_pid_vnr(new_owner); + + if (cmpxchg_futex_value_locked(&curval, uaddr, uval, newval)) + ret = -EFAULT; + else if (curval != uval) + ret = -EINVAL; + if (ret) { + raw_spin_unlock(&pi_state->pi_mutex.wait_lock); + return ret; + } + + raw_spin_lock_irq(&pi_state->owner->pi_lock); + WARN_ON(list_empty(&pi_state->list)); + list_del_init(&pi_state->list); + raw_spin_unlock_irq(&pi_state->owner->pi_lock); + + raw_spin_lock_irq(&new_owner->pi_lock); + WARN_ON(!list_empty(&pi_state->list)); + list_add(&pi_state->list, &new_owner->pi_state_list); + pi_state->owner = new_owner; + raw_spin_unlock_irq(&new_owner->pi_lock); + + raw_spin_unlock(&pi_state->pi_mutex.wait_lock); + + deboost = rt_mutex_futex_unlock(&pi_state->pi_mutex); + + /* + * We deboost after dropping hb->lock. That prevents a double + * wakeup on RT. + */ + spin_unlock(&hb->lock); + + if (deboost) + rt_mutex_adjust_prio(current); + + return 0; +} + +/* + * Express the locking dependencies for lockdep: + */ +static inline void +double_lock_hb(struct futex_hash_bucket *hb1, struct futex_hash_bucket *hb2) +{ + if (hb1 <= hb2) { + spin_lock(&hb1->lock); + if (hb1 < hb2) + spin_lock_nested(&hb2->lock, SINGLE_DEPTH_NESTING); + } else { /* hb1 > hb2 */ + spin_lock(&hb2->lock); + spin_lock_nested(&hb1->lock, SINGLE_DEPTH_NESTING); + } +} + +static inline void +double_unlock_hb(struct futex_hash_bucket *hb1, struct futex_hash_bucket *hb2) +{ + spin_unlock(&hb1->lock); + if (hb1 != hb2) + spin_unlock(&hb2->lock); +} + +/* + * Wake up waiters matching bitset queued on this futex (uaddr). + */ +static int +futex_wake(u32 __user *uaddr, unsigned int flags, int nr_wake, u32 bitset) +{ + struct futex_hash_bucket *hb; + struct futex_q *this, *next; + union futex_key key = FUTEX_KEY_INIT; + int ret; + WAKE_Q(wake_q); + + if (!bitset) + return -EINVAL; + + ret = get_futex_key(uaddr, flags & FLAGS_SHARED, &key, VERIFY_READ); + if (unlikely(ret != 0)) + goto out; + + hb = hash_futex(&key); + + /* Make sure we really have tasks to wakeup */ + if (!hb_waiters_pending(hb)) + goto out_put_key; + + spin_lock(&hb->lock); + + plist_for_each_entry_safe(this, next, &hb->chain, list) { + if (match_futex (&this->key, &key)) { + if (this->pi_state || this->rt_waiter) { + ret = -EINVAL; + break; + } + + /* Check if one of the bits is set in both bitsets */ + if (!(this->bitset & bitset)) + continue; + + mark_wake_futex(&wake_q, this); + if (++ret >= nr_wake) + break; + } + } + + spin_unlock(&hb->lock); + wake_up_q(&wake_q); +out_put_key: + put_futex_key(&key); +out: + return ret; +} + +/* + * Wake up all waiters hashed on the physical page that is mapped + * to this virtual address: + */ +static int +futex_wake_op(u32 __user *uaddr1, unsigned int flags, u32 __user *uaddr2, + int nr_wake, int nr_wake2, int op) +{ + union futex_key key1 = FUTEX_KEY_INIT, key2 = FUTEX_KEY_INIT; + struct futex_hash_bucket *hb1, *hb2; + struct futex_q *this, *next; + int ret, op_ret; + WAKE_Q(wake_q); + +retry: + ret = get_futex_key(uaddr1, flags & FLAGS_SHARED, &key1, VERIFY_READ); + if (unlikely(ret != 0)) + goto out; + ret = get_futex_key(uaddr2, flags & FLAGS_SHARED, &key2, VERIFY_WRITE); + if (unlikely(ret != 0)) + goto out_put_key1; + + hb1 = hash_futex(&key1); + hb2 = hash_futex(&key2); + +retry_private: + double_lock_hb(hb1, hb2); + op_ret = futex_atomic_op_inuser(op, uaddr2); + if (unlikely(op_ret < 0)) { + + double_unlock_hb(hb1, hb2); + +#ifndef CONFIG_MMU + /* + * we don't get EFAULT from MMU faults if we don't have an MMU, + * but we might get them from range checking + */ + ret = op_ret; + goto out_put_keys; +#endif + + if (unlikely(op_ret != -EFAULT)) { + ret = op_ret; + goto out_put_keys; + } + + ret = fault_in_user_writeable(uaddr2); + if (ret) + goto out_put_keys; + + if (!(flags & FLAGS_SHARED)) + goto retry_private; + + put_futex_key(&key2); + put_futex_key(&key1); + goto retry; + } + + plist_for_each_entry_safe(this, next, &hb1->chain, list) { + if (match_futex (&this->key, &key1)) { + if (this->pi_state || this->rt_waiter) { + ret = -EINVAL; + goto out_unlock; + } + mark_wake_futex(&wake_q, this); + if (++ret >= nr_wake) + break; + } + } + + if (op_ret > 0) { + op_ret = 0; + plist_for_each_entry_safe(this, next, &hb2->chain, list) { + if (match_futex (&this->key, &key2)) { + if (this->pi_state || this->rt_waiter) { + ret = -EINVAL; + goto out_unlock; + } + mark_wake_futex(&wake_q, this); + if (++op_ret >= nr_wake2) + break; + } + } + ret += op_ret; + } + +out_unlock: + double_unlock_hb(hb1, hb2); + wake_up_q(&wake_q); +out_put_keys: + put_futex_key(&key2); +out_put_key1: + put_futex_key(&key1); +out: + return ret; +} + +/** + * requeue_futex() - Requeue a futex_q from one hb to another + * @q: the futex_q to requeue + * @hb1: the source hash_bucket + * @hb2: the target hash_bucket + * @key2: the new key for the requeued futex_q + */ +static inline +void requeue_futex(struct futex_q *q, struct futex_hash_bucket *hb1, + struct futex_hash_bucket *hb2, union futex_key *key2) +{ + + /* + * If key1 and key2 hash to the same bucket, no need to + * requeue. + */ + if (likely(&hb1->chain != &hb2->chain)) { + plist_del(&q->list, &hb1->chain); + hb_waiters_dec(hb1); + plist_add(&q->list, &hb2->chain); + hb_waiters_inc(hb2); + q->lock_ptr = &hb2->lock; + } + get_futex_key_refs(key2); + q->key = *key2; +} + +/** + * requeue_pi_wake_futex() - Wake a task that acquired the lock during requeue + * @q: the futex_q + * @key: the key of the requeue target futex + * @hb: the hash_bucket of the requeue target futex + * + * During futex_requeue, with requeue_pi=1, it is possible to acquire the + * target futex if it is uncontended or via a lock steal. Set the futex_q key + * to the requeue target futex so the waiter can detect the wakeup on the right + * futex, but remove it from the hb and NULL the rt_waiter so it can detect + * atomic lock acquisition. Set the q->lock_ptr to the requeue target hb->lock + * to protect access to the pi_state to fixup the owner later. Must be called + * with both q->lock_ptr and hb->lock held. + */ +static inline +void requeue_pi_wake_futex(struct futex_q *q, union futex_key *key, + struct futex_hash_bucket *hb) +{ + get_futex_key_refs(key); + q->key = *key; + + __unqueue_futex(q); + + WARN_ON(!q->rt_waiter); + q->rt_waiter = NULL; + + q->lock_ptr = &hb->lock; + + wake_up_state(q->task, TASK_NORMAL); +} + +/** + * futex_proxy_trylock_atomic() - Attempt an atomic lock for the top waiter + * @pifutex: the user address of the to futex + * @hb1: the from futex hash bucket, must be locked by the caller + * @hb2: the to futex hash bucket, must be locked by the caller + * @key1: the from futex key + * @key2: the to futex key + * @ps: address to store the pi_state pointer + * @set_waiters: force setting the FUTEX_WAITERS bit (1) or not (0) + * + * Try and get the lock on behalf of the top waiter if we can do it atomically. + * Wake the top waiter if we succeed. If the caller specified set_waiters, + * then direct futex_lock_pi_atomic() to force setting the FUTEX_WAITERS bit. + * hb1 and hb2 must be held by the caller. + * + * Return: + * 0 - failed to acquire the lock atomically; + * >0 - acquired the lock, return value is vpid of the top_waiter + * <0 - error + */ +static int futex_proxy_trylock_atomic(u32 __user *pifutex, + struct futex_hash_bucket *hb1, + struct futex_hash_bucket *hb2, + union futex_key *key1, union futex_key *key2, + struct futex_pi_state **ps, int set_waiters) +{ + struct futex_q *top_waiter = NULL; + u32 curval; + int ret, vpid; + + if (get_futex_value_locked(&curval, pifutex)) + return -EFAULT; + + /* + * Find the top_waiter and determine if there are additional waiters. + * If the caller intends to requeue more than 1 waiter to pifutex, + * force futex_lock_pi_atomic() to set the FUTEX_WAITERS bit now, + * as we have means to handle the possible fault. If not, don't set + * the bit unecessarily as it will force the subsequent unlock to enter + * the kernel. + */ + top_waiter = futex_top_waiter(hb1, key1); + + /* There are no waiters, nothing for us to do. */ + if (!top_waiter) + return 0; + + /* Ensure we requeue to the expected futex. */ + if (!match_futex(top_waiter->requeue_pi_key, key2)) + return -EINVAL; + + /* + * Try to take the lock for top_waiter. Set the FUTEX_WAITERS bit in + * the contended case or if set_waiters is 1. The pi_state is returned + * in ps in contended cases. + */ + vpid = task_pid_vnr(top_waiter->task); + ret = futex_lock_pi_atomic(pifutex, hb2, key2, ps, top_waiter->task, + set_waiters); + if (ret == 1) { + requeue_pi_wake_futex(top_waiter, key2, hb2); + return vpid; + } + return ret; +} + +/** + * futex_requeue() - Requeue waiters from uaddr1 to uaddr2 + * @uaddr1: source futex user address + * @flags: futex flags (FLAGS_SHARED, etc.) + * @uaddr2: target futex user address + * @nr_wake: number of waiters to wake (must be 1 for requeue_pi) + * @nr_requeue: number of waiters to requeue (0-INT_MAX) + * @cmpval: @uaddr1 expected value (or %NULL) + * @requeue_pi: if we are attempting to requeue from a non-pi futex to a + * pi futex (pi to pi requeue is not supported) + * + * Requeue waiters on uaddr1 to uaddr2. In the requeue_pi case, try to acquire + * uaddr2 atomically on behalf of the top waiter. + * + * Return: + * >=0 - on success, the number of tasks requeued or woken; + * <0 - on error + */ +static int futex_requeue(u32 __user *uaddr1, unsigned int flags, + u32 __user *uaddr2, int nr_wake, int nr_requeue, + u32 *cmpval, int requeue_pi) +{ + union futex_key key1 = FUTEX_KEY_INIT, key2 = FUTEX_KEY_INIT; + int drop_count = 0, task_count = 0, ret; + struct futex_pi_state *pi_state = NULL; + struct futex_hash_bucket *hb1, *hb2; + struct futex_q *this, *next; + WAKE_Q(wake_q); + + if (requeue_pi) { + /* + * Requeue PI only works on two distinct uaddrs. This + * check is only valid for private futexes. See below. + */ + if (uaddr1 == uaddr2) + return -EINVAL; + + /* + * requeue_pi requires a pi_state, try to allocate it now + * without any locks in case it fails. + */ + if (refill_pi_state_cache()) + return -ENOMEM; + /* + * requeue_pi must wake as many tasks as it can, up to nr_wake + * + nr_requeue, since it acquires the rt_mutex prior to + * returning to userspace, so as to not leave the rt_mutex with + * waiters and no owner. However, second and third wake-ups + * cannot be predicted as they involve race conditions with the + * first wake and a fault while looking up the pi_state. Both + * pthread_cond_signal() and pthread_cond_broadcast() should + * use nr_wake=1. + */ + if (nr_wake != 1) + return -EINVAL; + } + +retry: + ret = get_futex_key(uaddr1, flags & FLAGS_SHARED, &key1, VERIFY_READ); + if (unlikely(ret != 0)) + goto out; + ret = get_futex_key(uaddr2, flags & FLAGS_SHARED, &key2, + requeue_pi ? VERIFY_WRITE : VERIFY_READ); + if (unlikely(ret != 0)) + goto out_put_key1; + + /* + * The check above which compares uaddrs is not sufficient for + * shared futexes. We need to compare the keys: + */ + if (requeue_pi && match_futex(&key1, &key2)) { + ret = -EINVAL; + goto out_put_keys; + } + + hb1 = hash_futex(&key1); + hb2 = hash_futex(&key2); + +retry_private: + hb_waiters_inc(hb2); + double_lock_hb(hb1, hb2); + + if (likely(cmpval != NULL)) { + u32 curval; + + ret = get_futex_value_locked(&curval, uaddr1); + + if (unlikely(ret)) { + double_unlock_hb(hb1, hb2); + hb_waiters_dec(hb2); + + ret = get_user(curval, uaddr1); + if (ret) + goto out_put_keys; + + if (!(flags & FLAGS_SHARED)) + goto retry_private; + + put_futex_key(&key2); + put_futex_key(&key1); + goto retry; + } + if (curval != *cmpval) { + ret = -EAGAIN; + goto out_unlock; + } + } + + if (requeue_pi && (task_count - nr_wake < nr_requeue)) { + /* + * Attempt to acquire uaddr2 and wake the top waiter. If we + * intend to requeue waiters, force setting the FUTEX_WAITERS + * bit. We force this here where we are able to easily handle + * faults rather in the requeue loop below. + */ + ret = futex_proxy_trylock_atomic(uaddr2, hb1, hb2, &key1, + &key2, &pi_state, nr_requeue); + + /* + * At this point the top_waiter has either taken uaddr2 or is + * waiting on it. If the former, then the pi_state will not + * exist yet, look it up one more time to ensure we have a + * reference to it. If the lock was taken, ret contains the + * vpid of the top waiter task. + */ + if (ret > 0) { + WARN_ON(pi_state); + drop_count++; + task_count++; + /* + * If we acquired the lock, then the user + * space value of uaddr2 should be vpid. It + * cannot be changed by the top waiter as it + * is blocked on hb2 lock if it tries to do + * so. If something fiddled with it behind our + * back the pi state lookup might unearth + * it. So we rather use the known value than + * rereading and handing potential crap to + * lookup_pi_state. + */ + ret = lookup_pi_state(ret, hb2, &key2, &pi_state); + } + + switch (ret) { + case 0: + break; + case -EFAULT: + free_pi_state(pi_state); + pi_state = NULL; + double_unlock_hb(hb1, hb2); + hb_waiters_dec(hb2); + put_futex_key(&key2); + put_futex_key(&key1); + ret = fault_in_user_writeable(uaddr2); + if (!ret) + goto retry; + goto out; + case -EAGAIN: + /* + * Two reasons for this: + * - Owner is exiting and we just wait for the + * exit to complete. + * - The user space value changed. + */ + free_pi_state(pi_state); + pi_state = NULL; + double_unlock_hb(hb1, hb2); + hb_waiters_dec(hb2); + put_futex_key(&key2); + put_futex_key(&key1); + cond_resched(); + goto retry; + default: + goto out_unlock; + } + } + + plist_for_each_entry_safe(this, next, &hb1->chain, list) { + if (task_count - nr_wake >= nr_requeue) + break; + + if (!match_futex(&this->key, &key1)) + continue; + + /* + * FUTEX_WAIT_REQEUE_PI and FUTEX_CMP_REQUEUE_PI should always + * be paired with each other and no other futex ops. + * + * We should never be requeueing a futex_q with a pi_state, + * which is awaiting a futex_unlock_pi(). + */ + if ((requeue_pi && !this->rt_waiter) || + (!requeue_pi && this->rt_waiter) || + this->pi_state) { + ret = -EINVAL; + break; + } + + /* + * Wake nr_wake waiters. For requeue_pi, if we acquired the + * lock, we already woke the top_waiter. If not, it will be + * woken by futex_unlock_pi(). + */ + if (++task_count <= nr_wake && !requeue_pi) { + mark_wake_futex(&wake_q, this); + continue; + } + + /* Ensure we requeue to the expected futex for requeue_pi. */ + if (requeue_pi && !match_futex(this->requeue_pi_key, &key2)) { + ret = -EINVAL; + break; + } + + /* + * Requeue nr_requeue waiters and possibly one more in the case + * of requeue_pi if we couldn't acquire the lock atomically. + */ + if (requeue_pi) { + /* Prepare the waiter to take the rt_mutex. */ + atomic_inc(&pi_state->refcount); + this->pi_state = pi_state; + ret = rt_mutex_start_proxy_lock(&pi_state->pi_mutex, + this->rt_waiter, + this->task); + if (ret == 1) { + /* We got the lock. */ + requeue_pi_wake_futex(this, &key2, hb2); + drop_count++; + continue; + } else if (ret == -EAGAIN) { + /* + * Waiter was woken by timeout or + * signal and has set pi_blocked_on to + * PI_WAKEUP_INPROGRESS before we + * tried to enqueue it on the rtmutex. + */ + this->pi_state = NULL; + free_pi_state(pi_state); + continue; + } else if (ret) { + /* -EDEADLK */ + this->pi_state = NULL; + free_pi_state(pi_state); + goto out_unlock; + } + } + requeue_futex(this, hb1, hb2, &key2); + drop_count++; + } + +out_unlock: + free_pi_state(pi_state); + double_unlock_hb(hb1, hb2); + wake_up_q(&wake_q); + hb_waiters_dec(hb2); + + /* + * drop_futex_key_refs() must be called outside the spinlocks. During + * the requeue we moved futex_q's from the hash bucket at key1 to the + * one at key2 and updated their key pointer. We no longer need to + * hold the references to key1. + */ + while (--drop_count >= 0) + drop_futex_key_refs(&key1); + +out_put_keys: + put_futex_key(&key2); +out_put_key1: + put_futex_key(&key1); +out: + return ret ? ret : task_count; +} + +/* The key must be already stored in q->key. */ +static inline struct futex_hash_bucket *queue_lock(struct futex_q *q) + __acquires(&hb->lock) +{ + struct futex_hash_bucket *hb; + + hb = hash_futex(&q->key); + + /* + * Increment the counter before taking the lock so that + * a potential waker won't miss a to-be-slept task that is + * waiting for the spinlock. This is safe as all queue_lock() + * users end up calling queue_me(). Similarly, for housekeeping, + * decrement the counter at queue_unlock() when some error has + * occurred and we don't end up adding the task to the list. + */ + hb_waiters_inc(hb); + + q->lock_ptr = &hb->lock; + + spin_lock(&hb->lock); /* implies MB (A) */ + return hb; +} + +static inline void +queue_unlock(struct futex_hash_bucket *hb) + __releases(&hb->lock) +{ + spin_unlock(&hb->lock); + hb_waiters_dec(hb); +} + +/** + * queue_me() - Enqueue the futex_q on the futex_hash_bucket + * @q: The futex_q to enqueue + * @hb: The destination hash bucket + * + * The hb->lock must be held by the caller, and is released here. A call to + * queue_me() is typically paired with exactly one call to unqueue_me(). The + * exceptions involve the PI related operations, which may use unqueue_me_pi() + * or nothing if the unqueue is done as part of the wake process and the unqueue + * state is implicit in the state of woken task (see futex_wait_requeue_pi() for + * an example). + */ +static inline void queue_me(struct futex_q *q, struct futex_hash_bucket *hb) + __releases(&hb->lock) +{ + int prio; + + /* + * The priority used to register this element is + * - either the real thread-priority for the real-time threads + * (i.e. threads with a priority lower than MAX_RT_PRIO) + * - or MAX_RT_PRIO for non-RT threads. + * Thus, all RT-threads are woken first in priority order, and + * the others are woken last, in FIFO order. + */ + prio = min(current->normal_prio, MAX_RT_PRIO); + + plist_node_init(&q->list, prio); + plist_add(&q->list, &hb->chain); + q->task = current; + spin_unlock(&hb->lock); +} + +/** + * unqueue_me() - Remove the futex_q from its futex_hash_bucket + * @q: The futex_q to unqueue + * + * The q->lock_ptr must not be held by the caller. A call to unqueue_me() must + * be paired with exactly one earlier call to queue_me(). + * + * Return: + * 1 - if the futex_q was still queued (and we removed unqueued it); + * 0 - if the futex_q was already removed by the waking thread + */ +static int unqueue_me(struct futex_q *q) +{ + spinlock_t *lock_ptr; + int ret = 0; + + /* In the common case we don't take the spinlock, which is nice. */ +retry: + lock_ptr = q->lock_ptr; + barrier(); + if (lock_ptr != NULL) { + spin_lock(lock_ptr); + /* + * q->lock_ptr can change between reading it and + * spin_lock(), causing us to take the wrong lock. This + * corrects the race condition. + * + * Reasoning goes like this: if we have the wrong lock, + * q->lock_ptr must have changed (maybe several times) + * between reading it and the spin_lock(). It can + * change again after the spin_lock() but only if it was + * already changed before the spin_lock(). It cannot, + * however, change back to the original value. Therefore + * we can detect whether we acquired the correct lock. + */ + if (unlikely(lock_ptr != q->lock_ptr)) { + spin_unlock(lock_ptr); + goto retry; + } + __unqueue_futex(q); + + BUG_ON(q->pi_state); + + spin_unlock(lock_ptr); + ret = 1; + } + + drop_futex_key_refs(&q->key); + return ret; +} + +/* + * PI futexes can not be requeued and must remove themself from the + * hash bucket. The hash bucket lock (i.e. lock_ptr) is held on entry + * and dropped here. + */ +static void unqueue_me_pi(struct futex_q *q) + __releases(q->lock_ptr) +{ + __unqueue_futex(q); + + BUG_ON(!q->pi_state); + free_pi_state(q->pi_state); + q->pi_state = NULL; + + spin_unlock(q->lock_ptr); +} + +/* + * Fixup the pi_state owner with the new owner. + * + * Must be called with hash bucket lock held and mm->sem held for non + * private futexes. + */ +static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q, + struct task_struct *newowner) +{ + u32 newtid = task_pid_vnr(newowner) | FUTEX_WAITERS; + struct futex_pi_state *pi_state = q->pi_state; + struct task_struct *oldowner = pi_state->owner; + u32 uval, uninitialized_var(curval), newval; + int ret; + + /* Owner died? */ + if (!pi_state->owner) + newtid |= FUTEX_OWNER_DIED; + + /* + * We are here either because we stole the rtmutex from the + * previous highest priority waiter or we are the highest priority + * waiter but failed to get the rtmutex the first time. + * We have to replace the newowner TID in the user space variable. + * This must be atomic as we have to preserve the owner died bit here. + * + * Note: We write the user space value _before_ changing the pi_state + * because we can fault here. Imagine swapped out pages or a fork + * that marked all the anonymous memory readonly for cow. + * + * Modifying pi_state _before_ the user space value would + * leave the pi_state in an inconsistent state when we fault + * here, because we need to drop the hash bucket lock to + * handle the fault. This might be observed in the PID check + * in lookup_pi_state. + */ +retry: + if (get_futex_value_locked(&uval, uaddr)) + goto handle_fault; + + while (1) { + newval = (uval & FUTEX_OWNER_DIED) | newtid; + + if (cmpxchg_futex_value_locked(&curval, uaddr, uval, newval)) + goto handle_fault; + if (curval == uval) + break; + uval = curval; + } + + /* + * We fixed up user space. Now we need to fix the pi_state + * itself. + */ + if (pi_state->owner != NULL) { + raw_spin_lock_irq(&pi_state->owner->pi_lock); + WARN_ON(list_empty(&pi_state->list)); + list_del_init(&pi_state->list); + raw_spin_unlock_irq(&pi_state->owner->pi_lock); + } + + pi_state->owner = newowner; + + raw_spin_lock_irq(&newowner->pi_lock); + WARN_ON(!list_empty(&pi_state->list)); + list_add(&pi_state->list, &newowner->pi_state_list); + raw_spin_unlock_irq(&newowner->pi_lock); + return 0; + + /* + * To handle the page fault we need to drop the hash bucket + * lock here. That gives the other task (either the highest priority + * waiter itself or the task which stole the rtmutex) the + * chance to try the fixup of the pi_state. So once we are + * back from handling the fault we need to check the pi_state + * after reacquiring the hash bucket lock and before trying to + * do another fixup. When the fixup has been done already we + * simply return. + */ +handle_fault: + spin_unlock(q->lock_ptr); + + ret = fault_in_user_writeable(uaddr); + + spin_lock(q->lock_ptr); + + /* + * Check if someone else fixed it for us: + */ + if (pi_state->owner != oldowner) + return 0; + + if (ret) + return ret; + + goto retry; +} + +static long futex_wait_restart(struct restart_block *restart); + +/** + * fixup_owner() - Post lock pi_state and corner case management + * @uaddr: user address of the futex + * @q: futex_q (contains pi_state and access to the rt_mutex) + * @locked: if the attempt to take the rt_mutex succeeded (1) or not (0) + * + * After attempting to lock an rt_mutex, this function is called to cleanup + * the pi_state owner as well as handle race conditions that may allow us to + * acquire the lock. Must be called with the hb lock held. + * + * Return: + * 1 - success, lock taken; + * 0 - success, lock not taken; + * <0 - on error (-EFAULT) + */ +static int fixup_owner(u32 __user *uaddr, struct futex_q *q, int locked) +{ + struct task_struct *owner; + int ret = 0; + + if (locked) { + /* + * Got the lock. We might not be the anticipated owner if we + * did a lock-steal - fix up the PI-state in that case: + */ + if (q->pi_state->owner != current) + ret = fixup_pi_state_owner(uaddr, q, current); + goto out; + } + + /* + * Catch the rare case, where the lock was released when we were on the + * way back before we locked the hash bucket. + */ + if (q->pi_state->owner == current) { + /* + * Try to get the rt_mutex now. This might fail as some other + * task acquired the rt_mutex after we removed ourself from the + * rt_mutex waiters list. + */ + if (rt_mutex_trylock(&q->pi_state->pi_mutex)) { + locked = 1; + goto out; + } + + /* + * pi_state is incorrect, some other task did a lock steal and + * we returned due to timeout or signal without taking the + * rt_mutex. Too late. + */ + raw_spin_lock(&q->pi_state->pi_mutex.wait_lock); + owner = rt_mutex_owner(&q->pi_state->pi_mutex); + if (!owner) + owner = rt_mutex_next_owner(&q->pi_state->pi_mutex); + raw_spin_unlock(&q->pi_state->pi_mutex.wait_lock); + ret = fixup_pi_state_owner(uaddr, q, owner); + goto out; + } + + /* + * Paranoia check. If we did not take the lock, then we should not be + * the owner of the rt_mutex. + */ + if (rt_mutex_owner(&q->pi_state->pi_mutex) == current) + printk(KERN_ERR "fixup_owner: ret = %d pi-mutex: %p " + "pi-state %p\n", ret, + q->pi_state->pi_mutex.owner, + q->pi_state->owner); + +out: + return ret ? ret : locked; +} + +/** + * futex_wait_queue_me() - queue_me() and wait for wakeup, timeout, or signal + * @hb: the futex hash bucket, must be locked by the caller + * @q: the futex_q to queue up on + * @timeout: the prepared hrtimer_sleeper, or null for no timeout + */ +static void futex_wait_queue_me(struct futex_hash_bucket *hb, struct futex_q *q, + struct hrtimer_sleeper *timeout) +{ + /* + * The task state is guaranteed to be set before another task can + * wake it. set_current_state() is implemented using set_mb() and + * queue_me() calls spin_unlock() upon completion, both serializing + * access to the hash list and forcing another memory barrier. + */ + set_current_state(TASK_INTERRUPTIBLE); + queue_me(q, hb); + + /* Arm the timer */ + if (timeout) { + hrtimer_start_expires(&timeout->timer, HRTIMER_MODE_ABS); + if (!hrtimer_active(&timeout->timer)) + timeout->task = NULL; + } + + /* + * If we have been removed from the hash list, then another task + * has tried to wake us, and we can skip the call to schedule(). + */ + if (likely(!plist_node_empty(&q->list))) { + /* + * If the timer has already expired, current will already be + * flagged for rescheduling. Only call schedule if there + * is no timeout, or if it has yet to expire. + */ + if (!timeout || timeout->task) + freezable_schedule(); + } + __set_current_state(TASK_RUNNING); +} + +/** + * futex_wait_setup() - Prepare to wait on a futex + * @uaddr: the futex userspace address + * @val: the expected value + * @flags: futex flags (FLAGS_SHARED, etc.) + * @q: the associated futex_q + * @hb: storage for hash_bucket pointer to be returned to caller + * + * Setup the futex_q and locate the hash_bucket. Get the futex value and + * compare it with the expected value. Handle atomic faults internally. + * Return with the hb lock held and a q.key reference on success, and unlocked + * with no q.key reference on failure. + * + * Return: + * 0 - uaddr contains val and hb has been locked; + * <1 - -EFAULT or -EWOULDBLOCK (uaddr does not contain val) and hb is unlocked + */ +static int futex_wait_setup(u32 __user *uaddr, u32 val, unsigned int flags, + struct futex_q *q, struct futex_hash_bucket **hb) +{ + u32 uval; + int ret; + + /* + * Access the page AFTER the hash-bucket is locked. + * Order is important: + * + * Userspace waiter: val = var; if (cond(val)) futex_wait(&var, val); + * Userspace waker: if (cond(var)) { var = new; futex_wake(&var); } + * + * The basic logical guarantee of a futex is that it blocks ONLY + * if cond(var) is known to be true at the time of blocking, for + * any cond. If we locked the hash-bucket after testing *uaddr, that + * would open a race condition where we could block indefinitely with + * cond(var) false, which would violate the guarantee. + * + * On the other hand, we insert q and release the hash-bucket only + * after testing *uaddr. This guarantees that futex_wait() will NOT + * absorb a wakeup if *uaddr does not match the desired values + * while the syscall executes. + */ +retry: + ret = get_futex_key(uaddr, flags & FLAGS_SHARED, &q->key, VERIFY_READ); + if (unlikely(ret != 0)) + return ret; + +retry_private: + *hb = queue_lock(q); + + ret = get_futex_value_locked(&uval, uaddr); + + if (ret) { + queue_unlock(*hb); + + ret = get_user(uval, uaddr); + if (ret) + goto out; + + if (!(flags & FLAGS_SHARED)) + goto retry_private; + + put_futex_key(&q->key); + goto retry; + } + + if (uval != val) { + queue_unlock(*hb); + ret = -EWOULDBLOCK; + } + +out: + if (ret) + put_futex_key(&q->key); + return ret; +} + +static int futex_wait(u32 __user *uaddr, unsigned int flags, u32 val, + ktime_t *abs_time, u32 bitset) +{ + struct hrtimer_sleeper timeout, *to = NULL; + struct restart_block *restart; + struct futex_hash_bucket *hb; + struct futex_q q = futex_q_init; + int ret; + + if (!bitset) + return -EINVAL; + q.bitset = bitset; + + if (abs_time) { + to = &timeout; + + hrtimer_init_on_stack(&to->timer, (flags & FLAGS_CLOCKRT) ? + CLOCK_REALTIME : CLOCK_MONOTONIC, + HRTIMER_MODE_ABS); + hrtimer_init_sleeper(to, current); + hrtimer_set_expires_range_ns(&to->timer, *abs_time, + current->timer_slack_ns); + } + +retry: + /* + * Prepare to wait on uaddr. On success, holds hb lock and increments + * q.key refs. + */ + ret = futex_wait_setup(uaddr, val, flags, &q, &hb); + if (ret) + goto out; + + /* queue_me and wait for wakeup, timeout, or a signal. */ + futex_wait_queue_me(hb, &q, to); + + /* If we were woken (and unqueued), we succeeded, whatever. */ + ret = 0; + /* unqueue_me() drops q.key ref */ + if (!unqueue_me(&q)) + goto out; + ret = -ETIMEDOUT; + if (to && !to->task) + goto out; + + /* + * We expect signal_pending(current), but we might be the + * victim of a spurious wakeup as well. + */ + if (!signal_pending(current)) + goto retry; + + ret = -ERESTARTSYS; + if (!abs_time) + goto out; + + restart = ¤t->restart_block; + restart->fn = futex_wait_restart; + restart->futex.uaddr = uaddr; + restart->futex.val = val; + restart->futex.time = abs_time->tv64; + restart->futex.bitset = bitset; + restart->futex.flags = flags | FLAGS_HAS_TIMEOUT; + + ret = -ERESTART_RESTARTBLOCK; + +out: + if (to) { + hrtimer_cancel(&to->timer); + destroy_hrtimer_on_stack(&to->timer); + } + return ret; +} + + +static long futex_wait_restart(struct restart_block *restart) +{ + u32 __user *uaddr = restart->futex.uaddr; + ktime_t t, *tp = NULL; + + if (restart->futex.flags & FLAGS_HAS_TIMEOUT) { + t.tv64 = restart->futex.time; + tp = &t; + } + restart->fn = do_no_restart_syscall; + + return (long)futex_wait(uaddr, restart->futex.flags, + restart->futex.val, tp, restart->futex.bitset); +} + + +/* + * Userspace tried a 0 -> TID atomic transition of the futex value + * and failed. The kernel side here does the whole locking operation: + * if there are waiters then it will block, it does PI, etc. (Due to + * races the kernel might see a 0 value of the futex too.) + */ +static int futex_lock_pi(u32 __user *uaddr, unsigned int flags, + ktime_t *time, int trylock) +{ + struct hrtimer_sleeper timeout, *to = NULL; + struct futex_hash_bucket *hb; + struct futex_q q = futex_q_init; + int res, ret; + + if (refill_pi_state_cache()) + return -ENOMEM; + + if (time) { + to = &timeout; + hrtimer_init_on_stack(&to->timer, CLOCK_REALTIME, + HRTIMER_MODE_ABS); + hrtimer_init_sleeper(to, current); + hrtimer_set_expires(&to->timer, *time); + } + +retry: + ret = get_futex_key(uaddr, flags & FLAGS_SHARED, &q.key, VERIFY_WRITE); + if (unlikely(ret != 0)) + goto out; + +retry_private: + hb = queue_lock(&q); + + ret = futex_lock_pi_atomic(uaddr, hb, &q.key, &q.pi_state, current, 0); + if (unlikely(ret)) { + switch (ret) { + case 1: + /* We got the lock. */ + ret = 0; + goto out_unlock_put_key; + case -EFAULT: + goto uaddr_faulted; + case -EAGAIN: + /* + * Two reasons for this: + * - Task is exiting and we just wait for the + * exit to complete. + * - The user space value changed. + */ + queue_unlock(hb); + put_futex_key(&q.key); + cond_resched(); + goto retry; + default: + goto out_unlock_put_key; + } + } + + /* + * Only actually queue now that the atomic ops are done: + */ + queue_me(&q, hb); + + WARN_ON(!q.pi_state); + /* + * Block on the PI mutex: + */ + if (!trylock) { + ret = rt_mutex_timed_futex_lock(&q.pi_state->pi_mutex, to); + } else { + ret = rt_mutex_trylock(&q.pi_state->pi_mutex); + /* Fixup the trylock return value: */ + ret = ret ? 0 : -EWOULDBLOCK; + } + + spin_lock(q.lock_ptr); + /* + * Fixup the pi_state owner and possibly acquire the lock if we + * haven't already. + */ + res = fixup_owner(uaddr, &q, !ret); + /* + * If fixup_owner() returned an error, proprogate that. If it acquired + * the lock, clear our -ETIMEDOUT or -EINTR. + */ + if (res) + ret = (res < 0) ? res : 0; + + /* + * If fixup_owner() faulted and was unable to handle the fault, unlock + * it and return the fault to userspace. + */ + if (ret && (rt_mutex_owner(&q.pi_state->pi_mutex) == current)) + rt_mutex_unlock(&q.pi_state->pi_mutex); + + /* Unqueue and drop the lock */ + unqueue_me_pi(&q); + + goto out_put_key; + +out_unlock_put_key: + queue_unlock(hb); + +out_put_key: + put_futex_key(&q.key); +out: + if (to) + destroy_hrtimer_on_stack(&to->timer); + return ret != -EINTR ? ret : -ERESTARTNOINTR; + +uaddr_faulted: + queue_unlock(hb); + + ret = fault_in_user_writeable(uaddr); + if (ret) + goto out_put_key; + + if (!(flags & FLAGS_SHARED)) + goto retry_private; + + put_futex_key(&q.key); + goto retry; +} + +/* + * Userspace attempted a TID -> 0 atomic transition, and failed. + * This is the in-kernel slowpath: we look up the PI state (if any), + * and do the rt-mutex unlock. + */ +static int futex_unlock_pi(u32 __user *uaddr, unsigned int flags) +{ + u32 uninitialized_var(curval), uval, vpid = task_pid_vnr(current); + union futex_key key = FUTEX_KEY_INIT; + struct futex_hash_bucket *hb; + struct futex_q *match; + int ret; + +retry: + if (get_user(uval, uaddr)) + return -EFAULT; + /* + * We release only a lock we actually own: + */ + if ((uval & FUTEX_TID_MASK) != vpid) + return -EPERM; + + ret = get_futex_key(uaddr, flags & FLAGS_SHARED, &key, VERIFY_WRITE); + if (ret) + return ret; + + hb = hash_futex(&key); + spin_lock(&hb->lock); + + /* + * Check waiters first. We do not trust user space values at + * all and we at least want to know if user space fiddled + * with the futex value instead of blindly unlocking. + */ + match = futex_top_waiter(hb, &key); + if (match) { + ret = wake_futex_pi(uaddr, uval, match, hb); + + /* + * In case of success wake_futex_pi dropped the hash + * bucket lock. + */ + if (!ret) + goto out_putkey; + + /* + * The atomic access to the futex value generated a + * pagefault, so retry the user-access and the wakeup: + */ + if (ret == -EFAULT) + goto pi_faulted; + + /* + * wake_futex_pi has detected invalid state. Tell user + * space. + */ + goto out_unlock; + } + + /* + * We have no kernel internal state, i.e. no waiters in the + * kernel. Waiters which are about to queue themselves are stuck + * on hb->lock. So we can safely ignore them. We do neither + * preserve the WAITERS bit not the OWNER_DIED one. We are the + * owner. + */ + if (cmpxchg_futex_value_locked(&curval, uaddr, uval, 0)) + goto pi_faulted; + + /* + * If uval has changed, let user space handle it. + */ + ret = (curval == uval) ? 0 : -EAGAIN; + +out_unlock: + spin_unlock(&hb->lock); +out_putkey: + put_futex_key(&key); + return ret; + +pi_faulted: + spin_unlock(&hb->lock); + put_futex_key(&key); + + ret = fault_in_user_writeable(uaddr); + if (!ret) + goto retry; + + return ret; +} + +/** + * handle_early_requeue_pi_wakeup() - Detect early wakeup on the initial futex + * @hb: the hash_bucket futex_q was original enqueued on + * @q: the futex_q woken while waiting to be requeued + * @key2: the futex_key of the requeue target futex + * @timeout: the timeout associated with the wait (NULL if none) + * + * Detect if the task was woken on the initial futex as opposed to the requeue + * target futex. If so, determine if it was a timeout or a signal that caused + * the wakeup and return the appropriate error code to the caller. Must be + * called with the hb lock held. + * + * Return: + * 0 = no early wakeup detected; + * <0 = -ETIMEDOUT or -ERESTARTNOINTR + */ +static inline +int handle_early_requeue_pi_wakeup(struct futex_hash_bucket *hb, + struct futex_q *q, union futex_key *key2, + struct hrtimer_sleeper *timeout) +{ + int ret = 0; + + /* + * With the hb lock held, we avoid races while we process the wakeup. + * We only need to hold hb (and not hb2) to ensure atomicity as the + * wakeup code can't change q.key from uaddr to uaddr2 if we hold hb. + * It can't be requeued from uaddr2 to something else since we don't + * support a PI aware source futex for requeue. + */ + if (!match_futex(&q->key, key2)) { + WARN_ON(q->lock_ptr && (&hb->lock != q->lock_ptr)); + /* + * We were woken prior to requeue by a timeout or a signal. + * Unqueue the futex_q and determine which it was. + */ + plist_del(&q->list, &hb->chain); + hb_waiters_dec(hb); + + /* Handle spurious wakeups gracefully */ + ret = -EWOULDBLOCK; + if (timeout && !timeout->task) + ret = -ETIMEDOUT; + else if (signal_pending(current)) + ret = -ERESTARTNOINTR; + } + return ret; +} + +/** + * futex_wait_requeue_pi() - Wait on uaddr and take uaddr2 + * @uaddr: the futex we initially wait on (non-pi) + * @flags: futex flags (FLAGS_SHARED, FLAGS_CLOCKRT, etc.), they must be + * the same type, no requeueing from private to shared, etc. + * @val: the expected value of uaddr + * @abs_time: absolute timeout + * @bitset: 32 bit wakeup bitset set by userspace, defaults to all + * @uaddr2: the pi futex we will take prior to returning to user-space + * + * The caller will wait on uaddr and will be requeued by futex_requeue() to + * uaddr2 which must be PI aware and unique from uaddr. Normal wakeup will wake + * on uaddr2 and complete the acquisition of the rt_mutex prior to returning to + * userspace. This ensures the rt_mutex maintains an owner when it has waiters; + * without one, the pi logic would not know which task to boost/deboost, if + * there was a need to. + * + * We call schedule in futex_wait_queue_me() when we enqueue and return there + * via the following-- + * 1) wakeup on uaddr2 after an atomic lock acquisition by futex_requeue() + * 2) wakeup on uaddr2 after a requeue + * 3) signal + * 4) timeout + * + * If 3, cleanup and return -ERESTARTNOINTR. + * + * If 2, we may then block on trying to take the rt_mutex and return via: + * 5) successful lock + * 6) signal + * 7) timeout + * 8) other lock acquisition failure + * + * If 6, return -EWOULDBLOCK (restarting the syscall would do the same). + * + * If 4 or 7, we cleanup and return with -ETIMEDOUT. + * + * Return: + * 0 - On success; + * <0 - On error + */ +static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, + u32 val, ktime_t *abs_time, u32 bitset, + u32 __user *uaddr2) +{ + struct hrtimer_sleeper timeout, *to = NULL; + struct rt_mutex_waiter rt_waiter; + struct rt_mutex *pi_mutex = NULL; + struct futex_hash_bucket *hb, *hb2; + union futex_key key2 = FUTEX_KEY_INIT; + struct futex_q q = futex_q_init; + int res, ret; + + if (uaddr == uaddr2) + return -EINVAL; + + if (!bitset) + return -EINVAL; + + if (abs_time) { + to = &timeout; + hrtimer_init_on_stack(&to->timer, (flags & FLAGS_CLOCKRT) ? + CLOCK_REALTIME : CLOCK_MONOTONIC, + HRTIMER_MODE_ABS); + hrtimer_init_sleeper(to, current); + hrtimer_set_expires_range_ns(&to->timer, *abs_time, + current->timer_slack_ns); + } + + /* + * The waiter is allocated on our stack, manipulated by the requeue + * code while we sleep on uaddr. + */ + rt_mutex_init_waiter(&rt_waiter, false); + + ret = get_futex_key(uaddr2, flags & FLAGS_SHARED, &key2, VERIFY_WRITE); + if (unlikely(ret != 0)) + goto out; + + q.bitset = bitset; + q.rt_waiter = &rt_waiter; + q.requeue_pi_key = &key2; + + /* + * Prepare to wait on uaddr. On success, increments q.key (key1) ref + * count. + */ + ret = futex_wait_setup(uaddr, val, flags, &q, &hb); + if (ret) + goto out_key2; + + /* + * The check above which compares uaddrs is not sufficient for + * shared futexes. We need to compare the keys: + */ + if (match_futex(&q.key, &key2)) { + queue_unlock(hb); + ret = -EINVAL; + goto out_put_keys; + } + + /* Queue the futex_q, drop the hb lock, wait for wakeup. */ + futex_wait_queue_me(hb, &q, to); + + /* + * On RT we must avoid races with requeue and trying to block + * on two mutexes (hb->lock and uaddr2's rtmutex) by + * serializing access to pi_blocked_on with pi_lock. + */ + raw_spin_lock_irq(¤t->pi_lock); + if (current->pi_blocked_on) { + /* + * We have been requeued or are in the process of + * being requeued. + */ + raw_spin_unlock_irq(¤t->pi_lock); + } else { + /* + * Setting pi_blocked_on to PI_WAKEUP_INPROGRESS + * prevents a concurrent requeue from moving us to the + * uaddr2 rtmutex. After that we can safely acquire + * (and possibly block on) hb->lock. + */ + current->pi_blocked_on = PI_WAKEUP_INPROGRESS; + raw_spin_unlock_irq(¤t->pi_lock); + + spin_lock(&hb->lock); + + /* + * Clean up pi_blocked_on. We might leak it otherwise + * when we succeeded with the hb->lock in the fast + * path. + */ + raw_spin_lock_irq(¤t->pi_lock); + current->pi_blocked_on = NULL; + raw_spin_unlock_irq(¤t->pi_lock); + + ret = handle_early_requeue_pi_wakeup(hb, &q, &key2, to); + spin_unlock(&hb->lock); + if (ret) + goto out_put_keys; + } + + /* + * In order to be here, we have either been requeued, are in + * the process of being requeued, or requeue successfully + * acquired uaddr2 on our behalf. If pi_blocked_on was + * non-null above, we may be racing with a requeue. Do not + * rely on q->lock_ptr to be hb2->lock until after blocking on + * hb->lock or hb2->lock. The futex_requeue dropped our key1 + * reference and incremented our key2 reference count. + */ + hb2 = hash_futex(&key2); + + /* Check if the requeue code acquired the second futex for us. */ + if (!q.rt_waiter) { + /* + * Got the lock. We might not be the anticipated owner if we + * did a lock-steal - fix up the PI-state in that case. + */ + if (q.pi_state && (q.pi_state->owner != current)) { + spin_lock(&hb2->lock); + BUG_ON(&hb2->lock != q.lock_ptr); + ret = fixup_pi_state_owner(uaddr2, &q, current); + spin_unlock(&hb2->lock); + } + } else { + /* + * We have been woken up by futex_unlock_pi(), a timeout, or a + * signal. futex_unlock_pi() will not destroy the lock_ptr nor + * the pi_state. + */ + WARN_ON(!q.pi_state); + pi_mutex = &q.pi_state->pi_mutex; + ret = rt_mutex_finish_proxy_lock(pi_mutex, to, &rt_waiter); + debug_rt_mutex_free_waiter(&rt_waiter); + + spin_lock(&hb2->lock); + BUG_ON(&hb2->lock != q.lock_ptr); + /* + * Fixup the pi_state owner and possibly acquire the lock if we + * haven't already. + */ + res = fixup_owner(uaddr2, &q, !ret); + /* + * If fixup_owner() returned an error, proprogate that. If it + * acquired the lock, clear -ETIMEDOUT or -EINTR. + */ + if (res) + ret = (res < 0) ? res : 0; + + /* Unqueue and drop the lock. */ + unqueue_me_pi(&q); + } + + /* + * If fixup_pi_state_owner() faulted and was unable to handle the + * fault, unlock the rt_mutex and return the fault to userspace. + */ + if (ret == -EFAULT) { + if (pi_mutex && rt_mutex_owner(pi_mutex) == current) + rt_mutex_unlock(pi_mutex); + } else if (ret == -EINTR) { + /* + * We've already been requeued, but cannot restart by calling + * futex_lock_pi() directly. We could restart this syscall, but + * it would detect that the user space "val" changed and return + * -EWOULDBLOCK. Save the overhead of the restart and return + * -EWOULDBLOCK directly. + */ + ret = -EWOULDBLOCK; + } + +out_put_keys: + put_futex_key(&q.key); +out_key2: + put_futex_key(&key2); + +out: + if (to) { + hrtimer_cancel(&to->timer); + destroy_hrtimer_on_stack(&to->timer); + } + return ret; +} + +/* + * Support for robust futexes: the kernel cleans up held futexes at + * thread exit time. + * + * Implementation: user-space maintains a per-thread list of locks it + * is holding. Upon do_exit(), the kernel carefully walks this list, + * and marks all locks that are owned by this thread with the + * FUTEX_OWNER_DIED bit, and wakes up a waiter (if any). The list is + * always manipulated with the lock held, so the list is private and + * per-thread. Userspace also maintains a per-thread 'list_op_pending' + * field, to allow the kernel to clean up if the thread dies after + * acquiring the lock, but just before it could have added itself to + * the list. There can only be one such pending lock. + */ + +/** + * sys_set_robust_list() - Set the robust-futex list head of a task + * @head: pointer to the list-head + * @len: length of the list-head, as userspace expects + */ +SYSCALL_DEFINE2(set_robust_list, struct robust_list_head __user *, head, + size_t, len) +{ + if (!futex_cmpxchg_enabled) + return -ENOSYS; + /* + * The kernel knows only one size for now: + */ + if (unlikely(len != sizeof(*head))) + return -EINVAL; + + current->robust_list = head; + + return 0; +} + +/** + * sys_get_robust_list() - Get the robust-futex list head of a task + * @pid: pid of the process [zero for current task] + * @head_ptr: pointer to a list-head pointer, the kernel fills it in + * @len_ptr: pointer to a length field, the kernel fills in the header size + */ +SYSCALL_DEFINE3(get_robust_list, int, pid, + struct robust_list_head __user * __user *, head_ptr, + size_t __user *, len_ptr) +{ + struct robust_list_head __user *head; + unsigned long ret; + struct task_struct *p; + + if (!futex_cmpxchg_enabled) + return -ENOSYS; + + rcu_read_lock(); + + ret = -ESRCH; + if (!pid) + p = current; + else { + p = find_task_by_vpid(pid); + if (!p) + goto err_unlock; + } + + ret = -EPERM; + if (!ptrace_may_access(p, PTRACE_MODE_READ)) + goto err_unlock; + + head = p->robust_list; + rcu_read_unlock(); + + if (put_user(sizeof(*head), len_ptr)) + return -EFAULT; + return put_user(head, head_ptr); + +err_unlock: + rcu_read_unlock(); + + return ret; +} + +/* + * Process a futex-list entry, check whether it's owned by the + * dying task, and do notification if so: + */ +int handle_futex_death(u32 __user *uaddr, struct task_struct *curr, int pi) +{ + u32 uval, uninitialized_var(nval), mval; + +retry: + if (get_user(uval, uaddr)) + return -1; + + if ((uval & FUTEX_TID_MASK) == task_pid_vnr(curr)) { + /* + * Ok, this dying thread is truly holding a futex + * of interest. Set the OWNER_DIED bit atomically + * via cmpxchg, and if the value had FUTEX_WAITERS + * set, wake up a waiter (if any). (We have to do a + * futex_wake() even if OWNER_DIED is already set - + * to handle the rare but possible case of recursive + * thread-death.) The rest of the cleanup is done in + * userspace. + */ + mval = (uval & FUTEX_WAITERS) | FUTEX_OWNER_DIED; + /* + * We are not holding a lock here, but we want to have + * the pagefault_disable/enable() protection because + * we want to handle the fault gracefully. If the + * access fails we try to fault in the futex with R/W + * verification via get_user_pages. get_user() above + * does not guarantee R/W access. If that fails we + * give up and leave the futex locked. + */ + if (cmpxchg_futex_value_locked(&nval, uaddr, uval, mval)) { + if (fault_in_user_writeable(uaddr)) + return -1; + goto retry; + } + if (nval != uval) + goto retry; + + /* + * Wake robust non-PI futexes here. The wakeup of + * PI futexes happens in exit_pi_state(): + */ + if (!pi && (uval & FUTEX_WAITERS)) + futex_wake(uaddr, 1, 1, FUTEX_BITSET_MATCH_ANY); + } + return 0; +} + +/* + * Fetch a robust-list pointer. Bit 0 signals PI futexes: + */ +static inline int fetch_robust_entry(struct robust_list __user **entry, + struct robust_list __user * __user *head, + unsigned int *pi) +{ + unsigned long uentry; + + if (get_user(uentry, (unsigned long __user *)head)) + return -EFAULT; + + *entry = (void __user *)(uentry & ~1UL); + *pi = uentry & 1; + + return 0; +} + +/* + * Walk curr->robust_list (very carefully, it's a userspace list!) + * and mark any locks found there dead, and notify any waiters. + * + * We silently return on any sign of list-walking problem. + */ +void exit_robust_list(struct task_struct *curr) +{ + struct robust_list_head __user *head = curr->robust_list; + struct robust_list __user *entry, *next_entry, *pending; + unsigned int limit = ROBUST_LIST_LIMIT, pi, pip; + unsigned int uninitialized_var(next_pi); + unsigned long futex_offset; + int rc; + + if (!futex_cmpxchg_enabled) + return; + + /* + * Fetch the list head (which was registered earlier, via + * sys_set_robust_list()): + */ + if (fetch_robust_entry(&entry, &head->list.next, &pi)) + return; + /* + * Fetch the relative futex offset: + */ + if (get_user(futex_offset, &head->futex_offset)) + return; + /* + * Fetch any possibly pending lock-add first, and handle it + * if it exists: + */ + if (fetch_robust_entry(&pending, &head->list_op_pending, &pip)) + return; + + next_entry = NULL; /* avoid warning with gcc */ + while (entry != &head->list) { + /* + * Fetch the next entry in the list before calling + * handle_futex_death: + */ + rc = fetch_robust_entry(&next_entry, &entry->next, &next_pi); + /* + * A pending lock might already be on the list, so + * don't process it twice: + */ + if (entry != pending) + if (handle_futex_death((void __user *)entry + futex_offset, + curr, pi)) + return; + if (rc) + return; + entry = next_entry; + pi = next_pi; + /* + * Avoid excessively long or circular lists: + */ + if (!--limit) + break; + + cond_resched(); + } + + if (pending) + handle_futex_death((void __user *)pending + futex_offset, + curr, pip); +} + +long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout, + u32 __user *uaddr2, u32 val2, u32 val3) +{ + int cmd = op & FUTEX_CMD_MASK; + unsigned int flags = 0; + + if (!(op & FUTEX_PRIVATE_FLAG)) + flags |= FLAGS_SHARED; + + if (op & FUTEX_CLOCK_REALTIME) { + flags |= FLAGS_CLOCKRT; + if (cmd != FUTEX_WAIT_BITSET && cmd != FUTEX_WAIT_REQUEUE_PI) + return -ENOSYS; + } + + switch (cmd) { + case FUTEX_LOCK_PI: + case FUTEX_UNLOCK_PI: + case FUTEX_TRYLOCK_PI: + case FUTEX_WAIT_REQUEUE_PI: + case FUTEX_CMP_REQUEUE_PI: + if (!futex_cmpxchg_enabled) + return -ENOSYS; + } + + switch (cmd) { + case FUTEX_WAIT: + val3 = FUTEX_BITSET_MATCH_ANY; + case FUTEX_WAIT_BITSET: + return futex_wait(uaddr, flags, val, timeout, val3); + case FUTEX_WAKE: + val3 = FUTEX_BITSET_MATCH_ANY; + case FUTEX_WAKE_BITSET: + return futex_wake(uaddr, flags, val, val3); + case FUTEX_REQUEUE: + return futex_requeue(uaddr, flags, uaddr2, val, val2, NULL, 0); + case FUTEX_CMP_REQUEUE: + return futex_requeue(uaddr, flags, uaddr2, val, val2, &val3, 0); + case FUTEX_WAKE_OP: + return futex_wake_op(uaddr, flags, uaddr2, val, val2, val3); + case FUTEX_LOCK_PI: + return futex_lock_pi(uaddr, flags, timeout, 0); + case FUTEX_UNLOCK_PI: + return futex_unlock_pi(uaddr, flags); + case FUTEX_TRYLOCK_PI: + return futex_lock_pi(uaddr, flags, NULL, 1); + case FUTEX_WAIT_REQUEUE_PI: + val3 = FUTEX_BITSET_MATCH_ANY; + return futex_wait_requeue_pi(uaddr, flags, val, timeout, val3, + uaddr2); + case FUTEX_CMP_REQUEUE_PI: + return futex_requeue(uaddr, flags, uaddr2, val, val2, &val3, 1); + } + return -ENOSYS; +} + + +SYSCALL_DEFINE6(futex, u32 __user *, uaddr, int, op, u32, val, + struct timespec __user *, utime, u32 __user *, uaddr2, + u32, val3) +{ + struct timespec ts; + ktime_t t, *tp = NULL; + u32 val2 = 0; + int cmd = op & FUTEX_CMD_MASK; + + if (utime && (cmd == FUTEX_WAIT || cmd == FUTEX_LOCK_PI || + cmd == FUTEX_WAIT_BITSET || + cmd == FUTEX_WAIT_REQUEUE_PI)) { + if (copy_from_user(&ts, utime, sizeof(ts)) != 0) + return -EFAULT; + if (!timespec_valid(&ts)) + return -EINVAL; + + t = timespec_to_ktime(ts); + if (cmd == FUTEX_WAIT) + t = ktime_add_safe(ktime_get(), t); + tp = &t; + } + /* + * requeue parameter in 'utime' if cmd == FUTEX_*_REQUEUE_*. + * number of waiters to wake in 'utime' if cmd == FUTEX_WAKE_OP. + */ + if (cmd == FUTEX_REQUEUE || cmd == FUTEX_CMP_REQUEUE || + cmd == FUTEX_CMP_REQUEUE_PI || cmd == FUTEX_WAKE_OP) + val2 = (u32) (unsigned long) utime; + + return do_futex(uaddr, op, val, tp, uaddr2, val2, val3); +} + +static void __init futex_detect_cmpxchg(void) +{ +#ifndef CONFIG_HAVE_FUTEX_CMPXCHG + u32 curval; + + /* + * This will fail and we want it. Some arch implementations do + * runtime detection of the futex_atomic_cmpxchg_inatomic() + * functionality. We want to know that before we call in any + * of the complex code paths. Also we want to prevent + * registration of robust lists in that case. NULL is + * guaranteed to fault and we get -EFAULT on functional + * implementation, the non-functional ones will return + * -ENOSYS. + */ + if (cmpxchg_futex_value_locked(&curval, NULL, 0, 0) == -EFAULT) + futex_cmpxchg_enabled = 1; +#endif +} + +static int __init futex_init(void) +{ + unsigned int futex_shift; + unsigned long i; + +#if CONFIG_BASE_SMALL + futex_hashsize = 16; +#else + futex_hashsize = roundup_pow_of_two(256 * num_possible_cpus()); +#endif + + futex_queues = alloc_large_system_hash("futex", sizeof(*futex_queues), + futex_hashsize, 0, + futex_hashsize < 256 ? HASH_SMALL : 0, + &futex_shift, NULL, + futex_hashsize, futex_hashsize); + futex_hashsize = 1UL << futex_shift; + + futex_detect_cmpxchg(); + + for (i = 0; i < futex_hashsize; i++) { + atomic_set(&futex_queues[i].waiters, 0); + plist_head_init(&futex_queues[i].chain); + spin_lock_init(&futex_queues[i].lock); + } + + return 0; +} +__initcall(futex_init); diff --git a/kernel/kernel/futex_compat.c b/kernel/kernel/futex_compat.c new file mode 100644 index 000000000..55c8c9349 --- /dev/null +++ b/kernel/kernel/futex_compat.c @@ -0,0 +1,201 @@ +/* + * linux/kernel/futex_compat.c + * + * Futex compatibililty routines. + * + * Copyright 2006, Red Hat, Inc., Ingo Molnar + */ + +#include +#include +#include +#include +#include +#include + +#include + + +/* + * Fetch a robust-list pointer. Bit 0 signals PI futexes: + */ +static inline int +fetch_robust_entry(compat_uptr_t *uentry, struct robust_list __user **entry, + compat_uptr_t __user *head, unsigned int *pi) +{ + if (get_user(*uentry, head)) + return -EFAULT; + + *entry = compat_ptr((*uentry) & ~1); + *pi = (unsigned int)(*uentry) & 1; + + return 0; +} + +static void __user *futex_uaddr(struct robust_list __user *entry, + compat_long_t futex_offset) +{ + compat_uptr_t base = ptr_to_compat(entry); + void __user *uaddr = compat_ptr(base + futex_offset); + + return uaddr; +} + +/* + * Walk curr->robust_list (very carefully, it's a userspace list!) + * and mark any locks found there dead, and notify any waiters. + * + * We silently return on any sign of list-walking problem. + */ +void compat_exit_robust_list(struct task_struct *curr) +{ + struct compat_robust_list_head __user *head = curr->compat_robust_list; + struct robust_list __user *entry, *next_entry, *pending; + unsigned int limit = ROBUST_LIST_LIMIT, pi, pip; + unsigned int uninitialized_var(next_pi); + compat_uptr_t uentry, next_uentry, upending; + compat_long_t futex_offset; + int rc; + + if (!futex_cmpxchg_enabled) + return; + + /* + * Fetch the list head (which was registered earlier, via + * sys_set_robust_list()): + */ + if (fetch_robust_entry(&uentry, &entry, &head->list.next, &pi)) + return; + /* + * Fetch the relative futex offset: + */ + if (get_user(futex_offset, &head->futex_offset)) + return; + /* + * Fetch any possibly pending lock-add first, and handle it + * if it exists: + */ + if (fetch_robust_entry(&upending, &pending, + &head->list_op_pending, &pip)) + return; + + next_entry = NULL; /* avoid warning with gcc */ + while (entry != (struct robust_list __user *) &head->list) { + /* + * Fetch the next entry in the list before calling + * handle_futex_death: + */ + rc = fetch_robust_entry(&next_uentry, &next_entry, + (compat_uptr_t __user *)&entry->next, &next_pi); + /* + * A pending lock might already be on the list, so + * dont process it twice: + */ + if (entry != pending) { + void __user *uaddr = futex_uaddr(entry, futex_offset); + + if (handle_futex_death(uaddr, curr, pi)) + return; + } + if (rc) + return; + uentry = next_uentry; + entry = next_entry; + pi = next_pi; + /* + * Avoid excessively long or circular lists: + */ + if (!--limit) + break; + + cond_resched(); + } + if (pending) { + void __user *uaddr = futex_uaddr(pending, futex_offset); + + handle_futex_death(uaddr, curr, pip); + } +} + +COMPAT_SYSCALL_DEFINE2(set_robust_list, + struct compat_robust_list_head __user *, head, + compat_size_t, len) +{ + if (!futex_cmpxchg_enabled) + return -ENOSYS; + + if (unlikely(len != sizeof(*head))) + return -EINVAL; + + current->compat_robust_list = head; + + return 0; +} + +COMPAT_SYSCALL_DEFINE3(get_robust_list, int, pid, + compat_uptr_t __user *, head_ptr, + compat_size_t __user *, len_ptr) +{ + struct compat_robust_list_head __user *head; + unsigned long ret; + struct task_struct *p; + + if (!futex_cmpxchg_enabled) + return -ENOSYS; + + rcu_read_lock(); + + ret = -ESRCH; + if (!pid) + p = current; + else { + p = find_task_by_vpid(pid); + if (!p) + goto err_unlock; + } + + ret = -EPERM; + if (!ptrace_may_access(p, PTRACE_MODE_READ)) + goto err_unlock; + + head = p->compat_robust_list; + rcu_read_unlock(); + + if (put_user(sizeof(*head), len_ptr)) + return -EFAULT; + return put_user(ptr_to_compat(head), head_ptr); + +err_unlock: + rcu_read_unlock(); + + return ret; +} + +COMPAT_SYSCALL_DEFINE6(futex, u32 __user *, uaddr, int, op, u32, val, + struct compat_timespec __user *, utime, u32 __user *, uaddr2, + u32, val3) +{ + struct timespec ts; + ktime_t t, *tp = NULL; + int val2 = 0; + int cmd = op & FUTEX_CMD_MASK; + + if (utime && (cmd == FUTEX_WAIT || cmd == FUTEX_LOCK_PI || + cmd == FUTEX_WAIT_BITSET || + cmd == FUTEX_WAIT_REQUEUE_PI)) { + if (compat_get_timespec(&ts, utime)) + return -EFAULT; + if (!timespec_valid(&ts)) + return -EINVAL; + + t = timespec_to_ktime(ts); + if (cmd == FUTEX_WAIT) + t = ktime_add_safe(ktime_get(), t); + tp = &t; + } + if (cmd == FUTEX_REQUEUE || cmd == FUTEX_CMP_REQUEUE || + cmd == FUTEX_CMP_REQUEUE_PI || cmd == FUTEX_WAKE_OP) + val2 = (int) (unsigned long) utime; + + return do_futex(uaddr, op, val, tp, uaddr2, val2, val3); +} diff --git a/kernel/kernel/gcov/Kconfig b/kernel/kernel/gcov/Kconfig new file mode 100644 index 000000000..c92e44855 --- /dev/null +++ b/kernel/kernel/gcov/Kconfig @@ -0,0 +1,82 @@ +menu "GCOV-based kernel profiling" + +config GCOV_KERNEL + bool "Enable gcov-based kernel profiling" + depends on DEBUG_FS + select CONSTRUCTORS if !UML + default n + ---help--- + This option enables gcov-based code profiling (e.g. for code coverage + measurements). + + If unsure, say N. + + Additionally specify CONFIG_GCOV_PROFILE_ALL=y to get profiling data + for the entire kernel. To enable profiling for specific files or + directories, add a line similar to the following to the respective + Makefile: + + For a single file (e.g. main.o): + GCOV_PROFILE_main.o := y + + For all files in one directory: + GCOV_PROFILE := y + + To exclude files from being profiled even when CONFIG_GCOV_PROFILE_ALL + is specified, use: + + GCOV_PROFILE_main.o := n + and: + GCOV_PROFILE := n + + Note that the debugfs filesystem has to be mounted to access + profiling data. + +config ARCH_HAS_GCOV_PROFILE_ALL + def_bool n + +config GCOV_PROFILE_ALL + bool "Profile entire Kernel" + depends on GCOV_KERNEL + depends on ARCH_HAS_GCOV_PROFILE_ALL + default n + ---help--- + This options activates profiling for the entire kernel. + + If unsure, say N. + + Note that a kernel compiled with profiling flags will be significantly + larger and run slower. Also be sure to exclude files from profiling + which are not linked to the kernel image to prevent linker errors. + +choice + prompt "Specify GCOV format" + depends on GCOV_KERNEL + default GCOV_FORMAT_AUTODETECT + ---help--- + The gcov format is usually determined by the GCC version, but there are + exceptions where format changes are integrated in lower-version GCCs. + In such a case use this option to adjust the format used in the kernel + accordingly. + + If unsure, choose "Autodetect". + +config GCOV_FORMAT_AUTODETECT + bool "Autodetect" + ---help--- + Select this option to use the format that corresponds to your GCC + version. + +config GCOV_FORMAT_3_4 + bool "GCC 3.4 format" + ---help--- + Select this option to use the format defined by GCC 3.4. + +config GCOV_FORMAT_4_7 + bool "GCC 4.7 format" + ---help--- + Select this option to use the format defined by GCC 4.7. + +endchoice + +endmenu diff --git a/kernel/kernel/gcov/Makefile b/kernel/kernel/gcov/Makefile new file mode 100644 index 000000000..752d6486b --- /dev/null +++ b/kernel/kernel/gcov/Makefile @@ -0,0 +1,7 @@ +ccflags-y := -DSRCTREE='"$(srctree)"' -DOBJTREE='"$(objtree)"' + +obj-y := base.o fs.o +obj-$(CONFIG_GCOV_FORMAT_3_4) += gcc_3_4.o +obj-$(CONFIG_GCOV_FORMAT_4_7) += gcc_4_7.o +obj-$(CONFIG_GCOV_FORMAT_AUTODETECT) += $(call cc-ifversion, -lt, 0407, \ + gcc_3_4.o, gcc_4_7.o) diff --git a/kernel/kernel/gcov/base.c b/kernel/kernel/gcov/base.c new file mode 100644 index 000000000..a744098e4 --- /dev/null +++ b/kernel/kernel/gcov/base.c @@ -0,0 +1,161 @@ +/* + * This code maintains a list of active profiling data structures. + * + * Copyright IBM Corp. 2009 + * Author(s): Peter Oberparleiter + * + * Uses gcc-internal data definitions. + * Based on the gcov-kernel patch by: + * Hubertus Franke + * Nigel Hinds + * Rajan Ravindran + * Peter Oberparleiter + * Paul Larson + */ + +#define pr_fmt(fmt) "gcov: " fmt + +#include +#include +#include +#include +#include "gcov.h" + +static int gcov_events_enabled; +static DEFINE_MUTEX(gcov_lock); + +/* + * __gcov_init is called by gcc-generated constructor code for each object + * file compiled with -fprofile-arcs. + */ +void __gcov_init(struct gcov_info *info) +{ + static unsigned int gcov_version; + + mutex_lock(&gcov_lock); + if (gcov_version == 0) { + gcov_version = gcov_info_version(info); + /* + * Printing gcc's version magic may prove useful for debugging + * incompatibility reports. + */ + pr_info("version magic: 0x%x\n", gcov_version); + } + /* + * Add new profiling data structure to list and inform event + * listener. + */ + gcov_info_link(info); + if (gcov_events_enabled) + gcov_event(GCOV_ADD, info); + mutex_unlock(&gcov_lock); +} +EXPORT_SYMBOL(__gcov_init); + +/* + * These functions may be referenced by gcc-generated profiling code but serve + * no function for kernel profiling. + */ +void __gcov_flush(void) +{ + /* Unused. */ +} +EXPORT_SYMBOL(__gcov_flush); + +void __gcov_merge_add(gcov_type *counters, unsigned int n_counters) +{ + /* Unused. */ +} +EXPORT_SYMBOL(__gcov_merge_add); + +void __gcov_merge_single(gcov_type *counters, unsigned int n_counters) +{ + /* Unused. */ +} +EXPORT_SYMBOL(__gcov_merge_single); + +void __gcov_merge_delta(gcov_type *counters, unsigned int n_counters) +{ + /* Unused. */ +} +EXPORT_SYMBOL(__gcov_merge_delta); + +void __gcov_merge_ior(gcov_type *counters, unsigned int n_counters) +{ + /* Unused. */ +} +EXPORT_SYMBOL(__gcov_merge_ior); + +void __gcov_merge_time_profile(gcov_type *counters, unsigned int n_counters) +{ + /* Unused. */ +} +EXPORT_SYMBOL(__gcov_merge_time_profile); + +/** + * gcov_enable_events - enable event reporting through gcov_event() + * + * Turn on reporting of profiling data load/unload-events through the + * gcov_event() callback. Also replay all previous events once. This function + * is needed because some events are potentially generated too early for the + * callback implementation to handle them initially. + */ +void gcov_enable_events(void) +{ + struct gcov_info *info = NULL; + + mutex_lock(&gcov_lock); + gcov_events_enabled = 1; + + /* Perform event callback for previously registered entries. */ + while ((info = gcov_info_next(info))) { + gcov_event(GCOV_ADD, info); + cond_resched(); + } + + mutex_unlock(&gcov_lock); +} + +#ifdef CONFIG_MODULES +static inline int within(void *addr, void *start, unsigned long size) +{ + return ((addr >= start) && (addr < start + size)); +} + +/* Update list and generate events when modules are unloaded. */ +static int gcov_module_notifier(struct notifier_block *nb, unsigned long event, + void *data) +{ + struct module *mod = data; + struct gcov_info *info = NULL; + struct gcov_info *prev = NULL; + + if (event != MODULE_STATE_GOING) + return NOTIFY_OK; + mutex_lock(&gcov_lock); + + /* Remove entries located in module from linked list. */ + while ((info = gcov_info_next(info))) { + if (within(info, mod->module_core, mod->core_size)) { + gcov_info_unlink(prev, info); + if (gcov_events_enabled) + gcov_event(GCOV_REMOVE, info); + } else + prev = info; + } + + mutex_unlock(&gcov_lock); + + return NOTIFY_OK; +} + +static struct notifier_block gcov_nb = { + .notifier_call = gcov_module_notifier, +}; + +static int __init gcov_init(void) +{ + return register_module_notifier(&gcov_nb); +} +device_initcall(gcov_init); +#endif /* CONFIG_MODULES */ diff --git a/kernel/kernel/gcov/fs.c b/kernel/kernel/gcov/fs.c new file mode 100644 index 000000000..edf67c493 --- /dev/null +++ b/kernel/kernel/gcov/fs.c @@ -0,0 +1,791 @@ +/* + * This code exports profiling data as debugfs files to userspace. + * + * Copyright IBM Corp. 2009 + * Author(s): Peter Oberparleiter + * + * Uses gcc-internal data definitions. + * Based on the gcov-kernel patch by: + * Hubertus Franke + * Nigel Hinds + * Rajan Ravindran + * Peter Oberparleiter + * Paul Larson + * Yi CDL Yang + */ + +#define pr_fmt(fmt) "gcov: " fmt + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include "gcov.h" + +/** + * struct gcov_node - represents a debugfs entry + * @list: list head for child node list + * @children: child nodes + * @all: list head for list of all nodes + * @parent: parent node + * @loaded_info: array of pointers to profiling data sets for loaded object + * files. + * @num_loaded: number of profiling data sets for loaded object files. + * @unloaded_info: accumulated copy of profiling data sets for unloaded + * object files. Used only when gcov_persist=1. + * @dentry: main debugfs entry, either a directory or data file + * @links: associated symbolic links + * @name: data file basename + * + * struct gcov_node represents an entity within the gcov/ subdirectory + * of debugfs. There are directory and data file nodes. The latter represent + * the actual synthesized data file plus any associated symbolic links which + * are needed by the gcov tool to work correctly. + */ +struct gcov_node { + struct list_head list; + struct list_head children; + struct list_head all; + struct gcov_node *parent; + struct gcov_info **loaded_info; + struct gcov_info *unloaded_info; + struct dentry *dentry; + struct dentry **links; + int num_loaded; + char name[0]; +}; + +static const char objtree[] = OBJTREE; +static const char srctree[] = SRCTREE; +static struct gcov_node root_node; +static struct dentry *reset_dentry; +static LIST_HEAD(all_head); +static DEFINE_MUTEX(node_lock); + +/* If non-zero, keep copies of profiling data for unloaded modules. */ +static int gcov_persist = 1; + +static int __init gcov_persist_setup(char *str) +{ + unsigned long val; + + if (kstrtoul(str, 0, &val)) { + pr_warn("invalid gcov_persist parameter '%s'\n", str); + return 0; + } + gcov_persist = val; + pr_info("setting gcov_persist to %d\n", gcov_persist); + + return 1; +} +__setup("gcov_persist=", gcov_persist_setup); + +/* + * seq_file.start() implementation for gcov data files. Note that the + * gcov_iterator interface is designed to be more restrictive than seq_file + * (no start from arbitrary position, etc.), to simplify the iterator + * implementation. + */ +static void *gcov_seq_start(struct seq_file *seq, loff_t *pos) +{ + loff_t i; + + gcov_iter_start(seq->private); + for (i = 0; i < *pos; i++) { + if (gcov_iter_next(seq->private)) + return NULL; + } + return seq->private; +} + +/* seq_file.next() implementation for gcov data files. */ +static void *gcov_seq_next(struct seq_file *seq, void *data, loff_t *pos) +{ + struct gcov_iterator *iter = data; + + if (gcov_iter_next(iter)) + return NULL; + (*pos)++; + + return iter; +} + +/* seq_file.show() implementation for gcov data files. */ +static int gcov_seq_show(struct seq_file *seq, void *data) +{ + struct gcov_iterator *iter = data; + + if (gcov_iter_write(iter, seq)) + return -EINVAL; + return 0; +} + +static void gcov_seq_stop(struct seq_file *seq, void *data) +{ + /* Unused. */ +} + +static const struct seq_operations gcov_seq_ops = { + .start = gcov_seq_start, + .next = gcov_seq_next, + .show = gcov_seq_show, + .stop = gcov_seq_stop, +}; + +/* + * Return a profiling data set associated with the given node. This is + * either a data set for a loaded object file or a data set copy in case + * all associated object files have been unloaded. + */ +static struct gcov_info *get_node_info(struct gcov_node *node) +{ + if (node->num_loaded > 0) + return node->loaded_info[0]; + + return node->unloaded_info; +} + +/* + * Return a newly allocated profiling data set which contains the sum of + * all profiling data associated with the given node. + */ +static struct gcov_info *get_accumulated_info(struct gcov_node *node) +{ + struct gcov_info *info; + int i = 0; + + if (node->unloaded_info) + info = gcov_info_dup(node->unloaded_info); + else + info = gcov_info_dup(node->loaded_info[i++]); + if (!info) + return NULL; + for (; i < node->num_loaded; i++) + gcov_info_add(info, node->loaded_info[i]); + + return info; +} + +/* + * open() implementation for gcov data files. Create a copy of the profiling + * data set and initialize the iterator and seq_file interface. + */ +static int gcov_seq_open(struct inode *inode, struct file *file) +{ + struct gcov_node *node = inode->i_private; + struct gcov_iterator *iter; + struct seq_file *seq; + struct gcov_info *info; + int rc = -ENOMEM; + + mutex_lock(&node_lock); + /* + * Read from a profiling data copy to minimize reference tracking + * complexity and concurrent access and to keep accumulating multiple + * profiling data sets associated with one node simple. + */ + info = get_accumulated_info(node); + if (!info) + goto out_unlock; + iter = gcov_iter_new(info); + if (!iter) + goto err_free_info; + rc = seq_open(file, &gcov_seq_ops); + if (rc) + goto err_free_iter_info; + seq = file->private_data; + seq->private = iter; +out_unlock: + mutex_unlock(&node_lock); + return rc; + +err_free_iter_info: + gcov_iter_free(iter); +err_free_info: + gcov_info_free(info); + goto out_unlock; +} + +/* + * release() implementation for gcov data files. Release resources allocated + * by open(). + */ +static int gcov_seq_release(struct inode *inode, struct file *file) +{ + struct gcov_iterator *iter; + struct gcov_info *info; + struct seq_file *seq; + + seq = file->private_data; + iter = seq->private; + info = gcov_iter_get_info(iter); + gcov_iter_free(iter); + gcov_info_free(info); + seq_release(inode, file); + + return 0; +} + +/* + * Find a node by the associated data file name. Needs to be called with + * node_lock held. + */ +static struct gcov_node *get_node_by_name(const char *name) +{ + struct gcov_node *node; + struct gcov_info *info; + + list_for_each_entry(node, &all_head, all) { + info = get_node_info(node); + if (info && (strcmp(gcov_info_filename(info), name) == 0)) + return node; + } + + return NULL; +} + +/* + * Reset all profiling data associated with the specified node. + */ +static void reset_node(struct gcov_node *node) +{ + int i; + + if (node->unloaded_info) + gcov_info_reset(node->unloaded_info); + for (i = 0; i < node->num_loaded; i++) + gcov_info_reset(node->loaded_info[i]); +} + +static void remove_node(struct gcov_node *node); + +/* + * write() implementation for gcov data files. Reset profiling data for the + * corresponding file. If all associated object files have been unloaded, + * remove the debug fs node as well. + */ +static ssize_t gcov_seq_write(struct file *file, const char __user *addr, + size_t len, loff_t *pos) +{ + struct seq_file *seq; + struct gcov_info *info; + struct gcov_node *node; + + seq = file->private_data; + info = gcov_iter_get_info(seq->private); + mutex_lock(&node_lock); + node = get_node_by_name(gcov_info_filename(info)); + if (node) { + /* Reset counts or remove node for unloaded modules. */ + if (node->num_loaded == 0) + remove_node(node); + else + reset_node(node); + } + /* Reset counts for open file. */ + gcov_info_reset(info); + mutex_unlock(&node_lock); + + return len; +} + +/* + * Given a string representing a file path of format: + * path/to/file.gcda + * construct and return a new string: + * path/to/file. + */ +static char *link_target(const char *dir, const char *path, const char *ext) +{ + char *target; + char *old_ext; + char *copy; + + copy = kstrdup(path, GFP_KERNEL); + if (!copy) + return NULL; + old_ext = strrchr(copy, '.'); + if (old_ext) + *old_ext = '\0'; + if (dir) + target = kasprintf(GFP_KERNEL, "%s/%s.%s", dir, copy, ext); + else + target = kasprintf(GFP_KERNEL, "%s.%s", copy, ext); + kfree(copy); + + return target; +} + +/* + * Construct a string representing the symbolic link target for the given + * gcov data file name and link type. Depending on the link type and the + * location of the data file, the link target can either point to a + * subdirectory of srctree, objtree or in an external location. + */ +static char *get_link_target(const char *filename, const struct gcov_link *ext) +{ + const char *rel; + char *result; + + if (strncmp(filename, objtree, strlen(objtree)) == 0) { + rel = filename + strlen(objtree) + 1; + if (ext->dir == SRC_TREE) + result = link_target(srctree, rel, ext->ext); + else + result = link_target(objtree, rel, ext->ext); + } else { + /* External compilation. */ + result = link_target(NULL, filename, ext->ext); + } + + return result; +} + +#define SKEW_PREFIX ".tmp_" + +/* + * For a filename .tmp_filename.ext return filename.ext. Needed to compensate + * for filename skewing caused by the mod-versioning mechanism. + */ +static const char *deskew(const char *basename) +{ + if (strncmp(basename, SKEW_PREFIX, sizeof(SKEW_PREFIX) - 1) == 0) + return basename + sizeof(SKEW_PREFIX) - 1; + return basename; +} + +/* + * Create links to additional files (usually .c and .gcno files) which the + * gcov tool expects to find in the same directory as the gcov data file. + */ +static void add_links(struct gcov_node *node, struct dentry *parent) +{ + const char *basename; + char *target; + int num; + int i; + + for (num = 0; gcov_link[num].ext; num++) + /* Nothing. */; + node->links = kcalloc(num, sizeof(struct dentry *), GFP_KERNEL); + if (!node->links) + return; + for (i = 0; i < num; i++) { + target = get_link_target( + gcov_info_filename(get_node_info(node)), + &gcov_link[i]); + if (!target) + goto out_err; + basename = kbasename(target); + if (basename == target) + goto out_err; + node->links[i] = debugfs_create_symlink(deskew(basename), + parent, target); + if (!node->links[i]) + goto out_err; + kfree(target); + } + + return; +out_err: + kfree(target); + while (i-- > 0) + debugfs_remove(node->links[i]); + kfree(node->links); + node->links = NULL; +} + +static const struct file_operations gcov_data_fops = { + .open = gcov_seq_open, + .release = gcov_seq_release, + .read = seq_read, + .llseek = seq_lseek, + .write = gcov_seq_write, +}; + +/* Basic initialization of a new node. */ +static void init_node(struct gcov_node *node, struct gcov_info *info, + const char *name, struct gcov_node *parent) +{ + INIT_LIST_HEAD(&node->list); + INIT_LIST_HEAD(&node->children); + INIT_LIST_HEAD(&node->all); + if (node->loaded_info) { + node->loaded_info[0] = info; + node->num_loaded = 1; + } + node->parent = parent; + if (name) + strcpy(node->name, name); +} + +/* + * Create a new node and associated debugfs entry. Needs to be called with + * node_lock held. + */ +static struct gcov_node *new_node(struct gcov_node *parent, + struct gcov_info *info, const char *name) +{ + struct gcov_node *node; + + node = kzalloc(sizeof(struct gcov_node) + strlen(name) + 1, GFP_KERNEL); + if (!node) + goto err_nomem; + if (info) { + node->loaded_info = kcalloc(1, sizeof(struct gcov_info *), + GFP_KERNEL); + if (!node->loaded_info) + goto err_nomem; + } + init_node(node, info, name, parent); + /* Differentiate between gcov data file nodes and directory nodes. */ + if (info) { + node->dentry = debugfs_create_file(deskew(node->name), 0600, + parent->dentry, node, &gcov_data_fops); + } else + node->dentry = debugfs_create_dir(node->name, parent->dentry); + if (!node->dentry) { + pr_warn("could not create file\n"); + kfree(node); + return NULL; + } + if (info) + add_links(node, parent->dentry); + list_add(&node->list, &parent->children); + list_add(&node->all, &all_head); + + return node; + +err_nomem: + kfree(node); + pr_warn("out of memory\n"); + return NULL; +} + +/* Remove symbolic links associated with node. */ +static void remove_links(struct gcov_node *node) +{ + int i; + + if (!node->links) + return; + for (i = 0; gcov_link[i].ext; i++) + debugfs_remove(node->links[i]); + kfree(node->links); + node->links = NULL; +} + +/* + * Remove node from all lists and debugfs and release associated resources. + * Needs to be called with node_lock held. + */ +static void release_node(struct gcov_node *node) +{ + list_del(&node->list); + list_del(&node->all); + debugfs_remove(node->dentry); + remove_links(node); + kfree(node->loaded_info); + if (node->unloaded_info) + gcov_info_free(node->unloaded_info); + kfree(node); +} + +/* Release node and empty parents. Needs to be called with node_lock held. */ +static void remove_node(struct gcov_node *node) +{ + struct gcov_node *parent; + + while ((node != &root_node) && list_empty(&node->children)) { + parent = node->parent; + release_node(node); + node = parent; + } +} + +/* + * Find child node with given basename. Needs to be called with node_lock + * held. + */ +static struct gcov_node *get_child_by_name(struct gcov_node *parent, + const char *name) +{ + struct gcov_node *node; + + list_for_each_entry(node, &parent->children, list) { + if (strcmp(node->name, name) == 0) + return node; + } + + return NULL; +} + +/* + * write() implementation for reset file. Reset all profiling data to zero + * and remove nodes for which all associated object files are unloaded. + */ +static ssize_t reset_write(struct file *file, const char __user *addr, + size_t len, loff_t *pos) +{ + struct gcov_node *node; + + mutex_lock(&node_lock); +restart: + list_for_each_entry(node, &all_head, all) { + if (node->num_loaded > 0) + reset_node(node); + else if (list_empty(&node->children)) { + remove_node(node); + /* Several nodes may have gone - restart loop. */ + goto restart; + } + } + mutex_unlock(&node_lock); + + return len; +} + +/* read() implementation for reset file. Unused. */ +static ssize_t reset_read(struct file *file, char __user *addr, size_t len, + loff_t *pos) +{ + /* Allow read operation so that a recursive copy won't fail. */ + return 0; +} + +static const struct file_operations gcov_reset_fops = { + .write = reset_write, + .read = reset_read, + .llseek = noop_llseek, +}; + +/* + * Create a node for a given profiling data set and add it to all lists and + * debugfs. Needs to be called with node_lock held. + */ +static void add_node(struct gcov_info *info) +{ + char *filename; + char *curr; + char *next; + struct gcov_node *parent; + struct gcov_node *node; + + filename = kstrdup(gcov_info_filename(info), GFP_KERNEL); + if (!filename) + return; + parent = &root_node; + /* Create directory nodes along the path. */ + for (curr = filename; (next = strchr(curr, '/')); curr = next + 1) { + if (curr == next) + continue; + *next = 0; + if (strcmp(curr, ".") == 0) + continue; + if (strcmp(curr, "..") == 0) { + if (!parent->parent) + goto err_remove; + parent = parent->parent; + continue; + } + node = get_child_by_name(parent, curr); + if (!node) { + node = new_node(parent, NULL, curr); + if (!node) + goto err_remove; + } + parent = node; + } + /* Create file node. */ + node = new_node(parent, info, curr); + if (!node) + goto err_remove; +out: + kfree(filename); + return; + +err_remove: + remove_node(parent); + goto out; +} + +/* + * Associate a profiling data set with an existing node. Needs to be called + * with node_lock held. + */ +static void add_info(struct gcov_node *node, struct gcov_info *info) +{ + struct gcov_info **loaded_info; + int num = node->num_loaded; + + /* + * Prepare new array. This is done first to simplify cleanup in + * case the new data set is incompatible, the node only contains + * unloaded data sets and there's not enough memory for the array. + */ + loaded_info = kcalloc(num + 1, sizeof(struct gcov_info *), GFP_KERNEL); + if (!loaded_info) { + pr_warn("could not add '%s' (out of memory)\n", + gcov_info_filename(info)); + return; + } + memcpy(loaded_info, node->loaded_info, + num * sizeof(struct gcov_info *)); + loaded_info[num] = info; + /* Check if the new data set is compatible. */ + if (num == 0) { + /* + * A module was unloaded, modified and reloaded. The new + * data set replaces the copy of the last one. + */ + if (!gcov_info_is_compatible(node->unloaded_info, info)) { + pr_warn("discarding saved data for %s " + "(incompatible version)\n", + gcov_info_filename(info)); + gcov_info_free(node->unloaded_info); + node->unloaded_info = NULL; + } + } else { + /* + * Two different versions of the same object file are loaded. + * The initial one takes precedence. + */ + if (!gcov_info_is_compatible(node->loaded_info[0], info)) { + pr_warn("could not add '%s' (incompatible " + "version)\n", gcov_info_filename(info)); + kfree(loaded_info); + return; + } + } + /* Overwrite previous array. */ + kfree(node->loaded_info); + node->loaded_info = loaded_info; + node->num_loaded = num + 1; +} + +/* + * Return the index of a profiling data set associated with a node. + */ +static int get_info_index(struct gcov_node *node, struct gcov_info *info) +{ + int i; + + for (i = 0; i < node->num_loaded; i++) { + if (node->loaded_info[i] == info) + return i; + } + return -ENOENT; +} + +/* + * Save the data of a profiling data set which is being unloaded. + */ +static void save_info(struct gcov_node *node, struct gcov_info *info) +{ + if (node->unloaded_info) + gcov_info_add(node->unloaded_info, info); + else { + node->unloaded_info = gcov_info_dup(info); + if (!node->unloaded_info) { + pr_warn("could not save data for '%s' " + "(out of memory)\n", + gcov_info_filename(info)); + } + } +} + +/* + * Disassociate a profiling data set from a node. Needs to be called with + * node_lock held. + */ +static void remove_info(struct gcov_node *node, struct gcov_info *info) +{ + int i; + + i = get_info_index(node, info); + if (i < 0) { + pr_warn("could not remove '%s' (not found)\n", + gcov_info_filename(info)); + return; + } + if (gcov_persist) + save_info(node, info); + /* Shrink array. */ + node->loaded_info[i] = node->loaded_info[node->num_loaded - 1]; + node->num_loaded--; + if (node->num_loaded > 0) + return; + /* Last loaded data set was removed. */ + kfree(node->loaded_info); + node->loaded_info = NULL; + node->num_loaded = 0; + if (!node->unloaded_info) + remove_node(node); +} + +/* + * Callback to create/remove profiling files when code compiled with + * -fprofile-arcs is loaded/unloaded. + */ +void gcov_event(enum gcov_action action, struct gcov_info *info) +{ + struct gcov_node *node; + + mutex_lock(&node_lock); + node = get_node_by_name(gcov_info_filename(info)); + switch (action) { + case GCOV_ADD: + if (node) + add_info(node, info); + else + add_node(info); + break; + case GCOV_REMOVE: + if (node) + remove_info(node, info); + else { + pr_warn("could not remove '%s' (not found)\n", + gcov_info_filename(info)); + } + break; + } + mutex_unlock(&node_lock); +} + +/* Create debugfs entries. */ +static __init int gcov_fs_init(void) +{ + int rc = -EIO; + + init_node(&root_node, NULL, NULL, NULL); + /* + * /sys/kernel/debug/gcov will be parent for the reset control file + * and all profiling files. + */ + root_node.dentry = debugfs_create_dir("gcov", NULL); + if (!root_node.dentry) + goto err_remove; + /* + * Create reset file which resets all profiling counts when written + * to. + */ + reset_dentry = debugfs_create_file("reset", 0600, root_node.dentry, + NULL, &gcov_reset_fops); + if (!reset_dentry) + goto err_remove; + /* Replay previous events to get our fs hierarchy up-to-date. */ + gcov_enable_events(); + return 0; + +err_remove: + pr_err("init failed\n"); + debugfs_remove(root_node.dentry); + + return rc; +} +device_initcall(gcov_fs_init); diff --git a/kernel/kernel/gcov/gcc_3_4.c b/kernel/kernel/gcov/gcc_3_4.c new file mode 100644 index 000000000..27bc88a35 --- /dev/null +++ b/kernel/kernel/gcov/gcc_3_4.c @@ -0,0 +1,562 @@ +/* + * This code provides functions to handle gcc's profiling data format + * introduced with gcc 3.4. Future versions of gcc may change the gcov + * format (as happened before), so all format-specific information needs + * to be kept modular and easily exchangeable. + * + * This file is based on gcc-internal definitions. Functions and data + * structures are defined to be compatible with gcc counterparts. + * For a better understanding, refer to gcc source: gcc/gcov-io.h. + * + * Copyright IBM Corp. 2009 + * Author(s): Peter Oberparleiter + * + * Uses gcc-internal data definitions. + */ + +#include +#include +#include +#include +#include +#include "gcov.h" + +#define GCOV_COUNTERS 5 + +static struct gcov_info *gcov_info_head; + +/** + * struct gcov_fn_info - profiling meta data per function + * @ident: object file-unique function identifier + * @checksum: function checksum + * @n_ctrs: number of values per counter type belonging to this function + * + * This data is generated by gcc during compilation and doesn't change + * at run-time. + */ +struct gcov_fn_info { + unsigned int ident; + unsigned int checksum; + unsigned int n_ctrs[0]; +}; + +/** + * struct gcov_ctr_info - profiling data per counter type + * @num: number of counter values for this type + * @values: array of counter values for this type + * @merge: merge function for counter values of this type (unused) + * + * This data is generated by gcc during compilation and doesn't change + * at run-time with the exception of the values array. + */ +struct gcov_ctr_info { + unsigned int num; + gcov_type *values; + void (*merge)(gcov_type *, unsigned int); +}; + +/** + * struct gcov_info - profiling data per object file + * @version: gcov version magic indicating the gcc version used for compilation + * @next: list head for a singly-linked list + * @stamp: time stamp + * @filename: name of the associated gcov data file + * @n_functions: number of instrumented functions + * @functions: function data + * @ctr_mask: mask specifying which counter types are active + * @counts: counter data per counter type + * + * This data is generated by gcc during compilation and doesn't change + * at run-time with the exception of the next pointer. + */ +struct gcov_info { + unsigned int version; + struct gcov_info *next; + unsigned int stamp; + const char *filename; + unsigned int n_functions; + const struct gcov_fn_info *functions; + unsigned int ctr_mask; + struct gcov_ctr_info counts[0]; +}; + +/** + * gcov_info_filename - return info filename + * @info: profiling data set + */ +const char *gcov_info_filename(struct gcov_info *info) +{ + return info->filename; +} + +/** + * gcov_info_version - return info version + * @info: profiling data set + */ +unsigned int gcov_info_version(struct gcov_info *info) +{ + return info->version; +} + +/** + * gcov_info_next - return next profiling data set + * @info: profiling data set + * + * Returns next gcov_info following @info or first gcov_info in the chain if + * @info is %NULL. + */ +struct gcov_info *gcov_info_next(struct gcov_info *info) +{ + if (!info) + return gcov_info_head; + + return info->next; +} + +/** + * gcov_info_link - link/add profiling data set to the list + * @info: profiling data set + */ +void gcov_info_link(struct gcov_info *info) +{ + info->next = gcov_info_head; + gcov_info_head = info; +} + +/** + * gcov_info_unlink - unlink/remove profiling data set from the list + * @prev: previous profiling data set + * @info: profiling data set + */ +void gcov_info_unlink(struct gcov_info *prev, struct gcov_info *info) +{ + if (prev) + prev->next = info->next; + else + gcov_info_head = info->next; +} + +/* Symbolic links to be created for each profiling data file. */ +const struct gcov_link gcov_link[] = { + { OBJ_TREE, "gcno" }, /* Link to .gcno file in $(objtree). */ + { 0, NULL}, +}; + +/* + * Determine whether a counter is active. Based on gcc magic. Doesn't change + * at run-time. + */ +static int counter_active(struct gcov_info *info, unsigned int type) +{ + return (1 << type) & info->ctr_mask; +} + +/* Determine number of active counters. Based on gcc magic. */ +static unsigned int num_counter_active(struct gcov_info *info) +{ + unsigned int i; + unsigned int result = 0; + + for (i = 0; i < GCOV_COUNTERS; i++) { + if (counter_active(info, i)) + result++; + } + return result; +} + +/** + * gcov_info_reset - reset profiling data to zero + * @info: profiling data set + */ +void gcov_info_reset(struct gcov_info *info) +{ + unsigned int active = num_counter_active(info); + unsigned int i; + + for (i = 0; i < active; i++) { + memset(info->counts[i].values, 0, + info->counts[i].num * sizeof(gcov_type)); + } +} + +/** + * gcov_info_is_compatible - check if profiling data can be added + * @info1: first profiling data set + * @info2: second profiling data set + * + * Returns non-zero if profiling data can be added, zero otherwise. + */ +int gcov_info_is_compatible(struct gcov_info *info1, struct gcov_info *info2) +{ + return (info1->stamp == info2->stamp); +} + +/** + * gcov_info_add - add up profiling data + * @dest: profiling data set to which data is added + * @source: profiling data set which is added + * + * Adds profiling counts of @source to @dest. + */ +void gcov_info_add(struct gcov_info *dest, struct gcov_info *source) +{ + unsigned int i; + unsigned int j; + + for (i = 0; i < num_counter_active(dest); i++) { + for (j = 0; j < dest->counts[i].num; j++) { + dest->counts[i].values[j] += + source->counts[i].values[j]; + } + } +} + +/* Get size of function info entry. Based on gcc magic. */ +static size_t get_fn_size(struct gcov_info *info) +{ + size_t size; + + size = sizeof(struct gcov_fn_info) + num_counter_active(info) * + sizeof(unsigned int); + if (__alignof__(struct gcov_fn_info) > sizeof(unsigned int)) + size = ALIGN(size, __alignof__(struct gcov_fn_info)); + return size; +} + +/* Get address of function info entry. Based on gcc magic. */ +static struct gcov_fn_info *get_fn_info(struct gcov_info *info, unsigned int fn) +{ + return (struct gcov_fn_info *) + ((char *) info->functions + fn * get_fn_size(info)); +} + +/** + * gcov_info_dup - duplicate profiling data set + * @info: profiling data set to duplicate + * + * Return newly allocated duplicate on success, %NULL on error. + */ +struct gcov_info *gcov_info_dup(struct gcov_info *info) +{ + struct gcov_info *dup; + unsigned int i; + unsigned int active; + + /* Duplicate gcov_info. */ + active = num_counter_active(info); + dup = kzalloc(sizeof(struct gcov_info) + + sizeof(struct gcov_ctr_info) * active, GFP_KERNEL); + if (!dup) + return NULL; + dup->version = info->version; + dup->stamp = info->stamp; + dup->n_functions = info->n_functions; + dup->ctr_mask = info->ctr_mask; + /* Duplicate filename. */ + dup->filename = kstrdup(info->filename, GFP_KERNEL); + if (!dup->filename) + goto err_free; + /* Duplicate table of functions. */ + dup->functions = kmemdup(info->functions, info->n_functions * + get_fn_size(info), GFP_KERNEL); + if (!dup->functions) + goto err_free; + /* Duplicate counter arrays. */ + for (i = 0; i < active ; i++) { + struct gcov_ctr_info *ctr = &info->counts[i]; + size_t size = ctr->num * sizeof(gcov_type); + + dup->counts[i].num = ctr->num; + dup->counts[i].merge = ctr->merge; + dup->counts[i].values = vmalloc(size); + if (!dup->counts[i].values) + goto err_free; + memcpy(dup->counts[i].values, ctr->values, size); + } + return dup; + +err_free: + gcov_info_free(dup); + return NULL; +} + +/** + * gcov_info_free - release memory for profiling data set duplicate + * @info: profiling data set duplicate to free + */ +void gcov_info_free(struct gcov_info *info) +{ + unsigned int active = num_counter_active(info); + unsigned int i; + + for (i = 0; i < active ; i++) + vfree(info->counts[i].values); + kfree(info->functions); + kfree(info->filename); + kfree(info); +} + +/** + * struct type_info - iterator helper array + * @ctr_type: counter type + * @offset: index of the first value of the current function for this type + * + * This array is needed to convert the in-memory data format into the in-file + * data format: + * + * In-memory: + * for each counter type + * for each function + * values + * + * In-file: + * for each function + * for each counter type + * values + * + * See gcc source gcc/gcov-io.h for more information on data organization. + */ +struct type_info { + int ctr_type; + unsigned int offset; +}; + +/** + * struct gcov_iterator - specifies current file position in logical records + * @info: associated profiling data + * @record: record type + * @function: function number + * @type: counter type + * @count: index into values array + * @num_types: number of counter types + * @type_info: helper array to get values-array offset for current function + */ +struct gcov_iterator { + struct gcov_info *info; + + int record; + unsigned int function; + unsigned int type; + unsigned int count; + + int num_types; + struct type_info type_info[0]; +}; + +static struct gcov_fn_info *get_func(struct gcov_iterator *iter) +{ + return get_fn_info(iter->info, iter->function); +} + +static struct type_info *get_type(struct gcov_iterator *iter) +{ + return &iter->type_info[iter->type]; +} + +/** + * gcov_iter_new - allocate and initialize profiling data iterator + * @info: profiling data set to be iterated + * + * Return file iterator on success, %NULL otherwise. + */ +struct gcov_iterator *gcov_iter_new(struct gcov_info *info) +{ + struct gcov_iterator *iter; + + iter = kzalloc(sizeof(struct gcov_iterator) + + num_counter_active(info) * sizeof(struct type_info), + GFP_KERNEL); + if (iter) + iter->info = info; + + return iter; +} + +/** + * gcov_iter_free - release memory for iterator + * @iter: file iterator to free + */ +void gcov_iter_free(struct gcov_iterator *iter) +{ + kfree(iter); +} + +/** + * gcov_iter_get_info - return profiling data set for given file iterator + * @iter: file iterator + */ +struct gcov_info *gcov_iter_get_info(struct gcov_iterator *iter) +{ + return iter->info; +} + +/** + * gcov_iter_start - reset file iterator to starting position + * @iter: file iterator + */ +void gcov_iter_start(struct gcov_iterator *iter) +{ + int i; + + iter->record = 0; + iter->function = 0; + iter->type = 0; + iter->count = 0; + iter->num_types = 0; + for (i = 0; i < GCOV_COUNTERS; i++) { + if (counter_active(iter->info, i)) { + iter->type_info[iter->num_types].ctr_type = i; + iter->type_info[iter->num_types++].offset = 0; + } + } +} + +/* Mapping of logical record number to actual file content. */ +#define RECORD_FILE_MAGIC 0 +#define RECORD_GCOV_VERSION 1 +#define RECORD_TIME_STAMP 2 +#define RECORD_FUNCTION_TAG 3 +#define RECORD_FUNCTON_TAG_LEN 4 +#define RECORD_FUNCTION_IDENT 5 +#define RECORD_FUNCTION_CHECK 6 +#define RECORD_COUNT_TAG 7 +#define RECORD_COUNT_LEN 8 +#define RECORD_COUNT 9 + +/** + * gcov_iter_next - advance file iterator to next logical record + * @iter: file iterator + * + * Return zero if new position is valid, non-zero if iterator has reached end. + */ +int gcov_iter_next(struct gcov_iterator *iter) +{ + switch (iter->record) { + case RECORD_FILE_MAGIC: + case RECORD_GCOV_VERSION: + case RECORD_FUNCTION_TAG: + case RECORD_FUNCTON_TAG_LEN: + case RECORD_FUNCTION_IDENT: + case RECORD_COUNT_TAG: + /* Advance to next record */ + iter->record++; + break; + case RECORD_COUNT: + /* Advance to next count */ + iter->count++; + /* fall through */ + case RECORD_COUNT_LEN: + if (iter->count < get_func(iter)->n_ctrs[iter->type]) { + iter->record = 9; + break; + } + /* Advance to next counter type */ + get_type(iter)->offset += iter->count; + iter->count = 0; + iter->type++; + /* fall through */ + case RECORD_FUNCTION_CHECK: + if (iter->type < iter->num_types) { + iter->record = 7; + break; + } + /* Advance to next function */ + iter->type = 0; + iter->function++; + /* fall through */ + case RECORD_TIME_STAMP: + if (iter->function < iter->info->n_functions) + iter->record = 3; + else + iter->record = -1; + break; + } + /* Check for EOF. */ + if (iter->record == -1) + return -EINVAL; + else + return 0; +} + +/** + * seq_write_gcov_u32 - write 32 bit number in gcov format to seq_file + * @seq: seq_file handle + * @v: value to be stored + * + * Number format defined by gcc: numbers are recorded in the 32 bit + * unsigned binary form of the endianness of the machine generating the + * file. + */ +static int seq_write_gcov_u32(struct seq_file *seq, u32 v) +{ + return seq_write(seq, &v, sizeof(v)); +} + +/** + * seq_write_gcov_u64 - write 64 bit number in gcov format to seq_file + * @seq: seq_file handle + * @v: value to be stored + * + * Number format defined by gcc: numbers are recorded in the 32 bit + * unsigned binary form of the endianness of the machine generating the + * file. 64 bit numbers are stored as two 32 bit numbers, the low part + * first. + */ +static int seq_write_gcov_u64(struct seq_file *seq, u64 v) +{ + u32 data[2]; + + data[0] = (v & 0xffffffffUL); + data[1] = (v >> 32); + return seq_write(seq, data, sizeof(data)); +} + +/** + * gcov_iter_write - write data for current pos to seq_file + * @iter: file iterator + * @seq: seq_file handle + * + * Return zero on success, non-zero otherwise. + */ +int gcov_iter_write(struct gcov_iterator *iter, struct seq_file *seq) +{ + int rc = -EINVAL; + + switch (iter->record) { + case RECORD_FILE_MAGIC: + rc = seq_write_gcov_u32(seq, GCOV_DATA_MAGIC); + break; + case RECORD_GCOV_VERSION: + rc = seq_write_gcov_u32(seq, iter->info->version); + break; + case RECORD_TIME_STAMP: + rc = seq_write_gcov_u32(seq, iter->info->stamp); + break; + case RECORD_FUNCTION_TAG: + rc = seq_write_gcov_u32(seq, GCOV_TAG_FUNCTION); + break; + case RECORD_FUNCTON_TAG_LEN: + rc = seq_write_gcov_u32(seq, 2); + break; + case RECORD_FUNCTION_IDENT: + rc = seq_write_gcov_u32(seq, get_func(iter)->ident); + break; + case RECORD_FUNCTION_CHECK: + rc = seq_write_gcov_u32(seq, get_func(iter)->checksum); + break; + case RECORD_COUNT_TAG: + rc = seq_write_gcov_u32(seq, + GCOV_TAG_FOR_COUNTER(get_type(iter)->ctr_type)); + break; + case RECORD_COUNT_LEN: + rc = seq_write_gcov_u32(seq, + get_func(iter)->n_ctrs[iter->type] * 2); + break; + case RECORD_COUNT: + rc = seq_write_gcov_u64(seq, + iter->info->counts[iter->type]. + values[iter->count + get_type(iter)->offset]); + break; + } + return rc; +} diff --git a/kernel/kernel/gcov/gcc_4_7.c b/kernel/kernel/gcov/gcc_4_7.c new file mode 100644 index 000000000..826ba9fb5 --- /dev/null +++ b/kernel/kernel/gcov/gcc_4_7.c @@ -0,0 +1,565 @@ +/* + * This code provides functions to handle gcc's profiling data format + * introduced with gcc 4.7. + * + * This file is based heavily on gcc_3_4.c file. + * + * For a better understanding, refer to gcc source: + * gcc/gcov-io.h + * libgcc/libgcov.c + * + * Uses gcc-internal data definitions. + */ + +#include +#include +#include +#include +#include +#include "gcov.h" + +#if __GNUC__ == 4 && __GNUC_MINOR__ >= 9 +#define GCOV_COUNTERS 9 +#else +#define GCOV_COUNTERS 8 +#endif + +#define GCOV_TAG_FUNCTION_LENGTH 3 + +static struct gcov_info *gcov_info_head; + +/** + * struct gcov_ctr_info - information about counters for a single function + * @num: number of counter values for this type + * @values: array of counter values for this type + * + * This data is generated by gcc during compilation and doesn't change + * at run-time with the exception of the values array. + */ +struct gcov_ctr_info { + unsigned int num; + gcov_type *values; +}; + +/** + * struct gcov_fn_info - profiling meta data per function + * @key: comdat key + * @ident: unique ident of function + * @lineno_checksum: function lineo_checksum + * @cfg_checksum: function cfg checksum + * @ctrs: instrumented counters + * + * This data is generated by gcc during compilation and doesn't change + * at run-time. + * + * Information about a single function. This uses the trailing array + * idiom. The number of counters is determined from the merge pointer + * array in gcov_info. The key is used to detect which of a set of + * comdat functions was selected -- it points to the gcov_info object + * of the object file containing the selected comdat function. + */ +struct gcov_fn_info { + const struct gcov_info *key; + unsigned int ident; + unsigned int lineno_checksum; + unsigned int cfg_checksum; + struct gcov_ctr_info ctrs[0]; +}; + +/** + * struct gcov_info - profiling data per object file + * @version: gcov version magic indicating the gcc version used for compilation + * @next: list head for a singly-linked list + * @stamp: uniquifying time stamp + * @filename: name of the associated gcov data file + * @merge: merge functions (null for unused counter type) + * @n_functions: number of instrumented functions + * @functions: pointer to pointers to function information + * + * This data is generated by gcc during compilation and doesn't change + * at run-time with the exception of the next pointer. + */ +struct gcov_info { + unsigned int version; + struct gcov_info *next; + unsigned int stamp; + const char *filename; + void (*merge[GCOV_COUNTERS])(gcov_type *, unsigned int); + unsigned int n_functions; + struct gcov_fn_info **functions; +}; + +/** + * gcov_info_filename - return info filename + * @info: profiling data set + */ +const char *gcov_info_filename(struct gcov_info *info) +{ + return info->filename; +} + +/** + * gcov_info_version - return info version + * @info: profiling data set + */ +unsigned int gcov_info_version(struct gcov_info *info) +{ + return info->version; +} + +/** + * gcov_info_next - return next profiling data set + * @info: profiling data set + * + * Returns next gcov_info following @info or first gcov_info in the chain if + * @info is %NULL. + */ +struct gcov_info *gcov_info_next(struct gcov_info *info) +{ + if (!info) + return gcov_info_head; + + return info->next; +} + +/** + * gcov_info_link - link/add profiling data set to the list + * @info: profiling data set + */ +void gcov_info_link(struct gcov_info *info) +{ + info->next = gcov_info_head; + gcov_info_head = info; +} + +/** + * gcov_info_unlink - unlink/remove profiling data set from the list + * @prev: previous profiling data set + * @info: profiling data set + */ +void gcov_info_unlink(struct gcov_info *prev, struct gcov_info *info) +{ + if (prev) + prev->next = info->next; + else + gcov_info_head = info->next; +} + +/* Symbolic links to be created for each profiling data file. */ +const struct gcov_link gcov_link[] = { + { OBJ_TREE, "gcno" }, /* Link to .gcno file in $(objtree). */ + { 0, NULL}, +}; + +/* + * Determine whether a counter is active. Doesn't change at run-time. + */ +static int counter_active(struct gcov_info *info, unsigned int type) +{ + return info->merge[type] ? 1 : 0; +} + +/* Determine number of active counters. Based on gcc magic. */ +static unsigned int num_counter_active(struct gcov_info *info) +{ + unsigned int i; + unsigned int result = 0; + + for (i = 0; i < GCOV_COUNTERS; i++) { + if (counter_active(info, i)) + result++; + } + return result; +} + +/** + * gcov_info_reset - reset profiling data to zero + * @info: profiling data set + */ +void gcov_info_reset(struct gcov_info *info) +{ + struct gcov_ctr_info *ci_ptr; + unsigned int fi_idx; + unsigned int ct_idx; + + for (fi_idx = 0; fi_idx < info->n_functions; fi_idx++) { + ci_ptr = info->functions[fi_idx]->ctrs; + + for (ct_idx = 0; ct_idx < GCOV_COUNTERS; ct_idx++) { + if (!counter_active(info, ct_idx)) + continue; + + memset(ci_ptr->values, 0, + sizeof(gcov_type) * ci_ptr->num); + ci_ptr++; + } + } +} + +/** + * gcov_info_is_compatible - check if profiling data can be added + * @info1: first profiling data set + * @info2: second profiling data set + * + * Returns non-zero if profiling data can be added, zero otherwise. + */ +int gcov_info_is_compatible(struct gcov_info *info1, struct gcov_info *info2) +{ + return (info1->stamp == info2->stamp); +} + +/** + * gcov_info_add - add up profiling data + * @dest: profiling data set to which data is added + * @source: profiling data set which is added + * + * Adds profiling counts of @source to @dest. + */ +void gcov_info_add(struct gcov_info *dst, struct gcov_info *src) +{ + struct gcov_ctr_info *dci_ptr; + struct gcov_ctr_info *sci_ptr; + unsigned int fi_idx; + unsigned int ct_idx; + unsigned int val_idx; + + for (fi_idx = 0; fi_idx < src->n_functions; fi_idx++) { + dci_ptr = dst->functions[fi_idx]->ctrs; + sci_ptr = src->functions[fi_idx]->ctrs; + + for (ct_idx = 0; ct_idx < GCOV_COUNTERS; ct_idx++) { + if (!counter_active(src, ct_idx)) + continue; + + for (val_idx = 0; val_idx < sci_ptr->num; val_idx++) + dci_ptr->values[val_idx] += + sci_ptr->values[val_idx]; + + dci_ptr++; + sci_ptr++; + } + } +} + +/** + * gcov_info_dup - duplicate profiling data set + * @info: profiling data set to duplicate + * + * Return newly allocated duplicate on success, %NULL on error. + */ +struct gcov_info *gcov_info_dup(struct gcov_info *info) +{ + struct gcov_info *dup; + struct gcov_ctr_info *dci_ptr; /* dst counter info */ + struct gcov_ctr_info *sci_ptr; /* src counter info */ + unsigned int active; + unsigned int fi_idx; /* function info idx */ + unsigned int ct_idx; /* counter type idx */ + size_t fi_size; /* function info size */ + size_t cv_size; /* counter values size */ + + dup = kmemdup(info, sizeof(*dup), GFP_KERNEL); + if (!dup) + return NULL; + + dup->next = NULL; + dup->filename = NULL; + dup->functions = NULL; + + dup->filename = kstrdup(info->filename, GFP_KERNEL); + if (!dup->filename) + goto err_free; + + dup->functions = kcalloc(info->n_functions, + sizeof(struct gcov_fn_info *), GFP_KERNEL); + if (!dup->functions) + goto err_free; + + active = num_counter_active(info); + fi_size = sizeof(struct gcov_fn_info); + fi_size += sizeof(struct gcov_ctr_info) * active; + + for (fi_idx = 0; fi_idx < info->n_functions; fi_idx++) { + dup->functions[fi_idx] = kzalloc(fi_size, GFP_KERNEL); + if (!dup->functions[fi_idx]) + goto err_free; + + *(dup->functions[fi_idx]) = *(info->functions[fi_idx]); + + sci_ptr = info->functions[fi_idx]->ctrs; + dci_ptr = dup->functions[fi_idx]->ctrs; + + for (ct_idx = 0; ct_idx < active; ct_idx++) { + + cv_size = sizeof(gcov_type) * sci_ptr->num; + + dci_ptr->values = vmalloc(cv_size); + + if (!dci_ptr->values) + goto err_free; + + dci_ptr->num = sci_ptr->num; + memcpy(dci_ptr->values, sci_ptr->values, cv_size); + + sci_ptr++; + dci_ptr++; + } + } + + return dup; +err_free: + gcov_info_free(dup); + return NULL; +} + +/** + * gcov_info_free - release memory for profiling data set duplicate + * @info: profiling data set duplicate to free + */ +void gcov_info_free(struct gcov_info *info) +{ + unsigned int active; + unsigned int fi_idx; + unsigned int ct_idx; + struct gcov_ctr_info *ci_ptr; + + if (!info->functions) + goto free_info; + + active = num_counter_active(info); + + for (fi_idx = 0; fi_idx < info->n_functions; fi_idx++) { + if (!info->functions[fi_idx]) + continue; + + ci_ptr = info->functions[fi_idx]->ctrs; + + for (ct_idx = 0; ct_idx < active; ct_idx++, ci_ptr++) + vfree(ci_ptr->values); + + kfree(info->functions[fi_idx]); + } + +free_info: + kfree(info->functions); + kfree(info->filename); + kfree(info); +} + +#define ITER_STRIDE PAGE_SIZE + +/** + * struct gcov_iterator - specifies current file position in logical records + * @info: associated profiling data + * @buffer: buffer containing file data + * @size: size of buffer + * @pos: current position in file + */ +struct gcov_iterator { + struct gcov_info *info; + void *buffer; + size_t size; + loff_t pos; +}; + +/** + * store_gcov_u32 - store 32 bit number in gcov format to buffer + * @buffer: target buffer or NULL + * @off: offset into the buffer + * @v: value to be stored + * + * Number format defined by gcc: numbers are recorded in the 32 bit + * unsigned binary form of the endianness of the machine generating the + * file. Returns the number of bytes stored. If @buffer is %NULL, doesn't + * store anything. + */ +static size_t store_gcov_u32(void *buffer, size_t off, u32 v) +{ + u32 *data; + + if (buffer) { + data = buffer + off; + *data = v; + } + + return sizeof(*data); +} + +/** + * store_gcov_u64 - store 64 bit number in gcov format to buffer + * @buffer: target buffer or NULL + * @off: offset into the buffer + * @v: value to be stored + * + * Number format defined by gcc: numbers are recorded in the 32 bit + * unsigned binary form of the endianness of the machine generating the + * file. 64 bit numbers are stored as two 32 bit numbers, the low part + * first. Returns the number of bytes stored. If @buffer is %NULL, doesn't store + * anything. + */ +static size_t store_gcov_u64(void *buffer, size_t off, u64 v) +{ + u32 *data; + + if (buffer) { + data = buffer + off; + + data[0] = (v & 0xffffffffUL); + data[1] = (v >> 32); + } + + return sizeof(*data) * 2; +} + +/** + * convert_to_gcda - convert profiling data set to gcda file format + * @buffer: the buffer to store file data or %NULL if no data should be stored + * @info: profiling data set to be converted + * + * Returns the number of bytes that were/would have been stored into the buffer. + */ +static size_t convert_to_gcda(char *buffer, struct gcov_info *info) +{ + struct gcov_fn_info *fi_ptr; + struct gcov_ctr_info *ci_ptr; + unsigned int fi_idx; + unsigned int ct_idx; + unsigned int cv_idx; + size_t pos = 0; + + /* File header. */ + pos += store_gcov_u32(buffer, pos, GCOV_DATA_MAGIC); + pos += store_gcov_u32(buffer, pos, info->version); + pos += store_gcov_u32(buffer, pos, info->stamp); + + for (fi_idx = 0; fi_idx < info->n_functions; fi_idx++) { + fi_ptr = info->functions[fi_idx]; + + /* Function record. */ + pos += store_gcov_u32(buffer, pos, GCOV_TAG_FUNCTION); + pos += store_gcov_u32(buffer, pos, GCOV_TAG_FUNCTION_LENGTH); + pos += store_gcov_u32(buffer, pos, fi_ptr->ident); + pos += store_gcov_u32(buffer, pos, fi_ptr->lineno_checksum); + pos += store_gcov_u32(buffer, pos, fi_ptr->cfg_checksum); + + ci_ptr = fi_ptr->ctrs; + + for (ct_idx = 0; ct_idx < GCOV_COUNTERS; ct_idx++) { + if (!counter_active(info, ct_idx)) + continue; + + /* Counter record. */ + pos += store_gcov_u32(buffer, pos, + GCOV_TAG_FOR_COUNTER(ct_idx)); + pos += store_gcov_u32(buffer, pos, ci_ptr->num * 2); + + for (cv_idx = 0; cv_idx < ci_ptr->num; cv_idx++) { + pos += store_gcov_u64(buffer, pos, + ci_ptr->values[cv_idx]); + } + + ci_ptr++; + } + } + + return pos; +} + +/** + * gcov_iter_new - allocate and initialize profiling data iterator + * @info: profiling data set to be iterated + * + * Return file iterator on success, %NULL otherwise. + */ +struct gcov_iterator *gcov_iter_new(struct gcov_info *info) +{ + struct gcov_iterator *iter; + + iter = kzalloc(sizeof(struct gcov_iterator), GFP_KERNEL); + if (!iter) + goto err_free; + + iter->info = info; + /* Dry-run to get the actual buffer size. */ + iter->size = convert_to_gcda(NULL, info); + iter->buffer = vmalloc(iter->size); + if (!iter->buffer) + goto err_free; + + convert_to_gcda(iter->buffer, info); + + return iter; + +err_free: + kfree(iter); + return NULL; +} + + +/** + * gcov_iter_get_info - return profiling data set for given file iterator + * @iter: file iterator + */ +void gcov_iter_free(struct gcov_iterator *iter) +{ + vfree(iter->buffer); + kfree(iter); +} + +/** + * gcov_iter_get_info - return profiling data set for given file iterator + * @iter: file iterator + */ +struct gcov_info *gcov_iter_get_info(struct gcov_iterator *iter) +{ + return iter->info; +} + +/** + * gcov_iter_start - reset file iterator to starting position + * @iter: file iterator + */ +void gcov_iter_start(struct gcov_iterator *iter) +{ + iter->pos = 0; +} + +/** + * gcov_iter_next - advance file iterator to next logical record + * @iter: file iterator + * + * Return zero if new position is valid, non-zero if iterator has reached end. + */ +int gcov_iter_next(struct gcov_iterator *iter) +{ + if (iter->pos < iter->size) + iter->pos += ITER_STRIDE; + + if (iter->pos >= iter->size) + return -EINVAL; + + return 0; +} + +/** + * gcov_iter_write - write data for current pos to seq_file + * @iter: file iterator + * @seq: seq_file handle + * + * Return zero on success, non-zero otherwise. + */ +int gcov_iter_write(struct gcov_iterator *iter, struct seq_file *seq) +{ + size_t len; + + if (iter->pos >= iter->size) + return -EINVAL; + + len = ITER_STRIDE; + if (iter->pos + len > iter->size) + len = iter->size - iter->pos; + + seq_write(seq, iter->buffer + iter->pos, len); + + return 0; +} diff --git a/kernel/kernel/gcov/gcov.h b/kernel/kernel/gcov/gcov.h new file mode 100644 index 000000000..92c8e22a2 --- /dev/null +++ b/kernel/kernel/gcov/gcov.h @@ -0,0 +1,85 @@ +/* + * Profiling infrastructure declarations. + * + * This file is based on gcc-internal definitions. Data structures are + * defined to be compatible with gcc counterparts. For a better + * understanding, refer to gcc source: gcc/gcov-io.h. + * + * Copyright IBM Corp. 2009 + * Author(s): Peter Oberparleiter + * + * Uses gcc-internal data definitions. + */ + +#ifndef GCOV_H +#define GCOV_H GCOV_H + +#include + +/* + * Profiling data types used for gcc 3.4 and above - these are defined by + * gcc and need to be kept as close to the original definition as possible to + * remain compatible. + */ +#define GCOV_DATA_MAGIC ((unsigned int) 0x67636461) +#define GCOV_TAG_FUNCTION ((unsigned int) 0x01000000) +#define GCOV_TAG_COUNTER_BASE ((unsigned int) 0x01a10000) +#define GCOV_TAG_FOR_COUNTER(count) \ + (GCOV_TAG_COUNTER_BASE + ((unsigned int) (count) << 17)) + +#if BITS_PER_LONG >= 64 +typedef long gcov_type; +#else +typedef long long gcov_type; +#endif + +/* Opaque gcov_info. The gcov structures can change as for example in gcc 4.7 so + * we cannot use full definition here and they need to be placed in gcc specific + * implementation of gcov. This also means no direct access to the members in + * generic code and usage of the interface below.*/ +struct gcov_info; + +/* Interface to access gcov_info data */ +const char *gcov_info_filename(struct gcov_info *info); +unsigned int gcov_info_version(struct gcov_info *info); +struct gcov_info *gcov_info_next(struct gcov_info *info); +void gcov_info_link(struct gcov_info *info); +void gcov_info_unlink(struct gcov_info *prev, struct gcov_info *info); + +/* Base interface. */ +enum gcov_action { + GCOV_ADD, + GCOV_REMOVE, +}; + +void gcov_event(enum gcov_action action, struct gcov_info *info); +void gcov_enable_events(void); + +/* Iterator control. */ +struct seq_file; +struct gcov_iterator; + +struct gcov_iterator *gcov_iter_new(struct gcov_info *info); +void gcov_iter_free(struct gcov_iterator *iter); +void gcov_iter_start(struct gcov_iterator *iter); +int gcov_iter_next(struct gcov_iterator *iter); +int gcov_iter_write(struct gcov_iterator *iter, struct seq_file *seq); +struct gcov_info *gcov_iter_get_info(struct gcov_iterator *iter); + +/* gcov_info control. */ +void gcov_info_reset(struct gcov_info *info); +int gcov_info_is_compatible(struct gcov_info *info1, struct gcov_info *info2); +void gcov_info_add(struct gcov_info *dest, struct gcov_info *source); +struct gcov_info *gcov_info_dup(struct gcov_info *info); +void gcov_info_free(struct gcov_info *info); + +struct gcov_link { + enum { + OBJ_TREE, + SRC_TREE, + } dir; + const char *ext; +}; +extern const struct gcov_link gcov_link[]; + +#endif /* GCOV_H */ diff --git a/kernel/kernel/groups.c b/kernel/kernel/groups.c new file mode 100644 index 000000000..74d431d25 --- /dev/null +++ b/kernel/kernel/groups.c @@ -0,0 +1,277 @@ +/* + * Supplementary group IDs + */ +#include +#include +#include +#include +#include +#include +#include + +struct group_info *groups_alloc(int gidsetsize) +{ + struct group_info *group_info; + int nblocks; + int i; + + nblocks = (gidsetsize + NGROUPS_PER_BLOCK - 1) / NGROUPS_PER_BLOCK; + /* Make sure we always allocate at least one indirect block pointer */ + nblocks = nblocks ? : 1; + group_info = kmalloc(sizeof(*group_info) + nblocks*sizeof(gid_t *), GFP_USER); + if (!group_info) + return NULL; + group_info->ngroups = gidsetsize; + group_info->nblocks = nblocks; + atomic_set(&group_info->usage, 1); + + if (gidsetsize <= NGROUPS_SMALL) + group_info->blocks[0] = group_info->small_block; + else { + for (i = 0; i < nblocks; i++) { + kgid_t *b; + b = (void *)__get_free_page(GFP_USER); + if (!b) + goto out_undo_partial_alloc; + group_info->blocks[i] = b; + } + } + return group_info; + +out_undo_partial_alloc: + while (--i >= 0) { + free_page((unsigned long)group_info->blocks[i]); + } + kfree(group_info); + return NULL; +} + +EXPORT_SYMBOL(groups_alloc); + +void groups_free(struct group_info *group_info) +{ + if (group_info->blocks[0] != group_info->small_block) { + int i; + for (i = 0; i < group_info->nblocks; i++) + free_page((unsigned long)group_info->blocks[i]); + } + kfree(group_info); +} + +EXPORT_SYMBOL(groups_free); + +/* export the group_info to a user-space array */ +static int groups_to_user(gid_t __user *grouplist, + const struct group_info *group_info) +{ + struct user_namespace *user_ns = current_user_ns(); + int i; + unsigned int count = group_info->ngroups; + + for (i = 0; i < count; i++) { + gid_t gid; + gid = from_kgid_munged(user_ns, GROUP_AT(group_info, i)); + if (put_user(gid, grouplist+i)) + return -EFAULT; + } + return 0; +} + +/* fill a group_info from a user-space array - it must be allocated already */ +static int groups_from_user(struct group_info *group_info, + gid_t __user *grouplist) +{ + struct user_namespace *user_ns = current_user_ns(); + int i; + unsigned int count = group_info->ngroups; + + for (i = 0; i < count; i++) { + gid_t gid; + kgid_t kgid; + if (get_user(gid, grouplist+i)) + return -EFAULT; + + kgid = make_kgid(user_ns, gid); + if (!gid_valid(kgid)) + return -EINVAL; + + GROUP_AT(group_info, i) = kgid; + } + return 0; +} + +/* a simple Shell sort */ +static void groups_sort(struct group_info *group_info) +{ + int base, max, stride; + int gidsetsize = group_info->ngroups; + + for (stride = 1; stride < gidsetsize; stride = 3 * stride + 1) + ; /* nothing */ + stride /= 3; + + while (stride) { + max = gidsetsize - stride; + for (base = 0; base < max; base++) { + int left = base; + int right = left + stride; + kgid_t tmp = GROUP_AT(group_info, right); + + while (left >= 0 && gid_gt(GROUP_AT(group_info, left), tmp)) { + GROUP_AT(group_info, right) = + GROUP_AT(group_info, left); + right = left; + left -= stride; + } + GROUP_AT(group_info, right) = tmp; + } + stride /= 3; + } +} + +/* a simple bsearch */ +int groups_search(const struct group_info *group_info, kgid_t grp) +{ + unsigned int left, right; + + if (!group_info) + return 0; + + left = 0; + right = group_info->ngroups; + while (left < right) { + unsigned int mid = (left+right)/2; + if (gid_gt(grp, GROUP_AT(group_info, mid))) + left = mid + 1; + else if (gid_lt(grp, GROUP_AT(group_info, mid))) + right = mid; + else + return 1; + } + return 0; +} + +/** + * set_groups - Change a group subscription in a set of credentials + * @new: The newly prepared set of credentials to alter + * @group_info: The group list to install + */ +void set_groups(struct cred *new, struct group_info *group_info) +{ + put_group_info(new->group_info); + groups_sort(group_info); + get_group_info(group_info); + new->group_info = group_info; +} + +EXPORT_SYMBOL(set_groups); + +/** + * set_current_groups - Change current's group subscription + * @group_info: The group list to impose + * + * Validate a group subscription and, if valid, impose it upon current's task + * security record. + */ +int set_current_groups(struct group_info *group_info) +{ + struct cred *new; + + new = prepare_creds(); + if (!new) + return -ENOMEM; + + set_groups(new, group_info); + return commit_creds(new); +} + +EXPORT_SYMBOL(set_current_groups); + +SYSCALL_DEFINE2(getgroups, int, gidsetsize, gid_t __user *, grouplist) +{ + const struct cred *cred = current_cred(); + int i; + + if (gidsetsize < 0) + return -EINVAL; + + /* no need to grab task_lock here; it cannot change */ + i = cred->group_info->ngroups; + if (gidsetsize) { + if (i > gidsetsize) { + i = -EINVAL; + goto out; + } + if (groups_to_user(grouplist, cred->group_info)) { + i = -EFAULT; + goto out; + } + } +out: + return i; +} + +bool may_setgroups(void) +{ + struct user_namespace *user_ns = current_user_ns(); + + return ns_capable(user_ns, CAP_SETGID) && + userns_may_setgroups(user_ns); +} + +/* + * SMP: Our groups are copy-on-write. We can set them safely + * without another task interfering. + */ + +SYSCALL_DEFINE2(setgroups, int, gidsetsize, gid_t __user *, grouplist) +{ + struct group_info *group_info; + int retval; + + if (!may_setgroups()) + return -EPERM; + if ((unsigned)gidsetsize > NGROUPS_MAX) + return -EINVAL; + + group_info = groups_alloc(gidsetsize); + if (!group_info) + return -ENOMEM; + retval = groups_from_user(group_info, grouplist); + if (retval) { + put_group_info(group_info); + return retval; + } + + retval = set_current_groups(group_info); + put_group_info(group_info); + + return retval; +} + +/* + * Check whether we're fsgid/egid or in the supplemental group.. + */ +int in_group_p(kgid_t grp) +{ + const struct cred *cred = current_cred(); + int retval = 1; + + if (!gid_eq(grp, cred->fsgid)) + retval = groups_search(cred->group_info, grp); + return retval; +} + +EXPORT_SYMBOL(in_group_p); + +int in_egroup_p(kgid_t grp) +{ + const struct cred *cred = current_cred(); + int retval = 1; + + if (!gid_eq(grp, cred->egid)) + retval = groups_search(cred->group_info, grp); + return retval; +} + +EXPORT_SYMBOL(in_egroup_p); diff --git a/kernel/kernel/hung_task.c b/kernel/kernel/hung_task.c new file mode 100644 index 000000000..e0f90c2b5 --- /dev/null +++ b/kernel/kernel/hung_task.c @@ -0,0 +1,251 @@ +/* + * Detect Hung Task + * + * kernel/hung_task.c - kernel thread for detecting tasks stuck in D state + * + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +/* + * The number of tasks checked: + */ +int __read_mostly sysctl_hung_task_check_count = PID_MAX_LIMIT; + +/* + * Limit number of tasks checked in a batch. + * + * This value controls the preemptibility of khungtaskd since preemption + * is disabled during the critical section. It also controls the size of + * the RCU grace period. So it needs to be upper-bound. + */ +#define HUNG_TASK_BATCHING 1024 + +/* + * Zero means infinite timeout - no checking done: + */ +unsigned long __read_mostly sysctl_hung_task_timeout_secs = CONFIG_DEFAULT_HUNG_TASK_TIMEOUT; + +int __read_mostly sysctl_hung_task_warnings = 10; + +static int __read_mostly did_panic; + +static struct task_struct *watchdog_task; + +/* + * Should we panic (and reboot, if panic_timeout= is set) when a + * hung task is detected: + */ +unsigned int __read_mostly sysctl_hung_task_panic = + CONFIG_BOOTPARAM_HUNG_TASK_PANIC_VALUE; + +static int __init hung_task_panic_setup(char *str) +{ + int rc = kstrtouint(str, 0, &sysctl_hung_task_panic); + + if (rc) + return rc; + return 1; +} +__setup("hung_task_panic=", hung_task_panic_setup); + +static int +hung_task_panic(struct notifier_block *this, unsigned long event, void *ptr) +{ + did_panic = 1; + + return NOTIFY_DONE; +} + +static struct notifier_block panic_block = { + .notifier_call = hung_task_panic, +}; + +static void check_hung_task(struct task_struct *t, unsigned long timeout) +{ + unsigned long switch_count = t->nvcsw + t->nivcsw; + + /* + * Ensure the task is not frozen. + * Also, skip vfork and any other user process that freezer should skip. + */ + if (unlikely(t->flags & (PF_FROZEN | PF_FREEZER_SKIP))) + return; + + /* + * When a freshly created task is scheduled once, changes its state to + * TASK_UNINTERRUPTIBLE without having ever been switched out once, it + * musn't be checked. + */ + if (unlikely(!switch_count)) + return; + + if (switch_count != t->last_switch_count) { + t->last_switch_count = switch_count; + return; + } + + trace_sched_process_hang(t); + + if (!sysctl_hung_task_warnings) + return; + + if (sysctl_hung_task_warnings > 0) + sysctl_hung_task_warnings--; + + /* + * Ok, the task did not get scheduled for more than 2 minutes, + * complain: + */ + pr_err("INFO: task %s:%d blocked for more than %ld seconds.\n", + t->comm, t->pid, timeout); + pr_err(" %s %s %.*s\n", + print_tainted(), init_utsname()->release, + (int)strcspn(init_utsname()->version, " "), + init_utsname()->version); + pr_err("\"echo 0 > /proc/sys/kernel/hung_task_timeout_secs\"" + " disables this message.\n"); + sched_show_task(t); + debug_show_held_locks(t); + + touch_nmi_watchdog(); + + if (sysctl_hung_task_panic) { + trigger_all_cpu_backtrace(); + panic("hung_task: blocked tasks"); + } +} + +/* + * To avoid extending the RCU grace period for an unbounded amount of time, + * periodically exit the critical section and enter a new one. + * + * For preemptible RCU it is sufficient to call rcu_read_unlock in order + * to exit the grace period. For classic RCU, a reschedule is required. + */ +static bool rcu_lock_break(struct task_struct *g, struct task_struct *t) +{ + bool can_cont; + + get_task_struct(g); + get_task_struct(t); + rcu_read_unlock(); + cond_resched(); + rcu_read_lock(); + can_cont = pid_alive(g) && pid_alive(t); + put_task_struct(t); + put_task_struct(g); + + return can_cont; +} + +/* + * Check whether a TASK_UNINTERRUPTIBLE does not get woken up for + * a really long time (120 seconds). If that happens, print out + * a warning. + */ +static void check_hung_uninterruptible_tasks(unsigned long timeout) +{ + int max_count = sysctl_hung_task_check_count; + int batch_count = HUNG_TASK_BATCHING; + struct task_struct *g, *t; + + /* + * If the system crashed already then all bets are off, + * do not report extra hung tasks: + */ + if (test_taint(TAINT_DIE) || did_panic) + return; + + rcu_read_lock(); + for_each_process_thread(g, t) { + if (!max_count--) + goto unlock; + if (!--batch_count) { + batch_count = HUNG_TASK_BATCHING; + if (!rcu_lock_break(g, t)) + goto unlock; + } + /* use "==" to skip the TASK_KILLABLE tasks waiting on NFS */ + if (t->state == TASK_UNINTERRUPTIBLE) + check_hung_task(t, timeout); + } + unlock: + rcu_read_unlock(); +} + +static unsigned long timeout_jiffies(unsigned long timeout) +{ + /* timeout of 0 will disable the watchdog */ + return timeout ? timeout * HZ : MAX_SCHEDULE_TIMEOUT; +} + +/* + * Process updating of timeout sysctl + */ +int proc_dohung_task_timeout_secs(struct ctl_table *table, int write, + void __user *buffer, + size_t *lenp, loff_t *ppos) +{ + int ret; + + ret = proc_doulongvec_minmax(table, write, buffer, lenp, ppos); + + if (ret || !write) + goto out; + + wake_up_process(watchdog_task); + + out: + return ret; +} + +static atomic_t reset_hung_task = ATOMIC_INIT(0); + +void reset_hung_task_detector(void) +{ + atomic_set(&reset_hung_task, 1); +} +EXPORT_SYMBOL_GPL(reset_hung_task_detector); + +/* + * kthread which checks for tasks stuck in D state + */ +static int watchdog(void *dummy) +{ + set_user_nice(current, 0); + + for ( ; ; ) { + unsigned long timeout = sysctl_hung_task_timeout_secs; + + while (schedule_timeout_interruptible(timeout_jiffies(timeout))) + timeout = sysctl_hung_task_timeout_secs; + + if (atomic_xchg(&reset_hung_task, 0)) + continue; + + check_hung_uninterruptible_tasks(timeout); + } + + return 0; +} + +static int __init hung_task_init(void) +{ + atomic_notifier_chain_register(&panic_notifier_list, &panic_block); + watchdog_task = kthread_run(watchdog, NULL, "khungtaskd"); + + return 0; +} +subsys_initcall(hung_task_init); diff --git a/kernel/kernel/irq/Kconfig b/kernel/kernel/irq/Kconfig new file mode 100644 index 000000000..9a76e3bed --- /dev/null +++ b/kernel/kernel/irq/Kconfig @@ -0,0 +1,103 @@ +menu "IRQ subsystem" +# Options selectable by the architecture code + +# Make sparse irq Kconfig switch below available +config MAY_HAVE_SPARSE_IRQ + bool + +# Legacy support, required for itanic +config GENERIC_IRQ_LEGACY + bool + +# Enable the generic irq autoprobe mechanism +config GENERIC_IRQ_PROBE + bool + +# Use the generic /proc/interrupts implementation +config GENERIC_IRQ_SHOW + bool + +# Print level/edge extra information +config GENERIC_IRQ_SHOW_LEVEL + bool + +# Facility to allocate a hardware interrupt. This is legacy support +# and should not be used in new code. Use irq domains instead. +config GENERIC_IRQ_LEGACY_ALLOC_HWIRQ + bool + +# Support for delayed migration from interrupt context +config GENERIC_PENDING_IRQ + bool + +# Alpha specific irq affinity mechanism +config AUTO_IRQ_AFFINITY + bool + +# Tasklet based software resend for pending interrupts on enable_irq() +config HARDIRQS_SW_RESEND + bool + +# Preflow handler support for fasteoi (sparc64) +config IRQ_PREFLOW_FASTEOI + bool + +# Edge style eoi based handler (cell) +config IRQ_EDGE_EOI_HANDLER + bool + +# Generic configurable interrupt chip implementation +config GENERIC_IRQ_CHIP + bool + select IRQ_DOMAIN + +# Generic irq_domain hw <--> linux irq number translation +config IRQ_DOMAIN + bool + +# Support for hierarchical irq domains +config IRQ_DOMAIN_HIERARCHY + bool + select IRQ_DOMAIN + +# Generic MSI interrupt support +config GENERIC_MSI_IRQ + bool + +# Generic MSI hierarchical interrupt domain support +config GENERIC_MSI_IRQ_DOMAIN + bool + select IRQ_DOMAIN_HIERARCHY + select GENERIC_MSI_IRQ + +config HANDLE_DOMAIN_IRQ + bool + +config IRQ_DOMAIN_DEBUG + bool "Expose hardware/virtual IRQ mapping via debugfs" + depends on IRQ_DOMAIN && DEBUG_FS + help + This option will show the mapping relationship between hardware irq + numbers and Linux irq numbers. The mapping is exposed via debugfs + in the file "irq_domain_mapping". + + If you don't know what this means you don't need it. + +# Support forced irq threading +config IRQ_FORCED_THREADING + bool + +config SPARSE_IRQ + bool "Support sparse irq numbering" if MAY_HAVE_SPARSE_IRQ + ---help--- + + Sparse irq numbering is useful for distro kernels that want + to define a high CONFIG_NR_CPUS value but still want to have + low kernel memory footprint on smaller machines. + + ( Sparse irqs can also be beneficial on NUMA boxes, as they spread + out the interrupt descriptors in a more NUMA-friendly way. ) + + If you don't know what to do here, say N. + +endmenu diff --git a/kernel/kernel/irq/Makefile b/kernel/kernel/irq/Makefile new file mode 100644 index 000000000..d12123526 --- /dev/null +++ b/kernel/kernel/irq/Makefile @@ -0,0 +1,9 @@ + +obj-y := irqdesc.o handle.o manage.o spurious.o resend.o chip.o dummychip.o devres.o +obj-$(CONFIG_GENERIC_IRQ_CHIP) += generic-chip.o +obj-$(CONFIG_GENERIC_IRQ_PROBE) += autoprobe.o +obj-$(CONFIG_IRQ_DOMAIN) += irqdomain.o +obj-$(CONFIG_PROC_FS) += proc.o +obj-$(CONFIG_GENERIC_PENDING_IRQ) += migration.o +obj-$(CONFIG_PM_SLEEP) += pm.o +obj-$(CONFIG_GENERIC_MSI_IRQ) += msi.o diff --git a/kernel/kernel/irq/autoprobe.c b/kernel/kernel/irq/autoprobe.c new file mode 100644 index 000000000..0119b9d46 --- /dev/null +++ b/kernel/kernel/irq/autoprobe.c @@ -0,0 +1,185 @@ +/* + * linux/kernel/irq/autoprobe.c + * + * Copyright (C) 1992, 1998-2004 Linus Torvalds, Ingo Molnar + * + * This file contains the interrupt probing code and driver APIs. + */ + +#include +#include +#include +#include +#include + +#include "internals.h" + +/* + * Autodetection depends on the fact that any interrupt that + * comes in on to an unassigned handler will get stuck with + * "IRQS_WAITING" cleared and the interrupt disabled. + */ +static DEFINE_MUTEX(probing_active); + +/** + * probe_irq_on - begin an interrupt autodetect + * + * Commence probing for an interrupt. The interrupts are scanned + * and a mask of potential interrupt lines is returned. + * + */ +unsigned long probe_irq_on(void) +{ + struct irq_desc *desc; + unsigned long mask = 0; + int i; + + /* + * quiesce the kernel, or at least the asynchronous portion + */ + async_synchronize_full(); + mutex_lock(&probing_active); + /* + * something may have generated an irq long ago and we want to + * flush such a longstanding irq before considering it as spurious. + */ + for_each_irq_desc_reverse(i, desc) { + raw_spin_lock_irq(&desc->lock); + if (!desc->action && irq_settings_can_probe(desc)) { + /* + * Some chips need to know about probing in + * progress: + */ + if (desc->irq_data.chip->irq_set_type) + desc->irq_data.chip->irq_set_type(&desc->irq_data, + IRQ_TYPE_PROBE); + irq_startup(desc, false); + } + raw_spin_unlock_irq(&desc->lock); + } + + /* Wait for longstanding interrupts to trigger. */ + msleep(20); + + /* + * enable any unassigned irqs + * (we must startup again here because if a longstanding irq + * happened in the previous stage, it may have masked itself) + */ + for_each_irq_desc_reverse(i, desc) { + raw_spin_lock_irq(&desc->lock); + if (!desc->action && irq_settings_can_probe(desc)) { + desc->istate |= IRQS_AUTODETECT | IRQS_WAITING; + if (irq_startup(desc, false)) + desc->istate |= IRQS_PENDING; + } + raw_spin_unlock_irq(&desc->lock); + } + + /* + * Wait for spurious interrupts to trigger + */ + msleep(100); + + /* + * Now filter out any obviously spurious interrupts + */ + for_each_irq_desc(i, desc) { + raw_spin_lock_irq(&desc->lock); + + if (desc->istate & IRQS_AUTODETECT) { + /* It triggered already - consider it spurious. */ + if (!(desc->istate & IRQS_WAITING)) { + desc->istate &= ~IRQS_AUTODETECT; + irq_shutdown(desc); + } else + if (i < 32) + mask |= 1 << i; + } + raw_spin_unlock_irq(&desc->lock); + } + + return mask; +} +EXPORT_SYMBOL(probe_irq_on); + +/** + * probe_irq_mask - scan a bitmap of interrupt lines + * @val: mask of interrupts to consider + * + * Scan the interrupt lines and return a bitmap of active + * autodetect interrupts. The interrupt probe logic state + * is then returned to its previous value. + * + * Note: we need to scan all the irq's even though we will + * only return autodetect irq numbers - just so that we reset + * them all to a known state. + */ +unsigned int probe_irq_mask(unsigned long val) +{ + unsigned int mask = 0; + struct irq_desc *desc; + int i; + + for_each_irq_desc(i, desc) { + raw_spin_lock_irq(&desc->lock); + if (desc->istate & IRQS_AUTODETECT) { + if (i < 16 && !(desc->istate & IRQS_WAITING)) + mask |= 1 << i; + + desc->istate &= ~IRQS_AUTODETECT; + irq_shutdown(desc); + } + raw_spin_unlock_irq(&desc->lock); + } + mutex_unlock(&probing_active); + + return mask & val; +} +EXPORT_SYMBOL(probe_irq_mask); + +/** + * probe_irq_off - end an interrupt autodetect + * @val: mask of potential interrupts (unused) + * + * Scans the unused interrupt lines and returns the line which + * appears to have triggered the interrupt. If no interrupt was + * found then zero is returned. If more than one interrupt is + * found then minus the first candidate is returned to indicate + * their is doubt. + * + * The interrupt probe logic state is returned to its previous + * value. + * + * BUGS: When used in a module (which arguably shouldn't happen) + * nothing prevents two IRQ probe callers from overlapping. The + * results of this are non-optimal. + */ +int probe_irq_off(unsigned long val) +{ + int i, irq_found = 0, nr_of_irqs = 0; + struct irq_desc *desc; + + for_each_irq_desc(i, desc) { + raw_spin_lock_irq(&desc->lock); + + if (desc->istate & IRQS_AUTODETECT) { + if (!(desc->istate & IRQS_WAITING)) { + if (!nr_of_irqs) + irq_found = i; + nr_of_irqs++; + } + desc->istate &= ~IRQS_AUTODETECT; + irq_shutdown(desc); + } + raw_spin_unlock_irq(&desc->lock); + } + mutex_unlock(&probing_active); + + if (nr_of_irqs > 1) + irq_found = -irq_found; + + return irq_found; +} +EXPORT_SYMBOL(probe_irq_off); + diff --git a/kernel/kernel/irq/chip.c b/kernel/kernel/irq/chip.c new file mode 100644 index 000000000..eb9a4ea39 --- /dev/null +++ b/kernel/kernel/irq/chip.c @@ -0,0 +1,993 @@ +/* + * linux/kernel/irq/chip.c + * + * Copyright (C) 1992, 1998-2006 Linus Torvalds, Ingo Molnar + * Copyright (C) 2005-2006, Thomas Gleixner, Russell King + * + * This file contains the core interrupt handling code, for irq-chip + * based architectures. + * + * Detailed information is available in Documentation/DocBook/genericirq + */ + +#include +#include +#include +#include +#include +#include + +#include + +#include "internals.h" + +/** + * irq_set_chip - set the irq chip for an irq + * @irq: irq number + * @chip: pointer to irq chip description structure + */ +int irq_set_chip(unsigned int irq, struct irq_chip *chip) +{ + unsigned long flags; + struct irq_desc *desc = irq_get_desc_lock(irq, &flags, 0); + + if (!desc) + return -EINVAL; + + if (!chip) + chip = &no_irq_chip; + + desc->irq_data.chip = chip; + irq_put_desc_unlock(desc, flags); + /* + * For !CONFIG_SPARSE_IRQ make the irq show up in + * allocated_irqs. + */ + irq_mark_irq(irq); + return 0; +} +EXPORT_SYMBOL(irq_set_chip); + +/** + * irq_set_type - set the irq trigger type for an irq + * @irq: irq number + * @type: IRQ_TYPE_{LEVEL,EDGE}_* value - see include/linux/irq.h + */ +int irq_set_irq_type(unsigned int irq, unsigned int type) +{ + unsigned long flags; + struct irq_desc *desc = irq_get_desc_buslock(irq, &flags, IRQ_GET_DESC_CHECK_GLOBAL); + int ret = 0; + + if (!desc) + return -EINVAL; + + type &= IRQ_TYPE_SENSE_MASK; + ret = __irq_set_trigger(desc, irq, type); + irq_put_desc_busunlock(desc, flags); + return ret; +} +EXPORT_SYMBOL(irq_set_irq_type); + +/** + * irq_set_handler_data - set irq handler data for an irq + * @irq: Interrupt number + * @data: Pointer to interrupt specific data + * + * Set the hardware irq controller data for an irq + */ +int irq_set_handler_data(unsigned int irq, void *data) +{ + unsigned long flags; + struct irq_desc *desc = irq_get_desc_lock(irq, &flags, 0); + + if (!desc) + return -EINVAL; + desc->irq_data.handler_data = data; + irq_put_desc_unlock(desc, flags); + return 0; +} +EXPORT_SYMBOL(irq_set_handler_data); + +/** + * irq_set_msi_desc_off - set MSI descriptor data for an irq at offset + * @irq_base: Interrupt number base + * @irq_offset: Interrupt number offset + * @entry: Pointer to MSI descriptor data + * + * Set the MSI descriptor entry for an irq at offset + */ +int irq_set_msi_desc_off(unsigned int irq_base, unsigned int irq_offset, + struct msi_desc *entry) +{ + unsigned long flags; + struct irq_desc *desc = irq_get_desc_lock(irq_base + irq_offset, &flags, IRQ_GET_DESC_CHECK_GLOBAL); + + if (!desc) + return -EINVAL; + desc->irq_data.msi_desc = entry; + if (entry && !irq_offset) + entry->irq = irq_base; + irq_put_desc_unlock(desc, flags); + return 0; +} + +/** + * irq_set_msi_desc - set MSI descriptor data for an irq + * @irq: Interrupt number + * @entry: Pointer to MSI descriptor data + * + * Set the MSI descriptor entry for an irq + */ +int irq_set_msi_desc(unsigned int irq, struct msi_desc *entry) +{ + return irq_set_msi_desc_off(irq, 0, entry); +} + +/** + * irq_set_chip_data - set irq chip data for an irq + * @irq: Interrupt number + * @data: Pointer to chip specific data + * + * Set the hardware irq chip data for an irq + */ +int irq_set_chip_data(unsigned int irq, void *data) +{ + unsigned long flags; + struct irq_desc *desc = irq_get_desc_lock(irq, &flags, 0); + + if (!desc) + return -EINVAL; + desc->irq_data.chip_data = data; + irq_put_desc_unlock(desc, flags); + return 0; +} +EXPORT_SYMBOL(irq_set_chip_data); + +struct irq_data *irq_get_irq_data(unsigned int irq) +{ + struct irq_desc *desc = irq_to_desc(irq); + + return desc ? &desc->irq_data : NULL; +} +EXPORT_SYMBOL_GPL(irq_get_irq_data); + +static void irq_state_clr_disabled(struct irq_desc *desc) +{ + irqd_clear(&desc->irq_data, IRQD_IRQ_DISABLED); +} + +static void irq_state_set_disabled(struct irq_desc *desc) +{ + irqd_set(&desc->irq_data, IRQD_IRQ_DISABLED); +} + +static void irq_state_clr_masked(struct irq_desc *desc) +{ + irqd_clear(&desc->irq_data, IRQD_IRQ_MASKED); +} + +static void irq_state_set_masked(struct irq_desc *desc) +{ + irqd_set(&desc->irq_data, IRQD_IRQ_MASKED); +} + +int irq_startup(struct irq_desc *desc, bool resend) +{ + int ret = 0; + + irq_state_clr_disabled(desc); + desc->depth = 0; + + irq_domain_activate_irq(&desc->irq_data); + if (desc->irq_data.chip->irq_startup) { + ret = desc->irq_data.chip->irq_startup(&desc->irq_data); + irq_state_clr_masked(desc); + } else { + irq_enable(desc); + } + if (resend) + check_irq_resend(desc, desc->irq_data.irq); + return ret; +} + +void irq_shutdown(struct irq_desc *desc) +{ + irq_state_set_disabled(desc); + desc->depth = 1; + if (desc->irq_data.chip->irq_shutdown) + desc->irq_data.chip->irq_shutdown(&desc->irq_data); + else if (desc->irq_data.chip->irq_disable) + desc->irq_data.chip->irq_disable(&desc->irq_data); + else + desc->irq_data.chip->irq_mask(&desc->irq_data); + irq_domain_deactivate_irq(&desc->irq_data); + irq_state_set_masked(desc); +} + +void irq_enable(struct irq_desc *desc) +{ + irq_state_clr_disabled(desc); + if (desc->irq_data.chip->irq_enable) + desc->irq_data.chip->irq_enable(&desc->irq_data); + else + desc->irq_data.chip->irq_unmask(&desc->irq_data); + irq_state_clr_masked(desc); +} + +/** + * irq_disable - Mark interrupt disabled + * @desc: irq descriptor which should be disabled + * + * If the chip does not implement the irq_disable callback, we + * use a lazy disable approach. That means we mark the interrupt + * disabled, but leave the hardware unmasked. That's an + * optimization because we avoid the hardware access for the + * common case where no interrupt happens after we marked it + * disabled. If an interrupt happens, then the interrupt flow + * handler masks the line at the hardware level and marks it + * pending. + */ +void irq_disable(struct irq_desc *desc) +{ + irq_state_set_disabled(desc); + if (desc->irq_data.chip->irq_disable) { + desc->irq_data.chip->irq_disable(&desc->irq_data); + irq_state_set_masked(desc); + } +} + +void irq_percpu_enable(struct irq_desc *desc, unsigned int cpu) +{ + if (desc->irq_data.chip->irq_enable) + desc->irq_data.chip->irq_enable(&desc->irq_data); + else + desc->irq_data.chip->irq_unmask(&desc->irq_data); + cpumask_set_cpu(cpu, desc->percpu_enabled); +} + +void irq_percpu_disable(struct irq_desc *desc, unsigned int cpu) +{ + if (desc->irq_data.chip->irq_disable) + desc->irq_data.chip->irq_disable(&desc->irq_data); + else + desc->irq_data.chip->irq_mask(&desc->irq_data); + cpumask_clear_cpu(cpu, desc->percpu_enabled); +} + +static inline void mask_ack_irq(struct irq_desc *desc) +{ + if (desc->irq_data.chip->irq_mask_ack) + desc->irq_data.chip->irq_mask_ack(&desc->irq_data); + else { + desc->irq_data.chip->irq_mask(&desc->irq_data); + if (desc->irq_data.chip->irq_ack) + desc->irq_data.chip->irq_ack(&desc->irq_data); + } + irq_state_set_masked(desc); +} + +void mask_irq(struct irq_desc *desc) +{ + if (desc->irq_data.chip->irq_mask) { + desc->irq_data.chip->irq_mask(&desc->irq_data); + irq_state_set_masked(desc); + } +} + +void unmask_irq(struct irq_desc *desc) +{ + if (desc->irq_data.chip->irq_unmask) { + desc->irq_data.chip->irq_unmask(&desc->irq_data); + irq_state_clr_masked(desc); + } +} + +void unmask_threaded_irq(struct irq_desc *desc) +{ + struct irq_chip *chip = desc->irq_data.chip; + + if (chip->flags & IRQCHIP_EOI_THREADED) + chip->irq_eoi(&desc->irq_data); + + if (chip->irq_unmask) { + chip->irq_unmask(&desc->irq_data); + irq_state_clr_masked(desc); + } +} + +/* + * handle_nested_irq - Handle a nested irq from a irq thread + * @irq: the interrupt number + * + * Handle interrupts which are nested into a threaded interrupt + * handler. The handler function is called inside the calling + * threads context. + */ +void handle_nested_irq(unsigned int irq) +{ + struct irq_desc *desc = irq_to_desc(irq); + struct irqaction *action; + irqreturn_t action_ret; + + might_sleep(); + + raw_spin_lock_irq(&desc->lock); + + desc->istate &= ~(IRQS_REPLAY | IRQS_WAITING); + kstat_incr_irqs_this_cpu(irq, desc); + + action = desc->action; + if (unlikely(!action || irqd_irq_disabled(&desc->irq_data))) { + desc->istate |= IRQS_PENDING; + goto out_unlock; + } + + irqd_set(&desc->irq_data, IRQD_IRQ_INPROGRESS); + raw_spin_unlock_irq(&desc->lock); + + action_ret = action->thread_fn(action->irq, action->dev_id); + if (!noirqdebug) + note_interrupt(irq, desc, action_ret); + + raw_spin_lock_irq(&desc->lock); + irqd_clear(&desc->irq_data, IRQD_IRQ_INPROGRESS); + +out_unlock: + raw_spin_unlock_irq(&desc->lock); +} +EXPORT_SYMBOL_GPL(handle_nested_irq); + +static bool irq_check_poll(struct irq_desc *desc) +{ + if (!(desc->istate & IRQS_POLL_INPROGRESS)) + return false; + return irq_wait_for_poll(desc); +} + +static bool irq_may_run(struct irq_desc *desc) +{ + unsigned int mask = IRQD_IRQ_INPROGRESS | IRQD_WAKEUP_ARMED; + + /* + * If the interrupt is not in progress and is not an armed + * wakeup interrupt, proceed. + */ + if (!irqd_has_set(&desc->irq_data, mask)) + return true; + + /* + * If the interrupt is an armed wakeup source, mark it pending + * and suspended, disable it and notify the pm core about the + * event. + */ + if (irq_pm_check_wakeup(desc)) + return false; + + /* + * Handle a potential concurrent poll on a different core. + */ + return irq_check_poll(desc); +} + +/** + * handle_simple_irq - Simple and software-decoded IRQs. + * @irq: the interrupt number + * @desc: the interrupt description structure for this irq + * + * Simple interrupts are either sent from a demultiplexing interrupt + * handler or come from hardware, where no interrupt hardware control + * is necessary. + * + * Note: The caller is expected to handle the ack, clear, mask and + * unmask issues if necessary. + */ +void +handle_simple_irq(unsigned int irq, struct irq_desc *desc) +{ + raw_spin_lock(&desc->lock); + + if (!irq_may_run(desc)) + goto out_unlock; + + desc->istate &= ~(IRQS_REPLAY | IRQS_WAITING); + kstat_incr_irqs_this_cpu(irq, desc); + + if (unlikely(!desc->action || irqd_irq_disabled(&desc->irq_data))) { + desc->istate |= IRQS_PENDING; + goto out_unlock; + } + + handle_irq_event(desc); + +out_unlock: + raw_spin_unlock(&desc->lock); +} +EXPORT_SYMBOL_GPL(handle_simple_irq); + +/* + * Called unconditionally from handle_level_irq() and only for oneshot + * interrupts from handle_fasteoi_irq() + */ +static void cond_unmask_irq(struct irq_desc *desc) +{ + /* + * We need to unmask in the following cases: + * - Standard level irq (IRQF_ONESHOT is not set) + * - Oneshot irq which did not wake the thread (caused by a + * spurious interrupt or a primary handler handling it + * completely). + */ + if (!irqd_irq_disabled(&desc->irq_data) && + irqd_irq_masked(&desc->irq_data) && !desc->threads_oneshot) + unmask_irq(desc); +} + +/** + * handle_level_irq - Level type irq handler + * @irq: the interrupt number + * @desc: the interrupt description structure for this irq + * + * Level type interrupts are active as long as the hardware line has + * the active level. This may require to mask the interrupt and unmask + * it after the associated handler has acknowledged the device, so the + * interrupt line is back to inactive. + */ +void +handle_level_irq(unsigned int irq, struct irq_desc *desc) +{ + raw_spin_lock(&desc->lock); + mask_ack_irq(desc); + + if (!irq_may_run(desc)) + goto out_unlock; + + desc->istate &= ~(IRQS_REPLAY | IRQS_WAITING); + kstat_incr_irqs_this_cpu(irq, desc); + + /* + * If its disabled or no action available + * keep it masked and get out of here + */ + if (unlikely(!desc->action || irqd_irq_disabled(&desc->irq_data))) { + desc->istate |= IRQS_PENDING; + goto out_unlock; + } + + handle_irq_event(desc); + + cond_unmask_irq(desc); + +out_unlock: + raw_spin_unlock(&desc->lock); +} +EXPORT_SYMBOL_GPL(handle_level_irq); + +#ifdef CONFIG_IRQ_PREFLOW_FASTEOI +static inline void preflow_handler(struct irq_desc *desc) +{ + if (desc->preflow_handler) + desc->preflow_handler(&desc->irq_data); +} +#else +static inline void preflow_handler(struct irq_desc *desc) { } +#endif + +static void cond_unmask_eoi_irq(struct irq_desc *desc, struct irq_chip *chip) +{ + if (!(desc->istate & IRQS_ONESHOT)) { + chip->irq_eoi(&desc->irq_data); + return; + } + /* + * We need to unmask in the following cases: + * - Oneshot irq which did not wake the thread (caused by a + * spurious interrupt or a primary handler handling it + * completely). + */ + if (!irqd_irq_disabled(&desc->irq_data) && + irqd_irq_masked(&desc->irq_data) && !desc->threads_oneshot) { + chip->irq_eoi(&desc->irq_data); + unmask_irq(desc); + } else if (!(chip->flags & IRQCHIP_EOI_THREADED)) { + chip->irq_eoi(&desc->irq_data); + } +} + +/** + * handle_fasteoi_irq - irq handler for transparent controllers + * @irq: the interrupt number + * @desc: the interrupt description structure for this irq + * + * Only a single callback will be issued to the chip: an ->eoi() + * call when the interrupt has been serviced. This enables support + * for modern forms of interrupt handlers, which handle the flow + * details in hardware, transparently. + */ +void +handle_fasteoi_irq(unsigned int irq, struct irq_desc *desc) +{ + struct irq_chip *chip = desc->irq_data.chip; + + raw_spin_lock(&desc->lock); + + if (!irq_may_run(desc)) + goto out; + + desc->istate &= ~(IRQS_REPLAY | IRQS_WAITING); + kstat_incr_irqs_this_cpu(irq, desc); + + /* + * If its disabled or no action available + * then mask it and get out of here: + */ + if (unlikely(!desc->action || irqd_irq_disabled(&desc->irq_data))) { + desc->istate |= IRQS_PENDING; + mask_irq(desc); + goto out; + } + + if (desc->istate & IRQS_ONESHOT) + mask_irq(desc); + + preflow_handler(desc); + handle_irq_event(desc); + + cond_unmask_eoi_irq(desc, chip); + + raw_spin_unlock(&desc->lock); + return; +out: + if (!(chip->flags & IRQCHIP_EOI_IF_HANDLED)) + chip->irq_eoi(&desc->irq_data); + raw_spin_unlock(&desc->lock); +} +EXPORT_SYMBOL_GPL(handle_fasteoi_irq); + +/** + * handle_edge_irq - edge type IRQ handler + * @irq: the interrupt number + * @desc: the interrupt description structure for this irq + * + * Interrupt occures on the falling and/or rising edge of a hardware + * signal. The occurrence is latched into the irq controller hardware + * and must be acked in order to be reenabled. After the ack another + * interrupt can happen on the same source even before the first one + * is handled by the associated event handler. If this happens it + * might be necessary to disable (mask) the interrupt depending on the + * controller hardware. This requires to reenable the interrupt inside + * of the loop which handles the interrupts which have arrived while + * the handler was running. If all pending interrupts are handled, the + * loop is left. + */ +void +handle_edge_irq(unsigned int irq, struct irq_desc *desc) +{ + raw_spin_lock(&desc->lock); + + desc->istate &= ~(IRQS_REPLAY | IRQS_WAITING); + + if (!irq_may_run(desc)) { + desc->istate |= IRQS_PENDING; + mask_ack_irq(desc); + goto out_unlock; + } + + /* + * If its disabled or no action available then mask it and get + * out of here. + */ + if (irqd_irq_disabled(&desc->irq_data) || !desc->action) { + desc->istate |= IRQS_PENDING; + mask_ack_irq(desc); + goto out_unlock; + } + + kstat_incr_irqs_this_cpu(irq, desc); + + /* Start handling the irq */ + desc->irq_data.chip->irq_ack(&desc->irq_data); + + do { + if (unlikely(!desc->action)) { + mask_irq(desc); + goto out_unlock; + } + + /* + * When another irq arrived while we were handling + * one, we could have masked the irq. + * Renable it, if it was not disabled in meantime. + */ + if (unlikely(desc->istate & IRQS_PENDING)) { + if (!irqd_irq_disabled(&desc->irq_data) && + irqd_irq_masked(&desc->irq_data)) + unmask_irq(desc); + } + + handle_irq_event(desc); + + } while ((desc->istate & IRQS_PENDING) && + !irqd_irq_disabled(&desc->irq_data)); + +out_unlock: + raw_spin_unlock(&desc->lock); +} +EXPORT_SYMBOL(handle_edge_irq); + +#ifdef CONFIG_IRQ_EDGE_EOI_HANDLER +/** + * handle_edge_eoi_irq - edge eoi type IRQ handler + * @irq: the interrupt number + * @desc: the interrupt description structure for this irq + * + * Similar as the above handle_edge_irq, but using eoi and w/o the + * mask/unmask logic. + */ +void handle_edge_eoi_irq(unsigned int irq, struct irq_desc *desc) +{ + struct irq_chip *chip = irq_desc_get_chip(desc); + + raw_spin_lock(&desc->lock); + + desc->istate &= ~(IRQS_REPLAY | IRQS_WAITING); + + if (!irq_may_run(desc)) { + desc->istate |= IRQS_PENDING; + goto out_eoi; + } + + /* + * If its disabled or no action available then mask it and get + * out of here. + */ + if (irqd_irq_disabled(&desc->irq_data) || !desc->action) { + desc->istate |= IRQS_PENDING; + goto out_eoi; + } + + kstat_incr_irqs_this_cpu(irq, desc); + + do { + if (unlikely(!desc->action)) + goto out_eoi; + + handle_irq_event(desc); + + } while ((desc->istate & IRQS_PENDING) && + !irqd_irq_disabled(&desc->irq_data)); + +out_eoi: + chip->irq_eoi(&desc->irq_data); + raw_spin_unlock(&desc->lock); +} +#endif + +/** + * handle_percpu_irq - Per CPU local irq handler + * @irq: the interrupt number + * @desc: the interrupt description structure for this irq + * + * Per CPU interrupts on SMP machines without locking requirements + */ +void +handle_percpu_irq(unsigned int irq, struct irq_desc *desc) +{ + struct irq_chip *chip = irq_desc_get_chip(desc); + + kstat_incr_irqs_this_cpu(irq, desc); + + if (chip->irq_ack) + chip->irq_ack(&desc->irq_data); + + handle_irq_event_percpu(desc, desc->action); + + if (chip->irq_eoi) + chip->irq_eoi(&desc->irq_data); +} + +/** + * handle_percpu_devid_irq - Per CPU local irq handler with per cpu dev ids + * @irq: the interrupt number + * @desc: the interrupt description structure for this irq + * + * Per CPU interrupts on SMP machines without locking requirements. Same as + * handle_percpu_irq() above but with the following extras: + * + * action->percpu_dev_id is a pointer to percpu variables which + * contain the real device id for the cpu on which this handler is + * called + */ +void handle_percpu_devid_irq(unsigned int irq, struct irq_desc *desc) +{ + struct irq_chip *chip = irq_desc_get_chip(desc); + struct irqaction *action = desc->action; + void *dev_id = raw_cpu_ptr(action->percpu_dev_id); + irqreturn_t res; + + kstat_incr_irqs_this_cpu(irq, desc); + + if (chip->irq_ack) + chip->irq_ack(&desc->irq_data); + + trace_irq_handler_entry(irq, action); + res = action->handler(irq, dev_id); + trace_irq_handler_exit(irq, action, res); + + if (chip->irq_eoi) + chip->irq_eoi(&desc->irq_data); +} + +void +__irq_set_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained, + const char *name) +{ + unsigned long flags; + struct irq_desc *desc = irq_get_desc_buslock(irq, &flags, 0); + + if (!desc) + return; + + if (!handle) { + handle = handle_bad_irq; + } else { + struct irq_data *irq_data = &desc->irq_data; +#ifdef CONFIG_IRQ_DOMAIN_HIERARCHY + /* + * With hierarchical domains we might run into a + * situation where the outermost chip is not yet set + * up, but the inner chips are there. Instead of + * bailing we install the handler, but obviously we + * cannot enable/startup the interrupt at this point. + */ + while (irq_data) { + if (irq_data->chip != &no_irq_chip) + break; + /* + * Bail out if the outer chip is not set up + * and the interrrupt supposed to be started + * right away. + */ + if (WARN_ON(is_chained)) + goto out; + /* Try the parent */ + irq_data = irq_data->parent_data; + } +#endif + if (WARN_ON(!irq_data || irq_data->chip == &no_irq_chip)) + goto out; + } + + /* Uninstall? */ + if (handle == handle_bad_irq) { + if (desc->irq_data.chip != &no_irq_chip) + mask_ack_irq(desc); + irq_state_set_disabled(desc); + desc->depth = 1; + } + desc->handle_irq = handle; + desc->name = name; + + if (handle != handle_bad_irq && is_chained) { + irq_settings_set_noprobe(desc); + irq_settings_set_norequest(desc); + irq_settings_set_nothread(desc); + irq_startup(desc, true); + } +out: + irq_put_desc_busunlock(desc, flags); +} +EXPORT_SYMBOL_GPL(__irq_set_handler); + +void +irq_set_chip_and_handler_name(unsigned int irq, struct irq_chip *chip, + irq_flow_handler_t handle, const char *name) +{ + irq_set_chip(irq, chip); + __irq_set_handler(irq, handle, 0, name); +} +EXPORT_SYMBOL_GPL(irq_set_chip_and_handler_name); + +void irq_modify_status(unsigned int irq, unsigned long clr, unsigned long set) +{ + unsigned long flags; + struct irq_desc *desc = irq_get_desc_lock(irq, &flags, 0); + + if (!desc) + return; + irq_settings_clr_and_set(desc, clr, set); + + irqd_clear(&desc->irq_data, IRQD_NO_BALANCING | IRQD_PER_CPU | + IRQD_TRIGGER_MASK | IRQD_LEVEL | IRQD_MOVE_PCNTXT); + if (irq_settings_has_no_balance_set(desc)) + irqd_set(&desc->irq_data, IRQD_NO_BALANCING); + if (irq_settings_is_per_cpu(desc)) + irqd_set(&desc->irq_data, IRQD_PER_CPU); + if (irq_settings_can_move_pcntxt(desc)) + irqd_set(&desc->irq_data, IRQD_MOVE_PCNTXT); + if (irq_settings_is_level(desc)) + irqd_set(&desc->irq_data, IRQD_LEVEL); + + irqd_set(&desc->irq_data, irq_settings_get_trigger_mask(desc)); + + irq_put_desc_unlock(desc, flags); +} +EXPORT_SYMBOL_GPL(irq_modify_status); + +/** + * irq_cpu_online - Invoke all irq_cpu_online functions. + * + * Iterate through all irqs and invoke the chip.irq_cpu_online() + * for each. + */ +void irq_cpu_online(void) +{ + struct irq_desc *desc; + struct irq_chip *chip; + unsigned long flags; + unsigned int irq; + + for_each_active_irq(irq) { + desc = irq_to_desc(irq); + if (!desc) + continue; + + raw_spin_lock_irqsave(&desc->lock, flags); + + chip = irq_data_get_irq_chip(&desc->irq_data); + if (chip && chip->irq_cpu_online && + (!(chip->flags & IRQCHIP_ONOFFLINE_ENABLED) || + !irqd_irq_disabled(&desc->irq_data))) + chip->irq_cpu_online(&desc->irq_data); + + raw_spin_unlock_irqrestore(&desc->lock, flags); + } +} + +/** + * irq_cpu_offline - Invoke all irq_cpu_offline functions. + * + * Iterate through all irqs and invoke the chip.irq_cpu_offline() + * for each. + */ +void irq_cpu_offline(void) +{ + struct irq_desc *desc; + struct irq_chip *chip; + unsigned long flags; + unsigned int irq; + + for_each_active_irq(irq) { + desc = irq_to_desc(irq); + if (!desc) + continue; + + raw_spin_lock_irqsave(&desc->lock, flags); + + chip = irq_data_get_irq_chip(&desc->irq_data); + if (chip && chip->irq_cpu_offline && + (!(chip->flags & IRQCHIP_ONOFFLINE_ENABLED) || + !irqd_irq_disabled(&desc->irq_data))) + chip->irq_cpu_offline(&desc->irq_data); + + raw_spin_unlock_irqrestore(&desc->lock, flags); + } +} + +#ifdef CONFIG_IRQ_DOMAIN_HIERARCHY +/** + * irq_chip_ack_parent - Acknowledge the parent interrupt + * @data: Pointer to interrupt specific data + */ +void irq_chip_ack_parent(struct irq_data *data) +{ + data = data->parent_data; + data->chip->irq_ack(data); +} + +/** + * irq_chip_mask_parent - Mask the parent interrupt + * @data: Pointer to interrupt specific data + */ +void irq_chip_mask_parent(struct irq_data *data) +{ + data = data->parent_data; + data->chip->irq_mask(data); +} + +/** + * irq_chip_unmask_parent - Unmask the parent interrupt + * @data: Pointer to interrupt specific data + */ +void irq_chip_unmask_parent(struct irq_data *data) +{ + data = data->parent_data; + data->chip->irq_unmask(data); +} + +/** + * irq_chip_eoi_parent - Invoke EOI on the parent interrupt + * @data: Pointer to interrupt specific data + */ +void irq_chip_eoi_parent(struct irq_data *data) +{ + data = data->parent_data; + data->chip->irq_eoi(data); +} + +/** + * irq_chip_set_affinity_parent - Set affinity on the parent interrupt + * @data: Pointer to interrupt specific data + * @dest: The affinity mask to set + * @force: Flag to enforce setting (disable online checks) + * + * Conditinal, as the underlying parent chip might not implement it. + */ +int irq_chip_set_affinity_parent(struct irq_data *data, + const struct cpumask *dest, bool force) +{ + data = data->parent_data; + if (data->chip->irq_set_affinity) + return data->chip->irq_set_affinity(data, dest, force); + + return -ENOSYS; +} + +/** + * irq_chip_retrigger_hierarchy - Retrigger an interrupt in hardware + * @data: Pointer to interrupt specific data + * + * Iterate through the domain hierarchy of the interrupt and check + * whether a hw retrigger function exists. If yes, invoke it. + */ +int irq_chip_retrigger_hierarchy(struct irq_data *data) +{ + for (data = data->parent_data; data; data = data->parent_data) + if (data->chip && data->chip->irq_retrigger) + return data->chip->irq_retrigger(data); + + return -ENOSYS; +} + +/** + * irq_chip_set_wake_parent - Set/reset wake-up on the parent interrupt + * @data: Pointer to interrupt specific data + * @on: Whether to set or reset the wake-up capability of this irq + * + * Conditional, as the underlying parent chip might not implement it. + */ +int irq_chip_set_wake_parent(struct irq_data *data, unsigned int on) +{ + data = data->parent_data; + if (data->chip->irq_set_wake) + return data->chip->irq_set_wake(data, on); + + return -ENOSYS; +} +#endif + +/** + * irq_chip_compose_msi_msg - Componse msi message for a irq chip + * @data: Pointer to interrupt specific data + * @msg: Pointer to the MSI message + * + * For hierarchical domains we find the first chip in the hierarchy + * which implements the irq_compose_msi_msg callback. For non + * hierarchical we use the top level chip. + */ +int irq_chip_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) +{ + struct irq_data *pos = NULL; + +#ifdef CONFIG_IRQ_DOMAIN_HIERARCHY + for (; data; data = data->parent_data) +#endif + if (data->chip && data->chip->irq_compose_msi_msg) + pos = data; + if (!pos) + return -ENOSYS; + + pos->chip->irq_compose_msi_msg(pos, msg); + + return 0; +} diff --git a/kernel/kernel/irq/debug.h b/kernel/kernel/irq/debug.h new file mode 100644 index 000000000..e75e29e44 --- /dev/null +++ b/kernel/kernel/irq/debug.h @@ -0,0 +1,45 @@ +/* + * Debugging printout: + */ + +#include + +#define ___P(f) if (desc->status_use_accessors & f) printk("%14s set\n", #f) +#define ___PS(f) if (desc->istate & f) printk("%14s set\n", #f) +/* FIXME */ +#define ___PD(f) do { } while (0) + +static inline void print_irq_desc(unsigned int irq, struct irq_desc *desc) +{ + printk("irq %d, desc: %p, depth: %d, count: %d, unhandled: %d\n", + irq, desc, desc->depth, desc->irq_count, desc->irqs_unhandled); + printk("->handle_irq(): %p, ", desc->handle_irq); + print_symbol("%s\n", (unsigned long)desc->handle_irq); + printk("->irq_data.chip(): %p, ", desc->irq_data.chip); + print_symbol("%s\n", (unsigned long)desc->irq_data.chip); + printk("->action(): %p\n", desc->action); + if (desc->action) { + printk("->action->handler(): %p, ", desc->action->handler); + print_symbol("%s\n", (unsigned long)desc->action->handler); + } + + ___P(IRQ_LEVEL); + ___P(IRQ_PER_CPU); + ___P(IRQ_NOPROBE); + ___P(IRQ_NOREQUEST); + ___P(IRQ_NOTHREAD); + ___P(IRQ_NOAUTOEN); + + ___PS(IRQS_AUTODETECT); + ___PS(IRQS_REPLAY); + ___PS(IRQS_WAITING); + ___PS(IRQS_PENDING); + + ___PD(IRQS_INPROGRESS); + ___PD(IRQS_DISABLED); + ___PD(IRQS_MASKED); +} + +#undef ___P +#undef ___PS +#undef ___PD diff --git a/kernel/kernel/irq/devres.c b/kernel/kernel/irq/devres.c new file mode 100644 index 000000000..74d90a754 --- /dev/null +++ b/kernel/kernel/irq/devres.c @@ -0,0 +1,139 @@ +#include +#include +#include +#include + +/* + * Device resource management aware IRQ request/free implementation. + */ +struct irq_devres { + unsigned int irq; + void *dev_id; +}; + +static void devm_irq_release(struct device *dev, void *res) +{ + struct irq_devres *this = res; + + free_irq(this->irq, this->dev_id); +} + +static int devm_irq_match(struct device *dev, void *res, void *data) +{ + struct irq_devres *this = res, *match = data; + + return this->irq == match->irq && this->dev_id == match->dev_id; +} + +/** + * devm_request_threaded_irq - allocate an interrupt line for a managed device + * @dev: device to request interrupt for + * @irq: Interrupt line to allocate + * @handler: Function to be called when the IRQ occurs + * @thread_fn: function to be called in a threaded interrupt context. NULL + * for devices which handle everything in @handler + * @irqflags: Interrupt type flags + * @devname: An ascii name for the claiming device + * @dev_id: A cookie passed back to the handler function + * + * Except for the extra @dev argument, this function takes the + * same arguments and performs the same function as + * request_threaded_irq(). IRQs requested with this function will be + * automatically freed on driver detach. + * + * If an IRQ allocated with this function needs to be freed + * separately, devm_free_irq() must be used. + */ +int devm_request_threaded_irq(struct device *dev, unsigned int irq, + irq_handler_t handler, irq_handler_t thread_fn, + unsigned long irqflags, const char *devname, + void *dev_id) +{ + struct irq_devres *dr; + int rc; + + dr = devres_alloc(devm_irq_release, sizeof(struct irq_devres), + GFP_KERNEL); + if (!dr) + return -ENOMEM; + + rc = request_threaded_irq(irq, handler, thread_fn, irqflags, devname, + dev_id); + if (rc) { + devres_free(dr); + return rc; + } + + dr->irq = irq; + dr->dev_id = dev_id; + devres_add(dev, dr); + + return 0; +} +EXPORT_SYMBOL(devm_request_threaded_irq); + +/** + * devm_request_any_context_irq - allocate an interrupt line for a managed device + * @dev: device to request interrupt for + * @irq: Interrupt line to allocate + * @handler: Function to be called when the IRQ occurs + * @thread_fn: function to be called in a threaded interrupt context. NULL + * for devices which handle everything in @handler + * @irqflags: Interrupt type flags + * @devname: An ascii name for the claiming device + * @dev_id: A cookie passed back to the handler function + * + * Except for the extra @dev argument, this function takes the + * same arguments and performs the same function as + * request_any_context_irq(). IRQs requested with this function will be + * automatically freed on driver detach. + * + * If an IRQ allocated with this function needs to be freed + * separately, devm_free_irq() must be used. + */ +int devm_request_any_context_irq(struct device *dev, unsigned int irq, + irq_handler_t handler, unsigned long irqflags, + const char *devname, void *dev_id) +{ + struct irq_devres *dr; + int rc; + + dr = devres_alloc(devm_irq_release, sizeof(struct irq_devres), + GFP_KERNEL); + if (!dr) + return -ENOMEM; + + rc = request_any_context_irq(irq, handler, irqflags, devname, dev_id); + if (rc < 0) { + devres_free(dr); + return rc; + } + + dr->irq = irq; + dr->dev_id = dev_id; + devres_add(dev, dr); + + return rc; +} +EXPORT_SYMBOL(devm_request_any_context_irq); + +/** + * devm_free_irq - free an interrupt + * @dev: device to free interrupt for + * @irq: Interrupt line to free + * @dev_id: Device identity to free + * + * Except for the extra @dev argument, this function takes the + * same arguments and performs the same function as free_irq(). + * This function instead of free_irq() should be used to manually + * free IRQs allocated with devm_request_irq(). + */ +void devm_free_irq(struct device *dev, unsigned int irq, void *dev_id) +{ + struct irq_devres match_data = { irq, dev_id }; + + WARN_ON(devres_destroy(dev, devm_irq_release, devm_irq_match, + &match_data)); + free_irq(irq, dev_id); +} +EXPORT_SYMBOL(devm_free_irq); diff --git a/kernel/kernel/irq/dummychip.c b/kernel/kernel/irq/dummychip.c new file mode 100644 index 000000000..2feb6feca --- /dev/null +++ b/kernel/kernel/irq/dummychip.c @@ -0,0 +1,62 @@ +/* + * Copyright (C) 1992, 1998-2006 Linus Torvalds, Ingo Molnar + * Copyright (C) 2005-2006, Thomas Gleixner, Russell King + * + * This file contains the dummy interrupt chip implementation + */ +#include +#include +#include + +#include "internals.h" + +/* + * What should we do if we get a hw irq event on an illegal vector? + * Each architecture has to answer this themself. + */ +static void ack_bad(struct irq_data *data) +{ + struct irq_desc *desc = irq_data_to_desc(data); + + print_irq_desc(data->irq, desc); + ack_bad_irq(data->irq); +} + +/* + * NOP functions + */ +static void noop(struct irq_data *data) { } + +static unsigned int noop_ret(struct irq_data *data) +{ + return 0; +} + +/* + * Generic no controller implementation + */ +struct irq_chip no_irq_chip = { + .name = "none", + .irq_startup = noop_ret, + .irq_shutdown = noop, + .irq_enable = noop, + .irq_disable = noop, + .irq_ack = ack_bad, +}; + +/* + * Generic dummy implementation which can be used for + * real dumb interrupt sources + */ +struct irq_chip dummy_irq_chip = { + .name = "dummy", + .irq_startup = noop_ret, + .irq_shutdown = noop, + .irq_enable = noop, + .irq_disable = noop, + .irq_ack = noop, + .irq_mask = noop, + .irq_unmask = noop, + .flags = IRQCHIP_SKIP_SET_WAKE, +}; +EXPORT_SYMBOL_GPL(dummy_irq_chip); diff --git a/kernel/kernel/irq/generic-chip.c b/kernel/kernel/irq/generic-chip.c new file mode 100644 index 000000000..61024e8ab --- /dev/null +++ b/kernel/kernel/irq/generic-chip.c @@ -0,0 +1,608 @@ +/* + * Library implementing the most common irq chip callback functions + * + * Copyright (C) 2011, Thomas Gleixner + */ +#include +#include +#include +#include +#include +#include +#include +#include + +#include "internals.h" + +static LIST_HEAD(gc_list); +static DEFINE_RAW_SPINLOCK(gc_lock); + +/** + * irq_gc_noop - NOOP function + * @d: irq_data + */ +void irq_gc_noop(struct irq_data *d) +{ +} + +/** + * irq_gc_mask_disable_reg - Mask chip via disable register + * @d: irq_data + * + * Chip has separate enable/disable registers instead of a single mask + * register. + */ +void irq_gc_mask_disable_reg(struct irq_data *d) +{ + struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d); + struct irq_chip_type *ct = irq_data_get_chip_type(d); + u32 mask = d->mask; + + irq_gc_lock(gc); + irq_reg_writel(gc, mask, ct->regs.disable); + *ct->mask_cache &= ~mask; + irq_gc_unlock(gc); +} + +/** + * irq_gc_mask_set_bit - Mask chip via setting bit in mask register + * @d: irq_data + * + * Chip has a single mask register. Values of this register are cached + * and protected by gc->lock + */ +void irq_gc_mask_set_bit(struct irq_data *d) +{ + struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d); + struct irq_chip_type *ct = irq_data_get_chip_type(d); + u32 mask = d->mask; + + irq_gc_lock(gc); + *ct->mask_cache |= mask; + irq_reg_writel(gc, *ct->mask_cache, ct->regs.mask); + irq_gc_unlock(gc); +} +EXPORT_SYMBOL_GPL(irq_gc_mask_set_bit); + +/** + * irq_gc_mask_clr_bit - Mask chip via clearing bit in mask register + * @d: irq_data + * + * Chip has a single mask register. Values of this register are cached + * and protected by gc->lock + */ +void irq_gc_mask_clr_bit(struct irq_data *d) +{ + struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d); + struct irq_chip_type *ct = irq_data_get_chip_type(d); + u32 mask = d->mask; + + irq_gc_lock(gc); + *ct->mask_cache &= ~mask; + irq_reg_writel(gc, *ct->mask_cache, ct->regs.mask); + irq_gc_unlock(gc); +} +EXPORT_SYMBOL_GPL(irq_gc_mask_clr_bit); + +/** + * irq_gc_unmask_enable_reg - Unmask chip via enable register + * @d: irq_data + * + * Chip has separate enable/disable registers instead of a single mask + * register. + */ +void irq_gc_unmask_enable_reg(struct irq_data *d) +{ + struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d); + struct irq_chip_type *ct = irq_data_get_chip_type(d); + u32 mask = d->mask; + + irq_gc_lock(gc); + irq_reg_writel(gc, mask, ct->regs.enable); + *ct->mask_cache |= mask; + irq_gc_unlock(gc); +} + +/** + * irq_gc_ack_set_bit - Ack pending interrupt via setting bit + * @d: irq_data + */ +void irq_gc_ack_set_bit(struct irq_data *d) +{ + struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d); + struct irq_chip_type *ct = irq_data_get_chip_type(d); + u32 mask = d->mask; + + irq_gc_lock(gc); + irq_reg_writel(gc, mask, ct->regs.ack); + irq_gc_unlock(gc); +} +EXPORT_SYMBOL_GPL(irq_gc_ack_set_bit); + +/** + * irq_gc_ack_clr_bit - Ack pending interrupt via clearing bit + * @d: irq_data + */ +void irq_gc_ack_clr_bit(struct irq_data *d) +{ + struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d); + struct irq_chip_type *ct = irq_data_get_chip_type(d); + u32 mask = ~d->mask; + + irq_gc_lock(gc); + irq_reg_writel(gc, mask, ct->regs.ack); + irq_gc_unlock(gc); +} + +/** + * irq_gc_mask_disable_reg_and_ack - Mask and ack pending interrupt + * @d: irq_data + */ +void irq_gc_mask_disable_reg_and_ack(struct irq_data *d) +{ + struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d); + struct irq_chip_type *ct = irq_data_get_chip_type(d); + u32 mask = d->mask; + + irq_gc_lock(gc); + irq_reg_writel(gc, mask, ct->regs.mask); + irq_reg_writel(gc, mask, ct->regs.ack); + irq_gc_unlock(gc); +} + +/** + * irq_gc_eoi - EOI interrupt + * @d: irq_data + */ +void irq_gc_eoi(struct irq_data *d) +{ + struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d); + struct irq_chip_type *ct = irq_data_get_chip_type(d); + u32 mask = d->mask; + + irq_gc_lock(gc); + irq_reg_writel(gc, mask, ct->regs.eoi); + irq_gc_unlock(gc); +} + +/** + * irq_gc_set_wake - Set/clr wake bit for an interrupt + * @d: irq_data + * @on: Indicates whether the wake bit should be set or cleared + * + * For chips where the wake from suspend functionality is not + * configured in a separate register and the wakeup active state is + * just stored in a bitmask. + */ +int irq_gc_set_wake(struct irq_data *d, unsigned int on) +{ + struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d); + u32 mask = d->mask; + + if (!(mask & gc->wake_enabled)) + return -EINVAL; + + irq_gc_lock(gc); + if (on) + gc->wake_active |= mask; + else + gc->wake_active &= ~mask; + irq_gc_unlock(gc); + return 0; +} + +static u32 irq_readl_be(void __iomem *addr) +{ + return ioread32be(addr); +} + +static void irq_writel_be(u32 val, void __iomem *addr) +{ + iowrite32be(val, addr); +} + +static void +irq_init_generic_chip(struct irq_chip_generic *gc, const char *name, + int num_ct, unsigned int irq_base, + void __iomem *reg_base, irq_flow_handler_t handler) +{ + raw_spin_lock_init(&gc->lock); + gc->num_ct = num_ct; + gc->irq_base = irq_base; + gc->reg_base = reg_base; + gc->chip_types->chip.name = name; + gc->chip_types->handler = handler; +} + +/** + * irq_alloc_generic_chip - Allocate a generic chip and initialize it + * @name: Name of the irq chip + * @num_ct: Number of irq_chip_type instances associated with this + * @irq_base: Interrupt base nr for this chip + * @reg_base: Register base address (virtual) + * @handler: Default flow handler associated with this chip + * + * Returns an initialized irq_chip_generic structure. The chip defaults + * to the primary (index 0) irq_chip_type and @handler + */ +struct irq_chip_generic * +irq_alloc_generic_chip(const char *name, int num_ct, unsigned int irq_base, + void __iomem *reg_base, irq_flow_handler_t handler) +{ + struct irq_chip_generic *gc; + unsigned long sz = sizeof(*gc) + num_ct * sizeof(struct irq_chip_type); + + gc = kzalloc(sz, GFP_KERNEL); + if (gc) { + irq_init_generic_chip(gc, name, num_ct, irq_base, reg_base, + handler); + } + return gc; +} +EXPORT_SYMBOL_GPL(irq_alloc_generic_chip); + +static void +irq_gc_init_mask_cache(struct irq_chip_generic *gc, enum irq_gc_flags flags) +{ + struct irq_chip_type *ct = gc->chip_types; + u32 *mskptr = &gc->mask_cache, mskreg = ct->regs.mask; + int i; + + for (i = 0; i < gc->num_ct; i++) { + if (flags & IRQ_GC_MASK_CACHE_PER_TYPE) { + mskptr = &ct[i].mask_cache_priv; + mskreg = ct[i].regs.mask; + } + ct[i].mask_cache = mskptr; + if (flags & IRQ_GC_INIT_MASK_CACHE) + *mskptr = irq_reg_readl(gc, mskreg); + } +} + +/** + * irq_alloc_domain_generic_chip - Allocate generic chips for an irq domain + * @d: irq domain for which to allocate chips + * @irqs_per_chip: Number of interrupts each chip handles + * @num_ct: Number of irq_chip_type instances associated with this + * @name: Name of the irq chip + * @handler: Default flow handler associated with these chips + * @clr: IRQ_* bits to clear in the mapping function + * @set: IRQ_* bits to set in the mapping function + * @gcflags: Generic chip specific setup flags + */ +int irq_alloc_domain_generic_chips(struct irq_domain *d, int irqs_per_chip, + int num_ct, const char *name, + irq_flow_handler_t handler, + unsigned int clr, unsigned int set, + enum irq_gc_flags gcflags) +{ + struct irq_domain_chip_generic *dgc; + struct irq_chip_generic *gc; + int numchips, sz, i; + unsigned long flags; + void *tmp; + + if (d->gc) + return -EBUSY; + + numchips = DIV_ROUND_UP(d->revmap_size, irqs_per_chip); + if (!numchips) + return -EINVAL; + + /* Allocate a pointer, generic chip and chiptypes for each chip */ + sz = sizeof(*dgc) + numchips * sizeof(gc); + sz += numchips * (sizeof(*gc) + num_ct * sizeof(struct irq_chip_type)); + + tmp = dgc = kzalloc(sz, GFP_KERNEL); + if (!dgc) + return -ENOMEM; + dgc->irqs_per_chip = irqs_per_chip; + dgc->num_chips = numchips; + dgc->irq_flags_to_set = set; + dgc->irq_flags_to_clear = clr; + dgc->gc_flags = gcflags; + d->gc = dgc; + + /* Calc pointer to the first generic chip */ + tmp += sizeof(*dgc) + numchips * sizeof(gc); + for (i = 0; i < numchips; i++) { + /* Store the pointer to the generic chip */ + dgc->gc[i] = gc = tmp; + irq_init_generic_chip(gc, name, num_ct, i * irqs_per_chip, + NULL, handler); + + gc->domain = d; + if (gcflags & IRQ_GC_BE_IO) { + gc->reg_readl = &irq_readl_be; + gc->reg_writel = &irq_writel_be; + } + + raw_spin_lock_irqsave(&gc_lock, flags); + list_add_tail(&gc->list, &gc_list); + raw_spin_unlock_irqrestore(&gc_lock, flags); + /* Calc pointer to the next generic chip */ + tmp += sizeof(*gc) + num_ct * sizeof(struct irq_chip_type); + } + d->name = name; + return 0; +} +EXPORT_SYMBOL_GPL(irq_alloc_domain_generic_chips); + +/** + * irq_get_domain_generic_chip - Get a pointer to the generic chip of a hw_irq + * @d: irq domain pointer + * @hw_irq: Hardware interrupt number + */ +struct irq_chip_generic * +irq_get_domain_generic_chip(struct irq_domain *d, unsigned int hw_irq) +{ + struct irq_domain_chip_generic *dgc = d->gc; + int idx; + + if (!dgc) + return NULL; + idx = hw_irq / dgc->irqs_per_chip; + if (idx >= dgc->num_chips) + return NULL; + return dgc->gc[idx]; +} +EXPORT_SYMBOL_GPL(irq_get_domain_generic_chip); + +/* + * Separate lockdep class for interrupt chip which can nest irq_desc + * lock. + */ +static struct lock_class_key irq_nested_lock_class; + +/* + * irq_map_generic_chip - Map a generic chip for an irq domain + */ +int irq_map_generic_chip(struct irq_domain *d, unsigned int virq, + irq_hw_number_t hw_irq) +{ + struct irq_data *data = irq_get_irq_data(virq); + struct irq_domain_chip_generic *dgc = d->gc; + struct irq_chip_generic *gc; + struct irq_chip_type *ct; + struct irq_chip *chip; + unsigned long flags; + int idx; + + if (!d->gc) + return -ENODEV; + + idx = hw_irq / dgc->irqs_per_chip; + if (idx >= dgc->num_chips) + return -EINVAL; + gc = dgc->gc[idx]; + + idx = hw_irq % dgc->irqs_per_chip; + + if (test_bit(idx, &gc->unused)) + return -ENOTSUPP; + + if (test_bit(idx, &gc->installed)) + return -EBUSY; + + ct = gc->chip_types; + chip = &ct->chip; + + /* We only init the cache for the first mapping of a generic chip */ + if (!gc->installed) { + raw_spin_lock_irqsave(&gc->lock, flags); + irq_gc_init_mask_cache(gc, dgc->gc_flags); + raw_spin_unlock_irqrestore(&gc->lock, flags); + } + + /* Mark the interrupt as installed */ + set_bit(idx, &gc->installed); + + if (dgc->gc_flags & IRQ_GC_INIT_NESTED_LOCK) + irq_set_lockdep_class(virq, &irq_nested_lock_class); + + if (chip->irq_calc_mask) + chip->irq_calc_mask(data); + else + data->mask = 1 << idx; + + irq_set_chip_and_handler(virq, chip, ct->handler); + irq_set_chip_data(virq, gc); + irq_modify_status(virq, dgc->irq_flags_to_clear, dgc->irq_flags_to_set); + return 0; +} +EXPORT_SYMBOL_GPL(irq_map_generic_chip); + +struct irq_domain_ops irq_generic_chip_ops = { + .map = irq_map_generic_chip, + .xlate = irq_domain_xlate_onetwocell, +}; +EXPORT_SYMBOL_GPL(irq_generic_chip_ops); + +/** + * irq_setup_generic_chip - Setup a range of interrupts with a generic chip + * @gc: Generic irq chip holding all data + * @msk: Bitmask holding the irqs to initialize relative to gc->irq_base + * @flags: Flags for initialization + * @clr: IRQ_* bits to clear + * @set: IRQ_* bits to set + * + * Set up max. 32 interrupts starting from gc->irq_base. Note, this + * initializes all interrupts to the primary irq_chip_type and its + * associated handler. + */ +void irq_setup_generic_chip(struct irq_chip_generic *gc, u32 msk, + enum irq_gc_flags flags, unsigned int clr, + unsigned int set) +{ + struct irq_chip_type *ct = gc->chip_types; + struct irq_chip *chip = &ct->chip; + unsigned int i; + + raw_spin_lock(&gc_lock); + list_add_tail(&gc->list, &gc_list); + raw_spin_unlock(&gc_lock); + + irq_gc_init_mask_cache(gc, flags); + + for (i = gc->irq_base; msk; msk >>= 1, i++) { + if (!(msk & 0x01)) + continue; + + if (flags & IRQ_GC_INIT_NESTED_LOCK) + irq_set_lockdep_class(i, &irq_nested_lock_class); + + if (!(flags & IRQ_GC_NO_MASK)) { + struct irq_data *d = irq_get_irq_data(i); + + if (chip->irq_calc_mask) + chip->irq_calc_mask(d); + else + d->mask = 1 << (i - gc->irq_base); + } + irq_set_chip_and_handler(i, chip, ct->handler); + irq_set_chip_data(i, gc); + irq_modify_status(i, clr, set); + } + gc->irq_cnt = i - gc->irq_base; +} +EXPORT_SYMBOL_GPL(irq_setup_generic_chip); + +/** + * irq_setup_alt_chip - Switch to alternative chip + * @d: irq_data for this interrupt + * @type: Flow type to be initialized + * + * Only to be called from chip->irq_set_type() callbacks. + */ +int irq_setup_alt_chip(struct irq_data *d, unsigned int type) +{ + struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d); + struct irq_chip_type *ct = gc->chip_types; + unsigned int i; + + for (i = 0; i < gc->num_ct; i++, ct++) { + if (ct->type & type) { + d->chip = &ct->chip; + irq_data_to_desc(d)->handle_irq = ct->handler; + return 0; + } + } + return -EINVAL; +} +EXPORT_SYMBOL_GPL(irq_setup_alt_chip); + +/** + * irq_remove_generic_chip - Remove a chip + * @gc: Generic irq chip holding all data + * @msk: Bitmask holding the irqs to initialize relative to gc->irq_base + * @clr: IRQ_* bits to clear + * @set: IRQ_* bits to set + * + * Remove up to 32 interrupts starting from gc->irq_base. + */ +void irq_remove_generic_chip(struct irq_chip_generic *gc, u32 msk, + unsigned int clr, unsigned int set) +{ + unsigned int i = gc->irq_base; + + raw_spin_lock(&gc_lock); + list_del(&gc->list); + raw_spin_unlock(&gc_lock); + + for (; msk; msk >>= 1, i++) { + if (!(msk & 0x01)) + continue; + + /* Remove handler first. That will mask the irq line */ + irq_set_handler(i, NULL); + irq_set_chip(i, &no_irq_chip); + irq_set_chip_data(i, NULL); + irq_modify_status(i, clr, set); + } +} +EXPORT_SYMBOL_GPL(irq_remove_generic_chip); + +static struct irq_data *irq_gc_get_irq_data(struct irq_chip_generic *gc) +{ + unsigned int virq; + + if (!gc->domain) + return irq_get_irq_data(gc->irq_base); + + /* + * We don't know which of the irqs has been actually + * installed. Use the first one. + */ + if (!gc->installed) + return NULL; + + virq = irq_find_mapping(gc->domain, gc->irq_base + __ffs(gc->installed)); + return virq ? irq_get_irq_data(virq) : NULL; +} + +#ifdef CONFIG_PM +static int irq_gc_suspend(void) +{ + struct irq_chip_generic *gc; + + list_for_each_entry(gc, &gc_list, list) { + struct irq_chip_type *ct = gc->chip_types; + + if (ct->chip.irq_suspend) { + struct irq_data *data = irq_gc_get_irq_data(gc); + + if (data) + ct->chip.irq_suspend(data); + } + } + return 0; +} + +static void irq_gc_resume(void) +{ + struct irq_chip_generic *gc; + + list_for_each_entry(gc, &gc_list, list) { + struct irq_chip_type *ct = gc->chip_types; + + if (ct->chip.irq_resume) { + struct irq_data *data = irq_gc_get_irq_data(gc); + + if (data) + ct->chip.irq_resume(data); + } + } +} +#else +#define irq_gc_suspend NULL +#define irq_gc_resume NULL +#endif + +static void irq_gc_shutdown(void) +{ + struct irq_chip_generic *gc; + + list_for_each_entry(gc, &gc_list, list) { + struct irq_chip_type *ct = gc->chip_types; + + if (ct->chip.irq_pm_shutdown) { + struct irq_data *data = irq_gc_get_irq_data(gc); + + if (data) + ct->chip.irq_pm_shutdown(data); + } + } +} + +static struct syscore_ops irq_gc_syscore_ops = { + .suspend = irq_gc_suspend, + .resume = irq_gc_resume, + .shutdown = irq_gc_shutdown, +}; + +static int __init irq_gc_init_ops(void) +{ + register_syscore_ops(&irq_gc_syscore_ops); + return 0; +} +device_initcall(irq_gc_init_ops); diff --git a/kernel/kernel/irq/handle.c b/kernel/kernel/irq/handle.c new file mode 100644 index 000000000..26a63672c --- /dev/null +++ b/kernel/kernel/irq/handle.c @@ -0,0 +1,203 @@ +/* + * linux/kernel/irq/handle.c + * + * Copyright (C) 1992, 1998-2006 Linus Torvalds, Ingo Molnar + * Copyright (C) 2005-2006, Thomas Gleixner, Russell King + * + * This file contains the core interrupt handling code. + * + * Detailed information is available in Documentation/DocBook/genericirq + * + */ + +#include +#include +#include +#include +#include + +#include + +#include "internals.h" + +/** + * handle_bad_irq - handle spurious and unhandled irqs + * @irq: the interrupt number + * @desc: description of the interrupt + * + * Handles spurious and unhandled IRQ's. It also prints a debugmessage. + */ +void handle_bad_irq(unsigned int irq, struct irq_desc *desc) +{ + print_irq_desc(irq, desc); + kstat_incr_irqs_this_cpu(irq, desc); + ack_bad_irq(irq); +} + +/* + * Special, empty irq handler: + */ +irqreturn_t no_action(int cpl, void *dev_id) +{ + return IRQ_NONE; +} +EXPORT_SYMBOL_GPL(no_action); + +static void warn_no_thread(unsigned int irq, struct irqaction *action) +{ + if (test_and_set_bit(IRQTF_WARNED, &action->thread_flags)) + return; + + printk(KERN_WARNING "IRQ %d device %s returned IRQ_WAKE_THREAD " + "but no thread function available.", irq, action->name); +} + +void __irq_wake_thread(struct irq_desc *desc, struct irqaction *action) +{ + /* + * In case the thread crashed and was killed we just pretend that + * we handled the interrupt. The hardirq handler has disabled the + * device interrupt, so no irq storm is lurking. + */ + if (action->thread->flags & PF_EXITING) + return; + + /* + * Wake up the handler thread for this action. If the + * RUNTHREAD bit is already set, nothing to do. + */ + if (test_and_set_bit(IRQTF_RUNTHREAD, &action->thread_flags)) + return; + + /* + * It's safe to OR the mask lockless here. We have only two + * places which write to threads_oneshot: This code and the + * irq thread. + * + * This code is the hard irq context and can never run on two + * cpus in parallel. If it ever does we have more serious + * problems than this bitmask. + * + * The irq threads of this irq which clear their "running" bit + * in threads_oneshot are serialized via desc->lock against + * each other and they are serialized against this code by + * IRQS_INPROGRESS. + * + * Hard irq handler: + * + * spin_lock(desc->lock); + * desc->state |= IRQS_INPROGRESS; + * spin_unlock(desc->lock); + * set_bit(IRQTF_RUNTHREAD, &action->thread_flags); + * desc->threads_oneshot |= mask; + * spin_lock(desc->lock); + * desc->state &= ~IRQS_INPROGRESS; + * spin_unlock(desc->lock); + * + * irq thread: + * + * again: + * spin_lock(desc->lock); + * if (desc->state & IRQS_INPROGRESS) { + * spin_unlock(desc->lock); + * while(desc->state & IRQS_INPROGRESS) + * cpu_relax(); + * goto again; + * } + * if (!test_bit(IRQTF_RUNTHREAD, &action->thread_flags)) + * desc->threads_oneshot &= ~mask; + * spin_unlock(desc->lock); + * + * So either the thread waits for us to clear IRQS_INPROGRESS + * or we are waiting in the flow handler for desc->lock to be + * released before we reach this point. The thread also checks + * IRQTF_RUNTHREAD under desc->lock. If set it leaves + * threads_oneshot untouched and runs the thread another time. + */ + desc->threads_oneshot |= action->thread_mask; + + /* + * We increment the threads_active counter in case we wake up + * the irq thread. The irq thread decrements the counter when + * it returns from the handler or in the exit path and wakes + * up waiters which are stuck in synchronize_irq() when the + * active count becomes zero. synchronize_irq() is serialized + * against this code (hard irq handler) via IRQS_INPROGRESS + * like the finalize_oneshot() code. See comment above. + */ + atomic_inc(&desc->threads_active); + + wake_up_process(action->thread); +} + +irqreturn_t +handle_irq_event_percpu(struct irq_desc *desc, struct irqaction *action) +{ + struct pt_regs *regs = get_irq_regs(); + u64 ip = regs ? instruction_pointer(regs) : 0; + irqreturn_t retval = IRQ_NONE; + unsigned int flags = 0, irq = desc->irq_data.irq; + + do { + irqreturn_t res; + + trace_irq_handler_entry(irq, action); + res = action->handler(irq, action->dev_id); + trace_irq_handler_exit(irq, action, res); + + if (WARN_ONCE(!irqs_disabled(),"irq %u handler %pF enabled interrupts\n", + irq, action->handler)) + local_irq_disable(); + + switch (res) { + case IRQ_WAKE_THREAD: + /* + * Catch drivers which return WAKE_THREAD but + * did not set up a thread function + */ + if (unlikely(!action->thread_fn)) { + warn_no_thread(irq, action); + break; + } + + __irq_wake_thread(desc, action); + + /* Fall through to add to randomness */ + case IRQ_HANDLED: + flags |= action->flags; + break; + + default: + break; + } + + retval |= res; + action = action->next; + } while (action); + +#ifndef CONFIG_PREEMPT_RT_FULL + add_interrupt_randomness(irq, flags, ip); +#else + desc->random_ip = ip; +#endif + + if (!noirqdebug) + note_interrupt(irq, desc, retval); + return retval; +} + +irqreturn_t handle_irq_event(struct irq_desc *desc) +{ + struct irqaction *action = desc->action; + irqreturn_t ret; + + desc->istate &= ~IRQS_PENDING; + irqd_set(&desc->irq_data, IRQD_IRQ_INPROGRESS); + raw_spin_unlock(&desc->lock); + + ret = handle_irq_event_percpu(desc, action); + + raw_spin_lock(&desc->lock); + irqd_clear(&desc->irq_data, IRQD_IRQ_INPROGRESS); + return ret; +} diff --git a/kernel/kernel/irq/internals.h b/kernel/kernel/irq/internals.h new file mode 100644 index 000000000..df553b0af --- /dev/null +++ b/kernel/kernel/irq/internals.h @@ -0,0 +1,212 @@ +/* + * IRQ subsystem internal functions and variables: + * + * Do not ever include this file from anything else than + * kernel/irq/. Do not even think about using any information outside + * of this file for your non core code. + */ +#include +#include + +#ifdef CONFIG_SPARSE_IRQ +# define IRQ_BITMAP_BITS (NR_IRQS + 8196) +#else +# define IRQ_BITMAP_BITS NR_IRQS +#endif + +#define istate core_internal_state__do_not_mess_with_it + +extern bool noirqdebug; + +/* + * Bits used by threaded handlers: + * IRQTF_RUNTHREAD - signals that the interrupt handler thread should run + * IRQTF_WARNED - warning "IRQ_WAKE_THREAD w/o thread_fn" has been printed + * IRQTF_AFFINITY - irq thread is requested to adjust affinity + * IRQTF_FORCED_THREAD - irq action is force threaded + */ +enum { + IRQTF_RUNTHREAD, + IRQTF_WARNED, + IRQTF_AFFINITY, + IRQTF_FORCED_THREAD, +}; + +/* + * Bit masks for desc->core_internal_state__do_not_mess_with_it + * + * IRQS_AUTODETECT - autodetection in progress + * IRQS_SPURIOUS_DISABLED - was disabled due to spurious interrupt + * detection + * IRQS_POLL_INPROGRESS - polling in progress + * IRQS_ONESHOT - irq is not unmasked in primary handler + * IRQS_REPLAY - irq is replayed + * IRQS_WAITING - irq is waiting + * IRQS_PENDING - irq is pending and replayed later + * IRQS_SUSPENDED - irq is suspended + */ +enum { + IRQS_AUTODETECT = 0x00000001, + IRQS_SPURIOUS_DISABLED = 0x00000002, + IRQS_POLL_INPROGRESS = 0x00000008, + IRQS_ONESHOT = 0x00000020, + IRQS_REPLAY = 0x00000040, + IRQS_WAITING = 0x00000080, + IRQS_PENDING = 0x00000200, + IRQS_SUSPENDED = 0x00000800, +}; + +#include "debug.h" +#include "settings.h" + +#define irq_data_to_desc(data) container_of(data, struct irq_desc, irq_data) + +extern int __irq_set_trigger(struct irq_desc *desc, unsigned int irq, + unsigned long flags); +extern void __disable_irq(struct irq_desc *desc, unsigned int irq); +extern void __enable_irq(struct irq_desc *desc, unsigned int irq); + +extern int irq_startup(struct irq_desc *desc, bool resend); +extern void irq_shutdown(struct irq_desc *desc); +extern void irq_enable(struct irq_desc *desc); +extern void irq_disable(struct irq_desc *desc); +extern void irq_percpu_enable(struct irq_desc *desc, unsigned int cpu); +extern void irq_percpu_disable(struct irq_desc *desc, unsigned int cpu); +extern void mask_irq(struct irq_desc *desc); +extern void unmask_irq(struct irq_desc *desc); +extern void unmask_threaded_irq(struct irq_desc *desc); + +#ifdef CONFIG_SPARSE_IRQ +static inline void irq_mark_irq(unsigned int irq) { } +extern void irq_lock_sparse(void); +extern void irq_unlock_sparse(void); +#else +extern void irq_mark_irq(unsigned int irq); +static inline void irq_lock_sparse(void) { } +static inline void irq_unlock_sparse(void) { } +#endif + +extern void init_kstat_irqs(struct irq_desc *desc, int node, int nr); + +irqreturn_t handle_irq_event_percpu(struct irq_desc *desc, struct irqaction *action); +irqreturn_t handle_irq_event(struct irq_desc *desc); + +/* Resending of interrupts :*/ +void check_irq_resend(struct irq_desc *desc, unsigned int irq); +bool irq_wait_for_poll(struct irq_desc *desc); +void __irq_wake_thread(struct irq_desc *desc, struct irqaction *action); + +#ifdef CONFIG_PROC_FS +extern void register_irq_proc(unsigned int irq, struct irq_desc *desc); +extern void unregister_irq_proc(unsigned int irq, struct irq_desc *desc); +extern void register_handler_proc(unsigned int irq, struct irqaction *action); +extern void unregister_handler_proc(unsigned int irq, struct irqaction *action); +#else +static inline void register_irq_proc(unsigned int irq, struct irq_desc *desc) { } +static inline void unregister_irq_proc(unsigned int irq, struct irq_desc *desc) { } +static inline void register_handler_proc(unsigned int irq, + struct irqaction *action) { } +static inline void unregister_handler_proc(unsigned int irq, + struct irqaction *action) { } +#endif + +extern int irq_select_affinity_usr(unsigned int irq, struct cpumask *mask); + +extern void irq_set_thread_affinity(struct irq_desc *desc); + +extern int irq_do_set_affinity(struct irq_data *data, + const struct cpumask *dest, bool force); + +/* Inline functions for support of irq chips on slow busses */ +static inline void chip_bus_lock(struct irq_desc *desc) +{ + if (unlikely(desc->irq_data.chip->irq_bus_lock)) + desc->irq_data.chip->irq_bus_lock(&desc->irq_data); +} + +static inline void chip_bus_sync_unlock(struct irq_desc *desc) +{ + if (unlikely(desc->irq_data.chip->irq_bus_sync_unlock)) + desc->irq_data.chip->irq_bus_sync_unlock(&desc->irq_data); +} + +#define _IRQ_DESC_CHECK (1 << 0) +#define _IRQ_DESC_PERCPU (1 << 1) + +#define IRQ_GET_DESC_CHECK_GLOBAL (_IRQ_DESC_CHECK) +#define IRQ_GET_DESC_CHECK_PERCPU (_IRQ_DESC_CHECK | _IRQ_DESC_PERCPU) + +struct irq_desc * +__irq_get_desc_lock(unsigned int irq, unsigned long *flags, bool bus, + unsigned int check); +void __irq_put_desc_unlock(struct irq_desc *desc, unsigned long flags, bool bus); + +static inline struct irq_desc * +irq_get_desc_buslock(unsigned int irq, unsigned long *flags, unsigned int check) +{ + return __irq_get_desc_lock(irq, flags, true, check); +} + +static inline void +irq_put_desc_busunlock(struct irq_desc *desc, unsigned long flags) +{ + __irq_put_desc_unlock(desc, flags, true); +} + +static inline struct irq_desc * +irq_get_desc_lock(unsigned int irq, unsigned long *flags, unsigned int check) +{ + return __irq_get_desc_lock(irq, flags, false, check); +} + +static inline void +irq_put_desc_unlock(struct irq_desc *desc, unsigned long flags) +{ + __irq_put_desc_unlock(desc, flags, false); +} + +/* + * Manipulation functions for irq_data.state + */ +static inline void irqd_set_move_pending(struct irq_data *d) +{ + d->state_use_accessors |= IRQD_SETAFFINITY_PENDING; +} + +static inline void irqd_clr_move_pending(struct irq_data *d) +{ + d->state_use_accessors &= ~IRQD_SETAFFINITY_PENDING; +} + +static inline void irqd_clear(struct irq_data *d, unsigned int mask) +{ + d->state_use_accessors &= ~mask; +} + +static inline void irqd_set(struct irq_data *d, unsigned int mask) +{ + d->state_use_accessors |= mask; +} + +static inline bool irqd_has_set(struct irq_data *d, unsigned int mask) +{ + return d->state_use_accessors & mask; +} + +static inline void kstat_incr_irqs_this_cpu(unsigned int irq, struct irq_desc *desc) +{ + __this_cpu_inc(*desc->kstat_irqs); + __this_cpu_inc(kstat.irqs_sum); +} + +#ifdef CONFIG_PM_SLEEP +bool irq_pm_check_wakeup(struct irq_desc *desc); +void irq_pm_install_action(struct irq_desc *desc, struct irqaction *action); +void irq_pm_remove_action(struct irq_desc *desc, struct irqaction *action); +#else +static inline bool irq_pm_check_wakeup(struct irq_desc *desc) { return false; } +static inline void +irq_pm_install_action(struct irq_desc *desc, struct irqaction *action) { } +static inline void +irq_pm_remove_action(struct irq_desc *desc, struct irqaction *action) { } +#endif diff --git a/kernel/kernel/irq/irqdesc.c b/kernel/kernel/irq/irqdesc.c new file mode 100644 index 000000000..99793b9b6 --- /dev/null +++ b/kernel/kernel/irq/irqdesc.c @@ -0,0 +1,648 @@ +/* + * Copyright (C) 1992, 1998-2006 Linus Torvalds, Ingo Molnar + * Copyright (C) 2005-2006, Thomas Gleixner, Russell King + * + * This file contains the interrupt descriptor management code + * + * Detailed information is available in Documentation/DocBook/genericirq + * + */ +#include +#include +#include +#include +#include +#include +#include +#include + +#include "internals.h" + +/* + * lockdep: we want to handle all irq_desc locks as a single lock-class: + */ +static struct lock_class_key irq_desc_lock_class; + +#if defined(CONFIG_SMP) +static void __init init_irq_default_affinity(void) +{ + alloc_cpumask_var(&irq_default_affinity, GFP_NOWAIT); + cpumask_setall(irq_default_affinity); +} +#else +static void __init init_irq_default_affinity(void) +{ +} +#endif + +#ifdef CONFIG_SMP +static int alloc_masks(struct irq_desc *desc, gfp_t gfp, int node) +{ + if (!zalloc_cpumask_var_node(&desc->irq_data.affinity, gfp, node)) + return -ENOMEM; + +#ifdef CONFIG_GENERIC_PENDING_IRQ + if (!zalloc_cpumask_var_node(&desc->pending_mask, gfp, node)) { + free_cpumask_var(desc->irq_data.affinity); + return -ENOMEM; + } +#endif + return 0; +} + +static void desc_smp_init(struct irq_desc *desc, int node) +{ + desc->irq_data.node = node; + cpumask_copy(desc->irq_data.affinity, irq_default_affinity); +#ifdef CONFIG_GENERIC_PENDING_IRQ + cpumask_clear(desc->pending_mask); +#endif +} + +static inline int desc_node(struct irq_desc *desc) +{ + return desc->irq_data.node; +} + +#else +static inline int +alloc_masks(struct irq_desc *desc, gfp_t gfp, int node) { return 0; } +static inline void desc_smp_init(struct irq_desc *desc, int node) { } +static inline int desc_node(struct irq_desc *desc) { return 0; } +#endif + +static void desc_set_defaults(unsigned int irq, struct irq_desc *desc, int node, + struct module *owner) +{ + int cpu; + + desc->irq_data.irq = irq; + desc->irq_data.chip = &no_irq_chip; + desc->irq_data.chip_data = NULL; + desc->irq_data.handler_data = NULL; + desc->irq_data.msi_desc = NULL; + irq_settings_clr_and_set(desc, ~0, _IRQ_DEFAULT_INIT_FLAGS); + irqd_set(&desc->irq_data, IRQD_IRQ_DISABLED); + desc->handle_irq = handle_bad_irq; + desc->depth = 1; + desc->irq_count = 0; + desc->irqs_unhandled = 0; + desc->name = NULL; + desc->owner = owner; + for_each_possible_cpu(cpu) + *per_cpu_ptr(desc->kstat_irqs, cpu) = 0; + desc_smp_init(desc, node); +} + +int nr_irqs = NR_IRQS; +EXPORT_SYMBOL_GPL(nr_irqs); + +static DEFINE_MUTEX(sparse_irq_lock); +static DECLARE_BITMAP(allocated_irqs, IRQ_BITMAP_BITS); + +#ifdef CONFIG_SPARSE_IRQ + +static RADIX_TREE(irq_desc_tree, GFP_KERNEL); + +static void irq_insert_desc(unsigned int irq, struct irq_desc *desc) +{ + radix_tree_insert(&irq_desc_tree, irq, desc); +} + +struct irq_desc *irq_to_desc(unsigned int irq) +{ + return radix_tree_lookup(&irq_desc_tree, irq); +} +EXPORT_SYMBOL(irq_to_desc); + +static void delete_irq_desc(unsigned int irq) +{ + radix_tree_delete(&irq_desc_tree, irq); +} + +#ifdef CONFIG_SMP +static void free_masks(struct irq_desc *desc) +{ +#ifdef CONFIG_GENERIC_PENDING_IRQ + free_cpumask_var(desc->pending_mask); +#endif + free_cpumask_var(desc->irq_data.affinity); +} +#else +static inline void free_masks(struct irq_desc *desc) { } +#endif + +void irq_lock_sparse(void) +{ + mutex_lock(&sparse_irq_lock); +} + +void irq_unlock_sparse(void) +{ + mutex_unlock(&sparse_irq_lock); +} + +static struct irq_desc *alloc_desc(int irq, int node, struct module *owner) +{ + struct irq_desc *desc; + gfp_t gfp = GFP_KERNEL; + + desc = kzalloc_node(sizeof(*desc), gfp, node); + if (!desc) + return NULL; + /* allocate based on nr_cpu_ids */ + desc->kstat_irqs = alloc_percpu(unsigned int); + if (!desc->kstat_irqs) + goto err_desc; + + if (alloc_masks(desc, gfp, node)) + goto err_kstat; + + raw_spin_lock_init(&desc->lock); + lockdep_set_class(&desc->lock, &irq_desc_lock_class); + + desc_set_defaults(irq, desc, node, owner); + + return desc; + +err_kstat: + free_percpu(desc->kstat_irqs); +err_desc: + kfree(desc); + return NULL; +} + +static void free_desc(unsigned int irq) +{ + struct irq_desc *desc = irq_to_desc(irq); + + unregister_irq_proc(irq, desc); + + /* + * sparse_irq_lock protects also show_interrupts() and + * kstat_irq_usr(). Once we deleted the descriptor from the + * sparse tree we can free it. Access in proc will fail to + * lookup the descriptor. + */ + mutex_lock(&sparse_irq_lock); + delete_irq_desc(irq); + mutex_unlock(&sparse_irq_lock); + + free_masks(desc); + free_percpu(desc->kstat_irqs); + kfree(desc); +} + +static int alloc_descs(unsigned int start, unsigned int cnt, int node, + struct module *owner) +{ + struct irq_desc *desc; + int i; + + for (i = 0; i < cnt; i++) { + desc = alloc_desc(start + i, node, owner); + if (!desc) + goto err; + mutex_lock(&sparse_irq_lock); + irq_insert_desc(start + i, desc); + mutex_unlock(&sparse_irq_lock); + } + return start; + +err: + for (i--; i >= 0; i--) + free_desc(start + i); + + mutex_lock(&sparse_irq_lock); + bitmap_clear(allocated_irqs, start, cnt); + mutex_unlock(&sparse_irq_lock); + return -ENOMEM; +} + +static int irq_expand_nr_irqs(unsigned int nr) +{ + if (nr > IRQ_BITMAP_BITS) + return -ENOMEM; + nr_irqs = nr; + return 0; +} + +int __init early_irq_init(void) +{ + int i, initcnt, node = first_online_node; + struct irq_desc *desc; + + init_irq_default_affinity(); + + /* Let arch update nr_irqs and return the nr of preallocated irqs */ + initcnt = arch_probe_nr_irqs(); + printk(KERN_INFO "NR_IRQS:%d nr_irqs:%d %d\n", NR_IRQS, nr_irqs, initcnt); + + if (WARN_ON(nr_irqs > IRQ_BITMAP_BITS)) + nr_irqs = IRQ_BITMAP_BITS; + + if (WARN_ON(initcnt > IRQ_BITMAP_BITS)) + initcnt = IRQ_BITMAP_BITS; + + if (initcnt > nr_irqs) + nr_irqs = initcnt; + + for (i = 0; i < initcnt; i++) { + desc = alloc_desc(i, node, NULL); + set_bit(i, allocated_irqs); + irq_insert_desc(i, desc); + } + return arch_early_irq_init(); +} + +#else /* !CONFIG_SPARSE_IRQ */ + +struct irq_desc irq_desc[NR_IRQS] __cacheline_aligned_in_smp = { + [0 ... NR_IRQS-1] = { + .handle_irq = handle_bad_irq, + .depth = 1, + .lock = __RAW_SPIN_LOCK_UNLOCKED(irq_desc->lock), + } +}; + +int __init early_irq_init(void) +{ + int count, i, node = first_online_node; + struct irq_desc *desc; + + init_irq_default_affinity(); + + printk(KERN_INFO "NR_IRQS:%d\n", NR_IRQS); + + desc = irq_desc; + count = ARRAY_SIZE(irq_desc); + + for (i = 0; i < count; i++) { + desc[i].kstat_irqs = alloc_percpu(unsigned int); + alloc_masks(&desc[i], GFP_KERNEL, node); + raw_spin_lock_init(&desc[i].lock); + lockdep_set_class(&desc[i].lock, &irq_desc_lock_class); + desc_set_defaults(i, &desc[i], node, NULL); + } + return arch_early_irq_init(); +} + +struct irq_desc *irq_to_desc(unsigned int irq) +{ + return (irq < NR_IRQS) ? irq_desc + irq : NULL; +} +EXPORT_SYMBOL(irq_to_desc); + +static void free_desc(unsigned int irq) +{ + struct irq_desc *desc = irq_to_desc(irq); + unsigned long flags; + + raw_spin_lock_irqsave(&desc->lock, flags); + desc_set_defaults(irq, desc, desc_node(desc), NULL); + raw_spin_unlock_irqrestore(&desc->lock, flags); +} + +static inline int alloc_descs(unsigned int start, unsigned int cnt, int node, + struct module *owner) +{ + u32 i; + + for (i = 0; i < cnt; i++) { + struct irq_desc *desc = irq_to_desc(start + i); + + desc->owner = owner; + } + return start; +} + +static int irq_expand_nr_irqs(unsigned int nr) +{ + return -ENOMEM; +} + +void irq_mark_irq(unsigned int irq) +{ + mutex_lock(&sparse_irq_lock); + bitmap_set(allocated_irqs, irq, 1); + mutex_unlock(&sparse_irq_lock); +} + +#ifdef CONFIG_GENERIC_IRQ_LEGACY +void irq_init_desc(unsigned int irq) +{ + free_desc(irq); +} +#endif + +#endif /* !CONFIG_SPARSE_IRQ */ + +/** + * generic_handle_irq - Invoke the handler for a particular irq + * @irq: The irq number to handle + * + */ +int generic_handle_irq(unsigned int irq) +{ + struct irq_desc *desc = irq_to_desc(irq); + + if (!desc) + return -EINVAL; + generic_handle_irq_desc(irq, desc); + return 0; +} +EXPORT_SYMBOL_GPL(generic_handle_irq); + +#ifdef CONFIG_HANDLE_DOMAIN_IRQ +/** + * __handle_domain_irq - Invoke the handler for a HW irq belonging to a domain + * @domain: The domain where to perform the lookup + * @hwirq: The HW irq number to convert to a logical one + * @lookup: Whether to perform the domain lookup or not + * @regs: Register file coming from the low-level handling code + * + * Returns: 0 on success, or -EINVAL if conversion has failed + */ +int __handle_domain_irq(struct irq_domain *domain, unsigned int hwirq, + bool lookup, struct pt_regs *regs) +{ + struct pt_regs *old_regs = set_irq_regs(regs); + unsigned int irq = hwirq; + int ret = 0; + + irq_enter(); + +#ifdef CONFIG_IRQ_DOMAIN + if (lookup) + irq = irq_find_mapping(domain, hwirq); +#endif + + /* + * Some hardware gives randomly wrong interrupts. Rather + * than crashing, do something sensible. + */ + if (unlikely(!irq || irq >= nr_irqs)) { + ack_bad_irq(irq); + ret = -EINVAL; + } else { + generic_handle_irq(irq); + } + + irq_exit(); + set_irq_regs(old_regs); + return ret; +} +#endif + +/* Dynamic interrupt handling */ + +/** + * irq_free_descs - free irq descriptors + * @from: Start of descriptor range + * @cnt: Number of consecutive irqs to free + */ +void irq_free_descs(unsigned int from, unsigned int cnt) +{ + int i; + + if (from >= nr_irqs || (from + cnt) > nr_irqs) + return; + + for (i = 0; i < cnt; i++) + free_desc(from + i); + + mutex_lock(&sparse_irq_lock); + bitmap_clear(allocated_irqs, from, cnt); + mutex_unlock(&sparse_irq_lock); +} +EXPORT_SYMBOL_GPL(irq_free_descs); + +/** + * irq_alloc_descs - allocate and initialize a range of irq descriptors + * @irq: Allocate for specific irq number if irq >= 0 + * @from: Start the search from this irq number + * @cnt: Number of consecutive irqs to allocate. + * @node: Preferred node on which the irq descriptor should be allocated + * @owner: Owning module (can be NULL) + * + * Returns the first irq number or error code + */ +int __ref +__irq_alloc_descs(int irq, unsigned int from, unsigned int cnt, int node, + struct module *owner) +{ + int start, ret; + + if (!cnt) + return -EINVAL; + + if (irq >= 0) { + if (from > irq) + return -EINVAL; + from = irq; + } else { + /* + * For interrupts which are freely allocated the + * architecture can force a lower bound to the @from + * argument. x86 uses this to exclude the GSI space. + */ + from = arch_dynirq_lower_bound(from); + } + + mutex_lock(&sparse_irq_lock); + + start = bitmap_find_next_zero_area(allocated_irqs, IRQ_BITMAP_BITS, + from, cnt, 0); + ret = -EEXIST; + if (irq >=0 && start != irq) + goto err; + + if (start + cnt > nr_irqs) { + ret = irq_expand_nr_irqs(start + cnt); + if (ret) + goto err; + } + + bitmap_set(allocated_irqs, start, cnt); + mutex_unlock(&sparse_irq_lock); + return alloc_descs(start, cnt, node, owner); + +err: + mutex_unlock(&sparse_irq_lock); + return ret; +} +EXPORT_SYMBOL_GPL(__irq_alloc_descs); + +#ifdef CONFIG_GENERIC_IRQ_LEGACY_ALLOC_HWIRQ +/** + * irq_alloc_hwirqs - Allocate an irq descriptor and initialize the hardware + * @cnt: number of interrupts to allocate + * @node: node on which to allocate + * + * Returns an interrupt number > 0 or 0, if the allocation fails. + */ +unsigned int irq_alloc_hwirqs(int cnt, int node) +{ + int i, irq = __irq_alloc_descs(-1, 0, cnt, node, NULL); + + if (irq < 0) + return 0; + + for (i = irq; cnt > 0; i++, cnt--) { + if (arch_setup_hwirq(i, node)) + goto err; + irq_clear_status_flags(i, _IRQ_NOREQUEST); + } + return irq; + +err: + for (i--; i >= irq; i--) { + irq_set_status_flags(i, _IRQ_NOREQUEST | _IRQ_NOPROBE); + arch_teardown_hwirq(i); + } + irq_free_descs(irq, cnt); + return 0; +} +EXPORT_SYMBOL_GPL(irq_alloc_hwirqs); + +/** + * irq_free_hwirqs - Free irq descriptor and cleanup the hardware + * @from: Free from irq number + * @cnt: number of interrupts to free + * + */ +void irq_free_hwirqs(unsigned int from, int cnt) +{ + int i, j; + + for (i = from, j = cnt; j > 0; i++, j--) { + irq_set_status_flags(i, _IRQ_NOREQUEST | _IRQ_NOPROBE); + arch_teardown_hwirq(i); + } + irq_free_descs(from, cnt); +} +EXPORT_SYMBOL_GPL(irq_free_hwirqs); +#endif + +/** + * irq_get_next_irq - get next allocated irq number + * @offset: where to start the search + * + * Returns next irq number after offset or nr_irqs if none is found. + */ +unsigned int irq_get_next_irq(unsigned int offset) +{ + return find_next_bit(allocated_irqs, nr_irqs, offset); +} + +struct irq_desc * +__irq_get_desc_lock(unsigned int irq, unsigned long *flags, bool bus, + unsigned int check) +{ + struct irq_desc *desc = irq_to_desc(irq); + + if (desc) { + if (check & _IRQ_DESC_CHECK) { + if ((check & _IRQ_DESC_PERCPU) && + !irq_settings_is_per_cpu_devid(desc)) + return NULL; + + if (!(check & _IRQ_DESC_PERCPU) && + irq_settings_is_per_cpu_devid(desc)) + return NULL; + } + + if (bus) + chip_bus_lock(desc); + raw_spin_lock_irqsave(&desc->lock, *flags); + } + return desc; +} + +void __irq_put_desc_unlock(struct irq_desc *desc, unsigned long flags, bool bus) +{ + raw_spin_unlock_irqrestore(&desc->lock, flags); + if (bus) + chip_bus_sync_unlock(desc); +} + +int irq_set_percpu_devid(unsigned int irq) +{ + struct irq_desc *desc = irq_to_desc(irq); + + if (!desc) + return -EINVAL; + + if (desc->percpu_enabled) + return -EINVAL; + + desc->percpu_enabled = kzalloc(sizeof(*desc->percpu_enabled), GFP_KERNEL); + + if (!desc->percpu_enabled) + return -ENOMEM; + + irq_set_percpu_devid_flags(irq); + return 0; +} + +void kstat_incr_irq_this_cpu(unsigned int irq) +{ + kstat_incr_irqs_this_cpu(irq, irq_to_desc(irq)); +} + +/** + * kstat_irqs_cpu - Get the statistics for an interrupt on a cpu + * @irq: The interrupt number + * @cpu: The cpu number + * + * Returns the sum of interrupt counts on @cpu since boot for + * @irq. The caller must ensure that the interrupt is not removed + * concurrently. + */ +unsigned int kstat_irqs_cpu(unsigned int irq, int cpu) +{ + struct irq_desc *desc = irq_to_desc(irq); + + return desc && desc->kstat_irqs ? + *per_cpu_ptr(desc->kstat_irqs, cpu) : 0; +} + +/** + * kstat_irqs - Get the statistics for an interrupt + * @irq: The interrupt number + * + * Returns the sum of interrupt counts on all cpus since boot for + * @irq. The caller must ensure that the interrupt is not removed + * concurrently. + */ +unsigned int kstat_irqs(unsigned int irq) +{ + struct irq_desc *desc = irq_to_desc(irq); + int cpu; + int sum = 0; + + if (!desc || !desc->kstat_irqs) + return 0; + for_each_possible_cpu(cpu) + sum += *per_cpu_ptr(desc->kstat_irqs, cpu); + return sum; +} + +/** + * kstat_irqs_usr - Get the statistics for an interrupt + * @irq: The interrupt number + * + * Returns the sum of interrupt counts on all cpus since boot for + * @irq. Contrary to kstat_irqs() this can be called from any + * preemptible context. It's protected against concurrent removal of + * an interrupt descriptor when sparse irqs are enabled. + */ +unsigned int kstat_irqs_usr(unsigned int irq) +{ + int sum; + + irq_lock_sparse(); + sum = kstat_irqs(irq); + irq_unlock_sparse(); + return sum; +} diff --git a/kernel/kernel/irq/irqdomain.c b/kernel/kernel/irq/irqdomain.c new file mode 100644 index 000000000..7fac31105 --- /dev/null +++ b/kernel/kernel/irq/irqdomain.c @@ -0,0 +1,1238 @@ +#define pr_fmt(fmt) "irq: " fmt + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +static LIST_HEAD(irq_domain_list); +static DEFINE_MUTEX(irq_domain_mutex); + +static DEFINE_MUTEX(revmap_trees_mutex); +static struct irq_domain *irq_default_domain; + +static int irq_domain_alloc_descs(int virq, unsigned int nr_irqs, + irq_hw_number_t hwirq, int node); +static void irq_domain_check_hierarchy(struct irq_domain *domain); + +/** + * __irq_domain_add() - Allocate a new irq_domain data structure + * @of_node: optional device-tree node of the interrupt controller + * @size: Size of linear map; 0 for radix mapping only + * @hwirq_max: Maximum number of interrupts supported by controller + * @direct_max: Maximum value of direct maps; Use ~0 for no limit; 0 for no + * direct mapping + * @ops: domain callbacks + * @host_data: Controller private data pointer + * + * Allocates and initialize and irq_domain structure. + * Returns pointer to IRQ domain, or NULL on failure. + */ +struct irq_domain *__irq_domain_add(struct device_node *of_node, int size, + irq_hw_number_t hwirq_max, int direct_max, + const struct irq_domain_ops *ops, + void *host_data) +{ + struct irq_domain *domain; + + domain = kzalloc_node(sizeof(*domain) + (sizeof(unsigned int) * size), + GFP_KERNEL, of_node_to_nid(of_node)); + if (WARN_ON(!domain)) + return NULL; + + /* Fill structure */ + INIT_RADIX_TREE(&domain->revmap_tree, GFP_KERNEL); + domain->ops = ops; + domain->host_data = host_data; + domain->of_node = of_node_get(of_node); + domain->hwirq_max = hwirq_max; + domain->revmap_size = size; + domain->revmap_direct_max_irq = direct_max; + irq_domain_check_hierarchy(domain); + + mutex_lock(&irq_domain_mutex); + list_add(&domain->link, &irq_domain_list); + mutex_unlock(&irq_domain_mutex); + + pr_debug("Added domain %s\n", domain->name); + return domain; +} +EXPORT_SYMBOL_GPL(__irq_domain_add); + +/** + * irq_domain_remove() - Remove an irq domain. + * @domain: domain to remove + * + * This routine is used to remove an irq domain. The caller must ensure + * that all mappings within the domain have been disposed of prior to + * use, depending on the revmap type. + */ +void irq_domain_remove(struct irq_domain *domain) +{ + mutex_lock(&irq_domain_mutex); + + /* + * radix_tree_delete() takes care of destroying the root + * node when all entries are removed. Shout if there are + * any mappings left. + */ + WARN_ON(domain->revmap_tree.height); + + list_del(&domain->link); + + /* + * If the going away domain is the default one, reset it. + */ + if (unlikely(irq_default_domain == domain)) + irq_set_default_host(NULL); + + mutex_unlock(&irq_domain_mutex); + + pr_debug("Removed domain %s\n", domain->name); + + of_node_put(domain->of_node); + kfree(domain); +} +EXPORT_SYMBOL_GPL(irq_domain_remove); + +/** + * irq_domain_add_simple() - Register an irq_domain and optionally map a range of irqs + * @of_node: pointer to interrupt controller's device tree node. + * @size: total number of irqs in mapping + * @first_irq: first number of irq block assigned to the domain, + * pass zero to assign irqs on-the-fly. If first_irq is non-zero, then + * pre-map all of the irqs in the domain to virqs starting at first_irq. + * @ops: domain callbacks + * @host_data: Controller private data pointer + * + * Allocates an irq_domain, and optionally if first_irq is positive then also + * allocate irq_descs and map all of the hwirqs to virqs starting at first_irq. + * + * This is intended to implement the expected behaviour for most + * interrupt controllers. If device tree is used, then first_irq will be 0 and + * irqs get mapped dynamically on the fly. However, if the controller requires + * static virq assignments (non-DT boot) then it will set that up correctly. + */ +struct irq_domain *irq_domain_add_simple(struct device_node *of_node, + unsigned int size, + unsigned int first_irq, + const struct irq_domain_ops *ops, + void *host_data) +{ + struct irq_domain *domain; + + domain = __irq_domain_add(of_node, size, size, 0, ops, host_data); + if (!domain) + return NULL; + + if (first_irq > 0) { + if (IS_ENABLED(CONFIG_SPARSE_IRQ)) { + /* attempt to allocated irq_descs */ + int rc = irq_alloc_descs(first_irq, first_irq, size, + of_node_to_nid(of_node)); + if (rc < 0) + pr_info("Cannot allocate irq_descs @ IRQ%d, assuming pre-allocated\n", + first_irq); + } + irq_domain_associate_many(domain, first_irq, 0, size); + } + + return domain; +} +EXPORT_SYMBOL_GPL(irq_domain_add_simple); + +/** + * irq_domain_add_legacy() - Allocate and register a legacy revmap irq_domain. + * @of_node: pointer to interrupt controller's device tree node. + * @size: total number of irqs in legacy mapping + * @first_irq: first number of irq block assigned to the domain + * @first_hwirq: first hwirq number to use for the translation. Should normally + * be '0', but a positive integer can be used if the effective + * hwirqs numbering does not begin at zero. + * @ops: map/unmap domain callbacks + * @host_data: Controller private data pointer + * + * Note: the map() callback will be called before this function returns + * for all legacy interrupts except 0 (which is always the invalid irq for + * a legacy controller). + */ +struct irq_domain *irq_domain_add_legacy(struct device_node *of_node, + unsigned int size, + unsigned int first_irq, + irq_hw_number_t first_hwirq, + const struct irq_domain_ops *ops, + void *host_data) +{ + struct irq_domain *domain; + + domain = __irq_domain_add(of_node, first_hwirq + size, + first_hwirq + size, 0, ops, host_data); + if (domain) + irq_domain_associate_many(domain, first_irq, first_hwirq, size); + + return domain; +} +EXPORT_SYMBOL_GPL(irq_domain_add_legacy); + +/** + * irq_find_host() - Locates a domain for a given device node + * @node: device-tree node of the interrupt controller + */ +struct irq_domain *irq_find_host(struct device_node *node) +{ + struct irq_domain *h, *found = NULL; + int rc; + + /* We might want to match the legacy controller last since + * it might potentially be set to match all interrupts in + * the absence of a device node. This isn't a problem so far + * yet though... + */ + mutex_lock(&irq_domain_mutex); + list_for_each_entry(h, &irq_domain_list, link) { + if (h->ops->match) + rc = h->ops->match(h, node); + else + rc = (h->of_node != NULL) && (h->of_node == node); + + if (rc) { + found = h; + break; + } + } + mutex_unlock(&irq_domain_mutex); + return found; +} +EXPORT_SYMBOL_GPL(irq_find_host); + +/** + * irq_set_default_host() - Set a "default" irq domain + * @domain: default domain pointer + * + * For convenience, it's possible to set a "default" domain that will be used + * whenever NULL is passed to irq_create_mapping(). It makes life easier for + * platforms that want to manipulate a few hard coded interrupt numbers that + * aren't properly represented in the device-tree. + */ +void irq_set_default_host(struct irq_domain *domain) +{ + pr_debug("Default domain set to @0x%p\n", domain); + + irq_default_domain = domain; +} +EXPORT_SYMBOL_GPL(irq_set_default_host); + +void irq_domain_disassociate(struct irq_domain *domain, unsigned int irq) +{ + struct irq_data *irq_data = irq_get_irq_data(irq); + irq_hw_number_t hwirq; + + if (WARN(!irq_data || irq_data->domain != domain, + "virq%i doesn't exist; cannot disassociate\n", irq)) + return; + + hwirq = irq_data->hwirq; + irq_set_status_flags(irq, IRQ_NOREQUEST); + + /* remove chip and handler */ + irq_set_chip_and_handler(irq, NULL, NULL); + + /* Make sure it's completed */ + synchronize_irq(irq); + + /* Tell the PIC about it */ + if (domain->ops->unmap) + domain->ops->unmap(domain, irq); + smp_mb(); + + irq_data->domain = NULL; + irq_data->hwirq = 0; + + /* Clear reverse map for this hwirq */ + if (hwirq < domain->revmap_size) { + domain->linear_revmap[hwirq] = 0; + } else { + mutex_lock(&revmap_trees_mutex); + radix_tree_delete(&domain->revmap_tree, hwirq); + mutex_unlock(&revmap_trees_mutex); + } +} + +int irq_domain_associate(struct irq_domain *domain, unsigned int virq, + irq_hw_number_t hwirq) +{ + struct irq_data *irq_data = irq_get_irq_data(virq); + int ret; + + if (WARN(hwirq >= domain->hwirq_max, + "error: hwirq 0x%x is too large for %s\n", (int)hwirq, domain->name)) + return -EINVAL; + if (WARN(!irq_data, "error: virq%i is not allocated", virq)) + return -EINVAL; + if (WARN(irq_data->domain, "error: virq%i is already associated", virq)) + return -EINVAL; + + mutex_lock(&irq_domain_mutex); + irq_data->hwirq = hwirq; + irq_data->domain = domain; + if (domain->ops->map) { + ret = domain->ops->map(domain, virq, hwirq); + if (ret != 0) { + /* + * If map() returns -EPERM, this interrupt is protected + * by the firmware or some other service and shall not + * be mapped. Don't bother telling the user about it. + */ + if (ret != -EPERM) { + pr_info("%s didn't like hwirq-0x%lx to VIRQ%i mapping (rc=%d)\n", + domain->name, hwirq, virq, ret); + } + irq_data->domain = NULL; + irq_data->hwirq = 0; + mutex_unlock(&irq_domain_mutex); + return ret; + } + + /* If not already assigned, give the domain the chip's name */ + if (!domain->name && irq_data->chip) + domain->name = irq_data->chip->name; + } + + if (hwirq < domain->revmap_size) { + domain->linear_revmap[hwirq] = virq; + } else { + mutex_lock(&revmap_trees_mutex); + radix_tree_insert(&domain->revmap_tree, hwirq, irq_data); + mutex_unlock(&revmap_trees_mutex); + } + mutex_unlock(&irq_domain_mutex); + + irq_clear_status_flags(virq, IRQ_NOREQUEST); + + return 0; +} +EXPORT_SYMBOL_GPL(irq_domain_associate); + +void irq_domain_associate_many(struct irq_domain *domain, unsigned int irq_base, + irq_hw_number_t hwirq_base, int count) +{ + int i; + + pr_debug("%s(%s, irqbase=%i, hwbase=%i, count=%i)\n", __func__, + of_node_full_name(domain->of_node), irq_base, (int)hwirq_base, count); + + for (i = 0; i < count; i++) { + irq_domain_associate(domain, irq_base + i, hwirq_base + i); + } +} +EXPORT_SYMBOL_GPL(irq_domain_associate_many); + +/** + * irq_create_direct_mapping() - Allocate an irq for direct mapping + * @domain: domain to allocate the irq for or NULL for default domain + * + * This routine is used for irq controllers which can choose the hardware + * interrupt numbers they generate. In such a case it's simplest to use + * the linux irq as the hardware interrupt number. It still uses the linear + * or radix tree to store the mapping, but the irq controller can optimize + * the revmap path by using the hwirq directly. + */ +unsigned int irq_create_direct_mapping(struct irq_domain *domain) +{ + unsigned int virq; + + if (domain == NULL) + domain = irq_default_domain; + + virq = irq_alloc_desc_from(1, of_node_to_nid(domain->of_node)); + if (!virq) { + pr_debug("create_direct virq allocation failed\n"); + return 0; + } + if (virq >= domain->revmap_direct_max_irq) { + pr_err("ERROR: no free irqs available below %i maximum\n", + domain->revmap_direct_max_irq); + irq_free_desc(virq); + return 0; + } + pr_debug("create_direct obtained virq %d\n", virq); + + if (irq_domain_associate(domain, virq, virq)) { + irq_free_desc(virq); + return 0; + } + + return virq; +} +EXPORT_SYMBOL_GPL(irq_create_direct_mapping); + +/** + * irq_create_mapping() - Map a hardware interrupt into linux irq space + * @domain: domain owning this hardware interrupt or NULL for default domain + * @hwirq: hardware irq number in that domain space + * + * Only one mapping per hardware interrupt is permitted. Returns a linux + * irq number. + * If the sense/trigger is to be specified, set_irq_type() should be called + * on the number returned from that call. + */ +unsigned int irq_create_mapping(struct irq_domain *domain, + irq_hw_number_t hwirq) +{ + int virq; + + pr_debug("irq_create_mapping(0x%p, 0x%lx)\n", domain, hwirq); + + /* Look for default domain if nececssary */ + if (domain == NULL) + domain = irq_default_domain; + if (domain == NULL) { + WARN(1, "%s(, %lx) called with NULL domain\n", __func__, hwirq); + return 0; + } + pr_debug("-> using domain @%p\n", domain); + + /* Check if mapping already exists */ + virq = irq_find_mapping(domain, hwirq); + if (virq) { + pr_debug("-> existing mapping on virq %d\n", virq); + return virq; + } + + /* Allocate a virtual interrupt number */ + virq = irq_domain_alloc_descs(-1, 1, hwirq, + of_node_to_nid(domain->of_node)); + if (virq <= 0) { + pr_debug("-> virq allocation failed\n"); + return 0; + } + + if (irq_domain_associate(domain, virq, hwirq)) { + irq_free_desc(virq); + return 0; + } + + pr_debug("irq %lu on domain %s mapped to virtual irq %u\n", + hwirq, of_node_full_name(domain->of_node), virq); + + return virq; +} +EXPORT_SYMBOL_GPL(irq_create_mapping); + +/** + * irq_create_strict_mappings() - Map a range of hw irqs to fixed linux irqs + * @domain: domain owning the interrupt range + * @irq_base: beginning of linux IRQ range + * @hwirq_base: beginning of hardware IRQ range + * @count: Number of interrupts to map + * + * This routine is used for allocating and mapping a range of hardware + * irqs to linux irqs where the linux irq numbers are at pre-defined + * locations. For use by controllers that already have static mappings + * to insert in to the domain. + * + * Non-linear users can use irq_create_identity_mapping() for IRQ-at-a-time + * domain insertion. + * + * 0 is returned upon success, while any failure to establish a static + * mapping is treated as an error. + */ +int irq_create_strict_mappings(struct irq_domain *domain, unsigned int irq_base, + irq_hw_number_t hwirq_base, int count) +{ + int ret; + + ret = irq_alloc_descs(irq_base, irq_base, count, + of_node_to_nid(domain->of_node)); + if (unlikely(ret < 0)) + return ret; + + irq_domain_associate_many(domain, irq_base, hwirq_base, count); + return 0; +} +EXPORT_SYMBOL_GPL(irq_create_strict_mappings); + +unsigned int irq_create_of_mapping(struct of_phandle_args *irq_data) +{ + struct irq_domain *domain; + irq_hw_number_t hwirq; + unsigned int type = IRQ_TYPE_NONE; + int virq; + + domain = irq_data->np ? irq_find_host(irq_data->np) : irq_default_domain; + if (!domain) { + pr_warn("no irq domain found for %s !\n", + of_node_full_name(irq_data->np)); + return 0; + } + + /* If domain has no translation, then we assume interrupt line */ + if (domain->ops->xlate == NULL) + hwirq = irq_data->args[0]; + else { + if (domain->ops->xlate(domain, irq_data->np, irq_data->args, + irq_data->args_count, &hwirq, &type)) + return 0; + } + + if (irq_domain_is_hierarchy(domain)) { + /* + * If we've already configured this interrupt, + * don't do it again, or hell will break loose. + */ + virq = irq_find_mapping(domain, hwirq); + if (virq) + return virq; + + virq = irq_domain_alloc_irqs(domain, 1, NUMA_NO_NODE, irq_data); + if (virq <= 0) + return 0; + } else { + /* Create mapping */ + virq = irq_create_mapping(domain, hwirq); + if (!virq) + return virq; + } + + /* Set type if specified and different than the current one */ + if (type != IRQ_TYPE_NONE && + type != irq_get_trigger_type(virq)) + irq_set_irq_type(virq, type); + return virq; +} +EXPORT_SYMBOL_GPL(irq_create_of_mapping); + +/** + * irq_dispose_mapping() - Unmap an interrupt + * @virq: linux irq number of the interrupt to unmap + */ +void irq_dispose_mapping(unsigned int virq) +{ + struct irq_data *irq_data = irq_get_irq_data(virq); + struct irq_domain *domain; + + if (!virq || !irq_data) + return; + + domain = irq_data->domain; + if (WARN_ON(domain == NULL)) + return; + + irq_domain_disassociate(domain, virq); + irq_free_desc(virq); +} +EXPORT_SYMBOL_GPL(irq_dispose_mapping); + +/** + * irq_find_mapping() - Find a linux irq from an hw irq number. + * @domain: domain owning this hardware interrupt + * @hwirq: hardware irq number in that domain space + */ +unsigned int irq_find_mapping(struct irq_domain *domain, + irq_hw_number_t hwirq) +{ + struct irq_data *data; + + /* Look for default domain if nececssary */ + if (domain == NULL) + domain = irq_default_domain; + if (domain == NULL) + return 0; + + if (hwirq < domain->revmap_direct_max_irq) { + data = irq_domain_get_irq_data(domain, hwirq); + if (data && data->hwirq == hwirq) + return hwirq; + } + + /* Check if the hwirq is in the linear revmap. */ + if (hwirq < domain->revmap_size) + return domain->linear_revmap[hwirq]; + + rcu_read_lock(); + data = radix_tree_lookup(&domain->revmap_tree, hwirq); + rcu_read_unlock(); + return data ? data->irq : 0; +} +EXPORT_SYMBOL_GPL(irq_find_mapping); + +#ifdef CONFIG_IRQ_DOMAIN_DEBUG +static int virq_debug_show(struct seq_file *m, void *private) +{ + unsigned long flags; + struct irq_desc *desc; + struct irq_domain *domain; + struct radix_tree_iter iter; + void *data, **slot; + int i; + + seq_printf(m, " %-16s %-6s %-10s %-10s %s\n", + "name", "mapped", "linear-max", "direct-max", "devtree-node"); + mutex_lock(&irq_domain_mutex); + list_for_each_entry(domain, &irq_domain_list, link) { + int count = 0; + radix_tree_for_each_slot(slot, &domain->revmap_tree, &iter, 0) + count++; + seq_printf(m, "%c%-16s %6u %10u %10u %s\n", + domain == irq_default_domain ? '*' : ' ', domain->name, + domain->revmap_size + count, domain->revmap_size, + domain->revmap_direct_max_irq, + domain->of_node ? of_node_full_name(domain->of_node) : ""); + } + mutex_unlock(&irq_domain_mutex); + + seq_printf(m, "%-5s %-7s %-15s %-*s %6s %-14s %s\n", "irq", "hwirq", + "chip name", (int)(2 * sizeof(void *) + 2), "chip data", + "active", "type", "domain"); + + for (i = 1; i < nr_irqs; i++) { + desc = irq_to_desc(i); + if (!desc) + continue; + + raw_spin_lock_irqsave(&desc->lock, flags); + domain = desc->irq_data.domain; + + if (domain) { + struct irq_chip *chip; + int hwirq = desc->irq_data.hwirq; + bool direct; + + seq_printf(m, "%5d ", i); + seq_printf(m, "0x%05x ", hwirq); + + chip = irq_desc_get_chip(desc); + seq_printf(m, "%-15s ", (chip && chip->name) ? chip->name : "none"); + + data = irq_desc_get_chip_data(desc); + seq_printf(m, data ? "0x%p " : " %p ", data); + + seq_printf(m, " %c ", (desc->action && desc->action->handler) ? '*' : ' '); + direct = (i == hwirq) && (i < domain->revmap_direct_max_irq); + seq_printf(m, "%6s%-8s ", + (hwirq < domain->revmap_size) ? "LINEAR" : "RADIX", + direct ? "(DIRECT)" : ""); + seq_printf(m, "%s\n", desc->irq_data.domain->name); + } + + raw_spin_unlock_irqrestore(&desc->lock, flags); + } + + return 0; +} + +static int virq_debug_open(struct inode *inode, struct file *file) +{ + return single_open(file, virq_debug_show, inode->i_private); +} + +static const struct file_operations virq_debug_fops = { + .open = virq_debug_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static int __init irq_debugfs_init(void) +{ + if (debugfs_create_file("irq_domain_mapping", S_IRUGO, NULL, + NULL, &virq_debug_fops) == NULL) + return -ENOMEM; + + return 0; +} +__initcall(irq_debugfs_init); +#endif /* CONFIG_IRQ_DOMAIN_DEBUG */ + +/** + * irq_domain_xlate_onecell() - Generic xlate for direct one cell bindings + * + * Device Tree IRQ specifier translation function which works with one cell + * bindings where the cell value maps directly to the hwirq number. + */ +int irq_domain_xlate_onecell(struct irq_domain *d, struct device_node *ctrlr, + const u32 *intspec, unsigned int intsize, + unsigned long *out_hwirq, unsigned int *out_type) +{ + if (WARN_ON(intsize < 1)) + return -EINVAL; + *out_hwirq = intspec[0]; + *out_type = IRQ_TYPE_NONE; + return 0; +} +EXPORT_SYMBOL_GPL(irq_domain_xlate_onecell); + +/** + * irq_domain_xlate_twocell() - Generic xlate for direct two cell bindings + * + * Device Tree IRQ specifier translation function which works with two cell + * bindings where the cell values map directly to the hwirq number + * and linux irq flags. + */ +int irq_domain_xlate_twocell(struct irq_domain *d, struct device_node *ctrlr, + const u32 *intspec, unsigned int intsize, + irq_hw_number_t *out_hwirq, unsigned int *out_type) +{ + if (WARN_ON(intsize < 2)) + return -EINVAL; + *out_hwirq = intspec[0]; + *out_type = intspec[1] & IRQ_TYPE_SENSE_MASK; + return 0; +} +EXPORT_SYMBOL_GPL(irq_domain_xlate_twocell); + +/** + * irq_domain_xlate_onetwocell() - Generic xlate for one or two cell bindings + * + * Device Tree IRQ specifier translation function which works with either one + * or two cell bindings where the cell values map directly to the hwirq number + * and linux irq flags. + * + * Note: don't use this function unless your interrupt controller explicitly + * supports both one and two cell bindings. For the majority of controllers + * the _onecell() or _twocell() variants above should be used. + */ +int irq_domain_xlate_onetwocell(struct irq_domain *d, + struct device_node *ctrlr, + const u32 *intspec, unsigned int intsize, + unsigned long *out_hwirq, unsigned int *out_type) +{ + if (WARN_ON(intsize < 1)) + return -EINVAL; + *out_hwirq = intspec[0]; + *out_type = (intsize > 1) ? intspec[1] : IRQ_TYPE_NONE; + return 0; +} +EXPORT_SYMBOL_GPL(irq_domain_xlate_onetwocell); + +const struct irq_domain_ops irq_domain_simple_ops = { + .xlate = irq_domain_xlate_onetwocell, +}; +EXPORT_SYMBOL_GPL(irq_domain_simple_ops); + +static int irq_domain_alloc_descs(int virq, unsigned int cnt, + irq_hw_number_t hwirq, int node) +{ + unsigned int hint; + + if (virq >= 0) { + virq = irq_alloc_descs(virq, virq, cnt, node); + } else { + hint = hwirq % nr_irqs; + if (hint == 0) + hint++; + virq = irq_alloc_descs_from(hint, cnt, node); + if (virq <= 0 && hint > 1) + virq = irq_alloc_descs_from(1, cnt, node); + } + + return virq; +} + +#ifdef CONFIG_IRQ_DOMAIN_HIERARCHY +/** + * irq_domain_add_hierarchy - Add a irqdomain into the hierarchy + * @parent: Parent irq domain to associate with the new domain + * @flags: Irq domain flags associated to the domain + * @size: Size of the domain. See below + * @node: Optional device-tree node of the interrupt controller + * @ops: Pointer to the interrupt domain callbacks + * @host_data: Controller private data pointer + * + * If @size is 0 a tree domain is created, otherwise a linear domain. + * + * If successful the parent is associated to the new domain and the + * domain flags are set. + * Returns pointer to IRQ domain, or NULL on failure. + */ +struct irq_domain *irq_domain_add_hierarchy(struct irq_domain *parent, + unsigned int flags, + unsigned int size, + struct device_node *node, + const struct irq_domain_ops *ops, + void *host_data) +{ + struct irq_domain *domain; + + if (size) + domain = irq_domain_add_linear(node, size, ops, host_data); + else + domain = irq_domain_add_tree(node, ops, host_data); + if (domain) { + domain->parent = parent; + domain->flags |= flags; + } + + return domain; +} + +static void irq_domain_insert_irq(int virq) +{ + struct irq_data *data; + + for (data = irq_get_irq_data(virq); data; data = data->parent_data) { + struct irq_domain *domain = data->domain; + irq_hw_number_t hwirq = data->hwirq; + + if (hwirq < domain->revmap_size) { + domain->linear_revmap[hwirq] = virq; + } else { + mutex_lock(&revmap_trees_mutex); + radix_tree_insert(&domain->revmap_tree, hwirq, data); + mutex_unlock(&revmap_trees_mutex); + } + + /* If not already assigned, give the domain the chip's name */ + if (!domain->name && data->chip) + domain->name = data->chip->name; + } + + irq_clear_status_flags(virq, IRQ_NOREQUEST); +} + +static void irq_domain_remove_irq(int virq) +{ + struct irq_data *data; + + irq_set_status_flags(virq, IRQ_NOREQUEST); + irq_set_chip_and_handler(virq, NULL, NULL); + synchronize_irq(virq); + smp_mb(); + + for (data = irq_get_irq_data(virq); data; data = data->parent_data) { + struct irq_domain *domain = data->domain; + irq_hw_number_t hwirq = data->hwirq; + + if (hwirq < domain->revmap_size) { + domain->linear_revmap[hwirq] = 0; + } else { + mutex_lock(&revmap_trees_mutex); + radix_tree_delete(&domain->revmap_tree, hwirq); + mutex_unlock(&revmap_trees_mutex); + } + } +} + +static struct irq_data *irq_domain_insert_irq_data(struct irq_domain *domain, + struct irq_data *child) +{ + struct irq_data *irq_data; + + irq_data = kzalloc_node(sizeof(*irq_data), GFP_KERNEL, child->node); + if (irq_data) { + child->parent_data = irq_data; + irq_data->irq = child->irq; + irq_data->node = child->node; + irq_data->domain = domain; + } + + return irq_data; +} + +static void irq_domain_free_irq_data(unsigned int virq, unsigned int nr_irqs) +{ + struct irq_data *irq_data, *tmp; + int i; + + for (i = 0; i < nr_irqs; i++) { + irq_data = irq_get_irq_data(virq + i); + tmp = irq_data->parent_data; + irq_data->parent_data = NULL; + irq_data->domain = NULL; + + while (tmp) { + irq_data = tmp; + tmp = tmp->parent_data; + kfree(irq_data); + } + } +} + +static int irq_domain_alloc_irq_data(struct irq_domain *domain, + unsigned int virq, unsigned int nr_irqs) +{ + struct irq_data *irq_data; + struct irq_domain *parent; + int i; + + /* The outermost irq_data is embedded in struct irq_desc */ + for (i = 0; i < nr_irqs; i++) { + irq_data = irq_get_irq_data(virq + i); + irq_data->domain = domain; + + for (parent = domain->parent; parent; parent = parent->parent) { + irq_data = irq_domain_insert_irq_data(parent, irq_data); + if (!irq_data) { + irq_domain_free_irq_data(virq, i + 1); + return -ENOMEM; + } + } + } + + return 0; +} + +/** + * irq_domain_get_irq_data - Get irq_data associated with @virq and @domain + * @domain: domain to match + * @virq: IRQ number to get irq_data + */ +struct irq_data *irq_domain_get_irq_data(struct irq_domain *domain, + unsigned int virq) +{ + struct irq_data *irq_data; + + for (irq_data = irq_get_irq_data(virq); irq_data; + irq_data = irq_data->parent_data) + if (irq_data->domain == domain) + return irq_data; + + return NULL; +} + +/** + * irq_domain_set_hwirq_and_chip - Set hwirq and irqchip of @virq at @domain + * @domain: Interrupt domain to match + * @virq: IRQ number + * @hwirq: The hwirq number + * @chip: The associated interrupt chip + * @chip_data: The associated chip data + */ +int irq_domain_set_hwirq_and_chip(struct irq_domain *domain, unsigned int virq, + irq_hw_number_t hwirq, struct irq_chip *chip, + void *chip_data) +{ + struct irq_data *irq_data = irq_domain_get_irq_data(domain, virq); + + if (!irq_data) + return -ENOENT; + + irq_data->hwirq = hwirq; + irq_data->chip = chip ? chip : &no_irq_chip; + irq_data->chip_data = chip_data; + + return 0; +} + +/** + * irq_domain_set_info - Set the complete data for a @virq in @domain + * @domain: Interrupt domain to match + * @virq: IRQ number + * @hwirq: The hardware interrupt number + * @chip: The associated interrupt chip + * @chip_data: The associated interrupt chip data + * @handler: The interrupt flow handler + * @handler_data: The interrupt flow handler data + * @handler_name: The interrupt handler name + */ +void irq_domain_set_info(struct irq_domain *domain, unsigned int virq, + irq_hw_number_t hwirq, struct irq_chip *chip, + void *chip_data, irq_flow_handler_t handler, + void *handler_data, const char *handler_name) +{ + irq_domain_set_hwirq_and_chip(domain, virq, hwirq, chip, chip_data); + __irq_set_handler(virq, handler, 0, handler_name); + irq_set_handler_data(virq, handler_data); +} + +/** + * irq_domain_reset_irq_data - Clear hwirq, chip and chip_data in @irq_data + * @irq_data: The pointer to irq_data + */ +void irq_domain_reset_irq_data(struct irq_data *irq_data) +{ + irq_data->hwirq = 0; + irq_data->chip = &no_irq_chip; + irq_data->chip_data = NULL; +} + +/** + * irq_domain_free_irqs_common - Clear irq_data and free the parent + * @domain: Interrupt domain to match + * @virq: IRQ number to start with + * @nr_irqs: The number of irqs to free + */ +void irq_domain_free_irqs_common(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs) +{ + struct irq_data *irq_data; + int i; + + for (i = 0; i < nr_irqs; i++) { + irq_data = irq_domain_get_irq_data(domain, virq + i); + if (irq_data) + irq_domain_reset_irq_data(irq_data); + } + irq_domain_free_irqs_parent(domain, virq, nr_irqs); +} + +/** + * irq_domain_free_irqs_top - Clear handler and handler data, clear irqdata and free parent + * @domain: Interrupt domain to match + * @virq: IRQ number to start with + * @nr_irqs: The number of irqs to free + */ +void irq_domain_free_irqs_top(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs) +{ + int i; + + for (i = 0; i < nr_irqs; i++) { + irq_set_handler_data(virq + i, NULL); + irq_set_handler(virq + i, NULL); + } + irq_domain_free_irqs_common(domain, virq, nr_irqs); +} + +static bool irq_domain_is_auto_recursive(struct irq_domain *domain) +{ + return domain->flags & IRQ_DOMAIN_FLAG_AUTO_RECURSIVE; +} + +static void irq_domain_free_irqs_recursive(struct irq_domain *domain, + unsigned int irq_base, + unsigned int nr_irqs) +{ + domain->ops->free(domain, irq_base, nr_irqs); + if (irq_domain_is_auto_recursive(domain)) { + BUG_ON(!domain->parent); + irq_domain_free_irqs_recursive(domain->parent, irq_base, + nr_irqs); + } +} + +static int irq_domain_alloc_irqs_recursive(struct irq_domain *domain, + unsigned int irq_base, + unsigned int nr_irqs, void *arg) +{ + int ret = 0; + struct irq_domain *parent = domain->parent; + bool recursive = irq_domain_is_auto_recursive(domain); + + BUG_ON(recursive && !parent); + if (recursive) + ret = irq_domain_alloc_irqs_recursive(parent, irq_base, + nr_irqs, arg); + if (ret >= 0) + ret = domain->ops->alloc(domain, irq_base, nr_irqs, arg); + if (ret < 0 && recursive) + irq_domain_free_irqs_recursive(parent, irq_base, nr_irqs); + + return ret; +} + +/** + * __irq_domain_alloc_irqs - Allocate IRQs from domain + * @domain: domain to allocate from + * @irq_base: allocate specified IRQ nubmer if irq_base >= 0 + * @nr_irqs: number of IRQs to allocate + * @node: NUMA node id for memory allocation + * @arg: domain specific argument + * @realloc: IRQ descriptors have already been allocated if true + * + * Allocate IRQ numbers and initialized all data structures to support + * hierarchy IRQ domains. + * Parameter @realloc is mainly to support legacy IRQs. + * Returns error code or allocated IRQ number + * + * The whole process to setup an IRQ has been split into two steps. + * The first step, __irq_domain_alloc_irqs(), is to allocate IRQ + * descriptor and required hardware resources. The second step, + * irq_domain_activate_irq(), is to program hardwares with preallocated + * resources. In this way, it's easier to rollback when failing to + * allocate resources. + */ +int __irq_domain_alloc_irqs(struct irq_domain *domain, int irq_base, + unsigned int nr_irqs, int node, void *arg, + bool realloc) +{ + int i, ret, virq; + + if (domain == NULL) { + domain = irq_default_domain; + if (WARN(!domain, "domain is NULL; cannot allocate IRQ\n")) + return -EINVAL; + } + + if (!domain->ops->alloc) { + pr_debug("domain->ops->alloc() is NULL\n"); + return -ENOSYS; + } + + if (realloc && irq_base >= 0) { + virq = irq_base; + } else { + virq = irq_domain_alloc_descs(irq_base, nr_irqs, 0, node); + if (virq < 0) { + pr_debug("cannot allocate IRQ(base %d, count %d)\n", + irq_base, nr_irqs); + return virq; + } + } + + if (irq_domain_alloc_irq_data(domain, virq, nr_irqs)) { + pr_debug("cannot allocate memory for IRQ%d\n", virq); + ret = -ENOMEM; + goto out_free_desc; + } + + mutex_lock(&irq_domain_mutex); + ret = irq_domain_alloc_irqs_recursive(domain, virq, nr_irqs, arg); + if (ret < 0) { + mutex_unlock(&irq_domain_mutex); + goto out_free_irq_data; + } + for (i = 0; i < nr_irqs; i++) + irq_domain_insert_irq(virq + i); + mutex_unlock(&irq_domain_mutex); + + return virq; + +out_free_irq_data: + irq_domain_free_irq_data(virq, nr_irqs); +out_free_desc: + irq_free_descs(virq, nr_irqs); + return ret; +} + +/** + * irq_domain_free_irqs - Free IRQ number and associated data structures + * @virq: base IRQ number + * @nr_irqs: number of IRQs to free + */ +void irq_domain_free_irqs(unsigned int virq, unsigned int nr_irqs) +{ + struct irq_data *data = irq_get_irq_data(virq); + int i; + + if (WARN(!data || !data->domain || !data->domain->ops->free, + "NULL pointer, cannot free irq\n")) + return; + + mutex_lock(&irq_domain_mutex); + for (i = 0; i < nr_irqs; i++) + irq_domain_remove_irq(virq + i); + irq_domain_free_irqs_recursive(data->domain, virq, nr_irqs); + mutex_unlock(&irq_domain_mutex); + + irq_domain_free_irq_data(virq, nr_irqs); + irq_free_descs(virq, nr_irqs); +} + +/** + * irq_domain_alloc_irqs_parent - Allocate interrupts from parent domain + * @irq_base: Base IRQ number + * @nr_irqs: Number of IRQs to allocate + * @arg: Allocation data (arch/domain specific) + * + * Check whether the domain has been setup recursive. If not allocate + * through the parent domain. + */ +int irq_domain_alloc_irqs_parent(struct irq_domain *domain, + unsigned int irq_base, unsigned int nr_irqs, + void *arg) +{ + /* irq_domain_alloc_irqs_recursive() has called parent's alloc() */ + if (irq_domain_is_auto_recursive(domain)) + return 0; + + domain = domain->parent; + if (domain) + return irq_domain_alloc_irqs_recursive(domain, irq_base, + nr_irqs, arg); + return -ENOSYS; +} + +/** + * irq_domain_free_irqs_parent - Free interrupts from parent domain + * @irq_base: Base IRQ number + * @nr_irqs: Number of IRQs to free + * + * Check whether the domain has been setup recursive. If not free + * through the parent domain. + */ +void irq_domain_free_irqs_parent(struct irq_domain *domain, + unsigned int irq_base, unsigned int nr_irqs) +{ + /* irq_domain_free_irqs_recursive() will call parent's free */ + if (!irq_domain_is_auto_recursive(domain) && domain->parent) + irq_domain_free_irqs_recursive(domain->parent, irq_base, + nr_irqs); +} + +/** + * irq_domain_activate_irq - Call domain_ops->activate recursively to activate + * interrupt + * @irq_data: outermost irq_data associated with interrupt + * + * This is the second step to call domain_ops->activate to program interrupt + * controllers, so the interrupt could actually get delivered. + */ +void irq_domain_activate_irq(struct irq_data *irq_data) +{ + if (irq_data && irq_data->domain) { + struct irq_domain *domain = irq_data->domain; + + if (irq_data->parent_data) + irq_domain_activate_irq(irq_data->parent_data); + if (domain->ops->activate) + domain->ops->activate(domain, irq_data); + } +} + +/** + * irq_domain_deactivate_irq - Call domain_ops->deactivate recursively to + * deactivate interrupt + * @irq_data: outermost irq_data associated with interrupt + * + * It calls domain_ops->deactivate to program interrupt controllers to disable + * interrupt delivery. + */ +void irq_domain_deactivate_irq(struct irq_data *irq_data) +{ + if (irq_data && irq_data->domain) { + struct irq_domain *domain = irq_data->domain; + + if (domain->ops->deactivate) + domain->ops->deactivate(domain, irq_data); + if (irq_data->parent_data) + irq_domain_deactivate_irq(irq_data->parent_data); + } +} + +static void irq_domain_check_hierarchy(struct irq_domain *domain) +{ + /* Hierarchy irq_domains must implement callback alloc() */ + if (domain->ops->alloc) + domain->flags |= IRQ_DOMAIN_FLAG_HIERARCHY; +} +#else /* CONFIG_IRQ_DOMAIN_HIERARCHY */ +/** + * irq_domain_get_irq_data - Get irq_data associated with @virq and @domain + * @domain: domain to match + * @virq: IRQ number to get irq_data + */ +struct irq_data *irq_domain_get_irq_data(struct irq_domain *domain, + unsigned int virq) +{ + struct irq_data *irq_data = irq_get_irq_data(virq); + + return (irq_data && irq_data->domain == domain) ? irq_data : NULL; +} + +static void irq_domain_check_hierarchy(struct irq_domain *domain) +{ +} +#endif /* CONFIG_IRQ_DOMAIN_HIERARCHY */ diff --git a/kernel/kernel/irq/manage.c b/kernel/kernel/irq/manage.c new file mode 100644 index 000000000..1b5c50a68 --- /dev/null +++ b/kernel/kernel/irq/manage.c @@ -0,0 +1,1983 @@ +/* + * linux/kernel/irq/manage.c + * + * Copyright (C) 1992, 1998-2006 Linus Torvalds, Ingo Molnar + * Copyright (C) 2005-2006 Thomas Gleixner + * + * This file contains driver APIs to the irq subsystem. + */ + +#define pr_fmt(fmt) "genirq: " fmt + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "internals.h" + +#ifdef CONFIG_IRQ_FORCED_THREADING +# ifndef CONFIG_PREEMPT_RT_BASE +__read_mostly bool force_irqthreads; + +static int __init setup_forced_irqthreads(char *arg) +{ + force_irqthreads = true; + return 0; +} +early_param("threadirqs", setup_forced_irqthreads); +# endif +#endif + +static void __synchronize_hardirq(struct irq_desc *desc) +{ + bool inprogress; + + do { + unsigned long flags; + + /* + * Wait until we're out of the critical section. This might + * give the wrong answer due to the lack of memory barriers. + */ + while (irqd_irq_inprogress(&desc->irq_data)) + cpu_relax(); + + /* Ok, that indicated we're done: double-check carefully. */ + raw_spin_lock_irqsave(&desc->lock, flags); + inprogress = irqd_irq_inprogress(&desc->irq_data); + raw_spin_unlock_irqrestore(&desc->lock, flags); + + /* Oops, that failed? */ + } while (inprogress); +} + +/** + * synchronize_hardirq - wait for pending hard IRQ handlers (on other CPUs) + * @irq: interrupt number to wait for + * + * This function waits for any pending hard IRQ handlers for this + * interrupt to complete before returning. If you use this + * function while holding a resource the IRQ handler may need you + * will deadlock. It does not take associated threaded handlers + * into account. + * + * Do not use this for shutdown scenarios where you must be sure + * that all parts (hardirq and threaded handler) have completed. + * + * Returns: false if a threaded handler is active. + * + * This function may be called - with care - from IRQ context. + */ +bool synchronize_hardirq(unsigned int irq) +{ + struct irq_desc *desc = irq_to_desc(irq); + + if (desc) { + __synchronize_hardirq(desc); + return !atomic_read(&desc->threads_active); + } + + return true; +} +EXPORT_SYMBOL(synchronize_hardirq); + +/** + * synchronize_irq - wait for pending IRQ handlers (on other CPUs) + * @irq: interrupt number to wait for + * + * This function waits for any pending IRQ handlers for this interrupt + * to complete before returning. If you use this function while + * holding a resource the IRQ handler may need you will deadlock. + * + * This function may be called - with care - from IRQ context. + */ +void synchronize_irq(unsigned int irq) +{ + struct irq_desc *desc = irq_to_desc(irq); + + if (desc) { + __synchronize_hardirq(desc); + /* + * We made sure that no hardirq handler is + * running. Now verify that no threaded handlers are + * active. + */ + wait_event(desc->wait_for_threads, + !atomic_read(&desc->threads_active)); + } +} +EXPORT_SYMBOL(synchronize_irq); + +#ifdef CONFIG_SMP +cpumask_var_t irq_default_affinity; + +/** + * irq_can_set_affinity - Check if the affinity of a given irq can be set + * @irq: Interrupt to check + * + */ +int irq_can_set_affinity(unsigned int irq) +{ + struct irq_desc *desc = irq_to_desc(irq); + + if (!desc || !irqd_can_balance(&desc->irq_data) || + !desc->irq_data.chip || !desc->irq_data.chip->irq_set_affinity) + return 0; + + return 1; +} + +/** + * irq_set_thread_affinity - Notify irq threads to adjust affinity + * @desc: irq descriptor which has affitnity changed + * + * We just set IRQTF_AFFINITY and delegate the affinity setting + * to the interrupt thread itself. We can not call + * set_cpus_allowed_ptr() here as we hold desc->lock and this + * code can be called from hard interrupt context. + */ +void irq_set_thread_affinity(struct irq_desc *desc) +{ + struct irqaction *action = desc->action; + + while (action) { + if (action->thread) + set_bit(IRQTF_AFFINITY, &action->thread_flags); + action = action->next; + } +} + +#ifdef CONFIG_GENERIC_PENDING_IRQ +static inline bool irq_can_move_pcntxt(struct irq_data *data) +{ + return irqd_can_move_in_process_context(data); +} +static inline bool irq_move_pending(struct irq_data *data) +{ + return irqd_is_setaffinity_pending(data); +} +static inline void +irq_copy_pending(struct irq_desc *desc, const struct cpumask *mask) +{ + cpumask_copy(desc->pending_mask, mask); +} +static inline void +irq_get_pending(struct cpumask *mask, struct irq_desc *desc) +{ + cpumask_copy(mask, desc->pending_mask); +} +#else +static inline bool irq_can_move_pcntxt(struct irq_data *data) { return true; } +static inline bool irq_move_pending(struct irq_data *data) { return false; } +static inline void +irq_copy_pending(struct irq_desc *desc, const struct cpumask *mask) { } +static inline void +irq_get_pending(struct cpumask *mask, struct irq_desc *desc) { } +#endif + +#ifdef CONFIG_PREEMPT_RT_FULL +static void _irq_affinity_notify(struct irq_affinity_notify *notify); +static struct task_struct *set_affinity_helper; +static LIST_HEAD(affinity_list); +static DEFINE_RAW_SPINLOCK(affinity_list_lock); + +static int set_affinity_thread(void *unused) +{ + while (1) { + struct irq_affinity_notify *notify; + int empty; + + set_current_state(TASK_INTERRUPTIBLE); + + raw_spin_lock_irq(&affinity_list_lock); + empty = list_empty(&affinity_list); + raw_spin_unlock_irq(&affinity_list_lock); + + if (empty) + schedule(); + if (kthread_should_stop()) + break; + set_current_state(TASK_RUNNING); +try_next: + notify = NULL; + + raw_spin_lock_irq(&affinity_list_lock); + if (!list_empty(&affinity_list)) { + notify = list_first_entry(&affinity_list, + struct irq_affinity_notify, list); + list_del_init(¬ify->list); + } + raw_spin_unlock_irq(&affinity_list_lock); + + if (!notify) + continue; + _irq_affinity_notify(notify); + goto try_next; + } + return 0; +} + +static void init_helper_thread(void) +{ + if (set_affinity_helper) + return; + set_affinity_helper = kthread_run(set_affinity_thread, NULL, + "affinity-cb"); + WARN_ON(IS_ERR(set_affinity_helper)); +} +#else + +static inline void init_helper_thread(void) { } + +#endif + +int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask, + bool force) +{ + struct irq_desc *desc = irq_data_to_desc(data); + struct irq_chip *chip = irq_data_get_irq_chip(data); + int ret; + + ret = chip->irq_set_affinity(data, mask, force); + switch (ret) { + case IRQ_SET_MASK_OK: + case IRQ_SET_MASK_OK_DONE: + cpumask_copy(data->affinity, mask); + case IRQ_SET_MASK_OK_NOCOPY: + irq_set_thread_affinity(desc); + ret = 0; + } + + return ret; +} + +int irq_set_affinity_locked(struct irq_data *data, const struct cpumask *mask, + bool force) +{ + struct irq_chip *chip = irq_data_get_irq_chip(data); + struct irq_desc *desc = irq_data_to_desc(data); + int ret = 0; + + if (!chip || !chip->irq_set_affinity) + return -EINVAL; + + if (irq_can_move_pcntxt(data)) { + ret = irq_do_set_affinity(data, mask, force); + } else { + irqd_set_move_pending(data); + irq_copy_pending(desc, mask); + } + + if (desc->affinity_notify) { + kref_get(&desc->affinity_notify->kref); + +#ifdef CONFIG_PREEMPT_RT_FULL + raw_spin_lock(&affinity_list_lock); + if (list_empty(&desc->affinity_notify->list)) + list_add_tail(&affinity_list, + &desc->affinity_notify->list); + raw_spin_unlock(&affinity_list_lock); + wake_up_process(set_affinity_helper); +#else + schedule_work(&desc->affinity_notify->work); +#endif + } + irqd_set(data, IRQD_AFFINITY_SET); + + return ret; +} + +int __irq_set_affinity(unsigned int irq, const struct cpumask *mask, bool force) +{ + struct irq_desc *desc = irq_to_desc(irq); + unsigned long flags; + int ret; + + if (!desc) + return -EINVAL; + + raw_spin_lock_irqsave(&desc->lock, flags); + ret = irq_set_affinity_locked(irq_desc_get_irq_data(desc), mask, force); + raw_spin_unlock_irqrestore(&desc->lock, flags); + return ret; +} + +int irq_set_affinity_hint(unsigned int irq, const struct cpumask *m) +{ + unsigned long flags; + struct irq_desc *desc = irq_get_desc_lock(irq, &flags, IRQ_GET_DESC_CHECK_GLOBAL); + + if (!desc) + return -EINVAL; + desc->affinity_hint = m; + irq_put_desc_unlock(desc, flags); + /* set the initial affinity to prevent every interrupt being on CPU0 */ + if (m) + __irq_set_affinity(irq, m, false); + return 0; +} +EXPORT_SYMBOL_GPL(irq_set_affinity_hint); + +static void _irq_affinity_notify(struct irq_affinity_notify *notify) +{ + struct irq_desc *desc = irq_to_desc(notify->irq); + cpumask_var_t cpumask; + unsigned long flags; + + if (!desc || !alloc_cpumask_var(&cpumask, GFP_KERNEL)) + goto out; + + raw_spin_lock_irqsave(&desc->lock, flags); + if (irq_move_pending(&desc->irq_data)) + irq_get_pending(cpumask, desc); + else + cpumask_copy(cpumask, desc->irq_data.affinity); + raw_spin_unlock_irqrestore(&desc->lock, flags); + + notify->notify(notify, cpumask); + + free_cpumask_var(cpumask); +out: + kref_put(¬ify->kref, notify->release); +} + +static void irq_affinity_notify(struct work_struct *work) +{ + struct irq_affinity_notify *notify = + container_of(work, struct irq_affinity_notify, work); + _irq_affinity_notify(notify); +} + +/** + * irq_set_affinity_notifier - control notification of IRQ affinity changes + * @irq: Interrupt for which to enable/disable notification + * @notify: Context for notification, or %NULL to disable + * notification. Function pointers must be initialised; + * the other fields will be initialised by this function. + * + * Must be called in process context. Notification may only be enabled + * after the IRQ is allocated and must be disabled before the IRQ is + * freed using free_irq(). + */ +int +irq_set_affinity_notifier(unsigned int irq, struct irq_affinity_notify *notify) +{ + struct irq_desc *desc = irq_to_desc(irq); + struct irq_affinity_notify *old_notify; + unsigned long flags; + + /* The release function is promised process context */ + might_sleep(); + + if (!desc) + return -EINVAL; + + /* Complete initialisation of *notify */ + if (notify) { + notify->irq = irq; + kref_init(¬ify->kref); + INIT_WORK(¬ify->work, irq_affinity_notify); + INIT_LIST_HEAD(¬ify->list); + init_helper_thread(); + } + + raw_spin_lock_irqsave(&desc->lock, flags); + old_notify = desc->affinity_notify; + desc->affinity_notify = notify; + raw_spin_unlock_irqrestore(&desc->lock, flags); + + if (old_notify) + kref_put(&old_notify->kref, old_notify->release); + + return 0; +} +EXPORT_SYMBOL_GPL(irq_set_affinity_notifier); + +#ifndef CONFIG_AUTO_IRQ_AFFINITY +/* + * Generic version of the affinity autoselector. + */ +static int +setup_affinity(unsigned int irq, struct irq_desc *desc, struct cpumask *mask) +{ + struct cpumask *set = irq_default_affinity; + int node = desc->irq_data.node; + + /* Excludes PER_CPU and NO_BALANCE interrupts */ + if (!irq_can_set_affinity(irq)) + return 0; + + /* + * Preserve an userspace affinity setup, but make sure that + * one of the targets is online. + */ + if (irqd_has_set(&desc->irq_data, IRQD_AFFINITY_SET)) { + if (cpumask_intersects(desc->irq_data.affinity, + cpu_online_mask)) + set = desc->irq_data.affinity; + else + irqd_clear(&desc->irq_data, IRQD_AFFINITY_SET); + } + + cpumask_and(mask, cpu_online_mask, set); + if (node != NUMA_NO_NODE) { + const struct cpumask *nodemask = cpumask_of_node(node); + + /* make sure at least one of the cpus in nodemask is online */ + if (cpumask_intersects(mask, nodemask)) + cpumask_and(mask, mask, nodemask); + } + irq_do_set_affinity(&desc->irq_data, mask, false); + return 0; +} +#else +static inline int +setup_affinity(unsigned int irq, struct irq_desc *d, struct cpumask *mask) +{ + return irq_select_affinity(irq); +} +#endif + +/* + * Called when affinity is set via /proc/irq + */ +int irq_select_affinity_usr(unsigned int irq, struct cpumask *mask) +{ + struct irq_desc *desc = irq_to_desc(irq); + unsigned long flags; + int ret; + + raw_spin_lock_irqsave(&desc->lock, flags); + ret = setup_affinity(irq, desc, mask); + raw_spin_unlock_irqrestore(&desc->lock, flags); + return ret; +} + +#else +static inline int +setup_affinity(unsigned int irq, struct irq_desc *desc, struct cpumask *mask) +{ + return 0; +} +#endif + +void __disable_irq(struct irq_desc *desc, unsigned int irq) +{ + if (!desc->depth++) + irq_disable(desc); +} + +static int __disable_irq_nosync(unsigned int irq) +{ + unsigned long flags; + struct irq_desc *desc = irq_get_desc_buslock(irq, &flags, IRQ_GET_DESC_CHECK_GLOBAL); + + if (!desc) + return -EINVAL; + __disable_irq(desc, irq); + irq_put_desc_busunlock(desc, flags); + return 0; +} + +/** + * disable_irq_nosync - disable an irq without waiting + * @irq: Interrupt to disable + * + * Disable the selected interrupt line. Disables and Enables are + * nested. + * Unlike disable_irq(), this function does not ensure existing + * instances of the IRQ handler have completed before returning. + * + * This function may be called from IRQ context. + */ +void disable_irq_nosync(unsigned int irq) +{ + __disable_irq_nosync(irq); +} +EXPORT_SYMBOL(disable_irq_nosync); + +/** + * disable_irq - disable an irq and wait for completion + * @irq: Interrupt to disable + * + * Disable the selected interrupt line. Enables and Disables are + * nested. + * This function waits for any pending IRQ handlers for this interrupt + * to complete before returning. If you use this function while + * holding a resource the IRQ handler may need you will deadlock. + * + * This function may be called - with care - from IRQ context. + */ +void disable_irq(unsigned int irq) +{ + if (!__disable_irq_nosync(irq)) + synchronize_irq(irq); +} +EXPORT_SYMBOL(disable_irq); + +/** + * disable_hardirq - disables an irq and waits for hardirq completion + * @irq: Interrupt to disable + * + * Disable the selected interrupt line. Enables and Disables are + * nested. + * This function waits for any pending hard IRQ handlers for this + * interrupt to complete before returning. If you use this function while + * holding a resource the hard IRQ handler may need you will deadlock. + * + * When used to optimistically disable an interrupt from atomic context + * the return value must be checked. + * + * Returns: false if a threaded handler is active. + * + * This function may be called - with care - from IRQ context. + */ +bool disable_hardirq(unsigned int irq) +{ + if (!__disable_irq_nosync(irq)) + return synchronize_hardirq(irq); + + return false; +} +EXPORT_SYMBOL_GPL(disable_hardirq); + +void __enable_irq(struct irq_desc *desc, unsigned int irq) +{ + switch (desc->depth) { + case 0: + err_out: + WARN(1, KERN_WARNING "Unbalanced enable for IRQ %d\n", irq); + break; + case 1: { + if (desc->istate & IRQS_SUSPENDED) + goto err_out; + /* Prevent probing on this irq: */ + irq_settings_set_noprobe(desc); + irq_enable(desc); + check_irq_resend(desc, irq); + /* fall-through */ + } + default: + desc->depth--; + } +} + +/** + * enable_irq - enable handling of an irq + * @irq: Interrupt to enable + * + * Undoes the effect of one call to disable_irq(). If this + * matches the last disable, processing of interrupts on this + * IRQ line is re-enabled. + * + * This function may be called from IRQ context only when + * desc->irq_data.chip->bus_lock and desc->chip->bus_sync_unlock are NULL ! + */ +void enable_irq(unsigned int irq) +{ + unsigned long flags; + struct irq_desc *desc = irq_get_desc_buslock(irq, &flags, IRQ_GET_DESC_CHECK_GLOBAL); + + if (!desc) + return; + if (WARN(!desc->irq_data.chip, + KERN_ERR "enable_irq before setup/request_irq: irq %u\n", irq)) + goto out; + + __enable_irq(desc, irq); +out: + irq_put_desc_busunlock(desc, flags); +} +EXPORT_SYMBOL(enable_irq); + +static int set_irq_wake_real(unsigned int irq, unsigned int on) +{ + struct irq_desc *desc = irq_to_desc(irq); + int ret = -ENXIO; + + if (irq_desc_get_chip(desc)->flags & IRQCHIP_SKIP_SET_WAKE) + return 0; + + if (desc->irq_data.chip->irq_set_wake) + ret = desc->irq_data.chip->irq_set_wake(&desc->irq_data, on); + + return ret; +} + +/** + * irq_set_irq_wake - control irq power management wakeup + * @irq: interrupt to control + * @on: enable/disable power management wakeup + * + * Enable/disable power management wakeup mode, which is + * disabled by default. Enables and disables must match, + * just as they match for non-wakeup mode support. + * + * Wakeup mode lets this IRQ wake the system from sleep + * states like "suspend to RAM". + */ +int irq_set_irq_wake(unsigned int irq, unsigned int on) +{ + unsigned long flags; + struct irq_desc *desc = irq_get_desc_buslock(irq, &flags, IRQ_GET_DESC_CHECK_GLOBAL); + int ret = 0; + + if (!desc) + return -EINVAL; + + /* wakeup-capable irqs can be shared between drivers that + * don't need to have the same sleep mode behaviors. + */ + if (on) { + if (desc->wake_depth++ == 0) { + ret = set_irq_wake_real(irq, on); + if (ret) + desc->wake_depth = 0; + else + irqd_set(&desc->irq_data, IRQD_WAKEUP_STATE); + } + } else { + if (desc->wake_depth == 0) { + WARN(1, "Unbalanced IRQ %d wake disable\n", irq); + } else if (--desc->wake_depth == 0) { + ret = set_irq_wake_real(irq, on); + if (ret) + desc->wake_depth = 1; + else + irqd_clear(&desc->irq_data, IRQD_WAKEUP_STATE); + } + } + irq_put_desc_busunlock(desc, flags); + return ret; +} +EXPORT_SYMBOL(irq_set_irq_wake); + +/* + * Internal function that tells the architecture code whether a + * particular irq has been exclusively allocated or is available + * for driver use. + */ +int can_request_irq(unsigned int irq, unsigned long irqflags) +{ + unsigned long flags; + struct irq_desc *desc = irq_get_desc_lock(irq, &flags, 0); + int canrequest = 0; + + if (!desc) + return 0; + + if (irq_settings_can_request(desc)) { + if (!desc->action || + irqflags & desc->action->flags & IRQF_SHARED) + canrequest = 1; + } + irq_put_desc_unlock(desc, flags); + return canrequest; +} + +int __irq_set_trigger(struct irq_desc *desc, unsigned int irq, + unsigned long flags) +{ + struct irq_chip *chip = desc->irq_data.chip; + int ret, unmask = 0; + + if (!chip || !chip->irq_set_type) { + /* + * IRQF_TRIGGER_* but the PIC does not support multiple + * flow-types? + */ + pr_debug("No set_type function for IRQ %d (%s)\n", irq, + chip ? (chip->name ? : "unknown") : "unknown"); + return 0; + } + + flags &= IRQ_TYPE_SENSE_MASK; + + if (chip->flags & IRQCHIP_SET_TYPE_MASKED) { + if (!irqd_irq_masked(&desc->irq_data)) + mask_irq(desc); + if (!irqd_irq_disabled(&desc->irq_data)) + unmask = 1; + } + + /* caller masked out all except trigger mode flags */ + ret = chip->irq_set_type(&desc->irq_data, flags); + + switch (ret) { + case IRQ_SET_MASK_OK: + case IRQ_SET_MASK_OK_DONE: + irqd_clear(&desc->irq_data, IRQD_TRIGGER_MASK); + irqd_set(&desc->irq_data, flags); + + case IRQ_SET_MASK_OK_NOCOPY: + flags = irqd_get_trigger_type(&desc->irq_data); + irq_settings_set_trigger_mask(desc, flags); + irqd_clear(&desc->irq_data, IRQD_LEVEL); + irq_settings_clr_level(desc); + if (flags & IRQ_TYPE_LEVEL_MASK) { + irq_settings_set_level(desc); + irqd_set(&desc->irq_data, IRQD_LEVEL); + } + + ret = 0; + break; + default: + pr_err("Setting trigger mode %lu for irq %u failed (%pF)\n", + flags, irq, chip->irq_set_type); + } + if (unmask) + unmask_irq(desc); + return ret; +} + +#ifdef CONFIG_HARDIRQS_SW_RESEND +int irq_set_parent(int irq, int parent_irq) +{ + unsigned long flags; + struct irq_desc *desc = irq_get_desc_lock(irq, &flags, 0); + + if (!desc) + return -EINVAL; + + desc->parent_irq = parent_irq; + + irq_put_desc_unlock(desc, flags); + return 0; +} +#endif + +/* + * Default primary interrupt handler for threaded interrupts. Is + * assigned as primary handler when request_threaded_irq is called + * with handler == NULL. Useful for oneshot interrupts. + */ +static irqreturn_t irq_default_primary_handler(int irq, void *dev_id) +{ + return IRQ_WAKE_THREAD; +} + +/* + * Primary handler for nested threaded interrupts. Should never be + * called. + */ +static irqreturn_t irq_nested_primary_handler(int irq, void *dev_id) +{ + WARN(1, "Primary handler called for nested irq %d\n", irq); + return IRQ_NONE; +} + +static int irq_wait_for_interrupt(struct irqaction *action) +{ + set_current_state(TASK_INTERRUPTIBLE); + + while (!kthread_should_stop()) { + + if (test_and_clear_bit(IRQTF_RUNTHREAD, + &action->thread_flags)) { + __set_current_state(TASK_RUNNING); + return 0; + } + schedule(); + set_current_state(TASK_INTERRUPTIBLE); + } + __set_current_state(TASK_RUNNING); + return -1; +} + +/* + * Oneshot interrupts keep the irq line masked until the threaded + * handler finished. unmask if the interrupt has not been disabled and + * is marked MASKED. + */ +static void irq_finalize_oneshot(struct irq_desc *desc, + struct irqaction *action) +{ + if (!(desc->istate & IRQS_ONESHOT)) + return; +again: + chip_bus_lock(desc); + raw_spin_lock_irq(&desc->lock); + + /* + * Implausible though it may be we need to protect us against + * the following scenario: + * + * The thread is faster done than the hard interrupt handler + * on the other CPU. If we unmask the irq line then the + * interrupt can come in again and masks the line, leaves due + * to IRQS_INPROGRESS and the irq line is masked forever. + * + * This also serializes the state of shared oneshot handlers + * versus "desc->threads_onehsot |= action->thread_mask;" in + * irq_wake_thread(). See the comment there which explains the + * serialization. + */ + if (unlikely(irqd_irq_inprogress(&desc->irq_data))) { + raw_spin_unlock_irq(&desc->lock); + chip_bus_sync_unlock(desc); + cpu_relax(); + goto again; + } + + /* + * Now check again, whether the thread should run. Otherwise + * we would clear the threads_oneshot bit of this thread which + * was just set. + */ + if (test_bit(IRQTF_RUNTHREAD, &action->thread_flags)) + goto out_unlock; + + desc->threads_oneshot &= ~action->thread_mask; + + if (!desc->threads_oneshot && !irqd_irq_disabled(&desc->irq_data) && + irqd_irq_masked(&desc->irq_data)) + unmask_threaded_irq(desc); + +out_unlock: + raw_spin_unlock_irq(&desc->lock); + chip_bus_sync_unlock(desc); +} + +#ifdef CONFIG_SMP +/* + * Check whether we need to change the affinity of the interrupt thread. + */ +static void +irq_thread_check_affinity(struct irq_desc *desc, struct irqaction *action) +{ + cpumask_var_t mask; + bool valid = true; + + if (!test_and_clear_bit(IRQTF_AFFINITY, &action->thread_flags)) + return; + + /* + * In case we are out of memory we set IRQTF_AFFINITY again and + * try again next time + */ + if (!alloc_cpumask_var(&mask, GFP_KERNEL)) { + set_bit(IRQTF_AFFINITY, &action->thread_flags); + return; + } + + raw_spin_lock_irq(&desc->lock); + /* + * This code is triggered unconditionally. Check the affinity + * mask pointer. For CPU_MASK_OFFSTACK=n this is optimized out. + */ + if (desc->irq_data.affinity) + cpumask_copy(mask, desc->irq_data.affinity); + else + valid = false; + raw_spin_unlock_irq(&desc->lock); + + if (valid) + set_cpus_allowed_ptr(current, mask); + free_cpumask_var(mask); +} +#else +static inline void +irq_thread_check_affinity(struct irq_desc *desc, struct irqaction *action) { } +#endif + +/* + * Interrupts which are not explicitely requested as threaded + * interrupts rely on the implicit bh/preempt disable of the hard irq + * context. So we need to disable bh here to avoid deadlocks and other + * side effects. + */ +static irqreturn_t +irq_forced_thread_fn(struct irq_desc *desc, struct irqaction *action) +{ + irqreturn_t ret; + + local_bh_disable(); + ret = action->thread_fn(action->irq, action->dev_id); + irq_finalize_oneshot(desc, action); + /* + * Interrupts which have real time requirements can be set up + * to avoid softirq processing in the thread handler. This is + * safe as these interrupts do not raise soft interrupts. + */ + if (irq_settings_no_softirq_call(desc)) + _local_bh_enable(); + else + local_bh_enable(); + return ret; +} + +/* + * Interrupts explicitly requested as threaded interrupts want to be + * preemtible - many of them need to sleep and wait for slow busses to + * complete. + */ +static irqreturn_t irq_thread_fn(struct irq_desc *desc, + struct irqaction *action) +{ + irqreturn_t ret; + + ret = action->thread_fn(action->irq, action->dev_id); + irq_finalize_oneshot(desc, action); + return ret; +} + +static void wake_threads_waitq(struct irq_desc *desc) +{ + if (atomic_dec_and_test(&desc->threads_active)) + wake_up(&desc->wait_for_threads); +} + +static void irq_thread_dtor(struct callback_head *unused) +{ + struct task_struct *tsk = current; + struct irq_desc *desc; + struct irqaction *action; + + if (WARN_ON_ONCE(!(current->flags & PF_EXITING))) + return; + + action = kthread_data(tsk); + + pr_err("exiting task \"%s\" (%d) is an active IRQ thread (irq %d)\n", + tsk->comm, tsk->pid, action->irq); + + + desc = irq_to_desc(action->irq); + /* + * If IRQTF_RUNTHREAD is set, we need to decrement + * desc->threads_active and wake possible waiters. + */ + if (test_and_clear_bit(IRQTF_RUNTHREAD, &action->thread_flags)) + wake_threads_waitq(desc); + + /* Prevent a stale desc->threads_oneshot */ + irq_finalize_oneshot(desc, action); +} + +/* + * Interrupt handler thread + */ +static int irq_thread(void *data) +{ + struct callback_head on_exit_work; + struct irqaction *action = data; + struct irq_desc *desc = irq_to_desc(action->irq); + irqreturn_t (*handler_fn)(struct irq_desc *desc, + struct irqaction *action); + + if (force_irqthreads && test_bit(IRQTF_FORCED_THREAD, + &action->thread_flags)) + handler_fn = irq_forced_thread_fn; + else + handler_fn = irq_thread_fn; + + init_task_work(&on_exit_work, irq_thread_dtor); + task_work_add(current, &on_exit_work, false); + + irq_thread_check_affinity(desc, action); + + while (!irq_wait_for_interrupt(action)) { + irqreturn_t action_ret; + + irq_thread_check_affinity(desc, action); + + action_ret = handler_fn(desc, action); + if (action_ret == IRQ_HANDLED) + atomic_inc(&desc->threads_handled); + +#ifdef CONFIG_PREEMPT_RT_FULL + migrate_disable(); + add_interrupt_randomness(action->irq, 0, + desc->random_ip ^ (unsigned long) action); + migrate_enable(); +#endif + wake_threads_waitq(desc); + } + + /* + * This is the regular exit path. __free_irq() is stopping the + * thread via kthread_stop() after calling + * synchronize_irq(). So neither IRQTF_RUNTHREAD nor the + * oneshot mask bit can be set. We cannot verify that as we + * cannot touch the oneshot mask at this point anymore as + * __setup_irq() might have given out currents thread_mask + * again. + */ + task_work_cancel(current, irq_thread_dtor); + return 0; +} + +/** + * irq_wake_thread - wake the irq thread for the action identified by dev_id + * @irq: Interrupt line + * @dev_id: Device identity for which the thread should be woken + * + */ +void irq_wake_thread(unsigned int irq, void *dev_id) +{ + struct irq_desc *desc = irq_to_desc(irq); + struct irqaction *action; + unsigned long flags; + + if (!desc || WARN_ON(irq_settings_is_per_cpu_devid(desc))) + return; + + raw_spin_lock_irqsave(&desc->lock, flags); + for (action = desc->action; action; action = action->next) { + if (action->dev_id == dev_id) { + if (action->thread) + __irq_wake_thread(desc, action); + break; + } + } + raw_spin_unlock_irqrestore(&desc->lock, flags); +} +EXPORT_SYMBOL_GPL(irq_wake_thread); + +static void irq_setup_forced_threading(struct irqaction *new) +{ + if (!force_irqthreads) + return; + if (new->flags & (IRQF_NO_THREAD | IRQF_PERCPU | IRQF_ONESHOT)) + return; + + new->flags |= IRQF_ONESHOT; + + if (!new->thread_fn) { + set_bit(IRQTF_FORCED_THREAD, &new->thread_flags); + new->thread_fn = new->handler; + new->handler = irq_default_primary_handler; + } +} + +static int irq_request_resources(struct irq_desc *desc) +{ + struct irq_data *d = &desc->irq_data; + struct irq_chip *c = d->chip; + + return c->irq_request_resources ? c->irq_request_resources(d) : 0; +} + +static void irq_release_resources(struct irq_desc *desc) +{ + struct irq_data *d = &desc->irq_data; + struct irq_chip *c = d->chip; + + if (c->irq_release_resources) + c->irq_release_resources(d); +} + +/* + * Internal function to register an irqaction - typically used to + * allocate special interrupts that are part of the architecture. + */ +static int +__setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) +{ + struct irqaction *old, **old_ptr; + unsigned long flags, thread_mask = 0; + int ret, nested, shared = 0; + cpumask_var_t mask; + + if (!desc) + return -EINVAL; + + if (desc->irq_data.chip == &no_irq_chip) + return -ENOSYS; + if (!try_module_get(desc->owner)) + return -ENODEV; + + /* + * Check whether the interrupt nests into another interrupt + * thread. + */ + nested = irq_settings_is_nested_thread(desc); + if (nested) { + if (!new->thread_fn) { + ret = -EINVAL; + goto out_mput; + } + /* + * Replace the primary handler which was provided from + * the driver for non nested interrupt handling by the + * dummy function which warns when called. + */ + new->handler = irq_nested_primary_handler; + } else { + if (irq_settings_can_thread(desc)) + irq_setup_forced_threading(new); + } + + /* + * Create a handler thread when a thread function is supplied + * and the interrupt does not nest into another interrupt + * thread. + */ + if (new->thread_fn && !nested) { + struct task_struct *t; + static const struct sched_param param = { + .sched_priority = MAX_USER_RT_PRIO/2, + }; + + t = kthread_create(irq_thread, new, "irq/%d-%s", irq, + new->name); + if (IS_ERR(t)) { + ret = PTR_ERR(t); + goto out_mput; + } + + sched_setscheduler_nocheck(t, SCHED_FIFO, ¶m); + + /* + * We keep the reference to the task struct even if + * the thread dies to avoid that the interrupt code + * references an already freed task_struct. + */ + get_task_struct(t); + new->thread = t; + /* + * Tell the thread to set its affinity. This is + * important for shared interrupt handlers as we do + * not invoke setup_affinity() for the secondary + * handlers as everything is already set up. Even for + * interrupts marked with IRQF_NO_BALANCE this is + * correct as we want the thread to move to the cpu(s) + * on which the requesting code placed the interrupt. + */ + set_bit(IRQTF_AFFINITY, &new->thread_flags); + } + + if (!alloc_cpumask_var(&mask, GFP_KERNEL)) { + ret = -ENOMEM; + goto out_thread; + } + + /* + * Drivers are often written to work w/o knowledge about the + * underlying irq chip implementation, so a request for a + * threaded irq without a primary hard irq context handler + * requires the ONESHOT flag to be set. Some irq chips like + * MSI based interrupts are per se one shot safe. Check the + * chip flags, so we can avoid the unmask dance at the end of + * the threaded handler for those. + */ + if (desc->irq_data.chip->flags & IRQCHIP_ONESHOT_SAFE) + new->flags &= ~IRQF_ONESHOT; + + /* + * The following block of code has to be executed atomically + */ + raw_spin_lock_irqsave(&desc->lock, flags); + old_ptr = &desc->action; + old = *old_ptr; + if (old) { + /* + * Can't share interrupts unless both agree to and are + * the same type (level, edge, polarity). So both flag + * fields must have IRQF_SHARED set and the bits which + * set the trigger type must match. Also all must + * agree on ONESHOT. + */ + if (!((old->flags & new->flags) & IRQF_SHARED) || + ((old->flags ^ new->flags) & IRQF_TRIGGER_MASK) || + ((old->flags ^ new->flags) & IRQF_ONESHOT)) + goto mismatch; + + /* All handlers must agree on per-cpuness */ + if ((old->flags & IRQF_PERCPU) != + (new->flags & IRQF_PERCPU)) + goto mismatch; + + /* add new interrupt at end of irq queue */ + do { + /* + * Or all existing action->thread_mask bits, + * so we can find the next zero bit for this + * new action. + */ + thread_mask |= old->thread_mask; + old_ptr = &old->next; + old = *old_ptr; + } while (old); + shared = 1; + } + + /* + * Setup the thread mask for this irqaction for ONESHOT. For + * !ONESHOT irqs the thread mask is 0 so we can avoid a + * conditional in irq_wake_thread(). + */ + if (new->flags & IRQF_ONESHOT) { + /* + * Unlikely to have 32 resp 64 irqs sharing one line, + * but who knows. + */ + if (thread_mask == ~0UL) { + ret = -EBUSY; + goto out_mask; + } + /* + * The thread_mask for the action is or'ed to + * desc->thread_active to indicate that the + * IRQF_ONESHOT thread handler has been woken, but not + * yet finished. The bit is cleared when a thread + * completes. When all threads of a shared interrupt + * line have completed desc->threads_active becomes + * zero and the interrupt line is unmasked. See + * handle.c:irq_wake_thread() for further information. + * + * If no thread is woken by primary (hard irq context) + * interrupt handlers, then desc->threads_active is + * also checked for zero to unmask the irq line in the + * affected hard irq flow handlers + * (handle_[fasteoi|level]_irq). + * + * The new action gets the first zero bit of + * thread_mask assigned. See the loop above which or's + * all existing action->thread_mask bits. + */ + new->thread_mask = 1 << ffz(thread_mask); + + } else if (new->handler == irq_default_primary_handler && + !(desc->irq_data.chip->flags & IRQCHIP_ONESHOT_SAFE)) { + /* + * The interrupt was requested with handler = NULL, so + * we use the default primary handler for it. But it + * does not have the oneshot flag set. In combination + * with level interrupts this is deadly, because the + * default primary handler just wakes the thread, then + * the irq lines is reenabled, but the device still + * has the level irq asserted. Rinse and repeat.... + * + * While this works for edge type interrupts, we play + * it safe and reject unconditionally because we can't + * say for sure which type this interrupt really + * has. The type flags are unreliable as the + * underlying chip implementation can override them. + */ + pr_err("Threaded irq requested with handler=NULL and !ONESHOT for irq %d\n", + irq); + ret = -EINVAL; + goto out_mask; + } + + if (!shared) { + ret = irq_request_resources(desc); + if (ret) { + pr_err("Failed to request resources for %s (irq %d) on irqchip %s\n", + new->name, irq, desc->irq_data.chip->name); + goto out_mask; + } + + init_waitqueue_head(&desc->wait_for_threads); + + /* Setup the type (level, edge polarity) if configured: */ + if (new->flags & IRQF_TRIGGER_MASK) { + ret = __irq_set_trigger(desc, irq, + new->flags & IRQF_TRIGGER_MASK); + + if (ret) + goto out_mask; + } + + desc->istate &= ~(IRQS_AUTODETECT | IRQS_SPURIOUS_DISABLED | \ + IRQS_ONESHOT | IRQS_WAITING); + irqd_clear(&desc->irq_data, IRQD_IRQ_INPROGRESS); + + if (new->flags & IRQF_PERCPU) { + irqd_set(&desc->irq_data, IRQD_PER_CPU); + irq_settings_set_per_cpu(desc); + } + + if (new->flags & IRQF_ONESHOT) + desc->istate |= IRQS_ONESHOT; + + if (irq_settings_can_autoenable(desc)) + irq_startup(desc, true); + else + /* Undo nested disables: */ + desc->depth = 1; + + /* Exclude IRQ from balancing if requested */ + if (new->flags & IRQF_NOBALANCING) { + irq_settings_set_no_balancing(desc); + irqd_set(&desc->irq_data, IRQD_NO_BALANCING); + } + + if (new->flags & IRQF_NO_SOFTIRQ_CALL) + irq_settings_set_no_softirq_call(desc); + + /* Set default affinity mask once everything is setup */ + setup_affinity(irq, desc, mask); + + } else if (new->flags & IRQF_TRIGGER_MASK) { + unsigned int nmsk = new->flags & IRQF_TRIGGER_MASK; + unsigned int omsk = irq_settings_get_trigger_mask(desc); + + if (nmsk != omsk) + /* hope the handler works with current trigger mode */ + pr_warning("irq %d uses trigger mode %u; requested %u\n", + irq, nmsk, omsk); + } + + new->irq = irq; + *old_ptr = new; + + irq_pm_install_action(desc, new); + + /* Reset broken irq detection when installing new handler */ + desc->irq_count = 0; + desc->irqs_unhandled = 0; + + /* + * Check whether we disabled the irq via the spurious handler + * before. Reenable it and give it another chance. + */ + if (shared && (desc->istate & IRQS_SPURIOUS_DISABLED)) { + desc->istate &= ~IRQS_SPURIOUS_DISABLED; + __enable_irq(desc, irq); + } + + raw_spin_unlock_irqrestore(&desc->lock, flags); + + /* + * Strictly no need to wake it up, but hung_task complains + * when no hard interrupt wakes the thread up. + */ + if (new->thread) + wake_up_process(new->thread); + + register_irq_proc(irq, desc); + new->dir = NULL; + register_handler_proc(irq, new); + free_cpumask_var(mask); + + return 0; + +mismatch: + if (!(new->flags & IRQF_PROBE_SHARED)) { + pr_err("Flags mismatch irq %d. %08x (%s) vs. %08x (%s)\n", + irq, new->flags, new->name, old->flags, old->name); +#ifdef CONFIG_DEBUG_SHIRQ + dump_stack(); +#endif + } + ret = -EBUSY; + +out_mask: + raw_spin_unlock_irqrestore(&desc->lock, flags); + free_cpumask_var(mask); + +out_thread: + if (new->thread) { + struct task_struct *t = new->thread; + + new->thread = NULL; + kthread_stop(t); + put_task_struct(t); + } +out_mput: + module_put(desc->owner); + return ret; +} + +/** + * setup_irq - setup an interrupt + * @irq: Interrupt line to setup + * @act: irqaction for the interrupt + * + * Used to statically setup interrupts in the early boot process. + */ +int setup_irq(unsigned int irq, struct irqaction *act) +{ + int retval; + struct irq_desc *desc = irq_to_desc(irq); + + if (WARN_ON(irq_settings_is_per_cpu_devid(desc))) + return -EINVAL; + chip_bus_lock(desc); + retval = __setup_irq(irq, desc, act); + chip_bus_sync_unlock(desc); + + return retval; +} +EXPORT_SYMBOL_GPL(setup_irq); + +/* + * Internal function to unregister an irqaction - used to free + * regular and special interrupts that are part of the architecture. + */ +static struct irqaction *__free_irq(unsigned int irq, void *dev_id) +{ + struct irq_desc *desc = irq_to_desc(irq); + struct irqaction *action, **action_ptr; + unsigned long flags; + + WARN(in_interrupt(), "Trying to free IRQ %d from IRQ context!\n", irq); + + if (!desc) + return NULL; + + raw_spin_lock_irqsave(&desc->lock, flags); + + /* + * There can be multiple actions per IRQ descriptor, find the right + * one based on the dev_id: + */ + action_ptr = &desc->action; + for (;;) { + action = *action_ptr; + + if (!action) { + WARN(1, "Trying to free already-free IRQ %d\n", irq); + raw_spin_unlock_irqrestore(&desc->lock, flags); + + return NULL; + } + + if (action->dev_id == dev_id) + break; + action_ptr = &action->next; + } + + /* Found it - now remove it from the list of entries: */ + *action_ptr = action->next; + + irq_pm_remove_action(desc, action); + + /* If this was the last handler, shut down the IRQ line: */ + if (!desc->action) { + irq_shutdown(desc); + irq_release_resources(desc); + } + +#ifdef CONFIG_SMP + /* make sure affinity_hint is cleaned up */ + if (WARN_ON_ONCE(desc->affinity_hint)) + desc->affinity_hint = NULL; +#endif + + raw_spin_unlock_irqrestore(&desc->lock, flags); + + unregister_handler_proc(irq, action); + + /* Make sure it's not being used on another CPU: */ + synchronize_irq(irq); + +#ifdef CONFIG_DEBUG_SHIRQ + /* + * It's a shared IRQ -- the driver ought to be prepared for an IRQ + * event to happen even now it's being freed, so let's make sure that + * is so by doing an extra call to the handler .... + * + * ( We do this after actually deregistering it, to make sure that a + * 'real' IRQ doesn't run in * parallel with our fake. ) + */ + if (action->flags & IRQF_SHARED) { + local_irq_save(flags); + action->handler(irq, dev_id); + local_irq_restore(flags); + } +#endif + + if (action->thread) { + kthread_stop(action->thread); + put_task_struct(action->thread); + } + + module_put(desc->owner); + return action; +} + +/** + * remove_irq - free an interrupt + * @irq: Interrupt line to free + * @act: irqaction for the interrupt + * + * Used to remove interrupts statically setup by the early boot process. + */ +void remove_irq(unsigned int irq, struct irqaction *act) +{ + struct irq_desc *desc = irq_to_desc(irq); + + if (desc && !WARN_ON(irq_settings_is_per_cpu_devid(desc))) + __free_irq(irq, act->dev_id); +} +EXPORT_SYMBOL_GPL(remove_irq); + +/** + * free_irq - free an interrupt allocated with request_irq + * @irq: Interrupt line to free + * @dev_id: Device identity to free + * + * Remove an interrupt handler. The handler is removed and if the + * interrupt line is no longer in use by any driver it is disabled. + * On a shared IRQ the caller must ensure the interrupt is disabled + * on the card it drives before calling this function. The function + * does not return until any executing interrupts for this IRQ + * have completed. + * + * This function must not be called from interrupt context. + */ +void free_irq(unsigned int irq, void *dev_id) +{ + struct irq_desc *desc = irq_to_desc(irq); + + if (!desc || WARN_ON(irq_settings_is_per_cpu_devid(desc))) + return; + +#ifdef CONFIG_SMP + if (WARN_ON(desc->affinity_notify)) + desc->affinity_notify = NULL; +#endif + + chip_bus_lock(desc); + kfree(__free_irq(irq, dev_id)); + chip_bus_sync_unlock(desc); +} +EXPORT_SYMBOL(free_irq); + +/** + * request_threaded_irq - allocate an interrupt line + * @irq: Interrupt line to allocate + * @handler: Function to be called when the IRQ occurs. + * Primary handler for threaded interrupts + * If NULL and thread_fn != NULL the default + * primary handler is installed + * @thread_fn: Function called from the irq handler thread + * If NULL, no irq thread is created + * @irqflags: Interrupt type flags + * @devname: An ascii name for the claiming device + * @dev_id: A cookie passed back to the handler function + * + * This call allocates interrupt resources and enables the + * interrupt line and IRQ handling. From the point this + * call is made your handler function may be invoked. Since + * your handler function must clear any interrupt the board + * raises, you must take care both to initialise your hardware + * and to set up the interrupt handler in the right order. + * + * If you want to set up a threaded irq handler for your device + * then you need to supply @handler and @thread_fn. @handler is + * still called in hard interrupt context and has to check + * whether the interrupt originates from the device. If yes it + * needs to disable the interrupt on the device and return + * IRQ_WAKE_THREAD which will wake up the handler thread and run + * @thread_fn. This split handler design is necessary to support + * shared interrupts. + * + * Dev_id must be globally unique. Normally the address of the + * device data structure is used as the cookie. Since the handler + * receives this value it makes sense to use it. + * + * If your interrupt is shared you must pass a non NULL dev_id + * as this is required when freeing the interrupt. + * + * Flags: + * + * IRQF_SHARED Interrupt is shared + * IRQF_TRIGGER_* Specify active edge(s) or level + * + */ +int request_threaded_irq(unsigned int irq, irq_handler_t handler, + irq_handler_t thread_fn, unsigned long irqflags, + const char *devname, void *dev_id) +{ + struct irqaction *action; + struct irq_desc *desc; + int retval; + + /* + * Sanity-check: shared interrupts must pass in a real dev-ID, + * otherwise we'll have trouble later trying to figure out + * which interrupt is which (messes up the interrupt freeing + * logic etc). + * + * Also IRQF_COND_SUSPEND only makes sense for shared interrupts and + * it cannot be set along with IRQF_NO_SUSPEND. + */ + if (((irqflags & IRQF_SHARED) && !dev_id) || + (!(irqflags & IRQF_SHARED) && (irqflags & IRQF_COND_SUSPEND)) || + ((irqflags & IRQF_NO_SUSPEND) && (irqflags & IRQF_COND_SUSPEND))) + return -EINVAL; + + desc = irq_to_desc(irq); + if (!desc) + return -EINVAL; + + if (!irq_settings_can_request(desc) || + WARN_ON(irq_settings_is_per_cpu_devid(desc))) + return -EINVAL; + + if (!handler) { + if (!thread_fn) + return -EINVAL; + handler = irq_default_primary_handler; + } + + action = kzalloc(sizeof(struct irqaction), GFP_KERNEL); + if (!action) + return -ENOMEM; + + action->handler = handler; + action->thread_fn = thread_fn; + action->flags = irqflags; + action->name = devname; + action->dev_id = dev_id; + + chip_bus_lock(desc); + retval = __setup_irq(irq, desc, action); + chip_bus_sync_unlock(desc); + + if (retval) + kfree(action); + +#ifdef CONFIG_DEBUG_SHIRQ_FIXME + if (!retval && (irqflags & IRQF_SHARED)) { + /* + * It's a shared IRQ -- the driver ought to be prepared for it + * to happen immediately, so let's make sure.... + * We disable the irq to make sure that a 'real' IRQ doesn't + * run in parallel with our fake. + */ + unsigned long flags; + + disable_irq(irq); + local_irq_save(flags); + + handler(irq, dev_id); + + local_irq_restore(flags); + enable_irq(irq); + } +#endif + return retval; +} +EXPORT_SYMBOL(request_threaded_irq); + +/** + * request_any_context_irq - allocate an interrupt line + * @irq: Interrupt line to allocate + * @handler: Function to be called when the IRQ occurs. + * Threaded handler for threaded interrupts. + * @flags: Interrupt type flags + * @name: An ascii name for the claiming device + * @dev_id: A cookie passed back to the handler function + * + * This call allocates interrupt resources and enables the + * interrupt line and IRQ handling. It selects either a + * hardirq or threaded handling method depending on the + * context. + * + * On failure, it returns a negative value. On success, + * it returns either IRQC_IS_HARDIRQ or IRQC_IS_NESTED. + */ +int request_any_context_irq(unsigned int irq, irq_handler_t handler, + unsigned long flags, const char *name, void *dev_id) +{ + struct irq_desc *desc = irq_to_desc(irq); + int ret; + + if (!desc) + return -EINVAL; + + if (irq_settings_is_nested_thread(desc)) { + ret = request_threaded_irq(irq, NULL, handler, + flags, name, dev_id); + return !ret ? IRQC_IS_NESTED : ret; + } + + ret = request_irq(irq, handler, flags, name, dev_id); + return !ret ? IRQC_IS_HARDIRQ : ret; +} +EXPORT_SYMBOL_GPL(request_any_context_irq); + +void enable_percpu_irq(unsigned int irq, unsigned int type) +{ + unsigned int cpu = smp_processor_id(); + unsigned long flags; + struct irq_desc *desc = irq_get_desc_lock(irq, &flags, IRQ_GET_DESC_CHECK_PERCPU); + + if (!desc) + return; + + type &= IRQ_TYPE_SENSE_MASK; + if (type != IRQ_TYPE_NONE) { + int ret; + + ret = __irq_set_trigger(desc, irq, type); + + if (ret) { + WARN(1, "failed to set type for IRQ%d\n", irq); + goto out; + } + } + + irq_percpu_enable(desc, cpu); +out: + irq_put_desc_unlock(desc, flags); +} +EXPORT_SYMBOL_GPL(enable_percpu_irq); + +void disable_percpu_irq(unsigned int irq) +{ + unsigned int cpu = smp_processor_id(); + unsigned long flags; + struct irq_desc *desc = irq_get_desc_lock(irq, &flags, IRQ_GET_DESC_CHECK_PERCPU); + + if (!desc) + return; + + irq_percpu_disable(desc, cpu); + irq_put_desc_unlock(desc, flags); +} +EXPORT_SYMBOL_GPL(disable_percpu_irq); + +/* + * Internal function to unregister a percpu irqaction. + */ +static struct irqaction *__free_percpu_irq(unsigned int irq, void __percpu *dev_id) +{ + struct irq_desc *desc = irq_to_desc(irq); + struct irqaction *action; + unsigned long flags; + + WARN(in_interrupt(), "Trying to free IRQ %d from IRQ context!\n", irq); + + if (!desc) + return NULL; + + raw_spin_lock_irqsave(&desc->lock, flags); + + action = desc->action; + if (!action || action->percpu_dev_id != dev_id) { + WARN(1, "Trying to free already-free IRQ %d\n", irq); + goto bad; + } + + if (!cpumask_empty(desc->percpu_enabled)) { + WARN(1, "percpu IRQ %d still enabled on CPU%d!\n", + irq, cpumask_first(desc->percpu_enabled)); + goto bad; + } + + /* Found it - now remove it from the list of entries: */ + desc->action = NULL; + + raw_spin_unlock_irqrestore(&desc->lock, flags); + + unregister_handler_proc(irq, action); + + module_put(desc->owner); + return action; + +bad: + raw_spin_unlock_irqrestore(&desc->lock, flags); + return NULL; +} + +/** + * remove_percpu_irq - free a per-cpu interrupt + * @irq: Interrupt line to free + * @act: irqaction for the interrupt + * + * Used to remove interrupts statically setup by the early boot process. + */ +void remove_percpu_irq(unsigned int irq, struct irqaction *act) +{ + struct irq_desc *desc = irq_to_desc(irq); + + if (desc && irq_settings_is_per_cpu_devid(desc)) + __free_percpu_irq(irq, act->percpu_dev_id); +} + +/** + * free_percpu_irq - free an interrupt allocated with request_percpu_irq + * @irq: Interrupt line to free + * @dev_id: Device identity to free + * + * Remove a percpu interrupt handler. The handler is removed, but + * the interrupt line is not disabled. This must be done on each + * CPU before calling this function. The function does not return + * until any executing interrupts for this IRQ have completed. + * + * This function must not be called from interrupt context. + */ +void free_percpu_irq(unsigned int irq, void __percpu *dev_id) +{ + struct irq_desc *desc = irq_to_desc(irq); + + if (!desc || !irq_settings_is_per_cpu_devid(desc)) + return; + + chip_bus_lock(desc); + kfree(__free_percpu_irq(irq, dev_id)); + chip_bus_sync_unlock(desc); +} + +/** + * setup_percpu_irq - setup a per-cpu interrupt + * @irq: Interrupt line to setup + * @act: irqaction for the interrupt + * + * Used to statically setup per-cpu interrupts in the early boot process. + */ +int setup_percpu_irq(unsigned int irq, struct irqaction *act) +{ + struct irq_desc *desc = irq_to_desc(irq); + int retval; + + if (!desc || !irq_settings_is_per_cpu_devid(desc)) + return -EINVAL; + chip_bus_lock(desc); + retval = __setup_irq(irq, desc, act); + chip_bus_sync_unlock(desc); + + return retval; +} + +/** + * request_percpu_irq - allocate a percpu interrupt line + * @irq: Interrupt line to allocate + * @handler: Function to be called when the IRQ occurs. + * @devname: An ascii name for the claiming device + * @dev_id: A percpu cookie passed back to the handler function + * + * This call allocates interrupt resources, but doesn't + * automatically enable the interrupt. It has to be done on each + * CPU using enable_percpu_irq(). + * + * Dev_id must be globally unique. It is a per-cpu variable, and + * the handler gets called with the interrupted CPU's instance of + * that variable. + */ +int request_percpu_irq(unsigned int irq, irq_handler_t handler, + const char *devname, void __percpu *dev_id) +{ + struct irqaction *action; + struct irq_desc *desc; + int retval; + + if (!dev_id) + return -EINVAL; + + desc = irq_to_desc(irq); + if (!desc || !irq_settings_can_request(desc) || + !irq_settings_is_per_cpu_devid(desc)) + return -EINVAL; + + action = kzalloc(sizeof(struct irqaction), GFP_KERNEL); + if (!action) + return -ENOMEM; + + action->handler = handler; + action->flags = IRQF_PERCPU | IRQF_NO_SUSPEND; + action->name = devname; + action->percpu_dev_id = dev_id; + + chip_bus_lock(desc); + retval = __setup_irq(irq, desc, action); + chip_bus_sync_unlock(desc); + + if (retval) + kfree(action); + + return retval; +} + +/** + * irq_get_irqchip_state - returns the irqchip state of a interrupt. + * @irq: Interrupt line that is forwarded to a VM + * @which: One of IRQCHIP_STATE_* the caller wants to know about + * @state: a pointer to a boolean where the state is to be storeed + * + * This call snapshots the internal irqchip state of an + * interrupt, returning into @state the bit corresponding to + * stage @which + * + * This function should be called with preemption disabled if the + * interrupt controller has per-cpu registers. + */ +int irq_get_irqchip_state(unsigned int irq, enum irqchip_irq_state which, + bool *state) +{ + struct irq_desc *desc; + struct irq_data *data; + struct irq_chip *chip; + unsigned long flags; + int err = -EINVAL; + + desc = irq_get_desc_buslock(irq, &flags, 0); + if (!desc) + return err; + + data = irq_desc_get_irq_data(desc); + + do { + chip = irq_data_get_irq_chip(data); + if (chip->irq_get_irqchip_state) + break; +#ifdef CONFIG_IRQ_DOMAIN_HIERARCHY + data = data->parent_data; +#else + data = NULL; +#endif + } while (data); + + if (data) + err = chip->irq_get_irqchip_state(data, which, state); + + irq_put_desc_busunlock(desc, flags); + return err; +} + +/** + * irq_set_irqchip_state - set the state of a forwarded interrupt. + * @irq: Interrupt line that is forwarded to a VM + * @which: State to be restored (one of IRQCHIP_STATE_*) + * @val: Value corresponding to @which + * + * This call sets the internal irqchip state of an interrupt, + * depending on the value of @which. + * + * This function should be called with preemption disabled if the + * interrupt controller has per-cpu registers. + */ +int irq_set_irqchip_state(unsigned int irq, enum irqchip_irq_state which, + bool val) +{ + struct irq_desc *desc; + struct irq_data *data; + struct irq_chip *chip; + unsigned long flags; + int err = -EINVAL; + + desc = irq_get_desc_buslock(irq, &flags, 0); + if (!desc) + return err; + + data = irq_desc_get_irq_data(desc); + + do { + chip = irq_data_get_irq_chip(data); + if (chip->irq_set_irqchip_state) + break; +#ifdef CONFIG_IRQ_DOMAIN_HIERARCHY + data = data->parent_data; +#else + data = NULL; +#endif + } while (data); + + if (data) + err = chip->irq_set_irqchip_state(data, which, val); + + irq_put_desc_busunlock(desc, flags); + return err; +} diff --git a/kernel/kernel/irq/migration.c b/kernel/kernel/irq/migration.c new file mode 100644 index 000000000..ca3f4aaff --- /dev/null +++ b/kernel/kernel/irq/migration.c @@ -0,0 +1,72 @@ + +#include +#include + +#include "internals.h" + +void irq_move_masked_irq(struct irq_data *idata) +{ + struct irq_desc *desc = irq_data_to_desc(idata); + struct irq_chip *chip = idata->chip; + + if (likely(!irqd_is_setaffinity_pending(&desc->irq_data))) + return; + + /* + * Paranoia: cpu-local interrupts shouldn't be calling in here anyway. + */ + if (!irqd_can_balance(&desc->irq_data)) { + WARN_ON(1); + return; + } + + irqd_clr_move_pending(&desc->irq_data); + + if (unlikely(cpumask_empty(desc->pending_mask))) + return; + + if (!chip->irq_set_affinity) + return; + + assert_raw_spin_locked(&desc->lock); + + /* + * If there was a valid mask to work with, please + * do the disable, re-program, enable sequence. + * This is *not* particularly important for level triggered + * but in a edge trigger case, we might be setting rte + * when an active trigger is coming in. This could + * cause some ioapics to mal-function. + * Being paranoid i guess! + * + * For correct operation this depends on the caller + * masking the irqs. + */ + if (cpumask_any_and(desc->pending_mask, cpu_online_mask) < nr_cpu_ids) + irq_do_set_affinity(&desc->irq_data, desc->pending_mask, false); + + cpumask_clear(desc->pending_mask); +} + +void irq_move_irq(struct irq_data *idata) +{ + bool masked; + + if (likely(!irqd_is_setaffinity_pending(idata))) + return; + + if (unlikely(irqd_irq_disabled(idata))) + return; + + /* + * Be careful vs. already masked interrupts. If this is a + * threaded interrupt with ONESHOT set, we can end up with an + * interrupt storm. + */ + masked = irqd_irq_masked(idata); + if (!masked) + idata->chip->irq_mask(idata); + irq_move_masked_irq(idata); + if (!masked) + idata->chip->irq_unmask(idata); +} diff --git a/kernel/kernel/irq/msi.c b/kernel/kernel/irq/msi.c new file mode 100644 index 000000000..474de5cb3 --- /dev/null +++ b/kernel/kernel/irq/msi.c @@ -0,0 +1,337 @@ +/* + * linux/kernel/irq/msi.c + * + * Copyright (C) 2014 Intel Corp. + * Author: Jiang Liu + * + * This file is licensed under GPLv2. + * + * This file contains common code to support Message Signalled Interrupt for + * PCI compatible and non PCI compatible devices. + */ +#include +#include +#include +#include +#include + +/* Temparory solution for building, will be removed later */ +#include + +void __get_cached_msi_msg(struct msi_desc *entry, struct msi_msg *msg) +{ + *msg = entry->msg; +} + +void get_cached_msi_msg(unsigned int irq, struct msi_msg *msg) +{ + struct msi_desc *entry = irq_get_msi_desc(irq); + + __get_cached_msi_msg(entry, msg); +} +EXPORT_SYMBOL_GPL(get_cached_msi_msg); + +#ifdef CONFIG_GENERIC_MSI_IRQ_DOMAIN +static inline void irq_chip_write_msi_msg(struct irq_data *data, + struct msi_msg *msg) +{ + data->chip->irq_write_msi_msg(data, msg); +} + +/** + * msi_domain_set_affinity - Generic affinity setter function for MSI domains + * @irq_data: The irq data associated to the interrupt + * @mask: The affinity mask to set + * @force: Flag to enforce setting (disable online checks) + * + * Intended to be used by MSI interrupt controllers which are + * implemented with hierarchical domains. + */ +int msi_domain_set_affinity(struct irq_data *irq_data, + const struct cpumask *mask, bool force) +{ + struct irq_data *parent = irq_data->parent_data; + struct msi_msg msg; + int ret; + + ret = parent->chip->irq_set_affinity(parent, mask, force); + if (ret >= 0 && ret != IRQ_SET_MASK_OK_DONE) { + BUG_ON(irq_chip_compose_msi_msg(irq_data, &msg)); + irq_chip_write_msi_msg(irq_data, &msg); + } + + return ret; +} + +static void msi_domain_activate(struct irq_domain *domain, + struct irq_data *irq_data) +{ + struct msi_msg msg; + + BUG_ON(irq_chip_compose_msi_msg(irq_data, &msg)); + irq_chip_write_msi_msg(irq_data, &msg); +} + +static void msi_domain_deactivate(struct irq_domain *domain, + struct irq_data *irq_data) +{ + struct msi_msg msg; + + memset(&msg, 0, sizeof(msg)); + irq_chip_write_msi_msg(irq_data, &msg); +} + +static int msi_domain_alloc(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs, void *arg) +{ + struct msi_domain_info *info = domain->host_data; + struct msi_domain_ops *ops = info->ops; + irq_hw_number_t hwirq = ops->get_hwirq(info, arg); + int i, ret; + + if (irq_find_mapping(domain, hwirq) > 0) + return -EEXIST; + + ret = irq_domain_alloc_irqs_parent(domain, virq, nr_irqs, arg); + if (ret < 0) + return ret; + + for (i = 0; i < nr_irqs; i++) { + ret = ops->msi_init(domain, info, virq + i, hwirq + i, arg); + if (ret < 0) { + if (ops->msi_free) { + for (i--; i > 0; i--) + ops->msi_free(domain, info, virq + i); + } + irq_domain_free_irqs_top(domain, virq, nr_irqs); + return ret; + } + } + + return 0; +} + +static void msi_domain_free(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs) +{ + struct msi_domain_info *info = domain->host_data; + int i; + + if (info->ops->msi_free) { + for (i = 0; i < nr_irqs; i++) + info->ops->msi_free(domain, info, virq + i); + } + irq_domain_free_irqs_top(domain, virq, nr_irqs); +} + +static struct irq_domain_ops msi_domain_ops = { + .alloc = msi_domain_alloc, + .free = msi_domain_free, + .activate = msi_domain_activate, + .deactivate = msi_domain_deactivate, +}; + +#ifdef GENERIC_MSI_DOMAIN_OPS +static irq_hw_number_t msi_domain_ops_get_hwirq(struct msi_domain_info *info, + msi_alloc_info_t *arg) +{ + return arg->hwirq; +} + +static int msi_domain_ops_prepare(struct irq_domain *domain, struct device *dev, + int nvec, msi_alloc_info_t *arg) +{ + memset(arg, 0, sizeof(*arg)); + return 0; +} + +static void msi_domain_ops_set_desc(msi_alloc_info_t *arg, + struct msi_desc *desc) +{ + arg->desc = desc; +} +#else +#define msi_domain_ops_get_hwirq NULL +#define msi_domain_ops_prepare NULL +#define msi_domain_ops_set_desc NULL +#endif /* !GENERIC_MSI_DOMAIN_OPS */ + +static int msi_domain_ops_init(struct irq_domain *domain, + struct msi_domain_info *info, + unsigned int virq, irq_hw_number_t hwirq, + msi_alloc_info_t *arg) +{ + irq_domain_set_hwirq_and_chip(domain, virq, hwirq, info->chip, + info->chip_data); + if (info->handler && info->handler_name) { + __irq_set_handler(virq, info->handler, 0, info->handler_name); + if (info->handler_data) + irq_set_handler_data(virq, info->handler_data); + } + return 0; +} + +static int msi_domain_ops_check(struct irq_domain *domain, + struct msi_domain_info *info, + struct device *dev) +{ + return 0; +} + +static struct msi_domain_ops msi_domain_ops_default = { + .get_hwirq = msi_domain_ops_get_hwirq, + .msi_init = msi_domain_ops_init, + .msi_check = msi_domain_ops_check, + .msi_prepare = msi_domain_ops_prepare, + .set_desc = msi_domain_ops_set_desc, +}; + +static void msi_domain_update_dom_ops(struct msi_domain_info *info) +{ + struct msi_domain_ops *ops = info->ops; + + if (ops == NULL) { + info->ops = &msi_domain_ops_default; + return; + } + + if (ops->get_hwirq == NULL) + ops->get_hwirq = msi_domain_ops_default.get_hwirq; + if (ops->msi_init == NULL) + ops->msi_init = msi_domain_ops_default.msi_init; + if (ops->msi_check == NULL) + ops->msi_check = msi_domain_ops_default.msi_check; + if (ops->msi_prepare == NULL) + ops->msi_prepare = msi_domain_ops_default.msi_prepare; + if (ops->set_desc == NULL) + ops->set_desc = msi_domain_ops_default.set_desc; +} + +static void msi_domain_update_chip_ops(struct msi_domain_info *info) +{ + struct irq_chip *chip = info->chip; + + BUG_ON(!chip); + if (!chip->irq_mask) + chip->irq_mask = pci_msi_mask_irq; + if (!chip->irq_unmask) + chip->irq_unmask = pci_msi_unmask_irq; + if (!chip->irq_set_affinity) + chip->irq_set_affinity = msi_domain_set_affinity; +} + +/** + * msi_create_irq_domain - Create a MSI interrupt domain + * @of_node: Optional device-tree node of the interrupt controller + * @info: MSI domain info + * @parent: Parent irq domain + */ +struct irq_domain *msi_create_irq_domain(struct device_node *node, + struct msi_domain_info *info, + struct irq_domain *parent) +{ + if (info->flags & MSI_FLAG_USE_DEF_DOM_OPS) + msi_domain_update_dom_ops(info); + if (info->flags & MSI_FLAG_USE_DEF_CHIP_OPS) + msi_domain_update_chip_ops(info); + + return irq_domain_add_hierarchy(parent, 0, 0, node, &msi_domain_ops, + info); +} + +/** + * msi_domain_alloc_irqs - Allocate interrupts from a MSI interrupt domain + * @domain: The domain to allocate from + * @dev: Pointer to device struct of the device for which the interrupts + * are allocated + * @nvec: The number of interrupts to allocate + * + * Returns 0 on success or an error code. + */ +int msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev, + int nvec) +{ + struct msi_domain_info *info = domain->host_data; + struct msi_domain_ops *ops = info->ops; + msi_alloc_info_t arg; + struct msi_desc *desc; + int i, ret, virq = -1; + + ret = ops->msi_check(domain, info, dev); + if (ret == 0) + ret = ops->msi_prepare(domain, dev, nvec, &arg); + if (ret) + return ret; + + for_each_msi_entry(desc, dev) { + ops->set_desc(&arg, desc); + if (info->flags & MSI_FLAG_IDENTITY_MAP) + virq = (int)ops->get_hwirq(info, &arg); + else + virq = -1; + + virq = __irq_domain_alloc_irqs(domain, virq, desc->nvec_used, + dev_to_node(dev), &arg, false); + if (virq < 0) { + ret = -ENOSPC; + if (ops->handle_error) + ret = ops->handle_error(domain, desc, ret); + if (ops->msi_finish) + ops->msi_finish(&arg, ret); + return ret; + } + + for (i = 0; i < desc->nvec_used; i++) + irq_set_msi_desc_off(virq, i, desc); + } + + if (ops->msi_finish) + ops->msi_finish(&arg, 0); + + for_each_msi_entry(desc, dev) { + if (desc->nvec_used == 1) + dev_dbg(dev, "irq %d for MSI\n", virq); + else + dev_dbg(dev, "irq [%d-%d] for MSI\n", + virq, virq + desc->nvec_used - 1); + } + + return 0; +} + +/** + * msi_domain_free_irqs - Free interrupts from a MSI interrupt @domain associated tp @dev + * @domain: The domain to managing the interrupts + * @dev: Pointer to device struct of the device for which the interrupts + * are free + */ +void msi_domain_free_irqs(struct irq_domain *domain, struct device *dev) +{ + struct msi_desc *desc; + + for_each_msi_entry(desc, dev) { + /* + * We might have failed to allocate an MSI early + * enough that there is no IRQ associated to this + * entry. If that's the case, don't do anything. + */ + if (desc->irq) { + irq_domain_free_irqs(desc->irq, desc->nvec_used); + desc->irq = 0; + } + } +} + +/** + * msi_get_domain_info - Get the MSI interrupt domain info for @domain + * @domain: The interrupt domain to retrieve data from + * + * Returns the pointer to the msi_domain_info stored in + * @domain->host_data. + */ +struct msi_domain_info *msi_get_domain_info(struct irq_domain *domain) +{ + return (struct msi_domain_info *)domain->host_data; +} + +#endif /* CONFIG_GENERIC_MSI_IRQ_DOMAIN */ diff --git a/kernel/kernel/irq/pm.c b/kernel/kernel/irq/pm.c new file mode 100644 index 000000000..5204a6d1b --- /dev/null +++ b/kernel/kernel/irq/pm.c @@ -0,0 +1,206 @@ +/* + * linux/kernel/irq/pm.c + * + * Copyright (C) 2009 Rafael J. Wysocki , Novell Inc. + * + * This file contains power management functions related to interrupts. + */ + +#include +#include +#include +#include +#include + +#include "internals.h" + +bool irq_pm_check_wakeup(struct irq_desc *desc) +{ + if (irqd_is_wakeup_armed(&desc->irq_data)) { + irqd_clear(&desc->irq_data, IRQD_WAKEUP_ARMED); + desc->istate |= IRQS_SUSPENDED | IRQS_PENDING; + desc->depth++; + irq_disable(desc); + pm_system_wakeup(); + return true; + } + return false; +} + +/* + * Called from __setup_irq() with desc->lock held after @action has + * been installed in the action chain. + */ +void irq_pm_install_action(struct irq_desc *desc, struct irqaction *action) +{ + desc->nr_actions++; + + if (action->flags & IRQF_FORCE_RESUME) + desc->force_resume_depth++; + + WARN_ON_ONCE(desc->force_resume_depth && + desc->force_resume_depth != desc->nr_actions); + + if (action->flags & IRQF_NO_SUSPEND) + desc->no_suspend_depth++; + else if (action->flags & IRQF_COND_SUSPEND) + desc->cond_suspend_depth++; + + WARN_ON_ONCE(desc->no_suspend_depth && + (desc->no_suspend_depth + + desc->cond_suspend_depth) != desc->nr_actions); +} + +/* + * Called from __free_irq() with desc->lock held after @action has + * been removed from the action chain. + */ +void irq_pm_remove_action(struct irq_desc *desc, struct irqaction *action) +{ + desc->nr_actions--; + + if (action->flags & IRQF_FORCE_RESUME) + desc->force_resume_depth--; + + if (action->flags & IRQF_NO_SUSPEND) + desc->no_suspend_depth--; + else if (action->flags & IRQF_COND_SUSPEND) + desc->cond_suspend_depth--; +} + +static bool suspend_device_irq(struct irq_desc *desc, int irq) +{ + if (!desc->action || desc->no_suspend_depth) + return false; + + if (irqd_is_wakeup_set(&desc->irq_data)) { + irqd_set(&desc->irq_data, IRQD_WAKEUP_ARMED); + /* + * We return true here to force the caller to issue + * synchronize_irq(). We need to make sure that the + * IRQD_WAKEUP_ARMED is visible before we return from + * suspend_device_irqs(). + */ + return true; + } + + desc->istate |= IRQS_SUSPENDED; + __disable_irq(desc, irq); + + /* + * Hardware which has no wakeup source configuration facility + * requires that the non wakeup interrupts are masked at the + * chip level. The chip implementation indicates that with + * IRQCHIP_MASK_ON_SUSPEND. + */ + if (irq_desc_get_chip(desc)->flags & IRQCHIP_MASK_ON_SUSPEND) + mask_irq(desc); + return true; +} + +/** + * suspend_device_irqs - disable all currently enabled interrupt lines + * + * During system-wide suspend or hibernation device drivers need to be + * prevented from receiving interrupts and this function is provided + * for this purpose. + * + * So we disable all interrupts and mark them IRQS_SUSPENDED except + * for those which are unused, those which are marked as not + * suspendable via an interrupt request with the flag IRQF_NO_SUSPEND + * set and those which are marked as active wakeup sources. + * + * The active wakeup sources are handled by the flow handler entry + * code which checks for the IRQD_WAKEUP_ARMED flag, suspends the + * interrupt and notifies the pm core about the wakeup. + */ +void suspend_device_irqs(void) +{ + struct irq_desc *desc; + int irq; + + for_each_irq_desc(irq, desc) { + unsigned long flags; + bool sync; + + raw_spin_lock_irqsave(&desc->lock, flags); + sync = suspend_device_irq(desc, irq); + raw_spin_unlock_irqrestore(&desc->lock, flags); + + if (sync) + synchronize_irq(irq); + } +} +EXPORT_SYMBOL_GPL(suspend_device_irqs); + +static void resume_irq(struct irq_desc *desc, int irq) +{ + irqd_clear(&desc->irq_data, IRQD_WAKEUP_ARMED); + + if (desc->istate & IRQS_SUSPENDED) + goto resume; + + /* Force resume the interrupt? */ + if (!desc->force_resume_depth) + return; + + /* Pretend that it got disabled ! */ + desc->depth++; +resume: + desc->istate &= ~IRQS_SUSPENDED; + __enable_irq(desc, irq); +} + +static void resume_irqs(bool want_early) +{ + struct irq_desc *desc; + int irq; + + for_each_irq_desc(irq, desc) { + unsigned long flags; + bool is_early = desc->action && + desc->action->flags & IRQF_EARLY_RESUME; + + if (!is_early && want_early) + continue; + + raw_spin_lock_irqsave(&desc->lock, flags); + resume_irq(desc, irq); + raw_spin_unlock_irqrestore(&desc->lock, flags); + } +} + +/** + * irq_pm_syscore_ops - enable interrupt lines early + * + * Enable all interrupt lines with %IRQF_EARLY_RESUME set. + */ +static void irq_pm_syscore_resume(void) +{ + resume_irqs(true); +} + +static struct syscore_ops irq_pm_syscore_ops = { + .resume = irq_pm_syscore_resume, +}; + +static int __init irq_pm_init_ops(void) +{ + register_syscore_ops(&irq_pm_syscore_ops); + return 0; +} + +device_initcall(irq_pm_init_ops); + +/** + * resume_device_irqs - enable interrupt lines disabled by suspend_device_irqs() + * + * Enable all non-%IRQF_EARLY_RESUME interrupt lines previously + * disabled by suspend_device_irqs() that have the IRQS_SUSPENDED flag + * set as well as those with %IRQF_FORCE_RESUME. + */ +void resume_device_irqs(void) +{ + resume_irqs(false); +} +EXPORT_SYMBOL_GPL(resume_device_irqs); diff --git a/kernel/kernel/irq/proc.c b/kernel/kernel/irq/proc.c new file mode 100644 index 000000000..df2f4642d --- /dev/null +++ b/kernel/kernel/irq/proc.c @@ -0,0 +1,501 @@ +/* + * linux/kernel/irq/proc.c + * + * Copyright (C) 1992, 1998-2004 Linus Torvalds, Ingo Molnar + * + * This file contains the /proc/irq/ handling code. + */ + +#include +#include +#include +#include +#include +#include + +#include "internals.h" + +/* + * Access rules: + * + * procfs protects read/write of /proc/irq/N/ files against a + * concurrent free of the interrupt descriptor. remove_proc_entry() + * immediately prevents new read/writes to happen and waits for + * already running read/write functions to complete. + * + * We remove the proc entries first and then delete the interrupt + * descriptor from the radix tree and free it. So it is guaranteed + * that irq_to_desc(N) is valid as long as the read/writes are + * permitted by procfs. + * + * The read from /proc/interrupts is a different problem because there + * is no protection. So the lookup and the access to irqdesc + * information must be protected by sparse_irq_lock. + */ +static struct proc_dir_entry *root_irq_dir; + +#ifdef CONFIG_SMP + +static int show_irq_affinity(int type, struct seq_file *m, void *v) +{ + struct irq_desc *desc = irq_to_desc((long)m->private); + const struct cpumask *mask = desc->irq_data.affinity; + +#ifdef CONFIG_GENERIC_PENDING_IRQ + if (irqd_is_setaffinity_pending(&desc->irq_data)) + mask = desc->pending_mask; +#endif + if (type) + seq_printf(m, "%*pbl\n", cpumask_pr_args(mask)); + else + seq_printf(m, "%*pb\n", cpumask_pr_args(mask)); + return 0; +} + +static int irq_affinity_hint_proc_show(struct seq_file *m, void *v) +{ + struct irq_desc *desc = irq_to_desc((long)m->private); + unsigned long flags; + cpumask_var_t mask; + + if (!zalloc_cpumask_var(&mask, GFP_KERNEL)) + return -ENOMEM; + + raw_spin_lock_irqsave(&desc->lock, flags); + if (desc->affinity_hint) + cpumask_copy(mask, desc->affinity_hint); + raw_spin_unlock_irqrestore(&desc->lock, flags); + + seq_printf(m, "%*pb\n", cpumask_pr_args(mask)); + free_cpumask_var(mask); + + return 0; +} + +#ifndef is_affinity_mask_valid +#define is_affinity_mask_valid(val) 1 +#endif + +int no_irq_affinity; +static int irq_affinity_proc_show(struct seq_file *m, void *v) +{ + return show_irq_affinity(0, m, v); +} + +static int irq_affinity_list_proc_show(struct seq_file *m, void *v) +{ + return show_irq_affinity(1, m, v); +} + + +static ssize_t write_irq_affinity(int type, struct file *file, + const char __user *buffer, size_t count, loff_t *pos) +{ + unsigned int irq = (int)(long)PDE_DATA(file_inode(file)); + cpumask_var_t new_value; + int err; + + if (!irq_can_set_affinity(irq) || no_irq_affinity) + return -EIO; + + if (!alloc_cpumask_var(&new_value, GFP_KERNEL)) + return -ENOMEM; + + if (type) + err = cpumask_parselist_user(buffer, count, new_value); + else + err = cpumask_parse_user(buffer, count, new_value); + if (err) + goto free_cpumask; + + if (!is_affinity_mask_valid(new_value)) { + err = -EINVAL; + goto free_cpumask; + } + + /* + * Do not allow disabling IRQs completely - it's a too easy + * way to make the system unusable accidentally :-) At least + * one online CPU still has to be targeted. + */ + if (!cpumask_intersects(new_value, cpu_online_mask)) { + /* Special case for empty set - allow the architecture + code to set default SMP affinity. */ + err = irq_select_affinity_usr(irq, new_value) ? -EINVAL : count; + } else { + irq_set_affinity(irq, new_value); + err = count; + } + +free_cpumask: + free_cpumask_var(new_value); + return err; +} + +static ssize_t irq_affinity_proc_write(struct file *file, + const char __user *buffer, size_t count, loff_t *pos) +{ + return write_irq_affinity(0, file, buffer, count, pos); +} + +static ssize_t irq_affinity_list_proc_write(struct file *file, + const char __user *buffer, size_t count, loff_t *pos) +{ + return write_irq_affinity(1, file, buffer, count, pos); +} + +static int irq_affinity_proc_open(struct inode *inode, struct file *file) +{ + return single_open(file, irq_affinity_proc_show, PDE_DATA(inode)); +} + +static int irq_affinity_list_proc_open(struct inode *inode, struct file *file) +{ + return single_open(file, irq_affinity_list_proc_show, PDE_DATA(inode)); +} + +static int irq_affinity_hint_proc_open(struct inode *inode, struct file *file) +{ + return single_open(file, irq_affinity_hint_proc_show, PDE_DATA(inode)); +} + +static const struct file_operations irq_affinity_proc_fops = { + .open = irq_affinity_proc_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, + .write = irq_affinity_proc_write, +}; + +static const struct file_operations irq_affinity_hint_proc_fops = { + .open = irq_affinity_hint_proc_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static const struct file_operations irq_affinity_list_proc_fops = { + .open = irq_affinity_list_proc_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, + .write = irq_affinity_list_proc_write, +}; + +static int default_affinity_show(struct seq_file *m, void *v) +{ + seq_printf(m, "%*pb\n", cpumask_pr_args(irq_default_affinity)); + return 0; +} + +static ssize_t default_affinity_write(struct file *file, + const char __user *buffer, size_t count, loff_t *ppos) +{ + cpumask_var_t new_value; + int err; + + if (!alloc_cpumask_var(&new_value, GFP_KERNEL)) + return -ENOMEM; + + err = cpumask_parse_user(buffer, count, new_value); + if (err) + goto out; + + if (!is_affinity_mask_valid(new_value)) { + err = -EINVAL; + goto out; + } + + /* + * Do not allow disabling IRQs completely - it's a too easy + * way to make the system unusable accidentally :-) At least + * one online CPU still has to be targeted. + */ + if (!cpumask_intersects(new_value, cpu_online_mask)) { + err = -EINVAL; + goto out; + } + + cpumask_copy(irq_default_affinity, new_value); + err = count; + +out: + free_cpumask_var(new_value); + return err; +} + +static int default_affinity_open(struct inode *inode, struct file *file) +{ + return single_open(file, default_affinity_show, PDE_DATA(inode)); +} + +static const struct file_operations default_affinity_proc_fops = { + .open = default_affinity_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, + .write = default_affinity_write, +}; + +static int irq_node_proc_show(struct seq_file *m, void *v) +{ + struct irq_desc *desc = irq_to_desc((long) m->private); + + seq_printf(m, "%d\n", desc->irq_data.node); + return 0; +} + +static int irq_node_proc_open(struct inode *inode, struct file *file) +{ + return single_open(file, irq_node_proc_show, PDE_DATA(inode)); +} + +static const struct file_operations irq_node_proc_fops = { + .open = irq_node_proc_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; +#endif + +static int irq_spurious_proc_show(struct seq_file *m, void *v) +{ + struct irq_desc *desc = irq_to_desc((long) m->private); + + seq_printf(m, "count %u\n" "unhandled %u\n" "last_unhandled %u ms\n", + desc->irq_count, desc->irqs_unhandled, + jiffies_to_msecs(desc->last_unhandled)); + return 0; +} + +static int irq_spurious_proc_open(struct inode *inode, struct file *file) +{ + return single_open(file, irq_spurious_proc_show, PDE_DATA(inode)); +} + +static const struct file_operations irq_spurious_proc_fops = { + .open = irq_spurious_proc_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +#define MAX_NAMELEN 128 + +static int name_unique(unsigned int irq, struct irqaction *new_action) +{ + struct irq_desc *desc = irq_to_desc(irq); + struct irqaction *action; + unsigned long flags; + int ret = 1; + + raw_spin_lock_irqsave(&desc->lock, flags); + for (action = desc->action ; action; action = action->next) { + if ((action != new_action) && action->name && + !strcmp(new_action->name, action->name)) { + ret = 0; + break; + } + } + raw_spin_unlock_irqrestore(&desc->lock, flags); + return ret; +} + +void register_handler_proc(unsigned int irq, struct irqaction *action) +{ + char name [MAX_NAMELEN]; + struct irq_desc *desc = irq_to_desc(irq); + + if (!desc->dir || action->dir || !action->name || + !name_unique(irq, action)) + return; + + memset(name, 0, MAX_NAMELEN); + snprintf(name, MAX_NAMELEN, "%s", action->name); + + /* create /proc/irq/1234/handler/ */ + action->dir = proc_mkdir(name, desc->dir); +} + +#undef MAX_NAMELEN + +#define MAX_NAMELEN 10 + +void register_irq_proc(unsigned int irq, struct irq_desc *desc) +{ + char name [MAX_NAMELEN]; + + if (!root_irq_dir || (desc->irq_data.chip == &no_irq_chip) || desc->dir) + return; + + memset(name, 0, MAX_NAMELEN); + sprintf(name, "%d", irq); + + /* create /proc/irq/1234 */ + desc->dir = proc_mkdir(name, root_irq_dir); + if (!desc->dir) + return; + +#ifdef CONFIG_SMP + /* create /proc/irq//smp_affinity */ + proc_create_data("smp_affinity", 0644, desc->dir, + &irq_affinity_proc_fops, (void *)(long)irq); + + /* create /proc/irq//affinity_hint */ + proc_create_data("affinity_hint", 0444, desc->dir, + &irq_affinity_hint_proc_fops, (void *)(long)irq); + + /* create /proc/irq//smp_affinity_list */ + proc_create_data("smp_affinity_list", 0644, desc->dir, + &irq_affinity_list_proc_fops, (void *)(long)irq); + + proc_create_data("node", 0444, desc->dir, + &irq_node_proc_fops, (void *)(long)irq); +#endif + + proc_create_data("spurious", 0444, desc->dir, + &irq_spurious_proc_fops, (void *)(long)irq); +} + +void unregister_irq_proc(unsigned int irq, struct irq_desc *desc) +{ + char name [MAX_NAMELEN]; + + if (!root_irq_dir || !desc->dir) + return; +#ifdef CONFIG_SMP + remove_proc_entry("smp_affinity", desc->dir); + remove_proc_entry("affinity_hint", desc->dir); + remove_proc_entry("smp_affinity_list", desc->dir); + remove_proc_entry("node", desc->dir); +#endif + remove_proc_entry("spurious", desc->dir); + + memset(name, 0, MAX_NAMELEN); + sprintf(name, "%u", irq); + remove_proc_entry(name, root_irq_dir); +} + +#undef MAX_NAMELEN + +void unregister_handler_proc(unsigned int irq, struct irqaction *action) +{ + proc_remove(action->dir); +} + +static void register_default_affinity_proc(void) +{ +#ifdef CONFIG_SMP + proc_create("irq/default_smp_affinity", 0644, NULL, + &default_affinity_proc_fops); +#endif +} + +void init_irq_proc(void) +{ + unsigned int irq; + struct irq_desc *desc; + + /* create /proc/irq */ + root_irq_dir = proc_mkdir("irq", NULL); + if (!root_irq_dir) + return; + + register_default_affinity_proc(); + + /* + * Create entries for all existing IRQs. + */ + for_each_irq_desc(irq, desc) { + if (!desc) + continue; + + register_irq_proc(irq, desc); + } +} + +#ifdef CONFIG_GENERIC_IRQ_SHOW + +int __weak arch_show_interrupts(struct seq_file *p, int prec) +{ + return 0; +} + +#ifndef ACTUAL_NR_IRQS +# define ACTUAL_NR_IRQS nr_irqs +#endif + +int show_interrupts(struct seq_file *p, void *v) +{ + static int prec; + + unsigned long flags, any_count = 0; + int i = *(loff_t *) v, j; + struct irqaction *action; + struct irq_desc *desc; + + if (i > ACTUAL_NR_IRQS) + return 0; + + if (i == ACTUAL_NR_IRQS) + return arch_show_interrupts(p, prec); + + /* print header and calculate the width of the first column */ + if (i == 0) { + for (prec = 3, j = 1000; prec < 10 && j <= nr_irqs; ++prec) + j *= 10; + + seq_printf(p, "%*s", prec + 8, ""); + for_each_online_cpu(j) + seq_printf(p, "CPU%-8d", j); + seq_putc(p, '\n'); + } + + irq_lock_sparse(); + desc = irq_to_desc(i); + if (!desc) + goto outsparse; + + raw_spin_lock_irqsave(&desc->lock, flags); + for_each_online_cpu(j) + any_count |= kstat_irqs_cpu(i, j); + action = desc->action; + if (!action && !any_count) + goto out; + + seq_printf(p, "%*d: ", prec, i); + for_each_online_cpu(j) + seq_printf(p, "%10u ", kstat_irqs_cpu(i, j)); + + if (desc->irq_data.chip) { + if (desc->irq_data.chip->irq_print_chip) + desc->irq_data.chip->irq_print_chip(&desc->irq_data, p); + else if (desc->irq_data.chip->name) + seq_printf(p, " %8s", desc->irq_data.chip->name); + else + seq_printf(p, " %8s", "-"); + } else { + seq_printf(p, " %8s", "None"); + } + if (desc->irq_data.domain) + seq_printf(p, " %*d", prec, (int) desc->irq_data.hwirq); +#ifdef CONFIG_GENERIC_IRQ_SHOW_LEVEL + seq_printf(p, " %-8s", irqd_is_level_type(&desc->irq_data) ? "Level" : "Edge"); +#endif + if (desc->name) + seq_printf(p, "-%-8s", desc->name); + + if (action) { + seq_printf(p, " %s", action->name); + while ((action = action->next) != NULL) + seq_printf(p, ", %s", action->name); + } + + seq_putc(p, '\n'); +out: + raw_spin_unlock_irqrestore(&desc->lock, flags); +outsparse: + irq_unlock_sparse(); + return 0; +} +#endif diff --git a/kernel/kernel/irq/resend.c b/kernel/kernel/irq/resend.c new file mode 100644 index 000000000..9065107f0 --- /dev/null +++ b/kernel/kernel/irq/resend.c @@ -0,0 +1,91 @@ +/* + * linux/kernel/irq/resend.c + * + * Copyright (C) 1992, 1998-2006 Linus Torvalds, Ingo Molnar + * Copyright (C) 2005-2006, Thomas Gleixner + * + * This file contains the IRQ-resend code + * + * If the interrupt is waiting to be processed, we try to re-run it. + * We can't directly run it from here since the caller might be in an + * interrupt-protected region. Not all irq controller chips can + * retrigger interrupts at the hardware level, so in those cases + * we allow the resending of IRQs via a tasklet. + */ + +#include +#include +#include +#include + +#include "internals.h" + +#ifdef CONFIG_HARDIRQS_SW_RESEND + +/* Bitmap to handle software resend of interrupts: */ +static DECLARE_BITMAP(irqs_resend, IRQ_BITMAP_BITS); + +/* + * Run software resends of IRQ's + */ +static void resend_irqs(unsigned long arg) +{ + struct irq_desc *desc; + int irq; + + while (!bitmap_empty(irqs_resend, nr_irqs)) { + irq = find_first_bit(irqs_resend, nr_irqs); + clear_bit(irq, irqs_resend); + desc = irq_to_desc(irq); + local_irq_disable(); + desc->handle_irq(irq, desc); + local_irq_enable(); + } +} + +/* Tasklet to handle resend: */ +static DECLARE_TASKLET(resend_tasklet, resend_irqs, 0); + +#endif + +/* + * IRQ resend + * + * Is called with interrupts disabled and desc->lock held. + */ +void check_irq_resend(struct irq_desc *desc, unsigned int irq) +{ + /* + * We do not resend level type interrupts. Level type + * interrupts are resent by hardware when they are still + * active. Clear the pending bit so suspend/resume does not + * get confused. + */ + if (irq_settings_is_level(desc)) { + desc->istate &= ~IRQS_PENDING; + return; + } + if (desc->istate & IRQS_REPLAY) + return; + if (desc->istate & IRQS_PENDING) { + desc->istate &= ~IRQS_PENDING; + desc->istate |= IRQS_REPLAY; + + if (!desc->irq_data.chip->irq_retrigger || + !desc->irq_data.chip->irq_retrigger(&desc->irq_data)) { +#ifdef CONFIG_HARDIRQS_SW_RESEND + /* + * If the interrupt has a parent irq and runs + * in the thread context of the parent irq, + * retrigger the parent. + */ + if (desc->parent_irq && + irq_settings_is_nested_thread(desc)) + irq = desc->parent_irq; + /* Set it pending and activate the softirq: */ + set_bit(irq, irqs_resend); + tasklet_schedule(&resend_tasklet); +#endif + } + } +} diff --git a/kernel/kernel/irq/settings.h b/kernel/kernel/irq/settings.h new file mode 100644 index 000000000..34b803b89 --- /dev/null +++ b/kernel/kernel/irq/settings.h @@ -0,0 +1,168 @@ +/* + * Internal header to deal with irq_desc->status which will be renamed + * to irq_desc->settings. + */ +enum { + _IRQ_DEFAULT_INIT_FLAGS = IRQ_DEFAULT_INIT_FLAGS, + _IRQ_PER_CPU = IRQ_PER_CPU, + _IRQ_LEVEL = IRQ_LEVEL, + _IRQ_NOPROBE = IRQ_NOPROBE, + _IRQ_NOREQUEST = IRQ_NOREQUEST, + _IRQ_NOTHREAD = IRQ_NOTHREAD, + _IRQ_NOAUTOEN = IRQ_NOAUTOEN, + _IRQ_MOVE_PCNTXT = IRQ_MOVE_PCNTXT, + _IRQ_NO_BALANCING = IRQ_NO_BALANCING, + _IRQ_NESTED_THREAD = IRQ_NESTED_THREAD, + _IRQ_PER_CPU_DEVID = IRQ_PER_CPU_DEVID, + _IRQ_IS_POLLED = IRQ_IS_POLLED, + _IRQ_NO_SOFTIRQ_CALL = IRQ_NO_SOFTIRQ_CALL, + _IRQF_MODIFY_MASK = IRQF_MODIFY_MASK, +}; + +#define IRQ_PER_CPU GOT_YOU_MORON +#define IRQ_NO_BALANCING GOT_YOU_MORON +#define IRQ_LEVEL GOT_YOU_MORON +#define IRQ_NOPROBE GOT_YOU_MORON +#define IRQ_NOREQUEST GOT_YOU_MORON +#define IRQ_NOTHREAD GOT_YOU_MORON +#define IRQ_NOAUTOEN GOT_YOU_MORON +#define IRQ_NESTED_THREAD GOT_YOU_MORON +#define IRQ_PER_CPU_DEVID GOT_YOU_MORON +#define IRQ_IS_POLLED GOT_YOU_MORON +#define IRQ_NO_SOFTIRQ_CALL GOT_YOU_MORON +#undef IRQF_MODIFY_MASK +#define IRQF_MODIFY_MASK GOT_YOU_MORON + +static inline void +irq_settings_clr_and_set(struct irq_desc *desc, u32 clr, u32 set) +{ + desc->status_use_accessors &= ~(clr & _IRQF_MODIFY_MASK); + desc->status_use_accessors |= (set & _IRQF_MODIFY_MASK); +} + +static inline bool irq_settings_no_softirq_call(struct irq_desc *desc) +{ + return desc->status_use_accessors & _IRQ_NO_SOFTIRQ_CALL; +} + +static inline void irq_settings_set_no_softirq_call(struct irq_desc *desc) +{ + desc->status_use_accessors |= _IRQ_NO_SOFTIRQ_CALL; +} + +static inline bool irq_settings_is_per_cpu(struct irq_desc *desc) +{ + return desc->status_use_accessors & _IRQ_PER_CPU; +} + +static inline bool irq_settings_is_per_cpu_devid(struct irq_desc *desc) +{ + return desc->status_use_accessors & _IRQ_PER_CPU_DEVID; +} + +static inline void irq_settings_set_per_cpu(struct irq_desc *desc) +{ + desc->status_use_accessors |= _IRQ_PER_CPU; +} + +static inline void irq_settings_set_no_balancing(struct irq_desc *desc) +{ + desc->status_use_accessors |= _IRQ_NO_BALANCING; +} + +static inline bool irq_settings_has_no_balance_set(struct irq_desc *desc) +{ + return desc->status_use_accessors & _IRQ_NO_BALANCING; +} + +static inline u32 irq_settings_get_trigger_mask(struct irq_desc *desc) +{ + return desc->status_use_accessors & IRQ_TYPE_SENSE_MASK; +} + +static inline void +irq_settings_set_trigger_mask(struct irq_desc *desc, u32 mask) +{ + desc->status_use_accessors &= ~IRQ_TYPE_SENSE_MASK; + desc->status_use_accessors |= mask & IRQ_TYPE_SENSE_MASK; +} + +static inline bool irq_settings_is_level(struct irq_desc *desc) +{ + return desc->status_use_accessors & _IRQ_LEVEL; +} + +static inline void irq_settings_clr_level(struct irq_desc *desc) +{ + desc->status_use_accessors &= ~_IRQ_LEVEL; +} + +static inline void irq_settings_set_level(struct irq_desc *desc) +{ + desc->status_use_accessors |= _IRQ_LEVEL; +} + +static inline bool irq_settings_can_request(struct irq_desc *desc) +{ + return !(desc->status_use_accessors & _IRQ_NOREQUEST); +} + +static inline void irq_settings_clr_norequest(struct irq_desc *desc) +{ + desc->status_use_accessors &= ~_IRQ_NOREQUEST; +} + +static inline void irq_settings_set_norequest(struct irq_desc *desc) +{ + desc->status_use_accessors |= _IRQ_NOREQUEST; +} + +static inline bool irq_settings_can_thread(struct irq_desc *desc) +{ + return !(desc->status_use_accessors & _IRQ_NOTHREAD); +} + +static inline void irq_settings_clr_nothread(struct irq_desc *desc) +{ + desc->status_use_accessors &= ~_IRQ_NOTHREAD; +} + +static inline void irq_settings_set_nothread(struct irq_desc *desc) +{ + desc->status_use_accessors |= _IRQ_NOTHREAD; +} + +static inline bool irq_settings_can_probe(struct irq_desc *desc) +{ + return !(desc->status_use_accessors & _IRQ_NOPROBE); +} + +static inline void irq_settings_clr_noprobe(struct irq_desc *desc) +{ + desc->status_use_accessors &= ~_IRQ_NOPROBE; +} + +static inline void irq_settings_set_noprobe(struct irq_desc *desc) +{ + desc->status_use_accessors |= _IRQ_NOPROBE; +} + +static inline bool irq_settings_can_move_pcntxt(struct irq_desc *desc) +{ + return desc->status_use_accessors & _IRQ_MOVE_PCNTXT; +} + +static inline bool irq_settings_can_autoenable(struct irq_desc *desc) +{ + return !(desc->status_use_accessors & _IRQ_NOAUTOEN); +} + +static inline bool irq_settings_is_nested_thread(struct irq_desc *desc) +{ + return desc->status_use_accessors & _IRQ_NESTED_THREAD; +} + +static inline bool irq_settings_is_polled(struct irq_desc *desc) +{ + return desc->status_use_accessors & _IRQ_IS_POLLED; +} diff --git a/kernel/kernel/irq/spurious.c b/kernel/kernel/irq/spurious.c new file mode 100644 index 000000000..903a69c45 --- /dev/null +++ b/kernel/kernel/irq/spurious.c @@ -0,0 +1,475 @@ +/* + * linux/kernel/irq/spurious.c + * + * Copyright (C) 1992, 1998-2004 Linus Torvalds, Ingo Molnar + * + * This file contains spurious interrupt handling. + */ + +#include +#include +#include +#include +#include +#include +#include + +#include "internals.h" + +static int irqfixup __read_mostly; + +#define POLL_SPURIOUS_IRQ_INTERVAL (HZ/10) +static void poll_spurious_irqs(unsigned long dummy); +static DEFINE_TIMER(poll_spurious_irq_timer, poll_spurious_irqs, 0, 0); +static int irq_poll_cpu; +static atomic_t irq_poll_active; + +/* + * We wait here for a poller to finish. + * + * If the poll runs on this CPU, then we yell loudly and return + * false. That will leave the interrupt line disabled in the worst + * case, but it should never happen. + * + * We wait until the poller is done and then recheck disabled and + * action (about to be disabled). Only if it's still active, we return + * true and let the handler run. + */ +bool irq_wait_for_poll(struct irq_desc *desc) +{ + if (WARN_ONCE(irq_poll_cpu == smp_processor_id(), + "irq poll in progress on cpu %d for irq %d\n", + smp_processor_id(), desc->irq_data.irq)) + return false; + +#ifdef CONFIG_SMP + do { + raw_spin_unlock(&desc->lock); + while (irqd_irq_inprogress(&desc->irq_data)) + cpu_relax(); + raw_spin_lock(&desc->lock); + } while (irqd_irq_inprogress(&desc->irq_data)); + /* Might have been disabled in meantime */ + return !irqd_irq_disabled(&desc->irq_data) && desc->action; +#else + return false; +#endif +} + + +/* + * Recovery handler for misrouted interrupts. + */ +static int try_one_irq(int irq, struct irq_desc *desc, bool force) +{ + irqreturn_t ret = IRQ_NONE; + struct irqaction *action; + + raw_spin_lock(&desc->lock); + + /* + * PER_CPU, nested thread interrupts and interrupts explicitely + * marked polled are excluded from polling. + */ + if (irq_settings_is_per_cpu(desc) || + irq_settings_is_nested_thread(desc) || + irq_settings_is_polled(desc)) + goto out; + + /* + * Do not poll disabled interrupts unless the spurious + * disabled poller asks explicitely. + */ + if (irqd_irq_disabled(&desc->irq_data) && !force) + goto out; + + /* + * All handlers must agree on IRQF_SHARED, so we test just the + * first. + */ + action = desc->action; + if (!action || !(action->flags & IRQF_SHARED) || + (action->flags & __IRQF_TIMER)) + goto out; + + /* Already running on another processor */ + if (irqd_irq_inprogress(&desc->irq_data)) { + /* + * Already running: If it is shared get the other + * CPU to go looking for our mystery interrupt too + */ + desc->istate |= IRQS_PENDING; + goto out; + } + + /* Mark it poll in progress */ + desc->istate |= IRQS_POLL_INPROGRESS; + do { + if (handle_irq_event(desc) == IRQ_HANDLED) + ret = IRQ_HANDLED; + /* Make sure that there is still a valid action */ + action = desc->action; + } while ((desc->istate & IRQS_PENDING) && action); + desc->istate &= ~IRQS_POLL_INPROGRESS; +out: + raw_spin_unlock(&desc->lock); + return ret == IRQ_HANDLED; +} + +static int misrouted_irq(int irq) +{ + struct irq_desc *desc; + int i, ok = 0; + + if (atomic_inc_return(&irq_poll_active) != 1) + goto out; + + irq_poll_cpu = smp_processor_id(); + + for_each_irq_desc(i, desc) { + if (!i) + continue; + + if (i == irq) /* Already tried */ + continue; + + if (try_one_irq(i, desc, false)) + ok = 1; + } +out: + atomic_dec(&irq_poll_active); + /* So the caller can adjust the irq error counts */ + return ok; +} + +static void poll_spurious_irqs(unsigned long dummy) +{ + struct irq_desc *desc; + int i; + + if (atomic_inc_return(&irq_poll_active) != 1) + goto out; + irq_poll_cpu = smp_processor_id(); + + for_each_irq_desc(i, desc) { + unsigned int state; + + if (!i) + continue; + + /* Racy but it doesn't matter */ + state = desc->istate; + barrier(); + if (!(state & IRQS_SPURIOUS_DISABLED)) + continue; + + local_irq_disable(); + try_one_irq(i, desc, true); + local_irq_enable(); + } +out: + atomic_dec(&irq_poll_active); + mod_timer(&poll_spurious_irq_timer, + jiffies + POLL_SPURIOUS_IRQ_INTERVAL); +} + +static inline int bad_action_ret(irqreturn_t action_ret) +{ + if (likely(action_ret <= (IRQ_HANDLED | IRQ_WAKE_THREAD))) + return 0; + return 1; +} + +/* + * If 99,900 of the previous 100,000 interrupts have not been handled + * then assume that the IRQ is stuck in some manner. Drop a diagnostic + * and try to turn the IRQ off. + * + * (The other 100-of-100,000 interrupts may have been a correctly + * functioning device sharing an IRQ with the failing one) + */ +static void +__report_bad_irq(unsigned int irq, struct irq_desc *desc, + irqreturn_t action_ret) +{ + struct irqaction *action; + unsigned long flags; + + if (bad_action_ret(action_ret)) { + printk(KERN_ERR "irq event %d: bogus return value %x\n", + irq, action_ret); + } else { + printk(KERN_ERR "irq %d: nobody cared (try booting with " + "the \"irqpoll\" option)\n", irq); + } + dump_stack(); + printk(KERN_ERR "handlers:\n"); + + /* + * We need to take desc->lock here. note_interrupt() is called + * w/o desc->lock held, but IRQ_PROGRESS set. We might race + * with something else removing an action. It's ok to take + * desc->lock here. See synchronize_irq(). + */ + raw_spin_lock_irqsave(&desc->lock, flags); + action = desc->action; + while (action) { + printk(KERN_ERR "[<%p>] %pf", action->handler, action->handler); + if (action->thread_fn) + printk(KERN_CONT " threaded [<%p>] %pf", + action->thread_fn, action->thread_fn); + printk(KERN_CONT "\n"); + action = action->next; + } + raw_spin_unlock_irqrestore(&desc->lock, flags); +} + +static void +report_bad_irq(unsigned int irq, struct irq_desc *desc, irqreturn_t action_ret) +{ + static int count = 100; + + if (count > 0) { + count--; + __report_bad_irq(irq, desc, action_ret); + } +} + +static inline int +try_misrouted_irq(unsigned int irq, struct irq_desc *desc, + irqreturn_t action_ret) +{ + struct irqaction *action; + + if (!irqfixup) + return 0; + + /* We didn't actually handle the IRQ - see if it was misrouted? */ + if (action_ret == IRQ_NONE) + return 1; + + /* + * But for 'irqfixup == 2' we also do it for handled interrupts if + * they are marked as IRQF_IRQPOLL (or for irq zero, which is the + * traditional PC timer interrupt.. Legacy) + */ + if (irqfixup < 2) + return 0; + + if (!irq) + return 1; + + /* + * Since we don't get the descriptor lock, "action" can + * change under us. We don't really care, but we don't + * want to follow a NULL pointer. So tell the compiler to + * just load it once by using a barrier. + */ + action = desc->action; + barrier(); + return action && (action->flags & IRQF_IRQPOLL); +} + +#define SPURIOUS_DEFERRED 0x80000000 + +void note_interrupt(unsigned int irq, struct irq_desc *desc, + irqreturn_t action_ret) +{ + if (desc->istate & IRQS_POLL_INPROGRESS || + irq_settings_is_polled(desc)) + return; + + if (bad_action_ret(action_ret)) { + report_bad_irq(irq, desc, action_ret); + return; + } + + /* + * We cannot call note_interrupt from the threaded handler + * because we need to look at the compound of all handlers + * (primary and threaded). Aside of that in the threaded + * shared case we have no serialization against an incoming + * hardware interrupt while we are dealing with a threaded + * result. + * + * So in case a thread is woken, we just note the fact and + * defer the analysis to the next hardware interrupt. + * + * The threaded handlers store whether they sucessfully + * handled an interrupt and we check whether that number + * changed versus the last invocation. + * + * We could handle all interrupts with the delayed by one + * mechanism, but for the non forced threaded case we'd just + * add pointless overhead to the straight hardirq interrupts + * for the sake of a few lines less code. + */ + if (action_ret & IRQ_WAKE_THREAD) { + /* + * There is a thread woken. Check whether one of the + * shared primary handlers returned IRQ_HANDLED. If + * not we defer the spurious detection to the next + * interrupt. + */ + if (action_ret == IRQ_WAKE_THREAD) { + int handled; + /* + * We use bit 31 of thread_handled_last to + * denote the deferred spurious detection + * active. No locking necessary as + * thread_handled_last is only accessed here + * and we have the guarantee that hard + * interrupts are not reentrant. + */ + if (!(desc->threads_handled_last & SPURIOUS_DEFERRED)) { + desc->threads_handled_last |= SPURIOUS_DEFERRED; + return; + } + /* + * Check whether one of the threaded handlers + * returned IRQ_HANDLED since the last + * interrupt happened. + * + * For simplicity we just set bit 31, as it is + * set in threads_handled_last as well. So we + * avoid extra masking. And we really do not + * care about the high bits of the handled + * count. We just care about the count being + * different than the one we saw before. + */ + handled = atomic_read(&desc->threads_handled); + handled |= SPURIOUS_DEFERRED; + if (handled != desc->threads_handled_last) { + action_ret = IRQ_HANDLED; + /* + * Note: We keep the SPURIOUS_DEFERRED + * bit set. We are handling the + * previous invocation right now. + * Keep it for the current one, so the + * next hardware interrupt will + * account for it. + */ + desc->threads_handled_last = handled; + } else { + /* + * None of the threaded handlers felt + * responsible for the last interrupt + * + * We keep the SPURIOUS_DEFERRED bit + * set in threads_handled_last as we + * need to account for the current + * interrupt as well. + */ + action_ret = IRQ_NONE; + } + } else { + /* + * One of the primary handlers returned + * IRQ_HANDLED. So we don't care about the + * threaded handlers on the same line. Clear + * the deferred detection bit. + * + * In theory we could/should check whether the + * deferred bit is set and take the result of + * the previous run into account here as + * well. But it's really not worth the + * trouble. If every other interrupt is + * handled we never trigger the spurious + * detector. And if this is just the one out + * of 100k unhandled ones which is handled + * then we merily delay the spurious detection + * by one hard interrupt. Not a real problem. + */ + desc->threads_handled_last &= ~SPURIOUS_DEFERRED; + } + } + + if (unlikely(action_ret == IRQ_NONE)) { + /* + * If we are seeing only the odd spurious IRQ caused by + * bus asynchronicity then don't eventually trigger an error, + * otherwise the counter becomes a doomsday timer for otherwise + * working systems + */ + if (time_after(jiffies, desc->last_unhandled + HZ/10)) + desc->irqs_unhandled = 1; + else + desc->irqs_unhandled++; + desc->last_unhandled = jiffies; + } + + if (unlikely(try_misrouted_irq(irq, desc, action_ret))) { + int ok = misrouted_irq(irq); + if (action_ret == IRQ_NONE) + desc->irqs_unhandled -= ok; + } + + desc->irq_count++; + if (likely(desc->irq_count < 100000)) + return; + + desc->irq_count = 0; + if (unlikely(desc->irqs_unhandled > 99900)) { + /* + * The interrupt is stuck + */ + __report_bad_irq(irq, desc, action_ret); + /* + * Now kill the IRQ + */ + printk(KERN_EMERG "Disabling IRQ #%d\n", irq); + desc->istate |= IRQS_SPURIOUS_DISABLED; + desc->depth++; + irq_disable(desc); + + mod_timer(&poll_spurious_irq_timer, + jiffies + POLL_SPURIOUS_IRQ_INTERVAL); + } + desc->irqs_unhandled = 0; +} + +bool noirqdebug __read_mostly; + +int noirqdebug_setup(char *str) +{ + noirqdebug = 1; + printk(KERN_INFO "IRQ lockup detection disabled\n"); + + return 1; +} + +__setup("noirqdebug", noirqdebug_setup); +module_param(noirqdebug, bool, 0644); +MODULE_PARM_DESC(noirqdebug, "Disable irq lockup detection when true"); + +static int __init irqfixup_setup(char *str) +{ +#ifdef CONFIG_PREEMPT_RT_BASE + pr_warn("irqfixup boot option not supported w/ CONFIG_PREEMPT_RT_BASE\n"); + return 1; +#endif + irqfixup = 1; + printk(KERN_WARNING "Misrouted IRQ fixup support enabled.\n"); + printk(KERN_WARNING "This may impact system performance.\n"); + + return 1; +} + +__setup("irqfixup", irqfixup_setup); +module_param(irqfixup, int, 0644); + +static int __init irqpoll_setup(char *str) +{ +#ifdef CONFIG_PREEMPT_RT_BASE + pr_warn("irqpoll boot option not supported w/ CONFIG_PREEMPT_RT_BASE\n"); + return 1; +#endif + irqfixup = 2; + printk(KERN_WARNING "Misrouted IRQ fixup and polling support " + "enabled\n"); + printk(KERN_WARNING "This may significantly impact system " + "performance\n"); + return 1; +} + +__setup("irqpoll", irqpoll_setup); diff --git a/kernel/kernel/irq_work.c b/kernel/kernel/irq_work.c new file mode 100644 index 000000000..5a0f45251 --- /dev/null +++ b/kernel/kernel/irq_work.c @@ -0,0 +1,217 @@ +/* + * Copyright (C) 2010 Red Hat, Inc., Peter Zijlstra + * + * Provides a framework for enqueueing and running callbacks from hardirq + * context. The enqueueing is NMI-safe. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + +static DEFINE_PER_CPU(struct llist_head, raised_list); +static DEFINE_PER_CPU(struct llist_head, lazy_list); + +/* + * Claim the entry so that no one else will poke at it. + */ +static bool irq_work_claim(struct irq_work *work) +{ + unsigned long flags, oflags, nflags; + + /* + * Start with our best wish as a premise but only trust any + * flag value after cmpxchg() result. + */ + flags = work->flags & ~IRQ_WORK_PENDING; + for (;;) { + nflags = flags | IRQ_WORK_FLAGS; + oflags = cmpxchg(&work->flags, flags, nflags); + if (oflags == flags) + break; + if (oflags & IRQ_WORK_PENDING) + return false; + flags = oflags; + cpu_relax(); + } + + return true; +} + +void __weak arch_irq_work_raise(void) +{ + /* + * Lame architectures will get the timer tick callback + */ +} + +#ifdef CONFIG_SMP +/* + * Enqueue the irq_work @work on @cpu unless it's already pending + * somewhere. + * + * Can be re-enqueued while the callback is still in progress. + */ +bool irq_work_queue_on(struct irq_work *work, int cpu) +{ + struct llist_head *list; + + /* All work should have been flushed before going offline */ + WARN_ON_ONCE(cpu_is_offline(cpu)); + + /* Arch remote IPI send/receive backend aren't NMI safe */ + WARN_ON_ONCE(in_nmi()); + + /* Only queue if not already pending */ + if (!irq_work_claim(work)) + return false; + + if (IS_ENABLED(CONFIG_PREEMPT_RT_FULL) && !(work->flags & IRQ_WORK_HARD_IRQ)) + list = &per_cpu(lazy_list, cpu); + else + list = &per_cpu(raised_list, cpu); + + if (llist_add(&work->llnode, list)) + arch_send_call_function_single_ipi(cpu); + + return true; +} +EXPORT_SYMBOL_GPL(irq_work_queue_on); +#endif + +/* Enqueue the irq work @work on the current CPU */ +bool irq_work_queue(struct irq_work *work) +{ + struct llist_head *list; + bool lazy_work, realtime = IS_ENABLED(CONFIG_PREEMPT_RT_FULL); + + /* Only queue if not already pending */ + if (!irq_work_claim(work)) + return false; + + /* Queue the entry and raise the IPI if needed. */ + preempt_disable(); + + lazy_work = work->flags & IRQ_WORK_LAZY; + + if (lazy_work || (realtime && !(work->flags & IRQ_WORK_HARD_IRQ))) + list = this_cpu_ptr(&lazy_list); + else + list = this_cpu_ptr(&raised_list); + + if (llist_add(&work->llnode, list)) { + if (!lazy_work || tick_nohz_tick_stopped()) + arch_irq_work_raise(); + } + + preempt_enable(); + + return true; +} +EXPORT_SYMBOL_GPL(irq_work_queue); + +bool irq_work_needs_cpu(void) +{ + struct llist_head *raised, *lazy; + + raised = this_cpu_ptr(&raised_list); + lazy = this_cpu_ptr(&lazy_list); + + if (llist_empty(raised) && llist_empty(lazy)) + return false; + + /* All work should have been flushed before going offline */ + WARN_ON_ONCE(cpu_is_offline(smp_processor_id())); + + return true; +} + +static void irq_work_run_list(struct llist_head *list) +{ + unsigned long flags; + struct irq_work *work; + struct llist_node *llnode; + + BUG_ON_NONRT(!irqs_disabled()); + + if (llist_empty(list)) + return; + + llnode = llist_del_all(list); + while (llnode != NULL) { + work = llist_entry(llnode, struct irq_work, llnode); + + llnode = llist_next(llnode); + + /* + * Clear the PENDING bit, after this point the @work + * can be re-used. + * Make it immediately visible so that other CPUs trying + * to claim that work don't rely on us to handle their data + * while we are in the middle of the func. + */ + flags = work->flags & ~IRQ_WORK_PENDING; + xchg(&work->flags, flags); + + work->func(work); + /* + * Clear the BUSY bit and return to the free state if + * no-one else claimed it meanwhile. + */ + (void)cmpxchg(&work->flags, flags, flags & ~IRQ_WORK_BUSY); + } +} + +/* + * hotplug calls this through: + * hotplug_cfd() -> flush_smp_call_function_queue() + */ +void irq_work_run(void) +{ + irq_work_run_list(this_cpu_ptr(&raised_list)); + if (IS_ENABLED(CONFIG_PREEMPT_RT_FULL)) { + /* + * NOTE: we raise softirq via IPI for safety, + * and execute in irq_work_tick() to move the + * overhead from hard to soft irq context. + */ + if (!llist_empty(this_cpu_ptr(&lazy_list))) + raise_softirq(TIMER_SOFTIRQ); + } else + irq_work_run_list(this_cpu_ptr(&lazy_list)); +} +EXPORT_SYMBOL_GPL(irq_work_run); + +void irq_work_tick(void) +{ + struct llist_head *raised = this_cpu_ptr(&raised_list); + + if (!llist_empty(raised) && !arch_irq_work_has_interrupt()) + irq_work_run_list(raised); + irq_work_run_list(this_cpu_ptr(&lazy_list)); +} + +/* + * Synchronize against the irq_work @entry, ensures the entry is not + * currently in use. + */ +void irq_work_sync(struct irq_work *work) +{ + WARN_ON_ONCE(irqs_disabled()); + + while (work->flags & IRQ_WORK_BUSY) + cpu_relax(); +} +EXPORT_SYMBOL_GPL(irq_work_sync); diff --git a/kernel/kernel/jump_label.c b/kernel/kernel/jump_label.c new file mode 100644 index 000000000..9019f15de --- /dev/null +++ b/kernel/kernel/jump_label.c @@ -0,0 +1,460 @@ +/* + * jump label support + * + * Copyright (C) 2009 Jason Baron + * Copyright (C) 2011 Peter Zijlstra + * + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#ifdef HAVE_JUMP_LABEL + +/* mutex to protect coming/going of the the jump_label table */ +static DEFINE_MUTEX(jump_label_mutex); + +void jump_label_lock(void) +{ + mutex_lock(&jump_label_mutex); +} + +void jump_label_unlock(void) +{ + mutex_unlock(&jump_label_mutex); +} + +static int jump_label_cmp(const void *a, const void *b) +{ + const struct jump_entry *jea = a; + const struct jump_entry *jeb = b; + + if (jea->key < jeb->key) + return -1; + + if (jea->key > jeb->key) + return 1; + + return 0; +} + +static void +jump_label_sort_entries(struct jump_entry *start, struct jump_entry *stop) +{ + unsigned long size; + + size = (((unsigned long)stop - (unsigned long)start) + / sizeof(struct jump_entry)); + sort(start, size, sizeof(struct jump_entry), jump_label_cmp, NULL); +} + +static void jump_label_update(struct static_key *key, int enable); + +void static_key_slow_inc(struct static_key *key) +{ + STATIC_KEY_CHECK_USE(); + if (atomic_inc_not_zero(&key->enabled)) + return; + + jump_label_lock(); + if (atomic_read(&key->enabled) == 0) { + if (!jump_label_get_branch_default(key)) + jump_label_update(key, JUMP_LABEL_ENABLE); + else + jump_label_update(key, JUMP_LABEL_DISABLE); + } + atomic_inc(&key->enabled); + jump_label_unlock(); +} +EXPORT_SYMBOL_GPL(static_key_slow_inc); + +static void __static_key_slow_dec(struct static_key *key, + unsigned long rate_limit, struct delayed_work *work) +{ + if (!atomic_dec_and_mutex_lock(&key->enabled, &jump_label_mutex)) { + WARN(atomic_read(&key->enabled) < 0, + "jump label: negative count!\n"); + return; + } + + if (rate_limit) { + atomic_inc(&key->enabled); + schedule_delayed_work(work, rate_limit); + } else { + if (!jump_label_get_branch_default(key)) + jump_label_update(key, JUMP_LABEL_DISABLE); + else + jump_label_update(key, JUMP_LABEL_ENABLE); + } + jump_label_unlock(); +} + +static void jump_label_update_timeout(struct work_struct *work) +{ + struct static_key_deferred *key = + container_of(work, struct static_key_deferred, work.work); + __static_key_slow_dec(&key->key, 0, NULL); +} + +void static_key_slow_dec(struct static_key *key) +{ + STATIC_KEY_CHECK_USE(); + __static_key_slow_dec(key, 0, NULL); +} +EXPORT_SYMBOL_GPL(static_key_slow_dec); + +void static_key_slow_dec_deferred(struct static_key_deferred *key) +{ + STATIC_KEY_CHECK_USE(); + __static_key_slow_dec(&key->key, key->timeout, &key->work); +} +EXPORT_SYMBOL_GPL(static_key_slow_dec_deferred); + +void jump_label_rate_limit(struct static_key_deferred *key, + unsigned long rl) +{ + STATIC_KEY_CHECK_USE(); + key->timeout = rl; + INIT_DELAYED_WORK(&key->work, jump_label_update_timeout); +} +EXPORT_SYMBOL_GPL(jump_label_rate_limit); + +static int addr_conflict(struct jump_entry *entry, void *start, void *end) +{ + if (entry->code <= (unsigned long)end && + entry->code + JUMP_LABEL_NOP_SIZE > (unsigned long)start) + return 1; + + return 0; +} + +static int __jump_label_text_reserved(struct jump_entry *iter_start, + struct jump_entry *iter_stop, void *start, void *end) +{ + struct jump_entry *iter; + + iter = iter_start; + while (iter < iter_stop) { + if (addr_conflict(iter, start, end)) + return 1; + iter++; + } + + return 0; +} + +/* + * Update code which is definitely not currently executing. + * Architectures which need heavyweight synchronization to modify + * running code can override this to make the non-live update case + * cheaper. + */ +void __weak __init_or_module arch_jump_label_transform_static(struct jump_entry *entry, + enum jump_label_type type) +{ + arch_jump_label_transform(entry, type); +} + +static void __jump_label_update(struct static_key *key, + struct jump_entry *entry, + struct jump_entry *stop, int enable) +{ + for (; (entry < stop) && + (entry->key == (jump_label_t)(unsigned long)key); + entry++) { + /* + * entry->code set to 0 invalidates module init text sections + * kernel_text_address() verifies we are not in core kernel + * init code, see jump_label_invalidate_module_init(). + */ + if (entry->code && kernel_text_address(entry->code)) + arch_jump_label_transform(entry, enable); + } +} + +static enum jump_label_type jump_label_type(struct static_key *key) +{ + bool true_branch = jump_label_get_branch_default(key); + bool state = static_key_enabled(key); + + if ((!true_branch && state) || (true_branch && !state)) + return JUMP_LABEL_ENABLE; + + return JUMP_LABEL_DISABLE; +} + +void __init jump_label_init(void) +{ + struct jump_entry *iter_start = __start___jump_table; + struct jump_entry *iter_stop = __stop___jump_table; + struct static_key *key = NULL; + struct jump_entry *iter; + + jump_label_lock(); + jump_label_sort_entries(iter_start, iter_stop); + + for (iter = iter_start; iter < iter_stop; iter++) { + struct static_key *iterk; + + iterk = (struct static_key *)(unsigned long)iter->key; + arch_jump_label_transform_static(iter, jump_label_type(iterk)); + if (iterk == key) + continue; + + key = iterk; + /* + * Set key->entries to iter, but preserve JUMP_LABEL_TRUE_BRANCH. + */ + *((unsigned long *)&key->entries) += (unsigned long)iter; +#ifdef CONFIG_MODULES + key->next = NULL; +#endif + } + static_key_initialized = true; + jump_label_unlock(); +} + +#ifdef CONFIG_MODULES + +struct static_key_mod { + struct static_key_mod *next; + struct jump_entry *entries; + struct module *mod; +}; + +static int __jump_label_mod_text_reserved(void *start, void *end) +{ + struct module *mod; + + mod = __module_text_address((unsigned long)start); + if (!mod) + return 0; + + WARN_ON_ONCE(__module_text_address((unsigned long)end) != mod); + + return __jump_label_text_reserved(mod->jump_entries, + mod->jump_entries + mod->num_jump_entries, + start, end); +} + +static void __jump_label_mod_update(struct static_key *key, int enable) +{ + struct static_key_mod *mod = key->next; + + while (mod) { + struct module *m = mod->mod; + + __jump_label_update(key, mod->entries, + m->jump_entries + m->num_jump_entries, + enable); + mod = mod->next; + } +} + +/*** + * apply_jump_label_nops - patch module jump labels with arch_get_jump_label_nop() + * @mod: module to patch + * + * Allow for run-time selection of the optimal nops. Before the module + * loads patch these with arch_get_jump_label_nop(), which is specified by + * the arch specific jump label code. + */ +void jump_label_apply_nops(struct module *mod) +{ + struct jump_entry *iter_start = mod->jump_entries; + struct jump_entry *iter_stop = iter_start + mod->num_jump_entries; + struct jump_entry *iter; + + /* if the module doesn't have jump label entries, just return */ + if (iter_start == iter_stop) + return; + + for (iter = iter_start; iter < iter_stop; iter++) { + arch_jump_label_transform_static(iter, JUMP_LABEL_DISABLE); + } +} + +static int jump_label_add_module(struct module *mod) +{ + struct jump_entry *iter_start = mod->jump_entries; + struct jump_entry *iter_stop = iter_start + mod->num_jump_entries; + struct jump_entry *iter; + struct static_key *key = NULL; + struct static_key_mod *jlm; + + /* if the module doesn't have jump label entries, just return */ + if (iter_start == iter_stop) + return 0; + + jump_label_sort_entries(iter_start, iter_stop); + + for (iter = iter_start; iter < iter_stop; iter++) { + struct static_key *iterk; + + iterk = (struct static_key *)(unsigned long)iter->key; + if (iterk == key) + continue; + + key = iterk; + if (__module_address(iter->key) == mod) { + /* + * Set key->entries to iter, but preserve JUMP_LABEL_TRUE_BRANCH. + */ + *((unsigned long *)&key->entries) += (unsigned long)iter; + key->next = NULL; + continue; + } + jlm = kzalloc(sizeof(struct static_key_mod), GFP_KERNEL); + if (!jlm) + return -ENOMEM; + jlm->mod = mod; + jlm->entries = iter; + jlm->next = key->next; + key->next = jlm; + + if (jump_label_type(key) == JUMP_LABEL_ENABLE) + __jump_label_update(key, iter, iter_stop, JUMP_LABEL_ENABLE); + } + + return 0; +} + +static void jump_label_del_module(struct module *mod) +{ + struct jump_entry *iter_start = mod->jump_entries; + struct jump_entry *iter_stop = iter_start + mod->num_jump_entries; + struct jump_entry *iter; + struct static_key *key = NULL; + struct static_key_mod *jlm, **prev; + + for (iter = iter_start; iter < iter_stop; iter++) { + if (iter->key == (jump_label_t)(unsigned long)key) + continue; + + key = (struct static_key *)(unsigned long)iter->key; + + if (__module_address(iter->key) == mod) + continue; + + prev = &key->next; + jlm = key->next; + + while (jlm && jlm->mod != mod) { + prev = &jlm->next; + jlm = jlm->next; + } + + if (jlm) { + *prev = jlm->next; + kfree(jlm); + } + } +} + +static void jump_label_invalidate_module_init(struct module *mod) +{ + struct jump_entry *iter_start = mod->jump_entries; + struct jump_entry *iter_stop = iter_start + mod->num_jump_entries; + struct jump_entry *iter; + + for (iter = iter_start; iter < iter_stop; iter++) { + if (within_module_init(iter->code, mod)) + iter->code = 0; + } +} + +static int +jump_label_module_notify(struct notifier_block *self, unsigned long val, + void *data) +{ + struct module *mod = data; + int ret = 0; + + switch (val) { + case MODULE_STATE_COMING: + jump_label_lock(); + ret = jump_label_add_module(mod); + if (ret) + jump_label_del_module(mod); + jump_label_unlock(); + break; + case MODULE_STATE_GOING: + jump_label_lock(); + jump_label_del_module(mod); + jump_label_unlock(); + break; + case MODULE_STATE_LIVE: + jump_label_lock(); + jump_label_invalidate_module_init(mod); + jump_label_unlock(); + break; + } + + return notifier_from_errno(ret); +} + +struct notifier_block jump_label_module_nb = { + .notifier_call = jump_label_module_notify, + .priority = 1, /* higher than tracepoints */ +}; + +static __init int jump_label_init_module(void) +{ + return register_module_notifier(&jump_label_module_nb); +} +early_initcall(jump_label_init_module); + +#endif /* CONFIG_MODULES */ + +/*** + * jump_label_text_reserved - check if addr range is reserved + * @start: start text addr + * @end: end text addr + * + * checks if the text addr located between @start and @end + * overlaps with any of the jump label patch addresses. Code + * that wants to modify kernel text should first verify that + * it does not overlap with any of the jump label addresses. + * Caller must hold jump_label_mutex. + * + * returns 1 if there is an overlap, 0 otherwise + */ +int jump_label_text_reserved(void *start, void *end) +{ + int ret = __jump_label_text_reserved(__start___jump_table, + __stop___jump_table, start, end); + + if (ret) + return ret; + +#ifdef CONFIG_MODULES + ret = __jump_label_mod_text_reserved(start, end); +#endif + return ret; +} + +static void jump_label_update(struct static_key *key, int enable) +{ + struct jump_entry *stop = __stop___jump_table; + struct jump_entry *entry = jump_label_get_entries(key); + +#ifdef CONFIG_MODULES + struct module *mod = __module_address((unsigned long)key); + + __jump_label_mod_update(key, enable); + + if (mod) + stop = mod->jump_entries + mod->num_jump_entries; +#endif + /* if there are no users, entry can be NULL */ + if (entry) + __jump_label_update(key, entry, stop, enable); +} + +#endif diff --git a/kernel/kernel/kallsyms.c b/kernel/kernel/kallsyms.c new file mode 100644 index 000000000..5c5987f10 --- /dev/null +++ b/kernel/kernel/kallsyms.c @@ -0,0 +1,608 @@ +/* + * kallsyms.c: in-kernel printing of symbolic oopses and stack traces. + * + * Rewritten and vastly simplified by Rusty Russell for in-kernel + * module loader: + * Copyright 2002 Rusty Russell IBM Corporation + * + * ChangeLog: + * + * (25/Aug/2004) Paulo Marques + * Changed the compression method from stem compression to "table lookup" + * compression (see scripts/kallsyms.c for a more complete description) + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include /* for cond_resched */ +#include +#include +#include +#include + +#include + +#ifdef CONFIG_KALLSYMS_ALL +#define all_var 1 +#else +#define all_var 0 +#endif + +/* + * These will be re-linked against their real values + * during the second link stage. + */ +extern const unsigned long kallsyms_addresses[] __weak; +extern const u8 kallsyms_names[] __weak; + +/* + * Tell the compiler that the count isn't in the small data section if the arch + * has one (eg: FRV). + */ +extern const unsigned long kallsyms_num_syms +__attribute__((weak, section(".rodata"))); + +extern const u8 kallsyms_token_table[] __weak; +extern const u16 kallsyms_token_index[] __weak; + +extern const unsigned long kallsyms_markers[] __weak; + +static inline int is_kernel_inittext(unsigned long addr) +{ + if (addr >= (unsigned long)_sinittext + && addr <= (unsigned long)_einittext) + return 1; + return 0; +} + +static inline int is_kernel_text(unsigned long addr) +{ + if ((addr >= (unsigned long)_stext && addr <= (unsigned long)_etext) || + arch_is_kernel_text(addr)) + return 1; + return in_gate_area_no_mm(addr); +} + +static inline int is_kernel(unsigned long addr) +{ + if (addr >= (unsigned long)_stext && addr <= (unsigned long)_end) + return 1; + return in_gate_area_no_mm(addr); +} + +static int is_ksym_addr(unsigned long addr) +{ + if (all_var) + return is_kernel(addr); + + return is_kernel_text(addr) || is_kernel_inittext(addr); +} + +/* + * Expand a compressed symbol data into the resulting uncompressed string, + * if uncompressed string is too long (>= maxlen), it will be truncated, + * given the offset to where the symbol is in the compressed stream. + */ +static unsigned int kallsyms_expand_symbol(unsigned int off, + char *result, size_t maxlen) +{ + int len, skipped_first = 0; + const u8 *tptr, *data; + + /* Get the compressed symbol length from the first symbol byte. */ + data = &kallsyms_names[off]; + len = *data; + data++; + + /* + * Update the offset to return the offset for the next symbol on + * the compressed stream. + */ + off += len + 1; + + /* + * For every byte on the compressed symbol data, copy the table + * entry for that byte. + */ + while (len) { + tptr = &kallsyms_token_table[kallsyms_token_index[*data]]; + data++; + len--; + + while (*tptr) { + if (skipped_first) { + if (maxlen <= 1) + goto tail; + *result = *tptr; + result++; + maxlen--; + } else + skipped_first = 1; + tptr++; + } + } + +tail: + if (maxlen) + *result = '\0'; + + /* Return to offset to the next symbol. */ + return off; +} + +/* + * Get symbol type information. This is encoded as a single char at the + * beginning of the symbol name. + */ +static char kallsyms_get_symbol_type(unsigned int off) +{ + /* + * Get just the first code, look it up in the token table, + * and return the first char from this token. + */ + return kallsyms_token_table[kallsyms_token_index[kallsyms_names[off + 1]]]; +} + + +/* + * Find the offset on the compressed stream given and index in the + * kallsyms array. + */ +static unsigned int get_symbol_offset(unsigned long pos) +{ + const u8 *name; + int i; + + /* + * Use the closest marker we have. We have markers every 256 positions, + * so that should be close enough. + */ + name = &kallsyms_names[kallsyms_markers[pos >> 8]]; + + /* + * Sequentially scan all the symbols up to the point we're searching + * for. Every symbol is stored in a [][ bytes of data] format, + * so we just need to add the len to the current pointer for every + * symbol we wish to skip. + */ + for (i = 0; i < (pos & 0xFF); i++) + name = name + (*name) + 1; + + return name - kallsyms_names; +} + +/* Lookup the address for this symbol. Returns 0 if not found. */ +unsigned long kallsyms_lookup_name(const char *name) +{ + char namebuf[KSYM_NAME_LEN]; + unsigned long i; + unsigned int off; + + for (i = 0, off = 0; i < kallsyms_num_syms; i++) { + off = kallsyms_expand_symbol(off, namebuf, ARRAY_SIZE(namebuf)); + + if (strcmp(namebuf, name) == 0) + return kallsyms_addresses[i]; + } + return module_kallsyms_lookup_name(name); +} +EXPORT_SYMBOL_GPL(kallsyms_lookup_name); + +int kallsyms_on_each_symbol(int (*fn)(void *, const char *, struct module *, + unsigned long), + void *data) +{ + char namebuf[KSYM_NAME_LEN]; + unsigned long i; + unsigned int off; + int ret; + + for (i = 0, off = 0; i < kallsyms_num_syms; i++) { + off = kallsyms_expand_symbol(off, namebuf, ARRAY_SIZE(namebuf)); + ret = fn(data, namebuf, NULL, kallsyms_addresses[i]); + if (ret != 0) + return ret; + } + return module_kallsyms_on_each_symbol(fn, data); +} +EXPORT_SYMBOL_GPL(kallsyms_on_each_symbol); + +static unsigned long get_symbol_pos(unsigned long addr, + unsigned long *symbolsize, + unsigned long *offset) +{ + unsigned long symbol_start = 0, symbol_end = 0; + unsigned long i, low, high, mid; + + /* This kernel should never had been booted. */ + BUG_ON(!kallsyms_addresses); + + /* Do a binary search on the sorted kallsyms_addresses array. */ + low = 0; + high = kallsyms_num_syms; + + while (high - low > 1) { + mid = low + (high - low) / 2; + if (kallsyms_addresses[mid] <= addr) + low = mid; + else + high = mid; + } + + /* + * Search for the first aliased symbol. Aliased + * symbols are symbols with the same address. + */ + while (low && kallsyms_addresses[low-1] == kallsyms_addresses[low]) + --low; + + symbol_start = kallsyms_addresses[low]; + + /* Search for next non-aliased symbol. */ + for (i = low + 1; i < kallsyms_num_syms; i++) { + if (kallsyms_addresses[i] > symbol_start) { + symbol_end = kallsyms_addresses[i]; + break; + } + } + + /* If we found no next symbol, we use the end of the section. */ + if (!symbol_end) { + if (is_kernel_inittext(addr)) + symbol_end = (unsigned long)_einittext; + else if (all_var) + symbol_end = (unsigned long)_end; + else + symbol_end = (unsigned long)_etext; + } + + if (symbolsize) + *symbolsize = symbol_end - symbol_start; + if (offset) + *offset = addr - symbol_start; + + return low; +} + +/* + * Lookup an address but don't bother to find any names. + */ +int kallsyms_lookup_size_offset(unsigned long addr, unsigned long *symbolsize, + unsigned long *offset) +{ + char namebuf[KSYM_NAME_LEN]; + if (is_ksym_addr(addr)) + return !!get_symbol_pos(addr, symbolsize, offset); + + return !!module_address_lookup(addr, symbolsize, offset, NULL, namebuf); +} + +/* + * Lookup an address + * - modname is set to NULL if it's in the kernel. + * - We guarantee that the returned name is valid until we reschedule even if. + * It resides in a module. + * - We also guarantee that modname will be valid until rescheduled. + */ +const char *kallsyms_lookup(unsigned long addr, + unsigned long *symbolsize, + unsigned long *offset, + char **modname, char *namebuf) +{ + namebuf[KSYM_NAME_LEN - 1] = 0; + namebuf[0] = 0; + + if (is_ksym_addr(addr)) { + unsigned long pos; + + pos = get_symbol_pos(addr, symbolsize, offset); + /* Grab name */ + kallsyms_expand_symbol(get_symbol_offset(pos), + namebuf, KSYM_NAME_LEN); + if (modname) + *modname = NULL; + return namebuf; + } + + /* See if it's in a module. */ + return module_address_lookup(addr, symbolsize, offset, modname, + namebuf); +} + +int lookup_symbol_name(unsigned long addr, char *symname) +{ + symname[0] = '\0'; + symname[KSYM_NAME_LEN - 1] = '\0'; + + if (is_ksym_addr(addr)) { + unsigned long pos; + + pos = get_symbol_pos(addr, NULL, NULL); + /* Grab name */ + kallsyms_expand_symbol(get_symbol_offset(pos), + symname, KSYM_NAME_LEN); + return 0; + } + /* See if it's in a module. */ + return lookup_module_symbol_name(addr, symname); +} + +int lookup_symbol_attrs(unsigned long addr, unsigned long *size, + unsigned long *offset, char *modname, char *name) +{ + name[0] = '\0'; + name[KSYM_NAME_LEN - 1] = '\0'; + + if (is_ksym_addr(addr)) { + unsigned long pos; + + pos = get_symbol_pos(addr, size, offset); + /* Grab name */ + kallsyms_expand_symbol(get_symbol_offset(pos), + name, KSYM_NAME_LEN); + modname[0] = '\0'; + return 0; + } + /* See if it's in a module. */ + return lookup_module_symbol_attrs(addr, size, offset, modname, name); +} + +/* Look up a kernel symbol and return it in a text buffer. */ +static int __sprint_symbol(char *buffer, unsigned long address, + int symbol_offset, int add_offset) +{ + char *modname; + const char *name; + unsigned long offset, size; + int len; + + address += symbol_offset; + name = kallsyms_lookup(address, &size, &offset, &modname, buffer); + if (!name) + return sprintf(buffer, "0x%lx", address - symbol_offset); + + if (name != buffer) + strcpy(buffer, name); + len = strlen(buffer); + offset -= symbol_offset; + + if (add_offset) + len += sprintf(buffer + len, "+%#lx/%#lx", offset, size); + + if (modname) + len += sprintf(buffer + len, " [%s]", modname); + + return len; +} + +/** + * sprint_symbol - Look up a kernel symbol and return it in a text buffer + * @buffer: buffer to be stored + * @address: address to lookup + * + * This function looks up a kernel symbol with @address and stores its name, + * offset, size and module name to @buffer if possible. If no symbol was found, + * just saves its @address as is. + * + * This function returns the number of bytes stored in @buffer. + */ +int sprint_symbol(char *buffer, unsigned long address) +{ + return __sprint_symbol(buffer, address, 0, 1); +} +EXPORT_SYMBOL_GPL(sprint_symbol); + +/** + * sprint_symbol_no_offset - Look up a kernel symbol and return it in a text buffer + * @buffer: buffer to be stored + * @address: address to lookup + * + * This function looks up a kernel symbol with @address and stores its name + * and module name to @buffer if possible. If no symbol was found, just saves + * its @address as is. + * + * This function returns the number of bytes stored in @buffer. + */ +int sprint_symbol_no_offset(char *buffer, unsigned long address) +{ + return __sprint_symbol(buffer, address, 0, 0); +} +EXPORT_SYMBOL_GPL(sprint_symbol_no_offset); + +/** + * sprint_backtrace - Look up a backtrace symbol and return it in a text buffer + * @buffer: buffer to be stored + * @address: address to lookup + * + * This function is for stack backtrace and does the same thing as + * sprint_symbol() but with modified/decreased @address. If there is a + * tail-call to the function marked "noreturn", gcc optimized out code after + * the call so that the stack-saved return address could point outside of the + * caller. This function ensures that kallsyms will find the original caller + * by decreasing @address. + * + * This function returns the number of bytes stored in @buffer. + */ +int sprint_backtrace(char *buffer, unsigned long address) +{ + return __sprint_symbol(buffer, address, -1, 1); +} + +/* Look up a kernel symbol and print it to the kernel messages. */ +void __print_symbol(const char *fmt, unsigned long address) +{ + char buffer[KSYM_SYMBOL_LEN]; + + sprint_symbol(buffer, address); + + printk(fmt, buffer); +} +EXPORT_SYMBOL(__print_symbol); + +/* To avoid using get_symbol_offset for every symbol, we carry prefix along. */ +struct kallsym_iter { + loff_t pos; + unsigned long value; + unsigned int nameoff; /* If iterating in core kernel symbols. */ + char type; + char name[KSYM_NAME_LEN]; + char module_name[MODULE_NAME_LEN]; + int exported; +}; + +static int get_ksymbol_mod(struct kallsym_iter *iter) +{ + if (module_get_kallsym(iter->pos - kallsyms_num_syms, &iter->value, + &iter->type, iter->name, iter->module_name, + &iter->exported) < 0) + return 0; + return 1; +} + +/* Returns space to next name. */ +static unsigned long get_ksymbol_core(struct kallsym_iter *iter) +{ + unsigned off = iter->nameoff; + + iter->module_name[0] = '\0'; + iter->value = kallsyms_addresses[iter->pos]; + + iter->type = kallsyms_get_symbol_type(off); + + off = kallsyms_expand_symbol(off, iter->name, ARRAY_SIZE(iter->name)); + + return off - iter->nameoff; +} + +static void reset_iter(struct kallsym_iter *iter, loff_t new_pos) +{ + iter->name[0] = '\0'; + iter->nameoff = get_symbol_offset(new_pos); + iter->pos = new_pos; +} + +/* Returns false if pos at or past end of file. */ +static int update_iter(struct kallsym_iter *iter, loff_t pos) +{ + /* Module symbols can be accessed randomly. */ + if (pos >= kallsyms_num_syms) { + iter->pos = pos; + return get_ksymbol_mod(iter); + } + + /* If we're not on the desired position, reset to new position. */ + if (pos != iter->pos) + reset_iter(iter, pos); + + iter->nameoff += get_ksymbol_core(iter); + iter->pos++; + + return 1; +} + +static void *s_next(struct seq_file *m, void *p, loff_t *pos) +{ + (*pos)++; + + if (!update_iter(m->private, *pos)) + return NULL; + return p; +} + +static void *s_start(struct seq_file *m, loff_t *pos) +{ + if (!update_iter(m->private, *pos)) + return NULL; + return m->private; +} + +static void s_stop(struct seq_file *m, void *p) +{ +} + +static int s_show(struct seq_file *m, void *p) +{ + struct kallsym_iter *iter = m->private; + + /* Some debugging symbols have no name. Ignore them. */ + if (!iter->name[0]) + return 0; + + if (iter->module_name[0]) { + char type; + + /* + * Label it "global" if it is exported, + * "local" if not exported. + */ + type = iter->exported ? toupper(iter->type) : + tolower(iter->type); + seq_printf(m, "%pK %c %s\t[%s]\n", (void *)iter->value, + type, iter->name, iter->module_name); + } else + seq_printf(m, "%pK %c %s\n", (void *)iter->value, + iter->type, iter->name); + return 0; +} + +static const struct seq_operations kallsyms_op = { + .start = s_start, + .next = s_next, + .stop = s_stop, + .show = s_show +}; + +static int kallsyms_open(struct inode *inode, struct file *file) +{ + /* + * We keep iterator in m->private, since normal case is to + * s_start from where we left off, so we avoid doing + * using get_symbol_offset for every symbol. + */ + struct kallsym_iter *iter; + iter = __seq_open_private(file, &kallsyms_op, sizeof(*iter)); + if (!iter) + return -ENOMEM; + reset_iter(iter, 0); + + return 0; +} + +#ifdef CONFIG_KGDB_KDB +const char *kdb_walk_kallsyms(loff_t *pos) +{ + static struct kallsym_iter kdb_walk_kallsyms_iter; + if (*pos == 0) { + memset(&kdb_walk_kallsyms_iter, 0, + sizeof(kdb_walk_kallsyms_iter)); + reset_iter(&kdb_walk_kallsyms_iter, 0); + } + while (1) { + if (!update_iter(&kdb_walk_kallsyms_iter, *pos)) + return NULL; + ++*pos; + /* Some debugging symbols have no name. Ignore them. */ + if (kdb_walk_kallsyms_iter.name[0]) + return kdb_walk_kallsyms_iter.name; + } +} +#endif /* CONFIG_KGDB_KDB */ + +static const struct file_operations kallsyms_operations = { + .open = kallsyms_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release_private, +}; + +static int __init kallsyms_init(void) +{ + proc_create("kallsyms", 0444, NULL, &kallsyms_operations); + return 0; +} +device_initcall(kallsyms_init); diff --git a/kernel/kernel/kcmp.c b/kernel/kernel/kcmp.c new file mode 100644 index 000000000..0aa69ea1d --- /dev/null +++ b/kernel/kernel/kcmp.c @@ -0,0 +1,198 @@ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +/* + * We don't expose the real in-memory order of objects for security reasons. + * But still the comparison results should be suitable for sorting. So we + * obfuscate kernel pointers values and compare the production instead. + * + * The obfuscation is done in two steps. First we xor the kernel pointer with + * a random value, which puts pointer into a new position in a reordered space. + * Secondly we multiply the xor production with a large odd random number to + * permute its bits even more (the odd multiplier guarantees that the product + * is unique ever after the high bits are truncated, since any odd number is + * relative prime to 2^n). + * + * Note also that the obfuscation itself is invisible to userspace and if needed + * it can be changed to an alternate scheme. + */ +static unsigned long cookies[KCMP_TYPES][2] __read_mostly; + +static long kptr_obfuscate(long v, int type) +{ + return (v ^ cookies[type][0]) * cookies[type][1]; +} + +/* + * 0 - equal, i.e. v1 = v2 + * 1 - less than, i.e. v1 < v2 + * 2 - greater than, i.e. v1 > v2 + * 3 - not equal but ordering unavailable (reserved for future) + */ +static int kcmp_ptr(void *v1, void *v2, enum kcmp_type type) +{ + long t1, t2; + + t1 = kptr_obfuscate((long)v1, type); + t2 = kptr_obfuscate((long)v2, type); + + return (t1 < t2) | ((t1 > t2) << 1); +} + +/* The caller must have pinned the task */ +static struct file * +get_file_raw_ptr(struct task_struct *task, unsigned int idx) +{ + struct file *file = NULL; + + task_lock(task); + rcu_read_lock(); + + if (task->files) + file = fcheck_files(task->files, idx); + + rcu_read_unlock(); + task_unlock(task); + + return file; +} + +static void kcmp_unlock(struct mutex *m1, struct mutex *m2) +{ + if (likely(m2 != m1)) + mutex_unlock(m2); + mutex_unlock(m1); +} + +static int kcmp_lock(struct mutex *m1, struct mutex *m2) +{ + int err; + + if (m2 > m1) + swap(m1, m2); + + err = mutex_lock_killable(m1); + if (!err && likely(m1 != m2)) { + err = mutex_lock_killable_nested(m2, SINGLE_DEPTH_NESTING); + if (err) + mutex_unlock(m1); + } + + return err; +} + +SYSCALL_DEFINE5(kcmp, pid_t, pid1, pid_t, pid2, int, type, + unsigned long, idx1, unsigned long, idx2) +{ + struct task_struct *task1, *task2; + int ret; + + rcu_read_lock(); + + /* + * Tasks are looked up in caller's PID namespace only. + */ + task1 = find_task_by_vpid(pid1); + task2 = find_task_by_vpid(pid2); + if (!task1 || !task2) + goto err_no_task; + + get_task_struct(task1); + get_task_struct(task2); + + rcu_read_unlock(); + + /* + * One should have enough rights to inspect task details. + */ + ret = kcmp_lock(&task1->signal->cred_guard_mutex, + &task2->signal->cred_guard_mutex); + if (ret) + goto err; + if (!ptrace_may_access(task1, PTRACE_MODE_READ) || + !ptrace_may_access(task2, PTRACE_MODE_READ)) { + ret = -EPERM; + goto err_unlock; + } + + switch (type) { + case KCMP_FILE: { + struct file *filp1, *filp2; + + filp1 = get_file_raw_ptr(task1, idx1); + filp2 = get_file_raw_ptr(task2, idx2); + + if (filp1 && filp2) + ret = kcmp_ptr(filp1, filp2, KCMP_FILE); + else + ret = -EBADF; + break; + } + case KCMP_VM: + ret = kcmp_ptr(task1->mm, task2->mm, KCMP_VM); + break; + case KCMP_FILES: + ret = kcmp_ptr(task1->files, task2->files, KCMP_FILES); + break; + case KCMP_FS: + ret = kcmp_ptr(task1->fs, task2->fs, KCMP_FS); + break; + case KCMP_SIGHAND: + ret = kcmp_ptr(task1->sighand, task2->sighand, KCMP_SIGHAND); + break; + case KCMP_IO: + ret = kcmp_ptr(task1->io_context, task2->io_context, KCMP_IO); + break; + case KCMP_SYSVSEM: +#ifdef CONFIG_SYSVIPC + ret = kcmp_ptr(task1->sysvsem.undo_list, + task2->sysvsem.undo_list, + KCMP_SYSVSEM); +#else + ret = -EOPNOTSUPP; +#endif + break; + default: + ret = -EINVAL; + break; + } + +err_unlock: + kcmp_unlock(&task1->signal->cred_guard_mutex, + &task2->signal->cred_guard_mutex); +err: + put_task_struct(task1); + put_task_struct(task2); + + return ret; + +err_no_task: + rcu_read_unlock(); + return -ESRCH; +} + +static __init int kcmp_cookies_init(void) +{ + int i; + + get_random_bytes(cookies, sizeof(cookies)); + + for (i = 0; i < KCMP_TYPES; i++) + cookies[i][1] |= (~(~0UL >> 1) | 1); + + return 0; +} +arch_initcall(kcmp_cookies_init); diff --git a/kernel/kernel/kexec.c b/kernel/kernel/kexec.c new file mode 100644 index 000000000..7a36fdcca --- /dev/null +++ b/kernel/kernel/kexec.c @@ -0,0 +1,2769 @@ +/* + * kexec.c - kexec system call + * Copyright (C) 2002-2004 Eric Biederman + * + * This source code is licensed under the GNU General Public License, + * Version 2. See the file COPYING for more details. + */ + +#define pr_fmt(fmt) "kexec: " fmt + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include + +#include +#include + +/* Per cpu memory for storing cpu states in case of system crash. */ +note_buf_t __percpu *crash_notes; + +/* vmcoreinfo stuff */ +static unsigned char vmcoreinfo_data[VMCOREINFO_BYTES]; +u32 vmcoreinfo_note[VMCOREINFO_NOTE_SIZE/4]; +size_t vmcoreinfo_size; +size_t vmcoreinfo_max_size = sizeof(vmcoreinfo_data); + +/* Flag to indicate we are going to kexec a new kernel */ +bool kexec_in_progress = false; + +/* + * Declare these symbols weak so that if architecture provides a purgatory, + * these will be overridden. + */ +char __weak kexec_purgatory[0]; +size_t __weak kexec_purgatory_size = 0; + +#ifdef CONFIG_KEXEC_FILE +static int kexec_calculate_store_digests(struct kimage *image); +#endif + +/* Location of the reserved area for the crash kernel */ +struct resource crashk_res = { + .name = "Crash kernel", + .start = 0, + .end = 0, + .flags = IORESOURCE_BUSY | IORESOURCE_MEM +}; +struct resource crashk_low_res = { + .name = "Crash kernel", + .start = 0, + .end = 0, + .flags = IORESOURCE_BUSY | IORESOURCE_MEM +}; + +int kexec_should_crash(struct task_struct *p) +{ + if (in_interrupt() || !p->pid || is_global_init(p) || panic_on_oops) + return 1; + return 0; +} + +/* + * When kexec transitions to the new kernel there is a one-to-one + * mapping between physical and virtual addresses. On processors + * where you can disable the MMU this is trivial, and easy. For + * others it is still a simple predictable page table to setup. + * + * In that environment kexec copies the new kernel to its final + * resting place. This means I can only support memory whose + * physical address can fit in an unsigned long. In particular + * addresses where (pfn << PAGE_SHIFT) > ULONG_MAX cannot be handled. + * If the assembly stub has more restrictive requirements + * KEXEC_SOURCE_MEMORY_LIMIT and KEXEC_DEST_MEMORY_LIMIT can be + * defined more restrictively in . + * + * The code for the transition from the current kernel to the + * the new kernel is placed in the control_code_buffer, whose size + * is given by KEXEC_CONTROL_PAGE_SIZE. In the best case only a single + * page of memory is necessary, but some architectures require more. + * Because this memory must be identity mapped in the transition from + * virtual to physical addresses it must live in the range + * 0 - TASK_SIZE, as only the user space mappings are arbitrarily + * modifiable. + * + * The assembly stub in the control code buffer is passed a linked list + * of descriptor pages detailing the source pages of the new kernel, + * and the destination addresses of those source pages. As this data + * structure is not used in the context of the current OS, it must + * be self-contained. + * + * The code has been made to work with highmem pages and will use a + * destination page in its final resting place (if it happens + * to allocate it). The end product of this is that most of the + * physical address space, and most of RAM can be used. + * + * Future directions include: + * - allocating a page table with the control code buffer identity + * mapped, to simplify machine_kexec and make kexec_on_panic more + * reliable. + */ + +/* + * KIMAGE_NO_DEST is an impossible destination address..., for + * allocating pages whose destination address we do not care about. + */ +#define KIMAGE_NO_DEST (-1UL) + +static int kimage_is_destination_range(struct kimage *image, + unsigned long start, unsigned long end); +static struct page *kimage_alloc_page(struct kimage *image, + gfp_t gfp_mask, + unsigned long dest); + +static int copy_user_segment_list(struct kimage *image, + unsigned long nr_segments, + struct kexec_segment __user *segments) +{ + int ret; + size_t segment_bytes; + + /* Read in the segments */ + image->nr_segments = nr_segments; + segment_bytes = nr_segments * sizeof(*segments); + ret = copy_from_user(image->segment, segments, segment_bytes); + if (ret) + ret = -EFAULT; + + return ret; +} + +static int sanity_check_segment_list(struct kimage *image) +{ + int result, i; + unsigned long nr_segments = image->nr_segments; + + /* + * Verify we have good destination addresses. The caller is + * responsible for making certain we don't attempt to load + * the new image into invalid or reserved areas of RAM. This + * just verifies it is an address we can use. + * + * Since the kernel does everything in page size chunks ensure + * the destination addresses are page aligned. Too many + * special cases crop of when we don't do this. The most + * insidious is getting overlapping destination addresses + * simply because addresses are changed to page size + * granularity. + */ + result = -EADDRNOTAVAIL; + for (i = 0; i < nr_segments; i++) { + unsigned long mstart, mend; + + mstart = image->segment[i].mem; + mend = mstart + image->segment[i].memsz; + if ((mstart & ~PAGE_MASK) || (mend & ~PAGE_MASK)) + return result; + if (mend >= KEXEC_DESTINATION_MEMORY_LIMIT) + return result; + } + + /* Verify our destination addresses do not overlap. + * If we alloed overlapping destination addresses + * through very weird things can happen with no + * easy explanation as one segment stops on another. + */ + result = -EINVAL; + for (i = 0; i < nr_segments; i++) { + unsigned long mstart, mend; + unsigned long j; + + mstart = image->segment[i].mem; + mend = mstart + image->segment[i].memsz; + for (j = 0; j < i; j++) { + unsigned long pstart, pend; + pstart = image->segment[j].mem; + pend = pstart + image->segment[j].memsz; + /* Do the segments overlap ? */ + if ((mend > pstart) && (mstart < pend)) + return result; + } + } + + /* Ensure our buffer sizes are strictly less than + * our memory sizes. This should always be the case, + * and it is easier to check up front than to be surprised + * later on. + */ + result = -EINVAL; + for (i = 0; i < nr_segments; i++) { + if (image->segment[i].bufsz > image->segment[i].memsz) + return result; + } + + /* + * Verify we have good destination addresses. Normally + * the caller is responsible for making certain we don't + * attempt to load the new image into invalid or reserved + * areas of RAM. But crash kernels are preloaded into a + * reserved area of ram. We must ensure the addresses + * are in the reserved area otherwise preloading the + * kernel could corrupt things. + */ + + if (image->type == KEXEC_TYPE_CRASH) { + result = -EADDRNOTAVAIL; + for (i = 0; i < nr_segments; i++) { + unsigned long mstart, mend; + + mstart = image->segment[i].mem; + mend = mstart + image->segment[i].memsz - 1; + /* Ensure we are within the crash kernel limits */ + if ((mstart < crashk_res.start) || + (mend > crashk_res.end)) + return result; + } + } + + return 0; +} + +static struct kimage *do_kimage_alloc_init(void) +{ + struct kimage *image; + + /* Allocate a controlling structure */ + image = kzalloc(sizeof(*image), GFP_KERNEL); + if (!image) + return NULL; + + image->head = 0; + image->entry = &image->head; + image->last_entry = &image->head; + image->control_page = ~0; /* By default this does not apply */ + image->type = KEXEC_TYPE_DEFAULT; + + /* Initialize the list of control pages */ + INIT_LIST_HEAD(&image->control_pages); + + /* Initialize the list of destination pages */ + INIT_LIST_HEAD(&image->dest_pages); + + /* Initialize the list of unusable pages */ + INIT_LIST_HEAD(&image->unusable_pages); + + return image; +} + +static void kimage_free_page_list(struct list_head *list); + +static int kimage_alloc_init(struct kimage **rimage, unsigned long entry, + unsigned long nr_segments, + struct kexec_segment __user *segments, + unsigned long flags) +{ + int ret; + struct kimage *image; + bool kexec_on_panic = flags & KEXEC_ON_CRASH; + + if (kexec_on_panic) { + /* Verify we have a valid entry point */ + if ((entry < crashk_res.start) || (entry > crashk_res.end)) + return -EADDRNOTAVAIL; + } + + /* Allocate and initialize a controlling structure */ + image = do_kimage_alloc_init(); + if (!image) + return -ENOMEM; + + image->start = entry; + + ret = copy_user_segment_list(image, nr_segments, segments); + if (ret) + goto out_free_image; + + ret = sanity_check_segment_list(image); + if (ret) + goto out_free_image; + + /* Enable the special crash kernel control page allocation policy. */ + if (kexec_on_panic) { + image->control_page = crashk_res.start; + image->type = KEXEC_TYPE_CRASH; + } + + /* + * Find a location for the control code buffer, and add it + * the vector of segments so that it's pages will also be + * counted as destination pages. + */ + ret = -ENOMEM; + image->control_code_page = kimage_alloc_control_pages(image, + get_order(KEXEC_CONTROL_PAGE_SIZE)); + if (!image->control_code_page) { + pr_err("Could not allocate control_code_buffer\n"); + goto out_free_image; + } + + if (!kexec_on_panic) { + image->swap_page = kimage_alloc_control_pages(image, 0); + if (!image->swap_page) { + pr_err("Could not allocate swap buffer\n"); + goto out_free_control_pages; + } + } + + *rimage = image; + return 0; +out_free_control_pages: + kimage_free_page_list(&image->control_pages); +out_free_image: + kfree(image); + return ret; +} + +#ifdef CONFIG_KEXEC_FILE +static int copy_file_from_fd(int fd, void **buf, unsigned long *buf_len) +{ + struct fd f = fdget(fd); + int ret; + struct kstat stat; + loff_t pos; + ssize_t bytes = 0; + + if (!f.file) + return -EBADF; + + ret = vfs_getattr(&f.file->f_path, &stat); + if (ret) + goto out; + + if (stat.size > INT_MAX) { + ret = -EFBIG; + goto out; + } + + /* Don't hand 0 to vmalloc, it whines. */ + if (stat.size == 0) { + ret = -EINVAL; + goto out; + } + + *buf = vmalloc(stat.size); + if (!*buf) { + ret = -ENOMEM; + goto out; + } + + pos = 0; + while (pos < stat.size) { + bytes = kernel_read(f.file, pos, (char *)(*buf) + pos, + stat.size - pos); + if (bytes < 0) { + vfree(*buf); + ret = bytes; + goto out; + } + + if (bytes == 0) + break; + pos += bytes; + } + + if (pos != stat.size) { + ret = -EBADF; + vfree(*buf); + goto out; + } + + *buf_len = pos; +out: + fdput(f); + return ret; +} + +/* Architectures can provide this probe function */ +int __weak arch_kexec_kernel_image_probe(struct kimage *image, void *buf, + unsigned long buf_len) +{ + return -ENOEXEC; +} + +void * __weak arch_kexec_kernel_image_load(struct kimage *image) +{ + return ERR_PTR(-ENOEXEC); +} + +void __weak arch_kimage_file_post_load_cleanup(struct kimage *image) +{ +} + +int __weak arch_kexec_kernel_verify_sig(struct kimage *image, void *buf, + unsigned long buf_len) +{ + return -EKEYREJECTED; +} + +/* Apply relocations of type RELA */ +int __weak +arch_kexec_apply_relocations_add(const Elf_Ehdr *ehdr, Elf_Shdr *sechdrs, + unsigned int relsec) +{ + pr_err("RELA relocation unsupported.\n"); + return -ENOEXEC; +} + +/* Apply relocations of type REL */ +int __weak +arch_kexec_apply_relocations(const Elf_Ehdr *ehdr, Elf_Shdr *sechdrs, + unsigned int relsec) +{ + pr_err("REL relocation unsupported.\n"); + return -ENOEXEC; +} + +/* + * Free up memory used by kernel, initrd, and command line. This is temporary + * memory allocation which is not needed any more after these buffers have + * been loaded into separate segments and have been copied elsewhere. + */ +static void kimage_file_post_load_cleanup(struct kimage *image) +{ + struct purgatory_info *pi = &image->purgatory_info; + + vfree(image->kernel_buf); + image->kernel_buf = NULL; + + vfree(image->initrd_buf); + image->initrd_buf = NULL; + + kfree(image->cmdline_buf); + image->cmdline_buf = NULL; + + vfree(pi->purgatory_buf); + pi->purgatory_buf = NULL; + + vfree(pi->sechdrs); + pi->sechdrs = NULL; + + /* See if architecture has anything to cleanup post load */ + arch_kimage_file_post_load_cleanup(image); + + /* + * Above call should have called into bootloader to free up + * any data stored in kimage->image_loader_data. It should + * be ok now to free it up. + */ + kfree(image->image_loader_data); + image->image_loader_data = NULL; +} + +/* + * In file mode list of segments is prepared by kernel. Copy relevant + * data from user space, do error checking, prepare segment list + */ +static int +kimage_file_prepare_segments(struct kimage *image, int kernel_fd, int initrd_fd, + const char __user *cmdline_ptr, + unsigned long cmdline_len, unsigned flags) +{ + int ret = 0; + void *ldata; + + ret = copy_file_from_fd(kernel_fd, &image->kernel_buf, + &image->kernel_buf_len); + if (ret) + return ret; + + /* Call arch image probe handlers */ + ret = arch_kexec_kernel_image_probe(image, image->kernel_buf, + image->kernel_buf_len); + + if (ret) + goto out; + +#ifdef CONFIG_KEXEC_VERIFY_SIG + ret = arch_kexec_kernel_verify_sig(image, image->kernel_buf, + image->kernel_buf_len); + if (ret) { + pr_debug("kernel signature verification failed.\n"); + goto out; + } + pr_debug("kernel signature verification successful.\n"); +#endif + /* It is possible that there no initramfs is being loaded */ + if (!(flags & KEXEC_FILE_NO_INITRAMFS)) { + ret = copy_file_from_fd(initrd_fd, &image->initrd_buf, + &image->initrd_buf_len); + if (ret) + goto out; + } + + if (cmdline_len) { + image->cmdline_buf = kzalloc(cmdline_len, GFP_KERNEL); + if (!image->cmdline_buf) { + ret = -ENOMEM; + goto out; + } + + ret = copy_from_user(image->cmdline_buf, cmdline_ptr, + cmdline_len); + if (ret) { + ret = -EFAULT; + goto out; + } + + image->cmdline_buf_len = cmdline_len; + + /* command line should be a string with last byte null */ + if (image->cmdline_buf[cmdline_len - 1] != '\0') { + ret = -EINVAL; + goto out; + } + } + + /* Call arch image load handlers */ + ldata = arch_kexec_kernel_image_load(image); + + if (IS_ERR(ldata)) { + ret = PTR_ERR(ldata); + goto out; + } + + image->image_loader_data = ldata; +out: + /* In case of error, free up all allocated memory in this function */ + if (ret) + kimage_file_post_load_cleanup(image); + return ret; +} + +static int +kimage_file_alloc_init(struct kimage **rimage, int kernel_fd, + int initrd_fd, const char __user *cmdline_ptr, + unsigned long cmdline_len, unsigned long flags) +{ + int ret; + struct kimage *image; + bool kexec_on_panic = flags & KEXEC_FILE_ON_CRASH; + + image = do_kimage_alloc_init(); + if (!image) + return -ENOMEM; + + image->file_mode = 1; + + if (kexec_on_panic) { + /* Enable special crash kernel control page alloc policy. */ + image->control_page = crashk_res.start; + image->type = KEXEC_TYPE_CRASH; + } + + ret = kimage_file_prepare_segments(image, kernel_fd, initrd_fd, + cmdline_ptr, cmdline_len, flags); + if (ret) + goto out_free_image; + + ret = sanity_check_segment_list(image); + if (ret) + goto out_free_post_load_bufs; + + ret = -ENOMEM; + image->control_code_page = kimage_alloc_control_pages(image, + get_order(KEXEC_CONTROL_PAGE_SIZE)); + if (!image->control_code_page) { + pr_err("Could not allocate control_code_buffer\n"); + goto out_free_post_load_bufs; + } + + if (!kexec_on_panic) { + image->swap_page = kimage_alloc_control_pages(image, 0); + if (!image->swap_page) { + pr_err("Could not allocate swap buffer\n"); + goto out_free_control_pages; + } + } + + *rimage = image; + return 0; +out_free_control_pages: + kimage_free_page_list(&image->control_pages); +out_free_post_load_bufs: + kimage_file_post_load_cleanup(image); +out_free_image: + kfree(image); + return ret; +} +#else /* CONFIG_KEXEC_FILE */ +static inline void kimage_file_post_load_cleanup(struct kimage *image) { } +#endif /* CONFIG_KEXEC_FILE */ + +static int kimage_is_destination_range(struct kimage *image, + unsigned long start, + unsigned long end) +{ + unsigned long i; + + for (i = 0; i < image->nr_segments; i++) { + unsigned long mstart, mend; + + mstart = image->segment[i].mem; + mend = mstart + image->segment[i].memsz; + if ((end > mstart) && (start < mend)) + return 1; + } + + return 0; +} + +static struct page *kimage_alloc_pages(gfp_t gfp_mask, unsigned int order) +{ + struct page *pages; + + pages = alloc_pages(gfp_mask, order); + if (pages) { + unsigned int count, i; + pages->mapping = NULL; + set_page_private(pages, order); + count = 1 << order; + for (i = 0; i < count; i++) + SetPageReserved(pages + i); + } + + return pages; +} + +static void kimage_free_pages(struct page *page) +{ + unsigned int order, count, i; + + order = page_private(page); + count = 1 << order; + for (i = 0; i < count; i++) + ClearPageReserved(page + i); + __free_pages(page, order); +} + +static void kimage_free_page_list(struct list_head *list) +{ + struct list_head *pos, *next; + + list_for_each_safe(pos, next, list) { + struct page *page; + + page = list_entry(pos, struct page, lru); + list_del(&page->lru); + kimage_free_pages(page); + } +} + +static struct page *kimage_alloc_normal_control_pages(struct kimage *image, + unsigned int order) +{ + /* Control pages are special, they are the intermediaries + * that are needed while we copy the rest of the pages + * to their final resting place. As such they must + * not conflict with either the destination addresses + * or memory the kernel is already using. + * + * The only case where we really need more than one of + * these are for architectures where we cannot disable + * the MMU and must instead generate an identity mapped + * page table for all of the memory. + * + * At worst this runs in O(N) of the image size. + */ + struct list_head extra_pages; + struct page *pages; + unsigned int count; + + count = 1 << order; + INIT_LIST_HEAD(&extra_pages); + + /* Loop while I can allocate a page and the page allocated + * is a destination page. + */ + do { + unsigned long pfn, epfn, addr, eaddr; + + pages = kimage_alloc_pages(KEXEC_CONTROL_MEMORY_GFP, order); + if (!pages) + break; + pfn = page_to_pfn(pages); + epfn = pfn + count; + addr = pfn << PAGE_SHIFT; + eaddr = epfn << PAGE_SHIFT; + if ((epfn >= (KEXEC_CONTROL_MEMORY_LIMIT >> PAGE_SHIFT)) || + kimage_is_destination_range(image, addr, eaddr)) { + list_add(&pages->lru, &extra_pages); + pages = NULL; + } + } while (!pages); + + if (pages) { + /* Remember the allocated page... */ + list_add(&pages->lru, &image->control_pages); + + /* Because the page is already in it's destination + * location we will never allocate another page at + * that address. Therefore kimage_alloc_pages + * will not return it (again) and we don't need + * to give it an entry in image->segment[]. + */ + } + /* Deal with the destination pages I have inadvertently allocated. + * + * Ideally I would convert multi-page allocations into single + * page allocations, and add everything to image->dest_pages. + * + * For now it is simpler to just free the pages. + */ + kimage_free_page_list(&extra_pages); + + return pages; +} + +static struct page *kimage_alloc_crash_control_pages(struct kimage *image, + unsigned int order) +{ + /* Control pages are special, they are the intermediaries + * that are needed while we copy the rest of the pages + * to their final resting place. As such they must + * not conflict with either the destination addresses + * or memory the kernel is already using. + * + * Control pages are also the only pags we must allocate + * when loading a crash kernel. All of the other pages + * are specified by the segments and we just memcpy + * into them directly. + * + * The only case where we really need more than one of + * these are for architectures where we cannot disable + * the MMU and must instead generate an identity mapped + * page table for all of the memory. + * + * Given the low demand this implements a very simple + * allocator that finds the first hole of the appropriate + * size in the reserved memory region, and allocates all + * of the memory up to and including the hole. + */ + unsigned long hole_start, hole_end, size; + struct page *pages; + + pages = NULL; + size = (1 << order) << PAGE_SHIFT; + hole_start = (image->control_page + (size - 1)) & ~(size - 1); + hole_end = hole_start + size - 1; + while (hole_end <= crashk_res.end) { + unsigned long i; + + if (hole_end > KEXEC_CRASH_CONTROL_MEMORY_LIMIT) + break; + /* See if I overlap any of the segments */ + for (i = 0; i < image->nr_segments; i++) { + unsigned long mstart, mend; + + mstart = image->segment[i].mem; + mend = mstart + image->segment[i].memsz - 1; + if ((hole_end >= mstart) && (hole_start <= mend)) { + /* Advance the hole to the end of the segment */ + hole_start = (mend + (size - 1)) & ~(size - 1); + hole_end = hole_start + size - 1; + break; + } + } + /* If I don't overlap any segments I have found my hole! */ + if (i == image->nr_segments) { + pages = pfn_to_page(hole_start >> PAGE_SHIFT); + break; + } + } + if (pages) + image->control_page = hole_end; + + return pages; +} + + +struct page *kimage_alloc_control_pages(struct kimage *image, + unsigned int order) +{ + struct page *pages = NULL; + + switch (image->type) { + case KEXEC_TYPE_DEFAULT: + pages = kimage_alloc_normal_control_pages(image, order); + break; + case KEXEC_TYPE_CRASH: + pages = kimage_alloc_crash_control_pages(image, order); + break; + } + + return pages; +} + +static int kimage_add_entry(struct kimage *image, kimage_entry_t entry) +{ + if (*image->entry != 0) + image->entry++; + + if (image->entry == image->last_entry) { + kimage_entry_t *ind_page; + struct page *page; + + page = kimage_alloc_page(image, GFP_KERNEL, KIMAGE_NO_DEST); + if (!page) + return -ENOMEM; + + ind_page = page_address(page); + *image->entry = virt_to_phys(ind_page) | IND_INDIRECTION; + image->entry = ind_page; + image->last_entry = ind_page + + ((PAGE_SIZE/sizeof(kimage_entry_t)) - 1); + } + *image->entry = entry; + image->entry++; + *image->entry = 0; + + return 0; +} + +static int kimage_set_destination(struct kimage *image, + unsigned long destination) +{ + int result; + + destination &= PAGE_MASK; + result = kimage_add_entry(image, destination | IND_DESTINATION); + + return result; +} + + +static int kimage_add_page(struct kimage *image, unsigned long page) +{ + int result; + + page &= PAGE_MASK; + result = kimage_add_entry(image, page | IND_SOURCE); + + return result; +} + + +static void kimage_free_extra_pages(struct kimage *image) +{ + /* Walk through and free any extra destination pages I may have */ + kimage_free_page_list(&image->dest_pages); + + /* Walk through and free any unusable pages I have cached */ + kimage_free_page_list(&image->unusable_pages); + +} +static void kimage_terminate(struct kimage *image) +{ + if (*image->entry != 0) + image->entry++; + + *image->entry = IND_DONE; +} + +#define for_each_kimage_entry(image, ptr, entry) \ + for (ptr = &image->head; (entry = *ptr) && !(entry & IND_DONE); \ + ptr = (entry & IND_INDIRECTION) ? \ + phys_to_virt((entry & PAGE_MASK)) : ptr + 1) + +static void kimage_free_entry(kimage_entry_t entry) +{ + struct page *page; + + page = pfn_to_page(entry >> PAGE_SHIFT); + kimage_free_pages(page); +} + +static void kimage_free(struct kimage *image) +{ + kimage_entry_t *ptr, entry; + kimage_entry_t ind = 0; + + if (!image) + return; + + kimage_free_extra_pages(image); + for_each_kimage_entry(image, ptr, entry) { + if (entry & IND_INDIRECTION) { + /* Free the previous indirection page */ + if (ind & IND_INDIRECTION) + kimage_free_entry(ind); + /* Save this indirection page until we are + * done with it. + */ + ind = entry; + } else if (entry & IND_SOURCE) + kimage_free_entry(entry); + } + /* Free the final indirection page */ + if (ind & IND_INDIRECTION) + kimage_free_entry(ind); + + /* Handle any machine specific cleanup */ + machine_kexec_cleanup(image); + + /* Free the kexec control pages... */ + kimage_free_page_list(&image->control_pages); + + /* + * Free up any temporary buffers allocated. This might hit if + * error occurred much later after buffer allocation. + */ + if (image->file_mode) + kimage_file_post_load_cleanup(image); + + kfree(image); +} + +static kimage_entry_t *kimage_dst_used(struct kimage *image, + unsigned long page) +{ + kimage_entry_t *ptr, entry; + unsigned long destination = 0; + + for_each_kimage_entry(image, ptr, entry) { + if (entry & IND_DESTINATION) + destination = entry & PAGE_MASK; + else if (entry & IND_SOURCE) { + if (page == destination) + return ptr; + destination += PAGE_SIZE; + } + } + + return NULL; +} + +static struct page *kimage_alloc_page(struct kimage *image, + gfp_t gfp_mask, + unsigned long destination) +{ + /* + * Here we implement safeguards to ensure that a source page + * is not copied to its destination page before the data on + * the destination page is no longer useful. + * + * To do this we maintain the invariant that a source page is + * either its own destination page, or it is not a + * destination page at all. + * + * That is slightly stronger than required, but the proof + * that no problems will not occur is trivial, and the + * implementation is simply to verify. + * + * When allocating all pages normally this algorithm will run + * in O(N) time, but in the worst case it will run in O(N^2) + * time. If the runtime is a problem the data structures can + * be fixed. + */ + struct page *page; + unsigned long addr; + + /* + * Walk through the list of destination pages, and see if I + * have a match. + */ + list_for_each_entry(page, &image->dest_pages, lru) { + addr = page_to_pfn(page) << PAGE_SHIFT; + if (addr == destination) { + list_del(&page->lru); + return page; + } + } + page = NULL; + while (1) { + kimage_entry_t *old; + + /* Allocate a page, if we run out of memory give up */ + page = kimage_alloc_pages(gfp_mask, 0); + if (!page) + return NULL; + /* If the page cannot be used file it away */ + if (page_to_pfn(page) > + (KEXEC_SOURCE_MEMORY_LIMIT >> PAGE_SHIFT)) { + list_add(&page->lru, &image->unusable_pages); + continue; + } + addr = page_to_pfn(page) << PAGE_SHIFT; + + /* If it is the destination page we want use it */ + if (addr == destination) + break; + + /* If the page is not a destination page use it */ + if (!kimage_is_destination_range(image, addr, + addr + PAGE_SIZE)) + break; + + /* + * I know that the page is someones destination page. + * See if there is already a source page for this + * destination page. And if so swap the source pages. + */ + old = kimage_dst_used(image, addr); + if (old) { + /* If so move it */ + unsigned long old_addr; + struct page *old_page; + + old_addr = *old & PAGE_MASK; + old_page = pfn_to_page(old_addr >> PAGE_SHIFT); + copy_highpage(page, old_page); + *old = addr | (*old & ~PAGE_MASK); + + /* The old page I have found cannot be a + * destination page, so return it if it's + * gfp_flags honor the ones passed in. + */ + if (!(gfp_mask & __GFP_HIGHMEM) && + PageHighMem(old_page)) { + kimage_free_pages(old_page); + continue; + } + addr = old_addr; + page = old_page; + break; + } else { + /* Place the page on the destination list I + * will use it later. + */ + list_add(&page->lru, &image->dest_pages); + } + } + + return page; +} + +static int kimage_load_normal_segment(struct kimage *image, + struct kexec_segment *segment) +{ + unsigned long maddr; + size_t ubytes, mbytes; + int result; + unsigned char __user *buf = NULL; + unsigned char *kbuf = NULL; + + result = 0; + if (image->file_mode) + kbuf = segment->kbuf; + else + buf = segment->buf; + ubytes = segment->bufsz; + mbytes = segment->memsz; + maddr = segment->mem; + + result = kimage_set_destination(image, maddr); + if (result < 0) + goto out; + + while (mbytes) { + struct page *page; + char *ptr; + size_t uchunk, mchunk; + + page = kimage_alloc_page(image, GFP_HIGHUSER, maddr); + if (!page) { + result = -ENOMEM; + goto out; + } + result = kimage_add_page(image, page_to_pfn(page) + << PAGE_SHIFT); + if (result < 0) + goto out; + + ptr = kmap(page); + /* Start with a clear page */ + clear_page(ptr); + ptr += maddr & ~PAGE_MASK; + mchunk = min_t(size_t, mbytes, + PAGE_SIZE - (maddr & ~PAGE_MASK)); + uchunk = min(ubytes, mchunk); + + /* For file based kexec, source pages are in kernel memory */ + if (image->file_mode) + memcpy(ptr, kbuf, uchunk); + else + result = copy_from_user(ptr, buf, uchunk); + kunmap(page); + if (result) { + result = -EFAULT; + goto out; + } + ubytes -= uchunk; + maddr += mchunk; + if (image->file_mode) + kbuf += mchunk; + else + buf += mchunk; + mbytes -= mchunk; + } +out: + return result; +} + +static int kimage_load_crash_segment(struct kimage *image, + struct kexec_segment *segment) +{ + /* For crash dumps kernels we simply copy the data from + * user space to it's destination. + * We do things a page at a time for the sake of kmap. + */ + unsigned long maddr; + size_t ubytes, mbytes; + int result; + unsigned char __user *buf = NULL; + unsigned char *kbuf = NULL; + + result = 0; + if (image->file_mode) + kbuf = segment->kbuf; + else + buf = segment->buf; + ubytes = segment->bufsz; + mbytes = segment->memsz; + maddr = segment->mem; + while (mbytes) { + struct page *page; + char *ptr; + size_t uchunk, mchunk; + + page = pfn_to_page(maddr >> PAGE_SHIFT); + if (!page) { + result = -ENOMEM; + goto out; + } + ptr = kmap(page); + ptr += maddr & ~PAGE_MASK; + mchunk = min_t(size_t, mbytes, + PAGE_SIZE - (maddr & ~PAGE_MASK)); + uchunk = min(ubytes, mchunk); + if (mchunk > uchunk) { + /* Zero the trailing part of the page */ + memset(ptr + uchunk, 0, mchunk - uchunk); + } + + /* For file based kexec, source pages are in kernel memory */ + if (image->file_mode) + memcpy(ptr, kbuf, uchunk); + else + result = copy_from_user(ptr, buf, uchunk); + kexec_flush_icache_page(page); + kunmap(page); + if (result) { + result = -EFAULT; + goto out; + } + ubytes -= uchunk; + maddr += mchunk; + if (image->file_mode) + kbuf += mchunk; + else + buf += mchunk; + mbytes -= mchunk; + } +out: + return result; +} + +static int kimage_load_segment(struct kimage *image, + struct kexec_segment *segment) +{ + int result = -ENOMEM; + + switch (image->type) { + case KEXEC_TYPE_DEFAULT: + result = kimage_load_normal_segment(image, segment); + break; + case KEXEC_TYPE_CRASH: + result = kimage_load_crash_segment(image, segment); + break; + } + + return result; +} + +/* + * Exec Kernel system call: for obvious reasons only root may call it. + * + * This call breaks up into three pieces. + * - A generic part which loads the new kernel from the current + * address space, and very carefully places the data in the + * allocated pages. + * + * - A generic part that interacts with the kernel and tells all of + * the devices to shut down. Preventing on-going dmas, and placing + * the devices in a consistent state so a later kernel can + * reinitialize them. + * + * - A machine specific part that includes the syscall number + * and then copies the image to it's final destination. And + * jumps into the image at entry. + * + * kexec does not sync, or unmount filesystems so if you need + * that to happen you need to do that yourself. + */ +struct kimage *kexec_image; +struct kimage *kexec_crash_image; +int kexec_load_disabled; + +static DEFINE_MUTEX(kexec_mutex); + +SYSCALL_DEFINE4(kexec_load, unsigned long, entry, unsigned long, nr_segments, + struct kexec_segment __user *, segments, unsigned long, flags) +{ + struct kimage **dest_image, *image; + int result; + + /* We only trust the superuser with rebooting the system. */ + if (!capable(CAP_SYS_BOOT) || kexec_load_disabled) + return -EPERM; + + /* + * Verify we have a legal set of flags + * This leaves us room for future extensions. + */ + if ((flags & KEXEC_FLAGS) != (flags & ~KEXEC_ARCH_MASK)) + return -EINVAL; + + /* Verify we are on the appropriate architecture */ + if (((flags & KEXEC_ARCH_MASK) != KEXEC_ARCH) && + ((flags & KEXEC_ARCH_MASK) != KEXEC_ARCH_DEFAULT)) + return -EINVAL; + + /* Put an artificial cap on the number + * of segments passed to kexec_load. + */ + if (nr_segments > KEXEC_SEGMENT_MAX) + return -EINVAL; + + image = NULL; + result = 0; + + /* Because we write directly to the reserved memory + * region when loading crash kernels we need a mutex here to + * prevent multiple crash kernels from attempting to load + * simultaneously, and to prevent a crash kernel from loading + * over the top of a in use crash kernel. + * + * KISS: always take the mutex. + */ + if (!mutex_trylock(&kexec_mutex)) + return -EBUSY; + + dest_image = &kexec_image; + if (flags & KEXEC_ON_CRASH) + dest_image = &kexec_crash_image; + if (nr_segments > 0) { + unsigned long i; + + if (flags & KEXEC_ON_CRASH) { + /* + * Loading another kernel to switch to if this one + * crashes. Free any current crash dump kernel before + * we corrupt it. + */ + + kimage_free(xchg(&kexec_crash_image, NULL)); + result = kimage_alloc_init(&image, entry, nr_segments, + segments, flags); + crash_map_reserved_pages(); + } else { + /* Loading another kernel to reboot into. */ + + result = kimage_alloc_init(&image, entry, nr_segments, + segments, flags); + } + if (result) + goto out; + + if (flags & KEXEC_PRESERVE_CONTEXT) + image->preserve_context = 1; + result = machine_kexec_prepare(image); + if (result) + goto out; + + for (i = 0; i < nr_segments; i++) { + result = kimage_load_segment(image, &image->segment[i]); + if (result) + goto out; + } + kimage_terminate(image); + if (flags & KEXEC_ON_CRASH) + crash_unmap_reserved_pages(); + } + /* Install the new kernel, and Uninstall the old */ + image = xchg(dest_image, image); + +out: + mutex_unlock(&kexec_mutex); + kimage_free(image); + + return result; +} + +/* + * Add and remove page tables for crashkernel memory + * + * Provide an empty default implementation here -- architecture + * code may override this + */ +void __weak crash_map_reserved_pages(void) +{} + +void __weak crash_unmap_reserved_pages(void) +{} + +#ifdef CONFIG_COMPAT +COMPAT_SYSCALL_DEFINE4(kexec_load, compat_ulong_t, entry, + compat_ulong_t, nr_segments, + struct compat_kexec_segment __user *, segments, + compat_ulong_t, flags) +{ + struct compat_kexec_segment in; + struct kexec_segment out, __user *ksegments; + unsigned long i, result; + + /* Don't allow clients that don't understand the native + * architecture to do anything. + */ + if ((flags & KEXEC_ARCH_MASK) == KEXEC_ARCH_DEFAULT) + return -EINVAL; + + if (nr_segments > KEXEC_SEGMENT_MAX) + return -EINVAL; + + ksegments = compat_alloc_user_space(nr_segments * sizeof(out)); + for (i = 0; i < nr_segments; i++) { + result = copy_from_user(&in, &segments[i], sizeof(in)); + if (result) + return -EFAULT; + + out.buf = compat_ptr(in.buf); + out.bufsz = in.bufsz; + out.mem = in.mem; + out.memsz = in.memsz; + + result = copy_to_user(&ksegments[i], &out, sizeof(out)); + if (result) + return -EFAULT; + } + + return sys_kexec_load(entry, nr_segments, ksegments, flags); +} +#endif + +#ifdef CONFIG_KEXEC_FILE +SYSCALL_DEFINE5(kexec_file_load, int, kernel_fd, int, initrd_fd, + unsigned long, cmdline_len, const char __user *, cmdline_ptr, + unsigned long, flags) +{ + int ret = 0, i; + struct kimage **dest_image, *image; + + /* We only trust the superuser with rebooting the system. */ + if (!capable(CAP_SYS_BOOT) || kexec_load_disabled) + return -EPERM; + + /* Make sure we have a legal set of flags */ + if (flags != (flags & KEXEC_FILE_FLAGS)) + return -EINVAL; + + image = NULL; + + if (!mutex_trylock(&kexec_mutex)) + return -EBUSY; + + dest_image = &kexec_image; + if (flags & KEXEC_FILE_ON_CRASH) + dest_image = &kexec_crash_image; + + if (flags & KEXEC_FILE_UNLOAD) + goto exchange; + + /* + * In case of crash, new kernel gets loaded in reserved region. It is + * same memory where old crash kernel might be loaded. Free any + * current crash dump kernel before we corrupt it. + */ + if (flags & KEXEC_FILE_ON_CRASH) + kimage_free(xchg(&kexec_crash_image, NULL)); + + ret = kimage_file_alloc_init(&image, kernel_fd, initrd_fd, cmdline_ptr, + cmdline_len, flags); + if (ret) + goto out; + + ret = machine_kexec_prepare(image); + if (ret) + goto out; + + ret = kexec_calculate_store_digests(image); + if (ret) + goto out; + + for (i = 0; i < image->nr_segments; i++) { + struct kexec_segment *ksegment; + + ksegment = &image->segment[i]; + pr_debug("Loading segment %d: buf=0x%p bufsz=0x%zx mem=0x%lx memsz=0x%zx\n", + i, ksegment->buf, ksegment->bufsz, ksegment->mem, + ksegment->memsz); + + ret = kimage_load_segment(image, &image->segment[i]); + if (ret) + goto out; + } + + kimage_terminate(image); + + /* + * Free up any temporary buffers allocated which are not needed + * after image has been loaded + */ + kimage_file_post_load_cleanup(image); +exchange: + image = xchg(dest_image, image); +out: + mutex_unlock(&kexec_mutex); + kimage_free(image); + return ret; +} + +#endif /* CONFIG_KEXEC_FILE */ + +void crash_kexec(struct pt_regs *regs) +{ + /* Take the kexec_mutex here to prevent sys_kexec_load + * running on one cpu from replacing the crash kernel + * we are using after a panic on a different cpu. + * + * If the crash kernel was not located in a fixed area + * of memory the xchg(&kexec_crash_image) would be + * sufficient. But since I reuse the memory... + */ + if (mutex_trylock(&kexec_mutex)) { + if (kexec_crash_image) { + struct pt_regs fixed_regs; + + crash_setup_regs(&fixed_regs, regs); + crash_save_vmcoreinfo(); + machine_crash_shutdown(&fixed_regs); + machine_kexec(kexec_crash_image); + } + mutex_unlock(&kexec_mutex); + } +} + +size_t crash_get_memory_size(void) +{ + size_t size = 0; + mutex_lock(&kexec_mutex); + if (crashk_res.end != crashk_res.start) + size = resource_size(&crashk_res); + mutex_unlock(&kexec_mutex); + return size; +} + +void __weak crash_free_reserved_phys_range(unsigned long begin, + unsigned long end) +{ + unsigned long addr; + + for (addr = begin; addr < end; addr += PAGE_SIZE) + free_reserved_page(pfn_to_page(addr >> PAGE_SHIFT)); +} + +int crash_shrink_memory(unsigned long new_size) +{ + int ret = 0; + unsigned long start, end; + unsigned long old_size; + struct resource *ram_res; + + mutex_lock(&kexec_mutex); + + if (kexec_crash_image) { + ret = -ENOENT; + goto unlock; + } + start = crashk_res.start; + end = crashk_res.end; + old_size = (end == 0) ? 0 : end - start + 1; + if (new_size >= old_size) { + ret = (new_size == old_size) ? 0 : -EINVAL; + goto unlock; + } + + ram_res = kzalloc(sizeof(*ram_res), GFP_KERNEL); + if (!ram_res) { + ret = -ENOMEM; + goto unlock; + } + + start = roundup(start, KEXEC_CRASH_MEM_ALIGN); + end = roundup(start + new_size, KEXEC_CRASH_MEM_ALIGN); + + crash_map_reserved_pages(); + crash_free_reserved_phys_range(end, crashk_res.end); + + if ((start == end) && (crashk_res.parent != NULL)) + release_resource(&crashk_res); + + ram_res->start = end; + ram_res->end = crashk_res.end; + ram_res->flags = IORESOURCE_BUSY | IORESOURCE_MEM; + ram_res->name = "System RAM"; + + crashk_res.end = end - 1; + + insert_resource(&iomem_resource, ram_res); + crash_unmap_reserved_pages(); + +unlock: + mutex_unlock(&kexec_mutex); + return ret; +} + +static u32 *append_elf_note(u32 *buf, char *name, unsigned type, void *data, + size_t data_len) +{ + struct elf_note note; + + note.n_namesz = strlen(name) + 1; + note.n_descsz = data_len; + note.n_type = type; + memcpy(buf, ¬e, sizeof(note)); + buf += (sizeof(note) + 3)/4; + memcpy(buf, name, note.n_namesz); + buf += (note.n_namesz + 3)/4; + memcpy(buf, data, note.n_descsz); + buf += (note.n_descsz + 3)/4; + + return buf; +} + +static void final_note(u32 *buf) +{ + struct elf_note note; + + note.n_namesz = 0; + note.n_descsz = 0; + note.n_type = 0; + memcpy(buf, ¬e, sizeof(note)); +} + +void crash_save_cpu(struct pt_regs *regs, int cpu) +{ + struct elf_prstatus prstatus; + u32 *buf; + + if ((cpu < 0) || (cpu >= nr_cpu_ids)) + return; + + /* Using ELF notes here is opportunistic. + * I need a well defined structure format + * for the data I pass, and I need tags + * on the data to indicate what information I have + * squirrelled away. ELF notes happen to provide + * all of that, so there is no need to invent something new. + */ + buf = (u32 *)per_cpu_ptr(crash_notes, cpu); + if (!buf) + return; + memset(&prstatus, 0, sizeof(prstatus)); + prstatus.pr_pid = current->pid; + elf_core_copy_kernel_regs(&prstatus.pr_reg, regs); + buf = append_elf_note(buf, KEXEC_CORE_NOTE_NAME, NT_PRSTATUS, + &prstatus, sizeof(prstatus)); + final_note(buf); +} + +static int __init crash_notes_memory_init(void) +{ + /* Allocate memory for saving cpu registers. */ + crash_notes = alloc_percpu(note_buf_t); + if (!crash_notes) { + pr_warn("Kexec: Memory allocation for saving cpu register states failed\n"); + return -ENOMEM; + } + return 0; +} +subsys_initcall(crash_notes_memory_init); + + +/* + * parsing the "crashkernel" commandline + * + * this code is intended to be called from architecture specific code + */ + + +/* + * This function parses command lines in the format + * + * crashkernel=ramsize-range:size[,...][@offset] + * + * The function returns 0 on success and -EINVAL on failure. + */ +static int __init parse_crashkernel_mem(char *cmdline, + unsigned long long system_ram, + unsigned long long *crash_size, + unsigned long long *crash_base) +{ + char *cur = cmdline, *tmp; + + /* for each entry of the comma-separated list */ + do { + unsigned long long start, end = ULLONG_MAX, size; + + /* get the start of the range */ + start = memparse(cur, &tmp); + if (cur == tmp) { + pr_warn("crashkernel: Memory value expected\n"); + return -EINVAL; + } + cur = tmp; + if (*cur != '-') { + pr_warn("crashkernel: '-' expected\n"); + return -EINVAL; + } + cur++; + + /* if no ':' is here, than we read the end */ + if (*cur != ':') { + end = memparse(cur, &tmp); + if (cur == tmp) { + pr_warn("crashkernel: Memory value expected\n"); + return -EINVAL; + } + cur = tmp; + if (end <= start) { + pr_warn("crashkernel: end <= start\n"); + return -EINVAL; + } + } + + if (*cur != ':') { + pr_warn("crashkernel: ':' expected\n"); + return -EINVAL; + } + cur++; + + size = memparse(cur, &tmp); + if (cur == tmp) { + pr_warn("Memory value expected\n"); + return -EINVAL; + } + cur = tmp; + if (size >= system_ram) { + pr_warn("crashkernel: invalid size\n"); + return -EINVAL; + } + + /* match ? */ + if (system_ram >= start && system_ram < end) { + *crash_size = size; + break; + } + } while (*cur++ == ','); + + if (*crash_size > 0) { + while (*cur && *cur != ' ' && *cur != '@') + cur++; + if (*cur == '@') { + cur++; + *crash_base = memparse(cur, &tmp); + if (cur == tmp) { + pr_warn("Memory value expected after '@'\n"); + return -EINVAL; + } + } + } + + return 0; +} + +/* + * That function parses "simple" (old) crashkernel command lines like + * + * crashkernel=size[@offset] + * + * It returns 0 on success and -EINVAL on failure. + */ +static int __init parse_crashkernel_simple(char *cmdline, + unsigned long long *crash_size, + unsigned long long *crash_base) +{ + char *cur = cmdline; + + *crash_size = memparse(cmdline, &cur); + if (cmdline == cur) { + pr_warn("crashkernel: memory value expected\n"); + return -EINVAL; + } + + if (*cur == '@') + *crash_base = memparse(cur+1, &cur); + else if (*cur != ' ' && *cur != '\0') { + pr_warn("crashkernel: unrecognized char\n"); + return -EINVAL; + } + + return 0; +} + +#define SUFFIX_HIGH 0 +#define SUFFIX_LOW 1 +#define SUFFIX_NULL 2 +static __initdata char *suffix_tbl[] = { + [SUFFIX_HIGH] = ",high", + [SUFFIX_LOW] = ",low", + [SUFFIX_NULL] = NULL, +}; + +/* + * That function parses "suffix" crashkernel command lines like + * + * crashkernel=size,[high|low] + * + * It returns 0 on success and -EINVAL on failure. + */ +static int __init parse_crashkernel_suffix(char *cmdline, + unsigned long long *crash_size, + const char *suffix) +{ + char *cur = cmdline; + + *crash_size = memparse(cmdline, &cur); + if (cmdline == cur) { + pr_warn("crashkernel: memory value expected\n"); + return -EINVAL; + } + + /* check with suffix */ + if (strncmp(cur, suffix, strlen(suffix))) { + pr_warn("crashkernel: unrecognized char\n"); + return -EINVAL; + } + cur += strlen(suffix); + if (*cur != ' ' && *cur != '\0') { + pr_warn("crashkernel: unrecognized char\n"); + return -EINVAL; + } + + return 0; +} + +static __init char *get_last_crashkernel(char *cmdline, + const char *name, + const char *suffix) +{ + char *p = cmdline, *ck_cmdline = NULL; + + /* find crashkernel and use the last one if there are more */ + p = strstr(p, name); + while (p) { + char *end_p = strchr(p, ' '); + char *q; + + if (!end_p) + end_p = p + strlen(p); + + if (!suffix) { + int i; + + /* skip the one with any known suffix */ + for (i = 0; suffix_tbl[i]; i++) { + q = end_p - strlen(suffix_tbl[i]); + if (!strncmp(q, suffix_tbl[i], + strlen(suffix_tbl[i]))) + goto next; + } + ck_cmdline = p; + } else { + q = end_p - strlen(suffix); + if (!strncmp(q, suffix, strlen(suffix))) + ck_cmdline = p; + } +next: + p = strstr(p+1, name); + } + + if (!ck_cmdline) + return NULL; + + return ck_cmdline; +} + +static int __init __parse_crashkernel(char *cmdline, + unsigned long long system_ram, + unsigned long long *crash_size, + unsigned long long *crash_base, + const char *name, + const char *suffix) +{ + char *first_colon, *first_space; + char *ck_cmdline; + + BUG_ON(!crash_size || !crash_base); + *crash_size = 0; + *crash_base = 0; + + ck_cmdline = get_last_crashkernel(cmdline, name, suffix); + + if (!ck_cmdline) + return -EINVAL; + + ck_cmdline += strlen(name); + + if (suffix) + return parse_crashkernel_suffix(ck_cmdline, crash_size, + suffix); + /* + * if the commandline contains a ':', then that's the extended + * syntax -- if not, it must be the classic syntax + */ + first_colon = strchr(ck_cmdline, ':'); + first_space = strchr(ck_cmdline, ' '); + if (first_colon && (!first_space || first_colon < first_space)) + return parse_crashkernel_mem(ck_cmdline, system_ram, + crash_size, crash_base); + + return parse_crashkernel_simple(ck_cmdline, crash_size, crash_base); +} + +/* + * That function is the entry point for command line parsing and should be + * called from the arch-specific code. + */ +int __init parse_crashkernel(char *cmdline, + unsigned long long system_ram, + unsigned long long *crash_size, + unsigned long long *crash_base) +{ + return __parse_crashkernel(cmdline, system_ram, crash_size, crash_base, + "crashkernel=", NULL); +} + +int __init parse_crashkernel_high(char *cmdline, + unsigned long long system_ram, + unsigned long long *crash_size, + unsigned long long *crash_base) +{ + return __parse_crashkernel(cmdline, system_ram, crash_size, crash_base, + "crashkernel=", suffix_tbl[SUFFIX_HIGH]); +} + +int __init parse_crashkernel_low(char *cmdline, + unsigned long long system_ram, + unsigned long long *crash_size, + unsigned long long *crash_base) +{ + return __parse_crashkernel(cmdline, system_ram, crash_size, crash_base, + "crashkernel=", suffix_tbl[SUFFIX_LOW]); +} + +static void update_vmcoreinfo_note(void) +{ + u32 *buf = vmcoreinfo_note; + + if (!vmcoreinfo_size) + return; + buf = append_elf_note(buf, VMCOREINFO_NOTE_NAME, 0, vmcoreinfo_data, + vmcoreinfo_size); + final_note(buf); +} + +void crash_save_vmcoreinfo(void) +{ + vmcoreinfo_append_str("CRASHTIME=%ld\n", get_seconds()); + update_vmcoreinfo_note(); +} + +void vmcoreinfo_append_str(const char *fmt, ...) +{ + va_list args; + char buf[0x50]; + size_t r; + + va_start(args, fmt); + r = vscnprintf(buf, sizeof(buf), fmt, args); + va_end(args); + + r = min(r, vmcoreinfo_max_size - vmcoreinfo_size); + + memcpy(&vmcoreinfo_data[vmcoreinfo_size], buf, r); + + vmcoreinfo_size += r; +} + +/* + * provide an empty default implementation here -- architecture + * code may override this + */ +void __weak arch_crash_save_vmcoreinfo(void) +{} + +unsigned long __weak paddr_vmcoreinfo_note(void) +{ + return __pa((unsigned long)(char *)&vmcoreinfo_note); +} + +static int __init crash_save_vmcoreinfo_init(void) +{ + VMCOREINFO_OSRELEASE(init_uts_ns.name.release); + VMCOREINFO_PAGESIZE(PAGE_SIZE); + + VMCOREINFO_SYMBOL(init_uts_ns); + VMCOREINFO_SYMBOL(node_online_map); +#ifdef CONFIG_MMU + VMCOREINFO_SYMBOL(swapper_pg_dir); +#endif + VMCOREINFO_SYMBOL(_stext); + VMCOREINFO_SYMBOL(vmap_area_list); + +#ifndef CONFIG_NEED_MULTIPLE_NODES + VMCOREINFO_SYMBOL(mem_map); + VMCOREINFO_SYMBOL(contig_page_data); +#endif +#ifdef CONFIG_SPARSEMEM + VMCOREINFO_SYMBOL(mem_section); + VMCOREINFO_LENGTH(mem_section, NR_SECTION_ROOTS); + VMCOREINFO_STRUCT_SIZE(mem_section); + VMCOREINFO_OFFSET(mem_section, section_mem_map); +#endif + VMCOREINFO_STRUCT_SIZE(page); + VMCOREINFO_STRUCT_SIZE(pglist_data); + VMCOREINFO_STRUCT_SIZE(zone); + VMCOREINFO_STRUCT_SIZE(free_area); + VMCOREINFO_STRUCT_SIZE(list_head); + VMCOREINFO_SIZE(nodemask_t); + VMCOREINFO_OFFSET(page, flags); + VMCOREINFO_OFFSET(page, _count); + VMCOREINFO_OFFSET(page, mapping); + VMCOREINFO_OFFSET(page, lru); + VMCOREINFO_OFFSET(page, _mapcount); + VMCOREINFO_OFFSET(page, private); + VMCOREINFO_OFFSET(pglist_data, node_zones); + VMCOREINFO_OFFSET(pglist_data, nr_zones); +#ifdef CONFIG_FLAT_NODE_MEM_MAP + VMCOREINFO_OFFSET(pglist_data, node_mem_map); +#endif + VMCOREINFO_OFFSET(pglist_data, node_start_pfn); + VMCOREINFO_OFFSET(pglist_data, node_spanned_pages); + VMCOREINFO_OFFSET(pglist_data, node_id); + VMCOREINFO_OFFSET(zone, free_area); + VMCOREINFO_OFFSET(zone, vm_stat); + VMCOREINFO_OFFSET(zone, spanned_pages); + VMCOREINFO_OFFSET(free_area, free_list); + VMCOREINFO_OFFSET(list_head, next); + VMCOREINFO_OFFSET(list_head, prev); + VMCOREINFO_OFFSET(vmap_area, va_start); + VMCOREINFO_OFFSET(vmap_area, list); + VMCOREINFO_LENGTH(zone.free_area, MAX_ORDER); + log_buf_kexec_setup(); + VMCOREINFO_LENGTH(free_area.free_list, MIGRATE_TYPES); + VMCOREINFO_NUMBER(NR_FREE_PAGES); + VMCOREINFO_NUMBER(PG_lru); + VMCOREINFO_NUMBER(PG_private); + VMCOREINFO_NUMBER(PG_swapcache); + VMCOREINFO_NUMBER(PG_slab); +#ifdef CONFIG_MEMORY_FAILURE + VMCOREINFO_NUMBER(PG_hwpoison); +#endif + VMCOREINFO_NUMBER(PG_head_mask); + VMCOREINFO_NUMBER(PAGE_BUDDY_MAPCOUNT_VALUE); +#ifdef CONFIG_HUGETLBFS + VMCOREINFO_SYMBOL(free_huge_page); +#endif + + arch_crash_save_vmcoreinfo(); + update_vmcoreinfo_note(); + + return 0; +} + +subsys_initcall(crash_save_vmcoreinfo_init); + +#ifdef CONFIG_KEXEC_FILE +static int locate_mem_hole_top_down(unsigned long start, unsigned long end, + struct kexec_buf *kbuf) +{ + struct kimage *image = kbuf->image; + unsigned long temp_start, temp_end; + + temp_end = min(end, kbuf->buf_max); + temp_start = temp_end - kbuf->memsz; + + do { + /* align down start */ + temp_start = temp_start & (~(kbuf->buf_align - 1)); + + if (temp_start < start || temp_start < kbuf->buf_min) + return 0; + + temp_end = temp_start + kbuf->memsz - 1; + + /* + * Make sure this does not conflict with any of existing + * segments + */ + if (kimage_is_destination_range(image, temp_start, temp_end)) { + temp_start = temp_start - PAGE_SIZE; + continue; + } + + /* We found a suitable memory range */ + break; + } while (1); + + /* If we are here, we found a suitable memory range */ + kbuf->mem = temp_start; + + /* Success, stop navigating through remaining System RAM ranges */ + return 1; +} + +static int locate_mem_hole_bottom_up(unsigned long start, unsigned long end, + struct kexec_buf *kbuf) +{ + struct kimage *image = kbuf->image; + unsigned long temp_start, temp_end; + + temp_start = max(start, kbuf->buf_min); + + do { + temp_start = ALIGN(temp_start, kbuf->buf_align); + temp_end = temp_start + kbuf->memsz - 1; + + if (temp_end > end || temp_end > kbuf->buf_max) + return 0; + /* + * Make sure this does not conflict with any of existing + * segments + */ + if (kimage_is_destination_range(image, temp_start, temp_end)) { + temp_start = temp_start + PAGE_SIZE; + continue; + } + + /* We found a suitable memory range */ + break; + } while (1); + + /* If we are here, we found a suitable memory range */ + kbuf->mem = temp_start; + + /* Success, stop navigating through remaining System RAM ranges */ + return 1; +} + +static int locate_mem_hole_callback(u64 start, u64 end, void *arg) +{ + struct kexec_buf *kbuf = (struct kexec_buf *)arg; + unsigned long sz = end - start + 1; + + /* Returning 0 will take to next memory range */ + if (sz < kbuf->memsz) + return 0; + + if (end < kbuf->buf_min || start > kbuf->buf_max) + return 0; + + /* + * Allocate memory top down with-in ram range. Otherwise bottom up + * allocation. + */ + if (kbuf->top_down) + return locate_mem_hole_top_down(start, end, kbuf); + return locate_mem_hole_bottom_up(start, end, kbuf); +} + +/* + * Helper function for placing a buffer in a kexec segment. This assumes + * that kexec_mutex is held. + */ +int kexec_add_buffer(struct kimage *image, char *buffer, unsigned long bufsz, + unsigned long memsz, unsigned long buf_align, + unsigned long buf_min, unsigned long buf_max, + bool top_down, unsigned long *load_addr) +{ + + struct kexec_segment *ksegment; + struct kexec_buf buf, *kbuf; + int ret; + + /* Currently adding segment this way is allowed only in file mode */ + if (!image->file_mode) + return -EINVAL; + + if (image->nr_segments >= KEXEC_SEGMENT_MAX) + return -EINVAL; + + /* + * Make sure we are not trying to add buffer after allocating + * control pages. All segments need to be placed first before + * any control pages are allocated. As control page allocation + * logic goes through list of segments to make sure there are + * no destination overlaps. + */ + if (!list_empty(&image->control_pages)) { + WARN_ON(1); + return -EINVAL; + } + + memset(&buf, 0, sizeof(struct kexec_buf)); + kbuf = &buf; + kbuf->image = image; + kbuf->buffer = buffer; + kbuf->bufsz = bufsz; + + kbuf->memsz = ALIGN(memsz, PAGE_SIZE); + kbuf->buf_align = max(buf_align, PAGE_SIZE); + kbuf->buf_min = buf_min; + kbuf->buf_max = buf_max; + kbuf->top_down = top_down; + + /* Walk the RAM ranges and allocate a suitable range for the buffer */ + if (image->type == KEXEC_TYPE_CRASH) + ret = walk_iomem_res("Crash kernel", + IORESOURCE_MEM | IORESOURCE_BUSY, + crashk_res.start, crashk_res.end, kbuf, + locate_mem_hole_callback); + else + ret = walk_system_ram_res(0, -1, kbuf, + locate_mem_hole_callback); + if (ret != 1) { + /* A suitable memory range could not be found for buffer */ + return -EADDRNOTAVAIL; + } + + /* Found a suitable memory range */ + ksegment = &image->segment[image->nr_segments]; + ksegment->kbuf = kbuf->buffer; + ksegment->bufsz = kbuf->bufsz; + ksegment->mem = kbuf->mem; + ksegment->memsz = kbuf->memsz; + image->nr_segments++; + *load_addr = ksegment->mem; + return 0; +} + +/* Calculate and store the digest of segments */ +static int kexec_calculate_store_digests(struct kimage *image) +{ + struct crypto_shash *tfm; + struct shash_desc *desc; + int ret = 0, i, j, zero_buf_sz, sha_region_sz; + size_t desc_size, nullsz; + char *digest; + void *zero_buf; + struct kexec_sha_region *sha_regions; + struct purgatory_info *pi = &image->purgatory_info; + + zero_buf = __va(page_to_pfn(ZERO_PAGE(0)) << PAGE_SHIFT); + zero_buf_sz = PAGE_SIZE; + + tfm = crypto_alloc_shash("sha256", 0, 0); + if (IS_ERR(tfm)) { + ret = PTR_ERR(tfm); + goto out; + } + + desc_size = crypto_shash_descsize(tfm) + sizeof(*desc); + desc = kzalloc(desc_size, GFP_KERNEL); + if (!desc) { + ret = -ENOMEM; + goto out_free_tfm; + } + + sha_region_sz = KEXEC_SEGMENT_MAX * sizeof(struct kexec_sha_region); + sha_regions = vzalloc(sha_region_sz); + if (!sha_regions) + goto out_free_desc; + + desc->tfm = tfm; + desc->flags = 0; + + ret = crypto_shash_init(desc); + if (ret < 0) + goto out_free_sha_regions; + + digest = kzalloc(SHA256_DIGEST_SIZE, GFP_KERNEL); + if (!digest) { + ret = -ENOMEM; + goto out_free_sha_regions; + } + + for (j = i = 0; i < image->nr_segments; i++) { + struct kexec_segment *ksegment; + + ksegment = &image->segment[i]; + /* + * Skip purgatory as it will be modified once we put digest + * info in purgatory. + */ + if (ksegment->kbuf == pi->purgatory_buf) + continue; + + ret = crypto_shash_update(desc, ksegment->kbuf, + ksegment->bufsz); + if (ret) + break; + + /* + * Assume rest of the buffer is filled with zero and + * update digest accordingly. + */ + nullsz = ksegment->memsz - ksegment->bufsz; + while (nullsz) { + unsigned long bytes = nullsz; + + if (bytes > zero_buf_sz) + bytes = zero_buf_sz; + ret = crypto_shash_update(desc, zero_buf, bytes); + if (ret) + break; + nullsz -= bytes; + } + + if (ret) + break; + + sha_regions[j].start = ksegment->mem; + sha_regions[j].len = ksegment->memsz; + j++; + } + + if (!ret) { + ret = crypto_shash_final(desc, digest); + if (ret) + goto out_free_digest; + ret = kexec_purgatory_get_set_symbol(image, "sha_regions", + sha_regions, sha_region_sz, 0); + if (ret) + goto out_free_digest; + + ret = kexec_purgatory_get_set_symbol(image, "sha256_digest", + digest, SHA256_DIGEST_SIZE, 0); + if (ret) + goto out_free_digest; + } + +out_free_digest: + kfree(digest); +out_free_sha_regions: + vfree(sha_regions); +out_free_desc: + kfree(desc); +out_free_tfm: + kfree(tfm); +out: + return ret; +} + +/* Actually load purgatory. Lot of code taken from kexec-tools */ +static int __kexec_load_purgatory(struct kimage *image, unsigned long min, + unsigned long max, int top_down) +{ + struct purgatory_info *pi = &image->purgatory_info; + unsigned long align, buf_align, bss_align, buf_sz, bss_sz, bss_pad; + unsigned long memsz, entry, load_addr, curr_load_addr, bss_addr, offset; + unsigned char *buf_addr, *src; + int i, ret = 0, entry_sidx = -1; + const Elf_Shdr *sechdrs_c; + Elf_Shdr *sechdrs = NULL; + void *purgatory_buf = NULL; + + /* + * sechdrs_c points to section headers in purgatory and are read + * only. No modifications allowed. + */ + sechdrs_c = (void *)pi->ehdr + pi->ehdr->e_shoff; + + /* + * We can not modify sechdrs_c[] and its fields. It is read only. + * Copy it over to a local copy where one can store some temporary + * data and free it at the end. We need to modify ->sh_addr and + * ->sh_offset fields to keep track of permanent and temporary + * locations of sections. + */ + sechdrs = vzalloc(pi->ehdr->e_shnum * sizeof(Elf_Shdr)); + if (!sechdrs) + return -ENOMEM; + + memcpy(sechdrs, sechdrs_c, pi->ehdr->e_shnum * sizeof(Elf_Shdr)); + + /* + * We seem to have multiple copies of sections. First copy is which + * is embedded in kernel in read only section. Some of these sections + * will be copied to a temporary buffer and relocated. And these + * sections will finally be copied to their final destination at + * segment load time. + * + * Use ->sh_offset to reflect section address in memory. It will + * point to original read only copy if section is not allocatable. + * Otherwise it will point to temporary copy which will be relocated. + * + * Use ->sh_addr to contain final address of the section where it + * will go during execution time. + */ + for (i = 0; i < pi->ehdr->e_shnum; i++) { + if (sechdrs[i].sh_type == SHT_NOBITS) + continue; + + sechdrs[i].sh_offset = (unsigned long)pi->ehdr + + sechdrs[i].sh_offset; + } + + /* + * Identify entry point section and make entry relative to section + * start. + */ + entry = pi->ehdr->e_entry; + for (i = 0; i < pi->ehdr->e_shnum; i++) { + if (!(sechdrs[i].sh_flags & SHF_ALLOC)) + continue; + + if (!(sechdrs[i].sh_flags & SHF_EXECINSTR)) + continue; + + /* Make entry section relative */ + if (sechdrs[i].sh_addr <= pi->ehdr->e_entry && + ((sechdrs[i].sh_addr + sechdrs[i].sh_size) > + pi->ehdr->e_entry)) { + entry_sidx = i; + entry -= sechdrs[i].sh_addr; + break; + } + } + + /* Determine how much memory is needed to load relocatable object. */ + buf_align = 1; + bss_align = 1; + buf_sz = 0; + bss_sz = 0; + + for (i = 0; i < pi->ehdr->e_shnum; i++) { + if (!(sechdrs[i].sh_flags & SHF_ALLOC)) + continue; + + align = sechdrs[i].sh_addralign; + if (sechdrs[i].sh_type != SHT_NOBITS) { + if (buf_align < align) + buf_align = align; + buf_sz = ALIGN(buf_sz, align); + buf_sz += sechdrs[i].sh_size; + } else { + /* bss section */ + if (bss_align < align) + bss_align = align; + bss_sz = ALIGN(bss_sz, align); + bss_sz += sechdrs[i].sh_size; + } + } + + /* Determine the bss padding required to align bss properly */ + bss_pad = 0; + if (buf_sz & (bss_align - 1)) + bss_pad = bss_align - (buf_sz & (bss_align - 1)); + + memsz = buf_sz + bss_pad + bss_sz; + + /* Allocate buffer for purgatory */ + purgatory_buf = vzalloc(buf_sz); + if (!purgatory_buf) { + ret = -ENOMEM; + goto out; + } + + if (buf_align < bss_align) + buf_align = bss_align; + + /* Add buffer to segment list */ + ret = kexec_add_buffer(image, purgatory_buf, buf_sz, memsz, + buf_align, min, max, top_down, + &pi->purgatory_load_addr); + if (ret) + goto out; + + /* Load SHF_ALLOC sections */ + buf_addr = purgatory_buf; + load_addr = curr_load_addr = pi->purgatory_load_addr; + bss_addr = load_addr + buf_sz + bss_pad; + + for (i = 0; i < pi->ehdr->e_shnum; i++) { + if (!(sechdrs[i].sh_flags & SHF_ALLOC)) + continue; + + align = sechdrs[i].sh_addralign; + if (sechdrs[i].sh_type != SHT_NOBITS) { + curr_load_addr = ALIGN(curr_load_addr, align); + offset = curr_load_addr - load_addr; + /* We already modifed ->sh_offset to keep src addr */ + src = (char *) sechdrs[i].sh_offset; + memcpy(buf_addr + offset, src, sechdrs[i].sh_size); + + /* Store load address and source address of section */ + sechdrs[i].sh_addr = curr_load_addr; + + /* + * This section got copied to temporary buffer. Update + * ->sh_offset accordingly. + */ + sechdrs[i].sh_offset = (unsigned long)(buf_addr + offset); + + /* Advance to the next address */ + curr_load_addr += sechdrs[i].sh_size; + } else { + bss_addr = ALIGN(bss_addr, align); + sechdrs[i].sh_addr = bss_addr; + bss_addr += sechdrs[i].sh_size; + } + } + + /* Update entry point based on load address of text section */ + if (entry_sidx >= 0) + entry += sechdrs[entry_sidx].sh_addr; + + /* Make kernel jump to purgatory after shutdown */ + image->start = entry; + + /* Used later to get/set symbol values */ + pi->sechdrs = sechdrs; + + /* + * Used later to identify which section is purgatory and skip it + * from checksumming. + */ + pi->purgatory_buf = purgatory_buf; + return ret; +out: + vfree(sechdrs); + vfree(purgatory_buf); + return ret; +} + +static int kexec_apply_relocations(struct kimage *image) +{ + int i, ret; + struct purgatory_info *pi = &image->purgatory_info; + Elf_Shdr *sechdrs = pi->sechdrs; + + /* Apply relocations */ + for (i = 0; i < pi->ehdr->e_shnum; i++) { + Elf_Shdr *section, *symtab; + + if (sechdrs[i].sh_type != SHT_RELA && + sechdrs[i].sh_type != SHT_REL) + continue; + + /* + * For section of type SHT_RELA/SHT_REL, + * ->sh_link contains section header index of associated + * symbol table. And ->sh_info contains section header + * index of section to which relocations apply. + */ + if (sechdrs[i].sh_info >= pi->ehdr->e_shnum || + sechdrs[i].sh_link >= pi->ehdr->e_shnum) + return -ENOEXEC; + + section = &sechdrs[sechdrs[i].sh_info]; + symtab = &sechdrs[sechdrs[i].sh_link]; + + if (!(section->sh_flags & SHF_ALLOC)) + continue; + + /* + * symtab->sh_link contain section header index of associated + * string table. + */ + if (symtab->sh_link >= pi->ehdr->e_shnum) + /* Invalid section number? */ + continue; + + /* + * Respective architecture needs to provide support for applying + * relocations of type SHT_RELA/SHT_REL. + */ + if (sechdrs[i].sh_type == SHT_RELA) + ret = arch_kexec_apply_relocations_add(pi->ehdr, + sechdrs, i); + else if (sechdrs[i].sh_type == SHT_REL) + ret = arch_kexec_apply_relocations(pi->ehdr, + sechdrs, i); + if (ret) + return ret; + } + + return 0; +} + +/* Load relocatable purgatory object and relocate it appropriately */ +int kexec_load_purgatory(struct kimage *image, unsigned long min, + unsigned long max, int top_down, + unsigned long *load_addr) +{ + struct purgatory_info *pi = &image->purgatory_info; + int ret; + + if (kexec_purgatory_size <= 0) + return -EINVAL; + + if (kexec_purgatory_size < sizeof(Elf_Ehdr)) + return -ENOEXEC; + + pi->ehdr = (Elf_Ehdr *)kexec_purgatory; + + if (memcmp(pi->ehdr->e_ident, ELFMAG, SELFMAG) != 0 + || pi->ehdr->e_type != ET_REL + || !elf_check_arch(pi->ehdr) + || pi->ehdr->e_shentsize != sizeof(Elf_Shdr)) + return -ENOEXEC; + + if (pi->ehdr->e_shoff >= kexec_purgatory_size + || (pi->ehdr->e_shnum * sizeof(Elf_Shdr) > + kexec_purgatory_size - pi->ehdr->e_shoff)) + return -ENOEXEC; + + ret = __kexec_load_purgatory(image, min, max, top_down); + if (ret) + return ret; + + ret = kexec_apply_relocations(image); + if (ret) + goto out; + + *load_addr = pi->purgatory_load_addr; + return 0; +out: + vfree(pi->sechdrs); + vfree(pi->purgatory_buf); + return ret; +} + +static Elf_Sym *kexec_purgatory_find_symbol(struct purgatory_info *pi, + const char *name) +{ + Elf_Sym *syms; + Elf_Shdr *sechdrs; + Elf_Ehdr *ehdr; + int i, k; + const char *strtab; + + if (!pi->sechdrs || !pi->ehdr) + return NULL; + + sechdrs = pi->sechdrs; + ehdr = pi->ehdr; + + for (i = 0; i < ehdr->e_shnum; i++) { + if (sechdrs[i].sh_type != SHT_SYMTAB) + continue; + + if (sechdrs[i].sh_link >= ehdr->e_shnum) + /* Invalid strtab section number */ + continue; + strtab = (char *)sechdrs[sechdrs[i].sh_link].sh_offset; + syms = (Elf_Sym *)sechdrs[i].sh_offset; + + /* Go through symbols for a match */ + for (k = 0; k < sechdrs[i].sh_size/sizeof(Elf_Sym); k++) { + if (ELF_ST_BIND(syms[k].st_info) != STB_GLOBAL) + continue; + + if (strcmp(strtab + syms[k].st_name, name) != 0) + continue; + + if (syms[k].st_shndx == SHN_UNDEF || + syms[k].st_shndx >= ehdr->e_shnum) { + pr_debug("Symbol: %s has bad section index %d.\n", + name, syms[k].st_shndx); + return NULL; + } + + /* Found the symbol we are looking for */ + return &syms[k]; + } + } + + return NULL; +} + +void *kexec_purgatory_get_symbol_addr(struct kimage *image, const char *name) +{ + struct purgatory_info *pi = &image->purgatory_info; + Elf_Sym *sym; + Elf_Shdr *sechdr; + + sym = kexec_purgatory_find_symbol(pi, name); + if (!sym) + return ERR_PTR(-EINVAL); + + sechdr = &pi->sechdrs[sym->st_shndx]; + + /* + * Returns the address where symbol will finally be loaded after + * kexec_load_segment() + */ + return (void *)(sechdr->sh_addr + sym->st_value); +} + +/* + * Get or set value of a symbol. If "get_value" is true, symbol value is + * returned in buf otherwise symbol value is set based on value in buf. + */ +int kexec_purgatory_get_set_symbol(struct kimage *image, const char *name, + void *buf, unsigned int size, bool get_value) +{ + Elf_Sym *sym; + Elf_Shdr *sechdrs; + struct purgatory_info *pi = &image->purgatory_info; + char *sym_buf; + + sym = kexec_purgatory_find_symbol(pi, name); + if (!sym) + return -EINVAL; + + if (sym->st_size != size) { + pr_err("symbol %s size mismatch: expected %lu actual %u\n", + name, (unsigned long)sym->st_size, size); + return -EINVAL; + } + + sechdrs = pi->sechdrs; + + if (sechdrs[sym->st_shndx].sh_type == SHT_NOBITS) { + pr_err("symbol %s is in a bss section. Cannot %s\n", name, + get_value ? "get" : "set"); + return -EINVAL; + } + + sym_buf = (unsigned char *)sechdrs[sym->st_shndx].sh_offset + + sym->st_value; + + if (get_value) + memcpy((void *)buf, sym_buf, size); + else + memcpy((void *)sym_buf, buf, size); + + return 0; +} +#endif /* CONFIG_KEXEC_FILE */ + +/* + * Move into place and start executing a preloaded standalone + * executable. If nothing was preloaded return an error. + */ +int kernel_kexec(void) +{ + int error = 0; + + if (!mutex_trylock(&kexec_mutex)) + return -EBUSY; + if (!kexec_image) { + error = -EINVAL; + goto Unlock; + } + +#ifdef CONFIG_KEXEC_JUMP + if (kexec_image->preserve_context) { + lock_system_sleep(); + pm_prepare_console(); + error = freeze_processes(); + if (error) { + error = -EBUSY; + goto Restore_console; + } + suspend_console(); + error = dpm_suspend_start(PMSG_FREEZE); + if (error) + goto Resume_console; + /* At this point, dpm_suspend_start() has been called, + * but *not* dpm_suspend_end(). We *must* call + * dpm_suspend_end() now. Otherwise, drivers for + * some devices (e.g. interrupt controllers) become + * desynchronized with the actual state of the + * hardware at resume time, and evil weirdness ensues. + */ + error = dpm_suspend_end(PMSG_FREEZE); + if (error) + goto Resume_devices; + error = disable_nonboot_cpus(); + if (error) + goto Enable_cpus; + local_irq_disable(); + error = syscore_suspend(); + if (error) + goto Enable_irqs; + } else +#endif + { + kexec_in_progress = true; + kernel_restart_prepare(NULL); + migrate_to_reboot_cpu(); + + /* + * migrate_to_reboot_cpu() disables CPU hotplug assuming that + * no further code needs to use CPU hotplug (which is true in + * the reboot case). However, the kexec path depends on using + * CPU hotplug again; so re-enable it here. + */ + cpu_hotplug_enable(); + pr_emerg("Starting new kernel\n"); + machine_shutdown(); + } + + machine_kexec(kexec_image); + +#ifdef CONFIG_KEXEC_JUMP + if (kexec_image->preserve_context) { + syscore_resume(); + Enable_irqs: + local_irq_enable(); + Enable_cpus: + enable_nonboot_cpus(); + dpm_resume_start(PMSG_RESTORE); + Resume_devices: + dpm_resume_end(PMSG_RESTORE); + Resume_console: + resume_console(); + thaw_processes(); + Restore_console: + pm_restore_console(); + unlock_system_sleep(); + } +#endif + + Unlock: + mutex_unlock(&kexec_mutex); + return error; +} diff --git a/kernel/kernel/kmod.c b/kernel/kernel/kmod.c new file mode 100644 index 000000000..2777f40a9 --- /dev/null +++ b/kernel/kernel/kmod.c @@ -0,0 +1,694 @@ +/* + kmod, the new module loader (replaces kerneld) + Kirk Petersen + + Reorganized not to be a daemon by Adam Richter, with guidance + from Greg Zornetzer. + + Modified to avoid chroot and file sharing problems. + Mikael Pettersson + + Limit the concurrent number of kmod modprobes to catch loops from + "modprobe needs a service that is in a module". + Keith Owens December 1999 + + Unblock all signals when we exec a usermode process. + Shuu Yamaguchi December 2000 + + call_usermodehelper wait flag, and remove exec_usermodehelper. + Rusty Russell Jan 2003 +*/ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +extern int max_threads; + +static struct workqueue_struct *khelper_wq; + +#define CAP_BSET (void *)1 +#define CAP_PI (void *)2 + +static kernel_cap_t usermodehelper_bset = CAP_FULL_SET; +static kernel_cap_t usermodehelper_inheritable = CAP_FULL_SET; +static DEFINE_SPINLOCK(umh_sysctl_lock); +static DECLARE_RWSEM(umhelper_sem); + +#ifdef CONFIG_MODULES + +/* + modprobe_path is set via /proc/sys. +*/ +char modprobe_path[KMOD_PATH_LEN] = "/sbin/modprobe"; + +static void free_modprobe_argv(struct subprocess_info *info) +{ + kfree(info->argv[3]); /* check call_modprobe() */ + kfree(info->argv); +} + +static int call_modprobe(char *module_name, int wait) +{ + struct subprocess_info *info; + static char *envp[] = { + "HOME=/", + "TERM=linux", + "PATH=/sbin:/usr/sbin:/bin:/usr/bin", + NULL + }; + + char **argv = kmalloc(sizeof(char *[5]), GFP_KERNEL); + if (!argv) + goto out; + + module_name = kstrdup(module_name, GFP_KERNEL); + if (!module_name) + goto free_argv; + + argv[0] = modprobe_path; + argv[1] = "-q"; + argv[2] = "--"; + argv[3] = module_name; /* check free_modprobe_argv() */ + argv[4] = NULL; + + info = call_usermodehelper_setup(modprobe_path, argv, envp, GFP_KERNEL, + NULL, free_modprobe_argv, NULL); + if (!info) + goto free_module_name; + + return call_usermodehelper_exec(info, wait | UMH_KILLABLE); + +free_module_name: + kfree(module_name); +free_argv: + kfree(argv); +out: + return -ENOMEM; +} + +/** + * __request_module - try to load a kernel module + * @wait: wait (or not) for the operation to complete + * @fmt: printf style format string for the name of the module + * @...: arguments as specified in the format string + * + * Load a module using the user mode module loader. The function returns + * zero on success or a negative errno code on failure. Note that a + * successful module load does not mean the module did not then unload + * and exit on an error of its own. Callers must check that the service + * they requested is now available not blindly invoke it. + * + * If module auto-loading support is disabled then this function + * becomes a no-operation. + */ +int __request_module(bool wait, const char *fmt, ...) +{ + va_list args; + char module_name[MODULE_NAME_LEN]; + unsigned int max_modprobes; + int ret; + static atomic_t kmod_concurrent = ATOMIC_INIT(0); +#define MAX_KMOD_CONCURRENT 50 /* Completely arbitrary value - KAO */ + static int kmod_loop_msg; + + /* + * We don't allow synchronous module loading from async. Module + * init may invoke async_synchronize_full() which will end up + * waiting for this task which already is waiting for the module + * loading to complete, leading to a deadlock. + */ + WARN_ON_ONCE(wait && current_is_async()); + + if (!modprobe_path[0]) + return 0; + + va_start(args, fmt); + ret = vsnprintf(module_name, MODULE_NAME_LEN, fmt, args); + va_end(args); + if (ret >= MODULE_NAME_LEN) + return -ENAMETOOLONG; + + ret = security_kernel_module_request(module_name); + if (ret) + return ret; + + /* If modprobe needs a service that is in a module, we get a recursive + * loop. Limit the number of running kmod threads to max_threads/2 or + * MAX_KMOD_CONCURRENT, whichever is the smaller. A cleaner method + * would be to run the parents of this process, counting how many times + * kmod was invoked. That would mean accessing the internals of the + * process tables to get the command line, proc_pid_cmdline is static + * and it is not worth changing the proc code just to handle this case. + * KAO. + * + * "trace the ppid" is simple, but will fail if someone's + * parent exits. I think this is as good as it gets. --RR + */ + max_modprobes = min(max_threads/2, MAX_KMOD_CONCURRENT); + atomic_inc(&kmod_concurrent); + if (atomic_read(&kmod_concurrent) > max_modprobes) { + /* We may be blaming an innocent here, but unlikely */ + if (kmod_loop_msg < 5) { + printk(KERN_ERR + "request_module: runaway loop modprobe %s\n", + module_name); + kmod_loop_msg++; + } + atomic_dec(&kmod_concurrent); + return -ENOMEM; + } + + trace_module_request(module_name, wait, _RET_IP_); + + ret = call_modprobe(module_name, wait ? UMH_WAIT_PROC : UMH_WAIT_EXEC); + + atomic_dec(&kmod_concurrent); + return ret; +} +EXPORT_SYMBOL(__request_module); +#endif /* CONFIG_MODULES */ + +static void call_usermodehelper_freeinfo(struct subprocess_info *info) +{ + if (info->cleanup) + (*info->cleanup)(info); + kfree(info); +} + +static void umh_complete(struct subprocess_info *sub_info) +{ + struct completion *comp = xchg(&sub_info->complete, NULL); + /* + * See call_usermodehelper_exec(). If xchg() returns NULL + * we own sub_info, the UMH_KILLABLE caller has gone away + * or the caller used UMH_NO_WAIT. + */ + if (comp) + complete(comp); + else + call_usermodehelper_freeinfo(sub_info); +} + +/* + * This is the task which runs the usermode application + */ +static int ____call_usermodehelper(void *data) +{ + struct subprocess_info *sub_info = data; + struct cred *new; + int retval; + + spin_lock_irq(¤t->sighand->siglock); + flush_signal_handlers(current, 1); + spin_unlock_irq(¤t->sighand->siglock); + + /* We can run anywhere, unlike our parent keventd(). */ + set_cpus_allowed_ptr(current, cpu_all_mask); + + /* + * Our parent is keventd, which runs with elevated scheduling priority. + * Avoid propagating that into the userspace child. + */ + set_user_nice(current, 0); + + retval = -ENOMEM; + new = prepare_kernel_cred(current); + if (!new) + goto out; + + spin_lock(&umh_sysctl_lock); + new->cap_bset = cap_intersect(usermodehelper_bset, new->cap_bset); + new->cap_inheritable = cap_intersect(usermodehelper_inheritable, + new->cap_inheritable); + spin_unlock(&umh_sysctl_lock); + + if (sub_info->init) { + retval = sub_info->init(sub_info, new); + if (retval) { + abort_creds(new); + goto out; + } + } + + commit_creds(new); + + retval = do_execve(getname_kernel(sub_info->path), + (const char __user *const __user *)sub_info->argv, + (const char __user *const __user *)sub_info->envp); +out: + sub_info->retval = retval; + /* wait_for_helper() will call umh_complete if UHM_WAIT_PROC. */ + if (!(sub_info->wait & UMH_WAIT_PROC)) + umh_complete(sub_info); + if (!retval) + return 0; + do_exit(0); +} + +/* Keventd can't block, but this (a child) can. */ +static int wait_for_helper(void *data) +{ + struct subprocess_info *sub_info = data; + pid_t pid; + + /* If SIGCLD is ignored sys_wait4 won't populate the status. */ + kernel_sigaction(SIGCHLD, SIG_DFL); + pid = kernel_thread(____call_usermodehelper, sub_info, SIGCHLD); + if (pid < 0) { + sub_info->retval = pid; + } else { + int ret = -ECHILD; + /* + * Normally it is bogus to call wait4() from in-kernel because + * wait4() wants to write the exit code to a userspace address. + * But wait_for_helper() always runs as keventd, and put_user() + * to a kernel address works OK for kernel threads, due to their + * having an mm_segment_t which spans the entire address space. + * + * Thus the __user pointer cast is valid here. + */ + sys_wait4(pid, (int __user *)&ret, 0, NULL); + + /* + * If ret is 0, either ____call_usermodehelper failed and the + * real error code is already in sub_info->retval or + * sub_info->retval is 0 anyway, so don't mess with it then. + */ + if (ret) + sub_info->retval = ret; + } + + umh_complete(sub_info); + do_exit(0); +} + +/* This is run by khelper thread */ +static void __call_usermodehelper(struct work_struct *work) +{ + struct subprocess_info *sub_info = + container_of(work, struct subprocess_info, work); + pid_t pid; + + if (sub_info->wait & UMH_WAIT_PROC) + pid = kernel_thread(wait_for_helper, sub_info, + CLONE_FS | CLONE_FILES | SIGCHLD); + else + pid = kernel_thread(____call_usermodehelper, sub_info, + SIGCHLD); + + if (pid < 0) { + sub_info->retval = pid; + umh_complete(sub_info); + } +} + +/* + * If set, call_usermodehelper_exec() will exit immediately returning -EBUSY + * (used for preventing user land processes from being created after the user + * land has been frozen during a system-wide hibernation or suspend operation). + * Should always be manipulated under umhelper_sem acquired for write. + */ +static enum umh_disable_depth usermodehelper_disabled = UMH_DISABLED; + +/* Number of helpers running */ +static atomic_t running_helpers = ATOMIC_INIT(0); + +/* + * Wait queue head used by usermodehelper_disable() to wait for all running + * helpers to finish. + */ +static DECLARE_WAIT_QUEUE_HEAD(running_helpers_waitq); + +/* + * Used by usermodehelper_read_lock_wait() to wait for usermodehelper_disabled + * to become 'false'. + */ +static DECLARE_WAIT_QUEUE_HEAD(usermodehelper_disabled_waitq); + +/* + * Time to wait for running_helpers to become zero before the setting of + * usermodehelper_disabled in usermodehelper_disable() fails + */ +#define RUNNING_HELPERS_TIMEOUT (5 * HZ) + +int usermodehelper_read_trylock(void) +{ + DEFINE_WAIT(wait); + int ret = 0; + + down_read(&umhelper_sem); + for (;;) { + prepare_to_wait(&usermodehelper_disabled_waitq, &wait, + TASK_INTERRUPTIBLE); + if (!usermodehelper_disabled) + break; + + if (usermodehelper_disabled == UMH_DISABLED) + ret = -EAGAIN; + + up_read(&umhelper_sem); + + if (ret) + break; + + schedule(); + try_to_freeze(); + + down_read(&umhelper_sem); + } + finish_wait(&usermodehelper_disabled_waitq, &wait); + return ret; +} +EXPORT_SYMBOL_GPL(usermodehelper_read_trylock); + +long usermodehelper_read_lock_wait(long timeout) +{ + DEFINE_WAIT(wait); + + if (timeout < 0) + return -EINVAL; + + down_read(&umhelper_sem); + for (;;) { + prepare_to_wait(&usermodehelper_disabled_waitq, &wait, + TASK_UNINTERRUPTIBLE); + if (!usermodehelper_disabled) + break; + + up_read(&umhelper_sem); + + timeout = schedule_timeout(timeout); + if (!timeout) + break; + + down_read(&umhelper_sem); + } + finish_wait(&usermodehelper_disabled_waitq, &wait); + return timeout; +} +EXPORT_SYMBOL_GPL(usermodehelper_read_lock_wait); + +void usermodehelper_read_unlock(void) +{ + up_read(&umhelper_sem); +} +EXPORT_SYMBOL_GPL(usermodehelper_read_unlock); + +/** + * __usermodehelper_set_disable_depth - Modify usermodehelper_disabled. + * @depth: New value to assign to usermodehelper_disabled. + * + * Change the value of usermodehelper_disabled (under umhelper_sem locked for + * writing) and wakeup tasks waiting for it to change. + */ +void __usermodehelper_set_disable_depth(enum umh_disable_depth depth) +{ + down_write(&umhelper_sem); + usermodehelper_disabled = depth; + wake_up(&usermodehelper_disabled_waitq); + up_write(&umhelper_sem); +} + +/** + * __usermodehelper_disable - Prevent new helpers from being started. + * @depth: New value to assign to usermodehelper_disabled. + * + * Set usermodehelper_disabled to @depth and wait for running helpers to exit. + */ +int __usermodehelper_disable(enum umh_disable_depth depth) +{ + long retval; + + if (!depth) + return -EINVAL; + + down_write(&umhelper_sem); + usermodehelper_disabled = depth; + up_write(&umhelper_sem); + + /* + * From now on call_usermodehelper_exec() won't start any new + * helpers, so it is sufficient if running_helpers turns out to + * be zero at one point (it may be increased later, but that + * doesn't matter). + */ + retval = wait_event_timeout(running_helpers_waitq, + atomic_read(&running_helpers) == 0, + RUNNING_HELPERS_TIMEOUT); + if (retval) + return 0; + + __usermodehelper_set_disable_depth(UMH_ENABLED); + return -EAGAIN; +} + +static void helper_lock(void) +{ + atomic_inc(&running_helpers); + smp_mb__after_atomic(); +} + +static void helper_unlock(void) +{ + if (atomic_dec_and_test(&running_helpers)) + wake_up(&running_helpers_waitq); +} + +/** + * call_usermodehelper_setup - prepare to call a usermode helper + * @path: path to usermode executable + * @argv: arg vector for process + * @envp: environment for process + * @gfp_mask: gfp mask for memory allocation + * @cleanup: a cleanup function + * @init: an init function + * @data: arbitrary context sensitive data + * + * Returns either %NULL on allocation failure, or a subprocess_info + * structure. This should be passed to call_usermodehelper_exec to + * exec the process and free the structure. + * + * The init function is used to customize the helper process prior to + * exec. A non-zero return code causes the process to error out, exit, + * and return the failure to the calling process + * + * The cleanup function is just before ethe subprocess_info is about to + * be freed. This can be used for freeing the argv and envp. The + * Function must be runnable in either a process context or the + * context in which call_usermodehelper_exec is called. + */ +struct subprocess_info *call_usermodehelper_setup(char *path, char **argv, + char **envp, gfp_t gfp_mask, + int (*init)(struct subprocess_info *info, struct cred *new), + void (*cleanup)(struct subprocess_info *info), + void *data) +{ + struct subprocess_info *sub_info; + sub_info = kzalloc(sizeof(struct subprocess_info), gfp_mask); + if (!sub_info) + goto out; + + INIT_WORK(&sub_info->work, __call_usermodehelper); + sub_info->path = path; + sub_info->argv = argv; + sub_info->envp = envp; + + sub_info->cleanup = cleanup; + sub_info->init = init; + sub_info->data = data; + out: + return sub_info; +} +EXPORT_SYMBOL(call_usermodehelper_setup); + +/** + * call_usermodehelper_exec - start a usermode application + * @sub_info: information about the subprocessa + * @wait: wait for the application to finish and return status. + * when UMH_NO_WAIT don't wait at all, but you get no useful error back + * when the program couldn't be exec'ed. This makes it safe to call + * from interrupt context. + * + * Runs a user-space application. The application is started + * asynchronously if wait is not set, and runs as a child of keventd. + * (ie. it runs with full root capabilities). + */ +int call_usermodehelper_exec(struct subprocess_info *sub_info, int wait) +{ + DECLARE_COMPLETION_ONSTACK(done); + int retval = 0; + + if (!sub_info->path) { + call_usermodehelper_freeinfo(sub_info); + return -EINVAL; + } + helper_lock(); + if (!khelper_wq || usermodehelper_disabled) { + retval = -EBUSY; + goto out; + } + /* + * Set the completion pointer only if there is a waiter. + * This makes it possible to use umh_complete to free + * the data structure in case of UMH_NO_WAIT. + */ + sub_info->complete = (wait == UMH_NO_WAIT) ? NULL : &done; + sub_info->wait = wait; + + queue_work(khelper_wq, &sub_info->work); + if (wait == UMH_NO_WAIT) /* task has freed sub_info */ + goto unlock; + + if (wait & UMH_KILLABLE) { + retval = wait_for_completion_killable(&done); + if (!retval) + goto wait_done; + + /* umh_complete() will see NULL and free sub_info */ + if (xchg(&sub_info->complete, NULL)) + goto unlock; + /* fallthrough, umh_complete() was already called */ + } + + wait_for_completion(&done); +wait_done: + retval = sub_info->retval; +out: + call_usermodehelper_freeinfo(sub_info); +unlock: + helper_unlock(); + return retval; +} +EXPORT_SYMBOL(call_usermodehelper_exec); + +/** + * call_usermodehelper() - prepare and start a usermode application + * @path: path to usermode executable + * @argv: arg vector for process + * @envp: environment for process + * @wait: wait for the application to finish and return status. + * when UMH_NO_WAIT don't wait at all, but you get no useful error back + * when the program couldn't be exec'ed. This makes it safe to call + * from interrupt context. + * + * This function is the equivalent to use call_usermodehelper_setup() and + * call_usermodehelper_exec(). + */ +int call_usermodehelper(char *path, char **argv, char **envp, int wait) +{ + struct subprocess_info *info; + gfp_t gfp_mask = (wait == UMH_NO_WAIT) ? GFP_ATOMIC : GFP_KERNEL; + + info = call_usermodehelper_setup(path, argv, envp, gfp_mask, + NULL, NULL, NULL); + if (info == NULL) + return -ENOMEM; + + return call_usermodehelper_exec(info, wait); +} +EXPORT_SYMBOL(call_usermodehelper); + +static int proc_cap_handler(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + struct ctl_table t; + unsigned long cap_array[_KERNEL_CAPABILITY_U32S]; + kernel_cap_t new_cap; + int err, i; + + if (write && (!capable(CAP_SETPCAP) || + !capable(CAP_SYS_MODULE))) + return -EPERM; + + /* + * convert from the global kernel_cap_t to the ulong array to print to + * userspace if this is a read. + */ + spin_lock(&umh_sysctl_lock); + for (i = 0; i < _KERNEL_CAPABILITY_U32S; i++) { + if (table->data == CAP_BSET) + cap_array[i] = usermodehelper_bset.cap[i]; + else if (table->data == CAP_PI) + cap_array[i] = usermodehelper_inheritable.cap[i]; + else + BUG(); + } + spin_unlock(&umh_sysctl_lock); + + t = *table; + t.data = &cap_array; + + /* + * actually read or write and array of ulongs from userspace. Remember + * these are least significant 32 bits first + */ + err = proc_doulongvec_minmax(&t, write, buffer, lenp, ppos); + if (err < 0) + return err; + + /* + * convert from the sysctl array of ulongs to the kernel_cap_t + * internal representation + */ + for (i = 0; i < _KERNEL_CAPABILITY_U32S; i++) + new_cap.cap[i] = cap_array[i]; + + /* + * Drop everything not in the new_cap (but don't add things) + */ + spin_lock(&umh_sysctl_lock); + if (write) { + if (table->data == CAP_BSET) + usermodehelper_bset = cap_intersect(usermodehelper_bset, new_cap); + if (table->data == CAP_PI) + usermodehelper_inheritable = cap_intersect(usermodehelper_inheritable, new_cap); + } + spin_unlock(&umh_sysctl_lock); + + return 0; +} + +struct ctl_table usermodehelper_table[] = { + { + .procname = "bset", + .data = CAP_BSET, + .maxlen = _KERNEL_CAPABILITY_U32S * sizeof(unsigned long), + .mode = 0600, + .proc_handler = proc_cap_handler, + }, + { + .procname = "inheritable", + .data = CAP_PI, + .maxlen = _KERNEL_CAPABILITY_U32S * sizeof(unsigned long), + .mode = 0600, + .proc_handler = proc_cap_handler, + }, + { } +}; + +void __init usermodehelper_init(void) +{ + khelper_wq = create_singlethread_workqueue("khelper"); + BUG_ON(!khelper_wq); +} diff --git a/kernel/kernel/kprobes.c b/kernel/kernel/kprobes.c new file mode 100644 index 000000000..c90e417bb --- /dev/null +++ b/kernel/kernel/kprobes.c @@ -0,0 +1,2472 @@ +/* + * Kernel Probes (KProbes) + * kernel/kprobes.c + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * + * Copyright (C) IBM Corporation, 2002, 2004 + * + * 2002-Oct Created by Vamsi Krishna S Kernel + * Probes initial implementation (includes suggestions from + * Rusty Russell). + * 2004-Aug Updated by Prasanna S Panchamukhi with + * hlists and exceptions notifier as suggested by Andi Kleen. + * 2004-July Suparna Bhattacharya added jumper probes + * interface to access function arguments. + * 2004-Sep Prasanna S Panchamukhi Changed Kprobes + * exceptions notifier to be first on the priority list. + * 2005-May Hien Nguyen , Jim Keniston + * and Prasanna S Panchamukhi + * added function-return probes. + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include + +#define KPROBE_HASH_BITS 6 +#define KPROBE_TABLE_SIZE (1 << KPROBE_HASH_BITS) + + +/* + * Some oddball architectures like 64bit powerpc have function descriptors + * so this must be overridable. + */ +#ifndef kprobe_lookup_name +#define kprobe_lookup_name(name, addr) \ + addr = ((kprobe_opcode_t *)(kallsyms_lookup_name(name))) +#endif + +static int kprobes_initialized; +static struct hlist_head kprobe_table[KPROBE_TABLE_SIZE]; +static struct hlist_head kretprobe_inst_table[KPROBE_TABLE_SIZE]; + +/* NOTE: change this value only with kprobe_mutex held */ +static bool kprobes_all_disarmed; + +/* This protects kprobe_table and optimizing_list */ +static DEFINE_MUTEX(kprobe_mutex); +static DEFINE_PER_CPU(struct kprobe *, kprobe_instance) = NULL; +static struct { + raw_spinlock_t lock ____cacheline_aligned_in_smp; +} kretprobe_table_locks[KPROBE_TABLE_SIZE]; + +static raw_spinlock_t *kretprobe_table_lock_ptr(unsigned long hash) +{ + return &(kretprobe_table_locks[hash].lock); +} + +/* Blacklist -- list of struct kprobe_blacklist_entry */ +static LIST_HEAD(kprobe_blacklist); + +#ifdef __ARCH_WANT_KPROBES_INSN_SLOT +/* + * kprobe->ainsn.insn points to the copy of the instruction to be + * single-stepped. x86_64, POWER4 and above have no-exec support and + * stepping on the instruction on a vmalloced/kmalloced/data page + * is a recipe for disaster + */ +struct kprobe_insn_page { + struct list_head list; + kprobe_opcode_t *insns; /* Page of instruction slots */ + struct kprobe_insn_cache *cache; + int nused; + int ngarbage; + char slot_used[]; +}; + +#define KPROBE_INSN_PAGE_SIZE(slots) \ + (offsetof(struct kprobe_insn_page, slot_used) + \ + (sizeof(char) * (slots))) + +static int slots_per_page(struct kprobe_insn_cache *c) +{ + return PAGE_SIZE/(c->insn_size * sizeof(kprobe_opcode_t)); +} + +enum kprobe_slot_state { + SLOT_CLEAN = 0, + SLOT_DIRTY = 1, + SLOT_USED = 2, +}; + +static void *alloc_insn_page(void) +{ + return module_alloc(PAGE_SIZE); +} + +static void free_insn_page(void *page) +{ + module_memfree(page); +} + +struct kprobe_insn_cache kprobe_insn_slots = { + .mutex = __MUTEX_INITIALIZER(kprobe_insn_slots.mutex), + .alloc = alloc_insn_page, + .free = free_insn_page, + .pages = LIST_HEAD_INIT(kprobe_insn_slots.pages), + .insn_size = MAX_INSN_SIZE, + .nr_garbage = 0, +}; +static int collect_garbage_slots(struct kprobe_insn_cache *c); + +/** + * __get_insn_slot() - Find a slot on an executable page for an instruction. + * We allocate an executable page if there's no room on existing ones. + */ +kprobe_opcode_t *__get_insn_slot(struct kprobe_insn_cache *c) +{ + struct kprobe_insn_page *kip; + kprobe_opcode_t *slot = NULL; + + mutex_lock(&c->mutex); + retry: + list_for_each_entry(kip, &c->pages, list) { + if (kip->nused < slots_per_page(c)) { + int i; + for (i = 0; i < slots_per_page(c); i++) { + if (kip->slot_used[i] == SLOT_CLEAN) { + kip->slot_used[i] = SLOT_USED; + kip->nused++; + slot = kip->insns + (i * c->insn_size); + goto out; + } + } + /* kip->nused is broken. Fix it. */ + kip->nused = slots_per_page(c); + WARN_ON(1); + } + } + + /* If there are any garbage slots, collect it and try again. */ + if (c->nr_garbage && collect_garbage_slots(c) == 0) + goto retry; + + /* All out of space. Need to allocate a new page. */ + kip = kmalloc(KPROBE_INSN_PAGE_SIZE(slots_per_page(c)), GFP_KERNEL); + if (!kip) + goto out; + + /* + * Use module_alloc so this page is within +/- 2GB of where the + * kernel image and loaded module images reside. This is required + * so x86_64 can correctly handle the %rip-relative fixups. + */ + kip->insns = c->alloc(); + if (!kip->insns) { + kfree(kip); + goto out; + } + INIT_LIST_HEAD(&kip->list); + memset(kip->slot_used, SLOT_CLEAN, slots_per_page(c)); + kip->slot_used[0] = SLOT_USED; + kip->nused = 1; + kip->ngarbage = 0; + kip->cache = c; + list_add(&kip->list, &c->pages); + slot = kip->insns; +out: + mutex_unlock(&c->mutex); + return slot; +} + +/* Return 1 if all garbages are collected, otherwise 0. */ +static int collect_one_slot(struct kprobe_insn_page *kip, int idx) +{ + kip->slot_used[idx] = SLOT_CLEAN; + kip->nused--; + if (kip->nused == 0) { + /* + * Page is no longer in use. Free it unless + * it's the last one. We keep the last one + * so as not to have to set it up again the + * next time somebody inserts a probe. + */ + if (!list_is_singular(&kip->list)) { + list_del(&kip->list); + kip->cache->free(kip->insns); + kfree(kip); + } + return 1; + } + return 0; +} + +static int collect_garbage_slots(struct kprobe_insn_cache *c) +{ + struct kprobe_insn_page *kip, *next; + + /* Ensure no-one is interrupted on the garbages */ + synchronize_sched(); + + list_for_each_entry_safe(kip, next, &c->pages, list) { + int i; + if (kip->ngarbage == 0) + continue; + kip->ngarbage = 0; /* we will collect all garbages */ + for (i = 0; i < slots_per_page(c); i++) { + if (kip->slot_used[i] == SLOT_DIRTY && + collect_one_slot(kip, i)) + break; + } + } + c->nr_garbage = 0; + return 0; +} + +void __free_insn_slot(struct kprobe_insn_cache *c, + kprobe_opcode_t *slot, int dirty) +{ + struct kprobe_insn_page *kip; + + mutex_lock(&c->mutex); + list_for_each_entry(kip, &c->pages, list) { + long idx = ((long)slot - (long)kip->insns) / + (c->insn_size * sizeof(kprobe_opcode_t)); + if (idx >= 0 && idx < slots_per_page(c)) { + WARN_ON(kip->slot_used[idx] != SLOT_USED); + if (dirty) { + kip->slot_used[idx] = SLOT_DIRTY; + kip->ngarbage++; + if (++c->nr_garbage > slots_per_page(c)) + collect_garbage_slots(c); + } else + collect_one_slot(kip, idx); + goto out; + } + } + /* Could not free this slot. */ + WARN_ON(1); +out: + mutex_unlock(&c->mutex); +} + +#ifdef CONFIG_OPTPROBES +/* For optimized_kprobe buffer */ +struct kprobe_insn_cache kprobe_optinsn_slots = { + .mutex = __MUTEX_INITIALIZER(kprobe_optinsn_slots.mutex), + .alloc = alloc_insn_page, + .free = free_insn_page, + .pages = LIST_HEAD_INIT(kprobe_optinsn_slots.pages), + /* .insn_size is initialized later */ + .nr_garbage = 0, +}; +#endif +#endif + +/* We have preemption disabled.. so it is safe to use __ versions */ +static inline void set_kprobe_instance(struct kprobe *kp) +{ + __this_cpu_write(kprobe_instance, kp); +} + +static inline void reset_kprobe_instance(void) +{ + __this_cpu_write(kprobe_instance, NULL); +} + +/* + * This routine is called either: + * - under the kprobe_mutex - during kprobe_[un]register() + * OR + * - with preemption disabled - from arch/xxx/kernel/kprobes.c + */ +struct kprobe *get_kprobe(void *addr) +{ + struct hlist_head *head; + struct kprobe *p; + + head = &kprobe_table[hash_ptr(addr, KPROBE_HASH_BITS)]; + hlist_for_each_entry_rcu(p, head, hlist) { + if (p->addr == addr) + return p; + } + + return NULL; +} +NOKPROBE_SYMBOL(get_kprobe); + +static int aggr_pre_handler(struct kprobe *p, struct pt_regs *regs); + +/* Return true if the kprobe is an aggregator */ +static inline int kprobe_aggrprobe(struct kprobe *p) +{ + return p->pre_handler == aggr_pre_handler; +} + +/* Return true(!0) if the kprobe is unused */ +static inline int kprobe_unused(struct kprobe *p) +{ + return kprobe_aggrprobe(p) && kprobe_disabled(p) && + list_empty(&p->list); +} + +/* + * Keep all fields in the kprobe consistent + */ +static inline void copy_kprobe(struct kprobe *ap, struct kprobe *p) +{ + memcpy(&p->opcode, &ap->opcode, sizeof(kprobe_opcode_t)); + memcpy(&p->ainsn, &ap->ainsn, sizeof(struct arch_specific_insn)); +} + +#ifdef CONFIG_OPTPROBES +/* NOTE: change this value only with kprobe_mutex held */ +static bool kprobes_allow_optimization; + +/* + * Call all pre_handler on the list, but ignores its return value. + * This must be called from arch-dep optimized caller. + */ +void opt_pre_handler(struct kprobe *p, struct pt_regs *regs) +{ + struct kprobe *kp; + + list_for_each_entry_rcu(kp, &p->list, list) { + if (kp->pre_handler && likely(!kprobe_disabled(kp))) { + set_kprobe_instance(kp); + kp->pre_handler(kp, regs); + } + reset_kprobe_instance(); + } +} +NOKPROBE_SYMBOL(opt_pre_handler); + +/* Free optimized instructions and optimized_kprobe */ +static void free_aggr_kprobe(struct kprobe *p) +{ + struct optimized_kprobe *op; + + op = container_of(p, struct optimized_kprobe, kp); + arch_remove_optimized_kprobe(op); + arch_remove_kprobe(p); + kfree(op); +} + +/* Return true(!0) if the kprobe is ready for optimization. */ +static inline int kprobe_optready(struct kprobe *p) +{ + struct optimized_kprobe *op; + + if (kprobe_aggrprobe(p)) { + op = container_of(p, struct optimized_kprobe, kp); + return arch_prepared_optinsn(&op->optinsn); + } + + return 0; +} + +/* Return true(!0) if the kprobe is disarmed. Note: p must be on hash list */ +static inline int kprobe_disarmed(struct kprobe *p) +{ + struct optimized_kprobe *op; + + /* If kprobe is not aggr/opt probe, just return kprobe is disabled */ + if (!kprobe_aggrprobe(p)) + return kprobe_disabled(p); + + op = container_of(p, struct optimized_kprobe, kp); + + return kprobe_disabled(p) && list_empty(&op->list); +} + +/* Return true(!0) if the probe is queued on (un)optimizing lists */ +static int kprobe_queued(struct kprobe *p) +{ + struct optimized_kprobe *op; + + if (kprobe_aggrprobe(p)) { + op = container_of(p, struct optimized_kprobe, kp); + if (!list_empty(&op->list)) + return 1; + } + return 0; +} + +/* + * Return an optimized kprobe whose optimizing code replaces + * instructions including addr (exclude breakpoint). + */ +static struct kprobe *get_optimized_kprobe(unsigned long addr) +{ + int i; + struct kprobe *p = NULL; + struct optimized_kprobe *op; + + /* Don't check i == 0, since that is a breakpoint case. */ + for (i = 1; !p && i < MAX_OPTIMIZED_LENGTH; i++) + p = get_kprobe((void *)(addr - i)); + + if (p && kprobe_optready(p)) { + op = container_of(p, struct optimized_kprobe, kp); + if (arch_within_optimized_kprobe(op, addr)) + return p; + } + + return NULL; +} + +/* Optimization staging list, protected by kprobe_mutex */ +static LIST_HEAD(optimizing_list); +static LIST_HEAD(unoptimizing_list); +static LIST_HEAD(freeing_list); + +static void kprobe_optimizer(struct work_struct *work); +static DECLARE_DELAYED_WORK(optimizing_work, kprobe_optimizer); +#define OPTIMIZE_DELAY 5 + +/* + * Optimize (replace a breakpoint with a jump) kprobes listed on + * optimizing_list. + */ +static void do_optimize_kprobes(void) +{ + /* Optimization never be done when disarmed */ + if (kprobes_all_disarmed || !kprobes_allow_optimization || + list_empty(&optimizing_list)) + return; + + /* + * The optimization/unoptimization refers online_cpus via + * stop_machine() and cpu-hotplug modifies online_cpus. + * And same time, text_mutex will be held in cpu-hotplug and here. + * This combination can cause a deadlock (cpu-hotplug try to lock + * text_mutex but stop_machine can not be done because online_cpus + * has been changed) + * To avoid this deadlock, we need to call get_online_cpus() + * for preventing cpu-hotplug outside of text_mutex locking. + */ + get_online_cpus(); + mutex_lock(&text_mutex); + arch_optimize_kprobes(&optimizing_list); + mutex_unlock(&text_mutex); + put_online_cpus(); +} + +/* + * Unoptimize (replace a jump with a breakpoint and remove the breakpoint + * if need) kprobes listed on unoptimizing_list. + */ +static void do_unoptimize_kprobes(void) +{ + struct optimized_kprobe *op, *tmp; + + /* Unoptimization must be done anytime */ + if (list_empty(&unoptimizing_list)) + return; + + /* Ditto to do_optimize_kprobes */ + get_online_cpus(); + mutex_lock(&text_mutex); + arch_unoptimize_kprobes(&unoptimizing_list, &freeing_list); + /* Loop free_list for disarming */ + list_for_each_entry_safe(op, tmp, &freeing_list, list) { + /* Disarm probes if marked disabled */ + if (kprobe_disabled(&op->kp)) + arch_disarm_kprobe(&op->kp); + if (kprobe_unused(&op->kp)) { + /* + * Remove unused probes from hash list. After waiting + * for synchronization, these probes are reclaimed. + * (reclaiming is done by do_free_cleaned_kprobes.) + */ + hlist_del_rcu(&op->kp.hlist); + } else + list_del_init(&op->list); + } + mutex_unlock(&text_mutex); + put_online_cpus(); +} + +/* Reclaim all kprobes on the free_list */ +static void do_free_cleaned_kprobes(void) +{ + struct optimized_kprobe *op, *tmp; + + list_for_each_entry_safe(op, tmp, &freeing_list, list) { + BUG_ON(!kprobe_unused(&op->kp)); + list_del_init(&op->list); + free_aggr_kprobe(&op->kp); + } +} + +/* Start optimizer after OPTIMIZE_DELAY passed */ +static void kick_kprobe_optimizer(void) +{ + schedule_delayed_work(&optimizing_work, OPTIMIZE_DELAY); +} + +/* Kprobe jump optimizer */ +static void kprobe_optimizer(struct work_struct *work) +{ + mutex_lock(&kprobe_mutex); + /* Lock modules while optimizing kprobes */ + mutex_lock(&module_mutex); + + /* + * Step 1: Unoptimize kprobes and collect cleaned (unused and disarmed) + * kprobes before waiting for quiesence period. + */ + do_unoptimize_kprobes(); + + /* + * Step 2: Wait for quiesence period to ensure all running interrupts + * are done. Because optprobe may modify multiple instructions + * there is a chance that Nth instruction is interrupted. In that + * case, running interrupt can return to 2nd-Nth byte of jump + * instruction. This wait is for avoiding it. + */ + synchronize_sched(); + + /* Step 3: Optimize kprobes after quiesence period */ + do_optimize_kprobes(); + + /* Step 4: Free cleaned kprobes after quiesence period */ + do_free_cleaned_kprobes(); + + mutex_unlock(&module_mutex); + mutex_unlock(&kprobe_mutex); + + /* Step 5: Kick optimizer again if needed */ + if (!list_empty(&optimizing_list) || !list_empty(&unoptimizing_list)) + kick_kprobe_optimizer(); +} + +/* Wait for completing optimization and unoptimization */ +static void wait_for_kprobe_optimizer(void) +{ + mutex_lock(&kprobe_mutex); + + while (!list_empty(&optimizing_list) || !list_empty(&unoptimizing_list)) { + mutex_unlock(&kprobe_mutex); + + /* this will also make optimizing_work execute immmediately */ + flush_delayed_work(&optimizing_work); + /* @optimizing_work might not have been queued yet, relax */ + cpu_relax(); + + mutex_lock(&kprobe_mutex); + } + + mutex_unlock(&kprobe_mutex); +} + +/* Optimize kprobe if p is ready to be optimized */ +static void optimize_kprobe(struct kprobe *p) +{ + struct optimized_kprobe *op; + + /* Check if the kprobe is disabled or not ready for optimization. */ + if (!kprobe_optready(p) || !kprobes_allow_optimization || + (kprobe_disabled(p) || kprobes_all_disarmed)) + return; + + /* Both of break_handler and post_handler are not supported. */ + if (p->break_handler || p->post_handler) + return; + + op = container_of(p, struct optimized_kprobe, kp); + + /* Check there is no other kprobes at the optimized instructions */ + if (arch_check_optimized_kprobe(op) < 0) + return; + + /* Check if it is already optimized. */ + if (op->kp.flags & KPROBE_FLAG_OPTIMIZED) + return; + op->kp.flags |= KPROBE_FLAG_OPTIMIZED; + + if (!list_empty(&op->list)) + /* This is under unoptimizing. Just dequeue the probe */ + list_del_init(&op->list); + else { + list_add(&op->list, &optimizing_list); + kick_kprobe_optimizer(); + } +} + +/* Short cut to direct unoptimizing */ +static void force_unoptimize_kprobe(struct optimized_kprobe *op) +{ + get_online_cpus(); + arch_unoptimize_kprobe(op); + put_online_cpus(); + if (kprobe_disabled(&op->kp)) + arch_disarm_kprobe(&op->kp); +} + +/* Unoptimize a kprobe if p is optimized */ +static void unoptimize_kprobe(struct kprobe *p, bool force) +{ + struct optimized_kprobe *op; + + if (!kprobe_aggrprobe(p) || kprobe_disarmed(p)) + return; /* This is not an optprobe nor optimized */ + + op = container_of(p, struct optimized_kprobe, kp); + if (!kprobe_optimized(p)) { + /* Unoptimized or unoptimizing case */ + if (force && !list_empty(&op->list)) { + /* + * Only if this is unoptimizing kprobe and forced, + * forcibly unoptimize it. (No need to unoptimize + * unoptimized kprobe again :) + */ + list_del_init(&op->list); + force_unoptimize_kprobe(op); + } + return; + } + + op->kp.flags &= ~KPROBE_FLAG_OPTIMIZED; + if (!list_empty(&op->list)) { + /* Dequeue from the optimization queue */ + list_del_init(&op->list); + return; + } + /* Optimized kprobe case */ + if (force) + /* Forcibly update the code: this is a special case */ + force_unoptimize_kprobe(op); + else { + list_add(&op->list, &unoptimizing_list); + kick_kprobe_optimizer(); + } +} + +/* Cancel unoptimizing for reusing */ +static void reuse_unused_kprobe(struct kprobe *ap) +{ + struct optimized_kprobe *op; + + BUG_ON(!kprobe_unused(ap)); + /* + * Unused kprobe MUST be on the way of delayed unoptimizing (means + * there is still a relative jump) and disabled. + */ + op = container_of(ap, struct optimized_kprobe, kp); + if (unlikely(list_empty(&op->list))) + printk(KERN_WARNING "Warning: found a stray unused " + "aggrprobe@%p\n", ap->addr); + /* Enable the probe again */ + ap->flags &= ~KPROBE_FLAG_DISABLED; + /* Optimize it again (remove from op->list) */ + BUG_ON(!kprobe_optready(ap)); + optimize_kprobe(ap); +} + +/* Remove optimized instructions */ +static void kill_optimized_kprobe(struct kprobe *p) +{ + struct optimized_kprobe *op; + + op = container_of(p, struct optimized_kprobe, kp); + if (!list_empty(&op->list)) + /* Dequeue from the (un)optimization queue */ + list_del_init(&op->list); + op->kp.flags &= ~KPROBE_FLAG_OPTIMIZED; + + if (kprobe_unused(p)) { + /* Enqueue if it is unused */ + list_add(&op->list, &freeing_list); + /* + * Remove unused probes from the hash list. After waiting + * for synchronization, this probe is reclaimed. + * (reclaiming is done by do_free_cleaned_kprobes().) + */ + hlist_del_rcu(&op->kp.hlist); + } + + /* Don't touch the code, because it is already freed. */ + arch_remove_optimized_kprobe(op); +} + +/* Try to prepare optimized instructions */ +static void prepare_optimized_kprobe(struct kprobe *p) +{ + struct optimized_kprobe *op; + + op = container_of(p, struct optimized_kprobe, kp); + arch_prepare_optimized_kprobe(op, p); +} + +/* Allocate new optimized_kprobe and try to prepare optimized instructions */ +static struct kprobe *alloc_aggr_kprobe(struct kprobe *p) +{ + struct optimized_kprobe *op; + + op = kzalloc(sizeof(struct optimized_kprobe), GFP_KERNEL); + if (!op) + return NULL; + + INIT_LIST_HEAD(&op->list); + op->kp.addr = p->addr; + arch_prepare_optimized_kprobe(op, p); + + return &op->kp; +} + +static void init_aggr_kprobe(struct kprobe *ap, struct kprobe *p); + +/* + * Prepare an optimized_kprobe and optimize it + * NOTE: p must be a normal registered kprobe + */ +static void try_to_optimize_kprobe(struct kprobe *p) +{ + struct kprobe *ap; + struct optimized_kprobe *op; + + /* Impossible to optimize ftrace-based kprobe */ + if (kprobe_ftrace(p)) + return; + + /* For preparing optimization, jump_label_text_reserved() is called */ + jump_label_lock(); + mutex_lock(&text_mutex); + + ap = alloc_aggr_kprobe(p); + if (!ap) + goto out; + + op = container_of(ap, struct optimized_kprobe, kp); + if (!arch_prepared_optinsn(&op->optinsn)) { + /* If failed to setup optimizing, fallback to kprobe */ + arch_remove_optimized_kprobe(op); + kfree(op); + goto out; + } + + init_aggr_kprobe(ap, p); + optimize_kprobe(ap); /* This just kicks optimizer thread */ + +out: + mutex_unlock(&text_mutex); + jump_label_unlock(); +} + +#ifdef CONFIG_SYSCTL +static void optimize_all_kprobes(void) +{ + struct hlist_head *head; + struct kprobe *p; + unsigned int i; + + mutex_lock(&kprobe_mutex); + /* If optimization is already allowed, just return */ + if (kprobes_allow_optimization) + goto out; + + kprobes_allow_optimization = true; + for (i = 0; i < KPROBE_TABLE_SIZE; i++) { + head = &kprobe_table[i]; + hlist_for_each_entry_rcu(p, head, hlist) + if (!kprobe_disabled(p)) + optimize_kprobe(p); + } + printk(KERN_INFO "Kprobes globally optimized\n"); +out: + mutex_unlock(&kprobe_mutex); +} + +static void unoptimize_all_kprobes(void) +{ + struct hlist_head *head; + struct kprobe *p; + unsigned int i; + + mutex_lock(&kprobe_mutex); + /* If optimization is already prohibited, just return */ + if (!kprobes_allow_optimization) { + mutex_unlock(&kprobe_mutex); + return; + } + + kprobes_allow_optimization = false; + for (i = 0; i < KPROBE_TABLE_SIZE; i++) { + head = &kprobe_table[i]; + hlist_for_each_entry_rcu(p, head, hlist) { + if (!kprobe_disabled(p)) + unoptimize_kprobe(p, false); + } + } + mutex_unlock(&kprobe_mutex); + + /* Wait for unoptimizing completion */ + wait_for_kprobe_optimizer(); + printk(KERN_INFO "Kprobes globally unoptimized\n"); +} + +static DEFINE_MUTEX(kprobe_sysctl_mutex); +int sysctl_kprobes_optimization; +int proc_kprobes_optimization_handler(struct ctl_table *table, int write, + void __user *buffer, size_t *length, + loff_t *ppos) +{ + int ret; + + mutex_lock(&kprobe_sysctl_mutex); + sysctl_kprobes_optimization = kprobes_allow_optimization ? 1 : 0; + ret = proc_dointvec_minmax(table, write, buffer, length, ppos); + + if (sysctl_kprobes_optimization) + optimize_all_kprobes(); + else + unoptimize_all_kprobes(); + mutex_unlock(&kprobe_sysctl_mutex); + + return ret; +} +#endif /* CONFIG_SYSCTL */ + +/* Put a breakpoint for a probe. Must be called with text_mutex locked */ +static void __arm_kprobe(struct kprobe *p) +{ + struct kprobe *_p; + + /* Check collision with other optimized kprobes */ + _p = get_optimized_kprobe((unsigned long)p->addr); + if (unlikely(_p)) + /* Fallback to unoptimized kprobe */ + unoptimize_kprobe(_p, true); + + arch_arm_kprobe(p); + optimize_kprobe(p); /* Try to optimize (add kprobe to a list) */ +} + +/* Remove the breakpoint of a probe. Must be called with text_mutex locked */ +static void __disarm_kprobe(struct kprobe *p, bool reopt) +{ + struct kprobe *_p; + + /* Try to unoptimize */ + unoptimize_kprobe(p, kprobes_all_disarmed); + + if (!kprobe_queued(p)) { + arch_disarm_kprobe(p); + /* If another kprobe was blocked, optimize it. */ + _p = get_optimized_kprobe((unsigned long)p->addr); + if (unlikely(_p) && reopt) + optimize_kprobe(_p); + } + /* TODO: reoptimize others after unoptimized this probe */ +} + +#else /* !CONFIG_OPTPROBES */ + +#define optimize_kprobe(p) do {} while (0) +#define unoptimize_kprobe(p, f) do {} while (0) +#define kill_optimized_kprobe(p) do {} while (0) +#define prepare_optimized_kprobe(p) do {} while (0) +#define try_to_optimize_kprobe(p) do {} while (0) +#define __arm_kprobe(p) arch_arm_kprobe(p) +#define __disarm_kprobe(p, o) arch_disarm_kprobe(p) +#define kprobe_disarmed(p) kprobe_disabled(p) +#define wait_for_kprobe_optimizer() do {} while (0) + +/* There should be no unused kprobes can be reused without optimization */ +static void reuse_unused_kprobe(struct kprobe *ap) +{ + printk(KERN_ERR "Error: There should be no unused kprobe here.\n"); + BUG_ON(kprobe_unused(ap)); +} + +static void free_aggr_kprobe(struct kprobe *p) +{ + arch_remove_kprobe(p); + kfree(p); +} + +static struct kprobe *alloc_aggr_kprobe(struct kprobe *p) +{ + return kzalloc(sizeof(struct kprobe), GFP_KERNEL); +} +#endif /* CONFIG_OPTPROBES */ + +#ifdef CONFIG_KPROBES_ON_FTRACE +static struct ftrace_ops kprobe_ftrace_ops __read_mostly = { + .func = kprobe_ftrace_handler, + .flags = FTRACE_OPS_FL_SAVE_REGS | FTRACE_OPS_FL_IPMODIFY, +}; +static int kprobe_ftrace_enabled; + +/* Must ensure p->addr is really on ftrace */ +static int prepare_kprobe(struct kprobe *p) +{ + if (!kprobe_ftrace(p)) + return arch_prepare_kprobe(p); + + return arch_prepare_kprobe_ftrace(p); +} + +/* Caller must lock kprobe_mutex */ +static void arm_kprobe_ftrace(struct kprobe *p) +{ + int ret; + + ret = ftrace_set_filter_ip(&kprobe_ftrace_ops, + (unsigned long)p->addr, 0, 0); + WARN(ret < 0, "Failed to arm kprobe-ftrace at %p (%d)\n", p->addr, ret); + kprobe_ftrace_enabled++; + if (kprobe_ftrace_enabled == 1) { + ret = register_ftrace_function(&kprobe_ftrace_ops); + WARN(ret < 0, "Failed to init kprobe-ftrace (%d)\n", ret); + } +} + +/* Caller must lock kprobe_mutex */ +static void disarm_kprobe_ftrace(struct kprobe *p) +{ + int ret; + + kprobe_ftrace_enabled--; + if (kprobe_ftrace_enabled == 0) { + ret = unregister_ftrace_function(&kprobe_ftrace_ops); + WARN(ret < 0, "Failed to init kprobe-ftrace (%d)\n", ret); + } + ret = ftrace_set_filter_ip(&kprobe_ftrace_ops, + (unsigned long)p->addr, 1, 0); + WARN(ret < 0, "Failed to disarm kprobe-ftrace at %p (%d)\n", p->addr, ret); +} +#else /* !CONFIG_KPROBES_ON_FTRACE */ +#define prepare_kprobe(p) arch_prepare_kprobe(p) +#define arm_kprobe_ftrace(p) do {} while (0) +#define disarm_kprobe_ftrace(p) do {} while (0) +#endif + +/* Arm a kprobe with text_mutex */ +static void arm_kprobe(struct kprobe *kp) +{ + if (unlikely(kprobe_ftrace(kp))) { + arm_kprobe_ftrace(kp); + return; + } + /* + * Here, since __arm_kprobe() doesn't use stop_machine(), + * this doesn't cause deadlock on text_mutex. So, we don't + * need get_online_cpus(). + */ + mutex_lock(&text_mutex); + __arm_kprobe(kp); + mutex_unlock(&text_mutex); +} + +/* Disarm a kprobe with text_mutex */ +static void disarm_kprobe(struct kprobe *kp, bool reopt) +{ + if (unlikely(kprobe_ftrace(kp))) { + disarm_kprobe_ftrace(kp); + return; + } + /* Ditto */ + mutex_lock(&text_mutex); + __disarm_kprobe(kp, reopt); + mutex_unlock(&text_mutex); +} + +/* + * Aggregate handlers for multiple kprobes support - these handlers + * take care of invoking the individual kprobe handlers on p->list + */ +static int aggr_pre_handler(struct kprobe *p, struct pt_regs *regs) +{ + struct kprobe *kp; + + list_for_each_entry_rcu(kp, &p->list, list) { + if (kp->pre_handler && likely(!kprobe_disabled(kp))) { + set_kprobe_instance(kp); + if (kp->pre_handler(kp, regs)) + return 1; + } + reset_kprobe_instance(); + } + return 0; +} +NOKPROBE_SYMBOL(aggr_pre_handler); + +static void aggr_post_handler(struct kprobe *p, struct pt_regs *regs, + unsigned long flags) +{ + struct kprobe *kp; + + list_for_each_entry_rcu(kp, &p->list, list) { + if (kp->post_handler && likely(!kprobe_disabled(kp))) { + set_kprobe_instance(kp); + kp->post_handler(kp, regs, flags); + reset_kprobe_instance(); + } + } +} +NOKPROBE_SYMBOL(aggr_post_handler); + +static int aggr_fault_handler(struct kprobe *p, struct pt_regs *regs, + int trapnr) +{ + struct kprobe *cur = __this_cpu_read(kprobe_instance); + + /* + * if we faulted "during" the execution of a user specified + * probe handler, invoke just that probe's fault handler + */ + if (cur && cur->fault_handler) { + if (cur->fault_handler(cur, regs, trapnr)) + return 1; + } + return 0; +} +NOKPROBE_SYMBOL(aggr_fault_handler); + +static int aggr_break_handler(struct kprobe *p, struct pt_regs *regs) +{ + struct kprobe *cur = __this_cpu_read(kprobe_instance); + int ret = 0; + + if (cur && cur->break_handler) { + if (cur->break_handler(cur, regs)) + ret = 1; + } + reset_kprobe_instance(); + return ret; +} +NOKPROBE_SYMBOL(aggr_break_handler); + +/* Walks the list and increments nmissed count for multiprobe case */ +void kprobes_inc_nmissed_count(struct kprobe *p) +{ + struct kprobe *kp; + if (!kprobe_aggrprobe(p)) { + p->nmissed++; + } else { + list_for_each_entry_rcu(kp, &p->list, list) + kp->nmissed++; + } + return; +} +NOKPROBE_SYMBOL(kprobes_inc_nmissed_count); + +void recycle_rp_inst(struct kretprobe_instance *ri, + struct hlist_head *head) +{ + struct kretprobe *rp = ri->rp; + + /* remove rp inst off the rprobe_inst_table */ + hlist_del(&ri->hlist); + INIT_HLIST_NODE(&ri->hlist); + if (likely(rp)) { + raw_spin_lock(&rp->lock); + hlist_add_head(&ri->hlist, &rp->free_instances); + raw_spin_unlock(&rp->lock); + } else + /* Unregistering */ + hlist_add_head(&ri->hlist, head); +} +NOKPROBE_SYMBOL(recycle_rp_inst); + +void kretprobe_hash_lock(struct task_struct *tsk, + struct hlist_head **head, unsigned long *flags) +__acquires(hlist_lock) +{ + unsigned long hash = hash_ptr(tsk, KPROBE_HASH_BITS); + raw_spinlock_t *hlist_lock; + + *head = &kretprobe_inst_table[hash]; + hlist_lock = kretprobe_table_lock_ptr(hash); + raw_spin_lock_irqsave(hlist_lock, *flags); +} +NOKPROBE_SYMBOL(kretprobe_hash_lock); + +static void kretprobe_table_lock(unsigned long hash, + unsigned long *flags) +__acquires(hlist_lock) +{ + raw_spinlock_t *hlist_lock = kretprobe_table_lock_ptr(hash); + raw_spin_lock_irqsave(hlist_lock, *flags); +} +NOKPROBE_SYMBOL(kretprobe_table_lock); + +void kretprobe_hash_unlock(struct task_struct *tsk, + unsigned long *flags) +__releases(hlist_lock) +{ + unsigned long hash = hash_ptr(tsk, KPROBE_HASH_BITS); + raw_spinlock_t *hlist_lock; + + hlist_lock = kretprobe_table_lock_ptr(hash); + raw_spin_unlock_irqrestore(hlist_lock, *flags); +} +NOKPROBE_SYMBOL(kretprobe_hash_unlock); + +static void kretprobe_table_unlock(unsigned long hash, + unsigned long *flags) +__releases(hlist_lock) +{ + raw_spinlock_t *hlist_lock = kretprobe_table_lock_ptr(hash); + raw_spin_unlock_irqrestore(hlist_lock, *flags); +} +NOKPROBE_SYMBOL(kretprobe_table_unlock); + +/* + * This function is called from finish_task_switch when task tk becomes dead, + * so that we can recycle any function-return probe instances associated + * with this task. These left over instances represent probed functions + * that have been called but will never return. + */ +void kprobe_flush_task(struct task_struct *tk) +{ + struct kretprobe_instance *ri; + struct hlist_head *head, empty_rp; + struct hlist_node *tmp; + unsigned long hash, flags = 0; + + if (unlikely(!kprobes_initialized)) + /* Early boot. kretprobe_table_locks not yet initialized. */ + return; + + INIT_HLIST_HEAD(&empty_rp); + hash = hash_ptr(tk, KPROBE_HASH_BITS); + head = &kretprobe_inst_table[hash]; + kretprobe_table_lock(hash, &flags); + hlist_for_each_entry_safe(ri, tmp, head, hlist) { + if (ri->task == tk) + recycle_rp_inst(ri, &empty_rp); + } + kretprobe_table_unlock(hash, &flags); + hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) { + hlist_del(&ri->hlist); + kfree(ri); + } +} +NOKPROBE_SYMBOL(kprobe_flush_task); + +static inline void free_rp_inst(struct kretprobe *rp) +{ + struct kretprobe_instance *ri; + struct hlist_node *next; + + hlist_for_each_entry_safe(ri, next, &rp->free_instances, hlist) { + hlist_del(&ri->hlist); + kfree(ri); + } +} + +static void cleanup_rp_inst(struct kretprobe *rp) +{ + unsigned long flags, hash; + struct kretprobe_instance *ri; + struct hlist_node *next; + struct hlist_head *head; + + /* No race here */ + for (hash = 0; hash < KPROBE_TABLE_SIZE; hash++) { + kretprobe_table_lock(hash, &flags); + head = &kretprobe_inst_table[hash]; + hlist_for_each_entry_safe(ri, next, head, hlist) { + if (ri->rp == rp) + ri->rp = NULL; + } + kretprobe_table_unlock(hash, &flags); + } + free_rp_inst(rp); +} +NOKPROBE_SYMBOL(cleanup_rp_inst); + +/* +* Add the new probe to ap->list. Fail if this is the +* second jprobe at the address - two jprobes can't coexist +*/ +static int add_new_kprobe(struct kprobe *ap, struct kprobe *p) +{ + BUG_ON(kprobe_gone(ap) || kprobe_gone(p)); + + if (p->break_handler || p->post_handler) + unoptimize_kprobe(ap, true); /* Fall back to normal kprobe */ + + if (p->break_handler) { + if (ap->break_handler) + return -EEXIST; + list_add_tail_rcu(&p->list, &ap->list); + ap->break_handler = aggr_break_handler; + } else + list_add_rcu(&p->list, &ap->list); + if (p->post_handler && !ap->post_handler) + ap->post_handler = aggr_post_handler; + + return 0; +} + +/* + * Fill in the required fields of the "manager kprobe". Replace the + * earlier kprobe in the hlist with the manager kprobe + */ +static void init_aggr_kprobe(struct kprobe *ap, struct kprobe *p) +{ + /* Copy p's insn slot to ap */ + copy_kprobe(p, ap); + flush_insn_slot(ap); + ap->addr = p->addr; + ap->flags = p->flags & ~KPROBE_FLAG_OPTIMIZED; + ap->pre_handler = aggr_pre_handler; + ap->fault_handler = aggr_fault_handler; + /* We don't care the kprobe which has gone. */ + if (p->post_handler && !kprobe_gone(p)) + ap->post_handler = aggr_post_handler; + if (p->break_handler && !kprobe_gone(p)) + ap->break_handler = aggr_break_handler; + + INIT_LIST_HEAD(&ap->list); + INIT_HLIST_NODE(&ap->hlist); + + list_add_rcu(&p->list, &ap->list); + hlist_replace_rcu(&p->hlist, &ap->hlist); +} + +/* + * This is the second or subsequent kprobe at the address - handle + * the intricacies + */ +static int register_aggr_kprobe(struct kprobe *orig_p, struct kprobe *p) +{ + int ret = 0; + struct kprobe *ap = orig_p; + + /* For preparing optimization, jump_label_text_reserved() is called */ + jump_label_lock(); + /* + * Get online CPUs to avoid text_mutex deadlock.with stop machine, + * which is invoked by unoptimize_kprobe() in add_new_kprobe() + */ + get_online_cpus(); + mutex_lock(&text_mutex); + + if (!kprobe_aggrprobe(orig_p)) { + /* If orig_p is not an aggr_kprobe, create new aggr_kprobe. */ + ap = alloc_aggr_kprobe(orig_p); + if (!ap) { + ret = -ENOMEM; + goto out; + } + init_aggr_kprobe(ap, orig_p); + } else if (kprobe_unused(ap)) + /* This probe is going to die. Rescue it */ + reuse_unused_kprobe(ap); + + if (kprobe_gone(ap)) { + /* + * Attempting to insert new probe at the same location that + * had a probe in the module vaddr area which already + * freed. So, the instruction slot has already been + * released. We need a new slot for the new probe. + */ + ret = arch_prepare_kprobe(ap); + if (ret) + /* + * Even if fail to allocate new slot, don't need to + * free aggr_probe. It will be used next time, or + * freed by unregister_kprobe. + */ + goto out; + + /* Prepare optimized instructions if possible. */ + prepare_optimized_kprobe(ap); + + /* + * Clear gone flag to prevent allocating new slot again, and + * set disabled flag because it is not armed yet. + */ + ap->flags = (ap->flags & ~KPROBE_FLAG_GONE) + | KPROBE_FLAG_DISABLED; + } + + /* Copy ap's insn slot to p */ + copy_kprobe(ap, p); + ret = add_new_kprobe(ap, p); + +out: + mutex_unlock(&text_mutex); + put_online_cpus(); + jump_label_unlock(); + + if (ret == 0 && kprobe_disabled(ap) && !kprobe_disabled(p)) { + ap->flags &= ~KPROBE_FLAG_DISABLED; + if (!kprobes_all_disarmed) + /* Arm the breakpoint again. */ + arm_kprobe(ap); + } + return ret; +} + +bool __weak arch_within_kprobe_blacklist(unsigned long addr) +{ + /* The __kprobes marked functions and entry code must not be probed */ + return addr >= (unsigned long)__kprobes_text_start && + addr < (unsigned long)__kprobes_text_end; +} + +static bool within_kprobe_blacklist(unsigned long addr) +{ + struct kprobe_blacklist_entry *ent; + + if (arch_within_kprobe_blacklist(addr)) + return true; + /* + * If there exists a kprobe_blacklist, verify and + * fail any probe registration in the prohibited area + */ + list_for_each_entry(ent, &kprobe_blacklist, list) { + if (addr >= ent->start_addr && addr < ent->end_addr) + return true; + } + + return false; +} + +/* + * If we have a symbol_name argument, look it up and add the offset field + * to it. This way, we can specify a relative address to a symbol. + * This returns encoded errors if it fails to look up symbol or invalid + * combination of parameters. + */ +static kprobe_opcode_t *kprobe_addr(struct kprobe *p) +{ + kprobe_opcode_t *addr = p->addr; + + if ((p->symbol_name && p->addr) || + (!p->symbol_name && !p->addr)) + goto invalid; + + if (p->symbol_name) { + kprobe_lookup_name(p->symbol_name, addr); + if (!addr) + return ERR_PTR(-ENOENT); + } + + addr = (kprobe_opcode_t *)(((char *)addr) + p->offset); + if (addr) + return addr; + +invalid: + return ERR_PTR(-EINVAL); +} + +/* Check passed kprobe is valid and return kprobe in kprobe_table. */ +static struct kprobe *__get_valid_kprobe(struct kprobe *p) +{ + struct kprobe *ap, *list_p; + + ap = get_kprobe(p->addr); + if (unlikely(!ap)) + return NULL; + + if (p != ap) { + list_for_each_entry_rcu(list_p, &ap->list, list) + if (list_p == p) + /* kprobe p is a valid probe */ + goto valid; + return NULL; + } +valid: + return ap; +} + +/* Return error if the kprobe is being re-registered */ +static inline int check_kprobe_rereg(struct kprobe *p) +{ + int ret = 0; + + mutex_lock(&kprobe_mutex); + if (__get_valid_kprobe(p)) + ret = -EINVAL; + mutex_unlock(&kprobe_mutex); + + return ret; +} + +int __weak arch_check_ftrace_location(struct kprobe *p) +{ + unsigned long ftrace_addr; + + ftrace_addr = ftrace_location((unsigned long)p->addr); + if (ftrace_addr) { +#ifdef CONFIG_KPROBES_ON_FTRACE + /* Given address is not on the instruction boundary */ + if ((unsigned long)p->addr != ftrace_addr) + return -EILSEQ; + p->flags |= KPROBE_FLAG_FTRACE; +#else /* !CONFIG_KPROBES_ON_FTRACE */ + return -EINVAL; +#endif + } + return 0; +} + +static int check_kprobe_address_safe(struct kprobe *p, + struct module **probed_mod) +{ + int ret; + + ret = arch_check_ftrace_location(p); + if (ret) + return ret; + jump_label_lock(); + preempt_disable(); + + /* Ensure it is not in reserved area nor out of text */ + if (!kernel_text_address((unsigned long) p->addr) || + within_kprobe_blacklist((unsigned long) p->addr) || + jump_label_text_reserved(p->addr, p->addr)) { + ret = -EINVAL; + goto out; + } + + /* Check if are we probing a module */ + *probed_mod = __module_text_address((unsigned long) p->addr); + if (*probed_mod) { + /* + * We must hold a refcount of the probed module while updating + * its code to prohibit unexpected unloading. + */ + if (unlikely(!try_module_get(*probed_mod))) { + ret = -ENOENT; + goto out; + } + + /* + * If the module freed .init.text, we couldn't insert + * kprobes in there. + */ + if (within_module_init((unsigned long)p->addr, *probed_mod) && + (*probed_mod)->state != MODULE_STATE_COMING) { + module_put(*probed_mod); + *probed_mod = NULL; + ret = -ENOENT; + } + } +out: + preempt_enable(); + jump_label_unlock(); + + return ret; +} + +int register_kprobe(struct kprobe *p) +{ + int ret; + struct kprobe *old_p; + struct module *probed_mod; + kprobe_opcode_t *addr; + + /* Adjust probe address from symbol */ + addr = kprobe_addr(p); + if (IS_ERR(addr)) + return PTR_ERR(addr); + p->addr = addr; + + ret = check_kprobe_rereg(p); + if (ret) + return ret; + + /* User can pass only KPROBE_FLAG_DISABLED to register_kprobe */ + p->flags &= KPROBE_FLAG_DISABLED; + p->nmissed = 0; + INIT_LIST_HEAD(&p->list); + + ret = check_kprobe_address_safe(p, &probed_mod); + if (ret) + return ret; + + mutex_lock(&kprobe_mutex); + + old_p = get_kprobe(p->addr); + if (old_p) { + /* Since this may unoptimize old_p, locking text_mutex. */ + ret = register_aggr_kprobe(old_p, p); + goto out; + } + + mutex_lock(&text_mutex); /* Avoiding text modification */ + ret = prepare_kprobe(p); + mutex_unlock(&text_mutex); + if (ret) + goto out; + + INIT_HLIST_NODE(&p->hlist); + hlist_add_head_rcu(&p->hlist, + &kprobe_table[hash_ptr(p->addr, KPROBE_HASH_BITS)]); + + if (!kprobes_all_disarmed && !kprobe_disabled(p)) + arm_kprobe(p); + + /* Try to optimize kprobe */ + try_to_optimize_kprobe(p); + +out: + mutex_unlock(&kprobe_mutex); + + if (probed_mod) + module_put(probed_mod); + + return ret; +} +EXPORT_SYMBOL_GPL(register_kprobe); + +/* Check if all probes on the aggrprobe are disabled */ +static int aggr_kprobe_disabled(struct kprobe *ap) +{ + struct kprobe *kp; + + list_for_each_entry_rcu(kp, &ap->list, list) + if (!kprobe_disabled(kp)) + /* + * There is an active probe on the list. + * We can't disable this ap. + */ + return 0; + + return 1; +} + +/* Disable one kprobe: Make sure called under kprobe_mutex is locked */ +static struct kprobe *__disable_kprobe(struct kprobe *p) +{ + struct kprobe *orig_p; + + /* Get an original kprobe for return */ + orig_p = __get_valid_kprobe(p); + if (unlikely(orig_p == NULL)) + return NULL; + + if (!kprobe_disabled(p)) { + /* Disable probe if it is a child probe */ + if (p != orig_p) + p->flags |= KPROBE_FLAG_DISABLED; + + /* Try to disarm and disable this/parent probe */ + if (p == orig_p || aggr_kprobe_disabled(orig_p)) { + /* + * If kprobes_all_disarmed is set, orig_p + * should have already been disarmed, so + * skip unneed disarming process. + */ + if (!kprobes_all_disarmed) + disarm_kprobe(orig_p, true); + orig_p->flags |= KPROBE_FLAG_DISABLED; + } + } + + return orig_p; +} + +/* + * Unregister a kprobe without a scheduler synchronization. + */ +static int __unregister_kprobe_top(struct kprobe *p) +{ + struct kprobe *ap, *list_p; + + /* Disable kprobe. This will disarm it if needed. */ + ap = __disable_kprobe(p); + if (ap == NULL) + return -EINVAL; + + if (ap == p) + /* + * This probe is an independent(and non-optimized) kprobe + * (not an aggrprobe). Remove from the hash list. + */ + goto disarmed; + + /* Following process expects this probe is an aggrprobe */ + WARN_ON(!kprobe_aggrprobe(ap)); + + if (list_is_singular(&ap->list) && kprobe_disarmed(ap)) + /* + * !disarmed could be happen if the probe is under delayed + * unoptimizing. + */ + goto disarmed; + else { + /* If disabling probe has special handlers, update aggrprobe */ + if (p->break_handler && !kprobe_gone(p)) + ap->break_handler = NULL; + if (p->post_handler && !kprobe_gone(p)) { + list_for_each_entry_rcu(list_p, &ap->list, list) { + if ((list_p != p) && (list_p->post_handler)) + goto noclean; + } + ap->post_handler = NULL; + } +noclean: + /* + * Remove from the aggrprobe: this path will do nothing in + * __unregister_kprobe_bottom(). + */ + list_del_rcu(&p->list); + if (!kprobe_disabled(ap) && !kprobes_all_disarmed) + /* + * Try to optimize this probe again, because post + * handler may have been changed. + */ + optimize_kprobe(ap); + } + return 0; + +disarmed: + BUG_ON(!kprobe_disarmed(ap)); + hlist_del_rcu(&ap->hlist); + return 0; +} + +static void __unregister_kprobe_bottom(struct kprobe *p) +{ + struct kprobe *ap; + + if (list_empty(&p->list)) + /* This is an independent kprobe */ + arch_remove_kprobe(p); + else if (list_is_singular(&p->list)) { + /* This is the last child of an aggrprobe */ + ap = list_entry(p->list.next, struct kprobe, list); + list_del(&p->list); + free_aggr_kprobe(ap); + } + /* Otherwise, do nothing. */ +} + +int register_kprobes(struct kprobe **kps, int num) +{ + int i, ret = 0; + + if (num <= 0) + return -EINVAL; + for (i = 0; i < num; i++) { + ret = register_kprobe(kps[i]); + if (ret < 0) { + if (i > 0) + unregister_kprobes(kps, i); + break; + } + } + return ret; +} +EXPORT_SYMBOL_GPL(register_kprobes); + +void unregister_kprobe(struct kprobe *p) +{ + unregister_kprobes(&p, 1); +} +EXPORT_SYMBOL_GPL(unregister_kprobe); + +void unregister_kprobes(struct kprobe **kps, int num) +{ + int i; + + if (num <= 0) + return; + mutex_lock(&kprobe_mutex); + for (i = 0; i < num; i++) + if (__unregister_kprobe_top(kps[i]) < 0) + kps[i]->addr = NULL; + mutex_unlock(&kprobe_mutex); + + synchronize_sched(); + for (i = 0; i < num; i++) + if (kps[i]->addr) + __unregister_kprobe_bottom(kps[i]); +} +EXPORT_SYMBOL_GPL(unregister_kprobes); + +static struct notifier_block kprobe_exceptions_nb = { + .notifier_call = kprobe_exceptions_notify, + .priority = 0x7fffffff /* we need to be notified first */ +}; + +unsigned long __weak arch_deref_entry_point(void *entry) +{ + return (unsigned long)entry; +} + +int register_jprobes(struct jprobe **jps, int num) +{ + struct jprobe *jp; + int ret = 0, i; + + if (num <= 0) + return -EINVAL; + for (i = 0; i < num; i++) { + unsigned long addr, offset; + jp = jps[i]; + addr = arch_deref_entry_point(jp->entry); + + /* Verify probepoint is a function entry point */ + if (kallsyms_lookup_size_offset(addr, NULL, &offset) && + offset == 0) { + jp->kp.pre_handler = setjmp_pre_handler; + jp->kp.break_handler = longjmp_break_handler; + ret = register_kprobe(&jp->kp); + } else + ret = -EINVAL; + + if (ret < 0) { + if (i > 0) + unregister_jprobes(jps, i); + break; + } + } + return ret; +} +EXPORT_SYMBOL_GPL(register_jprobes); + +int register_jprobe(struct jprobe *jp) +{ + return register_jprobes(&jp, 1); +} +EXPORT_SYMBOL_GPL(register_jprobe); + +void unregister_jprobe(struct jprobe *jp) +{ + unregister_jprobes(&jp, 1); +} +EXPORT_SYMBOL_GPL(unregister_jprobe); + +void unregister_jprobes(struct jprobe **jps, int num) +{ + int i; + + if (num <= 0) + return; + mutex_lock(&kprobe_mutex); + for (i = 0; i < num; i++) + if (__unregister_kprobe_top(&jps[i]->kp) < 0) + jps[i]->kp.addr = NULL; + mutex_unlock(&kprobe_mutex); + + synchronize_sched(); + for (i = 0; i < num; i++) { + if (jps[i]->kp.addr) + __unregister_kprobe_bottom(&jps[i]->kp); + } +} +EXPORT_SYMBOL_GPL(unregister_jprobes); + +#ifdef CONFIG_KRETPROBES +/* + * This kprobe pre_handler is registered with every kretprobe. When probe + * hits it will set up the return probe. + */ +static int pre_handler_kretprobe(struct kprobe *p, struct pt_regs *regs) +{ + struct kretprobe *rp = container_of(p, struct kretprobe, kp); + unsigned long hash, flags = 0; + struct kretprobe_instance *ri; + + /* + * To avoid deadlocks, prohibit return probing in NMI contexts, + * just skip the probe and increase the (inexact) 'nmissed' + * statistical counter, so that the user is informed that + * something happened: + */ + if (unlikely(in_nmi())) { + rp->nmissed++; + return 0; + } + + /* TODO: consider to only swap the RA after the last pre_handler fired */ + hash = hash_ptr(current, KPROBE_HASH_BITS); + raw_spin_lock_irqsave(&rp->lock, flags); + if (!hlist_empty(&rp->free_instances)) { + ri = hlist_entry(rp->free_instances.first, + struct kretprobe_instance, hlist); + hlist_del(&ri->hlist); + raw_spin_unlock_irqrestore(&rp->lock, flags); + + ri->rp = rp; + ri->task = current; + + if (rp->entry_handler && rp->entry_handler(ri, regs)) { + raw_spin_lock_irqsave(&rp->lock, flags); + hlist_add_head(&ri->hlist, &rp->free_instances); + raw_spin_unlock_irqrestore(&rp->lock, flags); + return 0; + } + + arch_prepare_kretprobe(ri, regs); + + /* XXX(hch): why is there no hlist_move_head? */ + INIT_HLIST_NODE(&ri->hlist); + kretprobe_table_lock(hash, &flags); + hlist_add_head(&ri->hlist, &kretprobe_inst_table[hash]); + kretprobe_table_unlock(hash, &flags); + } else { + rp->nmissed++; + raw_spin_unlock_irqrestore(&rp->lock, flags); + } + return 0; +} +NOKPROBE_SYMBOL(pre_handler_kretprobe); + +int register_kretprobe(struct kretprobe *rp) +{ + int ret = 0; + struct kretprobe_instance *inst; + int i; + void *addr; + + if (kretprobe_blacklist_size) { + addr = kprobe_addr(&rp->kp); + if (IS_ERR(addr)) + return PTR_ERR(addr); + + for (i = 0; kretprobe_blacklist[i].name != NULL; i++) { + if (kretprobe_blacklist[i].addr == addr) + return -EINVAL; + } + } + + rp->kp.pre_handler = pre_handler_kretprobe; + rp->kp.post_handler = NULL; + rp->kp.fault_handler = NULL; + rp->kp.break_handler = NULL; + + /* Pre-allocate memory for max kretprobe instances */ + if (rp->maxactive <= 0) { +#ifdef CONFIG_PREEMPT + rp->maxactive = max_t(unsigned int, 10, 2*num_possible_cpus()); +#else + rp->maxactive = num_possible_cpus(); +#endif + } + raw_spin_lock_init(&rp->lock); + INIT_HLIST_HEAD(&rp->free_instances); + for (i = 0; i < rp->maxactive; i++) { + inst = kmalloc(sizeof(struct kretprobe_instance) + + rp->data_size, GFP_KERNEL); + if (inst == NULL) { + free_rp_inst(rp); + return -ENOMEM; + } + INIT_HLIST_NODE(&inst->hlist); + hlist_add_head(&inst->hlist, &rp->free_instances); + } + + rp->nmissed = 0; + /* Establish function entry probe point */ + ret = register_kprobe(&rp->kp); + if (ret != 0) + free_rp_inst(rp); + return ret; +} +EXPORT_SYMBOL_GPL(register_kretprobe); + +int register_kretprobes(struct kretprobe **rps, int num) +{ + int ret = 0, i; + + if (num <= 0) + return -EINVAL; + for (i = 0; i < num; i++) { + ret = register_kretprobe(rps[i]); + if (ret < 0) { + if (i > 0) + unregister_kretprobes(rps, i); + break; + } + } + return ret; +} +EXPORT_SYMBOL_GPL(register_kretprobes); + +void unregister_kretprobe(struct kretprobe *rp) +{ + unregister_kretprobes(&rp, 1); +} +EXPORT_SYMBOL_GPL(unregister_kretprobe); + +void unregister_kretprobes(struct kretprobe **rps, int num) +{ + int i; + + if (num <= 0) + return; + mutex_lock(&kprobe_mutex); + for (i = 0; i < num; i++) + if (__unregister_kprobe_top(&rps[i]->kp) < 0) + rps[i]->kp.addr = NULL; + mutex_unlock(&kprobe_mutex); + + synchronize_sched(); + for (i = 0; i < num; i++) { + if (rps[i]->kp.addr) { + __unregister_kprobe_bottom(&rps[i]->kp); + cleanup_rp_inst(rps[i]); + } + } +} +EXPORT_SYMBOL_GPL(unregister_kretprobes); + +#else /* CONFIG_KRETPROBES */ +int register_kretprobe(struct kretprobe *rp) +{ + return -ENOSYS; +} +EXPORT_SYMBOL_GPL(register_kretprobe); + +int register_kretprobes(struct kretprobe **rps, int num) +{ + return -ENOSYS; +} +EXPORT_SYMBOL_GPL(register_kretprobes); + +void unregister_kretprobe(struct kretprobe *rp) +{ +} +EXPORT_SYMBOL_GPL(unregister_kretprobe); + +void unregister_kretprobes(struct kretprobe **rps, int num) +{ +} +EXPORT_SYMBOL_GPL(unregister_kretprobes); + +static int pre_handler_kretprobe(struct kprobe *p, struct pt_regs *regs) +{ + return 0; +} +NOKPROBE_SYMBOL(pre_handler_kretprobe); + +#endif /* CONFIG_KRETPROBES */ + +/* Set the kprobe gone and remove its instruction buffer. */ +static void kill_kprobe(struct kprobe *p) +{ + struct kprobe *kp; + + p->flags |= KPROBE_FLAG_GONE; + if (kprobe_aggrprobe(p)) { + /* + * If this is an aggr_kprobe, we have to list all the + * chained probes and mark them GONE. + */ + list_for_each_entry_rcu(kp, &p->list, list) + kp->flags |= KPROBE_FLAG_GONE; + p->post_handler = NULL; + p->break_handler = NULL; + kill_optimized_kprobe(p); + } + /* + * Here, we can remove insn_slot safely, because no thread calls + * the original probed function (which will be freed soon) any more. + */ + arch_remove_kprobe(p); +} + +/* Disable one kprobe */ +int disable_kprobe(struct kprobe *kp) +{ + int ret = 0; + + mutex_lock(&kprobe_mutex); + + /* Disable this kprobe */ + if (__disable_kprobe(kp) == NULL) + ret = -EINVAL; + + mutex_unlock(&kprobe_mutex); + return ret; +} +EXPORT_SYMBOL_GPL(disable_kprobe); + +/* Enable one kprobe */ +int enable_kprobe(struct kprobe *kp) +{ + int ret = 0; + struct kprobe *p; + + mutex_lock(&kprobe_mutex); + + /* Check whether specified probe is valid. */ + p = __get_valid_kprobe(kp); + if (unlikely(p == NULL)) { + ret = -EINVAL; + goto out; + } + + if (kprobe_gone(kp)) { + /* This kprobe has gone, we couldn't enable it. */ + ret = -EINVAL; + goto out; + } + + if (p != kp) + kp->flags &= ~KPROBE_FLAG_DISABLED; + + if (!kprobes_all_disarmed && kprobe_disabled(p)) { + p->flags &= ~KPROBE_FLAG_DISABLED; + arm_kprobe(p); + } +out: + mutex_unlock(&kprobe_mutex); + return ret; +} +EXPORT_SYMBOL_GPL(enable_kprobe); + +void dump_kprobe(struct kprobe *kp) +{ + printk(KERN_WARNING "Dumping kprobe:\n"); + printk(KERN_WARNING "Name: %s\nAddress: %p\nOffset: %x\n", + kp->symbol_name, kp->addr, kp->offset); +} +NOKPROBE_SYMBOL(dump_kprobe); + +/* + * Lookup and populate the kprobe_blacklist. + * + * Unlike the kretprobe blacklist, we'll need to determine + * the range of addresses that belong to the said functions, + * since a kprobe need not necessarily be at the beginning + * of a function. + */ +static int __init populate_kprobe_blacklist(unsigned long *start, + unsigned long *end) +{ + unsigned long *iter; + struct kprobe_blacklist_entry *ent; + unsigned long entry, offset = 0, size = 0; + + for (iter = start; iter < end; iter++) { + entry = arch_deref_entry_point((void *)*iter); + + if (!kernel_text_address(entry) || + !kallsyms_lookup_size_offset(entry, &size, &offset)) { + pr_err("Failed to find blacklist at %p\n", + (void *)entry); + continue; + } + + ent = kmalloc(sizeof(*ent), GFP_KERNEL); + if (!ent) + return -ENOMEM; + ent->start_addr = entry; + ent->end_addr = entry + size; + INIT_LIST_HEAD(&ent->list); + list_add_tail(&ent->list, &kprobe_blacklist); + } + return 0; +} + +/* Module notifier call back, checking kprobes on the module */ +static int kprobes_module_callback(struct notifier_block *nb, + unsigned long val, void *data) +{ + struct module *mod = data; + struct hlist_head *head; + struct kprobe *p; + unsigned int i; + int checkcore = (val == MODULE_STATE_GOING); + + if (val != MODULE_STATE_GOING && val != MODULE_STATE_LIVE) + return NOTIFY_DONE; + + /* + * When MODULE_STATE_GOING was notified, both of module .text and + * .init.text sections would be freed. When MODULE_STATE_LIVE was + * notified, only .init.text section would be freed. We need to + * disable kprobes which have been inserted in the sections. + */ + mutex_lock(&kprobe_mutex); + for (i = 0; i < KPROBE_TABLE_SIZE; i++) { + head = &kprobe_table[i]; + hlist_for_each_entry_rcu(p, head, hlist) + if (within_module_init((unsigned long)p->addr, mod) || + (checkcore && + within_module_core((unsigned long)p->addr, mod))) { + /* + * The vaddr this probe is installed will soon + * be vfreed buy not synced to disk. Hence, + * disarming the breakpoint isn't needed. + */ + kill_kprobe(p); + } + } + mutex_unlock(&kprobe_mutex); + return NOTIFY_DONE; +} + +static struct notifier_block kprobe_module_nb = { + .notifier_call = kprobes_module_callback, + .priority = 0 +}; + +/* Markers of _kprobe_blacklist section */ +extern unsigned long __start_kprobe_blacklist[]; +extern unsigned long __stop_kprobe_blacklist[]; + +static int __init init_kprobes(void) +{ + int i, err = 0; + + /* FIXME allocate the probe table, currently defined statically */ + /* initialize all list heads */ + for (i = 0; i < KPROBE_TABLE_SIZE; i++) { + INIT_HLIST_HEAD(&kprobe_table[i]); + INIT_HLIST_HEAD(&kretprobe_inst_table[i]); + raw_spin_lock_init(&(kretprobe_table_locks[i].lock)); + } + + err = populate_kprobe_blacklist(__start_kprobe_blacklist, + __stop_kprobe_blacklist); + if (err) { + pr_err("kprobes: failed to populate blacklist: %d\n", err); + pr_err("Please take care of using kprobes.\n"); + } + + if (kretprobe_blacklist_size) { + /* lookup the function address from its name */ + for (i = 0; kretprobe_blacklist[i].name != NULL; i++) { + kprobe_lookup_name(kretprobe_blacklist[i].name, + kretprobe_blacklist[i].addr); + if (!kretprobe_blacklist[i].addr) + printk("kretprobe: lookup failed: %s\n", + kretprobe_blacklist[i].name); + } + } + +#if defined(CONFIG_OPTPROBES) +#if defined(__ARCH_WANT_KPROBES_INSN_SLOT) + /* Init kprobe_optinsn_slots */ + kprobe_optinsn_slots.insn_size = MAX_OPTINSN_SIZE; +#endif + /* By default, kprobes can be optimized */ + kprobes_allow_optimization = true; +#endif + + /* By default, kprobes are armed */ + kprobes_all_disarmed = false; + + err = arch_init_kprobes(); + if (!err) + err = register_die_notifier(&kprobe_exceptions_nb); + if (!err) + err = register_module_notifier(&kprobe_module_nb); + + kprobes_initialized = (err == 0); + + if (!err) + init_test_probes(); + return err; +} + +#ifdef CONFIG_DEBUG_FS +static void report_probe(struct seq_file *pi, struct kprobe *p, + const char *sym, int offset, char *modname, struct kprobe *pp) +{ + char *kprobe_type; + + if (p->pre_handler == pre_handler_kretprobe) + kprobe_type = "r"; + else if (p->pre_handler == setjmp_pre_handler) + kprobe_type = "j"; + else + kprobe_type = "k"; + + if (sym) + seq_printf(pi, "%p %s %s+0x%x %s ", + p->addr, kprobe_type, sym, offset, + (modname ? modname : " ")); + else + seq_printf(pi, "%p %s %p ", + p->addr, kprobe_type, p->addr); + + if (!pp) + pp = p; + seq_printf(pi, "%s%s%s%s\n", + (kprobe_gone(p) ? "[GONE]" : ""), + ((kprobe_disabled(p) && !kprobe_gone(p)) ? "[DISABLED]" : ""), + (kprobe_optimized(pp) ? "[OPTIMIZED]" : ""), + (kprobe_ftrace(pp) ? "[FTRACE]" : "")); +} + +static void *kprobe_seq_start(struct seq_file *f, loff_t *pos) +{ + return (*pos < KPROBE_TABLE_SIZE) ? pos : NULL; +} + +static void *kprobe_seq_next(struct seq_file *f, void *v, loff_t *pos) +{ + (*pos)++; + if (*pos >= KPROBE_TABLE_SIZE) + return NULL; + return pos; +} + +static void kprobe_seq_stop(struct seq_file *f, void *v) +{ + /* Nothing to do */ +} + +static int show_kprobe_addr(struct seq_file *pi, void *v) +{ + struct hlist_head *head; + struct kprobe *p, *kp; + const char *sym = NULL; + unsigned int i = *(loff_t *) v; + unsigned long offset = 0; + char *modname, namebuf[KSYM_NAME_LEN]; + + head = &kprobe_table[i]; + preempt_disable(); + hlist_for_each_entry_rcu(p, head, hlist) { + sym = kallsyms_lookup((unsigned long)p->addr, NULL, + &offset, &modname, namebuf); + if (kprobe_aggrprobe(p)) { + list_for_each_entry_rcu(kp, &p->list, list) + report_probe(pi, kp, sym, offset, modname, p); + } else + report_probe(pi, p, sym, offset, modname, NULL); + } + preempt_enable(); + return 0; +} + +static const struct seq_operations kprobes_seq_ops = { + .start = kprobe_seq_start, + .next = kprobe_seq_next, + .stop = kprobe_seq_stop, + .show = show_kprobe_addr +}; + +static int kprobes_open(struct inode *inode, struct file *filp) +{ + return seq_open(filp, &kprobes_seq_ops); +} + +static const struct file_operations debugfs_kprobes_operations = { + .open = kprobes_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, +}; + +/* kprobes/blacklist -- shows which functions can not be probed */ +static void *kprobe_blacklist_seq_start(struct seq_file *m, loff_t *pos) +{ + return seq_list_start(&kprobe_blacklist, *pos); +} + +static void *kprobe_blacklist_seq_next(struct seq_file *m, void *v, loff_t *pos) +{ + return seq_list_next(v, &kprobe_blacklist, pos); +} + +static int kprobe_blacklist_seq_show(struct seq_file *m, void *v) +{ + struct kprobe_blacklist_entry *ent = + list_entry(v, struct kprobe_blacklist_entry, list); + + seq_printf(m, "0x%p-0x%p\t%ps\n", (void *)ent->start_addr, + (void *)ent->end_addr, (void *)ent->start_addr); + return 0; +} + +static const struct seq_operations kprobe_blacklist_seq_ops = { + .start = kprobe_blacklist_seq_start, + .next = kprobe_blacklist_seq_next, + .stop = kprobe_seq_stop, /* Reuse void function */ + .show = kprobe_blacklist_seq_show, +}; + +static int kprobe_blacklist_open(struct inode *inode, struct file *filp) +{ + return seq_open(filp, &kprobe_blacklist_seq_ops); +} + +static const struct file_operations debugfs_kprobe_blacklist_ops = { + .open = kprobe_blacklist_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, +}; + +static void arm_all_kprobes(void) +{ + struct hlist_head *head; + struct kprobe *p; + unsigned int i; + + mutex_lock(&kprobe_mutex); + + /* If kprobes are armed, just return */ + if (!kprobes_all_disarmed) + goto already_enabled; + + /* + * optimize_kprobe() called by arm_kprobe() checks + * kprobes_all_disarmed, so set kprobes_all_disarmed before + * arm_kprobe. + */ + kprobes_all_disarmed = false; + /* Arming kprobes doesn't optimize kprobe itself */ + for (i = 0; i < KPROBE_TABLE_SIZE; i++) { + head = &kprobe_table[i]; + hlist_for_each_entry_rcu(p, head, hlist) + if (!kprobe_disabled(p)) + arm_kprobe(p); + } + + printk(KERN_INFO "Kprobes globally enabled\n"); + +already_enabled: + mutex_unlock(&kprobe_mutex); + return; +} + +static void disarm_all_kprobes(void) +{ + struct hlist_head *head; + struct kprobe *p; + unsigned int i; + + mutex_lock(&kprobe_mutex); + + /* If kprobes are already disarmed, just return */ + if (kprobes_all_disarmed) { + mutex_unlock(&kprobe_mutex); + return; + } + + kprobes_all_disarmed = true; + printk(KERN_INFO "Kprobes globally disabled\n"); + + for (i = 0; i < KPROBE_TABLE_SIZE; i++) { + head = &kprobe_table[i]; + hlist_for_each_entry_rcu(p, head, hlist) { + if (!arch_trampoline_kprobe(p) && !kprobe_disabled(p)) + disarm_kprobe(p, false); + } + } + mutex_unlock(&kprobe_mutex); + + /* Wait for disarming all kprobes by optimizer */ + wait_for_kprobe_optimizer(); +} + +/* + * XXX: The debugfs bool file interface doesn't allow for callbacks + * when the bool state is switched. We can reuse that facility when + * available + */ +static ssize_t read_enabled_file_bool(struct file *file, + char __user *user_buf, size_t count, loff_t *ppos) +{ + char buf[3]; + + if (!kprobes_all_disarmed) + buf[0] = '1'; + else + buf[0] = '0'; + buf[1] = '\n'; + buf[2] = 0x00; + return simple_read_from_buffer(user_buf, count, ppos, buf, 2); +} + +static ssize_t write_enabled_file_bool(struct file *file, + const char __user *user_buf, size_t count, loff_t *ppos) +{ + char buf[32]; + size_t buf_size; + + buf_size = min(count, (sizeof(buf)-1)); + if (copy_from_user(buf, user_buf, buf_size)) + return -EFAULT; + + buf[buf_size] = '\0'; + switch (buf[0]) { + case 'y': + case 'Y': + case '1': + arm_all_kprobes(); + break; + case 'n': + case 'N': + case '0': + disarm_all_kprobes(); + break; + default: + return -EINVAL; + } + + return count; +} + +static const struct file_operations fops_kp = { + .read = read_enabled_file_bool, + .write = write_enabled_file_bool, + .llseek = default_llseek, +}; + +static int __init debugfs_kprobe_init(void) +{ + struct dentry *dir, *file; + unsigned int value = 1; + + dir = debugfs_create_dir("kprobes", NULL); + if (!dir) + return -ENOMEM; + + file = debugfs_create_file("list", 0444, dir, NULL, + &debugfs_kprobes_operations); + if (!file) + goto error; + + file = debugfs_create_file("enabled", 0600, dir, + &value, &fops_kp); + if (!file) + goto error; + + file = debugfs_create_file("blacklist", 0444, dir, NULL, + &debugfs_kprobe_blacklist_ops); + if (!file) + goto error; + + return 0; + +error: + debugfs_remove(dir); + return -ENOMEM; +} + +late_initcall(debugfs_kprobe_init); +#endif /* CONFIG_DEBUG_FS */ + +module_init(init_kprobes); + +/* defined in arch/.../kernel/kprobes.c */ +EXPORT_SYMBOL_GPL(jprobe_return); diff --git a/kernel/kernel/ksysfs.c b/kernel/kernel/ksysfs.c new file mode 100644 index 000000000..d6fc8eeaa --- /dev/null +++ b/kernel/kernel/ksysfs.c @@ -0,0 +1,255 @@ +/* + * kernel/ksysfs.c - sysfs attributes in /sys/kernel, which + * are not related to any other subsystem + * + * Copyright (C) 2004 Kay Sievers + * + * This file is release under the GPLv2 + * + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include /* rcu_expedited */ + +#define KERNEL_ATTR_RO(_name) \ +static struct kobj_attribute _name##_attr = __ATTR_RO(_name) + +#define KERNEL_ATTR_RW(_name) \ +static struct kobj_attribute _name##_attr = \ + __ATTR(_name, 0644, _name##_show, _name##_store) + +/* current uevent sequence number */ +static ssize_t uevent_seqnum_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return sprintf(buf, "%llu\n", (unsigned long long)uevent_seqnum); +} +KERNEL_ATTR_RO(uevent_seqnum); + +#ifdef CONFIG_UEVENT_HELPER +/* uevent helper program, used during early boot */ +static ssize_t uevent_helper_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return sprintf(buf, "%s\n", uevent_helper); +} +static ssize_t uevent_helper_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) +{ + if (count+1 > UEVENT_HELPER_PATH_LEN) + return -ENOENT; + memcpy(uevent_helper, buf, count); + uevent_helper[count] = '\0'; + if (count && uevent_helper[count-1] == '\n') + uevent_helper[count-1] = '\0'; + return count; +} +KERNEL_ATTR_RW(uevent_helper); +#endif + +#ifdef CONFIG_PROFILING +static ssize_t profiling_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return sprintf(buf, "%d\n", prof_on); +} +static ssize_t profiling_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) +{ + int ret; + + if (prof_on) + return -EEXIST; + /* + * This eventually calls into get_option() which + * has a ton of callers and is not const. It is + * easiest to cast it away here. + */ + profile_setup((char *)buf); + ret = profile_init(); + if (ret) + return ret; + ret = create_proc_profile(); + if (ret) + return ret; + return count; +} +KERNEL_ATTR_RW(profiling); +#endif + +#ifdef CONFIG_KEXEC +static ssize_t kexec_loaded_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return sprintf(buf, "%d\n", !!kexec_image); +} +KERNEL_ATTR_RO(kexec_loaded); + +static ssize_t kexec_crash_loaded_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return sprintf(buf, "%d\n", !!kexec_crash_image); +} +KERNEL_ATTR_RO(kexec_crash_loaded); + +static ssize_t kexec_crash_size_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return sprintf(buf, "%zu\n", crash_get_memory_size()); +} +static ssize_t kexec_crash_size_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) +{ + unsigned long cnt; + int ret; + + if (kstrtoul(buf, 0, &cnt)) + return -EINVAL; + + ret = crash_shrink_memory(cnt); + return ret < 0 ? ret : count; +} +KERNEL_ATTR_RW(kexec_crash_size); + +static ssize_t vmcoreinfo_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return sprintf(buf, "%lx %x\n", + paddr_vmcoreinfo_note(), + (unsigned int)sizeof(vmcoreinfo_note)); +} +KERNEL_ATTR_RO(vmcoreinfo); + +#endif /* CONFIG_KEXEC */ + +#if defined(CONFIG_PREEMPT_RT_FULL) +static ssize_t realtime_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return sprintf(buf, "%d\n", 1); +} +KERNEL_ATTR_RO(realtime); +#endif + +/* whether file capabilities are enabled */ +static ssize_t fscaps_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return sprintf(buf, "%d\n", file_caps_enabled); +} +KERNEL_ATTR_RO(fscaps); + +int rcu_expedited; +static ssize_t rcu_expedited_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return sprintf(buf, "%d\n", rcu_expedited); +} +static ssize_t rcu_expedited_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) +{ + if (kstrtoint(buf, 0, &rcu_expedited)) + return -EINVAL; + + return count; +} +KERNEL_ATTR_RW(rcu_expedited); + +/* + * Make /sys/kernel/notes give the raw contents of our kernel .notes section. + */ +extern const void __start_notes __weak; +extern const void __stop_notes __weak; +#define notes_size (&__stop_notes - &__start_notes) + +static ssize_t notes_read(struct file *filp, struct kobject *kobj, + struct bin_attribute *bin_attr, + char *buf, loff_t off, size_t count) +{ + memcpy(buf, &__start_notes + off, count); + return count; +} + +static struct bin_attribute notes_attr = { + .attr = { + .name = "notes", + .mode = S_IRUGO, + }, + .read = ¬es_read, +}; + +struct kobject *kernel_kobj; +EXPORT_SYMBOL_GPL(kernel_kobj); + +static struct attribute * kernel_attrs[] = { + &fscaps_attr.attr, + &uevent_seqnum_attr.attr, +#ifdef CONFIG_UEVENT_HELPER + &uevent_helper_attr.attr, +#endif +#ifdef CONFIG_PROFILING + &profiling_attr.attr, +#endif +#ifdef CONFIG_KEXEC + &kexec_loaded_attr.attr, + &kexec_crash_loaded_attr.attr, + &kexec_crash_size_attr.attr, + &vmcoreinfo_attr.attr, +#endif + &rcu_expedited_attr.attr, +#ifdef CONFIG_PREEMPT_RT_FULL + &realtime_attr.attr, +#endif + NULL +}; + +static struct attribute_group kernel_attr_group = { + .attrs = kernel_attrs, +}; + +static int __init ksysfs_init(void) +{ + int error; + + kernel_kobj = kobject_create_and_add("kernel", NULL); + if (!kernel_kobj) { + error = -ENOMEM; + goto exit; + } + error = sysfs_create_group(kernel_kobj, &kernel_attr_group); + if (error) + goto kset_exit; + + if (notes_size > 0) { + notes_attr.size = notes_size; + error = sysfs_create_bin_file(kernel_kobj, ¬es_attr); + if (error) + goto group_exit; + } + + return 0; + +group_exit: + sysfs_remove_group(kernel_kobj, &kernel_attr_group); +kset_exit: + kobject_put(kernel_kobj); +exit: + return error; +} + +core_initcall(ksysfs_init); diff --git a/kernel/kernel/kthread.c b/kernel/kernel/kthread.c new file mode 100644 index 000000000..10e489c44 --- /dev/null +++ b/kernel/kernel/kthread.c @@ -0,0 +1,692 @@ +/* Kernel thread helper functions. + * Copyright (C) 2004 IBM Corporation, Rusty Russell. + * + * Creation is done via kthreadd, so that we get a clean environment + * even if we're invoked from userspace (think modprobe, hotplug cpu, + * etc.). + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +static DEFINE_SPINLOCK(kthread_create_lock); +static LIST_HEAD(kthread_create_list); +struct task_struct *kthreadd_task; + +struct kthread_create_info +{ + /* Information passed to kthread() from kthreadd. */ + int (*threadfn)(void *data); + void *data; + int node; + + /* Result passed back to kthread_create() from kthreadd. */ + struct task_struct *result; + struct completion *done; + + struct list_head list; +}; + +struct kthread { + unsigned long flags; + unsigned int cpu; + void *data; + struct completion parked; + struct completion exited; +}; + +enum KTHREAD_BITS { + KTHREAD_IS_PER_CPU = 0, + KTHREAD_SHOULD_STOP, + KTHREAD_SHOULD_PARK, + KTHREAD_IS_PARKED, +}; + +#define __to_kthread(vfork) \ + container_of(vfork, struct kthread, exited) + +static inline struct kthread *to_kthread(struct task_struct *k) +{ + return __to_kthread(k->vfork_done); +} + +static struct kthread *to_live_kthread(struct task_struct *k) +{ + struct completion *vfork = ACCESS_ONCE(k->vfork_done); + if (likely(vfork)) + return __to_kthread(vfork); + return NULL; +} + +/** + * kthread_should_stop - should this kthread return now? + * + * When someone calls kthread_stop() on your kthread, it will be woken + * and this will return true. You should then return, and your return + * value will be passed through to kthread_stop(). + */ +bool kthread_should_stop(void) +{ + return test_bit(KTHREAD_SHOULD_STOP, &to_kthread(current)->flags); +} +EXPORT_SYMBOL(kthread_should_stop); + +/** + * kthread_should_park - should this kthread park now? + * + * When someone calls kthread_park() on your kthread, it will be woken + * and this will return true. You should then do the necessary + * cleanup and call kthread_parkme() + * + * Similar to kthread_should_stop(), but this keeps the thread alive + * and in a park position. kthread_unpark() "restarts" the thread and + * calls the thread function again. + */ +bool kthread_should_park(void) +{ + return test_bit(KTHREAD_SHOULD_PARK, &to_kthread(current)->flags); +} + +/** + * kthread_freezable_should_stop - should this freezable kthread return now? + * @was_frozen: optional out parameter, indicates whether %current was frozen + * + * kthread_should_stop() for freezable kthreads, which will enter + * refrigerator if necessary. This function is safe from kthread_stop() / + * freezer deadlock and freezable kthreads should use this function instead + * of calling try_to_freeze() directly. + */ +bool kthread_freezable_should_stop(bool *was_frozen) +{ + bool frozen = false; + + might_sleep(); + + if (unlikely(freezing(current))) + frozen = __refrigerator(true); + + if (was_frozen) + *was_frozen = frozen; + + return kthread_should_stop(); +} +EXPORT_SYMBOL_GPL(kthread_freezable_should_stop); + +/** + * kthread_data - return data value specified on kthread creation + * @task: kthread task in question + * + * Return the data value specified when kthread @task was created. + * The caller is responsible for ensuring the validity of @task when + * calling this function. + */ +void *kthread_data(struct task_struct *task) +{ + return to_kthread(task)->data; +} + +/** + * probe_kthread_data - speculative version of kthread_data() + * @task: possible kthread task in question + * + * @task could be a kthread task. Return the data value specified when it + * was created if accessible. If @task isn't a kthread task or its data is + * inaccessible for any reason, %NULL is returned. This function requires + * that @task itself is safe to dereference. + */ +void *probe_kthread_data(struct task_struct *task) +{ + struct kthread *kthread = to_kthread(task); + void *data = NULL; + + probe_kernel_read(&data, &kthread->data, sizeof(data)); + return data; +} + +static void __kthread_parkme(struct kthread *self) +{ + __set_current_state(TASK_PARKED); + while (test_bit(KTHREAD_SHOULD_PARK, &self->flags)) { + if (!test_and_set_bit(KTHREAD_IS_PARKED, &self->flags)) + complete(&self->parked); + schedule(); + __set_current_state(TASK_PARKED); + } + clear_bit(KTHREAD_IS_PARKED, &self->flags); + __set_current_state(TASK_RUNNING); +} + +void kthread_parkme(void) +{ + __kthread_parkme(to_kthread(current)); +} + +static int kthread(void *_create) +{ + /* Copy data: it's on kthread's stack */ + struct kthread_create_info *create = _create; + int (*threadfn)(void *data) = create->threadfn; + void *data = create->data; + struct completion *done; + struct kthread self; + int ret; + + self.flags = 0; + self.data = data; + init_completion(&self.exited); + init_completion(&self.parked); + current->vfork_done = &self.exited; + + /* If user was SIGKILLed, I release the structure. */ + done = xchg(&create->done, NULL); + if (!done) { + kfree(create); + do_exit(-EINTR); + } + /* OK, tell user we're spawned, wait for stop or wakeup */ + __set_current_state(TASK_UNINTERRUPTIBLE); + create->result = current; + complete(done); + schedule(); + + ret = -EINTR; + + if (!test_bit(KTHREAD_SHOULD_STOP, &self.flags)) { + __kthread_parkme(&self); + ret = threadfn(data); + } + /* we can't just return, we must preserve "self" on stack */ + do_exit(ret); +} + +/* called from do_fork() to get node information for about to be created task */ +int tsk_fork_get_node(struct task_struct *tsk) +{ +#ifdef CONFIG_NUMA + if (tsk == kthreadd_task) + return tsk->pref_node_fork; +#endif + return NUMA_NO_NODE; +} + +static void create_kthread(struct kthread_create_info *create) +{ + int pid; + +#ifdef CONFIG_NUMA + current->pref_node_fork = create->node; +#endif + /* We want our own signal handler (we take no signals by default). */ + pid = kernel_thread(kthread, create, CLONE_FS | CLONE_FILES | SIGCHLD); + if (pid < 0) { + /* If user was SIGKILLed, I release the structure. */ + struct completion *done = xchg(&create->done, NULL); + + if (!done) { + kfree(create); + return; + } + create->result = ERR_PTR(pid); + complete(done); + } +} + +/** + * kthread_create_on_node - create a kthread. + * @threadfn: the function to run until signal_pending(current). + * @data: data ptr for @threadfn. + * @node: memory node number. + * @namefmt: printf-style name for the thread. + * + * Description: This helper function creates and names a kernel + * thread. The thread will be stopped: use wake_up_process() to start + * it. See also kthread_run(). + * + * If thread is going to be bound on a particular cpu, give its node + * in @node, to get NUMA affinity for kthread stack, or else give -1. + * When woken, the thread will run @threadfn() with @data as its + * argument. @threadfn() can either call do_exit() directly if it is a + * standalone thread for which no one will call kthread_stop(), or + * return when 'kthread_should_stop()' is true (which means + * kthread_stop() has been called). The return value should be zero + * or a negative error number; it will be passed to kthread_stop(). + * + * Returns a task_struct or ERR_PTR(-ENOMEM) or ERR_PTR(-EINTR). + */ +struct task_struct *kthread_create_on_node(int (*threadfn)(void *data), + void *data, int node, + const char namefmt[], + ...) +{ + DECLARE_COMPLETION_ONSTACK(done); + struct task_struct *task; + struct kthread_create_info *create = kmalloc(sizeof(*create), + GFP_KERNEL); + + if (!create) + return ERR_PTR(-ENOMEM); + create->threadfn = threadfn; + create->data = data; + create->node = node; + create->done = &done; + + spin_lock(&kthread_create_lock); + list_add_tail(&create->list, &kthread_create_list); + spin_unlock(&kthread_create_lock); + + wake_up_process(kthreadd_task); + /* + * Wait for completion in killable state, for I might be chosen by + * the OOM killer while kthreadd is trying to allocate memory for + * new kernel thread. + */ + if (unlikely(wait_for_completion_killable(&done))) { + /* + * If I was SIGKILLed before kthreadd (or new kernel thread) + * calls complete(), leave the cleanup of this structure to + * that thread. + */ + if (xchg(&create->done, NULL)) + return ERR_PTR(-EINTR); + /* + * kthreadd (or new kernel thread) will call complete() + * shortly. + */ + wait_for_completion(&done); + } + task = create->result; + if (!IS_ERR(task)) { + static const struct sched_param param = { .sched_priority = 0 }; + va_list args; + + va_start(args, namefmt); + vsnprintf(task->comm, sizeof(task->comm), namefmt, args); + va_end(args); + /* + * root may have changed our (kthreadd's) priority or CPU mask. + * The kernel thread should not inherit these properties. + */ + sched_setscheduler_nocheck(task, SCHED_NORMAL, ¶m); + set_cpus_allowed_ptr(task, cpu_all_mask); + } + kfree(create); + return task; +} +EXPORT_SYMBOL(kthread_create_on_node); + +static void __kthread_bind(struct task_struct *p, unsigned int cpu, long state) +{ + /* Must have done schedule() in kthread() before we set_task_cpu */ + if (!wait_task_inactive(p, state)) { + WARN_ON(1); + return; + } + /* It's safe because the task is inactive. */ + do_set_cpus_allowed(p, cpumask_of(cpu)); + p->flags |= PF_NO_SETAFFINITY; +} + +/** + * kthread_bind - bind a just-created kthread to a cpu. + * @p: thread created by kthread_create(). + * @cpu: cpu (might not be online, must be possible) for @k to run on. + * + * Description: This function is equivalent to set_cpus_allowed(), + * except that @cpu doesn't need to be online, and the thread must be + * stopped (i.e., just returned from kthread_create()). + */ +void kthread_bind(struct task_struct *p, unsigned int cpu) +{ + __kthread_bind(p, cpu, TASK_UNINTERRUPTIBLE); +} +EXPORT_SYMBOL(kthread_bind); + +/** + * kthread_create_on_cpu - Create a cpu bound kthread + * @threadfn: the function to run until signal_pending(current). + * @data: data ptr for @threadfn. + * @cpu: The cpu on which the thread should be bound, + * @namefmt: printf-style name for the thread. Format is restricted + * to "name.*%u". Code fills in cpu number. + * + * Description: This helper function creates and names a kernel thread + * The thread will be woken and put into park mode. + */ +struct task_struct *kthread_create_on_cpu(int (*threadfn)(void *data), + void *data, unsigned int cpu, + const char *namefmt) +{ + struct task_struct *p; + + p = kthread_create_on_node(threadfn, data, cpu_to_node(cpu), namefmt, + cpu); + if (IS_ERR(p)) + return p; + set_bit(KTHREAD_IS_PER_CPU, &to_kthread(p)->flags); + to_kthread(p)->cpu = cpu; + /* Park the thread to get it out of TASK_UNINTERRUPTIBLE state */ + kthread_park(p); + return p; +} + +static void __kthread_unpark(struct task_struct *k, struct kthread *kthread) +{ + clear_bit(KTHREAD_SHOULD_PARK, &kthread->flags); + /* + * We clear the IS_PARKED bit here as we don't wait + * until the task has left the park code. So if we'd + * park before that happens we'd see the IS_PARKED bit + * which might be about to be cleared. + */ + if (test_and_clear_bit(KTHREAD_IS_PARKED, &kthread->flags)) { + if (test_bit(KTHREAD_IS_PER_CPU, &kthread->flags)) + __kthread_bind(k, kthread->cpu, TASK_PARKED); + wake_up_state(k, TASK_PARKED); + } +} + +/** + * kthread_unpark - unpark a thread created by kthread_create(). + * @k: thread created by kthread_create(). + * + * Sets kthread_should_park() for @k to return false, wakes it, and + * waits for it to return. If the thread is marked percpu then its + * bound to the cpu again. + */ +void kthread_unpark(struct task_struct *k) +{ + struct kthread *kthread = to_live_kthread(k); + + if (kthread) + __kthread_unpark(k, kthread); +} + +/** + * kthread_park - park a thread created by kthread_create(). + * @k: thread created by kthread_create(). + * + * Sets kthread_should_park() for @k to return true, wakes it, and + * waits for it to return. This can also be called after kthread_create() + * instead of calling wake_up_process(): the thread will park without + * calling threadfn(). + * + * Returns 0 if the thread is parked, -ENOSYS if the thread exited. + * If called by the kthread itself just the park bit is set. + */ +int kthread_park(struct task_struct *k) +{ + struct kthread *kthread = to_live_kthread(k); + int ret = -ENOSYS; + + if (kthread) { + if (!test_bit(KTHREAD_IS_PARKED, &kthread->flags)) { + set_bit(KTHREAD_SHOULD_PARK, &kthread->flags); + if (k != current) { + wake_up_process(k); + wait_for_completion(&kthread->parked); + } + } + ret = 0; + } + return ret; +} + +/** + * kthread_stop - stop a thread created by kthread_create(). + * @k: thread created by kthread_create(). + * + * Sets kthread_should_stop() for @k to return true, wakes it, and + * waits for it to exit. This can also be called after kthread_create() + * instead of calling wake_up_process(): the thread will exit without + * calling threadfn(). + * + * If threadfn() may call do_exit() itself, the caller must ensure + * task_struct can't go away. + * + * Returns the result of threadfn(), or %-EINTR if wake_up_process() + * was never called. + */ +int kthread_stop(struct task_struct *k) +{ + struct kthread *kthread; + int ret; + + trace_sched_kthread_stop(k); + + get_task_struct(k); + kthread = to_live_kthread(k); + if (kthread) { + set_bit(KTHREAD_SHOULD_STOP, &kthread->flags); + __kthread_unpark(k, kthread); + wake_up_process(k); + wait_for_completion(&kthread->exited); + } + ret = k->exit_code; + put_task_struct(k); + + trace_sched_kthread_stop_ret(ret); + return ret; +} +EXPORT_SYMBOL(kthread_stop); + +int kthreadd(void *unused) +{ + struct task_struct *tsk = current; + + /* Setup a clean context for our children to inherit. */ + set_task_comm(tsk, "kthreadd"); + ignore_signals(tsk); + set_cpus_allowed_ptr(tsk, cpu_all_mask); + set_mems_allowed(node_states[N_MEMORY]); + + current->flags |= PF_NOFREEZE; + + for (;;) { + set_current_state(TASK_INTERRUPTIBLE); + if (list_empty(&kthread_create_list)) + schedule(); + __set_current_state(TASK_RUNNING); + + spin_lock(&kthread_create_lock); + while (!list_empty(&kthread_create_list)) { + struct kthread_create_info *create; + + create = list_entry(kthread_create_list.next, + struct kthread_create_info, list); + list_del_init(&create->list); + spin_unlock(&kthread_create_lock); + + create_kthread(create); + + spin_lock(&kthread_create_lock); + } + spin_unlock(&kthread_create_lock); + } + + return 0; +} + +void __init_kthread_worker(struct kthread_worker *worker, + const char *name, + struct lock_class_key *key) +{ + spin_lock_init(&worker->lock); + lockdep_set_class_and_name(&worker->lock, key, name); + INIT_LIST_HEAD(&worker->work_list); + worker->task = NULL; +} +EXPORT_SYMBOL_GPL(__init_kthread_worker); + +/** + * kthread_worker_fn - kthread function to process kthread_worker + * @worker_ptr: pointer to initialized kthread_worker + * + * This function can be used as @threadfn to kthread_create() or + * kthread_run() with @worker_ptr argument pointing to an initialized + * kthread_worker. The started kthread will process work_list until + * the it is stopped with kthread_stop(). A kthread can also call + * this function directly after extra initialization. + * + * Different kthreads can be used for the same kthread_worker as long + * as there's only one kthread attached to it at any given time. A + * kthread_worker without an attached kthread simply collects queued + * kthread_works. + */ +int kthread_worker_fn(void *worker_ptr) +{ + struct kthread_worker *worker = worker_ptr; + struct kthread_work *work; + + WARN_ON(worker->task); + worker->task = current; +repeat: + set_current_state(TASK_INTERRUPTIBLE); /* mb paired w/ kthread_stop */ + + if (kthread_should_stop()) { + __set_current_state(TASK_RUNNING); + spin_lock_irq(&worker->lock); + worker->task = NULL; + spin_unlock_irq(&worker->lock); + return 0; + } + + work = NULL; + spin_lock_irq(&worker->lock); + if (!list_empty(&worker->work_list)) { + work = list_first_entry(&worker->work_list, + struct kthread_work, node); + list_del_init(&work->node); + } + worker->current_work = work; + spin_unlock_irq(&worker->lock); + + if (work) { + __set_current_state(TASK_RUNNING); + work->func(work); + } else if (!freezing(current)) + schedule(); + + try_to_freeze(); + goto repeat; +} +EXPORT_SYMBOL_GPL(kthread_worker_fn); + +/* insert @work before @pos in @worker */ +static void insert_kthread_work(struct kthread_worker *worker, + struct kthread_work *work, + struct list_head *pos) +{ + lockdep_assert_held(&worker->lock); + + list_add_tail(&work->node, pos); + work->worker = worker; + if (!worker->current_work && likely(worker->task)) + wake_up_process(worker->task); +} + +/** + * queue_kthread_work - queue a kthread_work + * @worker: target kthread_worker + * @work: kthread_work to queue + * + * Queue @work to work processor @task for async execution. @task + * must have been created with kthread_worker_create(). Returns %true + * if @work was successfully queued, %false if it was already pending. + */ +bool queue_kthread_work(struct kthread_worker *worker, + struct kthread_work *work) +{ + bool ret = false; + unsigned long flags; + + spin_lock_irqsave(&worker->lock, flags); + if (list_empty(&work->node)) { + insert_kthread_work(worker, work, &worker->work_list); + ret = true; + } + spin_unlock_irqrestore(&worker->lock, flags); + return ret; +} +EXPORT_SYMBOL_GPL(queue_kthread_work); + +struct kthread_flush_work { + struct kthread_work work; + struct completion done; +}; + +static void kthread_flush_work_fn(struct kthread_work *work) +{ + struct kthread_flush_work *fwork = + container_of(work, struct kthread_flush_work, work); + complete(&fwork->done); +} + +/** + * flush_kthread_work - flush a kthread_work + * @work: work to flush + * + * If @work is queued or executing, wait for it to finish execution. + */ +void flush_kthread_work(struct kthread_work *work) +{ + struct kthread_flush_work fwork = { + KTHREAD_WORK_INIT(fwork.work, kthread_flush_work_fn), + COMPLETION_INITIALIZER_ONSTACK(fwork.done), + }; + struct kthread_worker *worker; + bool noop = false; + +retry: + worker = work->worker; + if (!worker) + return; + + spin_lock_irq(&worker->lock); + if (work->worker != worker) { + spin_unlock_irq(&worker->lock); + goto retry; + } + + if (!list_empty(&work->node)) + insert_kthread_work(worker, &fwork.work, work->node.next); + else if (worker->current_work == work) + insert_kthread_work(worker, &fwork.work, worker->work_list.next); + else + noop = true; + + spin_unlock_irq(&worker->lock); + + if (!noop) + wait_for_completion(&fwork.done); +} +EXPORT_SYMBOL_GPL(flush_kthread_work); + +/** + * flush_kthread_worker - flush all current works on a kthread_worker + * @worker: worker to flush + * + * Wait until all currently executing or pending works on @worker are + * finished. + */ +void flush_kthread_worker(struct kthread_worker *worker) +{ + struct kthread_flush_work fwork = { + KTHREAD_WORK_INIT(fwork.work, kthread_flush_work_fn), + COMPLETION_INITIALIZER_ONSTACK(fwork.done), + }; + + queue_kthread_work(worker, &fwork.work); + wait_for_completion(&fwork.done); +} +EXPORT_SYMBOL_GPL(flush_kthread_worker); diff --git a/kernel/kernel/latencytop.c b/kernel/kernel/latencytop.c new file mode 100644 index 000000000..a02812743 --- /dev/null +++ b/kernel/kernel/latencytop.c @@ -0,0 +1,292 @@ +/* + * latencytop.c: Latency display infrastructure + * + * (C) Copyright 2008 Intel Corporation + * Author: Arjan van de Ven + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; version 2 + * of the License. + */ + +/* + * CONFIG_LATENCYTOP enables a kernel latency tracking infrastructure that is + * used by the "latencytop" userspace tool. The latency that is tracked is not + * the 'traditional' interrupt latency (which is primarily caused by something + * else consuming CPU), but instead, it is the latency an application encounters + * because the kernel sleeps on its behalf for various reasons. + * + * This code tracks 2 levels of statistics: + * 1) System level latency + * 2) Per process latency + * + * The latency is stored in fixed sized data structures in an accumulated form; + * if the "same" latency cause is hit twice, this will be tracked as one entry + * in the data structure. Both the count, total accumulated latency and maximum + * latency are tracked in this data structure. When the fixed size structure is + * full, no new causes are tracked until the buffer is flushed by writing to + * the /proc file; the userspace tool does this on a regular basis. + * + * A latency cause is identified by a stringified backtrace at the point that + * the scheduler gets invoked. The userland tool will use this string to + * identify the cause of the latency in human readable form. + * + * The information is exported via /proc/latency_stats and /proc//latency. + * These files look like this: + * + * Latency Top version : v0.1 + * 70 59433 4897 i915_irq_wait drm_ioctl vfs_ioctl do_vfs_ioctl sys_ioctl + * | | | | + * | | | +----> the stringified backtrace + * | | +---------> The maximum latency for this entry in microseconds + * | +--------------> The accumulated latency for this entry (microseconds) + * +-------------------> The number of times this entry is hit + * + * (note: the average latency is the accumulated latency divided by the number + * of times) + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +static DEFINE_RAW_SPINLOCK(latency_lock); + +#define MAXLR 128 +static struct latency_record latency_record[MAXLR]; + +int latencytop_enabled; + +void clear_all_latency_tracing(struct task_struct *p) +{ + unsigned long flags; + + if (!latencytop_enabled) + return; + + raw_spin_lock_irqsave(&latency_lock, flags); + memset(&p->latency_record, 0, sizeof(p->latency_record)); + p->latency_record_count = 0; + raw_spin_unlock_irqrestore(&latency_lock, flags); +} + +static void clear_global_latency_tracing(void) +{ + unsigned long flags; + + raw_spin_lock_irqsave(&latency_lock, flags); + memset(&latency_record, 0, sizeof(latency_record)); + raw_spin_unlock_irqrestore(&latency_lock, flags); +} + +static void __sched +account_global_scheduler_latency(struct task_struct *tsk, + struct latency_record *lat) +{ + int firstnonnull = MAXLR + 1; + int i; + + if (!latencytop_enabled) + return; + + /* skip kernel threads for now */ + if (!tsk->mm) + return; + + for (i = 0; i < MAXLR; i++) { + int q, same = 1; + + /* Nothing stored: */ + if (!latency_record[i].backtrace[0]) { + if (firstnonnull > i) + firstnonnull = i; + continue; + } + for (q = 0; q < LT_BACKTRACEDEPTH; q++) { + unsigned long record = lat->backtrace[q]; + + if (latency_record[i].backtrace[q] != record) { + same = 0; + break; + } + + /* 0 and ULONG_MAX entries mean end of backtrace: */ + if (record == 0 || record == ULONG_MAX) + break; + } + if (same) { + latency_record[i].count++; + latency_record[i].time += lat->time; + if (lat->time > latency_record[i].max) + latency_record[i].max = lat->time; + return; + } + } + + i = firstnonnull; + if (i >= MAXLR - 1) + return; + + /* Allocted a new one: */ + memcpy(&latency_record[i], lat, sizeof(struct latency_record)); +} + +/* + * Iterator to store a backtrace into a latency record entry + */ +static inline void store_stacktrace(struct task_struct *tsk, + struct latency_record *lat) +{ + struct stack_trace trace; + + memset(&trace, 0, sizeof(trace)); + trace.max_entries = LT_BACKTRACEDEPTH; + trace.entries = &lat->backtrace[0]; + save_stack_trace_tsk(tsk, &trace); +} + +/** + * __account_scheduler_latency - record an occurred latency + * @tsk - the task struct of the task hitting the latency + * @usecs - the duration of the latency in microseconds + * @inter - 1 if the sleep was interruptible, 0 if uninterruptible + * + * This function is the main entry point for recording latency entries + * as called by the scheduler. + * + * This function has a few special cases to deal with normal 'non-latency' + * sleeps: specifically, interruptible sleep longer than 5 msec is skipped + * since this usually is caused by waiting for events via select() and co. + * + * Negative latencies (caused by time going backwards) are also explicitly + * skipped. + */ +void __sched +__account_scheduler_latency(struct task_struct *tsk, int usecs, int inter) +{ + unsigned long flags; + int i, q; + struct latency_record lat; + + /* Long interruptible waits are generally user requested... */ + if (inter && usecs > 5000) + return; + + /* Negative sleeps are time going backwards */ + /* Zero-time sleeps are non-interesting */ + if (usecs <= 0) + return; + + memset(&lat, 0, sizeof(lat)); + lat.count = 1; + lat.time = usecs; + lat.max = usecs; + store_stacktrace(tsk, &lat); + + raw_spin_lock_irqsave(&latency_lock, flags); + + account_global_scheduler_latency(tsk, &lat); + + for (i = 0; i < tsk->latency_record_count; i++) { + struct latency_record *mylat; + int same = 1; + + mylat = &tsk->latency_record[i]; + for (q = 0; q < LT_BACKTRACEDEPTH; q++) { + unsigned long record = lat.backtrace[q]; + + if (mylat->backtrace[q] != record) { + same = 0; + break; + } + + /* 0 and ULONG_MAX entries mean end of backtrace: */ + if (record == 0 || record == ULONG_MAX) + break; + } + if (same) { + mylat->count++; + mylat->time += lat.time; + if (lat.time > mylat->max) + mylat->max = lat.time; + goto out_unlock; + } + } + + /* + * short term hack; if we're > 32 we stop; future we recycle: + */ + if (tsk->latency_record_count >= LT_SAVECOUNT) + goto out_unlock; + + /* Allocated a new one: */ + i = tsk->latency_record_count++; + memcpy(&tsk->latency_record[i], &lat, sizeof(struct latency_record)); + +out_unlock: + raw_spin_unlock_irqrestore(&latency_lock, flags); +} + +static int lstats_show(struct seq_file *m, void *v) +{ + int i; + + seq_puts(m, "Latency Top version : v0.1\n"); + + for (i = 0; i < MAXLR; i++) { + struct latency_record *lr = &latency_record[i]; + + if (lr->backtrace[0]) { + int q; + seq_printf(m, "%i %lu %lu", + lr->count, lr->time, lr->max); + for (q = 0; q < LT_BACKTRACEDEPTH; q++) { + unsigned long bt = lr->backtrace[q]; + if (!bt) + break; + if (bt == ULONG_MAX) + break; + seq_printf(m, " %ps", (void *)bt); + } + seq_puts(m, "\n"); + } + } + return 0; +} + +static ssize_t +lstats_write(struct file *file, const char __user *buf, size_t count, + loff_t *offs) +{ + clear_global_latency_tracing(); + + return count; +} + +static int lstats_open(struct inode *inode, struct file *filp) +{ + return single_open(filp, lstats_show, NULL); +} + +static const struct file_operations lstats_fops = { + .open = lstats_open, + .read = seq_read, + .write = lstats_write, + .llseek = seq_lseek, + .release = single_release, +}; + +static int __init init_lstats_procfs(void) +{ + proc_create("latency_stats", 0644, NULL, &lstats_fops); + return 0; +} +device_initcall(init_lstats_procfs); diff --git a/kernel/kernel/livepatch/Kconfig b/kernel/kernel/livepatch/Kconfig new file mode 100644 index 000000000..045022557 --- /dev/null +++ b/kernel/kernel/livepatch/Kconfig @@ -0,0 +1,18 @@ +config HAVE_LIVEPATCH + bool + help + Arch supports kernel live patching + +config LIVEPATCH + bool "Kernel Live Patching" + depends on DYNAMIC_FTRACE_WITH_REGS + depends on MODULES + depends on SYSFS + depends on KALLSYMS_ALL + depends on HAVE_LIVEPATCH + help + Say Y here if you want to support kernel live patching. + This option has no runtime impact until a kernel "patch" + module uses the interface provided by this option to register + a patch, causing calls to patched functions to be redirected + to new function code contained in the patch module. diff --git a/kernel/kernel/livepatch/Makefile b/kernel/kernel/livepatch/Makefile new file mode 100644 index 000000000..e8780c090 --- /dev/null +++ b/kernel/kernel/livepatch/Makefile @@ -0,0 +1,3 @@ +obj-$(CONFIG_LIVEPATCH) += livepatch.o + +livepatch-objs := core.o diff --git a/kernel/kernel/livepatch/core.c b/kernel/kernel/livepatch/core.c new file mode 100644 index 000000000..9ec555732 --- /dev/null +++ b/kernel/kernel/livepatch/core.c @@ -0,0 +1,1011 @@ +/* + * core.c - Kernel Live Patching Core + * + * Copyright (C) 2014 Seth Jennings + * Copyright (C) 2014 SUSE + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version 2 + * of the License, or (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, see . + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include +#include +#include +#include +#include +#include +#include + +/** + * struct klp_ops - structure for tracking registered ftrace ops structs + * + * A single ftrace_ops is shared between all enabled replacement functions + * (klp_func structs) which have the same old_addr. This allows the switch + * between function versions to happen instantaneously by updating the klp_ops + * struct's func_stack list. The winner is the klp_func at the top of the + * func_stack (front of the list). + * + * @node: node for the global klp_ops list + * @func_stack: list head for the stack of klp_func's (active func is on top) + * @fops: registered ftrace ops struct + */ +struct klp_ops { + struct list_head node; + struct list_head func_stack; + struct ftrace_ops fops; +}; + +/* + * The klp_mutex protects the global lists and state transitions of any + * structure reachable from them. References to any structure must be obtained + * under mutex protection (except in klp_ftrace_handler(), which uses RCU to + * ensure it gets consistent data). + */ +static DEFINE_MUTEX(klp_mutex); + +static LIST_HEAD(klp_patches); +static LIST_HEAD(klp_ops); + +static struct kobject *klp_root_kobj; + +static struct klp_ops *klp_find_ops(unsigned long old_addr) +{ + struct klp_ops *ops; + struct klp_func *func; + + list_for_each_entry(ops, &klp_ops, node) { + func = list_first_entry(&ops->func_stack, struct klp_func, + stack_node); + if (func->old_addr == old_addr) + return ops; + } + + return NULL; +} + +static bool klp_is_module(struct klp_object *obj) +{ + return obj->name; +} + +static bool klp_is_object_loaded(struct klp_object *obj) +{ + return !obj->name || obj->mod; +} + +/* sets obj->mod if object is not vmlinux and module is found */ +static void klp_find_object_module(struct klp_object *obj) +{ + struct module *mod; + + if (!klp_is_module(obj)) + return; + + mutex_lock(&module_mutex); + /* + * We do not want to block removal of patched modules and therefore + * we do not take a reference here. The patches are removed by + * a going module handler instead. + */ + mod = find_module(obj->name); + /* + * Do not mess work of the module coming and going notifiers. + * Note that the patch might still be needed before the going handler + * is called. Module functions can be called even in the GOING state + * until mod->exit() finishes. This is especially important for + * patches that modify semantic of the functions. + */ + if (mod && mod->klp_alive) + obj->mod = mod; + + mutex_unlock(&module_mutex); +} + +/* klp_mutex must be held by caller */ +static bool klp_is_patch_registered(struct klp_patch *patch) +{ + struct klp_patch *mypatch; + + list_for_each_entry(mypatch, &klp_patches, list) + if (mypatch == patch) + return true; + + return false; +} + +static bool klp_initialized(void) +{ + return klp_root_kobj; +} + +struct klp_find_arg { + const char *objname; + const char *name; + unsigned long addr; + /* + * If count == 0, the symbol was not found. If count == 1, a unique + * match was found and addr is set. If count > 1, there is + * unresolvable ambiguity among "count" number of symbols with the same + * name in the same object. + */ + unsigned long count; +}; + +static int klp_find_callback(void *data, const char *name, + struct module *mod, unsigned long addr) +{ + struct klp_find_arg *args = data; + + if ((mod && !args->objname) || (!mod && args->objname)) + return 0; + + if (strcmp(args->name, name)) + return 0; + + if (args->objname && strcmp(args->objname, mod->name)) + return 0; + + /* + * args->addr might be overwritten if another match is found + * but klp_find_object_symbol() handles this and only returns the + * addr if count == 1. + */ + args->addr = addr; + args->count++; + + return 0; +} + +static int klp_find_object_symbol(const char *objname, const char *name, + unsigned long *addr) +{ + struct klp_find_arg args = { + .objname = objname, + .name = name, + .addr = 0, + .count = 0 + }; + + mutex_lock(&module_mutex); + kallsyms_on_each_symbol(klp_find_callback, &args); + mutex_unlock(&module_mutex); + + if (args.count == 0) + pr_err("symbol '%s' not found in symbol table\n", name); + else if (args.count > 1) + pr_err("unresolvable ambiguity (%lu matches) on symbol '%s' in object '%s'\n", + args.count, name, objname); + else { + *addr = args.addr; + return 0; + } + + *addr = 0; + return -EINVAL; +} + +struct klp_verify_args { + const char *name; + const unsigned long addr; +}; + +static int klp_verify_callback(void *data, const char *name, + struct module *mod, unsigned long addr) +{ + struct klp_verify_args *args = data; + + if (!mod && + !strcmp(args->name, name) && + args->addr == addr) + return 1; + + return 0; +} + +static int klp_verify_vmlinux_symbol(const char *name, unsigned long addr) +{ + struct klp_verify_args args = { + .name = name, + .addr = addr, + }; + int ret; + + mutex_lock(&module_mutex); + ret = kallsyms_on_each_symbol(klp_verify_callback, &args); + mutex_unlock(&module_mutex); + + if (!ret) { + pr_err("symbol '%s' not found at specified address 0x%016lx, kernel mismatch?\n", + name, addr); + return -EINVAL; + } + + return 0; +} + +static int klp_find_verify_func_addr(struct klp_object *obj, + struct klp_func *func) +{ + int ret; + +#if defined(CONFIG_RANDOMIZE_BASE) + /* KASLR is enabled, disregard old_addr from user */ + func->old_addr = 0; +#endif + + if (!func->old_addr || klp_is_module(obj)) + ret = klp_find_object_symbol(obj->name, func->old_name, + &func->old_addr); + else + ret = klp_verify_vmlinux_symbol(func->old_name, + func->old_addr); + + return ret; +} + +/* + * external symbols are located outside the parent object (where the parent + * object is either vmlinux or the kmod being patched). + */ +static int klp_find_external_symbol(struct module *pmod, const char *name, + unsigned long *addr) +{ + const struct kernel_symbol *sym; + + /* first, check if it's an exported symbol */ + preempt_disable(); + sym = find_symbol(name, NULL, NULL, true, true); + if (sym) { + *addr = sym->value; + preempt_enable(); + return 0; + } + preempt_enable(); + + /* otherwise check if it's in another .o within the patch module */ + return klp_find_object_symbol(pmod->name, name, addr); +} + +static int klp_write_object_relocations(struct module *pmod, + struct klp_object *obj) +{ + int ret; + struct klp_reloc *reloc; + + if (WARN_ON(!klp_is_object_loaded(obj))) + return -EINVAL; + + if (WARN_ON(!obj->relocs)) + return -EINVAL; + + for (reloc = obj->relocs; reloc->name; reloc++) { + if (!klp_is_module(obj)) { + ret = klp_verify_vmlinux_symbol(reloc->name, + reloc->val); + if (ret) + return ret; + } else { + /* module, reloc->val needs to be discovered */ + if (reloc->external) + ret = klp_find_external_symbol(pmod, + reloc->name, + &reloc->val); + else + ret = klp_find_object_symbol(obj->mod->name, + reloc->name, + &reloc->val); + if (ret) + return ret; + } + ret = klp_write_module_reloc(pmod, reloc->type, reloc->loc, + reloc->val + reloc->addend); + if (ret) { + pr_err("relocation failed for symbol '%s' at 0x%016lx (%d)\n", + reloc->name, reloc->val, ret); + return ret; + } + } + + return 0; +} + +static void notrace klp_ftrace_handler(unsigned long ip, + unsigned long parent_ip, + struct ftrace_ops *fops, + struct pt_regs *regs) +{ + struct klp_ops *ops; + struct klp_func *func; + + ops = container_of(fops, struct klp_ops, fops); + + rcu_read_lock(); + func = list_first_or_null_rcu(&ops->func_stack, struct klp_func, + stack_node); + if (WARN_ON_ONCE(!func)) + goto unlock; + + klp_arch_set_pc(regs, (unsigned long)func->new_func); +unlock: + rcu_read_unlock(); +} + +static void klp_disable_func(struct klp_func *func) +{ + struct klp_ops *ops; + + WARN_ON(func->state != KLP_ENABLED); + WARN_ON(!func->old_addr); + + ops = klp_find_ops(func->old_addr); + if (WARN_ON(!ops)) + return; + + if (list_is_singular(&ops->func_stack)) { + WARN_ON(unregister_ftrace_function(&ops->fops)); + WARN_ON(ftrace_set_filter_ip(&ops->fops, func->old_addr, 1, 0)); + + list_del_rcu(&func->stack_node); + list_del(&ops->node); + kfree(ops); + } else { + list_del_rcu(&func->stack_node); + } + + func->state = KLP_DISABLED; +} + +static int klp_enable_func(struct klp_func *func) +{ + struct klp_ops *ops; + int ret; + + if (WARN_ON(!func->old_addr)) + return -EINVAL; + + if (WARN_ON(func->state != KLP_DISABLED)) + return -EINVAL; + + ops = klp_find_ops(func->old_addr); + if (!ops) { + ops = kzalloc(sizeof(*ops), GFP_KERNEL); + if (!ops) + return -ENOMEM; + + ops->fops.func = klp_ftrace_handler; + ops->fops.flags = FTRACE_OPS_FL_SAVE_REGS | + FTRACE_OPS_FL_DYNAMIC | + FTRACE_OPS_FL_IPMODIFY; + + list_add(&ops->node, &klp_ops); + + INIT_LIST_HEAD(&ops->func_stack); + list_add_rcu(&func->stack_node, &ops->func_stack); + + ret = ftrace_set_filter_ip(&ops->fops, func->old_addr, 0, 0); + if (ret) { + pr_err("failed to set ftrace filter for function '%s' (%d)\n", + func->old_name, ret); + goto err; + } + + ret = register_ftrace_function(&ops->fops); + if (ret) { + pr_err("failed to register ftrace handler for function '%s' (%d)\n", + func->old_name, ret); + ftrace_set_filter_ip(&ops->fops, func->old_addr, 1, 0); + goto err; + } + + + } else { + list_add_rcu(&func->stack_node, &ops->func_stack); + } + + func->state = KLP_ENABLED; + + return 0; + +err: + list_del_rcu(&func->stack_node); + list_del(&ops->node); + kfree(ops); + return ret; +} + +static void klp_disable_object(struct klp_object *obj) +{ + struct klp_func *func; + + for (func = obj->funcs; func->old_name; func++) + if (func->state == KLP_ENABLED) + klp_disable_func(func); + + obj->state = KLP_DISABLED; +} + +static int klp_enable_object(struct klp_object *obj) +{ + struct klp_func *func; + int ret; + + if (WARN_ON(obj->state != KLP_DISABLED)) + return -EINVAL; + + if (WARN_ON(!klp_is_object_loaded(obj))) + return -EINVAL; + + for (func = obj->funcs; func->old_name; func++) { + ret = klp_enable_func(func); + if (ret) { + klp_disable_object(obj); + return ret; + } + } + obj->state = KLP_ENABLED; + + return 0; +} + +static int __klp_disable_patch(struct klp_patch *patch) +{ + struct klp_object *obj; + + /* enforce stacking: only the last enabled patch can be disabled */ + if (!list_is_last(&patch->list, &klp_patches) && + list_next_entry(patch, list)->state == KLP_ENABLED) + return -EBUSY; + + pr_notice("disabling patch '%s'\n", patch->mod->name); + + for (obj = patch->objs; obj->funcs; obj++) { + if (obj->state == KLP_ENABLED) + klp_disable_object(obj); + } + + patch->state = KLP_DISABLED; + + return 0; +} + +/** + * klp_disable_patch() - disables a registered patch + * @patch: The registered, enabled patch to be disabled + * + * Unregisters the patched functions from ftrace. + * + * Return: 0 on success, otherwise error + */ +int klp_disable_patch(struct klp_patch *patch) +{ + int ret; + + mutex_lock(&klp_mutex); + + if (!klp_is_patch_registered(patch)) { + ret = -EINVAL; + goto err; + } + + if (patch->state == KLP_DISABLED) { + ret = -EINVAL; + goto err; + } + + ret = __klp_disable_patch(patch); + +err: + mutex_unlock(&klp_mutex); + return ret; +} +EXPORT_SYMBOL_GPL(klp_disable_patch); + +static int __klp_enable_patch(struct klp_patch *patch) +{ + struct klp_object *obj; + int ret; + + if (WARN_ON(patch->state != KLP_DISABLED)) + return -EINVAL; + + /* enforce stacking: only the first disabled patch can be enabled */ + if (patch->list.prev != &klp_patches && + list_prev_entry(patch, list)->state == KLP_DISABLED) + return -EBUSY; + + pr_notice_once("tainting kernel with TAINT_LIVEPATCH\n"); + add_taint(TAINT_LIVEPATCH, LOCKDEP_STILL_OK); + + pr_notice("enabling patch '%s'\n", patch->mod->name); + + for (obj = patch->objs; obj->funcs; obj++) { + if (!klp_is_object_loaded(obj)) + continue; + + ret = klp_enable_object(obj); + if (ret) + goto unregister; + } + + patch->state = KLP_ENABLED; + + return 0; + +unregister: + WARN_ON(__klp_disable_patch(patch)); + return ret; +} + +/** + * klp_enable_patch() - enables a registered patch + * @patch: The registered, disabled patch to be enabled + * + * Performs the needed symbol lookups and code relocations, + * then registers the patched functions with ftrace. + * + * Return: 0 on success, otherwise error + */ +int klp_enable_patch(struct klp_patch *patch) +{ + int ret; + + mutex_lock(&klp_mutex); + + if (!klp_is_patch_registered(patch)) { + ret = -EINVAL; + goto err; + } + + ret = __klp_enable_patch(patch); + +err: + mutex_unlock(&klp_mutex); + return ret; +} +EXPORT_SYMBOL_GPL(klp_enable_patch); + +/* + * Sysfs Interface + * + * /sys/kernel/livepatch + * /sys/kernel/livepatch/ + * /sys/kernel/livepatch//enabled + * /sys/kernel/livepatch// + * /sys/kernel/livepatch/// + */ + +static ssize_t enabled_store(struct kobject *kobj, struct kobj_attribute *attr, + const char *buf, size_t count) +{ + struct klp_patch *patch; + int ret; + unsigned long val; + + ret = kstrtoul(buf, 10, &val); + if (ret) + return -EINVAL; + + if (val != KLP_DISABLED && val != KLP_ENABLED) + return -EINVAL; + + patch = container_of(kobj, struct klp_patch, kobj); + + mutex_lock(&klp_mutex); + + if (val == patch->state) { + /* already in requested state */ + ret = -EINVAL; + goto err; + } + + if (val == KLP_ENABLED) { + ret = __klp_enable_patch(patch); + if (ret) + goto err; + } else { + ret = __klp_disable_patch(patch); + if (ret) + goto err; + } + + mutex_unlock(&klp_mutex); + + return count; + +err: + mutex_unlock(&klp_mutex); + return ret; +} + +static ssize_t enabled_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + struct klp_patch *patch; + + patch = container_of(kobj, struct klp_patch, kobj); + return snprintf(buf, PAGE_SIZE-1, "%d\n", patch->state); +} + +static struct kobj_attribute enabled_kobj_attr = __ATTR_RW(enabled); +static struct attribute *klp_patch_attrs[] = { + &enabled_kobj_attr.attr, + NULL +}; + +static void klp_kobj_release_patch(struct kobject *kobj) +{ + /* + * Once we have a consistency model we'll need to module_put() the + * patch module here. See klp_register_patch() for more details. + */ +} + +static struct kobj_type klp_ktype_patch = { + .release = klp_kobj_release_patch, + .sysfs_ops = &kobj_sysfs_ops, + .default_attrs = klp_patch_attrs, +}; + +static void klp_kobj_release_func(struct kobject *kobj) +{ +} + +static struct kobj_type klp_ktype_func = { + .release = klp_kobj_release_func, + .sysfs_ops = &kobj_sysfs_ops, +}; + +/* + * Free all functions' kobjects in the array up to some limit. When limit is + * NULL, all kobjects are freed. + */ +static void klp_free_funcs_limited(struct klp_object *obj, + struct klp_func *limit) +{ + struct klp_func *func; + + for (func = obj->funcs; func->old_name && func != limit; func++) + kobject_put(&func->kobj); +} + +/* Clean up when a patched object is unloaded */ +static void klp_free_object_loaded(struct klp_object *obj) +{ + struct klp_func *func; + + obj->mod = NULL; + + for (func = obj->funcs; func->old_name; func++) + func->old_addr = 0; +} + +/* + * Free all objects' kobjects in the array up to some limit. When limit is + * NULL, all kobjects are freed. + */ +static void klp_free_objects_limited(struct klp_patch *patch, + struct klp_object *limit) +{ + struct klp_object *obj; + + for (obj = patch->objs; obj->funcs && obj != limit; obj++) { + klp_free_funcs_limited(obj, NULL); + kobject_put(obj->kobj); + } +} + +static void klp_free_patch(struct klp_patch *patch) +{ + klp_free_objects_limited(patch, NULL); + if (!list_empty(&patch->list)) + list_del(&patch->list); + kobject_put(&patch->kobj); +} + +static int klp_init_func(struct klp_object *obj, struct klp_func *func) +{ + INIT_LIST_HEAD(&func->stack_node); + func->state = KLP_DISABLED; + + return kobject_init_and_add(&func->kobj, &klp_ktype_func, + obj->kobj, "%s", func->old_name); +} + +/* parts of the initialization that is done only when the object is loaded */ +static int klp_init_object_loaded(struct klp_patch *patch, + struct klp_object *obj) +{ + struct klp_func *func; + int ret; + + if (obj->relocs) { + ret = klp_write_object_relocations(patch->mod, obj); + if (ret) + return ret; + } + + for (func = obj->funcs; func->old_name; func++) { + ret = klp_find_verify_func_addr(obj, func); + if (ret) + return ret; + } + + return 0; +} + +static int klp_init_object(struct klp_patch *patch, struct klp_object *obj) +{ + struct klp_func *func; + int ret; + const char *name; + + if (!obj->funcs) + return -EINVAL; + + obj->state = KLP_DISABLED; + obj->mod = NULL; + + klp_find_object_module(obj); + + name = klp_is_module(obj) ? obj->name : "vmlinux"; + obj->kobj = kobject_create_and_add(name, &patch->kobj); + if (!obj->kobj) + return -ENOMEM; + + for (func = obj->funcs; func->old_name; func++) { + ret = klp_init_func(obj, func); + if (ret) + goto free; + } + + if (klp_is_object_loaded(obj)) { + ret = klp_init_object_loaded(patch, obj); + if (ret) + goto free; + } + + return 0; + +free: + klp_free_funcs_limited(obj, func); + kobject_put(obj->kobj); + return ret; +} + +static int klp_init_patch(struct klp_patch *patch) +{ + struct klp_object *obj; + int ret; + + if (!patch->objs) + return -EINVAL; + + mutex_lock(&klp_mutex); + + patch->state = KLP_DISABLED; + + ret = kobject_init_and_add(&patch->kobj, &klp_ktype_patch, + klp_root_kobj, "%s", patch->mod->name); + if (ret) + goto unlock; + + for (obj = patch->objs; obj->funcs; obj++) { + ret = klp_init_object(patch, obj); + if (ret) + goto free; + } + + list_add_tail(&patch->list, &klp_patches); + + mutex_unlock(&klp_mutex); + + return 0; + +free: + klp_free_objects_limited(patch, obj); + kobject_put(&patch->kobj); +unlock: + mutex_unlock(&klp_mutex); + return ret; +} + +/** + * klp_unregister_patch() - unregisters a patch + * @patch: Disabled patch to be unregistered + * + * Frees the data structures and removes the sysfs interface. + * + * Return: 0 on success, otherwise error + */ +int klp_unregister_patch(struct klp_patch *patch) +{ + int ret = 0; + + mutex_lock(&klp_mutex); + + if (!klp_is_patch_registered(patch)) { + ret = -EINVAL; + goto out; + } + + if (patch->state == KLP_ENABLED) { + ret = -EBUSY; + goto out; + } + + klp_free_patch(patch); + +out: + mutex_unlock(&klp_mutex); + return ret; +} +EXPORT_SYMBOL_GPL(klp_unregister_patch); + +/** + * klp_register_patch() - registers a patch + * @patch: Patch to be registered + * + * Initializes the data structure associated with the patch and + * creates the sysfs interface. + * + * Return: 0 on success, otherwise error + */ +int klp_register_patch(struct klp_patch *patch) +{ + int ret; + + if (!klp_initialized()) + return -ENODEV; + + if (!patch || !patch->mod) + return -EINVAL; + + /* + * A reference is taken on the patch module to prevent it from being + * unloaded. Right now, we don't allow patch modules to unload since + * there is currently no method to determine if a thread is still + * running in the patched code contained in the patch module once + * the ftrace registration is successful. + */ + if (!try_module_get(patch->mod)) + return -ENODEV; + + ret = klp_init_patch(patch); + if (ret) + module_put(patch->mod); + + return ret; +} +EXPORT_SYMBOL_GPL(klp_register_patch); + +static void klp_module_notify_coming(struct klp_patch *patch, + struct klp_object *obj) +{ + struct module *pmod = patch->mod; + struct module *mod = obj->mod; + int ret; + + ret = klp_init_object_loaded(patch, obj); + if (ret) + goto err; + + if (patch->state == KLP_DISABLED) + return; + + pr_notice("applying patch '%s' to loading module '%s'\n", + pmod->name, mod->name); + + ret = klp_enable_object(obj); + if (!ret) + return; + +err: + pr_warn("failed to apply patch '%s' to module '%s' (%d)\n", + pmod->name, mod->name, ret); +} + +static void klp_module_notify_going(struct klp_patch *patch, + struct klp_object *obj) +{ + struct module *pmod = patch->mod; + struct module *mod = obj->mod; + + if (patch->state == KLP_DISABLED) + goto disabled; + + pr_notice("reverting patch '%s' on unloading module '%s'\n", + pmod->name, mod->name); + + klp_disable_object(obj); + +disabled: + klp_free_object_loaded(obj); +} + +static int klp_module_notify(struct notifier_block *nb, unsigned long action, + void *data) +{ + struct module *mod = data; + struct klp_patch *patch; + struct klp_object *obj; + + if (action != MODULE_STATE_COMING && action != MODULE_STATE_GOING) + return 0; + + mutex_lock(&klp_mutex); + + /* + * Each module has to know that the notifier has been called. + * We never know what module will get patched by a new patch. + */ + if (action == MODULE_STATE_COMING) + mod->klp_alive = true; + else /* MODULE_STATE_GOING */ + mod->klp_alive = false; + + list_for_each_entry(patch, &klp_patches, list) { + for (obj = patch->objs; obj->funcs; obj++) { + if (!klp_is_module(obj) || strcmp(obj->name, mod->name)) + continue; + + if (action == MODULE_STATE_COMING) { + obj->mod = mod; + klp_module_notify_coming(patch, obj); + } else /* MODULE_STATE_GOING */ + klp_module_notify_going(patch, obj); + + break; + } + } + + mutex_unlock(&klp_mutex); + + return 0; +} + +static struct notifier_block klp_module_nb = { + .notifier_call = klp_module_notify, + .priority = INT_MIN+1, /* called late but before ftrace notifier */ +}; + +static int klp_init(void) +{ + int ret; + + ret = klp_check_compiler_support(); + if (ret) { + pr_info("Your compiler is too old; turning off.\n"); + return -EINVAL; + } + + ret = register_module_notifier(&klp_module_nb); + if (ret) + return ret; + + klp_root_kobj = kobject_create_and_add("livepatch", kernel_kobj); + if (!klp_root_kobj) { + ret = -ENOMEM; + goto unregister; + } + + return 0; + +unregister: + unregister_module_notifier(&klp_module_nb); + return ret; +} + +module_init(klp_init); diff --git a/kernel/kernel/locking/Makefile b/kernel/kernel/locking/Makefile new file mode 100644 index 000000000..ab269cf04 --- /dev/null +++ b/kernel/kernel/locking/Makefile @@ -0,0 +1,36 @@ + +obj-y += semaphore.o + +ifdef CONFIG_FUNCTION_TRACER +CFLAGS_REMOVE_lockdep.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_lockdep_proc.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_mutex-debug.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_rtmutex-debug.o = $(CC_FLAGS_FTRACE) +endif + +ifneq ($(CONFIG_PREEMPT_RT_FULL),y) +obj-y += mutex.o +obj-$(CONFIG_DEBUG_MUTEXES) += mutex-debug.o +obj-y += rwsem.o +endif +obj-$(CONFIG_LOCKDEP) += lockdep.o +ifeq ($(CONFIG_PROC_FS),y) +obj-$(CONFIG_LOCKDEP) += lockdep_proc.o +endif +obj-$(CONFIG_SMP) += spinlock.o +obj-$(CONFIG_LOCK_SPIN_ON_OWNER) += osq_lock.o +obj-$(CONFIG_SMP) += lglock.o +obj-$(CONFIG_PROVE_LOCKING) += spinlock.o +obj-$(CONFIG_RT_MUTEXES) += rtmutex.o +obj-$(CONFIG_DEBUG_RT_MUTEXES) += rtmutex-debug.o +obj-$(CONFIG_RT_MUTEX_TESTER) += rtmutex-tester.o +obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock.o +obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock_debug.o +ifneq ($(CONFIG_PREEMPT_RT_FULL),y) +obj-$(CONFIG_RWSEM_GENERIC_SPINLOCK) += rwsem-spinlock.o +obj-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem-xadd.o +endif +obj-$(CONFIG_PERCPU_RWSEM) += percpu-rwsem.o +obj-$(CONFIG_PREEMPT_RT_FULL) += rt.o +obj-$(CONFIG_QUEUE_RWLOCK) += qrwlock.o +obj-$(CONFIG_LOCK_TORTURE_TEST) += locktorture.o diff --git a/kernel/kernel/locking/lglock.c b/kernel/kernel/locking/lglock.c new file mode 100644 index 000000000..9397974b1 --- /dev/null +++ b/kernel/kernel/locking/lglock.c @@ -0,0 +1,132 @@ +/* See include/linux/lglock.h for description */ +#include +#include +#include +#include + +#ifndef CONFIG_PREEMPT_RT_FULL +# define lg_lock_ptr arch_spinlock_t +# define lg_do_lock(l) arch_spin_lock(l) +# define lg_do_unlock(l) arch_spin_unlock(l) +#else +# define lg_lock_ptr struct rt_mutex +# define lg_do_lock(l) __rt_spin_lock(l) +# define lg_do_unlock(l) __rt_spin_unlock(l) +#endif +/* + * Note there is no uninit, so lglocks cannot be defined in + * modules (but it's fine to use them from there) + * Could be added though, just undo lg_lock_init + */ + +void lg_lock_init(struct lglock *lg, char *name) +{ +#ifdef CONFIG_PREEMPT_RT_FULL + int i; + + for_each_possible_cpu(i) { + struct rt_mutex *lock = per_cpu_ptr(lg->lock, i); + + rt_mutex_init(lock); + } +#endif + LOCKDEP_INIT_MAP(&lg->lock_dep_map, name, &lg->lock_key, 0); +} +EXPORT_SYMBOL(lg_lock_init); + +void lg_local_lock(struct lglock *lg) +{ + lg_lock_ptr *lock; + + migrate_disable(); + lock_acquire_shared(&lg->lock_dep_map, 0, 0, NULL, _RET_IP_); + lock = this_cpu_ptr(lg->lock); + lg_do_lock(lock); +} +EXPORT_SYMBOL(lg_local_lock); + +void lg_local_unlock(struct lglock *lg) +{ + lg_lock_ptr *lock; + + lock_release(&lg->lock_dep_map, 1, _RET_IP_); + lock = this_cpu_ptr(lg->lock); + lg_do_unlock(lock); + migrate_enable(); +} +EXPORT_SYMBOL(lg_local_unlock); + +void lg_local_lock_cpu(struct lglock *lg, int cpu) +{ + lg_lock_ptr *lock; + + preempt_disable_nort(); + lock_acquire_shared(&lg->lock_dep_map, 0, 0, NULL, _RET_IP_); + lock = per_cpu_ptr(lg->lock, cpu); + lg_do_lock(lock); +} +EXPORT_SYMBOL(lg_local_lock_cpu); + +void lg_local_unlock_cpu(struct lglock *lg, int cpu) +{ + lg_lock_ptr *lock; + + lock_release(&lg->lock_dep_map, 1, _RET_IP_); + lock = per_cpu_ptr(lg->lock, cpu); + lg_do_unlock(lock); + preempt_enable_nort(); +} +EXPORT_SYMBOL(lg_local_unlock_cpu); + +void lg_global_lock(struct lglock *lg) +{ + int i; + + preempt_disable_nort(); + lock_acquire_exclusive(&lg->lock_dep_map, 0, 0, NULL, _RET_IP_); + for_each_possible_cpu(i) { + lg_lock_ptr *lock; + lock = per_cpu_ptr(lg->lock, i); + lg_do_lock(lock); + } +} +EXPORT_SYMBOL(lg_global_lock); + +void lg_global_unlock(struct lglock *lg) +{ + int i; + + lock_release(&lg->lock_dep_map, 1, _RET_IP_); + for_each_possible_cpu(i) { + lg_lock_ptr *lock; + lock = per_cpu_ptr(lg->lock, i); + lg_do_unlock(lock); + } + preempt_enable_nort(); +} +EXPORT_SYMBOL(lg_global_unlock); + +#ifdef CONFIG_PREEMPT_RT_FULL +/* + * HACK: If you use this, you get to keep the pieces. + * Used in queue_stop_cpus_work() when stop machinery + * is called from inactive CPU, so we can't schedule. + */ +# define lg_do_trylock_relax(l) \ + do { \ + while (!__rt_spin_trylock(l)) \ + cpu_relax(); \ + } while (0) + +void lg_global_trylock_relax(struct lglock *lg) +{ + int i; + + lock_acquire_exclusive(&lg->lock_dep_map, 0, 0, NULL, _RET_IP_); + for_each_possible_cpu(i) { + lg_lock_ptr *lock; + lock = per_cpu_ptr(lg->lock, i); + lg_do_trylock_relax(lock); + } +} +#endif diff --git a/kernel/kernel/locking/lockdep.c b/kernel/kernel/locking/lockdep.c new file mode 100644 index 000000000..577f02617 --- /dev/null +++ b/kernel/kernel/locking/lockdep.c @@ -0,0 +1,4306 @@ +/* + * kernel/lockdep.c + * + * Runtime locking correctness validator + * + * Started by Ingo Molnar: + * + * Copyright (C) 2006,2007 Red Hat, Inc., Ingo Molnar + * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra + * + * this code maps all the lock dependencies as they occur in a live kernel + * and will warn about the following classes of locking bugs: + * + * - lock inversion scenarios + * - circular lock dependencies + * - hardirq/softirq safe/unsafe locking bugs + * + * Bugs are reported even if the current locking scenario does not cause + * any deadlock at this point. + * + * I.e. if anytime in the past two locks were taken in a different order, + * even if it happened for another task, even if those were different + * locks (but of the same class as this lock), this code will detect it. + * + * Thanks to Arjan van de Ven for coming up with the initial idea of + * mapping lock dependencies runtime. + */ +#define DISABLE_BRANCH_PROFILING +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +#include "lockdep_internals.h" + +#define CREATE_TRACE_POINTS +#include + +#ifdef CONFIG_PROVE_LOCKING +int prove_locking = 1; +module_param(prove_locking, int, 0644); +#else +#define prove_locking 0 +#endif + +#ifdef CONFIG_LOCK_STAT +int lock_stat = 1; +module_param(lock_stat, int, 0644); +#else +#define lock_stat 0 +#endif + +/* + * lockdep_lock: protects the lockdep graph, the hashes and the + * class/list/hash allocators. + * + * This is one of the rare exceptions where it's justified + * to use a raw spinlock - we really dont want the spinlock + * code to recurse back into the lockdep code... + */ +static arch_spinlock_t lockdep_lock = (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED; + +static int graph_lock(void) +{ + arch_spin_lock(&lockdep_lock); + /* + * Make sure that if another CPU detected a bug while + * walking the graph we dont change it (while the other + * CPU is busy printing out stuff with the graph lock + * dropped already) + */ + if (!debug_locks) { + arch_spin_unlock(&lockdep_lock); + return 0; + } + /* prevent any recursions within lockdep from causing deadlocks */ + current->lockdep_recursion++; + return 1; +} + +static inline int graph_unlock(void) +{ + if (debug_locks && !arch_spin_is_locked(&lockdep_lock)) { + /* + * The lockdep graph lock isn't locked while we expect it to + * be, we're confused now, bye! + */ + return DEBUG_LOCKS_WARN_ON(1); + } + + current->lockdep_recursion--; + arch_spin_unlock(&lockdep_lock); + return 0; +} + +/* + * Turn lock debugging off and return with 0 if it was off already, + * and also release the graph lock: + */ +static inline int debug_locks_off_graph_unlock(void) +{ + int ret = debug_locks_off(); + + arch_spin_unlock(&lockdep_lock); + + return ret; +} + +static int lockdep_initialized; + +unsigned long nr_list_entries; +static struct lock_list list_entries[MAX_LOCKDEP_ENTRIES]; + +/* + * All data structures here are protected by the global debug_lock. + * + * Mutex key structs only get allocated, once during bootup, and never + * get freed - this significantly simplifies the debugging code. + */ +unsigned long nr_lock_classes; +static struct lock_class lock_classes[MAX_LOCKDEP_KEYS]; + +static inline struct lock_class *hlock_class(struct held_lock *hlock) +{ + if (!hlock->class_idx) { + /* + * Someone passed in garbage, we give up. + */ + DEBUG_LOCKS_WARN_ON(1); + return NULL; + } + return lock_classes + hlock->class_idx - 1; +} + +#ifdef CONFIG_LOCK_STAT +static DEFINE_PER_CPU(struct lock_class_stats[MAX_LOCKDEP_KEYS], + cpu_lock_stats); + +static inline u64 lockstat_clock(void) +{ + return local_clock(); +} + +static int lock_point(unsigned long points[], unsigned long ip) +{ + int i; + + for (i = 0; i < LOCKSTAT_POINTS; i++) { + if (points[i] == 0) { + points[i] = ip; + break; + } + if (points[i] == ip) + break; + } + + return i; +} + +static void lock_time_inc(struct lock_time *lt, u64 time) +{ + if (time > lt->max) + lt->max = time; + + if (time < lt->min || !lt->nr) + lt->min = time; + + lt->total += time; + lt->nr++; +} + +static inline void lock_time_add(struct lock_time *src, struct lock_time *dst) +{ + if (!src->nr) + return; + + if (src->max > dst->max) + dst->max = src->max; + + if (src->min < dst->min || !dst->nr) + dst->min = src->min; + + dst->total += src->total; + dst->nr += src->nr; +} + +struct lock_class_stats lock_stats(struct lock_class *class) +{ + struct lock_class_stats stats; + int cpu, i; + + memset(&stats, 0, sizeof(struct lock_class_stats)); + for_each_possible_cpu(cpu) { + struct lock_class_stats *pcs = + &per_cpu(cpu_lock_stats, cpu)[class - lock_classes]; + + for (i = 0; i < ARRAY_SIZE(stats.contention_point); i++) + stats.contention_point[i] += pcs->contention_point[i]; + + for (i = 0; i < ARRAY_SIZE(stats.contending_point); i++) + stats.contending_point[i] += pcs->contending_point[i]; + + lock_time_add(&pcs->read_waittime, &stats.read_waittime); + lock_time_add(&pcs->write_waittime, &stats.write_waittime); + + lock_time_add(&pcs->read_holdtime, &stats.read_holdtime); + lock_time_add(&pcs->write_holdtime, &stats.write_holdtime); + + for (i = 0; i < ARRAY_SIZE(stats.bounces); i++) + stats.bounces[i] += pcs->bounces[i]; + } + + return stats; +} + +void clear_lock_stats(struct lock_class *class) +{ + int cpu; + + for_each_possible_cpu(cpu) { + struct lock_class_stats *cpu_stats = + &per_cpu(cpu_lock_stats, cpu)[class - lock_classes]; + + memset(cpu_stats, 0, sizeof(struct lock_class_stats)); + } + memset(class->contention_point, 0, sizeof(class->contention_point)); + memset(class->contending_point, 0, sizeof(class->contending_point)); +} + +static struct lock_class_stats *get_lock_stats(struct lock_class *class) +{ + return &get_cpu_var(cpu_lock_stats)[class - lock_classes]; +} + +static void put_lock_stats(struct lock_class_stats *stats) +{ + put_cpu_var(cpu_lock_stats); +} + +static void lock_release_holdtime(struct held_lock *hlock) +{ + struct lock_class_stats *stats; + u64 holdtime; + + if (!lock_stat) + return; + + holdtime = lockstat_clock() - hlock->holdtime_stamp; + + stats = get_lock_stats(hlock_class(hlock)); + if (hlock->read) + lock_time_inc(&stats->read_holdtime, holdtime); + else + lock_time_inc(&stats->write_holdtime, holdtime); + put_lock_stats(stats); +} +#else +static inline void lock_release_holdtime(struct held_lock *hlock) +{ +} +#endif + +/* + * We keep a global list of all lock classes. The list only grows, + * never shrinks. The list is only accessed with the lockdep + * spinlock lock held. + */ +LIST_HEAD(all_lock_classes); + +/* + * The lockdep classes are in a hash-table as well, for fast lookup: + */ +#define CLASSHASH_BITS (MAX_LOCKDEP_KEYS_BITS - 1) +#define CLASSHASH_SIZE (1UL << CLASSHASH_BITS) +#define __classhashfn(key) hash_long((unsigned long)key, CLASSHASH_BITS) +#define classhashentry(key) (classhash_table + __classhashfn((key))) + +static struct list_head classhash_table[CLASSHASH_SIZE]; + +/* + * We put the lock dependency chains into a hash-table as well, to cache + * their existence: + */ +#define CHAINHASH_BITS (MAX_LOCKDEP_CHAINS_BITS-1) +#define CHAINHASH_SIZE (1UL << CHAINHASH_BITS) +#define __chainhashfn(chain) hash_long(chain, CHAINHASH_BITS) +#define chainhashentry(chain) (chainhash_table + __chainhashfn((chain))) + +static struct list_head chainhash_table[CHAINHASH_SIZE]; + +/* + * The hash key of the lock dependency chains is a hash itself too: + * it's a hash of all locks taken up to that lock, including that lock. + * It's a 64-bit hash, because it's important for the keys to be + * unique. + */ +#define iterate_chain_key(key1, key2) \ + (((key1) << MAX_LOCKDEP_KEYS_BITS) ^ \ + ((key1) >> (64-MAX_LOCKDEP_KEYS_BITS)) ^ \ + (key2)) + +void lockdep_off(void) +{ + current->lockdep_recursion++; +} +EXPORT_SYMBOL(lockdep_off); + +void lockdep_on(void) +{ + current->lockdep_recursion--; +} +EXPORT_SYMBOL(lockdep_on); + +/* + * Debugging switches: + */ + +#define VERBOSE 0 +#define VERY_VERBOSE 0 + +#if VERBOSE +# define HARDIRQ_VERBOSE 1 +# define SOFTIRQ_VERBOSE 1 +# define RECLAIM_VERBOSE 1 +#else +# define HARDIRQ_VERBOSE 0 +# define SOFTIRQ_VERBOSE 0 +# define RECLAIM_VERBOSE 0 +#endif + +#if VERBOSE || HARDIRQ_VERBOSE || SOFTIRQ_VERBOSE || RECLAIM_VERBOSE +/* + * Quick filtering for interesting events: + */ +static int class_filter(struct lock_class *class) +{ +#if 0 + /* Example */ + if (class->name_version == 1 && + !strcmp(class->name, "lockname")) + return 1; + if (class->name_version == 1 && + !strcmp(class->name, "&struct->lockfield")) + return 1; +#endif + /* Filter everything else. 1 would be to allow everything else */ + return 0; +} +#endif + +static int verbose(struct lock_class *class) +{ +#if VERBOSE + return class_filter(class); +#endif + return 0; +} + +/* + * Stack-trace: tightly packed array of stack backtrace + * addresses. Protected by the graph_lock. + */ +unsigned long nr_stack_trace_entries; +static unsigned long stack_trace[MAX_STACK_TRACE_ENTRIES]; + +static void print_lockdep_off(const char *bug_msg) +{ + printk(KERN_DEBUG "%s\n", bug_msg); + printk(KERN_DEBUG "turning off the locking correctness validator.\n"); +#ifdef CONFIG_LOCK_STAT + printk(KERN_DEBUG "Please attach the output of /proc/lock_stat to the bug report\n"); +#endif +} + +static int save_trace(struct stack_trace *trace) +{ + trace->nr_entries = 0; + trace->max_entries = MAX_STACK_TRACE_ENTRIES - nr_stack_trace_entries; + trace->entries = stack_trace + nr_stack_trace_entries; + + trace->skip = 3; + + save_stack_trace(trace); + + /* + * Some daft arches put -1 at the end to indicate its a full trace. + * + * this is buggy anyway, since it takes a whole extra entry so a + * complete trace that maxes out the entries provided will be reported + * as incomplete, friggin useless + */ + if (trace->nr_entries != 0 && + trace->entries[trace->nr_entries-1] == ULONG_MAX) + trace->nr_entries--; + + trace->max_entries = trace->nr_entries; + + nr_stack_trace_entries += trace->nr_entries; + + if (nr_stack_trace_entries >= MAX_STACK_TRACE_ENTRIES-1) { + if (!debug_locks_off_graph_unlock()) + return 0; + + print_lockdep_off("BUG: MAX_STACK_TRACE_ENTRIES too low!"); + dump_stack(); + + return 0; + } + + return 1; +} + +unsigned int nr_hardirq_chains; +unsigned int nr_softirq_chains; +unsigned int nr_process_chains; +unsigned int max_lockdep_depth; + +#ifdef CONFIG_DEBUG_LOCKDEP +/* + * We cannot printk in early bootup code. Not even early_printk() + * might work. So we mark any initialization errors and printk + * about it later on, in lockdep_info(). + */ +static int lockdep_init_error; +static const char *lock_init_error; +static unsigned long lockdep_init_trace_data[20]; +static struct stack_trace lockdep_init_trace = { + .max_entries = ARRAY_SIZE(lockdep_init_trace_data), + .entries = lockdep_init_trace_data, +}; + +/* + * Various lockdep statistics: + */ +DEFINE_PER_CPU(struct lockdep_stats, lockdep_stats); +#endif + +/* + * Locking printouts: + */ + +#define __USAGE(__STATE) \ + [LOCK_USED_IN_##__STATE] = "IN-"__stringify(__STATE)"-W", \ + [LOCK_ENABLED_##__STATE] = __stringify(__STATE)"-ON-W", \ + [LOCK_USED_IN_##__STATE##_READ] = "IN-"__stringify(__STATE)"-R",\ + [LOCK_ENABLED_##__STATE##_READ] = __stringify(__STATE)"-ON-R", + +static const char *usage_str[] = +{ +#define LOCKDEP_STATE(__STATE) __USAGE(__STATE) +#include "lockdep_states.h" +#undef LOCKDEP_STATE + [LOCK_USED] = "INITIAL USE", +}; + +const char * __get_key_name(struct lockdep_subclass_key *key, char *str) +{ + return kallsyms_lookup((unsigned long)key, NULL, NULL, NULL, str); +} + +static inline unsigned long lock_flag(enum lock_usage_bit bit) +{ + return 1UL << bit; +} + +static char get_usage_char(struct lock_class *class, enum lock_usage_bit bit) +{ + char c = '.'; + + if (class->usage_mask & lock_flag(bit + 2)) + c = '+'; + if (class->usage_mask & lock_flag(bit)) { + c = '-'; + if (class->usage_mask & lock_flag(bit + 2)) + c = '?'; + } + + return c; +} + +void get_usage_chars(struct lock_class *class, char usage[LOCK_USAGE_CHARS]) +{ + int i = 0; + +#define LOCKDEP_STATE(__STATE) \ + usage[i++] = get_usage_char(class, LOCK_USED_IN_##__STATE); \ + usage[i++] = get_usage_char(class, LOCK_USED_IN_##__STATE##_READ); +#include "lockdep_states.h" +#undef LOCKDEP_STATE + + usage[i] = '\0'; +} + +static void __print_lock_name(struct lock_class *class) +{ + char str[KSYM_NAME_LEN]; + const char *name; + + name = class->name; + if (!name) { + name = __get_key_name(class->key, str); + printk("%s", name); + } else { + printk("%s", name); + if (class->name_version > 1) + printk("#%d", class->name_version); + if (class->subclass) + printk("/%d", class->subclass); + } +} + +static void print_lock_name(struct lock_class *class) +{ + char usage[LOCK_USAGE_CHARS]; + + get_usage_chars(class, usage); + + printk(" ("); + __print_lock_name(class); + printk("){%s}", usage); +} + +static void print_lockdep_cache(struct lockdep_map *lock) +{ + const char *name; + char str[KSYM_NAME_LEN]; + + name = lock->name; + if (!name) + name = __get_key_name(lock->key->subkeys, str); + + printk("%s", name); +} + +static void print_lock(struct held_lock *hlock) +{ + /* + * We can be called locklessly through debug_show_all_locks() so be + * extra careful, the hlock might have been released and cleared. + */ + unsigned int class_idx = hlock->class_idx; + + /* Don't re-read hlock->class_idx, can't use READ_ONCE() on bitfields: */ + barrier(); + + if (!class_idx || (class_idx - 1) >= MAX_LOCKDEP_KEYS) { + printk("\n"); + return; + } + + print_lock_name(lock_classes + class_idx - 1); + printk(", at: "); + print_ip_sym(hlock->acquire_ip); +} + +static void lockdep_print_held_locks(struct task_struct *curr) +{ + int i, depth = curr->lockdep_depth; + + if (!depth) { + printk("no locks held by %s/%d.\n", curr->comm, task_pid_nr(curr)); + return; + } + printk("%d lock%s held by %s/%d:\n", + depth, depth > 1 ? "s" : "", curr->comm, task_pid_nr(curr)); + + for (i = 0; i < depth; i++) { + printk(" #%d: ", i); + print_lock(curr->held_locks + i); + } +} + +static void print_kernel_ident(void) +{ + printk("%s %.*s %s\n", init_utsname()->release, + (int)strcspn(init_utsname()->version, " "), + init_utsname()->version, + print_tainted()); +} + +static int very_verbose(struct lock_class *class) +{ +#if VERY_VERBOSE + return class_filter(class); +#endif + return 0; +} + +/* + * Is this the address of a static object: + */ +#ifdef __KERNEL__ +static int static_obj(void *obj) +{ + unsigned long start = (unsigned long) &_stext, + end = (unsigned long) &_end, + addr = (unsigned long) obj; + + /* + * static variable? + */ + if ((addr >= start) && (addr < end)) + return 1; + + if (arch_is_kernel_data(addr)) + return 1; + + /* + * in-kernel percpu var? + */ + if (is_kernel_percpu_address(addr)) + return 1; + + /* + * module static or percpu var? + */ + return is_module_address(addr) || is_module_percpu_address(addr); +} +#endif + +/* + * To make lock name printouts unique, we calculate a unique + * class->name_version generation counter: + */ +static int count_matching_names(struct lock_class *new_class) +{ + struct lock_class *class; + int count = 0; + + if (!new_class->name) + return 0; + + list_for_each_entry_rcu(class, &all_lock_classes, lock_entry) { + if (new_class->key - new_class->subclass == class->key) + return class->name_version; + if (class->name && !strcmp(class->name, new_class->name)) + count = max(count, class->name_version); + } + + return count + 1; +} + +/* + * Register a lock's class in the hash-table, if the class is not present + * yet. Otherwise we look it up. We cache the result in the lock object + * itself, so actual lookup of the hash should be once per lock object. + */ +static inline struct lock_class * +look_up_lock_class(struct lockdep_map *lock, unsigned int subclass) +{ + struct lockdep_subclass_key *key; + struct list_head *hash_head; + struct lock_class *class; + +#ifdef CONFIG_DEBUG_LOCKDEP + /* + * If the architecture calls into lockdep before initializing + * the hashes then we'll warn about it later. (we cannot printk + * right now) + */ + if (unlikely(!lockdep_initialized)) { + lockdep_init(); + lockdep_init_error = 1; + lock_init_error = lock->name; + save_stack_trace(&lockdep_init_trace); + } +#endif + + if (unlikely(subclass >= MAX_LOCKDEP_SUBCLASSES)) { + debug_locks_off(); + printk(KERN_ERR + "BUG: looking up invalid subclass: %u\n", subclass); + printk(KERN_ERR + "turning off the locking correctness validator.\n"); + dump_stack(); + return NULL; + } + + /* + * Static locks do not have their class-keys yet - for them the key + * is the lock object itself: + */ + if (unlikely(!lock->key)) + lock->key = (void *)lock; + + /* + * NOTE: the class-key must be unique. For dynamic locks, a static + * lock_class_key variable is passed in through the mutex_init() + * (or spin_lock_init()) call - which acts as the key. For static + * locks we use the lock object itself as the key. + */ + BUILD_BUG_ON(sizeof(struct lock_class_key) > + sizeof(struct lockdep_map)); + + key = lock->key->subkeys + subclass; + + hash_head = classhashentry(key); + + /* + * We do an RCU walk of the hash, see lockdep_free_key_range(). + */ + if (DEBUG_LOCKS_WARN_ON(!irqs_disabled())) + return NULL; + + list_for_each_entry_rcu(class, hash_head, hash_entry) { + if (class->key == key) { + /* + * Huh! same key, different name? Did someone trample + * on some memory? We're most confused. + */ + WARN_ON_ONCE(class->name != lock->name); + return class; + } + } + + return NULL; +} + +/* + * Register a lock's class in the hash-table, if the class is not present + * yet. Otherwise we look it up. We cache the result in the lock object + * itself, so actual lookup of the hash should be once per lock object. + */ +static inline struct lock_class * +register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force) +{ + struct lockdep_subclass_key *key; + struct list_head *hash_head; + struct lock_class *class; + + DEBUG_LOCKS_WARN_ON(!irqs_disabled()); + + class = look_up_lock_class(lock, subclass); + if (likely(class)) + goto out_set_class_cache; + + /* + * Debug-check: all keys must be persistent! + */ + if (!static_obj(lock->key)) { + debug_locks_off(); + printk("INFO: trying to register non-static key.\n"); + printk("the code is fine but needs lockdep annotation.\n"); + printk("turning off the locking correctness validator.\n"); + dump_stack(); + + return NULL; + } + + key = lock->key->subkeys + subclass; + hash_head = classhashentry(key); + + if (!graph_lock()) { + return NULL; + } + /* + * We have to do the hash-walk again, to avoid races + * with another CPU: + */ + list_for_each_entry_rcu(class, hash_head, hash_entry) { + if (class->key == key) + goto out_unlock_set; + } + + /* + * Allocate a new key from the static array, and add it to + * the hash: + */ + if (nr_lock_classes >= MAX_LOCKDEP_KEYS) { + if (!debug_locks_off_graph_unlock()) { + return NULL; + } + + print_lockdep_off("BUG: MAX_LOCKDEP_KEYS too low!"); + dump_stack(); + return NULL; + } + class = lock_classes + nr_lock_classes++; + debug_atomic_inc(nr_unused_locks); + class->key = key; + class->name = lock->name; + class->subclass = subclass; + INIT_LIST_HEAD(&class->lock_entry); + INIT_LIST_HEAD(&class->locks_before); + INIT_LIST_HEAD(&class->locks_after); + class->name_version = count_matching_names(class); + /* + * We use RCU's safe list-add method to make + * parallel walking of the hash-list safe: + */ + list_add_tail_rcu(&class->hash_entry, hash_head); + /* + * Add it to the global list of classes: + */ + list_add_tail_rcu(&class->lock_entry, &all_lock_classes); + + if (verbose(class)) { + graph_unlock(); + + printk("\nnew class %p: %s", class->key, class->name); + if (class->name_version > 1) + printk("#%d", class->name_version); + printk("\n"); + dump_stack(); + + if (!graph_lock()) { + return NULL; + } + } +out_unlock_set: + graph_unlock(); + +out_set_class_cache: + if (!subclass || force) + lock->class_cache[0] = class; + else if (subclass < NR_LOCKDEP_CACHING_CLASSES) + lock->class_cache[subclass] = class; + + /* + * Hash collision, did we smoke some? We found a class with a matching + * hash but the subclass -- which is hashed in -- didn't match. + */ + if (DEBUG_LOCKS_WARN_ON(class->subclass != subclass)) + return NULL; + + return class; +} + +#ifdef CONFIG_PROVE_LOCKING +/* + * Allocate a lockdep entry. (assumes the graph_lock held, returns + * with NULL on failure) + */ +static struct lock_list *alloc_list_entry(void) +{ + if (nr_list_entries >= MAX_LOCKDEP_ENTRIES) { + if (!debug_locks_off_graph_unlock()) + return NULL; + + print_lockdep_off("BUG: MAX_LOCKDEP_ENTRIES too low!"); + dump_stack(); + return NULL; + } + return list_entries + nr_list_entries++; +} + +/* + * Add a new dependency to the head of the list: + */ +static int add_lock_to_list(struct lock_class *class, struct lock_class *this, + struct list_head *head, unsigned long ip, + int distance, struct stack_trace *trace) +{ + struct lock_list *entry; + /* + * Lock not present yet - get a new dependency struct and + * add it to the list: + */ + entry = alloc_list_entry(); + if (!entry) + return 0; + + entry->class = this; + entry->distance = distance; + entry->trace = *trace; + /* + * Both allocation and removal are done under the graph lock; but + * iteration is under RCU-sched; see look_up_lock_class() and + * lockdep_free_key_range(). + */ + list_add_tail_rcu(&entry->entry, head); + + return 1; +} + +/* + * For good efficiency of modular, we use power of 2 + */ +#define MAX_CIRCULAR_QUEUE_SIZE 4096UL +#define CQ_MASK (MAX_CIRCULAR_QUEUE_SIZE-1) + +/* + * The circular_queue and helpers is used to implement the + * breadth-first search(BFS)algorithem, by which we can build + * the shortest path from the next lock to be acquired to the + * previous held lock if there is a circular between them. + */ +struct circular_queue { + unsigned long element[MAX_CIRCULAR_QUEUE_SIZE]; + unsigned int front, rear; +}; + +static struct circular_queue lock_cq; + +unsigned int max_bfs_queue_depth; + +static unsigned int lockdep_dependency_gen_id; + +static inline void __cq_init(struct circular_queue *cq) +{ + cq->front = cq->rear = 0; + lockdep_dependency_gen_id++; +} + +static inline int __cq_empty(struct circular_queue *cq) +{ + return (cq->front == cq->rear); +} + +static inline int __cq_full(struct circular_queue *cq) +{ + return ((cq->rear + 1) & CQ_MASK) == cq->front; +} + +static inline int __cq_enqueue(struct circular_queue *cq, unsigned long elem) +{ + if (__cq_full(cq)) + return -1; + + cq->element[cq->rear] = elem; + cq->rear = (cq->rear + 1) & CQ_MASK; + return 0; +} + +static inline int __cq_dequeue(struct circular_queue *cq, unsigned long *elem) +{ + if (__cq_empty(cq)) + return -1; + + *elem = cq->element[cq->front]; + cq->front = (cq->front + 1) & CQ_MASK; + return 0; +} + +static inline unsigned int __cq_get_elem_count(struct circular_queue *cq) +{ + return (cq->rear - cq->front) & CQ_MASK; +} + +static inline void mark_lock_accessed(struct lock_list *lock, + struct lock_list *parent) +{ + unsigned long nr; + + nr = lock - list_entries; + WARN_ON(nr >= nr_list_entries); /* Out-of-bounds, input fail */ + lock->parent = parent; + lock->class->dep_gen_id = lockdep_dependency_gen_id; +} + +static inline unsigned long lock_accessed(struct lock_list *lock) +{ + unsigned long nr; + + nr = lock - list_entries; + WARN_ON(nr >= nr_list_entries); /* Out-of-bounds, input fail */ + return lock->class->dep_gen_id == lockdep_dependency_gen_id; +} + +static inline struct lock_list *get_lock_parent(struct lock_list *child) +{ + return child->parent; +} + +static inline int get_lock_depth(struct lock_list *child) +{ + int depth = 0; + struct lock_list *parent; + + while ((parent = get_lock_parent(child))) { + child = parent; + depth++; + } + return depth; +} + +static int __bfs(struct lock_list *source_entry, + void *data, + int (*match)(struct lock_list *entry, void *data), + struct lock_list **target_entry, + int forward) +{ + struct lock_list *entry; + struct list_head *head; + struct circular_queue *cq = &lock_cq; + int ret = 1; + + if (match(source_entry, data)) { + *target_entry = source_entry; + ret = 0; + goto exit; + } + + if (forward) + head = &source_entry->class->locks_after; + else + head = &source_entry->class->locks_before; + + if (list_empty(head)) + goto exit; + + __cq_init(cq); + __cq_enqueue(cq, (unsigned long)source_entry); + + while (!__cq_empty(cq)) { + struct lock_list *lock; + + __cq_dequeue(cq, (unsigned long *)&lock); + + if (!lock->class) { + ret = -2; + goto exit; + } + + if (forward) + head = &lock->class->locks_after; + else + head = &lock->class->locks_before; + + DEBUG_LOCKS_WARN_ON(!irqs_disabled()); + + list_for_each_entry_rcu(entry, head, entry) { + if (!lock_accessed(entry)) { + unsigned int cq_depth; + mark_lock_accessed(entry, lock); + if (match(entry, data)) { + *target_entry = entry; + ret = 0; + goto exit; + } + + if (__cq_enqueue(cq, (unsigned long)entry)) { + ret = -1; + goto exit; + } + cq_depth = __cq_get_elem_count(cq); + if (max_bfs_queue_depth < cq_depth) + max_bfs_queue_depth = cq_depth; + } + } + } +exit: + return ret; +} + +static inline int __bfs_forwards(struct lock_list *src_entry, + void *data, + int (*match)(struct lock_list *entry, void *data), + struct lock_list **target_entry) +{ + return __bfs(src_entry, data, match, target_entry, 1); + +} + +static inline int __bfs_backwards(struct lock_list *src_entry, + void *data, + int (*match)(struct lock_list *entry, void *data), + struct lock_list **target_entry) +{ + return __bfs(src_entry, data, match, target_entry, 0); + +} + +/* + * Recursive, forwards-direction lock-dependency checking, used for + * both noncyclic checking and for hardirq-unsafe/softirq-unsafe + * checking. + */ + +/* + * Print a dependency chain entry (this is only done when a deadlock + * has been detected): + */ +static noinline int +print_circular_bug_entry(struct lock_list *target, int depth) +{ + if (debug_locks_silent) + return 0; + printk("\n-> #%u", depth); + print_lock_name(target->class); + printk(":\n"); + print_stack_trace(&target->trace, 6); + + return 0; +} + +static void +print_circular_lock_scenario(struct held_lock *src, + struct held_lock *tgt, + struct lock_list *prt) +{ + struct lock_class *source = hlock_class(src); + struct lock_class *target = hlock_class(tgt); + struct lock_class *parent = prt->class; + + /* + * A direct locking problem where unsafe_class lock is taken + * directly by safe_class lock, then all we need to show + * is the deadlock scenario, as it is obvious that the + * unsafe lock is taken under the safe lock. + * + * But if there is a chain instead, where the safe lock takes + * an intermediate lock (middle_class) where this lock is + * not the same as the safe lock, then the lock chain is + * used to describe the problem. Otherwise we would need + * to show a different CPU case for each link in the chain + * from the safe_class lock to the unsafe_class lock. + */ + if (parent != source) { + printk("Chain exists of:\n "); + __print_lock_name(source); + printk(" --> "); + __print_lock_name(parent); + printk(" --> "); + __print_lock_name(target); + printk("\n\n"); + } + + printk(" Possible unsafe locking scenario:\n\n"); + printk(" CPU0 CPU1\n"); + printk(" ---- ----\n"); + printk(" lock("); + __print_lock_name(target); + printk(");\n"); + printk(" lock("); + __print_lock_name(parent); + printk(");\n"); + printk(" lock("); + __print_lock_name(target); + printk(");\n"); + printk(" lock("); + __print_lock_name(source); + printk(");\n"); + printk("\n *** DEADLOCK ***\n\n"); +} + +/* + * When a circular dependency is detected, print the + * header first: + */ +static noinline int +print_circular_bug_header(struct lock_list *entry, unsigned int depth, + struct held_lock *check_src, + struct held_lock *check_tgt) +{ + struct task_struct *curr = current; + + if (debug_locks_silent) + return 0; + + printk("\n"); + printk("======================================================\n"); + printk("[ INFO: possible circular locking dependency detected ]\n"); + print_kernel_ident(); + printk("-------------------------------------------------------\n"); + printk("%s/%d is trying to acquire lock:\n", + curr->comm, task_pid_nr(curr)); + print_lock(check_src); + printk("\nbut task is already holding lock:\n"); + print_lock(check_tgt); + printk("\nwhich lock already depends on the new lock.\n\n"); + printk("\nthe existing dependency chain (in reverse order) is:\n"); + + print_circular_bug_entry(entry, depth); + + return 0; +} + +static inline int class_equal(struct lock_list *entry, void *data) +{ + return entry->class == data; +} + +static noinline int print_circular_bug(struct lock_list *this, + struct lock_list *target, + struct held_lock *check_src, + struct held_lock *check_tgt) +{ + struct task_struct *curr = current; + struct lock_list *parent; + struct lock_list *first_parent; + int depth; + + if (!debug_locks_off_graph_unlock() || debug_locks_silent) + return 0; + + if (!save_trace(&this->trace)) + return 0; + + depth = get_lock_depth(target); + + print_circular_bug_header(target, depth, check_src, check_tgt); + + parent = get_lock_parent(target); + first_parent = parent; + + while (parent) { + print_circular_bug_entry(parent, --depth); + parent = get_lock_parent(parent); + } + + printk("\nother info that might help us debug this:\n\n"); + print_circular_lock_scenario(check_src, check_tgt, + first_parent); + + lockdep_print_held_locks(curr); + + printk("\nstack backtrace:\n"); + dump_stack(); + + return 0; +} + +static noinline int print_bfs_bug(int ret) +{ + if (!debug_locks_off_graph_unlock()) + return 0; + + /* + * Breadth-first-search failed, graph got corrupted? + */ + WARN(1, "lockdep bfs error:%d\n", ret); + + return 0; +} + +static int noop_count(struct lock_list *entry, void *data) +{ + (*(unsigned long *)data)++; + return 0; +} + +static unsigned long __lockdep_count_forward_deps(struct lock_list *this) +{ + unsigned long count = 0; + struct lock_list *uninitialized_var(target_entry); + + __bfs_forwards(this, (void *)&count, noop_count, &target_entry); + + return count; +} +unsigned long lockdep_count_forward_deps(struct lock_class *class) +{ + unsigned long ret, flags; + struct lock_list this; + + this.parent = NULL; + this.class = class; + + local_irq_save(flags); + arch_spin_lock(&lockdep_lock); + ret = __lockdep_count_forward_deps(&this); + arch_spin_unlock(&lockdep_lock); + local_irq_restore(flags); + + return ret; +} + +static unsigned long __lockdep_count_backward_deps(struct lock_list *this) +{ + unsigned long count = 0; + struct lock_list *uninitialized_var(target_entry); + + __bfs_backwards(this, (void *)&count, noop_count, &target_entry); + + return count; +} + +unsigned long lockdep_count_backward_deps(struct lock_class *class) +{ + unsigned long ret, flags; + struct lock_list this; + + this.parent = NULL; + this.class = class; + + local_irq_save(flags); + arch_spin_lock(&lockdep_lock); + ret = __lockdep_count_backward_deps(&this); + arch_spin_unlock(&lockdep_lock); + local_irq_restore(flags); + + return ret; +} + +/* + * Prove that the dependency graph starting at can not + * lead to . Print an error and return 0 if it does. + */ +static noinline int +check_noncircular(struct lock_list *root, struct lock_class *target, + struct lock_list **target_entry) +{ + int result; + + debug_atomic_inc(nr_cyclic_checks); + + result = __bfs_forwards(root, target, class_equal, target_entry); + + return result; +} + +#if defined(CONFIG_TRACE_IRQFLAGS) && defined(CONFIG_PROVE_LOCKING) +/* + * Forwards and backwards subgraph searching, for the purposes of + * proving that two subgraphs can be connected by a new dependency + * without creating any illegal irq-safe -> irq-unsafe lock dependency. + */ + +static inline int usage_match(struct lock_list *entry, void *bit) +{ + return entry->class->usage_mask & (1 << (enum lock_usage_bit)bit); +} + + + +/* + * Find a node in the forwards-direction dependency sub-graph starting + * at @root->class that matches @bit. + * + * Return 0 if such a node exists in the subgraph, and put that node + * into *@target_entry. + * + * Return 1 otherwise and keep *@target_entry unchanged. + * Return <0 on error. + */ +static int +find_usage_forwards(struct lock_list *root, enum lock_usage_bit bit, + struct lock_list **target_entry) +{ + int result; + + debug_atomic_inc(nr_find_usage_forwards_checks); + + result = __bfs_forwards(root, (void *)bit, usage_match, target_entry); + + return result; +} + +/* + * Find a node in the backwards-direction dependency sub-graph starting + * at @root->class that matches @bit. + * + * Return 0 if such a node exists in the subgraph, and put that node + * into *@target_entry. + * + * Return 1 otherwise and keep *@target_entry unchanged. + * Return <0 on error. + */ +static int +find_usage_backwards(struct lock_list *root, enum lock_usage_bit bit, + struct lock_list **target_entry) +{ + int result; + + debug_atomic_inc(nr_find_usage_backwards_checks); + + result = __bfs_backwards(root, (void *)bit, usage_match, target_entry); + + return result; +} + +static void print_lock_class_header(struct lock_class *class, int depth) +{ + int bit; + + printk("%*s->", depth, ""); + print_lock_name(class); + printk(" ops: %lu", class->ops); + printk(" {\n"); + + for (bit = 0; bit < LOCK_USAGE_STATES; bit++) { + if (class->usage_mask & (1 << bit)) { + int len = depth; + + len += printk("%*s %s", depth, "", usage_str[bit]); + len += printk(" at:\n"); + print_stack_trace(class->usage_traces + bit, len); + } + } + printk("%*s }\n", depth, ""); + + printk("%*s ... key at: ",depth,""); + print_ip_sym((unsigned long)class->key); +} + +/* + * printk the shortest lock dependencies from @start to @end in reverse order: + */ +static void __used +print_shortest_lock_dependencies(struct lock_list *leaf, + struct lock_list *root) +{ + struct lock_list *entry = leaf; + int depth; + + /*compute depth from generated tree by BFS*/ + depth = get_lock_depth(leaf); + + do { + print_lock_class_header(entry->class, depth); + printk("%*s ... acquired at:\n", depth, ""); + print_stack_trace(&entry->trace, 2); + printk("\n"); + + if (depth == 0 && (entry != root)) { + printk("lockdep:%s bad path found in chain graph\n", __func__); + break; + } + + entry = get_lock_parent(entry); + depth--; + } while (entry && (depth >= 0)); + + return; +} + +static void +print_irq_lock_scenario(struct lock_list *safe_entry, + struct lock_list *unsafe_entry, + struct lock_class *prev_class, + struct lock_class *next_class) +{ + struct lock_class *safe_class = safe_entry->class; + struct lock_class *unsafe_class = unsafe_entry->class; + struct lock_class *middle_class = prev_class; + + if (middle_class == safe_class) + middle_class = next_class; + + /* + * A direct locking problem where unsafe_class lock is taken + * directly by safe_class lock, then all we need to show + * is the deadlock scenario, as it is obvious that the + * unsafe lock is taken under the safe lock. + * + * But if there is a chain instead, where the safe lock takes + * an intermediate lock (middle_class) where this lock is + * not the same as the safe lock, then the lock chain is + * used to describe the problem. Otherwise we would need + * to show a different CPU case for each link in the chain + * from the safe_class lock to the unsafe_class lock. + */ + if (middle_class != unsafe_class) { + printk("Chain exists of:\n "); + __print_lock_name(safe_class); + printk(" --> "); + __print_lock_name(middle_class); + printk(" --> "); + __print_lock_name(unsafe_class); + printk("\n\n"); + } + + printk(" Possible interrupt unsafe locking scenario:\n\n"); + printk(" CPU0 CPU1\n"); + printk(" ---- ----\n"); + printk(" lock("); + __print_lock_name(unsafe_class); + printk(");\n"); + printk(" local_irq_disable();\n"); + printk(" lock("); + __print_lock_name(safe_class); + printk(");\n"); + printk(" lock("); + __print_lock_name(middle_class); + printk(");\n"); + printk(" \n"); + printk(" lock("); + __print_lock_name(safe_class); + printk(");\n"); + printk("\n *** DEADLOCK ***\n\n"); +} + +static int +print_bad_irq_dependency(struct task_struct *curr, + struct lock_list *prev_root, + struct lock_list *next_root, + struct lock_list *backwards_entry, + struct lock_list *forwards_entry, + struct held_lock *prev, + struct held_lock *next, + enum lock_usage_bit bit1, + enum lock_usage_bit bit2, + const char *irqclass) +{ + if (!debug_locks_off_graph_unlock() || debug_locks_silent) + return 0; + + printk("\n"); + printk("======================================================\n"); + printk("[ INFO: %s-safe -> %s-unsafe lock order detected ]\n", + irqclass, irqclass); + print_kernel_ident(); + printk("------------------------------------------------------\n"); + printk("%s/%d [HC%u[%lu]:SC%u[%lu]:HE%u:SE%u] is trying to acquire:\n", + curr->comm, task_pid_nr(curr), + curr->hardirq_context, hardirq_count() >> HARDIRQ_SHIFT, + curr->softirq_context, softirq_count() >> SOFTIRQ_SHIFT, + curr->hardirqs_enabled, + curr->softirqs_enabled); + print_lock(next); + + printk("\nand this task is already holding:\n"); + print_lock(prev); + printk("which would create a new lock dependency:\n"); + print_lock_name(hlock_class(prev)); + printk(" ->"); + print_lock_name(hlock_class(next)); + printk("\n"); + + printk("\nbut this new dependency connects a %s-irq-safe lock:\n", + irqclass); + print_lock_name(backwards_entry->class); + printk("\n... which became %s-irq-safe at:\n", irqclass); + + print_stack_trace(backwards_entry->class->usage_traces + bit1, 1); + + printk("\nto a %s-irq-unsafe lock:\n", irqclass); + print_lock_name(forwards_entry->class); + printk("\n... which became %s-irq-unsafe at:\n", irqclass); + printk("..."); + + print_stack_trace(forwards_entry->class->usage_traces + bit2, 1); + + printk("\nother info that might help us debug this:\n\n"); + print_irq_lock_scenario(backwards_entry, forwards_entry, + hlock_class(prev), hlock_class(next)); + + lockdep_print_held_locks(curr); + + printk("\nthe dependencies between %s-irq-safe lock", irqclass); + printk(" and the holding lock:\n"); + if (!save_trace(&prev_root->trace)) + return 0; + print_shortest_lock_dependencies(backwards_entry, prev_root); + + printk("\nthe dependencies between the lock to be acquired"); + printk(" and %s-irq-unsafe lock:\n", irqclass); + if (!save_trace(&next_root->trace)) + return 0; + print_shortest_lock_dependencies(forwards_entry, next_root); + + printk("\nstack backtrace:\n"); + dump_stack(); + + return 0; +} + +static int +check_usage(struct task_struct *curr, struct held_lock *prev, + struct held_lock *next, enum lock_usage_bit bit_backwards, + enum lock_usage_bit bit_forwards, const char *irqclass) +{ + int ret; + struct lock_list this, that; + struct lock_list *uninitialized_var(target_entry); + struct lock_list *uninitialized_var(target_entry1); + + this.parent = NULL; + + this.class = hlock_class(prev); + ret = find_usage_backwards(&this, bit_backwards, &target_entry); + if (ret < 0) + return print_bfs_bug(ret); + if (ret == 1) + return ret; + + that.parent = NULL; + that.class = hlock_class(next); + ret = find_usage_forwards(&that, bit_forwards, &target_entry1); + if (ret < 0) + return print_bfs_bug(ret); + if (ret == 1) + return ret; + + return print_bad_irq_dependency(curr, &this, &that, + target_entry, target_entry1, + prev, next, + bit_backwards, bit_forwards, irqclass); +} + +static const char *state_names[] = { +#define LOCKDEP_STATE(__STATE) \ + __stringify(__STATE), +#include "lockdep_states.h" +#undef LOCKDEP_STATE +}; + +static const char *state_rnames[] = { +#define LOCKDEP_STATE(__STATE) \ + __stringify(__STATE)"-READ", +#include "lockdep_states.h" +#undef LOCKDEP_STATE +}; + +static inline const char *state_name(enum lock_usage_bit bit) +{ + return (bit & 1) ? state_rnames[bit >> 2] : state_names[bit >> 2]; +} + +static int exclusive_bit(int new_bit) +{ + /* + * USED_IN + * USED_IN_READ + * ENABLED + * ENABLED_READ + * + * bit 0 - write/read + * bit 1 - used_in/enabled + * bit 2+ state + */ + + int state = new_bit & ~3; + int dir = new_bit & 2; + + /* + * keep state, bit flip the direction and strip read. + */ + return state | (dir ^ 2); +} + +static int check_irq_usage(struct task_struct *curr, struct held_lock *prev, + struct held_lock *next, enum lock_usage_bit bit) +{ + /* + * Prove that the new dependency does not connect a hardirq-safe + * lock with a hardirq-unsafe lock - to achieve this we search + * the backwards-subgraph starting at , and the + * forwards-subgraph starting at : + */ + if (!check_usage(curr, prev, next, bit, + exclusive_bit(bit), state_name(bit))) + return 0; + + bit++; /* _READ */ + + /* + * Prove that the new dependency does not connect a hardirq-safe-read + * lock with a hardirq-unsafe lock - to achieve this we search + * the backwards-subgraph starting at , and the + * forwards-subgraph starting at : + */ + if (!check_usage(curr, prev, next, bit, + exclusive_bit(bit), state_name(bit))) + return 0; + + return 1; +} + +static int +check_prev_add_irq(struct task_struct *curr, struct held_lock *prev, + struct held_lock *next) +{ +#define LOCKDEP_STATE(__STATE) \ + if (!check_irq_usage(curr, prev, next, LOCK_USED_IN_##__STATE)) \ + return 0; +#include "lockdep_states.h" +#undef LOCKDEP_STATE + + return 1; +} + +static void inc_chains(void) +{ + if (current->hardirq_context) + nr_hardirq_chains++; + else { + if (current->softirq_context) + nr_softirq_chains++; + else + nr_process_chains++; + } +} + +#else + +static inline int +check_prev_add_irq(struct task_struct *curr, struct held_lock *prev, + struct held_lock *next) +{ + return 1; +} + +static inline void inc_chains(void) +{ + nr_process_chains++; +} + +#endif + +static void +print_deadlock_scenario(struct held_lock *nxt, + struct held_lock *prv) +{ + struct lock_class *next = hlock_class(nxt); + struct lock_class *prev = hlock_class(prv); + + printk(" Possible unsafe locking scenario:\n\n"); + printk(" CPU0\n"); + printk(" ----\n"); + printk(" lock("); + __print_lock_name(prev); + printk(");\n"); + printk(" lock("); + __print_lock_name(next); + printk(");\n"); + printk("\n *** DEADLOCK ***\n\n"); + printk(" May be due to missing lock nesting notation\n\n"); +} + +static int +print_deadlock_bug(struct task_struct *curr, struct held_lock *prev, + struct held_lock *next) +{ + if (!debug_locks_off_graph_unlock() || debug_locks_silent) + return 0; + + printk("\n"); + printk("=============================================\n"); + printk("[ INFO: possible recursive locking detected ]\n"); + print_kernel_ident(); + printk("---------------------------------------------\n"); + printk("%s/%d is trying to acquire lock:\n", + curr->comm, task_pid_nr(curr)); + print_lock(next); + printk("\nbut task is already holding lock:\n"); + print_lock(prev); + + printk("\nother info that might help us debug this:\n"); + print_deadlock_scenario(next, prev); + lockdep_print_held_locks(curr); + + printk("\nstack backtrace:\n"); + dump_stack(); + + return 0; +} + +/* + * Check whether we are holding such a class already. + * + * (Note that this has to be done separately, because the graph cannot + * detect such classes of deadlocks.) + * + * Returns: 0 on deadlock detected, 1 on OK, 2 on recursive read + */ +static int +check_deadlock(struct task_struct *curr, struct held_lock *next, + struct lockdep_map *next_instance, int read) +{ + struct held_lock *prev; + struct held_lock *nest = NULL; + int i; + + for (i = 0; i < curr->lockdep_depth; i++) { + prev = curr->held_locks + i; + + if (prev->instance == next->nest_lock) + nest = prev; + + if (hlock_class(prev) != hlock_class(next)) + continue; + + /* + * Allow read-after-read recursion of the same + * lock class (i.e. read_lock(lock)+read_lock(lock)): + */ + if ((read == 2) && prev->read) + return 2; + + /* + * We're holding the nest_lock, which serializes this lock's + * nesting behaviour. + */ + if (nest) + return 2; + + return print_deadlock_bug(curr, prev, next); + } + return 1; +} + +/* + * There was a chain-cache miss, and we are about to add a new dependency + * to a previous lock. We recursively validate the following rules: + * + * - would the adding of the -> dependency create a + * circular dependency in the graph? [== circular deadlock] + * + * - does the new prev->next dependency connect any hardirq-safe lock + * (in the full backwards-subgraph starting at ) with any + * hardirq-unsafe lock (in the full forwards-subgraph starting at + * )? [== illegal lock inversion with hardirq contexts] + * + * - does the new prev->next dependency connect any softirq-safe lock + * (in the full backwards-subgraph starting at ) with any + * softirq-unsafe lock (in the full forwards-subgraph starting at + * )? [== illegal lock inversion with softirq contexts] + * + * any of these scenarios could lead to a deadlock. + * + * Then if all the validations pass, we add the forwards and backwards + * dependency. + */ +static int +check_prev_add(struct task_struct *curr, struct held_lock *prev, + struct held_lock *next, int distance, int trylock_loop) +{ + struct lock_list *entry; + int ret; + struct lock_list this; + struct lock_list *uninitialized_var(target_entry); + /* + * Static variable, serialized by the graph_lock(). + * + * We use this static variable to save the stack trace in case + * we call into this function multiple times due to encountering + * trylocks in the held lock stack. + */ + static struct stack_trace trace; + + /* + * Prove that the new -> dependency would not + * create a circular dependency in the graph. (We do this by + * forward-recursing into the graph starting at , and + * checking whether we can reach .) + * + * We are using global variables to control the recursion, to + * keep the stackframe size of the recursive functions low: + */ + this.class = hlock_class(next); + this.parent = NULL; + ret = check_noncircular(&this, hlock_class(prev), &target_entry); + if (unlikely(!ret)) + return print_circular_bug(&this, target_entry, next, prev); + else if (unlikely(ret < 0)) + return print_bfs_bug(ret); + + if (!check_prev_add_irq(curr, prev, next)) + return 0; + + /* + * For recursive read-locks we do all the dependency checks, + * but we dont store read-triggered dependencies (only + * write-triggered dependencies). This ensures that only the + * write-side dependencies matter, and that if for example a + * write-lock never takes any other locks, then the reads are + * equivalent to a NOP. + */ + if (next->read == 2 || prev->read == 2) + return 1; + /* + * Is the -> dependency already present? + * + * (this may occur even though this is a new chain: consider + * e.g. the L1 -> L2 -> L3 -> L4 and the L5 -> L1 -> L2 -> L3 + * chains - the second one will be new, but L1 already has + * L2 added to its dependency list, due to the first chain.) + */ + list_for_each_entry(entry, &hlock_class(prev)->locks_after, entry) { + if (entry->class == hlock_class(next)) { + if (distance == 1) + entry->distance = 1; + return 2; + } + } + + if (!trylock_loop && !save_trace(&trace)) + return 0; + + /* + * Ok, all validations passed, add the new lock + * to the previous lock's dependency list: + */ + ret = add_lock_to_list(hlock_class(prev), hlock_class(next), + &hlock_class(prev)->locks_after, + next->acquire_ip, distance, &trace); + + if (!ret) + return 0; + + ret = add_lock_to_list(hlock_class(next), hlock_class(prev), + &hlock_class(next)->locks_before, + next->acquire_ip, distance, &trace); + if (!ret) + return 0; + + /* + * Debugging printouts: + */ + if (verbose(hlock_class(prev)) || verbose(hlock_class(next))) { + graph_unlock(); + printk("\n new dependency: "); + print_lock_name(hlock_class(prev)); + printk(" => "); + print_lock_name(hlock_class(next)); + printk("\n"); + dump_stack(); + return graph_lock(); + } + return 1; +} + +/* + * Add the dependency to all directly-previous locks that are 'relevant'. + * The ones that are relevant are (in increasing distance from curr): + * all consecutive trylock entries and the final non-trylock entry - or + * the end of this context's lock-chain - whichever comes first. + */ +static int +check_prevs_add(struct task_struct *curr, struct held_lock *next) +{ + int depth = curr->lockdep_depth; + int trylock_loop = 0; + struct held_lock *hlock; + + /* + * Debugging checks. + * + * Depth must not be zero for a non-head lock: + */ + if (!depth) + goto out_bug; + /* + * At least two relevant locks must exist for this + * to be a head: + */ + if (curr->held_locks[depth].irq_context != + curr->held_locks[depth-1].irq_context) + goto out_bug; + + for (;;) { + int distance = curr->lockdep_depth - depth + 1; + hlock = curr->held_locks + depth - 1; + /* + * Only non-recursive-read entries get new dependencies + * added: + */ + if (hlock->read != 2 && hlock->check) { + if (!check_prev_add(curr, hlock, next, + distance, trylock_loop)) + return 0; + /* + * Stop after the first non-trylock entry, + * as non-trylock entries have added their + * own direct dependencies already, so this + * lock is connected to them indirectly: + */ + if (!hlock->trylock) + break; + } + depth--; + /* + * End of lock-stack? + */ + if (!depth) + break; + /* + * Stop the search if we cross into another context: + */ + if (curr->held_locks[depth].irq_context != + curr->held_locks[depth-1].irq_context) + break; + trylock_loop = 1; + } + return 1; +out_bug: + if (!debug_locks_off_graph_unlock()) + return 0; + + /* + * Clearly we all shouldn't be here, but since we made it we + * can reliable say we messed up our state. See the above two + * gotos for reasons why we could possibly end up here. + */ + WARN_ON(1); + + return 0; +} + +unsigned long nr_lock_chains; +struct lock_chain lock_chains[MAX_LOCKDEP_CHAINS]; +int nr_chain_hlocks; +static u16 chain_hlocks[MAX_LOCKDEP_CHAIN_HLOCKS]; + +struct lock_class *lock_chain_get_class(struct lock_chain *chain, int i) +{ + return lock_classes + chain_hlocks[chain->base + i]; +} + +/* + * Look up a dependency chain. If the key is not present yet then + * add it and return 1 - in this case the new dependency chain is + * validated. If the key is already hashed, return 0. + * (On return with 1 graph_lock is held.) + */ +static inline int lookup_chain_cache(struct task_struct *curr, + struct held_lock *hlock, + u64 chain_key) +{ + struct lock_class *class = hlock_class(hlock); + struct list_head *hash_head = chainhashentry(chain_key); + struct lock_chain *chain; + struct held_lock *hlock_curr; + int i, j; + + /* + * We might need to take the graph lock, ensure we've got IRQs + * disabled to make this an IRQ-safe lock.. for recursion reasons + * lockdep won't complain about its own locking errors. + */ + if (DEBUG_LOCKS_WARN_ON(!irqs_disabled())) + return 0; + /* + * We can walk it lock-free, because entries only get added + * to the hash: + */ + list_for_each_entry_rcu(chain, hash_head, entry) { + if (chain->chain_key == chain_key) { +cache_hit: + debug_atomic_inc(chain_lookup_hits); + if (very_verbose(class)) + printk("\nhash chain already cached, key: " + "%016Lx tail class: [%p] %s\n", + (unsigned long long)chain_key, + class->key, class->name); + return 0; + } + } + if (very_verbose(class)) + printk("\nnew hash chain, key: %016Lx tail class: [%p] %s\n", + (unsigned long long)chain_key, class->key, class->name); + /* + * Allocate a new chain entry from the static array, and add + * it to the hash: + */ + if (!graph_lock()) + return 0; + /* + * We have to walk the chain again locked - to avoid duplicates: + */ + list_for_each_entry(chain, hash_head, entry) { + if (chain->chain_key == chain_key) { + graph_unlock(); + goto cache_hit; + } + } + if (unlikely(nr_lock_chains >= MAX_LOCKDEP_CHAINS)) { + if (!debug_locks_off_graph_unlock()) + return 0; + + print_lockdep_off("BUG: MAX_LOCKDEP_CHAINS too low!"); + dump_stack(); + return 0; + } + chain = lock_chains + nr_lock_chains++; + chain->chain_key = chain_key; + chain->irq_context = hlock->irq_context; + /* Find the first held_lock of current chain */ + for (i = curr->lockdep_depth - 1; i >= 0; i--) { + hlock_curr = curr->held_locks + i; + if (hlock_curr->irq_context != hlock->irq_context) + break; + } + i++; + chain->depth = curr->lockdep_depth + 1 - i; + if (likely(nr_chain_hlocks + chain->depth <= MAX_LOCKDEP_CHAIN_HLOCKS)) { + chain->base = nr_chain_hlocks; + nr_chain_hlocks += chain->depth; + for (j = 0; j < chain->depth - 1; j++, i++) { + int lock_id = curr->held_locks[i].class_idx - 1; + chain_hlocks[chain->base + j] = lock_id; + } + chain_hlocks[chain->base + j] = class - lock_classes; + } + list_add_tail_rcu(&chain->entry, hash_head); + debug_atomic_inc(chain_lookup_misses); + inc_chains(); + + return 1; +} + +static int validate_chain(struct task_struct *curr, struct lockdep_map *lock, + struct held_lock *hlock, int chain_head, u64 chain_key) +{ + /* + * Trylock needs to maintain the stack of held locks, but it + * does not add new dependencies, because trylock can be done + * in any order. + * + * We look up the chain_key and do the O(N^2) check and update of + * the dependencies only if this is a new dependency chain. + * (If lookup_chain_cache() returns with 1 it acquires + * graph_lock for us) + */ + if (!hlock->trylock && hlock->check && + lookup_chain_cache(curr, hlock, chain_key)) { + /* + * Check whether last held lock: + * + * - is irq-safe, if this lock is irq-unsafe + * - is softirq-safe, if this lock is hardirq-unsafe + * + * And check whether the new lock's dependency graph + * could lead back to the previous lock. + * + * any of these scenarios could lead to a deadlock. If + * All validations + */ + int ret = check_deadlock(curr, hlock, lock, hlock->read); + + if (!ret) + return 0; + /* + * Mark recursive read, as we jump over it when + * building dependencies (just like we jump over + * trylock entries): + */ + if (ret == 2) + hlock->read = 2; + /* + * Add dependency only if this lock is not the head + * of the chain, and if it's not a secondary read-lock: + */ + if (!chain_head && ret != 2) + if (!check_prevs_add(curr, hlock)) + return 0; + graph_unlock(); + } else + /* after lookup_chain_cache(): */ + if (unlikely(!debug_locks)) + return 0; + + return 1; +} +#else +static inline int validate_chain(struct task_struct *curr, + struct lockdep_map *lock, struct held_lock *hlock, + int chain_head, u64 chain_key) +{ + return 1; +} +#endif + +/* + * We are building curr_chain_key incrementally, so double-check + * it from scratch, to make sure that it's done correctly: + */ +static void check_chain_key(struct task_struct *curr) +{ +#ifdef CONFIG_DEBUG_LOCKDEP + struct held_lock *hlock, *prev_hlock = NULL; + unsigned int i, id; + u64 chain_key = 0; + + for (i = 0; i < curr->lockdep_depth; i++) { + hlock = curr->held_locks + i; + if (chain_key != hlock->prev_chain_key) { + debug_locks_off(); + /* + * We got mighty confused, our chain keys don't match + * with what we expect, someone trample on our task state? + */ + WARN(1, "hm#1, depth: %u [%u], %016Lx != %016Lx\n", + curr->lockdep_depth, i, + (unsigned long long)chain_key, + (unsigned long long)hlock->prev_chain_key); + return; + } + id = hlock->class_idx - 1; + /* + * Whoops ran out of static storage again? + */ + if (DEBUG_LOCKS_WARN_ON(id >= MAX_LOCKDEP_KEYS)) + return; + + if (prev_hlock && (prev_hlock->irq_context != + hlock->irq_context)) + chain_key = 0; + chain_key = iterate_chain_key(chain_key, id); + prev_hlock = hlock; + } + if (chain_key != curr->curr_chain_key) { + debug_locks_off(); + /* + * More smoking hash instead of calculating it, damn see these + * numbers float.. I bet that a pink elephant stepped on my memory. + */ + WARN(1, "hm#2, depth: %u [%u], %016Lx != %016Lx\n", + curr->lockdep_depth, i, + (unsigned long long)chain_key, + (unsigned long long)curr->curr_chain_key); + } +#endif +} + +static void +print_usage_bug_scenario(struct held_lock *lock) +{ + struct lock_class *class = hlock_class(lock); + + printk(" Possible unsafe locking scenario:\n\n"); + printk(" CPU0\n"); + printk(" ----\n"); + printk(" lock("); + __print_lock_name(class); + printk(");\n"); + printk(" \n"); + printk(" lock("); + __print_lock_name(class); + printk(");\n"); + printk("\n *** DEADLOCK ***\n\n"); +} + +static int +print_usage_bug(struct task_struct *curr, struct held_lock *this, + enum lock_usage_bit prev_bit, enum lock_usage_bit new_bit) +{ + if (!debug_locks_off_graph_unlock() || debug_locks_silent) + return 0; + + printk("\n"); + printk("=================================\n"); + printk("[ INFO: inconsistent lock state ]\n"); + print_kernel_ident(); + printk("---------------------------------\n"); + + printk("inconsistent {%s} -> {%s} usage.\n", + usage_str[prev_bit], usage_str[new_bit]); + + printk("%s/%d [HC%u[%lu]:SC%u[%lu]:HE%u:SE%u] takes:\n", + curr->comm, task_pid_nr(curr), + trace_hardirq_context(curr), hardirq_count() >> HARDIRQ_SHIFT, + trace_softirq_context(curr), softirq_count() >> SOFTIRQ_SHIFT, + trace_hardirqs_enabled(curr), + trace_softirqs_enabled(curr)); + print_lock(this); + + printk("{%s} state was registered at:\n", usage_str[prev_bit]); + print_stack_trace(hlock_class(this)->usage_traces + prev_bit, 1); + + print_irqtrace_events(curr); + printk("\nother info that might help us debug this:\n"); + print_usage_bug_scenario(this); + + lockdep_print_held_locks(curr); + + printk("\nstack backtrace:\n"); + dump_stack(); + + return 0; +} + +/* + * Print out an error if an invalid bit is set: + */ +static inline int +valid_state(struct task_struct *curr, struct held_lock *this, + enum lock_usage_bit new_bit, enum lock_usage_bit bad_bit) +{ + if (unlikely(hlock_class(this)->usage_mask & (1 << bad_bit))) + return print_usage_bug(curr, this, bad_bit, new_bit); + return 1; +} + +static int mark_lock(struct task_struct *curr, struct held_lock *this, + enum lock_usage_bit new_bit); + +#if defined(CONFIG_TRACE_IRQFLAGS) && defined(CONFIG_PROVE_LOCKING) + +/* + * print irq inversion bug: + */ +static int +print_irq_inversion_bug(struct task_struct *curr, + struct lock_list *root, struct lock_list *other, + struct held_lock *this, int forwards, + const char *irqclass) +{ + struct lock_list *entry = other; + struct lock_list *middle = NULL; + int depth; + + if (!debug_locks_off_graph_unlock() || debug_locks_silent) + return 0; + + printk("\n"); + printk("=========================================================\n"); + printk("[ INFO: possible irq lock inversion dependency detected ]\n"); + print_kernel_ident(); + printk("---------------------------------------------------------\n"); + printk("%s/%d just changed the state of lock:\n", + curr->comm, task_pid_nr(curr)); + print_lock(this); + if (forwards) + printk("but this lock took another, %s-unsafe lock in the past:\n", irqclass); + else + printk("but this lock was taken by another, %s-safe lock in the past:\n", irqclass); + print_lock_name(other->class); + printk("\n\nand interrupts could create inverse lock ordering between them.\n\n"); + + printk("\nother info that might help us debug this:\n"); + + /* Find a middle lock (if one exists) */ + depth = get_lock_depth(other); + do { + if (depth == 0 && (entry != root)) { + printk("lockdep:%s bad path found in chain graph\n", __func__); + break; + } + middle = entry; + entry = get_lock_parent(entry); + depth--; + } while (entry && entry != root && (depth >= 0)); + if (forwards) + print_irq_lock_scenario(root, other, + middle ? middle->class : root->class, other->class); + else + print_irq_lock_scenario(other, root, + middle ? middle->class : other->class, root->class); + + lockdep_print_held_locks(curr); + + printk("\nthe shortest dependencies between 2nd lock and 1st lock:\n"); + if (!save_trace(&root->trace)) + return 0; + print_shortest_lock_dependencies(other, root); + + printk("\nstack backtrace:\n"); + dump_stack(); + + return 0; +} + +/* + * Prove that in the forwards-direction subgraph starting at + * there is no lock matching : + */ +static int +check_usage_forwards(struct task_struct *curr, struct held_lock *this, + enum lock_usage_bit bit, const char *irqclass) +{ + int ret; + struct lock_list root; + struct lock_list *uninitialized_var(target_entry); + + root.parent = NULL; + root.class = hlock_class(this); + ret = find_usage_forwards(&root, bit, &target_entry); + if (ret < 0) + return print_bfs_bug(ret); + if (ret == 1) + return ret; + + return print_irq_inversion_bug(curr, &root, target_entry, + this, 1, irqclass); +} + +/* + * Prove that in the backwards-direction subgraph starting at + * there is no lock matching : + */ +static int +check_usage_backwards(struct task_struct *curr, struct held_lock *this, + enum lock_usage_bit bit, const char *irqclass) +{ + int ret; + struct lock_list root; + struct lock_list *uninitialized_var(target_entry); + + root.parent = NULL; + root.class = hlock_class(this); + ret = find_usage_backwards(&root, bit, &target_entry); + if (ret < 0) + return print_bfs_bug(ret); + if (ret == 1) + return ret; + + return print_irq_inversion_bug(curr, &root, target_entry, + this, 0, irqclass); +} + +void print_irqtrace_events(struct task_struct *curr) +{ + printk("irq event stamp: %u\n", curr->irq_events); + printk("hardirqs last enabled at (%u): ", curr->hardirq_enable_event); + print_ip_sym(curr->hardirq_enable_ip); + printk("hardirqs last disabled at (%u): ", curr->hardirq_disable_event); + print_ip_sym(curr->hardirq_disable_ip); + printk("softirqs last enabled at (%u): ", curr->softirq_enable_event); + print_ip_sym(curr->softirq_enable_ip); + printk("softirqs last disabled at (%u): ", curr->softirq_disable_event); + print_ip_sym(curr->softirq_disable_ip); +} + +static int HARDIRQ_verbose(struct lock_class *class) +{ +#if HARDIRQ_VERBOSE + return class_filter(class); +#endif + return 0; +} + +static int SOFTIRQ_verbose(struct lock_class *class) +{ +#if SOFTIRQ_VERBOSE + return class_filter(class); +#endif + return 0; +} + +static int RECLAIM_FS_verbose(struct lock_class *class) +{ +#if RECLAIM_VERBOSE + return class_filter(class); +#endif + return 0; +} + +#define STRICT_READ_CHECKS 1 + +static int (*state_verbose_f[])(struct lock_class *class) = { +#define LOCKDEP_STATE(__STATE) \ + __STATE##_verbose, +#include "lockdep_states.h" +#undef LOCKDEP_STATE +}; + +static inline int state_verbose(enum lock_usage_bit bit, + struct lock_class *class) +{ + return state_verbose_f[bit >> 2](class); +} + +typedef int (*check_usage_f)(struct task_struct *, struct held_lock *, + enum lock_usage_bit bit, const char *name); + +static int +mark_lock_irq(struct task_struct *curr, struct held_lock *this, + enum lock_usage_bit new_bit) +{ + int excl_bit = exclusive_bit(new_bit); + int read = new_bit & 1; + int dir = new_bit & 2; + + /* + * mark USED_IN has to look forwards -- to ensure no dependency + * has ENABLED state, which would allow recursion deadlocks. + * + * mark ENABLED has to look backwards -- to ensure no dependee + * has USED_IN state, which, again, would allow recursion deadlocks. + */ + check_usage_f usage = dir ? + check_usage_backwards : check_usage_forwards; + + /* + * Validate that this particular lock does not have conflicting + * usage states. + */ + if (!valid_state(curr, this, new_bit, excl_bit)) + return 0; + + /* + * Validate that the lock dependencies don't have conflicting usage + * states. + */ + if ((!read || !dir || STRICT_READ_CHECKS) && + !usage(curr, this, excl_bit, state_name(new_bit & ~1))) + return 0; + + /* + * Check for read in write conflicts + */ + if (!read) { + if (!valid_state(curr, this, new_bit, excl_bit + 1)) + return 0; + + if (STRICT_READ_CHECKS && + !usage(curr, this, excl_bit + 1, + state_name(new_bit + 1))) + return 0; + } + + if (state_verbose(new_bit, hlock_class(this))) + return 2; + + return 1; +} + +enum mark_type { +#define LOCKDEP_STATE(__STATE) __STATE, +#include "lockdep_states.h" +#undef LOCKDEP_STATE +}; + +/* + * Mark all held locks with a usage bit: + */ +static int +mark_held_locks(struct task_struct *curr, enum mark_type mark) +{ + enum lock_usage_bit usage_bit; + struct held_lock *hlock; + int i; + + for (i = 0; i < curr->lockdep_depth; i++) { + hlock = curr->held_locks + i; + + usage_bit = 2 + (mark << 2); /* ENABLED */ + if (hlock->read) + usage_bit += 1; /* READ */ + + BUG_ON(usage_bit >= LOCK_USAGE_STATES); + + if (!hlock->check) + continue; + + if (!mark_lock(curr, hlock, usage_bit)) + return 0; + } + + return 1; +} + +/* + * Hardirqs will be enabled: + */ +static void __trace_hardirqs_on_caller(unsigned long ip) +{ + struct task_struct *curr = current; + + /* we'll do an OFF -> ON transition: */ + curr->hardirqs_enabled = 1; + + /* + * We are going to turn hardirqs on, so set the + * usage bit for all held locks: + */ + if (!mark_held_locks(curr, HARDIRQ)) + return; + /* + * If we have softirqs enabled, then set the usage + * bit for all held locks. (disabled hardirqs prevented + * this bit from being set before) + */ + if (curr->softirqs_enabled) + if (!mark_held_locks(curr, SOFTIRQ)) + return; + + curr->hardirq_enable_ip = ip; + curr->hardirq_enable_event = ++curr->irq_events; + debug_atomic_inc(hardirqs_on_events); +} + +__visible void trace_hardirqs_on_caller(unsigned long ip) +{ + time_hardirqs_on(CALLER_ADDR0, ip); + + if (unlikely(!debug_locks || current->lockdep_recursion)) + return; + + if (unlikely(current->hardirqs_enabled)) { + /* + * Neither irq nor preemption are disabled here + * so this is racy by nature but losing one hit + * in a stat is not a big deal. + */ + __debug_atomic_inc(redundant_hardirqs_on); + return; + } + + /* + * We're enabling irqs and according to our state above irqs weren't + * already enabled, yet we find the hardware thinks they are in fact + * enabled.. someone messed up their IRQ state tracing. + */ + if (DEBUG_LOCKS_WARN_ON(!irqs_disabled())) + return; + + /* + * See the fine text that goes along with this variable definition. + */ + if (DEBUG_LOCKS_WARN_ON(unlikely(early_boot_irqs_disabled))) + return; + + /* + * Can't allow enabling interrupts while in an interrupt handler, + * that's general bad form and such. Recursion, limited stack etc.. + */ + if (DEBUG_LOCKS_WARN_ON(current->hardirq_context)) + return; + + current->lockdep_recursion = 1; + __trace_hardirqs_on_caller(ip); + current->lockdep_recursion = 0; +} +EXPORT_SYMBOL(trace_hardirqs_on_caller); + +void trace_hardirqs_on(void) +{ + trace_hardirqs_on_caller(CALLER_ADDR0); +} +EXPORT_SYMBOL(trace_hardirqs_on); + +/* + * Hardirqs were disabled: + */ +__visible void trace_hardirqs_off_caller(unsigned long ip) +{ + struct task_struct *curr = current; + + time_hardirqs_off(CALLER_ADDR0, ip); + + if (unlikely(!debug_locks || current->lockdep_recursion)) + return; + + /* + * So we're supposed to get called after you mask local IRQs, but for + * some reason the hardware doesn't quite think you did a proper job. + */ + if (DEBUG_LOCKS_WARN_ON(!irqs_disabled())) + return; + + if (curr->hardirqs_enabled) { + /* + * We have done an ON -> OFF transition: + */ + curr->hardirqs_enabled = 0; + curr->hardirq_disable_ip = ip; + curr->hardirq_disable_event = ++curr->irq_events; + debug_atomic_inc(hardirqs_off_events); + } else + debug_atomic_inc(redundant_hardirqs_off); +} +EXPORT_SYMBOL(trace_hardirqs_off_caller); + +void trace_hardirqs_off(void) +{ + trace_hardirqs_off_caller(CALLER_ADDR0); +} +EXPORT_SYMBOL(trace_hardirqs_off); + +/* + * Softirqs will be enabled: + */ +void trace_softirqs_on(unsigned long ip) +{ + struct task_struct *curr = current; + + if (unlikely(!debug_locks || current->lockdep_recursion)) + return; + + /* + * We fancy IRQs being disabled here, see softirq.c, avoids + * funny state and nesting things. + */ + if (DEBUG_LOCKS_WARN_ON(!irqs_disabled())) + return; + + if (curr->softirqs_enabled) { + debug_atomic_inc(redundant_softirqs_on); + return; + } + + current->lockdep_recursion = 1; + /* + * We'll do an OFF -> ON transition: + */ + curr->softirqs_enabled = 1; + curr->softirq_enable_ip = ip; + curr->softirq_enable_event = ++curr->irq_events; + debug_atomic_inc(softirqs_on_events); + /* + * We are going to turn softirqs on, so set the + * usage bit for all held locks, if hardirqs are + * enabled too: + */ + if (curr->hardirqs_enabled) + mark_held_locks(curr, SOFTIRQ); + current->lockdep_recursion = 0; +} + +/* + * Softirqs were disabled: + */ +void trace_softirqs_off(unsigned long ip) +{ + struct task_struct *curr = current; + + if (unlikely(!debug_locks || current->lockdep_recursion)) + return; + + /* + * We fancy IRQs being disabled here, see softirq.c + */ + if (DEBUG_LOCKS_WARN_ON(!irqs_disabled())) + return; + + if (curr->softirqs_enabled) { + /* + * We have done an ON -> OFF transition: + */ + curr->softirqs_enabled = 0; + curr->softirq_disable_ip = ip; + curr->softirq_disable_event = ++curr->irq_events; + debug_atomic_inc(softirqs_off_events); + /* + * Whoops, we wanted softirqs off, so why aren't they? + */ + DEBUG_LOCKS_WARN_ON(!softirq_count()); + } else + debug_atomic_inc(redundant_softirqs_off); +} + +static void __lockdep_trace_alloc(gfp_t gfp_mask, unsigned long flags) +{ + struct task_struct *curr = current; + + if (unlikely(!debug_locks)) + return; + + /* no reclaim without waiting on it */ + if (!(gfp_mask & __GFP_WAIT)) + return; + + /* this guy won't enter reclaim */ + if ((curr->flags & PF_MEMALLOC) && !(gfp_mask & __GFP_NOMEMALLOC)) + return; + + /* We're only interested __GFP_FS allocations for now */ + if (!(gfp_mask & __GFP_FS)) + return; + + /* + * Oi! Can't be having __GFP_FS allocations with IRQs disabled. + */ + if (DEBUG_LOCKS_WARN_ON(irqs_disabled_flags(flags))) + return; + + mark_held_locks(curr, RECLAIM_FS); +} + +static void check_flags(unsigned long flags); + +void lockdep_trace_alloc(gfp_t gfp_mask) +{ + unsigned long flags; + + if (unlikely(current->lockdep_recursion)) + return; + + raw_local_irq_save(flags); + check_flags(flags); + current->lockdep_recursion = 1; + __lockdep_trace_alloc(gfp_mask, flags); + current->lockdep_recursion = 0; + raw_local_irq_restore(flags); +} + +static int mark_irqflags(struct task_struct *curr, struct held_lock *hlock) +{ + /* + * If non-trylock use in a hardirq or softirq context, then + * mark the lock as used in these contexts: + */ + if (!hlock->trylock) { + if (hlock->read) { + if (curr->hardirq_context) + if (!mark_lock(curr, hlock, + LOCK_USED_IN_HARDIRQ_READ)) + return 0; + if (curr->softirq_context) + if (!mark_lock(curr, hlock, + LOCK_USED_IN_SOFTIRQ_READ)) + return 0; + } else { + if (curr->hardirq_context) + if (!mark_lock(curr, hlock, LOCK_USED_IN_HARDIRQ)) + return 0; + if (curr->softirq_context) + if (!mark_lock(curr, hlock, LOCK_USED_IN_SOFTIRQ)) + return 0; + } + } + if (!hlock->hardirqs_off) { + if (hlock->read) { + if (!mark_lock(curr, hlock, + LOCK_ENABLED_HARDIRQ_READ)) + return 0; + if (curr->softirqs_enabled) + if (!mark_lock(curr, hlock, + LOCK_ENABLED_SOFTIRQ_READ)) + return 0; + } else { + if (!mark_lock(curr, hlock, + LOCK_ENABLED_HARDIRQ)) + return 0; + if (curr->softirqs_enabled) + if (!mark_lock(curr, hlock, + LOCK_ENABLED_SOFTIRQ)) + return 0; + } + } + + /* + * We reuse the irq context infrastructure more broadly as a general + * context checking code. This tests GFP_FS recursion (a lock taken + * during reclaim for a GFP_FS allocation is held over a GFP_FS + * allocation). + */ + if (!hlock->trylock && (curr->lockdep_reclaim_gfp & __GFP_FS)) { + if (hlock->read) { + if (!mark_lock(curr, hlock, LOCK_USED_IN_RECLAIM_FS_READ)) + return 0; + } else { + if (!mark_lock(curr, hlock, LOCK_USED_IN_RECLAIM_FS)) + return 0; + } + } + + return 1; +} + +static int separate_irq_context(struct task_struct *curr, + struct held_lock *hlock) +{ + unsigned int depth = curr->lockdep_depth; + + /* + * Keep track of points where we cross into an interrupt context: + */ + hlock->irq_context = 2*(curr->hardirq_context ? 1 : 0) + + curr->softirq_context; + if (depth) { + struct held_lock *prev_hlock; + + prev_hlock = curr->held_locks + depth-1; + /* + * If we cross into another context, reset the + * hash key (this also prevents the checking and the + * adding of the dependency to 'prev'): + */ + if (prev_hlock->irq_context != hlock->irq_context) + return 1; + } + return 0; +} + +#else /* defined(CONFIG_TRACE_IRQFLAGS) && defined(CONFIG_PROVE_LOCKING) */ + +static inline +int mark_lock_irq(struct task_struct *curr, struct held_lock *this, + enum lock_usage_bit new_bit) +{ + WARN_ON(1); /* Impossible innit? when we don't have TRACE_IRQFLAG */ + return 1; +} + +static inline int mark_irqflags(struct task_struct *curr, + struct held_lock *hlock) +{ + return 1; +} + +static inline int separate_irq_context(struct task_struct *curr, + struct held_lock *hlock) +{ + return 0; +} + +void lockdep_trace_alloc(gfp_t gfp_mask) +{ +} + +#endif /* defined(CONFIG_TRACE_IRQFLAGS) && defined(CONFIG_PROVE_LOCKING) */ + +/* + * Mark a lock with a usage bit, and validate the state transition: + */ +static int mark_lock(struct task_struct *curr, struct held_lock *this, + enum lock_usage_bit new_bit) +{ + unsigned int new_mask = 1 << new_bit, ret = 1; + + /* + * If already set then do not dirty the cacheline, + * nor do any checks: + */ + if (likely(hlock_class(this)->usage_mask & new_mask)) + return 1; + + if (!graph_lock()) + return 0; + /* + * Make sure we didn't race: + */ + if (unlikely(hlock_class(this)->usage_mask & new_mask)) { + graph_unlock(); + return 1; + } + + hlock_class(this)->usage_mask |= new_mask; + + if (!save_trace(hlock_class(this)->usage_traces + new_bit)) + return 0; + + switch (new_bit) { +#define LOCKDEP_STATE(__STATE) \ + case LOCK_USED_IN_##__STATE: \ + case LOCK_USED_IN_##__STATE##_READ: \ + case LOCK_ENABLED_##__STATE: \ + case LOCK_ENABLED_##__STATE##_READ: +#include "lockdep_states.h" +#undef LOCKDEP_STATE + ret = mark_lock_irq(curr, this, new_bit); + if (!ret) + return 0; + break; + case LOCK_USED: + debug_atomic_dec(nr_unused_locks); + break; + default: + if (!debug_locks_off_graph_unlock()) + return 0; + WARN_ON(1); + return 0; + } + + graph_unlock(); + + /* + * We must printk outside of the graph_lock: + */ + if (ret == 2) { + printk("\nmarked lock as {%s}:\n", usage_str[new_bit]); + print_lock(this); + print_irqtrace_events(curr); + dump_stack(); + } + + return ret; +} + +/* + * Initialize a lock instance's lock-class mapping info: + */ +void lockdep_init_map(struct lockdep_map *lock, const char *name, + struct lock_class_key *key, int subclass) +{ + int i; + + kmemcheck_mark_initialized(lock, sizeof(*lock)); + + for (i = 0; i < NR_LOCKDEP_CACHING_CLASSES; i++) + lock->class_cache[i] = NULL; + +#ifdef CONFIG_LOCK_STAT + lock->cpu = raw_smp_processor_id(); +#endif + + /* + * Can't be having no nameless bastards around this place! + */ + if (DEBUG_LOCKS_WARN_ON(!name)) { + lock->name = "NULL"; + return; + } + + lock->name = name; + + /* + * No key, no joy, we need to hash something. + */ + if (DEBUG_LOCKS_WARN_ON(!key)) + return; + /* + * Sanity check, the lock-class key must be persistent: + */ + if (!static_obj(key)) { + printk("BUG: key %p not in .data!\n", key); + /* + * What it says above ^^^^^, I suggest you read it. + */ + DEBUG_LOCKS_WARN_ON(1); + return; + } + lock->key = key; + + if (unlikely(!debug_locks)) + return; + + if (subclass) { + unsigned long flags; + + if (DEBUG_LOCKS_WARN_ON(current->lockdep_recursion)) + return; + + raw_local_irq_save(flags); + current->lockdep_recursion = 1; + register_lock_class(lock, subclass, 1); + current->lockdep_recursion = 0; + raw_local_irq_restore(flags); + } +} +EXPORT_SYMBOL_GPL(lockdep_init_map); + +struct lock_class_key __lockdep_no_validate__; +EXPORT_SYMBOL_GPL(__lockdep_no_validate__); + +static int +print_lock_nested_lock_not_held(struct task_struct *curr, + struct held_lock *hlock, + unsigned long ip) +{ + if (!debug_locks_off()) + return 0; + if (debug_locks_silent) + return 0; + + printk("\n"); + printk("==================================\n"); + printk("[ BUG: Nested lock was not taken ]\n"); + print_kernel_ident(); + printk("----------------------------------\n"); + + printk("%s/%d is trying to lock:\n", curr->comm, task_pid_nr(curr)); + print_lock(hlock); + + printk("\nbut this task is not holding:\n"); + printk("%s\n", hlock->nest_lock->name); + + printk("\nstack backtrace:\n"); + dump_stack(); + + printk("\nother info that might help us debug this:\n"); + lockdep_print_held_locks(curr); + + printk("\nstack backtrace:\n"); + dump_stack(); + + return 0; +} + +static int __lock_is_held(struct lockdep_map *lock); + +/* + * This gets called for every mutex_lock*()/spin_lock*() operation. + * We maintain the dependency maps and validate the locking attempt: + */ +static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass, + int trylock, int read, int check, int hardirqs_off, + struct lockdep_map *nest_lock, unsigned long ip, + int references) +{ + struct task_struct *curr = current; + struct lock_class *class = NULL; + struct held_lock *hlock; + unsigned int depth, id; + int chain_head = 0; + int class_idx; + u64 chain_key; + + if (unlikely(!debug_locks)) + return 0; + + /* + * Lockdep should run with IRQs disabled, otherwise we could + * get an interrupt which would want to take locks, which would + * end up in lockdep and have you got a head-ache already? + */ + if (DEBUG_LOCKS_WARN_ON(!irqs_disabled())) + return 0; + + if (!prove_locking || lock->key == &__lockdep_no_validate__) + check = 0; + + if (subclass < NR_LOCKDEP_CACHING_CLASSES) + class = lock->class_cache[subclass]; + /* + * Not cached? + */ + if (unlikely(!class)) { + class = register_lock_class(lock, subclass, 0); + if (!class) + return 0; + } + atomic_inc((atomic_t *)&class->ops); + if (very_verbose(class)) { + printk("\nacquire class [%p] %s", class->key, class->name); + if (class->name_version > 1) + printk("#%d", class->name_version); + printk("\n"); + dump_stack(); + } + + /* + * Add the lock to the list of currently held locks. + * (we dont increase the depth just yet, up until the + * dependency checks are done) + */ + depth = curr->lockdep_depth; + /* + * Ran out of static storage for our per-task lock stack again have we? + */ + if (DEBUG_LOCKS_WARN_ON(depth >= MAX_LOCK_DEPTH)) + return 0; + + class_idx = class - lock_classes + 1; + + if (depth) { + hlock = curr->held_locks + depth - 1; + if (hlock->class_idx == class_idx && nest_lock) { + if (hlock->references) + hlock->references++; + else + hlock->references = 2; + + return 1; + } + } + + hlock = curr->held_locks + depth; + /* + * Plain impossible, we just registered it and checked it weren't no + * NULL like.. I bet this mushroom I ate was good! + */ + if (DEBUG_LOCKS_WARN_ON(!class)) + return 0; + hlock->class_idx = class_idx; + hlock->acquire_ip = ip; + hlock->instance = lock; + hlock->nest_lock = nest_lock; + hlock->trylock = trylock; + hlock->read = read; + hlock->check = check; + hlock->hardirqs_off = !!hardirqs_off; + hlock->references = references; +#ifdef CONFIG_LOCK_STAT + hlock->waittime_stamp = 0; + hlock->holdtime_stamp = lockstat_clock(); +#endif + + if (check && !mark_irqflags(curr, hlock)) + return 0; + + /* mark it as used: */ + if (!mark_lock(curr, hlock, LOCK_USED)) + return 0; + + /* + * Calculate the chain hash: it's the combined hash of all the + * lock keys along the dependency chain. We save the hash value + * at every step so that we can get the current hash easily + * after unlock. The chain hash is then used to cache dependency + * results. + * + * The 'key ID' is what is the most compact key value to drive + * the hash, not class->key. + */ + id = class - lock_classes; + /* + * Whoops, we did it again.. ran straight out of our static allocation. + */ + if (DEBUG_LOCKS_WARN_ON(id >= MAX_LOCKDEP_KEYS)) + return 0; + + chain_key = curr->curr_chain_key; + if (!depth) { + /* + * How can we have a chain hash when we ain't got no keys?! + */ + if (DEBUG_LOCKS_WARN_ON(chain_key != 0)) + return 0; + chain_head = 1; + } + + hlock->prev_chain_key = chain_key; + if (separate_irq_context(curr, hlock)) { + chain_key = 0; + chain_head = 1; + } + chain_key = iterate_chain_key(chain_key, id); + + if (nest_lock && !__lock_is_held(nest_lock)) + return print_lock_nested_lock_not_held(curr, hlock, ip); + + if (!validate_chain(curr, lock, hlock, chain_head, chain_key)) + return 0; + + curr->curr_chain_key = chain_key; + curr->lockdep_depth++; + check_chain_key(curr); +#ifdef CONFIG_DEBUG_LOCKDEP + if (unlikely(!debug_locks)) + return 0; +#endif + if (unlikely(curr->lockdep_depth >= MAX_LOCK_DEPTH)) { + debug_locks_off(); + print_lockdep_off("BUG: MAX_LOCK_DEPTH too low!"); + printk(KERN_DEBUG "depth: %i max: %lu!\n", + curr->lockdep_depth, MAX_LOCK_DEPTH); + + lockdep_print_held_locks(current); + debug_show_all_locks(); + dump_stack(); + + return 0; + } + + if (unlikely(curr->lockdep_depth > max_lockdep_depth)) + max_lockdep_depth = curr->lockdep_depth; + + return 1; +} + +static int +print_unlock_imbalance_bug(struct task_struct *curr, struct lockdep_map *lock, + unsigned long ip) +{ + if (!debug_locks_off()) + return 0; + if (debug_locks_silent) + return 0; + + printk("\n"); + printk("=====================================\n"); + printk("[ BUG: bad unlock balance detected! ]\n"); + print_kernel_ident(); + printk("-------------------------------------\n"); + printk("%s/%d is trying to release lock (", + curr->comm, task_pid_nr(curr)); + print_lockdep_cache(lock); + printk(") at:\n"); + print_ip_sym(ip); + printk("but there are no more locks to release!\n"); + printk("\nother info that might help us debug this:\n"); + lockdep_print_held_locks(curr); + + printk("\nstack backtrace:\n"); + dump_stack(); + + return 0; +} + +/* + * Common debugging checks for both nested and non-nested unlock: + */ +static int check_unlock(struct task_struct *curr, struct lockdep_map *lock, + unsigned long ip) +{ + if (unlikely(!debug_locks)) + return 0; + /* + * Lockdep should run with IRQs disabled, recursion, head-ache, etc.. + */ + if (DEBUG_LOCKS_WARN_ON(!irqs_disabled())) + return 0; + + if (curr->lockdep_depth <= 0) + return print_unlock_imbalance_bug(curr, lock, ip); + + return 1; +} + +static int match_held_lock(struct held_lock *hlock, struct lockdep_map *lock) +{ + if (hlock->instance == lock) + return 1; + + if (hlock->references) { + struct lock_class *class = lock->class_cache[0]; + + if (!class) + class = look_up_lock_class(lock, 0); + + /* + * If look_up_lock_class() failed to find a class, we're trying + * to test if we hold a lock that has never yet been acquired. + * Clearly if the lock hasn't been acquired _ever_, we're not + * holding it either, so report failure. + */ + if (!class) + return 0; + + /* + * References, but not a lock we're actually ref-counting? + * State got messed up, follow the sites that change ->references + * and try to make sense of it. + */ + if (DEBUG_LOCKS_WARN_ON(!hlock->nest_lock)) + return 0; + + if (hlock->class_idx == class - lock_classes + 1) + return 1; + } + + return 0; +} + +static int +__lock_set_class(struct lockdep_map *lock, const char *name, + struct lock_class_key *key, unsigned int subclass, + unsigned long ip) +{ + struct task_struct *curr = current; + struct held_lock *hlock, *prev_hlock; + struct lock_class *class; + unsigned int depth; + int i; + + depth = curr->lockdep_depth; + /* + * This function is about (re)setting the class of a held lock, + * yet we're not actually holding any locks. Naughty user! + */ + if (DEBUG_LOCKS_WARN_ON(!depth)) + return 0; + + prev_hlock = NULL; + for (i = depth-1; i >= 0; i--) { + hlock = curr->held_locks + i; + /* + * We must not cross into another context: + */ + if (prev_hlock && prev_hlock->irq_context != hlock->irq_context) + break; + if (match_held_lock(hlock, lock)) + goto found_it; + prev_hlock = hlock; + } + return print_unlock_imbalance_bug(curr, lock, ip); + +found_it: + lockdep_init_map(lock, name, key, 0); + class = register_lock_class(lock, subclass, 0); + hlock->class_idx = class - lock_classes + 1; + + curr->lockdep_depth = i; + curr->curr_chain_key = hlock->prev_chain_key; + + for (; i < depth; i++) { + hlock = curr->held_locks + i; + if (!__lock_acquire(hlock->instance, + hlock_class(hlock)->subclass, hlock->trylock, + hlock->read, hlock->check, hlock->hardirqs_off, + hlock->nest_lock, hlock->acquire_ip, + hlock->references)) + return 0; + } + + /* + * I took it apart and put it back together again, except now I have + * these 'spare' parts.. where shall I put them. + */ + if (DEBUG_LOCKS_WARN_ON(curr->lockdep_depth != depth)) + return 0; + return 1; +} + +/* + * Remove the lock to the list of currently held locks in a + * potentially non-nested (out of order) manner. This is a + * relatively rare operation, as all the unlock APIs default + * to nested mode (which uses lock_release()): + */ +static int +lock_release_non_nested(struct task_struct *curr, + struct lockdep_map *lock, unsigned long ip) +{ + struct held_lock *hlock, *prev_hlock; + unsigned int depth; + int i; + + /* + * Check whether the lock exists in the current stack + * of held locks: + */ + depth = curr->lockdep_depth; + /* + * So we're all set to release this lock.. wait what lock? We don't + * own any locks, you've been drinking again? + */ + if (DEBUG_LOCKS_WARN_ON(!depth)) + return 0; + + prev_hlock = NULL; + for (i = depth-1; i >= 0; i--) { + hlock = curr->held_locks + i; + /* + * We must not cross into another context: + */ + if (prev_hlock && prev_hlock->irq_context != hlock->irq_context) + break; + if (match_held_lock(hlock, lock)) + goto found_it; + prev_hlock = hlock; + } + return print_unlock_imbalance_bug(curr, lock, ip); + +found_it: + if (hlock->instance == lock) + lock_release_holdtime(hlock); + + if (hlock->references) { + hlock->references--; + if (hlock->references) { + /* + * We had, and after removing one, still have + * references, the current lock stack is still + * valid. We're done! + */ + return 1; + } + } + + /* + * We have the right lock to unlock, 'hlock' points to it. + * Now we remove it from the stack, and add back the other + * entries (if any), recalculating the hash along the way: + */ + + curr->lockdep_depth = i; + curr->curr_chain_key = hlock->prev_chain_key; + + for (i++; i < depth; i++) { + hlock = curr->held_locks + i; + if (!__lock_acquire(hlock->instance, + hlock_class(hlock)->subclass, hlock->trylock, + hlock->read, hlock->check, hlock->hardirqs_off, + hlock->nest_lock, hlock->acquire_ip, + hlock->references)) + return 0; + } + + /* + * We had N bottles of beer on the wall, we drank one, but now + * there's not N-1 bottles of beer left on the wall... + */ + if (DEBUG_LOCKS_WARN_ON(curr->lockdep_depth != depth - 1)) + return 0; + return 1; +} + +/* + * Remove the lock to the list of currently held locks - this gets + * called on mutex_unlock()/spin_unlock*() (or on a failed + * mutex_lock_interruptible()). This is done for unlocks that nest + * perfectly. (i.e. the current top of the lock-stack is unlocked) + */ +static int lock_release_nested(struct task_struct *curr, + struct lockdep_map *lock, unsigned long ip) +{ + struct held_lock *hlock; + unsigned int depth; + + /* + * Pop off the top of the lock stack: + */ + depth = curr->lockdep_depth - 1; + hlock = curr->held_locks + depth; + + /* + * Is the unlock non-nested: + */ + if (hlock->instance != lock || hlock->references) + return lock_release_non_nested(curr, lock, ip); + curr->lockdep_depth--; + + /* + * No more locks, but somehow we've got hash left over, who left it? + */ + if (DEBUG_LOCKS_WARN_ON(!depth && (hlock->prev_chain_key != 0))) + return 0; + + curr->curr_chain_key = hlock->prev_chain_key; + + lock_release_holdtime(hlock); + +#ifdef CONFIG_DEBUG_LOCKDEP + hlock->prev_chain_key = 0; + hlock->class_idx = 0; + hlock->acquire_ip = 0; + hlock->irq_context = 0; +#endif + return 1; +} + +/* + * Remove the lock to the list of currently held locks - this gets + * called on mutex_unlock()/spin_unlock*() (or on a failed + * mutex_lock_interruptible()). This is done for unlocks that nest + * perfectly. (i.e. the current top of the lock-stack is unlocked) + */ +static void +__lock_release(struct lockdep_map *lock, int nested, unsigned long ip) +{ + struct task_struct *curr = current; + + if (!check_unlock(curr, lock, ip)) + return; + + if (nested) { + if (!lock_release_nested(curr, lock, ip)) + return; + } else { + if (!lock_release_non_nested(curr, lock, ip)) + return; + } + + check_chain_key(curr); +} + +static int __lock_is_held(struct lockdep_map *lock) +{ + struct task_struct *curr = current; + int i; + + for (i = 0; i < curr->lockdep_depth; i++) { + struct held_lock *hlock = curr->held_locks + i; + + if (match_held_lock(hlock, lock)) + return 1; + } + + return 0; +} + +/* + * Check whether we follow the irq-flags state precisely: + */ +static void check_flags(unsigned long flags) +{ +#if defined(CONFIG_PROVE_LOCKING) && defined(CONFIG_DEBUG_LOCKDEP) && \ + defined(CONFIG_TRACE_IRQFLAGS) + if (!debug_locks) + return; + + if (irqs_disabled_flags(flags)) { + if (DEBUG_LOCKS_WARN_ON(current->hardirqs_enabled)) { + printk("possible reason: unannotated irqs-off.\n"); + } + } else { + if (DEBUG_LOCKS_WARN_ON(!current->hardirqs_enabled)) { + printk("possible reason: unannotated irqs-on.\n"); + } + } + +#ifndef CONFIG_PREEMPT_RT_FULL + /* + * We dont accurately track softirq state in e.g. + * hardirq contexts (such as on 4KSTACKS), so only + * check if not in hardirq contexts: + */ + if (!hardirq_count()) { + if (softirq_count()) { + /* like the above, but with softirqs */ + DEBUG_LOCKS_WARN_ON(current->softirqs_enabled); + } else { + /* lick the above, does it taste good? */ + DEBUG_LOCKS_WARN_ON(!current->softirqs_enabled); + } + } +#endif + + if (!debug_locks) + print_irqtrace_events(current); +#endif +} + +void lock_set_class(struct lockdep_map *lock, const char *name, + struct lock_class_key *key, unsigned int subclass, + unsigned long ip) +{ + unsigned long flags; + + if (unlikely(current->lockdep_recursion)) + return; + + raw_local_irq_save(flags); + current->lockdep_recursion = 1; + check_flags(flags); + if (__lock_set_class(lock, name, key, subclass, ip)) + check_chain_key(current); + current->lockdep_recursion = 0; + raw_local_irq_restore(flags); +} +EXPORT_SYMBOL_GPL(lock_set_class); + +/* + * We are not always called with irqs disabled - do that here, + * and also avoid lockdep recursion: + */ +void lock_acquire(struct lockdep_map *lock, unsigned int subclass, + int trylock, int read, int check, + struct lockdep_map *nest_lock, unsigned long ip) +{ + unsigned long flags; + + if (unlikely(current->lockdep_recursion)) + return; + + raw_local_irq_save(flags); + check_flags(flags); + + current->lockdep_recursion = 1; + trace_lock_acquire(lock, subclass, trylock, read, check, nest_lock, ip); + __lock_acquire(lock, subclass, trylock, read, check, + irqs_disabled_flags(flags), nest_lock, ip, 0); + current->lockdep_recursion = 0; + raw_local_irq_restore(flags); +} +EXPORT_SYMBOL_GPL(lock_acquire); + +void lock_release(struct lockdep_map *lock, int nested, + unsigned long ip) +{ + unsigned long flags; + + if (unlikely(current->lockdep_recursion)) + return; + + raw_local_irq_save(flags); + check_flags(flags); + current->lockdep_recursion = 1; + trace_lock_release(lock, ip); + __lock_release(lock, nested, ip); + current->lockdep_recursion = 0; + raw_local_irq_restore(flags); +} +EXPORT_SYMBOL_GPL(lock_release); + +int lock_is_held(struct lockdep_map *lock) +{ + unsigned long flags; + int ret = 0; + + if (unlikely(current->lockdep_recursion)) + return 1; /* avoid false negative lockdep_assert_held() */ + + raw_local_irq_save(flags); + check_flags(flags); + + current->lockdep_recursion = 1; + ret = __lock_is_held(lock); + current->lockdep_recursion = 0; + raw_local_irq_restore(flags); + + return ret; +} +EXPORT_SYMBOL_GPL(lock_is_held); + +void lockdep_set_current_reclaim_state(gfp_t gfp_mask) +{ + current->lockdep_reclaim_gfp = gfp_mask; +} + +void lockdep_clear_current_reclaim_state(void) +{ + current->lockdep_reclaim_gfp = 0; +} + +#ifdef CONFIG_LOCK_STAT +static int +print_lock_contention_bug(struct task_struct *curr, struct lockdep_map *lock, + unsigned long ip) +{ + if (!debug_locks_off()) + return 0; + if (debug_locks_silent) + return 0; + + printk("\n"); + printk("=================================\n"); + printk("[ BUG: bad contention detected! ]\n"); + print_kernel_ident(); + printk("---------------------------------\n"); + printk("%s/%d is trying to contend lock (", + curr->comm, task_pid_nr(curr)); + print_lockdep_cache(lock); + printk(") at:\n"); + print_ip_sym(ip); + printk("but there are no locks held!\n"); + printk("\nother info that might help us debug this:\n"); + lockdep_print_held_locks(curr); + + printk("\nstack backtrace:\n"); + dump_stack(); + + return 0; +} + +static void +__lock_contended(struct lockdep_map *lock, unsigned long ip) +{ + struct task_struct *curr = current; + struct held_lock *hlock, *prev_hlock; + struct lock_class_stats *stats; + unsigned int depth; + int i, contention_point, contending_point; + + depth = curr->lockdep_depth; + /* + * Whee, we contended on this lock, except it seems we're not + * actually trying to acquire anything much at all.. + */ + if (DEBUG_LOCKS_WARN_ON(!depth)) + return; + + prev_hlock = NULL; + for (i = depth-1; i >= 0; i--) { + hlock = curr->held_locks + i; + /* + * We must not cross into another context: + */ + if (prev_hlock && prev_hlock->irq_context != hlock->irq_context) + break; + if (match_held_lock(hlock, lock)) + goto found_it; + prev_hlock = hlock; + } + print_lock_contention_bug(curr, lock, ip); + return; + +found_it: + if (hlock->instance != lock) + return; + + hlock->waittime_stamp = lockstat_clock(); + + contention_point = lock_point(hlock_class(hlock)->contention_point, ip); + contending_point = lock_point(hlock_class(hlock)->contending_point, + lock->ip); + + stats = get_lock_stats(hlock_class(hlock)); + if (contention_point < LOCKSTAT_POINTS) + stats->contention_point[contention_point]++; + if (contending_point < LOCKSTAT_POINTS) + stats->contending_point[contending_point]++; + if (lock->cpu != smp_processor_id()) + stats->bounces[bounce_contended + !!hlock->read]++; + put_lock_stats(stats); +} + +static void +__lock_acquired(struct lockdep_map *lock, unsigned long ip) +{ + struct task_struct *curr = current; + struct held_lock *hlock, *prev_hlock; + struct lock_class_stats *stats; + unsigned int depth; + u64 now, waittime = 0; + int i, cpu; + + depth = curr->lockdep_depth; + /* + * Yay, we acquired ownership of this lock we didn't try to + * acquire, how the heck did that happen? + */ + if (DEBUG_LOCKS_WARN_ON(!depth)) + return; + + prev_hlock = NULL; + for (i = depth-1; i >= 0; i--) { + hlock = curr->held_locks + i; + /* + * We must not cross into another context: + */ + if (prev_hlock && prev_hlock->irq_context != hlock->irq_context) + break; + if (match_held_lock(hlock, lock)) + goto found_it; + prev_hlock = hlock; + } + print_lock_contention_bug(curr, lock, _RET_IP_); + return; + +found_it: + if (hlock->instance != lock) + return; + + cpu = smp_processor_id(); + if (hlock->waittime_stamp) { + now = lockstat_clock(); + waittime = now - hlock->waittime_stamp; + hlock->holdtime_stamp = now; + } + + trace_lock_acquired(lock, ip); + + stats = get_lock_stats(hlock_class(hlock)); + if (waittime) { + if (hlock->read) + lock_time_inc(&stats->read_waittime, waittime); + else + lock_time_inc(&stats->write_waittime, waittime); + } + if (lock->cpu != cpu) + stats->bounces[bounce_acquired + !!hlock->read]++; + put_lock_stats(stats); + + lock->cpu = cpu; + lock->ip = ip; +} + +void lock_contended(struct lockdep_map *lock, unsigned long ip) +{ + unsigned long flags; + + if (unlikely(!lock_stat)) + return; + + if (unlikely(current->lockdep_recursion)) + return; + + raw_local_irq_save(flags); + check_flags(flags); + current->lockdep_recursion = 1; + trace_lock_contended(lock, ip); + __lock_contended(lock, ip); + current->lockdep_recursion = 0; + raw_local_irq_restore(flags); +} +EXPORT_SYMBOL_GPL(lock_contended); + +void lock_acquired(struct lockdep_map *lock, unsigned long ip) +{ + unsigned long flags; + + if (unlikely(!lock_stat)) + return; + + if (unlikely(current->lockdep_recursion)) + return; + + raw_local_irq_save(flags); + check_flags(flags); + current->lockdep_recursion = 1; + __lock_acquired(lock, ip); + current->lockdep_recursion = 0; + raw_local_irq_restore(flags); +} +EXPORT_SYMBOL_GPL(lock_acquired); +#endif + +/* + * Used by the testsuite, sanitize the validator state + * after a simulated failure: + */ + +void lockdep_reset(void) +{ + unsigned long flags; + int i; + + raw_local_irq_save(flags); + current->curr_chain_key = 0; + current->lockdep_depth = 0; + current->lockdep_recursion = 0; + memset(current->held_locks, 0, MAX_LOCK_DEPTH*sizeof(struct held_lock)); + nr_hardirq_chains = 0; + nr_softirq_chains = 0; + nr_process_chains = 0; + debug_locks = 1; + for (i = 0; i < CHAINHASH_SIZE; i++) + INIT_LIST_HEAD(chainhash_table + i); + raw_local_irq_restore(flags); +} + +static void zap_class(struct lock_class *class) +{ + int i; + + /* + * Remove all dependencies this lock is + * involved in: + */ + for (i = 0; i < nr_list_entries; i++) { + if (list_entries[i].class == class) + list_del_rcu(&list_entries[i].entry); + } + /* + * Unhash the class and remove it from the all_lock_classes list: + */ + list_del_rcu(&class->hash_entry); + list_del_rcu(&class->lock_entry); + + RCU_INIT_POINTER(class->key, NULL); + RCU_INIT_POINTER(class->name, NULL); +} + +static inline int within(const void *addr, void *start, unsigned long size) +{ + return addr >= start && addr < start + size; +} + +/* + * Used in module.c to remove lock classes from memory that is going to be + * freed; and possibly re-used by other modules. + * + * We will have had one sync_sched() before getting here, so we're guaranteed + * nobody will look up these exact classes -- they're properly dead but still + * allocated. + */ +void lockdep_free_key_range(void *start, unsigned long size) +{ + struct lock_class *class; + struct list_head *head; + unsigned long flags; + int i; + int locked; + + raw_local_irq_save(flags); + locked = graph_lock(); + + /* + * Unhash all classes that were created by this module: + */ + for (i = 0; i < CLASSHASH_SIZE; i++) { + head = classhash_table + i; + if (list_empty(head)) + continue; + list_for_each_entry_rcu(class, head, hash_entry) { + if (within(class->key, start, size)) + zap_class(class); + else if (within(class->name, start, size)) + zap_class(class); + } + } + + if (locked) + graph_unlock(); + raw_local_irq_restore(flags); + + /* + * Wait for any possible iterators from look_up_lock_class() to pass + * before continuing to free the memory they refer to. + * + * sync_sched() is sufficient because the read-side is IRQ disable. + */ + synchronize_sched(); + + /* + * XXX at this point we could return the resources to the pool; + * instead we leak them. We would need to change to bitmap allocators + * instead of the linear allocators we have now. + */ +} + +void lockdep_reset_lock(struct lockdep_map *lock) +{ + struct lock_class *class; + struct list_head *head; + unsigned long flags; + int i, j; + int locked; + + raw_local_irq_save(flags); + + /* + * Remove all classes this lock might have: + */ + for (j = 0; j < MAX_LOCKDEP_SUBCLASSES; j++) { + /* + * If the class exists we look it up and zap it: + */ + class = look_up_lock_class(lock, j); + if (class) + zap_class(class); + } + /* + * Debug check: in the end all mapped classes should + * be gone. + */ + locked = graph_lock(); + for (i = 0; i < CLASSHASH_SIZE; i++) { + head = classhash_table + i; + if (list_empty(head)) + continue; + list_for_each_entry_rcu(class, head, hash_entry) { + int match = 0; + + for (j = 0; j < NR_LOCKDEP_CACHING_CLASSES; j++) + match |= class == lock->class_cache[j]; + + if (unlikely(match)) { + if (debug_locks_off_graph_unlock()) { + /* + * We all just reset everything, how did it match? + */ + WARN_ON(1); + } + goto out_restore; + } + } + } + if (locked) + graph_unlock(); + +out_restore: + raw_local_irq_restore(flags); +} + +void lockdep_init(void) +{ + int i; + + /* + * Some architectures have their own start_kernel() + * code which calls lockdep_init(), while we also + * call lockdep_init() from the start_kernel() itself, + * and we want to initialize the hashes only once: + */ + if (lockdep_initialized) + return; + + for (i = 0; i < CLASSHASH_SIZE; i++) + INIT_LIST_HEAD(classhash_table + i); + + for (i = 0; i < CHAINHASH_SIZE; i++) + INIT_LIST_HEAD(chainhash_table + i); + + lockdep_initialized = 1; +} + +void __init lockdep_info(void) +{ + printk("Lock dependency validator: Copyright (c) 2006 Red Hat, Inc., Ingo Molnar\n"); + + printk("... MAX_LOCKDEP_SUBCLASSES: %lu\n", MAX_LOCKDEP_SUBCLASSES); + printk("... MAX_LOCK_DEPTH: %lu\n", MAX_LOCK_DEPTH); + printk("... MAX_LOCKDEP_KEYS: %lu\n", MAX_LOCKDEP_KEYS); + printk("... CLASSHASH_SIZE: %lu\n", CLASSHASH_SIZE); + printk("... MAX_LOCKDEP_ENTRIES: %lu\n", MAX_LOCKDEP_ENTRIES); + printk("... MAX_LOCKDEP_CHAINS: %lu\n", MAX_LOCKDEP_CHAINS); + printk("... CHAINHASH_SIZE: %lu\n", CHAINHASH_SIZE); + + printk(" memory used by lock dependency info: %lu kB\n", + (sizeof(struct lock_class) * MAX_LOCKDEP_KEYS + + sizeof(struct list_head) * CLASSHASH_SIZE + + sizeof(struct lock_list) * MAX_LOCKDEP_ENTRIES + + sizeof(struct lock_chain) * MAX_LOCKDEP_CHAINS + + sizeof(struct list_head) * CHAINHASH_SIZE +#ifdef CONFIG_PROVE_LOCKING + + sizeof(struct circular_queue) +#endif + ) / 1024 + ); + + printk(" per task-struct memory footprint: %lu bytes\n", + sizeof(struct held_lock) * MAX_LOCK_DEPTH); + +#ifdef CONFIG_DEBUG_LOCKDEP + if (lockdep_init_error) { + printk("WARNING: lockdep init error! lock-%s was acquired" + "before lockdep_init\n", lock_init_error); + printk("Call stack leading to lockdep invocation was:\n"); + print_stack_trace(&lockdep_init_trace, 0); + } +#endif +} + +static void +print_freed_lock_bug(struct task_struct *curr, const void *mem_from, + const void *mem_to, struct held_lock *hlock) +{ + if (!debug_locks_off()) + return; + if (debug_locks_silent) + return; + + printk("\n"); + printk("=========================\n"); + printk("[ BUG: held lock freed! ]\n"); + print_kernel_ident(); + printk("-------------------------\n"); + printk("%s/%d is freeing memory %p-%p, with a lock still held there!\n", + curr->comm, task_pid_nr(curr), mem_from, mem_to-1); + print_lock(hlock); + lockdep_print_held_locks(curr); + + printk("\nstack backtrace:\n"); + dump_stack(); +} + +static inline int not_in_range(const void* mem_from, unsigned long mem_len, + const void* lock_from, unsigned long lock_len) +{ + return lock_from + lock_len <= mem_from || + mem_from + mem_len <= lock_from; +} + +/* + * Called when kernel memory is freed (or unmapped), or if a lock + * is destroyed or reinitialized - this code checks whether there is + * any held lock in the memory range of to : + */ +void debug_check_no_locks_freed(const void *mem_from, unsigned long mem_len) +{ + struct task_struct *curr = current; + struct held_lock *hlock; + unsigned long flags; + int i; + + if (unlikely(!debug_locks)) + return; + + local_irq_save(flags); + for (i = 0; i < curr->lockdep_depth; i++) { + hlock = curr->held_locks + i; + + if (not_in_range(mem_from, mem_len, hlock->instance, + sizeof(*hlock->instance))) + continue; + + print_freed_lock_bug(curr, mem_from, mem_from + mem_len, hlock); + break; + } + local_irq_restore(flags); +} +EXPORT_SYMBOL_GPL(debug_check_no_locks_freed); + +static void print_held_locks_bug(void) +{ + if (!debug_locks_off()) + return; + if (debug_locks_silent) + return; + + printk("\n"); + printk("=====================================\n"); + printk("[ BUG: %s/%d still has locks held! ]\n", + current->comm, task_pid_nr(current)); + print_kernel_ident(); + printk("-------------------------------------\n"); + lockdep_print_held_locks(current); + printk("\nstack backtrace:\n"); + dump_stack(); +} + +void debug_check_no_locks_held(void) +{ + if (unlikely(current->lockdep_depth > 0)) + print_held_locks_bug(); +} +EXPORT_SYMBOL_GPL(debug_check_no_locks_held); + +#ifdef __KERNEL__ +void debug_show_all_locks(void) +{ + struct task_struct *g, *p; + int count = 10; + int unlock = 1; + + if (unlikely(!debug_locks)) { + printk("INFO: lockdep is turned off.\n"); + return; + } + printk("\nShowing all locks held in the system:\n"); + + /* + * Here we try to get the tasklist_lock as hard as possible, + * if not successful after 2 seconds we ignore it (but keep + * trying). This is to enable a debug printout even if a + * tasklist_lock-holding task deadlocks or crashes. + */ +retry: + if (!read_trylock(&tasklist_lock)) { + if (count == 10) + printk("hm, tasklist_lock locked, retrying... "); + if (count) { + count--; + printk(" #%d", 10-count); + mdelay(200); + goto retry; + } + printk(" ignoring it.\n"); + unlock = 0; + } else { + if (count != 10) + printk(KERN_CONT " locked it.\n"); + } + + do_each_thread(g, p) { + /* + * It's not reliable to print a task's held locks + * if it's not sleeping (or if it's not the current + * task): + */ + if (p->state == TASK_RUNNING && p != current) + continue; + if (p->lockdep_depth) + lockdep_print_held_locks(p); + if (!unlock) + if (read_trylock(&tasklist_lock)) + unlock = 1; + } while_each_thread(g, p); + + printk("\n"); + printk("=============================================\n\n"); + + if (unlock) + read_unlock(&tasklist_lock); +} +EXPORT_SYMBOL_GPL(debug_show_all_locks); +#endif + +/* + * Careful: only use this function if you are sure that + * the task cannot run in parallel! + */ +void debug_show_held_locks(struct task_struct *task) +{ + if (unlikely(!debug_locks)) { + printk("INFO: lockdep is turned off.\n"); + return; + } + lockdep_print_held_locks(task); +} +EXPORT_SYMBOL_GPL(debug_show_held_locks); + +asmlinkage __visible void lockdep_sys_exit(void) +{ + struct task_struct *curr = current; + + if (unlikely(curr->lockdep_depth)) { + if (!debug_locks_off()) + return; + printk("\n"); + printk("================================================\n"); + printk("[ BUG: lock held when returning to user space! ]\n"); + print_kernel_ident(); + printk("------------------------------------------------\n"); + printk("%s/%d is leaving the kernel with locks still held!\n", + curr->comm, curr->pid); + lockdep_print_held_locks(curr); + } +} + +void lockdep_rcu_suspicious(const char *file, const int line, const char *s) +{ + struct task_struct *curr = current; + +#ifndef CONFIG_PROVE_RCU_REPEATEDLY + if (!debug_locks_off()) + return; +#endif /* #ifdef CONFIG_PROVE_RCU_REPEATEDLY */ + /* Note: the following can be executed concurrently, so be careful. */ + printk("\n"); + printk("===============================\n"); + printk("[ INFO: suspicious RCU usage. ]\n"); + print_kernel_ident(); + printk("-------------------------------\n"); + printk("%s:%d %s!\n", file, line, s); + printk("\nother info that might help us debug this:\n\n"); + printk("\n%srcu_scheduler_active = %d, debug_locks = %d\n", + !rcu_lockdep_current_cpu_online() + ? "RCU used illegally from offline CPU!\n" + : !rcu_is_watching() + ? "RCU used illegally from idle CPU!\n" + : "", + rcu_scheduler_active, debug_locks); + + /* + * If a CPU is in the RCU-free window in idle (ie: in the section + * between rcu_idle_enter() and rcu_idle_exit(), then RCU + * considers that CPU to be in an "extended quiescent state", + * which means that RCU will be completely ignoring that CPU. + * Therefore, rcu_read_lock() and friends have absolutely no + * effect on a CPU running in that state. In other words, even if + * such an RCU-idle CPU has called rcu_read_lock(), RCU might well + * delete data structures out from under it. RCU really has no + * choice here: we need to keep an RCU-free window in idle where + * the CPU may possibly enter into low power mode. This way we can + * notice an extended quiescent state to other CPUs that started a grace + * period. Otherwise we would delay any grace period as long as we run + * in the idle task. + * + * So complain bitterly if someone does call rcu_read_lock(), + * rcu_read_lock_bh() and so on from extended quiescent states. + */ + if (!rcu_is_watching()) + printk("RCU used illegally from extended quiescent state!\n"); + + lockdep_print_held_locks(curr); + printk("\nstack backtrace:\n"); + dump_stack(); +} +EXPORT_SYMBOL_GPL(lockdep_rcu_suspicious); diff --git a/kernel/kernel/locking/lockdep_internals.h b/kernel/kernel/locking/lockdep_internals.h new file mode 100644 index 000000000..51c4b24b6 --- /dev/null +++ b/kernel/kernel/locking/lockdep_internals.h @@ -0,0 +1,170 @@ +/* + * kernel/lockdep_internals.h + * + * Runtime locking correctness validator + * + * lockdep subsystem internal functions and variables. + */ + +/* + * Lock-class usage-state bits: + */ +enum lock_usage_bit { +#define LOCKDEP_STATE(__STATE) \ + LOCK_USED_IN_##__STATE, \ + LOCK_USED_IN_##__STATE##_READ, \ + LOCK_ENABLED_##__STATE, \ + LOCK_ENABLED_##__STATE##_READ, +#include "lockdep_states.h" +#undef LOCKDEP_STATE + LOCK_USED, + LOCK_USAGE_STATES +}; + +/* + * Usage-state bitmasks: + */ +#define __LOCKF(__STATE) LOCKF_##__STATE = (1 << LOCK_##__STATE), + +enum { +#define LOCKDEP_STATE(__STATE) \ + __LOCKF(USED_IN_##__STATE) \ + __LOCKF(USED_IN_##__STATE##_READ) \ + __LOCKF(ENABLED_##__STATE) \ + __LOCKF(ENABLED_##__STATE##_READ) +#include "lockdep_states.h" +#undef LOCKDEP_STATE + __LOCKF(USED) +}; + +#define LOCKF_ENABLED_IRQ (LOCKF_ENABLED_HARDIRQ | LOCKF_ENABLED_SOFTIRQ) +#define LOCKF_USED_IN_IRQ (LOCKF_USED_IN_HARDIRQ | LOCKF_USED_IN_SOFTIRQ) + +#define LOCKF_ENABLED_IRQ_READ \ + (LOCKF_ENABLED_HARDIRQ_READ | LOCKF_ENABLED_SOFTIRQ_READ) +#define LOCKF_USED_IN_IRQ_READ \ + (LOCKF_USED_IN_HARDIRQ_READ | LOCKF_USED_IN_SOFTIRQ_READ) + +/* + * MAX_LOCKDEP_ENTRIES is the maximum number of lock dependencies + * we track. + * + * We use the per-lock dependency maps in two ways: we grow it by adding + * every to-be-taken lock to all currently held lock's own dependency + * table (if it's not there yet), and we check it for lock order + * conflicts and deadlocks. + */ +#define MAX_LOCKDEP_ENTRIES 32768UL + +#define MAX_LOCKDEP_CHAINS_BITS 16 +#define MAX_LOCKDEP_CHAINS (1UL << MAX_LOCKDEP_CHAINS_BITS) + +#define MAX_LOCKDEP_CHAIN_HLOCKS (MAX_LOCKDEP_CHAINS*5) + +/* + * Stack-trace: tightly packed array of stack backtrace + * addresses. Protected by the hash_lock. + */ +#define MAX_STACK_TRACE_ENTRIES 524288UL + +extern struct list_head all_lock_classes; +extern struct lock_chain lock_chains[]; + +#define LOCK_USAGE_CHARS (1+LOCK_USAGE_STATES/2) + +extern void get_usage_chars(struct lock_class *class, + char usage[LOCK_USAGE_CHARS]); + +extern const char * __get_key_name(struct lockdep_subclass_key *key, char *str); + +struct lock_class *lock_chain_get_class(struct lock_chain *chain, int i); + +extern unsigned long nr_lock_classes; +extern unsigned long nr_list_entries; +extern unsigned long nr_lock_chains; +extern int nr_chain_hlocks; +extern unsigned long nr_stack_trace_entries; + +extern unsigned int nr_hardirq_chains; +extern unsigned int nr_softirq_chains; +extern unsigned int nr_process_chains; +extern unsigned int max_lockdep_depth; +extern unsigned int max_recursion_depth; + +extern unsigned int max_bfs_queue_depth; + +#ifdef CONFIG_PROVE_LOCKING +extern unsigned long lockdep_count_forward_deps(struct lock_class *); +extern unsigned long lockdep_count_backward_deps(struct lock_class *); +#else +static inline unsigned long +lockdep_count_forward_deps(struct lock_class *class) +{ + return 0; +} +static inline unsigned long +lockdep_count_backward_deps(struct lock_class *class) +{ + return 0; +} +#endif + +#ifdef CONFIG_DEBUG_LOCKDEP + +#include +/* + * Various lockdep statistics. + * We want them per cpu as they are often accessed in fast path + * and we want to avoid too much cache bouncing. + */ +struct lockdep_stats { + int chain_lookup_hits; + int chain_lookup_misses; + int hardirqs_on_events; + int hardirqs_off_events; + int redundant_hardirqs_on; + int redundant_hardirqs_off; + int softirqs_on_events; + int softirqs_off_events; + int redundant_softirqs_on; + int redundant_softirqs_off; + int nr_unused_locks; + int nr_cyclic_checks; + int nr_cyclic_check_recursions; + int nr_find_usage_forwards_checks; + int nr_find_usage_forwards_recursions; + int nr_find_usage_backwards_checks; + int nr_find_usage_backwards_recursions; +}; + +DECLARE_PER_CPU(struct lockdep_stats, lockdep_stats); + +#define __debug_atomic_inc(ptr) \ + this_cpu_inc(lockdep_stats.ptr); + +#define debug_atomic_inc(ptr) { \ + WARN_ON_ONCE(!irqs_disabled()); \ + __this_cpu_inc(lockdep_stats.ptr); \ +} + +#define debug_atomic_dec(ptr) { \ + WARN_ON_ONCE(!irqs_disabled()); \ + __this_cpu_dec(lockdep_stats.ptr); \ +} + +#define debug_atomic_read(ptr) ({ \ + struct lockdep_stats *__cpu_lockdep_stats; \ + unsigned long long __total = 0; \ + int __cpu; \ + for_each_possible_cpu(__cpu) { \ + __cpu_lockdep_stats = &per_cpu(lockdep_stats, __cpu); \ + __total += __cpu_lockdep_stats->ptr; \ + } \ + __total; \ +}) +#else +# define __debug_atomic_inc(ptr) do { } while (0) +# define debug_atomic_inc(ptr) do { } while (0) +# define debug_atomic_dec(ptr) do { } while (0) +# define debug_atomic_read(ptr) 0 +#endif diff --git a/kernel/kernel/locking/lockdep_proc.c b/kernel/kernel/locking/lockdep_proc.c new file mode 100644 index 000000000..d83d798be --- /dev/null +++ b/kernel/kernel/locking/lockdep_proc.c @@ -0,0 +1,695 @@ +/* + * kernel/lockdep_proc.c + * + * Runtime locking correctness validator + * + * Started by Ingo Molnar: + * + * Copyright (C) 2006,2007 Red Hat, Inc., Ingo Molnar + * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra + * + * Code for /proc/lockdep and /proc/lockdep_stats: + * + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "lockdep_internals.h" + +static void *l_next(struct seq_file *m, void *v, loff_t *pos) +{ + return seq_list_next(v, &all_lock_classes, pos); +} + +static void *l_start(struct seq_file *m, loff_t *pos) +{ + return seq_list_start_head(&all_lock_classes, *pos); +} + +static void l_stop(struct seq_file *m, void *v) +{ +} + +static void print_name(struct seq_file *m, struct lock_class *class) +{ + char str[KSYM_NAME_LEN]; + const char *name = class->name; + + if (!name) { + name = __get_key_name(class->key, str); + seq_printf(m, "%s", name); + } else{ + seq_printf(m, "%s", name); + if (class->name_version > 1) + seq_printf(m, "#%d", class->name_version); + if (class->subclass) + seq_printf(m, "/%d", class->subclass); + } +} + +static int l_show(struct seq_file *m, void *v) +{ + struct lock_class *class = list_entry(v, struct lock_class, lock_entry); + struct lock_list *entry; + char usage[LOCK_USAGE_CHARS]; + + if (v == &all_lock_classes) { + seq_printf(m, "all lock classes:\n"); + return 0; + } + + seq_printf(m, "%p", class->key); +#ifdef CONFIG_DEBUG_LOCKDEP + seq_printf(m, " OPS:%8ld", class->ops); +#endif +#ifdef CONFIG_PROVE_LOCKING + seq_printf(m, " FD:%5ld", lockdep_count_forward_deps(class)); + seq_printf(m, " BD:%5ld", lockdep_count_backward_deps(class)); +#endif + + get_usage_chars(class, usage); + seq_printf(m, " %s", usage); + + seq_printf(m, ": "); + print_name(m, class); + seq_puts(m, "\n"); + + list_for_each_entry(entry, &class->locks_after, entry) { + if (entry->distance == 1) { + seq_printf(m, " -> [%p] ", entry->class->key); + print_name(m, entry->class); + seq_puts(m, "\n"); + } + } + seq_puts(m, "\n"); + + return 0; +} + +static const struct seq_operations lockdep_ops = { + .start = l_start, + .next = l_next, + .stop = l_stop, + .show = l_show, +}; + +static int lockdep_open(struct inode *inode, struct file *file) +{ + return seq_open(file, &lockdep_ops); +} + +static const struct file_operations proc_lockdep_operations = { + .open = lockdep_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, +}; + +#ifdef CONFIG_PROVE_LOCKING +static void *lc_start(struct seq_file *m, loff_t *pos) +{ + if (*pos == 0) + return SEQ_START_TOKEN; + + if (*pos - 1 < nr_lock_chains) + return lock_chains + (*pos - 1); + + return NULL; +} + +static void *lc_next(struct seq_file *m, void *v, loff_t *pos) +{ + (*pos)++; + return lc_start(m, pos); +} + +static void lc_stop(struct seq_file *m, void *v) +{ +} + +static int lc_show(struct seq_file *m, void *v) +{ + struct lock_chain *chain = v; + struct lock_class *class; + int i; + + if (v == SEQ_START_TOKEN) { + seq_printf(m, "all lock chains:\n"); + return 0; + } + + seq_printf(m, "irq_context: %d\n", chain->irq_context); + + for (i = 0; i < chain->depth; i++) { + class = lock_chain_get_class(chain, i); + if (!class->key) + continue; + + seq_printf(m, "[%p] ", class->key); + print_name(m, class); + seq_puts(m, "\n"); + } + seq_puts(m, "\n"); + + return 0; +} + +static const struct seq_operations lockdep_chains_ops = { + .start = lc_start, + .next = lc_next, + .stop = lc_stop, + .show = lc_show, +}; + +static int lockdep_chains_open(struct inode *inode, struct file *file) +{ + return seq_open(file, &lockdep_chains_ops); +} + +static const struct file_operations proc_lockdep_chains_operations = { + .open = lockdep_chains_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, +}; +#endif /* CONFIG_PROVE_LOCKING */ + +static void lockdep_stats_debug_show(struct seq_file *m) +{ +#ifdef CONFIG_DEBUG_LOCKDEP + unsigned long long hi1 = debug_atomic_read(hardirqs_on_events), + hi2 = debug_atomic_read(hardirqs_off_events), + hr1 = debug_atomic_read(redundant_hardirqs_on), + hr2 = debug_atomic_read(redundant_hardirqs_off), + si1 = debug_atomic_read(softirqs_on_events), + si2 = debug_atomic_read(softirqs_off_events), + sr1 = debug_atomic_read(redundant_softirqs_on), + sr2 = debug_atomic_read(redundant_softirqs_off); + + seq_printf(m, " chain lookup misses: %11llu\n", + debug_atomic_read(chain_lookup_misses)); + seq_printf(m, " chain lookup hits: %11llu\n", + debug_atomic_read(chain_lookup_hits)); + seq_printf(m, " cyclic checks: %11llu\n", + debug_atomic_read(nr_cyclic_checks)); + seq_printf(m, " find-mask forwards checks: %11llu\n", + debug_atomic_read(nr_find_usage_forwards_checks)); + seq_printf(m, " find-mask backwards checks: %11llu\n", + debug_atomic_read(nr_find_usage_backwards_checks)); + + seq_printf(m, " hardirq on events: %11llu\n", hi1); + seq_printf(m, " hardirq off events: %11llu\n", hi2); + seq_printf(m, " redundant hardirq ons: %11llu\n", hr1); + seq_printf(m, " redundant hardirq offs: %11llu\n", hr2); + seq_printf(m, " softirq on events: %11llu\n", si1); + seq_printf(m, " softirq off events: %11llu\n", si2); + seq_printf(m, " redundant softirq ons: %11llu\n", sr1); + seq_printf(m, " redundant softirq offs: %11llu\n", sr2); +#endif +} + +static int lockdep_stats_show(struct seq_file *m, void *v) +{ + struct lock_class *class; + unsigned long nr_unused = 0, nr_uncategorized = 0, + nr_irq_safe = 0, nr_irq_unsafe = 0, + nr_softirq_safe = 0, nr_softirq_unsafe = 0, + nr_hardirq_safe = 0, nr_hardirq_unsafe = 0, + nr_irq_read_safe = 0, nr_irq_read_unsafe = 0, + nr_softirq_read_safe = 0, nr_softirq_read_unsafe = 0, + nr_hardirq_read_safe = 0, nr_hardirq_read_unsafe = 0, + sum_forward_deps = 0; + + list_for_each_entry(class, &all_lock_classes, lock_entry) { + + if (class->usage_mask == 0) + nr_unused++; + if (class->usage_mask == LOCKF_USED) + nr_uncategorized++; + if (class->usage_mask & LOCKF_USED_IN_IRQ) + nr_irq_safe++; + if (class->usage_mask & LOCKF_ENABLED_IRQ) + nr_irq_unsafe++; + if (class->usage_mask & LOCKF_USED_IN_SOFTIRQ) + nr_softirq_safe++; + if (class->usage_mask & LOCKF_ENABLED_SOFTIRQ) + nr_softirq_unsafe++; + if (class->usage_mask & LOCKF_USED_IN_HARDIRQ) + nr_hardirq_safe++; + if (class->usage_mask & LOCKF_ENABLED_HARDIRQ) + nr_hardirq_unsafe++; + if (class->usage_mask & LOCKF_USED_IN_IRQ_READ) + nr_irq_read_safe++; + if (class->usage_mask & LOCKF_ENABLED_IRQ_READ) + nr_irq_read_unsafe++; + if (class->usage_mask & LOCKF_USED_IN_SOFTIRQ_READ) + nr_softirq_read_safe++; + if (class->usage_mask & LOCKF_ENABLED_SOFTIRQ_READ) + nr_softirq_read_unsafe++; + if (class->usage_mask & LOCKF_USED_IN_HARDIRQ_READ) + nr_hardirq_read_safe++; + if (class->usage_mask & LOCKF_ENABLED_HARDIRQ_READ) + nr_hardirq_read_unsafe++; + +#ifdef CONFIG_PROVE_LOCKING + sum_forward_deps += lockdep_count_forward_deps(class); +#endif + } +#ifdef CONFIG_DEBUG_LOCKDEP + DEBUG_LOCKS_WARN_ON(debug_atomic_read(nr_unused_locks) != nr_unused); +#endif + seq_printf(m, " lock-classes: %11lu [max: %lu]\n", + nr_lock_classes, MAX_LOCKDEP_KEYS); + seq_printf(m, " direct dependencies: %11lu [max: %lu]\n", + nr_list_entries, MAX_LOCKDEP_ENTRIES); + seq_printf(m, " indirect dependencies: %11lu\n", + sum_forward_deps); + + /* + * Total number of dependencies: + * + * All irq-safe locks may nest inside irq-unsafe locks, + * plus all the other known dependencies: + */ + seq_printf(m, " all direct dependencies: %11lu\n", + nr_irq_unsafe * nr_irq_safe + + nr_hardirq_unsafe * nr_hardirq_safe + + nr_list_entries); + +#ifdef CONFIG_PROVE_LOCKING + seq_printf(m, " dependency chains: %11lu [max: %lu]\n", + nr_lock_chains, MAX_LOCKDEP_CHAINS); + seq_printf(m, " dependency chain hlocks: %11d [max: %lu]\n", + nr_chain_hlocks, MAX_LOCKDEP_CHAIN_HLOCKS); +#endif + +#ifdef CONFIG_TRACE_IRQFLAGS + seq_printf(m, " in-hardirq chains: %11u\n", + nr_hardirq_chains); + seq_printf(m, " in-softirq chains: %11u\n", + nr_softirq_chains); +#endif + seq_printf(m, " in-process chains: %11u\n", + nr_process_chains); + seq_printf(m, " stack-trace entries: %11lu [max: %lu]\n", + nr_stack_trace_entries, MAX_STACK_TRACE_ENTRIES); + seq_printf(m, " combined max dependencies: %11u\n", + (nr_hardirq_chains + 1) * + (nr_softirq_chains + 1) * + (nr_process_chains + 1) + ); + seq_printf(m, " hardirq-safe locks: %11lu\n", + nr_hardirq_safe); + seq_printf(m, " hardirq-unsafe locks: %11lu\n", + nr_hardirq_unsafe); + seq_printf(m, " softirq-safe locks: %11lu\n", + nr_softirq_safe); + seq_printf(m, " softirq-unsafe locks: %11lu\n", + nr_softirq_unsafe); + seq_printf(m, " irq-safe locks: %11lu\n", + nr_irq_safe); + seq_printf(m, " irq-unsafe locks: %11lu\n", + nr_irq_unsafe); + + seq_printf(m, " hardirq-read-safe locks: %11lu\n", + nr_hardirq_read_safe); + seq_printf(m, " hardirq-read-unsafe locks: %11lu\n", + nr_hardirq_read_unsafe); + seq_printf(m, " softirq-read-safe locks: %11lu\n", + nr_softirq_read_safe); + seq_printf(m, " softirq-read-unsafe locks: %11lu\n", + nr_softirq_read_unsafe); + seq_printf(m, " irq-read-safe locks: %11lu\n", + nr_irq_read_safe); + seq_printf(m, " irq-read-unsafe locks: %11lu\n", + nr_irq_read_unsafe); + + seq_printf(m, " uncategorized locks: %11lu\n", + nr_uncategorized); + seq_printf(m, " unused locks: %11lu\n", + nr_unused); + seq_printf(m, " max locking depth: %11u\n", + max_lockdep_depth); +#ifdef CONFIG_PROVE_LOCKING + seq_printf(m, " max bfs queue depth: %11u\n", + max_bfs_queue_depth); +#endif + lockdep_stats_debug_show(m); + seq_printf(m, " debug_locks: %11u\n", + debug_locks); + + return 0; +} + +static int lockdep_stats_open(struct inode *inode, struct file *file) +{ + return single_open(file, lockdep_stats_show, NULL); +} + +static const struct file_operations proc_lockdep_stats_operations = { + .open = lockdep_stats_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +#ifdef CONFIG_LOCK_STAT + +struct lock_stat_data { + struct lock_class *class; + struct lock_class_stats stats; +}; + +struct lock_stat_seq { + struct lock_stat_data *iter_end; + struct lock_stat_data stats[MAX_LOCKDEP_KEYS]; +}; + +/* + * sort on absolute number of contentions + */ +static int lock_stat_cmp(const void *l, const void *r) +{ + const struct lock_stat_data *dl = l, *dr = r; + unsigned long nl, nr; + + nl = dl->stats.read_waittime.nr + dl->stats.write_waittime.nr; + nr = dr->stats.read_waittime.nr + dr->stats.write_waittime.nr; + + return nr - nl; +} + +static void seq_line(struct seq_file *m, char c, int offset, int length) +{ + int i; + + for (i = 0; i < offset; i++) + seq_puts(m, " "); + for (i = 0; i < length; i++) + seq_printf(m, "%c", c); + seq_puts(m, "\n"); +} + +static void snprint_time(char *buf, size_t bufsiz, s64 nr) +{ + s64 div; + s32 rem; + + nr += 5; /* for display rounding */ + div = div_s64_rem(nr, 1000, &rem); + snprintf(buf, bufsiz, "%lld.%02d", (long long)div, (int)rem/10); +} + +static void seq_time(struct seq_file *m, s64 time) +{ + char num[15]; + + snprint_time(num, sizeof(num), time); + seq_printf(m, " %14s", num); +} + +static void seq_lock_time(struct seq_file *m, struct lock_time *lt) +{ + seq_printf(m, "%14lu", lt->nr); + seq_time(m, lt->min); + seq_time(m, lt->max); + seq_time(m, lt->total); + seq_time(m, lt->nr ? div_s64(lt->total, lt->nr) : 0); +} + +static void seq_stats(struct seq_file *m, struct lock_stat_data *data) +{ + struct lockdep_subclass_key *ckey; + struct lock_class_stats *stats; + struct lock_class *class; + const char *cname; + int i, namelen; + char name[39]; + + class = data->class; + stats = &data->stats; + + namelen = 38; + if (class->name_version > 1) + namelen -= 2; /* XXX truncates versions > 9 */ + if (class->subclass) + namelen -= 2; + + rcu_read_lock_sched(); + cname = rcu_dereference_sched(class->name); + ckey = rcu_dereference_sched(class->key); + + if (!cname && !ckey) { + rcu_read_unlock_sched(); + return; + + } else if (!cname) { + char str[KSYM_NAME_LEN]; + const char *key_name; + + key_name = __get_key_name(ckey, str); + snprintf(name, namelen, "%s", key_name); + } else { + snprintf(name, namelen, "%s", cname); + } + rcu_read_unlock_sched(); + + namelen = strlen(name); + if (class->name_version > 1) { + snprintf(name+namelen, 3, "#%d", class->name_version); + namelen += 2; + } + if (class->subclass) { + snprintf(name+namelen, 3, "/%d", class->subclass); + namelen += 2; + } + + if (stats->write_holdtime.nr) { + if (stats->read_holdtime.nr) + seq_printf(m, "%38s-W:", name); + else + seq_printf(m, "%40s:", name); + + seq_printf(m, "%14lu ", stats->bounces[bounce_contended_write]); + seq_lock_time(m, &stats->write_waittime); + seq_printf(m, " %14lu ", stats->bounces[bounce_acquired_write]); + seq_lock_time(m, &stats->write_holdtime); + seq_puts(m, "\n"); + } + + if (stats->read_holdtime.nr) { + seq_printf(m, "%38s-R:", name); + seq_printf(m, "%14lu ", stats->bounces[bounce_contended_read]); + seq_lock_time(m, &stats->read_waittime); + seq_printf(m, " %14lu ", stats->bounces[bounce_acquired_read]); + seq_lock_time(m, &stats->read_holdtime); + seq_puts(m, "\n"); + } + + if (stats->read_waittime.nr + stats->write_waittime.nr == 0) + return; + + if (stats->read_holdtime.nr) + namelen += 2; + + for (i = 0; i < LOCKSTAT_POINTS; i++) { + char ip[32]; + + if (class->contention_point[i] == 0) + break; + + if (!i) + seq_line(m, '-', 40-namelen, namelen); + + snprintf(ip, sizeof(ip), "[<%p>]", + (void *)class->contention_point[i]); + seq_printf(m, "%40s %14lu %29s %pS\n", + name, stats->contention_point[i], + ip, (void *)class->contention_point[i]); + } + for (i = 0; i < LOCKSTAT_POINTS; i++) { + char ip[32]; + + if (class->contending_point[i] == 0) + break; + + if (!i) + seq_line(m, '-', 40-namelen, namelen); + + snprintf(ip, sizeof(ip), "[<%p>]", + (void *)class->contending_point[i]); + seq_printf(m, "%40s %14lu %29s %pS\n", + name, stats->contending_point[i], + ip, (void *)class->contending_point[i]); + } + if (i) { + seq_puts(m, "\n"); + seq_line(m, '.', 0, 40 + 1 + 12 * (14 + 1)); + seq_puts(m, "\n"); + } +} + +static void seq_header(struct seq_file *m) +{ + seq_puts(m, "lock_stat version 0.4\n"); + + if (unlikely(!debug_locks)) + seq_printf(m, "*WARNING* lock debugging disabled!! - possibly due to a lockdep warning\n"); + + seq_line(m, '-', 0, 40 + 1 + 12 * (14 + 1)); + seq_printf(m, "%40s %14s %14s %14s %14s %14s %14s %14s %14s %14s %14s " + "%14s %14s\n", + "class name", + "con-bounces", + "contentions", + "waittime-min", + "waittime-max", + "waittime-total", + "waittime-avg", + "acq-bounces", + "acquisitions", + "holdtime-min", + "holdtime-max", + "holdtime-total", + "holdtime-avg"); + seq_line(m, '-', 0, 40 + 1 + 12 * (14 + 1)); + seq_printf(m, "\n"); +} + +static void *ls_start(struct seq_file *m, loff_t *pos) +{ + struct lock_stat_seq *data = m->private; + struct lock_stat_data *iter; + + if (*pos == 0) + return SEQ_START_TOKEN; + + iter = data->stats + (*pos - 1); + if (iter >= data->iter_end) + iter = NULL; + + return iter; +} + +static void *ls_next(struct seq_file *m, void *v, loff_t *pos) +{ + (*pos)++; + return ls_start(m, pos); +} + +static void ls_stop(struct seq_file *m, void *v) +{ +} + +static int ls_show(struct seq_file *m, void *v) +{ + if (v == SEQ_START_TOKEN) + seq_header(m); + else + seq_stats(m, v); + + return 0; +} + +static const struct seq_operations lockstat_ops = { + .start = ls_start, + .next = ls_next, + .stop = ls_stop, + .show = ls_show, +}; + +static int lock_stat_open(struct inode *inode, struct file *file) +{ + int res; + struct lock_class *class; + struct lock_stat_seq *data = vmalloc(sizeof(struct lock_stat_seq)); + + if (!data) + return -ENOMEM; + + res = seq_open(file, &lockstat_ops); + if (!res) { + struct lock_stat_data *iter = data->stats; + struct seq_file *m = file->private_data; + + list_for_each_entry(class, &all_lock_classes, lock_entry) { + iter->class = class; + iter->stats = lock_stats(class); + iter++; + } + data->iter_end = iter; + + sort(data->stats, data->iter_end - data->stats, + sizeof(struct lock_stat_data), + lock_stat_cmp, NULL); + + m->private = data; + } else + vfree(data); + + return res; +} + +static ssize_t lock_stat_write(struct file *file, const char __user *buf, + size_t count, loff_t *ppos) +{ + struct lock_class *class; + char c; + + if (count) { + if (get_user(c, buf)) + return -EFAULT; + + if (c != '0') + return count; + + list_for_each_entry(class, &all_lock_classes, lock_entry) + clear_lock_stats(class); + } + return count; +} + +static int lock_stat_release(struct inode *inode, struct file *file) +{ + struct seq_file *seq = file->private_data; + + vfree(seq->private); + return seq_release(inode, file); +} + +static const struct file_operations proc_lock_stat_operations = { + .open = lock_stat_open, + .write = lock_stat_write, + .read = seq_read, + .llseek = seq_lseek, + .release = lock_stat_release, +}; +#endif /* CONFIG_LOCK_STAT */ + +static int __init lockdep_proc_init(void) +{ + proc_create("lockdep", S_IRUSR, NULL, &proc_lockdep_operations); +#ifdef CONFIG_PROVE_LOCKING + proc_create("lockdep_chains", S_IRUSR, NULL, + &proc_lockdep_chains_operations); +#endif + proc_create("lockdep_stats", S_IRUSR, NULL, + &proc_lockdep_stats_operations); + +#ifdef CONFIG_LOCK_STAT + proc_create("lock_stat", S_IRUSR | S_IWUSR, NULL, + &proc_lock_stat_operations); +#endif + + return 0; +} + +__initcall(lockdep_proc_init); + diff --git a/kernel/kernel/locking/lockdep_states.h b/kernel/kernel/locking/lockdep_states.h new file mode 100644 index 000000000..995b0cc2b --- /dev/null +++ b/kernel/kernel/locking/lockdep_states.h @@ -0,0 +1,9 @@ +/* + * Lockdep states, + * + * please update XXX_LOCK_USAGE_STATES in include/linux/lockdep.h whenever + * you add one, or come up with a nice dynamic solution. + */ +LOCKDEP_STATE(HARDIRQ) +LOCKDEP_STATE(SOFTIRQ) +LOCKDEP_STATE(RECLAIM_FS) diff --git a/kernel/kernel/locking/locktorture.c b/kernel/kernel/locking/locktorture.c new file mode 100644 index 000000000..aa60d919e --- /dev/null +++ b/kernel/kernel/locking/locktorture.c @@ -0,0 +1,814 @@ +/* + * Module-based torture test facility for locking + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, you can access it online at + * http://www.gnu.org/licenses/gpl-2.0.html. + * + * Copyright (C) IBM Corporation, 2014 + * + * Author: Paul E. McKenney + * Based on kernel/rcu/torture.c. + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Paul E. McKenney "); + +torture_param(int, nwriters_stress, -1, + "Number of write-locking stress-test threads"); +torture_param(int, nreaders_stress, -1, + "Number of read-locking stress-test threads"); +torture_param(int, onoff_holdoff, 0, "Time after boot before CPU hotplugs (s)"); +torture_param(int, onoff_interval, 0, + "Time between CPU hotplugs (s), 0=disable"); +torture_param(int, shuffle_interval, 3, + "Number of jiffies between shuffles, 0=disable"); +torture_param(int, shutdown_secs, 0, "Shutdown time (j), <= zero to disable."); +torture_param(int, stat_interval, 60, + "Number of seconds between stats printk()s"); +torture_param(int, stutter, 5, "Number of jiffies to run/halt test, 0=disable"); +torture_param(bool, verbose, true, + "Enable verbose debugging printk()s"); + +static char *torture_type = "spin_lock"; +module_param(torture_type, charp, 0444); +MODULE_PARM_DESC(torture_type, + "Type of lock to torture (spin_lock, spin_lock_irq, mutex_lock, ...)"); + +static struct task_struct *stats_task; +static struct task_struct **writer_tasks; +static struct task_struct **reader_tasks; + +static bool lock_is_write_held; +static bool lock_is_read_held; + +struct lock_stress_stats { + long n_lock_fail; + long n_lock_acquired; +}; + +#if defined(MODULE) +#define LOCKTORTURE_RUNNABLE_INIT 1 +#else +#define LOCKTORTURE_RUNNABLE_INIT 0 +#endif +int torture_runnable = LOCKTORTURE_RUNNABLE_INIT; +module_param(torture_runnable, int, 0444); +MODULE_PARM_DESC(torture_runnable, "Start locktorture at module init"); + +/* Forward reference. */ +static void lock_torture_cleanup(void); + +/* + * Operations vector for selecting different types of tests. + */ +struct lock_torture_ops { + void (*init)(void); + int (*writelock)(void); + void (*write_delay)(struct torture_random_state *trsp); + void (*writeunlock)(void); + int (*readlock)(void); + void (*read_delay)(struct torture_random_state *trsp); + void (*readunlock)(void); + unsigned long flags; + const char *name; +}; + +struct lock_torture_cxt { + int nrealwriters_stress; + int nrealreaders_stress; + bool debug_lock; + atomic_t n_lock_torture_errors; + struct lock_torture_ops *cur_ops; + struct lock_stress_stats *lwsa; /* writer statistics */ + struct lock_stress_stats *lrsa; /* reader statistics */ +}; +static struct lock_torture_cxt cxt = { 0, 0, false, + ATOMIC_INIT(0), + NULL, NULL}; +/* + * Definitions for lock torture testing. + */ + +static int torture_lock_busted_write_lock(void) +{ + return 0; /* BUGGY, do not use in real life!!! */ +} + +static void torture_lock_busted_write_delay(struct torture_random_state *trsp) +{ + const unsigned long longdelay_us = 100; + + /* We want a long delay occasionally to force massive contention. */ + if (!(torture_random(trsp) % + (cxt.nrealwriters_stress * 2000 * longdelay_us))) + mdelay(longdelay_us); +#ifdef CONFIG_PREEMPT + if (!(torture_random(trsp) % (cxt.nrealwriters_stress * 20000))) + preempt_schedule(); /* Allow test to be preempted. */ +#endif +} + +static void torture_lock_busted_write_unlock(void) +{ + /* BUGGY, do not use in real life!!! */ +} + +static struct lock_torture_ops lock_busted_ops = { + .writelock = torture_lock_busted_write_lock, + .write_delay = torture_lock_busted_write_delay, + .writeunlock = torture_lock_busted_write_unlock, + .readlock = NULL, + .read_delay = NULL, + .readunlock = NULL, + .name = "lock_busted" +}; + +static DEFINE_SPINLOCK(torture_spinlock); + +static int torture_spin_lock_write_lock(void) __acquires(torture_spinlock) +{ + spin_lock(&torture_spinlock); + return 0; +} + +static void torture_spin_lock_write_delay(struct torture_random_state *trsp) +{ + const unsigned long shortdelay_us = 2; + const unsigned long longdelay_us = 100; + + /* We want a short delay mostly to emulate likely code, and + * we want a long delay occasionally to force massive contention. + */ + if (!(torture_random(trsp) % + (cxt.nrealwriters_stress * 2000 * longdelay_us))) + mdelay(longdelay_us); + if (!(torture_random(trsp) % + (cxt.nrealwriters_stress * 2 * shortdelay_us))) + udelay(shortdelay_us); +#ifdef CONFIG_PREEMPT + if (!(torture_random(trsp) % (cxt.nrealwriters_stress * 20000))) + preempt_schedule(); /* Allow test to be preempted. */ +#endif +} + +static void torture_spin_lock_write_unlock(void) __releases(torture_spinlock) +{ + spin_unlock(&torture_spinlock); +} + +static struct lock_torture_ops spin_lock_ops = { + .writelock = torture_spin_lock_write_lock, + .write_delay = torture_spin_lock_write_delay, + .writeunlock = torture_spin_lock_write_unlock, + .readlock = NULL, + .read_delay = NULL, + .readunlock = NULL, + .name = "spin_lock" +}; + +static int torture_spin_lock_write_lock_irq(void) +__acquires(torture_spinlock) +{ + unsigned long flags; + + spin_lock_irqsave(&torture_spinlock, flags); + cxt.cur_ops->flags = flags; + return 0; +} + +static void torture_lock_spin_write_unlock_irq(void) +__releases(torture_spinlock) +{ + spin_unlock_irqrestore(&torture_spinlock, cxt.cur_ops->flags); +} + +static struct lock_torture_ops spin_lock_irq_ops = { + .writelock = torture_spin_lock_write_lock_irq, + .write_delay = torture_spin_lock_write_delay, + .writeunlock = torture_lock_spin_write_unlock_irq, + .readlock = NULL, + .read_delay = NULL, + .readunlock = NULL, + .name = "spin_lock_irq" +}; + +static DEFINE_RWLOCK(torture_rwlock); + +static int torture_rwlock_write_lock(void) __acquires(torture_rwlock) +{ + write_lock(&torture_rwlock); + return 0; +} + +static void torture_rwlock_write_delay(struct torture_random_state *trsp) +{ + const unsigned long shortdelay_us = 2; + const unsigned long longdelay_ms = 100; + + /* We want a short delay mostly to emulate likely code, and + * we want a long delay occasionally to force massive contention. + */ + if (!(torture_random(trsp) % + (cxt.nrealwriters_stress * 2000 * longdelay_ms))) + mdelay(longdelay_ms); + else + udelay(shortdelay_us); +} + +static void torture_rwlock_write_unlock(void) __releases(torture_rwlock) +{ + write_unlock(&torture_rwlock); +} + +static int torture_rwlock_read_lock(void) __acquires(torture_rwlock) +{ + read_lock(&torture_rwlock); + return 0; +} + +static void torture_rwlock_read_delay(struct torture_random_state *trsp) +{ + const unsigned long shortdelay_us = 10; + const unsigned long longdelay_ms = 100; + + /* We want a short delay mostly to emulate likely code, and + * we want a long delay occasionally to force massive contention. + */ + if (!(torture_random(trsp) % + (cxt.nrealreaders_stress * 2000 * longdelay_ms))) + mdelay(longdelay_ms); + else + udelay(shortdelay_us); +} + +static void torture_rwlock_read_unlock(void) __releases(torture_rwlock) +{ + read_unlock(&torture_rwlock); +} + +static struct lock_torture_ops rw_lock_ops = { + .writelock = torture_rwlock_write_lock, + .write_delay = torture_rwlock_write_delay, + .writeunlock = torture_rwlock_write_unlock, + .readlock = torture_rwlock_read_lock, + .read_delay = torture_rwlock_read_delay, + .readunlock = torture_rwlock_read_unlock, + .name = "rw_lock" +}; + +static int torture_rwlock_write_lock_irq(void) __acquires(torture_rwlock) +{ + unsigned long flags; + + write_lock_irqsave(&torture_rwlock, flags); + cxt.cur_ops->flags = flags; + return 0; +} + +static void torture_rwlock_write_unlock_irq(void) +__releases(torture_rwlock) +{ + write_unlock_irqrestore(&torture_rwlock, cxt.cur_ops->flags); +} + +static int torture_rwlock_read_lock_irq(void) __acquires(torture_rwlock) +{ + unsigned long flags; + + read_lock_irqsave(&torture_rwlock, flags); + cxt.cur_ops->flags = flags; + return 0; +} + +static void torture_rwlock_read_unlock_irq(void) +__releases(torture_rwlock) +{ + write_unlock_irqrestore(&torture_rwlock, cxt.cur_ops->flags); +} + +static struct lock_torture_ops rw_lock_irq_ops = { + .writelock = torture_rwlock_write_lock_irq, + .write_delay = torture_rwlock_write_delay, + .writeunlock = torture_rwlock_write_unlock_irq, + .readlock = torture_rwlock_read_lock_irq, + .read_delay = torture_rwlock_read_delay, + .readunlock = torture_rwlock_read_unlock_irq, + .name = "rw_lock_irq" +}; + +static DEFINE_MUTEX(torture_mutex); + +static int torture_mutex_lock(void) __acquires(torture_mutex) +{ + mutex_lock(&torture_mutex); + return 0; +} + +static void torture_mutex_delay(struct torture_random_state *trsp) +{ + const unsigned long longdelay_ms = 100; + + /* We want a long delay occasionally to force massive contention. */ + if (!(torture_random(trsp) % + (cxt.nrealwriters_stress * 2000 * longdelay_ms))) + mdelay(longdelay_ms * 5); + else + mdelay(longdelay_ms / 5); +#ifdef CONFIG_PREEMPT + if (!(torture_random(trsp) % (cxt.nrealwriters_stress * 20000))) + preempt_schedule(); /* Allow test to be preempted. */ +#endif +} + +static void torture_mutex_unlock(void) __releases(torture_mutex) +{ + mutex_unlock(&torture_mutex); +} + +static struct lock_torture_ops mutex_lock_ops = { + .writelock = torture_mutex_lock, + .write_delay = torture_mutex_delay, + .writeunlock = torture_mutex_unlock, + .readlock = NULL, + .read_delay = NULL, + .readunlock = NULL, + .name = "mutex_lock" +}; + +static DECLARE_RWSEM(torture_rwsem); +static int torture_rwsem_down_write(void) __acquires(torture_rwsem) +{ + down_write(&torture_rwsem); + return 0; +} + +static void torture_rwsem_write_delay(struct torture_random_state *trsp) +{ + const unsigned long longdelay_ms = 100; + + /* We want a long delay occasionally to force massive contention. */ + if (!(torture_random(trsp) % + (cxt.nrealwriters_stress * 2000 * longdelay_ms))) + mdelay(longdelay_ms * 10); + else + mdelay(longdelay_ms / 10); +#ifdef CONFIG_PREEMPT + if (!(torture_random(trsp) % (cxt.nrealwriters_stress * 20000))) + preempt_schedule(); /* Allow test to be preempted. */ +#endif +} + +static void torture_rwsem_up_write(void) __releases(torture_rwsem) +{ + up_write(&torture_rwsem); +} + +static int torture_rwsem_down_read(void) __acquires(torture_rwsem) +{ + down_read(&torture_rwsem); + return 0; +} + +static void torture_rwsem_read_delay(struct torture_random_state *trsp) +{ + const unsigned long longdelay_ms = 100; + + /* We want a long delay occasionally to force massive contention. */ + if (!(torture_random(trsp) % + (cxt.nrealwriters_stress * 2000 * longdelay_ms))) + mdelay(longdelay_ms * 2); + else + mdelay(longdelay_ms / 2); +#ifdef CONFIG_PREEMPT + if (!(torture_random(trsp) % (cxt.nrealreaders_stress * 20000))) + preempt_schedule(); /* Allow test to be preempted. */ +#endif +} + +static void torture_rwsem_up_read(void) __releases(torture_rwsem) +{ + up_read(&torture_rwsem); +} + +static struct lock_torture_ops rwsem_lock_ops = { + .writelock = torture_rwsem_down_write, + .write_delay = torture_rwsem_write_delay, + .writeunlock = torture_rwsem_up_write, + .readlock = torture_rwsem_down_read, + .read_delay = torture_rwsem_read_delay, + .readunlock = torture_rwsem_up_read, + .name = "rwsem_lock" +}; + +/* + * Lock torture writer kthread. Repeatedly acquires and releases + * the lock, checking for duplicate acquisitions. + */ +static int lock_torture_writer(void *arg) +{ + struct lock_stress_stats *lwsp = arg; + static DEFINE_TORTURE_RANDOM(rand); + + VERBOSE_TOROUT_STRING("lock_torture_writer task started"); + set_user_nice(current, MAX_NICE); + + do { + if ((torture_random(&rand) & 0xfffff) == 0) + schedule_timeout_uninterruptible(1); + + cxt.cur_ops->writelock(); + if (WARN_ON_ONCE(lock_is_write_held)) + lwsp->n_lock_fail++; + lock_is_write_held = 1; + if (WARN_ON_ONCE(lock_is_read_held)) + lwsp->n_lock_fail++; /* rare, but... */ + + lwsp->n_lock_acquired++; + cxt.cur_ops->write_delay(&rand); + lock_is_write_held = 0; + cxt.cur_ops->writeunlock(); + + stutter_wait("lock_torture_writer"); + } while (!torture_must_stop()); + torture_kthread_stopping("lock_torture_writer"); + return 0; +} + +/* + * Lock torture reader kthread. Repeatedly acquires and releases + * the reader lock. + */ +static int lock_torture_reader(void *arg) +{ + struct lock_stress_stats *lrsp = arg; + static DEFINE_TORTURE_RANDOM(rand); + + VERBOSE_TOROUT_STRING("lock_torture_reader task started"); + set_user_nice(current, MAX_NICE); + + do { + if ((torture_random(&rand) & 0xfffff) == 0) + schedule_timeout_uninterruptible(1); + + cxt.cur_ops->readlock(); + lock_is_read_held = 1; + if (WARN_ON_ONCE(lock_is_write_held)) + lrsp->n_lock_fail++; /* rare, but... */ + + lrsp->n_lock_acquired++; + cxt.cur_ops->read_delay(&rand); + lock_is_read_held = 0; + cxt.cur_ops->readunlock(); + + stutter_wait("lock_torture_reader"); + } while (!torture_must_stop()); + torture_kthread_stopping("lock_torture_reader"); + return 0; +} + +/* + * Create an lock-torture-statistics message in the specified buffer. + */ +static void __torture_print_stats(char *page, + struct lock_stress_stats *statp, bool write) +{ + bool fail = 0; + int i, n_stress; + long max = 0; + long min = statp[0].n_lock_acquired; + long long sum = 0; + + n_stress = write ? cxt.nrealwriters_stress : cxt.nrealreaders_stress; + for (i = 0; i < n_stress; i++) { + if (statp[i].n_lock_fail) + fail = true; + sum += statp[i].n_lock_acquired; + if (max < statp[i].n_lock_fail) + max = statp[i].n_lock_fail; + if (min > statp[i].n_lock_fail) + min = statp[i].n_lock_fail; + } + page += sprintf(page, + "%s: Total: %lld Max/Min: %ld/%ld %s Fail: %d %s\n", + write ? "Writes" : "Reads ", + sum, max, min, max / 2 > min ? "???" : "", + fail, fail ? "!!!" : ""); + if (fail) + atomic_inc(&cxt.n_lock_torture_errors); +} + +/* + * Print torture statistics. Caller must ensure that there is only one + * call to this function at a given time!!! This is normally accomplished + * by relying on the module system to only have one copy of the module + * loaded, and then by giving the lock_torture_stats kthread full control + * (or the init/cleanup functions when lock_torture_stats thread is not + * running). + */ +static void lock_torture_stats_print(void) +{ + int size = cxt.nrealwriters_stress * 200 + 8192; + char *buf; + + if (cxt.cur_ops->readlock) + size += cxt.nrealreaders_stress * 200 + 8192; + + buf = kmalloc(size, GFP_KERNEL); + if (!buf) { + pr_err("lock_torture_stats_print: Out of memory, need: %d", + size); + return; + } + + __torture_print_stats(buf, cxt.lwsa, true); + pr_alert("%s", buf); + kfree(buf); + + if (cxt.cur_ops->readlock) { + buf = kmalloc(size, GFP_KERNEL); + if (!buf) { + pr_err("lock_torture_stats_print: Out of memory, need: %d", + size); + return; + } + + __torture_print_stats(buf, cxt.lrsa, false); + pr_alert("%s", buf); + kfree(buf); + } +} + +/* + * Periodically prints torture statistics, if periodic statistics printing + * was specified via the stat_interval module parameter. + * + * No need to worry about fullstop here, since this one doesn't reference + * volatile state or register callbacks. + */ +static int lock_torture_stats(void *arg) +{ + VERBOSE_TOROUT_STRING("lock_torture_stats task started"); + do { + schedule_timeout_interruptible(stat_interval * HZ); + lock_torture_stats_print(); + torture_shutdown_absorb("lock_torture_stats"); + } while (!torture_must_stop()); + torture_kthread_stopping("lock_torture_stats"); + return 0; +} + +static inline void +lock_torture_print_module_parms(struct lock_torture_ops *cur_ops, + const char *tag) +{ + pr_alert("%s" TORTURE_FLAG + "--- %s%s: nwriters_stress=%d nreaders_stress=%d stat_interval=%d verbose=%d shuffle_interval=%d stutter=%d shutdown_secs=%d onoff_interval=%d onoff_holdoff=%d\n", + torture_type, tag, cxt.debug_lock ? " [debug]": "", + cxt.nrealwriters_stress, cxt.nrealreaders_stress, stat_interval, + verbose, shuffle_interval, stutter, shutdown_secs, + onoff_interval, onoff_holdoff); +} + +static void lock_torture_cleanup(void) +{ + int i; + + if (torture_cleanup_begin()) + return; + + if (writer_tasks) { + for (i = 0; i < cxt.nrealwriters_stress; i++) + torture_stop_kthread(lock_torture_writer, + writer_tasks[i]); + kfree(writer_tasks); + writer_tasks = NULL; + } + + if (reader_tasks) { + for (i = 0; i < cxt.nrealreaders_stress; i++) + torture_stop_kthread(lock_torture_reader, + reader_tasks[i]); + kfree(reader_tasks); + reader_tasks = NULL; + } + + torture_stop_kthread(lock_torture_stats, stats_task); + lock_torture_stats_print(); /* -After- the stats thread is stopped! */ + + if (atomic_read(&cxt.n_lock_torture_errors)) + lock_torture_print_module_parms(cxt.cur_ops, + "End of test: FAILURE"); + else if (torture_onoff_failures()) + lock_torture_print_module_parms(cxt.cur_ops, + "End of test: LOCK_HOTPLUG"); + else + lock_torture_print_module_parms(cxt.cur_ops, + "End of test: SUCCESS"); + torture_cleanup_end(); +} + +static int __init lock_torture_init(void) +{ + int i, j; + int firsterr = 0; + static struct lock_torture_ops *torture_ops[] = { + &lock_busted_ops, + &spin_lock_ops, &spin_lock_irq_ops, + &rw_lock_ops, &rw_lock_irq_ops, + &mutex_lock_ops, + &rwsem_lock_ops, + }; + + if (!torture_init_begin(torture_type, verbose, &torture_runnable)) + return -EBUSY; + + /* Process args and tell the world that the torturer is on the job. */ + for (i = 0; i < ARRAY_SIZE(torture_ops); i++) { + cxt.cur_ops = torture_ops[i]; + if (strcmp(torture_type, cxt.cur_ops->name) == 0) + break; + } + if (i == ARRAY_SIZE(torture_ops)) { + pr_alert("lock-torture: invalid torture type: \"%s\"\n", + torture_type); + pr_alert("lock-torture types:"); + for (i = 0; i < ARRAY_SIZE(torture_ops); i++) + pr_alert(" %s", torture_ops[i]->name); + pr_alert("\n"); + torture_init_end(); + return -EINVAL; + } + if (cxt.cur_ops->init) + cxt.cur_ops->init(); /* no "goto unwind" prior to this point!!! */ + + if (nwriters_stress >= 0) + cxt.nrealwriters_stress = nwriters_stress; + else + cxt.nrealwriters_stress = 2 * num_online_cpus(); + +#ifdef CONFIG_DEBUG_MUTEXES + if (strncmp(torture_type, "mutex", 5) == 0) + cxt.debug_lock = true; +#endif +#ifdef CONFIG_DEBUG_SPINLOCK + if ((strncmp(torture_type, "spin", 4) == 0) || + (strncmp(torture_type, "rw_lock", 7) == 0)) + cxt.debug_lock = true; +#endif + + /* Initialize the statistics so that each run gets its own numbers. */ + + lock_is_write_held = 0; + cxt.lwsa = kmalloc(sizeof(*cxt.lwsa) * cxt.nrealwriters_stress, GFP_KERNEL); + if (cxt.lwsa == NULL) { + VERBOSE_TOROUT_STRING("cxt.lwsa: Out of memory"); + firsterr = -ENOMEM; + goto unwind; + } + for (i = 0; i < cxt.nrealwriters_stress; i++) { + cxt.lwsa[i].n_lock_fail = 0; + cxt.lwsa[i].n_lock_acquired = 0; + } + + if (cxt.cur_ops->readlock) { + if (nreaders_stress >= 0) + cxt.nrealreaders_stress = nreaders_stress; + else { + /* + * By default distribute evenly the number of + * readers and writers. We still run the same number + * of threads as the writer-only locks default. + */ + if (nwriters_stress < 0) /* user doesn't care */ + cxt.nrealwriters_stress = num_online_cpus(); + cxt.nrealreaders_stress = cxt.nrealwriters_stress; + } + + lock_is_read_held = 0; + cxt.lrsa = kmalloc(sizeof(*cxt.lrsa) * cxt.nrealreaders_stress, GFP_KERNEL); + if (cxt.lrsa == NULL) { + VERBOSE_TOROUT_STRING("cxt.lrsa: Out of memory"); + firsterr = -ENOMEM; + kfree(cxt.lwsa); + goto unwind; + } + + for (i = 0; i < cxt.nrealreaders_stress; i++) { + cxt.lrsa[i].n_lock_fail = 0; + cxt.lrsa[i].n_lock_acquired = 0; + } + } + lock_torture_print_module_parms(cxt.cur_ops, "Start of test"); + + /* Prepare torture context. */ + if (onoff_interval > 0) { + firsterr = torture_onoff_init(onoff_holdoff * HZ, + onoff_interval * HZ); + if (firsterr) + goto unwind; + } + if (shuffle_interval > 0) { + firsterr = torture_shuffle_init(shuffle_interval); + if (firsterr) + goto unwind; + } + if (shutdown_secs > 0) { + firsterr = torture_shutdown_init(shutdown_secs, + lock_torture_cleanup); + if (firsterr) + goto unwind; + } + if (stutter > 0) { + firsterr = torture_stutter_init(stutter); + if (firsterr) + goto unwind; + } + + writer_tasks = kzalloc(cxt.nrealwriters_stress * sizeof(writer_tasks[0]), + GFP_KERNEL); + if (writer_tasks == NULL) { + VERBOSE_TOROUT_ERRSTRING("writer_tasks: Out of memory"); + firsterr = -ENOMEM; + goto unwind; + } + + if (cxt.cur_ops->readlock) { + reader_tasks = kzalloc(cxt.nrealreaders_stress * sizeof(reader_tasks[0]), + GFP_KERNEL); + if (reader_tasks == NULL) { + VERBOSE_TOROUT_ERRSTRING("reader_tasks: Out of memory"); + firsterr = -ENOMEM; + goto unwind; + } + } + + /* + * Create the kthreads and start torturing (oh, those poor little locks). + * + * TODO: Note that we interleave writers with readers, giving writers a + * slight advantage, by creating its kthread first. This can be modified + * for very specific needs, or even let the user choose the policy, if + * ever wanted. + */ + for (i = 0, j = 0; i < cxt.nrealwriters_stress || + j < cxt.nrealreaders_stress; i++, j++) { + if (i >= cxt.nrealwriters_stress) + goto create_reader; + + /* Create writer. */ + firsterr = torture_create_kthread(lock_torture_writer, &cxt.lwsa[i], + writer_tasks[i]); + if (firsterr) + goto unwind; + + create_reader: + if (cxt.cur_ops->readlock == NULL || (j >= cxt.nrealreaders_stress)) + continue; + /* Create reader. */ + firsterr = torture_create_kthread(lock_torture_reader, &cxt.lrsa[j], + reader_tasks[j]); + if (firsterr) + goto unwind; + } + if (stat_interval > 0) { + firsterr = torture_create_kthread(lock_torture_stats, NULL, + stats_task); + if (firsterr) + goto unwind; + } + torture_init_end(); + return 0; + +unwind: + torture_init_end(); + lock_torture_cleanup(); + return firsterr; +} + +module_init(lock_torture_init); +module_exit(lock_torture_cleanup); diff --git a/kernel/kernel/locking/mcs_spinlock.h b/kernel/kernel/locking/mcs_spinlock.h new file mode 100644 index 000000000..75e114bdf --- /dev/null +++ b/kernel/kernel/locking/mcs_spinlock.h @@ -0,0 +1,111 @@ +/* + * MCS lock defines + * + * This file contains the main data structure and API definitions of MCS lock. + * + * The MCS lock (proposed by Mellor-Crummey and Scott) is a simple spin-lock + * with the desirable properties of being fair, and with each cpu trying + * to acquire the lock spinning on a local variable. + * It avoids expensive cache bouncings that common test-and-set spin-lock + * implementations incur. + */ +#ifndef __LINUX_MCS_SPINLOCK_H +#define __LINUX_MCS_SPINLOCK_H + +#include + +struct mcs_spinlock { + struct mcs_spinlock *next; + int locked; /* 1 if lock acquired */ +}; + +#ifndef arch_mcs_spin_lock_contended +/* + * Using smp_load_acquire() provides a memory barrier that ensures + * subsequent operations happen after the lock is acquired. + */ +#define arch_mcs_spin_lock_contended(l) \ +do { \ + while (!(smp_load_acquire(l))) \ + cpu_relax_lowlatency(); \ +} while (0) +#endif + +#ifndef arch_mcs_spin_unlock_contended +/* + * smp_store_release() provides a memory barrier to ensure all + * operations in the critical section has been completed before + * unlocking. + */ +#define arch_mcs_spin_unlock_contended(l) \ + smp_store_release((l), 1) +#endif + +/* + * Note: the smp_load_acquire/smp_store_release pair is not + * sufficient to form a full memory barrier across + * cpus for many architectures (except x86) for mcs_unlock and mcs_lock. + * For applications that need a full barrier across multiple cpus + * with mcs_unlock and mcs_lock pair, smp_mb__after_unlock_lock() should be + * used after mcs_lock. + */ + +/* + * In order to acquire the lock, the caller should declare a local node and + * pass a reference of the node to this function in addition to the lock. + * If the lock has already been acquired, then this will proceed to spin + * on this node->locked until the previous lock holder sets the node->locked + * in mcs_spin_unlock(). + */ +static inline +void mcs_spin_lock(struct mcs_spinlock **lock, struct mcs_spinlock *node) +{ + struct mcs_spinlock *prev; + + /* Init node */ + node->locked = 0; + node->next = NULL; + + prev = xchg(lock, node); + if (likely(prev == NULL)) { + /* + * Lock acquired, don't need to set node->locked to 1. Threads + * only spin on its own node->locked value for lock acquisition. + * However, since this thread can immediately acquire the lock + * and does not proceed to spin on its own node->locked, this + * value won't be used. If a debug mode is needed to + * audit lock status, then set node->locked value here. + */ + return; + } + WRITE_ONCE(prev->next, node); + + /* Wait until the lock holder passes the lock down. */ + arch_mcs_spin_lock_contended(&node->locked); +} + +/* + * Releases the lock. The caller should pass in the corresponding node that + * was used to acquire the lock. + */ +static inline +void mcs_spin_unlock(struct mcs_spinlock **lock, struct mcs_spinlock *node) +{ + struct mcs_spinlock *next = READ_ONCE(node->next); + + if (likely(!next)) { + /* + * Release the lock by setting it to NULL + */ + if (likely(cmpxchg(lock, node, NULL) == node)) + return; + /* Wait until the next pointer is set */ + while (!(next = READ_ONCE(node->next))) + cpu_relax_lowlatency(); + } + + /* Pass lock to next waiter. */ + arch_mcs_spin_unlock_contended(&next->locked); +} + +#endif /* __LINUX_MCS_SPINLOCK_H */ diff --git a/kernel/kernel/locking/mutex-debug.c b/kernel/kernel/locking/mutex-debug.c new file mode 100644 index 000000000..3ef373600 --- /dev/null +++ b/kernel/kernel/locking/mutex-debug.c @@ -0,0 +1,120 @@ +/* + * kernel/mutex-debug.c + * + * Debugging code for mutexes + * + * Started by Ingo Molnar: + * + * Copyright (C) 2004, 2005, 2006 Red Hat, Inc., Ingo Molnar + * + * lock debugging, locking tree, deadlock detection started by: + * + * Copyright (C) 2004, LynuxWorks, Inc., Igor Manyilov, Bill Huey + * Released under the General Public License (GPL). + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "mutex-debug.h" + +/* + * Must be called with lock->wait_lock held. + */ +void debug_mutex_lock_common(struct mutex *lock, struct mutex_waiter *waiter) +{ + memset(waiter, MUTEX_DEBUG_INIT, sizeof(*waiter)); + waiter->magic = waiter; + INIT_LIST_HEAD(&waiter->list); +} + +void debug_mutex_wake_waiter(struct mutex *lock, struct mutex_waiter *waiter) +{ + SMP_DEBUG_LOCKS_WARN_ON(!spin_is_locked(&lock->wait_lock)); + DEBUG_LOCKS_WARN_ON(list_empty(&lock->wait_list)); + DEBUG_LOCKS_WARN_ON(waiter->magic != waiter); + DEBUG_LOCKS_WARN_ON(list_empty(&waiter->list)); +} + +void debug_mutex_free_waiter(struct mutex_waiter *waiter) +{ + DEBUG_LOCKS_WARN_ON(!list_empty(&waiter->list)); + memset(waiter, MUTEX_DEBUG_FREE, sizeof(*waiter)); +} + +void debug_mutex_add_waiter(struct mutex *lock, struct mutex_waiter *waiter, + struct thread_info *ti) +{ + SMP_DEBUG_LOCKS_WARN_ON(!spin_is_locked(&lock->wait_lock)); + + /* Mark the current thread as blocked on the lock: */ + ti->task->blocked_on = waiter; +} + +void mutex_remove_waiter(struct mutex *lock, struct mutex_waiter *waiter, + struct thread_info *ti) +{ + DEBUG_LOCKS_WARN_ON(list_empty(&waiter->list)); + DEBUG_LOCKS_WARN_ON(waiter->task != ti->task); + DEBUG_LOCKS_WARN_ON(ti->task->blocked_on != waiter); + ti->task->blocked_on = NULL; + + list_del_init(&waiter->list); + waiter->task = NULL; +} + +void debug_mutex_unlock(struct mutex *lock) +{ + if (likely(debug_locks)) { + DEBUG_LOCKS_WARN_ON(lock->magic != lock); + + if (!lock->owner) + DEBUG_LOCKS_WARN_ON(!lock->owner); + else + DEBUG_LOCKS_WARN_ON(lock->owner != current); + + DEBUG_LOCKS_WARN_ON(!lock->wait_list.prev && !lock->wait_list.next); + } + + /* + * __mutex_slowpath_needs_to_unlock() is explicitly 0 for debug + * mutexes so that we can do it here after we've verified state. + */ + mutex_clear_owner(lock); + atomic_set(&lock->count, 1); +} + +void debug_mutex_init(struct mutex *lock, const char *name, + struct lock_class_key *key) +{ +#ifdef CONFIG_DEBUG_LOCK_ALLOC + /* + * Make sure we are not reinitializing a held lock: + */ + debug_check_no_locks_freed((void *)lock, sizeof(*lock)); + lockdep_init_map(&lock->dep_map, name, key, 0); +#endif + lock->magic = lock; +} + +/*** + * mutex_destroy - mark a mutex unusable + * @lock: the mutex to be destroyed + * + * This function marks the mutex uninitialized, and any subsequent + * use of the mutex is forbidden. The mutex must not be locked when + * this function is called. + */ +void mutex_destroy(struct mutex *lock) +{ + DEBUG_LOCKS_WARN_ON(mutex_is_locked(lock)); + lock->magic = NULL; +} + +EXPORT_SYMBOL_GPL(mutex_destroy); diff --git a/kernel/kernel/locking/mutex-debug.h b/kernel/kernel/locking/mutex-debug.h new file mode 100644 index 000000000..0799fd3e4 --- /dev/null +++ b/kernel/kernel/locking/mutex-debug.h @@ -0,0 +1,55 @@ +/* + * Mutexes: blocking mutual exclusion locks + * + * started by Ingo Molnar: + * + * Copyright (C) 2004, 2005, 2006 Red Hat, Inc., Ingo Molnar + * + * This file contains mutex debugging related internal declarations, + * prototypes and inline functions, for the CONFIG_DEBUG_MUTEXES case. + * More details are in kernel/mutex-debug.c. + */ + +/* + * This must be called with lock->wait_lock held. + */ +extern void debug_mutex_lock_common(struct mutex *lock, + struct mutex_waiter *waiter); +extern void debug_mutex_wake_waiter(struct mutex *lock, + struct mutex_waiter *waiter); +extern void debug_mutex_free_waiter(struct mutex_waiter *waiter); +extern void debug_mutex_add_waiter(struct mutex *lock, + struct mutex_waiter *waiter, + struct thread_info *ti); +extern void mutex_remove_waiter(struct mutex *lock, struct mutex_waiter *waiter, + struct thread_info *ti); +extern void debug_mutex_unlock(struct mutex *lock); +extern void debug_mutex_init(struct mutex *lock, const char *name, + struct lock_class_key *key); + +static inline void mutex_set_owner(struct mutex *lock) +{ + lock->owner = current; +} + +static inline void mutex_clear_owner(struct mutex *lock) +{ + lock->owner = NULL; +} + +#define spin_lock_mutex(lock, flags) \ + do { \ + struct mutex *l = container_of(lock, struct mutex, wait_lock); \ + \ + DEBUG_LOCKS_WARN_ON(in_interrupt()); \ + local_irq_save(flags); \ + arch_spin_lock(&(lock)->rlock.raw_lock);\ + DEBUG_LOCKS_WARN_ON(l->magic != l); \ + } while (0) + +#define spin_unlock_mutex(lock, flags) \ + do { \ + arch_spin_unlock(&(lock)->rlock.raw_lock); \ + local_irq_restore(flags); \ + preempt_check_resched(); \ + } while (0) diff --git a/kernel/kernel/locking/mutex.c b/kernel/kernel/locking/mutex.c new file mode 100644 index 000000000..4cccea6b8 --- /dev/null +++ b/kernel/kernel/locking/mutex.c @@ -0,0 +1,972 @@ +/* + * kernel/locking/mutex.c + * + * Mutexes: blocking mutual exclusion locks + * + * Started by Ingo Molnar: + * + * Copyright (C) 2004, 2005, 2006 Red Hat, Inc., Ingo Molnar + * + * Many thanks to Arjan van de Ven, Thomas Gleixner, Steven Rostedt and + * David Howells for suggestions and improvements. + * + * - Adaptive spinning for mutexes by Peter Zijlstra. (Ported to mainline + * from the -rt tree, where it was originally implemented for rtmutexes + * by Steven Rostedt, based on work by Gregory Haskins, Peter Morreale + * and Sven Dietrich. + * + * Also see Documentation/locking/mutex-design.txt. + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include + +/* + * In the DEBUG case we are using the "NULL fastpath" for mutexes, + * which forces all calls into the slowpath: + */ +#ifdef CONFIG_DEBUG_MUTEXES +# include "mutex-debug.h" +# include +/* + * Must be 0 for the debug case so we do not do the unlock outside of the + * wait_lock region. debug_mutex_unlock() will do the actual unlock in this + * case. + */ +# undef __mutex_slowpath_needs_to_unlock +# define __mutex_slowpath_needs_to_unlock() 0 +#else +# include "mutex.h" +# include +#endif + +void +__mutex_init(struct mutex *lock, const char *name, struct lock_class_key *key) +{ + atomic_set(&lock->count, 1); + spin_lock_init(&lock->wait_lock); + INIT_LIST_HEAD(&lock->wait_list); + mutex_clear_owner(lock); +#ifdef CONFIG_MUTEX_SPIN_ON_OWNER + osq_lock_init(&lock->osq); +#endif + + debug_mutex_init(lock, name, key); +} + +EXPORT_SYMBOL(__mutex_init); + +#ifndef CONFIG_DEBUG_LOCK_ALLOC +/* + * We split the mutex lock/unlock logic into separate fastpath and + * slowpath functions, to reduce the register pressure on the fastpath. + * We also put the fastpath first in the kernel image, to make sure the + * branch is predicted by the CPU as default-untaken. + */ +__visible void __sched __mutex_lock_slowpath(atomic_t *lock_count); + +/** + * mutex_lock - acquire the mutex + * @lock: the mutex to be acquired + * + * Lock the mutex exclusively for this task. If the mutex is not + * available right now, it will sleep until it can get it. + * + * The mutex must later on be released by the same task that + * acquired it. Recursive locking is not allowed. The task + * may not exit without first unlocking the mutex. Also, kernel + * memory where the mutex resides must not be freed with + * the mutex still locked. The mutex must first be initialized + * (or statically defined) before it can be locked. memset()-ing + * the mutex to 0 is not allowed. + * + * ( The CONFIG_DEBUG_MUTEXES .config option turns on debugging + * checks that will enforce the restrictions and will also do + * deadlock debugging. ) + * + * This function is similar to (but not equivalent to) down(). + */ +void __sched mutex_lock(struct mutex *lock) +{ + might_sleep(); + /* + * The locking fastpath is the 1->0 transition from + * 'unlocked' into 'locked' state. + */ + __mutex_fastpath_lock(&lock->count, __mutex_lock_slowpath); + mutex_set_owner(lock); +} + +EXPORT_SYMBOL(mutex_lock); +#endif + +static __always_inline void ww_mutex_lock_acquired(struct ww_mutex *ww, + struct ww_acquire_ctx *ww_ctx) +{ +#ifdef CONFIG_DEBUG_MUTEXES + /* + * If this WARN_ON triggers, you used ww_mutex_lock to acquire, + * but released with a normal mutex_unlock in this call. + * + * This should never happen, always use ww_mutex_unlock. + */ + DEBUG_LOCKS_WARN_ON(ww->ctx); + + /* + * Not quite done after calling ww_acquire_done() ? + */ + DEBUG_LOCKS_WARN_ON(ww_ctx->done_acquire); + + if (ww_ctx->contending_lock) { + /* + * After -EDEADLK you tried to + * acquire a different ww_mutex? Bad! + */ + DEBUG_LOCKS_WARN_ON(ww_ctx->contending_lock != ww); + + /* + * You called ww_mutex_lock after receiving -EDEADLK, + * but 'forgot' to unlock everything else first? + */ + DEBUG_LOCKS_WARN_ON(ww_ctx->acquired > 0); + ww_ctx->contending_lock = NULL; + } + + /* + * Naughty, using a different class will lead to undefined behavior! + */ + DEBUG_LOCKS_WARN_ON(ww_ctx->ww_class != ww->ww_class); +#endif + ww_ctx->acquired++; +} + +/* + * After acquiring lock with fastpath or when we lost out in contested + * slowpath, set ctx and wake up any waiters so they can recheck. + * + * This function is never called when CONFIG_DEBUG_LOCK_ALLOC is set, + * as the fastpath and opportunistic spinning are disabled in that case. + */ +static __always_inline void +ww_mutex_set_context_fastpath(struct ww_mutex *lock, + struct ww_acquire_ctx *ctx) +{ + unsigned long flags; + struct mutex_waiter *cur; + + ww_mutex_lock_acquired(lock, ctx); + + lock->ctx = ctx; + + /* + * The lock->ctx update should be visible on all cores before + * the atomic read is done, otherwise contended waiters might be + * missed. The contended waiters will either see ww_ctx == NULL + * and keep spinning, or it will acquire wait_lock, add itself + * to waiter list and sleep. + */ + smp_mb(); /* ^^^ */ + + /* + * Check if lock is contended, if not there is nobody to wake up + */ + if (likely(atomic_read(&lock->base.count) == 0)) + return; + + /* + * Uh oh, we raced in fastpath, wake up everyone in this case, + * so they can see the new lock->ctx. + */ + spin_lock_mutex(&lock->base.wait_lock, flags); + list_for_each_entry(cur, &lock->base.wait_list, list) { + debug_mutex_wake_waiter(&lock->base, cur); + wake_up_process(cur->task); + } + spin_unlock_mutex(&lock->base.wait_lock, flags); +} + +/* + * After acquiring lock in the slowpath set ctx and wake up any + * waiters so they can recheck. + * + * Callers must hold the mutex wait_lock. + */ +static __always_inline void +ww_mutex_set_context_slowpath(struct ww_mutex *lock, + struct ww_acquire_ctx *ctx) +{ + struct mutex_waiter *cur; + + ww_mutex_lock_acquired(lock, ctx); + lock->ctx = ctx; + + /* + * Give any possible sleeping processes the chance to wake up, + * so they can recheck if they have to back off. + */ + list_for_each_entry(cur, &lock->base.wait_list, list) { + debug_mutex_wake_waiter(&lock->base, cur); + wake_up_process(cur->task); + } +} + +#ifdef CONFIG_MUTEX_SPIN_ON_OWNER +/* + * Look out! "owner" is an entirely speculative pointer + * access and not reliable. + */ +static noinline +bool mutex_spin_on_owner(struct mutex *lock, struct task_struct *owner) +{ + bool ret = true; + + rcu_read_lock(); + while (lock->owner == owner) { + /* + * Ensure we emit the owner->on_cpu, dereference _after_ + * checking lock->owner still matches owner. If that fails, + * owner might point to freed memory. If it still matches, + * the rcu_read_lock() ensures the memory stays valid. + */ + barrier(); + + if (!owner->on_cpu || need_resched()) { + ret = false; + break; + } + + cpu_relax_lowlatency(); + } + rcu_read_unlock(); + + return ret; +} + +/* + * Initial check for entering the mutex spinning loop + */ +static inline int mutex_can_spin_on_owner(struct mutex *lock) +{ + struct task_struct *owner; + int retval = 1; + + if (need_resched()) + return 0; + + rcu_read_lock(); + owner = READ_ONCE(lock->owner); + if (owner) + retval = owner->on_cpu; + rcu_read_unlock(); + /* + * if lock->owner is not set, the mutex owner may have just acquired + * it and not set the owner yet or the mutex has been released. + */ + return retval; +} + +/* + * Atomically try to take the lock when it is available + */ +static inline bool mutex_try_to_acquire(struct mutex *lock) +{ + return !mutex_is_locked(lock) && + (atomic_cmpxchg(&lock->count, 1, 0) == 1); +} + +/* + * Optimistic spinning. + * + * We try to spin for acquisition when we find that the lock owner + * is currently running on a (different) CPU and while we don't + * need to reschedule. The rationale is that if the lock owner is + * running, it is likely to release the lock soon. + * + * Since this needs the lock owner, and this mutex implementation + * doesn't track the owner atomically in the lock field, we need to + * track it non-atomically. + * + * We can't do this for DEBUG_MUTEXES because that relies on wait_lock + * to serialize everything. + * + * The mutex spinners are queued up using MCS lock so that only one + * spinner can compete for the mutex. However, if mutex spinning isn't + * going to happen, there is no point in going through the lock/unlock + * overhead. + * + * Returns true when the lock was taken, otherwise false, indicating + * that we need to jump to the slowpath and sleep. + */ +static bool mutex_optimistic_spin(struct mutex *lock, + struct ww_acquire_ctx *ww_ctx, const bool use_ww_ctx) +{ + struct task_struct *task = current; + + if (!mutex_can_spin_on_owner(lock)) + goto done; + + /* + * In order to avoid a stampede of mutex spinners trying to + * acquire the mutex all at once, the spinners need to take a + * MCS (queued) lock first before spinning on the owner field. + */ + if (!osq_lock(&lock->osq)) + goto done; + + while (true) { + struct task_struct *owner; + + if (use_ww_ctx && ww_ctx->acquired > 0) { + struct ww_mutex *ww; + + ww = container_of(lock, struct ww_mutex, base); + /* + * If ww->ctx is set the contents are undefined, only + * by acquiring wait_lock there is a guarantee that + * they are not invalid when reading. + * + * As such, when deadlock detection needs to be + * performed the optimistic spinning cannot be done. + */ + if (READ_ONCE(ww->ctx)) + break; + } + + /* + * If there's an owner, wait for it to either + * release the lock or go to sleep. + */ + owner = READ_ONCE(lock->owner); + if (owner && !mutex_spin_on_owner(lock, owner)) + break; + + /* Try to acquire the mutex if it is unlocked. */ + if (mutex_try_to_acquire(lock)) { + lock_acquired(&lock->dep_map, ip); + + if (use_ww_ctx) { + struct ww_mutex *ww; + ww = container_of(lock, struct ww_mutex, base); + + ww_mutex_set_context_fastpath(ww, ww_ctx); + } + + mutex_set_owner(lock); + osq_unlock(&lock->osq); + return true; + } + + /* + * When there's no owner, we might have preempted between the + * owner acquiring the lock and setting the owner field. If + * we're an RT task that will live-lock because we won't let + * the owner complete. + */ + if (!owner && (need_resched() || rt_task(task))) + break; + + /* + * The cpu_relax() call is a compiler barrier which forces + * everything in this loop to be re-loaded. We don't need + * memory barriers as we'll eventually observe the right + * values at the cost of a few extra spins. + */ + cpu_relax_lowlatency(); + } + + osq_unlock(&lock->osq); +done: + /* + * If we fell out of the spin path because of need_resched(), + * reschedule now, before we try-lock the mutex. This avoids getting + * scheduled out right after we obtained the mutex. + */ + if (need_resched()) { + /* + * We _should_ have TASK_RUNNING here, but just in case + * we do not, make it so, otherwise we might get stuck. + */ + __set_current_state(TASK_RUNNING); + schedule_preempt_disabled(); + } + + return false; +} +#else +static bool mutex_optimistic_spin(struct mutex *lock, + struct ww_acquire_ctx *ww_ctx, const bool use_ww_ctx) +{ + return false; +} +#endif + +__visible __used noinline +void __sched __mutex_unlock_slowpath(atomic_t *lock_count); + +/** + * mutex_unlock - release the mutex + * @lock: the mutex to be released + * + * Unlock a mutex that has been locked by this task previously. + * + * This function must not be used in interrupt context. Unlocking + * of a not locked mutex is not allowed. + * + * This function is similar to (but not equivalent to) up(). + */ +void __sched mutex_unlock(struct mutex *lock) +{ + /* + * The unlocking fastpath is the 0->1 transition from 'locked' + * into 'unlocked' state: + */ +#ifndef CONFIG_DEBUG_MUTEXES + /* + * When debugging is enabled we must not clear the owner before time, + * the slow path will always be taken, and that clears the owner field + * after verifying that it was indeed current. + */ + mutex_clear_owner(lock); +#endif + __mutex_fastpath_unlock(&lock->count, __mutex_unlock_slowpath); +} + +EXPORT_SYMBOL(mutex_unlock); + +/** + * ww_mutex_unlock - release the w/w mutex + * @lock: the mutex to be released + * + * Unlock a mutex that has been locked by this task previously with any of the + * ww_mutex_lock* functions (with or without an acquire context). It is + * forbidden to release the locks after releasing the acquire context. + * + * This function must not be used in interrupt context. Unlocking + * of a unlocked mutex is not allowed. + */ +void __sched ww_mutex_unlock(struct ww_mutex *lock) +{ + /* + * The unlocking fastpath is the 0->1 transition from 'locked' + * into 'unlocked' state: + */ + if (lock->ctx) { +#ifdef CONFIG_DEBUG_MUTEXES + DEBUG_LOCKS_WARN_ON(!lock->ctx->acquired); +#endif + if (lock->ctx->acquired > 0) + lock->ctx->acquired--; + lock->ctx = NULL; + } + +#ifndef CONFIG_DEBUG_MUTEXES + /* + * When debugging is enabled we must not clear the owner before time, + * the slow path will always be taken, and that clears the owner field + * after verifying that it was indeed current. + */ + mutex_clear_owner(&lock->base); +#endif + __mutex_fastpath_unlock(&lock->base.count, __mutex_unlock_slowpath); +} +EXPORT_SYMBOL(ww_mutex_unlock); + +static inline int __sched +__ww_mutex_lock_check_stamp(struct mutex *lock, struct ww_acquire_ctx *ctx) +{ + struct ww_mutex *ww = container_of(lock, struct ww_mutex, base); + struct ww_acquire_ctx *hold_ctx = READ_ONCE(ww->ctx); + + if (!hold_ctx) + return 0; + + if (unlikely(ctx == hold_ctx)) + return -EALREADY; + + if (ctx->stamp - hold_ctx->stamp <= LONG_MAX && + (ctx->stamp != hold_ctx->stamp || ctx > hold_ctx)) { +#ifdef CONFIG_DEBUG_MUTEXES + DEBUG_LOCKS_WARN_ON(ctx->contending_lock); + ctx->contending_lock = ww; +#endif + return -EDEADLK; + } + + return 0; +} + +/* + * Lock a mutex (possibly interruptible), slowpath: + */ +static __always_inline int __sched +__mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, + struct lockdep_map *nest_lock, unsigned long ip, + struct ww_acquire_ctx *ww_ctx, const bool use_ww_ctx) +{ + struct task_struct *task = current; + struct mutex_waiter waiter; + unsigned long flags; + int ret; + + preempt_disable(); + mutex_acquire_nest(&lock->dep_map, subclass, 0, nest_lock, ip); + + if (mutex_optimistic_spin(lock, ww_ctx, use_ww_ctx)) { + /* got the lock, yay! */ + preempt_enable(); + return 0; + } + + spin_lock_mutex(&lock->wait_lock, flags); + + /* + * Once more, try to acquire the lock. Only try-lock the mutex if + * it is unlocked to reduce unnecessary xchg() operations. + */ + if (!mutex_is_locked(lock) && (atomic_xchg(&lock->count, 0) == 1)) + goto skip_wait; + + debug_mutex_lock_common(lock, &waiter); + debug_mutex_add_waiter(lock, &waiter, task_thread_info(task)); + + /* add waiting tasks to the end of the waitqueue (FIFO): */ + list_add_tail(&waiter.list, &lock->wait_list); + waiter.task = task; + + lock_contended(&lock->dep_map, ip); + + for (;;) { + /* + * Lets try to take the lock again - this is needed even if + * we get here for the first time (shortly after failing to + * acquire the lock), to make sure that we get a wakeup once + * it's unlocked. Later on, if we sleep, this is the + * operation that gives us the lock. We xchg it to -1, so + * that when we release the lock, we properly wake up the + * other waiters. We only attempt the xchg if the count is + * non-negative in order to avoid unnecessary xchg operations: + */ + if (atomic_read(&lock->count) >= 0 && + (atomic_xchg(&lock->count, -1) == 1)) + break; + + /* + * got a signal? (This code gets eliminated in the + * TASK_UNINTERRUPTIBLE case.) + */ + if (unlikely(signal_pending_state(state, task))) { + ret = -EINTR; + goto err; + } + + if (use_ww_ctx && ww_ctx->acquired > 0) { + ret = __ww_mutex_lock_check_stamp(lock, ww_ctx); + if (ret) + goto err; + } + + __set_task_state(task, state); + + /* didn't get the lock, go to sleep: */ + spin_unlock_mutex(&lock->wait_lock, flags); + schedule_preempt_disabled(); + spin_lock_mutex(&lock->wait_lock, flags); + } + __set_task_state(task, TASK_RUNNING); + + mutex_remove_waiter(lock, &waiter, current_thread_info()); + /* set it to 0 if there are no waiters left: */ + if (likely(list_empty(&lock->wait_list))) + atomic_set(&lock->count, 0); + debug_mutex_free_waiter(&waiter); + +skip_wait: + /* got the lock - cleanup and rejoice! */ + lock_acquired(&lock->dep_map, ip); + mutex_set_owner(lock); + + if (use_ww_ctx) { + struct ww_mutex *ww = container_of(lock, struct ww_mutex, base); + ww_mutex_set_context_slowpath(ww, ww_ctx); + } + + spin_unlock_mutex(&lock->wait_lock, flags); + preempt_enable(); + return 0; + +err: + mutex_remove_waiter(lock, &waiter, task_thread_info(task)); + spin_unlock_mutex(&lock->wait_lock, flags); + debug_mutex_free_waiter(&waiter); + mutex_release(&lock->dep_map, 1, ip); + preempt_enable(); + return ret; +} + +#ifdef CONFIG_DEBUG_LOCK_ALLOC +void __sched +mutex_lock_nested(struct mutex *lock, unsigned int subclass) +{ + might_sleep(); + __mutex_lock_common(lock, TASK_UNINTERRUPTIBLE, + subclass, NULL, _RET_IP_, NULL, 0); +} + +EXPORT_SYMBOL_GPL(mutex_lock_nested); + +void __sched +_mutex_lock_nest_lock(struct mutex *lock, struct lockdep_map *nest) +{ + might_sleep(); + __mutex_lock_common(lock, TASK_UNINTERRUPTIBLE, + 0, nest, _RET_IP_, NULL, 0); +} + +EXPORT_SYMBOL_GPL(_mutex_lock_nest_lock); + +int __sched +mutex_lock_killable_nested(struct mutex *lock, unsigned int subclass) +{ + might_sleep(); + return __mutex_lock_common(lock, TASK_KILLABLE, + subclass, NULL, _RET_IP_, NULL, 0); +} +EXPORT_SYMBOL_GPL(mutex_lock_killable_nested); + +int __sched +mutex_lock_interruptible_nested(struct mutex *lock, unsigned int subclass) +{ + might_sleep(); + return __mutex_lock_common(lock, TASK_INTERRUPTIBLE, + subclass, NULL, _RET_IP_, NULL, 0); +} + +EXPORT_SYMBOL_GPL(mutex_lock_interruptible_nested); + +static inline int +ww_mutex_deadlock_injection(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) +{ +#ifdef CONFIG_DEBUG_WW_MUTEX_SLOWPATH + unsigned tmp; + + if (ctx->deadlock_inject_countdown-- == 0) { + tmp = ctx->deadlock_inject_interval; + if (tmp > UINT_MAX/4) + tmp = UINT_MAX; + else + tmp = tmp*2 + tmp + tmp/2; + + ctx->deadlock_inject_interval = tmp; + ctx->deadlock_inject_countdown = tmp; + ctx->contending_lock = lock; + + ww_mutex_unlock(lock); + + return -EDEADLK; + } +#endif + + return 0; +} + +int __sched +__ww_mutex_lock(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) +{ + int ret; + + might_sleep(); + ret = __mutex_lock_common(&lock->base, TASK_UNINTERRUPTIBLE, + 0, &ctx->dep_map, _RET_IP_, ctx, 1); + if (!ret && ctx->acquired > 1) + return ww_mutex_deadlock_injection(lock, ctx); + + return ret; +} +EXPORT_SYMBOL_GPL(__ww_mutex_lock); + +int __sched +__ww_mutex_lock_interruptible(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) +{ + int ret; + + might_sleep(); + ret = __mutex_lock_common(&lock->base, TASK_INTERRUPTIBLE, + 0, &ctx->dep_map, _RET_IP_, ctx, 1); + + if (!ret && ctx->acquired > 1) + return ww_mutex_deadlock_injection(lock, ctx); + + return ret; +} +EXPORT_SYMBOL_GPL(__ww_mutex_lock_interruptible); + +#endif + +/* + * Release the lock, slowpath: + */ +static inline void +__mutex_unlock_common_slowpath(struct mutex *lock, int nested) +{ + unsigned long flags; + + /* + * As a performance measurement, release the lock before doing other + * wakeup related duties to follow. This allows other tasks to acquire + * the lock sooner, while still handling cleanups in past unlock calls. + * This can be done as we do not enforce strict equivalence between the + * mutex counter and wait_list. + * + * + * Some architectures leave the lock unlocked in the fastpath failure + * case, others need to leave it locked. In the later case we have to + * unlock it here - as the lock counter is currently 0 or negative. + */ + if (__mutex_slowpath_needs_to_unlock()) + atomic_set(&lock->count, 1); + + spin_lock_mutex(&lock->wait_lock, flags); + mutex_release(&lock->dep_map, nested, _RET_IP_); + debug_mutex_unlock(lock); + + if (!list_empty(&lock->wait_list)) { + /* get the first entry from the wait-list: */ + struct mutex_waiter *waiter = + list_entry(lock->wait_list.next, + struct mutex_waiter, list); + + debug_mutex_wake_waiter(lock, waiter); + + wake_up_process(waiter->task); + } + + spin_unlock_mutex(&lock->wait_lock, flags); +} + +/* + * Release the lock, slowpath: + */ +__visible void +__mutex_unlock_slowpath(atomic_t *lock_count) +{ + struct mutex *lock = container_of(lock_count, struct mutex, count); + + __mutex_unlock_common_slowpath(lock, 1); +} + +#ifndef CONFIG_DEBUG_LOCK_ALLOC +/* + * Here come the less common (and hence less performance-critical) APIs: + * mutex_lock_interruptible() and mutex_trylock(). + */ +static noinline int __sched +__mutex_lock_killable_slowpath(struct mutex *lock); + +static noinline int __sched +__mutex_lock_interruptible_slowpath(struct mutex *lock); + +/** + * mutex_lock_interruptible - acquire the mutex, interruptible + * @lock: the mutex to be acquired + * + * Lock the mutex like mutex_lock(), and return 0 if the mutex has + * been acquired or sleep until the mutex becomes available. If a + * signal arrives while waiting for the lock then this function + * returns -EINTR. + * + * This function is similar to (but not equivalent to) down_interruptible(). + */ +int __sched mutex_lock_interruptible(struct mutex *lock) +{ + int ret; + + might_sleep(); + ret = __mutex_fastpath_lock_retval(&lock->count); + if (likely(!ret)) { + mutex_set_owner(lock); + return 0; + } else + return __mutex_lock_interruptible_slowpath(lock); +} + +EXPORT_SYMBOL(mutex_lock_interruptible); + +int __sched mutex_lock_killable(struct mutex *lock) +{ + int ret; + + might_sleep(); + ret = __mutex_fastpath_lock_retval(&lock->count); + if (likely(!ret)) { + mutex_set_owner(lock); + return 0; + } else + return __mutex_lock_killable_slowpath(lock); +} +EXPORT_SYMBOL(mutex_lock_killable); + +__visible void __sched +__mutex_lock_slowpath(atomic_t *lock_count) +{ + struct mutex *lock = container_of(lock_count, struct mutex, count); + + __mutex_lock_common(lock, TASK_UNINTERRUPTIBLE, 0, + NULL, _RET_IP_, NULL, 0); +} + +static noinline int __sched +__mutex_lock_killable_slowpath(struct mutex *lock) +{ + return __mutex_lock_common(lock, TASK_KILLABLE, 0, + NULL, _RET_IP_, NULL, 0); +} + +static noinline int __sched +__mutex_lock_interruptible_slowpath(struct mutex *lock) +{ + return __mutex_lock_common(lock, TASK_INTERRUPTIBLE, 0, + NULL, _RET_IP_, NULL, 0); +} + +static noinline int __sched +__ww_mutex_lock_slowpath(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) +{ + return __mutex_lock_common(&lock->base, TASK_UNINTERRUPTIBLE, 0, + NULL, _RET_IP_, ctx, 1); +} + +static noinline int __sched +__ww_mutex_lock_interruptible_slowpath(struct ww_mutex *lock, + struct ww_acquire_ctx *ctx) +{ + return __mutex_lock_common(&lock->base, TASK_INTERRUPTIBLE, 0, + NULL, _RET_IP_, ctx, 1); +} + +#endif + +/* + * Spinlock based trylock, we take the spinlock and check whether we + * can get the lock: + */ +static inline int __mutex_trylock_slowpath(atomic_t *lock_count) +{ + struct mutex *lock = container_of(lock_count, struct mutex, count); + unsigned long flags; + int prev; + + /* No need to trylock if the mutex is locked. */ + if (mutex_is_locked(lock)) + return 0; + + spin_lock_mutex(&lock->wait_lock, flags); + + prev = atomic_xchg(&lock->count, -1); + if (likely(prev == 1)) { + mutex_set_owner(lock); + mutex_acquire(&lock->dep_map, 0, 1, _RET_IP_); + } + + /* Set it back to 0 if there are no waiters: */ + if (likely(list_empty(&lock->wait_list))) + atomic_set(&lock->count, 0); + + spin_unlock_mutex(&lock->wait_lock, flags); + + return prev == 1; +} + +/** + * mutex_trylock - try to acquire the mutex, without waiting + * @lock: the mutex to be acquired + * + * Try to acquire the mutex atomically. Returns 1 if the mutex + * has been acquired successfully, and 0 on contention. + * + * NOTE: this function follows the spin_trylock() convention, so + * it is negated from the down_trylock() return values! Be careful + * about this when converting semaphore users to mutexes. + * + * This function must not be used in interrupt context. The + * mutex must be released by the same task that acquired it. + */ +int __sched mutex_trylock(struct mutex *lock) +{ + int ret; + + ret = __mutex_fastpath_trylock(&lock->count, __mutex_trylock_slowpath); + if (ret) + mutex_set_owner(lock); + + return ret; +} +EXPORT_SYMBOL(mutex_trylock); + +#ifndef CONFIG_DEBUG_LOCK_ALLOC +int __sched +__ww_mutex_lock(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) +{ + int ret; + + might_sleep(); + + ret = __mutex_fastpath_lock_retval(&lock->base.count); + + if (likely(!ret)) { + ww_mutex_set_context_fastpath(lock, ctx); + mutex_set_owner(&lock->base); + } else + ret = __ww_mutex_lock_slowpath(lock, ctx); + return ret; +} +EXPORT_SYMBOL(__ww_mutex_lock); + +int __sched +__ww_mutex_lock_interruptible(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) +{ + int ret; + + might_sleep(); + + ret = __mutex_fastpath_lock_retval(&lock->base.count); + + if (likely(!ret)) { + ww_mutex_set_context_fastpath(lock, ctx); + mutex_set_owner(&lock->base); + } else + ret = __ww_mutex_lock_interruptible_slowpath(lock, ctx); + return ret; +} +EXPORT_SYMBOL(__ww_mutex_lock_interruptible); + +#endif + +/** + * atomic_dec_and_mutex_lock - return holding mutex if we dec to 0 + * @cnt: the atomic which we are to dec + * @lock: the mutex to return holding if we dec to 0 + * + * return true and hold lock if we dec to 0, return false otherwise + */ +int atomic_dec_and_mutex_lock(atomic_t *cnt, struct mutex *lock) +{ + /* dec if we can't possibly hit 0 */ + if (atomic_add_unless(cnt, -1, 1)) + return 0; + /* we might hit 0, so take the lock */ + mutex_lock(lock); + if (!atomic_dec_and_test(cnt)) { + /* when we actually did the dec, we didn't hit 0 */ + mutex_unlock(lock); + return 0; + } + /* we hit 0, and we hold the lock */ + return 1; +} +EXPORT_SYMBOL(atomic_dec_and_mutex_lock); diff --git a/kernel/kernel/locking/mutex.h b/kernel/kernel/locking/mutex.h new file mode 100644 index 000000000..5cda39760 --- /dev/null +++ b/kernel/kernel/locking/mutex.h @@ -0,0 +1,48 @@ +/* + * Mutexes: blocking mutual exclusion locks + * + * started by Ingo Molnar: + * + * Copyright (C) 2004, 2005, 2006 Red Hat, Inc., Ingo Molnar + * + * This file contains mutex debugging related internal prototypes, for the + * !CONFIG_DEBUG_MUTEXES case. Most of them are NOPs: + */ + +#define spin_lock_mutex(lock, flags) \ + do { spin_lock(lock); (void)(flags); } while (0) +#define spin_unlock_mutex(lock, flags) \ + do { spin_unlock(lock); (void)(flags); } while (0) +#define mutex_remove_waiter(lock, waiter, ti) \ + __list_del((waiter)->list.prev, (waiter)->list.next) + +#ifdef CONFIG_MUTEX_SPIN_ON_OWNER +static inline void mutex_set_owner(struct mutex *lock) +{ + lock->owner = current; +} + +static inline void mutex_clear_owner(struct mutex *lock) +{ + lock->owner = NULL; +} +#else +static inline void mutex_set_owner(struct mutex *lock) +{ +} + +static inline void mutex_clear_owner(struct mutex *lock) +{ +} +#endif + +#define debug_mutex_wake_waiter(lock, waiter) do { } while (0) +#define debug_mutex_free_waiter(waiter) do { } while (0) +#define debug_mutex_add_waiter(lock, waiter, ti) do { } while (0) +#define debug_mutex_unlock(lock) do { } while (0) +#define debug_mutex_init(lock, name, key) do { } while (0) + +static inline void +debug_mutex_lock_common(struct mutex *lock, struct mutex_waiter *waiter) +{ +} diff --git a/kernel/kernel/locking/osq_lock.c b/kernel/kernel/locking/osq_lock.c new file mode 100644 index 000000000..dc85ee23a --- /dev/null +++ b/kernel/kernel/locking/osq_lock.c @@ -0,0 +1,203 @@ +#include +#include +#include + +/* + * An MCS like lock especially tailored for optimistic spinning for sleeping + * lock implementations (mutex, rwsem, etc). + * + * Using a single mcs node per CPU is safe because sleeping locks should not be + * called from interrupt context and we have preemption disabled while + * spinning. + */ +static DEFINE_PER_CPU_SHARED_ALIGNED(struct optimistic_spin_node, osq_node); + +/* + * We use the value 0 to represent "no CPU", thus the encoded value + * will be the CPU number incremented by 1. + */ +static inline int encode_cpu(int cpu_nr) +{ + return cpu_nr + 1; +} + +static inline struct optimistic_spin_node *decode_cpu(int encoded_cpu_val) +{ + int cpu_nr = encoded_cpu_val - 1; + + return per_cpu_ptr(&osq_node, cpu_nr); +} + +/* + * Get a stable @node->next pointer, either for unlock() or unqueue() purposes. + * Can return NULL in case we were the last queued and we updated @lock instead. + */ +static inline struct optimistic_spin_node * +osq_wait_next(struct optimistic_spin_queue *lock, + struct optimistic_spin_node *node, + struct optimistic_spin_node *prev) +{ + struct optimistic_spin_node *next = NULL; + int curr = encode_cpu(smp_processor_id()); + int old; + + /* + * If there is a prev node in queue, then the 'old' value will be + * the prev node's CPU #, else it's set to OSQ_UNLOCKED_VAL since if + * we're currently last in queue, then the queue will then become empty. + */ + old = prev ? prev->cpu : OSQ_UNLOCKED_VAL; + + for (;;) { + if (atomic_read(&lock->tail) == curr && + atomic_cmpxchg(&lock->tail, curr, old) == curr) { + /* + * We were the last queued, we moved @lock back. @prev + * will now observe @lock and will complete its + * unlock()/unqueue(). + */ + break; + } + + /* + * We must xchg() the @node->next value, because if we were to + * leave it in, a concurrent unlock()/unqueue() from + * @node->next might complete Step-A and think its @prev is + * still valid. + * + * If the concurrent unlock()/unqueue() wins the race, we'll + * wait for either @lock to point to us, through its Step-B, or + * wait for a new @node->next from its Step-C. + */ + if (node->next) { + next = xchg(&node->next, NULL); + if (next) + break; + } + + cpu_relax_lowlatency(); + } + + return next; +} + +bool osq_lock(struct optimistic_spin_queue *lock) +{ + struct optimistic_spin_node *node = this_cpu_ptr(&osq_node); + struct optimistic_spin_node *prev, *next; + int curr = encode_cpu(smp_processor_id()); + int old; + + node->locked = 0; + node->next = NULL; + node->cpu = curr; + + old = atomic_xchg(&lock->tail, curr); + if (old == OSQ_UNLOCKED_VAL) + return true; + + prev = decode_cpu(old); + node->prev = prev; + WRITE_ONCE(prev->next, node); + + /* + * Normally @prev is untouchable after the above store; because at that + * moment unlock can proceed and wipe the node element from stack. + * + * However, since our nodes are static per-cpu storage, we're + * guaranteed their existence -- this allows us to apply + * cmpxchg in an attempt to undo our queueing. + */ + + while (!READ_ONCE(node->locked)) { + /* + * If we need to reschedule bail... so we can block. + */ + if (need_resched()) + goto unqueue; + + cpu_relax_lowlatency(); + } + return true; + +unqueue: + /* + * Step - A -- stabilize @prev + * + * Undo our @prev->next assignment; this will make @prev's + * unlock()/unqueue() wait for a next pointer since @lock points to us + * (or later). + */ + + for (;;) { + if (prev->next == node && + cmpxchg(&prev->next, node, NULL) == node) + break; + + /* + * We can only fail the cmpxchg() racing against an unlock(), + * in which case we should observe @node->locked becomming + * true. + */ + if (smp_load_acquire(&node->locked)) + return true; + + cpu_relax_lowlatency(); + + /* + * Or we race against a concurrent unqueue()'s step-B, in which + * case its step-C will write us a new @node->prev pointer. + */ + prev = READ_ONCE(node->prev); + } + + /* + * Step - B -- stabilize @next + * + * Similar to unlock(), wait for @node->next or move @lock from @node + * back to @prev. + */ + + next = osq_wait_next(lock, node, prev); + if (!next) + return false; + + /* + * Step - C -- unlink + * + * @prev is stable because its still waiting for a new @prev->next + * pointer, @next is stable because our @node->next pointer is NULL and + * it will wait in Step-A. + */ + + WRITE_ONCE(next->prev, prev); + WRITE_ONCE(prev->next, next); + + return false; +} + +void osq_unlock(struct optimistic_spin_queue *lock) +{ + struct optimistic_spin_node *node, *next; + int curr = encode_cpu(smp_processor_id()); + + /* + * Fast path for the uncontended case. + */ + if (likely(atomic_cmpxchg(&lock->tail, curr, OSQ_UNLOCKED_VAL) == curr)) + return; + + /* + * Second most likely case. + */ + node = this_cpu_ptr(&osq_node); + next = xchg(&node->next, NULL); + if (next) { + WRITE_ONCE(next->locked, 1); + return; + } + + next = osq_wait_next(lock, node, NULL); + if (next) + WRITE_ONCE(next->locked, 1); +} diff --git a/kernel/kernel/locking/percpu-rwsem.c b/kernel/kernel/locking/percpu-rwsem.c new file mode 100644 index 000000000..652a8ee8e --- /dev/null +++ b/kernel/kernel/locking/percpu-rwsem.c @@ -0,0 +1,165 @@ +#include +#include +#include +#include +#include +#include +#include +#include +#include + +int __percpu_init_rwsem(struct percpu_rw_semaphore *brw, + const char *name, struct lock_class_key *rwsem_key) +{ + brw->fast_read_ctr = alloc_percpu(int); + if (unlikely(!brw->fast_read_ctr)) + return -ENOMEM; + + /* ->rw_sem represents the whole percpu_rw_semaphore for lockdep */ + __init_rwsem(&brw->rw_sem, name, rwsem_key); + atomic_set(&brw->write_ctr, 0); + atomic_set(&brw->slow_read_ctr, 0); + init_waitqueue_head(&brw->write_waitq); + return 0; +} + +void percpu_free_rwsem(struct percpu_rw_semaphore *brw) +{ + free_percpu(brw->fast_read_ctr); + brw->fast_read_ctr = NULL; /* catch use after free bugs */ +} + +/* + * This is the fast-path for down_read/up_read, it only needs to ensure + * there is no pending writer (atomic_read(write_ctr) == 0) and inc/dec the + * fast per-cpu counter. The writer uses synchronize_sched_expedited() to + * serialize with the preempt-disabled section below. + * + * The nontrivial part is that we should guarantee acquire/release semantics + * in case when + * + * R_W: down_write() comes after up_read(), the writer should see all + * changes done by the reader + * or + * W_R: down_read() comes after up_write(), the reader should see all + * changes done by the writer + * + * If this helper fails the callers rely on the normal rw_semaphore and + * atomic_dec_and_test(), so in this case we have the necessary barriers. + * + * But if it succeeds we do not have any barriers, atomic_read(write_ctr) or + * __this_cpu_add() below can be reordered with any LOAD/STORE done by the + * reader inside the critical section. See the comments in down_write and + * up_write below. + */ +static bool update_fast_ctr(struct percpu_rw_semaphore *brw, unsigned int val) +{ + bool success = false; + + preempt_disable(); + if (likely(!atomic_read(&brw->write_ctr))) { + __this_cpu_add(*brw->fast_read_ctr, val); + success = true; + } + preempt_enable(); + + return success; +} + +/* + * Like the normal down_read() this is not recursive, the writer can + * come after the first percpu_down_read() and create the deadlock. + * + * Note: returns with lock_is_held(brw->rw_sem) == T for lockdep, + * percpu_up_read() does rwsem_release(). This pairs with the usage + * of ->rw_sem in percpu_down/up_write(). + */ +void percpu_down_read(struct percpu_rw_semaphore *brw) +{ + might_sleep(); + if (likely(update_fast_ctr(brw, +1))) { + rwsem_acquire_read(&brw->rw_sem.dep_map, 0, 0, _RET_IP_); + return; + } + + down_read(&brw->rw_sem); + atomic_inc(&brw->slow_read_ctr); + /* avoid up_read()->rwsem_release() */ + __up_read(&brw->rw_sem); +} + +void percpu_up_read(struct percpu_rw_semaphore *brw) +{ + rwsem_release(&brw->rw_sem.dep_map, 1, _RET_IP_); + + if (likely(update_fast_ctr(brw, -1))) + return; + + /* false-positive is possible but harmless */ + if (atomic_dec_and_test(&brw->slow_read_ctr)) + wake_up_all(&brw->write_waitq); +} + +static int clear_fast_ctr(struct percpu_rw_semaphore *brw) +{ + unsigned int sum = 0; + int cpu; + + for_each_possible_cpu(cpu) { + sum += per_cpu(*brw->fast_read_ctr, cpu); + per_cpu(*brw->fast_read_ctr, cpu) = 0; + } + + return sum; +} + +/* + * A writer increments ->write_ctr to force the readers to switch to the + * slow mode, note the atomic_read() check in update_fast_ctr(). + * + * After that the readers can only inc/dec the slow ->slow_read_ctr counter, + * ->fast_read_ctr is stable. Once the writer moves its sum into the slow + * counter it represents the number of active readers. + * + * Finally the writer takes ->rw_sem for writing and blocks the new readers, + * then waits until the slow counter becomes zero. + */ +void percpu_down_write(struct percpu_rw_semaphore *brw) +{ + /* tell update_fast_ctr() there is a pending writer */ + atomic_inc(&brw->write_ctr); + /* + * 1. Ensures that write_ctr != 0 is visible to any down_read/up_read + * so that update_fast_ctr() can't succeed. + * + * 2. Ensures we see the result of every previous this_cpu_add() in + * update_fast_ctr(). + * + * 3. Ensures that if any reader has exited its critical section via + * fast-path, it executes a full memory barrier before we return. + * See R_W case in the comment above update_fast_ctr(). + */ + synchronize_sched_expedited(); + + /* exclude other writers, and block the new readers completely */ + down_write(&brw->rw_sem); + + /* nobody can use fast_read_ctr, move its sum into slow_read_ctr */ + atomic_add(clear_fast_ctr(brw), &brw->slow_read_ctr); + + /* wait for all readers to complete their percpu_up_read() */ + wait_event(brw->write_waitq, !atomic_read(&brw->slow_read_ctr)); +} + +void percpu_up_write(struct percpu_rw_semaphore *brw) +{ + /* release the lock, but the readers can't use the fast-path */ + up_write(&brw->rw_sem); + /* + * Insert the barrier before the next fast-path in down_read, + * see W_R case in the comment above update_fast_ctr(). + */ + synchronize_sched_expedited(); + /* the last writer unblocks update_fast_ctr() */ + atomic_dec(&brw->write_ctr); +} diff --git a/kernel/kernel/locking/qrwlock.c b/kernel/kernel/locking/qrwlock.c new file mode 100644 index 000000000..f956ede7f --- /dev/null +++ b/kernel/kernel/locking/qrwlock.c @@ -0,0 +1,132 @@ +/* + * Queue read/write lock + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * (C) Copyright 2013-2014 Hewlett-Packard Development Company, L.P. + * + * Authors: Waiman Long + */ +#include +#include +#include +#include +#include +#include + +/** + * rspin_until_writer_unlock - inc reader count & spin until writer is gone + * @lock : Pointer to queue rwlock structure + * @writer: Current queue rwlock writer status byte + * + * In interrupt context or at the head of the queue, the reader will just + * increment the reader count & wait until the writer releases the lock. + */ +static __always_inline void +rspin_until_writer_unlock(struct qrwlock *lock, u32 cnts) +{ + while ((cnts & _QW_WMASK) == _QW_LOCKED) { + cpu_relax_lowlatency(); + cnts = smp_load_acquire((u32 *)&lock->cnts); + } +} + +/** + * queue_read_lock_slowpath - acquire read lock of a queue rwlock + * @lock: Pointer to queue rwlock structure + */ +void queue_read_lock_slowpath(struct qrwlock *lock) +{ + u32 cnts; + + /* + * Readers come here when they cannot get the lock without waiting + */ + if (unlikely(in_interrupt())) { + /* + * Readers in interrupt context will spin until the lock is + * available without waiting in the queue. + */ + cnts = smp_load_acquire((u32 *)&lock->cnts); + rspin_until_writer_unlock(lock, cnts); + return; + } + atomic_sub(_QR_BIAS, &lock->cnts); + + /* + * Put the reader into the wait queue + */ + arch_spin_lock(&lock->lock); + + /* + * At the head of the wait queue now, wait until the writer state + * goes to 0 and then try to increment the reader count and get + * the lock. It is possible that an incoming writer may steal the + * lock in the interim, so it is necessary to check the writer byte + * to make sure that the write lock isn't taken. + */ + while (atomic_read(&lock->cnts) & _QW_WMASK) + cpu_relax_lowlatency(); + + cnts = atomic_add_return(_QR_BIAS, &lock->cnts) - _QR_BIAS; + rspin_until_writer_unlock(lock, cnts); + + /* + * Signal the next one in queue to become queue head + */ + arch_spin_unlock(&lock->lock); +} +EXPORT_SYMBOL(queue_read_lock_slowpath); + +/** + * queue_write_lock_slowpath - acquire write lock of a queue rwlock + * @lock : Pointer to queue rwlock structure + */ +void queue_write_lock_slowpath(struct qrwlock *lock) +{ + u32 cnts; + + /* Put the writer into the wait queue */ + arch_spin_lock(&lock->lock); + + /* Try to acquire the lock directly if no reader is present */ + if (!atomic_read(&lock->cnts) && + (atomic_cmpxchg(&lock->cnts, 0, _QW_LOCKED) == 0)) + goto unlock; + + /* + * Set the waiting flag to notify readers that a writer is pending, + * or wait for a previous writer to go away. + */ + for (;;) { + cnts = atomic_read(&lock->cnts); + if (!(cnts & _QW_WMASK) && + (atomic_cmpxchg(&lock->cnts, cnts, + cnts | _QW_WAITING) == cnts)) + break; + + cpu_relax_lowlatency(); + } + + /* When no more readers, set the locked flag */ + for (;;) { + cnts = atomic_read(&lock->cnts); + if ((cnts == _QW_WAITING) && + (atomic_cmpxchg(&lock->cnts, _QW_WAITING, + _QW_LOCKED) == _QW_WAITING)) + break; + + cpu_relax_lowlatency(); + } +unlock: + arch_spin_unlock(&lock->lock); +} +EXPORT_SYMBOL(queue_write_lock_slowpath); diff --git a/kernel/kernel/locking/rt.c b/kernel/kernel/locking/rt.c new file mode 100644 index 000000000..c236efa48 --- /dev/null +++ b/kernel/kernel/locking/rt.c @@ -0,0 +1,461 @@ +/* + * kernel/rt.c + * + * Real-Time Preemption Support + * + * started by Ingo Molnar: + * + * Copyright (C) 2004-2006 Red Hat, Inc., Ingo Molnar + * Copyright (C) 2006, Timesys Corp., Thomas Gleixner + * + * historic credit for proving that Linux spinlocks can be implemented via + * RT-aware mutexes goes to many people: The Pmutex project (Dirk Grambow + * and others) who prototyped it on 2.4 and did lots of comparative + * research and analysis; TimeSys, for proving that you can implement a + * fully preemptible kernel via the use of IRQ threading and mutexes; + * Bill Huey for persuasively arguing on lkml that the mutex model is the + * right one; and to MontaVista, who ported pmutexes to 2.6. + * + * This code is a from-scratch implementation and is not based on pmutexes, + * but the idea of converting spinlocks to mutexes is used here too. + * + * lock debugging, locking tree, deadlock detection: + * + * Copyright (C) 2004, LynuxWorks, Inc., Igor Manyilov, Bill Huey + * Released under the General Public License (GPL). + * + * Includes portions of the generic R/W semaphore implementation from: + * + * Copyright (c) 2001 David Howells (dhowells@redhat.com). + * - Derived partially from idea by Andrea Arcangeli + * - Derived also from comments by Linus + * + * Pending ownership of locks and ownership stealing: + * + * Copyright (C) 2005, Kihon Technologies Inc., Steven Rostedt + * + * (also by Steven Rostedt) + * - Converted single pi_lock to individual task locks. + * + * By Esben Nielsen: + * Doing priority inheritance with help of the scheduler. + * + * Copyright (C) 2006, Timesys Corp., Thomas Gleixner + * - major rework based on Esben Nielsens initial patch + * - replaced thread_info references by task_struct refs + * - removed task->pending_owner dependency + * - BKL drop/reacquire for semaphore style locks to avoid deadlocks + * in the scheduler return path as discussed with Steven Rostedt + * + * Copyright (C) 2006, Kihon Technologies Inc. + * Steven Rostedt + * - debugged and patched Thomas Gleixner's rework. + * - added back the cmpxchg to the rework. + * - turned atomic require back on for SMP. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "rtmutex_common.h" + +/* + * struct mutex functions + */ +void __mutex_do_init(struct mutex *mutex, const char *name, + struct lock_class_key *key) +{ +#ifdef CONFIG_DEBUG_LOCK_ALLOC + /* + * Make sure we are not reinitializing a held lock: + */ + debug_check_no_locks_freed((void *)mutex, sizeof(*mutex)); + lockdep_init_map(&mutex->dep_map, name, key, 0); +#endif + mutex->lock.save_state = 0; +} +EXPORT_SYMBOL(__mutex_do_init); + +void __lockfunc _mutex_lock(struct mutex *lock) +{ + mutex_acquire(&lock->dep_map, 0, 0, _RET_IP_); + rt_mutex_lock(&lock->lock); +} +EXPORT_SYMBOL(_mutex_lock); + +int __lockfunc _mutex_lock_interruptible(struct mutex *lock) +{ + int ret; + + mutex_acquire(&lock->dep_map, 0, 0, _RET_IP_); + ret = rt_mutex_lock_interruptible(&lock->lock); + if (ret) + mutex_release(&lock->dep_map, 1, _RET_IP_); + return ret; +} +EXPORT_SYMBOL(_mutex_lock_interruptible); + +int __lockfunc _mutex_lock_killable(struct mutex *lock) +{ + int ret; + + mutex_acquire(&lock->dep_map, 0, 0, _RET_IP_); + ret = rt_mutex_lock_killable(&lock->lock); + if (ret) + mutex_release(&lock->dep_map, 1, _RET_IP_); + return ret; +} +EXPORT_SYMBOL(_mutex_lock_killable); + +#ifdef CONFIG_DEBUG_LOCK_ALLOC +void __lockfunc _mutex_lock_nested(struct mutex *lock, int subclass) +{ + mutex_acquire_nest(&lock->dep_map, subclass, 0, NULL, _RET_IP_); + rt_mutex_lock(&lock->lock); +} +EXPORT_SYMBOL(_mutex_lock_nested); + +void __lockfunc _mutex_lock_nest_lock(struct mutex *lock, struct lockdep_map *nest) +{ + mutex_acquire_nest(&lock->dep_map, 0, 0, nest, _RET_IP_); + rt_mutex_lock(&lock->lock); +} +EXPORT_SYMBOL(_mutex_lock_nest_lock); + +int __lockfunc _mutex_lock_interruptible_nested(struct mutex *lock, int subclass) +{ + int ret; + + mutex_acquire_nest(&lock->dep_map, subclass, 0, NULL, _RET_IP_); + ret = rt_mutex_lock_interruptible(&lock->lock); + if (ret) + mutex_release(&lock->dep_map, 1, _RET_IP_); + return ret; +} +EXPORT_SYMBOL(_mutex_lock_interruptible_nested); + +int __lockfunc _mutex_lock_killable_nested(struct mutex *lock, int subclass) +{ + int ret; + + mutex_acquire(&lock->dep_map, subclass, 0, _RET_IP_); + ret = rt_mutex_lock_killable(&lock->lock); + if (ret) + mutex_release(&lock->dep_map, 1, _RET_IP_); + return ret; +} +EXPORT_SYMBOL(_mutex_lock_killable_nested); +#endif + +int __lockfunc _mutex_trylock(struct mutex *lock) +{ + int ret = rt_mutex_trylock(&lock->lock); + + if (ret) + mutex_acquire(&lock->dep_map, 0, 1, _RET_IP_); + + return ret; +} +EXPORT_SYMBOL(_mutex_trylock); + +void __lockfunc _mutex_unlock(struct mutex *lock) +{ + mutex_release(&lock->dep_map, 1, _RET_IP_); + rt_mutex_unlock(&lock->lock); +} +EXPORT_SYMBOL(_mutex_unlock); + +/* + * rwlock_t functions + */ +int __lockfunc rt_write_trylock(rwlock_t *rwlock) +{ + int ret; + + migrate_disable(); + ret = rt_mutex_trylock(&rwlock->lock); + if (ret) + rwlock_acquire(&rwlock->dep_map, 0, 1, _RET_IP_); + else + migrate_enable(); + + return ret; +} +EXPORT_SYMBOL(rt_write_trylock); + +int __lockfunc rt_write_trylock_irqsave(rwlock_t *rwlock, unsigned long *flags) +{ + int ret; + + *flags = 0; + ret = rt_write_trylock(rwlock); + return ret; +} +EXPORT_SYMBOL(rt_write_trylock_irqsave); + +int __lockfunc rt_read_trylock(rwlock_t *rwlock) +{ + struct rt_mutex *lock = &rwlock->lock; + int ret = 1; + + /* + * recursive read locks succeed when current owns the lock, + * but not when read_depth == 0 which means that the lock is + * write locked. + */ + if (rt_mutex_owner(lock) != current) { + migrate_disable(); + ret = rt_mutex_trylock(lock); + if (ret) + rwlock_acquire(&rwlock->dep_map, 0, 1, _RET_IP_); + else + migrate_enable(); + + } else if (!rwlock->read_depth) { + ret = 0; + } + + if (ret) + rwlock->read_depth++; + + return ret; +} +EXPORT_SYMBOL(rt_read_trylock); + +void __lockfunc rt_write_lock(rwlock_t *rwlock) +{ + rwlock_acquire(&rwlock->dep_map, 0, 0, _RET_IP_); + migrate_disable(); + __rt_spin_lock(&rwlock->lock); +} +EXPORT_SYMBOL(rt_write_lock); + +void __lockfunc rt_read_lock(rwlock_t *rwlock) +{ + struct rt_mutex *lock = &rwlock->lock; + + + /* + * recursive read locks succeed when current owns the lock + */ + if (rt_mutex_owner(lock) != current) { + migrate_disable(); + rwlock_acquire(&rwlock->dep_map, 0, 0, _RET_IP_); + __rt_spin_lock(lock); + } + rwlock->read_depth++; +} + +EXPORT_SYMBOL(rt_read_lock); + +void __lockfunc rt_write_unlock(rwlock_t *rwlock) +{ + /* NOTE: we always pass in '1' for nested, for simplicity */ + rwlock_release(&rwlock->dep_map, 1, _RET_IP_); + __rt_spin_unlock(&rwlock->lock); + migrate_enable(); +} +EXPORT_SYMBOL(rt_write_unlock); + +void __lockfunc rt_read_unlock(rwlock_t *rwlock) +{ + /* Release the lock only when read_depth is down to 0 */ + if (--rwlock->read_depth == 0) { + rwlock_release(&rwlock->dep_map, 1, _RET_IP_); + __rt_spin_unlock(&rwlock->lock); + migrate_enable(); + } +} +EXPORT_SYMBOL(rt_read_unlock); + +unsigned long __lockfunc rt_write_lock_irqsave(rwlock_t *rwlock) +{ + rt_write_lock(rwlock); + + return 0; +} +EXPORT_SYMBOL(rt_write_lock_irqsave); + +unsigned long __lockfunc rt_read_lock_irqsave(rwlock_t *rwlock) +{ + rt_read_lock(rwlock); + + return 0; +} +EXPORT_SYMBOL(rt_read_lock_irqsave); + +void __rt_rwlock_init(rwlock_t *rwlock, char *name, struct lock_class_key *key) +{ +#ifdef CONFIG_DEBUG_LOCK_ALLOC + /* + * Make sure we are not reinitializing a held lock: + */ + debug_check_no_locks_freed((void *)rwlock, sizeof(*rwlock)); + lockdep_init_map(&rwlock->dep_map, name, key, 0); +#endif + rwlock->lock.save_state = 1; + rwlock->read_depth = 0; +} +EXPORT_SYMBOL(__rt_rwlock_init); + +/* + * rw_semaphores + */ + +void rt_up_write(struct rw_semaphore *rwsem) +{ + rwsem_release(&rwsem->dep_map, 1, _RET_IP_); + rt_mutex_unlock(&rwsem->lock); +} +EXPORT_SYMBOL(rt_up_write); + +void __rt_up_read(struct rw_semaphore *rwsem) +{ + if (--rwsem->read_depth == 0) + rt_mutex_unlock(&rwsem->lock); +} + +void rt_up_read(struct rw_semaphore *rwsem) +{ + rwsem_release(&rwsem->dep_map, 1, _RET_IP_); + __rt_up_read(rwsem); +} +EXPORT_SYMBOL(rt_up_read); + +/* + * downgrade a write lock into a read lock + * - just wake up any readers at the front of the queue + */ +void rt_downgrade_write(struct rw_semaphore *rwsem) +{ + BUG_ON(rt_mutex_owner(&rwsem->lock) != current); + rwsem->read_depth = 1; +} +EXPORT_SYMBOL(rt_downgrade_write); + +int rt_down_write_trylock(struct rw_semaphore *rwsem) +{ + int ret = rt_mutex_trylock(&rwsem->lock); + + if (ret) + rwsem_acquire(&rwsem->dep_map, 0, 1, _RET_IP_); + return ret; +} +EXPORT_SYMBOL(rt_down_write_trylock); + +void rt_down_write(struct rw_semaphore *rwsem) +{ + rwsem_acquire(&rwsem->dep_map, 0, 0, _RET_IP_); + rt_mutex_lock(&rwsem->lock); +} +EXPORT_SYMBOL(rt_down_write); + +void rt_down_write_nested(struct rw_semaphore *rwsem, int subclass) +{ + rwsem_acquire(&rwsem->dep_map, subclass, 0, _RET_IP_); + rt_mutex_lock(&rwsem->lock); +} +EXPORT_SYMBOL(rt_down_write_nested); + +void rt_down_write_nested_lock(struct rw_semaphore *rwsem, + struct lockdep_map *nest) +{ + rwsem_acquire_nest(&rwsem->dep_map, 0, 0, nest, _RET_IP_); + rt_mutex_lock(&rwsem->lock); +} +EXPORT_SYMBOL(rt_down_write_nested_lock); + +int rt_down_read_trylock(struct rw_semaphore *rwsem) +{ + struct rt_mutex *lock = &rwsem->lock; + int ret = 1; + + /* + * recursive read locks succeed when current owns the rwsem, + * but not when read_depth == 0 which means that the rwsem is + * write locked. + */ + if (rt_mutex_owner(lock) != current) + ret = rt_mutex_trylock(&rwsem->lock); + else if (!rwsem->read_depth) + ret = 0; + + if (ret) { + rwsem->read_depth++; + rwsem_acquire(&rwsem->dep_map, 0, 1, _RET_IP_); + } + return ret; +} +EXPORT_SYMBOL(rt_down_read_trylock); + +static void __rt_down_read(struct rw_semaphore *rwsem, int subclass) +{ + struct rt_mutex *lock = &rwsem->lock; + + rwsem_acquire_read(&rwsem->dep_map, subclass, 0, _RET_IP_); + + if (rt_mutex_owner(lock) != current) + rt_mutex_lock(&rwsem->lock); + rwsem->read_depth++; +} + +void rt_down_read(struct rw_semaphore *rwsem) +{ + __rt_down_read(rwsem, 0); +} +EXPORT_SYMBOL(rt_down_read); + +void rt_down_read_nested(struct rw_semaphore *rwsem, int subclass) +{ + __rt_down_read(rwsem, subclass); +} +EXPORT_SYMBOL(rt_down_read_nested); + +void __rt_rwsem_init(struct rw_semaphore *rwsem, const char *name, + struct lock_class_key *key) +{ +#ifdef CONFIG_DEBUG_LOCK_ALLOC + /* + * Make sure we are not reinitializing a held lock: + */ + debug_check_no_locks_freed((void *)rwsem, sizeof(*rwsem)); + lockdep_init_map(&rwsem->dep_map, name, key, 0); +#endif + rwsem->read_depth = 0; + rwsem->lock.save_state = 0; +} +EXPORT_SYMBOL(__rt_rwsem_init); + +/** + * atomic_dec_and_mutex_lock - return holding mutex if we dec to 0 + * @cnt: the atomic which we are to dec + * @lock: the mutex to return holding if we dec to 0 + * + * return true and hold lock if we dec to 0, return false otherwise + */ +int atomic_dec_and_mutex_lock(atomic_t *cnt, struct mutex *lock) +{ + /* dec if we can't possibly hit 0 */ + if (atomic_add_unless(cnt, -1, 1)) + return 0; + /* we might hit 0, so take the lock */ + mutex_lock(lock); + if (!atomic_dec_and_test(cnt)) { + /* when we actually did the dec, we didn't hit 0 */ + mutex_unlock(lock); + return 0; + } + /* we hit 0, and we hold the lock */ + return 1; +} +EXPORT_SYMBOL(atomic_dec_and_mutex_lock); diff --git a/kernel/kernel/locking/rtmutex-debug.c b/kernel/kernel/locking/rtmutex-debug.c new file mode 100644 index 000000000..62b6cee8e --- /dev/null +++ b/kernel/kernel/locking/rtmutex-debug.c @@ -0,0 +1,184 @@ +/* + * RT-Mutexes: blocking mutual exclusion locks with PI support + * + * started by Ingo Molnar and Thomas Gleixner: + * + * Copyright (C) 2004-2006 Red Hat, Inc., Ingo Molnar + * Copyright (C) 2006 Timesys Corp., Thomas Gleixner + * + * This code is based on the rt.c implementation in the preempt-rt tree. + * Portions of said code are + * + * Copyright (C) 2004 LynuxWorks, Inc., Igor Manyilov, Bill Huey + * Copyright (C) 2006 Esben Nielsen + * Copyright (C) 2006 Kihon Technologies Inc., + * Steven Rostedt + * + * See rt.c in preempt-rt for proper credits and further information + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "rtmutex_common.h" + +static void printk_task(struct task_struct *p) +{ + if (p) + printk("%16s:%5d [%p, %3d]", p->comm, task_pid_nr(p), p, p->prio); + else + printk(""); +} + +static void printk_lock(struct rt_mutex *lock, int print_owner) +{ + if (lock->name) + printk(" [%p] {%s}\n", + lock, lock->name); + else + printk(" [%p] {%s:%d}\n", + lock, lock->file, lock->line); + + if (print_owner && rt_mutex_owner(lock)) { + printk(".. ->owner: %p\n", lock->owner); + printk(".. held by: "); + printk_task(rt_mutex_owner(lock)); + printk("\n"); + } +} + +void rt_mutex_debug_task_free(struct task_struct *task) +{ + DEBUG_LOCKS_WARN_ON(!RB_EMPTY_ROOT(&task->pi_waiters)); + DEBUG_LOCKS_WARN_ON(task->pi_blocked_on); +} + +/* + * We fill out the fields in the waiter to store the information about + * the deadlock. We print when we return. act_waiter can be NULL in + * case of a remove waiter operation. + */ +void debug_rt_mutex_deadlock(enum rtmutex_chainwalk chwalk, + struct rt_mutex_waiter *act_waiter, + struct rt_mutex *lock) +{ + struct task_struct *task; + + if (!debug_locks || chwalk == RT_MUTEX_FULL_CHAINWALK || !act_waiter) + return; + + task = rt_mutex_owner(act_waiter->lock); + if (task && task != current) { + act_waiter->deadlock_task_pid = get_pid(task_pid(task)); + act_waiter->deadlock_lock = lock; + } +} + +void debug_rt_mutex_print_deadlock(struct rt_mutex_waiter *waiter) +{ + struct task_struct *task; + + if (!waiter->deadlock_lock || !debug_locks) + return; + + rcu_read_lock(); + task = pid_task(waiter->deadlock_task_pid, PIDTYPE_PID); + if (!task) { + rcu_read_unlock(); + return; + } + + if (!debug_locks_off()) { + rcu_read_unlock(); + return; + } + + printk("\n============================================\n"); + printk( "[ BUG: circular locking deadlock detected! ]\n"); + printk("%s\n", print_tainted()); + printk( "--------------------------------------------\n"); + printk("%s/%d is deadlocking current task %s/%d\n\n", + task->comm, task_pid_nr(task), + current->comm, task_pid_nr(current)); + + printk("\n1) %s/%d is trying to acquire this lock:\n", + current->comm, task_pid_nr(current)); + printk_lock(waiter->lock, 1); + + printk("\n2) %s/%d is blocked on this lock:\n", + task->comm, task_pid_nr(task)); + printk_lock(waiter->deadlock_lock, 1); + + debug_show_held_locks(current); + debug_show_held_locks(task); + + printk("\n%s/%d's [blocked] stackdump:\n\n", + task->comm, task_pid_nr(task)); + show_stack(task, NULL); + printk("\n%s/%d's [current] stackdump:\n\n", + current->comm, task_pid_nr(current)); + dump_stack(); + debug_show_all_locks(); + rcu_read_unlock(); + + printk("[ turning off deadlock detection." + "Please report this trace. ]\n\n"); +} + +void debug_rt_mutex_lock(struct rt_mutex *lock) +{ +} + +void debug_rt_mutex_unlock(struct rt_mutex *lock) +{ + DEBUG_LOCKS_WARN_ON(rt_mutex_owner(lock) != current); +} + +void +debug_rt_mutex_proxy_lock(struct rt_mutex *lock, struct task_struct *powner) +{ +} + +void debug_rt_mutex_proxy_unlock(struct rt_mutex *lock) +{ + DEBUG_LOCKS_WARN_ON(!rt_mutex_owner(lock)); +} + +void debug_rt_mutex_init_waiter(struct rt_mutex_waiter *waiter) +{ + memset(waiter, 0x11, sizeof(*waiter)); + waiter->deadlock_task_pid = NULL; +} + +void debug_rt_mutex_free_waiter(struct rt_mutex_waiter *waiter) +{ + put_pid(waiter->deadlock_task_pid); + memset(waiter, 0x22, sizeof(*waiter)); +} + +void debug_rt_mutex_init(struct rt_mutex *lock, const char *name) +{ + /* + * Make sure we are not reinitializing a held lock: + */ + debug_check_no_locks_freed((void *)lock, sizeof(*lock)); + lock->name = name; +} + +void +rt_mutex_deadlock_account_lock(struct rt_mutex *lock, struct task_struct *task) +{ +} + +void rt_mutex_deadlock_account_unlock(struct task_struct *task) +{ +} + diff --git a/kernel/kernel/locking/rtmutex-debug.h b/kernel/kernel/locking/rtmutex-debug.h new file mode 100644 index 000000000..d0519c343 --- /dev/null +++ b/kernel/kernel/locking/rtmutex-debug.h @@ -0,0 +1,39 @@ +/* + * RT-Mutexes: blocking mutual exclusion locks with PI support + * + * started by Ingo Molnar and Thomas Gleixner: + * + * Copyright (C) 2004-2006 Red Hat, Inc., Ingo Molnar + * Copyright (C) 2006, Timesys Corp., Thomas Gleixner + * + * This file contains macros used solely by rtmutex.c. Debug version. + */ + +extern void +rt_mutex_deadlock_account_lock(struct rt_mutex *lock, struct task_struct *task); +extern void rt_mutex_deadlock_account_unlock(struct task_struct *task); +extern void debug_rt_mutex_init_waiter(struct rt_mutex_waiter *waiter); +extern void debug_rt_mutex_free_waiter(struct rt_mutex_waiter *waiter); +extern void debug_rt_mutex_init(struct rt_mutex *lock, const char *name); +extern void debug_rt_mutex_lock(struct rt_mutex *lock); +extern void debug_rt_mutex_unlock(struct rt_mutex *lock); +extern void debug_rt_mutex_proxy_lock(struct rt_mutex *lock, + struct task_struct *powner); +extern void debug_rt_mutex_proxy_unlock(struct rt_mutex *lock); +extern void debug_rt_mutex_deadlock(enum rtmutex_chainwalk chwalk, + struct rt_mutex_waiter *waiter, + struct rt_mutex *lock); +extern void debug_rt_mutex_print_deadlock(struct rt_mutex_waiter *waiter); +# define debug_rt_mutex_reset_waiter(w) \ + do { (w)->deadlock_lock = NULL; } while (0) + +static inline bool debug_rt_mutex_detect_deadlock(struct rt_mutex_waiter *waiter, + enum rtmutex_chainwalk walk) +{ + return (waiter != NULL); +} + +static inline void rt_mutex_print_deadlock(struct rt_mutex_waiter *w) +{ + debug_rt_mutex_print_deadlock(w); +} diff --git a/kernel/kernel/locking/rtmutex-tester.c b/kernel/kernel/locking/rtmutex-tester.c new file mode 100644 index 000000000..1d96dd0d9 --- /dev/null +++ b/kernel/kernel/locking/rtmutex-tester.c @@ -0,0 +1,420 @@ +/* + * RT-Mutex-tester: scriptable tester for rt mutexes + * + * started by Thomas Gleixner: + * + * Copyright (C) 2006, Timesys Corp., Thomas Gleixner + * + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "rtmutex.h" + +#define MAX_RT_TEST_THREADS 8 +#define MAX_RT_TEST_MUTEXES 8 + +static spinlock_t rttest_lock; +static atomic_t rttest_event; + +struct test_thread_data { + int opcode; + int opdata; + int mutexes[MAX_RT_TEST_MUTEXES]; + int event; + struct device dev; +}; + +static struct test_thread_data thread_data[MAX_RT_TEST_THREADS]; +static struct task_struct *threads[MAX_RT_TEST_THREADS]; +static struct rt_mutex mutexes[MAX_RT_TEST_MUTEXES]; + +enum test_opcodes { + RTTEST_NOP = 0, + RTTEST_SCHEDOT, /* 1 Sched other, data = nice */ + RTTEST_SCHEDRT, /* 2 Sched fifo, data = prio */ + RTTEST_LOCK, /* 3 Lock uninterruptible, data = lockindex */ + RTTEST_LOCKNOWAIT, /* 4 Lock uninterruptible no wait in wakeup, data = lockindex */ + RTTEST_LOCKINT, /* 5 Lock interruptible, data = lockindex */ + RTTEST_LOCKINTNOWAIT, /* 6 Lock interruptible no wait in wakeup, data = lockindex */ + RTTEST_LOCKCONT, /* 7 Continue locking after the wakeup delay */ + RTTEST_UNLOCK, /* 8 Unlock, data = lockindex */ + /* 9, 10 - reserved for BKL commemoration */ + RTTEST_SIGNAL = 11, /* 11 Signal other test thread, data = thread id */ + RTTEST_RESETEVENT = 98, /* 98 Reset event counter */ + RTTEST_RESET = 99, /* 99 Reset all pending operations */ +}; + +static int handle_op(struct test_thread_data *td, int lockwakeup) +{ + int i, id, ret = -EINVAL; + + switch(td->opcode) { + + case RTTEST_NOP: + return 0; + + case RTTEST_LOCKCONT: + td->mutexes[td->opdata] = 1; + td->event = atomic_add_return(1, &rttest_event); + return 0; + + case RTTEST_RESET: + for (i = 0; i < MAX_RT_TEST_MUTEXES; i++) { + if (td->mutexes[i] == 4) { + rt_mutex_unlock(&mutexes[i]); + td->mutexes[i] = 0; + } + } + return 0; + + case RTTEST_RESETEVENT: + atomic_set(&rttest_event, 0); + return 0; + + default: + if (lockwakeup) + return ret; + } + + switch(td->opcode) { + + case RTTEST_LOCK: + case RTTEST_LOCKNOWAIT: + id = td->opdata; + if (id < 0 || id >= MAX_RT_TEST_MUTEXES) + return ret; + + td->mutexes[id] = 1; + td->event = atomic_add_return(1, &rttest_event); + rt_mutex_lock(&mutexes[id]); + td->event = atomic_add_return(1, &rttest_event); + td->mutexes[id] = 4; + return 0; + + case RTTEST_LOCKINT: + case RTTEST_LOCKINTNOWAIT: + id = td->opdata; + if (id < 0 || id >= MAX_RT_TEST_MUTEXES) + return ret; + + td->mutexes[id] = 1; + td->event = atomic_add_return(1, &rttest_event); + ret = rt_mutex_lock_interruptible(&mutexes[id], 0); + td->event = atomic_add_return(1, &rttest_event); + td->mutexes[id] = ret ? 0 : 4; + return ret ? -EINTR : 0; + + case RTTEST_UNLOCK: + id = td->opdata; + if (id < 0 || id >= MAX_RT_TEST_MUTEXES || td->mutexes[id] != 4) + return ret; + + td->event = atomic_add_return(1, &rttest_event); + rt_mutex_unlock(&mutexes[id]); + td->event = atomic_add_return(1, &rttest_event); + td->mutexes[id] = 0; + return 0; + + default: + break; + } + return ret; +} + +/* + * Schedule replacement for rtsem_down(). Only called for threads with + * PF_MUTEX_TESTER set. + * + * This allows us to have finegrained control over the event flow. + * + */ +void schedule_rt_mutex_test(struct rt_mutex *mutex) +{ + int tid, op, dat; + struct test_thread_data *td; + + /* We have to lookup the task */ + for (tid = 0; tid < MAX_RT_TEST_THREADS; tid++) { + if (threads[tid] == current) + break; + } + + BUG_ON(tid == MAX_RT_TEST_THREADS); + + td = &thread_data[tid]; + + op = td->opcode; + dat = td->opdata; + + switch (op) { + case RTTEST_LOCK: + case RTTEST_LOCKINT: + case RTTEST_LOCKNOWAIT: + case RTTEST_LOCKINTNOWAIT: + if (mutex != &mutexes[dat]) + break; + + if (td->mutexes[dat] != 1) + break; + + td->mutexes[dat] = 2; + td->event = atomic_add_return(1, &rttest_event); + break; + + default: + break; + } + + schedule(); + + + switch (op) { + case RTTEST_LOCK: + case RTTEST_LOCKINT: + if (mutex != &mutexes[dat]) + return; + + if (td->mutexes[dat] != 2) + return; + + td->mutexes[dat] = 3; + td->event = atomic_add_return(1, &rttest_event); + break; + + case RTTEST_LOCKNOWAIT: + case RTTEST_LOCKINTNOWAIT: + if (mutex != &mutexes[dat]) + return; + + if (td->mutexes[dat] != 2) + return; + + td->mutexes[dat] = 1; + td->event = atomic_add_return(1, &rttest_event); + return; + + default: + return; + } + + td->opcode = 0; + + for (;;) { + set_current_state(TASK_INTERRUPTIBLE); + + if (td->opcode > 0) { + int ret; + + set_current_state(TASK_RUNNING); + ret = handle_op(td, 1); + set_current_state(TASK_INTERRUPTIBLE); + if (td->opcode == RTTEST_LOCKCONT) + break; + td->opcode = ret; + } + + /* Wait for the next command to be executed */ + schedule(); + } + + /* Restore previous command and data */ + td->opcode = op; + td->opdata = dat; +} + +static int test_func(void *data) +{ + struct test_thread_data *td = data; + int ret; + + current->flags |= PF_MUTEX_TESTER; + set_freezable(); + allow_signal(SIGHUP); + + for(;;) { + + set_current_state(TASK_INTERRUPTIBLE); + + if (td->opcode > 0) { + set_current_state(TASK_RUNNING); + ret = handle_op(td, 0); + set_current_state(TASK_INTERRUPTIBLE); + td->opcode = ret; + } + + /* Wait for the next command to be executed */ + schedule(); + try_to_freeze(); + + if (signal_pending(current)) + flush_signals(current); + + if(kthread_should_stop()) + break; + } + return 0; +} + +/** + * sysfs_test_command - interface for test commands + * @dev: thread reference + * @buf: command for actual step + * @count: length of buffer + * + * command syntax: + * + * opcode:data + */ +static ssize_t sysfs_test_command(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) +{ + struct sched_param schedpar; + struct test_thread_data *td; + char cmdbuf[32]; + int op, dat, tid, ret; + + td = container_of(dev, struct test_thread_data, dev); + tid = td->dev.id; + + /* strings from sysfs write are not 0 terminated! */ + if (count >= sizeof(cmdbuf)) + return -EINVAL; + + /* strip of \n: */ + if (buf[count-1] == '\n') + count--; + if (count < 1) + return -EINVAL; + + memcpy(cmdbuf, buf, count); + cmdbuf[count] = 0; + + if (sscanf(cmdbuf, "%d:%d", &op, &dat) != 2) + return -EINVAL; + + switch (op) { + case RTTEST_SCHEDOT: + schedpar.sched_priority = 0; + ret = sched_setscheduler(threads[tid], SCHED_NORMAL, &schedpar); + if (ret) + return ret; + set_user_nice(current, 0); + break; + + case RTTEST_SCHEDRT: + schedpar.sched_priority = dat; + ret = sched_setscheduler(threads[tid], SCHED_FIFO, &schedpar); + if (ret) + return ret; + break; + + case RTTEST_SIGNAL: + send_sig(SIGHUP, threads[tid], 0); + break; + + default: + if (td->opcode > 0) + return -EBUSY; + td->opdata = dat; + td->opcode = op; + wake_up_process(threads[tid]); + } + + return count; +} + +/** + * sysfs_test_status - sysfs interface for rt tester + * @dev: thread to query + * @buf: char buffer to be filled with thread status info + */ +static ssize_t sysfs_test_status(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct test_thread_data *td; + struct task_struct *tsk; + char *curr = buf; + int i; + + td = container_of(dev, struct test_thread_data, dev); + tsk = threads[td->dev.id]; + + spin_lock(&rttest_lock); + + curr += sprintf(curr, + "O: %4d, E:%8d, S: 0x%08lx, P: %4d, N: %4d, B: %p, M:", + td->opcode, td->event, tsk->state, + (MAX_RT_PRIO - 1) - tsk->prio, + (MAX_RT_PRIO - 1) - tsk->normal_prio, + tsk->pi_blocked_on); + + for (i = MAX_RT_TEST_MUTEXES - 1; i >=0 ; i--) + curr += sprintf(curr, "%d", td->mutexes[i]); + + spin_unlock(&rttest_lock); + + curr += sprintf(curr, ", T: %p, R: %p\n", tsk, + mutexes[td->dev.id].owner); + + return curr - buf; +} + +static DEVICE_ATTR(status, S_IRUSR, sysfs_test_status, NULL); +static DEVICE_ATTR(command, S_IWUSR, NULL, sysfs_test_command); + +static struct bus_type rttest_subsys = { + .name = "rttest", + .dev_name = "rttest", +}; + +static int init_test_thread(int id) +{ + thread_data[id].dev.bus = &rttest_subsys; + thread_data[id].dev.id = id; + + threads[id] = kthread_run(test_func, &thread_data[id], "rt-test-%d", id); + if (IS_ERR(threads[id])) + return PTR_ERR(threads[id]); + + return device_register(&thread_data[id].dev); +} + +static int init_rttest(void) +{ + int ret, i; + + spin_lock_init(&rttest_lock); + + for (i = 0; i < MAX_RT_TEST_MUTEXES; i++) + rt_mutex_init(&mutexes[i]); + + ret = subsys_system_register(&rttest_subsys, NULL); + if (ret) + return ret; + + for (i = 0; i < MAX_RT_TEST_THREADS; i++) { + ret = init_test_thread(i); + if (ret) + break; + ret = device_create_file(&thread_data[i].dev, &dev_attr_status); + if (ret) + break; + ret = device_create_file(&thread_data[i].dev, &dev_attr_command); + if (ret) + break; + } + + printk("Initializing RT-Tester: %s\n", ret ? "Failed" : "OK" ); + + return ret; +} + +device_initcall(init_rttest); diff --git a/kernel/kernel/locking/rtmutex.c b/kernel/kernel/locking/rtmutex.c new file mode 100644 index 000000000..2822aceb8 --- /dev/null +++ b/kernel/kernel/locking/rtmutex.c @@ -0,0 +1,2300 @@ +/* + * RT-Mutexes: simple blocking mutual exclusion locks with PI support + * + * started by Ingo Molnar and Thomas Gleixner. + * + * Copyright (C) 2004-2006 Red Hat, Inc., Ingo Molnar + * Copyright (C) 2005-2006 Timesys Corp., Thomas Gleixner + * Copyright (C) 2005 Kihon Technologies Inc., Steven Rostedt + * Copyright (C) 2006 Esben Nielsen + * Adaptive Spinlocks: + * Copyright (C) 2008 Novell, Inc., Gregory Haskins, Sven Dietrich, + * and Peter Morreale, + * Adaptive Spinlocks simplification: + * Copyright (C) 2008 Red Hat, Inc., Steven Rostedt + * + * See Documentation/locking/rt-mutex-design.txt for details. + */ +#include +#include +#include +#include +#include +#include +#include + +#include "rtmutex_common.h" + +/* + * lock->owner state tracking: + * + * lock->owner holds the task_struct pointer of the owner. Bit 0 + * is used to keep track of the "lock has waiters" state. + * + * owner bit0 + * NULL 0 lock is free (fast acquire possible) + * NULL 1 lock is free and has waiters and the top waiter + * is going to take the lock* + * taskpointer 0 lock is held (fast release possible) + * taskpointer 1 lock is held and has waiters** + * + * The fast atomic compare exchange based acquire and release is only + * possible when bit 0 of lock->owner is 0. + * + * (*) It also can be a transitional state when grabbing the lock + * with ->wait_lock is held. To prevent any fast path cmpxchg to the lock, + * we need to set the bit0 before looking at the lock, and the owner may be + * NULL in this small time, hence this can be a transitional state. + * + * (**) There is a small time when bit 0 is set but there are no + * waiters. This can happen when grabbing the lock in the slow path. + * To prevent a cmpxchg of the owner releasing the lock, we need to + * set this bit before looking at the lock. + */ + +static void +rt_mutex_set_owner(struct rt_mutex *lock, struct task_struct *owner) +{ + unsigned long val = (unsigned long)owner; + + if (rt_mutex_has_waiters(lock)) + val |= RT_MUTEX_HAS_WAITERS; + + lock->owner = (struct task_struct *)val; +} + +static inline void clear_rt_mutex_waiters(struct rt_mutex *lock) +{ + lock->owner = (struct task_struct *) + ((unsigned long)lock->owner & ~RT_MUTEX_HAS_WAITERS); +} + +static void fixup_rt_mutex_waiters(struct rt_mutex *lock) +{ + if (!rt_mutex_has_waiters(lock)) + clear_rt_mutex_waiters(lock); +} + +static int rt_mutex_real_waiter(struct rt_mutex_waiter *waiter) +{ + return waiter && waiter != PI_WAKEUP_INPROGRESS && + waiter != PI_REQUEUE_INPROGRESS; +} + +/* + * We can speed up the acquire/release, if the architecture + * supports cmpxchg and if there's no debugging state to be set up + */ +#if defined(__HAVE_ARCH_CMPXCHG) && !defined(CONFIG_DEBUG_RT_MUTEXES) +# define rt_mutex_cmpxchg(l,c,n) (cmpxchg(&l->owner, c, n) == c) +static inline void mark_rt_mutex_waiters(struct rt_mutex *lock) +{ + unsigned long owner, *p = (unsigned long *) &lock->owner; + + do { + owner = *p; + } while (cmpxchg(p, owner, owner | RT_MUTEX_HAS_WAITERS) != owner); +} + +/* + * Safe fastpath aware unlock: + * 1) Clear the waiters bit + * 2) Drop lock->wait_lock + * 3) Try to unlock the lock with cmpxchg + */ +static inline bool unlock_rt_mutex_safe(struct rt_mutex *lock) + __releases(lock->wait_lock) +{ + struct task_struct *owner = rt_mutex_owner(lock); + + clear_rt_mutex_waiters(lock); + raw_spin_unlock(&lock->wait_lock); + /* + * If a new waiter comes in between the unlock and the cmpxchg + * we have two situations: + * + * unlock(wait_lock); + * lock(wait_lock); + * cmpxchg(p, owner, 0) == owner + * mark_rt_mutex_waiters(lock); + * acquire(lock); + * or: + * + * unlock(wait_lock); + * lock(wait_lock); + * mark_rt_mutex_waiters(lock); + * + * cmpxchg(p, owner, 0) != owner + * enqueue_waiter(); + * unlock(wait_lock); + * lock(wait_lock); + * wake waiter(); + * unlock(wait_lock); + * lock(wait_lock); + * acquire(lock); + */ + return rt_mutex_cmpxchg(lock, owner, NULL); +} + +#else +# define rt_mutex_cmpxchg(l,c,n) (0) +static inline void mark_rt_mutex_waiters(struct rt_mutex *lock) +{ + lock->owner = (struct task_struct *) + ((unsigned long)lock->owner | RT_MUTEX_HAS_WAITERS); +} + +/* + * Simple slow path only version: lock->owner is protected by lock->wait_lock. + */ +static inline bool unlock_rt_mutex_safe(struct rt_mutex *lock) + __releases(lock->wait_lock) +{ + lock->owner = NULL; + raw_spin_unlock(&lock->wait_lock); + return true; +} +#endif + +static inline int +rt_mutex_waiter_less(struct rt_mutex_waiter *left, + struct rt_mutex_waiter *right) +{ + if (left->prio < right->prio) + return 1; + + /* + * If both waiters have dl_prio(), we check the deadlines of the + * associated tasks. + * If left waiter has a dl_prio(), and we didn't return 1 above, + * then right waiter has a dl_prio() too. + */ + if (dl_prio(left->prio)) + return (left->task->dl.deadline < right->task->dl.deadline); + + return 0; +} + +static void +rt_mutex_enqueue(struct rt_mutex *lock, struct rt_mutex_waiter *waiter) +{ + struct rb_node **link = &lock->waiters.rb_node; + struct rb_node *parent = NULL; + struct rt_mutex_waiter *entry; + int leftmost = 1; + + while (*link) { + parent = *link; + entry = rb_entry(parent, struct rt_mutex_waiter, tree_entry); + if (rt_mutex_waiter_less(waiter, entry)) { + link = &parent->rb_left; + } else { + link = &parent->rb_right; + leftmost = 0; + } + } + + if (leftmost) + lock->waiters_leftmost = &waiter->tree_entry; + + rb_link_node(&waiter->tree_entry, parent, link); + rb_insert_color(&waiter->tree_entry, &lock->waiters); +} + +static void +rt_mutex_dequeue(struct rt_mutex *lock, struct rt_mutex_waiter *waiter) +{ + if (RB_EMPTY_NODE(&waiter->tree_entry)) + return; + + if (lock->waiters_leftmost == &waiter->tree_entry) + lock->waiters_leftmost = rb_next(&waiter->tree_entry); + + rb_erase(&waiter->tree_entry, &lock->waiters); + RB_CLEAR_NODE(&waiter->tree_entry); +} + +static void +rt_mutex_enqueue_pi(struct task_struct *task, struct rt_mutex_waiter *waiter) +{ + struct rb_node **link = &task->pi_waiters.rb_node; + struct rb_node *parent = NULL; + struct rt_mutex_waiter *entry; + int leftmost = 1; + + while (*link) { + parent = *link; + entry = rb_entry(parent, struct rt_mutex_waiter, pi_tree_entry); + if (rt_mutex_waiter_less(waiter, entry)) { + link = &parent->rb_left; + } else { + link = &parent->rb_right; + leftmost = 0; + } + } + + if (leftmost) + task->pi_waiters_leftmost = &waiter->pi_tree_entry; + + rb_link_node(&waiter->pi_tree_entry, parent, link); + rb_insert_color(&waiter->pi_tree_entry, &task->pi_waiters); +} + +static void +rt_mutex_dequeue_pi(struct task_struct *task, struct rt_mutex_waiter *waiter) +{ + if (RB_EMPTY_NODE(&waiter->pi_tree_entry)) + return; + + if (task->pi_waiters_leftmost == &waiter->pi_tree_entry) + task->pi_waiters_leftmost = rb_next(&waiter->pi_tree_entry); + + rb_erase(&waiter->pi_tree_entry, &task->pi_waiters); + RB_CLEAR_NODE(&waiter->pi_tree_entry); +} + +/* + * Calculate task priority from the waiter tree priority + * + * Return task->normal_prio when the waiter tree is empty or when + * the waiter is not allowed to do priority boosting + */ +int rt_mutex_getprio(struct task_struct *task) +{ + if (likely(!task_has_pi_waiters(task))) + return task->normal_prio; + + return min(task_top_pi_waiter(task)->prio, + task->normal_prio); +} + +struct task_struct *rt_mutex_get_top_task(struct task_struct *task) +{ + if (likely(!task_has_pi_waiters(task))) + return NULL; + + return task_top_pi_waiter(task)->task; +} + +/* + * Called by sched_setscheduler() to get the priority which will be + * effective after the change. + */ +int rt_mutex_get_effective_prio(struct task_struct *task, int newprio) +{ + if (!task_has_pi_waiters(task)) + return newprio; + + if (task_top_pi_waiter(task)->task->prio <= newprio) + return task_top_pi_waiter(task)->task->prio; + return newprio; +} + +/* + * Adjust the priority of a task, after its pi_waiters got modified. + * + * This can be both boosting and unboosting. task->pi_lock must be held. + */ +static void __rt_mutex_adjust_prio(struct task_struct *task) +{ + int prio = rt_mutex_getprio(task); + + if (task->prio != prio || dl_prio(prio)) + rt_mutex_setprio(task, prio); +} + +/* + * Adjust task priority (undo boosting). Called from the exit path of + * rt_mutex_slowunlock() and rt_mutex_slowlock(). + * + * (Note: We do this outside of the protection of lock->wait_lock to + * allow the lock to be taken while or before we readjust the priority + * of task. We do not use the spin_xx_mutex() variants here as we are + * outside of the debug path.) + */ +void rt_mutex_adjust_prio(struct task_struct *task) +{ + unsigned long flags; + + raw_spin_lock_irqsave(&task->pi_lock, flags); + __rt_mutex_adjust_prio(task); + raw_spin_unlock_irqrestore(&task->pi_lock, flags); +} + +/* + * Deadlock detection is conditional: + * + * If CONFIG_DEBUG_RT_MUTEXES=n, deadlock detection is only conducted + * if the detect argument is == RT_MUTEX_FULL_CHAINWALK. + * + * If CONFIG_DEBUG_RT_MUTEXES=y, deadlock detection is always + * conducted independent of the detect argument. + * + * If the waiter argument is NULL this indicates the deboost path and + * deadlock detection is disabled independent of the detect argument + * and the config settings. + */ +static bool rt_mutex_cond_detect_deadlock(struct rt_mutex_waiter *waiter, + enum rtmutex_chainwalk chwalk) +{ + /* + * This is just a wrapper function for the following call, + * because debug_rt_mutex_detect_deadlock() smells like a magic + * debug feature and I wanted to keep the cond function in the + * main source file along with the comments instead of having + * two of the same in the headers. + */ + return debug_rt_mutex_detect_deadlock(waiter, chwalk); +} + +static void rt_mutex_wake_waiter(struct rt_mutex_waiter *waiter) +{ + if (waiter->savestate) + wake_up_lock_sleeper(waiter->task); + else + wake_up_process(waiter->task); +} + +/* + * Max number of times we'll walk the boosting chain: + */ +int max_lock_depth = 1024; + +static inline struct rt_mutex *task_blocked_on_lock(struct task_struct *p) +{ + return rt_mutex_real_waiter(p->pi_blocked_on) ? + p->pi_blocked_on->lock : NULL; +} + +/* + * Adjust the priority chain. Also used for deadlock detection. + * Decreases task's usage by one - may thus free the task. + * + * @task: the task owning the mutex (owner) for which a chain walk is + * probably needed + * @chwalk: do we have to carry out deadlock detection? + * @orig_lock: the mutex (can be NULL if we are walking the chain to recheck + * things for a task that has just got its priority adjusted, and + * is waiting on a mutex) + * @next_lock: the mutex on which the owner of @orig_lock was blocked before + * we dropped its pi_lock. Is never dereferenced, only used for + * comparison to detect lock chain changes. + * @orig_waiter: rt_mutex_waiter struct for the task that has just donated + * its priority to the mutex owner (can be NULL in the case + * depicted above or if the top waiter is gone away and we are + * actually deboosting the owner) + * @top_task: the current top waiter + * + * Returns 0 or -EDEADLK. + * + * Chain walk basics and protection scope + * + * [R] refcount on task + * [P] task->pi_lock held + * [L] rtmutex->wait_lock held + * + * Step Description Protected by + * function arguments: + * @task [R] + * @orig_lock if != NULL @top_task is blocked on it + * @next_lock Unprotected. Cannot be + * dereferenced. Only used for + * comparison. + * @orig_waiter if != NULL @top_task is blocked on it + * @top_task current, or in case of proxy + * locking protected by calling + * code + * again: + * loop_sanity_check(); + * retry: + * [1] lock(task->pi_lock); [R] acquire [P] + * [2] waiter = task->pi_blocked_on; [P] + * [3] check_exit_conditions_1(); [P] + * [4] lock = waiter->lock; [P] + * [5] if (!try_lock(lock->wait_lock)) { [P] try to acquire [L] + * unlock(task->pi_lock); release [P] + * goto retry; + * } + * [6] check_exit_conditions_2(); [P] + [L] + * [7] requeue_lock_waiter(lock, waiter); [P] + [L] + * [8] unlock(task->pi_lock); release [P] + * put_task_struct(task); release [R] + * [9] check_exit_conditions_3(); [L] + * [10] task = owner(lock); [L] + * get_task_struct(task); [L] acquire [R] + * lock(task->pi_lock); [L] acquire [P] + * [11] requeue_pi_waiter(tsk, waiters(lock));[P] + [L] + * [12] check_exit_conditions_4(); [P] + [L] + * [13] unlock(task->pi_lock); release [P] + * unlock(lock->wait_lock); release [L] + * goto again; + */ +static int rt_mutex_adjust_prio_chain(struct task_struct *task, + enum rtmutex_chainwalk chwalk, + struct rt_mutex *orig_lock, + struct rt_mutex *next_lock, + struct rt_mutex_waiter *orig_waiter, + struct task_struct *top_task) +{ + struct rt_mutex_waiter *waiter, *top_waiter = orig_waiter; + struct rt_mutex_waiter *prerequeue_top_waiter; + int ret = 0, depth = 0; + struct rt_mutex *lock; + bool detect_deadlock; + unsigned long flags; + bool requeue = true; + + detect_deadlock = rt_mutex_cond_detect_deadlock(orig_waiter, chwalk); + + /* + * The (de)boosting is a step by step approach with a lot of + * pitfalls. We want this to be preemptible and we want hold a + * maximum of two locks per step. So we have to check + * carefully whether things change under us. + */ + again: + /* + * We limit the lock chain length for each invocation. + */ + if (++depth > max_lock_depth) { + static int prev_max; + + /* + * Print this only once. If the admin changes the limit, + * print a new message when reaching the limit again. + */ + if (prev_max != max_lock_depth) { + prev_max = max_lock_depth; + printk(KERN_WARNING "Maximum lock depth %d reached " + "task: %s (%d)\n", max_lock_depth, + top_task->comm, task_pid_nr(top_task)); + } + put_task_struct(task); + + return -EDEADLK; + } + + /* + * We are fully preemptible here and only hold the refcount on + * @task. So everything can have changed under us since the + * caller or our own code below (goto retry/again) dropped all + * locks. + */ + retry: + /* + * [1] Task cannot go away as we did a get_task() before ! + */ + raw_spin_lock_irqsave(&task->pi_lock, flags); + + /* + * [2] Get the waiter on which @task is blocked on. + */ + waiter = task->pi_blocked_on; + + /* + * [3] check_exit_conditions_1() protected by task->pi_lock. + */ + + /* + * Check whether the end of the boosting chain has been + * reached or the state of the chain has changed while we + * dropped the locks. + */ + if (!rt_mutex_real_waiter(waiter)) + goto out_unlock_pi; + + /* + * Check the orig_waiter state. After we dropped the locks, + * the previous owner of the lock might have released the lock. + */ + if (orig_waiter && !rt_mutex_owner(orig_lock)) + goto out_unlock_pi; + + /* + * We dropped all locks after taking a refcount on @task, so + * the task might have moved on in the lock chain or even left + * the chain completely and blocks now on an unrelated lock or + * on @orig_lock. + * + * We stored the lock on which @task was blocked in @next_lock, + * so we can detect the chain change. + */ + if (next_lock != waiter->lock) + goto out_unlock_pi; + + /* + * Drop out, when the task has no waiters. Note, + * top_waiter can be NULL, when we are in the deboosting + * mode! + */ + if (top_waiter) { + if (!task_has_pi_waiters(task)) + goto out_unlock_pi; + /* + * If deadlock detection is off, we stop here if we + * are not the top pi waiter of the task. If deadlock + * detection is enabled we continue, but stop the + * requeueing in the chain walk. + */ + if (top_waiter != task_top_pi_waiter(task)) { + if (!detect_deadlock) + goto out_unlock_pi; + else + requeue = false; + } + } + + /* + * If the waiter priority is the same as the task priority + * then there is no further priority adjustment necessary. If + * deadlock detection is off, we stop the chain walk. If its + * enabled we continue, but stop the requeueing in the chain + * walk. + */ + if (waiter->prio == task->prio) { + if (!detect_deadlock) + goto out_unlock_pi; + else + requeue = false; + } + + /* + * [4] Get the next lock + */ + lock = waiter->lock; + /* + * [5] We need to trylock here as we are holding task->pi_lock, + * which is the reverse lock order versus the other rtmutex + * operations. + */ + if (!raw_spin_trylock(&lock->wait_lock)) { + raw_spin_unlock_irqrestore(&task->pi_lock, flags); + cpu_relax(); + goto retry; + } + + /* + * [6] check_exit_conditions_2() protected by task->pi_lock and + * lock->wait_lock. + * + * Deadlock detection. If the lock is the same as the original + * lock which caused us to walk the lock chain or if the + * current lock is owned by the task which initiated the chain + * walk, we detected a deadlock. + */ + if (lock == orig_lock || rt_mutex_owner(lock) == top_task) { + debug_rt_mutex_deadlock(chwalk, orig_waiter, lock); + raw_spin_unlock(&lock->wait_lock); + ret = -EDEADLK; + goto out_unlock_pi; + } + + /* + * If we just follow the lock chain for deadlock detection, no + * need to do all the requeue operations. To avoid a truckload + * of conditionals around the various places below, just do the + * minimum chain walk checks. + */ + if (!requeue) { + /* + * No requeue[7] here. Just release @task [8] + */ + raw_spin_unlock_irqrestore(&task->pi_lock, flags); + put_task_struct(task); + + /* + * [9] check_exit_conditions_3 protected by lock->wait_lock. + * If there is no owner of the lock, end of chain. + */ + if (!rt_mutex_owner(lock)) { + raw_spin_unlock(&lock->wait_lock); + return 0; + } + + /* [10] Grab the next task, i.e. owner of @lock */ + task = rt_mutex_owner(lock); + get_task_struct(task); + raw_spin_lock_irqsave(&task->pi_lock, flags); + + /* + * No requeue [11] here. We just do deadlock detection. + * + * [12] Store whether owner is blocked + * itself. Decision is made after dropping the locks + */ + next_lock = task_blocked_on_lock(task); + /* + * Get the top waiter for the next iteration + */ + top_waiter = rt_mutex_top_waiter(lock); + + /* [13] Drop locks */ + raw_spin_unlock_irqrestore(&task->pi_lock, flags); + raw_spin_unlock(&lock->wait_lock); + + /* If owner is not blocked, end of chain. */ + if (!next_lock) + goto out_put_task; + goto again; + } + + /* + * Store the current top waiter before doing the requeue + * operation on @lock. We need it for the boost/deboost + * decision below. + */ + prerequeue_top_waiter = rt_mutex_top_waiter(lock); + + /* [7] Requeue the waiter in the lock waiter list. */ + rt_mutex_dequeue(lock, waiter); + waiter->prio = task->prio; + rt_mutex_enqueue(lock, waiter); + + /* [8] Release the task */ + raw_spin_unlock_irqrestore(&task->pi_lock, flags); + put_task_struct(task); + + /* + * [9] check_exit_conditions_3 protected by lock->wait_lock. + * + * We must abort the chain walk if there is no lock owner even + * in the dead lock detection case, as we have nothing to + * follow here. This is the end of the chain we are walking. + */ + if (!rt_mutex_owner(lock)) { + struct rt_mutex_waiter *lock_top_waiter; + + /* + * If the requeue [7] above changed the top waiter, + * then we need to wake the new top waiter up to try + * to get the lock. + */ + lock_top_waiter = rt_mutex_top_waiter(lock); + if (prerequeue_top_waiter != lock_top_waiter) + rt_mutex_wake_waiter(lock_top_waiter); + raw_spin_unlock(&lock->wait_lock); + return 0; + } + + /* [10] Grab the next task, i.e. the owner of @lock */ + task = rt_mutex_owner(lock); + get_task_struct(task); + raw_spin_lock_irqsave(&task->pi_lock, flags); + + /* [11] requeue the pi waiters if necessary */ + if (waiter == rt_mutex_top_waiter(lock)) { + /* + * The waiter became the new top (highest priority) + * waiter on the lock. Replace the previous top waiter + * in the owner tasks pi waiters list with this waiter + * and adjust the priority of the owner. + */ + rt_mutex_dequeue_pi(task, prerequeue_top_waiter); + rt_mutex_enqueue_pi(task, waiter); + __rt_mutex_adjust_prio(task); + + } else if (prerequeue_top_waiter == waiter) { + /* + * The waiter was the top waiter on the lock, but is + * no longer the top prority waiter. Replace waiter in + * the owner tasks pi waiters list with the new top + * (highest priority) waiter and adjust the priority + * of the owner. + * The new top waiter is stored in @waiter so that + * @waiter == @top_waiter evaluates to true below and + * we continue to deboost the rest of the chain. + */ + rt_mutex_dequeue_pi(task, waiter); + waiter = rt_mutex_top_waiter(lock); + rt_mutex_enqueue_pi(task, waiter); + __rt_mutex_adjust_prio(task); + } else { + /* + * Nothing changed. No need to do any priority + * adjustment. + */ + } + + /* + * [12] check_exit_conditions_4() protected by task->pi_lock + * and lock->wait_lock. The actual decisions are made after we + * dropped the locks. + * + * Check whether the task which owns the current lock is pi + * blocked itself. If yes we store a pointer to the lock for + * the lock chain change detection above. After we dropped + * task->pi_lock next_lock cannot be dereferenced anymore. + */ + next_lock = task_blocked_on_lock(task); + /* + * Store the top waiter of @lock for the end of chain walk + * decision below. + */ + top_waiter = rt_mutex_top_waiter(lock); + + /* [13] Drop the locks */ + raw_spin_unlock_irqrestore(&task->pi_lock, flags); + raw_spin_unlock(&lock->wait_lock); + + /* + * Make the actual exit decisions [12], based on the stored + * values. + * + * We reached the end of the lock chain. Stop right here. No + * point to go back just to figure that out. + */ + if (!next_lock) + goto out_put_task; + + /* + * If the current waiter is not the top waiter on the lock, + * then we can stop the chain walk here if we are not in full + * deadlock detection mode. + */ + if (!detect_deadlock && waiter != top_waiter) + goto out_put_task; + + goto again; + + out_unlock_pi: + raw_spin_unlock_irqrestore(&task->pi_lock, flags); + out_put_task: + put_task_struct(task); + + return ret; +} + + +#define STEAL_NORMAL 0 +#define STEAL_LATERAL 1 + +/* + * Note that RT tasks are excluded from lateral-steals to prevent the + * introduction of an unbounded latency + */ +static inline int lock_is_stealable(struct task_struct *task, + struct task_struct *pendowner, int mode) +{ + if (mode == STEAL_NORMAL || rt_task(task)) { + if (task->prio >= pendowner->prio) + return 0; + } else if (task->prio > pendowner->prio) + return 0; + return 1; +} + +/* + * Try to take an rt-mutex + * + * Must be called with lock->wait_lock held. + * + * @lock: The lock to be acquired. + * @task: The task which wants to acquire the lock + * @waiter: The waiter that is queued to the lock's wait list if the + * callsite called task_blocked_on_lock(), otherwise NULL + */ +static int __try_to_take_rt_mutex(struct rt_mutex *lock, + struct task_struct *task, + struct rt_mutex_waiter *waiter, int mode) +{ + unsigned long flags; + + /* + * Before testing whether we can acquire @lock, we set the + * RT_MUTEX_HAS_WAITERS bit in @lock->owner. This forces all + * other tasks which try to modify @lock into the slow path + * and they serialize on @lock->wait_lock. + * + * The RT_MUTEX_HAS_WAITERS bit can have a transitional state + * as explained at the top of this file if and only if: + * + * - There is a lock owner. The caller must fixup the + * transient state if it does a trylock or leaves the lock + * function due to a signal or timeout. + * + * - @task acquires the lock and there are no other + * waiters. This is undone in rt_mutex_set_owner(@task) at + * the end of this function. + */ + mark_rt_mutex_waiters(lock); + + /* + * If @lock has an owner, give up. + */ + if (rt_mutex_owner(lock)) + return 0; + + /* + * If @waiter != NULL, @task has already enqueued the waiter + * into @lock waiter list. If @waiter == NULL then this is a + * trylock attempt. + */ + if (waiter) { + /* + * If waiter is not the highest priority waiter of + * @lock, give up. + */ + if (waiter != rt_mutex_top_waiter(lock)) { + /* XXX lock_is_stealable() ? */ + return 0; + } + + /* + * We can acquire the lock. Remove the waiter from the + * lock waiters list. + */ + rt_mutex_dequeue(lock, waiter); + + } else { + /* + * If the lock has waiters already we check whether @task is + * eligible to take over the lock. + * + * If there are no other waiters, @task can acquire + * the lock. @task->pi_blocked_on is NULL, so it does + * not need to be dequeued. + */ + if (rt_mutex_has_waiters(lock)) { + struct task_struct *pown = rt_mutex_top_waiter(lock)->task; + + if (task != pown && !lock_is_stealable(task, pown, mode)) + return 0; + /* + * The current top waiter stays enqueued. We + * don't have to change anything in the lock + * waiters order. + */ + } else { + /* + * No waiters. Take the lock without the + * pi_lock dance.@task->pi_blocked_on is NULL + * and we have no waiters to enqueue in @task + * pi waiters list. + */ + goto takeit; + } + } + + /* + * Clear @task->pi_blocked_on. Requires protection by + * @task->pi_lock. Redundant operation for the @waiter == NULL + * case, but conditionals are more expensive than a redundant + * store. + */ + raw_spin_lock_irqsave(&task->pi_lock, flags); + task->pi_blocked_on = NULL; + /* + * Finish the lock acquisition. @task is the new owner. If + * other waiters exist we have to insert the highest priority + * waiter into @task->pi_waiters list. + */ + if (rt_mutex_has_waiters(lock)) + rt_mutex_enqueue_pi(task, rt_mutex_top_waiter(lock)); + raw_spin_unlock_irqrestore(&task->pi_lock, flags); + +takeit: + /* We got the lock. */ + debug_rt_mutex_lock(lock); + + /* + * This either preserves the RT_MUTEX_HAS_WAITERS bit if there + * are still waiters or clears it. + */ + rt_mutex_set_owner(lock, task); + + rt_mutex_deadlock_account_lock(lock, task); + + return 1; +} + +#ifdef CONFIG_PREEMPT_RT_FULL +/* + * preemptible spin_lock functions: + */ +static inline void rt_spin_lock_fastlock(struct rt_mutex *lock, + void (*slowfn)(struct rt_mutex *lock)) +{ + might_sleep_no_state_check(); + + if (likely(rt_mutex_cmpxchg(lock, NULL, current))) + rt_mutex_deadlock_account_lock(lock, current); + else + slowfn(lock); +} + +static inline void rt_spin_lock_fastunlock(struct rt_mutex *lock, + void (*slowfn)(struct rt_mutex *lock)) +{ + if (likely(rt_mutex_cmpxchg(lock, current, NULL))) + rt_mutex_deadlock_account_unlock(current); + else + slowfn(lock); +} +#ifdef CONFIG_SMP +/* + * Note that owner is a speculative pointer and dereferencing relies + * on rcu_read_lock() and the check against the lock owner. + */ +static int adaptive_wait(struct rt_mutex *lock, + struct task_struct *owner) +{ + int res = 0; + + rcu_read_lock(); + for (;;) { + if (owner != rt_mutex_owner(lock)) + break; + /* + * Ensure that owner->on_cpu is dereferenced _after_ + * checking the above to be valid. + */ + barrier(); + if (!owner->on_cpu) { + res = 1; + break; + } + cpu_relax(); + } + rcu_read_unlock(); + return res; +} +#else +static int adaptive_wait(struct rt_mutex *lock, + struct task_struct *orig_owner) +{ + return 1; +} +#endif + +# define pi_lock(lock) raw_spin_lock_irq(lock) +# define pi_unlock(lock) raw_spin_unlock_irq(lock) + +static int task_blocks_on_rt_mutex(struct rt_mutex *lock, + struct rt_mutex_waiter *waiter, + struct task_struct *task, + enum rtmutex_chainwalk chwalk); +/* + * Slow path lock function spin_lock style: this variant is very + * careful not to miss any non-lock wakeups. + * + * We store the current state under p->pi_lock in p->saved_state and + * the try_to_wake_up() code handles this accordingly. + */ +static void noinline __sched rt_spin_lock_slowlock(struct rt_mutex *lock) +{ + struct task_struct *lock_owner, *self = current; + struct rt_mutex_waiter waiter, *top_waiter; + int ret; + + rt_mutex_init_waiter(&waiter, true); + + raw_spin_lock(&lock->wait_lock); + + if (__try_to_take_rt_mutex(lock, self, NULL, STEAL_LATERAL)) { + raw_spin_unlock(&lock->wait_lock); + return; + } + + BUG_ON(rt_mutex_owner(lock) == self); + + /* + * We save whatever state the task is in and we'll restore it + * after acquiring the lock taking real wakeups into account + * as well. We are serialized via pi_lock against wakeups. See + * try_to_wake_up(). + */ + pi_lock(&self->pi_lock); + self->saved_state = self->state; + __set_current_state_no_track(TASK_UNINTERRUPTIBLE); + pi_unlock(&self->pi_lock); + + ret = task_blocks_on_rt_mutex(lock, &waiter, self, 0); + BUG_ON(ret); + + for (;;) { + /* Try to acquire the lock again. */ + if (__try_to_take_rt_mutex(lock, self, &waiter, STEAL_LATERAL)) + break; + + top_waiter = rt_mutex_top_waiter(lock); + lock_owner = rt_mutex_owner(lock); + + raw_spin_unlock(&lock->wait_lock); + + debug_rt_mutex_print_deadlock(&waiter); + + if (top_waiter != &waiter || adaptive_wait(lock, lock_owner)) + schedule_rt_mutex(lock); + + raw_spin_lock(&lock->wait_lock); + + pi_lock(&self->pi_lock); + __set_current_state_no_track(TASK_UNINTERRUPTIBLE); + pi_unlock(&self->pi_lock); + } + + /* + * Restore the task state to current->saved_state. We set it + * to the original state above and the try_to_wake_up() code + * has possibly updated it when a real (non-rtmutex) wakeup + * happened while we were blocked. Clear saved_state so + * try_to_wakeup() does not get confused. + */ + pi_lock(&self->pi_lock); + __set_current_state_no_track(self->saved_state); + self->saved_state = TASK_RUNNING; + pi_unlock(&self->pi_lock); + + /* + * try_to_take_rt_mutex() sets the waiter bit + * unconditionally. We might have to fix that up: + */ + fixup_rt_mutex_waiters(lock); + + BUG_ON(rt_mutex_has_waiters(lock) && &waiter == rt_mutex_top_waiter(lock)); + BUG_ON(!RB_EMPTY_NODE(&waiter.tree_entry)); + + raw_spin_unlock(&lock->wait_lock); + + debug_rt_mutex_free_waiter(&waiter); +} + +static void wakeup_next_waiter(struct rt_mutex *lock); +/* + * Slow path to release a rt_mutex spin_lock style + */ +static void noinline __sched rt_spin_lock_slowunlock(struct rt_mutex *lock) +{ + raw_spin_lock(&lock->wait_lock); + + debug_rt_mutex_unlock(lock); + + rt_mutex_deadlock_account_unlock(current); + + if (!rt_mutex_has_waiters(lock)) { + lock->owner = NULL; + raw_spin_unlock(&lock->wait_lock); + return; + } + + wakeup_next_waiter(lock); + + raw_spin_unlock(&lock->wait_lock); + + /* Undo pi boosting.when necessary */ + rt_mutex_adjust_prio(current); +} + +void __lockfunc rt_spin_lock(spinlock_t *lock) +{ + rt_spin_lock_fastlock(&lock->lock, rt_spin_lock_slowlock); + spin_acquire(&lock->dep_map, 0, 0, _RET_IP_); +} +EXPORT_SYMBOL(rt_spin_lock); + +void __lockfunc __rt_spin_lock(struct rt_mutex *lock) +{ + rt_spin_lock_fastlock(lock, rt_spin_lock_slowlock); +} +EXPORT_SYMBOL(__rt_spin_lock); + +#ifdef CONFIG_DEBUG_LOCK_ALLOC +void __lockfunc rt_spin_lock_nested(spinlock_t *lock, int subclass) +{ + rt_spin_lock_fastlock(&lock->lock, rt_spin_lock_slowlock); + spin_acquire(&lock->dep_map, subclass, 0, _RET_IP_); +} +EXPORT_SYMBOL(rt_spin_lock_nested); +#endif + +void __lockfunc rt_spin_unlock(spinlock_t *lock) +{ + /* NOTE: we always pass in '1' for nested, for simplicity */ + spin_release(&lock->dep_map, 1, _RET_IP_); + rt_spin_lock_fastunlock(&lock->lock, rt_spin_lock_slowunlock); +} +EXPORT_SYMBOL(rt_spin_unlock); + +void __lockfunc __rt_spin_unlock(struct rt_mutex *lock) +{ + rt_spin_lock_fastunlock(lock, rt_spin_lock_slowunlock); +} +EXPORT_SYMBOL(__rt_spin_unlock); + +/* + * Wait for the lock to get unlocked: instead of polling for an unlock + * (like raw spinlocks do), we lock and unlock, to force the kernel to + * schedule if there's contention: + */ +void __lockfunc rt_spin_unlock_wait(spinlock_t *lock) +{ + spin_lock(lock); + spin_unlock(lock); +} +EXPORT_SYMBOL(rt_spin_unlock_wait); + +int __lockfunc __rt_spin_trylock(struct rt_mutex *lock) +{ + return rt_mutex_trylock(lock); +} + +int __lockfunc rt_spin_trylock(spinlock_t *lock) +{ + int ret = rt_mutex_trylock(&lock->lock); + + if (ret) + spin_acquire(&lock->dep_map, 0, 1, _RET_IP_); + return ret; +} +EXPORT_SYMBOL(rt_spin_trylock); + +int __lockfunc rt_spin_trylock_bh(spinlock_t *lock) +{ + int ret; + + local_bh_disable(); + ret = rt_mutex_trylock(&lock->lock); + if (ret) { + migrate_disable(); + spin_acquire(&lock->dep_map, 0, 1, _RET_IP_); + } else + local_bh_enable(); + return ret; +} +EXPORT_SYMBOL(rt_spin_trylock_bh); + +int __lockfunc rt_spin_trylock_irqsave(spinlock_t *lock, unsigned long *flags) +{ + int ret; + + *flags = 0; + ret = rt_mutex_trylock(&lock->lock); + if (ret) { + migrate_disable(); + spin_acquire(&lock->dep_map, 0, 1, _RET_IP_); + } + return ret; +} +EXPORT_SYMBOL(rt_spin_trylock_irqsave); + +int atomic_dec_and_spin_lock(atomic_t *atomic, spinlock_t *lock) +{ + /* Subtract 1 from counter unless that drops it to 0 (ie. it was 1) */ + if (atomic_add_unless(atomic, -1, 1)) + return 0; + migrate_disable(); + rt_spin_lock(lock); + if (atomic_dec_and_test(atomic)) + return 1; + rt_spin_unlock(lock); + migrate_enable(); + return 0; +} +EXPORT_SYMBOL(atomic_dec_and_spin_lock); + + void +__rt_spin_lock_init(spinlock_t *lock, char *name, struct lock_class_key *key) +{ +#ifdef CONFIG_DEBUG_LOCK_ALLOC + /* + * Make sure we are not reinitializing a held lock: + */ + debug_check_no_locks_freed((void *)lock, sizeof(*lock)); + lockdep_init_map(&lock->dep_map, name, key, 0); +#endif +} +EXPORT_SYMBOL(__rt_spin_lock_init); + +#endif /* PREEMPT_RT_FULL */ + +#ifdef CONFIG_PREEMPT_RT_FULL + static inline int __sched +__mutex_lock_check_stamp(struct rt_mutex *lock, struct ww_acquire_ctx *ctx) +{ + struct ww_mutex *ww = container_of(lock, struct ww_mutex, base.lock); + struct ww_acquire_ctx *hold_ctx = ACCESS_ONCE(ww->ctx); + + if (!hold_ctx) + return 0; + + if (unlikely(ctx == hold_ctx)) + return -EALREADY; + + if (ctx->stamp - hold_ctx->stamp <= LONG_MAX && + (ctx->stamp != hold_ctx->stamp || ctx > hold_ctx)) { +#ifdef CONFIG_DEBUG_MUTEXES + DEBUG_LOCKS_WARN_ON(ctx->contending_lock); + ctx->contending_lock = ww; +#endif + return -EDEADLK; + } + + return 0; +} +#else + static inline int __sched +__mutex_lock_check_stamp(struct rt_mutex *lock, struct ww_acquire_ctx *ctx) +{ + BUG(); + return 0; +} + +#endif + +static inline int +try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task, + struct rt_mutex_waiter *waiter) +{ + return __try_to_take_rt_mutex(lock, task, waiter, STEAL_NORMAL); +} + +/* + * Task blocks on lock. + * + * Prepare waiter and propagate pi chain + * + * This must be called with lock->wait_lock held. + */ +static int task_blocks_on_rt_mutex(struct rt_mutex *lock, + struct rt_mutex_waiter *waiter, + struct task_struct *task, + enum rtmutex_chainwalk chwalk) +{ + struct task_struct *owner = rt_mutex_owner(lock); + struct rt_mutex_waiter *top_waiter = waiter; + struct rt_mutex *next_lock; + int chain_walk = 0, res; + unsigned long flags; + + /* + * Early deadlock detection. We really don't want the task to + * enqueue on itself just to untangle the mess later. It's not + * only an optimization. We drop the locks, so another waiter + * can come in before the chain walk detects the deadlock. So + * the other will detect the deadlock and return -EDEADLOCK, + * which is wrong, as the other waiter is not in a deadlock + * situation. + */ + if (owner == task) + return -EDEADLK; + + raw_spin_lock_irqsave(&task->pi_lock, flags); + + /* + * In the case of futex requeue PI, this will be a proxy + * lock. The task will wake unaware that it is enqueueed on + * this lock. Avoid blocking on two locks and corrupting + * pi_blocked_on via the PI_WAKEUP_INPROGRESS + * flag. futex_wait_requeue_pi() sets this when it wakes up + * before requeue (due to a signal or timeout). Do not enqueue + * the task if PI_WAKEUP_INPROGRESS is set. + */ + if (task != current && task->pi_blocked_on == PI_WAKEUP_INPROGRESS) { + raw_spin_unlock_irqrestore(&task->pi_lock, flags); + return -EAGAIN; + } + + BUG_ON(rt_mutex_real_waiter(task->pi_blocked_on)); + + __rt_mutex_adjust_prio(task); + waiter->task = task; + waiter->lock = lock; + waiter->prio = task->prio; + + /* Get the top priority waiter on the lock */ + if (rt_mutex_has_waiters(lock)) + top_waiter = rt_mutex_top_waiter(lock); + rt_mutex_enqueue(lock, waiter); + + task->pi_blocked_on = waiter; + + raw_spin_unlock_irqrestore(&task->pi_lock, flags); + + if (!owner) + return 0; + + raw_spin_lock_irqsave(&owner->pi_lock, flags); + if (waiter == rt_mutex_top_waiter(lock)) { + rt_mutex_dequeue_pi(owner, top_waiter); + rt_mutex_enqueue_pi(owner, waiter); + + __rt_mutex_adjust_prio(owner); + if (rt_mutex_real_waiter(owner->pi_blocked_on)) + chain_walk = 1; + } else if (rt_mutex_cond_detect_deadlock(waiter, chwalk)) { + chain_walk = 1; + } + + /* Store the lock on which owner is blocked or NULL */ + next_lock = task_blocked_on_lock(owner); + + raw_spin_unlock_irqrestore(&owner->pi_lock, flags); + /* + * Even if full deadlock detection is on, if the owner is not + * blocked itself, we can avoid finding this out in the chain + * walk. + */ + if (!chain_walk || !next_lock) + return 0; + + /* + * The owner can't disappear while holding a lock, + * so the owner struct is protected by wait_lock. + * Gets dropped in rt_mutex_adjust_prio_chain()! + */ + get_task_struct(owner); + + raw_spin_unlock(&lock->wait_lock); + + res = rt_mutex_adjust_prio_chain(owner, chwalk, lock, + next_lock, waiter, task); + + raw_spin_lock(&lock->wait_lock); + + return res; +} + +/* + * Wake up the next waiter on the lock. + * + * Remove the top waiter from the current tasks pi waiter list, + * wake it up and return whether the current task needs to undo + * a potential priority boosting. + * + * Called with lock->wait_lock held. + */ +static void wakeup_next_waiter(struct rt_mutex *lock) +{ + struct rt_mutex_waiter *waiter; + unsigned long flags; + + raw_spin_lock_irqsave(¤t->pi_lock, flags); + + waiter = rt_mutex_top_waiter(lock); + + /* + * Remove it from current->pi_waiters. We do not adjust a + * possible priority boost right now. We execute wakeup in the + * boosted mode and go back to normal after releasing + * lock->wait_lock. + */ + rt_mutex_dequeue_pi(current, waiter); + + /* + * As we are waking up the top waiter, and the waiter stays + * queued on the lock until it gets the lock, this lock + * obviously has waiters. Just set the bit here and this has + * the added benefit of forcing all new tasks into the + * slow path making sure no task of lower priority than + * the top waiter can steal this lock. + */ + lock->owner = (void *) RT_MUTEX_HAS_WAITERS; + + raw_spin_unlock_irqrestore(¤t->pi_lock, flags); + + /* + * It's safe to dereference waiter as it cannot go away as + * long as we hold lock->wait_lock. The waiter task needs to + * acquire it in order to dequeue the waiter. + */ + rt_mutex_wake_waiter(waiter); +} + +/* + * Remove a waiter from a lock and give up + * + * Must be called with lock->wait_lock held and + * have just failed to try_to_take_rt_mutex(). + */ +static void remove_waiter(struct rt_mutex *lock, + struct rt_mutex_waiter *waiter) +{ + bool is_top_waiter = (waiter == rt_mutex_top_waiter(lock)); + struct task_struct *owner = rt_mutex_owner(lock); + struct rt_mutex *next_lock = NULL; + unsigned long flags; + + raw_spin_lock_irqsave(¤t->pi_lock, flags); + rt_mutex_dequeue(lock, waiter); + current->pi_blocked_on = NULL; + raw_spin_unlock_irqrestore(¤t->pi_lock, flags); + + /* + * Only update priority if the waiter was the highest priority + * waiter of the lock and there is an owner to update. + */ + if (!owner || !is_top_waiter) + return; + + raw_spin_lock_irqsave(&owner->pi_lock, flags); + + rt_mutex_dequeue_pi(owner, waiter); + + if (rt_mutex_has_waiters(lock)) + rt_mutex_enqueue_pi(owner, rt_mutex_top_waiter(lock)); + + __rt_mutex_adjust_prio(owner); + + /* Store the lock on which owner is blocked or NULL */ + if (rt_mutex_real_waiter(owner->pi_blocked_on)) + next_lock = task_blocked_on_lock(owner); + + raw_spin_unlock_irqrestore(&owner->pi_lock, flags); + + /* + * Don't walk the chain, if the owner task is not blocked + * itself. + */ + if (!next_lock) + return; + + /* gets dropped in rt_mutex_adjust_prio_chain()! */ + get_task_struct(owner); + + raw_spin_unlock(&lock->wait_lock); + + rt_mutex_adjust_prio_chain(owner, RT_MUTEX_MIN_CHAINWALK, lock, + next_lock, NULL, current); + + raw_spin_lock(&lock->wait_lock); +} + +/* + * Recheck the pi chain, in case we got a priority setting + * + * Called from sched_setscheduler + */ +void rt_mutex_adjust_pi(struct task_struct *task) +{ + struct rt_mutex_waiter *waiter; + struct rt_mutex *next_lock; + unsigned long flags; + + raw_spin_lock_irqsave(&task->pi_lock, flags); + + waiter = task->pi_blocked_on; + if (!rt_mutex_real_waiter(waiter) || (waiter->prio == task->prio && + !dl_prio(task->prio))) { + raw_spin_unlock_irqrestore(&task->pi_lock, flags); + return; + } + next_lock = waiter->lock; + + /* gets dropped in rt_mutex_adjust_prio_chain()! */ + get_task_struct(task); + + raw_spin_unlock_irqrestore(&task->pi_lock, flags); + rt_mutex_adjust_prio_chain(task, RT_MUTEX_MIN_CHAINWALK, NULL, + next_lock, NULL, task); +} + +/** + * __rt_mutex_slowlock() - Perform the wait-wake-try-to-take loop + * @lock: the rt_mutex to take + * @state: the state the task should block in (TASK_INTERRUPTIBLE + * or TASK_UNINTERRUPTIBLE) + * @timeout: the pre-initialized and started timer, or NULL for none + * @waiter: the pre-initialized rt_mutex_waiter + * + * lock->wait_lock must be held by the caller. + */ +static int __sched +__rt_mutex_slowlock(struct rt_mutex *lock, int state, + struct hrtimer_sleeper *timeout, + struct rt_mutex_waiter *waiter, + struct ww_acquire_ctx *ww_ctx) +{ + int ret = 0; + + for (;;) { + /* Try to acquire the lock: */ + if (try_to_take_rt_mutex(lock, current, waiter)) + break; + + /* + * TASK_INTERRUPTIBLE checks for signals and + * timeout. Ignored otherwise. + */ + if (unlikely(state == TASK_INTERRUPTIBLE)) { + /* Signal pending? */ + if (signal_pending(current)) + ret = -EINTR; + if (timeout && !timeout->task) + ret = -ETIMEDOUT; + if (ret) + break; + } + + if (ww_ctx && ww_ctx->acquired > 0) { + ret = __mutex_lock_check_stamp(lock, ww_ctx); + if (ret) + break; + } + + raw_spin_unlock(&lock->wait_lock); + + debug_rt_mutex_print_deadlock(waiter); + + schedule_rt_mutex(lock); + + raw_spin_lock(&lock->wait_lock); + set_current_state(state); + } + + __set_current_state(TASK_RUNNING); + return ret; +} + +static void rt_mutex_handle_deadlock(int res, int detect_deadlock, + struct rt_mutex_waiter *w) +{ + /* + * If the result is not -EDEADLOCK or the caller requested + * deadlock detection, nothing to do here. + */ + if (res != -EDEADLOCK || detect_deadlock) + return; + + /* + * Yell lowdly and stop the task right here. + */ + rt_mutex_print_deadlock(w); + while (1) { + set_current_state(TASK_INTERRUPTIBLE); + schedule(); + } +} + +static __always_inline void ww_mutex_lock_acquired(struct ww_mutex *ww, + struct ww_acquire_ctx *ww_ctx) +{ +#ifdef CONFIG_DEBUG_MUTEXES + /* + * If this WARN_ON triggers, you used ww_mutex_lock to acquire, + * but released with a normal mutex_unlock in this call. + * + * This should never happen, always use ww_mutex_unlock. + */ + DEBUG_LOCKS_WARN_ON(ww->ctx); + + /* + * Not quite done after calling ww_acquire_done() ? + */ + DEBUG_LOCKS_WARN_ON(ww_ctx->done_acquire); + + if (ww_ctx->contending_lock) { + /* + * After -EDEADLK you tried to + * acquire a different ww_mutex? Bad! + */ + DEBUG_LOCKS_WARN_ON(ww_ctx->contending_lock != ww); + + /* + * You called ww_mutex_lock after receiving -EDEADLK, + * but 'forgot' to unlock everything else first? + */ + DEBUG_LOCKS_WARN_ON(ww_ctx->acquired > 0); + ww_ctx->contending_lock = NULL; + } + + /* + * Naughty, using a different class will lead to undefined behavior! + */ + DEBUG_LOCKS_WARN_ON(ww_ctx->ww_class != ww->ww_class); +#endif + ww_ctx->acquired++; +} + +#ifdef CONFIG_PREEMPT_RT_FULL +static void ww_mutex_account_lock(struct rt_mutex *lock, + struct ww_acquire_ctx *ww_ctx) +{ + struct ww_mutex *ww = container_of(lock, struct ww_mutex, base.lock); + struct rt_mutex_waiter *waiter, *n; + + /* + * This branch gets optimized out for the common case, + * and is only important for ww_mutex_lock. + */ + ww_mutex_lock_acquired(ww, ww_ctx); + ww->ctx = ww_ctx; + + /* + * Give any possible sleeping processes the chance to wake up, + * so they can recheck if they have to back off. + */ + rbtree_postorder_for_each_entry_safe(waiter, n, &lock->waiters, + tree_entry) { + /* XXX debug rt mutex waiter wakeup */ + + BUG_ON(waiter->lock != lock); + rt_mutex_wake_waiter(waiter); + } +} + +#else + +static void ww_mutex_account_lock(struct rt_mutex *lock, + struct ww_acquire_ctx *ww_ctx) +{ + BUG(); +} +#endif + +/* + * Slow path lock function: + */ +static int __sched +rt_mutex_slowlock(struct rt_mutex *lock, int state, + struct hrtimer_sleeper *timeout, + enum rtmutex_chainwalk chwalk, + struct ww_acquire_ctx *ww_ctx) +{ + struct rt_mutex_waiter waiter; + int ret = 0; + + rt_mutex_init_waiter(&waiter, false); + + raw_spin_lock(&lock->wait_lock); + + /* Try to acquire the lock again: */ + if (try_to_take_rt_mutex(lock, current, NULL)) { + if (ww_ctx) + ww_mutex_account_lock(lock, ww_ctx); + raw_spin_unlock(&lock->wait_lock); + return 0; + } + + set_current_state(state); + + /* Setup the timer, when timeout != NULL */ + if (unlikely(timeout)) { + hrtimer_start_expires(&timeout->timer, HRTIMER_MODE_ABS); + if (!hrtimer_active(&timeout->timer)) + timeout->task = NULL; + } + + ret = task_blocks_on_rt_mutex(lock, &waiter, current, chwalk); + + if (likely(!ret)) + /* sleep on the mutex */ + ret = __rt_mutex_slowlock(lock, state, timeout, &waiter, + ww_ctx); + else if (ww_ctx) { + /* ww_mutex received EDEADLK, let it become EALREADY */ + ret = __mutex_lock_check_stamp(lock, ww_ctx); + BUG_ON(!ret); + } + + if (unlikely(ret)) { + __set_current_state(TASK_RUNNING); + if (rt_mutex_has_waiters(lock)) + remove_waiter(lock, &waiter); + /* ww_mutex want to report EDEADLK/EALREADY, let them */ + if (!ww_ctx) + rt_mutex_handle_deadlock(ret, chwalk, &waiter); + } else if (ww_ctx) { + ww_mutex_account_lock(lock, ww_ctx); + } + + /* + * try_to_take_rt_mutex() sets the waiter bit + * unconditionally. We might have to fix that up. + */ + fixup_rt_mutex_waiters(lock); + + raw_spin_unlock(&lock->wait_lock); + + /* Remove pending timer: */ + if (unlikely(timeout)) + hrtimer_cancel(&timeout->timer); + + debug_rt_mutex_free_waiter(&waiter); + + return ret; +} + +/* + * Slow path try-lock function: + */ +static inline int rt_mutex_slowtrylock(struct rt_mutex *lock) +{ + int ret; + + /* + * If the lock already has an owner we fail to get the lock. + * This can be done without taking the @lock->wait_lock as + * it is only being read, and this is a trylock anyway. + */ + if (rt_mutex_owner(lock)) + return 0; + + /* + * The mutex has currently no owner. Lock the wait lock and + * try to acquire the lock. + */ + raw_spin_lock(&lock->wait_lock); + + ret = try_to_take_rt_mutex(lock, current, NULL); + + /* + * try_to_take_rt_mutex() sets the lock waiters bit + * unconditionally. Clean this up. + */ + fixup_rt_mutex_waiters(lock); + + raw_spin_unlock(&lock->wait_lock); + + return ret; +} + +/* + * Slow path to release a rt-mutex: + */ +static bool __sched +rt_mutex_slowunlock(struct rt_mutex *lock) +{ + raw_spin_lock(&lock->wait_lock); + + debug_rt_mutex_unlock(lock); + + rt_mutex_deadlock_account_unlock(current); + + /* + * We must be careful here if the fast path is enabled. If we + * have no waiters queued we cannot set owner to NULL here + * because of: + * + * foo->lock->owner = NULL; + * rtmutex_lock(foo->lock); <- fast path + * free = atomic_dec_and_test(foo->refcnt); + * rtmutex_unlock(foo->lock); <- fast path + * if (free) + * kfree(foo); + * raw_spin_unlock(foo->lock->wait_lock); + * + * So for the fastpath enabled kernel: + * + * Nothing can set the waiters bit as long as we hold + * lock->wait_lock. So we do the following sequence: + * + * owner = rt_mutex_owner(lock); + * clear_rt_mutex_waiters(lock); + * raw_spin_unlock(&lock->wait_lock); + * if (cmpxchg(&lock->owner, owner, 0) == owner) + * return; + * goto retry; + * + * The fastpath disabled variant is simple as all access to + * lock->owner is serialized by lock->wait_lock: + * + * lock->owner = NULL; + * raw_spin_unlock(&lock->wait_lock); + */ + while (!rt_mutex_has_waiters(lock)) { + /* Drops lock->wait_lock ! */ + if (unlock_rt_mutex_safe(lock) == true) + return false; + /* Relock the rtmutex and try again */ + raw_spin_lock(&lock->wait_lock); + } + + /* + * The wakeup next waiter path does not suffer from the above + * race. See the comments there. + */ + wakeup_next_waiter(lock); + + raw_spin_unlock(&lock->wait_lock); + + return true; +} + +/* + * debug aware fast / slowpath lock,trylock,unlock + * + * The atomic acquire/release ops are compiled away, when either the + * architecture does not support cmpxchg or when debugging is enabled. + */ +static inline int +rt_mutex_fastlock(struct rt_mutex *lock, int state, + struct ww_acquire_ctx *ww_ctx, + int (*slowfn)(struct rt_mutex *lock, int state, + struct hrtimer_sleeper *timeout, + enum rtmutex_chainwalk chwalk, + struct ww_acquire_ctx *ww_ctx)) +{ + if (likely(rt_mutex_cmpxchg(lock, NULL, current))) { + rt_mutex_deadlock_account_lock(lock, current); + return 0; + } else + return slowfn(lock, state, NULL, RT_MUTEX_MIN_CHAINWALK, + ww_ctx); +} + +static inline int +rt_mutex_timed_fastlock(struct rt_mutex *lock, int state, + struct hrtimer_sleeper *timeout, + enum rtmutex_chainwalk chwalk, + struct ww_acquire_ctx *ww_ctx, + int (*slowfn)(struct rt_mutex *lock, int state, + struct hrtimer_sleeper *timeout, + enum rtmutex_chainwalk chwalk, + struct ww_acquire_ctx *ww_ctx)) +{ + if (chwalk == RT_MUTEX_MIN_CHAINWALK && + likely(rt_mutex_cmpxchg(lock, NULL, current))) { + rt_mutex_deadlock_account_lock(lock, current); + return 0; + } else + return slowfn(lock, state, timeout, chwalk, ww_ctx); +} + +static inline int +rt_mutex_fasttrylock(struct rt_mutex *lock, + int (*slowfn)(struct rt_mutex *lock)) +{ + if (likely(rt_mutex_cmpxchg(lock, NULL, current))) { + rt_mutex_deadlock_account_lock(lock, current); + return 1; + } + return slowfn(lock); +} + +static inline void +rt_mutex_fastunlock(struct rt_mutex *lock, + bool (*slowfn)(struct rt_mutex *lock)) +{ + if (likely(rt_mutex_cmpxchg(lock, current, NULL))) { + rt_mutex_deadlock_account_unlock(current); + } else if (slowfn(lock)) { + /* Undo pi boosting if necessary: */ + rt_mutex_adjust_prio(current); + } +} + +/** + * rt_mutex_lock - lock a rt_mutex + * + * @lock: the rt_mutex to be locked + */ +void __sched rt_mutex_lock(struct rt_mutex *lock) +{ + might_sleep(); + + rt_mutex_fastlock(lock, TASK_UNINTERRUPTIBLE, NULL, rt_mutex_slowlock); +} +EXPORT_SYMBOL_GPL(rt_mutex_lock); + +/** + * rt_mutex_lock_interruptible - lock a rt_mutex interruptible + * + * @lock: the rt_mutex to be locked + * + * Returns: + * 0 on success + * -EINTR when interrupted by a signal + */ +int __sched rt_mutex_lock_interruptible(struct rt_mutex *lock) +{ + might_sleep(); + + return rt_mutex_fastlock(lock, TASK_INTERRUPTIBLE, NULL, rt_mutex_slowlock); +} +EXPORT_SYMBOL_GPL(rt_mutex_lock_interruptible); + +/* + * Futex variant with full deadlock detection. + */ +int rt_mutex_timed_futex_lock(struct rt_mutex *lock, + struct hrtimer_sleeper *timeout) +{ + might_sleep(); + + return rt_mutex_timed_fastlock(lock, TASK_INTERRUPTIBLE, timeout, + RT_MUTEX_FULL_CHAINWALK, NULL, + rt_mutex_slowlock); +} + +/** + * rt_mutex_lock_killable - lock a rt_mutex killable + * + * @lock: the rt_mutex to be locked + * @detect_deadlock: deadlock detection on/off + * + * Returns: + * 0 on success + * -EINTR when interrupted by a signal + * -EDEADLK when the lock would deadlock (when deadlock detection is on) + */ +int __sched rt_mutex_lock_killable(struct rt_mutex *lock) +{ + might_sleep(); + + return rt_mutex_fastlock(lock, TASK_KILLABLE, NULL, rt_mutex_slowlock); +} +EXPORT_SYMBOL_GPL(rt_mutex_lock_killable); + +/** + * rt_mutex_timed_lock - lock a rt_mutex interruptible + * the timeout structure is provided + * by the caller + * + * @lock: the rt_mutex to be locked + * @timeout: timeout structure or NULL (no timeout) + * + * Returns: + * 0 on success + * -EINTR when interrupted by a signal + * -ETIMEDOUT when the timeout expired + */ +int +rt_mutex_timed_lock(struct rt_mutex *lock, struct hrtimer_sleeper *timeout) +{ + might_sleep(); + + return rt_mutex_timed_fastlock(lock, TASK_INTERRUPTIBLE, timeout, + RT_MUTEX_MIN_CHAINWALK, + NULL, + rt_mutex_slowlock); +} +EXPORT_SYMBOL_GPL(rt_mutex_timed_lock); + +/** + * rt_mutex_trylock - try to lock a rt_mutex + * + * @lock: the rt_mutex to be locked + * + * Returns 1 on success and 0 on contention + */ +int __sched rt_mutex_trylock(struct rt_mutex *lock) +{ + return rt_mutex_fasttrylock(lock, rt_mutex_slowtrylock); +} +EXPORT_SYMBOL_GPL(rt_mutex_trylock); + +/** + * rt_mutex_unlock - unlock a rt_mutex + * + * @lock: the rt_mutex to be unlocked + */ +void __sched rt_mutex_unlock(struct rt_mutex *lock) +{ + rt_mutex_fastunlock(lock, rt_mutex_slowunlock); +} +EXPORT_SYMBOL_GPL(rt_mutex_unlock); + +/** + * rt_mutex_futex_unlock - Futex variant of rt_mutex_unlock + * @lock: the rt_mutex to be unlocked + * + * Returns: true/false indicating whether priority adjustment is + * required or not. + */ +bool __sched rt_mutex_futex_unlock(struct rt_mutex *lock) +{ + if (likely(rt_mutex_cmpxchg(lock, current, NULL))) { + rt_mutex_deadlock_account_unlock(current); + return false; + } + return rt_mutex_slowunlock(lock); +} + +/** + * rt_mutex_destroy - mark a mutex unusable + * @lock: the mutex to be destroyed + * + * This function marks the mutex uninitialized, and any subsequent + * use of the mutex is forbidden. The mutex must not be locked when + * this function is called. + */ +void rt_mutex_destroy(struct rt_mutex *lock) +{ + WARN_ON(rt_mutex_is_locked(lock)); +#ifdef CONFIG_DEBUG_RT_MUTEXES + lock->magic = NULL; +#endif +} + +EXPORT_SYMBOL_GPL(rt_mutex_destroy); + +/** + * __rt_mutex_init - initialize the rt lock + * + * @lock: the rt lock to be initialized + * + * Initialize the rt lock to unlocked state. + * + * Initializing of a locked rt lock is not allowed + */ +void __rt_mutex_init(struct rt_mutex *lock, const char *name) +{ + lock->owner = NULL; + lock->waiters = RB_ROOT; + lock->waiters_leftmost = NULL; + + debug_rt_mutex_init(lock, name); +} +EXPORT_SYMBOL(__rt_mutex_init); + +/** + * rt_mutex_init_proxy_locked - initialize and lock a rt_mutex on behalf of a + * proxy owner + * + * @lock: the rt_mutex to be locked + * @proxy_owner:the task to set as owner + * + * No locking. Caller has to do serializing itself + * Special API call for PI-futex support + */ +void rt_mutex_init_proxy_locked(struct rt_mutex *lock, + struct task_struct *proxy_owner) +{ + rt_mutex_init(lock); + debug_rt_mutex_proxy_lock(lock, proxy_owner); + rt_mutex_set_owner(lock, proxy_owner); + rt_mutex_deadlock_account_lock(lock, proxy_owner); +} + +/** + * rt_mutex_proxy_unlock - release a lock on behalf of owner + * + * @lock: the rt_mutex to be locked + * + * No locking. Caller has to do serializing itself + * Special API call for PI-futex support + */ +void rt_mutex_proxy_unlock(struct rt_mutex *lock, + struct task_struct *proxy_owner) +{ + debug_rt_mutex_proxy_unlock(lock); + rt_mutex_set_owner(lock, NULL); + rt_mutex_deadlock_account_unlock(proxy_owner); +} + +/** + * rt_mutex_start_proxy_lock() - Start lock acquisition for another task + * @lock: the rt_mutex to take + * @waiter: the pre-initialized rt_mutex_waiter + * @task: the task to prepare + * + * Returns: + * 0 - task blocked on lock + * 1 - acquired the lock for task, caller should wake it up + * <0 - error + * + * Special API call for FUTEX_REQUEUE_PI support. + */ +int rt_mutex_start_proxy_lock(struct rt_mutex *lock, + struct rt_mutex_waiter *waiter, + struct task_struct *task) +{ + int ret; + + raw_spin_lock(&lock->wait_lock); + + if (try_to_take_rt_mutex(lock, task, NULL)) { + raw_spin_unlock(&lock->wait_lock); + return 1; + } + +#ifdef CONFIG_PREEMPT_RT_FULL + /* + * In PREEMPT_RT there's an added race. + * If the task, that we are about to requeue, times out, + * it can set the PI_WAKEUP_INPROGRESS. This tells the requeue + * to skip this task. But right after the task sets + * its pi_blocked_on to PI_WAKEUP_INPROGRESS it can then + * block on the spin_lock(&hb->lock), which in RT is an rtmutex. + * This will replace the PI_WAKEUP_INPROGRESS with the actual + * lock that it blocks on. We *must not* place this task + * on this proxy lock in that case. + * + * To prevent this race, we first take the task's pi_lock + * and check if it has updated its pi_blocked_on. If it has, + * we assume that it woke up and we return -EAGAIN. + * Otherwise, we set the task's pi_blocked_on to + * PI_REQUEUE_INPROGRESS, so that if the task is waking up + * it will know that we are in the process of requeuing it. + */ + raw_spin_lock_irq(&task->pi_lock); + if (task->pi_blocked_on) { + raw_spin_unlock_irq(&task->pi_lock); + raw_spin_unlock(&lock->wait_lock); + return -EAGAIN; + } + task->pi_blocked_on = PI_REQUEUE_INPROGRESS; + raw_spin_unlock_irq(&task->pi_lock); +#endif + + /* We enforce deadlock detection for futexes */ + ret = task_blocks_on_rt_mutex(lock, waiter, task, + RT_MUTEX_FULL_CHAINWALK); + + if (ret && !rt_mutex_owner(lock)) { + /* + * Reset the return value. We might have + * returned with -EDEADLK and the owner + * released the lock while we were walking the + * pi chain. Let the waiter sort it out. + */ + ret = 0; + } + + if (unlikely(ret)) + remove_waiter(lock, waiter); + + raw_spin_unlock(&lock->wait_lock); + + debug_rt_mutex_print_deadlock(waiter); + + return ret; +} + +/** + * rt_mutex_next_owner - return the next owner of the lock + * + * @lock: the rt lock query + * + * Returns the next owner of the lock or NULL + * + * Caller has to serialize against other accessors to the lock + * itself. + * + * Special API call for PI-futex support + */ +struct task_struct *rt_mutex_next_owner(struct rt_mutex *lock) +{ + if (!rt_mutex_has_waiters(lock)) + return NULL; + + return rt_mutex_top_waiter(lock)->task; +} + +/** + * rt_mutex_finish_proxy_lock() - Complete lock acquisition + * @lock: the rt_mutex we were woken on + * @to: the timeout, null if none. hrtimer should already have + * been started. + * @waiter: the pre-initialized rt_mutex_waiter + * + * Complete the lock acquisition started our behalf by another thread. + * + * Returns: + * 0 - success + * <0 - error, one of -EINTR, -ETIMEDOUT + * + * Special API call for PI-futex requeue support + */ +int rt_mutex_finish_proxy_lock(struct rt_mutex *lock, + struct hrtimer_sleeper *to, + struct rt_mutex_waiter *waiter) +{ + int ret; + + raw_spin_lock(&lock->wait_lock); + + set_current_state(TASK_INTERRUPTIBLE); + + /* sleep on the mutex */ + ret = __rt_mutex_slowlock(lock, TASK_INTERRUPTIBLE, to, waiter, NULL); + + if (unlikely(ret)) + remove_waiter(lock, waiter); + + /* + * try_to_take_rt_mutex() sets the waiter bit unconditionally. We might + * have to fix that up. + */ + fixup_rt_mutex_waiters(lock); + + raw_spin_unlock(&lock->wait_lock); + + return ret; +} + +static inline int +ww_mutex_deadlock_injection(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) +{ +#ifdef CONFIG_DEBUG_WW_MUTEX_SLOWPATH + unsigned tmp; + + if (ctx->deadlock_inject_countdown-- == 0) { + tmp = ctx->deadlock_inject_interval; + if (tmp > UINT_MAX/4) + tmp = UINT_MAX; + else + tmp = tmp*2 + tmp + tmp/2; + + ctx->deadlock_inject_interval = tmp; + ctx->deadlock_inject_countdown = tmp; + ctx->contending_lock = lock; + + ww_mutex_unlock(lock); + + return -EDEADLK; + } +#endif + + return 0; +} + +#ifdef CONFIG_PREEMPT_RT_FULL +int __sched +__ww_mutex_lock_interruptible(struct ww_mutex *lock, struct ww_acquire_ctx *ww_ctx) +{ + int ret; + + might_sleep(); + + mutex_acquire_nest(&lock->base.dep_map, 0, 0, &ww_ctx->dep_map, _RET_IP_); + ret = rt_mutex_slowlock(&lock->base.lock, TASK_INTERRUPTIBLE, NULL, 0, ww_ctx); + if (ret) + mutex_release(&lock->base.dep_map, 1, _RET_IP_); + else if (!ret && ww_ctx->acquired > 1) + return ww_mutex_deadlock_injection(lock, ww_ctx); + + return ret; +} +EXPORT_SYMBOL_GPL(__ww_mutex_lock_interruptible); + +int __sched +__ww_mutex_lock(struct ww_mutex *lock, struct ww_acquire_ctx *ww_ctx) +{ + int ret; + + might_sleep(); + + mutex_acquire_nest(&lock->base.dep_map, 0, 0, &ww_ctx->dep_map, _RET_IP_); + ret = rt_mutex_slowlock(&lock->base.lock, TASK_UNINTERRUPTIBLE, NULL, 0, ww_ctx); + if (ret) + mutex_release(&lock->base.dep_map, 1, _RET_IP_); + else if (!ret && ww_ctx->acquired > 1) + return ww_mutex_deadlock_injection(lock, ww_ctx); + + return ret; +} +EXPORT_SYMBOL_GPL(__ww_mutex_lock); + +void __sched ww_mutex_unlock(struct ww_mutex *lock) +{ + int nest = !!lock->ctx; + + /* + * The unlocking fastpath is the 0->1 transition from 'locked' + * into 'unlocked' state: + */ + if (nest) { +#ifdef CONFIG_DEBUG_MUTEXES + DEBUG_LOCKS_WARN_ON(!lock->ctx->acquired); +#endif + if (lock->ctx->acquired > 0) + lock->ctx->acquired--; + lock->ctx = NULL; + } + + mutex_release(&lock->base.dep_map, nest, _RET_IP_); + rt_mutex_unlock(&lock->base.lock); +} +EXPORT_SYMBOL(ww_mutex_unlock); +#endif diff --git a/kernel/kernel/locking/rtmutex.h b/kernel/kernel/locking/rtmutex.h new file mode 100644 index 000000000..c4060584c --- /dev/null +++ b/kernel/kernel/locking/rtmutex.h @@ -0,0 +1,36 @@ +/* + * RT-Mutexes: blocking mutual exclusion locks with PI support + * + * started by Ingo Molnar and Thomas Gleixner: + * + * Copyright (C) 2004-2006 Red Hat, Inc., Ingo Molnar + * Copyright (C) 2006, Timesys Corp., Thomas Gleixner + * + * This file contains macros used solely by rtmutex.c. + * Non-debug version. + */ + +#define rt_mutex_deadlock_check(l) (0) +#define rt_mutex_deadlock_account_lock(m, t) do { } while (0) +#define rt_mutex_deadlock_account_unlock(l) do { } while (0) +#define debug_rt_mutex_init_waiter(w) do { } while (0) +#define debug_rt_mutex_free_waiter(w) do { } while (0) +#define debug_rt_mutex_lock(l) do { } while (0) +#define debug_rt_mutex_proxy_lock(l,p) do { } while (0) +#define debug_rt_mutex_proxy_unlock(l) do { } while (0) +#define debug_rt_mutex_unlock(l) do { } while (0) +#define debug_rt_mutex_init(m, n) do { } while (0) +#define debug_rt_mutex_deadlock(d, a ,l) do { } while (0) +#define debug_rt_mutex_print_deadlock(w) do { } while (0) +#define debug_rt_mutex_reset_waiter(w) do { } while (0) + +static inline void rt_mutex_print_deadlock(struct rt_mutex_waiter *w) +{ + WARN(1, "rtmutex deadlock detected\n"); +} + +static inline bool debug_rt_mutex_detect_deadlock(struct rt_mutex_waiter *w, + enum rtmutex_chainwalk walk) +{ + return walk == RT_MUTEX_FULL_CHAINWALK; +} diff --git a/kernel/kernel/locking/rtmutex_common.h b/kernel/kernel/locking/rtmutex_common.h new file mode 100644 index 000000000..4d317e9a5 --- /dev/null +++ b/kernel/kernel/locking/rtmutex_common.h @@ -0,0 +1,159 @@ +/* + * RT Mutexes: blocking mutual exclusion locks with PI support + * + * started by Ingo Molnar and Thomas Gleixner: + * + * Copyright (C) 2004-2006 Red Hat, Inc., Ingo Molnar + * Copyright (C) 2006, Timesys Corp., Thomas Gleixner + * + * This file contains the private data structure and API definitions. + */ + +#ifndef __KERNEL_RTMUTEX_COMMON_H +#define __KERNEL_RTMUTEX_COMMON_H + +#include + +/* + * The rtmutex in kernel tester is independent of rtmutex debugging. We + * call schedule_rt_mutex_test() instead of schedule() for the tasks which + * belong to the tester. That way we can delay the wakeup path of those + * threads to provoke lock stealing and testing of complex boosting scenarios. + */ +#ifdef CONFIG_RT_MUTEX_TESTER + +extern void schedule_rt_mutex_test(struct rt_mutex *lock); + +#define schedule_rt_mutex(_lock) \ + do { \ + if (!(current->flags & PF_MUTEX_TESTER)) \ + schedule(); \ + else \ + schedule_rt_mutex_test(_lock); \ + } while (0) + +#else +# define schedule_rt_mutex(_lock) schedule() +#endif + +/* + * This is the control structure for tasks blocked on a rt_mutex, + * which is allocated on the kernel stack on of the blocked task. + * + * @tree_entry: pi node to enqueue into the mutex waiters tree + * @pi_tree_entry: pi node to enqueue into the mutex owner waiters tree + * @task: task reference to the blocked task + */ +struct rt_mutex_waiter { + struct rb_node tree_entry; + struct rb_node pi_tree_entry; + struct task_struct *task; + struct rt_mutex *lock; + bool savestate; +#ifdef CONFIG_DEBUG_RT_MUTEXES + unsigned long ip; + struct pid *deadlock_task_pid; + struct rt_mutex *deadlock_lock; +#endif + int prio; +}; + +/* + * Various helpers to access the waiters-tree: + */ +static inline int rt_mutex_has_waiters(struct rt_mutex *lock) +{ + return !RB_EMPTY_ROOT(&lock->waiters); +} + +static inline struct rt_mutex_waiter * +rt_mutex_top_waiter(struct rt_mutex *lock) +{ + struct rt_mutex_waiter *w; + + w = rb_entry(lock->waiters_leftmost, struct rt_mutex_waiter, + tree_entry); + BUG_ON(w->lock != lock); + + return w; +} + +static inline int task_has_pi_waiters(struct task_struct *p) +{ + return !RB_EMPTY_ROOT(&p->pi_waiters); +} + +static inline struct rt_mutex_waiter * +task_top_pi_waiter(struct task_struct *p) +{ + return rb_entry(p->pi_waiters_leftmost, struct rt_mutex_waiter, + pi_tree_entry); +} + +/* + * lock->owner state tracking: + */ +#define RT_MUTEX_HAS_WAITERS 1UL +#define RT_MUTEX_OWNER_MASKALL 1UL + +static inline struct task_struct *rt_mutex_owner(struct rt_mutex *lock) +{ + return (struct task_struct *) + ((unsigned long)lock->owner & ~RT_MUTEX_OWNER_MASKALL); +} + +/* + * Constants for rt mutex functions which have a selectable deadlock + * detection. + * + * RT_MUTEX_MIN_CHAINWALK: Stops the lock chain walk when there are + * no further PI adjustments to be made. + * + * RT_MUTEX_FULL_CHAINWALK: Invoke deadlock detection with a full + * walk of the lock chain. + */ +enum rtmutex_chainwalk { + RT_MUTEX_MIN_CHAINWALK, + RT_MUTEX_FULL_CHAINWALK, +}; + +/* + * PI-futex support (proxy locking functions, etc.): + */ +#define PI_WAKEUP_INPROGRESS ((struct rt_mutex_waiter *) 1) +#define PI_REQUEUE_INPROGRESS ((struct rt_mutex_waiter *) 2) + +extern struct task_struct *rt_mutex_next_owner(struct rt_mutex *lock); +extern void rt_mutex_init_proxy_locked(struct rt_mutex *lock, + struct task_struct *proxy_owner); +extern void rt_mutex_proxy_unlock(struct rt_mutex *lock, + struct task_struct *proxy_owner); +extern int rt_mutex_start_proxy_lock(struct rt_mutex *lock, + struct rt_mutex_waiter *waiter, + struct task_struct *task); +extern int rt_mutex_finish_proxy_lock(struct rt_mutex *lock, + struct hrtimer_sleeper *to, + struct rt_mutex_waiter *waiter); +extern int rt_mutex_timed_futex_lock(struct rt_mutex *l, struct hrtimer_sleeper *to); + +extern bool rt_mutex_futex_unlock(struct rt_mutex *lock); + +extern void rt_mutex_adjust_prio(struct task_struct *task); + +#ifdef CONFIG_DEBUG_RT_MUTEXES +# include "rtmutex-debug.h" +#else +# include "rtmutex.h" +#endif + +static inline void +rt_mutex_init_waiter(struct rt_mutex_waiter *waiter, bool savestate) +{ + debug_rt_mutex_init_waiter(waiter); + waiter->task = NULL; + waiter->savestate = savestate; + RB_CLEAR_NODE(&waiter->pi_tree_entry); + RB_CLEAR_NODE(&waiter->tree_entry); +} + +#endif diff --git a/kernel/kernel/locking/rwsem-spinlock.c b/kernel/kernel/locking/rwsem-spinlock.c new file mode 100644 index 000000000..3a5048572 --- /dev/null +++ b/kernel/kernel/locking/rwsem-spinlock.c @@ -0,0 +1,303 @@ +/* rwsem-spinlock.c: R/W semaphores: contention handling functions for + * generic spinlock implementation + * + * Copyright (c) 2001 David Howells (dhowells@redhat.com). + * - Derived partially from idea by Andrea Arcangeli + * - Derived also from comments by Linus + */ +#include +#include +#include + +enum rwsem_waiter_type { + RWSEM_WAITING_FOR_WRITE, + RWSEM_WAITING_FOR_READ +}; + +struct rwsem_waiter { + struct list_head list; + struct task_struct *task; + enum rwsem_waiter_type type; +}; + +int rwsem_is_locked(struct rw_semaphore *sem) +{ + int ret = 1; + unsigned long flags; + + if (raw_spin_trylock_irqsave(&sem->wait_lock, flags)) { + ret = (sem->count != 0); + raw_spin_unlock_irqrestore(&sem->wait_lock, flags); + } + return ret; +} +EXPORT_SYMBOL(rwsem_is_locked); + +/* + * initialise the semaphore + */ +void __init_rwsem(struct rw_semaphore *sem, const char *name, + struct lock_class_key *key) +{ +#ifdef CONFIG_DEBUG_LOCK_ALLOC + /* + * Make sure we are not reinitializing a held semaphore: + */ + debug_check_no_locks_freed((void *)sem, sizeof(*sem)); + lockdep_init_map(&sem->dep_map, name, key, 0); +#endif + sem->count = 0; + raw_spin_lock_init(&sem->wait_lock); + INIT_LIST_HEAD(&sem->wait_list); +} +EXPORT_SYMBOL(__init_rwsem); + +/* + * handle the lock release when processes blocked on it that can now run + * - if we come here, then: + * - the 'active count' _reached_ zero + * - the 'waiting count' is non-zero + * - the spinlock must be held by the caller + * - woken process blocks are discarded from the list after having task zeroed + * - writers are only woken if wakewrite is non-zero + */ +static inline struct rw_semaphore * +__rwsem_do_wake(struct rw_semaphore *sem, int wakewrite) +{ + struct rwsem_waiter *waiter; + struct task_struct *tsk; + int woken; + + waiter = list_entry(sem->wait_list.next, struct rwsem_waiter, list); + + if (waiter->type == RWSEM_WAITING_FOR_WRITE) { + if (wakewrite) + /* Wake up a writer. Note that we do not grant it the + * lock - it will have to acquire it when it runs. */ + wake_up_process(waiter->task); + goto out; + } + + /* grant an infinite number of read locks to the front of the queue */ + woken = 0; + do { + struct list_head *next = waiter->list.next; + + list_del(&waiter->list); + tsk = waiter->task; + /* + * Make sure we do not wakeup the next reader before + * setting the nil condition to grant the next reader; + * otherwise we could miss the wakeup on the other + * side and end up sleeping again. See the pairing + * in rwsem_down_read_failed(). + */ + smp_mb(); + waiter->task = NULL; + wake_up_process(tsk); + put_task_struct(tsk); + woken++; + if (next == &sem->wait_list) + break; + waiter = list_entry(next, struct rwsem_waiter, list); + } while (waiter->type != RWSEM_WAITING_FOR_WRITE); + + sem->count += woken; + + out: + return sem; +} + +/* + * wake a single writer + */ +static inline struct rw_semaphore * +__rwsem_wake_one_writer(struct rw_semaphore *sem) +{ + struct rwsem_waiter *waiter; + + waiter = list_entry(sem->wait_list.next, struct rwsem_waiter, list); + wake_up_process(waiter->task); + + return sem; +} + +/* + * get a read lock on the semaphore + */ +void __sched __down_read(struct rw_semaphore *sem) +{ + struct rwsem_waiter waiter; + struct task_struct *tsk; + unsigned long flags; + + raw_spin_lock_irqsave(&sem->wait_lock, flags); + + if (sem->count >= 0 && list_empty(&sem->wait_list)) { + /* granted */ + sem->count++; + raw_spin_unlock_irqrestore(&sem->wait_lock, flags); + goto out; + } + + tsk = current; + set_task_state(tsk, TASK_UNINTERRUPTIBLE); + + /* set up my own style of waitqueue */ + waiter.task = tsk; + waiter.type = RWSEM_WAITING_FOR_READ; + get_task_struct(tsk); + + list_add_tail(&waiter.list, &sem->wait_list); + + /* we don't need to touch the semaphore struct anymore */ + raw_spin_unlock_irqrestore(&sem->wait_lock, flags); + + /* wait to be given the lock */ + for (;;) { + if (!waiter.task) + break; + schedule(); + set_task_state(tsk, TASK_UNINTERRUPTIBLE); + } + + __set_task_state(tsk, TASK_RUNNING); + out: + ; +} + +/* + * trylock for reading -- returns 1 if successful, 0 if contention + */ +int __down_read_trylock(struct rw_semaphore *sem) +{ + unsigned long flags; + int ret = 0; + + + raw_spin_lock_irqsave(&sem->wait_lock, flags); + + if (sem->count >= 0 && list_empty(&sem->wait_list)) { + /* granted */ + sem->count++; + ret = 1; + } + + raw_spin_unlock_irqrestore(&sem->wait_lock, flags); + + return ret; +} + +/* + * get a write lock on the semaphore + */ +void __sched __down_write_nested(struct rw_semaphore *sem, int subclass) +{ + struct rwsem_waiter waiter; + struct task_struct *tsk; + unsigned long flags; + + raw_spin_lock_irqsave(&sem->wait_lock, flags); + + /* set up my own style of waitqueue */ + tsk = current; + waiter.task = tsk; + waiter.type = RWSEM_WAITING_FOR_WRITE; + list_add_tail(&waiter.list, &sem->wait_list); + + /* wait for someone to release the lock */ + for (;;) { + /* + * That is the key to support write lock stealing: allows the + * task already on CPU to get the lock soon rather than put + * itself into sleep and waiting for system woke it or someone + * else in the head of the wait list up. + */ + if (sem->count == 0) + break; + set_task_state(tsk, TASK_UNINTERRUPTIBLE); + raw_spin_unlock_irqrestore(&sem->wait_lock, flags); + schedule(); + raw_spin_lock_irqsave(&sem->wait_lock, flags); + } + /* got the lock */ + sem->count = -1; + list_del(&waiter.list); + + raw_spin_unlock_irqrestore(&sem->wait_lock, flags); +} + +void __sched __down_write(struct rw_semaphore *sem) +{ + __down_write_nested(sem, 0); +} + +/* + * trylock for writing -- returns 1 if successful, 0 if contention + */ +int __down_write_trylock(struct rw_semaphore *sem) +{ + unsigned long flags; + int ret = 0; + + raw_spin_lock_irqsave(&sem->wait_lock, flags); + + if (sem->count == 0) { + /* got the lock */ + sem->count = -1; + ret = 1; + } + + raw_spin_unlock_irqrestore(&sem->wait_lock, flags); + + return ret; +} + +/* + * release a read lock on the semaphore + */ +void __up_read(struct rw_semaphore *sem) +{ + unsigned long flags; + + raw_spin_lock_irqsave(&sem->wait_lock, flags); + + if (--sem->count == 0 && !list_empty(&sem->wait_list)) + sem = __rwsem_wake_one_writer(sem); + + raw_spin_unlock_irqrestore(&sem->wait_lock, flags); +} + +/* + * release a write lock on the semaphore + */ +void __up_write(struct rw_semaphore *sem) +{ + unsigned long flags; + + raw_spin_lock_irqsave(&sem->wait_lock, flags); + + sem->count = 0; + if (!list_empty(&sem->wait_list)) + sem = __rwsem_do_wake(sem, 1); + + raw_spin_unlock_irqrestore(&sem->wait_lock, flags); +} + +/* + * downgrade a write lock into a read lock + * - just wake up any readers at the front of the queue + */ +void __downgrade_write(struct rw_semaphore *sem) +{ + unsigned long flags; + + raw_spin_lock_irqsave(&sem->wait_lock, flags); + + sem->count = 1; + if (!list_empty(&sem->wait_list)) + sem = __rwsem_do_wake(sem, 0); + + raw_spin_unlock_irqrestore(&sem->wait_lock, flags); +} + diff --git a/kernel/kernel/locking/rwsem-xadd.c b/kernel/kernel/locking/rwsem-xadd.c new file mode 100644 index 000000000..3417d0172 --- /dev/null +++ b/kernel/kernel/locking/rwsem-xadd.c @@ -0,0 +1,531 @@ +/* rwsem.c: R/W semaphores: contention handling functions + * + * Written by David Howells (dhowells@redhat.com). + * Derived from arch/i386/kernel/semaphore.c + * + * Writer lock-stealing by Alex Shi + * and Michel Lespinasse + * + * Optimistic spinning by Tim Chen + * and Davidlohr Bueso . Based on mutexes. + */ +#include +#include +#include +#include +#include +#include + +#include "rwsem.h" + +/* + * Guide to the rw_semaphore's count field for common values. + * (32-bit case illustrated, similar for 64-bit) + * + * 0x0000000X (1) X readers active or attempting lock, no writer waiting + * X = #active_readers + #readers attempting to lock + * (X*ACTIVE_BIAS) + * + * 0x00000000 rwsem is unlocked, and no one is waiting for the lock or + * attempting to read lock or write lock. + * + * 0xffff000X (1) X readers active or attempting lock, with waiters for lock + * X = #active readers + # readers attempting lock + * (X*ACTIVE_BIAS + WAITING_BIAS) + * (2) 1 writer attempting lock, no waiters for lock + * X-1 = #active readers + #readers attempting lock + * ((X-1)*ACTIVE_BIAS + ACTIVE_WRITE_BIAS) + * (3) 1 writer active, no waiters for lock + * X-1 = #active readers + #readers attempting lock + * ((X-1)*ACTIVE_BIAS + ACTIVE_WRITE_BIAS) + * + * 0xffff0001 (1) 1 reader active or attempting lock, waiters for lock + * (WAITING_BIAS + ACTIVE_BIAS) + * (2) 1 writer active or attempting lock, no waiters for lock + * (ACTIVE_WRITE_BIAS) + * + * 0xffff0000 (1) There are writers or readers queued but none active + * or in the process of attempting lock. + * (WAITING_BIAS) + * Note: writer can attempt to steal lock for this count by adding + * ACTIVE_WRITE_BIAS in cmpxchg and checking the old count + * + * 0xfffe0001 (1) 1 writer active, or attempting lock. Waiters on queue. + * (ACTIVE_WRITE_BIAS + WAITING_BIAS) + * + * Note: Readers attempt to lock by adding ACTIVE_BIAS in down_read and checking + * the count becomes more than 0 for successful lock acquisition, + * i.e. the case where there are only readers or nobody has lock. + * (1st and 2nd case above). + * + * Writers attempt to lock by adding ACTIVE_WRITE_BIAS in down_write and + * checking the count becomes ACTIVE_WRITE_BIAS for successful lock + * acquisition (i.e. nobody else has lock or attempts lock). If + * unsuccessful, in rwsem_down_write_failed, we'll check to see if there + * are only waiters but none active (5th case above), and attempt to + * steal the lock. + * + */ + +/* + * Initialize an rwsem: + */ +void __init_rwsem(struct rw_semaphore *sem, const char *name, + struct lock_class_key *key) +{ +#ifdef CONFIG_DEBUG_LOCK_ALLOC + /* + * Make sure we are not reinitializing a held semaphore: + */ + debug_check_no_locks_freed((void *)sem, sizeof(*sem)); + lockdep_init_map(&sem->dep_map, name, key, 0); +#endif + sem->count = RWSEM_UNLOCKED_VALUE; + raw_spin_lock_init(&sem->wait_lock); + INIT_LIST_HEAD(&sem->wait_list); +#ifdef CONFIG_RWSEM_SPIN_ON_OWNER + sem->owner = NULL; + osq_lock_init(&sem->osq); +#endif +} + +EXPORT_SYMBOL(__init_rwsem); + +enum rwsem_waiter_type { + RWSEM_WAITING_FOR_WRITE, + RWSEM_WAITING_FOR_READ +}; + +struct rwsem_waiter { + struct list_head list; + struct task_struct *task; + enum rwsem_waiter_type type; +}; + +enum rwsem_wake_type { + RWSEM_WAKE_ANY, /* Wake whatever's at head of wait list */ + RWSEM_WAKE_READERS, /* Wake readers only */ + RWSEM_WAKE_READ_OWNED /* Waker thread holds the read lock */ +}; + +/* + * handle the lock release when processes blocked on it that can now run + * - if we come here from up_xxxx(), then: + * - the 'active part' of count (&0x0000ffff) reached 0 (but may have changed) + * - the 'waiting part' of count (&0xffff0000) is -ve (and will still be so) + * - there must be someone on the queue + * - the spinlock must be held by the caller + * - woken process blocks are discarded from the list after having task zeroed + * - writers are only woken if downgrading is false + */ +static struct rw_semaphore * +__rwsem_do_wake(struct rw_semaphore *sem, enum rwsem_wake_type wake_type) +{ + struct rwsem_waiter *waiter; + struct task_struct *tsk; + struct list_head *next; + long oldcount, woken, loop, adjustment; + + waiter = list_entry(sem->wait_list.next, struct rwsem_waiter, list); + if (waiter->type == RWSEM_WAITING_FOR_WRITE) { + if (wake_type == RWSEM_WAKE_ANY) + /* Wake writer at the front of the queue, but do not + * grant it the lock yet as we want other writers + * to be able to steal it. Readers, on the other hand, + * will block as they will notice the queued writer. + */ + wake_up_process(waiter->task); + goto out; + } + + /* Writers might steal the lock before we grant it to the next reader. + * We prefer to do the first reader grant before counting readers + * so we can bail out early if a writer stole the lock. + */ + adjustment = 0; + if (wake_type != RWSEM_WAKE_READ_OWNED) { + adjustment = RWSEM_ACTIVE_READ_BIAS; + try_reader_grant: + oldcount = rwsem_atomic_update(adjustment, sem) - adjustment; + if (unlikely(oldcount < RWSEM_WAITING_BIAS)) { + /* A writer stole the lock. Undo our reader grant. */ + if (rwsem_atomic_update(-adjustment, sem) & + RWSEM_ACTIVE_MASK) + goto out; + /* Last active locker left. Retry waking readers. */ + goto try_reader_grant; + } + } + + /* Grant an infinite number of read locks to the readers at the front + * of the queue. Note we increment the 'active part' of the count by + * the number of readers before waking any processes up. + */ + woken = 0; + do { + woken++; + + if (waiter->list.next == &sem->wait_list) + break; + + waiter = list_entry(waiter->list.next, + struct rwsem_waiter, list); + + } while (waiter->type != RWSEM_WAITING_FOR_WRITE); + + adjustment = woken * RWSEM_ACTIVE_READ_BIAS - adjustment; + if (waiter->type != RWSEM_WAITING_FOR_WRITE) + /* hit end of list above */ + adjustment -= RWSEM_WAITING_BIAS; + + if (adjustment) + rwsem_atomic_add(adjustment, sem); + + next = sem->wait_list.next; + loop = woken; + do { + waiter = list_entry(next, struct rwsem_waiter, list); + next = waiter->list.next; + tsk = waiter->task; + /* + * Make sure we do not wakeup the next reader before + * setting the nil condition to grant the next reader; + * otherwise we could miss the wakeup on the other + * side and end up sleeping again. See the pairing + * in rwsem_down_read_failed(). + */ + smp_mb(); + waiter->task = NULL; + wake_up_process(tsk); + put_task_struct(tsk); + } while (--loop); + + sem->wait_list.next = next; + next->prev = &sem->wait_list; + + out: + return sem; +} + +/* + * Wait for the read lock to be granted + */ +__visible +struct rw_semaphore __sched *rwsem_down_read_failed(struct rw_semaphore *sem) +{ + long count, adjustment = -RWSEM_ACTIVE_READ_BIAS; + struct rwsem_waiter waiter; + struct task_struct *tsk = current; + + /* set up my own style of waitqueue */ + waiter.task = tsk; + waiter.type = RWSEM_WAITING_FOR_READ; + get_task_struct(tsk); + + raw_spin_lock_irq(&sem->wait_lock); + if (list_empty(&sem->wait_list)) + adjustment += RWSEM_WAITING_BIAS; + list_add_tail(&waiter.list, &sem->wait_list); + + /* we're now waiting on the lock, but no longer actively locking */ + count = rwsem_atomic_update(adjustment, sem); + + /* If there are no active locks, wake the front queued process(es). + * + * If there are no writers and we are first in the queue, + * wake our own waiter to join the existing active readers ! + */ + if (count == RWSEM_WAITING_BIAS || + (count > RWSEM_WAITING_BIAS && + adjustment != -RWSEM_ACTIVE_READ_BIAS)) + sem = __rwsem_do_wake(sem, RWSEM_WAKE_ANY); + + raw_spin_unlock_irq(&sem->wait_lock); + + /* wait to be given the lock */ + while (true) { + set_task_state(tsk, TASK_UNINTERRUPTIBLE); + if (!waiter.task) + break; + schedule(); + } + + __set_task_state(tsk, TASK_RUNNING); + return sem; +} +EXPORT_SYMBOL(rwsem_down_read_failed); + +static inline bool rwsem_try_write_lock(long count, struct rw_semaphore *sem) +{ + /* + * Try acquiring the write lock. Check count first in order + * to reduce unnecessary expensive cmpxchg() operations. + */ + if (count == RWSEM_WAITING_BIAS && + cmpxchg(&sem->count, RWSEM_WAITING_BIAS, + RWSEM_ACTIVE_WRITE_BIAS) == RWSEM_WAITING_BIAS) { + if (!list_is_singular(&sem->wait_list)) + rwsem_atomic_update(RWSEM_WAITING_BIAS, sem); + rwsem_set_owner(sem); + return true; + } + + return false; +} + +#ifdef CONFIG_RWSEM_SPIN_ON_OWNER +/* + * Try to acquire write lock before the writer has been put on wait queue. + */ +static inline bool rwsem_try_write_lock_unqueued(struct rw_semaphore *sem) +{ + long old, count = READ_ONCE(sem->count); + + while (true) { + if (!(count == 0 || count == RWSEM_WAITING_BIAS)) + return false; + + old = cmpxchg(&sem->count, count, count + RWSEM_ACTIVE_WRITE_BIAS); + if (old == count) { + rwsem_set_owner(sem); + return true; + } + + count = old; + } +} + +static inline bool rwsem_can_spin_on_owner(struct rw_semaphore *sem) +{ + struct task_struct *owner; + bool ret = true; + + if (need_resched()) + return false; + + rcu_read_lock(); + owner = READ_ONCE(sem->owner); + if (!owner) { + long count = READ_ONCE(sem->count); + /* + * If sem->owner is not set, yet we have just recently entered the + * slowpath with the lock being active, then there is a possibility + * reader(s) may have the lock. To be safe, bail spinning in these + * situations. + */ + if (count & RWSEM_ACTIVE_MASK) + ret = false; + goto done; + } + + ret = owner->on_cpu; +done: + rcu_read_unlock(); + return ret; +} + +static noinline +bool rwsem_spin_on_owner(struct rw_semaphore *sem, struct task_struct *owner) +{ + long count; + + rcu_read_lock(); + while (sem->owner == owner) { + /* + * Ensure we emit the owner->on_cpu, dereference _after_ + * checking sem->owner still matches owner, if that fails, + * owner might point to free()d memory, if it still matches, + * the rcu_read_lock() ensures the memory stays valid. + */ + barrier(); + + /* abort spinning when need_resched or owner is not running */ + if (!owner->on_cpu || need_resched()) { + rcu_read_unlock(); + return false; + } + + cpu_relax_lowlatency(); + } + rcu_read_unlock(); + + if (READ_ONCE(sem->owner)) + return true; /* new owner, continue spinning */ + + /* + * When the owner is not set, the lock could be free or + * held by readers. Check the counter to verify the + * state. + */ + count = READ_ONCE(sem->count); + return (count == 0 || count == RWSEM_WAITING_BIAS); +} + +static bool rwsem_optimistic_spin(struct rw_semaphore *sem) +{ + struct task_struct *owner; + bool taken = false; + + preempt_disable(); + + /* sem->wait_lock should not be held when doing optimistic spinning */ + if (!rwsem_can_spin_on_owner(sem)) + goto done; + + if (!osq_lock(&sem->osq)) + goto done; + + while (true) { + owner = READ_ONCE(sem->owner); + if (owner && !rwsem_spin_on_owner(sem, owner)) + break; + + /* wait_lock will be acquired if write_lock is obtained */ + if (rwsem_try_write_lock_unqueued(sem)) { + taken = true; + break; + } + + /* + * When there's no owner, we might have preempted between the + * owner acquiring the lock and setting the owner field. If + * we're an RT task that will live-lock because we won't let + * the owner complete. + */ + if (!owner && (need_resched() || rt_task(current))) + break; + + /* + * The cpu_relax() call is a compiler barrier which forces + * everything in this loop to be re-loaded. We don't need + * memory barriers as we'll eventually observe the right + * values at the cost of a few extra spins. + */ + cpu_relax_lowlatency(); + } + osq_unlock(&sem->osq); +done: + preempt_enable(); + return taken; +} + +#else +static bool rwsem_optimistic_spin(struct rw_semaphore *sem) +{ + return false; +} +#endif + +/* + * Wait until we successfully acquire the write lock + */ +__visible +struct rw_semaphore __sched *rwsem_down_write_failed(struct rw_semaphore *sem) +{ + long count; + bool waiting = true; /* any queued threads before us */ + struct rwsem_waiter waiter; + + /* undo write bias from down_write operation, stop active locking */ + count = rwsem_atomic_update(-RWSEM_ACTIVE_WRITE_BIAS, sem); + + /* do optimistic spinning and steal lock if possible */ + if (rwsem_optimistic_spin(sem)) + return sem; + + /* + * Optimistic spinning failed, proceed to the slowpath + * and block until we can acquire the sem. + */ + waiter.task = current; + waiter.type = RWSEM_WAITING_FOR_WRITE; + + raw_spin_lock_irq(&sem->wait_lock); + + /* account for this before adding a new element to the list */ + if (list_empty(&sem->wait_list)) + waiting = false; + + list_add_tail(&waiter.list, &sem->wait_list); + + /* we're now waiting on the lock, but no longer actively locking */ + if (waiting) { + count = READ_ONCE(sem->count); + + /* + * If there were already threads queued before us and there are + * no active writers, the lock must be read owned; so we try to + * wake any read locks that were queued ahead of us. + */ + if (count > RWSEM_WAITING_BIAS) + sem = __rwsem_do_wake(sem, RWSEM_WAKE_READERS); + + } else + count = rwsem_atomic_update(RWSEM_WAITING_BIAS, sem); + + /* wait until we successfully acquire the lock */ + set_current_state(TASK_UNINTERRUPTIBLE); + while (true) { + if (rwsem_try_write_lock(count, sem)) + break; + raw_spin_unlock_irq(&sem->wait_lock); + + /* Block until there are no active lockers. */ + do { + schedule(); + set_current_state(TASK_UNINTERRUPTIBLE); + } while ((count = sem->count) & RWSEM_ACTIVE_MASK); + + raw_spin_lock_irq(&sem->wait_lock); + } + __set_current_state(TASK_RUNNING); + + list_del(&waiter.list); + raw_spin_unlock_irq(&sem->wait_lock); + + return sem; +} +EXPORT_SYMBOL(rwsem_down_write_failed); + +/* + * handle waking up a waiter on the semaphore + * - up_read/up_write has decremented the active part of count if we come here + */ +__visible +struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem) +{ + unsigned long flags; + + raw_spin_lock_irqsave(&sem->wait_lock, flags); + + /* do nothing if list empty */ + if (!list_empty(&sem->wait_list)) + sem = __rwsem_do_wake(sem, RWSEM_WAKE_ANY); + + raw_spin_unlock_irqrestore(&sem->wait_lock, flags); + + return sem; +} +EXPORT_SYMBOL(rwsem_wake); + +/* + * downgrade a write lock into a read lock + * - caller incremented waiting part of count and discovered it still negative + * - just wake up any readers at the front of the queue + */ +__visible +struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem) +{ + unsigned long flags; + + raw_spin_lock_irqsave(&sem->wait_lock, flags); + + /* do nothing if list empty */ + if (!list_empty(&sem->wait_list)) + sem = __rwsem_do_wake(sem, RWSEM_WAKE_READ_OWNED); + + raw_spin_unlock_irqrestore(&sem->wait_lock, flags); + + return sem; +} +EXPORT_SYMBOL(rwsem_downgrade_wake); diff --git a/kernel/kernel/locking/rwsem.c b/kernel/kernel/locking/rwsem.c new file mode 100644 index 000000000..205be0ce3 --- /dev/null +++ b/kernel/kernel/locking/rwsem.c @@ -0,0 +1,166 @@ +/* kernel/rwsem.c: R/W semaphores, public implementation + * + * Written by David Howells (dhowells@redhat.com). + * Derived from asm-i386/semaphore.h + */ + +#include +#include +#include +#include +#include +#include + +#include "rwsem.h" + +/* + * lock for reading + */ +void __sched down_read(struct rw_semaphore *sem) +{ + might_sleep(); + rwsem_acquire_read(&sem->dep_map, 0, 0, _RET_IP_); + + LOCK_CONTENDED(sem, __down_read_trylock, __down_read); +} + +EXPORT_SYMBOL(down_read); + +/* + * trylock for reading -- returns 1 if successful, 0 if contention + */ +int down_read_trylock(struct rw_semaphore *sem) +{ + int ret = __down_read_trylock(sem); + + if (ret == 1) + rwsem_acquire_read(&sem->dep_map, 0, 1, _RET_IP_); + return ret; +} + +EXPORT_SYMBOL(down_read_trylock); + +/* + * lock for writing + */ +void __sched down_write(struct rw_semaphore *sem) +{ + might_sleep(); + rwsem_acquire(&sem->dep_map, 0, 0, _RET_IP_); + + LOCK_CONTENDED(sem, __down_write_trylock, __down_write); + rwsem_set_owner(sem); +} + +EXPORT_SYMBOL(down_write); + +/* + * trylock for writing -- returns 1 if successful, 0 if contention + */ +int down_write_trylock(struct rw_semaphore *sem) +{ + int ret = __down_write_trylock(sem); + + if (ret == 1) { + rwsem_acquire(&sem->dep_map, 0, 1, _RET_IP_); + rwsem_set_owner(sem); + } + + return ret; +} + +EXPORT_SYMBOL(down_write_trylock); + +/* + * release a read lock + */ +void up_read(struct rw_semaphore *sem) +{ + rwsem_release(&sem->dep_map, 1, _RET_IP_); + + __up_read(sem); +} + +EXPORT_SYMBOL(up_read); + +/* + * release a write lock + */ +void up_write(struct rw_semaphore *sem) +{ + rwsem_release(&sem->dep_map, 1, _RET_IP_); + + rwsem_clear_owner(sem); + __up_write(sem); +} + +EXPORT_SYMBOL(up_write); + +/* + * downgrade write lock to read lock + */ +void downgrade_write(struct rw_semaphore *sem) +{ + /* + * lockdep: a downgraded write will live on as a write + * dependency. + */ + rwsem_clear_owner(sem); + __downgrade_write(sem); +} + +EXPORT_SYMBOL(downgrade_write); + +#ifdef CONFIG_DEBUG_LOCK_ALLOC + +void down_read_nested(struct rw_semaphore *sem, int subclass) +{ + might_sleep(); + rwsem_acquire_read(&sem->dep_map, subclass, 0, _RET_IP_); + + LOCK_CONTENDED(sem, __down_read_trylock, __down_read); +} + +EXPORT_SYMBOL(down_read_nested); + +void _down_write_nest_lock(struct rw_semaphore *sem, struct lockdep_map *nest) +{ + might_sleep(); + rwsem_acquire_nest(&sem->dep_map, 0, 0, nest, _RET_IP_); + + LOCK_CONTENDED(sem, __down_write_trylock, __down_write); + rwsem_set_owner(sem); +} + +EXPORT_SYMBOL(_down_write_nest_lock); + +void down_read_non_owner(struct rw_semaphore *sem) +{ + might_sleep(); + + __down_read(sem); +} + +EXPORT_SYMBOL(down_read_non_owner); + +void down_write_nested(struct rw_semaphore *sem, int subclass) +{ + might_sleep(); + rwsem_acquire(&sem->dep_map, subclass, 0, _RET_IP_); + + LOCK_CONTENDED(sem, __down_write_trylock, __down_write); + rwsem_set_owner(sem); +} + +EXPORT_SYMBOL(down_write_nested); + +void up_read_non_owner(struct rw_semaphore *sem) +{ + __up_read(sem); +} + +EXPORT_SYMBOL(up_read_non_owner); + +#endif + + diff --git a/kernel/kernel/locking/rwsem.h b/kernel/kernel/locking/rwsem.h new file mode 100644 index 000000000..870ed9a5b --- /dev/null +++ b/kernel/kernel/locking/rwsem.h @@ -0,0 +1,20 @@ +#ifdef CONFIG_RWSEM_SPIN_ON_OWNER +static inline void rwsem_set_owner(struct rw_semaphore *sem) +{ + sem->owner = current; +} + +static inline void rwsem_clear_owner(struct rw_semaphore *sem) +{ + sem->owner = NULL; +} + +#else +static inline void rwsem_set_owner(struct rw_semaphore *sem) +{ +} + +static inline void rwsem_clear_owner(struct rw_semaphore *sem) +{ +} +#endif diff --git a/kernel/kernel/locking/semaphore.c b/kernel/kernel/locking/semaphore.c new file mode 100644 index 000000000..b8120abe5 --- /dev/null +++ b/kernel/kernel/locking/semaphore.c @@ -0,0 +1,263 @@ +/* + * Copyright (c) 2008 Intel Corporation + * Author: Matthew Wilcox + * + * Distributed under the terms of the GNU GPL, version 2 + * + * This file implements counting semaphores. + * A counting semaphore may be acquired 'n' times before sleeping. + * See mutex.c for single-acquisition sleeping locks which enforce + * rules which allow code to be debugged more easily. + */ + +/* + * Some notes on the implementation: + * + * The spinlock controls access to the other members of the semaphore. + * down_trylock() and up() can be called from interrupt context, so we + * have to disable interrupts when taking the lock. It turns out various + * parts of the kernel expect to be able to use down() on a semaphore in + * interrupt context when they know it will succeed, so we have to use + * irqsave variants for down(), down_interruptible() and down_killable() + * too. + * + * The ->count variable represents how many more tasks can acquire this + * semaphore. If it's zero, there may be tasks waiting on the wait_list. + */ + +#include +#include +#include +#include +#include +#include +#include + +static noinline void __down(struct semaphore *sem); +static noinline int __down_interruptible(struct semaphore *sem); +static noinline int __down_killable(struct semaphore *sem); +static noinline int __down_timeout(struct semaphore *sem, long timeout); +static noinline void __up(struct semaphore *sem); + +/** + * down - acquire the semaphore + * @sem: the semaphore to be acquired + * + * Acquires the semaphore. If no more tasks are allowed to acquire the + * semaphore, calling this function will put the task to sleep until the + * semaphore is released. + * + * Use of this function is deprecated, please use down_interruptible() or + * down_killable() instead. + */ +void down(struct semaphore *sem) +{ + unsigned long flags; + + raw_spin_lock_irqsave(&sem->lock, flags); + if (likely(sem->count > 0)) + sem->count--; + else + __down(sem); + raw_spin_unlock_irqrestore(&sem->lock, flags); +} +EXPORT_SYMBOL(down); + +/** + * down_interruptible - acquire the semaphore unless interrupted + * @sem: the semaphore to be acquired + * + * Attempts to acquire the semaphore. If no more tasks are allowed to + * acquire the semaphore, calling this function will put the task to sleep. + * If the sleep is interrupted by a signal, this function will return -EINTR. + * If the semaphore is successfully acquired, this function returns 0. + */ +int down_interruptible(struct semaphore *sem) +{ + unsigned long flags; + int result = 0; + + raw_spin_lock_irqsave(&sem->lock, flags); + if (likely(sem->count > 0)) + sem->count--; + else + result = __down_interruptible(sem); + raw_spin_unlock_irqrestore(&sem->lock, flags); + + return result; +} +EXPORT_SYMBOL(down_interruptible); + +/** + * down_killable - acquire the semaphore unless killed + * @sem: the semaphore to be acquired + * + * Attempts to acquire the semaphore. If no more tasks are allowed to + * acquire the semaphore, calling this function will put the task to sleep. + * If the sleep is interrupted by a fatal signal, this function will return + * -EINTR. If the semaphore is successfully acquired, this function returns + * 0. + */ +int down_killable(struct semaphore *sem) +{ + unsigned long flags; + int result = 0; + + raw_spin_lock_irqsave(&sem->lock, flags); + if (likely(sem->count > 0)) + sem->count--; + else + result = __down_killable(sem); + raw_spin_unlock_irqrestore(&sem->lock, flags); + + return result; +} +EXPORT_SYMBOL(down_killable); + +/** + * down_trylock - try to acquire the semaphore, without waiting + * @sem: the semaphore to be acquired + * + * Try to acquire the semaphore atomically. Returns 0 if the semaphore has + * been acquired successfully or 1 if it it cannot be acquired. + * + * NOTE: This return value is inverted from both spin_trylock and + * mutex_trylock! Be careful about this when converting code. + * + * Unlike mutex_trylock, this function can be used from interrupt context, + * and the semaphore can be released by any task or interrupt. + */ +int down_trylock(struct semaphore *sem) +{ + unsigned long flags; + int count; + + raw_spin_lock_irqsave(&sem->lock, flags); + count = sem->count - 1; + if (likely(count >= 0)) + sem->count = count; + raw_spin_unlock_irqrestore(&sem->lock, flags); + + return (count < 0); +} +EXPORT_SYMBOL(down_trylock); + +/** + * down_timeout - acquire the semaphore within a specified time + * @sem: the semaphore to be acquired + * @timeout: how long to wait before failing + * + * Attempts to acquire the semaphore. If no more tasks are allowed to + * acquire the semaphore, calling this function will put the task to sleep. + * If the semaphore is not released within the specified number of jiffies, + * this function returns -ETIME. It returns 0 if the semaphore was acquired. + */ +int down_timeout(struct semaphore *sem, long timeout) +{ + unsigned long flags; + int result = 0; + + raw_spin_lock_irqsave(&sem->lock, flags); + if (likely(sem->count > 0)) + sem->count--; + else + result = __down_timeout(sem, timeout); + raw_spin_unlock_irqrestore(&sem->lock, flags); + + return result; +} +EXPORT_SYMBOL(down_timeout); + +/** + * up - release the semaphore + * @sem: the semaphore to release + * + * Release the semaphore. Unlike mutexes, up() may be called from any + * context and even by tasks which have never called down(). + */ +void up(struct semaphore *sem) +{ + unsigned long flags; + + raw_spin_lock_irqsave(&sem->lock, flags); + if (likely(list_empty(&sem->wait_list))) + sem->count++; + else + __up(sem); + raw_spin_unlock_irqrestore(&sem->lock, flags); +} +EXPORT_SYMBOL(up); + +/* Functions for the contended case */ + +struct semaphore_waiter { + struct list_head list; + struct task_struct *task; + bool up; +}; + +/* + * Because this function is inlined, the 'state' parameter will be + * constant, and thus optimised away by the compiler. Likewise the + * 'timeout' parameter for the cases without timeouts. + */ +static inline int __sched __down_common(struct semaphore *sem, long state, + long timeout) +{ + struct task_struct *task = current; + struct semaphore_waiter waiter; + + list_add_tail(&waiter.list, &sem->wait_list); + waiter.task = task; + waiter.up = false; + + for (;;) { + if (signal_pending_state(state, task)) + goto interrupted; + if (unlikely(timeout <= 0)) + goto timed_out; + __set_task_state(task, state); + raw_spin_unlock_irq(&sem->lock); + timeout = schedule_timeout(timeout); + raw_spin_lock_irq(&sem->lock); + if (waiter.up) + return 0; + } + + timed_out: + list_del(&waiter.list); + return -ETIME; + + interrupted: + list_del(&waiter.list); + return -EINTR; +} + +static noinline void __sched __down(struct semaphore *sem) +{ + __down_common(sem, TASK_UNINTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT); +} + +static noinline int __sched __down_interruptible(struct semaphore *sem) +{ + return __down_common(sem, TASK_INTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT); +} + +static noinline int __sched __down_killable(struct semaphore *sem) +{ + return __down_common(sem, TASK_KILLABLE, MAX_SCHEDULE_TIMEOUT); +} + +static noinline int __sched __down_timeout(struct semaphore *sem, long timeout) +{ + return __down_common(sem, TASK_UNINTERRUPTIBLE, timeout); +} + +static noinline void __sched __up(struct semaphore *sem) +{ + struct semaphore_waiter *waiter = list_first_entry(&sem->wait_list, + struct semaphore_waiter, list); + list_del(&waiter->list); + waiter->up = true; + wake_up_process(waiter->task); +} diff --git a/kernel/kernel/locking/spinlock.c b/kernel/kernel/locking/spinlock.c new file mode 100644 index 000000000..909779647 --- /dev/null +++ b/kernel/kernel/locking/spinlock.c @@ -0,0 +1,414 @@ +/* + * Copyright (2004) Linus Torvalds + * + * Author: Zwane Mwaikambo + * + * Copyright (2004, 2005) Ingo Molnar + * + * This file contains the spinlock/rwlock implementations for the + * SMP and the DEBUG_SPINLOCK cases. (UP-nondebug inlines them) + * + * Note that some architectures have special knowledge about the + * stack frames of these functions in their profile_pc. If you + * change anything significant here that could change the stack + * frame contact the architecture maintainers. + */ + +#include +#include +#include +#include +#include +#include + +/* + * If lockdep is enabled then we use the non-preemption spin-ops + * even on CONFIG_PREEMPT, because lockdep assumes that interrupts are + * not re-enabled during lock-acquire (which the preempt-spin-ops do): + */ +#if !defined(CONFIG_GENERIC_LOCKBREAK) || defined(CONFIG_DEBUG_LOCK_ALLOC) +/* + * The __lock_function inlines are taken from + * include/linux/spinlock_api_smp.h + */ +#else +#define raw_read_can_lock(l) read_can_lock(l) +#define raw_write_can_lock(l) write_can_lock(l) + +/* + * Some architectures can relax in favour of the CPU owning the lock. + */ +#ifndef arch_read_relax +# define arch_read_relax(l) cpu_relax() +#endif +#ifndef arch_write_relax +# define arch_write_relax(l) cpu_relax() +#endif +#ifndef arch_spin_relax +# define arch_spin_relax(l) cpu_relax() +#endif + +/* + * We build the __lock_function inlines here. They are too large for + * inlining all over the place, but here is only one user per function + * which embedds them into the calling _lock_function below. + * + * This could be a long-held lock. We both prepare to spin for a long + * time (making _this_ CPU preemptable if possible), and we also signal + * towards that other CPU that it should break the lock ASAP. + */ +#define BUILD_LOCK_OPS(op, locktype) \ +void __lockfunc __raw_##op##_lock(locktype##_t *lock) \ +{ \ + for (;;) { \ + preempt_disable(); \ + if (likely(do_raw_##op##_trylock(lock))) \ + break; \ + preempt_enable(); \ + \ + if (!(lock)->break_lock) \ + (lock)->break_lock = 1; \ + while (!raw_##op##_can_lock(lock) && (lock)->break_lock)\ + arch_##op##_relax(&lock->raw_lock); \ + } \ + (lock)->break_lock = 0; \ +} \ + \ +unsigned long __lockfunc __raw_##op##_lock_irqsave(locktype##_t *lock) \ +{ \ + unsigned long flags; \ + \ + for (;;) { \ + preempt_disable(); \ + local_irq_save(flags); \ + if (likely(do_raw_##op##_trylock(lock))) \ + break; \ + local_irq_restore(flags); \ + preempt_enable(); \ + \ + if (!(lock)->break_lock) \ + (lock)->break_lock = 1; \ + while (!raw_##op##_can_lock(lock) && (lock)->break_lock)\ + arch_##op##_relax(&lock->raw_lock); \ + } \ + (lock)->break_lock = 0; \ + return flags; \ +} \ + \ +void __lockfunc __raw_##op##_lock_irq(locktype##_t *lock) \ +{ \ + _raw_##op##_lock_irqsave(lock); \ +} \ + \ +void __lockfunc __raw_##op##_lock_bh(locktype##_t *lock) \ +{ \ + unsigned long flags; \ + \ + /* */ \ + /* Careful: we must exclude softirqs too, hence the */ \ + /* irq-disabling. We use the generic preemption-aware */ \ + /* function: */ \ + /**/ \ + flags = _raw_##op##_lock_irqsave(lock); \ + local_bh_disable(); \ + local_irq_restore(flags); \ +} \ + +/* + * Build preemption-friendly versions of the following + * lock-spinning functions: + * + * __[spin|read|write]_lock() + * __[spin|read|write]_lock_irq() + * __[spin|read|write]_lock_irqsave() + * __[spin|read|write]_lock_bh() + */ +BUILD_LOCK_OPS(spin, raw_spinlock); + +#ifndef CONFIG_PREEMPT_RT_FULL +BUILD_LOCK_OPS(read, rwlock); +BUILD_LOCK_OPS(write, rwlock); +#endif + +#endif + +#ifndef CONFIG_INLINE_SPIN_TRYLOCK +int __lockfunc _raw_spin_trylock(raw_spinlock_t *lock) +{ + return __raw_spin_trylock(lock); +} +EXPORT_SYMBOL(_raw_spin_trylock); +#endif + +#ifndef CONFIG_INLINE_SPIN_TRYLOCK_BH +int __lockfunc _raw_spin_trylock_bh(raw_spinlock_t *lock) +{ + return __raw_spin_trylock_bh(lock); +} +EXPORT_SYMBOL(_raw_spin_trylock_bh); +#endif + +#ifndef CONFIG_INLINE_SPIN_LOCK +void __lockfunc _raw_spin_lock(raw_spinlock_t *lock) +{ + __raw_spin_lock(lock); +} +EXPORT_SYMBOL(_raw_spin_lock); +#endif + +#ifndef CONFIG_INLINE_SPIN_LOCK_IRQSAVE +unsigned long __lockfunc _raw_spin_lock_irqsave(raw_spinlock_t *lock) +{ + return __raw_spin_lock_irqsave(lock); +} +EXPORT_SYMBOL(_raw_spin_lock_irqsave); +#endif + +#ifndef CONFIG_INLINE_SPIN_LOCK_IRQ +void __lockfunc _raw_spin_lock_irq(raw_spinlock_t *lock) +{ + __raw_spin_lock_irq(lock); +} +EXPORT_SYMBOL(_raw_spin_lock_irq); +#endif + +#ifndef CONFIG_INLINE_SPIN_LOCK_BH +void __lockfunc _raw_spin_lock_bh(raw_spinlock_t *lock) +{ + __raw_spin_lock_bh(lock); +} +EXPORT_SYMBOL(_raw_spin_lock_bh); +#endif + +#ifdef CONFIG_UNINLINE_SPIN_UNLOCK +void __lockfunc _raw_spin_unlock(raw_spinlock_t *lock) +{ + __raw_spin_unlock(lock); +} +EXPORT_SYMBOL(_raw_spin_unlock); +#endif + +#ifndef CONFIG_INLINE_SPIN_UNLOCK_IRQRESTORE +void __lockfunc _raw_spin_unlock_irqrestore(raw_spinlock_t *lock, unsigned long flags) +{ + __raw_spin_unlock_irqrestore(lock, flags); +} +EXPORT_SYMBOL(_raw_spin_unlock_irqrestore); +#endif + +#ifndef CONFIG_INLINE_SPIN_UNLOCK_IRQ +void __lockfunc _raw_spin_unlock_irq(raw_spinlock_t *lock) +{ + __raw_spin_unlock_irq(lock); +} +EXPORT_SYMBOL(_raw_spin_unlock_irq); +#endif + +#ifndef CONFIG_INLINE_SPIN_UNLOCK_BH +void __lockfunc _raw_spin_unlock_bh(raw_spinlock_t *lock) +{ + __raw_spin_unlock_bh(lock); +} +EXPORT_SYMBOL(_raw_spin_unlock_bh); +#endif + +#ifndef CONFIG_PREEMPT_RT_FULL + +#ifndef CONFIG_INLINE_READ_TRYLOCK +int __lockfunc _raw_read_trylock(rwlock_t *lock) +{ + return __raw_read_trylock(lock); +} +EXPORT_SYMBOL(_raw_read_trylock); +#endif + +#ifndef CONFIG_INLINE_READ_LOCK +void __lockfunc _raw_read_lock(rwlock_t *lock) +{ + __raw_read_lock(lock); +} +EXPORT_SYMBOL(_raw_read_lock); +#endif + +#ifndef CONFIG_INLINE_READ_LOCK_IRQSAVE +unsigned long __lockfunc _raw_read_lock_irqsave(rwlock_t *lock) +{ + return __raw_read_lock_irqsave(lock); +} +EXPORT_SYMBOL(_raw_read_lock_irqsave); +#endif + +#ifndef CONFIG_INLINE_READ_LOCK_IRQ +void __lockfunc _raw_read_lock_irq(rwlock_t *lock) +{ + __raw_read_lock_irq(lock); +} +EXPORT_SYMBOL(_raw_read_lock_irq); +#endif + +#ifndef CONFIG_INLINE_READ_LOCK_BH +void __lockfunc _raw_read_lock_bh(rwlock_t *lock) +{ + __raw_read_lock_bh(lock); +} +EXPORT_SYMBOL(_raw_read_lock_bh); +#endif + +#ifndef CONFIG_INLINE_READ_UNLOCK +void __lockfunc _raw_read_unlock(rwlock_t *lock) +{ + __raw_read_unlock(lock); +} +EXPORT_SYMBOL(_raw_read_unlock); +#endif + +#ifndef CONFIG_INLINE_READ_UNLOCK_IRQRESTORE +void __lockfunc _raw_read_unlock_irqrestore(rwlock_t *lock, unsigned long flags) +{ + __raw_read_unlock_irqrestore(lock, flags); +} +EXPORT_SYMBOL(_raw_read_unlock_irqrestore); +#endif + +#ifndef CONFIG_INLINE_READ_UNLOCK_IRQ +void __lockfunc _raw_read_unlock_irq(rwlock_t *lock) +{ + __raw_read_unlock_irq(lock); +} +EXPORT_SYMBOL(_raw_read_unlock_irq); +#endif + +#ifndef CONFIG_INLINE_READ_UNLOCK_BH +void __lockfunc _raw_read_unlock_bh(rwlock_t *lock) +{ + __raw_read_unlock_bh(lock); +} +EXPORT_SYMBOL(_raw_read_unlock_bh); +#endif + +#ifndef CONFIG_INLINE_WRITE_TRYLOCK +int __lockfunc _raw_write_trylock(rwlock_t *lock) +{ + return __raw_write_trylock(lock); +} +EXPORT_SYMBOL(_raw_write_trylock); +#endif + +#ifndef CONFIG_INLINE_WRITE_LOCK +void __lockfunc _raw_write_lock(rwlock_t *lock) +{ + __raw_write_lock(lock); +} +EXPORT_SYMBOL(_raw_write_lock); +#endif + +#ifndef CONFIG_INLINE_WRITE_LOCK_IRQSAVE +unsigned long __lockfunc _raw_write_lock_irqsave(rwlock_t *lock) +{ + return __raw_write_lock_irqsave(lock); +} +EXPORT_SYMBOL(_raw_write_lock_irqsave); +#endif + +#ifndef CONFIG_INLINE_WRITE_LOCK_IRQ +void __lockfunc _raw_write_lock_irq(rwlock_t *lock) +{ + __raw_write_lock_irq(lock); +} +EXPORT_SYMBOL(_raw_write_lock_irq); +#endif + +#ifndef CONFIG_INLINE_WRITE_LOCK_BH +void __lockfunc _raw_write_lock_bh(rwlock_t *lock) +{ + __raw_write_lock_bh(lock); +} +EXPORT_SYMBOL(_raw_write_lock_bh); +#endif + +#ifndef CONFIG_INLINE_WRITE_UNLOCK +void __lockfunc _raw_write_unlock(rwlock_t *lock) +{ + __raw_write_unlock(lock); +} +EXPORT_SYMBOL(_raw_write_unlock); +#endif + +#ifndef CONFIG_INLINE_WRITE_UNLOCK_IRQRESTORE +void __lockfunc _raw_write_unlock_irqrestore(rwlock_t *lock, unsigned long flags) +{ + __raw_write_unlock_irqrestore(lock, flags); +} +EXPORT_SYMBOL(_raw_write_unlock_irqrestore); +#endif + +#ifndef CONFIG_INLINE_WRITE_UNLOCK_IRQ +void __lockfunc _raw_write_unlock_irq(rwlock_t *lock) +{ + __raw_write_unlock_irq(lock); +} +EXPORT_SYMBOL(_raw_write_unlock_irq); +#endif + +#ifndef CONFIG_INLINE_WRITE_UNLOCK_BH +void __lockfunc _raw_write_unlock_bh(rwlock_t *lock) +{ + __raw_write_unlock_bh(lock); +} +EXPORT_SYMBOL(_raw_write_unlock_bh); +#endif + +#endif /* !PREEMPT_RT_FULL */ + +#ifdef CONFIG_DEBUG_LOCK_ALLOC + +void __lockfunc _raw_spin_lock_nested(raw_spinlock_t *lock, int subclass) +{ + preempt_disable(); + spin_acquire(&lock->dep_map, subclass, 0, _RET_IP_); + LOCK_CONTENDED(lock, do_raw_spin_trylock, do_raw_spin_lock); +} +EXPORT_SYMBOL(_raw_spin_lock_nested); + +void __lockfunc _raw_spin_lock_bh_nested(raw_spinlock_t *lock, int subclass) +{ + __local_bh_disable_ip(_RET_IP_, SOFTIRQ_LOCK_OFFSET); + spin_acquire(&lock->dep_map, subclass, 0, _RET_IP_); + LOCK_CONTENDED(lock, do_raw_spin_trylock, do_raw_spin_lock); +} +EXPORT_SYMBOL(_raw_spin_lock_bh_nested); + +unsigned long __lockfunc _raw_spin_lock_irqsave_nested(raw_spinlock_t *lock, + int subclass) +{ + unsigned long flags; + + local_irq_save(flags); + preempt_disable(); + spin_acquire(&lock->dep_map, subclass, 0, _RET_IP_); + LOCK_CONTENDED_FLAGS(lock, do_raw_spin_trylock, do_raw_spin_lock, + do_raw_spin_lock_flags, &flags); + return flags; +} +EXPORT_SYMBOL(_raw_spin_lock_irqsave_nested); + +void __lockfunc _raw_spin_lock_nest_lock(raw_spinlock_t *lock, + struct lockdep_map *nest_lock) +{ + preempt_disable(); + spin_acquire_nest(&lock->dep_map, 0, 0, nest_lock, _RET_IP_); + LOCK_CONTENDED(lock, do_raw_spin_trylock, do_raw_spin_lock); +} +EXPORT_SYMBOL(_raw_spin_lock_nest_lock); + +#endif + +notrace int in_lock_functions(unsigned long addr) +{ + /* Linker adds these: start and end of __lockfunc functions */ + extern char __lock_text_start[], __lock_text_end[]; + + return addr >= (unsigned long)__lock_text_start + && addr < (unsigned long)__lock_text_end; +} +EXPORT_SYMBOL(in_lock_functions); diff --git a/kernel/kernel/locking/spinlock_debug.c b/kernel/kernel/locking/spinlock_debug.c new file mode 100644 index 000000000..94970338d --- /dev/null +++ b/kernel/kernel/locking/spinlock_debug.c @@ -0,0 +1,307 @@ +/* + * Copyright 2005, Red Hat, Inc., Ingo Molnar + * Released under the General Public License (GPL). + * + * This file contains the spinlock/rwlock implementations for + * DEBUG_SPINLOCK. + */ + +#include +#include +#include +#include +#include +#include + +void __raw_spin_lock_init(raw_spinlock_t *lock, const char *name, + struct lock_class_key *key) +{ +#ifdef CONFIG_DEBUG_LOCK_ALLOC + /* + * Make sure we are not reinitializing a held lock: + */ + debug_check_no_locks_freed((void *)lock, sizeof(*lock)); + lockdep_init_map(&lock->dep_map, name, key, 0); +#endif + lock->raw_lock = (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED; + lock->magic = SPINLOCK_MAGIC; + lock->owner = SPINLOCK_OWNER_INIT; + lock->owner_cpu = -1; +} + +EXPORT_SYMBOL(__raw_spin_lock_init); + +#ifndef CONFIG_PREEMPT_RT_FULL +void __rwlock_init(rwlock_t *lock, const char *name, + struct lock_class_key *key) +{ +#ifdef CONFIG_DEBUG_LOCK_ALLOC + /* + * Make sure we are not reinitializing a held lock: + */ + debug_check_no_locks_freed((void *)lock, sizeof(*lock)); + lockdep_init_map(&lock->dep_map, name, key, 0); +#endif + lock->raw_lock = (arch_rwlock_t) __ARCH_RW_LOCK_UNLOCKED; + lock->magic = RWLOCK_MAGIC; + lock->owner = SPINLOCK_OWNER_INIT; + lock->owner_cpu = -1; +} + +EXPORT_SYMBOL(__rwlock_init); +#endif + +static void spin_dump(raw_spinlock_t *lock, const char *msg) +{ + struct task_struct *owner = NULL; + + if (lock->owner && lock->owner != SPINLOCK_OWNER_INIT) + owner = lock->owner; + printk(KERN_EMERG "BUG: spinlock %s on CPU#%d, %s/%d\n", + msg, raw_smp_processor_id(), + current->comm, task_pid_nr(current)); + printk(KERN_EMERG " lock: %pS, .magic: %08x, .owner: %s/%d, " + ".owner_cpu: %d\n", + lock, lock->magic, + owner ? owner->comm : "", + owner ? task_pid_nr(owner) : -1, + lock->owner_cpu); + dump_stack(); +} + +static void spin_bug(raw_spinlock_t *lock, const char *msg) +{ + if (!debug_locks_off()) + return; + + spin_dump(lock, msg); +} + +#define SPIN_BUG_ON(cond, lock, msg) if (unlikely(cond)) spin_bug(lock, msg) + +static inline void +debug_spin_lock_before(raw_spinlock_t *lock) +{ + SPIN_BUG_ON(lock->magic != SPINLOCK_MAGIC, lock, "bad magic"); + SPIN_BUG_ON(lock->owner == current, lock, "recursion"); + SPIN_BUG_ON(lock->owner_cpu == raw_smp_processor_id(), + lock, "cpu recursion"); +} + +static inline void debug_spin_lock_after(raw_spinlock_t *lock) +{ + lock->owner_cpu = raw_smp_processor_id(); + lock->owner = current; +} + +static inline void debug_spin_unlock(raw_spinlock_t *lock) +{ + SPIN_BUG_ON(lock->magic != SPINLOCK_MAGIC, lock, "bad magic"); + SPIN_BUG_ON(!raw_spin_is_locked(lock), lock, "already unlocked"); + SPIN_BUG_ON(lock->owner != current, lock, "wrong owner"); + SPIN_BUG_ON(lock->owner_cpu != raw_smp_processor_id(), + lock, "wrong CPU"); + lock->owner = SPINLOCK_OWNER_INIT; + lock->owner_cpu = -1; +} + +static void __spin_lock_debug(raw_spinlock_t *lock) +{ + u64 i; + u64 loops = loops_per_jiffy * HZ; + + for (i = 0; i < loops; i++) { + if (arch_spin_trylock(&lock->raw_lock)) + return; + __delay(1); + } + /* lockup suspected: */ + spin_dump(lock, "lockup suspected"); +#ifdef CONFIG_SMP + trigger_all_cpu_backtrace(); +#endif + + /* + * The trylock above was causing a livelock. Give the lower level arch + * specific lock code a chance to acquire the lock. We have already + * printed a warning/backtrace at this point. The non-debug arch + * specific code might actually succeed in acquiring the lock. If it is + * not successful, the end-result is the same - there is no forward + * progress. + */ + arch_spin_lock(&lock->raw_lock); +} + +void do_raw_spin_lock(raw_spinlock_t *lock) +{ + debug_spin_lock_before(lock); + if (unlikely(!arch_spin_trylock(&lock->raw_lock))) + __spin_lock_debug(lock); + debug_spin_lock_after(lock); +} + +int do_raw_spin_trylock(raw_spinlock_t *lock) +{ + int ret = arch_spin_trylock(&lock->raw_lock); + + if (ret) + debug_spin_lock_after(lock); +#ifndef CONFIG_SMP + /* + * Must not happen on UP: + */ + SPIN_BUG_ON(!ret, lock, "trylock failure on UP"); +#endif + return ret; +} + +void do_raw_spin_unlock(raw_spinlock_t *lock) +{ + debug_spin_unlock(lock); + arch_spin_unlock(&lock->raw_lock); +} + +#ifndef CONFIG_PREEMPT_RT_FULL +static void rwlock_bug(rwlock_t *lock, const char *msg) +{ + if (!debug_locks_off()) + return; + + printk(KERN_EMERG "BUG: rwlock %s on CPU#%d, %s/%d, %p\n", + msg, raw_smp_processor_id(), current->comm, + task_pid_nr(current), lock); + dump_stack(); +} + +#define RWLOCK_BUG_ON(cond, lock, msg) if (unlikely(cond)) rwlock_bug(lock, msg) + +#if 0 /* __write_lock_debug() can lock up - maybe this can too? */ +static void __read_lock_debug(rwlock_t *lock) +{ + u64 i; + u64 loops = loops_per_jiffy * HZ; + int print_once = 1; + + for (;;) { + for (i = 0; i < loops; i++) { + if (arch_read_trylock(&lock->raw_lock)) + return; + __delay(1); + } + /* lockup suspected: */ + if (print_once) { + print_once = 0; + printk(KERN_EMERG "BUG: read-lock lockup on CPU#%d, " + "%s/%d, %p\n", + raw_smp_processor_id(), current->comm, + current->pid, lock); + dump_stack(); + } + } +} +#endif + +void do_raw_read_lock(rwlock_t *lock) +{ + RWLOCK_BUG_ON(lock->magic != RWLOCK_MAGIC, lock, "bad magic"); + arch_read_lock(&lock->raw_lock); +} + +int do_raw_read_trylock(rwlock_t *lock) +{ + int ret = arch_read_trylock(&lock->raw_lock); + +#ifndef CONFIG_SMP + /* + * Must not happen on UP: + */ + RWLOCK_BUG_ON(!ret, lock, "trylock failure on UP"); +#endif + return ret; +} + +void do_raw_read_unlock(rwlock_t *lock) +{ + RWLOCK_BUG_ON(lock->magic != RWLOCK_MAGIC, lock, "bad magic"); + arch_read_unlock(&lock->raw_lock); +} + +static inline void debug_write_lock_before(rwlock_t *lock) +{ + RWLOCK_BUG_ON(lock->magic != RWLOCK_MAGIC, lock, "bad magic"); + RWLOCK_BUG_ON(lock->owner == current, lock, "recursion"); + RWLOCK_BUG_ON(lock->owner_cpu == raw_smp_processor_id(), + lock, "cpu recursion"); +} + +static inline void debug_write_lock_after(rwlock_t *lock) +{ + lock->owner_cpu = raw_smp_processor_id(); + lock->owner = current; +} + +static inline void debug_write_unlock(rwlock_t *lock) +{ + RWLOCK_BUG_ON(lock->magic != RWLOCK_MAGIC, lock, "bad magic"); + RWLOCK_BUG_ON(lock->owner != current, lock, "wrong owner"); + RWLOCK_BUG_ON(lock->owner_cpu != raw_smp_processor_id(), + lock, "wrong CPU"); + lock->owner = SPINLOCK_OWNER_INIT; + lock->owner_cpu = -1; +} + +#if 0 /* This can cause lockups */ +static void __write_lock_debug(rwlock_t *lock) +{ + u64 i; + u64 loops = loops_per_jiffy * HZ; + int print_once = 1; + + for (;;) { + for (i = 0; i < loops; i++) { + if (arch_write_trylock(&lock->raw_lock)) + return; + __delay(1); + } + /* lockup suspected: */ + if (print_once) { + print_once = 0; + printk(KERN_EMERG "BUG: write-lock lockup on CPU#%d, " + "%s/%d, %p\n", + raw_smp_processor_id(), current->comm, + current->pid, lock); + dump_stack(); + } + } +} +#endif + +void do_raw_write_lock(rwlock_t *lock) +{ + debug_write_lock_before(lock); + arch_write_lock(&lock->raw_lock); + debug_write_lock_after(lock); +} + +int do_raw_write_trylock(rwlock_t *lock) +{ + int ret = arch_write_trylock(&lock->raw_lock); + + if (ret) + debug_write_lock_after(lock); +#ifndef CONFIG_SMP + /* + * Must not happen on UP: + */ + RWLOCK_BUG_ON(!ret, lock, "trylock failure on UP"); +#endif + return ret; +} + +void do_raw_write_unlock(rwlock_t *lock) +{ + debug_write_unlock(lock); + arch_write_unlock(&lock->raw_lock); +} + +#endif diff --git a/kernel/kernel/module-internal.h b/kernel/kernel/module-internal.h new file mode 100644 index 000000000..915e123a4 --- /dev/null +++ b/kernel/kernel/module-internal.h @@ -0,0 +1,12 @@ +/* Module internals + * + * Copyright (C) 2012 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public Licence + * as published by the Free Software Foundation; either version + * 2 of the Licence, or (at your option) any later version. + */ + +extern int mod_verify_sig(const void *mod, unsigned long *_modlen); diff --git a/kernel/kernel/module.c b/kernel/kernel/module.c new file mode 100644 index 000000000..cfc9e843a --- /dev/null +++ b/kernel/kernel/module.c @@ -0,0 +1,3917 @@ +/* + Copyright (C) 2002 Richard Henderson + Copyright (C) 2001 Rusty Russell, 2002, 2010 Rusty Russell IBM. + + This program is free software; you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation; either version 2 of the License, or + (at your option) any later version. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU General Public License for more details. + + You should have received a copy of the GNU General Public License + along with this program; if not, write to the Free Software + Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA +*/ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include "module-internal.h" + +#define CREATE_TRACE_POINTS +#include + +#ifndef ARCH_SHF_SMALL +#define ARCH_SHF_SMALL 0 +#endif + +/* + * Modules' sections will be aligned on page boundaries + * to ensure complete separation of code and data, but + * only when CONFIG_DEBUG_SET_MODULE_RONX=y + */ +#ifdef CONFIG_DEBUG_SET_MODULE_RONX +# define debug_align(X) ALIGN(X, PAGE_SIZE) +#else +# define debug_align(X) (X) +#endif + +/* + * Given BASE and SIZE this macro calculates the number of pages the + * memory regions occupies + */ +#define MOD_NUMBER_OF_PAGES(BASE, SIZE) (((SIZE) > 0) ? \ + (PFN_DOWN((unsigned long)(BASE) + (SIZE) - 1) - \ + PFN_DOWN((unsigned long)BASE) + 1) \ + : (0UL)) + +/* If this is set, the section belongs in the init part of the module */ +#define INIT_OFFSET_MASK (1UL << (BITS_PER_LONG-1)) + +/* + * Mutex protects: + * 1) List of modules (also safely readable with preempt_disable), + * 2) module_use links, + * 3) module_addr_min/module_addr_max. + * (delete and add uses RCU list operations). */ +DEFINE_MUTEX(module_mutex); +EXPORT_SYMBOL_GPL(module_mutex); +static LIST_HEAD(modules); +#ifdef CONFIG_KGDB_KDB +struct list_head *kdb_modules = &modules; /* kdb needs the list of modules */ +#endif /* CONFIG_KGDB_KDB */ + +#ifdef CONFIG_MODULE_SIG +#ifdef CONFIG_MODULE_SIG_FORCE +static bool sig_enforce = true; +#else +static bool sig_enforce = false; + +static int param_set_bool_enable_only(const char *val, + const struct kernel_param *kp) +{ + int err; + bool test; + struct kernel_param dummy_kp = *kp; + + dummy_kp.arg = &test; + + err = param_set_bool(val, &dummy_kp); + if (err) + return err; + + /* Don't let them unset it once it's set! */ + if (!test && sig_enforce) + return -EROFS; + + if (test) + sig_enforce = true; + return 0; +} + +static const struct kernel_param_ops param_ops_bool_enable_only = { + .flags = KERNEL_PARAM_OPS_FL_NOARG, + .set = param_set_bool_enable_only, + .get = param_get_bool, +}; +#define param_check_bool_enable_only param_check_bool + +module_param(sig_enforce, bool_enable_only, 0644); +#endif /* !CONFIG_MODULE_SIG_FORCE */ +#endif /* CONFIG_MODULE_SIG */ + +/* Block module loading/unloading? */ +int modules_disabled = 0; +core_param(nomodule, modules_disabled, bint, 0); + +/* Waiting for a module to finish initializing? */ +static DECLARE_WAIT_QUEUE_HEAD(module_wq); + +static BLOCKING_NOTIFIER_HEAD(module_notify_list); + +/* Bounds of module allocation, for speeding __module_address. + * Protected by module_mutex. */ +static unsigned long module_addr_min = -1UL, module_addr_max = 0; + +int register_module_notifier(struct notifier_block *nb) +{ + return blocking_notifier_chain_register(&module_notify_list, nb); +} +EXPORT_SYMBOL(register_module_notifier); + +int unregister_module_notifier(struct notifier_block *nb) +{ + return blocking_notifier_chain_unregister(&module_notify_list, nb); +} +EXPORT_SYMBOL(unregister_module_notifier); + +struct load_info { + Elf_Ehdr *hdr; + unsigned long len; + Elf_Shdr *sechdrs; + char *secstrings, *strtab; + unsigned long symoffs, stroffs; + struct _ddebug *debug; + unsigned int num_debug; + bool sig_ok; + struct { + unsigned int sym, str, mod, vers, info, pcpu; + } index; +}; + +/* We require a truly strong try_module_get(): 0 means failure due to + ongoing or failed initialization etc. */ +static inline int strong_try_module_get(struct module *mod) +{ + BUG_ON(mod && mod->state == MODULE_STATE_UNFORMED); + if (mod && mod->state == MODULE_STATE_COMING) + return -EBUSY; + if (try_module_get(mod)) + return 0; + else + return -ENOENT; +} + +static inline void add_taint_module(struct module *mod, unsigned flag, + enum lockdep_ok lockdep_ok) +{ + add_taint(flag, lockdep_ok); + mod->taints |= (1U << flag); +} + +/* + * A thread that wants to hold a reference to a module only while it + * is running can call this to safely exit. nfsd and lockd use this. + */ +void __module_put_and_exit(struct module *mod, long code) +{ + module_put(mod); + do_exit(code); +} +EXPORT_SYMBOL(__module_put_and_exit); + +/* Find a module section: 0 means not found. */ +static unsigned int find_sec(const struct load_info *info, const char *name) +{ + unsigned int i; + + for (i = 1; i < info->hdr->e_shnum; i++) { + Elf_Shdr *shdr = &info->sechdrs[i]; + /* Alloc bit cleared means "ignore it." */ + if ((shdr->sh_flags & SHF_ALLOC) + && strcmp(info->secstrings + shdr->sh_name, name) == 0) + return i; + } + return 0; +} + +/* Find a module section, or NULL. */ +static void *section_addr(const struct load_info *info, const char *name) +{ + /* Section 0 has sh_addr 0. */ + return (void *)info->sechdrs[find_sec(info, name)].sh_addr; +} + +/* Find a module section, or NULL. Fill in number of "objects" in section. */ +static void *section_objs(const struct load_info *info, + const char *name, + size_t object_size, + unsigned int *num) +{ + unsigned int sec = find_sec(info, name); + + /* Section 0 has sh_addr 0 and sh_size 0. */ + *num = info->sechdrs[sec].sh_size / object_size; + return (void *)info->sechdrs[sec].sh_addr; +} + +/* Provided by the linker */ +extern const struct kernel_symbol __start___ksymtab[]; +extern const struct kernel_symbol __stop___ksymtab[]; +extern const struct kernel_symbol __start___ksymtab_gpl[]; +extern const struct kernel_symbol __stop___ksymtab_gpl[]; +extern const struct kernel_symbol __start___ksymtab_gpl_future[]; +extern const struct kernel_symbol __stop___ksymtab_gpl_future[]; +extern const unsigned long __start___kcrctab[]; +extern const unsigned long __start___kcrctab_gpl[]; +extern const unsigned long __start___kcrctab_gpl_future[]; +#ifdef CONFIG_UNUSED_SYMBOLS +extern const struct kernel_symbol __start___ksymtab_unused[]; +extern const struct kernel_symbol __stop___ksymtab_unused[]; +extern const struct kernel_symbol __start___ksymtab_unused_gpl[]; +extern const struct kernel_symbol __stop___ksymtab_unused_gpl[]; +extern const unsigned long __start___kcrctab_unused[]; +extern const unsigned long __start___kcrctab_unused_gpl[]; +#endif + +#ifndef CONFIG_MODVERSIONS +#define symversion(base, idx) NULL +#else +#define symversion(base, idx) ((base != NULL) ? ((base) + (idx)) : NULL) +#endif + +static bool each_symbol_in_section(const struct symsearch *arr, + unsigned int arrsize, + struct module *owner, + bool (*fn)(const struct symsearch *syms, + struct module *owner, + void *data), + void *data) +{ + unsigned int j; + + for (j = 0; j < arrsize; j++) { + if (fn(&arr[j], owner, data)) + return true; + } + + return false; +} + +/* Returns true as soon as fn returns true, otherwise false. */ +bool each_symbol_section(bool (*fn)(const struct symsearch *arr, + struct module *owner, + void *data), + void *data) +{ + struct module *mod; + static const struct symsearch arr[] = { + { __start___ksymtab, __stop___ksymtab, __start___kcrctab, + NOT_GPL_ONLY, false }, + { __start___ksymtab_gpl, __stop___ksymtab_gpl, + __start___kcrctab_gpl, + GPL_ONLY, false }, + { __start___ksymtab_gpl_future, __stop___ksymtab_gpl_future, + __start___kcrctab_gpl_future, + WILL_BE_GPL_ONLY, false }, +#ifdef CONFIG_UNUSED_SYMBOLS + { __start___ksymtab_unused, __stop___ksymtab_unused, + __start___kcrctab_unused, + NOT_GPL_ONLY, true }, + { __start___ksymtab_unused_gpl, __stop___ksymtab_unused_gpl, + __start___kcrctab_unused_gpl, + GPL_ONLY, true }, +#endif + }; + + if (each_symbol_in_section(arr, ARRAY_SIZE(arr), NULL, fn, data)) + return true; + + list_for_each_entry_rcu(mod, &modules, list) { + struct symsearch arr[] = { + { mod->syms, mod->syms + mod->num_syms, mod->crcs, + NOT_GPL_ONLY, false }, + { mod->gpl_syms, mod->gpl_syms + mod->num_gpl_syms, + mod->gpl_crcs, + GPL_ONLY, false }, + { mod->gpl_future_syms, + mod->gpl_future_syms + mod->num_gpl_future_syms, + mod->gpl_future_crcs, + WILL_BE_GPL_ONLY, false }, +#ifdef CONFIG_UNUSED_SYMBOLS + { mod->unused_syms, + mod->unused_syms + mod->num_unused_syms, + mod->unused_crcs, + NOT_GPL_ONLY, true }, + { mod->unused_gpl_syms, + mod->unused_gpl_syms + mod->num_unused_gpl_syms, + mod->unused_gpl_crcs, + GPL_ONLY, true }, +#endif + }; + + if (mod->state == MODULE_STATE_UNFORMED) + continue; + + if (each_symbol_in_section(arr, ARRAY_SIZE(arr), mod, fn, data)) + return true; + } + return false; +} +EXPORT_SYMBOL_GPL(each_symbol_section); + +struct find_symbol_arg { + /* Input */ + const char *name; + bool gplok; + bool warn; + + /* Output */ + struct module *owner; + const unsigned long *crc; + const struct kernel_symbol *sym; +}; + +static bool check_symbol(const struct symsearch *syms, + struct module *owner, + unsigned int symnum, void *data) +{ + struct find_symbol_arg *fsa = data; + + if (!fsa->gplok) { + if (syms->licence == GPL_ONLY) + return false; + if (syms->licence == WILL_BE_GPL_ONLY && fsa->warn) { + pr_warn("Symbol %s is being used by a non-GPL module, " + "which will not be allowed in the future\n", + fsa->name); + } + } + +#ifdef CONFIG_UNUSED_SYMBOLS + if (syms->unused && fsa->warn) { + pr_warn("Symbol %s is marked as UNUSED, however this module is " + "using it.\n", fsa->name); + pr_warn("This symbol will go away in the future.\n"); + pr_warn("Please evaluate if this is the right api to use and " + "if it really is, submit a report to the linux kernel " + "mailing list together with submitting your code for " + "inclusion.\n"); + } +#endif + + fsa->owner = owner; + fsa->crc = symversion(syms->crcs, symnum); + fsa->sym = &syms->start[symnum]; + return true; +} + +static int cmp_name(const void *va, const void *vb) +{ + const char *a; + const struct kernel_symbol *b; + a = va; b = vb; + return strcmp(a, b->name); +} + +static bool find_symbol_in_section(const struct symsearch *syms, + struct module *owner, + void *data) +{ + struct find_symbol_arg *fsa = data; + struct kernel_symbol *sym; + + sym = bsearch(fsa->name, syms->start, syms->stop - syms->start, + sizeof(struct kernel_symbol), cmp_name); + + if (sym != NULL && check_symbol(syms, owner, sym - syms->start, data)) + return true; + + return false; +} + +/* Find a symbol and return it, along with, (optional) crc and + * (optional) module which owns it. Needs preempt disabled or module_mutex. */ +const struct kernel_symbol *find_symbol(const char *name, + struct module **owner, + const unsigned long **crc, + bool gplok, + bool warn) +{ + struct find_symbol_arg fsa; + + fsa.name = name; + fsa.gplok = gplok; + fsa.warn = warn; + + if (each_symbol_section(find_symbol_in_section, &fsa)) { + if (owner) + *owner = fsa.owner; + if (crc) + *crc = fsa.crc; + return fsa.sym; + } + + pr_debug("Failed to find symbol %s\n", name); + return NULL; +} +EXPORT_SYMBOL_GPL(find_symbol); + +/* Search for module by name: must hold module_mutex. */ +static struct module *find_module_all(const char *name, size_t len, + bool even_unformed) +{ + struct module *mod; + + list_for_each_entry(mod, &modules, list) { + if (!even_unformed && mod->state == MODULE_STATE_UNFORMED) + continue; + if (strlen(mod->name) == len && !memcmp(mod->name, name, len)) + return mod; + } + return NULL; +} + +struct module *find_module(const char *name) +{ + return find_module_all(name, strlen(name), false); +} +EXPORT_SYMBOL_GPL(find_module); + +#ifdef CONFIG_SMP + +static inline void __percpu *mod_percpu(struct module *mod) +{ + return mod->percpu; +} + +static int percpu_modalloc(struct module *mod, struct load_info *info) +{ + Elf_Shdr *pcpusec = &info->sechdrs[info->index.pcpu]; + unsigned long align = pcpusec->sh_addralign; + + if (!pcpusec->sh_size) + return 0; + + if (align > PAGE_SIZE) { + pr_warn("%s: per-cpu alignment %li > %li\n", + mod->name, align, PAGE_SIZE); + align = PAGE_SIZE; + } + + mod->percpu = __alloc_reserved_percpu(pcpusec->sh_size, align); + if (!mod->percpu) { + pr_warn("%s: Could not allocate %lu bytes percpu data\n", + mod->name, (unsigned long)pcpusec->sh_size); + return -ENOMEM; + } + mod->percpu_size = pcpusec->sh_size; + return 0; +} + +static void percpu_modfree(struct module *mod) +{ + free_percpu(mod->percpu); +} + +static unsigned int find_pcpusec(struct load_info *info) +{ + return find_sec(info, ".data..percpu"); +} + +static void percpu_modcopy(struct module *mod, + const void *from, unsigned long size) +{ + int cpu; + + for_each_possible_cpu(cpu) + memcpy(per_cpu_ptr(mod->percpu, cpu), from, size); +} + +/** + * is_module_percpu_address - test whether address is from module static percpu + * @addr: address to test + * + * Test whether @addr belongs to module static percpu area. + * + * RETURNS: + * %true if @addr is from module static percpu area + */ +bool is_module_percpu_address(unsigned long addr) +{ + struct module *mod; + unsigned int cpu; + + preempt_disable(); + + list_for_each_entry_rcu(mod, &modules, list) { + if (mod->state == MODULE_STATE_UNFORMED) + continue; + if (!mod->percpu_size) + continue; + for_each_possible_cpu(cpu) { + void *start = per_cpu_ptr(mod->percpu, cpu); + + if ((void *)addr >= start && + (void *)addr < start + mod->percpu_size) { + preempt_enable(); + return true; + } + } + } + + preempt_enable(); + return false; +} + +#else /* ... !CONFIG_SMP */ + +static inline void __percpu *mod_percpu(struct module *mod) +{ + return NULL; +} +static int percpu_modalloc(struct module *mod, struct load_info *info) +{ + /* UP modules shouldn't have this section: ENOMEM isn't quite right */ + if (info->sechdrs[info->index.pcpu].sh_size != 0) + return -ENOMEM; + return 0; +} +static inline void percpu_modfree(struct module *mod) +{ +} +static unsigned int find_pcpusec(struct load_info *info) +{ + return 0; +} +static inline void percpu_modcopy(struct module *mod, + const void *from, unsigned long size) +{ + /* pcpusec should be 0, and size of that section should be 0. */ + BUG_ON(size != 0); +} +bool is_module_percpu_address(unsigned long addr) +{ + return false; +} + +#endif /* CONFIG_SMP */ + +#define MODINFO_ATTR(field) \ +static void setup_modinfo_##field(struct module *mod, const char *s) \ +{ \ + mod->field = kstrdup(s, GFP_KERNEL); \ +} \ +static ssize_t show_modinfo_##field(struct module_attribute *mattr, \ + struct module_kobject *mk, char *buffer) \ +{ \ + return scnprintf(buffer, PAGE_SIZE, "%s\n", mk->mod->field); \ +} \ +static int modinfo_##field##_exists(struct module *mod) \ +{ \ + return mod->field != NULL; \ +} \ +static void free_modinfo_##field(struct module *mod) \ +{ \ + kfree(mod->field); \ + mod->field = NULL; \ +} \ +static struct module_attribute modinfo_##field = { \ + .attr = { .name = __stringify(field), .mode = 0444 }, \ + .show = show_modinfo_##field, \ + .setup = setup_modinfo_##field, \ + .test = modinfo_##field##_exists, \ + .free = free_modinfo_##field, \ +}; + +MODINFO_ATTR(version); +MODINFO_ATTR(srcversion); + +static char last_unloaded_module[MODULE_NAME_LEN+1]; + +#ifdef CONFIG_MODULE_UNLOAD + +EXPORT_TRACEPOINT_SYMBOL(module_get); + +/* MODULE_REF_BASE is the base reference count by kmodule loader. */ +#define MODULE_REF_BASE 1 + +/* Init the unload section of the module. */ +static int module_unload_init(struct module *mod) +{ + /* + * Initialize reference counter to MODULE_REF_BASE. + * refcnt == 0 means module is going. + */ + atomic_set(&mod->refcnt, MODULE_REF_BASE); + + INIT_LIST_HEAD(&mod->source_list); + INIT_LIST_HEAD(&mod->target_list); + + /* Hold reference count during initialization. */ + atomic_inc(&mod->refcnt); + + return 0; +} + +/* Does a already use b? */ +static int already_uses(struct module *a, struct module *b) +{ + struct module_use *use; + + list_for_each_entry(use, &b->source_list, source_list) { + if (use->source == a) { + pr_debug("%s uses %s!\n", a->name, b->name); + return 1; + } + } + pr_debug("%s does not use %s!\n", a->name, b->name); + return 0; +} + +/* + * Module a uses b + * - we add 'a' as a "source", 'b' as a "target" of module use + * - the module_use is added to the list of 'b' sources (so + * 'b' can walk the list to see who sourced them), and of 'a' + * targets (so 'a' can see what modules it targets). + */ +static int add_module_usage(struct module *a, struct module *b) +{ + struct module_use *use; + + pr_debug("Allocating new usage for %s.\n", a->name); + use = kmalloc(sizeof(*use), GFP_ATOMIC); + if (!use) { + pr_warn("%s: out of memory loading\n", a->name); + return -ENOMEM; + } + + use->source = a; + use->target = b; + list_add(&use->source_list, &b->source_list); + list_add(&use->target_list, &a->target_list); + return 0; +} + +/* Module a uses b: caller needs module_mutex() */ +int ref_module(struct module *a, struct module *b) +{ + int err; + + if (b == NULL || already_uses(a, b)) + return 0; + + /* If module isn't available, we fail. */ + err = strong_try_module_get(b); + if (err) + return err; + + err = add_module_usage(a, b); + if (err) { + module_put(b); + return err; + } + return 0; +} +EXPORT_SYMBOL_GPL(ref_module); + +/* Clear the unload stuff of the module. */ +static void module_unload_free(struct module *mod) +{ + struct module_use *use, *tmp; + + mutex_lock(&module_mutex); + list_for_each_entry_safe(use, tmp, &mod->target_list, target_list) { + struct module *i = use->target; + pr_debug("%s unusing %s\n", mod->name, i->name); + module_put(i); + list_del(&use->source_list); + list_del(&use->target_list); + kfree(use); + } + mutex_unlock(&module_mutex); +} + +#ifdef CONFIG_MODULE_FORCE_UNLOAD +static inline int try_force_unload(unsigned int flags) +{ + int ret = (flags & O_TRUNC); + if (ret) + add_taint(TAINT_FORCED_RMMOD, LOCKDEP_NOW_UNRELIABLE); + return ret; +} +#else +static inline int try_force_unload(unsigned int flags) +{ + return 0; +} +#endif /* CONFIG_MODULE_FORCE_UNLOAD */ + +/* Try to release refcount of module, 0 means success. */ +static int try_release_module_ref(struct module *mod) +{ + int ret; + + /* Try to decrement refcnt which we set at loading */ + ret = atomic_sub_return(MODULE_REF_BASE, &mod->refcnt); + BUG_ON(ret < 0); + if (ret) + /* Someone can put this right now, recover with checking */ + ret = atomic_add_unless(&mod->refcnt, MODULE_REF_BASE, 0); + + return ret; +} + +static int try_stop_module(struct module *mod, int flags, int *forced) +{ + /* If it's not unused, quit unless we're forcing. */ + if (try_release_module_ref(mod) != 0) { + *forced = try_force_unload(flags); + if (!(*forced)) + return -EWOULDBLOCK; + } + + /* Mark it as dying. */ + mod->state = MODULE_STATE_GOING; + + return 0; +} + +/** + * module_refcount - return the refcount or -1 if unloading + * + * @mod: the module we're checking + * + * Returns: + * -1 if the module is in the process of unloading + * otherwise the number of references in the kernel to the module + */ +int module_refcount(struct module *mod) +{ + return atomic_read(&mod->refcnt) - MODULE_REF_BASE; +} +EXPORT_SYMBOL(module_refcount); + +/* This exists whether we can unload or not */ +static void free_module(struct module *mod); + +SYSCALL_DEFINE2(delete_module, const char __user *, name_user, + unsigned int, flags) +{ + struct module *mod; + char name[MODULE_NAME_LEN]; + int ret, forced = 0; + + if (!capable(CAP_SYS_MODULE) || modules_disabled) + return -EPERM; + + if (strncpy_from_user(name, name_user, MODULE_NAME_LEN-1) < 0) + return -EFAULT; + name[MODULE_NAME_LEN-1] = '\0'; + + if (mutex_lock_interruptible(&module_mutex) != 0) + return -EINTR; + + mod = find_module(name); + if (!mod) { + ret = -ENOENT; + goto out; + } + + if (!list_empty(&mod->source_list)) { + /* Other modules depend on us: get rid of them first. */ + ret = -EWOULDBLOCK; + goto out; + } + + /* Doing init or already dying? */ + if (mod->state != MODULE_STATE_LIVE) { + /* FIXME: if (force), slam module count damn the torpedoes */ + pr_debug("%s already dying\n", mod->name); + ret = -EBUSY; + goto out; + } + + /* If it has an init func, it must have an exit func to unload */ + if (mod->init && !mod->exit) { + forced = try_force_unload(flags); + if (!forced) { + /* This module can't be removed */ + ret = -EBUSY; + goto out; + } + } + + /* Stop the machine so refcounts can't move and disable module. */ + ret = try_stop_module(mod, flags, &forced); + if (ret != 0) + goto out; + + mutex_unlock(&module_mutex); + /* Final destruction now no one is using it. */ + if (mod->exit != NULL) + mod->exit(); + blocking_notifier_call_chain(&module_notify_list, + MODULE_STATE_GOING, mod); + async_synchronize_full(); + + /* Store the name of the last unloaded module for diagnostic purposes */ + strlcpy(last_unloaded_module, mod->name, sizeof(last_unloaded_module)); + + free_module(mod); + return 0; +out: + mutex_unlock(&module_mutex); + return ret; +} + +static inline void print_unload_info(struct seq_file *m, struct module *mod) +{ + struct module_use *use; + int printed_something = 0; + + seq_printf(m, " %i ", module_refcount(mod)); + + /* + * Always include a trailing , so userspace can differentiate + * between this and the old multi-field proc format. + */ + list_for_each_entry(use, &mod->source_list, source_list) { + printed_something = 1; + seq_printf(m, "%s,", use->source->name); + } + + if (mod->init != NULL && mod->exit == NULL) { + printed_something = 1; + seq_puts(m, "[permanent],"); + } + + if (!printed_something) + seq_puts(m, "-"); +} + +void __symbol_put(const char *symbol) +{ + struct module *owner; + + preempt_disable(); + if (!find_symbol(symbol, &owner, NULL, true, false)) + BUG(); + module_put(owner); + preempt_enable(); +} +EXPORT_SYMBOL(__symbol_put); + +/* Note this assumes addr is a function, which it currently always is. */ +void symbol_put_addr(void *addr) +{ + struct module *modaddr; + unsigned long a = (unsigned long)dereference_function_descriptor(addr); + + if (core_kernel_text(a)) + return; + + /* module_text_address is safe here: we're supposed to have reference + * to module from symbol_get, so it can't go away. */ + modaddr = __module_text_address(a); + BUG_ON(!modaddr); + module_put(modaddr); +} +EXPORT_SYMBOL_GPL(symbol_put_addr); + +static ssize_t show_refcnt(struct module_attribute *mattr, + struct module_kobject *mk, char *buffer) +{ + return sprintf(buffer, "%i\n", module_refcount(mk->mod)); +} + +static struct module_attribute modinfo_refcnt = + __ATTR(refcnt, 0444, show_refcnt, NULL); + +void __module_get(struct module *module) +{ + if (module) { + preempt_disable(); + atomic_inc(&module->refcnt); + trace_module_get(module, _RET_IP_); + preempt_enable(); + } +} +EXPORT_SYMBOL(__module_get); + +bool try_module_get(struct module *module) +{ + bool ret = true; + + if (module) { + preempt_disable(); + /* Note: here, we can fail to get a reference */ + if (likely(module_is_live(module) && + atomic_inc_not_zero(&module->refcnt) != 0)) + trace_module_get(module, _RET_IP_); + else + ret = false; + + preempt_enable(); + } + return ret; +} +EXPORT_SYMBOL(try_module_get); + +void module_put(struct module *module) +{ + int ret; + + if (module) { + preempt_disable(); + ret = atomic_dec_if_positive(&module->refcnt); + WARN_ON(ret < 0); /* Failed to put refcount */ + trace_module_put(module, _RET_IP_); + preempt_enable(); + } +} +EXPORT_SYMBOL(module_put); + +#else /* !CONFIG_MODULE_UNLOAD */ +static inline void print_unload_info(struct seq_file *m, struct module *mod) +{ + /* We don't know the usage count, or what modules are using. */ + seq_puts(m, " - -"); +} + +static inline void module_unload_free(struct module *mod) +{ +} + +int ref_module(struct module *a, struct module *b) +{ + return strong_try_module_get(b); +} +EXPORT_SYMBOL_GPL(ref_module); + +static inline int module_unload_init(struct module *mod) +{ + return 0; +} +#endif /* CONFIG_MODULE_UNLOAD */ + +static size_t module_flags_taint(struct module *mod, char *buf) +{ + size_t l = 0; + + if (mod->taints & (1 << TAINT_PROPRIETARY_MODULE)) + buf[l++] = 'P'; + if (mod->taints & (1 << TAINT_OOT_MODULE)) + buf[l++] = 'O'; + if (mod->taints & (1 << TAINT_FORCED_MODULE)) + buf[l++] = 'F'; + if (mod->taints & (1 << TAINT_CRAP)) + buf[l++] = 'C'; + if (mod->taints & (1 << TAINT_UNSIGNED_MODULE)) + buf[l++] = 'E'; + /* + * TAINT_FORCED_RMMOD: could be added. + * TAINT_CPU_OUT_OF_SPEC, TAINT_MACHINE_CHECK, TAINT_BAD_PAGE don't + * apply to modules. + */ + return l; +} + +static ssize_t show_initstate(struct module_attribute *mattr, + struct module_kobject *mk, char *buffer) +{ + const char *state = "unknown"; + + switch (mk->mod->state) { + case MODULE_STATE_LIVE: + state = "live"; + break; + case MODULE_STATE_COMING: + state = "coming"; + break; + case MODULE_STATE_GOING: + state = "going"; + break; + default: + BUG(); + } + return sprintf(buffer, "%s\n", state); +} + +static struct module_attribute modinfo_initstate = + __ATTR(initstate, 0444, show_initstate, NULL); + +static ssize_t store_uevent(struct module_attribute *mattr, + struct module_kobject *mk, + const char *buffer, size_t count) +{ + enum kobject_action action; + + if (kobject_action_type(buffer, count, &action) == 0) + kobject_uevent(&mk->kobj, action); + return count; +} + +struct module_attribute module_uevent = + __ATTR(uevent, 0200, NULL, store_uevent); + +static ssize_t show_coresize(struct module_attribute *mattr, + struct module_kobject *mk, char *buffer) +{ + return sprintf(buffer, "%u\n", mk->mod->core_size); +} + +static struct module_attribute modinfo_coresize = + __ATTR(coresize, 0444, show_coresize, NULL); + +static ssize_t show_initsize(struct module_attribute *mattr, + struct module_kobject *mk, char *buffer) +{ + return sprintf(buffer, "%u\n", mk->mod->init_size); +} + +static struct module_attribute modinfo_initsize = + __ATTR(initsize, 0444, show_initsize, NULL); + +static ssize_t show_taint(struct module_attribute *mattr, + struct module_kobject *mk, char *buffer) +{ + size_t l; + + l = module_flags_taint(mk->mod, buffer); + buffer[l++] = '\n'; + return l; +} + +static struct module_attribute modinfo_taint = + __ATTR(taint, 0444, show_taint, NULL); + +static struct module_attribute *modinfo_attrs[] = { + &module_uevent, + &modinfo_version, + &modinfo_srcversion, + &modinfo_initstate, + &modinfo_coresize, + &modinfo_initsize, + &modinfo_taint, +#ifdef CONFIG_MODULE_UNLOAD + &modinfo_refcnt, +#endif + NULL, +}; + +static const char vermagic[] = VERMAGIC_STRING; + +static int try_to_force_load(struct module *mod, const char *reason) +{ +#ifdef CONFIG_MODULE_FORCE_LOAD + if (!test_taint(TAINT_FORCED_MODULE)) + pr_warn("%s: %s: kernel tainted.\n", mod->name, reason); + add_taint_module(mod, TAINT_FORCED_MODULE, LOCKDEP_NOW_UNRELIABLE); + return 0; +#else + return -ENOEXEC; +#endif +} + +#ifdef CONFIG_MODVERSIONS +/* If the arch applies (non-zero) relocations to kernel kcrctab, unapply it. */ +static unsigned long maybe_relocated(unsigned long crc, + const struct module *crc_owner) +{ +#ifdef ARCH_RELOCATES_KCRCTAB + if (crc_owner == NULL) + return crc - (unsigned long)reloc_start; +#endif + return crc; +} + +static int check_version(Elf_Shdr *sechdrs, + unsigned int versindex, + const char *symname, + struct module *mod, + const unsigned long *crc, + const struct module *crc_owner) +{ + unsigned int i, num_versions; + struct modversion_info *versions; + + /* Exporting module didn't supply crcs? OK, we're already tainted. */ + if (!crc) + return 1; + + /* No versions at all? modprobe --force does this. */ + if (versindex == 0) + return try_to_force_load(mod, symname) == 0; + + versions = (void *) sechdrs[versindex].sh_addr; + num_versions = sechdrs[versindex].sh_size + / sizeof(struct modversion_info); + + for (i = 0; i < num_versions; i++) { + if (strcmp(versions[i].name, symname) != 0) + continue; + + if (versions[i].crc == maybe_relocated(*crc, crc_owner)) + return 1; + pr_debug("Found checksum %lX vs module %lX\n", + maybe_relocated(*crc, crc_owner), versions[i].crc); + goto bad_version; + } + + pr_warn("%s: no symbol version for %s\n", mod->name, symname); + return 0; + +bad_version: + pr_warn("%s: disagrees about version of symbol %s\n", + mod->name, symname); + return 0; +} + +static inline int check_modstruct_version(Elf_Shdr *sechdrs, + unsigned int versindex, + struct module *mod) +{ + const unsigned long *crc; + + /* Since this should be found in kernel (which can't be removed), + * no locking is necessary. */ + if (!find_symbol(VMLINUX_SYMBOL_STR(module_layout), NULL, + &crc, true, false)) + BUG(); + return check_version(sechdrs, versindex, + VMLINUX_SYMBOL_STR(module_layout), mod, crc, + NULL); +} + +/* First part is kernel version, which we ignore if module has crcs. */ +static inline int same_magic(const char *amagic, const char *bmagic, + bool has_crcs) +{ + if (has_crcs) { + amagic += strcspn(amagic, " "); + bmagic += strcspn(bmagic, " "); + } + return strcmp(amagic, bmagic) == 0; +} +#else +static inline int check_version(Elf_Shdr *sechdrs, + unsigned int versindex, + const char *symname, + struct module *mod, + const unsigned long *crc, + const struct module *crc_owner) +{ + return 1; +} + +static inline int check_modstruct_version(Elf_Shdr *sechdrs, + unsigned int versindex, + struct module *mod) +{ + return 1; +} + +static inline int same_magic(const char *amagic, const char *bmagic, + bool has_crcs) +{ + return strcmp(amagic, bmagic) == 0; +} +#endif /* CONFIG_MODVERSIONS */ + +/* Resolve a symbol for this module. I.e. if we find one, record usage. */ +static const struct kernel_symbol *resolve_symbol(struct module *mod, + const struct load_info *info, + const char *name, + char ownername[]) +{ + struct module *owner; + const struct kernel_symbol *sym; + const unsigned long *crc; + int err; + + /* + * The module_mutex should not be a heavily contended lock; + * if we get the occasional sleep here, we'll go an extra iteration + * in the wait_event_interruptible(), which is harmless. + */ + sched_annotate_sleep(); + mutex_lock(&module_mutex); + sym = find_symbol(name, &owner, &crc, + !(mod->taints & (1 << TAINT_PROPRIETARY_MODULE)), true); + if (!sym) + goto unlock; + + if (!check_version(info->sechdrs, info->index.vers, name, mod, crc, + owner)) { + sym = ERR_PTR(-EINVAL); + goto getname; + } + + err = ref_module(mod, owner); + if (err) { + sym = ERR_PTR(err); + goto getname; + } + +getname: + /* We must make copy under the lock if we failed to get ref. */ + strncpy(ownername, module_name(owner), MODULE_NAME_LEN); +unlock: + mutex_unlock(&module_mutex); + return sym; +} + +static const struct kernel_symbol * +resolve_symbol_wait(struct module *mod, + const struct load_info *info, + const char *name) +{ + const struct kernel_symbol *ksym; + char owner[MODULE_NAME_LEN]; + + if (wait_event_interruptible_timeout(module_wq, + !IS_ERR(ksym = resolve_symbol(mod, info, name, owner)) + || PTR_ERR(ksym) != -EBUSY, + 30 * HZ) <= 0) { + pr_warn("%s: gave up waiting for init of module %s.\n", + mod->name, owner); + } + return ksym; +} + +/* + * /sys/module/foo/sections stuff + * J. Corbet + */ +#ifdef CONFIG_SYSFS + +#ifdef CONFIG_KALLSYMS +static inline bool sect_empty(const Elf_Shdr *sect) +{ + return !(sect->sh_flags & SHF_ALLOC) || sect->sh_size == 0; +} + +struct module_sect_attr { + struct module_attribute mattr; + char *name; + unsigned long address; +}; + +struct module_sect_attrs { + struct attribute_group grp; + unsigned int nsections; + struct module_sect_attr attrs[0]; +}; + +static ssize_t module_sect_show(struct module_attribute *mattr, + struct module_kobject *mk, char *buf) +{ + struct module_sect_attr *sattr = + container_of(mattr, struct module_sect_attr, mattr); + return sprintf(buf, "0x%pK\n", (void *)sattr->address); +} + +static void free_sect_attrs(struct module_sect_attrs *sect_attrs) +{ + unsigned int section; + + for (section = 0; section < sect_attrs->nsections; section++) + kfree(sect_attrs->attrs[section].name); + kfree(sect_attrs); +} + +static void add_sect_attrs(struct module *mod, const struct load_info *info) +{ + unsigned int nloaded = 0, i, size[2]; + struct module_sect_attrs *sect_attrs; + struct module_sect_attr *sattr; + struct attribute **gattr; + + /* Count loaded sections and allocate structures */ + for (i = 0; i < info->hdr->e_shnum; i++) + if (!sect_empty(&info->sechdrs[i])) + nloaded++; + size[0] = ALIGN(sizeof(*sect_attrs) + + nloaded * sizeof(sect_attrs->attrs[0]), + sizeof(sect_attrs->grp.attrs[0])); + size[1] = (nloaded + 1) * sizeof(sect_attrs->grp.attrs[0]); + sect_attrs = kzalloc(size[0] + size[1], GFP_KERNEL); + if (sect_attrs == NULL) + return; + + /* Setup section attributes. */ + sect_attrs->grp.name = "sections"; + sect_attrs->grp.attrs = (void *)sect_attrs + size[0]; + + sect_attrs->nsections = 0; + sattr = §_attrs->attrs[0]; + gattr = §_attrs->grp.attrs[0]; + for (i = 0; i < info->hdr->e_shnum; i++) { + Elf_Shdr *sec = &info->sechdrs[i]; + if (sect_empty(sec)) + continue; + sattr->address = sec->sh_addr; + sattr->name = kstrdup(info->secstrings + sec->sh_name, + GFP_KERNEL); + if (sattr->name == NULL) + goto out; + sect_attrs->nsections++; + sysfs_attr_init(&sattr->mattr.attr); + sattr->mattr.show = module_sect_show; + sattr->mattr.store = NULL; + sattr->mattr.attr.name = sattr->name; + sattr->mattr.attr.mode = S_IRUGO; + *(gattr++) = &(sattr++)->mattr.attr; + } + *gattr = NULL; + + if (sysfs_create_group(&mod->mkobj.kobj, §_attrs->grp)) + goto out; + + mod->sect_attrs = sect_attrs; + return; + out: + free_sect_attrs(sect_attrs); +} + +static void remove_sect_attrs(struct module *mod) +{ + if (mod->sect_attrs) { + sysfs_remove_group(&mod->mkobj.kobj, + &mod->sect_attrs->grp); + /* We are positive that no one is using any sect attrs + * at this point. Deallocate immediately. */ + free_sect_attrs(mod->sect_attrs); + mod->sect_attrs = NULL; + } +} + +/* + * /sys/module/foo/notes/.section.name gives contents of SHT_NOTE sections. + */ + +struct module_notes_attrs { + struct kobject *dir; + unsigned int notes; + struct bin_attribute attrs[0]; +}; + +static ssize_t module_notes_read(struct file *filp, struct kobject *kobj, + struct bin_attribute *bin_attr, + char *buf, loff_t pos, size_t count) +{ + /* + * The caller checked the pos and count against our size. + */ + memcpy(buf, bin_attr->private + pos, count); + return count; +} + +static void free_notes_attrs(struct module_notes_attrs *notes_attrs, + unsigned int i) +{ + if (notes_attrs->dir) { + while (i-- > 0) + sysfs_remove_bin_file(notes_attrs->dir, + ¬es_attrs->attrs[i]); + kobject_put(notes_attrs->dir); + } + kfree(notes_attrs); +} + +static void add_notes_attrs(struct module *mod, const struct load_info *info) +{ + unsigned int notes, loaded, i; + struct module_notes_attrs *notes_attrs; + struct bin_attribute *nattr; + + /* failed to create section attributes, so can't create notes */ + if (!mod->sect_attrs) + return; + + /* Count notes sections and allocate structures. */ + notes = 0; + for (i = 0; i < info->hdr->e_shnum; i++) + if (!sect_empty(&info->sechdrs[i]) && + (info->sechdrs[i].sh_type == SHT_NOTE)) + ++notes; + + if (notes == 0) + return; + + notes_attrs = kzalloc(sizeof(*notes_attrs) + + notes * sizeof(notes_attrs->attrs[0]), + GFP_KERNEL); + if (notes_attrs == NULL) + return; + + notes_attrs->notes = notes; + nattr = ¬es_attrs->attrs[0]; + for (loaded = i = 0; i < info->hdr->e_shnum; ++i) { + if (sect_empty(&info->sechdrs[i])) + continue; + if (info->sechdrs[i].sh_type == SHT_NOTE) { + sysfs_bin_attr_init(nattr); + nattr->attr.name = mod->sect_attrs->attrs[loaded].name; + nattr->attr.mode = S_IRUGO; + nattr->size = info->sechdrs[i].sh_size; + nattr->private = (void *) info->sechdrs[i].sh_addr; + nattr->read = module_notes_read; + ++nattr; + } + ++loaded; + } + + notes_attrs->dir = kobject_create_and_add("notes", &mod->mkobj.kobj); + if (!notes_attrs->dir) + goto out; + + for (i = 0; i < notes; ++i) + if (sysfs_create_bin_file(notes_attrs->dir, + ¬es_attrs->attrs[i])) + goto out; + + mod->notes_attrs = notes_attrs; + return; + + out: + free_notes_attrs(notes_attrs, i); +} + +static void remove_notes_attrs(struct module *mod) +{ + if (mod->notes_attrs) + free_notes_attrs(mod->notes_attrs, mod->notes_attrs->notes); +} + +#else + +static inline void add_sect_attrs(struct module *mod, + const struct load_info *info) +{ +} + +static inline void remove_sect_attrs(struct module *mod) +{ +} + +static inline void add_notes_attrs(struct module *mod, + const struct load_info *info) +{ +} + +static inline void remove_notes_attrs(struct module *mod) +{ +} +#endif /* CONFIG_KALLSYMS */ + +static void add_usage_links(struct module *mod) +{ +#ifdef CONFIG_MODULE_UNLOAD + struct module_use *use; + int nowarn; + + mutex_lock(&module_mutex); + list_for_each_entry(use, &mod->target_list, target_list) { + nowarn = sysfs_create_link(use->target->holders_dir, + &mod->mkobj.kobj, mod->name); + } + mutex_unlock(&module_mutex); +#endif +} + +static void del_usage_links(struct module *mod) +{ +#ifdef CONFIG_MODULE_UNLOAD + struct module_use *use; + + mutex_lock(&module_mutex); + list_for_each_entry(use, &mod->target_list, target_list) + sysfs_remove_link(use->target->holders_dir, mod->name); + mutex_unlock(&module_mutex); +#endif +} + +static int module_add_modinfo_attrs(struct module *mod) +{ + struct module_attribute *attr; + struct module_attribute *temp_attr; + int error = 0; + int i; + + mod->modinfo_attrs = kzalloc((sizeof(struct module_attribute) * + (ARRAY_SIZE(modinfo_attrs) + 1)), + GFP_KERNEL); + if (!mod->modinfo_attrs) + return -ENOMEM; + + temp_attr = mod->modinfo_attrs; + for (i = 0; (attr = modinfo_attrs[i]) && !error; i++) { + if (!attr->test || + (attr->test && attr->test(mod))) { + memcpy(temp_attr, attr, sizeof(*temp_attr)); + sysfs_attr_init(&temp_attr->attr); + error = sysfs_create_file(&mod->mkobj.kobj, + &temp_attr->attr); + ++temp_attr; + } + } + return error; +} + +static void module_remove_modinfo_attrs(struct module *mod) +{ + struct module_attribute *attr; + int i; + + for (i = 0; (attr = &mod->modinfo_attrs[i]); i++) { + /* pick a field to test for end of list */ + if (!attr->attr.name) + break; + sysfs_remove_file(&mod->mkobj.kobj, &attr->attr); + if (attr->free) + attr->free(mod); + } + kfree(mod->modinfo_attrs); +} + +static void mod_kobject_put(struct module *mod) +{ + DECLARE_COMPLETION_ONSTACK(c); + mod->mkobj.kobj_completion = &c; + kobject_put(&mod->mkobj.kobj); + wait_for_completion(&c); +} + +static int mod_sysfs_init(struct module *mod) +{ + int err; + struct kobject *kobj; + + if (!module_sysfs_initialized) { + pr_err("%s: module sysfs not initialized\n", mod->name); + err = -EINVAL; + goto out; + } + + kobj = kset_find_obj(module_kset, mod->name); + if (kobj) { + pr_err("%s: module is already loaded\n", mod->name); + kobject_put(kobj); + err = -EINVAL; + goto out; + } + + mod->mkobj.mod = mod; + + memset(&mod->mkobj.kobj, 0, sizeof(mod->mkobj.kobj)); + mod->mkobj.kobj.kset = module_kset; + err = kobject_init_and_add(&mod->mkobj.kobj, &module_ktype, NULL, + "%s", mod->name); + if (err) + mod_kobject_put(mod); + + /* delay uevent until full sysfs population */ +out: + return err; +} + +static int mod_sysfs_setup(struct module *mod, + const struct load_info *info, + struct kernel_param *kparam, + unsigned int num_params) +{ + int err; + + err = mod_sysfs_init(mod); + if (err) + goto out; + + mod->holders_dir = kobject_create_and_add("holders", &mod->mkobj.kobj); + if (!mod->holders_dir) { + err = -ENOMEM; + goto out_unreg; + } + + err = module_param_sysfs_setup(mod, kparam, num_params); + if (err) + goto out_unreg_holders; + + err = module_add_modinfo_attrs(mod); + if (err) + goto out_unreg_param; + + add_usage_links(mod); + add_sect_attrs(mod, info); + add_notes_attrs(mod, info); + + kobject_uevent(&mod->mkobj.kobj, KOBJ_ADD); + return 0; + +out_unreg_param: + module_param_sysfs_remove(mod); +out_unreg_holders: + kobject_put(mod->holders_dir); +out_unreg: + mod_kobject_put(mod); +out: + return err; +} + +static void mod_sysfs_fini(struct module *mod) +{ + remove_notes_attrs(mod); + remove_sect_attrs(mod); + mod_kobject_put(mod); +} + +#else /* !CONFIG_SYSFS */ + +static int mod_sysfs_setup(struct module *mod, + const struct load_info *info, + struct kernel_param *kparam, + unsigned int num_params) +{ + return 0; +} + +static void mod_sysfs_fini(struct module *mod) +{ +} + +static void module_remove_modinfo_attrs(struct module *mod) +{ +} + +static void del_usage_links(struct module *mod) +{ +} + +#endif /* CONFIG_SYSFS */ + +static void mod_sysfs_teardown(struct module *mod) +{ + del_usage_links(mod); + module_remove_modinfo_attrs(mod); + module_param_sysfs_remove(mod); + kobject_put(mod->mkobj.drivers_dir); + kobject_put(mod->holders_dir); + mod_sysfs_fini(mod); +} + +#ifdef CONFIG_DEBUG_SET_MODULE_RONX +/* + * LKM RO/NX protection: protect module's text/ro-data + * from modification and any data from execution. + */ +void set_page_attributes(void *start, void *end, int (*set)(unsigned long start, int num_pages)) +{ + unsigned long begin_pfn = PFN_DOWN((unsigned long)start); + unsigned long end_pfn = PFN_DOWN((unsigned long)end); + + if (end_pfn > begin_pfn) + set(begin_pfn << PAGE_SHIFT, end_pfn - begin_pfn); +} + +static void set_section_ro_nx(void *base, + unsigned long text_size, + unsigned long ro_size, + unsigned long total_size) +{ + /* begin and end PFNs of the current subsection */ + unsigned long begin_pfn; + unsigned long end_pfn; + + /* + * Set RO for module text and RO-data: + * - Always protect first page. + * - Do not protect last partial page. + */ + if (ro_size > 0) + set_page_attributes(base, base + ro_size, set_memory_ro); + + /* + * Set NX permissions for module data: + * - Do not protect first partial page. + * - Always protect last page. + */ + if (total_size > text_size) { + begin_pfn = PFN_UP((unsigned long)base + text_size); + end_pfn = PFN_UP((unsigned long)base + total_size); + if (end_pfn > begin_pfn) + set_memory_nx(begin_pfn << PAGE_SHIFT, end_pfn - begin_pfn); + } +} + +static void unset_module_core_ro_nx(struct module *mod) +{ + set_page_attributes(mod->module_core + mod->core_text_size, + mod->module_core + mod->core_size, + set_memory_x); + set_page_attributes(mod->module_core, + mod->module_core + mod->core_ro_size, + set_memory_rw); +} + +static void unset_module_init_ro_nx(struct module *mod) +{ + set_page_attributes(mod->module_init + mod->init_text_size, + mod->module_init + mod->init_size, + set_memory_x); + set_page_attributes(mod->module_init, + mod->module_init + mod->init_ro_size, + set_memory_rw); +} + +/* Iterate through all modules and set each module's text as RW */ +void set_all_modules_text_rw(void) +{ + struct module *mod; + + mutex_lock(&module_mutex); + list_for_each_entry_rcu(mod, &modules, list) { + if (mod->state == MODULE_STATE_UNFORMED) + continue; + if ((mod->module_core) && (mod->core_text_size)) { + set_page_attributes(mod->module_core, + mod->module_core + mod->core_text_size, + set_memory_rw); + } + if ((mod->module_init) && (mod->init_text_size)) { + set_page_attributes(mod->module_init, + mod->module_init + mod->init_text_size, + set_memory_rw); + } + } + mutex_unlock(&module_mutex); +} + +/* Iterate through all modules and set each module's text as RO */ +void set_all_modules_text_ro(void) +{ + struct module *mod; + + mutex_lock(&module_mutex); + list_for_each_entry_rcu(mod, &modules, list) { + if (mod->state == MODULE_STATE_UNFORMED) + continue; + if ((mod->module_core) && (mod->core_text_size)) { + set_page_attributes(mod->module_core, + mod->module_core + mod->core_text_size, + set_memory_ro); + } + if ((mod->module_init) && (mod->init_text_size)) { + set_page_attributes(mod->module_init, + mod->module_init + mod->init_text_size, + set_memory_ro); + } + } + mutex_unlock(&module_mutex); +} +#else +static inline void set_section_ro_nx(void *base, unsigned long text_size, unsigned long ro_size, unsigned long total_size) { } +static void unset_module_core_ro_nx(struct module *mod) { } +static void unset_module_init_ro_nx(struct module *mod) { } +#endif + +void __weak module_memfree(void *module_region) +{ + vfree(module_region); +} + +void __weak module_arch_cleanup(struct module *mod) +{ +} + +void __weak module_arch_freeing_init(struct module *mod) +{ +} + +/* Free a module, remove from lists, etc. */ +static void free_module(struct module *mod) +{ + trace_module_free(mod); + + mod_sysfs_teardown(mod); + + /* We leave it in list to prevent duplicate loads, but make sure + * that noone uses it while it's being deconstructed. */ + mutex_lock(&module_mutex); + mod->state = MODULE_STATE_UNFORMED; + mutex_unlock(&module_mutex); + + /* Remove dynamic debug info */ + ddebug_remove_module(mod->name); + + /* Arch-specific cleanup. */ + module_arch_cleanup(mod); + + /* Module unload stuff */ + module_unload_free(mod); + + /* Free any allocated parameters. */ + destroy_params(mod->kp, mod->num_kp); + + /* Now we can delete it from the lists */ + mutex_lock(&module_mutex); + /* Unlink carefully: kallsyms could be walking list. */ + list_del_rcu(&mod->list); + /* Remove this module from bug list, this uses list_del_rcu */ + module_bug_cleanup(mod); + /* Wait for RCU synchronizing before releasing mod->list and buglist. */ + synchronize_rcu(); + mutex_unlock(&module_mutex); + + /* This may be NULL, but that's OK */ + unset_module_init_ro_nx(mod); + module_arch_freeing_init(mod); + module_memfree(mod->module_init); + kfree(mod->args); + percpu_modfree(mod); + + /* Free lock-classes; relies on the preceding sync_rcu(). */ + lockdep_free_key_range(mod->module_core, mod->core_size); + + /* Finally, free the core (containing the module structure) */ + unset_module_core_ro_nx(mod); + module_memfree(mod->module_core); + +#ifdef CONFIG_MPU + update_protections(current->mm); +#endif +} + +void *__symbol_get(const char *symbol) +{ + struct module *owner; + const struct kernel_symbol *sym; + + preempt_disable(); + sym = find_symbol(symbol, &owner, NULL, true, true); + if (sym && strong_try_module_get(owner)) + sym = NULL; + preempt_enable(); + + return sym ? (void *)sym->value : NULL; +} +EXPORT_SYMBOL_GPL(__symbol_get); + +/* + * Ensure that an exported symbol [global namespace] does not already exist + * in the kernel or in some other module's exported symbol table. + * + * You must hold the module_mutex. + */ +static int verify_export_symbols(struct module *mod) +{ + unsigned int i; + struct module *owner; + const struct kernel_symbol *s; + struct { + const struct kernel_symbol *sym; + unsigned int num; + } arr[] = { + { mod->syms, mod->num_syms }, + { mod->gpl_syms, mod->num_gpl_syms }, + { mod->gpl_future_syms, mod->num_gpl_future_syms }, +#ifdef CONFIG_UNUSED_SYMBOLS + { mod->unused_syms, mod->num_unused_syms }, + { mod->unused_gpl_syms, mod->num_unused_gpl_syms }, +#endif + }; + + for (i = 0; i < ARRAY_SIZE(arr); i++) { + for (s = arr[i].sym; s < arr[i].sym + arr[i].num; s++) { + if (find_symbol(s->name, &owner, NULL, true, false)) { + pr_err("%s: exports duplicate symbol %s" + " (owned by %s)\n", + mod->name, s->name, module_name(owner)); + return -ENOEXEC; + } + } + } + return 0; +} + +/* Change all symbols so that st_value encodes the pointer directly. */ +static int simplify_symbols(struct module *mod, const struct load_info *info) +{ + Elf_Shdr *symsec = &info->sechdrs[info->index.sym]; + Elf_Sym *sym = (void *)symsec->sh_addr; + unsigned long secbase; + unsigned int i; + int ret = 0; + const struct kernel_symbol *ksym; + + for (i = 1; i < symsec->sh_size / sizeof(Elf_Sym); i++) { + const char *name = info->strtab + sym[i].st_name; + + switch (sym[i].st_shndx) { + case SHN_COMMON: + /* Ignore common symbols */ + if (!strncmp(name, "__gnu_lto", 9)) + break; + + /* We compiled with -fno-common. These are not + supposed to happen. */ + pr_debug("Common symbol: %s\n", name); + pr_warn("%s: please compile with -fno-common\n", + mod->name); + ret = -ENOEXEC; + break; + + case SHN_ABS: + /* Don't need to do anything */ + pr_debug("Absolute symbol: 0x%08lx\n", + (long)sym[i].st_value); + break; + + case SHN_UNDEF: + ksym = resolve_symbol_wait(mod, info, name); + /* Ok if resolved. */ + if (ksym && !IS_ERR(ksym)) { + sym[i].st_value = ksym->value; + break; + } + + /* Ok if weak. */ + if (!ksym && ELF_ST_BIND(sym[i].st_info) == STB_WEAK) + break; + + pr_warn("%s: Unknown symbol %s (err %li)\n", + mod->name, name, PTR_ERR(ksym)); + ret = PTR_ERR(ksym) ?: -ENOENT; + break; + + default: + /* Divert to percpu allocation if a percpu var. */ + if (sym[i].st_shndx == info->index.pcpu) + secbase = (unsigned long)mod_percpu(mod); + else + secbase = info->sechdrs[sym[i].st_shndx].sh_addr; + sym[i].st_value += secbase; + break; + } + } + + return ret; +} + +static int apply_relocations(struct module *mod, const struct load_info *info) +{ + unsigned int i; + int err = 0; + + /* Now do relocations. */ + for (i = 1; i < info->hdr->e_shnum; i++) { + unsigned int infosec = info->sechdrs[i].sh_info; + + /* Not a valid relocation section? */ + if (infosec >= info->hdr->e_shnum) + continue; + + /* Don't bother with non-allocated sections */ + if (!(info->sechdrs[infosec].sh_flags & SHF_ALLOC)) + continue; + + if (info->sechdrs[i].sh_type == SHT_REL) + err = apply_relocate(info->sechdrs, info->strtab, + info->index.sym, i, mod); + else if (info->sechdrs[i].sh_type == SHT_RELA) + err = apply_relocate_add(info->sechdrs, info->strtab, + info->index.sym, i, mod); + if (err < 0) + break; + } + return err; +} + +/* Additional bytes needed by arch in front of individual sections */ +unsigned int __weak arch_mod_section_prepend(struct module *mod, + unsigned int section) +{ + /* default implementation just returns zero */ + return 0; +} + +/* Update size with this section: return offset. */ +static long get_offset(struct module *mod, unsigned int *size, + Elf_Shdr *sechdr, unsigned int section) +{ + long ret; + + *size += arch_mod_section_prepend(mod, section); + ret = ALIGN(*size, sechdr->sh_addralign ?: 1); + *size = ret + sechdr->sh_size; + return ret; +} + +/* Lay out the SHF_ALLOC sections in a way not dissimilar to how ld + might -- code, read-only data, read-write data, small data. Tally + sizes, and place the offsets into sh_entsize fields: high bit means it + belongs in init. */ +static void layout_sections(struct module *mod, struct load_info *info) +{ + static unsigned long const masks[][2] = { + /* NOTE: all executable code must be the first section + * in this array; otherwise modify the text_size + * finder in the two loops below */ + { SHF_EXECINSTR | SHF_ALLOC, ARCH_SHF_SMALL }, + { SHF_ALLOC, SHF_WRITE | ARCH_SHF_SMALL }, + { SHF_WRITE | SHF_ALLOC, ARCH_SHF_SMALL }, + { ARCH_SHF_SMALL | SHF_ALLOC, 0 } + }; + unsigned int m, i; + + for (i = 0; i < info->hdr->e_shnum; i++) + info->sechdrs[i].sh_entsize = ~0UL; + + pr_debug("Core section allocation order:\n"); + for (m = 0; m < ARRAY_SIZE(masks); ++m) { + for (i = 0; i < info->hdr->e_shnum; ++i) { + Elf_Shdr *s = &info->sechdrs[i]; + const char *sname = info->secstrings + s->sh_name; + + if ((s->sh_flags & masks[m][0]) != masks[m][0] + || (s->sh_flags & masks[m][1]) + || s->sh_entsize != ~0UL + || strstarts(sname, ".init")) + continue; + s->sh_entsize = get_offset(mod, &mod->core_size, s, i); + pr_debug("\t%s\n", sname); + } + switch (m) { + case 0: /* executable */ + mod->core_size = debug_align(mod->core_size); + mod->core_text_size = mod->core_size; + break; + case 1: /* RO: text and ro-data */ + mod->core_size = debug_align(mod->core_size); + mod->core_ro_size = mod->core_size; + break; + case 3: /* whole core */ + mod->core_size = debug_align(mod->core_size); + break; + } + } + + pr_debug("Init section allocation order:\n"); + for (m = 0; m < ARRAY_SIZE(masks); ++m) { + for (i = 0; i < info->hdr->e_shnum; ++i) { + Elf_Shdr *s = &info->sechdrs[i]; + const char *sname = info->secstrings + s->sh_name; + + if ((s->sh_flags & masks[m][0]) != masks[m][0] + || (s->sh_flags & masks[m][1]) + || s->sh_entsize != ~0UL + || !strstarts(sname, ".init")) + continue; + s->sh_entsize = (get_offset(mod, &mod->init_size, s, i) + | INIT_OFFSET_MASK); + pr_debug("\t%s\n", sname); + } + switch (m) { + case 0: /* executable */ + mod->init_size = debug_align(mod->init_size); + mod->init_text_size = mod->init_size; + break; + case 1: /* RO: text and ro-data */ + mod->init_size = debug_align(mod->init_size); + mod->init_ro_size = mod->init_size; + break; + case 3: /* whole init */ + mod->init_size = debug_align(mod->init_size); + break; + } + } +} + +static void set_license(struct module *mod, const char *license) +{ + if (!license) + license = "unspecified"; + + if (!license_is_gpl_compatible(license)) { + if (!test_taint(TAINT_PROPRIETARY_MODULE)) + pr_warn("%s: module license '%s' taints kernel.\n", + mod->name, license); + add_taint_module(mod, TAINT_PROPRIETARY_MODULE, + LOCKDEP_NOW_UNRELIABLE); + } +} + +/* Parse tag=value strings from .modinfo section */ +static char *next_string(char *string, unsigned long *secsize) +{ + /* Skip non-zero chars */ + while (string[0]) { + string++; + if ((*secsize)-- <= 1) + return NULL; + } + + /* Skip any zero padding. */ + while (!string[0]) { + string++; + if ((*secsize)-- <= 1) + return NULL; + } + return string; +} + +static char *get_modinfo(struct load_info *info, const char *tag) +{ + char *p; + unsigned int taglen = strlen(tag); + Elf_Shdr *infosec = &info->sechdrs[info->index.info]; + unsigned long size = infosec->sh_size; + + for (p = (char *)infosec->sh_addr; p; p = next_string(p, &size)) { + if (strncmp(p, tag, taglen) == 0 && p[taglen] == '=') + return p + taglen + 1; + } + return NULL; +} + +static void setup_modinfo(struct module *mod, struct load_info *info) +{ + struct module_attribute *attr; + int i; + + for (i = 0; (attr = modinfo_attrs[i]); i++) { + if (attr->setup) + attr->setup(mod, get_modinfo(info, attr->attr.name)); + } +} + +static void free_modinfo(struct module *mod) +{ + struct module_attribute *attr; + int i; + + for (i = 0; (attr = modinfo_attrs[i]); i++) { + if (attr->free) + attr->free(mod); + } +} + +#ifdef CONFIG_KALLSYMS + +/* lookup symbol in given range of kernel_symbols */ +static const struct kernel_symbol *lookup_symbol(const char *name, + const struct kernel_symbol *start, + const struct kernel_symbol *stop) +{ + return bsearch(name, start, stop - start, + sizeof(struct kernel_symbol), cmp_name); +} + +static int is_exported(const char *name, unsigned long value, + const struct module *mod) +{ + const struct kernel_symbol *ks; + if (!mod) + ks = lookup_symbol(name, __start___ksymtab, __stop___ksymtab); + else + ks = lookup_symbol(name, mod->syms, mod->syms + mod->num_syms); + return ks != NULL && ks->value == value; +} + +/* As per nm */ +static char elf_type(const Elf_Sym *sym, const struct load_info *info) +{ + const Elf_Shdr *sechdrs = info->sechdrs; + + if (ELF_ST_BIND(sym->st_info) == STB_WEAK) { + if (ELF_ST_TYPE(sym->st_info) == STT_OBJECT) + return 'v'; + else + return 'w'; + } + if (sym->st_shndx == SHN_UNDEF) + return 'U'; + if (sym->st_shndx == SHN_ABS) + return 'a'; + if (sym->st_shndx >= SHN_LORESERVE) + return '?'; + if (sechdrs[sym->st_shndx].sh_flags & SHF_EXECINSTR) + return 't'; + if (sechdrs[sym->st_shndx].sh_flags & SHF_ALLOC + && sechdrs[sym->st_shndx].sh_type != SHT_NOBITS) { + if (!(sechdrs[sym->st_shndx].sh_flags & SHF_WRITE)) + return 'r'; + else if (sechdrs[sym->st_shndx].sh_flags & ARCH_SHF_SMALL) + return 'g'; + else + return 'd'; + } + if (sechdrs[sym->st_shndx].sh_type == SHT_NOBITS) { + if (sechdrs[sym->st_shndx].sh_flags & ARCH_SHF_SMALL) + return 's'; + else + return 'b'; + } + if (strstarts(info->secstrings + sechdrs[sym->st_shndx].sh_name, + ".debug")) { + return 'n'; + } + return '?'; +} + +static bool is_core_symbol(const Elf_Sym *src, const Elf_Shdr *sechdrs, + unsigned int shnum) +{ + const Elf_Shdr *sec; + + if (src->st_shndx == SHN_UNDEF + || src->st_shndx >= shnum + || !src->st_name) + return false; + + sec = sechdrs + src->st_shndx; + if (!(sec->sh_flags & SHF_ALLOC) +#ifndef CONFIG_KALLSYMS_ALL + || !(sec->sh_flags & SHF_EXECINSTR) +#endif + || (sec->sh_entsize & INIT_OFFSET_MASK)) + return false; + + return true; +} + +/* + * We only allocate and copy the strings needed by the parts of symtab + * we keep. This is simple, but has the effect of making multiple + * copies of duplicates. We could be more sophisticated, see + * linux-kernel thread starting with + * <73defb5e4bca04a6431392cc341112b1@localhost>. + */ +static void layout_symtab(struct module *mod, struct load_info *info) +{ + Elf_Shdr *symsect = info->sechdrs + info->index.sym; + Elf_Shdr *strsect = info->sechdrs + info->index.str; + const Elf_Sym *src; + unsigned int i, nsrc, ndst, strtab_size = 0; + + /* Put symbol section at end of init part of module. */ + symsect->sh_flags |= SHF_ALLOC; + symsect->sh_entsize = get_offset(mod, &mod->init_size, symsect, + info->index.sym) | INIT_OFFSET_MASK; + pr_debug("\t%s\n", info->secstrings + symsect->sh_name); + + src = (void *)info->hdr + symsect->sh_offset; + nsrc = symsect->sh_size / sizeof(*src); + + /* Compute total space required for the core symbols' strtab. */ + for (ndst = i = 0; i < nsrc; i++) { + if (i == 0 || + is_core_symbol(src+i, info->sechdrs, info->hdr->e_shnum)) { + strtab_size += strlen(&info->strtab[src[i].st_name])+1; + ndst++; + } + } + + /* Append room for core symbols at end of core part. */ + info->symoffs = ALIGN(mod->core_size, symsect->sh_addralign ?: 1); + info->stroffs = mod->core_size = info->symoffs + ndst * sizeof(Elf_Sym); + mod->core_size += strtab_size; + mod->core_size = debug_align(mod->core_size); + + /* Put string table section at end of init part of module. */ + strsect->sh_flags |= SHF_ALLOC; + strsect->sh_entsize = get_offset(mod, &mod->init_size, strsect, + info->index.str) | INIT_OFFSET_MASK; + mod->init_size = debug_align(mod->init_size); + pr_debug("\t%s\n", info->secstrings + strsect->sh_name); +} + +static void add_kallsyms(struct module *mod, const struct load_info *info) +{ + unsigned int i, ndst; + const Elf_Sym *src; + Elf_Sym *dst; + char *s; + Elf_Shdr *symsec = &info->sechdrs[info->index.sym]; + + mod->symtab = (void *)symsec->sh_addr; + mod->num_symtab = symsec->sh_size / sizeof(Elf_Sym); + /* Make sure we get permanent strtab: don't use info->strtab. */ + mod->strtab = (void *)info->sechdrs[info->index.str].sh_addr; + + /* Set types up while we still have access to sections. */ + for (i = 0; i < mod->num_symtab; i++) + mod->symtab[i].st_info = elf_type(&mod->symtab[i], info); + + mod->core_symtab = dst = mod->module_core + info->symoffs; + mod->core_strtab = s = mod->module_core + info->stroffs; + src = mod->symtab; + for (ndst = i = 0; i < mod->num_symtab; i++) { + if (i == 0 || + is_core_symbol(src+i, info->sechdrs, info->hdr->e_shnum)) { + dst[ndst] = src[i]; + dst[ndst++].st_name = s - mod->core_strtab; + s += strlcpy(s, &mod->strtab[src[i].st_name], + KSYM_NAME_LEN) + 1; + } + } + mod->core_num_syms = ndst; +} +#else +static inline void layout_symtab(struct module *mod, struct load_info *info) +{ +} + +static void add_kallsyms(struct module *mod, const struct load_info *info) +{ +} +#endif /* CONFIG_KALLSYMS */ + +static void dynamic_debug_setup(struct _ddebug *debug, unsigned int num) +{ + if (!debug) + return; +#ifdef CONFIG_DYNAMIC_DEBUG + if (ddebug_add_module(debug, num, debug->modname)) + pr_err("dynamic debug error adding module: %s\n", + debug->modname); +#endif +} + +static void dynamic_debug_remove(struct _ddebug *debug) +{ + if (debug) + ddebug_remove_module(debug->modname); +} + +void * __weak module_alloc(unsigned long size) +{ + return vmalloc_exec(size); +} + +static void *module_alloc_update_bounds(unsigned long size) +{ + void *ret = module_alloc(size); + + if (ret) { + mutex_lock(&module_mutex); + /* Update module bounds. */ + if ((unsigned long)ret < module_addr_min) + module_addr_min = (unsigned long)ret; + if ((unsigned long)ret + size > module_addr_max) + module_addr_max = (unsigned long)ret + size; + mutex_unlock(&module_mutex); + } + return ret; +} + +#ifdef CONFIG_DEBUG_KMEMLEAK +static void kmemleak_load_module(const struct module *mod, + const struct load_info *info) +{ + unsigned int i; + + /* only scan the sections containing data */ + kmemleak_scan_area(mod, sizeof(struct module), GFP_KERNEL); + + for (i = 1; i < info->hdr->e_shnum; i++) { + /* Scan all writable sections that's not executable */ + if (!(info->sechdrs[i].sh_flags & SHF_ALLOC) || + !(info->sechdrs[i].sh_flags & SHF_WRITE) || + (info->sechdrs[i].sh_flags & SHF_EXECINSTR)) + continue; + + kmemleak_scan_area((void *)info->sechdrs[i].sh_addr, + info->sechdrs[i].sh_size, GFP_KERNEL); + } +} +#else +static inline void kmemleak_load_module(const struct module *mod, + const struct load_info *info) +{ +} +#endif + +#ifdef CONFIG_MODULE_SIG +static int module_sig_check(struct load_info *info) +{ + int err = -ENOKEY; + const unsigned long markerlen = sizeof(MODULE_SIG_STRING) - 1; + const void *mod = info->hdr; + + if (info->len > markerlen && + memcmp(mod + info->len - markerlen, MODULE_SIG_STRING, markerlen) == 0) { + /* We truncate the module to discard the signature */ + info->len -= markerlen; + err = mod_verify_sig(mod, &info->len); + } + + if (!err) { + info->sig_ok = true; + return 0; + } + + /* Not having a signature is only an error if we're strict. */ + if (err == -ENOKEY && !sig_enforce) + err = 0; + + return err; +} +#else /* !CONFIG_MODULE_SIG */ +static int module_sig_check(struct load_info *info) +{ + return 0; +} +#endif /* !CONFIG_MODULE_SIG */ + +/* Sanity checks against invalid binaries, wrong arch, weird elf version. */ +static int elf_header_check(struct load_info *info) +{ + if (info->len < sizeof(*(info->hdr))) + return -ENOEXEC; + + if (memcmp(info->hdr->e_ident, ELFMAG, SELFMAG) != 0 + || info->hdr->e_type != ET_REL + || !elf_check_arch(info->hdr) + || info->hdr->e_shentsize != sizeof(Elf_Shdr)) + return -ENOEXEC; + + if (info->hdr->e_shoff >= info->len + || (info->hdr->e_shnum * sizeof(Elf_Shdr) > + info->len - info->hdr->e_shoff)) + return -ENOEXEC; + + return 0; +} + +#define COPY_CHUNK_SIZE (16*PAGE_SIZE) + +static int copy_chunked_from_user(void *dst, const void __user *usrc, unsigned long len) +{ + do { + unsigned long n = min(len, COPY_CHUNK_SIZE); + + if (copy_from_user(dst, usrc, n) != 0) + return -EFAULT; + cond_resched(); + dst += n; + usrc += n; + len -= n; + } while (len); + return 0; +} + +/* Sets info->hdr and info->len. */ +static int copy_module_from_user(const void __user *umod, unsigned long len, + struct load_info *info) +{ + int err; + + info->len = len; + if (info->len < sizeof(*(info->hdr))) + return -ENOEXEC; + + err = security_kernel_module_from_file(NULL); + if (err) + return err; + + /* Suck in entire file: we'll want most of it. */ + info->hdr = __vmalloc(info->len, + GFP_KERNEL | __GFP_HIGHMEM | __GFP_NOWARN, PAGE_KERNEL); + if (!info->hdr) + return -ENOMEM; + + if (copy_chunked_from_user(info->hdr, umod, info->len) != 0) { + vfree(info->hdr); + return -EFAULT; + } + + return 0; +} + +/* Sets info->hdr and info->len. */ +static int copy_module_from_fd(int fd, struct load_info *info) +{ + struct fd f = fdget(fd); + int err; + struct kstat stat; + loff_t pos; + ssize_t bytes = 0; + + if (!f.file) + return -ENOEXEC; + + err = security_kernel_module_from_file(f.file); + if (err) + goto out; + + err = vfs_getattr(&f.file->f_path, &stat); + if (err) + goto out; + + if (stat.size > INT_MAX) { + err = -EFBIG; + goto out; + } + + /* Don't hand 0 to vmalloc, it whines. */ + if (stat.size == 0) { + err = -EINVAL; + goto out; + } + + info->hdr = vmalloc(stat.size); + if (!info->hdr) { + err = -ENOMEM; + goto out; + } + + pos = 0; + while (pos < stat.size) { + bytes = kernel_read(f.file, pos, (char *)(info->hdr) + pos, + stat.size - pos); + if (bytes < 0) { + vfree(info->hdr); + err = bytes; + goto out; + } + if (bytes == 0) + break; + pos += bytes; + } + info->len = pos; + +out: + fdput(f); + return err; +} + +static void free_copy(struct load_info *info) +{ + vfree(info->hdr); +} + +static int rewrite_section_headers(struct load_info *info, int flags) +{ + unsigned int i; + + /* This should always be true, but let's be sure. */ + info->sechdrs[0].sh_addr = 0; + + for (i = 1; i < info->hdr->e_shnum; i++) { + Elf_Shdr *shdr = &info->sechdrs[i]; + if (shdr->sh_type != SHT_NOBITS + && info->len < shdr->sh_offset + shdr->sh_size) { + pr_err("Module len %lu truncated\n", info->len); + return -ENOEXEC; + } + + /* Mark all sections sh_addr with their address in the + temporary image. */ + shdr->sh_addr = (size_t)info->hdr + shdr->sh_offset; + +#ifndef CONFIG_MODULE_UNLOAD + /* Don't load .exit sections */ + if (strstarts(info->secstrings+shdr->sh_name, ".exit")) + shdr->sh_flags &= ~(unsigned long)SHF_ALLOC; +#endif + } + + /* Track but don't keep modinfo and version sections. */ + if (flags & MODULE_INIT_IGNORE_MODVERSIONS) + info->index.vers = 0; /* Pretend no __versions section! */ + else + info->index.vers = find_sec(info, "__versions"); + info->index.info = find_sec(info, ".modinfo"); + info->sechdrs[info->index.info].sh_flags &= ~(unsigned long)SHF_ALLOC; + info->sechdrs[info->index.vers].sh_flags &= ~(unsigned long)SHF_ALLOC; + return 0; +} + +/* + * Set up our basic convenience variables (pointers to section headers, + * search for module section index etc), and do some basic section + * verification. + * + * Return the temporary module pointer (we'll replace it with the final + * one when we move the module sections around). + */ +static struct module *setup_load_info(struct load_info *info, int flags) +{ + unsigned int i; + int err; + struct module *mod; + + /* Set up the convenience variables */ + info->sechdrs = (void *)info->hdr + info->hdr->e_shoff; + info->secstrings = (void *)info->hdr + + info->sechdrs[info->hdr->e_shstrndx].sh_offset; + + err = rewrite_section_headers(info, flags); + if (err) + return ERR_PTR(err); + + /* Find internal symbols and strings. */ + for (i = 1; i < info->hdr->e_shnum; i++) { + if (info->sechdrs[i].sh_type == SHT_SYMTAB) { + info->index.sym = i; + info->index.str = info->sechdrs[i].sh_link; + info->strtab = (char *)info->hdr + + info->sechdrs[info->index.str].sh_offset; + break; + } + } + + info->index.mod = find_sec(info, ".gnu.linkonce.this_module"); + if (!info->index.mod) { + pr_warn("No module found in object\n"); + return ERR_PTR(-ENOEXEC); + } + /* This is temporary: point mod into copy of data. */ + mod = (void *)info->sechdrs[info->index.mod].sh_addr; + + if (info->index.sym == 0) { + pr_warn("%s: module has no symbols (stripped?)\n", mod->name); + return ERR_PTR(-ENOEXEC); + } + + info->index.pcpu = find_pcpusec(info); + + /* Check module struct version now, before we try to use module. */ + if (!check_modstruct_version(info->sechdrs, info->index.vers, mod)) + return ERR_PTR(-ENOEXEC); + + return mod; +} + +static int check_modinfo(struct module *mod, struct load_info *info, int flags) +{ + const char *modmagic = get_modinfo(info, "vermagic"); + int err; + + if (flags & MODULE_INIT_IGNORE_VERMAGIC) + modmagic = NULL; + + /* This is allowed: modprobe --force will invalidate it. */ + if (!modmagic) { + err = try_to_force_load(mod, "bad vermagic"); + if (err) + return err; + } else if (!same_magic(modmagic, vermagic, info->index.vers)) { + pr_err("%s: version magic '%s' should be '%s'\n", + mod->name, modmagic, vermagic); + return -ENOEXEC; + } + + if (!get_modinfo(info, "intree")) + add_taint_module(mod, TAINT_OOT_MODULE, LOCKDEP_STILL_OK); + + if (get_modinfo(info, "staging")) { + add_taint_module(mod, TAINT_CRAP, LOCKDEP_STILL_OK); + pr_warn("%s: module is from the staging directory, the quality " + "is unknown, you have been warned.\n", mod->name); + } + + /* Set up license info based on the info section */ + set_license(mod, get_modinfo(info, "license")); + + return 0; +} + +static int find_module_sections(struct module *mod, struct load_info *info) +{ + mod->kp = section_objs(info, "__param", + sizeof(*mod->kp), &mod->num_kp); + mod->syms = section_objs(info, "__ksymtab", + sizeof(*mod->syms), &mod->num_syms); + mod->crcs = section_addr(info, "__kcrctab"); + mod->gpl_syms = section_objs(info, "__ksymtab_gpl", + sizeof(*mod->gpl_syms), + &mod->num_gpl_syms); + mod->gpl_crcs = section_addr(info, "__kcrctab_gpl"); + mod->gpl_future_syms = section_objs(info, + "__ksymtab_gpl_future", + sizeof(*mod->gpl_future_syms), + &mod->num_gpl_future_syms); + mod->gpl_future_crcs = section_addr(info, "__kcrctab_gpl_future"); + +#ifdef CONFIG_UNUSED_SYMBOLS + mod->unused_syms = section_objs(info, "__ksymtab_unused", + sizeof(*mod->unused_syms), + &mod->num_unused_syms); + mod->unused_crcs = section_addr(info, "__kcrctab_unused"); + mod->unused_gpl_syms = section_objs(info, "__ksymtab_unused_gpl", + sizeof(*mod->unused_gpl_syms), + &mod->num_unused_gpl_syms); + mod->unused_gpl_crcs = section_addr(info, "__kcrctab_unused_gpl"); +#endif +#ifdef CONFIG_CONSTRUCTORS + mod->ctors = section_objs(info, ".ctors", + sizeof(*mod->ctors), &mod->num_ctors); + if (!mod->ctors) + mod->ctors = section_objs(info, ".init_array", + sizeof(*mod->ctors), &mod->num_ctors); + else if (find_sec(info, ".init_array")) { + /* + * This shouldn't happen with same compiler and binutils + * building all parts of the module. + */ + pr_warn("%s: has both .ctors and .init_array.\n", + mod->name); + return -EINVAL; + } +#endif + +#ifdef CONFIG_TRACEPOINTS + mod->tracepoints_ptrs = section_objs(info, "__tracepoints_ptrs", + sizeof(*mod->tracepoints_ptrs), + &mod->num_tracepoints); +#endif +#ifdef HAVE_JUMP_LABEL + mod->jump_entries = section_objs(info, "__jump_table", + sizeof(*mod->jump_entries), + &mod->num_jump_entries); +#endif +#ifdef CONFIG_EVENT_TRACING + mod->trace_events = section_objs(info, "_ftrace_events", + sizeof(*mod->trace_events), + &mod->num_trace_events); + mod->trace_enums = section_objs(info, "_ftrace_enum_map", + sizeof(*mod->trace_enums), + &mod->num_trace_enums); +#endif +#ifdef CONFIG_TRACING + mod->trace_bprintk_fmt_start = section_objs(info, "__trace_printk_fmt", + sizeof(*mod->trace_bprintk_fmt_start), + &mod->num_trace_bprintk_fmt); +#endif +#ifdef CONFIG_FTRACE_MCOUNT_RECORD + /* sechdrs[0].sh_size is always zero */ + mod->ftrace_callsites = section_objs(info, "__mcount_loc", + sizeof(*mod->ftrace_callsites), + &mod->num_ftrace_callsites); +#endif + + mod->extable = section_objs(info, "__ex_table", + sizeof(*mod->extable), &mod->num_exentries); + + if (section_addr(info, "__obsparm")) + pr_warn("%s: Ignoring obsolete parameters\n", mod->name); + + info->debug = section_objs(info, "__verbose", + sizeof(*info->debug), &info->num_debug); + + return 0; +} + +static int move_module(struct module *mod, struct load_info *info) +{ + int i; + void *ptr; + + /* Do the allocs. */ + ptr = module_alloc_update_bounds(mod->core_size); + /* + * The pointer to this block is stored in the module structure + * which is inside the block. Just mark it as not being a + * leak. + */ + kmemleak_not_leak(ptr); + if (!ptr) + return -ENOMEM; + + memset(ptr, 0, mod->core_size); + mod->module_core = ptr; + + if (mod->init_size) { + ptr = module_alloc_update_bounds(mod->init_size); + /* + * The pointer to this block is stored in the module structure + * which is inside the block. This block doesn't need to be + * scanned as it contains data and code that will be freed + * after the module is initialized. + */ + kmemleak_ignore(ptr); + if (!ptr) { + module_memfree(mod->module_core); + return -ENOMEM; + } + memset(ptr, 0, mod->init_size); + mod->module_init = ptr; + } else + mod->module_init = NULL; + + /* Transfer each section which specifies SHF_ALLOC */ + pr_debug("final section addresses:\n"); + for (i = 0; i < info->hdr->e_shnum; i++) { + void *dest; + Elf_Shdr *shdr = &info->sechdrs[i]; + + if (!(shdr->sh_flags & SHF_ALLOC)) + continue; + + if (shdr->sh_entsize & INIT_OFFSET_MASK) + dest = mod->module_init + + (shdr->sh_entsize & ~INIT_OFFSET_MASK); + else + dest = mod->module_core + shdr->sh_entsize; + + if (shdr->sh_type != SHT_NOBITS) + memcpy(dest, (void *)shdr->sh_addr, shdr->sh_size); + /* Update sh_addr to point to copy in image. */ + shdr->sh_addr = (unsigned long)dest; + pr_debug("\t0x%lx %s\n", + (long)shdr->sh_addr, info->secstrings + shdr->sh_name); + } + + return 0; +} + +static int check_module_license_and_versions(struct module *mod) +{ + /* + * ndiswrapper is under GPL by itself, but loads proprietary modules. + * Don't use add_taint_module(), as it would prevent ndiswrapper from + * using GPL-only symbols it needs. + */ + if (strcmp(mod->name, "ndiswrapper") == 0) + add_taint(TAINT_PROPRIETARY_MODULE, LOCKDEP_NOW_UNRELIABLE); + + /* driverloader was caught wrongly pretending to be under GPL */ + if (strcmp(mod->name, "driverloader") == 0) + add_taint_module(mod, TAINT_PROPRIETARY_MODULE, + LOCKDEP_NOW_UNRELIABLE); + + /* lve claims to be GPL but upstream won't provide source */ + if (strcmp(mod->name, "lve") == 0) + add_taint_module(mod, TAINT_PROPRIETARY_MODULE, + LOCKDEP_NOW_UNRELIABLE); + +#ifdef CONFIG_MODVERSIONS + if ((mod->num_syms && !mod->crcs) + || (mod->num_gpl_syms && !mod->gpl_crcs) + || (mod->num_gpl_future_syms && !mod->gpl_future_crcs) +#ifdef CONFIG_UNUSED_SYMBOLS + || (mod->num_unused_syms && !mod->unused_crcs) + || (mod->num_unused_gpl_syms && !mod->unused_gpl_crcs) +#endif + ) { + return try_to_force_load(mod, + "no versions for exported symbols"); + } +#endif + return 0; +} + +static void flush_module_icache(const struct module *mod) +{ + mm_segment_t old_fs; + + /* flush the icache in correct context */ + old_fs = get_fs(); + set_fs(KERNEL_DS); + + /* + * Flush the instruction cache, since we've played with text. + * Do it before processing of module parameters, so the module + * can provide parameter accessor functions of its own. + */ + if (mod->module_init) + flush_icache_range((unsigned long)mod->module_init, + (unsigned long)mod->module_init + + mod->init_size); + flush_icache_range((unsigned long)mod->module_core, + (unsigned long)mod->module_core + mod->core_size); + + set_fs(old_fs); +} + +int __weak module_frob_arch_sections(Elf_Ehdr *hdr, + Elf_Shdr *sechdrs, + char *secstrings, + struct module *mod) +{ + return 0; +} + +static struct module *layout_and_allocate(struct load_info *info, int flags) +{ + /* Module within temporary copy. */ + struct module *mod; + int err; + + mod = setup_load_info(info, flags); + if (IS_ERR(mod)) + return mod; + + err = check_modinfo(mod, info, flags); + if (err) + return ERR_PTR(err); + + /* Allow arches to frob section contents and sizes. */ + err = module_frob_arch_sections(info->hdr, info->sechdrs, + info->secstrings, mod); + if (err < 0) + return ERR_PTR(err); + + /* We will do a special allocation for per-cpu sections later. */ + info->sechdrs[info->index.pcpu].sh_flags &= ~(unsigned long)SHF_ALLOC; + + /* Determine total sizes, and put offsets in sh_entsize. For now + this is done generically; there doesn't appear to be any + special cases for the architectures. */ + layout_sections(mod, info); + layout_symtab(mod, info); + + /* Allocate and move to the final place */ + err = move_module(mod, info); + if (err) + return ERR_PTR(err); + + /* Module has been copied to its final place now: return it. */ + mod = (void *)info->sechdrs[info->index.mod].sh_addr; + kmemleak_load_module(mod, info); + return mod; +} + +/* mod is no longer valid after this! */ +static void module_deallocate(struct module *mod, struct load_info *info) +{ + percpu_modfree(mod); + module_arch_freeing_init(mod); + module_memfree(mod->module_init); + module_memfree(mod->module_core); +} + +int __weak module_finalize(const Elf_Ehdr *hdr, + const Elf_Shdr *sechdrs, + struct module *me) +{ + return 0; +} + +static int post_relocation(struct module *mod, const struct load_info *info) +{ + /* Sort exception table now relocations are done. */ + sort_extable(mod->extable, mod->extable + mod->num_exentries); + + /* Copy relocated percpu area over. */ + percpu_modcopy(mod, (void *)info->sechdrs[info->index.pcpu].sh_addr, + info->sechdrs[info->index.pcpu].sh_size); + + /* Setup kallsyms-specific fields. */ + add_kallsyms(mod, info); + + /* Arch-specific module finalizing. */ + return module_finalize(info->hdr, info->sechdrs, mod); +} + +/* Is this module of this name done loading? No locks held. */ +static bool finished_loading(const char *name) +{ + struct module *mod; + bool ret; + + /* + * The module_mutex should not be a heavily contended lock; + * if we get the occasional sleep here, we'll go an extra iteration + * in the wait_event_interruptible(), which is harmless. + */ + sched_annotate_sleep(); + mutex_lock(&module_mutex); + mod = find_module_all(name, strlen(name), true); + ret = !mod || mod->state == MODULE_STATE_LIVE + || mod->state == MODULE_STATE_GOING; + mutex_unlock(&module_mutex); + + return ret; +} + +/* Call module constructors. */ +static void do_mod_ctors(struct module *mod) +{ +#ifdef CONFIG_CONSTRUCTORS + unsigned long i; + + for (i = 0; i < mod->num_ctors; i++) + mod->ctors[i](); +#endif +} + +/* For freeing module_init on success, in case kallsyms traversing */ +struct mod_initfree { + struct rcu_head rcu; + void *module_init; +}; + +static void do_free_init(struct rcu_head *head) +{ + struct mod_initfree *m = container_of(head, struct mod_initfree, rcu); + module_memfree(m->module_init); + kfree(m); +} + +/* + * This is where the real work happens. + * + * Keep it uninlined to provide a reliable breakpoint target, e.g. for the gdb + * helper command 'lx-symbols'. + */ +static noinline int do_init_module(struct module *mod) +{ + int ret = 0; + struct mod_initfree *freeinit; + + freeinit = kmalloc(sizeof(*freeinit), GFP_KERNEL); + if (!freeinit) { + ret = -ENOMEM; + goto fail; + } + freeinit->module_init = mod->module_init; + + /* + * We want to find out whether @mod uses async during init. Clear + * PF_USED_ASYNC. async_schedule*() will set it. + */ + current->flags &= ~PF_USED_ASYNC; + + do_mod_ctors(mod); + /* Start the module */ + if (mod->init != NULL) + ret = do_one_initcall(mod->init); + if (ret < 0) { + goto fail_free_freeinit; + } + if (ret > 0) { + pr_warn("%s: '%s'->init suspiciously returned %d, it should " + "follow 0/-E convention\n" + "%s: loading module anyway...\n", + __func__, mod->name, ret, __func__); + dump_stack(); + } + + /* Now it's a first class citizen! */ + mod->state = MODULE_STATE_LIVE; + blocking_notifier_call_chain(&module_notify_list, + MODULE_STATE_LIVE, mod); + + /* + * We need to finish all async code before the module init sequence + * is done. This has potential to deadlock. For example, a newly + * detected block device can trigger request_module() of the + * default iosched from async probing task. Once userland helper + * reaches here, async_synchronize_full() will wait on the async + * task waiting on request_module() and deadlock. + * + * This deadlock is avoided by perfomring async_synchronize_full() + * iff module init queued any async jobs. This isn't a full + * solution as it will deadlock the same if module loading from + * async jobs nests more than once; however, due to the various + * constraints, this hack seems to be the best option for now. + * Please refer to the following thread for details. + * + * http://thread.gmane.org/gmane.linux.kernel/1420814 + */ + if (current->flags & PF_USED_ASYNC) + async_synchronize_full(); + + mutex_lock(&module_mutex); + /* Drop initial reference. */ + module_put(mod); + trim_init_extable(mod); +#ifdef CONFIG_KALLSYMS + mod->num_symtab = mod->core_num_syms; + mod->symtab = mod->core_symtab; + mod->strtab = mod->core_strtab; +#endif + unset_module_init_ro_nx(mod); + module_arch_freeing_init(mod); + mod->module_init = NULL; + mod->init_size = 0; + mod->init_ro_size = 0; + mod->init_text_size = 0; + /* + * We want to free module_init, but be aware that kallsyms may be + * walking this with preempt disabled. In all the failure paths, + * we call synchronize_rcu/synchronize_sched, but we don't want + * to slow down the success path, so use actual RCU here. + */ + call_rcu(&freeinit->rcu, do_free_init); + mutex_unlock(&module_mutex); + wake_up_all(&module_wq); + + return 0; + +fail_free_freeinit: + kfree(freeinit); +fail: + /* Try to protect us from buggy refcounters. */ + mod->state = MODULE_STATE_GOING; + synchronize_sched(); + module_put(mod); + blocking_notifier_call_chain(&module_notify_list, + MODULE_STATE_GOING, mod); + free_module(mod); + wake_up_all(&module_wq); + return ret; +} + +static int may_init_module(void) +{ + if (!capable(CAP_SYS_MODULE) || modules_disabled) + return -EPERM; + + return 0; +} + +/* + * We try to place it in the list now to make sure it's unique before + * we dedicate too many resources. In particular, temporary percpu + * memory exhaustion. + */ +static int add_unformed_module(struct module *mod) +{ + int err; + struct module *old; + + mod->state = MODULE_STATE_UNFORMED; + +again: + mutex_lock(&module_mutex); + old = find_module_all(mod->name, strlen(mod->name), true); + if (old != NULL) { + if (old->state == MODULE_STATE_COMING + || old->state == MODULE_STATE_UNFORMED) { + /* Wait in case it fails to load. */ + mutex_unlock(&module_mutex); + err = wait_event_interruptible(module_wq, + finished_loading(mod->name)); + if (err) + goto out_unlocked; + goto again; + } + err = -EEXIST; + goto out; + } + list_add_rcu(&mod->list, &modules); + err = 0; + +out: + mutex_unlock(&module_mutex); +out_unlocked: + return err; +} + +static int complete_formation(struct module *mod, struct load_info *info) +{ + int err; + + mutex_lock(&module_mutex); + + /* Find duplicate symbols (must be called under lock). */ + err = verify_export_symbols(mod); + if (err < 0) + goto out; + + /* This relies on module_mutex for list integrity. */ + module_bug_finalize(info->hdr, info->sechdrs, mod); + + /* Set RO and NX regions for core */ + set_section_ro_nx(mod->module_core, + mod->core_text_size, + mod->core_ro_size, + mod->core_size); + + /* Set RO and NX regions for init */ + set_section_ro_nx(mod->module_init, + mod->init_text_size, + mod->init_ro_size, + mod->init_size); + + /* Mark state as coming so strong_try_module_get() ignores us, + * but kallsyms etc. can see us. */ + mod->state = MODULE_STATE_COMING; + mutex_unlock(&module_mutex); + + blocking_notifier_call_chain(&module_notify_list, + MODULE_STATE_COMING, mod); + return 0; + +out: + mutex_unlock(&module_mutex); + return err; +} + +static int unknown_module_param_cb(char *param, char *val, const char *modname) +{ + /* Check for magic 'dyndbg' arg */ + int ret = ddebug_dyndbg_module_param_cb(param, val, modname); + if (ret != 0) + pr_warn("%s: unknown parameter '%s' ignored\n", modname, param); + return 0; +} + +/* Allocate and load the module: note that size of section 0 is always + zero, and we rely on this for optional sections. */ +static int load_module(struct load_info *info, const char __user *uargs, + int flags) +{ + struct module *mod; + long err; + char *after_dashes; + + err = module_sig_check(info); + if (err) + goto free_copy; + + err = elf_header_check(info); + if (err) + goto free_copy; + + /* Figure out module layout, and allocate all the memory. */ + mod = layout_and_allocate(info, flags); + if (IS_ERR(mod)) { + err = PTR_ERR(mod); + goto free_copy; + } + + /* Reserve our place in the list. */ + err = add_unformed_module(mod); + if (err) + goto free_module; + +#ifdef CONFIG_MODULE_SIG + mod->sig_ok = info->sig_ok; + if (!mod->sig_ok) { + pr_notice_once("%s: module verification failed: signature " + "and/or required key missing - tainting " + "kernel\n", mod->name); + add_taint_module(mod, TAINT_UNSIGNED_MODULE, LOCKDEP_STILL_OK); + } +#endif + + /* To avoid stressing percpu allocator, do this once we're unique. */ + err = percpu_modalloc(mod, info); + if (err) + goto unlink_mod; + + /* Now module is in final location, initialize linked lists, etc. */ + err = module_unload_init(mod); + if (err) + goto unlink_mod; + + /* Now we've got everything in the final locations, we can + * find optional sections. */ + err = find_module_sections(mod, info); + if (err) + goto free_unload; + + err = check_module_license_and_versions(mod); + if (err) + goto free_unload; + + /* Set up MODINFO_ATTR fields */ + setup_modinfo(mod, info); + + /* Fix up syms, so that st_value is a pointer to location. */ + err = simplify_symbols(mod, info); + if (err < 0) + goto free_modinfo; + + err = apply_relocations(mod, info); + if (err < 0) + goto free_modinfo; + + err = post_relocation(mod, info); + if (err < 0) + goto free_modinfo; + + flush_module_icache(mod); + + /* Now copy in args */ + mod->args = strndup_user(uargs, ~0UL >> 1); + if (IS_ERR(mod->args)) { + err = PTR_ERR(mod->args); + goto free_arch_cleanup; + } + + dynamic_debug_setup(info->debug, info->num_debug); + + /* Ftrace init must be called in the MODULE_STATE_UNFORMED state */ + ftrace_module_init(mod); + + /* Finally it's fully formed, ready to start executing. */ + err = complete_formation(mod, info); + if (err) + goto ddebug_cleanup; + + /* Module is ready to execute: parsing args may do that. */ + after_dashes = parse_args(mod->name, mod->args, mod->kp, mod->num_kp, + -32768, 32767, unknown_module_param_cb); + if (IS_ERR(after_dashes)) { + err = PTR_ERR(after_dashes); + goto bug_cleanup; + } else if (after_dashes) { + pr_warn("%s: parameters '%s' after `--' ignored\n", + mod->name, after_dashes); + } + + /* Link in to syfs. */ + err = mod_sysfs_setup(mod, info, mod->kp, mod->num_kp); + if (err < 0) + goto bug_cleanup; + + /* Get rid of temporary copy. */ + free_copy(info); + + /* Done! */ + trace_module_load(mod); + + return do_init_module(mod); + + bug_cleanup: + /* module_bug_cleanup needs module_mutex protection */ + mutex_lock(&module_mutex); + module_bug_cleanup(mod); + mutex_unlock(&module_mutex); + + blocking_notifier_call_chain(&module_notify_list, + MODULE_STATE_GOING, mod); + + /* we can't deallocate the module until we clear memory protection */ + unset_module_init_ro_nx(mod); + unset_module_core_ro_nx(mod); + + ddebug_cleanup: + dynamic_debug_remove(info->debug); + synchronize_sched(); + kfree(mod->args); + free_arch_cleanup: + module_arch_cleanup(mod); + free_modinfo: + free_modinfo(mod); + free_unload: + module_unload_free(mod); + unlink_mod: + mutex_lock(&module_mutex); + /* Unlink carefully: kallsyms could be walking list. */ + list_del_rcu(&mod->list); + wake_up_all(&module_wq); + /* Wait for RCU synchronizing before releasing mod->list. */ + synchronize_rcu(); + mutex_unlock(&module_mutex); + free_module: + /* Free lock-classes; relies on the preceding sync_rcu() */ + lockdep_free_key_range(mod->module_core, mod->core_size); + + module_deallocate(mod, info); + free_copy: + free_copy(info); + return err; +} + +SYSCALL_DEFINE3(init_module, void __user *, umod, + unsigned long, len, const char __user *, uargs) +{ + int err; + struct load_info info = { }; + + err = may_init_module(); + if (err) + return err; + + pr_debug("init_module: umod=%p, len=%lu, uargs=%p\n", + umod, len, uargs); + + err = copy_module_from_user(umod, len, &info); + if (err) + return err; + + return load_module(&info, uargs, 0); +} + +SYSCALL_DEFINE3(finit_module, int, fd, const char __user *, uargs, int, flags) +{ + int err; + struct load_info info = { }; + + err = may_init_module(); + if (err) + return err; + + pr_debug("finit_module: fd=%d, uargs=%p, flags=%i\n", fd, uargs, flags); + + if (flags & ~(MODULE_INIT_IGNORE_MODVERSIONS + |MODULE_INIT_IGNORE_VERMAGIC)) + return -EINVAL; + + err = copy_module_from_fd(fd, &info); + if (err) + return err; + + return load_module(&info, uargs, flags); +} + +static inline int within(unsigned long addr, void *start, unsigned long size) +{ + return ((void *)addr >= start && (void *)addr < start + size); +} + +#ifdef CONFIG_KALLSYMS +/* + * This ignores the intensely annoying "mapping symbols" found + * in ARM ELF files: $a, $t and $d. + */ +static inline int is_arm_mapping_symbol(const char *str) +{ + if (str[0] == '.' && str[1] == 'L') + return true; + return str[0] == '$' && strchr("axtd", str[1]) + && (str[2] == '\0' || str[2] == '.'); +} + +static const char *get_ksymbol(struct module *mod, + unsigned long addr, + unsigned long *size, + unsigned long *offset) +{ + unsigned int i, best = 0; + unsigned long nextval; + + /* At worse, next value is at end of module */ + if (within_module_init(addr, mod)) + nextval = (unsigned long)mod->module_init+mod->init_text_size; + else + nextval = (unsigned long)mod->module_core+mod->core_text_size; + + /* Scan for closest preceding symbol, and next symbol. (ELF + starts real symbols at 1). */ + for (i = 1; i < mod->num_symtab; i++) { + if (mod->symtab[i].st_shndx == SHN_UNDEF) + continue; + + /* We ignore unnamed symbols: they're uninformative + * and inserted at a whim. */ + if (mod->symtab[i].st_value <= addr + && mod->symtab[i].st_value > mod->symtab[best].st_value + && *(mod->strtab + mod->symtab[i].st_name) != '\0' + && !is_arm_mapping_symbol(mod->strtab + mod->symtab[i].st_name)) + best = i; + if (mod->symtab[i].st_value > addr + && mod->symtab[i].st_value < nextval + && *(mod->strtab + mod->symtab[i].st_name) != '\0' + && !is_arm_mapping_symbol(mod->strtab + mod->symtab[i].st_name)) + nextval = mod->symtab[i].st_value; + } + + if (!best) + return NULL; + + if (size) + *size = nextval - mod->symtab[best].st_value; + if (offset) + *offset = addr - mod->symtab[best].st_value; + return mod->strtab + mod->symtab[best].st_name; +} + +/* For kallsyms to ask for address resolution. NULL means not found. Careful + * not to lock to avoid deadlock on oopses, simply disable preemption. */ +const char *module_address_lookup(unsigned long addr, + unsigned long *size, + unsigned long *offset, + char **modname, + char *namebuf) +{ + struct module *mod; + const char *ret = NULL; + + preempt_disable(); + list_for_each_entry_rcu(mod, &modules, list) { + if (mod->state == MODULE_STATE_UNFORMED) + continue; + if (within_module(addr, mod)) { + if (modname) + *modname = mod->name; + ret = get_ksymbol(mod, addr, size, offset); + break; + } + } + /* Make a copy in here where it's safe */ + if (ret) { + strncpy(namebuf, ret, KSYM_NAME_LEN - 1); + ret = namebuf; + } + preempt_enable(); + return ret; +} + +int lookup_module_symbol_name(unsigned long addr, char *symname) +{ + struct module *mod; + + preempt_disable(); + list_for_each_entry_rcu(mod, &modules, list) { + if (mod->state == MODULE_STATE_UNFORMED) + continue; + if (within_module(addr, mod)) { + const char *sym; + + sym = get_ksymbol(mod, addr, NULL, NULL); + if (!sym) + goto out; + strlcpy(symname, sym, KSYM_NAME_LEN); + preempt_enable(); + return 0; + } + } +out: + preempt_enable(); + return -ERANGE; +} + +int lookup_module_symbol_attrs(unsigned long addr, unsigned long *size, + unsigned long *offset, char *modname, char *name) +{ + struct module *mod; + + preempt_disable(); + list_for_each_entry_rcu(mod, &modules, list) { + if (mod->state == MODULE_STATE_UNFORMED) + continue; + if (within_module(addr, mod)) { + const char *sym; + + sym = get_ksymbol(mod, addr, size, offset); + if (!sym) + goto out; + if (modname) + strlcpy(modname, mod->name, MODULE_NAME_LEN); + if (name) + strlcpy(name, sym, KSYM_NAME_LEN); + preempt_enable(); + return 0; + } + } +out: + preempt_enable(); + return -ERANGE; +} + +int module_get_kallsym(unsigned int symnum, unsigned long *value, char *type, + char *name, char *module_name, int *exported) +{ + struct module *mod; + + preempt_disable(); + list_for_each_entry_rcu(mod, &modules, list) { + if (mod->state == MODULE_STATE_UNFORMED) + continue; + if (symnum < mod->num_symtab) { + *value = mod->symtab[symnum].st_value; + *type = mod->symtab[symnum].st_info; + strlcpy(name, mod->strtab + mod->symtab[symnum].st_name, + KSYM_NAME_LEN); + strlcpy(module_name, mod->name, MODULE_NAME_LEN); + *exported = is_exported(name, *value, mod); + preempt_enable(); + return 0; + } + symnum -= mod->num_symtab; + } + preempt_enable(); + return -ERANGE; +} + +static unsigned long mod_find_symname(struct module *mod, const char *name) +{ + unsigned int i; + + for (i = 0; i < mod->num_symtab; i++) + if (strcmp(name, mod->strtab+mod->symtab[i].st_name) == 0 && + mod->symtab[i].st_info != 'U') + return mod->symtab[i].st_value; + return 0; +} + +/* Look for this name: can be of form module:name. */ +unsigned long module_kallsyms_lookup_name(const char *name) +{ + struct module *mod; + char *colon; + unsigned long ret = 0; + + /* Don't lock: we're in enough trouble already. */ + preempt_disable(); + if ((colon = strchr(name, ':')) != NULL) { + if ((mod = find_module_all(name, colon - name, false)) != NULL) + ret = mod_find_symname(mod, colon+1); + } else { + list_for_each_entry_rcu(mod, &modules, list) { + if (mod->state == MODULE_STATE_UNFORMED) + continue; + if ((ret = mod_find_symname(mod, name)) != 0) + break; + } + } + preempt_enable(); + return ret; +} + +int module_kallsyms_on_each_symbol(int (*fn)(void *, const char *, + struct module *, unsigned long), + void *data) +{ + struct module *mod; + unsigned int i; + int ret; + + list_for_each_entry(mod, &modules, list) { + if (mod->state == MODULE_STATE_UNFORMED) + continue; + for (i = 0; i < mod->num_symtab; i++) { + ret = fn(data, mod->strtab + mod->symtab[i].st_name, + mod, mod->symtab[i].st_value); + if (ret != 0) + return ret; + } + } + return 0; +} +#endif /* CONFIG_KALLSYMS */ + +static char *module_flags(struct module *mod, char *buf) +{ + int bx = 0; + + BUG_ON(mod->state == MODULE_STATE_UNFORMED); + if (mod->taints || + mod->state == MODULE_STATE_GOING || + mod->state == MODULE_STATE_COMING) { + buf[bx++] = '('; + bx += module_flags_taint(mod, buf + bx); + /* Show a - for module-is-being-unloaded */ + if (mod->state == MODULE_STATE_GOING) + buf[bx++] = '-'; + /* Show a + for module-is-being-loaded */ + if (mod->state == MODULE_STATE_COMING) + buf[bx++] = '+'; + buf[bx++] = ')'; + } + buf[bx] = '\0'; + + return buf; +} + +#ifdef CONFIG_PROC_FS +/* Called by the /proc file system to return a list of modules. */ +static void *m_start(struct seq_file *m, loff_t *pos) +{ + mutex_lock(&module_mutex); + return seq_list_start(&modules, *pos); +} + +static void *m_next(struct seq_file *m, void *p, loff_t *pos) +{ + return seq_list_next(p, &modules, pos); +} + +static void m_stop(struct seq_file *m, void *p) +{ + mutex_unlock(&module_mutex); +} + +static int m_show(struct seq_file *m, void *p) +{ + struct module *mod = list_entry(p, struct module, list); + char buf[8]; + + /* We always ignore unformed modules. */ + if (mod->state == MODULE_STATE_UNFORMED) + return 0; + + seq_printf(m, "%s %u", + mod->name, mod->init_size + mod->core_size); + print_unload_info(m, mod); + + /* Informative for users. */ + seq_printf(m, " %s", + mod->state == MODULE_STATE_GOING ? "Unloading" : + mod->state == MODULE_STATE_COMING ? "Loading" : + "Live"); + /* Used by oprofile and other similar tools. */ + seq_printf(m, " 0x%pK", mod->module_core); + + /* Taints info */ + if (mod->taints) + seq_printf(m, " %s", module_flags(mod, buf)); + + seq_puts(m, "\n"); + return 0; +} + +/* Format: modulename size refcount deps address + + Where refcount is a number or -, and deps is a comma-separated list + of depends or -. +*/ +static const struct seq_operations modules_op = { + .start = m_start, + .next = m_next, + .stop = m_stop, + .show = m_show +}; + +static int modules_open(struct inode *inode, struct file *file) +{ + return seq_open(file, &modules_op); +} + +static const struct file_operations proc_modules_operations = { + .open = modules_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, +}; + +static int __init proc_modules_init(void) +{ + proc_create("modules", 0, NULL, &proc_modules_operations); + return 0; +} +module_init(proc_modules_init); +#endif + +/* Given an address, look for it in the module exception tables. */ +const struct exception_table_entry *search_module_extables(unsigned long addr) +{ + const struct exception_table_entry *e = NULL; + struct module *mod; + + preempt_disable(); + list_for_each_entry_rcu(mod, &modules, list) { + if (mod->state == MODULE_STATE_UNFORMED) + continue; + if (mod->num_exentries == 0) + continue; + + e = search_extable(mod->extable, + mod->extable + mod->num_exentries - 1, + addr); + if (e) + break; + } + preempt_enable(); + + /* Now, if we found one, we are running inside it now, hence + we cannot unload the module, hence no refcnt needed. */ + return e; +} + +/* + * is_module_address - is this address inside a module? + * @addr: the address to check. + * + * See is_module_text_address() if you simply want to see if the address + * is code (not data). + */ +bool is_module_address(unsigned long addr) +{ + bool ret; + + preempt_disable(); + ret = __module_address(addr) != NULL; + preempt_enable(); + + return ret; +} + +/* + * __module_address - get the module which contains an address. + * @addr: the address. + * + * Must be called with preempt disabled or module mutex held so that + * module doesn't get freed during this. + */ +struct module *__module_address(unsigned long addr) +{ + struct module *mod; + + if (addr < module_addr_min || addr > module_addr_max) + return NULL; + + list_for_each_entry_rcu(mod, &modules, list) { + if (mod->state == MODULE_STATE_UNFORMED) + continue; + if (within_module(addr, mod)) + return mod; + } + return NULL; +} +EXPORT_SYMBOL_GPL(__module_address); + +/* + * is_module_text_address - is this address inside module code? + * @addr: the address to check. + * + * See is_module_address() if you simply want to see if the address is + * anywhere in a module. See kernel_text_address() for testing if an + * address corresponds to kernel or module code. + */ +bool is_module_text_address(unsigned long addr) +{ + bool ret; + + preempt_disable(); + ret = __module_text_address(addr) != NULL; + preempt_enable(); + + return ret; +} + +/* + * __module_text_address - get the module whose code contains an address. + * @addr: the address. + * + * Must be called with preempt disabled or module mutex held so that + * module doesn't get freed during this. + */ +struct module *__module_text_address(unsigned long addr) +{ + struct module *mod = __module_address(addr); + if (mod) { + /* Make sure it's within the text section. */ + if (!within(addr, mod->module_init, mod->init_text_size) + && !within(addr, mod->module_core, mod->core_text_size)) + mod = NULL; + } + return mod; +} +EXPORT_SYMBOL_GPL(__module_text_address); + +/* Don't grab lock, we're oopsing. */ +void print_modules(void) +{ + struct module *mod; + char buf[8]; + + printk(KERN_DEFAULT "Modules linked in:"); + /* Most callers should already have preempt disabled, but make sure */ + preempt_disable(); + list_for_each_entry_rcu(mod, &modules, list) { + if (mod->state == MODULE_STATE_UNFORMED) + continue; + pr_cont(" %s%s", mod->name, module_flags(mod, buf)); + } + preempt_enable(); + if (last_unloaded_module[0]) + pr_cont(" [last unloaded: %s]", last_unloaded_module); + pr_cont("\n"); +} + +#ifdef CONFIG_MODVERSIONS +/* Generate the signature for all relevant module structures here. + * If these change, we don't want to try to parse the module. */ +void module_layout(struct module *mod, + struct modversion_info *ver, + struct kernel_param *kp, + struct kernel_symbol *ks, + struct tracepoint * const *tp) +{ +} +EXPORT_SYMBOL(module_layout); +#endif diff --git a/kernel/kernel/module_signing.c b/kernel/kernel/module_signing.c new file mode 100644 index 000000000..be5b8fac4 --- /dev/null +++ b/kernel/kernel/module_signing.c @@ -0,0 +1,250 @@ +/* Module signature checker + * + * Copyright (C) 2012 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public Licence + * as published by the Free Software Foundation; either version + * 2 of the Licence, or (at your option) any later version. + */ + +#include +#include +#include +#include +#include +#include +#include "module-internal.h" + +/* + * Module signature information block. + * + * The constituents of the signature section are, in order: + * + * - Signer's name + * - Key identifier + * - Signature data + * - Information block + */ +struct module_signature { + u8 algo; /* Public-key crypto algorithm [enum pkey_algo] */ + u8 hash; /* Digest algorithm [enum hash_algo] */ + u8 id_type; /* Key identifier type [enum pkey_id_type] */ + u8 signer_len; /* Length of signer's name */ + u8 key_id_len; /* Length of key identifier */ + u8 __pad[3]; + __be32 sig_len; /* Length of signature data */ +}; + +/* + * Digest the module contents. + */ +static struct public_key_signature *mod_make_digest(enum hash_algo hash, + const void *mod, + unsigned long modlen) +{ + struct public_key_signature *pks; + struct crypto_shash *tfm; + struct shash_desc *desc; + size_t digest_size, desc_size; + int ret; + + pr_devel("==>%s()\n", __func__); + + /* Allocate the hashing algorithm we're going to need and find out how + * big the hash operational data will be. + */ + tfm = crypto_alloc_shash(hash_algo_name[hash], 0, 0); + if (IS_ERR(tfm)) + return (PTR_ERR(tfm) == -ENOENT) ? ERR_PTR(-ENOPKG) : ERR_CAST(tfm); + + desc_size = crypto_shash_descsize(tfm) + sizeof(*desc); + digest_size = crypto_shash_digestsize(tfm); + + /* We allocate the hash operational data storage on the end of our + * context data and the digest output buffer on the end of that. + */ + ret = -ENOMEM; + pks = kzalloc(digest_size + sizeof(*pks) + desc_size, GFP_KERNEL); + if (!pks) + goto error_no_pks; + + pks->pkey_hash_algo = hash; + pks->digest = (u8 *)pks + sizeof(*pks) + desc_size; + pks->digest_size = digest_size; + + desc = (void *)pks + sizeof(*pks); + desc->tfm = tfm; + desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP; + + ret = crypto_shash_init(desc); + if (ret < 0) + goto error; + + ret = crypto_shash_finup(desc, mod, modlen, pks->digest); + if (ret < 0) + goto error; + + crypto_free_shash(tfm); + pr_devel("<==%s() = ok\n", __func__); + return pks; + +error: + kfree(pks); +error_no_pks: + crypto_free_shash(tfm); + pr_devel("<==%s() = %d\n", __func__, ret); + return ERR_PTR(ret); +} + +/* + * Extract an MPI array from the signature data. This represents the actual + * signature. Each raw MPI is prefaced by a BE 2-byte value indicating the + * size of the MPI in bytes. + * + * RSA signatures only have one MPI, so currently we only read one. + */ +static int mod_extract_mpi_array(struct public_key_signature *pks, + const void *data, size_t len) +{ + size_t nbytes; + MPI mpi; + + if (len < 3) + return -EBADMSG; + nbytes = ((const u8 *)data)[0] << 8 | ((const u8 *)data)[1]; + data += 2; + len -= 2; + if (len != nbytes) + return -EBADMSG; + + mpi = mpi_read_raw_data(data, nbytes); + if (!mpi) + return -ENOMEM; + pks->mpi[0] = mpi; + pks->nr_mpi = 1; + return 0; +} + +/* + * Request an asymmetric key. + */ +static struct key *request_asymmetric_key(const char *signer, size_t signer_len, + const u8 *key_id, size_t key_id_len) +{ + key_ref_t key; + size_t i; + char *id, *q; + + pr_devel("==>%s(,%zu,,%zu)\n", __func__, signer_len, key_id_len); + + /* Construct an identifier. */ + id = kmalloc(signer_len + 2 + key_id_len * 2 + 1, GFP_KERNEL); + if (!id) + return ERR_PTR(-ENOKEY); + + memcpy(id, signer, signer_len); + + q = id + signer_len; + *q++ = ':'; + *q++ = ' '; + for (i = 0; i < key_id_len; i++) { + *q++ = hex_asc[*key_id >> 4]; + *q++ = hex_asc[*key_id++ & 0x0f]; + } + + *q = 0; + + pr_debug("Look up: \"%s\"\n", id); + + key = keyring_search(make_key_ref(system_trusted_keyring, 1), + &key_type_asymmetric, id); + if (IS_ERR(key)) + pr_warn("Request for unknown module key '%s' err %ld\n", + id, PTR_ERR(key)); + kfree(id); + + if (IS_ERR(key)) { + switch (PTR_ERR(key)) { + /* Hide some search errors */ + case -EACCES: + case -ENOTDIR: + case -EAGAIN: + return ERR_PTR(-ENOKEY); + default: + return ERR_CAST(key); + } + } + + pr_devel("<==%s() = 0 [%x]\n", __func__, key_serial(key_ref_to_ptr(key))); + return key_ref_to_ptr(key); +} + +/* + * Verify the signature on a module. + */ +int mod_verify_sig(const void *mod, unsigned long *_modlen) +{ + struct public_key_signature *pks; + struct module_signature ms; + struct key *key; + const void *sig; + size_t modlen = *_modlen, sig_len; + int ret; + + pr_devel("==>%s(,%zu)\n", __func__, modlen); + + if (modlen <= sizeof(ms)) + return -EBADMSG; + + memcpy(&ms, mod + (modlen - sizeof(ms)), sizeof(ms)); + modlen -= sizeof(ms); + + sig_len = be32_to_cpu(ms.sig_len); + if (sig_len >= modlen) + return -EBADMSG; + modlen -= sig_len; + if ((size_t)ms.signer_len + ms.key_id_len >= modlen) + return -EBADMSG; + modlen -= (size_t)ms.signer_len + ms.key_id_len; + + *_modlen = modlen; + sig = mod + modlen; + + /* For the moment, only support RSA and X.509 identifiers */ + if (ms.algo != PKEY_ALGO_RSA || + ms.id_type != PKEY_ID_X509) + return -ENOPKG; + + if (ms.hash >= PKEY_HASH__LAST || + !hash_algo_name[ms.hash]) + return -ENOPKG; + + key = request_asymmetric_key(sig, ms.signer_len, + sig + ms.signer_len, ms.key_id_len); + if (IS_ERR(key)) + return PTR_ERR(key); + + pks = mod_make_digest(ms.hash, mod, modlen); + if (IS_ERR(pks)) { + ret = PTR_ERR(pks); + goto error_put_key; + } + + ret = mod_extract_mpi_array(pks, sig + ms.signer_len + ms.key_id_len, + sig_len); + if (ret < 0) + goto error_free_pks; + + ret = verify_signature(key, pks); + pr_devel("verify_signature() = %d\n", ret); + +error_free_pks: + mpi_free(pks->rsa.s); + kfree(pks); +error_put_key: + key_put(key); + pr_devel("<==%s() = %d\n", __func__, ret); + return ret; +} diff --git a/kernel/kernel/notifier.c b/kernel/kernel/notifier.c new file mode 100644 index 000000000..ae9fc7cc3 --- /dev/null +++ b/kernel/kernel/notifier.c @@ -0,0 +1,562 @@ +#include +#include +#include +#include +#include +#include +#include + +/* + * Notifier list for kernel code which wants to be called + * at shutdown. This is used to stop any idling DMA operations + * and the like. + */ +BLOCKING_NOTIFIER_HEAD(reboot_notifier_list); + +/* + * Notifier chain core routines. The exported routines below + * are layered on top of these, with appropriate locking added. + */ + +static int notifier_chain_register(struct notifier_block **nl, + struct notifier_block *n) +{ + while ((*nl) != NULL) { + if (n->priority > (*nl)->priority) + break; + nl = &((*nl)->next); + } + n->next = *nl; + rcu_assign_pointer(*nl, n); + return 0; +} + +static int notifier_chain_cond_register(struct notifier_block **nl, + struct notifier_block *n) +{ + while ((*nl) != NULL) { + if ((*nl) == n) + return 0; + if (n->priority > (*nl)->priority) + break; + nl = &((*nl)->next); + } + n->next = *nl; + rcu_assign_pointer(*nl, n); + return 0; +} + +static int notifier_chain_unregister(struct notifier_block **nl, + struct notifier_block *n) +{ + while ((*nl) != NULL) { + if ((*nl) == n) { + rcu_assign_pointer(*nl, n->next); + return 0; + } + nl = &((*nl)->next); + } + return -ENOENT; +} + +/** + * notifier_call_chain - Informs the registered notifiers about an event. + * @nl: Pointer to head of the blocking notifier chain + * @val: Value passed unmodified to notifier function + * @v: Pointer passed unmodified to notifier function + * @nr_to_call: Number of notifier functions to be called. Don't care + * value of this parameter is -1. + * @nr_calls: Records the number of notifications sent. Don't care + * value of this field is NULL. + * @returns: notifier_call_chain returns the value returned by the + * last notifier function called. + */ +static int notifier_call_chain(struct notifier_block **nl, + unsigned long val, void *v, + int nr_to_call, int *nr_calls) +{ + int ret = NOTIFY_DONE; + struct notifier_block *nb, *next_nb; + + nb = rcu_dereference_raw(*nl); + + while (nb && nr_to_call) { + next_nb = rcu_dereference_raw(nb->next); + +#ifdef CONFIG_DEBUG_NOTIFIERS + if (unlikely(!func_ptr_is_kernel_text(nb->notifier_call))) { + WARN(1, "Invalid notifier called!"); + nb = next_nb; + continue; + } +#endif + ret = nb->notifier_call(nb, val, v); + + if (nr_calls) + (*nr_calls)++; + + if ((ret & NOTIFY_STOP_MASK) == NOTIFY_STOP_MASK) + break; + nb = next_nb; + nr_to_call--; + } + return ret; +} +NOKPROBE_SYMBOL(notifier_call_chain); + +/* + * Atomic notifier chain routines. Registration and unregistration + * use a spinlock, and call_chain is synchronized by RCU (no locks). + */ + +/** + * atomic_notifier_chain_register - Add notifier to an atomic notifier chain + * @nh: Pointer to head of the atomic notifier chain + * @n: New entry in notifier chain + * + * Adds a notifier to an atomic notifier chain. + * + * Currently always returns zero. + */ +int atomic_notifier_chain_register(struct atomic_notifier_head *nh, + struct notifier_block *n) +{ + unsigned long flags; + int ret; + + spin_lock_irqsave(&nh->lock, flags); + ret = notifier_chain_register(&nh->head, n); + spin_unlock_irqrestore(&nh->lock, flags); + return ret; +} +EXPORT_SYMBOL_GPL(atomic_notifier_chain_register); + +/** + * atomic_notifier_chain_unregister - Remove notifier from an atomic notifier chain + * @nh: Pointer to head of the atomic notifier chain + * @n: Entry to remove from notifier chain + * + * Removes a notifier from an atomic notifier chain. + * + * Returns zero on success or %-ENOENT on failure. + */ +int atomic_notifier_chain_unregister(struct atomic_notifier_head *nh, + struct notifier_block *n) +{ + unsigned long flags; + int ret; + + spin_lock_irqsave(&nh->lock, flags); + ret = notifier_chain_unregister(&nh->head, n); + spin_unlock_irqrestore(&nh->lock, flags); + synchronize_rcu(); + return ret; +} +EXPORT_SYMBOL_GPL(atomic_notifier_chain_unregister); + +/** + * __atomic_notifier_call_chain - Call functions in an atomic notifier chain + * @nh: Pointer to head of the atomic notifier chain + * @val: Value passed unmodified to notifier function + * @v: Pointer passed unmodified to notifier function + * @nr_to_call: See the comment for notifier_call_chain. + * @nr_calls: See the comment for notifier_call_chain. + * + * Calls each function in a notifier chain in turn. The functions + * run in an atomic context, so they must not block. + * This routine uses RCU to synchronize with changes to the chain. + * + * If the return value of the notifier can be and'ed + * with %NOTIFY_STOP_MASK then atomic_notifier_call_chain() + * will return immediately, with the return value of + * the notifier function which halted execution. + * Otherwise the return value is the return value + * of the last notifier function called. + */ +int __atomic_notifier_call_chain(struct atomic_notifier_head *nh, + unsigned long val, void *v, + int nr_to_call, int *nr_calls) +{ + int ret; + + rcu_read_lock(); + ret = notifier_call_chain(&nh->head, val, v, nr_to_call, nr_calls); + rcu_read_unlock(); + return ret; +} +EXPORT_SYMBOL_GPL(__atomic_notifier_call_chain); +NOKPROBE_SYMBOL(__atomic_notifier_call_chain); + +int atomic_notifier_call_chain(struct atomic_notifier_head *nh, + unsigned long val, void *v) +{ + return __atomic_notifier_call_chain(nh, val, v, -1, NULL); +} +EXPORT_SYMBOL_GPL(atomic_notifier_call_chain); +NOKPROBE_SYMBOL(atomic_notifier_call_chain); + +/* + * Blocking notifier chain routines. All access to the chain is + * synchronized by an rwsem. + */ + +/** + * blocking_notifier_chain_register - Add notifier to a blocking notifier chain + * @nh: Pointer to head of the blocking notifier chain + * @n: New entry in notifier chain + * + * Adds a notifier to a blocking notifier chain. + * Must be called in process context. + * + * Currently always returns zero. + */ +int blocking_notifier_chain_register(struct blocking_notifier_head *nh, + struct notifier_block *n) +{ + int ret; + + /* + * This code gets used during boot-up, when task switching is + * not yet working and interrupts must remain disabled. At + * such times we must not call down_write(). + */ + if (unlikely(system_state == SYSTEM_BOOTING)) + return notifier_chain_register(&nh->head, n); + + down_write(&nh->rwsem); + ret = notifier_chain_register(&nh->head, n); + up_write(&nh->rwsem); + return ret; +} +EXPORT_SYMBOL_GPL(blocking_notifier_chain_register); + +/** + * blocking_notifier_chain_cond_register - Cond add notifier to a blocking notifier chain + * @nh: Pointer to head of the blocking notifier chain + * @n: New entry in notifier chain + * + * Adds a notifier to a blocking notifier chain, only if not already + * present in the chain. + * Must be called in process context. + * + * Currently always returns zero. + */ +int blocking_notifier_chain_cond_register(struct blocking_notifier_head *nh, + struct notifier_block *n) +{ + int ret; + + down_write(&nh->rwsem); + ret = notifier_chain_cond_register(&nh->head, n); + up_write(&nh->rwsem); + return ret; +} +EXPORT_SYMBOL_GPL(blocking_notifier_chain_cond_register); + +/** + * blocking_notifier_chain_unregister - Remove notifier from a blocking notifier chain + * @nh: Pointer to head of the blocking notifier chain + * @n: Entry to remove from notifier chain + * + * Removes a notifier from a blocking notifier chain. + * Must be called from process context. + * + * Returns zero on success or %-ENOENT on failure. + */ +int blocking_notifier_chain_unregister(struct blocking_notifier_head *nh, + struct notifier_block *n) +{ + int ret; + + /* + * This code gets used during boot-up, when task switching is + * not yet working and interrupts must remain disabled. At + * such times we must not call down_write(). + */ + if (unlikely(system_state == SYSTEM_BOOTING)) + return notifier_chain_unregister(&nh->head, n); + + down_write(&nh->rwsem); + ret = notifier_chain_unregister(&nh->head, n); + up_write(&nh->rwsem); + return ret; +} +EXPORT_SYMBOL_GPL(blocking_notifier_chain_unregister); + +/** + * __blocking_notifier_call_chain - Call functions in a blocking notifier chain + * @nh: Pointer to head of the blocking notifier chain + * @val: Value passed unmodified to notifier function + * @v: Pointer passed unmodified to notifier function + * @nr_to_call: See comment for notifier_call_chain. + * @nr_calls: See comment for notifier_call_chain. + * + * Calls each function in a notifier chain in turn. The functions + * run in a process context, so they are allowed to block. + * + * If the return value of the notifier can be and'ed + * with %NOTIFY_STOP_MASK then blocking_notifier_call_chain() + * will return immediately, with the return value of + * the notifier function which halted execution. + * Otherwise the return value is the return value + * of the last notifier function called. + */ +int __blocking_notifier_call_chain(struct blocking_notifier_head *nh, + unsigned long val, void *v, + int nr_to_call, int *nr_calls) +{ + int ret = NOTIFY_DONE; + + /* + * We check the head outside the lock, but if this access is + * racy then it does not matter what the result of the test + * is, we re-check the list after having taken the lock anyway: + */ + if (rcu_access_pointer(nh->head)) { + down_read(&nh->rwsem); + ret = notifier_call_chain(&nh->head, val, v, nr_to_call, + nr_calls); + up_read(&nh->rwsem); + } + return ret; +} +EXPORT_SYMBOL_GPL(__blocking_notifier_call_chain); + +int blocking_notifier_call_chain(struct blocking_notifier_head *nh, + unsigned long val, void *v) +{ + return __blocking_notifier_call_chain(nh, val, v, -1, NULL); +} +EXPORT_SYMBOL_GPL(blocking_notifier_call_chain); + +/* + * Raw notifier chain routines. There is no protection; + * the caller must provide it. Use at your own risk! + */ + +/** + * raw_notifier_chain_register - Add notifier to a raw notifier chain + * @nh: Pointer to head of the raw notifier chain + * @n: New entry in notifier chain + * + * Adds a notifier to a raw notifier chain. + * All locking must be provided by the caller. + * + * Currently always returns zero. + */ +int raw_notifier_chain_register(struct raw_notifier_head *nh, + struct notifier_block *n) +{ + return notifier_chain_register(&nh->head, n); +} +EXPORT_SYMBOL_GPL(raw_notifier_chain_register); + +/** + * raw_notifier_chain_unregister - Remove notifier from a raw notifier chain + * @nh: Pointer to head of the raw notifier chain + * @n: Entry to remove from notifier chain + * + * Removes a notifier from a raw notifier chain. + * All locking must be provided by the caller. + * + * Returns zero on success or %-ENOENT on failure. + */ +int raw_notifier_chain_unregister(struct raw_notifier_head *nh, + struct notifier_block *n) +{ + return notifier_chain_unregister(&nh->head, n); +} +EXPORT_SYMBOL_GPL(raw_notifier_chain_unregister); + +/** + * __raw_notifier_call_chain - Call functions in a raw notifier chain + * @nh: Pointer to head of the raw notifier chain + * @val: Value passed unmodified to notifier function + * @v: Pointer passed unmodified to notifier function + * @nr_to_call: See comment for notifier_call_chain. + * @nr_calls: See comment for notifier_call_chain + * + * Calls each function in a notifier chain in turn. The functions + * run in an undefined context. + * All locking must be provided by the caller. + * + * If the return value of the notifier can be and'ed + * with %NOTIFY_STOP_MASK then raw_notifier_call_chain() + * will return immediately, with the return value of + * the notifier function which halted execution. + * Otherwise the return value is the return value + * of the last notifier function called. + */ +int __raw_notifier_call_chain(struct raw_notifier_head *nh, + unsigned long val, void *v, + int nr_to_call, int *nr_calls) +{ + return notifier_call_chain(&nh->head, val, v, nr_to_call, nr_calls); +} +EXPORT_SYMBOL_GPL(__raw_notifier_call_chain); + +int raw_notifier_call_chain(struct raw_notifier_head *nh, + unsigned long val, void *v) +{ + return __raw_notifier_call_chain(nh, val, v, -1, NULL); +} +EXPORT_SYMBOL_GPL(raw_notifier_call_chain); + +#ifdef CONFIG_SRCU +/* + * SRCU notifier chain routines. Registration and unregistration + * use a mutex, and call_chain is synchronized by SRCU (no locks). + */ + +/** + * srcu_notifier_chain_register - Add notifier to an SRCU notifier chain + * @nh: Pointer to head of the SRCU notifier chain + * @n: New entry in notifier chain + * + * Adds a notifier to an SRCU notifier chain. + * Must be called in process context. + * + * Currently always returns zero. + */ +int srcu_notifier_chain_register(struct srcu_notifier_head *nh, + struct notifier_block *n) +{ + int ret; + + /* + * This code gets used during boot-up, when task switching is + * not yet working and interrupts must remain disabled. At + * such times we must not call mutex_lock(). + */ + if (unlikely(system_state == SYSTEM_BOOTING)) + return notifier_chain_register(&nh->head, n); + + mutex_lock(&nh->mutex); + ret = notifier_chain_register(&nh->head, n); + mutex_unlock(&nh->mutex); + return ret; +} +EXPORT_SYMBOL_GPL(srcu_notifier_chain_register); + +/** + * srcu_notifier_chain_unregister - Remove notifier from an SRCU notifier chain + * @nh: Pointer to head of the SRCU notifier chain + * @n: Entry to remove from notifier chain + * + * Removes a notifier from an SRCU notifier chain. + * Must be called from process context. + * + * Returns zero on success or %-ENOENT on failure. + */ +int srcu_notifier_chain_unregister(struct srcu_notifier_head *nh, + struct notifier_block *n) +{ + int ret; + + /* + * This code gets used during boot-up, when task switching is + * not yet working and interrupts must remain disabled. At + * such times we must not call mutex_lock(). + */ + if (unlikely(system_state == SYSTEM_BOOTING)) + return notifier_chain_unregister(&nh->head, n); + + mutex_lock(&nh->mutex); + ret = notifier_chain_unregister(&nh->head, n); + mutex_unlock(&nh->mutex); + synchronize_srcu(&nh->srcu); + return ret; +} +EXPORT_SYMBOL_GPL(srcu_notifier_chain_unregister); + +/** + * __srcu_notifier_call_chain - Call functions in an SRCU notifier chain + * @nh: Pointer to head of the SRCU notifier chain + * @val: Value passed unmodified to notifier function + * @v: Pointer passed unmodified to notifier function + * @nr_to_call: See comment for notifier_call_chain. + * @nr_calls: See comment for notifier_call_chain + * + * Calls each function in a notifier chain in turn. The functions + * run in a process context, so they are allowed to block. + * + * If the return value of the notifier can be and'ed + * with %NOTIFY_STOP_MASK then srcu_notifier_call_chain() + * will return immediately, with the return value of + * the notifier function which halted execution. + * Otherwise the return value is the return value + * of the last notifier function called. + */ +int __srcu_notifier_call_chain(struct srcu_notifier_head *nh, + unsigned long val, void *v, + int nr_to_call, int *nr_calls) +{ + int ret; + int idx; + + idx = srcu_read_lock(&nh->srcu); + ret = notifier_call_chain(&nh->head, val, v, nr_to_call, nr_calls); + srcu_read_unlock(&nh->srcu, idx); + return ret; +} +EXPORT_SYMBOL_GPL(__srcu_notifier_call_chain); + +int srcu_notifier_call_chain(struct srcu_notifier_head *nh, + unsigned long val, void *v) +{ + return __srcu_notifier_call_chain(nh, val, v, -1, NULL); +} +EXPORT_SYMBOL_GPL(srcu_notifier_call_chain); + +/** + * srcu_init_notifier_head - Initialize an SRCU notifier head + * @nh: Pointer to head of the srcu notifier chain + * + * Unlike other sorts of notifier heads, SRCU notifier heads require + * dynamic initialization. Be sure to call this routine before + * calling any of the other SRCU notifier routines for this head. + * + * If an SRCU notifier head is deallocated, it must first be cleaned + * up by calling srcu_cleanup_notifier_head(). Otherwise the head's + * per-cpu data (used by the SRCU mechanism) will leak. + */ +void srcu_init_notifier_head(struct srcu_notifier_head *nh) +{ + mutex_init(&nh->mutex); + if (init_srcu_struct(&nh->srcu) < 0) + BUG(); + nh->head = NULL; +} +EXPORT_SYMBOL_GPL(srcu_init_notifier_head); + +#endif /* CONFIG_SRCU */ + +static ATOMIC_NOTIFIER_HEAD(die_chain); + +int notrace notify_die(enum die_val val, const char *str, + struct pt_regs *regs, long err, int trap, int sig) +{ + struct die_args args = { + .regs = regs, + .str = str, + .err = err, + .trapnr = trap, + .signr = sig, + + }; + return atomic_notifier_call_chain(&die_chain, val, &args); +} +NOKPROBE_SYMBOL(notify_die); + +int register_die_notifier(struct notifier_block *nb) +{ + vmalloc_sync_all(); + return atomic_notifier_chain_register(&die_chain, nb); +} +EXPORT_SYMBOL_GPL(register_die_notifier); + +int unregister_die_notifier(struct notifier_block *nb) +{ + return atomic_notifier_chain_unregister(&die_chain, nb); +} +EXPORT_SYMBOL_GPL(unregister_die_notifier); diff --git a/kernel/kernel/nsproxy.c b/kernel/kernel/nsproxy.c new file mode 100644 index 000000000..49746c81a --- /dev/null +++ b/kernel/kernel/nsproxy.c @@ -0,0 +1,259 @@ +/* + * Copyright (C) 2006 IBM Corporation + * + * Author: Serge Hallyn + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License as + * published by the Free Software Foundation, version 2 of the + * License. + * + * Jun 2006 - namespaces support + * OpenVZ, SWsoft Inc. + * Pavel Emelianov + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +static struct kmem_cache *nsproxy_cachep; + +struct nsproxy init_nsproxy = { + .count = ATOMIC_INIT(1), + .uts_ns = &init_uts_ns, +#if defined(CONFIG_POSIX_MQUEUE) || defined(CONFIG_SYSVIPC) + .ipc_ns = &init_ipc_ns, +#endif + .mnt_ns = NULL, + .pid_ns_for_children = &init_pid_ns, +#ifdef CONFIG_NET + .net_ns = &init_net, +#endif +}; + +static inline struct nsproxy *create_nsproxy(void) +{ + struct nsproxy *nsproxy; + + nsproxy = kmem_cache_alloc(nsproxy_cachep, GFP_KERNEL); + if (nsproxy) + atomic_set(&nsproxy->count, 1); + return nsproxy; +} + +/* + * Create new nsproxy and all of its the associated namespaces. + * Return the newly created nsproxy. Do not attach this to the task, + * leave it to the caller to do proper locking and attach it to task. + */ +static struct nsproxy *create_new_namespaces(unsigned long flags, + struct task_struct *tsk, struct user_namespace *user_ns, + struct fs_struct *new_fs) +{ + struct nsproxy *new_nsp; + int err; + + new_nsp = create_nsproxy(); + if (!new_nsp) + return ERR_PTR(-ENOMEM); + + new_nsp->mnt_ns = copy_mnt_ns(flags, tsk->nsproxy->mnt_ns, user_ns, new_fs); + if (IS_ERR(new_nsp->mnt_ns)) { + err = PTR_ERR(new_nsp->mnt_ns); + goto out_ns; + } + + new_nsp->uts_ns = copy_utsname(flags, user_ns, tsk->nsproxy->uts_ns); + if (IS_ERR(new_nsp->uts_ns)) { + err = PTR_ERR(new_nsp->uts_ns); + goto out_uts; + } + + new_nsp->ipc_ns = copy_ipcs(flags, user_ns, tsk->nsproxy->ipc_ns); + if (IS_ERR(new_nsp->ipc_ns)) { + err = PTR_ERR(new_nsp->ipc_ns); + goto out_ipc; + } + + new_nsp->pid_ns_for_children = + copy_pid_ns(flags, user_ns, tsk->nsproxy->pid_ns_for_children); + if (IS_ERR(new_nsp->pid_ns_for_children)) { + err = PTR_ERR(new_nsp->pid_ns_for_children); + goto out_pid; + } + + new_nsp->net_ns = copy_net_ns(flags, user_ns, tsk->nsproxy->net_ns); + if (IS_ERR(new_nsp->net_ns)) { + err = PTR_ERR(new_nsp->net_ns); + goto out_net; + } + + return new_nsp; + +out_net: + if (new_nsp->pid_ns_for_children) + put_pid_ns(new_nsp->pid_ns_for_children); +out_pid: + if (new_nsp->ipc_ns) + put_ipc_ns(new_nsp->ipc_ns); +out_ipc: + if (new_nsp->uts_ns) + put_uts_ns(new_nsp->uts_ns); +out_uts: + if (new_nsp->mnt_ns) + put_mnt_ns(new_nsp->mnt_ns); +out_ns: + kmem_cache_free(nsproxy_cachep, new_nsp); + return ERR_PTR(err); +} + +/* + * called from clone. This now handles copy for nsproxy and all + * namespaces therein. + */ +int copy_namespaces(unsigned long flags, struct task_struct *tsk) +{ + struct nsproxy *old_ns = tsk->nsproxy; + struct user_namespace *user_ns = task_cred_xxx(tsk, user_ns); + struct nsproxy *new_ns; + + if (likely(!(flags & (CLONE_NEWNS | CLONE_NEWUTS | CLONE_NEWIPC | + CLONE_NEWPID | CLONE_NEWNET)))) { + get_nsproxy(old_ns); + return 0; + } + + if (!ns_capable(user_ns, CAP_SYS_ADMIN)) + return -EPERM; + + /* + * CLONE_NEWIPC must detach from the undolist: after switching + * to a new ipc namespace, the semaphore arrays from the old + * namespace are unreachable. In clone parlance, CLONE_SYSVSEM + * means share undolist with parent, so we must forbid using + * it along with CLONE_NEWIPC. + */ + if ((flags & (CLONE_NEWIPC | CLONE_SYSVSEM)) == + (CLONE_NEWIPC | CLONE_SYSVSEM)) + return -EINVAL; + + new_ns = create_new_namespaces(flags, tsk, user_ns, tsk->fs); + if (IS_ERR(new_ns)) + return PTR_ERR(new_ns); + + tsk->nsproxy = new_ns; + return 0; +} + +void free_nsproxy(struct nsproxy *ns) +{ + if (ns->mnt_ns) + put_mnt_ns(ns->mnt_ns); + if (ns->uts_ns) + put_uts_ns(ns->uts_ns); + if (ns->ipc_ns) + put_ipc_ns(ns->ipc_ns); + if (ns->pid_ns_for_children) + put_pid_ns(ns->pid_ns_for_children); + put_net(ns->net_ns); + kmem_cache_free(nsproxy_cachep, ns); +} + +/* + * Called from unshare. Unshare all the namespaces part of nsproxy. + * On success, returns the new nsproxy. + */ +int unshare_nsproxy_namespaces(unsigned long unshare_flags, + struct nsproxy **new_nsp, struct cred *new_cred, struct fs_struct *new_fs) +{ + struct user_namespace *user_ns; + int err = 0; + + if (!(unshare_flags & (CLONE_NEWNS | CLONE_NEWUTS | CLONE_NEWIPC | + CLONE_NEWNET | CLONE_NEWPID))) + return 0; + + user_ns = new_cred ? new_cred->user_ns : current_user_ns(); + if (!ns_capable(user_ns, CAP_SYS_ADMIN)) + return -EPERM; + + *new_nsp = create_new_namespaces(unshare_flags, current, user_ns, + new_fs ? new_fs : current->fs); + if (IS_ERR(*new_nsp)) { + err = PTR_ERR(*new_nsp); + goto out; + } + +out: + return err; +} + +void switch_task_namespaces(struct task_struct *p, struct nsproxy *new) +{ + struct nsproxy *ns; + + might_sleep(); + + task_lock(p); + ns = p->nsproxy; + p->nsproxy = new; + task_unlock(p); + + if (ns && atomic_dec_and_test(&ns->count)) + free_nsproxy(ns); +} + +void exit_task_namespaces(struct task_struct *p) +{ + switch_task_namespaces(p, NULL); +} + +SYSCALL_DEFINE2(setns, int, fd, int, nstype) +{ + struct task_struct *tsk = current; + struct nsproxy *new_nsproxy; + struct file *file; + struct ns_common *ns; + int err; + + file = proc_ns_fget(fd); + if (IS_ERR(file)) + return PTR_ERR(file); + + err = -EINVAL; + ns = get_proc_ns(file_inode(file)); + if (nstype && (ns->ops->type != nstype)) + goto out; + + new_nsproxy = create_new_namespaces(0, tsk, current_user_ns(), tsk->fs); + if (IS_ERR(new_nsproxy)) { + err = PTR_ERR(new_nsproxy); + goto out; + } + + err = ns->ops->install(new_nsproxy, ns); + if (err) { + free_nsproxy(new_nsproxy); + goto out; + } + switch_task_namespaces(tsk, new_nsproxy); +out: + fput(file); + return err; +} + +int __init nsproxy_cache_init(void) +{ + nsproxy_cachep = KMEM_CACHE(nsproxy, SLAB_PANIC); + return 0; +} diff --git a/kernel/kernel/padata.c b/kernel/kernel/padata.c new file mode 100644 index 000000000..b38bea9c4 --- /dev/null +++ b/kernel/kernel/padata.c @@ -0,0 +1,1105 @@ +/* + * padata.c - generic interface to process data streams in parallel + * + * See Documentation/padata.txt for an api documentation. + * + * Copyright (C) 2008, 2009 secunet Security Networks AG + * Copyright (C) 2008, 2009 Steffen Klassert + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License along with + * this program; if not, write to the Free Software Foundation, Inc., + * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define MAX_OBJ_NUM 1000 + +static int padata_index_to_cpu(struct parallel_data *pd, int cpu_index) +{ + int cpu, target_cpu; + + target_cpu = cpumask_first(pd->cpumask.pcpu); + for (cpu = 0; cpu < cpu_index; cpu++) + target_cpu = cpumask_next(target_cpu, pd->cpumask.pcpu); + + return target_cpu; +} + +static int padata_cpu_hash(struct parallel_data *pd) +{ + unsigned int seq_nr; + int cpu_index; + + /* + * Hash the sequence numbers to the cpus by taking + * seq_nr mod. number of cpus in use. + */ + + seq_nr = atomic_inc_return(&pd->seq_nr); + cpu_index = seq_nr % cpumask_weight(pd->cpumask.pcpu); + + return padata_index_to_cpu(pd, cpu_index); +} + +static void padata_parallel_worker(struct work_struct *parallel_work) +{ + struct padata_parallel_queue *pqueue; + struct parallel_data *pd; + struct padata_instance *pinst; + LIST_HEAD(local_list); + + local_bh_disable(); + pqueue = container_of(parallel_work, + struct padata_parallel_queue, work); + pd = pqueue->pd; + pinst = pd->pinst; + + spin_lock(&pqueue->parallel.lock); + list_replace_init(&pqueue->parallel.list, &local_list); + spin_unlock(&pqueue->parallel.lock); + + while (!list_empty(&local_list)) { + struct padata_priv *padata; + + padata = list_entry(local_list.next, + struct padata_priv, list); + + list_del_init(&padata->list); + + padata->parallel(padata); + } + + local_bh_enable(); +} + +/** + * padata_do_parallel - padata parallelization function + * + * @pinst: padata instance + * @padata: object to be parallelized + * @cb_cpu: cpu the serialization callback function will run on, + * must be in the serial cpumask of padata(i.e. cpumask.cbcpu). + * + * The parallelization callback function will run with BHs off. + * Note: Every object which is parallelized by padata_do_parallel + * must be seen by padata_do_serial. + */ +int padata_do_parallel(struct padata_instance *pinst, + struct padata_priv *padata, int cb_cpu) +{ + int target_cpu, err; + struct padata_parallel_queue *queue; + struct parallel_data *pd; + + rcu_read_lock_bh(); + + pd = rcu_dereference_bh(pinst->pd); + + err = -EINVAL; + if (!(pinst->flags & PADATA_INIT) || pinst->flags & PADATA_INVALID) + goto out; + + if (!cpumask_test_cpu(cb_cpu, pd->cpumask.cbcpu)) + goto out; + + err = -EBUSY; + if ((pinst->flags & PADATA_RESET)) + goto out; + + if (atomic_read(&pd->refcnt) >= MAX_OBJ_NUM) + goto out; + + err = 0; + atomic_inc(&pd->refcnt); + padata->pd = pd; + padata->cb_cpu = cb_cpu; + + target_cpu = padata_cpu_hash(pd); + queue = per_cpu_ptr(pd->pqueue, target_cpu); + + spin_lock(&queue->parallel.lock); + list_add_tail(&padata->list, &queue->parallel.list); + spin_unlock(&queue->parallel.lock); + + queue_work_on(target_cpu, pinst->wq, &queue->work); + +out: + rcu_read_unlock_bh(); + + return err; +} +EXPORT_SYMBOL(padata_do_parallel); + +/* + * padata_get_next - Get the next object that needs serialization. + * + * Return values are: + * + * A pointer to the control struct of the next object that needs + * serialization, if present in one of the percpu reorder queues. + * + * NULL, if all percpu reorder queues are empty. + * + * -EINPROGRESS, if the next object that needs serialization will + * be parallel processed by another cpu and is not yet present in + * the cpu's reorder queue. + * + * -ENODATA, if this cpu has to do the parallel processing for + * the next object. + */ +static struct padata_priv *padata_get_next(struct parallel_data *pd) +{ + int cpu, num_cpus; + unsigned int next_nr, next_index; + struct padata_parallel_queue *next_queue; + struct padata_priv *padata; + struct padata_list *reorder; + + num_cpus = cpumask_weight(pd->cpumask.pcpu); + + /* + * Calculate the percpu reorder queue and the sequence + * number of the next object. + */ + next_nr = pd->processed; + next_index = next_nr % num_cpus; + cpu = padata_index_to_cpu(pd, next_index); + next_queue = per_cpu_ptr(pd->pqueue, cpu); + + padata = NULL; + + reorder = &next_queue->reorder; + + if (!list_empty(&reorder->list)) { + padata = list_entry(reorder->list.next, + struct padata_priv, list); + + spin_lock(&reorder->lock); + list_del_init(&padata->list); + atomic_dec(&pd->reorder_objects); + spin_unlock(&reorder->lock); + + pd->processed++; + + goto out; + } + + if (__this_cpu_read(pd->pqueue->cpu_index) == next_queue->cpu_index) { + padata = ERR_PTR(-ENODATA); + goto out; + } + + padata = ERR_PTR(-EINPROGRESS); +out: + return padata; +} + +static void padata_reorder(struct parallel_data *pd) +{ + int cb_cpu; + struct padata_priv *padata; + struct padata_serial_queue *squeue; + struct padata_instance *pinst = pd->pinst; + + /* + * We need to ensure that only one cpu can work on dequeueing of + * the reorder queue the time. Calculating in which percpu reorder + * queue the next object will arrive takes some time. A spinlock + * would be highly contended. Also it is not clear in which order + * the objects arrive to the reorder queues. So a cpu could wait to + * get the lock just to notice that there is nothing to do at the + * moment. Therefore we use a trylock and let the holder of the lock + * care for all the objects enqueued during the holdtime of the lock. + */ + if (!spin_trylock_bh(&pd->lock)) + return; + + while (1) { + padata = padata_get_next(pd); + + /* + * All reorder queues are empty, or the next object that needs + * serialization is parallel processed by another cpu and is + * still on it's way to the cpu's reorder queue, nothing to + * do for now. + */ + if (!padata || PTR_ERR(padata) == -EINPROGRESS) + break; + + /* + * This cpu has to do the parallel processing of the next + * object. It's waiting in the cpu's parallelization queue, + * so exit immediately. + */ + if (PTR_ERR(padata) == -ENODATA) { + del_timer(&pd->timer); + spin_unlock_bh(&pd->lock); + return; + } + + cb_cpu = padata->cb_cpu; + squeue = per_cpu_ptr(pd->squeue, cb_cpu); + + spin_lock(&squeue->serial.lock); + list_add_tail(&padata->list, &squeue->serial.list); + spin_unlock(&squeue->serial.lock); + + queue_work_on(cb_cpu, pinst->wq, &squeue->work); + } + + spin_unlock_bh(&pd->lock); + + /* + * The next object that needs serialization might have arrived to + * the reorder queues in the meantime, we will be called again + * from the timer function if no one else cares for it. + */ + if (atomic_read(&pd->reorder_objects) + && !(pinst->flags & PADATA_RESET)) + mod_timer(&pd->timer, jiffies + HZ); + else + del_timer(&pd->timer); + + return; +} + +static void padata_reorder_timer(unsigned long arg) +{ + struct parallel_data *pd = (struct parallel_data *)arg; + + padata_reorder(pd); +} + +static void padata_serial_worker(struct work_struct *serial_work) +{ + struct padata_serial_queue *squeue; + struct parallel_data *pd; + LIST_HEAD(local_list); + + local_bh_disable(); + squeue = container_of(serial_work, struct padata_serial_queue, work); + pd = squeue->pd; + + spin_lock(&squeue->serial.lock); + list_replace_init(&squeue->serial.list, &local_list); + spin_unlock(&squeue->serial.lock); + + while (!list_empty(&local_list)) { + struct padata_priv *padata; + + padata = list_entry(local_list.next, + struct padata_priv, list); + + list_del_init(&padata->list); + + padata->serial(padata); + atomic_dec(&pd->refcnt); + } + local_bh_enable(); +} + +/** + * padata_do_serial - padata serialization function + * + * @padata: object to be serialized. + * + * padata_do_serial must be called for every parallelized object. + * The serialization callback function will run with BHs off. + */ +void padata_do_serial(struct padata_priv *padata) +{ + int cpu; + struct padata_parallel_queue *pqueue; + struct parallel_data *pd; + + pd = padata->pd; + + cpu = get_cpu(); + pqueue = per_cpu_ptr(pd->pqueue, cpu); + + spin_lock(&pqueue->reorder.lock); + atomic_inc(&pd->reorder_objects); + list_add_tail(&padata->list, &pqueue->reorder.list); + spin_unlock(&pqueue->reorder.lock); + + put_cpu(); + + padata_reorder(pd); +} +EXPORT_SYMBOL(padata_do_serial); + +static int padata_setup_cpumasks(struct parallel_data *pd, + const struct cpumask *pcpumask, + const struct cpumask *cbcpumask) +{ + if (!alloc_cpumask_var(&pd->cpumask.pcpu, GFP_KERNEL)) + return -ENOMEM; + + cpumask_and(pd->cpumask.pcpu, pcpumask, cpu_online_mask); + if (!alloc_cpumask_var(&pd->cpumask.cbcpu, GFP_KERNEL)) { + free_cpumask_var(pd->cpumask.cbcpu); + return -ENOMEM; + } + + cpumask_and(pd->cpumask.cbcpu, cbcpumask, cpu_online_mask); + return 0; +} + +static void __padata_list_init(struct padata_list *pd_list) +{ + INIT_LIST_HEAD(&pd_list->list); + spin_lock_init(&pd_list->lock); +} + +/* Initialize all percpu queues used by serial workers */ +static void padata_init_squeues(struct parallel_data *pd) +{ + int cpu; + struct padata_serial_queue *squeue; + + for_each_cpu(cpu, pd->cpumask.cbcpu) { + squeue = per_cpu_ptr(pd->squeue, cpu); + squeue->pd = pd; + __padata_list_init(&squeue->serial); + INIT_WORK(&squeue->work, padata_serial_worker); + } +} + +/* Initialize all percpu queues used by parallel workers */ +static void padata_init_pqueues(struct parallel_data *pd) +{ + int cpu_index, cpu; + struct padata_parallel_queue *pqueue; + + cpu_index = 0; + for_each_cpu(cpu, pd->cpumask.pcpu) { + pqueue = per_cpu_ptr(pd->pqueue, cpu); + pqueue->pd = pd; + pqueue->cpu_index = cpu_index; + cpu_index++; + + __padata_list_init(&pqueue->reorder); + __padata_list_init(&pqueue->parallel); + INIT_WORK(&pqueue->work, padata_parallel_worker); + atomic_set(&pqueue->num_obj, 0); + } +} + +/* Allocate and initialize the internal cpumask dependend resources. */ +static struct parallel_data *padata_alloc_pd(struct padata_instance *pinst, + const struct cpumask *pcpumask, + const struct cpumask *cbcpumask) +{ + struct parallel_data *pd; + + pd = kzalloc(sizeof(struct parallel_data), GFP_KERNEL); + if (!pd) + goto err; + + pd->pqueue = alloc_percpu(struct padata_parallel_queue); + if (!pd->pqueue) + goto err_free_pd; + + pd->squeue = alloc_percpu(struct padata_serial_queue); + if (!pd->squeue) + goto err_free_pqueue; + if (padata_setup_cpumasks(pd, pcpumask, cbcpumask) < 0) + goto err_free_squeue; + + padata_init_pqueues(pd); + padata_init_squeues(pd); + setup_timer(&pd->timer, padata_reorder_timer, (unsigned long)pd); + atomic_set(&pd->seq_nr, -1); + atomic_set(&pd->reorder_objects, 0); + atomic_set(&pd->refcnt, 0); + pd->pinst = pinst; + spin_lock_init(&pd->lock); + + return pd; + +err_free_squeue: + free_percpu(pd->squeue); +err_free_pqueue: + free_percpu(pd->pqueue); +err_free_pd: + kfree(pd); +err: + return NULL; +} + +static void padata_free_pd(struct parallel_data *pd) +{ + free_cpumask_var(pd->cpumask.pcpu); + free_cpumask_var(pd->cpumask.cbcpu); + free_percpu(pd->pqueue); + free_percpu(pd->squeue); + kfree(pd); +} + +/* Flush all objects out of the padata queues. */ +static void padata_flush_queues(struct parallel_data *pd) +{ + int cpu; + struct padata_parallel_queue *pqueue; + struct padata_serial_queue *squeue; + + for_each_cpu(cpu, pd->cpumask.pcpu) { + pqueue = per_cpu_ptr(pd->pqueue, cpu); + flush_work(&pqueue->work); + } + + del_timer_sync(&pd->timer); + + if (atomic_read(&pd->reorder_objects)) + padata_reorder(pd); + + for_each_cpu(cpu, pd->cpumask.cbcpu) { + squeue = per_cpu_ptr(pd->squeue, cpu); + flush_work(&squeue->work); + } + + BUG_ON(atomic_read(&pd->refcnt) != 0); +} + +static void __padata_start(struct padata_instance *pinst) +{ + pinst->flags |= PADATA_INIT; +} + +static void __padata_stop(struct padata_instance *pinst) +{ + if (!(pinst->flags & PADATA_INIT)) + return; + + pinst->flags &= ~PADATA_INIT; + + synchronize_rcu(); + + get_online_cpus(); + padata_flush_queues(pinst->pd); + put_online_cpus(); +} + +/* Replace the internal control structure with a new one. */ +static void padata_replace(struct padata_instance *pinst, + struct parallel_data *pd_new) +{ + struct parallel_data *pd_old = pinst->pd; + int notification_mask = 0; + + pinst->flags |= PADATA_RESET; + + rcu_assign_pointer(pinst->pd, pd_new); + + synchronize_rcu(); + + if (!cpumask_equal(pd_old->cpumask.pcpu, pd_new->cpumask.pcpu)) + notification_mask |= PADATA_CPU_PARALLEL; + if (!cpumask_equal(pd_old->cpumask.cbcpu, pd_new->cpumask.cbcpu)) + notification_mask |= PADATA_CPU_SERIAL; + + padata_flush_queues(pd_old); + padata_free_pd(pd_old); + + if (notification_mask) + blocking_notifier_call_chain(&pinst->cpumask_change_notifier, + notification_mask, + &pd_new->cpumask); + + pinst->flags &= ~PADATA_RESET; +} + +/** + * padata_register_cpumask_notifier - Registers a notifier that will be called + * if either pcpu or cbcpu or both cpumasks change. + * + * @pinst: A poineter to padata instance + * @nblock: A pointer to notifier block. + */ +int padata_register_cpumask_notifier(struct padata_instance *pinst, + struct notifier_block *nblock) +{ + return blocking_notifier_chain_register(&pinst->cpumask_change_notifier, + nblock); +} +EXPORT_SYMBOL(padata_register_cpumask_notifier); + +/** + * padata_unregister_cpumask_notifier - Unregisters cpumask notifier + * registered earlier using padata_register_cpumask_notifier + * + * @pinst: A pointer to data instance. + * @nlock: A pointer to notifier block. + */ +int padata_unregister_cpumask_notifier(struct padata_instance *pinst, + struct notifier_block *nblock) +{ + return blocking_notifier_chain_unregister( + &pinst->cpumask_change_notifier, + nblock); +} +EXPORT_SYMBOL(padata_unregister_cpumask_notifier); + + +/* If cpumask contains no active cpu, we mark the instance as invalid. */ +static bool padata_validate_cpumask(struct padata_instance *pinst, + const struct cpumask *cpumask) +{ + if (!cpumask_intersects(cpumask, cpu_online_mask)) { + pinst->flags |= PADATA_INVALID; + return false; + } + + pinst->flags &= ~PADATA_INVALID; + return true; +} + +static int __padata_set_cpumasks(struct padata_instance *pinst, + cpumask_var_t pcpumask, + cpumask_var_t cbcpumask) +{ + int valid; + struct parallel_data *pd; + + valid = padata_validate_cpumask(pinst, pcpumask); + if (!valid) { + __padata_stop(pinst); + goto out_replace; + } + + valid = padata_validate_cpumask(pinst, cbcpumask); + if (!valid) + __padata_stop(pinst); + +out_replace: + pd = padata_alloc_pd(pinst, pcpumask, cbcpumask); + if (!pd) + return -ENOMEM; + + cpumask_copy(pinst->cpumask.pcpu, pcpumask); + cpumask_copy(pinst->cpumask.cbcpu, cbcpumask); + + padata_replace(pinst, pd); + + if (valid) + __padata_start(pinst); + + return 0; +} + +/** + * padata_set_cpumasks - Set both parallel and serial cpumasks. The first + * one is used by parallel workers and the second one + * by the wokers doing serialization. + * + * @pinst: padata instance + * @pcpumask: the cpumask to use for parallel workers + * @cbcpumask: the cpumsak to use for serial workers + */ +int padata_set_cpumasks(struct padata_instance *pinst, cpumask_var_t pcpumask, + cpumask_var_t cbcpumask) +{ + int err; + + mutex_lock(&pinst->lock); + get_online_cpus(); + + err = __padata_set_cpumasks(pinst, pcpumask, cbcpumask); + + put_online_cpus(); + mutex_unlock(&pinst->lock); + + return err; + +} +EXPORT_SYMBOL(padata_set_cpumasks); + +/** + * padata_set_cpumask: Sets specified by @cpumask_type cpumask to the value + * equivalent to @cpumask. + * + * @pinst: padata instance + * @cpumask_type: PADATA_CPU_SERIAL or PADATA_CPU_PARALLEL corresponding + * to parallel and serial cpumasks respectively. + * @cpumask: the cpumask to use + */ +int padata_set_cpumask(struct padata_instance *pinst, int cpumask_type, + cpumask_var_t cpumask) +{ + struct cpumask *serial_mask, *parallel_mask; + int err = -EINVAL; + + mutex_lock(&pinst->lock); + get_online_cpus(); + + switch (cpumask_type) { + case PADATA_CPU_PARALLEL: + serial_mask = pinst->cpumask.cbcpu; + parallel_mask = cpumask; + break; + case PADATA_CPU_SERIAL: + parallel_mask = pinst->cpumask.pcpu; + serial_mask = cpumask; + break; + default: + goto out; + } + + err = __padata_set_cpumasks(pinst, parallel_mask, serial_mask); + +out: + put_online_cpus(); + mutex_unlock(&pinst->lock); + + return err; +} +EXPORT_SYMBOL(padata_set_cpumask); + +static int __padata_add_cpu(struct padata_instance *pinst, int cpu) +{ + struct parallel_data *pd; + + if (cpumask_test_cpu(cpu, cpu_online_mask)) { + pd = padata_alloc_pd(pinst, pinst->cpumask.pcpu, + pinst->cpumask.cbcpu); + if (!pd) + return -ENOMEM; + + padata_replace(pinst, pd); + + if (padata_validate_cpumask(pinst, pinst->cpumask.pcpu) && + padata_validate_cpumask(pinst, pinst->cpumask.cbcpu)) + __padata_start(pinst); + } + + return 0; +} + + /** + * padata_add_cpu - add a cpu to one or both(parallel and serial) + * padata cpumasks. + * + * @pinst: padata instance + * @cpu: cpu to add + * @mask: bitmask of flags specifying to which cpumask @cpu shuld be added. + * The @mask may be any combination of the following flags: + * PADATA_CPU_SERIAL - serial cpumask + * PADATA_CPU_PARALLEL - parallel cpumask + */ + +int padata_add_cpu(struct padata_instance *pinst, int cpu, int mask) +{ + int err; + + if (!(mask & (PADATA_CPU_SERIAL | PADATA_CPU_PARALLEL))) + return -EINVAL; + + mutex_lock(&pinst->lock); + + get_online_cpus(); + if (mask & PADATA_CPU_SERIAL) + cpumask_set_cpu(cpu, pinst->cpumask.cbcpu); + if (mask & PADATA_CPU_PARALLEL) + cpumask_set_cpu(cpu, pinst->cpumask.pcpu); + + err = __padata_add_cpu(pinst, cpu); + put_online_cpus(); + + mutex_unlock(&pinst->lock); + + return err; +} +EXPORT_SYMBOL(padata_add_cpu); + +static int __padata_remove_cpu(struct padata_instance *pinst, int cpu) +{ + struct parallel_data *pd = NULL; + + if (cpumask_test_cpu(cpu, cpu_online_mask)) { + + if (!padata_validate_cpumask(pinst, pinst->cpumask.pcpu) || + !padata_validate_cpumask(pinst, pinst->cpumask.cbcpu)) + __padata_stop(pinst); + + pd = padata_alloc_pd(pinst, pinst->cpumask.pcpu, + pinst->cpumask.cbcpu); + if (!pd) + return -ENOMEM; + + padata_replace(pinst, pd); + + cpumask_clear_cpu(cpu, pd->cpumask.cbcpu); + cpumask_clear_cpu(cpu, pd->cpumask.pcpu); + } + + return 0; +} + + /** + * padata_remove_cpu - remove a cpu from the one or both(serial and parallel) + * padata cpumasks. + * + * @pinst: padata instance + * @cpu: cpu to remove + * @mask: bitmask specifying from which cpumask @cpu should be removed + * The @mask may be any combination of the following flags: + * PADATA_CPU_SERIAL - serial cpumask + * PADATA_CPU_PARALLEL - parallel cpumask + */ +int padata_remove_cpu(struct padata_instance *pinst, int cpu, int mask) +{ + int err; + + if (!(mask & (PADATA_CPU_SERIAL | PADATA_CPU_PARALLEL))) + return -EINVAL; + + mutex_lock(&pinst->lock); + + get_online_cpus(); + if (mask & PADATA_CPU_SERIAL) + cpumask_clear_cpu(cpu, pinst->cpumask.cbcpu); + if (mask & PADATA_CPU_PARALLEL) + cpumask_clear_cpu(cpu, pinst->cpumask.pcpu); + + err = __padata_remove_cpu(pinst, cpu); + put_online_cpus(); + + mutex_unlock(&pinst->lock); + + return err; +} +EXPORT_SYMBOL(padata_remove_cpu); + +/** + * padata_start - start the parallel processing + * + * @pinst: padata instance to start + */ +int padata_start(struct padata_instance *pinst) +{ + int err = 0; + + mutex_lock(&pinst->lock); + + if (pinst->flags & PADATA_INVALID) + err =-EINVAL; + + __padata_start(pinst); + + mutex_unlock(&pinst->lock); + + return err; +} +EXPORT_SYMBOL(padata_start); + +/** + * padata_stop - stop the parallel processing + * + * @pinst: padata instance to stop + */ +void padata_stop(struct padata_instance *pinst) +{ + mutex_lock(&pinst->lock); + __padata_stop(pinst); + mutex_unlock(&pinst->lock); +} +EXPORT_SYMBOL(padata_stop); + +#ifdef CONFIG_HOTPLUG_CPU + +static inline int pinst_has_cpu(struct padata_instance *pinst, int cpu) +{ + return cpumask_test_cpu(cpu, pinst->cpumask.pcpu) || + cpumask_test_cpu(cpu, pinst->cpumask.cbcpu); +} + + +static int padata_cpu_callback(struct notifier_block *nfb, + unsigned long action, void *hcpu) +{ + int err; + struct padata_instance *pinst; + int cpu = (unsigned long)hcpu; + + pinst = container_of(nfb, struct padata_instance, cpu_notifier); + + switch (action) { + case CPU_ONLINE: + case CPU_ONLINE_FROZEN: + case CPU_DOWN_FAILED: + case CPU_DOWN_FAILED_FROZEN: + if (!pinst_has_cpu(pinst, cpu)) + break; + mutex_lock(&pinst->lock); + err = __padata_add_cpu(pinst, cpu); + mutex_unlock(&pinst->lock); + if (err) + return notifier_from_errno(err); + break; + + case CPU_DOWN_PREPARE: + case CPU_DOWN_PREPARE_FROZEN: + case CPU_UP_CANCELED: + case CPU_UP_CANCELED_FROZEN: + if (!pinst_has_cpu(pinst, cpu)) + break; + mutex_lock(&pinst->lock); + err = __padata_remove_cpu(pinst, cpu); + mutex_unlock(&pinst->lock); + if (err) + return notifier_from_errno(err); + break; + } + + return NOTIFY_OK; +} +#endif + +static void __padata_free(struct padata_instance *pinst) +{ +#ifdef CONFIG_HOTPLUG_CPU + unregister_hotcpu_notifier(&pinst->cpu_notifier); +#endif + + padata_stop(pinst); + padata_free_pd(pinst->pd); + free_cpumask_var(pinst->cpumask.pcpu); + free_cpumask_var(pinst->cpumask.cbcpu); + kfree(pinst); +} + +#define kobj2pinst(_kobj) \ + container_of(_kobj, struct padata_instance, kobj) +#define attr2pentry(_attr) \ + container_of(_attr, struct padata_sysfs_entry, attr) + +static void padata_sysfs_release(struct kobject *kobj) +{ + struct padata_instance *pinst = kobj2pinst(kobj); + __padata_free(pinst); +} + +struct padata_sysfs_entry { + struct attribute attr; + ssize_t (*show)(struct padata_instance *, struct attribute *, char *); + ssize_t (*store)(struct padata_instance *, struct attribute *, + const char *, size_t); +}; + +static ssize_t show_cpumask(struct padata_instance *pinst, + struct attribute *attr, char *buf) +{ + struct cpumask *cpumask; + ssize_t len; + + mutex_lock(&pinst->lock); + if (!strcmp(attr->name, "serial_cpumask")) + cpumask = pinst->cpumask.cbcpu; + else + cpumask = pinst->cpumask.pcpu; + + len = snprintf(buf, PAGE_SIZE, "%*pb\n", + nr_cpu_ids, cpumask_bits(cpumask)); + mutex_unlock(&pinst->lock); + return len < PAGE_SIZE ? len : -EINVAL; +} + +static ssize_t store_cpumask(struct padata_instance *pinst, + struct attribute *attr, + const char *buf, size_t count) +{ + cpumask_var_t new_cpumask; + ssize_t ret; + int mask_type; + + if (!alloc_cpumask_var(&new_cpumask, GFP_KERNEL)) + return -ENOMEM; + + ret = bitmap_parse(buf, count, cpumask_bits(new_cpumask), + nr_cpumask_bits); + if (ret < 0) + goto out; + + mask_type = !strcmp(attr->name, "serial_cpumask") ? + PADATA_CPU_SERIAL : PADATA_CPU_PARALLEL; + ret = padata_set_cpumask(pinst, mask_type, new_cpumask); + if (!ret) + ret = count; + +out: + free_cpumask_var(new_cpumask); + return ret; +} + +#define PADATA_ATTR_RW(_name, _show_name, _store_name) \ + static struct padata_sysfs_entry _name##_attr = \ + __ATTR(_name, 0644, _show_name, _store_name) +#define PADATA_ATTR_RO(_name, _show_name) \ + static struct padata_sysfs_entry _name##_attr = \ + __ATTR(_name, 0400, _show_name, NULL) + +PADATA_ATTR_RW(serial_cpumask, show_cpumask, store_cpumask); +PADATA_ATTR_RW(parallel_cpumask, show_cpumask, store_cpumask); + +/* + * Padata sysfs provides the following objects: + * serial_cpumask [RW] - cpumask for serial workers + * parallel_cpumask [RW] - cpumask for parallel workers + */ +static struct attribute *padata_default_attrs[] = { + &serial_cpumask_attr.attr, + ¶llel_cpumask_attr.attr, + NULL, +}; + +static ssize_t padata_sysfs_show(struct kobject *kobj, + struct attribute *attr, char *buf) +{ + struct padata_instance *pinst; + struct padata_sysfs_entry *pentry; + ssize_t ret = -EIO; + + pinst = kobj2pinst(kobj); + pentry = attr2pentry(attr); + if (pentry->show) + ret = pentry->show(pinst, attr, buf); + + return ret; +} + +static ssize_t padata_sysfs_store(struct kobject *kobj, struct attribute *attr, + const char *buf, size_t count) +{ + struct padata_instance *pinst; + struct padata_sysfs_entry *pentry; + ssize_t ret = -EIO; + + pinst = kobj2pinst(kobj); + pentry = attr2pentry(attr); + if (pentry->show) + ret = pentry->store(pinst, attr, buf, count); + + return ret; +} + +static const struct sysfs_ops padata_sysfs_ops = { + .show = padata_sysfs_show, + .store = padata_sysfs_store, +}; + +static struct kobj_type padata_attr_type = { + .sysfs_ops = &padata_sysfs_ops, + .default_attrs = padata_default_attrs, + .release = padata_sysfs_release, +}; + +/** + * padata_alloc_possible - Allocate and initialize padata instance. + * Use the cpu_possible_mask for serial and + * parallel workers. + * + * @wq: workqueue to use for the allocated padata instance + */ +struct padata_instance *padata_alloc_possible(struct workqueue_struct *wq) +{ + return padata_alloc(wq, cpu_possible_mask, cpu_possible_mask); +} +EXPORT_SYMBOL(padata_alloc_possible); + +/** + * padata_alloc - allocate and initialize a padata instance and specify + * cpumasks for serial and parallel workers. + * + * @wq: workqueue to use for the allocated padata instance + * @pcpumask: cpumask that will be used for padata parallelization + * @cbcpumask: cpumask that will be used for padata serialization + */ +struct padata_instance *padata_alloc(struct workqueue_struct *wq, + const struct cpumask *pcpumask, + const struct cpumask *cbcpumask) +{ + struct padata_instance *pinst; + struct parallel_data *pd = NULL; + + pinst = kzalloc(sizeof(struct padata_instance), GFP_KERNEL); + if (!pinst) + goto err; + + get_online_cpus(); + if (!alloc_cpumask_var(&pinst->cpumask.pcpu, GFP_KERNEL)) + goto err_free_inst; + if (!alloc_cpumask_var(&pinst->cpumask.cbcpu, GFP_KERNEL)) { + free_cpumask_var(pinst->cpumask.pcpu); + goto err_free_inst; + } + if (!padata_validate_cpumask(pinst, pcpumask) || + !padata_validate_cpumask(pinst, cbcpumask)) + goto err_free_masks; + + pd = padata_alloc_pd(pinst, pcpumask, cbcpumask); + if (!pd) + goto err_free_masks; + + rcu_assign_pointer(pinst->pd, pd); + + pinst->wq = wq; + + cpumask_copy(pinst->cpumask.pcpu, pcpumask); + cpumask_copy(pinst->cpumask.cbcpu, cbcpumask); + + pinst->flags = 0; + + put_online_cpus(); + + BLOCKING_INIT_NOTIFIER_HEAD(&pinst->cpumask_change_notifier); + kobject_init(&pinst->kobj, &padata_attr_type); + mutex_init(&pinst->lock); + +#ifdef CONFIG_HOTPLUG_CPU + pinst->cpu_notifier.notifier_call = padata_cpu_callback; + pinst->cpu_notifier.priority = 0; + register_hotcpu_notifier(&pinst->cpu_notifier); +#endif + + return pinst; + +err_free_masks: + free_cpumask_var(pinst->cpumask.pcpu); + free_cpumask_var(pinst->cpumask.cbcpu); +err_free_inst: + kfree(pinst); + put_online_cpus(); +err: + return NULL; +} +EXPORT_SYMBOL(padata_alloc); + +/** + * padata_free - free a padata instance + * + * @padata_inst: padata instance to free + */ +void padata_free(struct padata_instance *pinst) +{ + kobject_put(&pinst->kobj); +} +EXPORT_SYMBOL(padata_free); diff --git a/kernel/kernel/panic.c b/kernel/kernel/panic.c new file mode 100644 index 000000000..04360904f --- /dev/null +++ b/kernel/kernel/panic.c @@ -0,0 +1,521 @@ +/* + * linux/kernel/panic.c + * + * Copyright (C) 1991, 1992 Linus Torvalds + */ + +/* + * This function is used through-out the kernel (including mm and fs) + * to indicate a major problem. + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define PANIC_TIMER_STEP 100 +#define PANIC_BLINK_SPD 18 + +int panic_on_oops = CONFIG_PANIC_ON_OOPS_VALUE; +static unsigned long tainted_mask; +static int pause_on_oops; +static int pause_on_oops_flag; +static DEFINE_SPINLOCK(pause_on_oops_lock); +static bool crash_kexec_post_notifiers; +int panic_on_warn __read_mostly; + +int panic_timeout = CONFIG_PANIC_TIMEOUT; +EXPORT_SYMBOL_GPL(panic_timeout); + +ATOMIC_NOTIFIER_HEAD(panic_notifier_list); + +EXPORT_SYMBOL(panic_notifier_list); + +static long no_blink(int state) +{ + return 0; +} + +/* Returns how long it waited in ms */ +long (*panic_blink)(int state); +EXPORT_SYMBOL(panic_blink); + +/* + * Stop ourself in panic -- architecture code may override this + */ +void __weak panic_smp_self_stop(void) +{ + while (1) + cpu_relax(); +} + +/** + * panic - halt the system + * @fmt: The text string to print + * + * Display a message, then perform cleanups. + * + * This function never returns. + */ +void panic(const char *fmt, ...) +{ + static DEFINE_SPINLOCK(panic_lock); + static char buf[1024]; + va_list args; + long i, i_next = 0; + int state = 0; + + /* + * Disable local interrupts. This will prevent panic_smp_self_stop + * from deadlocking the first cpu that invokes the panic, since + * there is nothing to prevent an interrupt handler (that runs + * after the panic_lock is acquired) from invoking panic again. + */ + local_irq_disable(); + + /* + * It's possible to come here directly from a panic-assertion and + * not have preempt disabled. Some functions called from here want + * preempt to be disabled. No point enabling it later though... + * + * Only one CPU is allowed to execute the panic code from here. For + * multiple parallel invocations of panic, all other CPUs either + * stop themself or will wait until they are stopped by the 1st CPU + * with smp_send_stop(). + */ + if (!spin_trylock(&panic_lock)) + panic_smp_self_stop(); + + console_verbose(); + bust_spinlocks(1); + va_start(args, fmt); + vsnprintf(buf, sizeof(buf), fmt, args); + va_end(args); + pr_emerg("Kernel panic - not syncing: %s\n", buf); +#ifdef CONFIG_DEBUG_BUGVERBOSE + /* + * Avoid nested stack-dumping if a panic occurs during oops processing + */ + if (!test_taint(TAINT_DIE) && oops_in_progress <= 1) + dump_stack(); +#endif + + /* + * If we have crashed and we have a crash kernel loaded let it handle + * everything else. + * If we want to run this after calling panic_notifiers, pass + * the "crash_kexec_post_notifiers" option to the kernel. + */ + if (!crash_kexec_post_notifiers) + crash_kexec(NULL); + + /* + * Note smp_send_stop is the usual smp shutdown function, which + * unfortunately means it may not be hardened to work in a panic + * situation. + */ + smp_send_stop(); + + /* + * Run any panic handlers, including those that might need to + * add information to the kmsg dump output. + */ + atomic_notifier_call_chain(&panic_notifier_list, 0, buf); + + kmsg_dump(KMSG_DUMP_PANIC); + + /* + * If you doubt kdump always works fine in any situation, + * "crash_kexec_post_notifiers" offers you a chance to run + * panic_notifiers and dumping kmsg before kdump. + * Note: since some panic_notifiers can make crashed kernel + * more unstable, it can increase risks of the kdump failure too. + */ + crash_kexec(NULL); + + bust_spinlocks(0); + + if (!panic_blink) + panic_blink = no_blink; + + if (panic_timeout > 0) { + /* + * Delay timeout seconds before rebooting the machine. + * We can't use the "normal" timers since we just panicked. + */ + pr_emerg("Rebooting in %d seconds..", panic_timeout); + + for (i = 0; i < panic_timeout * 1000; i += PANIC_TIMER_STEP) { + touch_nmi_watchdog(); + if (i >= i_next) { + i += panic_blink(state ^= 1); + i_next = i + 3600 / PANIC_BLINK_SPD; + } + mdelay(PANIC_TIMER_STEP); + } + } + if (panic_timeout != 0) { + /* + * This will not be a clean reboot, with everything + * shutting down. But if there is a chance of + * rebooting the system it will be rebooted. + */ + emergency_restart(); + } +#ifdef __sparc__ + { + extern int stop_a_enabled; + /* Make sure the user can actually press Stop-A (L1-A) */ + stop_a_enabled = 1; + pr_emerg("Press Stop-A (L1-A) to return to the boot prom\n"); + } +#endif +#if defined(CONFIG_S390) + { + unsigned long caller; + + caller = (unsigned long)__builtin_return_address(0); + disabled_wait(caller); + } +#endif + pr_emerg("---[ end Kernel panic - not syncing: %s\n", buf); + local_irq_enable(); + for (i = 0; ; i += PANIC_TIMER_STEP) { + touch_softlockup_watchdog(); + if (i >= i_next) { + i += panic_blink(state ^= 1); + i_next = i + 3600 / PANIC_BLINK_SPD; + } + mdelay(PANIC_TIMER_STEP); + } +} + +EXPORT_SYMBOL(panic); + + +struct tnt { + u8 bit; + char true; + char false; +}; + +static const struct tnt tnts[] = { + { TAINT_PROPRIETARY_MODULE, 'P', 'G' }, + { TAINT_FORCED_MODULE, 'F', ' ' }, + { TAINT_CPU_OUT_OF_SPEC, 'S', ' ' }, + { TAINT_FORCED_RMMOD, 'R', ' ' }, + { TAINT_MACHINE_CHECK, 'M', ' ' }, + { TAINT_BAD_PAGE, 'B', ' ' }, + { TAINT_USER, 'U', ' ' }, + { TAINT_DIE, 'D', ' ' }, + { TAINT_OVERRIDDEN_ACPI_TABLE, 'A', ' ' }, + { TAINT_WARN, 'W', ' ' }, + { TAINT_CRAP, 'C', ' ' }, + { TAINT_FIRMWARE_WORKAROUND, 'I', ' ' }, + { TAINT_OOT_MODULE, 'O', ' ' }, + { TAINT_UNSIGNED_MODULE, 'E', ' ' }, + { TAINT_SOFTLOCKUP, 'L', ' ' }, + { TAINT_LIVEPATCH, 'K', ' ' }, +}; + +/** + * print_tainted - return a string to represent the kernel taint state. + * + * 'P' - Proprietary module has been loaded. + * 'F' - Module has been forcibly loaded. + * 'S' - SMP with CPUs not designed for SMP. + * 'R' - User forced a module unload. + * 'M' - System experienced a machine check exception. + * 'B' - System has hit bad_page. + * 'U' - Userspace-defined naughtiness. + * 'D' - Kernel has oopsed before + * 'A' - ACPI table overridden. + * 'W' - Taint on warning. + * 'C' - modules from drivers/staging are loaded. + * 'I' - Working around severe firmware bug. + * 'O' - Out-of-tree module has been loaded. + * 'E' - Unsigned module has been loaded. + * 'L' - A soft lockup has previously occurred. + * 'K' - Kernel has been live patched. + * + * The string is overwritten by the next call to print_tainted(). + */ +const char *print_tainted(void) +{ + static char buf[ARRAY_SIZE(tnts) + sizeof("Tainted: ")]; + + if (tainted_mask) { + char *s; + int i; + + s = buf + sprintf(buf, "Tainted: "); + for (i = 0; i < ARRAY_SIZE(tnts); i++) { + const struct tnt *t = &tnts[i]; + *s++ = test_bit(t->bit, &tainted_mask) ? + t->true : t->false; + } + *s = 0; + } else + snprintf(buf, sizeof(buf), "Not tainted"); + + return buf; +} + +int test_taint(unsigned flag) +{ + return test_bit(flag, &tainted_mask); +} +EXPORT_SYMBOL(test_taint); + +unsigned long get_taint(void) +{ + return tainted_mask; +} + +/** + * add_taint: add a taint flag if not already set. + * @flag: one of the TAINT_* constants. + * @lockdep_ok: whether lock debugging is still OK. + * + * If something bad has gone wrong, you'll want @lockdebug_ok = false, but for + * some notewortht-but-not-corrupting cases, it can be set to true. + */ +void add_taint(unsigned flag, enum lockdep_ok lockdep_ok) +{ + if (lockdep_ok == LOCKDEP_NOW_UNRELIABLE && __debug_locks_off()) + pr_warn("Disabling lock debugging due to kernel taint\n"); + + set_bit(flag, &tainted_mask); +} +EXPORT_SYMBOL(add_taint); + +static void spin_msec(int msecs) +{ + int i; + + for (i = 0; i < msecs; i++) { + touch_nmi_watchdog(); + mdelay(1); + } +} + +/* + * It just happens that oops_enter() and oops_exit() are identically + * implemented... + */ +static void do_oops_enter_exit(void) +{ + unsigned long flags; + static int spin_counter; + + if (!pause_on_oops) + return; + + spin_lock_irqsave(&pause_on_oops_lock, flags); + if (pause_on_oops_flag == 0) { + /* This CPU may now print the oops message */ + pause_on_oops_flag = 1; + } else { + /* We need to stall this CPU */ + if (!spin_counter) { + /* This CPU gets to do the counting */ + spin_counter = pause_on_oops; + do { + spin_unlock(&pause_on_oops_lock); + spin_msec(MSEC_PER_SEC); + spin_lock(&pause_on_oops_lock); + } while (--spin_counter); + pause_on_oops_flag = 0; + } else { + /* This CPU waits for a different one */ + while (spin_counter) { + spin_unlock(&pause_on_oops_lock); + spin_msec(1); + spin_lock(&pause_on_oops_lock); + } + } + } + spin_unlock_irqrestore(&pause_on_oops_lock, flags); +} + +/* + * Return true if the calling CPU is allowed to print oops-related info. + * This is a bit racy.. + */ +int oops_may_print(void) +{ + return pause_on_oops_flag == 0; +} + +/* + * Called when the architecture enters its oops handler, before it prints + * anything. If this is the first CPU to oops, and it's oopsing the first + * time then let it proceed. + * + * This is all enabled by the pause_on_oops kernel boot option. We do all + * this to ensure that oopses don't scroll off the screen. It has the + * side-effect of preventing later-oopsing CPUs from mucking up the display, + * too. + * + * It turns out that the CPU which is allowed to print ends up pausing for + * the right duration, whereas all the other CPUs pause for twice as long: + * once in oops_enter(), once in oops_exit(). + */ +void oops_enter(void) +{ + tracing_off(); + /* can't trust the integrity of the kernel anymore: */ + debug_locks_off(); + do_oops_enter_exit(); +} + +/* + * 64-bit random ID for oopses: + */ +static u64 oops_id; + +static int init_oops_id(void) +{ +#ifndef CONFIG_PREEMPT_RT_FULL + if (!oops_id) + get_random_bytes(&oops_id, sizeof(oops_id)); + else +#endif + oops_id++; + + return 0; +} +late_initcall(init_oops_id); + +void print_oops_end_marker(void) +{ + init_oops_id(); + pr_warn("---[ end trace %016llx ]---\n", (unsigned long long)oops_id); +} + +/* + * Called when the architecture exits its oops handler, after printing + * everything. + */ +void oops_exit(void) +{ + do_oops_enter_exit(); + print_oops_end_marker(); + kmsg_dump(KMSG_DUMP_OOPS); +} + +#ifdef WANT_WARN_ON_SLOWPATH +struct slowpath_args { + const char *fmt; + va_list args; +}; + +static void warn_slowpath_common(const char *file, int line, void *caller, + unsigned taint, struct slowpath_args *args) +{ + disable_trace_on_warning(); + + pr_warn("------------[ cut here ]------------\n"); + pr_warn("WARNING: CPU: %d PID: %d at %s:%d %pS()\n", + raw_smp_processor_id(), current->pid, file, line, caller); + + if (args) + vprintk(args->fmt, args->args); + + if (panic_on_warn) { + /* + * This thread may hit another WARN() in the panic path. + * Resetting this prevents additional WARN() from panicking the + * system on this thread. Other threads are blocked by the + * panic_mutex in panic(). + */ + panic_on_warn = 0; + panic("panic_on_warn set ...\n"); + } + + print_modules(); + dump_stack(); + print_oops_end_marker(); + /* Just a warning, don't kill lockdep. */ + add_taint(taint, LOCKDEP_STILL_OK); +} + +void warn_slowpath_fmt(const char *file, int line, const char *fmt, ...) +{ + struct slowpath_args args; + + args.fmt = fmt; + va_start(args.args, fmt); + warn_slowpath_common(file, line, __builtin_return_address(0), + TAINT_WARN, &args); + va_end(args.args); +} +EXPORT_SYMBOL(warn_slowpath_fmt); + +void warn_slowpath_fmt_taint(const char *file, int line, + unsigned taint, const char *fmt, ...) +{ + struct slowpath_args args; + + args.fmt = fmt; + va_start(args.args, fmt); + warn_slowpath_common(file, line, __builtin_return_address(0), + taint, &args); + va_end(args.args); +} +EXPORT_SYMBOL(warn_slowpath_fmt_taint); + +void warn_slowpath_null(const char *file, int line) +{ + warn_slowpath_common(file, line, __builtin_return_address(0), + TAINT_WARN, NULL); +} +EXPORT_SYMBOL(warn_slowpath_null); +#endif + +#ifdef CONFIG_CC_STACKPROTECTOR + +/* + * Called when gcc's -fstack-protector feature is used, and + * gcc detects corruption of the on-stack canary value + */ +__visible void __stack_chk_fail(void) +{ + panic("stack-protector: Kernel stack is corrupted in: %p\n", + __builtin_return_address(0)); +} +EXPORT_SYMBOL(__stack_chk_fail); + +#endif + +core_param(panic, panic_timeout, int, 0644); +core_param(pause_on_oops, pause_on_oops, int, 0644); +core_param(panic_on_warn, panic_on_warn, int, 0644); + +static int __init setup_crash_kexec_post_notifiers(char *s) +{ + crash_kexec_post_notifiers = true; + return 0; +} +early_param("crash_kexec_post_notifiers", setup_crash_kexec_post_notifiers); + +static int __init oops_setup(char *s) +{ + if (!s) + return -EINVAL; + if (!strcmp(s, "panic")) + panic_on_oops = 1; + return 0; +} +early_param("oops", oops_setup); diff --git a/kernel/kernel/params.c b/kernel/kernel/params.c new file mode 100644 index 000000000..a22d6a759 --- /dev/null +++ b/kernel/kernel/params.c @@ -0,0 +1,954 @@ +/* Helpers for initial module or kernel cmdline parsing + Copyright (C) 2001 Rusty Russell. + + This program is free software; you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation; either version 2 of the License, or + (at your option) any later version. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU General Public License for more details. + + You should have received a copy of the GNU General Public License + along with this program; if not, write to the Free Software + Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA +*/ +#include +#include +#include +#include +#include +#include +#include +#include +#include + +/* Protects all parameters, and incidentally kmalloced_param list. */ +static DEFINE_MUTEX(param_lock); + +/* This just allows us to keep track of which parameters are kmalloced. */ +struct kmalloced_param { + struct list_head list; + char val[]; +}; +static LIST_HEAD(kmalloced_params); + +static void *kmalloc_parameter(unsigned int size) +{ + struct kmalloced_param *p; + + p = kmalloc(sizeof(*p) + size, GFP_KERNEL); + if (!p) + return NULL; + + list_add(&p->list, &kmalloced_params); + return p->val; +} + +/* Does nothing if parameter wasn't kmalloced above. */ +static void maybe_kfree_parameter(void *param) +{ + struct kmalloced_param *p; + + list_for_each_entry(p, &kmalloced_params, list) { + if (p->val == param) { + list_del(&p->list); + kfree(p); + break; + } + } +} + +static char dash2underscore(char c) +{ + if (c == '-') + return '_'; + return c; +} + +bool parameqn(const char *a, const char *b, size_t n) +{ + size_t i; + + for (i = 0; i < n; i++) { + if (dash2underscore(a[i]) != dash2underscore(b[i])) + return false; + } + return true; +} + +bool parameq(const char *a, const char *b) +{ + return parameqn(a, b, strlen(a)+1); +} + +static void param_check_unsafe(const struct kernel_param *kp) +{ + if (kp->flags & KERNEL_PARAM_FL_UNSAFE) { + pr_warn("Setting dangerous option %s - tainting kernel\n", + kp->name); + add_taint(TAINT_USER, LOCKDEP_STILL_OK); + } +} + +static int parse_one(char *param, + char *val, + const char *doing, + const struct kernel_param *params, + unsigned num_params, + s16 min_level, + s16 max_level, + int (*handle_unknown)(char *param, char *val, + const char *doing)) +{ + unsigned int i; + int err; + + /* Find parameter */ + for (i = 0; i < num_params; i++) { + if (parameq(param, params[i].name)) { + if (params[i].level < min_level + || params[i].level > max_level) + return 0; + /* No one handled NULL, so do it here. */ + if (!val && + !(params[i].ops->flags & KERNEL_PARAM_OPS_FL_NOARG)) + return -EINVAL; + pr_debug("handling %s with %p\n", param, + params[i].ops->set); + mutex_lock(¶m_lock); + param_check_unsafe(¶ms[i]); + err = params[i].ops->set(val, ¶ms[i]); + mutex_unlock(¶m_lock); + return err; + } + } + + if (handle_unknown) { + pr_debug("doing %s: %s='%s'\n", doing, param, val); + return handle_unknown(param, val, doing); + } + + pr_debug("Unknown argument '%s'\n", param); + return -ENOENT; +} + +/* You can use " around spaces, but can't escape ". */ +/* Hyphens and underscores equivalent in parameter names. */ +static char *next_arg(char *args, char **param, char **val) +{ + unsigned int i, equals = 0; + int in_quote = 0, quoted = 0; + char *next; + + if (*args == '"') { + args++; + in_quote = 1; + quoted = 1; + } + + for (i = 0; args[i]; i++) { + if (isspace(args[i]) && !in_quote) + break; + if (equals == 0) { + if (args[i] == '=') + equals = i; + } + if (args[i] == '"') + in_quote = !in_quote; + } + + *param = args; + if (!equals) + *val = NULL; + else { + args[equals] = '\0'; + *val = args + equals + 1; + + /* Don't include quotes in value. */ + if (**val == '"') { + (*val)++; + if (args[i-1] == '"') + args[i-1] = '\0'; + } + } + if (quoted && args[i-1] == '"') + args[i-1] = '\0'; + + if (args[i]) { + args[i] = '\0'; + next = args + i + 1; + } else + next = args + i; + + /* Chew up trailing spaces. */ + return skip_spaces(next); +} + +/* Args looks like "foo=bar,bar2 baz=fuz wiz". */ +char *parse_args(const char *doing, + char *args, + const struct kernel_param *params, + unsigned num, + s16 min_level, + s16 max_level, + int (*unknown)(char *param, char *val, const char *doing)) +{ + char *param, *val; + + /* Chew leading spaces */ + args = skip_spaces(args); + + if (*args) + pr_debug("doing %s, parsing ARGS: '%s'\n", doing, args); + + while (*args) { + int ret; + int irq_was_disabled; + + args = next_arg(args, ¶m, &val); + /* Stop at -- */ + if (!val && strcmp(param, "--") == 0) + return args; + irq_was_disabled = irqs_disabled(); + ret = parse_one(param, val, doing, params, num, + min_level, max_level, unknown); + if (irq_was_disabled && !irqs_disabled()) + pr_warn("%s: option '%s' enabled irq's!\n", + doing, param); + + switch (ret) { + case -ENOENT: + pr_err("%s: Unknown parameter `%s'\n", doing, param); + return ERR_PTR(ret); + case -ENOSPC: + pr_err("%s: `%s' too large for parameter `%s'\n", + doing, val ?: "", param); + return ERR_PTR(ret); + case 0: + break; + default: + pr_err("%s: `%s' invalid for parameter `%s'\n", + doing, val ?: "", param); + return ERR_PTR(ret); + } + } + + /* All parsed OK. */ + return NULL; +} + +/* Lazy bastard, eh? */ +#define STANDARD_PARAM_DEF(name, type, format, strtolfn) \ + int param_set_##name(const char *val, const struct kernel_param *kp) \ + { \ + return strtolfn(val, 0, (type *)kp->arg); \ + } \ + int param_get_##name(char *buffer, const struct kernel_param *kp) \ + { \ + return scnprintf(buffer, PAGE_SIZE, format, \ + *((type *)kp->arg)); \ + } \ + struct kernel_param_ops param_ops_##name = { \ + .set = param_set_##name, \ + .get = param_get_##name, \ + }; \ + EXPORT_SYMBOL(param_set_##name); \ + EXPORT_SYMBOL(param_get_##name); \ + EXPORT_SYMBOL(param_ops_##name) + + +STANDARD_PARAM_DEF(byte, unsigned char, "%hhu", kstrtou8); +STANDARD_PARAM_DEF(short, short, "%hi", kstrtos16); +STANDARD_PARAM_DEF(ushort, unsigned short, "%hu", kstrtou16); +STANDARD_PARAM_DEF(int, int, "%i", kstrtoint); +STANDARD_PARAM_DEF(uint, unsigned int, "%u", kstrtouint); +STANDARD_PARAM_DEF(long, long, "%li", kstrtol); +STANDARD_PARAM_DEF(ulong, unsigned long, "%lu", kstrtoul); +STANDARD_PARAM_DEF(ullong, unsigned long long, "%llu", kstrtoull); + +int param_set_charp(const char *val, const struct kernel_param *kp) +{ + if (strlen(val) > 1024) { + pr_err("%s: string parameter too long\n", kp->name); + return -ENOSPC; + } + + maybe_kfree_parameter(*(char **)kp->arg); + + /* This is a hack. We can't kmalloc in early boot, and we + * don't need to; this mangled commandline is preserved. */ + if (slab_is_available()) { + *(char **)kp->arg = kmalloc_parameter(strlen(val)+1); + if (!*(char **)kp->arg) + return -ENOMEM; + strcpy(*(char **)kp->arg, val); + } else + *(const char **)kp->arg = val; + + return 0; +} +EXPORT_SYMBOL(param_set_charp); + +int param_get_charp(char *buffer, const struct kernel_param *kp) +{ + return scnprintf(buffer, PAGE_SIZE, "%s", *((char **)kp->arg)); +} +EXPORT_SYMBOL(param_get_charp); + +static void param_free_charp(void *arg) +{ + maybe_kfree_parameter(*((char **)arg)); +} + +struct kernel_param_ops param_ops_charp = { + .set = param_set_charp, + .get = param_get_charp, + .free = param_free_charp, +}; +EXPORT_SYMBOL(param_ops_charp); + +/* Actually could be a bool or an int, for historical reasons. */ +int param_set_bool(const char *val, const struct kernel_param *kp) +{ + /* No equals means "set"... */ + if (!val) val = "1"; + + /* One of =[yYnN01] */ + return strtobool(val, kp->arg); +} +EXPORT_SYMBOL(param_set_bool); + +int param_get_bool(char *buffer, const struct kernel_param *kp) +{ + /* Y and N chosen as being relatively non-coder friendly */ + return sprintf(buffer, "%c", *(bool *)kp->arg ? 'Y' : 'N'); +} +EXPORT_SYMBOL(param_get_bool); + +struct kernel_param_ops param_ops_bool = { + .flags = KERNEL_PARAM_OPS_FL_NOARG, + .set = param_set_bool, + .get = param_get_bool, +}; +EXPORT_SYMBOL(param_ops_bool); + +/* This one must be bool. */ +int param_set_invbool(const char *val, const struct kernel_param *kp) +{ + int ret; + bool boolval; + struct kernel_param dummy; + + dummy.arg = &boolval; + ret = param_set_bool(val, &dummy); + if (ret == 0) + *(bool *)kp->arg = !boolval; + return ret; +} +EXPORT_SYMBOL(param_set_invbool); + +int param_get_invbool(char *buffer, const struct kernel_param *kp) +{ + return sprintf(buffer, "%c", (*(bool *)kp->arg) ? 'N' : 'Y'); +} +EXPORT_SYMBOL(param_get_invbool); + +struct kernel_param_ops param_ops_invbool = { + .set = param_set_invbool, + .get = param_get_invbool, +}; +EXPORT_SYMBOL(param_ops_invbool); + +int param_set_bint(const char *val, const struct kernel_param *kp) +{ + struct kernel_param boolkp; + bool v; + int ret; + + /* Match bool exactly, by re-using it. */ + boolkp = *kp; + boolkp.arg = &v; + + ret = param_set_bool(val, &boolkp); + if (ret == 0) + *(int *)kp->arg = v; + return ret; +} +EXPORT_SYMBOL(param_set_bint); + +struct kernel_param_ops param_ops_bint = { + .flags = KERNEL_PARAM_OPS_FL_NOARG, + .set = param_set_bint, + .get = param_get_int, +}; +EXPORT_SYMBOL(param_ops_bint); + +/* We break the rule and mangle the string. */ +static int param_array(const char *name, + const char *val, + unsigned int min, unsigned int max, + void *elem, int elemsize, + int (*set)(const char *, const struct kernel_param *kp), + s16 level, + unsigned int *num) +{ + int ret; + struct kernel_param kp; + char save; + + /* Get the name right for errors. */ + kp.name = name; + kp.arg = elem; + kp.level = level; + + *num = 0; + /* We expect a comma-separated list of values. */ + do { + int len; + + if (*num == max) { + pr_err("%s: can only take %i arguments\n", name, max); + return -EINVAL; + } + len = strcspn(val, ","); + + /* nul-terminate and parse */ + save = val[len]; + ((char *)val)[len] = '\0'; + BUG_ON(!mutex_is_locked(¶m_lock)); + ret = set(val, &kp); + + if (ret != 0) + return ret; + kp.arg += elemsize; + val += len+1; + (*num)++; + } while (save == ','); + + if (*num < min) { + pr_err("%s: needs at least %i arguments\n", name, min); + return -EINVAL; + } + return 0; +} + +static int param_array_set(const char *val, const struct kernel_param *kp) +{ + const struct kparam_array *arr = kp->arr; + unsigned int temp_num; + + return param_array(kp->name, val, 1, arr->max, arr->elem, + arr->elemsize, arr->ops->set, kp->level, + arr->num ?: &temp_num); +} + +static int param_array_get(char *buffer, const struct kernel_param *kp) +{ + int i, off, ret; + const struct kparam_array *arr = kp->arr; + struct kernel_param p; + + p = *kp; + for (i = off = 0; i < (arr->num ? *arr->num : arr->max); i++) { + if (i) + buffer[off++] = ','; + p.arg = arr->elem + arr->elemsize * i; + BUG_ON(!mutex_is_locked(¶m_lock)); + ret = arr->ops->get(buffer + off, &p); + if (ret < 0) + return ret; + off += ret; + } + buffer[off] = '\0'; + return off; +} + +static void param_array_free(void *arg) +{ + unsigned int i; + const struct kparam_array *arr = arg; + + if (arr->ops->free) + for (i = 0; i < (arr->num ? *arr->num : arr->max); i++) + arr->ops->free(arr->elem + arr->elemsize * i); +} + +struct kernel_param_ops param_array_ops = { + .set = param_array_set, + .get = param_array_get, + .free = param_array_free, +}; +EXPORT_SYMBOL(param_array_ops); + +int param_set_copystring(const char *val, const struct kernel_param *kp) +{ + const struct kparam_string *kps = kp->str; + + if (strlen(val)+1 > kps->maxlen) { + pr_err("%s: string doesn't fit in %u chars.\n", + kp->name, kps->maxlen-1); + return -ENOSPC; + } + strcpy(kps->string, val); + return 0; +} +EXPORT_SYMBOL(param_set_copystring); + +int param_get_string(char *buffer, const struct kernel_param *kp) +{ + const struct kparam_string *kps = kp->str; + return strlcpy(buffer, kps->string, kps->maxlen); +} +EXPORT_SYMBOL(param_get_string); + +struct kernel_param_ops param_ops_string = { + .set = param_set_copystring, + .get = param_get_string, +}; +EXPORT_SYMBOL(param_ops_string); + +/* sysfs output in /sys/modules/XYZ/parameters/ */ +#define to_module_attr(n) container_of(n, struct module_attribute, attr) +#define to_module_kobject(n) container_of(n, struct module_kobject, kobj) + +struct param_attribute +{ + struct module_attribute mattr; + const struct kernel_param *param; +}; + +struct module_param_attrs +{ + unsigned int num; + struct attribute_group grp; + struct param_attribute attrs[0]; +}; + +#ifdef CONFIG_SYSFS +#define to_param_attr(n) container_of(n, struct param_attribute, mattr) + +static ssize_t param_attr_show(struct module_attribute *mattr, + struct module_kobject *mk, char *buf) +{ + int count; + struct param_attribute *attribute = to_param_attr(mattr); + + if (!attribute->param->ops->get) + return -EPERM; + + mutex_lock(¶m_lock); + count = attribute->param->ops->get(buf, attribute->param); + mutex_unlock(¶m_lock); + if (count > 0) { + strcat(buf, "\n"); + ++count; + } + return count; +} + +/* sysfs always hands a nul-terminated string in buf. We rely on that. */ +static ssize_t param_attr_store(struct module_attribute *mattr, + struct module_kobject *km, + const char *buf, size_t len) +{ + int err; + struct param_attribute *attribute = to_param_attr(mattr); + + if (!attribute->param->ops->set) + return -EPERM; + + mutex_lock(¶m_lock); + param_check_unsafe(attribute->param); + err = attribute->param->ops->set(buf, attribute->param); + mutex_unlock(¶m_lock); + if (!err) + return len; + return err; +} +#endif + +#ifdef CONFIG_MODULES +#define __modinit +#else +#define __modinit __init +#endif + +#ifdef CONFIG_SYSFS +void __kernel_param_lock(void) +{ + mutex_lock(¶m_lock); +} +EXPORT_SYMBOL(__kernel_param_lock); + +void __kernel_param_unlock(void) +{ + mutex_unlock(¶m_lock); +} +EXPORT_SYMBOL(__kernel_param_unlock); + +/* + * add_sysfs_param - add a parameter to sysfs + * @mk: struct module_kobject + * @kparam: the actual parameter definition to add to sysfs + * @name: name of parameter + * + * Create a kobject if for a (per-module) parameter if mp NULL, and + * create file in sysfs. Returns an error on out of memory. Always cleans up + * if there's an error. + */ +static __modinit int add_sysfs_param(struct module_kobject *mk, + const struct kernel_param *kp, + const char *name) +{ + struct module_param_attrs *new_mp; + struct attribute **new_attrs; + unsigned int i; + + /* We don't bother calling this with invisible parameters. */ + BUG_ON(!kp->perm); + + if (!mk->mp) { + /* First allocation. */ + mk->mp = kzalloc(sizeof(*mk->mp), GFP_KERNEL); + if (!mk->mp) + return -ENOMEM; + mk->mp->grp.name = "parameters"; + /* NULL-terminated attribute array. */ + mk->mp->grp.attrs = kzalloc(sizeof(mk->mp->grp.attrs[0]), + GFP_KERNEL); + /* Caller will cleanup via free_module_param_attrs */ + if (!mk->mp->grp.attrs) + return -ENOMEM; + } + + /* Enlarge allocations. */ + new_mp = krealloc(mk->mp, + sizeof(*mk->mp) + + sizeof(mk->mp->attrs[0]) * (mk->mp->num + 1), + GFP_KERNEL); + if (!new_mp) + return -ENOMEM; + mk->mp = new_mp; + + /* Extra pointer for NULL terminator */ + new_attrs = krealloc(mk->mp->grp.attrs, + sizeof(mk->mp->grp.attrs[0]) * (mk->mp->num + 2), + GFP_KERNEL); + if (!new_attrs) + return -ENOMEM; + mk->mp->grp.attrs = new_attrs; + + /* Tack new one on the end. */ + memset(&mk->mp->attrs[mk->mp->num], 0, sizeof(mk->mp->attrs[0])); + sysfs_attr_init(&mk->mp->attrs[mk->mp->num].mattr.attr); + mk->mp->attrs[mk->mp->num].param = kp; + mk->mp->attrs[mk->mp->num].mattr.show = param_attr_show; + /* Do not allow runtime DAC changes to make param writable. */ + if ((kp->perm & (S_IWUSR | S_IWGRP | S_IWOTH)) != 0) + mk->mp->attrs[mk->mp->num].mattr.store = param_attr_store; + else + mk->mp->attrs[mk->mp->num].mattr.store = NULL; + mk->mp->attrs[mk->mp->num].mattr.attr.name = (char *)name; + mk->mp->attrs[mk->mp->num].mattr.attr.mode = kp->perm; + mk->mp->num++; + + /* Fix up all the pointers, since krealloc can move us */ + for (i = 0; i < mk->mp->num; i++) + mk->mp->grp.attrs[i] = &mk->mp->attrs[i].mattr.attr; + mk->mp->grp.attrs[mk->mp->num] = NULL; + return 0; +} + +#ifdef CONFIG_MODULES +static void free_module_param_attrs(struct module_kobject *mk) +{ + if (mk->mp) + kfree(mk->mp->grp.attrs); + kfree(mk->mp); + mk->mp = NULL; +} + +/* + * module_param_sysfs_setup - setup sysfs support for one module + * @mod: module + * @kparam: module parameters (array) + * @num_params: number of module parameters + * + * Adds sysfs entries for module parameters under + * /sys/module/[mod->name]/parameters/ + */ +int module_param_sysfs_setup(struct module *mod, + const struct kernel_param *kparam, + unsigned int num_params) +{ + int i, err; + bool params = false; + + for (i = 0; i < num_params; i++) { + if (kparam[i].perm == 0) + continue; + err = add_sysfs_param(&mod->mkobj, &kparam[i], kparam[i].name); + if (err) { + free_module_param_attrs(&mod->mkobj); + return err; + } + params = true; + } + + if (!params) + return 0; + + /* Create the param group. */ + err = sysfs_create_group(&mod->mkobj.kobj, &mod->mkobj.mp->grp); + if (err) + free_module_param_attrs(&mod->mkobj); + return err; +} + +/* + * module_param_sysfs_remove - remove sysfs support for one module + * @mod: module + * + * Remove sysfs entries for module parameters and the corresponding + * kobject. + */ +void module_param_sysfs_remove(struct module *mod) +{ + if (mod->mkobj.mp) { + sysfs_remove_group(&mod->mkobj.kobj, &mod->mkobj.mp->grp); + /* We are positive that no one is using any param + * attrs at this point. Deallocate immediately. */ + free_module_param_attrs(&mod->mkobj); + } +} +#endif + +void destroy_params(const struct kernel_param *params, unsigned num) +{ + unsigned int i; + + for (i = 0; i < num; i++) + if (params[i].ops->free) + params[i].ops->free(params[i].arg); +} + +static struct module_kobject * __init locate_module_kobject(const char *name) +{ + struct module_kobject *mk; + struct kobject *kobj; + int err; + + kobj = kset_find_obj(module_kset, name); + if (kobj) { + mk = to_module_kobject(kobj); + } else { + mk = kzalloc(sizeof(struct module_kobject), GFP_KERNEL); + BUG_ON(!mk); + + mk->mod = THIS_MODULE; + mk->kobj.kset = module_kset; + err = kobject_init_and_add(&mk->kobj, &module_ktype, NULL, + "%s", name); +#ifdef CONFIG_MODULES + if (!err) + err = sysfs_create_file(&mk->kobj, &module_uevent.attr); +#endif + if (err) { + kobject_put(&mk->kobj); + pr_crit("Adding module '%s' to sysfs failed (%d), the system may be unstable.\n", + name, err); + return NULL; + } + + /* So that we hold reference in both cases. */ + kobject_get(&mk->kobj); + } + + return mk; +} + +static void __init kernel_add_sysfs_param(const char *name, + const struct kernel_param *kparam, + unsigned int name_skip) +{ + struct module_kobject *mk; + int err; + + mk = locate_module_kobject(name); + if (!mk) + return; + + /* We need to remove old parameters before adding more. */ + if (mk->mp) + sysfs_remove_group(&mk->kobj, &mk->mp->grp); + + /* These should not fail at boot. */ + err = add_sysfs_param(mk, kparam, kparam->name + name_skip); + BUG_ON(err); + err = sysfs_create_group(&mk->kobj, &mk->mp->grp); + BUG_ON(err); + kobject_uevent(&mk->kobj, KOBJ_ADD); + kobject_put(&mk->kobj); +} + +/* + * param_sysfs_builtin - add sysfs parameters for built-in modules + * + * Add module_parameters to sysfs for "modules" built into the kernel. + * + * The "module" name (KBUILD_MODNAME) is stored before a dot, the + * "parameter" name is stored behind a dot in kernel_param->name. So, + * extract the "module" name for all built-in kernel_param-eters, + * and for all who have the same, call kernel_add_sysfs_param. + */ +static void __init param_sysfs_builtin(void) +{ + const struct kernel_param *kp; + unsigned int name_len; + char modname[MODULE_NAME_LEN]; + + for (kp = __start___param; kp < __stop___param; kp++) { + char *dot; + + if (kp->perm == 0) + continue; + + dot = strchr(kp->name, '.'); + if (!dot) { + /* This happens for core_param() */ + strcpy(modname, "kernel"); + name_len = 0; + } else { + name_len = dot - kp->name + 1; + strlcpy(modname, kp->name, name_len); + } + kernel_add_sysfs_param(modname, kp, name_len); + } +} + +ssize_t __modver_version_show(struct module_attribute *mattr, + struct module_kobject *mk, char *buf) +{ + struct module_version_attribute *vattr = + container_of(mattr, struct module_version_attribute, mattr); + + return scnprintf(buf, PAGE_SIZE, "%s\n", vattr->version); +} + +extern const struct module_version_attribute *__start___modver[]; +extern const struct module_version_attribute *__stop___modver[]; + +static void __init version_sysfs_builtin(void) +{ + const struct module_version_attribute **p; + struct module_kobject *mk; + int err; + + for (p = __start___modver; p < __stop___modver; p++) { + const struct module_version_attribute *vattr = *p; + + mk = locate_module_kobject(vattr->module_name); + if (mk) { + err = sysfs_create_file(&mk->kobj, &vattr->mattr.attr); + kobject_uevent(&mk->kobj, KOBJ_ADD); + kobject_put(&mk->kobj); + } + } +} + +/* module-related sysfs stuff */ + +static ssize_t module_attr_show(struct kobject *kobj, + struct attribute *attr, + char *buf) +{ + struct module_attribute *attribute; + struct module_kobject *mk; + int ret; + + attribute = to_module_attr(attr); + mk = to_module_kobject(kobj); + + if (!attribute->show) + return -EIO; + + ret = attribute->show(attribute, mk, buf); + + return ret; +} + +static ssize_t module_attr_store(struct kobject *kobj, + struct attribute *attr, + const char *buf, size_t len) +{ + struct module_attribute *attribute; + struct module_kobject *mk; + int ret; + + attribute = to_module_attr(attr); + mk = to_module_kobject(kobj); + + if (!attribute->store) + return -EIO; + + ret = attribute->store(attribute, mk, buf, len); + + return ret; +} + +static const struct sysfs_ops module_sysfs_ops = { + .show = module_attr_show, + .store = module_attr_store, +}; + +static int uevent_filter(struct kset *kset, struct kobject *kobj) +{ + struct kobj_type *ktype = get_ktype(kobj); + + if (ktype == &module_ktype) + return 1; + return 0; +} + +static const struct kset_uevent_ops module_uevent_ops = { + .filter = uevent_filter, +}; + +struct kset *module_kset; +int module_sysfs_initialized; + +static void module_kobj_release(struct kobject *kobj) +{ + struct module_kobject *mk = to_module_kobject(kobj); + complete(mk->kobj_completion); +} + +struct kobj_type module_ktype = { + .release = module_kobj_release, + .sysfs_ops = &module_sysfs_ops, +}; + +/* + * param_sysfs_init - wrapper for built-in params support + */ +static int __init param_sysfs_init(void) +{ + module_kset = kset_create_and_add("module", &module_uevent_ops, NULL); + if (!module_kset) { + printk(KERN_WARNING "%s (%d): error creating kset\n", + __FILE__, __LINE__); + return -ENOMEM; + } + module_sysfs_initialized = 1; + + version_sysfs_builtin(); + param_sysfs_builtin(); + + return 0; +} +subsys_initcall(param_sysfs_init); + +#endif /* CONFIG_SYSFS */ diff --git a/kernel/kernel/pid.c b/kernel/kernel/pid.c new file mode 100644 index 000000000..4fd07d5b7 --- /dev/null +++ b/kernel/kernel/pid.c @@ -0,0 +1,609 @@ +/* + * Generic pidhash and scalable, time-bounded PID allocator + * + * (C) 2002-2003 Nadia Yvette Chambers, IBM + * (C) 2004 Nadia Yvette Chambers, Oracle + * (C) 2002-2004 Ingo Molnar, Red Hat + * + * pid-structures are backing objects for tasks sharing a given ID to chain + * against. There is very little to them aside from hashing them and + * parking tasks using given ID's on a list. + * + * The hash is always changed with the tasklist_lock write-acquired, + * and the hash is only accessed with the tasklist_lock at least + * read-acquired, so there's no additional SMP locking needed here. + * + * We have a list of bitmap pages, which bitmaps represent the PID space. + * Allocating and freeing PIDs is completely lockless. The worst-case + * allocation scenario when all but one out of 1 million PIDs possible are + * allocated already: the scanning of 32 list entries and at most PAGE_SIZE + * bytes. The typical fastpath is a single successful setbit. Freeing is O(1). + * + * Pid namespaces: + * (C) 2007 Pavel Emelyanov , OpenVZ, SWsoft Inc. + * (C) 2007 Sukadev Bhattiprolu , IBM + * Many thanks to Oleg Nesterov for comments and help + * + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define pid_hashfn(nr, ns) \ + hash_long((unsigned long)nr + (unsigned long)ns, pidhash_shift) +static struct hlist_head *pid_hash; +static unsigned int pidhash_shift = 4; +struct pid init_struct_pid = INIT_STRUCT_PID; + +int pid_max = PID_MAX_DEFAULT; + +#define RESERVED_PIDS 300 + +int pid_max_min = RESERVED_PIDS + 1; +int pid_max_max = PID_MAX_LIMIT; + +static inline int mk_pid(struct pid_namespace *pid_ns, + struct pidmap *map, int off) +{ + return (map - pid_ns->pidmap)*BITS_PER_PAGE + off; +} + +#define find_next_offset(map, off) \ + find_next_zero_bit((map)->page, BITS_PER_PAGE, off) + +/* + * PID-map pages start out as NULL, they get allocated upon + * first use and are never deallocated. This way a low pid_max + * value does not cause lots of bitmaps to be allocated, but + * the scheme scales to up to 4 million PIDs, runtime. + */ +struct pid_namespace init_pid_ns = { + .kref = { + .refcount = ATOMIC_INIT(2), + }, + .pidmap = { + [ 0 ... PIDMAP_ENTRIES-1] = { ATOMIC_INIT(BITS_PER_PAGE), NULL } + }, + .last_pid = 0, + .nr_hashed = PIDNS_HASH_ADDING, + .level = 0, + .child_reaper = &init_task, + .user_ns = &init_user_ns, + .ns.inum = PROC_PID_INIT_INO, +#ifdef CONFIG_PID_NS + .ns.ops = &pidns_operations, +#endif +}; +EXPORT_SYMBOL_GPL(init_pid_ns); + +/* + * Note: disable interrupts while the pidmap_lock is held as an + * interrupt might come in and do read_lock(&tasklist_lock). + * + * If we don't disable interrupts there is a nasty deadlock between + * detach_pid()->free_pid() and another cpu that does + * spin_lock(&pidmap_lock) followed by an interrupt routine that does + * read_lock(&tasklist_lock); + * + * After we clean up the tasklist_lock and know there are no + * irq handlers that take it we can leave the interrupts enabled. + * For now it is easier to be safe than to prove it can't happen. + */ + +static __cacheline_aligned_in_smp DEFINE_SPINLOCK(pidmap_lock); + +static void free_pidmap(struct upid *upid) +{ + int nr = upid->nr; + struct pidmap *map = upid->ns->pidmap + nr / BITS_PER_PAGE; + int offset = nr & BITS_PER_PAGE_MASK; + + clear_bit(offset, map->page); + atomic_inc(&map->nr_free); +} + +/* + * If we started walking pids at 'base', is 'a' seen before 'b'? + */ +static int pid_before(int base, int a, int b) +{ + /* + * This is the same as saying + * + * (a - base + MAXUINT) % MAXUINT < (b - base + MAXUINT) % MAXUINT + * and that mapping orders 'a' and 'b' with respect to 'base'. + */ + return (unsigned)(a - base) < (unsigned)(b - base); +} + +/* + * We might be racing with someone else trying to set pid_ns->last_pid + * at the pid allocation time (there's also a sysctl for this, but racing + * with this one is OK, see comment in kernel/pid_namespace.c about it). + * We want the winner to have the "later" value, because if the + * "earlier" value prevails, then a pid may get reused immediately. + * + * Since pids rollover, it is not sufficient to just pick the bigger + * value. We have to consider where we started counting from. + * + * 'base' is the value of pid_ns->last_pid that we observed when + * we started looking for a pid. + * + * 'pid' is the pid that we eventually found. + */ +static void set_last_pid(struct pid_namespace *pid_ns, int base, int pid) +{ + int prev; + int last_write = base; + do { + prev = last_write; + last_write = cmpxchg(&pid_ns->last_pid, prev, pid); + } while ((prev != last_write) && (pid_before(base, last_write, pid))); +} + +static int alloc_pidmap(struct pid_namespace *pid_ns) +{ + int i, offset, max_scan, pid, last = pid_ns->last_pid; + struct pidmap *map; + + pid = last + 1; + if (pid >= pid_max) + pid = RESERVED_PIDS; + offset = pid & BITS_PER_PAGE_MASK; + map = &pid_ns->pidmap[pid/BITS_PER_PAGE]; + /* + * If last_pid points into the middle of the map->page we + * want to scan this bitmap block twice, the second time + * we start with offset == 0 (or RESERVED_PIDS). + */ + max_scan = DIV_ROUND_UP(pid_max, BITS_PER_PAGE) - !offset; + for (i = 0; i <= max_scan; ++i) { + if (unlikely(!map->page)) { + void *page = kzalloc(PAGE_SIZE, GFP_KERNEL); + /* + * Free the page if someone raced with us + * installing it: + */ + spin_lock_irq(&pidmap_lock); + if (!map->page) { + map->page = page; + page = NULL; + } + spin_unlock_irq(&pidmap_lock); + kfree(page); + if (unlikely(!map->page)) + return -ENOMEM; + } + if (likely(atomic_read(&map->nr_free))) { + for ( ; ; ) { + if (!test_and_set_bit(offset, map->page)) { + atomic_dec(&map->nr_free); + set_last_pid(pid_ns, last, pid); + return pid; + } + offset = find_next_offset(map, offset); + if (offset >= BITS_PER_PAGE) + break; + pid = mk_pid(pid_ns, map, offset); + if (pid >= pid_max) + break; + } + } + if (map < &pid_ns->pidmap[(pid_max-1)/BITS_PER_PAGE]) { + ++map; + offset = 0; + } else { + map = &pid_ns->pidmap[0]; + offset = RESERVED_PIDS; + if (unlikely(last == offset)) + break; + } + pid = mk_pid(pid_ns, map, offset); + } + return -EAGAIN; +} + +int next_pidmap(struct pid_namespace *pid_ns, unsigned int last) +{ + int offset; + struct pidmap *map, *end; + + if (last >= PID_MAX_LIMIT) + return -1; + + offset = (last + 1) & BITS_PER_PAGE_MASK; + map = &pid_ns->pidmap[(last + 1)/BITS_PER_PAGE]; + end = &pid_ns->pidmap[PIDMAP_ENTRIES]; + for (; map < end; map++, offset = 0) { + if (unlikely(!map->page)) + continue; + offset = find_next_bit((map)->page, BITS_PER_PAGE, offset); + if (offset < BITS_PER_PAGE) + return mk_pid(pid_ns, map, offset); + } + return -1; +} + +void put_pid(struct pid *pid) +{ + struct pid_namespace *ns; + + if (!pid) + return; + + ns = pid->numbers[pid->level].ns; + if ((atomic_read(&pid->count) == 1) || + atomic_dec_and_test(&pid->count)) { + kmem_cache_free(ns->pid_cachep, pid); + put_pid_ns(ns); + } +} +EXPORT_SYMBOL_GPL(put_pid); + +static void delayed_put_pid(struct rcu_head *rhp) +{ + struct pid *pid = container_of(rhp, struct pid, rcu); + put_pid(pid); +} + +void free_pid(struct pid *pid) +{ + /* We can be called with write_lock_irq(&tasklist_lock) held */ + int i; + unsigned long flags; + + spin_lock_irqsave(&pidmap_lock, flags); + for (i = 0; i <= pid->level; i++) { + struct upid *upid = pid->numbers + i; + struct pid_namespace *ns = upid->ns; + hlist_del_rcu(&upid->pid_chain); + switch(--ns->nr_hashed) { + case 2: + case 1: + /* When all that is left in the pid namespace + * is the reaper wake up the reaper. The reaper + * may be sleeping in zap_pid_ns_processes(). + */ + wake_up_process(ns->child_reaper); + break; + case PIDNS_HASH_ADDING: + /* Handle a fork failure of the first process */ + WARN_ON(ns->child_reaper); + ns->nr_hashed = 0; + /* fall through */ + case 0: + schedule_work(&ns->proc_work); + break; + } + } + spin_unlock_irqrestore(&pidmap_lock, flags); + + for (i = 0; i <= pid->level; i++) + free_pidmap(pid->numbers + i); + + call_rcu(&pid->rcu, delayed_put_pid); +} + +struct pid *alloc_pid(struct pid_namespace *ns) +{ + struct pid *pid; + enum pid_type type; + int i, nr; + struct pid_namespace *tmp; + struct upid *upid; + int retval = -ENOMEM; + + pid = kmem_cache_alloc(ns->pid_cachep, GFP_KERNEL); + if (!pid) + return ERR_PTR(retval); + + tmp = ns; + pid->level = ns->level; + for (i = ns->level; i >= 0; i--) { + nr = alloc_pidmap(tmp); + if (IS_ERR_VALUE(nr)) { + retval = nr; + goto out_free; + } + + pid->numbers[i].nr = nr; + pid->numbers[i].ns = tmp; + tmp = tmp->parent; + } + + if (unlikely(is_child_reaper(pid))) { + if (pid_ns_prepare_proc(ns)) + goto out_free; + } + + get_pid_ns(ns); + atomic_set(&pid->count, 1); + for (type = 0; type < PIDTYPE_MAX; ++type) + INIT_HLIST_HEAD(&pid->tasks[type]); + + upid = pid->numbers + ns->level; + spin_lock_irq(&pidmap_lock); + if (!(ns->nr_hashed & PIDNS_HASH_ADDING)) + goto out_unlock; + for ( ; upid >= pid->numbers; --upid) { + hlist_add_head_rcu(&upid->pid_chain, + &pid_hash[pid_hashfn(upid->nr, upid->ns)]); + upid->ns->nr_hashed++; + } + spin_unlock_irq(&pidmap_lock); + + return pid; + +out_unlock: + spin_unlock_irq(&pidmap_lock); + put_pid_ns(ns); + +out_free: + while (++i <= ns->level) + free_pidmap(pid->numbers + i); + + kmem_cache_free(ns->pid_cachep, pid); + return ERR_PTR(retval); +} + +void disable_pid_allocation(struct pid_namespace *ns) +{ + spin_lock_irq(&pidmap_lock); + ns->nr_hashed &= ~PIDNS_HASH_ADDING; + spin_unlock_irq(&pidmap_lock); +} + +struct pid *find_pid_ns(int nr, struct pid_namespace *ns) +{ + struct upid *pnr; + + hlist_for_each_entry_rcu(pnr, + &pid_hash[pid_hashfn(nr, ns)], pid_chain) + if (pnr->nr == nr && pnr->ns == ns) + return container_of(pnr, struct pid, + numbers[ns->level]); + + return NULL; +} +EXPORT_SYMBOL_GPL(find_pid_ns); + +struct pid *find_vpid(int nr) +{ + return find_pid_ns(nr, task_active_pid_ns(current)); +} +EXPORT_SYMBOL_GPL(find_vpid); + +/* + * attach_pid() must be called with the tasklist_lock write-held. + */ +void attach_pid(struct task_struct *task, enum pid_type type) +{ + struct pid_link *link = &task->pids[type]; + hlist_add_head_rcu(&link->node, &link->pid->tasks[type]); +} + +static void __change_pid(struct task_struct *task, enum pid_type type, + struct pid *new) +{ + struct pid_link *link; + struct pid *pid; + int tmp; + + link = &task->pids[type]; + pid = link->pid; + + hlist_del_rcu(&link->node); + link->pid = new; + + for (tmp = PIDTYPE_MAX; --tmp >= 0; ) + if (!hlist_empty(&pid->tasks[tmp])) + return; + + free_pid(pid); +} + +void detach_pid(struct task_struct *task, enum pid_type type) +{ + __change_pid(task, type, NULL); +} + +void change_pid(struct task_struct *task, enum pid_type type, + struct pid *pid) +{ + __change_pid(task, type, pid); + attach_pid(task, type); +} + +/* transfer_pid is an optimization of attach_pid(new), detach_pid(old) */ +void transfer_pid(struct task_struct *old, struct task_struct *new, + enum pid_type type) +{ + new->pids[type].pid = old->pids[type].pid; + hlist_replace_rcu(&old->pids[type].node, &new->pids[type].node); +} + +struct task_struct *pid_task(struct pid *pid, enum pid_type type) +{ + struct task_struct *result = NULL; + if (pid) { + struct hlist_node *first; + first = rcu_dereference_check(hlist_first_rcu(&pid->tasks[type]), + lockdep_tasklist_lock_is_held()); + if (first) + result = hlist_entry(first, struct task_struct, pids[(type)].node); + } + return result; +} +EXPORT_SYMBOL(pid_task); + +/* + * Must be called under rcu_read_lock(). + */ +struct task_struct *find_task_by_pid_ns(pid_t nr, struct pid_namespace *ns) +{ + rcu_lockdep_assert(rcu_read_lock_held(), + "find_task_by_pid_ns() needs rcu_read_lock()" + " protection"); + return pid_task(find_pid_ns(nr, ns), PIDTYPE_PID); +} + +struct task_struct *find_task_by_vpid(pid_t vnr) +{ + return find_task_by_pid_ns(vnr, task_active_pid_ns(current)); +} + +struct pid *get_task_pid(struct task_struct *task, enum pid_type type) +{ + struct pid *pid; + rcu_read_lock(); + if (type != PIDTYPE_PID) + task = task->group_leader; + pid = get_pid(task->pids[type].pid); + rcu_read_unlock(); + return pid; +} +EXPORT_SYMBOL_GPL(get_task_pid); + +struct task_struct *get_pid_task(struct pid *pid, enum pid_type type) +{ + struct task_struct *result; + rcu_read_lock(); + result = pid_task(pid, type); + if (result) + get_task_struct(result); + rcu_read_unlock(); + return result; +} +EXPORT_SYMBOL_GPL(get_pid_task); + +struct pid *find_get_pid(pid_t nr) +{ + struct pid *pid; + + rcu_read_lock(); + pid = get_pid(find_vpid(nr)); + rcu_read_unlock(); + + return pid; +} +EXPORT_SYMBOL_GPL(find_get_pid); + +pid_t pid_nr_ns(struct pid *pid, struct pid_namespace *ns) +{ + struct upid *upid; + pid_t nr = 0; + + if (pid && ns->level <= pid->level) { + upid = &pid->numbers[ns->level]; + if (upid->ns == ns) + nr = upid->nr; + } + return nr; +} +EXPORT_SYMBOL_GPL(pid_nr_ns); + +pid_t pid_vnr(struct pid *pid) +{ + return pid_nr_ns(pid, task_active_pid_ns(current)); +} +EXPORT_SYMBOL_GPL(pid_vnr); + +pid_t __task_pid_nr_ns(struct task_struct *task, enum pid_type type, + struct pid_namespace *ns) +{ + pid_t nr = 0; + + rcu_read_lock(); + if (!ns) + ns = task_active_pid_ns(current); + if (likely(pid_alive(task))) { + if (type != PIDTYPE_PID) + task = task->group_leader; + nr = pid_nr_ns(task->pids[type].pid, ns); + } + rcu_read_unlock(); + + return nr; +} +EXPORT_SYMBOL(__task_pid_nr_ns); + +pid_t task_tgid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns) +{ + return pid_nr_ns(task_tgid(tsk), ns); +} +EXPORT_SYMBOL(task_tgid_nr_ns); + +struct pid_namespace *task_active_pid_ns(struct task_struct *tsk) +{ + return ns_of_pid(task_pid(tsk)); +} +EXPORT_SYMBOL_GPL(task_active_pid_ns); + +/* + * Used by proc to find the first pid that is greater than or equal to nr. + * + * If there is a pid at nr this function is exactly the same as find_pid_ns. + */ +struct pid *find_ge_pid(int nr, struct pid_namespace *ns) +{ + struct pid *pid; + + do { + pid = find_pid_ns(nr, ns); + if (pid) + break; + nr = next_pidmap(ns, nr); + } while (nr > 0); + + return pid; +} + +/* + * The pid hash table is scaled according to the amount of memory in the + * machine. From a minimum of 16 slots up to 4096 slots at one gigabyte or + * more. + */ +void __init pidhash_init(void) +{ + unsigned int i, pidhash_size; + + pid_hash = alloc_large_system_hash("PID", sizeof(*pid_hash), 0, 18, + HASH_EARLY | HASH_SMALL, + &pidhash_shift, NULL, + 0, 4096); + pidhash_size = 1U << pidhash_shift; + + for (i = 0; i < pidhash_size; i++) + INIT_HLIST_HEAD(&pid_hash[i]); +} + +void __init pidmap_init(void) +{ + /* Veryify no one has done anything silly */ + BUILD_BUG_ON(PID_MAX_LIMIT >= PIDNS_HASH_ADDING); + + /* bump default and minimum pid_max based on number of cpus */ + pid_max = min(pid_max_max, max_t(int, pid_max, + PIDS_PER_CPU_DEFAULT * num_possible_cpus())); + pid_max_min = max_t(int, pid_max_min, + PIDS_PER_CPU_MIN * num_possible_cpus()); + pr_info("pid_max: default: %u minimum: %u\n", pid_max, pid_max_min); + + init_pid_ns.pidmap[0].page = kzalloc(PAGE_SIZE, GFP_KERNEL); + /* Reserve PID 0. We never call free_pidmap(0) */ + set_bit(0, init_pid_ns.pidmap[0].page); + atomic_dec(&init_pid_ns.pidmap[0].nr_free); + + init_pid_ns.pid_cachep = KMEM_CACHE(pid, + SLAB_HWCACHE_ALIGN | SLAB_PANIC); +} diff --git a/kernel/kernel/pid_namespace.c b/kernel/kernel/pid_namespace.c new file mode 100644 index 000000000..a65ba137f --- /dev/null +++ b/kernel/kernel/pid_namespace.c @@ -0,0 +1,409 @@ +/* + * Pid namespaces + * + * Authors: + * (C) 2007 Pavel Emelyanov , OpenVZ, SWsoft Inc. + * (C) 2007 Sukadev Bhattiprolu , IBM + * Many thanks to Oleg Nesterov for comments and help + * + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +struct pid_cache { + int nr_ids; + char name[16]; + struct kmem_cache *cachep; + struct list_head list; +}; + +static LIST_HEAD(pid_caches_lh); +static DEFINE_MUTEX(pid_caches_mutex); +static struct kmem_cache *pid_ns_cachep; + +/* + * creates the kmem cache to allocate pids from. + * @nr_ids: the number of numerical ids this pid will have to carry + */ + +static struct kmem_cache *create_pid_cachep(int nr_ids) +{ + struct pid_cache *pcache; + struct kmem_cache *cachep; + + mutex_lock(&pid_caches_mutex); + list_for_each_entry(pcache, &pid_caches_lh, list) + if (pcache->nr_ids == nr_ids) + goto out; + + pcache = kmalloc(sizeof(struct pid_cache), GFP_KERNEL); + if (pcache == NULL) + goto err_alloc; + + snprintf(pcache->name, sizeof(pcache->name), "pid_%d", nr_ids); + cachep = kmem_cache_create(pcache->name, + sizeof(struct pid) + (nr_ids - 1) * sizeof(struct upid), + 0, SLAB_HWCACHE_ALIGN, NULL); + if (cachep == NULL) + goto err_cachep; + + pcache->nr_ids = nr_ids; + pcache->cachep = cachep; + list_add(&pcache->list, &pid_caches_lh); +out: + mutex_unlock(&pid_caches_mutex); + return pcache->cachep; + +err_cachep: + kfree(pcache); +err_alloc: + mutex_unlock(&pid_caches_mutex); + return NULL; +} + +static void proc_cleanup_work(struct work_struct *work) +{ + struct pid_namespace *ns = container_of(work, struct pid_namespace, proc_work); + pid_ns_release_proc(ns); +} + +/* MAX_PID_NS_LEVEL is needed for limiting size of 'struct pid' */ +#define MAX_PID_NS_LEVEL 32 + +static struct pid_namespace *create_pid_namespace(struct user_namespace *user_ns, + struct pid_namespace *parent_pid_ns) +{ + struct pid_namespace *ns; + unsigned int level = parent_pid_ns->level + 1; + int i; + int err; + + if (level > MAX_PID_NS_LEVEL) { + err = -EINVAL; + goto out; + } + + err = -ENOMEM; + ns = kmem_cache_zalloc(pid_ns_cachep, GFP_KERNEL); + if (ns == NULL) + goto out; + + ns->pidmap[0].page = kzalloc(PAGE_SIZE, GFP_KERNEL); + if (!ns->pidmap[0].page) + goto out_free; + + ns->pid_cachep = create_pid_cachep(level + 1); + if (ns->pid_cachep == NULL) + goto out_free_map; + + err = ns_alloc_inum(&ns->ns); + if (err) + goto out_free_map; + ns->ns.ops = &pidns_operations; + + kref_init(&ns->kref); + ns->level = level; + ns->parent = get_pid_ns(parent_pid_ns); + ns->user_ns = get_user_ns(user_ns); + ns->nr_hashed = PIDNS_HASH_ADDING; + INIT_WORK(&ns->proc_work, proc_cleanup_work); + + set_bit(0, ns->pidmap[0].page); + atomic_set(&ns->pidmap[0].nr_free, BITS_PER_PAGE - 1); + + for (i = 1; i < PIDMAP_ENTRIES; i++) + atomic_set(&ns->pidmap[i].nr_free, BITS_PER_PAGE); + + return ns; + +out_free_map: + kfree(ns->pidmap[0].page); +out_free: + kmem_cache_free(pid_ns_cachep, ns); +out: + return ERR_PTR(err); +} + +static void delayed_free_pidns(struct rcu_head *p) +{ + kmem_cache_free(pid_ns_cachep, + container_of(p, struct pid_namespace, rcu)); +} + +static void destroy_pid_namespace(struct pid_namespace *ns) +{ + int i; + + ns_free_inum(&ns->ns); + for (i = 0; i < PIDMAP_ENTRIES; i++) + kfree(ns->pidmap[i].page); + put_user_ns(ns->user_ns); + call_rcu(&ns->rcu, delayed_free_pidns); +} + +struct pid_namespace *copy_pid_ns(unsigned long flags, + struct user_namespace *user_ns, struct pid_namespace *old_ns) +{ + if (!(flags & CLONE_NEWPID)) + return get_pid_ns(old_ns); + if (task_active_pid_ns(current) != old_ns) + return ERR_PTR(-EINVAL); + return create_pid_namespace(user_ns, old_ns); +} + +static void free_pid_ns(struct kref *kref) +{ + struct pid_namespace *ns; + + ns = container_of(kref, struct pid_namespace, kref); + destroy_pid_namespace(ns); +} + +void put_pid_ns(struct pid_namespace *ns) +{ + struct pid_namespace *parent; + + while (ns != &init_pid_ns) { + parent = ns->parent; + if (!kref_put(&ns->kref, free_pid_ns)) + break; + ns = parent; + } +} +EXPORT_SYMBOL_GPL(put_pid_ns); + +void zap_pid_ns_processes(struct pid_namespace *pid_ns) +{ + int nr; + int rc; + struct task_struct *task, *me = current; + int init_pids = thread_group_leader(me) ? 1 : 2; + + /* Don't allow any more processes into the pid namespace */ + disable_pid_allocation(pid_ns); + + /* + * Ignore SIGCHLD causing any terminated children to autoreap. + * This speeds up the namespace shutdown, plus see the comment + * below. + */ + spin_lock_irq(&me->sighand->siglock); + me->sighand->action[SIGCHLD - 1].sa.sa_handler = SIG_IGN; + spin_unlock_irq(&me->sighand->siglock); + + /* + * The last thread in the cgroup-init thread group is terminating. + * Find remaining pid_ts in the namespace, signal and wait for them + * to exit. + * + * Note: This signals each threads in the namespace - even those that + * belong to the same thread group, To avoid this, we would have + * to walk the entire tasklist looking a processes in this + * namespace, but that could be unnecessarily expensive if the + * pid namespace has just a few processes. Or we need to + * maintain a tasklist for each pid namespace. + * + */ + read_lock(&tasklist_lock); + nr = next_pidmap(pid_ns, 1); + while (nr > 0) { + rcu_read_lock(); + + task = pid_task(find_vpid(nr), PIDTYPE_PID); + if (task && !__fatal_signal_pending(task)) + send_sig_info(SIGKILL, SEND_SIG_FORCED, task); + + rcu_read_unlock(); + + nr = next_pidmap(pid_ns, nr); + } + read_unlock(&tasklist_lock); + + /* + * Reap the EXIT_ZOMBIE children we had before we ignored SIGCHLD. + * sys_wait4() will also block until our children traced from the + * parent namespace are detached and become EXIT_DEAD. + */ + do { + clear_thread_flag(TIF_SIGPENDING); + rc = sys_wait4(-1, NULL, __WALL, NULL); + } while (rc != -ECHILD); + + /* + * sys_wait4() above can't reap the EXIT_DEAD children but we do not + * really care, we could reparent them to the global init. We could + * exit and reap ->child_reaper even if it is not the last thread in + * this pid_ns, free_pid(nr_hashed == 0) calls proc_cleanup_work(), + * pid_ns can not go away until proc_kill_sb() drops the reference. + * + * But this ns can also have other tasks injected by setns()+fork(). + * Again, ignoring the user visible semantics we do not really need + * to wait until they are all reaped, but they can be reparented to + * us and thus we need to ensure that pid->child_reaper stays valid + * until they all go away. See free_pid()->wake_up_process(). + * + * We rely on ignored SIGCHLD, an injected zombie must be autoreaped + * if reparented. + */ + for (;;) { + set_current_state(TASK_UNINTERRUPTIBLE); + if (pid_ns->nr_hashed == init_pids) + break; + schedule(); + } + __set_current_state(TASK_RUNNING); + + if (pid_ns->reboot) + current->signal->group_exit_code = pid_ns->reboot; + + acct_exit_ns(pid_ns); + return; +} + +#ifdef CONFIG_CHECKPOINT_RESTORE +static int pid_ns_ctl_handler(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + struct pid_namespace *pid_ns = task_active_pid_ns(current); + struct ctl_table tmp = *table; + + if (write && !ns_capable(pid_ns->user_ns, CAP_SYS_ADMIN)) + return -EPERM; + + /* + * Writing directly to ns' last_pid field is OK, since this field + * is volatile in a living namespace anyway and a code writing to + * it should synchronize its usage with external means. + */ + + tmp.data = &pid_ns->last_pid; + return proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos); +} + +extern int pid_max; +static int zero = 0; +static struct ctl_table pid_ns_ctl_table[] = { + { + .procname = "ns_last_pid", + .maxlen = sizeof(int), + .mode = 0666, /* permissions are checked in the handler */ + .proc_handler = pid_ns_ctl_handler, + .extra1 = &zero, + .extra2 = &pid_max, + }, + { } +}; +static struct ctl_path kern_path[] = { { .procname = "kernel", }, { } }; +#endif /* CONFIG_CHECKPOINT_RESTORE */ + +int reboot_pid_ns(struct pid_namespace *pid_ns, int cmd) +{ + if (pid_ns == &init_pid_ns) + return 0; + + switch (cmd) { + case LINUX_REBOOT_CMD_RESTART2: + case LINUX_REBOOT_CMD_RESTART: + pid_ns->reboot = SIGHUP; + break; + + case LINUX_REBOOT_CMD_POWER_OFF: + case LINUX_REBOOT_CMD_HALT: + pid_ns->reboot = SIGINT; + break; + default: + return -EINVAL; + } + + read_lock(&tasklist_lock); + force_sig(SIGKILL, pid_ns->child_reaper); + read_unlock(&tasklist_lock); + + do_exit(0); + + /* Not reached */ + return 0; +} + +static inline struct pid_namespace *to_pid_ns(struct ns_common *ns) +{ + return container_of(ns, struct pid_namespace, ns); +} + +static struct ns_common *pidns_get(struct task_struct *task) +{ + struct pid_namespace *ns; + + rcu_read_lock(); + ns = task_active_pid_ns(task); + if (ns) + get_pid_ns(ns); + rcu_read_unlock(); + + return ns ? &ns->ns : NULL; +} + +static void pidns_put(struct ns_common *ns) +{ + put_pid_ns(to_pid_ns(ns)); +} + +static int pidns_install(struct nsproxy *nsproxy, struct ns_common *ns) +{ + struct pid_namespace *active = task_active_pid_ns(current); + struct pid_namespace *ancestor, *new = to_pid_ns(ns); + + if (!ns_capable(new->user_ns, CAP_SYS_ADMIN) || + !ns_capable(current_user_ns(), CAP_SYS_ADMIN)) + return -EPERM; + + /* + * Only allow entering the current active pid namespace + * or a child of the current active pid namespace. + * + * This is required for fork to return a usable pid value and + * this maintains the property that processes and their + * children can not escape their current pid namespace. + */ + if (new->level < active->level) + return -EINVAL; + + ancestor = new; + while (ancestor->level > active->level) + ancestor = ancestor->parent; + if (ancestor != active) + return -EINVAL; + + put_pid_ns(nsproxy->pid_ns_for_children); + nsproxy->pid_ns_for_children = get_pid_ns(new); + return 0; +} + +const struct proc_ns_operations pidns_operations = { + .name = "pid", + .type = CLONE_NEWPID, + .get = pidns_get, + .put = pidns_put, + .install = pidns_install, +}; + +static __init int pid_namespaces_init(void) +{ + pid_ns_cachep = KMEM_CACHE(pid_namespace, SLAB_PANIC); + +#ifdef CONFIG_CHECKPOINT_RESTORE + register_sysctl_paths(kern_path, pid_ns_ctl_table); +#endif + return 0; +} + +__initcall(pid_namespaces_init); diff --git a/kernel/kernel/power/Kconfig b/kernel/kernel/power/Kconfig new file mode 100644 index 000000000..7e01f78f0 --- /dev/null +++ b/kernel/kernel/power/Kconfig @@ -0,0 +1,303 @@ +config SUSPEND + bool "Suspend to RAM and standby" + depends on ARCH_SUSPEND_POSSIBLE + default y + ---help--- + Allow the system to enter sleep states in which main memory is + powered and thus its contents are preserved, such as the + suspend-to-RAM state (e.g. the ACPI S3 state). + +config SUSPEND_FREEZER + bool "Enable freezer for suspend to RAM/standby" \ + if ARCH_WANTS_FREEZER_CONTROL || BROKEN + depends on SUSPEND + default y + help + This allows you to turn off the freezer for suspend. If this is + done, no tasks are frozen for suspend to RAM/standby. + + Turning OFF this setting is NOT recommended! If in doubt, say Y. + +config HIBERNATE_CALLBACKS + bool + +config HIBERNATION + bool "Hibernation (aka 'suspend to disk')" + depends on SWAP && ARCH_HIBERNATION_POSSIBLE + select HIBERNATE_CALLBACKS + select LZO_COMPRESS + select LZO_DECOMPRESS + select CRC32 + ---help--- + Enable the suspend to disk (STD) functionality, which is usually + called "hibernation" in user interfaces. STD checkpoints the + system and powers it off; and restores that checkpoint on reboot. + + You can suspend your machine with 'echo disk > /sys/power/state' + after placing resume=/dev/swappartition on the kernel command line + in your bootloader's configuration file. + + Alternatively, you can use the additional userland tools available + from . + + In principle it does not require ACPI or APM, although for example + ACPI will be used for the final steps when it is available. One + of the reasons to use software suspend is that the firmware hooks + for suspend states like suspend-to-RAM (STR) often don't work very + well with Linux. + + It creates an image which is saved in your active swap. Upon the next + boot, pass the 'resume=/dev/swappartition' argument to the kernel to + have it detect the saved image, restore memory state from it, and + continue to run as before. If you do not want the previous state to + be reloaded, then use the 'noresume' kernel command line argument. + Note, however, that fsck will be run on your filesystems and you will + need to run mkswap against the swap partition used for the suspend. + + It also works with swap files to a limited extent (for details see + ). + + Right now you may boot without resuming and resume later but in the + meantime you cannot use the swap partition(s)/file(s) involved in + suspending. Also in this case you must not use the filesystems + that were mounted before the suspend. In particular, you MUST NOT + MOUNT any journaled filesystems mounted before the suspend or they + will get corrupted in a nasty way. + + For more information take a look at . + +config ARCH_SAVE_PAGE_KEYS + bool + +config PM_STD_PARTITION + string "Default resume partition" + depends on HIBERNATION + default "" + ---help--- + The default resume partition is the partition that the suspend- + to-disk implementation will look for a suspended disk image. + + The partition specified here will be different for almost every user. + It should be a valid swap partition (at least for now) that is turned + on before suspending. + + The partition specified can be overridden by specifying: + + resume=/dev/ + + which will set the resume partition to the device specified. + + Note there is currently not a way to specify which device to save the + suspended image to. It will simply pick the first available swap + device. + +config PM_SLEEP + def_bool y + depends on SUSPEND || HIBERNATE_CALLBACKS + select PM + +config PM_SLEEP_SMP + def_bool y + depends on SMP + depends on ARCH_SUSPEND_POSSIBLE || ARCH_HIBERNATION_POSSIBLE + depends on PM_SLEEP + select HOTPLUG_CPU + +config PM_AUTOSLEEP + bool "Opportunistic sleep" + depends on PM_SLEEP + default n + ---help--- + Allow the kernel to trigger a system transition into a global sleep + state automatically whenever there are no active wakeup sources. + +config PM_WAKELOCKS + bool "User space wakeup sources interface" + depends on PM_SLEEP + default n + ---help--- + Allow user space to create, activate and deactivate wakeup source + objects with the help of a sysfs-based interface. + +config PM_WAKELOCKS_LIMIT + int "Maximum number of user space wakeup sources (0 = no limit)" + range 0 100000 + default 100 + depends on PM_WAKELOCKS + +config PM_WAKELOCKS_GC + bool "Garbage collector for user space wakeup sources" + depends on PM_WAKELOCKS + default y + +config PM + bool "Device power management core functionality" + ---help--- + Enable functionality allowing I/O devices to be put into energy-saving + (low power) states, for example after a specified period of inactivity + (autosuspended), and woken up in response to a hardware-generated + wake-up event or a driver's request. + + Hardware support is generally required for this functionality to work + and the bus type drivers of the buses the devices are on are + responsible for the actual handling of device suspend requests and + wake-up events. + +config PM_DEBUG + bool "Power Management Debug Support" + depends on PM + ---help--- + This option enables various debugging support in the Power Management + code. This is helpful when debugging and reporting PM bugs, like + suspend support. + +config PM_ADVANCED_DEBUG + bool "Extra PM attributes in sysfs for low-level debugging/testing" + depends on PM_DEBUG + ---help--- + Add extra sysfs attributes allowing one to access some Power Management + fields of device objects from user space. If you are not a kernel + developer interested in debugging/testing Power Management, say "no". + +config PM_TEST_SUSPEND + bool "Test suspend/resume and wakealarm during bootup" + depends on SUSPEND && PM_DEBUG && RTC_CLASS=y + ---help--- + This option will let you suspend your machine during bootup, and + make it wake up a few seconds later using an RTC wakeup alarm. + Enable this with a kernel parameter like "test_suspend=mem". + + You probably want to have your system's RTC driver statically + linked, ensuring that it's available when this test runs. + +config PM_SLEEP_DEBUG + def_bool y + depends on PM_DEBUG && PM_SLEEP + +config DPM_WATCHDOG + bool "Device suspend/resume watchdog" + depends on PM_DEBUG && PSTORE + ---help--- + Sets up a watchdog timer to capture drivers that are + locked up attempting to suspend/resume a device. + A detected lockup causes system panic with message + captured in pstore device for inspection in subsequent + boot session. + +config DPM_WATCHDOG_TIMEOUT + int "Watchdog timeout in seconds" + range 1 120 + default 12 + depends on DPM_WATCHDOG + +config PM_TRACE + bool + help + This enables code to save the last PM event point across + reboot. The architecture needs to support this, x86 for + example does by saving things in the RTC, see below. + + The architecture specific code must provide the extern + functions from as well as the + header with a TRACE_RESUME() macro. + + The way the information is presented is architecture- + dependent, x86 will print the information during a + late_initcall. + +config PM_TRACE_RTC + bool "Suspend/resume event tracing" + depends on PM_SLEEP_DEBUG + depends on X86 + select PM_TRACE + ---help--- + This enables some cheesy code to save the last PM event point in the + RTC across reboots, so that you can debug a machine that just hangs + during suspend (or more commonly, during resume). + + To use this debugging feature you should attempt to suspend the + machine, reboot it and then run + + dmesg -s 1000000 | grep 'hash matches' + + CAUTION: this option will cause your machine's real-time clock to be + set to an invalid time after a resume. + +config APM_EMULATION + tristate "Advanced Power Management Emulation" + depends on PM && SYS_SUPPORTS_APM_EMULATION + help + APM is a BIOS specification for saving power using several different + techniques. This is mostly useful for battery powered laptops with + APM compliant BIOSes. If you say Y here, the system time will be + reset after a RESUME operation, the /proc/apm device will provide + battery status information, and user-space programs will receive + notification of APM "events" (e.g. battery status change). + + In order to use APM, you will need supporting software. For location + and more information, read + and the Battery Powered Linux mini-HOWTO, available from + . + + This driver does not spin down disk drives (see the hdparm(8) + manpage ("man 8 hdparm") for that), and it doesn't turn off + VESA-compliant "green" monitors. + + Generally, if you don't have a battery in your machine, there isn't + much point in using this driver and you should say N. If you get + random kernel OOPSes or reboots that don't seem to be related to + anything, try disabling/enabling this option (or disabling/enabling + APM in your BIOS). + +config PM_OPP + bool + select SRCU + ---help--- + SOCs have a standard set of tuples consisting of frequency and + voltage pairs that the device will support per voltage domain. This + is called Operating Performance Point or OPP. The actual definitions + of OPP varies over silicon within the same family of devices. + + OPP layer organizes the data internally using device pointers + representing individual voltage domains and provides SOC + implementations a ready to use framework to manage OPPs. + For more information, read + +config PM_CLK + def_bool y + depends on PM && HAVE_CLK + +config PM_GENERIC_DOMAINS + bool + depends on PM + +config WQ_POWER_EFFICIENT_DEFAULT + bool "Enable workqueue power-efficient mode by default" + depends on PM + default n + help + Per-cpu workqueues are generally preferred because they show + better performance thanks to cache locality; unfortunately, + per-cpu workqueues tend to be more power hungry than unbound + workqueues. + + Enabling workqueue.power_efficient kernel parameter makes the + per-cpu workqueues which were observed to contribute + significantly to power consumption unbound, leading to measurably + lower power usage at the cost of small performance overhead. + + This config option determines whether workqueue.power_efficient + is enabled by default. + + If in doubt, say N. + +config PM_GENERIC_DOMAINS_SLEEP + def_bool y + depends on PM_SLEEP && PM_GENERIC_DOMAINS + +config PM_GENERIC_DOMAINS_OF + def_bool y + depends on PM_GENERIC_DOMAINS && OF + +config CPU_PM + bool diff --git a/kernel/kernel/power/Makefile b/kernel/kernel/power/Makefile new file mode 100644 index 000000000..29472bff1 --- /dev/null +++ b/kernel/kernel/power/Makefile @@ -0,0 +1,15 @@ + +ccflags-$(CONFIG_PM_DEBUG) := -DDEBUG + +obj-y += qos.o +obj-$(CONFIG_PM) += main.o +obj-$(CONFIG_VT_CONSOLE_SLEEP) += console.o +obj-$(CONFIG_FREEZER) += process.o +obj-$(CONFIG_SUSPEND) += suspend.o +obj-$(CONFIG_PM_TEST_SUSPEND) += suspend_test.o +obj-$(CONFIG_HIBERNATION) += hibernate.o snapshot.o swap.o user.o \ + block_io.o +obj-$(CONFIG_PM_AUTOSLEEP) += autosleep.o +obj-$(CONFIG_PM_WAKELOCKS) += wakelock.o + +obj-$(CONFIG_MAGIC_SYSRQ) += poweroff.o diff --git a/kernel/kernel/power/autosleep.c b/kernel/kernel/power/autosleep.c new file mode 100644 index 000000000..9012ecf7b --- /dev/null +++ b/kernel/kernel/power/autosleep.c @@ -0,0 +1,128 @@ +/* + * kernel/power/autosleep.c + * + * Opportunistic sleep support. + * + * Copyright (C) 2012 Rafael J. Wysocki + */ + +#include +#include +#include + +#include "power.h" + +static suspend_state_t autosleep_state; +static struct workqueue_struct *autosleep_wq; +/* + * Note: it is only safe to mutex_lock(&autosleep_lock) if a wakeup_source + * is active, otherwise a deadlock with try_to_suspend() is possible. + * Alternatively mutex_lock_interruptible() can be used. This will then fail + * if an auto_sleep cycle tries to freeze processes. + */ +static DEFINE_MUTEX(autosleep_lock); +static struct wakeup_source *autosleep_ws; + +static void try_to_suspend(struct work_struct *work) +{ + unsigned int initial_count, final_count; + + if (!pm_get_wakeup_count(&initial_count, true)) + goto out; + + mutex_lock(&autosleep_lock); + + if (!pm_save_wakeup_count(initial_count) || + system_state != SYSTEM_RUNNING) { + mutex_unlock(&autosleep_lock); + goto out; + } + + if (autosleep_state == PM_SUSPEND_ON) { + mutex_unlock(&autosleep_lock); + return; + } + if (autosleep_state >= PM_SUSPEND_MAX) + hibernate(); + else + pm_suspend(autosleep_state); + + mutex_unlock(&autosleep_lock); + + if (!pm_get_wakeup_count(&final_count, false)) + goto out; + + /* + * If the wakeup occured for an unknown reason, wait to prevent the + * system from trying to suspend and waking up in a tight loop. + */ + if (final_count == initial_count) + schedule_timeout_uninterruptible(HZ / 2); + + out: + queue_up_suspend_work(); +} + +static DECLARE_WORK(suspend_work, try_to_suspend); + +void queue_up_suspend_work(void) +{ + if (autosleep_state > PM_SUSPEND_ON) + queue_work(autosleep_wq, &suspend_work); +} + +suspend_state_t pm_autosleep_state(void) +{ + return autosleep_state; +} + +int pm_autosleep_lock(void) +{ + return mutex_lock_interruptible(&autosleep_lock); +} + +void pm_autosleep_unlock(void) +{ + mutex_unlock(&autosleep_lock); +} + +int pm_autosleep_set_state(suspend_state_t state) +{ + +#ifndef CONFIG_HIBERNATION + if (state >= PM_SUSPEND_MAX) + return -EINVAL; +#endif + + __pm_stay_awake(autosleep_ws); + + mutex_lock(&autosleep_lock); + + autosleep_state = state; + + __pm_relax(autosleep_ws); + + if (state > PM_SUSPEND_ON) { + pm_wakep_autosleep_enabled(true); + queue_up_suspend_work(); + } else { + pm_wakep_autosleep_enabled(false); + } + + mutex_unlock(&autosleep_lock); + return 0; +} + +int __init pm_autosleep_init(void) +{ + autosleep_ws = wakeup_source_register("autosleep"); + if (!autosleep_ws) + return -ENOMEM; + + autosleep_wq = alloc_ordered_workqueue("autosleep", 0); + if (autosleep_wq) + return 0; + + wakeup_source_unregister(autosleep_ws); + return -ENOMEM; +} diff --git a/kernel/kernel/power/block_io.c b/kernel/kernel/power/block_io.c new file mode 100644 index 000000000..9a58bc258 --- /dev/null +++ b/kernel/kernel/power/block_io.c @@ -0,0 +1,103 @@ +/* + * This file provides functions for block I/O operations on swap/file. + * + * Copyright (C) 1998,2001-2005 Pavel Machek + * Copyright (C) 2006 Rafael J. Wysocki + * + * This file is released under the GPLv2. + */ + +#include +#include +#include +#include + +#include "power.h" + +/** + * submit - submit BIO request. + * @rw: READ or WRITE. + * @off physical offset of page. + * @page: page we're reading or writing. + * @bio_chain: list of pending biod (for async reading) + * + * Straight from the textbook - allocate and initialize the bio. + * If we're reading, make sure the page is marked as dirty. + * Then submit it and, if @bio_chain == NULL, wait. + */ +static int submit(int rw, struct block_device *bdev, sector_t sector, + struct page *page, struct bio **bio_chain) +{ + const int bio_rw = rw | REQ_SYNC; + struct bio *bio; + + bio = bio_alloc(__GFP_WAIT | __GFP_HIGH, 1); + bio->bi_iter.bi_sector = sector; + bio->bi_bdev = bdev; + bio->bi_end_io = end_swap_bio_read; + + if (bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE) { + printk(KERN_ERR "PM: Adding page to bio failed at %llu\n", + (unsigned long long)sector); + bio_put(bio); + return -EFAULT; + } + + lock_page(page); + bio_get(bio); + + if (bio_chain == NULL) { + submit_bio(bio_rw, bio); + wait_on_page_locked(page); + if (rw == READ) + bio_set_pages_dirty(bio); + bio_put(bio); + } else { + if (rw == READ) + get_page(page); /* These pages are freed later */ + bio->bi_private = *bio_chain; + *bio_chain = bio; + submit_bio(bio_rw, bio); + } + return 0; +} + +int hib_bio_read_page(pgoff_t page_off, void *addr, struct bio **bio_chain) +{ + return submit(READ, hib_resume_bdev, page_off * (PAGE_SIZE >> 9), + virt_to_page(addr), bio_chain); +} + +int hib_bio_write_page(pgoff_t page_off, void *addr, struct bio **bio_chain) +{ + return submit(WRITE, hib_resume_bdev, page_off * (PAGE_SIZE >> 9), + virt_to_page(addr), bio_chain); +} + +int hib_wait_on_bio_chain(struct bio **bio_chain) +{ + struct bio *bio; + struct bio *next_bio; + int ret = 0; + + if (bio_chain == NULL) + return 0; + + bio = *bio_chain; + if (bio == NULL) + return 0; + while (bio) { + struct page *page; + + next_bio = bio->bi_private; + page = bio->bi_io_vec[0].bv_page; + wait_on_page_locked(page); + if (!PageUptodate(page) || PageError(page)) + ret = -EIO; + put_page(page); + bio_put(bio); + bio = next_bio; + } + *bio_chain = NULL; + return ret; +} diff --git a/kernel/kernel/power/console.c b/kernel/kernel/power/console.c new file mode 100644 index 000000000..aba9c545a --- /dev/null +++ b/kernel/kernel/power/console.c @@ -0,0 +1,151 @@ +/* + * Functions for saving/restoring console. + * + * Originally from swsusp. + */ + +#include +#include +#include +#include +#include +#include +#include "power.h" + +#define SUSPEND_CONSOLE (MAX_NR_CONSOLES-1) + +static int orig_fgconsole, orig_kmsg; + +static DEFINE_MUTEX(vt_switch_mutex); + +struct pm_vt_switch { + struct list_head head; + struct device *dev; + bool required; +}; + +static LIST_HEAD(pm_vt_switch_list); + + +/** + * pm_vt_switch_required - indicate VT switch at suspend requirements + * @dev: device + * @required: if true, caller needs VT switch at suspend/resume time + * + * The different console drivers may or may not require VT switches across + * suspend/resume, depending on how they handle restoring video state and + * what may be running. + * + * Drivers can indicate support for switchless suspend/resume, which can + * save time and flicker, by using this routine and passing 'false' as + * the argument. If any loaded driver needs VT switching, or the + * no_console_suspend argument has been passed on the command line, VT + * switches will occur. + */ +void pm_vt_switch_required(struct device *dev, bool required) +{ + struct pm_vt_switch *entry, *tmp; + + mutex_lock(&vt_switch_mutex); + list_for_each_entry(tmp, &pm_vt_switch_list, head) { + if (tmp->dev == dev) { + /* already registered, update requirement */ + tmp->required = required; + goto out; + } + } + + entry = kmalloc(sizeof(*entry), GFP_KERNEL); + if (!entry) + goto out; + + entry->required = required; + entry->dev = dev; + + list_add(&entry->head, &pm_vt_switch_list); +out: + mutex_unlock(&vt_switch_mutex); +} +EXPORT_SYMBOL(pm_vt_switch_required); + +/** + * pm_vt_switch_unregister - stop tracking a device's VT switching needs + * @dev: device + * + * Remove @dev from the vt switch list. + */ +void pm_vt_switch_unregister(struct device *dev) +{ + struct pm_vt_switch *tmp; + + mutex_lock(&vt_switch_mutex); + list_for_each_entry(tmp, &pm_vt_switch_list, head) { + if (tmp->dev == dev) { + list_del(&tmp->head); + kfree(tmp); + break; + } + } + mutex_unlock(&vt_switch_mutex); +} +EXPORT_SYMBOL(pm_vt_switch_unregister); + +/* + * There are three cases when a VT switch on suspend/resume are required: + * 1) no driver has indicated a requirement one way or another, so preserve + * the old behavior + * 2) console suspend is disabled, we want to see debug messages across + * suspend/resume + * 3) any registered driver indicates it needs a VT switch + * + * If none of these conditions is present, meaning we have at least one driver + * that doesn't need the switch, and none that do, we can avoid it to make + * resume look a little prettier (and suspend too, but that's usually hidden, + * e.g. when closing the lid on a laptop). + */ +static bool pm_vt_switch(void) +{ + struct pm_vt_switch *entry; + bool ret = true; + + mutex_lock(&vt_switch_mutex); + if (list_empty(&pm_vt_switch_list)) + goto out; + + if (!console_suspend_enabled) + goto out; + + list_for_each_entry(entry, &pm_vt_switch_list, head) { + if (entry->required) + goto out; + } + + ret = false; +out: + mutex_unlock(&vt_switch_mutex); + return ret; +} + +int pm_prepare_console(void) +{ + if (!pm_vt_switch()) + return 0; + + orig_fgconsole = vt_move_to_console(SUSPEND_CONSOLE, 1); + if (orig_fgconsole < 0) + return 1; + + orig_kmsg = vt_kmsg_redirect(SUSPEND_CONSOLE); + return 0; +} + +void pm_restore_console(void) +{ + if (!pm_vt_switch()) + return; + + if (orig_fgconsole >= 0) { + vt_move_to_console(orig_fgconsole, 0); + vt_kmsg_redirect(orig_kmsg); + } +} diff --git a/kernel/kernel/power/hibernate.c b/kernel/kernel/power/hibernate.c new file mode 100644 index 000000000..b8f41a363 --- /dev/null +++ b/kernel/kernel/power/hibernate.c @@ -0,0 +1,1173 @@ +/* + * kernel/power/hibernate.c - Hibernation (a.k.a suspend-to-disk) support. + * + * Copyright (c) 2003 Patrick Mochel + * Copyright (c) 2003 Open Source Development Lab + * Copyright (c) 2004 Pavel Machek + * Copyright (c) 2009 Rafael J. Wysocki, Novell Inc. + * Copyright (C) 2012 Bojan Smojver + * + * This file is released under the GPLv2. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "power.h" + + +static int nocompress; +static int noresume; +static int nohibernate; +static int resume_wait; +static unsigned int resume_delay; +static char resume_file[256] = CONFIG_PM_STD_PARTITION; +dev_t swsusp_resume_device; +sector_t swsusp_resume_block; +__visible int in_suspend __nosavedata; + +enum { + HIBERNATION_INVALID, + HIBERNATION_PLATFORM, + HIBERNATION_SHUTDOWN, + HIBERNATION_REBOOT, +#ifdef CONFIG_SUSPEND + HIBERNATION_SUSPEND, +#endif + /* keep last */ + __HIBERNATION_AFTER_LAST +}; +#define HIBERNATION_MAX (__HIBERNATION_AFTER_LAST-1) +#define HIBERNATION_FIRST (HIBERNATION_INVALID + 1) + +static int hibernation_mode = HIBERNATION_SHUTDOWN; + +bool freezer_test_done; + +static const struct platform_hibernation_ops *hibernation_ops; + +bool hibernation_available(void) +{ + return (nohibernate == 0); +} + +/** + * hibernation_set_ops - Set the global hibernate operations. + * @ops: Hibernation operations to use in subsequent hibernation transitions. + */ +void hibernation_set_ops(const struct platform_hibernation_ops *ops) +{ + if (ops && !(ops->begin && ops->end && ops->pre_snapshot + && ops->prepare && ops->finish && ops->enter && ops->pre_restore + && ops->restore_cleanup && ops->leave)) { + WARN_ON(1); + return; + } + lock_system_sleep(); + hibernation_ops = ops; + if (ops) + hibernation_mode = HIBERNATION_PLATFORM; + else if (hibernation_mode == HIBERNATION_PLATFORM) + hibernation_mode = HIBERNATION_SHUTDOWN; + + unlock_system_sleep(); +} +EXPORT_SYMBOL_GPL(hibernation_set_ops); + +static bool entering_platform_hibernation; + +bool system_entering_hibernation(void) +{ + return entering_platform_hibernation; +} +EXPORT_SYMBOL(system_entering_hibernation); + +#ifdef CONFIG_PM_DEBUG +static void hibernation_debug_sleep(void) +{ + printk(KERN_INFO "hibernation debug: Waiting for 5 seconds.\n"); + mdelay(5000); +} + +static int hibernation_test(int level) +{ + if (pm_test_level == level) { + hibernation_debug_sleep(); + return 1; + } + return 0; +} +#else /* !CONFIG_PM_DEBUG */ +static int hibernation_test(int level) { return 0; } +#endif /* !CONFIG_PM_DEBUG */ + +/** + * platform_begin - Call platform to start hibernation. + * @platform_mode: Whether or not to use the platform driver. + */ +static int platform_begin(int platform_mode) +{ + return (platform_mode && hibernation_ops) ? + hibernation_ops->begin() : 0; +} + +/** + * platform_end - Call platform to finish transition to the working state. + * @platform_mode: Whether or not to use the platform driver. + */ +static void platform_end(int platform_mode) +{ + if (platform_mode && hibernation_ops) + hibernation_ops->end(); +} + +/** + * platform_pre_snapshot - Call platform to prepare the machine for hibernation. + * @platform_mode: Whether or not to use the platform driver. + * + * Use the platform driver to prepare the system for creating a hibernate image, + * if so configured, and return an error code if that fails. + */ + +static int platform_pre_snapshot(int platform_mode) +{ + return (platform_mode && hibernation_ops) ? + hibernation_ops->pre_snapshot() : 0; +} + +/** + * platform_leave - Call platform to prepare a transition to the working state. + * @platform_mode: Whether or not to use the platform driver. + * + * Use the platform driver prepare to prepare the machine for switching to the + * normal mode of operation. + * + * This routine is called on one CPU with interrupts disabled. + */ +static void platform_leave(int platform_mode) +{ + if (platform_mode && hibernation_ops) + hibernation_ops->leave(); +} + +/** + * platform_finish - Call platform to switch the system to the working state. + * @platform_mode: Whether or not to use the platform driver. + * + * Use the platform driver to switch the machine to the normal mode of + * operation. + * + * This routine must be called after platform_prepare(). + */ +static void platform_finish(int platform_mode) +{ + if (platform_mode && hibernation_ops) + hibernation_ops->finish(); +} + +/** + * platform_pre_restore - Prepare for hibernate image restoration. + * @platform_mode: Whether or not to use the platform driver. + * + * Use the platform driver to prepare the system for resume from a hibernation + * image. + * + * If the restore fails after this function has been called, + * platform_restore_cleanup() must be called. + */ +static int platform_pre_restore(int platform_mode) +{ + return (platform_mode && hibernation_ops) ? + hibernation_ops->pre_restore() : 0; +} + +/** + * platform_restore_cleanup - Switch to the working state after failing restore. + * @platform_mode: Whether or not to use the platform driver. + * + * Use the platform driver to switch the system to the normal mode of operation + * after a failing restore. + * + * If platform_pre_restore() has been called before the failing restore, this + * function must be called too, regardless of the result of + * platform_pre_restore(). + */ +static void platform_restore_cleanup(int platform_mode) +{ + if (platform_mode && hibernation_ops) + hibernation_ops->restore_cleanup(); +} + +/** + * platform_recover - Recover from a failure to suspend devices. + * @platform_mode: Whether or not to use the platform driver. + */ +static void platform_recover(int platform_mode) +{ + if (platform_mode && hibernation_ops && hibernation_ops->recover) + hibernation_ops->recover(); +} + +/** + * swsusp_show_speed - Print time elapsed between two events during hibernation. + * @start: Starting event. + * @stop: Final event. + * @nr_pages: Number of memory pages processed between @start and @stop. + * @msg: Additional diagnostic message to print. + */ +void swsusp_show_speed(ktime_t start, ktime_t stop, + unsigned nr_pages, char *msg) +{ + ktime_t diff; + u64 elapsed_centisecs64; + unsigned int centisecs; + unsigned int k; + unsigned int kps; + + diff = ktime_sub(stop, start); + elapsed_centisecs64 = ktime_divns(diff, 10*NSEC_PER_MSEC); + centisecs = elapsed_centisecs64; + if (centisecs == 0) + centisecs = 1; /* avoid div-by-zero */ + k = nr_pages * (PAGE_SIZE / 1024); + kps = (k * 100) / centisecs; + printk(KERN_INFO "PM: %s %u kbytes in %u.%02u seconds (%u.%02u MB/s)\n", + msg, k, + centisecs / 100, centisecs % 100, + kps / 1000, (kps % 1000) / 10); +} + +/** + * create_image - Create a hibernation image. + * @platform_mode: Whether or not to use the platform driver. + * + * Execute device drivers' "late" and "noirq" freeze callbacks, create a + * hibernation image and run the drivers' "noirq" and "early" thaw callbacks. + * + * Control reappears in this routine after the subsequent restore. + */ +static int create_image(int platform_mode) +{ + int error; + + error = dpm_suspend_end(PMSG_FREEZE); + if (error) { + printk(KERN_ERR "PM: Some devices failed to power down, " + "aborting hibernation\n"); + return error; + } + + error = platform_pre_snapshot(platform_mode); + if (error || hibernation_test(TEST_PLATFORM)) + goto Platform_finish; + + error = disable_nonboot_cpus(); + if (error || hibernation_test(TEST_CPUS)) + goto Enable_cpus; + + local_irq_disable(); + + system_state = SYSTEM_SUSPEND; + + error = syscore_suspend(); + if (error) { + printk(KERN_ERR "PM: Some system devices failed to power down, " + "aborting hibernation\n"); + goto Enable_irqs; + } + + if (hibernation_test(TEST_CORE) || pm_wakeup_pending()) + goto Power_up; + + in_suspend = 1; + save_processor_state(); + trace_suspend_resume(TPS("machine_suspend"), PM_EVENT_HIBERNATE, true); + error = swsusp_arch_suspend(); + trace_suspend_resume(TPS("machine_suspend"), PM_EVENT_HIBERNATE, false); + if (error) + printk(KERN_ERR "PM: Error %d creating hibernation image\n", + error); + /* Restore control flow magically appears here */ + restore_processor_state(); + if (!in_suspend) + events_check_enabled = false; + + platform_leave(platform_mode); + + Power_up: + syscore_resume(); + + Enable_irqs: + system_state = SYSTEM_RUNNING; + local_irq_enable(); + + Enable_cpus: + enable_nonboot_cpus(); + + Platform_finish: + platform_finish(platform_mode); + + dpm_resume_start(in_suspend ? + (error ? PMSG_RECOVER : PMSG_THAW) : PMSG_RESTORE); + + return error; +} + +/** + * hibernation_snapshot - Quiesce devices and create a hibernation image. + * @platform_mode: If set, use platform driver to prepare for the transition. + * + * This routine must be called with pm_mutex held. + */ +int hibernation_snapshot(int platform_mode) +{ + pm_message_t msg; + int error; + + error = platform_begin(platform_mode); + if (error) + goto Close; + + /* Preallocate image memory before shutting down devices. */ + error = hibernate_preallocate_memory(); + if (error) + goto Close; + + error = freeze_kernel_threads(); + if (error) + goto Cleanup; + + if (hibernation_test(TEST_FREEZER)) { + + /* + * Indicate to the caller that we are returning due to a + * successful freezer test. + */ + freezer_test_done = true; + goto Thaw; + } + + error = dpm_prepare(PMSG_FREEZE); + if (error) { + dpm_complete(PMSG_RECOVER); + goto Thaw; + } + + suspend_console(); + pm_restrict_gfp_mask(); + + error = dpm_suspend(PMSG_FREEZE); + + if (error || hibernation_test(TEST_DEVICES)) + platform_recover(platform_mode); + else + error = create_image(platform_mode); + + /* + * In the case that we call create_image() above, the control + * returns here (1) after the image has been created or the + * image creation has failed and (2) after a successful restore. + */ + + /* We may need to release the preallocated image pages here. */ + if (error || !in_suspend) + swsusp_free(); + + msg = in_suspend ? (error ? PMSG_RECOVER : PMSG_THAW) : PMSG_RESTORE; + dpm_resume(msg); + + if (error || !in_suspend) + pm_restore_gfp_mask(); + + resume_console(); + dpm_complete(msg); + + Close: + platform_end(platform_mode); + return error; + + Thaw: + thaw_kernel_threads(); + Cleanup: + swsusp_free(); + goto Close; +} + +/** + * resume_target_kernel - Restore system state from a hibernation image. + * @platform_mode: Whether or not to use the platform driver. + * + * Execute device drivers' "noirq" and "late" freeze callbacks, restore the + * contents of highmem that have not been restored yet from the image and run + * the low-level code that will restore the remaining contents of memory and + * switch to the just restored target kernel. + */ +static int resume_target_kernel(bool platform_mode) +{ + int error; + + error = dpm_suspend_end(PMSG_QUIESCE); + if (error) { + printk(KERN_ERR "PM: Some devices failed to power down, " + "aborting resume\n"); + return error; + } + + error = platform_pre_restore(platform_mode); + if (error) + goto Cleanup; + + error = disable_nonboot_cpus(); + if (error) + goto Enable_cpus; + + local_irq_disable(); + system_state = SYSTEM_SUSPEND; + + error = syscore_suspend(); + if (error) + goto Enable_irqs; + + save_processor_state(); + error = restore_highmem(); + if (!error) { + error = swsusp_arch_resume(); + /* + * The code below is only ever reached in case of a failure. + * Otherwise, execution continues at the place where + * swsusp_arch_suspend() was called. + */ + BUG_ON(!error); + /* + * This call to restore_highmem() reverts the changes made by + * the previous one. + */ + restore_highmem(); + } + /* + * The only reason why swsusp_arch_resume() can fail is memory being + * very tight, so we have to free it as soon as we can to avoid + * subsequent failures. + */ + swsusp_free(); + restore_processor_state(); + touch_softlockup_watchdog(); + + syscore_resume(); + + Enable_irqs: + system_state = SYSTEM_RUNNING; + local_irq_enable(); + + Enable_cpus: + enable_nonboot_cpus(); + + Cleanup: + platform_restore_cleanup(platform_mode); + + dpm_resume_start(PMSG_RECOVER); + + return error; +} + +/** + * hibernation_restore - Quiesce devices and restore from a hibernation image. + * @platform_mode: If set, use platform driver to prepare for the transition. + * + * This routine must be called with pm_mutex held. If it is successful, control + * reappears in the restored target kernel in hibernation_snapshot(). + */ +int hibernation_restore(int platform_mode) +{ + int error; + + pm_prepare_console(); + suspend_console(); + pm_restrict_gfp_mask(); + error = dpm_suspend_start(PMSG_QUIESCE); + if (!error) { + error = resume_target_kernel(platform_mode); + /* + * The above should either succeed and jump to the new kernel, + * or return with an error. Otherwise things are just + * undefined, so let's be paranoid. + */ + BUG_ON(!error); + } + dpm_resume_end(PMSG_RECOVER); + pm_restore_gfp_mask(); + resume_console(); + pm_restore_console(); + return error; +} + +/** + * hibernation_platform_enter - Power off the system using the platform driver. + */ +int hibernation_platform_enter(void) +{ + int error; + + if (!hibernation_ops) + return -ENOSYS; + + /* + * We have cancelled the power transition by running + * hibernation_ops->finish() before saving the image, so we should let + * the firmware know that we're going to enter the sleep state after all + */ + error = hibernation_ops->begin(); + if (error) + goto Close; + + entering_platform_hibernation = true; + suspend_console(); + error = dpm_suspend_start(PMSG_HIBERNATE); + if (error) { + if (hibernation_ops->recover) + hibernation_ops->recover(); + goto Resume_devices; + } + + error = dpm_suspend_end(PMSG_HIBERNATE); + if (error) + goto Resume_devices; + + error = hibernation_ops->prepare(); + if (error) + goto Platform_finish; + + error = disable_nonboot_cpus(); + if (error) + goto Platform_finish; + + local_irq_disable(); + system_state = SYSTEM_SUSPEND; + syscore_suspend(); + if (pm_wakeup_pending()) { + error = -EAGAIN; + goto Power_up; + } + + hibernation_ops->enter(); + /* We should never get here */ + while (1); + + Power_up: + syscore_resume(); + system_state = SYSTEM_RUNNING; + local_irq_enable(); + enable_nonboot_cpus(); + + Platform_finish: + hibernation_ops->finish(); + + dpm_resume_start(PMSG_RESTORE); + + Resume_devices: + entering_platform_hibernation = false; + dpm_resume_end(PMSG_RESTORE); + resume_console(); + + Close: + hibernation_ops->end(); + + return error; +} + +/** + * power_down - Shut the machine down for hibernation. + * + * Use the platform driver, if configured, to put the system into the sleep + * state corresponding to hibernation, or try to power it off or reboot, + * depending on the value of hibernation_mode. + */ +static void power_down(void) +{ +#ifdef CONFIG_SUSPEND + int error; +#endif + + switch (hibernation_mode) { + case HIBERNATION_REBOOT: + kernel_restart(NULL); + break; + case HIBERNATION_PLATFORM: + hibernation_platform_enter(); + case HIBERNATION_SHUTDOWN: + if (pm_power_off) + kernel_power_off(); + break; +#ifdef CONFIG_SUSPEND + case HIBERNATION_SUSPEND: + error = suspend_devices_and_enter(PM_SUSPEND_MEM); + if (error) { + if (hibernation_ops) + hibernation_mode = HIBERNATION_PLATFORM; + else + hibernation_mode = HIBERNATION_SHUTDOWN; + power_down(); + } + /* + * Restore swap signature. + */ + error = swsusp_unmark(); + if (error) + printk(KERN_ERR "PM: Swap will be unusable! " + "Try swapon -a.\n"); + return; +#endif + } + kernel_halt(); + /* + * Valid image is on the disk, if we continue we risk serious data + * corruption after resume. + */ + printk(KERN_CRIT "PM: Please power down manually\n"); + while (1) + cpu_relax(); +} + +/** + * hibernate - Carry out system hibernation, including saving the image. + */ +int hibernate(void) +{ + int error; + + if (!hibernation_available()) { + pr_debug("PM: Hibernation not available.\n"); + return -EPERM; + } + + lock_system_sleep(); + /* The snapshot device should not be opened while we're running */ + if (!atomic_add_unless(&snapshot_device_available, -1, 0)) { + error = -EBUSY; + goto Unlock; + } + + pm_prepare_console(); + error = pm_notifier_call_chain(PM_HIBERNATION_PREPARE); + if (error) + goto Exit; + + printk(KERN_INFO "PM: Syncing filesystems ... "); + sys_sync(); + printk("done.\n"); + + error = freeze_processes(); + if (error) + goto Exit; + + lock_device_hotplug(); + /* Allocate memory management structures */ + error = create_basic_memory_bitmaps(); + if (error) + goto Thaw; + + error = hibernation_snapshot(hibernation_mode == HIBERNATION_PLATFORM); + if (error || freezer_test_done) + goto Free_bitmaps; + + if (in_suspend) { + unsigned int flags = 0; + + if (hibernation_mode == HIBERNATION_PLATFORM) + flags |= SF_PLATFORM_MODE; + if (nocompress) + flags |= SF_NOCOMPRESS_MODE; + else + flags |= SF_CRC32_MODE; + + pr_debug("PM: writing image.\n"); + error = swsusp_write(flags); + swsusp_free(); + if (!error) + power_down(); + in_suspend = 0; + pm_restore_gfp_mask(); + } else { + pr_debug("PM: Image restored successfully.\n"); + } + + Free_bitmaps: + free_basic_memory_bitmaps(); + Thaw: + unlock_device_hotplug(); + thaw_processes(); + + /* Don't bother checking whether freezer_test_done is true */ + freezer_test_done = false; + Exit: + pm_notifier_call_chain(PM_POST_HIBERNATION); + pm_restore_console(); + atomic_inc(&snapshot_device_available); + Unlock: + unlock_system_sleep(); + return error; +} + + +/** + * software_resume - Resume from a saved hibernation image. + * + * This routine is called as a late initcall, when all devices have been + * discovered and initialized already. + * + * The image reading code is called to see if there is a hibernation image + * available for reading. If that is the case, devices are quiesced and the + * contents of memory is restored from the saved image. + * + * If this is successful, control reappears in the restored target kernel in + * hibernation_snaphot() which returns to hibernate(). Otherwise, the routine + * attempts to recover gracefully and make the kernel return to the normal mode + * of operation. + */ +static int software_resume(void) +{ + int error; + unsigned int flags; + + /* + * If the user said "noresume".. bail out early. + */ + if (noresume || !hibernation_available()) + return 0; + + /* + * name_to_dev_t() below takes a sysfs buffer mutex when sysfs + * is configured into the kernel. Since the regular hibernate + * trigger path is via sysfs which takes a buffer mutex before + * calling hibernate functions (which take pm_mutex) this can + * cause lockdep to complain about a possible ABBA deadlock + * which cannot happen since we're in the boot code here and + * sysfs can't be invoked yet. Therefore, we use a subclass + * here to avoid lockdep complaining. + */ + mutex_lock_nested(&pm_mutex, SINGLE_DEPTH_NESTING); + + if (swsusp_resume_device) + goto Check_image; + + if (!strlen(resume_file)) { + error = -ENOENT; + goto Unlock; + } + + pr_debug("PM: Checking hibernation image partition %s\n", resume_file); + + if (resume_delay) { + printk(KERN_INFO "Waiting %dsec before reading resume device...\n", + resume_delay); + ssleep(resume_delay); + } + + /* Check if the device is there */ + swsusp_resume_device = name_to_dev_t(resume_file); + + /* + * name_to_dev_t is ineffective to verify parition if resume_file is in + * integer format. (e.g. major:minor) + */ + if (isdigit(resume_file[0]) && resume_wait) { + int partno; + while (!get_gendisk(swsusp_resume_device, &partno)) + msleep(10); + } + + if (!swsusp_resume_device) { + /* + * Some device discovery might still be in progress; we need + * to wait for this to finish. + */ + wait_for_device_probe(); + + if (resume_wait) { + while ((swsusp_resume_device = name_to_dev_t(resume_file)) == 0) + msleep(10); + async_synchronize_full(); + } + + swsusp_resume_device = name_to_dev_t(resume_file); + if (!swsusp_resume_device) { + error = -ENODEV; + goto Unlock; + } + } + + Check_image: + pr_debug("PM: Hibernation image partition %d:%d present\n", + MAJOR(swsusp_resume_device), MINOR(swsusp_resume_device)); + + pr_debug("PM: Looking for hibernation image.\n"); + error = swsusp_check(); + if (error) + goto Unlock; + + /* The snapshot device should not be opened while we're running */ + if (!atomic_add_unless(&snapshot_device_available, -1, 0)) { + error = -EBUSY; + swsusp_close(FMODE_READ); + goto Unlock; + } + + pm_prepare_console(); + error = pm_notifier_call_chain(PM_RESTORE_PREPARE); + if (error) + goto Close_Finish; + + pr_debug("PM: Preparing processes for restore.\n"); + error = freeze_processes(); + if (error) + goto Close_Finish; + + pr_debug("PM: Loading hibernation image.\n"); + + lock_device_hotplug(); + error = create_basic_memory_bitmaps(); + if (error) + goto Thaw; + + error = swsusp_read(&flags); + swsusp_close(FMODE_READ); + if (!error) + hibernation_restore(flags & SF_PLATFORM_MODE); + + printk(KERN_ERR "PM: Failed to load hibernation image, recovering.\n"); + swsusp_free(); + free_basic_memory_bitmaps(); + Thaw: + unlock_device_hotplug(); + thaw_processes(); + Finish: + pm_notifier_call_chain(PM_POST_RESTORE); + pm_restore_console(); + atomic_inc(&snapshot_device_available); + /* For success case, the suspend path will release the lock */ + Unlock: + mutex_unlock(&pm_mutex); + pr_debug("PM: Hibernation image not present or could not be loaded.\n"); + return error; + Close_Finish: + swsusp_close(FMODE_READ); + goto Finish; +} + +late_initcall_sync(software_resume); + + +static const char * const hibernation_modes[] = { + [HIBERNATION_PLATFORM] = "platform", + [HIBERNATION_SHUTDOWN] = "shutdown", + [HIBERNATION_REBOOT] = "reboot", +#ifdef CONFIG_SUSPEND + [HIBERNATION_SUSPEND] = "suspend", +#endif +}; + +/* + * /sys/power/disk - Control hibernation mode. + * + * Hibernation can be handled in several ways. There are a few different ways + * to put the system into the sleep state: using the platform driver (e.g. ACPI + * or other hibernation_ops), powering it off or rebooting it (for testing + * mostly). + * + * The sysfs file /sys/power/disk provides an interface for selecting the + * hibernation mode to use. Reading from this file causes the available modes + * to be printed. There are 3 modes that can be supported: + * + * 'platform' + * 'shutdown' + * 'reboot' + * + * If a platform hibernation driver is in use, 'platform' will be supported + * and will be used by default. Otherwise, 'shutdown' will be used by default. + * The selected option (i.e. the one corresponding to the current value of + * hibernation_mode) is enclosed by a square bracket. + * + * To select a given hibernation mode it is necessary to write the mode's + * string representation (as returned by reading from /sys/power/disk) back + * into /sys/power/disk. + */ + +static ssize_t disk_show(struct kobject *kobj, struct kobj_attribute *attr, + char *buf) +{ + int i; + char *start = buf; + + if (!hibernation_available()) + return sprintf(buf, "[disabled]\n"); + + for (i = HIBERNATION_FIRST; i <= HIBERNATION_MAX; i++) { + if (!hibernation_modes[i]) + continue; + switch (i) { + case HIBERNATION_SHUTDOWN: + case HIBERNATION_REBOOT: +#ifdef CONFIG_SUSPEND + case HIBERNATION_SUSPEND: +#endif + break; + case HIBERNATION_PLATFORM: + if (hibernation_ops) + break; + /* not a valid mode, continue with loop */ + continue; + } + if (i == hibernation_mode) + buf += sprintf(buf, "[%s] ", hibernation_modes[i]); + else + buf += sprintf(buf, "%s ", hibernation_modes[i]); + } + buf += sprintf(buf, "\n"); + return buf-start; +} + +static ssize_t disk_store(struct kobject *kobj, struct kobj_attribute *attr, + const char *buf, size_t n) +{ + int error = 0; + int i; + int len; + char *p; + int mode = HIBERNATION_INVALID; + + if (!hibernation_available()) + return -EPERM; + + p = memchr(buf, '\n', n); + len = p ? p - buf : n; + + lock_system_sleep(); + for (i = HIBERNATION_FIRST; i <= HIBERNATION_MAX; i++) { + if (len == strlen(hibernation_modes[i]) + && !strncmp(buf, hibernation_modes[i], len)) { + mode = i; + break; + } + } + if (mode != HIBERNATION_INVALID) { + switch (mode) { + case HIBERNATION_SHUTDOWN: + case HIBERNATION_REBOOT: +#ifdef CONFIG_SUSPEND + case HIBERNATION_SUSPEND: +#endif + hibernation_mode = mode; + break; + case HIBERNATION_PLATFORM: + if (hibernation_ops) + hibernation_mode = mode; + else + error = -EINVAL; + } + } else + error = -EINVAL; + + if (!error) + pr_debug("PM: Hibernation mode set to '%s'\n", + hibernation_modes[mode]); + unlock_system_sleep(); + return error ? error : n; +} + +power_attr(disk); + +static ssize_t resume_show(struct kobject *kobj, struct kobj_attribute *attr, + char *buf) +{ + return sprintf(buf,"%d:%d\n", MAJOR(swsusp_resume_device), + MINOR(swsusp_resume_device)); +} + +static ssize_t resume_store(struct kobject *kobj, struct kobj_attribute *attr, + const char *buf, size_t n) +{ + dev_t res; + int len = n; + char *name; + + if (len && buf[len-1] == '\n') + len--; + name = kstrndup(buf, len, GFP_KERNEL); + if (!name) + return -ENOMEM; + + res = name_to_dev_t(name); + kfree(name); + if (!res) + return -EINVAL; + + lock_system_sleep(); + swsusp_resume_device = res; + unlock_system_sleep(); + printk(KERN_INFO "PM: Starting manual resume from disk\n"); + noresume = 0; + software_resume(); + return n; +} + +power_attr(resume); + +static ssize_t image_size_show(struct kobject *kobj, struct kobj_attribute *attr, + char *buf) +{ + return sprintf(buf, "%lu\n", image_size); +} + +static ssize_t image_size_store(struct kobject *kobj, struct kobj_attribute *attr, + const char *buf, size_t n) +{ + unsigned long size; + + if (sscanf(buf, "%lu", &size) == 1) { + image_size = size; + return n; + } + + return -EINVAL; +} + +power_attr(image_size); + +static ssize_t reserved_size_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return sprintf(buf, "%lu\n", reserved_size); +} + +static ssize_t reserved_size_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t n) +{ + unsigned long size; + + if (sscanf(buf, "%lu", &size) == 1) { + reserved_size = size; + return n; + } + + return -EINVAL; +} + +power_attr(reserved_size); + +static struct attribute * g[] = { + &disk_attr.attr, + &resume_attr.attr, + &image_size_attr.attr, + &reserved_size_attr.attr, + NULL, +}; + + +static struct attribute_group attr_group = { + .attrs = g, +}; + + +static int __init pm_disk_init(void) +{ + return sysfs_create_group(power_kobj, &attr_group); +} + +core_initcall(pm_disk_init); + + +static int __init resume_setup(char *str) +{ + if (noresume) + return 1; + + strncpy( resume_file, str, 255 ); + return 1; +} + +static int __init resume_offset_setup(char *str) +{ + unsigned long long offset; + + if (noresume) + return 1; + + if (sscanf(str, "%llu", &offset) == 1) + swsusp_resume_block = offset; + + return 1; +} + +static int __init hibernate_setup(char *str) +{ + if (!strncmp(str, "noresume", 8)) + noresume = 1; + else if (!strncmp(str, "nocompress", 10)) + nocompress = 1; + else if (!strncmp(str, "no", 2)) { + noresume = 1; + nohibernate = 1; + } + return 1; +} + +static int __init noresume_setup(char *str) +{ + noresume = 1; + return 1; +} + +static int __init resumewait_setup(char *str) +{ + resume_wait = 1; + return 1; +} + +static int __init resumedelay_setup(char *str) +{ + int rc = kstrtouint(str, 0, &resume_delay); + + if (rc) + return rc; + return 1; +} + +static int __init nohibernate_setup(char *str) +{ + noresume = 1; + nohibernate = 1; + return 1; +} + +static int __init kaslr_nohibernate_setup(char *str) +{ + return nohibernate_setup(str); +} + +__setup("noresume", noresume_setup); +__setup("resume_offset=", resume_offset_setup); +__setup("resume=", resume_setup); +__setup("hibernate=", hibernate_setup); +__setup("resumewait", resumewait_setup); +__setup("resumedelay=", resumedelay_setup); +__setup("nohibernate", nohibernate_setup); +__setup("kaslr", kaslr_nohibernate_setup); diff --git a/kernel/kernel/power/main.c b/kernel/kernel/power/main.c new file mode 100644 index 000000000..86e8157a4 --- /dev/null +++ b/kernel/kernel/power/main.c @@ -0,0 +1,646 @@ +/* + * kernel/power/main.c - PM subsystem core functionality. + * + * Copyright (c) 2003 Patrick Mochel + * Copyright (c) 2003 Open Source Development Lab + * + * This file is released under the GPLv2 + * + */ + +#include +#include +#include +#include +#include +#include +#include + +#include "power.h" + +DEFINE_MUTEX(pm_mutex); + +#ifdef CONFIG_PM_SLEEP + +/* Routines for PM-transition notifications */ + +static BLOCKING_NOTIFIER_HEAD(pm_chain_head); + +int register_pm_notifier(struct notifier_block *nb) +{ + return blocking_notifier_chain_register(&pm_chain_head, nb); +} +EXPORT_SYMBOL_GPL(register_pm_notifier); + +int unregister_pm_notifier(struct notifier_block *nb) +{ + return blocking_notifier_chain_unregister(&pm_chain_head, nb); +} +EXPORT_SYMBOL_GPL(unregister_pm_notifier); + +int pm_notifier_call_chain(unsigned long val) +{ + int ret = blocking_notifier_call_chain(&pm_chain_head, val, NULL); + + return notifier_to_errno(ret); +} + +/* If set, devices may be suspended and resumed asynchronously. */ +int pm_async_enabled = 1; + +static ssize_t pm_async_show(struct kobject *kobj, struct kobj_attribute *attr, + char *buf) +{ + return sprintf(buf, "%d\n", pm_async_enabled); +} + +static ssize_t pm_async_store(struct kobject *kobj, struct kobj_attribute *attr, + const char *buf, size_t n) +{ + unsigned long val; + + if (kstrtoul(buf, 10, &val)) + return -EINVAL; + + if (val > 1) + return -EINVAL; + + pm_async_enabled = val; + return n; +} + +power_attr(pm_async); + +#ifdef CONFIG_PM_DEBUG +int pm_test_level = TEST_NONE; + +static const char * const pm_tests[__TEST_AFTER_LAST] = { + [TEST_NONE] = "none", + [TEST_CORE] = "core", + [TEST_CPUS] = "processors", + [TEST_PLATFORM] = "platform", + [TEST_DEVICES] = "devices", + [TEST_FREEZER] = "freezer", +}; + +static ssize_t pm_test_show(struct kobject *kobj, struct kobj_attribute *attr, + char *buf) +{ + char *s = buf; + int level; + + for (level = TEST_FIRST; level <= TEST_MAX; level++) + if (pm_tests[level]) { + if (level == pm_test_level) + s += sprintf(s, "[%s] ", pm_tests[level]); + else + s += sprintf(s, "%s ", pm_tests[level]); + } + + if (s != buf) + /* convert the last space to a newline */ + *(s-1) = '\n'; + + return (s - buf); +} + +static ssize_t pm_test_store(struct kobject *kobj, struct kobj_attribute *attr, + const char *buf, size_t n) +{ + const char * const *s; + int level; + char *p; + int len; + int error = -EINVAL; + + p = memchr(buf, '\n', n); + len = p ? p - buf : n; + + lock_system_sleep(); + + level = TEST_FIRST; + for (s = &pm_tests[level]; level <= TEST_MAX; s++, level++) + if (*s && len == strlen(*s) && !strncmp(buf, *s, len)) { + pm_test_level = level; + error = 0; + break; + } + + unlock_system_sleep(); + + return error ? error : n; +} + +power_attr(pm_test); +#endif /* CONFIG_PM_DEBUG */ + +#ifdef CONFIG_DEBUG_FS +static char *suspend_step_name(enum suspend_stat_step step) +{ + switch (step) { + case SUSPEND_FREEZE: + return "freeze"; + case SUSPEND_PREPARE: + return "prepare"; + case SUSPEND_SUSPEND: + return "suspend"; + case SUSPEND_SUSPEND_NOIRQ: + return "suspend_noirq"; + case SUSPEND_RESUME_NOIRQ: + return "resume_noirq"; + case SUSPEND_RESUME: + return "resume"; + default: + return ""; + } +} + +static int suspend_stats_show(struct seq_file *s, void *unused) +{ + int i, index, last_dev, last_errno, last_step; + + last_dev = suspend_stats.last_failed_dev + REC_FAILED_NUM - 1; + last_dev %= REC_FAILED_NUM; + last_errno = suspend_stats.last_failed_errno + REC_FAILED_NUM - 1; + last_errno %= REC_FAILED_NUM; + last_step = suspend_stats.last_failed_step + REC_FAILED_NUM - 1; + last_step %= REC_FAILED_NUM; + seq_printf(s, "%s: %d\n%s: %d\n%s: %d\n%s: %d\n%s: %d\n" + "%s: %d\n%s: %d\n%s: %d\n%s: %d\n%s: %d\n", + "success", suspend_stats.success, + "fail", suspend_stats.fail, + "failed_freeze", suspend_stats.failed_freeze, + "failed_prepare", suspend_stats.failed_prepare, + "failed_suspend", suspend_stats.failed_suspend, + "failed_suspend_late", + suspend_stats.failed_suspend_late, + "failed_suspend_noirq", + suspend_stats.failed_suspend_noirq, + "failed_resume", suspend_stats.failed_resume, + "failed_resume_early", + suspend_stats.failed_resume_early, + "failed_resume_noirq", + suspend_stats.failed_resume_noirq); + seq_printf(s, "failures:\n last_failed_dev:\t%-s\n", + suspend_stats.failed_devs[last_dev]); + for (i = 1; i < REC_FAILED_NUM; i++) { + index = last_dev + REC_FAILED_NUM - i; + index %= REC_FAILED_NUM; + seq_printf(s, "\t\t\t%-s\n", + suspend_stats.failed_devs[index]); + } + seq_printf(s, " last_failed_errno:\t%-d\n", + suspend_stats.errno[last_errno]); + for (i = 1; i < REC_FAILED_NUM; i++) { + index = last_errno + REC_FAILED_NUM - i; + index %= REC_FAILED_NUM; + seq_printf(s, "\t\t\t%-d\n", + suspend_stats.errno[index]); + } + seq_printf(s, " last_failed_step:\t%-s\n", + suspend_step_name( + suspend_stats.failed_steps[last_step])); + for (i = 1; i < REC_FAILED_NUM; i++) { + index = last_step + REC_FAILED_NUM - i; + index %= REC_FAILED_NUM; + seq_printf(s, "\t\t\t%-s\n", + suspend_step_name( + suspend_stats.failed_steps[index])); + } + + return 0; +} + +static int suspend_stats_open(struct inode *inode, struct file *file) +{ + return single_open(file, suspend_stats_show, NULL); +} + +static const struct file_operations suspend_stats_operations = { + .open = suspend_stats_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static int __init pm_debugfs_init(void) +{ + debugfs_create_file("suspend_stats", S_IFREG | S_IRUGO, + NULL, NULL, &suspend_stats_operations); + return 0; +} + +late_initcall(pm_debugfs_init); +#endif /* CONFIG_DEBUG_FS */ + +#endif /* CONFIG_PM_SLEEP */ + +#ifdef CONFIG_PM_SLEEP_DEBUG +/* + * pm_print_times: print time taken by devices to suspend and resume. + * + * show() returns whether printing of suspend and resume times is enabled. + * store() accepts 0 or 1. 0 disables printing and 1 enables it. + */ +bool pm_print_times_enabled; + +static ssize_t pm_print_times_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return sprintf(buf, "%d\n", pm_print_times_enabled); +} + +static ssize_t pm_print_times_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t n) +{ + unsigned long val; + + if (kstrtoul(buf, 10, &val)) + return -EINVAL; + + if (val > 1) + return -EINVAL; + + pm_print_times_enabled = !!val; + return n; +} + +power_attr(pm_print_times); + +static inline void pm_print_times_init(void) +{ + pm_print_times_enabled = !!initcall_debug; +} +#else /* !CONFIG_PP_SLEEP_DEBUG */ +static inline void pm_print_times_init(void) {} +#endif /* CONFIG_PM_SLEEP_DEBUG */ + +struct kobject *power_kobj; + +/** + * state - control system sleep states. + * + * show() returns available sleep state labels, which may be "mem", "standby", + * "freeze" and "disk" (hibernation). See Documentation/power/states.txt for a + * description of what they mean. + * + * store() accepts one of those strings, translates it into the proper + * enumerated value, and initiates a suspend transition. + */ +static ssize_t state_show(struct kobject *kobj, struct kobj_attribute *attr, + char *buf) +{ + char *s = buf; +#ifdef CONFIG_SUSPEND + suspend_state_t i; + + for (i = PM_SUSPEND_MIN; i < PM_SUSPEND_MAX; i++) + if (pm_states[i]) + s += sprintf(s,"%s ", pm_states[i]); + +#endif + if (hibernation_available()) + s += sprintf(s, "disk "); + if (s != buf) + /* convert the last space to a newline */ + *(s-1) = '\n'; + return (s - buf); +} + +static suspend_state_t decode_state(const char *buf, size_t n) +{ +#ifdef CONFIG_SUSPEND + suspend_state_t state; +#endif + char *p; + int len; + + p = memchr(buf, '\n', n); + len = p ? p - buf : n; + + /* Check hibernation first. */ + if (len == 4 && !strncmp(buf, "disk", len)) + return PM_SUSPEND_MAX; + +#ifdef CONFIG_SUSPEND + for (state = PM_SUSPEND_MIN; state < PM_SUSPEND_MAX; state++) { + const char *label = pm_states[state]; + + if (label && len == strlen(label) && !strncmp(buf, label, len)) + return state; + } +#endif + + return PM_SUSPEND_ON; +} + +static ssize_t state_store(struct kobject *kobj, struct kobj_attribute *attr, + const char *buf, size_t n) +{ + suspend_state_t state; + int error; + + error = pm_autosleep_lock(); + if (error) + return error; + + if (pm_autosleep_state() > PM_SUSPEND_ON) { + error = -EBUSY; + goto out; + } + + state = decode_state(buf, n); + if (state < PM_SUSPEND_MAX) + error = pm_suspend(state); + else if (state == PM_SUSPEND_MAX) + error = hibernate(); + else + error = -EINVAL; + + out: + pm_autosleep_unlock(); + return error ? error : n; +} + +power_attr(state); + +#ifdef CONFIG_PM_SLEEP +/* + * The 'wakeup_count' attribute, along with the functions defined in + * drivers/base/power/wakeup.c, provides a means by which wakeup events can be + * handled in a non-racy way. + * + * If a wakeup event occurs when the system is in a sleep state, it simply is + * woken up. In turn, if an event that would wake the system up from a sleep + * state occurs when it is undergoing a transition to that sleep state, the + * transition should be aborted. Moreover, if such an event occurs when the + * system is in the working state, an attempt to start a transition to the + * given sleep state should fail during certain period after the detection of + * the event. Using the 'state' attribute alone is not sufficient to satisfy + * these requirements, because a wakeup event may occur exactly when 'state' + * is being written to and may be delivered to user space right before it is + * frozen, so the event will remain only partially processed until the system is + * woken up by another event. In particular, it won't cause the transition to + * a sleep state to be aborted. + * + * This difficulty may be overcome if user space uses 'wakeup_count' before + * writing to 'state'. It first should read from 'wakeup_count' and store + * the read value. Then, after carrying out its own preparations for the system + * transition to a sleep state, it should write the stored value to + * 'wakeup_count'. If that fails, at least one wakeup event has occurred since + * 'wakeup_count' was read and 'state' should not be written to. Otherwise, it + * is allowed to write to 'state', but the transition will be aborted if there + * are any wakeup events detected after 'wakeup_count' was written to. + */ + +static ssize_t wakeup_count_show(struct kobject *kobj, + struct kobj_attribute *attr, + char *buf) +{ + unsigned int val; + + return pm_get_wakeup_count(&val, true) ? + sprintf(buf, "%u\n", val) : -EINTR; +} + +static ssize_t wakeup_count_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t n) +{ + unsigned int val; + int error; + + error = pm_autosleep_lock(); + if (error) + return error; + + if (pm_autosleep_state() > PM_SUSPEND_ON) { + error = -EBUSY; + goto out; + } + + error = -EINVAL; + if (sscanf(buf, "%u", &val) == 1) { + if (pm_save_wakeup_count(val)) + error = n; + else + pm_print_active_wakeup_sources(); + } + + out: + pm_autosleep_unlock(); + return error; +} + +power_attr(wakeup_count); + +#ifdef CONFIG_PM_AUTOSLEEP +static ssize_t autosleep_show(struct kobject *kobj, + struct kobj_attribute *attr, + char *buf) +{ + suspend_state_t state = pm_autosleep_state(); + + if (state == PM_SUSPEND_ON) + return sprintf(buf, "off\n"); + +#ifdef CONFIG_SUSPEND + if (state < PM_SUSPEND_MAX) + return sprintf(buf, "%s\n", pm_states[state] ? + pm_states[state] : "error"); +#endif +#ifdef CONFIG_HIBERNATION + return sprintf(buf, "disk\n"); +#else + return sprintf(buf, "error"); +#endif +} + +static ssize_t autosleep_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t n) +{ + suspend_state_t state = decode_state(buf, n); + int error; + + if (state == PM_SUSPEND_ON + && strcmp(buf, "off") && strcmp(buf, "off\n")) + return -EINVAL; + + error = pm_autosleep_set_state(state); + return error ? error : n; +} + +power_attr(autosleep); +#endif /* CONFIG_PM_AUTOSLEEP */ + +#ifdef CONFIG_PM_WAKELOCKS +static ssize_t wake_lock_show(struct kobject *kobj, + struct kobj_attribute *attr, + char *buf) +{ + return pm_show_wakelocks(buf, true); +} + +static ssize_t wake_lock_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t n) +{ + int error = pm_wake_lock(buf); + return error ? error : n; +} + +power_attr(wake_lock); + +static ssize_t wake_unlock_show(struct kobject *kobj, + struct kobj_attribute *attr, + char *buf) +{ + return pm_show_wakelocks(buf, false); +} + +static ssize_t wake_unlock_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t n) +{ + int error = pm_wake_unlock(buf); + return error ? error : n; +} + +power_attr(wake_unlock); + +#endif /* CONFIG_PM_WAKELOCKS */ +#endif /* CONFIG_PM_SLEEP */ + +#ifdef CONFIG_PM_TRACE +int pm_trace_enabled; + +static ssize_t pm_trace_show(struct kobject *kobj, struct kobj_attribute *attr, + char *buf) +{ + return sprintf(buf, "%d\n", pm_trace_enabled); +} + +static ssize_t +pm_trace_store(struct kobject *kobj, struct kobj_attribute *attr, + const char *buf, size_t n) +{ + int val; + + if (sscanf(buf, "%d", &val) == 1) { + pm_trace_enabled = !!val; + if (pm_trace_enabled) { + pr_warn("PM: Enabling pm_trace changes system date and time during resume.\n" + "PM: Correct system time has to be restored manually after resume.\n"); + } + return n; + } + return -EINVAL; +} + +power_attr(pm_trace); + +static ssize_t pm_trace_dev_match_show(struct kobject *kobj, + struct kobj_attribute *attr, + char *buf) +{ + return show_trace_dev_match(buf, PAGE_SIZE); +} + +static ssize_t +pm_trace_dev_match_store(struct kobject *kobj, struct kobj_attribute *attr, + const char *buf, size_t n) +{ + return -EINVAL; +} + +power_attr(pm_trace_dev_match); + +#endif /* CONFIG_PM_TRACE */ + +#ifdef CONFIG_FREEZER +static ssize_t pm_freeze_timeout_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return sprintf(buf, "%u\n", freeze_timeout_msecs); +} + +static ssize_t pm_freeze_timeout_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t n) +{ + unsigned long val; + + if (kstrtoul(buf, 10, &val)) + return -EINVAL; + + freeze_timeout_msecs = val; + return n; +} + +power_attr(pm_freeze_timeout); + +#endif /* CONFIG_FREEZER*/ + +static struct attribute * g[] = { + &state_attr.attr, +#ifdef CONFIG_PM_TRACE + &pm_trace_attr.attr, + &pm_trace_dev_match_attr.attr, +#endif +#ifdef CONFIG_PM_SLEEP + &pm_async_attr.attr, + &wakeup_count_attr.attr, +#ifdef CONFIG_PM_AUTOSLEEP + &autosleep_attr.attr, +#endif +#ifdef CONFIG_PM_WAKELOCKS + &wake_lock_attr.attr, + &wake_unlock_attr.attr, +#endif +#ifdef CONFIG_PM_DEBUG + &pm_test_attr.attr, +#endif +#ifdef CONFIG_PM_SLEEP_DEBUG + &pm_print_times_attr.attr, +#endif +#endif +#ifdef CONFIG_FREEZER + &pm_freeze_timeout_attr.attr, +#endif + NULL, +}; + +static struct attribute_group attr_group = { + .attrs = g, +}; + +struct workqueue_struct *pm_wq; +EXPORT_SYMBOL_GPL(pm_wq); + +static int __init pm_start_workqueue(void) +{ + pm_wq = alloc_workqueue("pm", WQ_FREEZABLE, 0); + + return pm_wq ? 0 : -ENOMEM; +} + +static int __init pm_init(void) +{ + int error = pm_start_workqueue(); + if (error) + return error; + hibernate_image_size_init(); + hibernate_reserved_size_init(); + power_kobj = kobject_create_and_add("power", NULL); + if (!power_kobj) + return -ENOMEM; + error = sysfs_create_group(power_kobj, &attr_group); + if (error) + return error; + pm_print_times_init(); + return pm_autosleep_init(); +} + +core_initcall(pm_init); diff --git a/kernel/kernel/power/power.h b/kernel/kernel/power/power.h new file mode 100644 index 000000000..ce9b8328a --- /dev/null +++ b/kernel/kernel/power/power.h @@ -0,0 +1,297 @@ +#include +#include +#include +#include +#include + +struct swsusp_info { + struct new_utsname uts; + u32 version_code; + unsigned long num_physpages; + int cpus; + unsigned long image_pages; + unsigned long pages; + unsigned long size; +} __aligned(PAGE_SIZE); + +#ifdef CONFIG_HIBERNATION +/* kernel/power/snapshot.c */ +extern void __init hibernate_reserved_size_init(void); +extern void __init hibernate_image_size_init(void); + +#ifdef CONFIG_ARCH_HIBERNATION_HEADER +/* Maximum size of architecture specific data in a hibernation header */ +#define MAX_ARCH_HEADER_SIZE (sizeof(struct new_utsname) + 4) + +extern int arch_hibernation_header_save(void *addr, unsigned int max_size); +extern int arch_hibernation_header_restore(void *addr); + +static inline int init_header_complete(struct swsusp_info *info) +{ + return arch_hibernation_header_save(info, MAX_ARCH_HEADER_SIZE); +} + +static inline char *check_image_kernel(struct swsusp_info *info) +{ + return arch_hibernation_header_restore(info) ? + "architecture specific data" : NULL; +} +#endif /* CONFIG_ARCH_HIBERNATION_HEADER */ + +/* + * Keep some memory free so that I/O operations can succeed without paging + * [Might this be more than 4 MB?] + */ +#define PAGES_FOR_IO ((4096 * 1024) >> PAGE_SHIFT) + +/* + * Keep 1 MB of memory free so that device drivers can allocate some pages in + * their .suspend() routines without breaking the suspend to disk. + */ +#define SPARE_PAGES ((1024 * 1024) >> PAGE_SHIFT) + +asmlinkage int swsusp_save(void); + +/* kernel/power/hibernate.c */ +extern bool freezer_test_done; + +extern int hibernation_snapshot(int platform_mode); +extern int hibernation_restore(int platform_mode); +extern int hibernation_platform_enter(void); + +#else /* !CONFIG_HIBERNATION */ + +static inline void hibernate_reserved_size_init(void) {} +static inline void hibernate_image_size_init(void) {} +#endif /* !CONFIG_HIBERNATION */ + +extern int pfn_is_nosave(unsigned long); + +#define power_attr(_name) \ +static struct kobj_attribute _name##_attr = { \ + .attr = { \ + .name = __stringify(_name), \ + .mode = 0644, \ + }, \ + .show = _name##_show, \ + .store = _name##_store, \ +} + +/* Preferred image size in bytes (default 500 MB) */ +extern unsigned long image_size; +/* Size of memory reserved for drivers (default SPARE_PAGES x PAGE_SIZE) */ +extern unsigned long reserved_size; +extern int in_suspend; +extern dev_t swsusp_resume_device; +extern sector_t swsusp_resume_block; + +extern asmlinkage int swsusp_arch_suspend(void); +extern asmlinkage int swsusp_arch_resume(void); + +extern int create_basic_memory_bitmaps(void); +extern void free_basic_memory_bitmaps(void); +extern int hibernate_preallocate_memory(void); + +/** + * Auxiliary structure used for reading the snapshot image data and + * metadata from and writing them to the list of page backup entries + * (PBEs) which is the main data structure of swsusp. + * + * Using struct snapshot_handle we can transfer the image, including its + * metadata, as a continuous sequence of bytes with the help of + * snapshot_read_next() and snapshot_write_next(). + * + * The code that writes the image to a storage or transfers it to + * the user land is required to use snapshot_read_next() for this + * purpose and it should not make any assumptions regarding the internal + * structure of the image. Similarly, the code that reads the image from + * a storage or transfers it from the user land is required to use + * snapshot_write_next(). + * + * This may allow us to change the internal structure of the image + * in the future with considerably less effort. + */ + +struct snapshot_handle { + unsigned int cur; /* number of the block of PAGE_SIZE bytes the + * next operation will refer to (ie. current) + */ + void *buffer; /* address of the block to read from + * or write to + */ + int sync_read; /* Set to one to notify the caller of + * snapshot_write_next() that it may + * need to call wait_on_bio_chain() + */ +}; + +/* This macro returns the address from/to which the caller of + * snapshot_read_next()/snapshot_write_next() is allowed to + * read/write data after the function returns + */ +#define data_of(handle) ((handle).buffer) + +extern unsigned int snapshot_additional_pages(struct zone *zone); +extern unsigned long snapshot_get_image_size(void); +extern int snapshot_read_next(struct snapshot_handle *handle); +extern int snapshot_write_next(struct snapshot_handle *handle); +extern void snapshot_write_finalize(struct snapshot_handle *handle); +extern int snapshot_image_loaded(struct snapshot_handle *handle); + +/* If unset, the snapshot device cannot be open. */ +extern atomic_t snapshot_device_available; + +extern sector_t alloc_swapdev_block(int swap); +extern void free_all_swap_pages(int swap); +extern int swsusp_swap_in_use(void); + +/* + * Flags that can be passed from the hibernatig hernel to the "boot" kernel in + * the image header. + */ +#define SF_PLATFORM_MODE 1 +#define SF_NOCOMPRESS_MODE 2 +#define SF_CRC32_MODE 4 + +/* kernel/power/hibernate.c */ +extern int swsusp_check(void); +extern void swsusp_free(void); +extern int swsusp_read(unsigned int *flags_p); +extern int swsusp_write(unsigned int flags); +extern void swsusp_close(fmode_t); +#ifdef CONFIG_SUSPEND +extern int swsusp_unmark(void); +#endif + +/* kernel/power/block_io.c */ +extern struct block_device *hib_resume_bdev; + +extern int hib_bio_read_page(pgoff_t page_off, void *addr, + struct bio **bio_chain); +extern int hib_bio_write_page(pgoff_t page_off, void *addr, + struct bio **bio_chain); +extern int hib_wait_on_bio_chain(struct bio **bio_chain); + +struct timeval; +/* kernel/power/swsusp.c */ +extern void swsusp_show_speed(ktime_t, ktime_t, unsigned int, char *); + +#ifdef CONFIG_SUSPEND +/* kernel/power/suspend.c */ +extern const char *pm_labels[]; +extern const char *pm_states[]; + +extern int suspend_devices_and_enter(suspend_state_t state); +#else /* !CONFIG_SUSPEND */ +static inline int suspend_devices_and_enter(suspend_state_t state) +{ + return -ENOSYS; +} +#endif /* !CONFIG_SUSPEND */ + +#ifdef CONFIG_PM_TEST_SUSPEND +/* kernel/power/suspend_test.c */ +extern void suspend_test_start(void); +extern void suspend_test_finish(const char *label); +#else /* !CONFIG_PM_TEST_SUSPEND */ +static inline void suspend_test_start(void) {} +static inline void suspend_test_finish(const char *label) {} +#endif /* !CONFIG_PM_TEST_SUSPEND */ + +#ifdef CONFIG_PM_SLEEP +/* kernel/power/main.c */ +extern int pm_notifier_call_chain(unsigned long val); +#endif + +#ifdef CONFIG_HIGHMEM +int restore_highmem(void); +#else +static inline unsigned int count_highmem_pages(void) { return 0; } +static inline int restore_highmem(void) { return 0; } +#endif + +/* + * Suspend test levels + */ +enum { + /* keep first */ + TEST_NONE, + TEST_CORE, + TEST_CPUS, + TEST_PLATFORM, + TEST_DEVICES, + TEST_FREEZER, + /* keep last */ + __TEST_AFTER_LAST +}; + +#define TEST_FIRST TEST_NONE +#define TEST_MAX (__TEST_AFTER_LAST - 1) + +extern int pm_test_level; + +#ifdef CONFIG_SUSPEND_FREEZER +static inline int suspend_freeze_processes(void) +{ + int error; + + error = freeze_processes(); + /* + * freeze_processes() automatically thaws every task if freezing + * fails. So we need not do anything extra upon error. + */ + if (error) + return error; + + error = freeze_kernel_threads(); + /* + * freeze_kernel_threads() thaws only kernel threads upon freezing + * failure. So we have to thaw the userspace tasks ourselves. + */ + if (error) + thaw_processes(); + + return error; +} + +static inline void suspend_thaw_processes(void) +{ + thaw_processes(); +} +#else +static inline int suspend_freeze_processes(void) +{ + return 0; +} + +static inline void suspend_thaw_processes(void) +{ +} +#endif + +#ifdef CONFIG_PM_AUTOSLEEP + +/* kernel/power/autosleep.c */ +extern int pm_autosleep_init(void); +extern int pm_autosleep_lock(void); +extern void pm_autosleep_unlock(void); +extern suspend_state_t pm_autosleep_state(void); +extern int pm_autosleep_set_state(suspend_state_t state); + +#else /* !CONFIG_PM_AUTOSLEEP */ + +static inline int pm_autosleep_init(void) { return 0; } +static inline int pm_autosleep_lock(void) { return 0; } +static inline void pm_autosleep_unlock(void) {} +static inline suspend_state_t pm_autosleep_state(void) { return PM_SUSPEND_ON; } + +#endif /* !CONFIG_PM_AUTOSLEEP */ + +#ifdef CONFIG_PM_WAKELOCKS + +/* kernel/power/wakelock.c */ +extern ssize_t pm_show_wakelocks(char *buf, bool show_active); +extern int pm_wake_lock(const char *buf); +extern int pm_wake_unlock(const char *buf); + +#endif /* !CONFIG_PM_WAKELOCKS */ diff --git a/kernel/kernel/power/poweroff.c b/kernel/kernel/power/poweroff.c new file mode 100644 index 000000000..7ef6866b5 --- /dev/null +++ b/kernel/kernel/power/poweroff.c @@ -0,0 +1,46 @@ +/* + * poweroff.c - sysrq handler to gracefully power down machine. + * + * This file is released under the GPL v2 + */ + +#include +#include +#include +#include +#include +#include +#include + +/* + * When the user hits Sys-Rq o to power down the machine this is the + * callback we use. + */ + +static void do_poweroff(struct work_struct *dummy) +{ + kernel_power_off(); +} + +static DECLARE_WORK(poweroff_work, do_poweroff); + +static void handle_poweroff(int key) +{ + /* run sysrq poweroff on boot cpu */ + schedule_work_on(cpumask_first(cpu_online_mask), &poweroff_work); +} + +static struct sysrq_key_op sysrq_poweroff_op = { + .handler = handle_poweroff, + .help_msg = "poweroff(o)", + .action_msg = "Power Off", + .enable_mask = SYSRQ_ENABLE_BOOT, +}; + +static int __init pm_sysrq_init(void) +{ + register_sysrq_key('o', &sysrq_poweroff_op); + return 0; +} + +subsys_initcall(pm_sysrq_init); diff --git a/kernel/kernel/power/process.c b/kernel/kernel/power/process.c new file mode 100644 index 000000000..564f786df --- /dev/null +++ b/kernel/kernel/power/process.c @@ -0,0 +1,237 @@ +/* + * drivers/power/process.c - Functions for starting/stopping processes on + * suspend transitions. + * + * Originally from swsusp. + */ + + +#undef DEBUG + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +/* + * Timeout for stopping processes + */ +unsigned int __read_mostly freeze_timeout_msecs = 20 * MSEC_PER_SEC; + +static int try_to_freeze_tasks(bool user_only) +{ + struct task_struct *g, *p; + unsigned long end_time; + unsigned int todo; + bool wq_busy = false; + struct timeval start, end; + u64 elapsed_msecs64; + unsigned int elapsed_msecs; + bool wakeup = false; + int sleep_usecs = USEC_PER_MSEC; + + do_gettimeofday(&start); + + end_time = jiffies + msecs_to_jiffies(freeze_timeout_msecs); + + if (!user_only) + freeze_workqueues_begin(); + + while (true) { + todo = 0; + read_lock(&tasklist_lock); + for_each_process_thread(g, p) { + if (p == current || !freeze_task(p)) + continue; + + if (!freezer_should_skip(p)) + todo++; + } + read_unlock(&tasklist_lock); + + if (!user_only) { + wq_busy = freeze_workqueues_busy(); + todo += wq_busy; + } + + if (!todo || time_after(jiffies, end_time)) + break; + + if (pm_wakeup_pending()) { + wakeup = true; + break; + } + + /* + * We need to retry, but first give the freezing tasks some + * time to enter the refrigerator. Start with an initial + * 1 ms sleep followed by exponential backoff until 8 ms. + */ + usleep_range(sleep_usecs / 2, sleep_usecs); + if (sleep_usecs < 8 * USEC_PER_MSEC) + sleep_usecs *= 2; + } + + do_gettimeofday(&end); + elapsed_msecs64 = timeval_to_ns(&end) - timeval_to_ns(&start); + do_div(elapsed_msecs64, NSEC_PER_MSEC); + elapsed_msecs = elapsed_msecs64; + + if (todo) { + pr_cont("\n"); + pr_err("Freezing of tasks %s after %d.%03d seconds " + "(%d tasks refusing to freeze, wq_busy=%d):\n", + wakeup ? "aborted" : "failed", + elapsed_msecs / 1000, elapsed_msecs % 1000, + todo - wq_busy, wq_busy); + + if (!wakeup) { + read_lock(&tasklist_lock); + for_each_process_thread(g, p) { + if (p != current && !freezer_should_skip(p) + && freezing(p) && !frozen(p)) + sched_show_task(p); + } + read_unlock(&tasklist_lock); + } + } else { + pr_cont("(elapsed %d.%03d seconds) ", elapsed_msecs / 1000, + elapsed_msecs % 1000); + } + + return todo ? -EBUSY : 0; +} + +/** + * freeze_processes - Signal user space processes to enter the refrigerator. + * The current thread will not be frozen. The same process that calls + * freeze_processes must later call thaw_processes. + * + * On success, returns 0. On failure, -errno and system is fully thawed. + */ +int freeze_processes(void) +{ + int error; + + error = __usermodehelper_disable(UMH_FREEZING); + if (error) + return error; + + /* Make sure this task doesn't get frozen */ + current->flags |= PF_SUSPEND_TASK; + + if (!pm_freezing) + atomic_inc(&system_freezing_cnt); + + pm_wakeup_clear(); + pr_info("Freezing user space processes ... "); + pm_freezing = true; + error = try_to_freeze_tasks(true); + if (!error) { + __usermodehelper_set_disable_depth(UMH_DISABLED); + pr_cont("done."); + } + pr_cont("\n"); + BUG_ON(in_atomic()); + + /* + * Now that the whole userspace is frozen we need to disbale + * the OOM killer to disallow any further interference with + * killable tasks. + */ + if (!error && !oom_killer_disable()) + error = -EBUSY; + + if (error) + thaw_processes(); + return error; +} + +/** + * freeze_kernel_threads - Make freezable kernel threads go to the refrigerator. + * + * On success, returns 0. On failure, -errno and only the kernel threads are + * thawed, so as to give a chance to the caller to do additional cleanups + * (if any) before thawing the userspace tasks. So, it is the responsibility + * of the caller to thaw the userspace tasks, when the time is right. + */ +int freeze_kernel_threads(void) +{ + int error; + + pr_info("Freezing remaining freezable tasks ... "); + + pm_nosig_freezing = true; + error = try_to_freeze_tasks(false); + if (!error) + pr_cont("done."); + + pr_cont("\n"); + BUG_ON(in_atomic()); + + if (error) + thaw_kernel_threads(); + return error; +} + +void thaw_processes(void) +{ + struct task_struct *g, *p; + struct task_struct *curr = current; + + trace_suspend_resume(TPS("thaw_processes"), 0, true); + if (pm_freezing) + atomic_dec(&system_freezing_cnt); + pm_freezing = false; + pm_nosig_freezing = false; + + oom_killer_enable(); + + pr_info("Restarting tasks ... "); + + __usermodehelper_set_disable_depth(UMH_FREEZING); + thaw_workqueues(); + + read_lock(&tasklist_lock); + for_each_process_thread(g, p) { + /* No other threads should have PF_SUSPEND_TASK set */ + WARN_ON((p != curr) && (p->flags & PF_SUSPEND_TASK)); + __thaw_task(p); + } + read_unlock(&tasklist_lock); + + WARN_ON(!(curr->flags & PF_SUSPEND_TASK)); + curr->flags &= ~PF_SUSPEND_TASK; + + usermodehelper_enable(); + + schedule(); + pr_cont("done.\n"); + trace_suspend_resume(TPS("thaw_processes"), 0, false); +} + +void thaw_kernel_threads(void) +{ + struct task_struct *g, *p; + + pm_nosig_freezing = false; + pr_info("Restarting kernel threads ... "); + + thaw_workqueues(); + + read_lock(&tasklist_lock); + for_each_process_thread(g, p) { + if (p->flags & (PF_KTHREAD | PF_WQ_WORKER)) + __thaw_task(p); + } + read_unlock(&tasklist_lock); + + schedule(); + pr_cont("done.\n"); +} diff --git a/kernel/kernel/power/qos.c b/kernel/kernel/power/qos.c new file mode 100644 index 000000000..97b0df713 --- /dev/null +++ b/kernel/kernel/power/qos.c @@ -0,0 +1,713 @@ +/* + * This module exposes the interface to kernel space for specifying + * QoS dependencies. It provides infrastructure for registration of: + * + * Dependents on a QoS value : register requests + * Watchers of QoS value : get notified when target QoS value changes + * + * This QoS design is best effort based. Dependents register their QoS needs. + * Watchers register to keep track of the current QoS needs of the system. + * + * There are 3 basic classes of QoS parameter: latency, timeout, throughput + * each have defined units: + * latency: usec + * timeout: usec <-- currently not used. + * throughput: kbs (kilo byte / sec) + * + * There are lists of pm_qos_objects each one wrapping requests, notifiers + * + * User mode requests on a QOS parameter register themselves to the + * subsystem by opening the device node /dev/... and writing there request to + * the node. As long as the process holds a file handle open to the node the + * client continues to be accounted for. Upon file release the usermode + * request is removed and a new qos target is computed. This way when the + * request that the application has is cleaned up when closes the file + * pointer or exits the pm_qos_object will get an opportunity to clean up. + * + * Mark Gross + */ + +/*#define DEBUG*/ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include + +/* + * locking rule: all changes to constraints or notifiers lists + * or pm_qos_object list and pm_qos_objects need to happen with pm_qos_lock + * held, taken with _irqsave. One lock to rule them all + */ +struct pm_qos_object { + struct pm_qos_constraints *constraints; + struct miscdevice pm_qos_power_miscdev; + char *name; +}; + +static DEFINE_SPINLOCK(pm_qos_lock); + +static struct pm_qos_object null_pm_qos; + +static BLOCKING_NOTIFIER_HEAD(cpu_dma_lat_notifier); +static struct pm_qos_constraints cpu_dma_constraints = { + .list = PLIST_HEAD_INIT(cpu_dma_constraints.list), + .target_value = PM_QOS_CPU_DMA_LAT_DEFAULT_VALUE, + .default_value = PM_QOS_CPU_DMA_LAT_DEFAULT_VALUE, + .no_constraint_value = PM_QOS_CPU_DMA_LAT_DEFAULT_VALUE, + .type = PM_QOS_MIN, + .notifiers = &cpu_dma_lat_notifier, +}; +static struct pm_qos_object cpu_dma_pm_qos = { + .constraints = &cpu_dma_constraints, + .name = "cpu_dma_latency", +}; + +static BLOCKING_NOTIFIER_HEAD(network_lat_notifier); +static struct pm_qos_constraints network_lat_constraints = { + .list = PLIST_HEAD_INIT(network_lat_constraints.list), + .target_value = PM_QOS_NETWORK_LAT_DEFAULT_VALUE, + .default_value = PM_QOS_NETWORK_LAT_DEFAULT_VALUE, + .no_constraint_value = PM_QOS_NETWORK_LAT_DEFAULT_VALUE, + .type = PM_QOS_MIN, + .notifiers = &network_lat_notifier, +}; +static struct pm_qos_object network_lat_pm_qos = { + .constraints = &network_lat_constraints, + .name = "network_latency", +}; + + +static BLOCKING_NOTIFIER_HEAD(network_throughput_notifier); +static struct pm_qos_constraints network_tput_constraints = { + .list = PLIST_HEAD_INIT(network_tput_constraints.list), + .target_value = PM_QOS_NETWORK_THROUGHPUT_DEFAULT_VALUE, + .default_value = PM_QOS_NETWORK_THROUGHPUT_DEFAULT_VALUE, + .no_constraint_value = PM_QOS_NETWORK_THROUGHPUT_DEFAULT_VALUE, + .type = PM_QOS_MAX, + .notifiers = &network_throughput_notifier, +}; +static struct pm_qos_object network_throughput_pm_qos = { + .constraints = &network_tput_constraints, + .name = "network_throughput", +}; + + +static BLOCKING_NOTIFIER_HEAD(memory_bandwidth_notifier); +static struct pm_qos_constraints memory_bw_constraints = { + .list = PLIST_HEAD_INIT(memory_bw_constraints.list), + .target_value = PM_QOS_MEMORY_BANDWIDTH_DEFAULT_VALUE, + .default_value = PM_QOS_MEMORY_BANDWIDTH_DEFAULT_VALUE, + .no_constraint_value = PM_QOS_MEMORY_BANDWIDTH_DEFAULT_VALUE, + .type = PM_QOS_SUM, + .notifiers = &memory_bandwidth_notifier, +}; +static struct pm_qos_object memory_bandwidth_pm_qos = { + .constraints = &memory_bw_constraints, + .name = "memory_bandwidth", +}; + + +static struct pm_qos_object *pm_qos_array[] = { + &null_pm_qos, + &cpu_dma_pm_qos, + &network_lat_pm_qos, + &network_throughput_pm_qos, + &memory_bandwidth_pm_qos, +}; + +static ssize_t pm_qos_power_write(struct file *filp, const char __user *buf, + size_t count, loff_t *f_pos); +static ssize_t pm_qos_power_read(struct file *filp, char __user *buf, + size_t count, loff_t *f_pos); +static int pm_qos_power_open(struct inode *inode, struct file *filp); +static int pm_qos_power_release(struct inode *inode, struct file *filp); + +static const struct file_operations pm_qos_power_fops = { + .write = pm_qos_power_write, + .read = pm_qos_power_read, + .open = pm_qos_power_open, + .release = pm_qos_power_release, + .llseek = noop_llseek, +}; + +/* unlocked internal variant */ +static inline int pm_qos_get_value(struct pm_qos_constraints *c) +{ + struct plist_node *node; + int total_value = 0; + + if (plist_head_empty(&c->list)) + return c->no_constraint_value; + + switch (c->type) { + case PM_QOS_MIN: + return plist_first(&c->list)->prio; + + case PM_QOS_MAX: + return plist_last(&c->list)->prio; + + case PM_QOS_SUM: + plist_for_each(node, &c->list) + total_value += node->prio; + + return total_value; + + default: + /* runtime check for not using enum */ + BUG(); + return PM_QOS_DEFAULT_VALUE; + } +} + +s32 pm_qos_read_value(struct pm_qos_constraints *c) +{ + return c->target_value; +} + +static inline void pm_qos_set_value(struct pm_qos_constraints *c, s32 value) +{ + c->target_value = value; +} + +static inline int pm_qos_get_value(struct pm_qos_constraints *c); +static int pm_qos_dbg_show_requests(struct seq_file *s, void *unused) +{ + struct pm_qos_object *qos = (struct pm_qos_object *)s->private; + struct pm_qos_constraints *c; + struct pm_qos_request *req; + char *type; + unsigned long flags; + int tot_reqs = 0; + int active_reqs = 0; + + if (IS_ERR_OR_NULL(qos)) { + pr_err("%s: bad qos param!\n", __func__); + return -EINVAL; + } + c = qos->constraints; + if (IS_ERR_OR_NULL(c)) { + pr_err("%s: Bad constraints on qos?\n", __func__); + return -EINVAL; + } + + /* Lock to ensure we have a snapshot */ + spin_lock_irqsave(&pm_qos_lock, flags); + if (plist_head_empty(&c->list)) { + seq_puts(s, "Empty!\n"); + goto out; + } + + switch (c->type) { + case PM_QOS_MIN: + type = "Minimum"; + break; + case PM_QOS_MAX: + type = "Maximum"; + break; + case PM_QOS_SUM: + type = "Sum"; + break; + default: + type = "Unknown"; + } + + plist_for_each_entry(req, &c->list, node) { + char *state = "Default"; + + if ((req->node).prio != c->default_value) { + active_reqs++; + state = "Active"; + } + tot_reqs++; + seq_printf(s, "%d: %d: %s\n", tot_reqs, + (req->node).prio, state); + } + + seq_printf(s, "Type=%s, Value=%d, Requests: active=%d / total=%d\n", + type, pm_qos_get_value(c), active_reqs, tot_reqs); + +out: + spin_unlock_irqrestore(&pm_qos_lock, flags); + return 0; +} + +static int pm_qos_dbg_open(struct inode *inode, struct file *file) +{ + return single_open(file, pm_qos_dbg_show_requests, + inode->i_private); +} + +static const struct file_operations pm_qos_debug_fops = { + .open = pm_qos_dbg_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +/** + * pm_qos_update_target - manages the constraints list and calls the notifiers + * if needed + * @c: constraints data struct + * @node: request to add to the list, to update or to remove + * @action: action to take on the constraints list + * @value: value of the request to add or update + * + * This function returns 1 if the aggregated constraint value has changed, 0 + * otherwise. + */ +int pm_qos_update_target(struct pm_qos_constraints *c, struct plist_node *node, + enum pm_qos_req_action action, int value) +{ + unsigned long flags; + int prev_value, curr_value, new_value; + int ret; + + spin_lock_irqsave(&pm_qos_lock, flags); + prev_value = pm_qos_get_value(c); + if (value == PM_QOS_DEFAULT_VALUE) + new_value = c->default_value; + else + new_value = value; + + switch (action) { + case PM_QOS_REMOVE_REQ: + plist_del(node, &c->list); + break; + case PM_QOS_UPDATE_REQ: + /* + * to change the list, we atomically remove, reinit + * with new value and add, then see if the extremal + * changed + */ + plist_del(node, &c->list); + case PM_QOS_ADD_REQ: + plist_node_init(node, new_value); + plist_add(node, &c->list); + break; + default: + /* no action */ + ; + } + + curr_value = pm_qos_get_value(c); + pm_qos_set_value(c, curr_value); + + spin_unlock_irqrestore(&pm_qos_lock, flags); + + trace_pm_qos_update_target(action, prev_value, curr_value); + if (prev_value != curr_value) { + ret = 1; + if (c->notifiers) + blocking_notifier_call_chain(c->notifiers, + (unsigned long)curr_value, + NULL); + } else { + ret = 0; + } + return ret; +} + +/** + * pm_qos_flags_remove_req - Remove device PM QoS flags request. + * @pqf: Device PM QoS flags set to remove the request from. + * @req: Request to remove from the set. + */ +static void pm_qos_flags_remove_req(struct pm_qos_flags *pqf, + struct pm_qos_flags_request *req) +{ + s32 val = 0; + + list_del(&req->node); + list_for_each_entry(req, &pqf->list, node) + val |= req->flags; + + pqf->effective_flags = val; +} + +/** + * pm_qos_update_flags - Update a set of PM QoS flags. + * @pqf: Set of flags to update. + * @req: Request to add to the set, to modify, or to remove from the set. + * @action: Action to take on the set. + * @val: Value of the request to add or modify. + * + * Update the given set of PM QoS flags and call notifiers if the aggregate + * value has changed. Returns 1 if the aggregate constraint value has changed, + * 0 otherwise. + */ +bool pm_qos_update_flags(struct pm_qos_flags *pqf, + struct pm_qos_flags_request *req, + enum pm_qos_req_action action, s32 val) +{ + unsigned long irqflags; + s32 prev_value, curr_value; + + spin_lock_irqsave(&pm_qos_lock, irqflags); + + prev_value = list_empty(&pqf->list) ? 0 : pqf->effective_flags; + + switch (action) { + case PM_QOS_REMOVE_REQ: + pm_qos_flags_remove_req(pqf, req); + break; + case PM_QOS_UPDATE_REQ: + pm_qos_flags_remove_req(pqf, req); + case PM_QOS_ADD_REQ: + req->flags = val; + INIT_LIST_HEAD(&req->node); + list_add_tail(&req->node, &pqf->list); + pqf->effective_flags |= val; + break; + default: + /* no action */ + ; + } + + curr_value = list_empty(&pqf->list) ? 0 : pqf->effective_flags; + + spin_unlock_irqrestore(&pm_qos_lock, irqflags); + + trace_pm_qos_update_flags(action, prev_value, curr_value); + return prev_value != curr_value; +} + +/** + * pm_qos_request - returns current system wide qos expectation + * @pm_qos_class: identification of which qos value is requested + * + * This function returns the current target value. + */ +int pm_qos_request(int pm_qos_class) +{ + return pm_qos_read_value(pm_qos_array[pm_qos_class]->constraints); +} +EXPORT_SYMBOL_GPL(pm_qos_request); + +int pm_qos_request_active(struct pm_qos_request *req) +{ + return req->pm_qos_class != 0; +} +EXPORT_SYMBOL_GPL(pm_qos_request_active); + +static void __pm_qos_update_request(struct pm_qos_request *req, + s32 new_value) +{ + trace_pm_qos_update_request(req->pm_qos_class, new_value); + + if (new_value != req->node.prio) + pm_qos_update_target( + pm_qos_array[req->pm_qos_class]->constraints, + &req->node, PM_QOS_UPDATE_REQ, new_value); +} + +/** + * pm_qos_work_fn - the timeout handler of pm_qos_update_request_timeout + * @work: work struct for the delayed work (timeout) + * + * This cancels the timeout request by falling back to the default at timeout. + */ +static void pm_qos_work_fn(struct work_struct *work) +{ + struct pm_qos_request *req = container_of(to_delayed_work(work), + struct pm_qos_request, + work); + + __pm_qos_update_request(req, PM_QOS_DEFAULT_VALUE); +} + +/** + * pm_qos_add_request - inserts new qos request into the list + * @req: pointer to a preallocated handle + * @pm_qos_class: identifies which list of qos request to use + * @value: defines the qos request + * + * This function inserts a new entry in the pm_qos_class list of requested qos + * performance characteristics. It recomputes the aggregate QoS expectations + * for the pm_qos_class of parameters and initializes the pm_qos_request + * handle. Caller needs to save this handle for later use in updates and + * removal. + */ + +void pm_qos_add_request(struct pm_qos_request *req, + int pm_qos_class, s32 value) +{ + if (!req) /*guard against callers passing in null */ + return; + + if (pm_qos_request_active(req)) { + WARN(1, KERN_ERR "pm_qos_add_request() called for already added request\n"); + return; + } + req->pm_qos_class = pm_qos_class; + INIT_DELAYED_WORK(&req->work, pm_qos_work_fn); + trace_pm_qos_add_request(pm_qos_class, value); + pm_qos_update_target(pm_qos_array[pm_qos_class]->constraints, + &req->node, PM_QOS_ADD_REQ, value); +} +EXPORT_SYMBOL_GPL(pm_qos_add_request); + +/** + * pm_qos_update_request - modifies an existing qos request + * @req : handle to list element holding a pm_qos request to use + * @value: defines the qos request + * + * Updates an existing qos request for the pm_qos_class of parameters along + * with updating the target pm_qos_class value. + * + * Attempts are made to make this code callable on hot code paths. + */ +void pm_qos_update_request(struct pm_qos_request *req, + s32 new_value) +{ + if (!req) /*guard against callers passing in null */ + return; + + if (!pm_qos_request_active(req)) { + WARN(1, KERN_ERR "pm_qos_update_request() called for unknown object\n"); + return; + } + + cancel_delayed_work_sync(&req->work); + __pm_qos_update_request(req, new_value); +} +EXPORT_SYMBOL_GPL(pm_qos_update_request); + +/** + * pm_qos_update_request_timeout - modifies an existing qos request temporarily. + * @req : handle to list element holding a pm_qos request to use + * @new_value: defines the temporal qos request + * @timeout_us: the effective duration of this qos request in usecs. + * + * After timeout_us, this qos request is cancelled automatically. + */ +void pm_qos_update_request_timeout(struct pm_qos_request *req, s32 new_value, + unsigned long timeout_us) +{ + if (!req) + return; + if (WARN(!pm_qos_request_active(req), + "%s called for unknown object.", __func__)) + return; + + cancel_delayed_work_sync(&req->work); + + trace_pm_qos_update_request_timeout(req->pm_qos_class, + new_value, timeout_us); + if (new_value != req->node.prio) + pm_qos_update_target( + pm_qos_array[req->pm_qos_class]->constraints, + &req->node, PM_QOS_UPDATE_REQ, new_value); + + schedule_delayed_work(&req->work, usecs_to_jiffies(timeout_us)); +} + +/** + * pm_qos_remove_request - modifies an existing qos request + * @req: handle to request list element + * + * Will remove pm qos request from the list of constraints and + * recompute the current target value for the pm_qos_class. Call this + * on slow code paths. + */ +void pm_qos_remove_request(struct pm_qos_request *req) +{ + if (!req) /*guard against callers passing in null */ + return; + /* silent return to keep pcm code cleaner */ + + if (!pm_qos_request_active(req)) { + WARN(1, KERN_ERR "pm_qos_remove_request() called for unknown object\n"); + return; + } + + cancel_delayed_work_sync(&req->work); + + trace_pm_qos_remove_request(req->pm_qos_class, PM_QOS_DEFAULT_VALUE); + pm_qos_update_target(pm_qos_array[req->pm_qos_class]->constraints, + &req->node, PM_QOS_REMOVE_REQ, + PM_QOS_DEFAULT_VALUE); + memset(req, 0, sizeof(*req)); +} +EXPORT_SYMBOL_GPL(pm_qos_remove_request); + +/** + * pm_qos_add_notifier - sets notification entry for changes to target value + * @pm_qos_class: identifies which qos target changes should be notified. + * @notifier: notifier block managed by caller. + * + * will register the notifier into a notification chain that gets called + * upon changes to the pm_qos_class target value. + */ +int pm_qos_add_notifier(int pm_qos_class, struct notifier_block *notifier) +{ + int retval; + + retval = blocking_notifier_chain_register( + pm_qos_array[pm_qos_class]->constraints->notifiers, + notifier); + + return retval; +} +EXPORT_SYMBOL_GPL(pm_qos_add_notifier); + +/** + * pm_qos_remove_notifier - deletes notification entry from chain. + * @pm_qos_class: identifies which qos target changes are notified. + * @notifier: notifier block to be removed. + * + * will remove the notifier from the notification chain that gets called + * upon changes to the pm_qos_class target value. + */ +int pm_qos_remove_notifier(int pm_qos_class, struct notifier_block *notifier) +{ + int retval; + + retval = blocking_notifier_chain_unregister( + pm_qos_array[pm_qos_class]->constraints->notifiers, + notifier); + + return retval; +} +EXPORT_SYMBOL_GPL(pm_qos_remove_notifier); + +/* User space interface to PM QoS classes via misc devices */ +static int register_pm_qos_misc(struct pm_qos_object *qos, struct dentry *d) +{ + qos->pm_qos_power_miscdev.minor = MISC_DYNAMIC_MINOR; + qos->pm_qos_power_miscdev.name = qos->name; + qos->pm_qos_power_miscdev.fops = &pm_qos_power_fops; + + if (d) { + (void)debugfs_create_file(qos->name, S_IRUGO, d, + (void *)qos, &pm_qos_debug_fops); + } + + return misc_register(&qos->pm_qos_power_miscdev); +} + +static int find_pm_qos_object_by_minor(int minor) +{ + int pm_qos_class; + + for (pm_qos_class = PM_QOS_CPU_DMA_LATENCY; + pm_qos_class < PM_QOS_NUM_CLASSES; pm_qos_class++) { + if (minor == + pm_qos_array[pm_qos_class]->pm_qos_power_miscdev.minor) + return pm_qos_class; + } + return -1; +} + +static int pm_qos_power_open(struct inode *inode, struct file *filp) +{ + long pm_qos_class; + + pm_qos_class = find_pm_qos_object_by_minor(iminor(inode)); + if (pm_qos_class >= PM_QOS_CPU_DMA_LATENCY) { + struct pm_qos_request *req = kzalloc(sizeof(*req), GFP_KERNEL); + if (!req) + return -ENOMEM; + + pm_qos_add_request(req, pm_qos_class, PM_QOS_DEFAULT_VALUE); + filp->private_data = req; + + return 0; + } + return -EPERM; +} + +static int pm_qos_power_release(struct inode *inode, struct file *filp) +{ + struct pm_qos_request *req; + + req = filp->private_data; + pm_qos_remove_request(req); + kfree(req); + + return 0; +} + + +static ssize_t pm_qos_power_read(struct file *filp, char __user *buf, + size_t count, loff_t *f_pos) +{ + s32 value; + unsigned long flags; + struct pm_qos_request *req = filp->private_data; + + if (!req) + return -EINVAL; + if (!pm_qos_request_active(req)) + return -EINVAL; + + spin_lock_irqsave(&pm_qos_lock, flags); + value = pm_qos_get_value(pm_qos_array[req->pm_qos_class]->constraints); + spin_unlock_irqrestore(&pm_qos_lock, flags); + + return simple_read_from_buffer(buf, count, f_pos, &value, sizeof(s32)); +} + +static ssize_t pm_qos_power_write(struct file *filp, const char __user *buf, + size_t count, loff_t *f_pos) +{ + s32 value; + struct pm_qos_request *req; + + if (count == sizeof(s32)) { + if (copy_from_user(&value, buf, sizeof(s32))) + return -EFAULT; + } else { + int ret; + + ret = kstrtos32_from_user(buf, count, 16, &value); + if (ret) + return ret; + } + + req = filp->private_data; + pm_qos_update_request(req, value); + + return count; +} + + +static int __init pm_qos_power_init(void) +{ + int ret = 0; + int i; + struct dentry *d; + + BUILD_BUG_ON(ARRAY_SIZE(pm_qos_array) != PM_QOS_NUM_CLASSES); + + d = debugfs_create_dir("pm_qos", NULL); + if (IS_ERR_OR_NULL(d)) + d = NULL; + + for (i = PM_QOS_CPU_DMA_LATENCY; i < PM_QOS_NUM_CLASSES; i++) { + ret = register_pm_qos_misc(pm_qos_array[i], d); + if (ret < 0) { + printk(KERN_ERR "pm_qos_param: %s setup failed\n", + pm_qos_array[i]->name); + return ret; + } + } + + return ret; +} + +late_initcall(pm_qos_power_init); diff --git a/kernel/kernel/power/snapshot.c b/kernel/kernel/power/snapshot.c new file mode 100644 index 000000000..5235dd4e1 --- /dev/null +++ b/kernel/kernel/power/snapshot.c @@ -0,0 +1,2607 @@ +/* + * linux/kernel/power/snapshot.c + * + * This file provides system snapshot/restore functionality for swsusp. + * + * Copyright (C) 1998-2005 Pavel Machek + * Copyright (C) 2006 Rafael J. Wysocki + * + * This file is released under the GPLv2. + * + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include + +#include "power.h" + +static int swsusp_page_is_free(struct page *); +static void swsusp_set_page_forbidden(struct page *); +static void swsusp_unset_page_forbidden(struct page *); + +/* + * Number of bytes to reserve for memory allocations made by device drivers + * from their ->freeze() and ->freeze_noirq() callbacks so that they don't + * cause image creation to fail (tunable via /sys/power/reserved_size). + */ +unsigned long reserved_size; + +void __init hibernate_reserved_size_init(void) +{ + reserved_size = SPARE_PAGES * PAGE_SIZE; +} + +/* + * Preferred image size in bytes (tunable via /sys/power/image_size). + * When it is set to N, swsusp will do its best to ensure the image + * size will not exceed N bytes, but if that is impossible, it will + * try to create the smallest image possible. + */ +unsigned long image_size; + +void __init hibernate_image_size_init(void) +{ + image_size = ((totalram_pages * 2) / 5) * PAGE_SIZE; +} + +/* List of PBEs needed for restoring the pages that were allocated before + * the suspend and included in the suspend image, but have also been + * allocated by the "resume" kernel, so their contents cannot be written + * directly to their "original" page frames. + */ +struct pbe *restore_pblist; + +/* Pointer to an auxiliary buffer (1 page) */ +static void *buffer; + +/** + * @safe_needed - on resume, for storing the PBE list and the image, + * we can only use memory pages that do not conflict with the pages + * used before suspend. The unsafe pages have PageNosaveFree set + * and we count them using unsafe_pages. + * + * Each allocated image page is marked as PageNosave and PageNosaveFree + * so that swsusp_free() can release it. + */ + +#define PG_ANY 0 +#define PG_SAFE 1 +#define PG_UNSAFE_CLEAR 1 +#define PG_UNSAFE_KEEP 0 + +static unsigned int allocated_unsafe_pages; + +static void *get_image_page(gfp_t gfp_mask, int safe_needed) +{ + void *res; + + res = (void *)get_zeroed_page(gfp_mask); + if (safe_needed) + while (res && swsusp_page_is_free(virt_to_page(res))) { + /* The page is unsafe, mark it for swsusp_free() */ + swsusp_set_page_forbidden(virt_to_page(res)); + allocated_unsafe_pages++; + res = (void *)get_zeroed_page(gfp_mask); + } + if (res) { + swsusp_set_page_forbidden(virt_to_page(res)); + swsusp_set_page_free(virt_to_page(res)); + } + return res; +} + +unsigned long get_safe_page(gfp_t gfp_mask) +{ + return (unsigned long)get_image_page(gfp_mask, PG_SAFE); +} + +static struct page *alloc_image_page(gfp_t gfp_mask) +{ + struct page *page; + + page = alloc_page(gfp_mask); + if (page) { + swsusp_set_page_forbidden(page); + swsusp_set_page_free(page); + } + return page; +} + +/** + * free_image_page - free page represented by @addr, allocated with + * get_image_page (page flags set by it must be cleared) + */ + +static inline void free_image_page(void *addr, int clear_nosave_free) +{ + struct page *page; + + BUG_ON(!virt_addr_valid(addr)); + + page = virt_to_page(addr); + + swsusp_unset_page_forbidden(page); + if (clear_nosave_free) + swsusp_unset_page_free(page); + + __free_page(page); +} + +/* struct linked_page is used to build chains of pages */ + +#define LINKED_PAGE_DATA_SIZE (PAGE_SIZE - sizeof(void *)) + +struct linked_page { + struct linked_page *next; + char data[LINKED_PAGE_DATA_SIZE]; +} __packed; + +static inline void +free_list_of_pages(struct linked_page *list, int clear_page_nosave) +{ + while (list) { + struct linked_page *lp = list->next; + + free_image_page(list, clear_page_nosave); + list = lp; + } +} + +/** + * struct chain_allocator is used for allocating small objects out of + * a linked list of pages called 'the chain'. + * + * The chain grows each time when there is no room for a new object in + * the current page. The allocated objects cannot be freed individually. + * It is only possible to free them all at once, by freeing the entire + * chain. + * + * NOTE: The chain allocator may be inefficient if the allocated objects + * are not much smaller than PAGE_SIZE. + */ + +struct chain_allocator { + struct linked_page *chain; /* the chain */ + unsigned int used_space; /* total size of objects allocated out + * of the current page + */ + gfp_t gfp_mask; /* mask for allocating pages */ + int safe_needed; /* if set, only "safe" pages are allocated */ +}; + +static void +chain_init(struct chain_allocator *ca, gfp_t gfp_mask, int safe_needed) +{ + ca->chain = NULL; + ca->used_space = LINKED_PAGE_DATA_SIZE; + ca->gfp_mask = gfp_mask; + ca->safe_needed = safe_needed; +} + +static void *chain_alloc(struct chain_allocator *ca, unsigned int size) +{ + void *ret; + + if (LINKED_PAGE_DATA_SIZE - ca->used_space < size) { + struct linked_page *lp; + + lp = get_image_page(ca->gfp_mask, ca->safe_needed); + if (!lp) + return NULL; + + lp->next = ca->chain; + ca->chain = lp; + ca->used_space = 0; + } + ret = ca->chain->data + ca->used_space; + ca->used_space += size; + return ret; +} + +/** + * Data types related to memory bitmaps. + * + * Memory bitmap is a structure consiting of many linked lists of + * objects. The main list's elements are of type struct zone_bitmap + * and each of them corresonds to one zone. For each zone bitmap + * object there is a list of objects of type struct bm_block that + * represent each blocks of bitmap in which information is stored. + * + * struct memory_bitmap contains a pointer to the main list of zone + * bitmap objects, a struct bm_position used for browsing the bitmap, + * and a pointer to the list of pages used for allocating all of the + * zone bitmap objects and bitmap block objects. + * + * NOTE: It has to be possible to lay out the bitmap in memory + * using only allocations of order 0. Additionally, the bitmap is + * designed to work with arbitrary number of zones (this is over the + * top for now, but let's avoid making unnecessary assumptions ;-). + * + * struct zone_bitmap contains a pointer to a list of bitmap block + * objects and a pointer to the bitmap block object that has been + * most recently used for setting bits. Additionally, it contains the + * pfns that correspond to the start and end of the represented zone. + * + * struct bm_block contains a pointer to the memory page in which + * information is stored (in the form of a block of bitmap) + * It also contains the pfns that correspond to the start and end of + * the represented memory area. + * + * The memory bitmap is organized as a radix tree to guarantee fast random + * access to the bits. There is one radix tree for each zone (as returned + * from create_mem_extents). + * + * One radix tree is represented by one struct mem_zone_bm_rtree. There are + * two linked lists for the nodes of the tree, one for the inner nodes and + * one for the leave nodes. The linked leave nodes are used for fast linear + * access of the memory bitmap. + * + * The struct rtree_node represents one node of the radix tree. + */ + +#define BM_END_OF_MAP (~0UL) + +#define BM_BITS_PER_BLOCK (PAGE_SIZE * BITS_PER_BYTE) +#define BM_BLOCK_SHIFT (PAGE_SHIFT + 3) +#define BM_BLOCK_MASK ((1UL << BM_BLOCK_SHIFT) - 1) + +/* + * struct rtree_node is a wrapper struct to link the nodes + * of the rtree together for easy linear iteration over + * bits and easy freeing + */ +struct rtree_node { + struct list_head list; + unsigned long *data; +}; + +/* + * struct mem_zone_bm_rtree represents a bitmap used for one + * populated memory zone. + */ +struct mem_zone_bm_rtree { + struct list_head list; /* Link Zones together */ + struct list_head nodes; /* Radix Tree inner nodes */ + struct list_head leaves; /* Radix Tree leaves */ + unsigned long start_pfn; /* Zone start page frame */ + unsigned long end_pfn; /* Zone end page frame + 1 */ + struct rtree_node *rtree; /* Radix Tree Root */ + int levels; /* Number of Radix Tree Levels */ + unsigned int blocks; /* Number of Bitmap Blocks */ +}; + +/* strcut bm_position is used for browsing memory bitmaps */ + +struct bm_position { + struct mem_zone_bm_rtree *zone; + struct rtree_node *node; + unsigned long node_pfn; + int node_bit; +}; + +struct memory_bitmap { + struct list_head zones; + struct linked_page *p_list; /* list of pages used to store zone + * bitmap objects and bitmap block + * objects + */ + struct bm_position cur; /* most recently used bit position */ +}; + +/* Functions that operate on memory bitmaps */ + +#define BM_ENTRIES_PER_LEVEL (PAGE_SIZE / sizeof(unsigned long)) +#if BITS_PER_LONG == 32 +#define BM_RTREE_LEVEL_SHIFT (PAGE_SHIFT - 2) +#else +#define BM_RTREE_LEVEL_SHIFT (PAGE_SHIFT - 3) +#endif +#define BM_RTREE_LEVEL_MASK ((1UL << BM_RTREE_LEVEL_SHIFT) - 1) + +/* + * alloc_rtree_node - Allocate a new node and add it to the radix tree. + * + * This function is used to allocate inner nodes as well as the + * leave nodes of the radix tree. It also adds the node to the + * corresponding linked list passed in by the *list parameter. + */ +static struct rtree_node *alloc_rtree_node(gfp_t gfp_mask, int safe_needed, + struct chain_allocator *ca, + struct list_head *list) +{ + struct rtree_node *node; + + node = chain_alloc(ca, sizeof(struct rtree_node)); + if (!node) + return NULL; + + node->data = get_image_page(gfp_mask, safe_needed); + if (!node->data) + return NULL; + + list_add_tail(&node->list, list); + + return node; +} + +/* + * add_rtree_block - Add a new leave node to the radix tree + * + * The leave nodes need to be allocated in order to keep the leaves + * linked list in order. This is guaranteed by the zone->blocks + * counter. + */ +static int add_rtree_block(struct mem_zone_bm_rtree *zone, gfp_t gfp_mask, + int safe_needed, struct chain_allocator *ca) +{ + struct rtree_node *node, *block, **dst; + unsigned int levels_needed, block_nr; + int i; + + block_nr = zone->blocks; + levels_needed = 0; + + /* How many levels do we need for this block nr? */ + while (block_nr) { + levels_needed += 1; + block_nr >>= BM_RTREE_LEVEL_SHIFT; + } + + /* Make sure the rtree has enough levels */ + for (i = zone->levels; i < levels_needed; i++) { + node = alloc_rtree_node(gfp_mask, safe_needed, ca, + &zone->nodes); + if (!node) + return -ENOMEM; + + node->data[0] = (unsigned long)zone->rtree; + zone->rtree = node; + zone->levels += 1; + } + + /* Allocate new block */ + block = alloc_rtree_node(gfp_mask, safe_needed, ca, &zone->leaves); + if (!block) + return -ENOMEM; + + /* Now walk the rtree to insert the block */ + node = zone->rtree; + dst = &zone->rtree; + block_nr = zone->blocks; + for (i = zone->levels; i > 0; i--) { + int index; + + if (!node) { + node = alloc_rtree_node(gfp_mask, safe_needed, ca, + &zone->nodes); + if (!node) + return -ENOMEM; + *dst = node; + } + + index = block_nr >> ((i - 1) * BM_RTREE_LEVEL_SHIFT); + index &= BM_RTREE_LEVEL_MASK; + dst = (struct rtree_node **)&((*dst)->data[index]); + node = *dst; + } + + zone->blocks += 1; + *dst = block; + + return 0; +} + +static void free_zone_bm_rtree(struct mem_zone_bm_rtree *zone, + int clear_nosave_free); + +/* + * create_zone_bm_rtree - create a radix tree for one zone + * + * Allocated the mem_zone_bm_rtree structure and initializes it. + * This function also allocated and builds the radix tree for the + * zone. + */ +static struct mem_zone_bm_rtree * +create_zone_bm_rtree(gfp_t gfp_mask, int safe_needed, + struct chain_allocator *ca, + unsigned long start, unsigned long end) +{ + struct mem_zone_bm_rtree *zone; + unsigned int i, nr_blocks; + unsigned long pages; + + pages = end - start; + zone = chain_alloc(ca, sizeof(struct mem_zone_bm_rtree)); + if (!zone) + return NULL; + + INIT_LIST_HEAD(&zone->nodes); + INIT_LIST_HEAD(&zone->leaves); + zone->start_pfn = start; + zone->end_pfn = end; + nr_blocks = DIV_ROUND_UP(pages, BM_BITS_PER_BLOCK); + + for (i = 0; i < nr_blocks; i++) { + if (add_rtree_block(zone, gfp_mask, safe_needed, ca)) { + free_zone_bm_rtree(zone, PG_UNSAFE_CLEAR); + return NULL; + } + } + + return zone; +} + +/* + * free_zone_bm_rtree - Free the memory of the radix tree + * + * Free all node pages of the radix tree. The mem_zone_bm_rtree + * structure itself is not freed here nor are the rtree_node + * structs. + */ +static void free_zone_bm_rtree(struct mem_zone_bm_rtree *zone, + int clear_nosave_free) +{ + struct rtree_node *node; + + list_for_each_entry(node, &zone->nodes, list) + free_image_page(node->data, clear_nosave_free); + + list_for_each_entry(node, &zone->leaves, list) + free_image_page(node->data, clear_nosave_free); +} + +static void memory_bm_position_reset(struct memory_bitmap *bm) +{ + bm->cur.zone = list_entry(bm->zones.next, struct mem_zone_bm_rtree, + list); + bm->cur.node = list_entry(bm->cur.zone->leaves.next, + struct rtree_node, list); + bm->cur.node_pfn = 0; + bm->cur.node_bit = 0; +} + +static void memory_bm_free(struct memory_bitmap *bm, int clear_nosave_free); + +struct mem_extent { + struct list_head hook; + unsigned long start; + unsigned long end; +}; + +/** + * free_mem_extents - free a list of memory extents + * @list - list of extents to empty + */ +static void free_mem_extents(struct list_head *list) +{ + struct mem_extent *ext, *aux; + + list_for_each_entry_safe(ext, aux, list, hook) { + list_del(&ext->hook); + kfree(ext); + } +} + +/** + * create_mem_extents - create a list of memory extents representing + * contiguous ranges of PFNs + * @list - list to put the extents into + * @gfp_mask - mask to use for memory allocations + */ +static int create_mem_extents(struct list_head *list, gfp_t gfp_mask) +{ + struct zone *zone; + + INIT_LIST_HEAD(list); + + for_each_populated_zone(zone) { + unsigned long zone_start, zone_end; + struct mem_extent *ext, *cur, *aux; + + zone_start = zone->zone_start_pfn; + zone_end = zone_end_pfn(zone); + + list_for_each_entry(ext, list, hook) + if (zone_start <= ext->end) + break; + + if (&ext->hook == list || zone_end < ext->start) { + /* New extent is necessary */ + struct mem_extent *new_ext; + + new_ext = kzalloc(sizeof(struct mem_extent), gfp_mask); + if (!new_ext) { + free_mem_extents(list); + return -ENOMEM; + } + new_ext->start = zone_start; + new_ext->end = zone_end; + list_add_tail(&new_ext->hook, &ext->hook); + continue; + } + + /* Merge this zone's range of PFNs with the existing one */ + if (zone_start < ext->start) + ext->start = zone_start; + if (zone_end > ext->end) + ext->end = zone_end; + + /* More merging may be possible */ + cur = ext; + list_for_each_entry_safe_continue(cur, aux, list, hook) { + if (zone_end < cur->start) + break; + if (zone_end < cur->end) + ext->end = cur->end; + list_del(&cur->hook); + kfree(cur); + } + } + + return 0; +} + +/** + * memory_bm_create - allocate memory for a memory bitmap + */ +static int +memory_bm_create(struct memory_bitmap *bm, gfp_t gfp_mask, int safe_needed) +{ + struct chain_allocator ca; + struct list_head mem_extents; + struct mem_extent *ext; + int error; + + chain_init(&ca, gfp_mask, safe_needed); + INIT_LIST_HEAD(&bm->zones); + + error = create_mem_extents(&mem_extents, gfp_mask); + if (error) + return error; + + list_for_each_entry(ext, &mem_extents, hook) { + struct mem_zone_bm_rtree *zone; + + zone = create_zone_bm_rtree(gfp_mask, safe_needed, &ca, + ext->start, ext->end); + if (!zone) { + error = -ENOMEM; + goto Error; + } + list_add_tail(&zone->list, &bm->zones); + } + + bm->p_list = ca.chain; + memory_bm_position_reset(bm); + Exit: + free_mem_extents(&mem_extents); + return error; + + Error: + bm->p_list = ca.chain; + memory_bm_free(bm, PG_UNSAFE_CLEAR); + goto Exit; +} + +/** + * memory_bm_free - free memory occupied by the memory bitmap @bm + */ +static void memory_bm_free(struct memory_bitmap *bm, int clear_nosave_free) +{ + struct mem_zone_bm_rtree *zone; + + list_for_each_entry(zone, &bm->zones, list) + free_zone_bm_rtree(zone, clear_nosave_free); + + free_list_of_pages(bm->p_list, clear_nosave_free); + + INIT_LIST_HEAD(&bm->zones); +} + +/** + * memory_bm_find_bit - Find the bit for pfn in the memory + * bitmap + * + * Find the bit in the bitmap @bm that corresponds to given pfn. + * The cur.zone, cur.block and cur.node_pfn member of @bm are + * updated. + * It walks the radix tree to find the page which contains the bit for + * pfn and returns the bit position in **addr and *bit_nr. + */ +static int memory_bm_find_bit(struct memory_bitmap *bm, unsigned long pfn, + void **addr, unsigned int *bit_nr) +{ + struct mem_zone_bm_rtree *curr, *zone; + struct rtree_node *node; + int i, block_nr; + + zone = bm->cur.zone; + + if (pfn >= zone->start_pfn && pfn < zone->end_pfn) + goto zone_found; + + zone = NULL; + + /* Find the right zone */ + list_for_each_entry(curr, &bm->zones, list) { + if (pfn >= curr->start_pfn && pfn < curr->end_pfn) { + zone = curr; + break; + } + } + + if (!zone) + return -EFAULT; + +zone_found: + /* + * We have a zone. Now walk the radix tree to find the leave + * node for our pfn. + */ + + node = bm->cur.node; + if (((pfn - zone->start_pfn) & ~BM_BLOCK_MASK) == bm->cur.node_pfn) + goto node_found; + + node = zone->rtree; + block_nr = (pfn - zone->start_pfn) >> BM_BLOCK_SHIFT; + + for (i = zone->levels; i > 0; i--) { + int index; + + index = block_nr >> ((i - 1) * BM_RTREE_LEVEL_SHIFT); + index &= BM_RTREE_LEVEL_MASK; + BUG_ON(node->data[index] == 0); + node = (struct rtree_node *)node->data[index]; + } + +node_found: + /* Update last position */ + bm->cur.zone = zone; + bm->cur.node = node; + bm->cur.node_pfn = (pfn - zone->start_pfn) & ~BM_BLOCK_MASK; + + /* Set return values */ + *addr = node->data; + *bit_nr = (pfn - zone->start_pfn) & BM_BLOCK_MASK; + + return 0; +} + +static void memory_bm_set_bit(struct memory_bitmap *bm, unsigned long pfn) +{ + void *addr; + unsigned int bit; + int error; + + error = memory_bm_find_bit(bm, pfn, &addr, &bit); + BUG_ON(error); + set_bit(bit, addr); +} + +static int mem_bm_set_bit_check(struct memory_bitmap *bm, unsigned long pfn) +{ + void *addr; + unsigned int bit; + int error; + + error = memory_bm_find_bit(bm, pfn, &addr, &bit); + if (!error) + set_bit(bit, addr); + + return error; +} + +static void memory_bm_clear_bit(struct memory_bitmap *bm, unsigned long pfn) +{ + void *addr; + unsigned int bit; + int error; + + error = memory_bm_find_bit(bm, pfn, &addr, &bit); + BUG_ON(error); + clear_bit(bit, addr); +} + +static void memory_bm_clear_current(struct memory_bitmap *bm) +{ + int bit; + + bit = max(bm->cur.node_bit - 1, 0); + clear_bit(bit, bm->cur.node->data); +} + +static int memory_bm_test_bit(struct memory_bitmap *bm, unsigned long pfn) +{ + void *addr; + unsigned int bit; + int error; + + error = memory_bm_find_bit(bm, pfn, &addr, &bit); + BUG_ON(error); + return test_bit(bit, addr); +} + +static bool memory_bm_pfn_present(struct memory_bitmap *bm, unsigned long pfn) +{ + void *addr; + unsigned int bit; + + return !memory_bm_find_bit(bm, pfn, &addr, &bit); +} + +/* + * rtree_next_node - Jumps to the next leave node + * + * Sets the position to the beginning of the next node in the + * memory bitmap. This is either the next node in the current + * zone's radix tree or the first node in the radix tree of the + * next zone. + * + * Returns true if there is a next node, false otherwise. + */ +static bool rtree_next_node(struct memory_bitmap *bm) +{ + bm->cur.node = list_entry(bm->cur.node->list.next, + struct rtree_node, list); + if (&bm->cur.node->list != &bm->cur.zone->leaves) { + bm->cur.node_pfn += BM_BITS_PER_BLOCK; + bm->cur.node_bit = 0; + touch_softlockup_watchdog(); + return true; + } + + /* No more nodes, goto next zone */ + bm->cur.zone = list_entry(bm->cur.zone->list.next, + struct mem_zone_bm_rtree, list); + if (&bm->cur.zone->list != &bm->zones) { + bm->cur.node = list_entry(bm->cur.zone->leaves.next, + struct rtree_node, list); + bm->cur.node_pfn = 0; + bm->cur.node_bit = 0; + return true; + } + + /* No more zones */ + return false; +} + +/** + * memory_bm_rtree_next_pfn - Find the next set bit in the bitmap @bm + * + * Starting from the last returned position this function searches + * for the next set bit in the memory bitmap and returns its + * number. If no more bit is set BM_END_OF_MAP is returned. + * + * It is required to run memory_bm_position_reset() before the + * first call to this function. + */ +static unsigned long memory_bm_next_pfn(struct memory_bitmap *bm) +{ + unsigned long bits, pfn, pages; + int bit; + + do { + pages = bm->cur.zone->end_pfn - bm->cur.zone->start_pfn; + bits = min(pages - bm->cur.node_pfn, BM_BITS_PER_BLOCK); + bit = find_next_bit(bm->cur.node->data, bits, + bm->cur.node_bit); + if (bit < bits) { + pfn = bm->cur.zone->start_pfn + bm->cur.node_pfn + bit; + bm->cur.node_bit = bit + 1; + return pfn; + } + } while (rtree_next_node(bm)); + + return BM_END_OF_MAP; +} + +/** + * This structure represents a range of page frames the contents of which + * should not be saved during the suspend. + */ + +struct nosave_region { + struct list_head list; + unsigned long start_pfn; + unsigned long end_pfn; +}; + +static LIST_HEAD(nosave_regions); + +/** + * register_nosave_region - register a range of page frames the contents + * of which should not be saved during the suspend (to be used in the early + * initialization code) + */ + +void __init +__register_nosave_region(unsigned long start_pfn, unsigned long end_pfn, + int use_kmalloc) +{ + struct nosave_region *region; + + if (start_pfn >= end_pfn) + return; + + if (!list_empty(&nosave_regions)) { + /* Try to extend the previous region (they should be sorted) */ + region = list_entry(nosave_regions.prev, + struct nosave_region, list); + if (region->end_pfn == start_pfn) { + region->end_pfn = end_pfn; + goto Report; + } + } + if (use_kmalloc) { + /* during init, this shouldn't fail */ + region = kmalloc(sizeof(struct nosave_region), GFP_KERNEL); + BUG_ON(!region); + } else + /* This allocation cannot fail */ + region = memblock_virt_alloc(sizeof(struct nosave_region), 0); + region->start_pfn = start_pfn; + region->end_pfn = end_pfn; + list_add_tail(®ion->list, &nosave_regions); + Report: + printk(KERN_INFO "PM: Registered nosave memory: [mem %#010llx-%#010llx]\n", + (unsigned long long) start_pfn << PAGE_SHIFT, + ((unsigned long long) end_pfn << PAGE_SHIFT) - 1); +} + +/* + * Set bits in this map correspond to the page frames the contents of which + * should not be saved during the suspend. + */ +static struct memory_bitmap *forbidden_pages_map; + +/* Set bits in this map correspond to free page frames. */ +static struct memory_bitmap *free_pages_map; + +/* + * Each page frame allocated for creating the image is marked by setting the + * corresponding bits in forbidden_pages_map and free_pages_map simultaneously + */ + +void swsusp_set_page_free(struct page *page) +{ + if (free_pages_map) + memory_bm_set_bit(free_pages_map, page_to_pfn(page)); +} + +static int swsusp_page_is_free(struct page *page) +{ + return free_pages_map ? + memory_bm_test_bit(free_pages_map, page_to_pfn(page)) : 0; +} + +void swsusp_unset_page_free(struct page *page) +{ + if (free_pages_map) + memory_bm_clear_bit(free_pages_map, page_to_pfn(page)); +} + +static void swsusp_set_page_forbidden(struct page *page) +{ + if (forbidden_pages_map) + memory_bm_set_bit(forbidden_pages_map, page_to_pfn(page)); +} + +int swsusp_page_is_forbidden(struct page *page) +{ + return forbidden_pages_map ? + memory_bm_test_bit(forbidden_pages_map, page_to_pfn(page)) : 0; +} + +static void swsusp_unset_page_forbidden(struct page *page) +{ + if (forbidden_pages_map) + memory_bm_clear_bit(forbidden_pages_map, page_to_pfn(page)); +} + +/** + * mark_nosave_pages - set bits corresponding to the page frames the + * contents of which should not be saved in a given bitmap. + */ + +static void mark_nosave_pages(struct memory_bitmap *bm) +{ + struct nosave_region *region; + + if (list_empty(&nosave_regions)) + return; + + list_for_each_entry(region, &nosave_regions, list) { + unsigned long pfn; + + pr_debug("PM: Marking nosave pages: [mem %#010llx-%#010llx]\n", + (unsigned long long) region->start_pfn << PAGE_SHIFT, + ((unsigned long long) region->end_pfn << PAGE_SHIFT) + - 1); + + for (pfn = region->start_pfn; pfn < region->end_pfn; pfn++) + if (pfn_valid(pfn)) { + /* + * It is safe to ignore the result of + * mem_bm_set_bit_check() here, since we won't + * touch the PFNs for which the error is + * returned anyway. + */ + mem_bm_set_bit_check(bm, pfn); + } + } +} + +/** + * create_basic_memory_bitmaps - create bitmaps needed for marking page + * frames that should not be saved and free page frames. The pointers + * forbidden_pages_map and free_pages_map are only modified if everything + * goes well, because we don't want the bits to be used before both bitmaps + * are set up. + */ + +int create_basic_memory_bitmaps(void) +{ + struct memory_bitmap *bm1, *bm2; + int error = 0; + + if (forbidden_pages_map && free_pages_map) + return 0; + else + BUG_ON(forbidden_pages_map || free_pages_map); + + bm1 = kzalloc(sizeof(struct memory_bitmap), GFP_KERNEL); + if (!bm1) + return -ENOMEM; + + error = memory_bm_create(bm1, GFP_KERNEL, PG_ANY); + if (error) + goto Free_first_object; + + bm2 = kzalloc(sizeof(struct memory_bitmap), GFP_KERNEL); + if (!bm2) + goto Free_first_bitmap; + + error = memory_bm_create(bm2, GFP_KERNEL, PG_ANY); + if (error) + goto Free_second_object; + + forbidden_pages_map = bm1; + free_pages_map = bm2; + mark_nosave_pages(forbidden_pages_map); + + pr_debug("PM: Basic memory bitmaps created\n"); + + return 0; + + Free_second_object: + kfree(bm2); + Free_first_bitmap: + memory_bm_free(bm1, PG_UNSAFE_CLEAR); + Free_first_object: + kfree(bm1); + return -ENOMEM; +} + +/** + * free_basic_memory_bitmaps - free memory bitmaps allocated by + * create_basic_memory_bitmaps(). The auxiliary pointers are necessary + * so that the bitmaps themselves are not referred to while they are being + * freed. + */ + +void free_basic_memory_bitmaps(void) +{ + struct memory_bitmap *bm1, *bm2; + + if (WARN_ON(!(forbidden_pages_map && free_pages_map))) + return; + + bm1 = forbidden_pages_map; + bm2 = free_pages_map; + forbidden_pages_map = NULL; + free_pages_map = NULL; + memory_bm_free(bm1, PG_UNSAFE_CLEAR); + kfree(bm1); + memory_bm_free(bm2, PG_UNSAFE_CLEAR); + kfree(bm2); + + pr_debug("PM: Basic memory bitmaps freed\n"); +} + +/** + * snapshot_additional_pages - estimate the number of additional pages + * be needed for setting up the suspend image data structures for given + * zone (usually the returned value is greater than the exact number) + */ + +unsigned int snapshot_additional_pages(struct zone *zone) +{ + unsigned int rtree, nodes; + + rtree = nodes = DIV_ROUND_UP(zone->spanned_pages, BM_BITS_PER_BLOCK); + rtree += DIV_ROUND_UP(rtree * sizeof(struct rtree_node), + LINKED_PAGE_DATA_SIZE); + while (nodes > 1) { + nodes = DIV_ROUND_UP(nodes, BM_ENTRIES_PER_LEVEL); + rtree += nodes; + } + + return 2 * rtree; +} + +#ifdef CONFIG_HIGHMEM +/** + * count_free_highmem_pages - compute the total number of free highmem + * pages, system-wide. + */ + +static unsigned int count_free_highmem_pages(void) +{ + struct zone *zone; + unsigned int cnt = 0; + + for_each_populated_zone(zone) + if (is_highmem(zone)) + cnt += zone_page_state(zone, NR_FREE_PAGES); + + return cnt; +} + +/** + * saveable_highmem_page - Determine whether a highmem page should be + * included in the suspend image. + * + * We should save the page if it isn't Nosave or NosaveFree, or Reserved, + * and it isn't a part of a free chunk of pages. + */ +static struct page *saveable_highmem_page(struct zone *zone, unsigned long pfn) +{ + struct page *page; + + if (!pfn_valid(pfn)) + return NULL; + + page = pfn_to_page(pfn); + if (page_zone(page) != zone) + return NULL; + + BUG_ON(!PageHighMem(page)); + + if (swsusp_page_is_forbidden(page) || swsusp_page_is_free(page) || + PageReserved(page)) + return NULL; + + if (page_is_guard(page)) + return NULL; + + return page; +} + +/** + * count_highmem_pages - compute the total number of saveable highmem + * pages. + */ + +static unsigned int count_highmem_pages(void) +{ + struct zone *zone; + unsigned int n = 0; + + for_each_populated_zone(zone) { + unsigned long pfn, max_zone_pfn; + + if (!is_highmem(zone)) + continue; + + mark_free_pages(zone); + max_zone_pfn = zone_end_pfn(zone); + for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++) + if (saveable_highmem_page(zone, pfn)) + n++; + } + return n; +} +#else +static inline void *saveable_highmem_page(struct zone *z, unsigned long p) +{ + return NULL; +} +#endif /* CONFIG_HIGHMEM */ + +/** + * saveable_page - Determine whether a non-highmem page should be included + * in the suspend image. + * + * We should save the page if it isn't Nosave, and is not in the range + * of pages statically defined as 'unsaveable', and it isn't a part of + * a free chunk of pages. + */ +static struct page *saveable_page(struct zone *zone, unsigned long pfn) +{ + struct page *page; + + if (!pfn_valid(pfn)) + return NULL; + + page = pfn_to_page(pfn); + if (page_zone(page) != zone) + return NULL; + + BUG_ON(PageHighMem(page)); + + if (swsusp_page_is_forbidden(page) || swsusp_page_is_free(page)) + return NULL; + + if (PageReserved(page) + && (!kernel_page_present(page) || pfn_is_nosave(pfn))) + return NULL; + + if (page_is_guard(page)) + return NULL; + + return page; +} + +/** + * count_data_pages - compute the total number of saveable non-highmem + * pages. + */ + +static unsigned int count_data_pages(void) +{ + struct zone *zone; + unsigned long pfn, max_zone_pfn; + unsigned int n = 0; + + for_each_populated_zone(zone) { + if (is_highmem(zone)) + continue; + + mark_free_pages(zone); + max_zone_pfn = zone_end_pfn(zone); + for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++) + if (saveable_page(zone, pfn)) + n++; + } + return n; +} + +/* This is needed, because copy_page and memcpy are not usable for copying + * task structs. + */ +static inline void do_copy_page(long *dst, long *src) +{ + int n; + + for (n = PAGE_SIZE / sizeof(long); n; n--) + *dst++ = *src++; +} + + +/** + * safe_copy_page - check if the page we are going to copy is marked as + * present in the kernel page tables (this always is the case if + * CONFIG_DEBUG_PAGEALLOC is not set and in that case + * kernel_page_present() always returns 'true'). + */ +static void safe_copy_page(void *dst, struct page *s_page) +{ + if (kernel_page_present(s_page)) { + do_copy_page(dst, page_address(s_page)); + } else { + kernel_map_pages(s_page, 1, 1); + do_copy_page(dst, page_address(s_page)); + kernel_map_pages(s_page, 1, 0); + } +} + + +#ifdef CONFIG_HIGHMEM +static inline struct page * +page_is_saveable(struct zone *zone, unsigned long pfn) +{ + return is_highmem(zone) ? + saveable_highmem_page(zone, pfn) : saveable_page(zone, pfn); +} + +static void copy_data_page(unsigned long dst_pfn, unsigned long src_pfn) +{ + struct page *s_page, *d_page; + void *src, *dst; + + s_page = pfn_to_page(src_pfn); + d_page = pfn_to_page(dst_pfn); + if (PageHighMem(s_page)) { + src = kmap_atomic(s_page); + dst = kmap_atomic(d_page); + do_copy_page(dst, src); + kunmap_atomic(dst); + kunmap_atomic(src); + } else { + if (PageHighMem(d_page)) { + /* Page pointed to by src may contain some kernel + * data modified by kmap_atomic() + */ + safe_copy_page(buffer, s_page); + dst = kmap_atomic(d_page); + copy_page(dst, buffer); + kunmap_atomic(dst); + } else { + safe_copy_page(page_address(d_page), s_page); + } + } +} +#else +#define page_is_saveable(zone, pfn) saveable_page(zone, pfn) + +static inline void copy_data_page(unsigned long dst_pfn, unsigned long src_pfn) +{ + safe_copy_page(page_address(pfn_to_page(dst_pfn)), + pfn_to_page(src_pfn)); +} +#endif /* CONFIG_HIGHMEM */ + +static void +copy_data_pages(struct memory_bitmap *copy_bm, struct memory_bitmap *orig_bm) +{ + struct zone *zone; + unsigned long pfn; + + for_each_populated_zone(zone) { + unsigned long max_zone_pfn; + + mark_free_pages(zone); + max_zone_pfn = zone_end_pfn(zone); + for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++) + if (page_is_saveable(zone, pfn)) + memory_bm_set_bit(orig_bm, pfn); + } + memory_bm_position_reset(orig_bm); + memory_bm_position_reset(copy_bm); + for(;;) { + pfn = memory_bm_next_pfn(orig_bm); + if (unlikely(pfn == BM_END_OF_MAP)) + break; + copy_data_page(memory_bm_next_pfn(copy_bm), pfn); + } +} + +/* Total number of image pages */ +static unsigned int nr_copy_pages; +/* Number of pages needed for saving the original pfns of the image pages */ +static unsigned int nr_meta_pages; +/* + * Numbers of normal and highmem page frames allocated for hibernation image + * before suspending devices. + */ +unsigned int alloc_normal, alloc_highmem; +/* + * Memory bitmap used for marking saveable pages (during hibernation) or + * hibernation image pages (during restore) + */ +static struct memory_bitmap orig_bm; +/* + * Memory bitmap used during hibernation for marking allocated page frames that + * will contain copies of saveable pages. During restore it is initially used + * for marking hibernation image pages, but then the set bits from it are + * duplicated in @orig_bm and it is released. On highmem systems it is next + * used for marking "safe" highmem pages, but it has to be reinitialized for + * this purpose. + */ +static struct memory_bitmap copy_bm; + +/** + * swsusp_free - free pages allocated for the suspend. + * + * Suspend pages are alocated before the atomic copy is made, so we + * need to release them after the resume. + */ + +void swsusp_free(void) +{ + unsigned long fb_pfn, fr_pfn; + + if (!forbidden_pages_map || !free_pages_map) + goto out; + + memory_bm_position_reset(forbidden_pages_map); + memory_bm_position_reset(free_pages_map); + +loop: + fr_pfn = memory_bm_next_pfn(free_pages_map); + fb_pfn = memory_bm_next_pfn(forbidden_pages_map); + + /* + * Find the next bit set in both bitmaps. This is guaranteed to + * terminate when fb_pfn == fr_pfn == BM_END_OF_MAP. + */ + do { + if (fb_pfn < fr_pfn) + fb_pfn = memory_bm_next_pfn(forbidden_pages_map); + if (fr_pfn < fb_pfn) + fr_pfn = memory_bm_next_pfn(free_pages_map); + } while (fb_pfn != fr_pfn); + + if (fr_pfn != BM_END_OF_MAP && pfn_valid(fr_pfn)) { + struct page *page = pfn_to_page(fr_pfn); + + memory_bm_clear_current(forbidden_pages_map); + memory_bm_clear_current(free_pages_map); + __free_page(page); + goto loop; + } + +out: + nr_copy_pages = 0; + nr_meta_pages = 0; + restore_pblist = NULL; + buffer = NULL; + alloc_normal = 0; + alloc_highmem = 0; +} + +/* Helper functions used for the shrinking of memory. */ + +#define GFP_IMAGE (GFP_KERNEL | __GFP_NOWARN) + +/** + * preallocate_image_pages - Allocate a number of pages for hibernation image + * @nr_pages: Number of page frames to allocate. + * @mask: GFP flags to use for the allocation. + * + * Return value: Number of page frames actually allocated + */ +static unsigned long preallocate_image_pages(unsigned long nr_pages, gfp_t mask) +{ + unsigned long nr_alloc = 0; + + while (nr_pages > 0) { + struct page *page; + + page = alloc_image_page(mask); + if (!page) + break; + memory_bm_set_bit(©_bm, page_to_pfn(page)); + if (PageHighMem(page)) + alloc_highmem++; + else + alloc_normal++; + nr_pages--; + nr_alloc++; + } + + return nr_alloc; +} + +static unsigned long preallocate_image_memory(unsigned long nr_pages, + unsigned long avail_normal) +{ + unsigned long alloc; + + if (avail_normal <= alloc_normal) + return 0; + + alloc = avail_normal - alloc_normal; + if (nr_pages < alloc) + alloc = nr_pages; + + return preallocate_image_pages(alloc, GFP_IMAGE); +} + +#ifdef CONFIG_HIGHMEM +static unsigned long preallocate_image_highmem(unsigned long nr_pages) +{ + return preallocate_image_pages(nr_pages, GFP_IMAGE | __GFP_HIGHMEM); +} + +/** + * __fraction - Compute (an approximation of) x * (multiplier / base) + */ +static unsigned long __fraction(u64 x, u64 multiplier, u64 base) +{ + x *= multiplier; + do_div(x, base); + return (unsigned long)x; +} + +static unsigned long preallocate_highmem_fraction(unsigned long nr_pages, + unsigned long highmem, + unsigned long total) +{ + unsigned long alloc = __fraction(nr_pages, highmem, total); + + return preallocate_image_pages(alloc, GFP_IMAGE | __GFP_HIGHMEM); +} +#else /* CONFIG_HIGHMEM */ +static inline unsigned long preallocate_image_highmem(unsigned long nr_pages) +{ + return 0; +} + +static inline unsigned long preallocate_highmem_fraction(unsigned long nr_pages, + unsigned long highmem, + unsigned long total) +{ + return 0; +} +#endif /* CONFIG_HIGHMEM */ + +/** + * free_unnecessary_pages - Release preallocated pages not needed for the image + */ +static unsigned long free_unnecessary_pages(void) +{ + unsigned long save, to_free_normal, to_free_highmem, free; + + save = count_data_pages(); + if (alloc_normal >= save) { + to_free_normal = alloc_normal - save; + save = 0; + } else { + to_free_normal = 0; + save -= alloc_normal; + } + save += count_highmem_pages(); + if (alloc_highmem >= save) { + to_free_highmem = alloc_highmem - save; + } else { + to_free_highmem = 0; + save -= alloc_highmem; + if (to_free_normal > save) + to_free_normal -= save; + else + to_free_normal = 0; + } + free = to_free_normal + to_free_highmem; + + memory_bm_position_reset(©_bm); + + while (to_free_normal > 0 || to_free_highmem > 0) { + unsigned long pfn = memory_bm_next_pfn(©_bm); + struct page *page = pfn_to_page(pfn); + + if (PageHighMem(page)) { + if (!to_free_highmem) + continue; + to_free_highmem--; + alloc_highmem--; + } else { + if (!to_free_normal) + continue; + to_free_normal--; + alloc_normal--; + } + memory_bm_clear_bit(©_bm, pfn); + swsusp_unset_page_forbidden(page); + swsusp_unset_page_free(page); + __free_page(page); + } + + return free; +} + +/** + * minimum_image_size - Estimate the minimum acceptable size of an image + * @saveable: Number of saveable pages in the system. + * + * We want to avoid attempting to free too much memory too hard, so estimate the + * minimum acceptable size of a hibernation image to use as the lower limit for + * preallocating memory. + * + * We assume that the minimum image size should be proportional to + * + * [number of saveable pages] - [number of pages that can be freed in theory] + * + * where the second term is the sum of (1) reclaimable slab pages, (2) active + * and (3) inactive anonymous pages, (4) active and (5) inactive file pages, + * minus mapped file pages. + */ +static unsigned long minimum_image_size(unsigned long saveable) +{ + unsigned long size; + + size = global_page_state(NR_SLAB_RECLAIMABLE) + + global_page_state(NR_ACTIVE_ANON) + + global_page_state(NR_INACTIVE_ANON) + + global_page_state(NR_ACTIVE_FILE) + + global_page_state(NR_INACTIVE_FILE) + - global_page_state(NR_FILE_MAPPED); + + return saveable <= size ? 0 : saveable - size; +} + +/** + * hibernate_preallocate_memory - Preallocate memory for hibernation image + * + * To create a hibernation image it is necessary to make a copy of every page + * frame in use. We also need a number of page frames to be free during + * hibernation for allocations made while saving the image and for device + * drivers, in case they need to allocate memory from their hibernation + * callbacks (these two numbers are given by PAGES_FOR_IO (which is a rough + * estimate) and reserverd_size divided by PAGE_SIZE (which is tunable through + * /sys/power/reserved_size, respectively). To make this happen, we compute the + * total number of available page frames and allocate at least + * + * ([page frames total] + PAGES_FOR_IO + [metadata pages]) / 2 + * + 2 * DIV_ROUND_UP(reserved_size, PAGE_SIZE) + * + * of them, which corresponds to the maximum size of a hibernation image. + * + * If image_size is set below the number following from the above formula, + * the preallocation of memory is continued until the total number of saveable + * pages in the system is below the requested image size or the minimum + * acceptable image size returned by minimum_image_size(), whichever is greater. + */ +int hibernate_preallocate_memory(void) +{ + struct zone *zone; + unsigned long saveable, size, max_size, count, highmem, pages = 0; + unsigned long alloc, save_highmem, pages_highmem, avail_normal; + ktime_t start, stop; + int error; + + printk(KERN_INFO "PM: Preallocating image memory... "); + start = ktime_get(); + + error = memory_bm_create(&orig_bm, GFP_IMAGE, PG_ANY); + if (error) + goto err_out; + + error = memory_bm_create(©_bm, GFP_IMAGE, PG_ANY); + if (error) + goto err_out; + + alloc_normal = 0; + alloc_highmem = 0; + + /* Count the number of saveable data pages. */ + save_highmem = count_highmem_pages(); + saveable = count_data_pages(); + + /* + * Compute the total number of page frames we can use (count) and the + * number of pages needed for image metadata (size). + */ + count = saveable; + saveable += save_highmem; + highmem = save_highmem; + size = 0; + for_each_populated_zone(zone) { + size += snapshot_additional_pages(zone); + if (is_highmem(zone)) + highmem += zone_page_state(zone, NR_FREE_PAGES); + else + count += zone_page_state(zone, NR_FREE_PAGES); + } + avail_normal = count; + count += highmem; + count -= totalreserve_pages; + + /* Add number of pages required for page keys (s390 only). */ + size += page_key_additional_pages(saveable); + + /* Compute the maximum number of saveable pages to leave in memory. */ + max_size = (count - (size + PAGES_FOR_IO)) / 2 + - 2 * DIV_ROUND_UP(reserved_size, PAGE_SIZE); + /* Compute the desired number of image pages specified by image_size. */ + size = DIV_ROUND_UP(image_size, PAGE_SIZE); + if (size > max_size) + size = max_size; + /* + * If the desired number of image pages is at least as large as the + * current number of saveable pages in memory, allocate page frames for + * the image and we're done. + */ + if (size >= saveable) { + pages = preallocate_image_highmem(save_highmem); + pages += preallocate_image_memory(saveable - pages, avail_normal); + goto out; + } + + /* Estimate the minimum size of the image. */ + pages = minimum_image_size(saveable); + /* + * To avoid excessive pressure on the normal zone, leave room in it to + * accommodate an image of the minimum size (unless it's already too + * small, in which case don't preallocate pages from it at all). + */ + if (avail_normal > pages) + avail_normal -= pages; + else + avail_normal = 0; + if (size < pages) + size = min_t(unsigned long, pages, max_size); + + /* + * Let the memory management subsystem know that we're going to need a + * large number of page frames to allocate and make it free some memory. + * NOTE: If this is not done, performance will be hurt badly in some + * test cases. + */ + shrink_all_memory(saveable - size); + + /* + * The number of saveable pages in memory was too high, so apply some + * pressure to decrease it. First, make room for the largest possible + * image and fail if that doesn't work. Next, try to decrease the size + * of the image as much as indicated by 'size' using allocations from + * highmem and non-highmem zones separately. + */ + pages_highmem = preallocate_image_highmem(highmem / 2); + alloc = count - max_size; + if (alloc > pages_highmem) + alloc -= pages_highmem; + else + alloc = 0; + pages = preallocate_image_memory(alloc, avail_normal); + if (pages < alloc) { + /* We have exhausted non-highmem pages, try highmem. */ + alloc -= pages; + pages += pages_highmem; + pages_highmem = preallocate_image_highmem(alloc); + if (pages_highmem < alloc) + goto err_out; + pages += pages_highmem; + /* + * size is the desired number of saveable pages to leave in + * memory, so try to preallocate (all memory - size) pages. + */ + alloc = (count - pages) - size; + pages += preallocate_image_highmem(alloc); + } else { + /* + * There are approximately max_size saveable pages at this point + * and we want to reduce this number down to size. + */ + alloc = max_size - size; + size = preallocate_highmem_fraction(alloc, highmem, count); + pages_highmem += size; + alloc -= size; + size = preallocate_image_memory(alloc, avail_normal); + pages_highmem += preallocate_image_highmem(alloc - size); + pages += pages_highmem + size; + } + + /* + * We only need as many page frames for the image as there are saveable + * pages in memory, but we have allocated more. Release the excessive + * ones now. + */ + pages -= free_unnecessary_pages(); + + out: + stop = ktime_get(); + printk(KERN_CONT "done (allocated %lu pages)\n", pages); + swsusp_show_speed(start, stop, pages, "Allocated"); + + return 0; + + err_out: + printk(KERN_CONT "\n"); + swsusp_free(); + return -ENOMEM; +} + +#ifdef CONFIG_HIGHMEM +/** + * count_pages_for_highmem - compute the number of non-highmem pages + * that will be necessary for creating copies of highmem pages. + */ + +static unsigned int count_pages_for_highmem(unsigned int nr_highmem) +{ + unsigned int free_highmem = count_free_highmem_pages() + alloc_highmem; + + if (free_highmem >= nr_highmem) + nr_highmem = 0; + else + nr_highmem -= free_highmem; + + return nr_highmem; +} +#else +static unsigned int +count_pages_for_highmem(unsigned int nr_highmem) { return 0; } +#endif /* CONFIG_HIGHMEM */ + +/** + * enough_free_mem - Make sure we have enough free memory for the + * snapshot image. + */ + +static int enough_free_mem(unsigned int nr_pages, unsigned int nr_highmem) +{ + struct zone *zone; + unsigned int free = alloc_normal; + + for_each_populated_zone(zone) + if (!is_highmem(zone)) + free += zone_page_state(zone, NR_FREE_PAGES); + + nr_pages += count_pages_for_highmem(nr_highmem); + pr_debug("PM: Normal pages needed: %u + %u, available pages: %u\n", + nr_pages, PAGES_FOR_IO, free); + + return free > nr_pages + PAGES_FOR_IO; +} + +#ifdef CONFIG_HIGHMEM +/** + * get_highmem_buffer - if there are some highmem pages in the suspend + * image, we may need the buffer to copy them and/or load their data. + */ + +static inline int get_highmem_buffer(int safe_needed) +{ + buffer = get_image_page(GFP_ATOMIC | __GFP_COLD, safe_needed); + return buffer ? 0 : -ENOMEM; +} + +/** + * alloc_highmem_image_pages - allocate some highmem pages for the image. + * Try to allocate as many pages as needed, but if the number of free + * highmem pages is lesser than that, allocate them all. + */ + +static inline unsigned int +alloc_highmem_pages(struct memory_bitmap *bm, unsigned int nr_highmem) +{ + unsigned int to_alloc = count_free_highmem_pages(); + + if (to_alloc > nr_highmem) + to_alloc = nr_highmem; + + nr_highmem -= to_alloc; + while (to_alloc-- > 0) { + struct page *page; + + page = alloc_image_page(__GFP_HIGHMEM); + memory_bm_set_bit(bm, page_to_pfn(page)); + } + return nr_highmem; +} +#else +static inline int get_highmem_buffer(int safe_needed) { return 0; } + +static inline unsigned int +alloc_highmem_pages(struct memory_bitmap *bm, unsigned int n) { return 0; } +#endif /* CONFIG_HIGHMEM */ + +/** + * swsusp_alloc - allocate memory for the suspend image + * + * We first try to allocate as many highmem pages as there are + * saveable highmem pages in the system. If that fails, we allocate + * non-highmem pages for the copies of the remaining highmem ones. + * + * In this approach it is likely that the copies of highmem pages will + * also be located in the high memory, because of the way in which + * copy_data_pages() works. + */ + +static int +swsusp_alloc(struct memory_bitmap *orig_bm, struct memory_bitmap *copy_bm, + unsigned int nr_pages, unsigned int nr_highmem) +{ + if (nr_highmem > 0) { + if (get_highmem_buffer(PG_ANY)) + goto err_out; + if (nr_highmem > alloc_highmem) { + nr_highmem -= alloc_highmem; + nr_pages += alloc_highmem_pages(copy_bm, nr_highmem); + } + } + if (nr_pages > alloc_normal) { + nr_pages -= alloc_normal; + while (nr_pages-- > 0) { + struct page *page; + + page = alloc_image_page(GFP_ATOMIC | __GFP_COLD); + if (!page) + goto err_out; + memory_bm_set_bit(copy_bm, page_to_pfn(page)); + } + } + + return 0; + + err_out: + swsusp_free(); + return -ENOMEM; +} + +asmlinkage __visible int swsusp_save(void) +{ + unsigned int nr_pages, nr_highmem; + + printk(KERN_INFO "PM: Creating hibernation image:\n"); + + drain_local_pages(NULL); + nr_pages = count_data_pages(); + nr_highmem = count_highmem_pages(); + printk(KERN_INFO "PM: Need to copy %u pages\n", nr_pages + nr_highmem); + + if (!enough_free_mem(nr_pages, nr_highmem)) { + printk(KERN_ERR "PM: Not enough free memory\n"); + return -ENOMEM; + } + + if (swsusp_alloc(&orig_bm, ©_bm, nr_pages, nr_highmem)) { + printk(KERN_ERR "PM: Memory allocation failed\n"); + return -ENOMEM; + } + + /* During allocating of suspend pagedir, new cold pages may appear. + * Kill them. + */ + drain_local_pages(NULL); + copy_data_pages(©_bm, &orig_bm); + + /* + * End of critical section. From now on, we can write to memory, + * but we should not touch disk. This specially means we must _not_ + * touch swap space! Except we must write out our image of course. + */ + + nr_pages += nr_highmem; + nr_copy_pages = nr_pages; + nr_meta_pages = DIV_ROUND_UP(nr_pages * sizeof(long), PAGE_SIZE); + + printk(KERN_INFO "PM: Hibernation image created (%d pages copied)\n", + nr_pages); + + return 0; +} + +#ifndef CONFIG_ARCH_HIBERNATION_HEADER +static int init_header_complete(struct swsusp_info *info) +{ + memcpy(&info->uts, init_utsname(), sizeof(struct new_utsname)); + info->version_code = LINUX_VERSION_CODE; + return 0; +} + +static char *check_image_kernel(struct swsusp_info *info) +{ + if (info->version_code != LINUX_VERSION_CODE) + return "kernel version"; + if (strcmp(info->uts.sysname,init_utsname()->sysname)) + return "system type"; + if (strcmp(info->uts.release,init_utsname()->release)) + return "kernel release"; + if (strcmp(info->uts.version,init_utsname()->version)) + return "version"; + if (strcmp(info->uts.machine,init_utsname()->machine)) + return "machine"; + return NULL; +} +#endif /* CONFIG_ARCH_HIBERNATION_HEADER */ + +unsigned long snapshot_get_image_size(void) +{ + return nr_copy_pages + nr_meta_pages + 1; +} + +static int init_header(struct swsusp_info *info) +{ + memset(info, 0, sizeof(struct swsusp_info)); + info->num_physpages = get_num_physpages(); + info->image_pages = nr_copy_pages; + info->pages = snapshot_get_image_size(); + info->size = info->pages; + info->size <<= PAGE_SHIFT; + return init_header_complete(info); +} + +/** + * pack_pfns - pfns corresponding to the set bits found in the bitmap @bm + * are stored in the array @buf[] (1 page at a time) + */ + +static inline void +pack_pfns(unsigned long *buf, struct memory_bitmap *bm) +{ + int j; + + for (j = 0; j < PAGE_SIZE / sizeof(long); j++) { + buf[j] = memory_bm_next_pfn(bm); + if (unlikely(buf[j] == BM_END_OF_MAP)) + break; + /* Save page key for data page (s390 only). */ + page_key_read(buf + j); + } +} + +/** + * snapshot_read_next - used for reading the system memory snapshot. + * + * On the first call to it @handle should point to a zeroed + * snapshot_handle structure. The structure gets updated and a pointer + * to it should be passed to this function every next time. + * + * On success the function returns a positive number. Then, the caller + * is allowed to read up to the returned number of bytes from the memory + * location computed by the data_of() macro. + * + * The function returns 0 to indicate the end of data stream condition, + * and a negative number is returned on error. In such cases the + * structure pointed to by @handle is not updated and should not be used + * any more. + */ + +int snapshot_read_next(struct snapshot_handle *handle) +{ + if (handle->cur > nr_meta_pages + nr_copy_pages) + return 0; + + if (!buffer) { + /* This makes the buffer be freed by swsusp_free() */ + buffer = get_image_page(GFP_ATOMIC, PG_ANY); + if (!buffer) + return -ENOMEM; + } + if (!handle->cur) { + int error; + + error = init_header((struct swsusp_info *)buffer); + if (error) + return error; + handle->buffer = buffer; + memory_bm_position_reset(&orig_bm); + memory_bm_position_reset(©_bm); + } else if (handle->cur <= nr_meta_pages) { + clear_page(buffer); + pack_pfns(buffer, &orig_bm); + } else { + struct page *page; + + page = pfn_to_page(memory_bm_next_pfn(©_bm)); + if (PageHighMem(page)) { + /* Highmem pages are copied to the buffer, + * because we can't return with a kmapped + * highmem page (we may not be called again). + */ + void *kaddr; + + kaddr = kmap_atomic(page); + copy_page(buffer, kaddr); + kunmap_atomic(kaddr); + handle->buffer = buffer; + } else { + handle->buffer = page_address(page); + } + } + handle->cur++; + return PAGE_SIZE; +} + +/** + * mark_unsafe_pages - mark the pages that cannot be used for storing + * the image during resume, because they conflict with the pages that + * had been used before suspend + */ + +static int mark_unsafe_pages(struct memory_bitmap *bm) +{ + struct zone *zone; + unsigned long pfn, max_zone_pfn; + + /* Clear page flags */ + for_each_populated_zone(zone) { + max_zone_pfn = zone_end_pfn(zone); + for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++) + if (pfn_valid(pfn)) + swsusp_unset_page_free(pfn_to_page(pfn)); + } + + /* Mark pages that correspond to the "original" pfns as "unsafe" */ + memory_bm_position_reset(bm); + do { + pfn = memory_bm_next_pfn(bm); + if (likely(pfn != BM_END_OF_MAP)) { + if (likely(pfn_valid(pfn))) + swsusp_set_page_free(pfn_to_page(pfn)); + else + return -EFAULT; + } + } while (pfn != BM_END_OF_MAP); + + allocated_unsafe_pages = 0; + + return 0; +} + +static void +duplicate_memory_bitmap(struct memory_bitmap *dst, struct memory_bitmap *src) +{ + unsigned long pfn; + + memory_bm_position_reset(src); + pfn = memory_bm_next_pfn(src); + while (pfn != BM_END_OF_MAP) { + memory_bm_set_bit(dst, pfn); + pfn = memory_bm_next_pfn(src); + } +} + +static int check_header(struct swsusp_info *info) +{ + char *reason; + + reason = check_image_kernel(info); + if (!reason && info->num_physpages != get_num_physpages()) + reason = "memory size"; + if (reason) { + printk(KERN_ERR "PM: Image mismatch: %s\n", reason); + return -EPERM; + } + return 0; +} + +/** + * load header - check the image header and copy data from it + */ + +static int +load_header(struct swsusp_info *info) +{ + int error; + + restore_pblist = NULL; + error = check_header(info); + if (!error) { + nr_copy_pages = info->image_pages; + nr_meta_pages = info->pages - info->image_pages - 1; + } + return error; +} + +/** + * unpack_orig_pfns - for each element of @buf[] (1 page at a time) set + * the corresponding bit in the memory bitmap @bm + */ +static int unpack_orig_pfns(unsigned long *buf, struct memory_bitmap *bm) +{ + int j; + + for (j = 0; j < PAGE_SIZE / sizeof(long); j++) { + if (unlikely(buf[j] == BM_END_OF_MAP)) + break; + + /* Extract and buffer page key for data page (s390 only). */ + page_key_memorize(buf + j); + + if (memory_bm_pfn_present(bm, buf[j])) + memory_bm_set_bit(bm, buf[j]); + else + return -EFAULT; + } + + return 0; +} + +/* List of "safe" pages that may be used to store data loaded from the suspend + * image + */ +static struct linked_page *safe_pages_list; + +#ifdef CONFIG_HIGHMEM +/* struct highmem_pbe is used for creating the list of highmem pages that + * should be restored atomically during the resume from disk, because the page + * frames they have occupied before the suspend are in use. + */ +struct highmem_pbe { + struct page *copy_page; /* data is here now */ + struct page *orig_page; /* data was here before the suspend */ + struct highmem_pbe *next; +}; + +/* List of highmem PBEs needed for restoring the highmem pages that were + * allocated before the suspend and included in the suspend image, but have + * also been allocated by the "resume" kernel, so their contents cannot be + * written directly to their "original" page frames. + */ +static struct highmem_pbe *highmem_pblist; + +/** + * count_highmem_image_pages - compute the number of highmem pages in the + * suspend image. The bits in the memory bitmap @bm that correspond to the + * image pages are assumed to be set. + */ + +static unsigned int count_highmem_image_pages(struct memory_bitmap *bm) +{ + unsigned long pfn; + unsigned int cnt = 0; + + memory_bm_position_reset(bm); + pfn = memory_bm_next_pfn(bm); + while (pfn != BM_END_OF_MAP) { + if (PageHighMem(pfn_to_page(pfn))) + cnt++; + + pfn = memory_bm_next_pfn(bm); + } + return cnt; +} + +/** + * prepare_highmem_image - try to allocate as many highmem pages as + * there are highmem image pages (@nr_highmem_p points to the variable + * containing the number of highmem image pages). The pages that are + * "safe" (ie. will not be overwritten when the suspend image is + * restored) have the corresponding bits set in @bm (it must be + * unitialized). + * + * NOTE: This function should not be called if there are no highmem + * image pages. + */ + +static unsigned int safe_highmem_pages; + +static struct memory_bitmap *safe_highmem_bm; + +static int +prepare_highmem_image(struct memory_bitmap *bm, unsigned int *nr_highmem_p) +{ + unsigned int to_alloc; + + if (memory_bm_create(bm, GFP_ATOMIC, PG_SAFE)) + return -ENOMEM; + + if (get_highmem_buffer(PG_SAFE)) + return -ENOMEM; + + to_alloc = count_free_highmem_pages(); + if (to_alloc > *nr_highmem_p) + to_alloc = *nr_highmem_p; + else + *nr_highmem_p = to_alloc; + + safe_highmem_pages = 0; + while (to_alloc-- > 0) { + struct page *page; + + page = alloc_page(__GFP_HIGHMEM); + if (!swsusp_page_is_free(page)) { + /* The page is "safe", set its bit the bitmap */ + memory_bm_set_bit(bm, page_to_pfn(page)); + safe_highmem_pages++; + } + /* Mark the page as allocated */ + swsusp_set_page_forbidden(page); + swsusp_set_page_free(page); + } + memory_bm_position_reset(bm); + safe_highmem_bm = bm; + return 0; +} + +/** + * get_highmem_page_buffer - for given highmem image page find the buffer + * that suspend_write_next() should set for its caller to write to. + * + * If the page is to be saved to its "original" page frame or a copy of + * the page is to be made in the highmem, @buffer is returned. Otherwise, + * the copy of the page is to be made in normal memory, so the address of + * the copy is returned. + * + * If @buffer is returned, the caller of suspend_write_next() will write + * the page's contents to @buffer, so they will have to be copied to the + * right location on the next call to suspend_write_next() and it is done + * with the help of copy_last_highmem_page(). For this purpose, if + * @buffer is returned, @last_highmem page is set to the page to which + * the data will have to be copied from @buffer. + */ + +static struct page *last_highmem_page; + +static void * +get_highmem_page_buffer(struct page *page, struct chain_allocator *ca) +{ + struct highmem_pbe *pbe; + void *kaddr; + + if (swsusp_page_is_forbidden(page) && swsusp_page_is_free(page)) { + /* We have allocated the "original" page frame and we can + * use it directly to store the loaded page. + */ + last_highmem_page = page; + return buffer; + } + /* The "original" page frame has not been allocated and we have to + * use a "safe" page frame to store the loaded page. + */ + pbe = chain_alloc(ca, sizeof(struct highmem_pbe)); + if (!pbe) { + swsusp_free(); + return ERR_PTR(-ENOMEM); + } + pbe->orig_page = page; + if (safe_highmem_pages > 0) { + struct page *tmp; + + /* Copy of the page will be stored in high memory */ + kaddr = buffer; + tmp = pfn_to_page(memory_bm_next_pfn(safe_highmem_bm)); + safe_highmem_pages--; + last_highmem_page = tmp; + pbe->copy_page = tmp; + } else { + /* Copy of the page will be stored in normal memory */ + kaddr = safe_pages_list; + safe_pages_list = safe_pages_list->next; + pbe->copy_page = virt_to_page(kaddr); + } + pbe->next = highmem_pblist; + highmem_pblist = pbe; + return kaddr; +} + +/** + * copy_last_highmem_page - copy the contents of a highmem image from + * @buffer, where the caller of snapshot_write_next() has place them, + * to the right location represented by @last_highmem_page . + */ + +static void copy_last_highmem_page(void) +{ + if (last_highmem_page) { + void *dst; + + dst = kmap_atomic(last_highmem_page); + copy_page(dst, buffer); + kunmap_atomic(dst); + last_highmem_page = NULL; + } +} + +static inline int last_highmem_page_copied(void) +{ + return !last_highmem_page; +} + +static inline void free_highmem_data(void) +{ + if (safe_highmem_bm) + memory_bm_free(safe_highmem_bm, PG_UNSAFE_CLEAR); + + if (buffer) + free_image_page(buffer, PG_UNSAFE_CLEAR); +} +#else +static unsigned int +count_highmem_image_pages(struct memory_bitmap *bm) { return 0; } + +static inline int +prepare_highmem_image(struct memory_bitmap *bm, unsigned int *nr_highmem_p) +{ + return 0; +} + +static inline void * +get_highmem_page_buffer(struct page *page, struct chain_allocator *ca) +{ + return ERR_PTR(-EINVAL); +} + +static inline void copy_last_highmem_page(void) {} +static inline int last_highmem_page_copied(void) { return 1; } +static inline void free_highmem_data(void) {} +#endif /* CONFIG_HIGHMEM */ + +/** + * prepare_image - use the memory bitmap @bm to mark the pages that will + * be overwritten in the process of restoring the system memory state + * from the suspend image ("unsafe" pages) and allocate memory for the + * image. + * + * The idea is to allocate a new memory bitmap first and then allocate + * as many pages as needed for the image data, but not to assign these + * pages to specific tasks initially. Instead, we just mark them as + * allocated and create a lists of "safe" pages that will be used + * later. On systems with high memory a list of "safe" highmem pages is + * also created. + */ + +#define PBES_PER_LINKED_PAGE (LINKED_PAGE_DATA_SIZE / sizeof(struct pbe)) + +static int +prepare_image(struct memory_bitmap *new_bm, struct memory_bitmap *bm) +{ + unsigned int nr_pages, nr_highmem; + struct linked_page *sp_list, *lp; + int error; + + /* If there is no highmem, the buffer will not be necessary */ + free_image_page(buffer, PG_UNSAFE_CLEAR); + buffer = NULL; + + nr_highmem = count_highmem_image_pages(bm); + error = mark_unsafe_pages(bm); + if (error) + goto Free; + + error = memory_bm_create(new_bm, GFP_ATOMIC, PG_SAFE); + if (error) + goto Free; + + duplicate_memory_bitmap(new_bm, bm); + memory_bm_free(bm, PG_UNSAFE_KEEP); + if (nr_highmem > 0) { + error = prepare_highmem_image(bm, &nr_highmem); + if (error) + goto Free; + } + /* Reserve some safe pages for potential later use. + * + * NOTE: This way we make sure there will be enough safe pages for the + * chain_alloc() in get_buffer(). It is a bit wasteful, but + * nr_copy_pages cannot be greater than 50% of the memory anyway. + */ + sp_list = NULL; + /* nr_copy_pages cannot be lesser than allocated_unsafe_pages */ + nr_pages = nr_copy_pages - nr_highmem - allocated_unsafe_pages; + nr_pages = DIV_ROUND_UP(nr_pages, PBES_PER_LINKED_PAGE); + while (nr_pages > 0) { + lp = get_image_page(GFP_ATOMIC, PG_SAFE); + if (!lp) { + error = -ENOMEM; + goto Free; + } + lp->next = sp_list; + sp_list = lp; + nr_pages--; + } + /* Preallocate memory for the image */ + safe_pages_list = NULL; + nr_pages = nr_copy_pages - nr_highmem - allocated_unsafe_pages; + while (nr_pages > 0) { + lp = (struct linked_page *)get_zeroed_page(GFP_ATOMIC); + if (!lp) { + error = -ENOMEM; + goto Free; + } + if (!swsusp_page_is_free(virt_to_page(lp))) { + /* The page is "safe", add it to the list */ + lp->next = safe_pages_list; + safe_pages_list = lp; + } + /* Mark the page as allocated */ + swsusp_set_page_forbidden(virt_to_page(lp)); + swsusp_set_page_free(virt_to_page(lp)); + nr_pages--; + } + /* Free the reserved safe pages so that chain_alloc() can use them */ + while (sp_list) { + lp = sp_list->next; + free_image_page(sp_list, PG_UNSAFE_CLEAR); + sp_list = lp; + } + return 0; + + Free: + swsusp_free(); + return error; +} + +/** + * get_buffer - compute the address that snapshot_write_next() should + * set for its caller to write to. + */ + +static void *get_buffer(struct memory_bitmap *bm, struct chain_allocator *ca) +{ + struct pbe *pbe; + struct page *page; + unsigned long pfn = memory_bm_next_pfn(bm); + + if (pfn == BM_END_OF_MAP) + return ERR_PTR(-EFAULT); + + page = pfn_to_page(pfn); + if (PageHighMem(page)) + return get_highmem_page_buffer(page, ca); + + if (swsusp_page_is_forbidden(page) && swsusp_page_is_free(page)) + /* We have allocated the "original" page frame and we can + * use it directly to store the loaded page. + */ + return page_address(page); + + /* The "original" page frame has not been allocated and we have to + * use a "safe" page frame to store the loaded page. + */ + pbe = chain_alloc(ca, sizeof(struct pbe)); + if (!pbe) { + swsusp_free(); + return ERR_PTR(-ENOMEM); + } + pbe->orig_address = page_address(page); + pbe->address = safe_pages_list; + safe_pages_list = safe_pages_list->next; + pbe->next = restore_pblist; + restore_pblist = pbe; + return pbe->address; +} + +/** + * snapshot_write_next - used for writing the system memory snapshot. + * + * On the first call to it @handle should point to a zeroed + * snapshot_handle structure. The structure gets updated and a pointer + * to it should be passed to this function every next time. + * + * On success the function returns a positive number. Then, the caller + * is allowed to write up to the returned number of bytes to the memory + * location computed by the data_of() macro. + * + * The function returns 0 to indicate the "end of file" condition, + * and a negative number is returned on error. In such cases the + * structure pointed to by @handle is not updated and should not be used + * any more. + */ + +int snapshot_write_next(struct snapshot_handle *handle) +{ + static struct chain_allocator ca; + int error = 0; + + /* Check if we have already loaded the entire image */ + if (handle->cur > 1 && handle->cur > nr_meta_pages + nr_copy_pages) + return 0; + + handle->sync_read = 1; + + if (!handle->cur) { + if (!buffer) + /* This makes the buffer be freed by swsusp_free() */ + buffer = get_image_page(GFP_ATOMIC, PG_ANY); + + if (!buffer) + return -ENOMEM; + + handle->buffer = buffer; + } else if (handle->cur == 1) { + error = load_header(buffer); + if (error) + return error; + + error = memory_bm_create(©_bm, GFP_ATOMIC, PG_ANY); + if (error) + return error; + + /* Allocate buffer for page keys. */ + error = page_key_alloc(nr_copy_pages); + if (error) + return error; + + } else if (handle->cur <= nr_meta_pages + 1) { + error = unpack_orig_pfns(buffer, ©_bm); + if (error) + return error; + + if (handle->cur == nr_meta_pages + 1) { + error = prepare_image(&orig_bm, ©_bm); + if (error) + return error; + + chain_init(&ca, GFP_ATOMIC, PG_SAFE); + memory_bm_position_reset(&orig_bm); + restore_pblist = NULL; + handle->buffer = get_buffer(&orig_bm, &ca); + handle->sync_read = 0; + if (IS_ERR(handle->buffer)) + return PTR_ERR(handle->buffer); + } + } else { + copy_last_highmem_page(); + /* Restore page key for data page (s390 only). */ + page_key_write(handle->buffer); + handle->buffer = get_buffer(&orig_bm, &ca); + if (IS_ERR(handle->buffer)) + return PTR_ERR(handle->buffer); + if (handle->buffer != buffer) + handle->sync_read = 0; + } + handle->cur++; + return PAGE_SIZE; +} + +/** + * snapshot_write_finalize - must be called after the last call to + * snapshot_write_next() in case the last page in the image happens + * to be a highmem page and its contents should be stored in the + * highmem. Additionally, it releases the memory that will not be + * used any more. + */ + +void snapshot_write_finalize(struct snapshot_handle *handle) +{ + copy_last_highmem_page(); + /* Restore page key for data page (s390 only). */ + page_key_write(handle->buffer); + page_key_free(); + /* Free only if we have loaded the image entirely */ + if (handle->cur > 1 && handle->cur > nr_meta_pages + nr_copy_pages) { + memory_bm_free(&orig_bm, PG_UNSAFE_CLEAR); + free_highmem_data(); + } +} + +int snapshot_image_loaded(struct snapshot_handle *handle) +{ + return !(!nr_copy_pages || !last_highmem_page_copied() || + handle->cur <= nr_meta_pages + nr_copy_pages); +} + +#ifdef CONFIG_HIGHMEM +/* Assumes that @buf is ready and points to a "safe" page */ +static inline void +swap_two_pages_data(struct page *p1, struct page *p2, void *buf) +{ + void *kaddr1, *kaddr2; + + kaddr1 = kmap_atomic(p1); + kaddr2 = kmap_atomic(p2); + copy_page(buf, kaddr1); + copy_page(kaddr1, kaddr2); + copy_page(kaddr2, buf); + kunmap_atomic(kaddr2); + kunmap_atomic(kaddr1); +} + +/** + * restore_highmem - for each highmem page that was allocated before + * the suspend and included in the suspend image, and also has been + * allocated by the "resume" kernel swap its current (ie. "before + * resume") contents with the previous (ie. "before suspend") one. + * + * If the resume eventually fails, we can call this function once + * again and restore the "before resume" highmem state. + */ + +int restore_highmem(void) +{ + struct highmem_pbe *pbe = highmem_pblist; + void *buf; + + if (!pbe) + return 0; + + buf = get_image_page(GFP_ATOMIC, PG_SAFE); + if (!buf) + return -ENOMEM; + + while (pbe) { + swap_two_pages_data(pbe->copy_page, pbe->orig_page, buf); + pbe = pbe->next; + } + free_image_page(buf, PG_UNSAFE_CLEAR); + return 0; +} +#endif /* CONFIG_HIGHMEM */ diff --git a/kernel/kernel/power/suspend.c b/kernel/kernel/power/suspend.c new file mode 100644 index 000000000..db920b170 --- /dev/null +++ b/kernel/kernel/power/suspend.c @@ -0,0 +1,540 @@ +/* + * kernel/power/suspend.c - Suspend to RAM and standby functionality. + * + * Copyright (c) 2003 Patrick Mochel + * Copyright (c) 2003 Open Source Development Lab + * Copyright (c) 2009 Rafael J. Wysocki , Novell Inc. + * + * This file is released under the GPLv2. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "power.h" + +const char *pm_labels[] = { "mem", "standby", "freeze", NULL }; +const char *pm_states[PM_SUSPEND_MAX]; + +static const struct platform_suspend_ops *suspend_ops; +static const struct platform_freeze_ops *freeze_ops; +static DECLARE_WAIT_QUEUE_HEAD(suspend_freeze_wait_head); + +enum freeze_state __read_mostly suspend_freeze_state; +static DEFINE_SPINLOCK(suspend_freeze_lock); + +void freeze_set_ops(const struct platform_freeze_ops *ops) +{ + lock_system_sleep(); + freeze_ops = ops; + unlock_system_sleep(); +} + +static void freeze_begin(void) +{ + suspend_freeze_state = FREEZE_STATE_NONE; +} + +static void freeze_enter(void) +{ + spin_lock_irq(&suspend_freeze_lock); + if (pm_wakeup_pending()) + goto out; + + suspend_freeze_state = FREEZE_STATE_ENTER; + spin_unlock_irq(&suspend_freeze_lock); + + get_online_cpus(); + cpuidle_resume(); + + /* Push all the CPUs into the idle loop. */ + wake_up_all_idle_cpus(); + pr_debug("PM: suspend-to-idle\n"); + /* Make the current CPU wait so it can enter the idle loop too. */ + wait_event(suspend_freeze_wait_head, + suspend_freeze_state == FREEZE_STATE_WAKE); + pr_debug("PM: resume from suspend-to-idle\n"); + + cpuidle_pause(); + put_online_cpus(); + + spin_lock_irq(&suspend_freeze_lock); + + out: + suspend_freeze_state = FREEZE_STATE_NONE; + spin_unlock_irq(&suspend_freeze_lock); +} + +void freeze_wake(void) +{ + unsigned long flags; + + spin_lock_irqsave(&suspend_freeze_lock, flags); + if (suspend_freeze_state > FREEZE_STATE_NONE) { + suspend_freeze_state = FREEZE_STATE_WAKE; + wake_up(&suspend_freeze_wait_head); + } + spin_unlock_irqrestore(&suspend_freeze_lock, flags); +} +EXPORT_SYMBOL_GPL(freeze_wake); + +static bool valid_state(suspend_state_t state) +{ + /* + * PM_SUSPEND_STANDBY and PM_SUSPEND_MEM states need low level + * support and need to be valid to the low level + * implementation, no valid callback implies that none are valid. + */ + return suspend_ops && suspend_ops->valid && suspend_ops->valid(state); +} + +/* + * If this is set, the "mem" label always corresponds to the deepest sleep state + * available, the "standby" label corresponds to the second deepest sleep state + * available (if any), and the "freeze" label corresponds to the remaining + * available sleep state (if there is one). + */ +static bool relative_states; + +static int __init sleep_states_setup(char *str) +{ + relative_states = !strncmp(str, "1", 1); + pm_states[PM_SUSPEND_FREEZE] = pm_labels[relative_states ? 0 : 2]; + return 1; +} + +__setup("relative_sleep_states=", sleep_states_setup); + +/** + * suspend_set_ops - Set the global suspend method table. + * @ops: Suspend operations to use. + */ +void suspend_set_ops(const struct platform_suspend_ops *ops) +{ + suspend_state_t i; + int j = 0; + + lock_system_sleep(); + + suspend_ops = ops; + for (i = PM_SUSPEND_MEM; i >= PM_SUSPEND_STANDBY; i--) + if (valid_state(i)) { + pm_states[i] = pm_labels[j++]; + } else if (!relative_states) { + pm_states[i] = NULL; + j++; + } + + pm_states[PM_SUSPEND_FREEZE] = pm_labels[j]; + + unlock_system_sleep(); +} +EXPORT_SYMBOL_GPL(suspend_set_ops); + +/** + * suspend_valid_only_mem - Generic memory-only valid callback. + * + * Platform drivers that implement mem suspend only and only need to check for + * that in their .valid() callback can use this instead of rolling their own + * .valid() callback. + */ +int suspend_valid_only_mem(suspend_state_t state) +{ + return state == PM_SUSPEND_MEM; +} +EXPORT_SYMBOL_GPL(suspend_valid_only_mem); + +static bool sleep_state_supported(suspend_state_t state) +{ + return state == PM_SUSPEND_FREEZE || (suspend_ops && suspend_ops->enter); +} + +static int platform_suspend_prepare(suspend_state_t state) +{ + return state != PM_SUSPEND_FREEZE && suspend_ops->prepare ? + suspend_ops->prepare() : 0; +} + +static int platform_suspend_prepare_late(suspend_state_t state) +{ + return state == PM_SUSPEND_FREEZE && freeze_ops && freeze_ops->prepare ? + freeze_ops->prepare() : 0; +} + +static int platform_suspend_prepare_noirq(suspend_state_t state) +{ + return state != PM_SUSPEND_FREEZE && suspend_ops->prepare_late ? + suspend_ops->prepare_late() : 0; +} + +static void platform_resume_noirq(suspend_state_t state) +{ + if (state != PM_SUSPEND_FREEZE && suspend_ops->wake) + suspend_ops->wake(); +} + +static void platform_resume_early(suspend_state_t state) +{ + if (state == PM_SUSPEND_FREEZE && freeze_ops && freeze_ops->restore) + freeze_ops->restore(); +} + +static void platform_resume_finish(suspend_state_t state) +{ + if (state != PM_SUSPEND_FREEZE && suspend_ops->finish) + suspend_ops->finish(); +} + +static int platform_suspend_begin(suspend_state_t state) +{ + if (state == PM_SUSPEND_FREEZE && freeze_ops && freeze_ops->begin) + return freeze_ops->begin(); + else if (suspend_ops->begin) + return suspend_ops->begin(state); + else + return 0; +} + +static void platform_resume_end(suspend_state_t state) +{ + if (state == PM_SUSPEND_FREEZE && freeze_ops && freeze_ops->end) + freeze_ops->end(); + else if (suspend_ops->end) + suspend_ops->end(); +} + +static void platform_recover(suspend_state_t state) +{ + if (state != PM_SUSPEND_FREEZE && suspend_ops->recover) + suspend_ops->recover(); +} + +static bool platform_suspend_again(suspend_state_t state) +{ + return state != PM_SUSPEND_FREEZE && suspend_ops->suspend_again ? + suspend_ops->suspend_again() : false; +} + +#ifdef CONFIG_PM_DEBUG +static unsigned int pm_test_delay = 5; +module_param(pm_test_delay, uint, 0644); +MODULE_PARM_DESC(pm_test_delay, + "Number of seconds to wait before resuming from suspend test"); +#endif + +static int suspend_test(int level) +{ +#ifdef CONFIG_PM_DEBUG + if (pm_test_level == level) { + printk(KERN_INFO "suspend debug: Waiting for %d second(s).\n", + pm_test_delay); + mdelay(pm_test_delay * 1000); + return 1; + } +#endif /* !CONFIG_PM_DEBUG */ + return 0; +} + +/** + * suspend_prepare - Prepare for entering system sleep state. + * + * Common code run for every system sleep state that can be entered (except for + * hibernation). Run suspend notifiers, allocate the "suspend" console and + * freeze processes. + */ +static int suspend_prepare(suspend_state_t state) +{ + int error; + + if (!sleep_state_supported(state)) + return -EPERM; + + pm_prepare_console(); + + error = pm_notifier_call_chain(PM_SUSPEND_PREPARE); + if (error) + goto Finish; + + trace_suspend_resume(TPS("freeze_processes"), 0, true); + error = suspend_freeze_processes(); + trace_suspend_resume(TPS("freeze_processes"), 0, false); + if (!error) + return 0; + + suspend_stats.failed_freeze++; + dpm_save_failed_step(SUSPEND_FREEZE); + Finish: + pm_notifier_call_chain(PM_POST_SUSPEND); + pm_restore_console(); + return error; +} + +/* default implementation */ +void __weak arch_suspend_disable_irqs(void) +{ + local_irq_disable(); +} + +/* default implementation */ +void __weak arch_suspend_enable_irqs(void) +{ + local_irq_enable(); +} + +/** + * suspend_enter - Make the system enter the given sleep state. + * @state: System sleep state to enter. + * @wakeup: Returns information that the sleep state should not be re-entered. + * + * This function should be called after devices have been suspended. + */ +static int suspend_enter(suspend_state_t state, bool *wakeup) +{ + int error; + + error = platform_suspend_prepare(state); + if (error) + goto Platform_finish; + + error = dpm_suspend_late(PMSG_SUSPEND); + if (error) { + printk(KERN_ERR "PM: late suspend of devices failed\n"); + goto Platform_finish; + } + error = platform_suspend_prepare_late(state); + if (error) + goto Devices_early_resume; + + error = dpm_suspend_noirq(PMSG_SUSPEND); + if (error) { + printk(KERN_ERR "PM: noirq suspend of devices failed\n"); + goto Platform_early_resume; + } + error = platform_suspend_prepare_noirq(state); + if (error) + goto Platform_wake; + + if (suspend_test(TEST_PLATFORM)) + goto Platform_wake; + + /* + * PM_SUSPEND_FREEZE equals + * frozen processes + suspended devices + idle processors. + * Thus we should invoke freeze_enter() soon after + * all the devices are suspended. + */ + if (state == PM_SUSPEND_FREEZE) { + trace_suspend_resume(TPS("machine_suspend"), state, true); + freeze_enter(); + trace_suspend_resume(TPS("machine_suspend"), state, false); + goto Platform_wake; + } + + error = disable_nonboot_cpus(); + if (error || suspend_test(TEST_CPUS)) + goto Enable_cpus; + + arch_suspend_disable_irqs(); + BUG_ON(!irqs_disabled()); + + system_state = SYSTEM_SUSPEND; + + error = syscore_suspend(); + if (!error) { + *wakeup = pm_wakeup_pending(); + if (!(suspend_test(TEST_CORE) || *wakeup)) { + trace_suspend_resume(TPS("machine_suspend"), + state, true); + error = suspend_ops->enter(state); + trace_suspend_resume(TPS("machine_suspend"), + state, false); + events_check_enabled = false; + } + syscore_resume(); + } + + system_state = SYSTEM_RUNNING; + + arch_suspend_enable_irqs(); + BUG_ON(irqs_disabled()); + + Enable_cpus: + enable_nonboot_cpus(); + + Platform_wake: + platform_resume_noirq(state); + dpm_resume_noirq(PMSG_RESUME); + + Platform_early_resume: + platform_resume_early(state); + + Devices_early_resume: + dpm_resume_early(PMSG_RESUME); + + Platform_finish: + platform_resume_finish(state); + return error; +} + +/** + * suspend_devices_and_enter - Suspend devices and enter system sleep state. + * @state: System sleep state to enter. + */ +int suspend_devices_and_enter(suspend_state_t state) +{ + int error; + bool wakeup = false; + + if (!sleep_state_supported(state)) + return -ENOSYS; + + error = platform_suspend_begin(state); + if (error) + goto Close; + + suspend_console(); + suspend_test_start(); + error = dpm_suspend_start(PMSG_SUSPEND); + if (error) { + pr_err("PM: Some devices failed to suspend, or early wake event detected\n"); + goto Recover_platform; + } + suspend_test_finish("suspend devices"); + if (suspend_test(TEST_DEVICES)) + goto Recover_platform; + + do { + error = suspend_enter(state, &wakeup); + } while (!error && !wakeup && platform_suspend_again(state)); + + Resume_devices: + suspend_test_start(); + dpm_resume_end(PMSG_RESUME); + suspend_test_finish("resume devices"); + trace_suspend_resume(TPS("resume_console"), state, true); + resume_console(); + trace_suspend_resume(TPS("resume_console"), state, false); + + Close: + platform_resume_end(state); + return error; + + Recover_platform: + platform_recover(state); + goto Resume_devices; +} + +/** + * suspend_finish - Clean up before finishing the suspend sequence. + * + * Call platform code to clean up, restart processes, and free the console that + * we've allocated. This routine is not called for hibernation. + */ +static void suspend_finish(void) +{ + suspend_thaw_processes(); + pm_notifier_call_chain(PM_POST_SUSPEND); + pm_restore_console(); +} + +/** + * enter_state - Do common work needed to enter system sleep state. + * @state: System sleep state to enter. + * + * Make sure that no one else is trying to put the system into a sleep state. + * Fail if that's not the case. Otherwise, prepare for system suspend, make the + * system enter the given sleep state and clean up after wakeup. + */ +static int enter_state(suspend_state_t state) +{ + int error; + + trace_suspend_resume(TPS("suspend_enter"), state, true); + if (state == PM_SUSPEND_FREEZE) { +#ifdef CONFIG_PM_DEBUG + if (pm_test_level != TEST_NONE && pm_test_level <= TEST_CPUS) { + pr_warning("PM: Unsupported test mode for freeze state," + "please choose none/freezer/devices/platform.\n"); + return -EAGAIN; + } +#endif + } else if (!valid_state(state)) { + return -EINVAL; + } + if (!mutex_trylock(&pm_mutex)) + return -EBUSY; + + if (state == PM_SUSPEND_FREEZE) + freeze_begin(); + + trace_suspend_resume(TPS("sync_filesystems"), 0, true); + printk(KERN_INFO "PM: Syncing filesystems ... "); + sys_sync(); + printk("done.\n"); + trace_suspend_resume(TPS("sync_filesystems"), 0, false); + + pr_debug("PM: Preparing system for %s sleep\n", pm_states[state]); + error = suspend_prepare(state); + if (error) + goto Unlock; + + if (suspend_test(TEST_FREEZER)) + goto Finish; + + trace_suspend_resume(TPS("suspend_enter"), state, false); + pr_debug("PM: Entering %s sleep\n", pm_states[state]); + pm_restrict_gfp_mask(); + error = suspend_devices_and_enter(state); + pm_restore_gfp_mask(); + + Finish: + pr_debug("PM: Finishing wakeup.\n"); + suspend_finish(); + Unlock: + mutex_unlock(&pm_mutex); + return error; +} + +/** + * pm_suspend - Externally visible function for suspending the system. + * @state: System sleep state to enter. + * + * Check if the value of @state represents one of the supported states, + * execute enter_state() and update system suspend statistics. + */ +int pm_suspend(suspend_state_t state) +{ + int error; + + if (state <= PM_SUSPEND_ON || state >= PM_SUSPEND_MAX) + return -EINVAL; + + error = enter_state(state); + if (error) { + suspend_stats.fail++; + dpm_save_failed_errno(error); + } else { + suspend_stats.success++; + } + return error; +} +EXPORT_SYMBOL(pm_suspend); diff --git a/kernel/kernel/power/suspend_test.c b/kernel/kernel/power/suspend_test.c new file mode 100644 index 000000000..084452e34 --- /dev/null +++ b/kernel/kernel/power/suspend_test.c @@ -0,0 +1,218 @@ +/* + * kernel/power/suspend_test.c - Suspend to RAM and standby test facility. + * + * Copyright (c) 2009 Pavel Machek + * + * This file is released under the GPLv2. + */ + +#include +#include + +#include "power.h" + +/* + * We test the system suspend code by setting an RTC wakealarm a short + * time in the future, then suspending. Suspending the devices won't + * normally take long ... some systems only need a few milliseconds. + * + * The time it takes is system-specific though, so when we test this + * during system bootup we allow a LOT of time. + */ +#define TEST_SUSPEND_SECONDS 10 + +static unsigned long suspend_test_start_time; +static u32 test_repeat_count_max = 1; +static u32 test_repeat_count_current; + +void suspend_test_start(void) +{ + /* FIXME Use better timebase than "jiffies", ideally a clocksource. + * What we want is a hardware counter that will work correctly even + * during the irqs-are-off stages of the suspend/resume cycle... + */ + suspend_test_start_time = jiffies; +} + +void suspend_test_finish(const char *label) +{ + long nj = jiffies - suspend_test_start_time; + unsigned msec; + + msec = jiffies_to_msecs(abs(nj)); + pr_info("PM: %s took %d.%03d seconds\n", label, + msec / 1000, msec % 1000); + + /* Warning on suspend means the RTC alarm period needs to be + * larger -- the system was sooo slooowwww to suspend that the + * alarm (should have) fired before the system went to sleep! + * + * Warning on either suspend or resume also means the system + * has some performance issues. The stack dump of a WARN_ON + * is more likely to get the right attention than a printk... + */ + WARN(msec > (TEST_SUSPEND_SECONDS * 1000), + "Component: %s, time: %u\n", label, msec); +} + +/* + * To test system suspend, we need a hands-off mechanism to resume the + * system. RTCs wake alarms are a common self-contained mechanism. + */ + +static void __init test_wakealarm(struct rtc_device *rtc, suspend_state_t state) +{ + static char err_readtime[] __initdata = + KERN_ERR "PM: can't read %s time, err %d\n"; + static char err_wakealarm [] __initdata = + KERN_ERR "PM: can't set %s wakealarm, err %d\n"; + static char err_suspend[] __initdata = + KERN_ERR "PM: suspend test failed, error %d\n"; + static char info_test[] __initdata = + KERN_INFO "PM: test RTC wakeup from '%s' suspend\n"; + + unsigned long now; + struct rtc_wkalrm alm; + int status; + + /* this may fail if the RTC hasn't been initialized */ +repeat: + status = rtc_read_time(rtc, &alm.time); + if (status < 0) { + printk(err_readtime, dev_name(&rtc->dev), status); + return; + } + rtc_tm_to_time(&alm.time, &now); + + memset(&alm, 0, sizeof alm); + rtc_time_to_tm(now + TEST_SUSPEND_SECONDS, &alm.time); + alm.enabled = true; + + status = rtc_set_alarm(rtc, &alm); + if (status < 0) { + printk(err_wakealarm, dev_name(&rtc->dev), status); + return; + } + + if (state == PM_SUSPEND_MEM) { + printk(info_test, pm_states[state]); + status = pm_suspend(state); + if (status == -ENODEV) + state = PM_SUSPEND_STANDBY; + } + if (state == PM_SUSPEND_STANDBY) { + printk(info_test, pm_states[state]); + status = pm_suspend(state); + if (status < 0) + state = PM_SUSPEND_FREEZE; + } + if (state == PM_SUSPEND_FREEZE) { + printk(info_test, pm_states[state]); + status = pm_suspend(state); + } + + if (status < 0) + printk(err_suspend, status); + + test_repeat_count_current++; + if (test_repeat_count_current < test_repeat_count_max) + goto repeat; + + /* Some platforms can't detect that the alarm triggered the + * wakeup, or (accordingly) disable it after it afterwards. + * It's supposed to give oneshot behavior; cope. + */ + alm.enabled = false; + rtc_set_alarm(rtc, &alm); +} + +static int __init has_wakealarm(struct device *dev, const void *data) +{ + struct rtc_device *candidate = to_rtc_device(dev); + + if (!candidate->ops->set_alarm) + return 0; + if (!device_may_wakeup(candidate->dev.parent)) + return 0; + + return 1; +} + +/* + * Kernel options like "test_suspend=mem" force suspend/resume sanity tests + * at startup time. They're normally disabled, for faster boot and because + * we can't know which states really work on this particular system. + */ +static const char *test_state_label __initdata; + +static char warn_bad_state[] __initdata = + KERN_WARNING "PM: can't test '%s' suspend state\n"; + +static int __init setup_test_suspend(char *value) +{ + int i; + char *repeat; + char *suspend_type; + + /* example : "=mem[,N]" ==> "mem[,N]" */ + value++; + suspend_type = strsep(&value, ","); + if (!suspend_type) + return 0; + + repeat = strsep(&value, ","); + if (repeat) { + if (kstrtou32(repeat, 0, &test_repeat_count_max)) + return 0; + } + + for (i = 0; pm_labels[i]; i++) + if (!strcmp(pm_labels[i], suspend_type)) { + test_state_label = pm_labels[i]; + return 0; + } + + printk(warn_bad_state, suspend_type); + return 0; +} +__setup("test_suspend", setup_test_suspend); + +static int __init test_suspend(void) +{ + static char warn_no_rtc[] __initdata = + KERN_WARNING "PM: no wakealarm-capable RTC driver is ready\n"; + + struct rtc_device *rtc = NULL; + struct device *dev; + suspend_state_t test_state; + + /* PM is initialized by now; is that state testable? */ + if (!test_state_label) + return 0; + + for (test_state = PM_SUSPEND_MIN; test_state < PM_SUSPEND_MAX; test_state++) { + const char *state_label = pm_states[test_state]; + + if (state_label && !strcmp(test_state_label, state_label)) + break; + } + if (test_state == PM_SUSPEND_MAX) { + printk(warn_bad_state, test_state_label); + return 0; + } + + /* RTCs have initialized by now too ... can we use one? */ + dev = class_find_device(rtc_class, NULL, NULL, has_wakealarm); + if (dev) + rtc = rtc_class_open(dev_name(dev)); + if (!rtc) { + printk(warn_no_rtc); + return 0; + } + + /* go for it */ + test_wakealarm(rtc, test_state); + rtc_class_close(rtc); + return 0; +} +late_initcall(test_suspend); diff --git a/kernel/kernel/power/swap.c b/kernel/kernel/power/swap.c new file mode 100644 index 000000000..570aff817 --- /dev/null +++ b/kernel/kernel/power/swap.c @@ -0,0 +1,1512 @@ +/* + * linux/kernel/power/swap.c + * + * This file provides functions for reading the suspend image from + * and writing it to a swap partition. + * + * Copyright (C) 1998,2001-2005 Pavel Machek + * Copyright (C) 2006 Rafael J. Wysocki + * Copyright (C) 2010-2012 Bojan Smojver + * + * This file is released under the GPLv2. + * + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "power.h" + +#define HIBERNATE_SIG "S1SUSPEND" + +/* + * The swap map is a data structure used for keeping track of each page + * written to a swap partition. It consists of many swap_map_page + * structures that contain each an array of MAP_PAGE_ENTRIES swap entries. + * These structures are stored on the swap and linked together with the + * help of the .next_swap member. + * + * The swap map is created during suspend. The swap map pages are + * allocated and populated one at a time, so we only need one memory + * page to set up the entire structure. + * + * During resume we pick up all swap_map_page structures into a list. + */ + +#define MAP_PAGE_ENTRIES (PAGE_SIZE / sizeof(sector_t) - 1) + +/* + * Number of free pages that are not high. + */ +static inline unsigned long low_free_pages(void) +{ + return nr_free_pages() - nr_free_highpages(); +} + +/* + * Number of pages required to be kept free while writing the image. Always + * half of all available low pages before the writing starts. + */ +static inline unsigned long reqd_free_pages(void) +{ + return low_free_pages() / 2; +} + +struct swap_map_page { + sector_t entries[MAP_PAGE_ENTRIES]; + sector_t next_swap; +}; + +struct swap_map_page_list { + struct swap_map_page *map; + struct swap_map_page_list *next; +}; + +/** + * The swap_map_handle structure is used for handling swap in + * a file-alike way + */ + +struct swap_map_handle { + struct swap_map_page *cur; + struct swap_map_page_list *maps; + sector_t cur_swap; + sector_t first_sector; + unsigned int k; + unsigned long reqd_free_pages; + u32 crc32; +}; + +struct swsusp_header { + char reserved[PAGE_SIZE - 20 - sizeof(sector_t) - sizeof(int) - + sizeof(u32)]; + u32 crc32; + sector_t image; + unsigned int flags; /* Flags to pass to the "boot" kernel */ + char orig_sig[10]; + char sig[10]; +} __packed; + +static struct swsusp_header *swsusp_header; + +/** + * The following functions are used for tracing the allocated + * swap pages, so that they can be freed in case of an error. + */ + +struct swsusp_extent { + struct rb_node node; + unsigned long start; + unsigned long end; +}; + +static struct rb_root swsusp_extents = RB_ROOT; + +static int swsusp_extents_insert(unsigned long swap_offset) +{ + struct rb_node **new = &(swsusp_extents.rb_node); + struct rb_node *parent = NULL; + struct swsusp_extent *ext; + + /* Figure out where to put the new node */ + while (*new) { + ext = rb_entry(*new, struct swsusp_extent, node); + parent = *new; + if (swap_offset < ext->start) { + /* Try to merge */ + if (swap_offset == ext->start - 1) { + ext->start--; + return 0; + } + new = &((*new)->rb_left); + } else if (swap_offset > ext->end) { + /* Try to merge */ + if (swap_offset == ext->end + 1) { + ext->end++; + return 0; + } + new = &((*new)->rb_right); + } else { + /* It already is in the tree */ + return -EINVAL; + } + } + /* Add the new node and rebalance the tree. */ + ext = kzalloc(sizeof(struct swsusp_extent), GFP_KERNEL); + if (!ext) + return -ENOMEM; + + ext->start = swap_offset; + ext->end = swap_offset; + rb_link_node(&ext->node, parent, new); + rb_insert_color(&ext->node, &swsusp_extents); + return 0; +} + +/** + * alloc_swapdev_block - allocate a swap page and register that it has + * been allocated, so that it can be freed in case of an error. + */ + +sector_t alloc_swapdev_block(int swap) +{ + unsigned long offset; + + offset = swp_offset(get_swap_page_of_type(swap)); + if (offset) { + if (swsusp_extents_insert(offset)) + swap_free(swp_entry(swap, offset)); + else + return swapdev_block(swap, offset); + } + return 0; +} + +/** + * free_all_swap_pages - free swap pages allocated for saving image data. + * It also frees the extents used to register which swap entries had been + * allocated. + */ + +void free_all_swap_pages(int swap) +{ + struct rb_node *node; + + while ((node = swsusp_extents.rb_node)) { + struct swsusp_extent *ext; + unsigned long offset; + + ext = container_of(node, struct swsusp_extent, node); + rb_erase(node, &swsusp_extents); + for (offset = ext->start; offset <= ext->end; offset++) + swap_free(swp_entry(swap, offset)); + + kfree(ext); + } +} + +int swsusp_swap_in_use(void) +{ + return (swsusp_extents.rb_node != NULL); +} + +/* + * General things + */ + +static unsigned short root_swap = 0xffff; +struct block_device *hib_resume_bdev; + +/* + * Saving part + */ + +static int mark_swapfiles(struct swap_map_handle *handle, unsigned int flags) +{ + int error; + + hib_bio_read_page(swsusp_resume_block, swsusp_header, NULL); + if (!memcmp("SWAP-SPACE",swsusp_header->sig, 10) || + !memcmp("SWAPSPACE2",swsusp_header->sig, 10)) { + memcpy(swsusp_header->orig_sig,swsusp_header->sig, 10); + memcpy(swsusp_header->sig, HIBERNATE_SIG, 10); + swsusp_header->image = handle->first_sector; + swsusp_header->flags = flags; + if (flags & SF_CRC32_MODE) + swsusp_header->crc32 = handle->crc32; + error = hib_bio_write_page(swsusp_resume_block, + swsusp_header, NULL); + } else { + printk(KERN_ERR "PM: Swap header not found!\n"); + error = -ENODEV; + } + return error; +} + +/** + * swsusp_swap_check - check if the resume device is a swap device + * and get its index (if so) + * + * This is called before saving image + */ +static int swsusp_swap_check(void) +{ + int res; + + res = swap_type_of(swsusp_resume_device, swsusp_resume_block, + &hib_resume_bdev); + if (res < 0) + return res; + + root_swap = res; + res = blkdev_get(hib_resume_bdev, FMODE_WRITE, NULL); + if (res) + return res; + + res = set_blocksize(hib_resume_bdev, PAGE_SIZE); + if (res < 0) + blkdev_put(hib_resume_bdev, FMODE_WRITE); + + return res; +} + +/** + * write_page - Write one page to given swap location. + * @buf: Address we're writing. + * @offset: Offset of the swap page we're writing to. + * @bio_chain: Link the next write BIO here + */ + +static int write_page(void *buf, sector_t offset, struct bio **bio_chain) +{ + void *src; + int ret; + + if (!offset) + return -ENOSPC; + + if (bio_chain) { + src = (void *)__get_free_page(__GFP_WAIT | __GFP_NOWARN | + __GFP_NORETRY); + if (src) { + copy_page(src, buf); + } else { + ret = hib_wait_on_bio_chain(bio_chain); /* Free pages */ + if (ret) + return ret; + src = (void *)__get_free_page(__GFP_WAIT | + __GFP_NOWARN | + __GFP_NORETRY); + if (src) { + copy_page(src, buf); + } else { + WARN_ON_ONCE(1); + bio_chain = NULL; /* Go synchronous */ + src = buf; + } + } + } else { + src = buf; + } + return hib_bio_write_page(offset, src, bio_chain); +} + +static void release_swap_writer(struct swap_map_handle *handle) +{ + if (handle->cur) + free_page((unsigned long)handle->cur); + handle->cur = NULL; +} + +static int get_swap_writer(struct swap_map_handle *handle) +{ + int ret; + + ret = swsusp_swap_check(); + if (ret) { + if (ret != -ENOSPC) + printk(KERN_ERR "PM: Cannot find swap device, try " + "swapon -a.\n"); + return ret; + } + handle->cur = (struct swap_map_page *)get_zeroed_page(GFP_KERNEL); + if (!handle->cur) { + ret = -ENOMEM; + goto err_close; + } + handle->cur_swap = alloc_swapdev_block(root_swap); + if (!handle->cur_swap) { + ret = -ENOSPC; + goto err_rel; + } + handle->k = 0; + handle->reqd_free_pages = reqd_free_pages(); + handle->first_sector = handle->cur_swap; + return 0; +err_rel: + release_swap_writer(handle); +err_close: + swsusp_close(FMODE_WRITE); + return ret; +} + +static int swap_write_page(struct swap_map_handle *handle, void *buf, + struct bio **bio_chain) +{ + int error = 0; + sector_t offset; + + if (!handle->cur) + return -EINVAL; + offset = alloc_swapdev_block(root_swap); + error = write_page(buf, offset, bio_chain); + if (error) + return error; + handle->cur->entries[handle->k++] = offset; + if (handle->k >= MAP_PAGE_ENTRIES) { + offset = alloc_swapdev_block(root_swap); + if (!offset) + return -ENOSPC; + handle->cur->next_swap = offset; + error = write_page(handle->cur, handle->cur_swap, bio_chain); + if (error) + goto out; + clear_page(handle->cur); + handle->cur_swap = offset; + handle->k = 0; + + if (bio_chain && low_free_pages() <= handle->reqd_free_pages) { + error = hib_wait_on_bio_chain(bio_chain); + if (error) + goto out; + /* + * Recalculate the number of required free pages, to + * make sure we never take more than half. + */ + handle->reqd_free_pages = reqd_free_pages(); + } + } + out: + return error; +} + +static int flush_swap_writer(struct swap_map_handle *handle) +{ + if (handle->cur && handle->cur_swap) + return write_page(handle->cur, handle->cur_swap, NULL); + else + return -EINVAL; +} + +static int swap_writer_finish(struct swap_map_handle *handle, + unsigned int flags, int error) +{ + if (!error) { + flush_swap_writer(handle); + printk(KERN_INFO "PM: S"); + error = mark_swapfiles(handle, flags); + printk("|\n"); + } + + if (error) + free_all_swap_pages(root_swap); + release_swap_writer(handle); + swsusp_close(FMODE_WRITE); + + return error; +} + +/* We need to remember how much compressed data we need to read. */ +#define LZO_HEADER sizeof(size_t) + +/* Number of pages/bytes we'll compress at one time. */ +#define LZO_UNC_PAGES 32 +#define LZO_UNC_SIZE (LZO_UNC_PAGES * PAGE_SIZE) + +/* Number of pages/bytes we need for compressed data (worst case). */ +#define LZO_CMP_PAGES DIV_ROUND_UP(lzo1x_worst_compress(LZO_UNC_SIZE) + \ + LZO_HEADER, PAGE_SIZE) +#define LZO_CMP_SIZE (LZO_CMP_PAGES * PAGE_SIZE) + +/* Maximum number of threads for compression/decompression. */ +#define LZO_THREADS 3 + +/* Minimum/maximum number of pages for read buffering. */ +#define LZO_MIN_RD_PAGES 1024 +#define LZO_MAX_RD_PAGES 8192 + + +/** + * save_image - save the suspend image data + */ + +static int save_image(struct swap_map_handle *handle, + struct snapshot_handle *snapshot, + unsigned int nr_to_write) +{ + unsigned int m; + int ret; + int nr_pages; + int err2; + struct bio *bio; + ktime_t start; + ktime_t stop; + + printk(KERN_INFO "PM: Saving image data pages (%u pages)...\n", + nr_to_write); + m = nr_to_write / 10; + if (!m) + m = 1; + nr_pages = 0; + bio = NULL; + start = ktime_get(); + while (1) { + ret = snapshot_read_next(snapshot); + if (ret <= 0) + break; + ret = swap_write_page(handle, data_of(*snapshot), &bio); + if (ret) + break; + if (!(nr_pages % m)) + printk(KERN_INFO "PM: Image saving progress: %3d%%\n", + nr_pages / m * 10); + nr_pages++; + } + err2 = hib_wait_on_bio_chain(&bio); + stop = ktime_get(); + if (!ret) + ret = err2; + if (!ret) + printk(KERN_INFO "PM: Image saving done.\n"); + swsusp_show_speed(start, stop, nr_to_write, "Wrote"); + return ret; +} + +/** + * Structure used for CRC32. + */ +struct crc_data { + struct task_struct *thr; /* thread */ + atomic_t ready; /* ready to start flag */ + atomic_t stop; /* ready to stop flag */ + unsigned run_threads; /* nr current threads */ + wait_queue_head_t go; /* start crc update */ + wait_queue_head_t done; /* crc update done */ + u32 *crc32; /* points to handle's crc32 */ + size_t *unc_len[LZO_THREADS]; /* uncompressed lengths */ + unsigned char *unc[LZO_THREADS]; /* uncompressed data */ +}; + +/** + * CRC32 update function that runs in its own thread. + */ +static int crc32_threadfn(void *data) +{ + struct crc_data *d = data; + unsigned i; + + while (1) { + wait_event(d->go, atomic_read(&d->ready) || + kthread_should_stop()); + if (kthread_should_stop()) { + d->thr = NULL; + atomic_set(&d->stop, 1); + wake_up(&d->done); + break; + } + atomic_set(&d->ready, 0); + + for (i = 0; i < d->run_threads; i++) + *d->crc32 = crc32_le(*d->crc32, + d->unc[i], *d->unc_len[i]); + atomic_set(&d->stop, 1); + wake_up(&d->done); + } + return 0; +} +/** + * Structure used for LZO data compression. + */ +struct cmp_data { + struct task_struct *thr; /* thread */ + atomic_t ready; /* ready to start flag */ + atomic_t stop; /* ready to stop flag */ + int ret; /* return code */ + wait_queue_head_t go; /* start compression */ + wait_queue_head_t done; /* compression done */ + size_t unc_len; /* uncompressed length */ + size_t cmp_len; /* compressed length */ + unsigned char unc[LZO_UNC_SIZE]; /* uncompressed buffer */ + unsigned char cmp[LZO_CMP_SIZE]; /* compressed buffer */ + unsigned char wrk[LZO1X_1_MEM_COMPRESS]; /* compression workspace */ +}; + +/** + * Compression function that runs in its own thread. + */ +static int lzo_compress_threadfn(void *data) +{ + struct cmp_data *d = data; + + while (1) { + wait_event(d->go, atomic_read(&d->ready) || + kthread_should_stop()); + if (kthread_should_stop()) { + d->thr = NULL; + d->ret = -1; + atomic_set(&d->stop, 1); + wake_up(&d->done); + break; + } + atomic_set(&d->ready, 0); + + d->ret = lzo1x_1_compress(d->unc, d->unc_len, + d->cmp + LZO_HEADER, &d->cmp_len, + d->wrk); + atomic_set(&d->stop, 1); + wake_up(&d->done); + } + return 0; +} + +/** + * save_image_lzo - Save the suspend image data compressed with LZO. + * @handle: Swap map handle to use for saving the image. + * @snapshot: Image to read data from. + * @nr_to_write: Number of pages to save. + */ +static int save_image_lzo(struct swap_map_handle *handle, + struct snapshot_handle *snapshot, + unsigned int nr_to_write) +{ + unsigned int m; + int ret = 0; + int nr_pages; + int err2; + struct bio *bio; + ktime_t start; + ktime_t stop; + size_t off; + unsigned thr, run_threads, nr_threads; + unsigned char *page = NULL; + struct cmp_data *data = NULL; + struct crc_data *crc = NULL; + + /* + * We'll limit the number of threads for compression to limit memory + * footprint. + */ + nr_threads = num_online_cpus() - 1; + nr_threads = clamp_val(nr_threads, 1, LZO_THREADS); + + page = (void *)__get_free_page(__GFP_WAIT | __GFP_HIGH); + if (!page) { + printk(KERN_ERR "PM: Failed to allocate LZO page\n"); + ret = -ENOMEM; + goto out_clean; + } + + data = vmalloc(sizeof(*data) * nr_threads); + if (!data) { + printk(KERN_ERR "PM: Failed to allocate LZO data\n"); + ret = -ENOMEM; + goto out_clean; + } + for (thr = 0; thr < nr_threads; thr++) + memset(&data[thr], 0, offsetof(struct cmp_data, go)); + + crc = kmalloc(sizeof(*crc), GFP_KERNEL); + if (!crc) { + printk(KERN_ERR "PM: Failed to allocate crc\n"); + ret = -ENOMEM; + goto out_clean; + } + memset(crc, 0, offsetof(struct crc_data, go)); + + /* + * Start the compression threads. + */ + for (thr = 0; thr < nr_threads; thr++) { + init_waitqueue_head(&data[thr].go); + init_waitqueue_head(&data[thr].done); + + data[thr].thr = kthread_run(lzo_compress_threadfn, + &data[thr], + "image_compress/%u", thr); + if (IS_ERR(data[thr].thr)) { + data[thr].thr = NULL; + printk(KERN_ERR + "PM: Cannot start compression threads\n"); + ret = -ENOMEM; + goto out_clean; + } + } + + /* + * Start the CRC32 thread. + */ + init_waitqueue_head(&crc->go); + init_waitqueue_head(&crc->done); + + handle->crc32 = 0; + crc->crc32 = &handle->crc32; + for (thr = 0; thr < nr_threads; thr++) { + crc->unc[thr] = data[thr].unc; + crc->unc_len[thr] = &data[thr].unc_len; + } + + crc->thr = kthread_run(crc32_threadfn, crc, "image_crc32"); + if (IS_ERR(crc->thr)) { + crc->thr = NULL; + printk(KERN_ERR "PM: Cannot start CRC32 thread\n"); + ret = -ENOMEM; + goto out_clean; + } + + /* + * Adjust the number of required free pages after all allocations have + * been done. We don't want to run out of pages when writing. + */ + handle->reqd_free_pages = reqd_free_pages(); + + printk(KERN_INFO + "PM: Using %u thread(s) for compression.\n" + "PM: Compressing and saving image data (%u pages)...\n", + nr_threads, nr_to_write); + m = nr_to_write / 10; + if (!m) + m = 1; + nr_pages = 0; + bio = NULL; + start = ktime_get(); + for (;;) { + for (thr = 0; thr < nr_threads; thr++) { + for (off = 0; off < LZO_UNC_SIZE; off += PAGE_SIZE) { + ret = snapshot_read_next(snapshot); + if (ret < 0) + goto out_finish; + + if (!ret) + break; + + memcpy(data[thr].unc + off, + data_of(*snapshot), PAGE_SIZE); + + if (!(nr_pages % m)) + printk(KERN_INFO + "PM: Image saving progress: " + "%3d%%\n", + nr_pages / m * 10); + nr_pages++; + } + if (!off) + break; + + data[thr].unc_len = off; + + atomic_set(&data[thr].ready, 1); + wake_up(&data[thr].go); + } + + if (!thr) + break; + + crc->run_threads = thr; + atomic_set(&crc->ready, 1); + wake_up(&crc->go); + + for (run_threads = thr, thr = 0; thr < run_threads; thr++) { + wait_event(data[thr].done, + atomic_read(&data[thr].stop)); + atomic_set(&data[thr].stop, 0); + + ret = data[thr].ret; + + if (ret < 0) { + printk(KERN_ERR "PM: LZO compression failed\n"); + goto out_finish; + } + + if (unlikely(!data[thr].cmp_len || + data[thr].cmp_len > + lzo1x_worst_compress(data[thr].unc_len))) { + printk(KERN_ERR + "PM: Invalid LZO compressed length\n"); + ret = -1; + goto out_finish; + } + + *(size_t *)data[thr].cmp = data[thr].cmp_len; + + /* + * Given we are writing one page at a time to disk, we + * copy that much from the buffer, although the last + * bit will likely be smaller than full page. This is + * OK - we saved the length of the compressed data, so + * any garbage at the end will be discarded when we + * read it. + */ + for (off = 0; + off < LZO_HEADER + data[thr].cmp_len; + off += PAGE_SIZE) { + memcpy(page, data[thr].cmp + off, PAGE_SIZE); + + ret = swap_write_page(handle, page, &bio); + if (ret) + goto out_finish; + } + } + + wait_event(crc->done, atomic_read(&crc->stop)); + atomic_set(&crc->stop, 0); + } + +out_finish: + err2 = hib_wait_on_bio_chain(&bio); + stop = ktime_get(); + if (!ret) + ret = err2; + if (!ret) + printk(KERN_INFO "PM: Image saving done.\n"); + swsusp_show_speed(start, stop, nr_to_write, "Wrote"); +out_clean: + if (crc) { + if (crc->thr) + kthread_stop(crc->thr); + kfree(crc); + } + if (data) { + for (thr = 0; thr < nr_threads; thr++) + if (data[thr].thr) + kthread_stop(data[thr].thr); + vfree(data); + } + if (page) free_page((unsigned long)page); + + return ret; +} + +/** + * enough_swap - Make sure we have enough swap to save the image. + * + * Returns TRUE or FALSE after checking the total amount of swap + * space avaiable from the resume partition. + */ + +static int enough_swap(unsigned int nr_pages, unsigned int flags) +{ + unsigned int free_swap = count_swap_pages(root_swap, 1); + unsigned int required; + + pr_debug("PM: Free swap pages: %u\n", free_swap); + + required = PAGES_FOR_IO + nr_pages; + return free_swap > required; +} + +/** + * swsusp_write - Write entire image and metadata. + * @flags: flags to pass to the "boot" kernel in the image header + * + * It is important _NOT_ to umount filesystems at this point. We want + * them synced (in case something goes wrong) but we DO not want to mark + * filesystem clean: it is not. (And it does not matter, if we resume + * correctly, we'll mark system clean, anyway.) + */ + +int swsusp_write(unsigned int flags) +{ + struct swap_map_handle handle; + struct snapshot_handle snapshot; + struct swsusp_info *header; + unsigned long pages; + int error; + + pages = snapshot_get_image_size(); + error = get_swap_writer(&handle); + if (error) { + printk(KERN_ERR "PM: Cannot get swap writer\n"); + return error; + } + if (flags & SF_NOCOMPRESS_MODE) { + if (!enough_swap(pages, flags)) { + printk(KERN_ERR "PM: Not enough free swap\n"); + error = -ENOSPC; + goto out_finish; + } + } + memset(&snapshot, 0, sizeof(struct snapshot_handle)); + error = snapshot_read_next(&snapshot); + if (error < PAGE_SIZE) { + if (error >= 0) + error = -EFAULT; + + goto out_finish; + } + header = (struct swsusp_info *)data_of(snapshot); + error = swap_write_page(&handle, header, NULL); + if (!error) { + error = (flags & SF_NOCOMPRESS_MODE) ? + save_image(&handle, &snapshot, pages - 1) : + save_image_lzo(&handle, &snapshot, pages - 1); + } +out_finish: + error = swap_writer_finish(&handle, flags, error); + return error; +} + +/** + * The following functions allow us to read data using a swap map + * in a file-alike way + */ + +static void release_swap_reader(struct swap_map_handle *handle) +{ + struct swap_map_page_list *tmp; + + while (handle->maps) { + if (handle->maps->map) + free_page((unsigned long)handle->maps->map); + tmp = handle->maps; + handle->maps = handle->maps->next; + kfree(tmp); + } + handle->cur = NULL; +} + +static int get_swap_reader(struct swap_map_handle *handle, + unsigned int *flags_p) +{ + int error; + struct swap_map_page_list *tmp, *last; + sector_t offset; + + *flags_p = swsusp_header->flags; + + if (!swsusp_header->image) /* how can this happen? */ + return -EINVAL; + + handle->cur = NULL; + last = handle->maps = NULL; + offset = swsusp_header->image; + while (offset) { + tmp = kmalloc(sizeof(*handle->maps), GFP_KERNEL); + if (!tmp) { + release_swap_reader(handle); + return -ENOMEM; + } + memset(tmp, 0, sizeof(*tmp)); + if (!handle->maps) + handle->maps = tmp; + if (last) + last->next = tmp; + last = tmp; + + tmp->map = (struct swap_map_page *) + __get_free_page(__GFP_WAIT | __GFP_HIGH); + if (!tmp->map) { + release_swap_reader(handle); + return -ENOMEM; + } + + error = hib_bio_read_page(offset, tmp->map, NULL); + if (error) { + release_swap_reader(handle); + return error; + } + offset = tmp->map->next_swap; + } + handle->k = 0; + handle->cur = handle->maps->map; + return 0; +} + +static int swap_read_page(struct swap_map_handle *handle, void *buf, + struct bio **bio_chain) +{ + sector_t offset; + int error; + struct swap_map_page_list *tmp; + + if (!handle->cur) + return -EINVAL; + offset = handle->cur->entries[handle->k]; + if (!offset) + return -EFAULT; + error = hib_bio_read_page(offset, buf, bio_chain); + if (error) + return error; + if (++handle->k >= MAP_PAGE_ENTRIES) { + handle->k = 0; + free_page((unsigned long)handle->maps->map); + tmp = handle->maps; + handle->maps = handle->maps->next; + kfree(tmp); + if (!handle->maps) + release_swap_reader(handle); + else + handle->cur = handle->maps->map; + } + return error; +} + +static int swap_reader_finish(struct swap_map_handle *handle) +{ + release_swap_reader(handle); + + return 0; +} + +/** + * load_image - load the image using the swap map handle + * @handle and the snapshot handle @snapshot + * (assume there are @nr_pages pages to load) + */ + +static int load_image(struct swap_map_handle *handle, + struct snapshot_handle *snapshot, + unsigned int nr_to_read) +{ + unsigned int m; + int ret = 0; + ktime_t start; + ktime_t stop; + struct bio *bio; + int err2; + unsigned nr_pages; + + printk(KERN_INFO "PM: Loading image data pages (%u pages)...\n", + nr_to_read); + m = nr_to_read / 10; + if (!m) + m = 1; + nr_pages = 0; + bio = NULL; + start = ktime_get(); + for ( ; ; ) { + ret = snapshot_write_next(snapshot); + if (ret <= 0) + break; + ret = swap_read_page(handle, data_of(*snapshot), &bio); + if (ret) + break; + if (snapshot->sync_read) + ret = hib_wait_on_bio_chain(&bio); + if (ret) + break; + if (!(nr_pages % m)) + printk(KERN_INFO "PM: Image loading progress: %3d%%\n", + nr_pages / m * 10); + nr_pages++; + } + err2 = hib_wait_on_bio_chain(&bio); + stop = ktime_get(); + if (!ret) + ret = err2; + if (!ret) { + printk(KERN_INFO "PM: Image loading done.\n"); + snapshot_write_finalize(snapshot); + if (!snapshot_image_loaded(snapshot)) + ret = -ENODATA; + } + swsusp_show_speed(start, stop, nr_to_read, "Read"); + return ret; +} + +/** + * Structure used for LZO data decompression. + */ +struct dec_data { + struct task_struct *thr; /* thread */ + atomic_t ready; /* ready to start flag */ + atomic_t stop; /* ready to stop flag */ + int ret; /* return code */ + wait_queue_head_t go; /* start decompression */ + wait_queue_head_t done; /* decompression done */ + size_t unc_len; /* uncompressed length */ + size_t cmp_len; /* compressed length */ + unsigned char unc[LZO_UNC_SIZE]; /* uncompressed buffer */ + unsigned char cmp[LZO_CMP_SIZE]; /* compressed buffer */ +}; + +/** + * Deompression function that runs in its own thread. + */ +static int lzo_decompress_threadfn(void *data) +{ + struct dec_data *d = data; + + while (1) { + wait_event(d->go, atomic_read(&d->ready) || + kthread_should_stop()); + if (kthread_should_stop()) { + d->thr = NULL; + d->ret = -1; + atomic_set(&d->stop, 1); + wake_up(&d->done); + break; + } + atomic_set(&d->ready, 0); + + d->unc_len = LZO_UNC_SIZE; + d->ret = lzo1x_decompress_safe(d->cmp + LZO_HEADER, d->cmp_len, + d->unc, &d->unc_len); + atomic_set(&d->stop, 1); + wake_up(&d->done); + } + return 0; +} + +/** + * load_image_lzo - Load compressed image data and decompress them with LZO. + * @handle: Swap map handle to use for loading data. + * @snapshot: Image to copy uncompressed data into. + * @nr_to_read: Number of pages to load. + */ +static int load_image_lzo(struct swap_map_handle *handle, + struct snapshot_handle *snapshot, + unsigned int nr_to_read) +{ + unsigned int m; + int ret = 0; + int eof = 0; + struct bio *bio; + ktime_t start; + ktime_t stop; + unsigned nr_pages; + size_t off; + unsigned i, thr, run_threads, nr_threads; + unsigned ring = 0, pg = 0, ring_size = 0, + have = 0, want, need, asked = 0; + unsigned long read_pages = 0; + unsigned char **page = NULL; + struct dec_data *data = NULL; + struct crc_data *crc = NULL; + + /* + * We'll limit the number of threads for decompression to limit memory + * footprint. + */ + nr_threads = num_online_cpus() - 1; + nr_threads = clamp_val(nr_threads, 1, LZO_THREADS); + + page = vmalloc(sizeof(*page) * LZO_MAX_RD_PAGES); + if (!page) { + printk(KERN_ERR "PM: Failed to allocate LZO page\n"); + ret = -ENOMEM; + goto out_clean; + } + + data = vmalloc(sizeof(*data) * nr_threads); + if (!data) { + printk(KERN_ERR "PM: Failed to allocate LZO data\n"); + ret = -ENOMEM; + goto out_clean; + } + for (thr = 0; thr < nr_threads; thr++) + memset(&data[thr], 0, offsetof(struct dec_data, go)); + + crc = kmalloc(sizeof(*crc), GFP_KERNEL); + if (!crc) { + printk(KERN_ERR "PM: Failed to allocate crc\n"); + ret = -ENOMEM; + goto out_clean; + } + memset(crc, 0, offsetof(struct crc_data, go)); + + /* + * Start the decompression threads. + */ + for (thr = 0; thr < nr_threads; thr++) { + init_waitqueue_head(&data[thr].go); + init_waitqueue_head(&data[thr].done); + + data[thr].thr = kthread_run(lzo_decompress_threadfn, + &data[thr], + "image_decompress/%u", thr); + if (IS_ERR(data[thr].thr)) { + data[thr].thr = NULL; + printk(KERN_ERR + "PM: Cannot start decompression threads\n"); + ret = -ENOMEM; + goto out_clean; + } + } + + /* + * Start the CRC32 thread. + */ + init_waitqueue_head(&crc->go); + init_waitqueue_head(&crc->done); + + handle->crc32 = 0; + crc->crc32 = &handle->crc32; + for (thr = 0; thr < nr_threads; thr++) { + crc->unc[thr] = data[thr].unc; + crc->unc_len[thr] = &data[thr].unc_len; + } + + crc->thr = kthread_run(crc32_threadfn, crc, "image_crc32"); + if (IS_ERR(crc->thr)) { + crc->thr = NULL; + printk(KERN_ERR "PM: Cannot start CRC32 thread\n"); + ret = -ENOMEM; + goto out_clean; + } + + /* + * Set the number of pages for read buffering. + * This is complete guesswork, because we'll only know the real + * picture once prepare_image() is called, which is much later on + * during the image load phase. We'll assume the worst case and + * say that none of the image pages are from high memory. + */ + if (low_free_pages() > snapshot_get_image_size()) + read_pages = (low_free_pages() - snapshot_get_image_size()) / 2; + read_pages = clamp_val(read_pages, LZO_MIN_RD_PAGES, LZO_MAX_RD_PAGES); + + for (i = 0; i < read_pages; i++) { + page[i] = (void *)__get_free_page(i < LZO_CMP_PAGES ? + __GFP_WAIT | __GFP_HIGH : + __GFP_WAIT | __GFP_NOWARN | + __GFP_NORETRY); + + if (!page[i]) { + if (i < LZO_CMP_PAGES) { + ring_size = i; + printk(KERN_ERR + "PM: Failed to allocate LZO pages\n"); + ret = -ENOMEM; + goto out_clean; + } else { + break; + } + } + } + want = ring_size = i; + + printk(KERN_INFO + "PM: Using %u thread(s) for decompression.\n" + "PM: Loading and decompressing image data (%u pages)...\n", + nr_threads, nr_to_read); + m = nr_to_read / 10; + if (!m) + m = 1; + nr_pages = 0; + bio = NULL; + start = ktime_get(); + + ret = snapshot_write_next(snapshot); + if (ret <= 0) + goto out_finish; + + for(;;) { + for (i = 0; !eof && i < want; i++) { + ret = swap_read_page(handle, page[ring], &bio); + if (ret) { + /* + * On real read error, finish. On end of data, + * set EOF flag and just exit the read loop. + */ + if (handle->cur && + handle->cur->entries[handle->k]) { + goto out_finish; + } else { + eof = 1; + break; + } + } + if (++ring >= ring_size) + ring = 0; + } + asked += i; + want -= i; + + /* + * We are out of data, wait for some more. + */ + if (!have) { + if (!asked) + break; + + ret = hib_wait_on_bio_chain(&bio); + if (ret) + goto out_finish; + have += asked; + asked = 0; + if (eof) + eof = 2; + } + + if (crc->run_threads) { + wait_event(crc->done, atomic_read(&crc->stop)); + atomic_set(&crc->stop, 0); + crc->run_threads = 0; + } + + for (thr = 0; have && thr < nr_threads; thr++) { + data[thr].cmp_len = *(size_t *)page[pg]; + if (unlikely(!data[thr].cmp_len || + data[thr].cmp_len > + lzo1x_worst_compress(LZO_UNC_SIZE))) { + printk(KERN_ERR + "PM: Invalid LZO compressed length\n"); + ret = -1; + goto out_finish; + } + + need = DIV_ROUND_UP(data[thr].cmp_len + LZO_HEADER, + PAGE_SIZE); + if (need > have) { + if (eof > 1) { + ret = -1; + goto out_finish; + } + break; + } + + for (off = 0; + off < LZO_HEADER + data[thr].cmp_len; + off += PAGE_SIZE) { + memcpy(data[thr].cmp + off, + page[pg], PAGE_SIZE); + have--; + want++; + if (++pg >= ring_size) + pg = 0; + } + + atomic_set(&data[thr].ready, 1); + wake_up(&data[thr].go); + } + + /* + * Wait for more data while we are decompressing. + */ + if (have < LZO_CMP_PAGES && asked) { + ret = hib_wait_on_bio_chain(&bio); + if (ret) + goto out_finish; + have += asked; + asked = 0; + if (eof) + eof = 2; + } + + for (run_threads = thr, thr = 0; thr < run_threads; thr++) { + wait_event(data[thr].done, + atomic_read(&data[thr].stop)); + atomic_set(&data[thr].stop, 0); + + ret = data[thr].ret; + + if (ret < 0) { + printk(KERN_ERR + "PM: LZO decompression failed\n"); + goto out_finish; + } + + if (unlikely(!data[thr].unc_len || + data[thr].unc_len > LZO_UNC_SIZE || + data[thr].unc_len & (PAGE_SIZE - 1))) { + printk(KERN_ERR + "PM: Invalid LZO uncompressed length\n"); + ret = -1; + goto out_finish; + } + + for (off = 0; + off < data[thr].unc_len; off += PAGE_SIZE) { + memcpy(data_of(*snapshot), + data[thr].unc + off, PAGE_SIZE); + + if (!(nr_pages % m)) + printk(KERN_INFO + "PM: Image loading progress: " + "%3d%%\n", + nr_pages / m * 10); + nr_pages++; + + ret = snapshot_write_next(snapshot); + if (ret <= 0) { + crc->run_threads = thr + 1; + atomic_set(&crc->ready, 1); + wake_up(&crc->go); + goto out_finish; + } + } + } + + crc->run_threads = thr; + atomic_set(&crc->ready, 1); + wake_up(&crc->go); + } + +out_finish: + if (crc->run_threads) { + wait_event(crc->done, atomic_read(&crc->stop)); + atomic_set(&crc->stop, 0); + } + stop = ktime_get(); + if (!ret) { + printk(KERN_INFO "PM: Image loading done.\n"); + snapshot_write_finalize(snapshot); + if (!snapshot_image_loaded(snapshot)) + ret = -ENODATA; + if (!ret) { + if (swsusp_header->flags & SF_CRC32_MODE) { + if(handle->crc32 != swsusp_header->crc32) { + printk(KERN_ERR + "PM: Invalid image CRC32!\n"); + ret = -ENODATA; + } + } + } + } + swsusp_show_speed(start, stop, nr_to_read, "Read"); +out_clean: + for (i = 0; i < ring_size; i++) + free_page((unsigned long)page[i]); + if (crc) { + if (crc->thr) + kthread_stop(crc->thr); + kfree(crc); + } + if (data) { + for (thr = 0; thr < nr_threads; thr++) + if (data[thr].thr) + kthread_stop(data[thr].thr); + vfree(data); + } + vfree(page); + + return ret; +} + +/** + * swsusp_read - read the hibernation image. + * @flags_p: flags passed by the "frozen" kernel in the image header should + * be written into this memory location + */ + +int swsusp_read(unsigned int *flags_p) +{ + int error; + struct swap_map_handle handle; + struct snapshot_handle snapshot; + struct swsusp_info *header; + + memset(&snapshot, 0, sizeof(struct snapshot_handle)); + error = snapshot_write_next(&snapshot); + if (error < PAGE_SIZE) + return error < 0 ? error : -EFAULT; + header = (struct swsusp_info *)data_of(snapshot); + error = get_swap_reader(&handle, flags_p); + if (error) + goto end; + if (!error) + error = swap_read_page(&handle, header, NULL); + if (!error) { + error = (*flags_p & SF_NOCOMPRESS_MODE) ? + load_image(&handle, &snapshot, header->pages - 1) : + load_image_lzo(&handle, &snapshot, header->pages - 1); + } + swap_reader_finish(&handle); +end: + if (!error) + pr_debug("PM: Image successfully loaded\n"); + else + pr_debug("PM: Error %d resuming\n", error); + return error; +} + +/** + * swsusp_check - Check for swsusp signature in the resume device + */ + +int swsusp_check(void) +{ + int error; + + hib_resume_bdev = blkdev_get_by_dev(swsusp_resume_device, + FMODE_READ, NULL); + if (!IS_ERR(hib_resume_bdev)) { + set_blocksize(hib_resume_bdev, PAGE_SIZE); + clear_page(swsusp_header); + error = hib_bio_read_page(swsusp_resume_block, + swsusp_header, NULL); + if (error) + goto put; + + if (!memcmp(HIBERNATE_SIG, swsusp_header->sig, 10)) { + memcpy(swsusp_header->sig, swsusp_header->orig_sig, 10); + /* Reset swap signature now */ + error = hib_bio_write_page(swsusp_resume_block, + swsusp_header, NULL); + } else { + error = -EINVAL; + } + +put: + if (error) + blkdev_put(hib_resume_bdev, FMODE_READ); + else + pr_debug("PM: Image signature found, resuming\n"); + } else { + error = PTR_ERR(hib_resume_bdev); + } + + if (error) + pr_debug("PM: Image not found (code %d)\n", error); + + return error; +} + +/** + * swsusp_close - close swap device. + */ + +void swsusp_close(fmode_t mode) +{ + if (IS_ERR(hib_resume_bdev)) { + pr_debug("PM: Image device not initialised\n"); + return; + } + + blkdev_put(hib_resume_bdev, mode); +} + +/** + * swsusp_unmark - Unmark swsusp signature in the resume device + */ + +#ifdef CONFIG_SUSPEND +int swsusp_unmark(void) +{ + int error; + + hib_bio_read_page(swsusp_resume_block, swsusp_header, NULL); + if (!memcmp(HIBERNATE_SIG,swsusp_header->sig, 10)) { + memcpy(swsusp_header->sig,swsusp_header->orig_sig, 10); + error = hib_bio_write_page(swsusp_resume_block, + swsusp_header, NULL); + } else { + printk(KERN_ERR "PM: Cannot find swsusp signature!\n"); + error = -ENODEV; + } + + /* + * We just returned from suspend, we don't need the image any more. + */ + free_all_swap_pages(root_swap); + + return error; +} +#endif + +static int swsusp_header_init(void) +{ + swsusp_header = (struct swsusp_header*) __get_free_page(GFP_KERNEL); + if (!swsusp_header) + panic("Could not allocate memory for swsusp_header\n"); + return 0; +} + +core_initcall(swsusp_header_init); diff --git a/kernel/kernel/power/user.c b/kernel/kernel/power/user.c new file mode 100644 index 000000000..526e89114 --- /dev/null +++ b/kernel/kernel/power/user.c @@ -0,0 +1,478 @@ +/* + * linux/kernel/power/user.c + * + * This file provides the user space interface for software suspend/resume. + * + * Copyright (C) 2006 Rafael J. Wysocki + * + * This file is released under the GPLv2. + * + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +#include "power.h" + + +#define SNAPSHOT_MINOR 231 + +static struct snapshot_data { + struct snapshot_handle handle; + int swap; + int mode; + bool frozen; + bool ready; + bool platform_support; + bool free_bitmaps; +} snapshot_state; + +atomic_t snapshot_device_available = ATOMIC_INIT(1); + +static int snapshot_open(struct inode *inode, struct file *filp) +{ + struct snapshot_data *data; + int error; + + if (!hibernation_available()) + return -EPERM; + + lock_system_sleep(); + + if (!atomic_add_unless(&snapshot_device_available, -1, 0)) { + error = -EBUSY; + goto Unlock; + } + + if ((filp->f_flags & O_ACCMODE) == O_RDWR) { + atomic_inc(&snapshot_device_available); + error = -ENOSYS; + goto Unlock; + } + nonseekable_open(inode, filp); + data = &snapshot_state; + filp->private_data = data; + memset(&data->handle, 0, sizeof(struct snapshot_handle)); + if ((filp->f_flags & O_ACCMODE) == O_RDONLY) { + /* Hibernating. The image device should be accessible. */ + data->swap = swsusp_resume_device ? + swap_type_of(swsusp_resume_device, 0, NULL) : -1; + data->mode = O_RDONLY; + data->free_bitmaps = false; + error = pm_notifier_call_chain(PM_HIBERNATION_PREPARE); + if (error) + pm_notifier_call_chain(PM_POST_HIBERNATION); + } else { + /* + * Resuming. We may need to wait for the image device to + * appear. + */ + wait_for_device_probe(); + + data->swap = -1; + data->mode = O_WRONLY; + error = pm_notifier_call_chain(PM_RESTORE_PREPARE); + if (!error) { + error = create_basic_memory_bitmaps(); + data->free_bitmaps = !error; + } + if (error) + pm_notifier_call_chain(PM_POST_RESTORE); + } + if (error) + atomic_inc(&snapshot_device_available); + + data->frozen = false; + data->ready = false; + data->platform_support = false; + + Unlock: + unlock_system_sleep(); + + return error; +} + +static int snapshot_release(struct inode *inode, struct file *filp) +{ + struct snapshot_data *data; + + lock_system_sleep(); + + swsusp_free(); + data = filp->private_data; + free_all_swap_pages(data->swap); + if (data->frozen) { + pm_restore_gfp_mask(); + free_basic_memory_bitmaps(); + thaw_processes(); + } else if (data->free_bitmaps) { + free_basic_memory_bitmaps(); + } + pm_notifier_call_chain(data->mode == O_RDONLY ? + PM_POST_HIBERNATION : PM_POST_RESTORE); + atomic_inc(&snapshot_device_available); + + unlock_system_sleep(); + + return 0; +} + +static ssize_t snapshot_read(struct file *filp, char __user *buf, + size_t count, loff_t *offp) +{ + struct snapshot_data *data; + ssize_t res; + loff_t pg_offp = *offp & ~PAGE_MASK; + + lock_system_sleep(); + + data = filp->private_data; + if (!data->ready) { + res = -ENODATA; + goto Unlock; + } + if (!pg_offp) { /* on page boundary? */ + res = snapshot_read_next(&data->handle); + if (res <= 0) + goto Unlock; + } else { + res = PAGE_SIZE - pg_offp; + } + + res = simple_read_from_buffer(buf, count, &pg_offp, + data_of(data->handle), res); + if (res > 0) + *offp += res; + + Unlock: + unlock_system_sleep(); + + return res; +} + +static ssize_t snapshot_write(struct file *filp, const char __user *buf, + size_t count, loff_t *offp) +{ + struct snapshot_data *data; + ssize_t res; + loff_t pg_offp = *offp & ~PAGE_MASK; + + lock_system_sleep(); + + data = filp->private_data; + + if (!pg_offp) { + res = snapshot_write_next(&data->handle); + if (res <= 0) + goto unlock; + } else { + res = PAGE_SIZE - pg_offp; + } + + res = simple_write_to_buffer(data_of(data->handle), res, &pg_offp, + buf, count); + if (res > 0) + *offp += res; +unlock: + unlock_system_sleep(); + + return res; +} + +static long snapshot_ioctl(struct file *filp, unsigned int cmd, + unsigned long arg) +{ + int error = 0; + struct snapshot_data *data; + loff_t size; + sector_t offset; + + if (_IOC_TYPE(cmd) != SNAPSHOT_IOC_MAGIC) + return -ENOTTY; + if (_IOC_NR(cmd) > SNAPSHOT_IOC_MAXNR) + return -ENOTTY; + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + if (!mutex_trylock(&pm_mutex)) + return -EBUSY; + + lock_device_hotplug(); + data = filp->private_data; + + switch (cmd) { + + case SNAPSHOT_FREEZE: + if (data->frozen) + break; + + printk("Syncing filesystems ... "); + sys_sync(); + printk("done.\n"); + + error = freeze_processes(); + if (error) + break; + + error = create_basic_memory_bitmaps(); + if (error) + thaw_processes(); + else + data->frozen = true; + + break; + + case SNAPSHOT_UNFREEZE: + if (!data->frozen || data->ready) + break; + pm_restore_gfp_mask(); + free_basic_memory_bitmaps(); + data->free_bitmaps = false; + thaw_processes(); + data->frozen = false; + break; + + case SNAPSHOT_CREATE_IMAGE: + if (data->mode != O_RDONLY || !data->frozen || data->ready) { + error = -EPERM; + break; + } + pm_restore_gfp_mask(); + error = hibernation_snapshot(data->platform_support); + if (!error) { + error = put_user(in_suspend, (int __user *)arg); + data->ready = !freezer_test_done && !error; + freezer_test_done = false; + } + break; + + case SNAPSHOT_ATOMIC_RESTORE: + snapshot_write_finalize(&data->handle); + if (data->mode != O_WRONLY || !data->frozen || + !snapshot_image_loaded(&data->handle)) { + error = -EPERM; + break; + } + error = hibernation_restore(data->platform_support); + break; + + case SNAPSHOT_FREE: + swsusp_free(); + memset(&data->handle, 0, sizeof(struct snapshot_handle)); + data->ready = false; + /* + * It is necessary to thaw kernel threads here, because + * SNAPSHOT_CREATE_IMAGE may be invoked directly after + * SNAPSHOT_FREE. In that case, if kernel threads were not + * thawed, the preallocation of memory carried out by + * hibernation_snapshot() might run into problems (i.e. it + * might fail or even deadlock). + */ + thaw_kernel_threads(); + break; + + case SNAPSHOT_PREF_IMAGE_SIZE: + image_size = arg; + break; + + case SNAPSHOT_GET_IMAGE_SIZE: + if (!data->ready) { + error = -ENODATA; + break; + } + size = snapshot_get_image_size(); + size <<= PAGE_SHIFT; + error = put_user(size, (loff_t __user *)arg); + break; + + case SNAPSHOT_AVAIL_SWAP_SIZE: + size = count_swap_pages(data->swap, 1); + size <<= PAGE_SHIFT; + error = put_user(size, (loff_t __user *)arg); + break; + + case SNAPSHOT_ALLOC_SWAP_PAGE: + if (data->swap < 0 || data->swap >= MAX_SWAPFILES) { + error = -ENODEV; + break; + } + offset = alloc_swapdev_block(data->swap); + if (offset) { + offset <<= PAGE_SHIFT; + error = put_user(offset, (loff_t __user *)arg); + } else { + error = -ENOSPC; + } + break; + + case SNAPSHOT_FREE_SWAP_PAGES: + if (data->swap < 0 || data->swap >= MAX_SWAPFILES) { + error = -ENODEV; + break; + } + free_all_swap_pages(data->swap); + break; + + case SNAPSHOT_S2RAM: + if (!data->frozen) { + error = -EPERM; + break; + } + /* + * Tasks are frozen and the notifiers have been called with + * PM_HIBERNATION_PREPARE + */ + error = suspend_devices_and_enter(PM_SUSPEND_MEM); + data->ready = false; + break; + + case SNAPSHOT_PLATFORM_SUPPORT: + data->platform_support = !!arg; + break; + + case SNAPSHOT_POWER_OFF: + if (data->platform_support) + error = hibernation_platform_enter(); + break; + + case SNAPSHOT_SET_SWAP_AREA: + if (swsusp_swap_in_use()) { + error = -EPERM; + } else { + struct resume_swap_area swap_area; + dev_t swdev; + + error = copy_from_user(&swap_area, (void __user *)arg, + sizeof(struct resume_swap_area)); + if (error) { + error = -EFAULT; + break; + } + + /* + * User space encodes device types as two-byte values, + * so we need to recode them + */ + swdev = new_decode_dev(swap_area.dev); + if (swdev) { + offset = swap_area.offset; + data->swap = swap_type_of(swdev, offset, NULL); + if (data->swap < 0) + error = -ENODEV; + } else { + data->swap = -1; + error = -EINVAL; + } + } + break; + + default: + error = -ENOTTY; + + } + + unlock_device_hotplug(); + mutex_unlock(&pm_mutex); + + return error; +} + +#ifdef CONFIG_COMPAT + +struct compat_resume_swap_area { + compat_loff_t offset; + u32 dev; +} __packed; + +static long +snapshot_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) +{ + BUILD_BUG_ON(sizeof(loff_t) != sizeof(compat_loff_t)); + + switch (cmd) { + case SNAPSHOT_GET_IMAGE_SIZE: + case SNAPSHOT_AVAIL_SWAP_SIZE: + case SNAPSHOT_ALLOC_SWAP_PAGE: { + compat_loff_t __user *uoffset = compat_ptr(arg); + loff_t offset; + mm_segment_t old_fs; + int err; + + old_fs = get_fs(); + set_fs(KERNEL_DS); + err = snapshot_ioctl(file, cmd, (unsigned long) &offset); + set_fs(old_fs); + if (!err && put_user(offset, uoffset)) + err = -EFAULT; + return err; + } + + case SNAPSHOT_CREATE_IMAGE: + return snapshot_ioctl(file, cmd, + (unsigned long) compat_ptr(arg)); + + case SNAPSHOT_SET_SWAP_AREA: { + struct compat_resume_swap_area __user *u_swap_area = + compat_ptr(arg); + struct resume_swap_area swap_area; + mm_segment_t old_fs; + int err; + + err = get_user(swap_area.offset, &u_swap_area->offset); + err |= get_user(swap_area.dev, &u_swap_area->dev); + if (err) + return -EFAULT; + old_fs = get_fs(); + set_fs(KERNEL_DS); + err = snapshot_ioctl(file, SNAPSHOT_SET_SWAP_AREA, + (unsigned long) &swap_area); + set_fs(old_fs); + return err; + } + + default: + return snapshot_ioctl(file, cmd, arg); + } +} + +#endif /* CONFIG_COMPAT */ + +static const struct file_operations snapshot_fops = { + .open = snapshot_open, + .release = snapshot_release, + .read = snapshot_read, + .write = snapshot_write, + .llseek = no_llseek, + .unlocked_ioctl = snapshot_ioctl, +#ifdef CONFIG_COMPAT + .compat_ioctl = snapshot_compat_ioctl, +#endif +}; + +static struct miscdevice snapshot_device = { + .minor = SNAPSHOT_MINOR, + .name = "snapshot", + .fops = &snapshot_fops, +}; + +static int __init snapshot_device_init(void) +{ + return misc_register(&snapshot_device); +}; + +device_initcall(snapshot_device_init); diff --git a/kernel/kernel/power/wakelock.c b/kernel/kernel/power/wakelock.c new file mode 100644 index 000000000..019069c84 --- /dev/null +++ b/kernel/kernel/power/wakelock.c @@ -0,0 +1,268 @@ +/* + * kernel/power/wakelock.c + * + * User space wakeup sources support. + * + * Copyright (C) 2012 Rafael J. Wysocki + * + * This code is based on the analogous interface allowing user space to + * manipulate wakelocks on Android. + */ + +#include +#include +#include +#include +#include +#include +#include +#include + +#include "power.h" + +static DEFINE_MUTEX(wakelocks_lock); + +struct wakelock { + char *name; + struct rb_node node; + struct wakeup_source ws; +#ifdef CONFIG_PM_WAKELOCKS_GC + struct list_head lru; +#endif +}; + +static struct rb_root wakelocks_tree = RB_ROOT; + +ssize_t pm_show_wakelocks(char *buf, bool show_active) +{ + struct rb_node *node; + struct wakelock *wl; + char *str = buf; + char *end = buf + PAGE_SIZE; + + mutex_lock(&wakelocks_lock); + + for (node = rb_first(&wakelocks_tree); node; node = rb_next(node)) { + wl = rb_entry(node, struct wakelock, node); + if (wl->ws.active == show_active) + str += scnprintf(str, end - str, "%s ", wl->name); + } + if (str > buf) + str--; + + str += scnprintf(str, end - str, "\n"); + + mutex_unlock(&wakelocks_lock); + return (str - buf); +} + +#if CONFIG_PM_WAKELOCKS_LIMIT > 0 +static unsigned int number_of_wakelocks; + +static inline bool wakelocks_limit_exceeded(void) +{ + return number_of_wakelocks > CONFIG_PM_WAKELOCKS_LIMIT; +} + +static inline void increment_wakelocks_number(void) +{ + number_of_wakelocks++; +} + +static inline void decrement_wakelocks_number(void) +{ + number_of_wakelocks--; +} +#else /* CONFIG_PM_WAKELOCKS_LIMIT = 0 */ +static inline bool wakelocks_limit_exceeded(void) { return false; } +static inline void increment_wakelocks_number(void) {} +static inline void decrement_wakelocks_number(void) {} +#endif /* CONFIG_PM_WAKELOCKS_LIMIT */ + +#ifdef CONFIG_PM_WAKELOCKS_GC +#define WL_GC_COUNT_MAX 100 +#define WL_GC_TIME_SEC 300 + +static LIST_HEAD(wakelocks_lru_list); +static unsigned int wakelocks_gc_count; + +static inline void wakelocks_lru_add(struct wakelock *wl) +{ + list_add(&wl->lru, &wakelocks_lru_list); +} + +static inline void wakelocks_lru_most_recent(struct wakelock *wl) +{ + list_move(&wl->lru, &wakelocks_lru_list); +} + +static void wakelocks_gc(void) +{ + struct wakelock *wl, *aux; + ktime_t now; + + if (++wakelocks_gc_count <= WL_GC_COUNT_MAX) + return; + + now = ktime_get(); + list_for_each_entry_safe_reverse(wl, aux, &wakelocks_lru_list, lru) { + u64 idle_time_ns; + bool active; + + spin_lock_irq(&wl->ws.lock); + idle_time_ns = ktime_to_ns(ktime_sub(now, wl->ws.last_time)); + active = wl->ws.active; + spin_unlock_irq(&wl->ws.lock); + + if (idle_time_ns < ((u64)WL_GC_TIME_SEC * NSEC_PER_SEC)) + break; + + if (!active) { + wakeup_source_remove(&wl->ws); + rb_erase(&wl->node, &wakelocks_tree); + list_del(&wl->lru); + kfree(wl->name); + kfree(wl); + decrement_wakelocks_number(); + } + } + wakelocks_gc_count = 0; +} +#else /* !CONFIG_PM_WAKELOCKS_GC */ +static inline void wakelocks_lru_add(struct wakelock *wl) {} +static inline void wakelocks_lru_most_recent(struct wakelock *wl) {} +static inline void wakelocks_gc(void) {} +#endif /* !CONFIG_PM_WAKELOCKS_GC */ + +static struct wakelock *wakelock_lookup_add(const char *name, size_t len, + bool add_if_not_found) +{ + struct rb_node **node = &wakelocks_tree.rb_node; + struct rb_node *parent = *node; + struct wakelock *wl; + + while (*node) { + int diff; + + parent = *node; + wl = rb_entry(*node, struct wakelock, node); + diff = strncmp(name, wl->name, len); + if (diff == 0) { + if (wl->name[len]) + diff = -1; + else + return wl; + } + if (diff < 0) + node = &(*node)->rb_left; + else + node = &(*node)->rb_right; + } + if (!add_if_not_found) + return ERR_PTR(-EINVAL); + + if (wakelocks_limit_exceeded()) + return ERR_PTR(-ENOSPC); + + /* Not found, we have to add a new one. */ + wl = kzalloc(sizeof(*wl), GFP_KERNEL); + if (!wl) + return ERR_PTR(-ENOMEM); + + wl->name = kstrndup(name, len, GFP_KERNEL); + if (!wl->name) { + kfree(wl); + return ERR_PTR(-ENOMEM); + } + wl->ws.name = wl->name; + wakeup_source_add(&wl->ws); + rb_link_node(&wl->node, parent, node); + rb_insert_color(&wl->node, &wakelocks_tree); + wakelocks_lru_add(wl); + increment_wakelocks_number(); + return wl; +} + +int pm_wake_lock(const char *buf) +{ + const char *str = buf; + struct wakelock *wl; + u64 timeout_ns = 0; + size_t len; + int ret = 0; + + if (!capable(CAP_BLOCK_SUSPEND)) + return -EPERM; + + while (*str && !isspace(*str)) + str++; + + len = str - buf; + if (!len) + return -EINVAL; + + if (*str && *str != '\n') { + /* Find out if there's a valid timeout string appended. */ + ret = kstrtou64(skip_spaces(str), 10, &timeout_ns); + if (ret) + return -EINVAL; + } + + mutex_lock(&wakelocks_lock); + + wl = wakelock_lookup_add(buf, len, true); + if (IS_ERR(wl)) { + ret = PTR_ERR(wl); + goto out; + } + if (timeout_ns) { + u64 timeout_ms = timeout_ns + NSEC_PER_MSEC - 1; + + do_div(timeout_ms, NSEC_PER_MSEC); + __pm_wakeup_event(&wl->ws, timeout_ms); + } else { + __pm_stay_awake(&wl->ws); + } + + wakelocks_lru_most_recent(wl); + + out: + mutex_unlock(&wakelocks_lock); + return ret; +} + +int pm_wake_unlock(const char *buf) +{ + struct wakelock *wl; + size_t len; + int ret = 0; + + if (!capable(CAP_BLOCK_SUSPEND)) + return -EPERM; + + len = strlen(buf); + if (!len) + return -EINVAL; + + if (buf[len-1] == '\n') + len--; + + if (!len) + return -EINVAL; + + mutex_lock(&wakelocks_lock); + + wl = wakelock_lookup_add(buf, len, false); + if (IS_ERR(wl)) { + ret = PTR_ERR(wl); + goto out; + } + __pm_relax(&wl->ws); + + wakelocks_lru_most_recent(wl); + wakelocks_gc(); + + out: + mutex_unlock(&wakelocks_lock); + return ret; +} diff --git a/kernel/kernel/printk/Makefile b/kernel/kernel/printk/Makefile new file mode 100644 index 000000000..85405bdcf --- /dev/null +++ b/kernel/kernel/printk/Makefile @@ -0,0 +1,2 @@ +obj-y = printk.o +obj-$(CONFIG_A11Y_BRAILLE_CONSOLE) += braille.o diff --git a/kernel/kernel/printk/braille.c b/kernel/kernel/printk/braille.c new file mode 100644 index 000000000..276762f3a --- /dev/null +++ b/kernel/kernel/printk/braille.c @@ -0,0 +1,49 @@ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include +#include + +#include "console_cmdline.h" +#include "braille.h" + +char *_braille_console_setup(char **str, char **brl_options) +{ + if (!memcmp(*str, "brl,", 4)) { + *brl_options = ""; + *str += 4; + } else if (!memcmp(str, "brl=", 4)) { + *brl_options = *str + 4; + *str = strchr(*brl_options, ','); + if (!*str) + pr_err("need port name after brl=\n"); + else + *((*str)++) = 0; + } else + return NULL; + + return *str; +} + +int +_braille_register_console(struct console *console, struct console_cmdline *c) +{ + int rtn = 0; + + if (c->brl_options) { + console->flags |= CON_BRL; + rtn = braille_register_console(console, c->index, c->options, + c->brl_options); + } + + return rtn; +} + +int +_braille_unregister_console(struct console *console) +{ + if (console->flags & CON_BRL) + return braille_unregister_console(console); + + return 0; +} diff --git a/kernel/kernel/printk/braille.h b/kernel/kernel/printk/braille.h new file mode 100644 index 000000000..769d77114 --- /dev/null +++ b/kernel/kernel/printk/braille.h @@ -0,0 +1,48 @@ +#ifndef _PRINTK_BRAILLE_H +#define _PRINTK_BRAILLE_H + +#ifdef CONFIG_A11Y_BRAILLE_CONSOLE + +static inline void +braille_set_options(struct console_cmdline *c, char *brl_options) +{ + c->brl_options = brl_options; +} + +char * +_braille_console_setup(char **str, char **brl_options); + +int +_braille_register_console(struct console *console, struct console_cmdline *c); + +int +_braille_unregister_console(struct console *console); + +#else + +static inline void +braille_set_options(struct console_cmdline *c, char *brl_options) +{ +} + +static inline char * +_braille_console_setup(char **str, char **brl_options) +{ + return NULL; +} + +static inline int +_braille_register_console(struct console *console, struct console_cmdline *c) +{ + return 0; +} + +static inline int +_braille_unregister_console(struct console *console) +{ + return 0; +} + +#endif + +#endif diff --git a/kernel/kernel/printk/console_cmdline.h b/kernel/kernel/printk/console_cmdline.h new file mode 100644 index 000000000..2ca4a8b5f --- /dev/null +++ b/kernel/kernel/printk/console_cmdline.h @@ -0,0 +1,14 @@ +#ifndef _CONSOLE_CMDLINE_H +#define _CONSOLE_CMDLINE_H + +struct console_cmdline +{ + char name[16]; /* Name of the driver */ + int index; /* Minor dev. to use */ + char *options; /* Options for the driver */ +#ifdef CONFIG_A11Y_BRAILLE_CONSOLE + char *brl_options; /* Options for braille driver */ +#endif +}; + +#endif diff --git a/kernel/kernel/printk/printk.c b/kernel/kernel/printk/printk.c new file mode 100644 index 000000000..6062a0442 --- /dev/null +++ b/kernel/kernel/printk/printk.c @@ -0,0 +1,3156 @@ +/* + * linux/kernel/printk.c + * + * Copyright (C) 1991, 1992 Linus Torvalds + * + * Modified to make sys_syslog() more flexible: added commands to + * return the last 4k of kernel messages, regardless of whether + * they've been read or not. Added option to suppress kernel printk's + * to the console. Added hook for sending the console messages + * elsewhere, in preparation for a serial line console (someday). + * Ted Ts'o, 2/11/93. + * Modified for sysctl support, 1/8/97, Chris Horn. + * Fixed SMP synchronization, 08/08/99, Manfred Spraul + * manfred@colorfullife.com + * Rewrote bits to get rid of console_lock + * 01Mar01 Andrew Morton + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include /* For in_interrupt() */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +#define CREATE_TRACE_POINTS +#include + +#include "console_cmdline.h" +#include "braille.h" + +int console_printk[4] = { + CONSOLE_LOGLEVEL_DEFAULT, /* console_loglevel */ + MESSAGE_LOGLEVEL_DEFAULT, /* default_message_loglevel */ + CONSOLE_LOGLEVEL_MIN, /* minimum_console_loglevel */ + CONSOLE_LOGLEVEL_DEFAULT, /* default_console_loglevel */ +}; + +/* + * Low level drivers may need that to know if they can schedule in + * their unblank() callback or not. So let's export it. + */ +int oops_in_progress; +EXPORT_SYMBOL(oops_in_progress); + +/* + * console_sem protects the console_drivers list, and also + * provides serialisation for access to the entire console + * driver system. + */ +static DEFINE_SEMAPHORE(console_sem); +struct console *console_drivers; +EXPORT_SYMBOL_GPL(console_drivers); + +#ifdef CONFIG_LOCKDEP +static struct lockdep_map console_lock_dep_map = { + .name = "console_lock" +}; +#endif + +/* + * Helper macros to handle lockdep when locking/unlocking console_sem. We use + * macros instead of functions so that _RET_IP_ contains useful information. + */ +#define down_console_sem() do { \ + down(&console_sem);\ + mutex_acquire(&console_lock_dep_map, 0, 0, _RET_IP_);\ +} while (0) + +static int __down_trylock_console_sem(unsigned long ip) +{ + if (down_trylock(&console_sem)) + return 1; + mutex_acquire(&console_lock_dep_map, 0, 1, ip); + return 0; +} +#define down_trylock_console_sem() __down_trylock_console_sem(_RET_IP_) + +#define up_console_sem() do { \ + mutex_release(&console_lock_dep_map, 1, _RET_IP_);\ + up(&console_sem);\ +} while (0) + +/* + * This is used for debugging the mess that is the VT code by + * keeping track if we have the console semaphore held. It's + * definitely not the perfect debug tool (we don't know if _WE_ + * hold it and are racing, but it helps tracking those weird code + * paths in the console code where we end up in places I want + * locked without the console sempahore held). + */ +static int console_locked, console_suspended; + +/* + * If exclusive_console is non-NULL then only this console is to be printed to. + */ +static struct console *exclusive_console; + +/* + * Array of consoles built from command line options (console=) + */ + +#define MAX_CMDLINECONSOLES 8 + +static struct console_cmdline console_cmdline[MAX_CMDLINECONSOLES]; + +static int selected_console = -1; +static int preferred_console = -1; +int console_set_on_cmdline; +EXPORT_SYMBOL(console_set_on_cmdline); + +/* Flag: console code may call schedule() */ +static int console_may_schedule; + +/* + * The printk log buffer consists of a chain of concatenated variable + * length records. Every record starts with a record header, containing + * the overall length of the record. + * + * The heads to the first and last entry in the buffer, as well as the + * sequence numbers of these entries are maintained when messages are + * stored. + * + * If the heads indicate available messages, the length in the header + * tells the start next message. A length == 0 for the next message + * indicates a wrap-around to the beginning of the buffer. + * + * Every record carries the monotonic timestamp in microseconds, as well as + * the standard userspace syslog level and syslog facility. The usual + * kernel messages use LOG_KERN; userspace-injected messages always carry + * a matching syslog facility, by default LOG_USER. The origin of every + * message can be reliably determined that way. + * + * The human readable log message directly follows the message header. The + * length of the message text is stored in the header, the stored message + * is not terminated. + * + * Optionally, a message can carry a dictionary of properties (key/value pairs), + * to provide userspace with a machine-readable message context. + * + * Examples for well-defined, commonly used property names are: + * DEVICE=b12:8 device identifier + * b12:8 block dev_t + * c127:3 char dev_t + * n8 netdev ifindex + * +sound:card0 subsystem:devname + * SUBSYSTEM=pci driver-core subsystem name + * + * Valid characters in property names are [a-zA-Z0-9.-_]. The plain text value + * follows directly after a '=' character. Every property is terminated by + * a '\0' character. The last property is not terminated. + * + * Example of a message structure: + * 0000 ff 8f 00 00 00 00 00 00 monotonic time in nsec + * 0008 34 00 record is 52 bytes long + * 000a 0b 00 text is 11 bytes long + * 000c 1f 00 dictionary is 23 bytes long + * 000e 03 00 LOG_KERN (facility) LOG_ERR (level) + * 0010 69 74 27 73 20 61 20 6c "it's a l" + * 69 6e 65 "ine" + * 001b 44 45 56 49 43 "DEVIC" + * 45 3d 62 38 3a 32 00 44 "E=b8:2\0D" + * 52 49 56 45 52 3d 62 75 "RIVER=bu" + * 67 "g" + * 0032 00 00 00 padding to next message header + * + * The 'struct printk_log' buffer header must never be directly exported to + * userspace, it is a kernel-private implementation detail that might + * need to be changed in the future, when the requirements change. + * + * /dev/kmsg exports the structured data in the following line format: + * "level,sequnum,timestamp;\n" + * + * The optional key/value pairs are attached as continuation lines starting + * with a space character and terminated by a newline. All possible + * non-prinatable characters are escaped in the "\xff" notation. + * + * Users of the export format should ignore possible additional values + * separated by ',', and find the message after the ';' character. + */ + +enum log_flags { + LOG_NOCONS = 1, /* already flushed, do not print to console */ + LOG_NEWLINE = 2, /* text ended with a newline */ + LOG_PREFIX = 4, /* text started with a prefix */ + LOG_CONT = 8, /* text is a fragment of a continuation line */ +}; + +struct printk_log { + u64 ts_nsec; /* timestamp in nanoseconds */ + u16 len; /* length of entire record */ + u16 text_len; /* length of text buffer */ + u16 dict_len; /* length of dictionary buffer */ + u8 facility; /* syslog facility */ + u8 flags:5; /* internal record flags */ + u8 level:3; /* syslog level */ +}; + +/* + * The logbuf_lock protects kmsg buffer, indices, counters. This can be taken + * within the scheduler's rq lock. It must be released before calling + * console_unlock() or anything else that might wake up a process. + */ +static DEFINE_RAW_SPINLOCK(logbuf_lock); + +#ifdef CONFIG_PRINTK +DECLARE_WAIT_QUEUE_HEAD(log_wait); +/* the next printk record to read by syslog(READ) or /proc/kmsg */ +static u64 syslog_seq; +static u32 syslog_idx; +static enum log_flags syslog_prev; +static size_t syslog_partial; + +/* index and sequence number of the first record stored in the buffer */ +static u64 log_first_seq; +static u32 log_first_idx; + +/* index and sequence number of the next record to store in the buffer */ +static u64 log_next_seq; +static u32 log_next_idx; + +/* the next printk record to write to the console */ +static u64 console_seq; +static u32 console_idx; +static enum log_flags console_prev; + +/* the next printk record to read after the last 'clear' command */ +static u64 clear_seq; +static u32 clear_idx; + +#define PREFIX_MAX 32 +#define LOG_LINE_MAX (1024 - PREFIX_MAX) + +/* record buffer */ +#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) +#define LOG_ALIGN 4 +#else +#define LOG_ALIGN __alignof__(struct printk_log) +#endif +#define __LOG_BUF_LEN (1 << CONFIG_LOG_BUF_SHIFT) +static char __log_buf[__LOG_BUF_LEN] __aligned(LOG_ALIGN); +static char *log_buf = __log_buf; +static u32 log_buf_len = __LOG_BUF_LEN; + +/* Return log buffer address */ +char *log_buf_addr_get(void) +{ + return log_buf; +} + +/* Return log buffer size */ +u32 log_buf_len_get(void) +{ + return log_buf_len; +} + +/* human readable text of the record */ +static char *log_text(const struct printk_log *msg) +{ + return (char *)msg + sizeof(struct printk_log); +} + +/* optional key/value pair dictionary attached to the record */ +static char *log_dict(const struct printk_log *msg) +{ + return (char *)msg + sizeof(struct printk_log) + msg->text_len; +} + +/* get record by index; idx must point to valid msg */ +static struct printk_log *log_from_idx(u32 idx) +{ + struct printk_log *msg = (struct printk_log *)(log_buf + idx); + + /* + * A length == 0 record is the end of buffer marker. Wrap around and + * read the message at the start of the buffer. + */ + if (!msg->len) + return (struct printk_log *)log_buf; + return msg; +} + +/* get next record; idx must point to valid msg */ +static u32 log_next(u32 idx) +{ + struct printk_log *msg = (struct printk_log *)(log_buf + idx); + + /* length == 0 indicates the end of the buffer; wrap */ + /* + * A length == 0 record is the end of buffer marker. Wrap around and + * read the message at the start of the buffer as *this* one, and + * return the one after that. + */ + if (!msg->len) { + msg = (struct printk_log *)log_buf; + return msg->len; + } + return idx + msg->len; +} + +/* + * Check whether there is enough free space for the given message. + * + * The same values of first_idx and next_idx mean that the buffer + * is either empty or full. + * + * If the buffer is empty, we must respect the position of the indexes. + * They cannot be reset to the beginning of the buffer. + */ +static int logbuf_has_space(u32 msg_size, bool empty) +{ + u32 free; + + if (log_next_idx > log_first_idx || empty) + free = max(log_buf_len - log_next_idx, log_first_idx); + else + free = log_first_idx - log_next_idx; + + /* + * We need space also for an empty header that signalizes wrapping + * of the buffer. + */ + return free >= msg_size + sizeof(struct printk_log); +} + +static int log_make_free_space(u32 msg_size) +{ + while (log_first_seq < log_next_seq) { + if (logbuf_has_space(msg_size, false)) + return 0; + /* drop old messages until we have enough contiguous space */ + log_first_idx = log_next(log_first_idx); + log_first_seq++; + } + + /* sequence numbers are equal, so the log buffer is empty */ + if (logbuf_has_space(msg_size, true)) + return 0; + + return -ENOMEM; +} + +/* compute the message size including the padding bytes */ +static u32 msg_used_size(u16 text_len, u16 dict_len, u32 *pad_len) +{ + u32 size; + + size = sizeof(struct printk_log) + text_len + dict_len; + *pad_len = (-size) & (LOG_ALIGN - 1); + size += *pad_len; + + return size; +} + +/* + * Define how much of the log buffer we could take at maximum. The value + * must be greater than two. Note that only half of the buffer is available + * when the index points to the middle. + */ +#define MAX_LOG_TAKE_PART 4 +static const char trunc_msg[] = ""; + +static u32 truncate_msg(u16 *text_len, u16 *trunc_msg_len, + u16 *dict_len, u32 *pad_len) +{ + /* + * The message should not take the whole buffer. Otherwise, it might + * get removed too soon. + */ + u32 max_text_len = log_buf_len / MAX_LOG_TAKE_PART; + if (*text_len > max_text_len) + *text_len = max_text_len; + /* enable the warning message */ + *trunc_msg_len = strlen(trunc_msg); + /* disable the "dict" completely */ + *dict_len = 0; + /* compute the size again, count also the warning message */ + return msg_used_size(*text_len + *trunc_msg_len, 0, pad_len); +} + +/* insert record into the buffer, discard old ones, update heads */ +static int log_store(int facility, int level, + enum log_flags flags, u64 ts_nsec, + const char *dict, u16 dict_len, + const char *text, u16 text_len) +{ + struct printk_log *msg; + u32 size, pad_len; + u16 trunc_msg_len = 0; + + /* number of '\0' padding bytes to next message */ + size = msg_used_size(text_len, dict_len, &pad_len); + + if (log_make_free_space(size)) { + /* truncate the message if it is too long for empty buffer */ + size = truncate_msg(&text_len, &trunc_msg_len, + &dict_len, &pad_len); + /* survive when the log buffer is too small for trunc_msg */ + if (log_make_free_space(size)) + return 0; + } + + if (log_next_idx + size + sizeof(struct printk_log) > log_buf_len) { + /* + * This message + an additional empty header does not fit + * at the end of the buffer. Add an empty header with len == 0 + * to signify a wrap around. + */ + memset(log_buf + log_next_idx, 0, sizeof(struct printk_log)); + log_next_idx = 0; + } + + /* fill message */ + msg = (struct printk_log *)(log_buf + log_next_idx); + memcpy(log_text(msg), text, text_len); + msg->text_len = text_len; + if (trunc_msg_len) { + memcpy(log_text(msg) + text_len, trunc_msg, trunc_msg_len); + msg->text_len += trunc_msg_len; + } + memcpy(log_dict(msg), dict, dict_len); + msg->dict_len = dict_len; + msg->facility = facility; + msg->level = level & 7; + msg->flags = flags & 0x1f; + if (ts_nsec > 0) + msg->ts_nsec = ts_nsec; + else + msg->ts_nsec = local_clock(); + memset(log_dict(msg) + dict_len, 0, pad_len); + msg->len = size; + + /* insert message */ + log_next_idx += msg->len; + log_next_seq++; + + return msg->text_len; +} + +int dmesg_restrict = IS_ENABLED(CONFIG_SECURITY_DMESG_RESTRICT); + +static int syslog_action_restricted(int type) +{ + if (dmesg_restrict) + return 1; + /* + * Unless restricted, we allow "read all" and "get buffer size" + * for everybody. + */ + return type != SYSLOG_ACTION_READ_ALL && + type != SYSLOG_ACTION_SIZE_BUFFER; +} + +int check_syslog_permissions(int type, bool from_file) +{ + /* + * If this is from /proc/kmsg and we've already opened it, then we've + * already done the capabilities checks at open time. + */ + if (from_file && type != SYSLOG_ACTION_OPEN) + return 0; + + if (syslog_action_restricted(type)) { + if (capable(CAP_SYSLOG)) + return 0; + /* + * For historical reasons, accept CAP_SYS_ADMIN too, with + * a warning. + */ + if (capable(CAP_SYS_ADMIN)) { + pr_warn_once("%s (%d): Attempt to access syslog with " + "CAP_SYS_ADMIN but no CAP_SYSLOG " + "(deprecated).\n", + current->comm, task_pid_nr(current)); + return 0; + } + return -EPERM; + } + return security_syslog(type); +} + + +/* /dev/kmsg - userspace message inject/listen interface */ +struct devkmsg_user { + u64 seq; + u32 idx; + enum log_flags prev; + struct mutex lock; + char buf[8192]; +}; + +static ssize_t devkmsg_write(struct kiocb *iocb, struct iov_iter *from) +{ + char *buf, *line; + int i; + int level = default_message_loglevel; + int facility = 1; /* LOG_USER */ + size_t len = iov_iter_count(from); + ssize_t ret = len; + + if (len > LOG_LINE_MAX) + return -EINVAL; + buf = kmalloc(len+1, GFP_KERNEL); + if (buf == NULL) + return -ENOMEM; + + buf[len] = '\0'; + if (copy_from_iter(buf, len, from) != len) { + kfree(buf); + return -EFAULT; + } + + /* + * Extract and skip the syslog prefix <[0-9]*>. Coming from userspace + * the decimal value represents 32bit, the lower 3 bit are the log + * level, the rest are the log facility. + * + * If no prefix or no userspace facility is specified, we + * enforce LOG_USER, to be able to reliably distinguish + * kernel-generated messages from userspace-injected ones. + */ + line = buf; + if (line[0] == '<') { + char *endp = NULL; + + i = simple_strtoul(line+1, &endp, 10); + if (endp && endp[0] == '>') { + level = i & 7; + if (i >> 3) + facility = i >> 3; + endp++; + len -= endp - line; + line = endp; + } + } + + printk_emit(facility, level, NULL, 0, "%s", line); + kfree(buf); + return ret; +} + +static ssize_t devkmsg_read(struct file *file, char __user *buf, + size_t count, loff_t *ppos) +{ + struct devkmsg_user *user = file->private_data; + struct printk_log *msg; + u64 ts_usec; + size_t i; + char cont = '-'; + size_t len; + ssize_t ret; + + if (!user) + return -EBADF; + + ret = mutex_lock_interruptible(&user->lock); + if (ret) + return ret; + raw_spin_lock_irq(&logbuf_lock); + while (user->seq == log_next_seq) { + if (file->f_flags & O_NONBLOCK) { + ret = -EAGAIN; + raw_spin_unlock_irq(&logbuf_lock); + goto out; + } + + raw_spin_unlock_irq(&logbuf_lock); + ret = wait_event_interruptible(log_wait, + user->seq != log_next_seq); + if (ret) + goto out; + raw_spin_lock_irq(&logbuf_lock); + } + + if (user->seq < log_first_seq) { + /* our last seen message is gone, return error and reset */ + user->idx = log_first_idx; + user->seq = log_first_seq; + ret = -EPIPE; + raw_spin_unlock_irq(&logbuf_lock); + goto out; + } + + msg = log_from_idx(user->idx); + ts_usec = msg->ts_nsec; + do_div(ts_usec, 1000); + + /* + * If we couldn't merge continuation line fragments during the print, + * export the stored flags to allow an optional external merge of the + * records. Merging the records isn't always neccessarily correct, like + * when we hit a race during printing. In most cases though, it produces + * better readable output. 'c' in the record flags mark the first + * fragment of a line, '+' the following. + */ + if (msg->flags & LOG_CONT && !(user->prev & LOG_CONT)) + cont = 'c'; + else if ((msg->flags & LOG_CONT) || + ((user->prev & LOG_CONT) && !(msg->flags & LOG_PREFIX))) + cont = '+'; + + len = sprintf(user->buf, "%u,%llu,%llu,%c;", + (msg->facility << 3) | msg->level, + user->seq, ts_usec, cont); + user->prev = msg->flags; + + /* escape non-printable characters */ + for (i = 0; i < msg->text_len; i++) { + unsigned char c = log_text(msg)[i]; + + if (c < ' ' || c >= 127 || c == '\\') + len += sprintf(user->buf + len, "\\x%02x", c); + else + user->buf[len++] = c; + } + user->buf[len++] = '\n'; + + if (msg->dict_len) { + bool line = true; + + for (i = 0; i < msg->dict_len; i++) { + unsigned char c = log_dict(msg)[i]; + + if (line) { + user->buf[len++] = ' '; + line = false; + } + + if (c == '\0') { + user->buf[len++] = '\n'; + line = true; + continue; + } + + if (c < ' ' || c >= 127 || c == '\\') { + len += sprintf(user->buf + len, "\\x%02x", c); + continue; + } + + user->buf[len++] = c; + } + user->buf[len++] = '\n'; + } + + user->idx = log_next(user->idx); + user->seq++; + raw_spin_unlock_irq(&logbuf_lock); + + if (len > count) { + ret = -EINVAL; + goto out; + } + + if (copy_to_user(buf, user->buf, len)) { + ret = -EFAULT; + goto out; + } + ret = len; +out: + mutex_unlock(&user->lock); + return ret; +} + +static loff_t devkmsg_llseek(struct file *file, loff_t offset, int whence) +{ + struct devkmsg_user *user = file->private_data; + loff_t ret = 0; + + if (!user) + return -EBADF; + if (offset) + return -ESPIPE; + + raw_spin_lock_irq(&logbuf_lock); + switch (whence) { + case SEEK_SET: + /* the first record */ + user->idx = log_first_idx; + user->seq = log_first_seq; + break; + case SEEK_DATA: + /* + * The first record after the last SYSLOG_ACTION_CLEAR, + * like issued by 'dmesg -c'. Reading /dev/kmsg itself + * changes no global state, and does not clear anything. + */ + user->idx = clear_idx; + user->seq = clear_seq; + break; + case SEEK_END: + /* after the last record */ + user->idx = log_next_idx; + user->seq = log_next_seq; + break; + default: + ret = -EINVAL; + } + raw_spin_unlock_irq(&logbuf_lock); + return ret; +} + +static unsigned int devkmsg_poll(struct file *file, poll_table *wait) +{ + struct devkmsg_user *user = file->private_data; + int ret = 0; + + if (!user) + return POLLERR|POLLNVAL; + + poll_wait(file, &log_wait, wait); + + raw_spin_lock_irq(&logbuf_lock); + if (user->seq < log_next_seq) { + /* return error when data has vanished underneath us */ + if (user->seq < log_first_seq) + ret = POLLIN|POLLRDNORM|POLLERR|POLLPRI; + else + ret = POLLIN|POLLRDNORM; + } + raw_spin_unlock_irq(&logbuf_lock); + + return ret; +} + +static int devkmsg_open(struct inode *inode, struct file *file) +{ + struct devkmsg_user *user; + int err; + + /* write-only does not need any file context */ + if ((file->f_flags & O_ACCMODE) == O_WRONLY) + return 0; + + err = check_syslog_permissions(SYSLOG_ACTION_READ_ALL, + SYSLOG_FROM_READER); + if (err) + return err; + + user = kmalloc(sizeof(struct devkmsg_user), GFP_KERNEL); + if (!user) + return -ENOMEM; + + mutex_init(&user->lock); + + raw_spin_lock_irq(&logbuf_lock); + user->idx = log_first_idx; + user->seq = log_first_seq; + raw_spin_unlock_irq(&logbuf_lock); + + file->private_data = user; + return 0; +} + +static int devkmsg_release(struct inode *inode, struct file *file) +{ + struct devkmsg_user *user = file->private_data; + + if (!user) + return 0; + + mutex_destroy(&user->lock); + kfree(user); + return 0; +} + +const struct file_operations kmsg_fops = { + .open = devkmsg_open, + .read = devkmsg_read, + .write_iter = devkmsg_write, + .llseek = devkmsg_llseek, + .poll = devkmsg_poll, + .release = devkmsg_release, +}; + +#ifdef CONFIG_KEXEC +/* + * This appends the listed symbols to /proc/vmcore + * + * /proc/vmcore is used by various utilities, like crash and makedumpfile to + * obtain access to symbols that are otherwise very difficult to locate. These + * symbols are specifically used so that utilities can access and extract the + * dmesg log from a vmcore file after a crash. + */ +void log_buf_kexec_setup(void) +{ + VMCOREINFO_SYMBOL(log_buf); + VMCOREINFO_SYMBOL(log_buf_len); + VMCOREINFO_SYMBOL(log_first_idx); + VMCOREINFO_SYMBOL(log_next_idx); + /* + * Export struct printk_log size and field offsets. User space tools can + * parse it and detect any changes to structure down the line. + */ + VMCOREINFO_STRUCT_SIZE(printk_log); + VMCOREINFO_OFFSET(printk_log, ts_nsec); + VMCOREINFO_OFFSET(printk_log, len); + VMCOREINFO_OFFSET(printk_log, text_len); + VMCOREINFO_OFFSET(printk_log, dict_len); +} +#endif + +/* requested log_buf_len from kernel cmdline */ +static unsigned long __initdata new_log_buf_len; + +/* we practice scaling the ring buffer by powers of 2 */ +static void __init log_buf_len_update(unsigned size) +{ + if (size) + size = roundup_pow_of_two(size); + if (size > log_buf_len) + new_log_buf_len = size; +} + +/* save requested log_buf_len since it's too early to process it */ +static int __init log_buf_len_setup(char *str) +{ + unsigned size = memparse(str, &str); + + log_buf_len_update(size); + + return 0; +} +early_param("log_buf_len", log_buf_len_setup); + +#ifdef CONFIG_SMP +#define __LOG_CPU_MAX_BUF_LEN (1 << CONFIG_LOG_CPU_MAX_BUF_SHIFT) + +static void __init log_buf_add_cpu(void) +{ + unsigned int cpu_extra; + + /* + * archs should set up cpu_possible_bits properly with + * set_cpu_possible() after setup_arch() but just in + * case lets ensure this is valid. + */ + if (num_possible_cpus() == 1) + return; + + cpu_extra = (num_possible_cpus() - 1) * __LOG_CPU_MAX_BUF_LEN; + + /* by default this will only continue through for large > 64 CPUs */ + if (cpu_extra <= __LOG_BUF_LEN / 2) + return; + + pr_info("log_buf_len individual max cpu contribution: %d bytes\n", + __LOG_CPU_MAX_BUF_LEN); + pr_info("log_buf_len total cpu_extra contributions: %d bytes\n", + cpu_extra); + pr_info("log_buf_len min size: %d bytes\n", __LOG_BUF_LEN); + + log_buf_len_update(cpu_extra + __LOG_BUF_LEN); +} +#else /* !CONFIG_SMP */ +static inline void log_buf_add_cpu(void) {} +#endif /* CONFIG_SMP */ + +void __init setup_log_buf(int early) +{ + unsigned long flags; + char *new_log_buf; + int free; + + if (log_buf != __log_buf) + return; + + if (!early && !new_log_buf_len) + log_buf_add_cpu(); + + if (!new_log_buf_len) + return; + + if (early) { + new_log_buf = + memblock_virt_alloc(new_log_buf_len, LOG_ALIGN); + } else { + new_log_buf = memblock_virt_alloc_nopanic(new_log_buf_len, + LOG_ALIGN); + } + + if (unlikely(!new_log_buf)) { + pr_err("log_buf_len: %ld bytes not available\n", + new_log_buf_len); + return; + } + + raw_spin_lock_irqsave(&logbuf_lock, flags); + log_buf_len = new_log_buf_len; + log_buf = new_log_buf; + new_log_buf_len = 0; + free = __LOG_BUF_LEN - log_next_idx; + memcpy(log_buf, __log_buf, __LOG_BUF_LEN); + raw_spin_unlock_irqrestore(&logbuf_lock, flags); + + pr_info("log_buf_len: %d bytes\n", log_buf_len); + pr_info("early log buf free: %d(%d%%)\n", + free, (free * 100) / __LOG_BUF_LEN); +} + +static bool __read_mostly ignore_loglevel; + +static int __init ignore_loglevel_setup(char *str) +{ + ignore_loglevel = true; + pr_info("debug: ignoring loglevel setting.\n"); + + return 0; +} + +early_param("ignore_loglevel", ignore_loglevel_setup); +module_param(ignore_loglevel, bool, S_IRUGO | S_IWUSR); +MODULE_PARM_DESC(ignore_loglevel, + "ignore loglevel setting (prints all kernel messages to the console)"); + +#ifdef CONFIG_BOOT_PRINTK_DELAY + +static int boot_delay; /* msecs delay after each printk during bootup */ +static unsigned long long loops_per_msec; /* based on boot_delay */ + +static int __init boot_delay_setup(char *str) +{ + unsigned long lpj; + + lpj = preset_lpj ? preset_lpj : 1000000; /* some guess */ + loops_per_msec = (unsigned long long)lpj / 1000 * HZ; + + get_option(&str, &boot_delay); + if (boot_delay > 10 * 1000) + boot_delay = 0; + + pr_debug("boot_delay: %u, preset_lpj: %ld, lpj: %lu, " + "HZ: %d, loops_per_msec: %llu\n", + boot_delay, preset_lpj, lpj, HZ, loops_per_msec); + return 0; +} +early_param("boot_delay", boot_delay_setup); + +static void boot_delay_msec(int level) +{ + unsigned long long k; + unsigned long timeout; + + if ((boot_delay == 0 || system_state != SYSTEM_BOOTING) + || (level >= console_loglevel && !ignore_loglevel)) { + return; + } + + k = (unsigned long long)loops_per_msec * boot_delay; + + timeout = jiffies + msecs_to_jiffies(boot_delay); + while (k) { + k--; + cpu_relax(); + /* + * use (volatile) jiffies to prevent + * compiler reduction; loop termination via jiffies + * is secondary and may or may not happen. + */ + if (time_after(jiffies, timeout)) + break; + touch_nmi_watchdog(); + } +} +#else +static inline void boot_delay_msec(int level) +{ +} +#endif + +static bool printk_time = IS_ENABLED(CONFIG_PRINTK_TIME); +module_param_named(time, printk_time, bool, S_IRUGO | S_IWUSR); + +static size_t print_time(u64 ts, char *buf) +{ + unsigned long rem_nsec; + + if (!printk_time) + return 0; + + rem_nsec = do_div(ts, 1000000000); + + if (!buf) + return snprintf(NULL, 0, "[%5lu.000000] ", (unsigned long)ts); + + return sprintf(buf, "[%5lu.%06lu] ", + (unsigned long)ts, rem_nsec / 1000); +} + +static size_t print_prefix(const struct printk_log *msg, bool syslog, char *buf) +{ + size_t len = 0; + unsigned int prefix = (msg->facility << 3) | msg->level; + + if (syslog) { + if (buf) { + len += sprintf(buf, "<%u>", prefix); + } else { + len += 3; + if (prefix > 999) + len += 3; + else if (prefix > 99) + len += 2; + else if (prefix > 9) + len++; + } + } + + len += print_time(msg->ts_nsec, buf ? buf + len : NULL); + return len; +} + +static size_t msg_print_text(const struct printk_log *msg, enum log_flags prev, + bool syslog, char *buf, size_t size) +{ + const char *text = log_text(msg); + size_t text_size = msg->text_len; + bool prefix = true; + bool newline = true; + size_t len = 0; + + if ((prev & LOG_CONT) && !(msg->flags & LOG_PREFIX)) + prefix = false; + + if (msg->flags & LOG_CONT) { + if ((prev & LOG_CONT) && !(prev & LOG_NEWLINE)) + prefix = false; + + if (!(msg->flags & LOG_NEWLINE)) + newline = false; + } + + do { + const char *next = memchr(text, '\n', text_size); + size_t text_len; + + if (next) { + text_len = next - text; + next++; + text_size -= next - text; + } else { + text_len = text_size; + } + + if (buf) { + if (print_prefix(msg, syslog, NULL) + + text_len + 1 >= size - len) + break; + + if (prefix) + len += print_prefix(msg, syslog, buf + len); + memcpy(buf + len, text, text_len); + len += text_len; + if (next || newline) + buf[len++] = '\n'; + } else { + /* SYSLOG_ACTION_* buffer size only calculation */ + if (prefix) + len += print_prefix(msg, syslog, NULL); + len += text_len; + if (next || newline) + len++; + } + + prefix = true; + text = next; + } while (text); + + return len; +} + +static int syslog_print(char __user *buf, int size) +{ + char *text; + struct printk_log *msg; + int len = 0; + + text = kmalloc(LOG_LINE_MAX + PREFIX_MAX, GFP_KERNEL); + if (!text) + return -ENOMEM; + + while (size > 0) { + size_t n; + size_t skip; + + raw_spin_lock_irq(&logbuf_lock); + if (syslog_seq < log_first_seq) { + /* messages are gone, move to first one */ + syslog_seq = log_first_seq; + syslog_idx = log_first_idx; + syslog_prev = 0; + syslog_partial = 0; + } + if (syslog_seq == log_next_seq) { + raw_spin_unlock_irq(&logbuf_lock); + break; + } + + skip = syslog_partial; + msg = log_from_idx(syslog_idx); + n = msg_print_text(msg, syslog_prev, true, text, + LOG_LINE_MAX + PREFIX_MAX); + if (n - syslog_partial <= size) { + /* message fits into buffer, move forward */ + syslog_idx = log_next(syslog_idx); + syslog_seq++; + syslog_prev = msg->flags; + n -= syslog_partial; + syslog_partial = 0; + } else if (!len){ + /* partial read(), remember position */ + n = size; + syslog_partial += n; + } else + n = 0; + raw_spin_unlock_irq(&logbuf_lock); + + if (!n) + break; + + if (copy_to_user(buf, text + skip, n)) { + if (!len) + len = -EFAULT; + break; + } + + len += n; + size -= n; + buf += n; + } + + kfree(text); + return len; +} + +static int syslog_print_all(char __user *buf, int size, bool clear) +{ + char *text; + int len = 0; + int attempts = 0; + + text = kmalloc(LOG_LINE_MAX + PREFIX_MAX, GFP_KERNEL); + if (!text) + return -ENOMEM; + + raw_spin_lock_irq(&logbuf_lock); + if (buf) { + u64 next_seq; + u64 seq; + u32 idx; + enum log_flags prev; + int num_msg; +try_again: + attempts++; + if (attempts > 10) { + len = -EBUSY; + goto out; + } + num_msg = 0; + if (clear_seq < log_first_seq) { + /* messages are gone, move to first available one */ + clear_seq = log_first_seq; + clear_idx = log_first_idx; + } + + /* + * Find first record that fits, including all following records, + * into the user-provided buffer for this dump. + */ + seq = clear_seq; + idx = clear_idx; + prev = 0; + while (seq < log_next_seq) { + struct printk_log *msg = log_from_idx(idx); + + len += msg_print_text(msg, prev, true, NULL, 0); + prev = msg->flags; + idx = log_next(idx); + seq++; + num_msg++; + if (num_msg > 5) { + num_msg = 0; + raw_spin_unlock_irq(&logbuf_lock); + raw_spin_lock_irq(&logbuf_lock); + if (clear_seq < log_first_seq) + goto try_again; + } + } + + /* move first record forward until length fits into the buffer */ + seq = clear_seq; + idx = clear_idx; + prev = 0; + while (len > size && seq < log_next_seq) { + struct printk_log *msg = log_from_idx(idx); + + len -= msg_print_text(msg, prev, true, NULL, 0); + prev = msg->flags; + idx = log_next(idx); + seq++; + num_msg++; + if (num_msg > 5) { + num_msg = 0; + raw_spin_unlock_irq(&logbuf_lock); + raw_spin_lock_irq(&logbuf_lock); + if (clear_seq < log_first_seq) + goto try_again; + } + } + + /* last message fitting into this dump */ + next_seq = log_next_seq; + + len = 0; + while (len >= 0 && seq < next_seq) { + struct printk_log *msg = log_from_idx(idx); + int textlen; + + textlen = msg_print_text(msg, prev, true, text, + LOG_LINE_MAX + PREFIX_MAX); + if (textlen < 0) { + len = textlen; + break; + } + idx = log_next(idx); + seq++; + prev = msg->flags; + + raw_spin_unlock_irq(&logbuf_lock); + if (copy_to_user(buf + len, text, textlen)) + len = -EFAULT; + else + len += textlen; + raw_spin_lock_irq(&logbuf_lock); + + if (seq < log_first_seq) { + /* messages are gone, move to next one */ + seq = log_first_seq; + idx = log_first_idx; + prev = 0; + } + } + } + + if (clear) { + clear_seq = log_next_seq; + clear_idx = log_next_idx; + } +out: + raw_spin_unlock_irq(&logbuf_lock); + + kfree(text); + return len; +} + +int do_syslog(int type, char __user *buf, int len, bool from_file) +{ + bool clear = false; + static int saved_console_loglevel = LOGLEVEL_DEFAULT; + int error; + + error = check_syslog_permissions(type, from_file); + if (error) + goto out; + + error = security_syslog(type); + if (error) + return error; + + switch (type) { + case SYSLOG_ACTION_CLOSE: /* Close log */ + break; + case SYSLOG_ACTION_OPEN: /* Open log */ + break; + case SYSLOG_ACTION_READ: /* Read from log */ + error = -EINVAL; + if (!buf || len < 0) + goto out; + error = 0; + if (!len) + goto out; + if (!access_ok(VERIFY_WRITE, buf, len)) { + error = -EFAULT; + goto out; + } + error = wait_event_interruptible(log_wait, + syslog_seq != log_next_seq); + if (error) + goto out; + error = syslog_print(buf, len); + break; + /* Read/clear last kernel messages */ + case SYSLOG_ACTION_READ_CLEAR: + clear = true; + /* FALL THRU */ + /* Read last kernel messages */ + case SYSLOG_ACTION_READ_ALL: + error = -EINVAL; + if (!buf || len < 0) + goto out; + error = 0; + if (!len) + goto out; + if (!access_ok(VERIFY_WRITE, buf, len)) { + error = -EFAULT; + goto out; + } + error = syslog_print_all(buf, len, clear); + break; + /* Clear ring buffer */ + case SYSLOG_ACTION_CLEAR: + syslog_print_all(NULL, 0, true); + break; + /* Disable logging to console */ + case SYSLOG_ACTION_CONSOLE_OFF: + if (saved_console_loglevel == LOGLEVEL_DEFAULT) + saved_console_loglevel = console_loglevel; + console_loglevel = minimum_console_loglevel; + break; + /* Enable logging to console */ + case SYSLOG_ACTION_CONSOLE_ON: + if (saved_console_loglevel != LOGLEVEL_DEFAULT) { + console_loglevel = saved_console_loglevel; + saved_console_loglevel = LOGLEVEL_DEFAULT; + } + break; + /* Set level of messages printed to console */ + case SYSLOG_ACTION_CONSOLE_LEVEL: + error = -EINVAL; + if (len < 1 || len > 8) + goto out; + if (len < minimum_console_loglevel) + len = minimum_console_loglevel; + console_loglevel = len; + /* Implicitly re-enable logging to console */ + saved_console_loglevel = LOGLEVEL_DEFAULT; + error = 0; + break; + /* Number of chars in the log buffer */ + case SYSLOG_ACTION_SIZE_UNREAD: + raw_spin_lock_irq(&logbuf_lock); + if (syslog_seq < log_first_seq) { + /* messages are gone, move to first one */ + syslog_seq = log_first_seq; + syslog_idx = log_first_idx; + syslog_prev = 0; + syslog_partial = 0; + } + if (from_file) { + /* + * Short-cut for poll(/"proc/kmsg") which simply checks + * for pending data, not the size; return the count of + * records, not the length. + */ + error = log_next_seq - syslog_seq; + } else { + u64 seq = syslog_seq; + u32 idx = syslog_idx; + enum log_flags prev = syslog_prev; + + error = 0; + while (seq < log_next_seq) { + struct printk_log *msg = log_from_idx(idx); + + error += msg_print_text(msg, prev, true, NULL, 0); + idx = log_next(idx); + seq++; + prev = msg->flags; + } + error -= syslog_partial; + } + raw_spin_unlock_irq(&logbuf_lock); + break; + /* Size of the log buffer */ + case SYSLOG_ACTION_SIZE_BUFFER: + error = log_buf_len; + break; + default: + error = -EINVAL; + break; + } +out: + return error; +} + +SYSCALL_DEFINE3(syslog, int, type, char __user *, buf, int, len) +{ + return do_syslog(type, buf, len, SYSLOG_FROM_READER); +} + +/* + * Call the console drivers, asking them to write out + * log_buf[start] to log_buf[end - 1]. + * The console_lock must be held. + */ +static void call_console_drivers(int level, const char *text, size_t len) +{ + struct console *con; + + trace_console(text, len); + + if (level >= console_loglevel && !ignore_loglevel) + return; + if (!console_drivers) + return; + + migrate_disable(); + for_each_console(con) { + if (exclusive_console && con != exclusive_console) + continue; + if (!(con->flags & CON_ENABLED)) + continue; + if (!con->write) + continue; + if (!cpu_online(smp_processor_id()) && + !(con->flags & CON_ANYTIME)) + continue; + con->write(con, text, len); + } + migrate_enable(); +} + +/* + * Zap console related locks when oopsing. + * To leave time for slow consoles to print a full oops, + * only zap at most once every 30 seconds. + */ +static void zap_locks(void) +{ + static unsigned long oops_timestamp; + + if (time_after_eq(jiffies, oops_timestamp) && + !time_after(jiffies, oops_timestamp + 30 * HZ)) + return; + + oops_timestamp = jiffies; + + debug_locks_off(); + /* If a crash is occurring, make sure we can't deadlock */ + raw_spin_lock_init(&logbuf_lock); + /* And make sure that we print immediately */ + sema_init(&console_sem, 1); +} + +/* + * Check if we have any console that is capable of printing while cpu is + * booting or shutting down. Requires console_sem. + */ +static int have_callable_console(void) +{ + struct console *con; + + for_each_console(con) + if (con->flags & CON_ANYTIME) + return 1; + + return 0; +} + +/* + * Can we actually use the console at this time on this cpu? + * + * Console drivers may assume that per-cpu resources have been allocated. So + * unless they're explicitly marked as being able to cope (CON_ANYTIME) don't + * call them until this CPU is officially up. + */ +static inline int can_use_console(unsigned int cpu) +{ + return cpu_online(cpu) || have_callable_console(); +} + +/* + * Try to get console ownership to actually show the kernel + * messages from a 'printk'. Return true (and with the + * console_lock held, and 'console_locked' set) if it + * is successful, false otherwise. + */ +static int console_trylock_for_printk(void) +{ + unsigned int cpu = smp_processor_id(); +#ifdef CONFIG_PREEMPT_RT_FULL + int lock = !early_boot_irqs_disabled && (preempt_count() == 0) && + !irqs_disabled(); +#else + int lock = 1; +#endif + + if (!lock) + return 0; + + if (!console_trylock()) + return 0; + /* + * If we can't use the console, we need to release the console + * semaphore by hand to avoid flushing the buffer. We need to hold the + * console semaphore in order to do this test safely. + */ + if (!can_use_console(cpu)) { + console_locked = 0; + up_console_sem(); + return 0; + } + return 1; +} + +int printk_delay_msec __read_mostly; + +static inline void printk_delay(void) +{ + if (unlikely(printk_delay_msec)) { + int m = printk_delay_msec; + + while (m--) { + mdelay(1); + touch_nmi_watchdog(); + } + } +} + +/* + * Continuation lines are buffered, and not committed to the record buffer + * until the line is complete, or a race forces it. The line fragments + * though, are printed immediately to the consoles to ensure everything has + * reached the console in case of a kernel crash. + */ +static struct cont { + char buf[LOG_LINE_MAX]; + size_t len; /* length == 0 means unused buffer */ + size_t cons; /* bytes written to console */ + struct task_struct *owner; /* task of first print*/ + u64 ts_nsec; /* time of first print */ + u8 level; /* log level of first message */ + u8 facility; /* log facility of first message */ + enum log_flags flags; /* prefix, newline flags */ + bool flushed:1; /* buffer sealed and committed */ +} cont; + +static void cont_flush(enum log_flags flags) +{ + if (cont.flushed) + return; + if (cont.len == 0) + return; + + if (cont.cons) { + /* + * If a fragment of this line was directly flushed to the + * console; wait for the console to pick up the rest of the + * line. LOG_NOCONS suppresses a duplicated output. + */ + log_store(cont.facility, cont.level, flags | LOG_NOCONS, + cont.ts_nsec, NULL, 0, cont.buf, cont.len); + cont.flags = flags; + cont.flushed = true; + } else { + /* + * If no fragment of this line ever reached the console, + * just submit it to the store and free the buffer. + */ + log_store(cont.facility, cont.level, flags, 0, + NULL, 0, cont.buf, cont.len); + cont.len = 0; + } +} + +static bool cont_add(int facility, int level, const char *text, size_t len) +{ + if (cont.len && cont.flushed) + return false; + + if (cont.len + len > sizeof(cont.buf)) { + /* the line gets too long, split it up in separate records */ + cont_flush(LOG_CONT); + return false; + } + + if (!cont.len) { + cont.facility = facility; + cont.level = level; + cont.owner = current; + cont.ts_nsec = local_clock(); + cont.flags = 0; + cont.cons = 0; + cont.flushed = false; + } + + memcpy(cont.buf + cont.len, text, len); + cont.len += len; + + if (cont.len > (sizeof(cont.buf) * 80) / 100) + cont_flush(LOG_CONT); + + return true; +} + +static size_t cont_print_text(char *text, size_t size) +{ + size_t textlen = 0; + size_t len; + + if (cont.cons == 0 && (console_prev & LOG_NEWLINE)) { + textlen += print_time(cont.ts_nsec, text); + size -= textlen; + } + + len = cont.len - cont.cons; + if (len > 0) { + if (len+1 > size) + len = size-1; + memcpy(text + textlen, cont.buf + cont.cons, len); + textlen += len; + cont.cons = cont.len; + } + + if (cont.flushed) { + if (cont.flags & LOG_NEWLINE) + text[textlen++] = '\n'; + /* got everything, release buffer */ + cont.len = 0; + } + return textlen; +} + +#ifdef CONFIG_EARLY_PRINTK +struct console *early_console; + +static void early_vprintk(const char *fmt, va_list ap) +{ + if (early_console) { + char buf[512]; + int n = vscnprintf(buf, sizeof(buf), fmt, ap); + + early_console->write(early_console, buf, n); + } +} + +asmlinkage void early_printk(const char *fmt, ...) +{ + va_list ap; + + va_start(ap, fmt); + early_vprintk(fmt, ap); + va_end(ap); +} + +/* + * This is independent of any log levels - a global + * kill switch that turns off all of printk. + * + * Used by the NMI watchdog if early-printk is enabled. + */ +static bool __read_mostly printk_killswitch; + +static int __init force_early_printk_setup(char *str) +{ + printk_killswitch = true; + return 0; +} +early_param("force_early_printk", force_early_printk_setup); + +void printk_kill(void) +{ + printk_killswitch = true; +} + +static int forced_early_printk(const char *fmt, va_list ap) +{ + if (!printk_killswitch) + return 0; + early_vprintk(fmt, ap); + return 1; +} +#else +static inline int forced_early_printk(const char *fmt, va_list ap) +{ + return 0; +} +#endif + +asmlinkage int vprintk_emit(int facility, int level, + const char *dict, size_t dictlen, + const char *fmt, va_list args) +{ + static int recursion_bug; + static char textbuf[LOG_LINE_MAX]; + char *text = textbuf; + size_t text_len = 0; + enum log_flags lflags = 0; + unsigned long flags; + int this_cpu; + int printed_len = 0; + bool in_sched = false; + /* cpu currently holding logbuf_lock in this function */ + static unsigned int logbuf_cpu = UINT_MAX; + + /* + * Fall back to early_printk if a debugging subsystem has + * killed printk output + */ + if (unlikely(forced_early_printk(fmt, args))) + return 1; + + if (level == LOGLEVEL_SCHED) { + level = LOGLEVEL_DEFAULT; + in_sched = true; + } + + boot_delay_msec(level); + printk_delay(); + + /* This stops the holder of console_sem just where we want him */ + local_irq_save(flags); + this_cpu = smp_processor_id(); + + /* + * Ouch, printk recursed into itself! + */ + if (unlikely(logbuf_cpu == this_cpu)) { + /* + * If a crash is occurring during printk() on this CPU, + * then try to get the crash message out but make sure + * we can't deadlock. Otherwise just return to avoid the + * recursion and return - but flag the recursion so that + * it can be printed at the next appropriate moment: + */ + if (!oops_in_progress && !lockdep_recursing(current)) { + recursion_bug = 1; + local_irq_restore(flags); + return 0; + } + zap_locks(); + } + + lockdep_off(); + raw_spin_lock(&logbuf_lock); + logbuf_cpu = this_cpu; + + if (unlikely(recursion_bug)) { + static const char recursion_msg[] = + "BUG: recent printk recursion!"; + + recursion_bug = 0; + /* emit KERN_CRIT message */ + printed_len += log_store(0, 2, LOG_PREFIX|LOG_NEWLINE, 0, + NULL, 0, recursion_msg, + strlen(recursion_msg)); + } + + /* + * The printf needs to come first; we need the syslog + * prefix which might be passed-in as a parameter. + */ + text_len = vscnprintf(text, sizeof(textbuf), fmt, args); + + /* mark and strip a trailing newline */ + if (text_len && text[text_len-1] == '\n') { + text_len--; + lflags |= LOG_NEWLINE; + } + + /* strip kernel syslog prefix and extract log level or control flags */ + if (facility == 0) { + int kern_level = printk_get_level(text); + + if (kern_level) { + const char *end_of_header = printk_skip_level(text); + switch (kern_level) { + case '0' ... '7': + if (level == LOGLEVEL_DEFAULT) + level = kern_level - '0'; + /* fallthrough */ + case 'd': /* KERN_DEFAULT */ + lflags |= LOG_PREFIX; + } + /* + * No need to check length here because vscnprintf + * put '\0' at the end of the string. Only valid and + * newly printed level is detected. + */ + text_len -= end_of_header - text; + text = (char *)end_of_header; + } + } + + if (level == LOGLEVEL_DEFAULT) + level = default_message_loglevel; + + if (dict) + lflags |= LOG_PREFIX|LOG_NEWLINE; + + if (!(lflags & LOG_NEWLINE)) { + /* + * Flush the conflicting buffer. An earlier newline was missing, + * or another task also prints continuation lines. + */ + if (cont.len && (lflags & LOG_PREFIX || cont.owner != current)) + cont_flush(LOG_NEWLINE); + + /* buffer line if possible, otherwise store it right away */ + if (cont_add(facility, level, text, text_len)) + printed_len += text_len; + else + printed_len += log_store(facility, level, + lflags | LOG_CONT, 0, + dict, dictlen, text, text_len); + } else { + bool stored = false; + + /* + * If an earlier newline was missing and it was the same task, + * either merge it with the current buffer and flush, or if + * there was a race with interrupts (prefix == true) then just + * flush it out and store this line separately. + * If the preceding printk was from a different task and missed + * a newline, flush and append the newline. + */ + if (cont.len) { + if (cont.owner == current && !(lflags & LOG_PREFIX)) + stored = cont_add(facility, level, text, + text_len); + cont_flush(LOG_NEWLINE); + } + + if (stored) + printed_len += text_len; + else + printed_len += log_store(facility, level, lflags, 0, + dict, dictlen, text, text_len); + } + + logbuf_cpu = UINT_MAX; + raw_spin_unlock(&logbuf_lock); + lockdep_on(); + local_irq_restore(flags); + + /* If called from the scheduler, we can not call up(). */ + if (!in_sched) { + lockdep_off(); + /* + * Disable preemption to avoid being preempted while holding + * console_sem which would prevent anyone from printing to + * console + */ + migrate_disable(); + /* + * Try to acquire and then immediately release the console + * semaphore. The release will print out buffers and wake up + * /dev/kmsg and syslog() users. + */ + if (console_trylock_for_printk()) + console_unlock(); + migrate_enable(); + lockdep_on(); + } + + return printed_len; +} +EXPORT_SYMBOL(vprintk_emit); + +asmlinkage int vprintk(const char *fmt, va_list args) +{ + return vprintk_emit(0, LOGLEVEL_DEFAULT, NULL, 0, fmt, args); +} +EXPORT_SYMBOL(vprintk); + +asmlinkage int printk_emit(int facility, int level, + const char *dict, size_t dictlen, + const char *fmt, ...) +{ + va_list args; + int r; + + va_start(args, fmt); + r = vprintk_emit(facility, level, dict, dictlen, fmt, args); + va_end(args); + + return r; +} +EXPORT_SYMBOL(printk_emit); + +int vprintk_default(const char *fmt, va_list args) +{ + int r; + +#ifdef CONFIG_KGDB_KDB + if (unlikely(kdb_trap_printk)) { + r = vkdb_printf(KDB_MSGSRC_PRINTK, fmt, args); + return r; + } +#endif + r = vprintk_emit(0, LOGLEVEL_DEFAULT, NULL, 0, fmt, args); + + return r; +} +EXPORT_SYMBOL_GPL(vprintk_default); + +/* + * This allows printk to be diverted to another function per cpu. + * This is useful for calling printk functions from within NMI + * without worrying about race conditions that can lock up the + * box. + */ +DEFINE_PER_CPU(printk_func_t, printk_func) = vprintk_default; + +/** + * printk - print a kernel message + * @fmt: format string + * + * This is printk(). It can be called from any context. We want it to work. + * + * We try to grab the console_lock. If we succeed, it's easy - we log the + * output and call the console drivers. If we fail to get the semaphore, we + * place the output into the log buffer and return. The current holder of + * the console_sem will notice the new output in console_unlock(); and will + * send it to the consoles before releasing the lock. + * + * One effect of this deferred printing is that code which calls printk() and + * then changes console_loglevel may break. This is because console_loglevel + * is inspected when the actual printing occurs. + * + * See also: + * printf(3) + * + * See the vsnprintf() documentation for format string extensions over C99. + */ +asmlinkage __visible int printk(const char *fmt, ...) +{ + printk_func_t vprintk_func; + va_list args; + int r; + + va_start(args, fmt); + + /* + * If a caller overrides the per_cpu printk_func, then it needs + * to disable preemption when calling printk(). Otherwise + * the printk_func should be set to the default. No need to + * disable preemption here. + */ + vprintk_func = this_cpu_read(printk_func); + r = vprintk_func(fmt, args); + + va_end(args); + + return r; +} +EXPORT_SYMBOL(printk); + +#else /* CONFIG_PRINTK */ + +#define LOG_LINE_MAX 0 +#define PREFIX_MAX 0 + +static u64 syslog_seq; +static u32 syslog_idx; +static u64 console_seq; +static u32 console_idx; +static enum log_flags syslog_prev; +static u64 log_first_seq; +static u32 log_first_idx; +static u64 log_next_seq; +static enum log_flags console_prev; +static struct cont { + size_t len; + size_t cons; + u8 level; + bool flushed:1; +} cont; +static struct printk_log *log_from_idx(u32 idx) { return NULL; } +static u32 log_next(u32 idx) { return 0; } +static void call_console_drivers(int level, const char *text, size_t len) {} +static size_t msg_print_text(const struct printk_log *msg, enum log_flags prev, + bool syslog, char *buf, size_t size) { return 0; } +static size_t cont_print_text(char *text, size_t size) { return 0; } + +/* Still needs to be defined for users */ +DEFINE_PER_CPU(printk_func_t, printk_func); + +#endif /* CONFIG_PRINTK */ + +static int __add_preferred_console(char *name, int idx, char *options, + char *brl_options) +{ + struct console_cmdline *c; + int i; + + /* + * See if this tty is not yet registered, and + * if we have a slot free. + */ + for (i = 0, c = console_cmdline; + i < MAX_CMDLINECONSOLES && c->name[0]; + i++, c++) { + if (strcmp(c->name, name) == 0 && c->index == idx) { + if (!brl_options) + selected_console = i; + return 0; + } + } + if (i == MAX_CMDLINECONSOLES) + return -E2BIG; + if (!brl_options) + selected_console = i; + strlcpy(c->name, name, sizeof(c->name)); + c->options = options; + braille_set_options(c, brl_options); + + c->index = idx; + return 0; +} +/* + * Set up a console. Called via do_early_param() in init/main.c + * for each "console=" parameter in the boot command line. + */ +static int __init console_setup(char *str) +{ + char buf[sizeof(console_cmdline[0].name) + 4]; /* 4 for "ttyS" */ + char *s, *options, *brl_options = NULL; + int idx; + + if (_braille_console_setup(&str, &brl_options)) + return 1; + + /* + * Decode str into name, index, options. + */ + if (str[0] >= '0' && str[0] <= '9') { + strcpy(buf, "ttyS"); + strncpy(buf + 4, str, sizeof(buf) - 5); + } else { + strncpy(buf, str, sizeof(buf) - 1); + } + buf[sizeof(buf) - 1] = 0; + options = strchr(str, ','); + if (options) + *(options++) = 0; +#ifdef __sparc__ + if (!strcmp(str, "ttya")) + strcpy(buf, "ttyS0"); + if (!strcmp(str, "ttyb")) + strcpy(buf, "ttyS1"); +#endif + for (s = buf; *s; s++) + if (isdigit(*s) || *s == ',') + break; + idx = simple_strtoul(s, NULL, 10); + *s = 0; + + __add_preferred_console(buf, idx, options, brl_options); + console_set_on_cmdline = 1; + return 1; +} +__setup("console=", console_setup); + +/** + * add_preferred_console - add a device to the list of preferred consoles. + * @name: device name + * @idx: device index + * @options: options for this console + * + * The last preferred console added will be used for kernel messages + * and stdin/out/err for init. Normally this is used by console_setup + * above to handle user-supplied console arguments; however it can also + * be used by arch-specific code either to override the user or more + * commonly to provide a default console (ie from PROM variables) when + * the user has not supplied one. + */ +int add_preferred_console(char *name, int idx, char *options) +{ + return __add_preferred_console(name, idx, options, NULL); +} + +bool console_suspend_enabled = true; +EXPORT_SYMBOL(console_suspend_enabled); + +static int __init console_suspend_disable(char *str) +{ + console_suspend_enabled = false; + return 1; +} +__setup("no_console_suspend", console_suspend_disable); +module_param_named(console_suspend, console_suspend_enabled, + bool, S_IRUGO | S_IWUSR); +MODULE_PARM_DESC(console_suspend, "suspend console during suspend" + " and hibernate operations"); + +/** + * suspend_console - suspend the console subsystem + * + * This disables printk() while we go into suspend states + */ +void suspend_console(void) +{ + if (!console_suspend_enabled) + return; + printk("Suspending console(s) (use no_console_suspend to debug)\n"); + console_lock(); + console_suspended = 1; + up_console_sem(); +} + +void resume_console(void) +{ + if (!console_suspend_enabled) + return; + down_console_sem(); + console_suspended = 0; + console_unlock(); +} + +/** + * console_cpu_notify - print deferred console messages after CPU hotplug + * @self: notifier struct + * @action: CPU hotplug event + * @hcpu: unused + * + * If printk() is called from a CPU that is not online yet, the messages + * will be spooled but will not show up on the console. This function is + * called when a new CPU comes online (or fails to come up), and ensures + * that any such output gets printed. + */ +static int console_cpu_notify(struct notifier_block *self, + unsigned long action, void *hcpu) +{ + switch (action) { + case CPU_ONLINE: + case CPU_DEAD: + case CPU_DOWN_FAILED: + case CPU_UP_CANCELED: + console_lock(); + console_unlock(); + } + return NOTIFY_OK; +} + +/** + * console_lock - lock the console system for exclusive use. + * + * Acquires a lock which guarantees that the caller has + * exclusive access to the console system and the console_drivers list. + * + * Can sleep, returns nothing. + */ +void console_lock(void) +{ + might_sleep(); + + down_console_sem(); + if (console_suspended) + return; + console_locked = 1; + console_may_schedule = 1; +} +EXPORT_SYMBOL(console_lock); + +/** + * console_trylock - try to lock the console system for exclusive use. + * + * Try to acquire a lock which guarantees that the caller has exclusive + * access to the console system and the console_drivers list. + * + * returns 1 on success, and 0 on failure to acquire the lock. + */ +int console_trylock(void) +{ + if (down_trylock_console_sem()) + return 0; + if (console_suspended) { + up_console_sem(); + return 0; + } + console_locked = 1; + console_may_schedule = 0; + return 1; +} +EXPORT_SYMBOL(console_trylock); + +int is_console_locked(void) +{ + return console_locked; +} + +static void console_cont_flush(char *text, size_t size) +{ + unsigned long flags; + size_t len; + + raw_spin_lock_irqsave(&logbuf_lock, flags); + + if (!cont.len) + goto out; + + /* + * We still queue earlier records, likely because the console was + * busy. The earlier ones need to be printed before this one, we + * did not flush any fragment so far, so just let it queue up. + */ + if (console_seq < log_next_seq && !cont.cons) + goto out; + + len = cont_print_text(text, size); +#ifndef CONFIG_PREEMPT_RT_FULL + raw_spin_unlock(&logbuf_lock); + stop_critical_timings(); + call_console_drivers(cont.level, text, len); + start_critical_timings(); + local_irq_restore(flags); +#else + raw_spin_unlock_irqrestore(&logbuf_lock, flags); + call_console_drivers(cont.level, text, len); +#endif + return; +out: + raw_spin_unlock_irqrestore(&logbuf_lock, flags); +} + +/** + * console_unlock - unlock the console system + * + * Releases the console_lock which the caller holds on the console system + * and the console driver list. + * + * While the console_lock was held, console output may have been buffered + * by printk(). If this is the case, console_unlock(); emits + * the output prior to releasing the lock. + * + * If there is output waiting, we wake /dev/kmsg and syslog() users. + * + * console_unlock(); may be called from any context. + */ +void console_unlock(void) +{ + static char text[LOG_LINE_MAX + PREFIX_MAX]; + static u64 seen_seq; + unsigned long flags; + bool wake_klogd = false; + bool retry; + + if (console_suspended) { + up_console_sem(); + return; + } + + console_may_schedule = 0; + + /* flush buffered message fragment immediately to console */ + console_cont_flush(text, sizeof(text)); +again: + for (;;) { + struct printk_log *msg; + size_t len; + int level; + + raw_spin_lock_irqsave(&logbuf_lock, flags); + if (seen_seq != log_next_seq) { + wake_klogd = true; + seen_seq = log_next_seq; + } + + if (console_seq < log_first_seq) { + len = sprintf(text, "** %u printk messages dropped ** ", + (unsigned)(log_first_seq - console_seq)); + + /* messages are gone, move to first one */ + console_seq = log_first_seq; + console_idx = log_first_idx; + console_prev = 0; + } else { + len = 0; + } +skip: + if (console_seq == log_next_seq) + break; + + msg = log_from_idx(console_idx); + if (msg->flags & LOG_NOCONS) { + /* + * Skip record we have buffered and already printed + * directly to the console when we received it. + */ + console_idx = log_next(console_idx); + console_seq++; + /* + * We will get here again when we register a new + * CON_PRINTBUFFER console. Clear the flag so we + * will properly dump everything later. + */ + msg->flags &= ~LOG_NOCONS; + console_prev = msg->flags; + goto skip; + } + + level = msg->level; + len += msg_print_text(msg, console_prev, false, + text + len, sizeof(text) - len); + console_idx = log_next(console_idx); + console_seq++; + console_prev = msg->flags; +#ifdef CONFIG_PREEMPT_RT_FULL + raw_spin_unlock_irqrestore(&logbuf_lock, flags); + call_console_drivers(level, text, len); +#else + raw_spin_unlock(&logbuf_lock); + + stop_critical_timings(); /* don't trace print latency */ + call_console_drivers(level, text, len); + start_critical_timings(); + local_irq_restore(flags); +#endif + } + console_locked = 0; + + /* Release the exclusive_console once it is used */ + if (unlikely(exclusive_console)) + exclusive_console = NULL; + + raw_spin_unlock(&logbuf_lock); + + up_console_sem(); + + /* + * Someone could have filled up the buffer again, so re-check if there's + * something to flush. In case we cannot trylock the console_sem again, + * there's a new owner and the console_unlock() from them will do the + * flush, no worries. + */ + raw_spin_lock(&logbuf_lock); + retry = console_seq != log_next_seq; + raw_spin_unlock_irqrestore(&logbuf_lock, flags); + + if (retry && console_trylock()) + goto again; + + if (wake_klogd) + wake_up_klogd(); +} +EXPORT_SYMBOL(console_unlock); + +/** + * console_conditional_schedule - yield the CPU if required + * + * If the console code is currently allowed to sleep, and + * if this CPU should yield the CPU to another task, do + * so here. + * + * Must be called within console_lock();. + */ +void __sched console_conditional_schedule(void) +{ + if (console_may_schedule) + cond_resched(); +} +EXPORT_SYMBOL(console_conditional_schedule); + +void console_unblank(void) +{ + struct console *c; + + /* + * console_unblank can no longer be called in interrupt context unless + * oops_in_progress is set to 1.. + */ + if (oops_in_progress) { + if (down_trylock_console_sem() != 0) + return; + } else + console_lock(); + + console_locked = 1; + console_may_schedule = 0; + for_each_console(c) + if ((c->flags & CON_ENABLED) && c->unblank) + c->unblank(); + console_unlock(); +} + +/* + * Return the console tty driver structure and its associated index + */ +struct tty_driver *console_device(int *index) +{ + struct console *c; + struct tty_driver *driver = NULL; + + console_lock(); + for_each_console(c) { + if (!c->device) + continue; + driver = c->device(c, index); + if (driver) + break; + } + console_unlock(); + return driver; +} + +/* + * Prevent further output on the passed console device so that (for example) + * serial drivers can disable console output before suspending a port, and can + * re-enable output afterwards. + */ +void console_stop(struct console *console) +{ + console_lock(); + console->flags &= ~CON_ENABLED; + console_unlock(); +} +EXPORT_SYMBOL(console_stop); + +void console_start(struct console *console) +{ + console_lock(); + console->flags |= CON_ENABLED; + console_unlock(); +} +EXPORT_SYMBOL(console_start); + +static int __read_mostly keep_bootcon; + +static int __init keep_bootcon_setup(char *str) +{ + keep_bootcon = 1; + pr_info("debug: skip boot console de-registration.\n"); + + return 0; +} + +early_param("keep_bootcon", keep_bootcon_setup); + +/* + * The console driver calls this routine during kernel initialization + * to register the console printing procedure with printk() and to + * print any messages that were printed by the kernel before the + * console driver was initialized. + * + * This can happen pretty early during the boot process (because of + * early_printk) - sometimes before setup_arch() completes - be careful + * of what kernel features are used - they may not be initialised yet. + * + * There are two types of consoles - bootconsoles (early_printk) and + * "real" consoles (everything which is not a bootconsole) which are + * handled differently. + * - Any number of bootconsoles can be registered at any time. + * - As soon as a "real" console is registered, all bootconsoles + * will be unregistered automatically. + * - Once a "real" console is registered, any attempt to register a + * bootconsoles will be rejected + */ +void register_console(struct console *newcon) +{ + int i; + unsigned long flags; + struct console *bcon = NULL; + struct console_cmdline *c; + + if (console_drivers) + for_each_console(bcon) + if (WARN(bcon == newcon, + "console '%s%d' already registered\n", + bcon->name, bcon->index)) + return; + + /* + * before we register a new CON_BOOT console, make sure we don't + * already have a valid console + */ + if (console_drivers && newcon->flags & CON_BOOT) { + /* find the last or real console */ + for_each_console(bcon) { + if (!(bcon->flags & CON_BOOT)) { + pr_info("Too late to register bootconsole %s%d\n", + newcon->name, newcon->index); + return; + } + } + } + + if (console_drivers && console_drivers->flags & CON_BOOT) + bcon = console_drivers; + + if (preferred_console < 0 || bcon || !console_drivers) + preferred_console = selected_console; + + /* + * See if we want to use this console driver. If we + * didn't select a console we take the first one + * that registers here. + */ + if (preferred_console < 0) { + if (newcon->index < 0) + newcon->index = 0; + if (newcon->setup == NULL || + newcon->setup(newcon, NULL) == 0) { + newcon->flags |= CON_ENABLED; + if (newcon->device) { + newcon->flags |= CON_CONSDEV; + preferred_console = 0; + } + } + } + + /* + * See if this console matches one we selected on + * the command line. + */ + for (i = 0, c = console_cmdline; + i < MAX_CMDLINECONSOLES && c->name[0]; + i++, c++) { + if (!newcon->match || + newcon->match(newcon, c->name, c->index, c->options) != 0) { + /* default matching */ + BUILD_BUG_ON(sizeof(c->name) != sizeof(newcon->name)); + if (strcmp(c->name, newcon->name) != 0) + continue; + if (newcon->index >= 0 && + newcon->index != c->index) + continue; + if (newcon->index < 0) + newcon->index = c->index; + + if (_braille_register_console(newcon, c)) + return; + + if (newcon->setup && + newcon->setup(newcon, c->options) != 0) + break; + } + + newcon->flags |= CON_ENABLED; + if (i == selected_console) { + newcon->flags |= CON_CONSDEV; + preferred_console = selected_console; + } + break; + } + + if (!(newcon->flags & CON_ENABLED)) + return; + + /* + * If we have a bootconsole, and are switching to a real console, + * don't print everything out again, since when the boot console, and + * the real console are the same physical device, it's annoying to + * see the beginning boot messages twice + */ + if (bcon && ((newcon->flags & (CON_CONSDEV | CON_BOOT)) == CON_CONSDEV)) + newcon->flags &= ~CON_PRINTBUFFER; + + /* + * Put this console in the list - keep the + * preferred driver at the head of the list. + */ + console_lock(); + if ((newcon->flags & CON_CONSDEV) || console_drivers == NULL) { + newcon->next = console_drivers; + console_drivers = newcon; + if (newcon->next) + newcon->next->flags &= ~CON_CONSDEV; + } else { + newcon->next = console_drivers->next; + console_drivers->next = newcon; + } + if (newcon->flags & CON_PRINTBUFFER) { + /* + * console_unlock(); will print out the buffered messages + * for us. + */ + raw_spin_lock_irqsave(&logbuf_lock, flags); + console_seq = syslog_seq; + console_idx = syslog_idx; + console_prev = syslog_prev; + raw_spin_unlock_irqrestore(&logbuf_lock, flags); + /* + * We're about to replay the log buffer. Only do this to the + * just-registered console to avoid excessive message spam to + * the already-registered consoles. + */ + exclusive_console = newcon; + } + console_unlock(); + console_sysfs_notify(); + + /* + * By unregistering the bootconsoles after we enable the real console + * we get the "console xxx enabled" message on all the consoles - + * boot consoles, real consoles, etc - this is to ensure that end + * users know there might be something in the kernel's log buffer that + * went to the bootconsole (that they do not see on the real console) + */ + pr_info("%sconsole [%s%d] enabled\n", + (newcon->flags & CON_BOOT) ? "boot" : "" , + newcon->name, newcon->index); + if (bcon && + ((newcon->flags & (CON_CONSDEV | CON_BOOT)) == CON_CONSDEV) && + !keep_bootcon) { + /* We need to iterate through all boot consoles, to make + * sure we print everything out, before we unregister them. + */ + for_each_console(bcon) + if (bcon->flags & CON_BOOT) + unregister_console(bcon); + } +} +EXPORT_SYMBOL(register_console); + +int unregister_console(struct console *console) +{ + struct console *a, *b; + int res; + + pr_info("%sconsole [%s%d] disabled\n", + (console->flags & CON_BOOT) ? "boot" : "" , + console->name, console->index); + + res = _braille_unregister_console(console); + if (res) + return res; + + res = 1; + console_lock(); + if (console_drivers == console) { + console_drivers=console->next; + res = 0; + } else if (console_drivers) { + for (a=console_drivers->next, b=console_drivers ; + a; b=a, a=b->next) { + if (a == console) { + b->next = a->next; + res = 0; + break; + } + } + } + + /* + * If this isn't the last console and it has CON_CONSDEV set, we + * need to set it on the next preferred console. + */ + if (console_drivers != NULL && console->flags & CON_CONSDEV) + console_drivers->flags |= CON_CONSDEV; + + console->flags &= ~CON_ENABLED; + console_unlock(); + console_sysfs_notify(); + return res; +} +EXPORT_SYMBOL(unregister_console); + +static int __init printk_late_init(void) +{ + struct console *con; + + for_each_console(con) { + if (!keep_bootcon && con->flags & CON_BOOT) { + unregister_console(con); + } + } + hotcpu_notifier(console_cpu_notify, 0); + return 0; +} +late_initcall(printk_late_init); + +#if defined CONFIG_PRINTK +/* + * Delayed printk version, for scheduler-internal messages: + */ +#define PRINTK_PENDING_WAKEUP 0x01 +#define PRINTK_PENDING_OUTPUT 0x02 + +static DEFINE_PER_CPU(int, printk_pending); + +static void wake_up_klogd_work_func(struct irq_work *irq_work) +{ + int pending = __this_cpu_xchg(printk_pending, 0); + + if (pending & PRINTK_PENDING_OUTPUT) { + /* If trylock fails, someone else is doing the printing */ + if (console_trylock()) + console_unlock(); + } + + if (pending & PRINTK_PENDING_WAKEUP) + wake_up_interruptible(&log_wait); +} + +static DEFINE_PER_CPU(struct irq_work, wake_up_klogd_work) = { + .func = wake_up_klogd_work_func, + .flags = IRQ_WORK_LAZY, +}; + +void wake_up_klogd(void) +{ + preempt_disable(); + if (waitqueue_active(&log_wait)) { + this_cpu_or(printk_pending, PRINTK_PENDING_WAKEUP); + irq_work_queue(this_cpu_ptr(&wake_up_klogd_work)); + } + preempt_enable(); +} + +int printk_deferred(const char *fmt, ...) +{ + va_list args; + int r; + + preempt_disable(); + va_start(args, fmt); + r = vprintk_emit(0, LOGLEVEL_SCHED, NULL, 0, fmt, args); + va_end(args); + + __this_cpu_or(printk_pending, PRINTK_PENDING_OUTPUT); + irq_work_queue(this_cpu_ptr(&wake_up_klogd_work)); + preempt_enable(); + + return r; +} + +/* + * printk rate limiting, lifted from the networking subsystem. + * + * This enforces a rate limit: not more than 10 kernel messages + * every 5s to make a denial-of-service attack impossible. + */ +DEFINE_RATELIMIT_STATE(printk_ratelimit_state, 5 * HZ, 10); + +int __printk_ratelimit(const char *func) +{ + return ___ratelimit(&printk_ratelimit_state, func); +} +EXPORT_SYMBOL(__printk_ratelimit); + +/** + * printk_timed_ratelimit - caller-controlled printk ratelimiting + * @caller_jiffies: pointer to caller's state + * @interval_msecs: minimum interval between prints + * + * printk_timed_ratelimit() returns true if more than @interval_msecs + * milliseconds have elapsed since the last time printk_timed_ratelimit() + * returned true. + */ +bool printk_timed_ratelimit(unsigned long *caller_jiffies, + unsigned int interval_msecs) +{ + unsigned long elapsed = jiffies - *caller_jiffies; + + if (*caller_jiffies && elapsed <= msecs_to_jiffies(interval_msecs)) + return false; + + *caller_jiffies = jiffies; + return true; +} +EXPORT_SYMBOL(printk_timed_ratelimit); + +static DEFINE_SPINLOCK(dump_list_lock); +static LIST_HEAD(dump_list); + +/** + * kmsg_dump_register - register a kernel log dumper. + * @dumper: pointer to the kmsg_dumper structure + * + * Adds a kernel log dumper to the system. The dump callback in the + * structure will be called when the kernel oopses or panics and must be + * set. Returns zero on success and %-EINVAL or %-EBUSY otherwise. + */ +int kmsg_dump_register(struct kmsg_dumper *dumper) +{ + unsigned long flags; + int err = -EBUSY; + + /* The dump callback needs to be set */ + if (!dumper->dump) + return -EINVAL; + + spin_lock_irqsave(&dump_list_lock, flags); + /* Don't allow registering multiple times */ + if (!dumper->registered) { + dumper->registered = 1; + list_add_tail_rcu(&dumper->list, &dump_list); + err = 0; + } + spin_unlock_irqrestore(&dump_list_lock, flags); + + return err; +} +EXPORT_SYMBOL_GPL(kmsg_dump_register); + +/** + * kmsg_dump_unregister - unregister a kmsg dumper. + * @dumper: pointer to the kmsg_dumper structure + * + * Removes a dump device from the system. Returns zero on success and + * %-EINVAL otherwise. + */ +int kmsg_dump_unregister(struct kmsg_dumper *dumper) +{ + unsigned long flags; + int err = -EINVAL; + + spin_lock_irqsave(&dump_list_lock, flags); + if (dumper->registered) { + dumper->registered = 0; + list_del_rcu(&dumper->list); + err = 0; + } + spin_unlock_irqrestore(&dump_list_lock, flags); + synchronize_rcu(); + + return err; +} +EXPORT_SYMBOL_GPL(kmsg_dump_unregister); + +static bool always_kmsg_dump; +module_param_named(always_kmsg_dump, always_kmsg_dump, bool, S_IRUGO | S_IWUSR); + +/** + * kmsg_dump - dump kernel log to kernel message dumpers. + * @reason: the reason (oops, panic etc) for dumping + * + * Call each of the registered dumper's dump() callback, which can + * retrieve the kmsg records with kmsg_dump_get_line() or + * kmsg_dump_get_buffer(). + */ +void kmsg_dump(enum kmsg_dump_reason reason) +{ + struct kmsg_dumper *dumper; + unsigned long flags; + + if ((reason > KMSG_DUMP_OOPS) && !always_kmsg_dump) + return; + + rcu_read_lock(); + list_for_each_entry_rcu(dumper, &dump_list, list) { + if (dumper->max_reason && reason > dumper->max_reason) + continue; + + /* initialize iterator with data about the stored records */ + dumper->active = true; + + raw_spin_lock_irqsave(&logbuf_lock, flags); + dumper->cur_seq = clear_seq; + dumper->cur_idx = clear_idx; + dumper->next_seq = log_next_seq; + dumper->next_idx = log_next_idx; + raw_spin_unlock_irqrestore(&logbuf_lock, flags); + + /* invoke dumper which will iterate over records */ + dumper->dump(dumper, reason); + + /* reset iterator */ + dumper->active = false; + } + rcu_read_unlock(); +} + +/** + * kmsg_dump_get_line_nolock - retrieve one kmsg log line (unlocked version) + * @dumper: registered kmsg dumper + * @syslog: include the "<4>" prefixes + * @line: buffer to copy the line to + * @size: maximum size of the buffer + * @len: length of line placed into buffer + * + * Start at the beginning of the kmsg buffer, with the oldest kmsg + * record, and copy one record into the provided buffer. + * + * Consecutive calls will return the next available record moving + * towards the end of the buffer with the youngest messages. + * + * A return value of FALSE indicates that there are no more records to + * read. + * + * The function is similar to kmsg_dump_get_line(), but grabs no locks. + */ +bool kmsg_dump_get_line_nolock(struct kmsg_dumper *dumper, bool syslog, + char *line, size_t size, size_t *len) +{ + struct printk_log *msg; + size_t l = 0; + bool ret = false; + + if (!dumper->active) + goto out; + + if (dumper->cur_seq < log_first_seq) { + /* messages are gone, move to first available one */ + dumper->cur_seq = log_first_seq; + dumper->cur_idx = log_first_idx; + } + + /* last entry */ + if (dumper->cur_seq >= log_next_seq) + goto out; + + msg = log_from_idx(dumper->cur_idx); + l = msg_print_text(msg, 0, syslog, line, size); + + dumper->cur_idx = log_next(dumper->cur_idx); + dumper->cur_seq++; + ret = true; +out: + if (len) + *len = l; + return ret; +} + +/** + * kmsg_dump_get_line - retrieve one kmsg log line + * @dumper: registered kmsg dumper + * @syslog: include the "<4>" prefixes + * @line: buffer to copy the line to + * @size: maximum size of the buffer + * @len: length of line placed into buffer + * + * Start at the beginning of the kmsg buffer, with the oldest kmsg + * record, and copy one record into the provided buffer. + * + * Consecutive calls will return the next available record moving + * towards the end of the buffer with the youngest messages. + * + * A return value of FALSE indicates that there are no more records to + * read. + */ +bool kmsg_dump_get_line(struct kmsg_dumper *dumper, bool syslog, + char *line, size_t size, size_t *len) +{ + unsigned long flags; + bool ret; + + raw_spin_lock_irqsave(&logbuf_lock, flags); + ret = kmsg_dump_get_line_nolock(dumper, syslog, line, size, len); + raw_spin_unlock_irqrestore(&logbuf_lock, flags); + + return ret; +} +EXPORT_SYMBOL_GPL(kmsg_dump_get_line); + +/** + * kmsg_dump_get_buffer - copy kmsg log lines + * @dumper: registered kmsg dumper + * @syslog: include the "<4>" prefixes + * @buf: buffer to copy the line to + * @size: maximum size of the buffer + * @len: length of line placed into buffer + * + * Start at the end of the kmsg buffer and fill the provided buffer + * with as many of the the *youngest* kmsg records that fit into it. + * If the buffer is large enough, all available kmsg records will be + * copied with a single call. + * + * Consecutive calls will fill the buffer with the next block of + * available older records, not including the earlier retrieved ones. + * + * A return value of FALSE indicates that there are no more records to + * read. + */ +bool kmsg_dump_get_buffer(struct kmsg_dumper *dumper, bool syslog, + char *buf, size_t size, size_t *len) +{ + unsigned long flags; + u64 seq; + u32 idx; + u64 next_seq; + u32 next_idx; + enum log_flags prev; + size_t l = 0; + bool ret = false; + + if (!dumper->active) + goto out; + + raw_spin_lock_irqsave(&logbuf_lock, flags); + if (dumper->cur_seq < log_first_seq) { + /* messages are gone, move to first available one */ + dumper->cur_seq = log_first_seq; + dumper->cur_idx = log_first_idx; + } + + /* last entry */ + if (dumper->cur_seq >= dumper->next_seq) { + raw_spin_unlock_irqrestore(&logbuf_lock, flags); + goto out; + } + + /* calculate length of entire buffer */ + seq = dumper->cur_seq; + idx = dumper->cur_idx; + prev = 0; + while (seq < dumper->next_seq) { + struct printk_log *msg = log_from_idx(idx); + + l += msg_print_text(msg, prev, true, NULL, 0); + idx = log_next(idx); + seq++; + prev = msg->flags; + } + + /* move first record forward until length fits into the buffer */ + seq = dumper->cur_seq; + idx = dumper->cur_idx; + prev = 0; + while (l > size && seq < dumper->next_seq) { + struct printk_log *msg = log_from_idx(idx); + + l -= msg_print_text(msg, prev, true, NULL, 0); + idx = log_next(idx); + seq++; + prev = msg->flags; + } + + /* last message in next interation */ + next_seq = seq; + next_idx = idx; + + l = 0; + while (seq < dumper->next_seq) { + struct printk_log *msg = log_from_idx(idx); + + l += msg_print_text(msg, prev, syslog, buf + l, size - l); + idx = log_next(idx); + seq++; + prev = msg->flags; + } + + dumper->next_seq = next_seq; + dumper->next_idx = next_idx; + ret = true; + raw_spin_unlock_irqrestore(&logbuf_lock, flags); +out: + if (len) + *len = l; + return ret; +} +EXPORT_SYMBOL_GPL(kmsg_dump_get_buffer); + +/** + * kmsg_dump_rewind_nolock - reset the interator (unlocked version) + * @dumper: registered kmsg dumper + * + * Reset the dumper's iterator so that kmsg_dump_get_line() and + * kmsg_dump_get_buffer() can be called again and used multiple + * times within the same dumper.dump() callback. + * + * The function is similar to kmsg_dump_rewind(), but grabs no locks. + */ +void kmsg_dump_rewind_nolock(struct kmsg_dumper *dumper) +{ + dumper->cur_seq = clear_seq; + dumper->cur_idx = clear_idx; + dumper->next_seq = log_next_seq; + dumper->next_idx = log_next_idx; +} + +/** + * kmsg_dump_rewind - reset the interator + * @dumper: registered kmsg dumper + * + * Reset the dumper's iterator so that kmsg_dump_get_line() and + * kmsg_dump_get_buffer() can be called again and used multiple + * times within the same dumper.dump() callback. + */ +void kmsg_dump_rewind(struct kmsg_dumper *dumper) +{ + unsigned long flags; + + raw_spin_lock_irqsave(&logbuf_lock, flags); + kmsg_dump_rewind_nolock(dumper); + raw_spin_unlock_irqrestore(&logbuf_lock, flags); +} +EXPORT_SYMBOL_GPL(kmsg_dump_rewind); + +static char dump_stack_arch_desc_str[128]; + +/** + * dump_stack_set_arch_desc - set arch-specific str to show with task dumps + * @fmt: printf-style format string + * @...: arguments for the format string + * + * The configured string will be printed right after utsname during task + * dumps. Usually used to add arch-specific system identifiers. If an + * arch wants to make use of such an ID string, it should initialize this + * as soon as possible during boot. + */ +void __init dump_stack_set_arch_desc(const char *fmt, ...) +{ + va_list args; + + va_start(args, fmt); + vsnprintf(dump_stack_arch_desc_str, sizeof(dump_stack_arch_desc_str), + fmt, args); + va_end(args); +} + +/** + * dump_stack_print_info - print generic debug info for dump_stack() + * @log_lvl: log level + * + * Arch-specific dump_stack() implementations can use this function to + * print out the same debug information as the generic dump_stack(). + */ +void dump_stack_print_info(const char *log_lvl) +{ + printk("%sCPU: %d PID: %d Comm: %.20s %s %s %.*s\n", + log_lvl, raw_smp_processor_id(), current->pid, current->comm, + print_tainted(), init_utsname()->release, + (int)strcspn(init_utsname()->version, " "), + init_utsname()->version); + + if (dump_stack_arch_desc_str[0] != '\0') + printk("%sHardware name: %s\n", + log_lvl, dump_stack_arch_desc_str); + + print_worker_info(log_lvl, current); +} + +/** + * show_regs_print_info - print generic debug info for show_regs() + * @log_lvl: log level + * + * show_regs() implementations can use this function to print out generic + * debug information. + */ +void show_regs_print_info(const char *log_lvl) +{ + dump_stack_print_info(log_lvl); + + printk("%stask: %p ti: %p task.ti: %p\n", + log_lvl, current, current_thread_info(), + task_thread_info(current)); +} + +#endif diff --git a/kernel/kernel/profile.c b/kernel/kernel/profile.c new file mode 100644 index 000000000..a7bcd28d6 --- /dev/null +++ b/kernel/kernel/profile.c @@ -0,0 +1,613 @@ +/* + * linux/kernel/profile.c + * Simple profiling. Manages a direct-mapped profile hit count buffer, + * with configurable resolution, support for restricting the cpus on + * which profiling is done, and switching between cpu time and + * schedule() calls via kernel command line parameters passed at boot. + * + * Scheduler profiling support, Arjan van de Ven and Ingo Molnar, + * Red Hat, July 2004 + * Consolidation of architecture support code for profiling, + * Nadia Yvette Chambers, Oracle, July 2004 + * Amortized hit count accounting via per-cpu open-addressed hashtables + * to resolve timer interrupt livelocks, Nadia Yvette Chambers, + * Oracle, 2004 + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +struct profile_hit { + u32 pc, hits; +}; +#define PROFILE_GRPSHIFT 3 +#define PROFILE_GRPSZ (1 << PROFILE_GRPSHIFT) +#define NR_PROFILE_HIT (PAGE_SIZE/sizeof(struct profile_hit)) +#define NR_PROFILE_GRP (NR_PROFILE_HIT/PROFILE_GRPSZ) + +static atomic_t *prof_buffer; +static unsigned long prof_len, prof_shift; + +int prof_on __read_mostly; +EXPORT_SYMBOL_GPL(prof_on); + +static cpumask_var_t prof_cpu_mask; +#ifdef CONFIG_SMP +static DEFINE_PER_CPU(struct profile_hit *[2], cpu_profile_hits); +static DEFINE_PER_CPU(int, cpu_profile_flip); +static DEFINE_MUTEX(profile_flip_mutex); +#endif /* CONFIG_SMP */ + +int profile_setup(char *str) +{ + static const char schedstr[] = "schedule"; + static const char sleepstr[] = "sleep"; + static const char kvmstr[] = "kvm"; + int par; + + if (!strncmp(str, sleepstr, strlen(sleepstr))) { +#ifdef CONFIG_SCHEDSTATS + prof_on = SLEEP_PROFILING; + if (str[strlen(sleepstr)] == ',') + str += strlen(sleepstr) + 1; + if (get_option(&str, &par)) + prof_shift = par; + pr_info("kernel sleep profiling enabled (shift: %ld)\n", + prof_shift); +#else + pr_warn("kernel sleep profiling requires CONFIG_SCHEDSTATS\n"); +#endif /* CONFIG_SCHEDSTATS */ + } else if (!strncmp(str, schedstr, strlen(schedstr))) { + prof_on = SCHED_PROFILING; + if (str[strlen(schedstr)] == ',') + str += strlen(schedstr) + 1; + if (get_option(&str, &par)) + prof_shift = par; + pr_info("kernel schedule profiling enabled (shift: %ld)\n", + prof_shift); + } else if (!strncmp(str, kvmstr, strlen(kvmstr))) { + prof_on = KVM_PROFILING; + if (str[strlen(kvmstr)] == ',') + str += strlen(kvmstr) + 1; + if (get_option(&str, &par)) + prof_shift = par; + pr_info("kernel KVM profiling enabled (shift: %ld)\n", + prof_shift); + } else if (get_option(&str, &par)) { + prof_shift = par; + prof_on = CPU_PROFILING; + pr_info("kernel profiling enabled (shift: %ld)\n", + prof_shift); + } + return 1; +} +__setup("profile=", profile_setup); + + +int __ref profile_init(void) +{ + int buffer_bytes; + if (!prof_on) + return 0; + + /* only text is profiled */ + prof_len = (_etext - _stext) >> prof_shift; + buffer_bytes = prof_len*sizeof(atomic_t); + + if (!alloc_cpumask_var(&prof_cpu_mask, GFP_KERNEL)) + return -ENOMEM; + + cpumask_copy(prof_cpu_mask, cpu_possible_mask); + + prof_buffer = kzalloc(buffer_bytes, GFP_KERNEL|__GFP_NOWARN); + if (prof_buffer) + return 0; + + prof_buffer = alloc_pages_exact(buffer_bytes, + GFP_KERNEL|__GFP_ZERO|__GFP_NOWARN); + if (prof_buffer) + return 0; + + prof_buffer = vzalloc(buffer_bytes); + if (prof_buffer) + return 0; + + free_cpumask_var(prof_cpu_mask); + return -ENOMEM; +} + +/* Profile event notifications */ + +static BLOCKING_NOTIFIER_HEAD(task_exit_notifier); +static ATOMIC_NOTIFIER_HEAD(task_free_notifier); +static BLOCKING_NOTIFIER_HEAD(munmap_notifier); + +void profile_task_exit(struct task_struct *task) +{ + blocking_notifier_call_chain(&task_exit_notifier, 0, task); +} + +int profile_handoff_task(struct task_struct *task) +{ + int ret; + ret = atomic_notifier_call_chain(&task_free_notifier, 0, task); + return (ret == NOTIFY_OK) ? 1 : 0; +} + +void profile_munmap(unsigned long addr) +{ + blocking_notifier_call_chain(&munmap_notifier, 0, (void *)addr); +} + +int task_handoff_register(struct notifier_block *n) +{ + return atomic_notifier_chain_register(&task_free_notifier, n); +} +EXPORT_SYMBOL_GPL(task_handoff_register); + +int task_handoff_unregister(struct notifier_block *n) +{ + return atomic_notifier_chain_unregister(&task_free_notifier, n); +} +EXPORT_SYMBOL_GPL(task_handoff_unregister); + +int profile_event_register(enum profile_type type, struct notifier_block *n) +{ + int err = -EINVAL; + + switch (type) { + case PROFILE_TASK_EXIT: + err = blocking_notifier_chain_register( + &task_exit_notifier, n); + break; + case PROFILE_MUNMAP: + err = blocking_notifier_chain_register( + &munmap_notifier, n); + break; + } + + return err; +} +EXPORT_SYMBOL_GPL(profile_event_register); + +int profile_event_unregister(enum profile_type type, struct notifier_block *n) +{ + int err = -EINVAL; + + switch (type) { + case PROFILE_TASK_EXIT: + err = blocking_notifier_chain_unregister( + &task_exit_notifier, n); + break; + case PROFILE_MUNMAP: + err = blocking_notifier_chain_unregister( + &munmap_notifier, n); + break; + } + + return err; +} +EXPORT_SYMBOL_GPL(profile_event_unregister); + +#ifdef CONFIG_SMP +/* + * Each cpu has a pair of open-addressed hashtables for pending + * profile hits. read_profile() IPI's all cpus to request them + * to flip buffers and flushes their contents to prof_buffer itself. + * Flip requests are serialized by the profile_flip_mutex. The sole + * use of having a second hashtable is for avoiding cacheline + * contention that would otherwise happen during flushes of pending + * profile hits required for the accuracy of reported profile hits + * and so resurrect the interrupt livelock issue. + * + * The open-addressed hashtables are indexed by profile buffer slot + * and hold the number of pending hits to that profile buffer slot on + * a cpu in an entry. When the hashtable overflows, all pending hits + * are accounted to their corresponding profile buffer slots with + * atomic_add() and the hashtable emptied. As numerous pending hits + * may be accounted to a profile buffer slot in a hashtable entry, + * this amortizes a number of atomic profile buffer increments likely + * to be far larger than the number of entries in the hashtable, + * particularly given that the number of distinct profile buffer + * positions to which hits are accounted during short intervals (e.g. + * several seconds) is usually very small. Exclusion from buffer + * flipping is provided by interrupt disablement (note that for + * SCHED_PROFILING or SLEEP_PROFILING profile_hit() may be called from + * process context). + * The hash function is meant to be lightweight as opposed to strong, + * and was vaguely inspired by ppc64 firmware-supported inverted + * pagetable hash functions, but uses a full hashtable full of finite + * collision chains, not just pairs of them. + * + * -- nyc + */ +static void __profile_flip_buffers(void *unused) +{ + int cpu = smp_processor_id(); + + per_cpu(cpu_profile_flip, cpu) = !per_cpu(cpu_profile_flip, cpu); +} + +static void profile_flip_buffers(void) +{ + int i, j, cpu; + + mutex_lock(&profile_flip_mutex); + j = per_cpu(cpu_profile_flip, get_cpu()); + put_cpu(); + on_each_cpu(__profile_flip_buffers, NULL, 1); + for_each_online_cpu(cpu) { + struct profile_hit *hits = per_cpu(cpu_profile_hits, cpu)[j]; + for (i = 0; i < NR_PROFILE_HIT; ++i) { + if (!hits[i].hits) { + if (hits[i].pc) + hits[i].pc = 0; + continue; + } + atomic_add(hits[i].hits, &prof_buffer[hits[i].pc]); + hits[i].hits = hits[i].pc = 0; + } + } + mutex_unlock(&profile_flip_mutex); +} + +static void profile_discard_flip_buffers(void) +{ + int i, cpu; + + mutex_lock(&profile_flip_mutex); + i = per_cpu(cpu_profile_flip, get_cpu()); + put_cpu(); + on_each_cpu(__profile_flip_buffers, NULL, 1); + for_each_online_cpu(cpu) { + struct profile_hit *hits = per_cpu(cpu_profile_hits, cpu)[i]; + memset(hits, 0, NR_PROFILE_HIT*sizeof(struct profile_hit)); + } + mutex_unlock(&profile_flip_mutex); +} + +static void do_profile_hits(int type, void *__pc, unsigned int nr_hits) +{ + unsigned long primary, secondary, flags, pc = (unsigned long)__pc; + int i, j, cpu; + struct profile_hit *hits; + + pc = min((pc - (unsigned long)_stext) >> prof_shift, prof_len - 1); + i = primary = (pc & (NR_PROFILE_GRP - 1)) << PROFILE_GRPSHIFT; + secondary = (~(pc << 1) & (NR_PROFILE_GRP - 1)) << PROFILE_GRPSHIFT; + cpu = get_cpu(); + hits = per_cpu(cpu_profile_hits, cpu)[per_cpu(cpu_profile_flip, cpu)]; + if (!hits) { + put_cpu(); + return; + } + /* + * We buffer the global profiler buffer into a per-CPU + * queue and thus reduce the number of global (and possibly + * NUMA-alien) accesses. The write-queue is self-coalescing: + */ + local_irq_save(flags); + do { + for (j = 0; j < PROFILE_GRPSZ; ++j) { + if (hits[i + j].pc == pc) { + hits[i + j].hits += nr_hits; + goto out; + } else if (!hits[i + j].hits) { + hits[i + j].pc = pc; + hits[i + j].hits = nr_hits; + goto out; + } + } + i = (i + secondary) & (NR_PROFILE_HIT - 1); + } while (i != primary); + + /* + * Add the current hit(s) and flush the write-queue out + * to the global buffer: + */ + atomic_add(nr_hits, &prof_buffer[pc]); + for (i = 0; i < NR_PROFILE_HIT; ++i) { + atomic_add(hits[i].hits, &prof_buffer[hits[i].pc]); + hits[i].pc = hits[i].hits = 0; + } +out: + local_irq_restore(flags); + put_cpu(); +} + +static int profile_cpu_callback(struct notifier_block *info, + unsigned long action, void *__cpu) +{ + int node, cpu = (unsigned long)__cpu; + struct page *page; + + switch (action) { + case CPU_UP_PREPARE: + case CPU_UP_PREPARE_FROZEN: + node = cpu_to_mem(cpu); + per_cpu(cpu_profile_flip, cpu) = 0; + if (!per_cpu(cpu_profile_hits, cpu)[1]) { + page = alloc_pages_exact_node(node, + GFP_KERNEL | __GFP_ZERO, + 0); + if (!page) + return notifier_from_errno(-ENOMEM); + per_cpu(cpu_profile_hits, cpu)[1] = page_address(page); + } + if (!per_cpu(cpu_profile_hits, cpu)[0]) { + page = alloc_pages_exact_node(node, + GFP_KERNEL | __GFP_ZERO, + 0); + if (!page) + goto out_free; + per_cpu(cpu_profile_hits, cpu)[0] = page_address(page); + } + break; +out_free: + page = virt_to_page(per_cpu(cpu_profile_hits, cpu)[1]); + per_cpu(cpu_profile_hits, cpu)[1] = NULL; + __free_page(page); + return notifier_from_errno(-ENOMEM); + case CPU_ONLINE: + case CPU_ONLINE_FROZEN: + if (prof_cpu_mask != NULL) + cpumask_set_cpu(cpu, prof_cpu_mask); + break; + case CPU_UP_CANCELED: + case CPU_UP_CANCELED_FROZEN: + case CPU_DEAD: + case CPU_DEAD_FROZEN: + if (prof_cpu_mask != NULL) + cpumask_clear_cpu(cpu, prof_cpu_mask); + if (per_cpu(cpu_profile_hits, cpu)[0]) { + page = virt_to_page(per_cpu(cpu_profile_hits, cpu)[0]); + per_cpu(cpu_profile_hits, cpu)[0] = NULL; + __free_page(page); + } + if (per_cpu(cpu_profile_hits, cpu)[1]) { + page = virt_to_page(per_cpu(cpu_profile_hits, cpu)[1]); + per_cpu(cpu_profile_hits, cpu)[1] = NULL; + __free_page(page); + } + break; + } + return NOTIFY_OK; +} +#else /* !CONFIG_SMP */ +#define profile_flip_buffers() do { } while (0) +#define profile_discard_flip_buffers() do { } while (0) +#define profile_cpu_callback NULL + +static void do_profile_hits(int type, void *__pc, unsigned int nr_hits) +{ + unsigned long pc; + pc = ((unsigned long)__pc - (unsigned long)_stext) >> prof_shift; + atomic_add(nr_hits, &prof_buffer[min(pc, prof_len - 1)]); +} +#endif /* !CONFIG_SMP */ + +void profile_hits(int type, void *__pc, unsigned int nr_hits) +{ + if (prof_on != type || !prof_buffer) + return; + do_profile_hits(type, __pc, nr_hits); +} +EXPORT_SYMBOL_GPL(profile_hits); + +void profile_tick(int type) +{ + struct pt_regs *regs = get_irq_regs(); + + if (!user_mode(regs) && prof_cpu_mask != NULL && + cpumask_test_cpu(smp_processor_id(), prof_cpu_mask)) + profile_hit(type, (void *)profile_pc(regs)); +} + +#ifdef CONFIG_PROC_FS +#include +#include +#include + +static int prof_cpu_mask_proc_show(struct seq_file *m, void *v) +{ + seq_printf(m, "%*pb\n", cpumask_pr_args(prof_cpu_mask)); + return 0; +} + +static int prof_cpu_mask_proc_open(struct inode *inode, struct file *file) +{ + return single_open(file, prof_cpu_mask_proc_show, NULL); +} + +static ssize_t prof_cpu_mask_proc_write(struct file *file, + const char __user *buffer, size_t count, loff_t *pos) +{ + cpumask_var_t new_value; + int err; + + if (!alloc_cpumask_var(&new_value, GFP_KERNEL)) + return -ENOMEM; + + err = cpumask_parse_user(buffer, count, new_value); + if (!err) { + cpumask_copy(prof_cpu_mask, new_value); + err = count; + } + free_cpumask_var(new_value); + return err; +} + +static const struct file_operations prof_cpu_mask_proc_fops = { + .open = prof_cpu_mask_proc_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, + .write = prof_cpu_mask_proc_write, +}; + +void create_prof_cpu_mask(void) +{ + /* create /proc/irq/prof_cpu_mask */ + proc_create("irq/prof_cpu_mask", 0600, NULL, &prof_cpu_mask_proc_fops); +} + +/* + * This function accesses profiling information. The returned data is + * binary: the sampling step and the actual contents of the profile + * buffer. Use of the program readprofile is recommended in order to + * get meaningful info out of these data. + */ +static ssize_t +read_profile(struct file *file, char __user *buf, size_t count, loff_t *ppos) +{ + unsigned long p = *ppos; + ssize_t read; + char *pnt; + unsigned int sample_step = 1 << prof_shift; + + profile_flip_buffers(); + if (p >= (prof_len+1)*sizeof(unsigned int)) + return 0; + if (count > (prof_len+1)*sizeof(unsigned int) - p) + count = (prof_len+1)*sizeof(unsigned int) - p; + read = 0; + + while (p < sizeof(unsigned int) && count > 0) { + if (put_user(*((char *)(&sample_step)+p), buf)) + return -EFAULT; + buf++; p++; count--; read++; + } + pnt = (char *)prof_buffer + p - sizeof(atomic_t); + if (copy_to_user(buf, (void *)pnt, count)) + return -EFAULT; + read += count; + *ppos += read; + return read; +} + +/* + * Writing to /proc/profile resets the counters + * + * Writing a 'profiling multiplier' value into it also re-sets the profiling + * interrupt frequency, on architectures that support this. + */ +static ssize_t write_profile(struct file *file, const char __user *buf, + size_t count, loff_t *ppos) +{ +#ifdef CONFIG_SMP + extern int setup_profiling_timer(unsigned int multiplier); + + if (count == sizeof(int)) { + unsigned int multiplier; + + if (copy_from_user(&multiplier, buf, sizeof(int))) + return -EFAULT; + + if (setup_profiling_timer(multiplier)) + return -EINVAL; + } +#endif + profile_discard_flip_buffers(); + memset(prof_buffer, 0, prof_len * sizeof(atomic_t)); + return count; +} + +static const struct file_operations proc_profile_operations = { + .read = read_profile, + .write = write_profile, + .llseek = default_llseek, +}; + +#ifdef CONFIG_SMP +static void profile_nop(void *unused) +{ +} + +static int create_hash_tables(void) +{ + int cpu; + + for_each_online_cpu(cpu) { + int node = cpu_to_mem(cpu); + struct page *page; + + page = alloc_pages_exact_node(node, + GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE, + 0); + if (!page) + goto out_cleanup; + per_cpu(cpu_profile_hits, cpu)[1] + = (struct profile_hit *)page_address(page); + page = alloc_pages_exact_node(node, + GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE, + 0); + if (!page) + goto out_cleanup; + per_cpu(cpu_profile_hits, cpu)[0] + = (struct profile_hit *)page_address(page); + } + return 0; +out_cleanup: + prof_on = 0; + smp_mb(); + on_each_cpu(profile_nop, NULL, 1); + for_each_online_cpu(cpu) { + struct page *page; + + if (per_cpu(cpu_profile_hits, cpu)[0]) { + page = virt_to_page(per_cpu(cpu_profile_hits, cpu)[0]); + per_cpu(cpu_profile_hits, cpu)[0] = NULL; + __free_page(page); + } + if (per_cpu(cpu_profile_hits, cpu)[1]) { + page = virt_to_page(per_cpu(cpu_profile_hits, cpu)[1]); + per_cpu(cpu_profile_hits, cpu)[1] = NULL; + __free_page(page); + } + } + return -1; +} +#else +#define create_hash_tables() ({ 0; }) +#endif + +int __ref create_proc_profile(void) /* false positive from hotcpu_notifier */ +{ + struct proc_dir_entry *entry; + int err = 0; + + if (!prof_on) + return 0; + + cpu_notifier_register_begin(); + + if (create_hash_tables()) { + err = -ENOMEM; + goto out; + } + + entry = proc_create("profile", S_IWUSR | S_IRUGO, + NULL, &proc_profile_operations); + if (!entry) + goto out; + proc_set_size(entry, (1 + prof_len) * sizeof(atomic_t)); + __hotcpu_notifier(profile_cpu_callback, 0); + +out: + cpu_notifier_register_done(); + return err; +} +subsys_initcall(create_proc_profile); +#endif /* CONFIG_PROC_FS */ diff --git a/kernel/kernel/ptrace.c b/kernel/kernel/ptrace.c new file mode 100644 index 000000000..b8d001b89 --- /dev/null +++ b/kernel/kernel/ptrace.c @@ -0,0 +1,1224 @@ +/* + * linux/kernel/ptrace.c + * + * (C) Copyright 1999 Linus Torvalds + * + * Common interfaces for "ptrace()" which we do not want + * to continually duplicate across every architecture. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + +/* + * ptrace a task: make the debugger its new parent and + * move it to the ptrace list. + * + * Must be called with the tasklist lock write-held. + */ +void __ptrace_link(struct task_struct *child, struct task_struct *new_parent) +{ + BUG_ON(!list_empty(&child->ptrace_entry)); + list_add(&child->ptrace_entry, &new_parent->ptraced); + child->parent = new_parent; +} + +/** + * __ptrace_unlink - unlink ptracee and restore its execution state + * @child: ptracee to be unlinked + * + * Remove @child from the ptrace list, move it back to the original parent, + * and restore the execution state so that it conforms to the group stop + * state. + * + * Unlinking can happen via two paths - explicit PTRACE_DETACH or ptracer + * exiting. For PTRACE_DETACH, unless the ptracee has been killed between + * ptrace_check_attach() and here, it's guaranteed to be in TASK_TRACED. + * If the ptracer is exiting, the ptracee can be in any state. + * + * After detach, the ptracee should be in a state which conforms to the + * group stop. If the group is stopped or in the process of stopping, the + * ptracee should be put into TASK_STOPPED; otherwise, it should be woken + * up from TASK_TRACED. + * + * If the ptracee is in TASK_TRACED and needs to be moved to TASK_STOPPED, + * it goes through TRACED -> RUNNING -> STOPPED transition which is similar + * to but in the opposite direction of what happens while attaching to a + * stopped task. However, in this direction, the intermediate RUNNING + * state is not hidden even from the current ptracer and if it immediately + * re-attaches and performs a WNOHANG wait(2), it may fail. + * + * CONTEXT: + * write_lock_irq(tasklist_lock) + */ +void __ptrace_unlink(struct task_struct *child) +{ + BUG_ON(!child->ptrace); + + child->ptrace = 0; + child->parent = child->real_parent; + list_del_init(&child->ptrace_entry); + + spin_lock(&child->sighand->siglock); + + /* + * Clear all pending traps and TRAPPING. TRAPPING should be + * cleared regardless of JOBCTL_STOP_PENDING. Do it explicitly. + */ + task_clear_jobctl_pending(child, JOBCTL_TRAP_MASK); + task_clear_jobctl_trapping(child); + + /* + * Reinstate JOBCTL_STOP_PENDING if group stop is in effect and + * @child isn't dead. + */ + if (!(child->flags & PF_EXITING) && + (child->signal->flags & SIGNAL_STOP_STOPPED || + child->signal->group_stop_count)) { + child->jobctl |= JOBCTL_STOP_PENDING; + + /* + * This is only possible if this thread was cloned by the + * traced task running in the stopped group, set the signal + * for the future reports. + * FIXME: we should change ptrace_init_task() to handle this + * case. + */ + if (!(child->jobctl & JOBCTL_STOP_SIGMASK)) + child->jobctl |= SIGSTOP; + } + + /* + * If transition to TASK_STOPPED is pending or in TASK_TRACED, kick + * @child in the butt. Note that @resume should be used iff @child + * is in TASK_TRACED; otherwise, we might unduly disrupt + * TASK_KILLABLE sleeps. + */ + if (child->jobctl & JOBCTL_STOP_PENDING || task_is_traced(child)) + ptrace_signal_wake_up(child, true); + + spin_unlock(&child->sighand->siglock); +} + +/* Ensure that nothing can wake it up, even SIGKILL */ +static bool ptrace_freeze_traced(struct task_struct *task) +{ + bool ret = false; + + /* Lockless, nobody but us can set this flag */ + if (task->jobctl & JOBCTL_LISTENING) + return ret; + + spin_lock_irq(&task->sighand->siglock); + if (task_is_traced(task) && !__fatal_signal_pending(task)) { + raw_spin_lock_irq(&task->pi_lock); + if (task->state & __TASK_TRACED) + task->state = __TASK_TRACED; + else + task->saved_state = __TASK_TRACED; + raw_spin_unlock_irq(&task->pi_lock); + ret = true; + } + spin_unlock_irq(&task->sighand->siglock); + + return ret; +} + +static void ptrace_unfreeze_traced(struct task_struct *task) +{ + if (task->state != __TASK_TRACED) + return; + + WARN_ON(!task->ptrace || task->parent != current); + + spin_lock_irq(&task->sighand->siglock); + if (__fatal_signal_pending(task)) + wake_up_state(task, __TASK_TRACED); + else + task->state = TASK_TRACED; + spin_unlock_irq(&task->sighand->siglock); +} + +/** + * ptrace_check_attach - check whether ptracee is ready for ptrace operation + * @child: ptracee to check for + * @ignore_state: don't check whether @child is currently %TASK_TRACED + * + * Check whether @child is being ptraced by %current and ready for further + * ptrace operations. If @ignore_state is %false, @child also should be in + * %TASK_TRACED state and on return the child is guaranteed to be traced + * and not executing. If @ignore_state is %true, @child can be in any + * state. + * + * CONTEXT: + * Grabs and releases tasklist_lock and @child->sighand->siglock. + * + * RETURNS: + * 0 on success, -ESRCH if %child is not ready. + */ +static int ptrace_check_attach(struct task_struct *child, bool ignore_state) +{ + int ret = -ESRCH; + + /* + * We take the read lock around doing both checks to close a + * possible race where someone else was tracing our child and + * detached between these two checks. After this locked check, + * we are sure that this is our traced child and that can only + * be changed by us so it's not changing right after this. + */ + read_lock(&tasklist_lock); + if (child->ptrace && child->parent == current) { + WARN_ON(child->state == __TASK_TRACED); + /* + * child->sighand can't be NULL, release_task() + * does ptrace_unlink() before __exit_signal(). + */ + if (ignore_state || ptrace_freeze_traced(child)) + ret = 0; + } + read_unlock(&tasklist_lock); + + if (!ret && !ignore_state) { + if (!wait_task_inactive(child, __TASK_TRACED)) { + /* + * This can only happen if may_ptrace_stop() fails and + * ptrace_stop() changes ->state back to TASK_RUNNING, + * so we should not worry about leaking __TASK_TRACED. + */ + WARN_ON(child->state == __TASK_TRACED); + ret = -ESRCH; + } + } + + return ret; +} + +static int ptrace_has_cap(struct user_namespace *ns, unsigned int mode) +{ + if (mode & PTRACE_MODE_NOAUDIT) + return has_ns_capability_noaudit(current, ns, CAP_SYS_PTRACE); + else + return has_ns_capability(current, ns, CAP_SYS_PTRACE); +} + +/* Returns 0 on success, -errno on denial. */ +static int __ptrace_may_access(struct task_struct *task, unsigned int mode) +{ + const struct cred *cred = current_cred(), *tcred; + + /* May we inspect the given task? + * This check is used both for attaching with ptrace + * and for allowing access to sensitive information in /proc. + * + * ptrace_attach denies several cases that /proc allows + * because setting up the necessary parent/child relationship + * or halting the specified task is impossible. + */ + int dumpable = 0; + /* Don't let security modules deny introspection */ + if (same_thread_group(task, current)) + return 0; + rcu_read_lock(); + tcred = __task_cred(task); + if (uid_eq(cred->uid, tcred->euid) && + uid_eq(cred->uid, tcred->suid) && + uid_eq(cred->uid, tcred->uid) && + gid_eq(cred->gid, tcred->egid) && + gid_eq(cred->gid, tcred->sgid) && + gid_eq(cred->gid, tcred->gid)) + goto ok; + if (ptrace_has_cap(tcred->user_ns, mode)) + goto ok; + rcu_read_unlock(); + return -EPERM; +ok: + rcu_read_unlock(); + smp_rmb(); + if (task->mm) + dumpable = get_dumpable(task->mm); + rcu_read_lock(); + if (dumpable != SUID_DUMP_USER && + !ptrace_has_cap(__task_cred(task)->user_ns, mode)) { + rcu_read_unlock(); + return -EPERM; + } + rcu_read_unlock(); + + return security_ptrace_access_check(task, mode); +} + +bool ptrace_may_access(struct task_struct *task, unsigned int mode) +{ + int err; + task_lock(task); + err = __ptrace_may_access(task, mode); + task_unlock(task); + return !err; +} + +static int ptrace_attach(struct task_struct *task, long request, + unsigned long addr, + unsigned long flags) +{ + bool seize = (request == PTRACE_SEIZE); + int retval; + + retval = -EIO; + if (seize) { + if (addr != 0) + goto out; + if (flags & ~(unsigned long)PTRACE_O_MASK) + goto out; + flags = PT_PTRACED | PT_SEIZED | (flags << PT_OPT_FLAG_SHIFT); + } else { + flags = PT_PTRACED; + } + + audit_ptrace(task); + + retval = -EPERM; + if (unlikely(task->flags & PF_KTHREAD)) + goto out; + if (same_thread_group(task, current)) + goto out; + + /* + * Protect exec's credential calculations against our interference; + * SUID, SGID and LSM creds get determined differently + * under ptrace. + */ + retval = -ERESTARTNOINTR; + if (mutex_lock_interruptible(&task->signal->cred_guard_mutex)) + goto out; + + task_lock(task); + retval = __ptrace_may_access(task, PTRACE_MODE_ATTACH); + task_unlock(task); + if (retval) + goto unlock_creds; + + write_lock_irq(&tasklist_lock); + retval = -EPERM; + if (unlikely(task->exit_state)) + goto unlock_tasklist; + if (task->ptrace) + goto unlock_tasklist; + + if (seize) + flags |= PT_SEIZED; + rcu_read_lock(); + if (ns_capable(__task_cred(task)->user_ns, CAP_SYS_PTRACE)) + flags |= PT_PTRACE_CAP; + rcu_read_unlock(); + task->ptrace = flags; + + __ptrace_link(task, current); + + /* SEIZE doesn't trap tracee on attach */ + if (!seize) + send_sig_info(SIGSTOP, SEND_SIG_FORCED, task); + + spin_lock(&task->sighand->siglock); + + /* + * If the task is already STOPPED, set JOBCTL_TRAP_STOP and + * TRAPPING, and kick it so that it transits to TRACED. TRAPPING + * will be cleared if the child completes the transition or any + * event which clears the group stop states happens. We'll wait + * for the transition to complete before returning from this + * function. + * + * This hides STOPPED -> RUNNING -> TRACED transition from the + * attaching thread but a different thread in the same group can + * still observe the transient RUNNING state. IOW, if another + * thread's WNOHANG wait(2) on the stopped tracee races against + * ATTACH, the wait(2) may fail due to the transient RUNNING. + * + * The following task_is_stopped() test is safe as both transitions + * in and out of STOPPED are protected by siglock. + */ + if (task_is_stopped(task) && + task_set_jobctl_pending(task, JOBCTL_TRAP_STOP | JOBCTL_TRAPPING)) + signal_wake_up_state(task, __TASK_STOPPED); + + spin_unlock(&task->sighand->siglock); + + retval = 0; +unlock_tasklist: + write_unlock_irq(&tasklist_lock); +unlock_creds: + mutex_unlock(&task->signal->cred_guard_mutex); +out: + if (!retval) { + wait_on_bit(&task->jobctl, JOBCTL_TRAPPING_BIT, + TASK_UNINTERRUPTIBLE); + proc_ptrace_connector(task, PTRACE_ATTACH); + } + + return retval; +} + +/** + * ptrace_traceme -- helper for PTRACE_TRACEME + * + * Performs checks and sets PT_PTRACED. + * Should be used by all ptrace implementations for PTRACE_TRACEME. + */ +static int ptrace_traceme(void) +{ + int ret = -EPERM; + + write_lock_irq(&tasklist_lock); + /* Are we already being traced? */ + if (!current->ptrace) { + ret = security_ptrace_traceme(current->parent); + /* + * Check PF_EXITING to ensure ->real_parent has not passed + * exit_ptrace(). Otherwise we don't report the error but + * pretend ->real_parent untraces us right after return. + */ + if (!ret && !(current->real_parent->flags & PF_EXITING)) { + current->ptrace = PT_PTRACED; + __ptrace_link(current, current->real_parent); + } + } + write_unlock_irq(&tasklist_lock); + + return ret; +} + +/* + * Called with irqs disabled, returns true if childs should reap themselves. + */ +static int ignoring_children(struct sighand_struct *sigh) +{ + int ret; + spin_lock(&sigh->siglock); + ret = (sigh->action[SIGCHLD-1].sa.sa_handler == SIG_IGN) || + (sigh->action[SIGCHLD-1].sa.sa_flags & SA_NOCLDWAIT); + spin_unlock(&sigh->siglock); + return ret; +} + +/* + * Called with tasklist_lock held for writing. + * Unlink a traced task, and clean it up if it was a traced zombie. + * Return true if it needs to be reaped with release_task(). + * (We can't call release_task() here because we already hold tasklist_lock.) + * + * If it's a zombie, our attachedness prevented normal parent notification + * or self-reaping. Do notification now if it would have happened earlier. + * If it should reap itself, return true. + * + * If it's our own child, there is no notification to do. But if our normal + * children self-reap, then this child was prevented by ptrace and we must + * reap it now, in that case we must also wake up sub-threads sleeping in + * do_wait(). + */ +static bool __ptrace_detach(struct task_struct *tracer, struct task_struct *p) +{ + bool dead; + + __ptrace_unlink(p); + + if (p->exit_state != EXIT_ZOMBIE) + return false; + + dead = !thread_group_leader(p); + + if (!dead && thread_group_empty(p)) { + if (!same_thread_group(p->real_parent, tracer)) + dead = do_notify_parent(p, p->exit_signal); + else if (ignoring_children(tracer->sighand)) { + __wake_up_parent(p, tracer); + dead = true; + } + } + /* Mark it as in the process of being reaped. */ + if (dead) + p->exit_state = EXIT_DEAD; + return dead; +} + +static int ptrace_detach(struct task_struct *child, unsigned int data) +{ + if (!valid_signal(data)) + return -EIO; + + /* Architecture-specific hardware disable .. */ + ptrace_disable(child); + clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE); + + write_lock_irq(&tasklist_lock); + /* + * We rely on ptrace_freeze_traced(). It can't be killed and + * untraced by another thread, it can't be a zombie. + */ + WARN_ON(!child->ptrace || child->exit_state); + /* + * tasklist_lock avoids the race with wait_task_stopped(), see + * the comment in ptrace_resume(). + */ + child->exit_code = data; + __ptrace_detach(current, child); + write_unlock_irq(&tasklist_lock); + + proc_ptrace_connector(child, PTRACE_DETACH); + + return 0; +} + +/* + * Detach all tasks we were using ptrace on. Called with tasklist held + * for writing. + */ +void exit_ptrace(struct task_struct *tracer, struct list_head *dead) +{ + struct task_struct *p, *n; + + list_for_each_entry_safe(p, n, &tracer->ptraced, ptrace_entry) { + if (unlikely(p->ptrace & PT_EXITKILL)) + send_sig_info(SIGKILL, SEND_SIG_FORCED, p); + + if (__ptrace_detach(tracer, p)) + list_add(&p->ptrace_entry, dead); + } +} + +int ptrace_readdata(struct task_struct *tsk, unsigned long src, char __user *dst, int len) +{ + int copied = 0; + + while (len > 0) { + char buf[128]; + int this_len, retval; + + this_len = (len > sizeof(buf)) ? sizeof(buf) : len; + retval = access_process_vm(tsk, src, buf, this_len, 0); + if (!retval) { + if (copied) + break; + return -EIO; + } + if (copy_to_user(dst, buf, retval)) + return -EFAULT; + copied += retval; + src += retval; + dst += retval; + len -= retval; + } + return copied; +} + +int ptrace_writedata(struct task_struct *tsk, char __user *src, unsigned long dst, int len) +{ + int copied = 0; + + while (len > 0) { + char buf[128]; + int this_len, retval; + + this_len = (len > sizeof(buf)) ? sizeof(buf) : len; + if (copy_from_user(buf, src, this_len)) + return -EFAULT; + retval = access_process_vm(tsk, dst, buf, this_len, 1); + if (!retval) { + if (copied) + break; + return -EIO; + } + copied += retval; + src += retval; + dst += retval; + len -= retval; + } + return copied; +} + +static int ptrace_setoptions(struct task_struct *child, unsigned long data) +{ + unsigned flags; + + if (data & ~(unsigned long)PTRACE_O_MASK) + return -EINVAL; + + /* Avoid intermediate state when all opts are cleared */ + flags = child->ptrace; + flags &= ~(PTRACE_O_MASK << PT_OPT_FLAG_SHIFT); + flags |= (data << PT_OPT_FLAG_SHIFT); + child->ptrace = flags; + + return 0; +} + +static int ptrace_getsiginfo(struct task_struct *child, siginfo_t *info) +{ + unsigned long flags; + int error = -ESRCH; + + if (lock_task_sighand(child, &flags)) { + error = -EINVAL; + if (likely(child->last_siginfo != NULL)) { + *info = *child->last_siginfo; + error = 0; + } + unlock_task_sighand(child, &flags); + } + return error; +} + +static int ptrace_setsiginfo(struct task_struct *child, const siginfo_t *info) +{ + unsigned long flags; + int error = -ESRCH; + + if (lock_task_sighand(child, &flags)) { + error = -EINVAL; + if (likely(child->last_siginfo != NULL)) { + *child->last_siginfo = *info; + error = 0; + } + unlock_task_sighand(child, &flags); + } + return error; +} + +static int ptrace_peek_siginfo(struct task_struct *child, + unsigned long addr, + unsigned long data) +{ + struct ptrace_peeksiginfo_args arg; + struct sigpending *pending; + struct sigqueue *q; + int ret, i; + + ret = copy_from_user(&arg, (void __user *) addr, + sizeof(struct ptrace_peeksiginfo_args)); + if (ret) + return -EFAULT; + + if (arg.flags & ~PTRACE_PEEKSIGINFO_SHARED) + return -EINVAL; /* unknown flags */ + + if (arg.nr < 0) + return -EINVAL; + + if (arg.flags & PTRACE_PEEKSIGINFO_SHARED) + pending = &child->signal->shared_pending; + else + pending = &child->pending; + + for (i = 0; i < arg.nr; ) { + siginfo_t info; + s32 off = arg.off + i; + + spin_lock_irq(&child->sighand->siglock); + list_for_each_entry(q, &pending->list, list) { + if (!off--) { + copy_siginfo(&info, &q->info); + break; + } + } + spin_unlock_irq(&child->sighand->siglock); + + if (off >= 0) /* beyond the end of the list */ + break; + +#ifdef CONFIG_COMPAT + if (unlikely(is_compat_task())) { + compat_siginfo_t __user *uinfo = compat_ptr(data); + + if (copy_siginfo_to_user32(uinfo, &info) || + __put_user(info.si_code, &uinfo->si_code)) { + ret = -EFAULT; + break; + } + + } else +#endif + { + siginfo_t __user *uinfo = (siginfo_t __user *) data; + + if (copy_siginfo_to_user(uinfo, &info) || + __put_user(info.si_code, &uinfo->si_code)) { + ret = -EFAULT; + break; + } + } + + data += sizeof(siginfo_t); + i++; + + if (signal_pending(current)) + break; + + cond_resched(); + } + + if (i > 0) + return i; + + return ret; +} + +#ifdef PTRACE_SINGLESTEP +#define is_singlestep(request) ((request) == PTRACE_SINGLESTEP) +#else +#define is_singlestep(request) 0 +#endif + +#ifdef PTRACE_SINGLEBLOCK +#define is_singleblock(request) ((request) == PTRACE_SINGLEBLOCK) +#else +#define is_singleblock(request) 0 +#endif + +#ifdef PTRACE_SYSEMU +#define is_sysemu_singlestep(request) ((request) == PTRACE_SYSEMU_SINGLESTEP) +#else +#define is_sysemu_singlestep(request) 0 +#endif + +static int ptrace_resume(struct task_struct *child, long request, + unsigned long data) +{ + bool need_siglock; + + if (!valid_signal(data)) + return -EIO; + + if (request == PTRACE_SYSCALL) + set_tsk_thread_flag(child, TIF_SYSCALL_TRACE); + else + clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE); + +#ifdef TIF_SYSCALL_EMU + if (request == PTRACE_SYSEMU || request == PTRACE_SYSEMU_SINGLESTEP) + set_tsk_thread_flag(child, TIF_SYSCALL_EMU); + else + clear_tsk_thread_flag(child, TIF_SYSCALL_EMU); +#endif + + if (is_singleblock(request)) { + if (unlikely(!arch_has_block_step())) + return -EIO; + user_enable_block_step(child); + } else if (is_singlestep(request) || is_sysemu_singlestep(request)) { + if (unlikely(!arch_has_single_step())) + return -EIO; + user_enable_single_step(child); + } else { + user_disable_single_step(child); + } + + /* + * Change ->exit_code and ->state under siglock to avoid the race + * with wait_task_stopped() in between; a non-zero ->exit_code will + * wrongly look like another report from tracee. + * + * Note that we need siglock even if ->exit_code == data and/or this + * status was not reported yet, the new status must not be cleared by + * wait_task_stopped() after resume. + * + * If data == 0 we do not care if wait_task_stopped() reports the old + * status and clears the code too; this can't race with the tracee, it + * takes siglock after resume. + */ + need_siglock = data && !thread_group_empty(current); + if (need_siglock) + spin_lock_irq(&child->sighand->siglock); + child->exit_code = data; + wake_up_state(child, __TASK_TRACED); + if (need_siglock) + spin_unlock_irq(&child->sighand->siglock); + + return 0; +} + +#ifdef CONFIG_HAVE_ARCH_TRACEHOOK + +static const struct user_regset * +find_regset(const struct user_regset_view *view, unsigned int type) +{ + const struct user_regset *regset; + int n; + + for (n = 0; n < view->n; ++n) { + regset = view->regsets + n; + if (regset->core_note_type == type) + return regset; + } + + return NULL; +} + +static int ptrace_regset(struct task_struct *task, int req, unsigned int type, + struct iovec *kiov) +{ + const struct user_regset_view *view = task_user_regset_view(task); + const struct user_regset *regset = find_regset(view, type); + int regset_no; + + if (!regset || (kiov->iov_len % regset->size) != 0) + return -EINVAL; + + regset_no = regset - view->regsets; + kiov->iov_len = min(kiov->iov_len, + (__kernel_size_t) (regset->n * regset->size)); + + if (req == PTRACE_GETREGSET) + return copy_regset_to_user(task, view, regset_no, 0, + kiov->iov_len, kiov->iov_base); + else + return copy_regset_from_user(task, view, regset_no, 0, + kiov->iov_len, kiov->iov_base); +} + +/* + * This is declared in linux/regset.h and defined in machine-dependent + * code. We put the export here, near the primary machine-neutral use, + * to ensure no machine forgets it. + */ +EXPORT_SYMBOL_GPL(task_user_regset_view); +#endif + +int ptrace_request(struct task_struct *child, long request, + unsigned long addr, unsigned long data) +{ + bool seized = child->ptrace & PT_SEIZED; + int ret = -EIO; + siginfo_t siginfo, *si; + void __user *datavp = (void __user *) data; + unsigned long __user *datalp = datavp; + unsigned long flags; + + switch (request) { + case PTRACE_PEEKTEXT: + case PTRACE_PEEKDATA: + return generic_ptrace_peekdata(child, addr, data); + case PTRACE_POKETEXT: + case PTRACE_POKEDATA: + return generic_ptrace_pokedata(child, addr, data); + +#ifdef PTRACE_OLDSETOPTIONS + case PTRACE_OLDSETOPTIONS: +#endif + case PTRACE_SETOPTIONS: + ret = ptrace_setoptions(child, data); + break; + case PTRACE_GETEVENTMSG: + ret = put_user(child->ptrace_message, datalp); + break; + + case PTRACE_PEEKSIGINFO: + ret = ptrace_peek_siginfo(child, addr, data); + break; + + case PTRACE_GETSIGINFO: + ret = ptrace_getsiginfo(child, &siginfo); + if (!ret) + ret = copy_siginfo_to_user(datavp, &siginfo); + break; + + case PTRACE_SETSIGINFO: + if (copy_from_user(&siginfo, datavp, sizeof siginfo)) + ret = -EFAULT; + else + ret = ptrace_setsiginfo(child, &siginfo); + break; + + case PTRACE_GETSIGMASK: + if (addr != sizeof(sigset_t)) { + ret = -EINVAL; + break; + } + + if (copy_to_user(datavp, &child->blocked, sizeof(sigset_t))) + ret = -EFAULT; + else + ret = 0; + + break; + + case PTRACE_SETSIGMASK: { + sigset_t new_set; + + if (addr != sizeof(sigset_t)) { + ret = -EINVAL; + break; + } + + if (copy_from_user(&new_set, datavp, sizeof(sigset_t))) { + ret = -EFAULT; + break; + } + + sigdelsetmask(&new_set, sigmask(SIGKILL)|sigmask(SIGSTOP)); + + /* + * Every thread does recalc_sigpending() after resume, so + * retarget_shared_pending() and recalc_sigpending() are not + * called here. + */ + spin_lock_irq(&child->sighand->siglock); + child->blocked = new_set; + spin_unlock_irq(&child->sighand->siglock); + + ret = 0; + break; + } + + case PTRACE_INTERRUPT: + /* + * Stop tracee without any side-effect on signal or job + * control. At least one trap is guaranteed to happen + * after this request. If @child is already trapped, the + * current trap is not disturbed and another trap will + * happen after the current trap is ended with PTRACE_CONT. + * + * The actual trap might not be PTRACE_EVENT_STOP trap but + * the pending condition is cleared regardless. + */ + if (unlikely(!seized || !lock_task_sighand(child, &flags))) + break; + + /* + * INTERRUPT doesn't disturb existing trap sans one + * exception. If ptracer issued LISTEN for the current + * STOP, this INTERRUPT should clear LISTEN and re-trap + * tracee into STOP. + */ + if (likely(task_set_jobctl_pending(child, JOBCTL_TRAP_STOP))) + ptrace_signal_wake_up(child, child->jobctl & JOBCTL_LISTENING); + + unlock_task_sighand(child, &flags); + ret = 0; + break; + + case PTRACE_LISTEN: + /* + * Listen for events. Tracee must be in STOP. It's not + * resumed per-se but is not considered to be in TRACED by + * wait(2) or ptrace(2). If an async event (e.g. group + * stop state change) happens, tracee will enter STOP trap + * again. Alternatively, ptracer can issue INTERRUPT to + * finish listening and re-trap tracee into STOP. + */ + if (unlikely(!seized || !lock_task_sighand(child, &flags))) + break; + + si = child->last_siginfo; + if (likely(si && (si->si_code >> 8) == PTRACE_EVENT_STOP)) { + child->jobctl |= JOBCTL_LISTENING; + /* + * If NOTIFY is set, it means event happened between + * start of this trap and now. Trigger re-trap. + */ + if (child->jobctl & JOBCTL_TRAP_NOTIFY) + ptrace_signal_wake_up(child, true); + ret = 0; + } + unlock_task_sighand(child, &flags); + break; + + case PTRACE_DETACH: /* detach a process that was attached. */ + ret = ptrace_detach(child, data); + break; + +#ifdef CONFIG_BINFMT_ELF_FDPIC + case PTRACE_GETFDPIC: { + struct mm_struct *mm = get_task_mm(child); + unsigned long tmp = 0; + + ret = -ESRCH; + if (!mm) + break; + + switch (addr) { + case PTRACE_GETFDPIC_EXEC: + tmp = mm->context.exec_fdpic_loadmap; + break; + case PTRACE_GETFDPIC_INTERP: + tmp = mm->context.interp_fdpic_loadmap; + break; + default: + break; + } + mmput(mm); + + ret = put_user(tmp, datalp); + break; + } +#endif + +#ifdef PTRACE_SINGLESTEP + case PTRACE_SINGLESTEP: +#endif +#ifdef PTRACE_SINGLEBLOCK + case PTRACE_SINGLEBLOCK: +#endif +#ifdef PTRACE_SYSEMU + case PTRACE_SYSEMU: + case PTRACE_SYSEMU_SINGLESTEP: +#endif + case PTRACE_SYSCALL: + case PTRACE_CONT: + return ptrace_resume(child, request, data); + + case PTRACE_KILL: + if (child->exit_state) /* already dead */ + return 0; + return ptrace_resume(child, request, SIGKILL); + +#ifdef CONFIG_HAVE_ARCH_TRACEHOOK + case PTRACE_GETREGSET: + case PTRACE_SETREGSET: { + struct iovec kiov; + struct iovec __user *uiov = datavp; + + if (!access_ok(VERIFY_WRITE, uiov, sizeof(*uiov))) + return -EFAULT; + + if (__get_user(kiov.iov_base, &uiov->iov_base) || + __get_user(kiov.iov_len, &uiov->iov_len)) + return -EFAULT; + + ret = ptrace_regset(child, request, addr, &kiov); + if (!ret) + ret = __put_user(kiov.iov_len, &uiov->iov_len); + break; + } +#endif + default: + break; + } + + return ret; +} + +static struct task_struct *ptrace_get_task_struct(pid_t pid) +{ + struct task_struct *child; + + rcu_read_lock(); + child = find_task_by_vpid(pid); + if (child) + get_task_struct(child); + rcu_read_unlock(); + + if (!child) + return ERR_PTR(-ESRCH); + return child; +} + +#ifndef arch_ptrace_attach +#define arch_ptrace_attach(child) do { } while (0) +#endif + +SYSCALL_DEFINE4(ptrace, long, request, long, pid, unsigned long, addr, + unsigned long, data) +{ + struct task_struct *child; + long ret; + + if (request == PTRACE_TRACEME) { + ret = ptrace_traceme(); + if (!ret) + arch_ptrace_attach(current); + goto out; + } + + child = ptrace_get_task_struct(pid); + if (IS_ERR(child)) { + ret = PTR_ERR(child); + goto out; + } + + if (request == PTRACE_ATTACH || request == PTRACE_SEIZE) { + ret = ptrace_attach(child, request, addr, data); + /* + * Some architectures need to do book-keeping after + * a ptrace attach. + */ + if (!ret) + arch_ptrace_attach(child); + goto out_put_task_struct; + } + + ret = ptrace_check_attach(child, request == PTRACE_KILL || + request == PTRACE_INTERRUPT); + if (ret < 0) + goto out_put_task_struct; + + ret = arch_ptrace(child, request, addr, data); + if (ret || request != PTRACE_DETACH) + ptrace_unfreeze_traced(child); + + out_put_task_struct: + put_task_struct(child); + out: + return ret; +} + +int generic_ptrace_peekdata(struct task_struct *tsk, unsigned long addr, + unsigned long data) +{ + unsigned long tmp; + int copied; + + copied = access_process_vm(tsk, addr, &tmp, sizeof(tmp), 0); + if (copied != sizeof(tmp)) + return -EIO; + return put_user(tmp, (unsigned long __user *)data); +} + +int generic_ptrace_pokedata(struct task_struct *tsk, unsigned long addr, + unsigned long data) +{ + int copied; + + copied = access_process_vm(tsk, addr, &data, sizeof(data), 1); + return (copied == sizeof(data)) ? 0 : -EIO; +} + +#if defined CONFIG_COMPAT + +int compat_ptrace_request(struct task_struct *child, compat_long_t request, + compat_ulong_t addr, compat_ulong_t data) +{ + compat_ulong_t __user *datap = compat_ptr(data); + compat_ulong_t word; + siginfo_t siginfo; + int ret; + + switch (request) { + case PTRACE_PEEKTEXT: + case PTRACE_PEEKDATA: + ret = access_process_vm(child, addr, &word, sizeof(word), 0); + if (ret != sizeof(word)) + ret = -EIO; + else + ret = put_user(word, datap); + break; + + case PTRACE_POKETEXT: + case PTRACE_POKEDATA: + ret = access_process_vm(child, addr, &data, sizeof(data), 1); + ret = (ret != sizeof(data) ? -EIO : 0); + break; + + case PTRACE_GETEVENTMSG: + ret = put_user((compat_ulong_t) child->ptrace_message, datap); + break; + + case PTRACE_GETSIGINFO: + ret = ptrace_getsiginfo(child, &siginfo); + if (!ret) + ret = copy_siginfo_to_user32( + (struct compat_siginfo __user *) datap, + &siginfo); + break; + + case PTRACE_SETSIGINFO: + memset(&siginfo, 0, sizeof siginfo); + if (copy_siginfo_from_user32( + &siginfo, (struct compat_siginfo __user *) datap)) + ret = -EFAULT; + else + ret = ptrace_setsiginfo(child, &siginfo); + break; +#ifdef CONFIG_HAVE_ARCH_TRACEHOOK + case PTRACE_GETREGSET: + case PTRACE_SETREGSET: + { + struct iovec kiov; + struct compat_iovec __user *uiov = + (struct compat_iovec __user *) datap; + compat_uptr_t ptr; + compat_size_t len; + + if (!access_ok(VERIFY_WRITE, uiov, sizeof(*uiov))) + return -EFAULT; + + if (__get_user(ptr, &uiov->iov_base) || + __get_user(len, &uiov->iov_len)) + return -EFAULT; + + kiov.iov_base = compat_ptr(ptr); + kiov.iov_len = len; + + ret = ptrace_regset(child, request, addr, &kiov); + if (!ret) + ret = __put_user(kiov.iov_len, &uiov->iov_len); + break; + } +#endif + + default: + ret = ptrace_request(child, request, addr, data); + } + + return ret; +} + +COMPAT_SYSCALL_DEFINE4(ptrace, compat_long_t, request, compat_long_t, pid, + compat_long_t, addr, compat_long_t, data) +{ + struct task_struct *child; + long ret; + + if (request == PTRACE_TRACEME) { + ret = ptrace_traceme(); + goto out; + } + + child = ptrace_get_task_struct(pid); + if (IS_ERR(child)) { + ret = PTR_ERR(child); + goto out; + } + + if (request == PTRACE_ATTACH || request == PTRACE_SEIZE) { + ret = ptrace_attach(child, request, addr, data); + /* + * Some architectures need to do book-keeping after + * a ptrace attach. + */ + if (!ret) + arch_ptrace_attach(child); + goto out_put_task_struct; + } + + ret = ptrace_check_attach(child, request == PTRACE_KILL || + request == PTRACE_INTERRUPT); + if (!ret) { + ret = compat_arch_ptrace(child, request, addr, data); + if (ret || request != PTRACE_DETACH) + ptrace_unfreeze_traced(child); + } + + out_put_task_struct: + put_task_struct(child); + out: + return ret; +} +#endif /* CONFIG_COMPAT */ diff --git a/kernel/kernel/range.c b/kernel/kernel/range.c new file mode 100644 index 000000000..82cfc285b --- /dev/null +++ b/kernel/kernel/range.c @@ -0,0 +1,163 @@ +/* + * Range add and subtract + */ +#include +#include +#include +#include +#include + +int add_range(struct range *range, int az, int nr_range, u64 start, u64 end) +{ + if (start >= end) + return nr_range; + + /* Out of slots: */ + if (nr_range >= az) + return nr_range; + + range[nr_range].start = start; + range[nr_range].end = end; + + nr_range++; + + return nr_range; +} + +int add_range_with_merge(struct range *range, int az, int nr_range, + u64 start, u64 end) +{ + int i; + + if (start >= end) + return nr_range; + + /* get new start/end: */ + for (i = 0; i < nr_range; i++) { + u64 common_start, common_end; + + if (!range[i].end) + continue; + + common_start = max(range[i].start, start); + common_end = min(range[i].end, end); + if (common_start > common_end) + continue; + + /* new start/end, will add it back at last */ + start = min(range[i].start, start); + end = max(range[i].end, end); + + memmove(&range[i], &range[i + 1], + (nr_range - (i + 1)) * sizeof(range[i])); + range[nr_range - 1].start = 0; + range[nr_range - 1].end = 0; + nr_range--; + i--; + } + + /* Need to add it: */ + return add_range(range, az, nr_range, start, end); +} + +void subtract_range(struct range *range, int az, u64 start, u64 end) +{ + int i, j; + + if (start >= end) + return; + + for (j = 0; j < az; j++) { + if (!range[j].end) + continue; + + if (start <= range[j].start && end >= range[j].end) { + range[j].start = 0; + range[j].end = 0; + continue; + } + + if (start <= range[j].start && end < range[j].end && + range[j].start < end) { + range[j].start = end; + continue; + } + + + if (start > range[j].start && end >= range[j].end && + range[j].end > start) { + range[j].end = start; + continue; + } + + if (start > range[j].start && end < range[j].end) { + /* Find the new spare: */ + for (i = 0; i < az; i++) { + if (range[i].end == 0) + break; + } + if (i < az) { + range[i].end = range[j].end; + range[i].start = end; + } else { + pr_err("%s: run out of slot in ranges\n", + __func__); + } + range[j].end = start; + continue; + } + } +} + +static int cmp_range(const void *x1, const void *x2) +{ + const struct range *r1 = x1; + const struct range *r2 = x2; + + if (r1->start < r2->start) + return -1; + if (r1->start > r2->start) + return 1; + return 0; +} + +int clean_sort_range(struct range *range, int az) +{ + int i, j, k = az - 1, nr_range = az; + + for (i = 0; i < k; i++) { + if (range[i].end) + continue; + for (j = k; j > i; j--) { + if (range[j].end) { + k = j; + break; + } + } + if (j == i) + break; + range[i].start = range[k].start; + range[i].end = range[k].end; + range[k].start = 0; + range[k].end = 0; + k--; + } + /* count it */ + for (i = 0; i < az; i++) { + if (!range[i].end) { + nr_range = i; + break; + } + } + + /* sort them */ + sort(range, nr_range, sizeof(struct range), cmp_range, NULL); + + return nr_range; +} + +void sort_range(struct range *range, int nr_range) +{ + /* sort them */ + sort(range, nr_range, sizeof(struct range), cmp_range, NULL); +} diff --git a/kernel/kernel/rcu/Makefile b/kernel/kernel/rcu/Makefile new file mode 100644 index 000000000..50a808424 --- /dev/null +++ b/kernel/kernel/rcu/Makefile @@ -0,0 +1,7 @@ +obj-y += update.o +obj-$(CONFIG_SRCU) += srcu.o +obj-$(CONFIG_RCU_TORTURE_TEST) += rcutorture.o +obj-$(CONFIG_TREE_RCU) += tree.o +obj-$(CONFIG_PREEMPT_RCU) += tree.o +obj-$(CONFIG_TREE_RCU_TRACE) += tree_trace.o +obj-$(CONFIG_TINY_RCU) += tiny.o diff --git a/kernel/kernel/rcu/rcu.h b/kernel/kernel/rcu/rcu.h new file mode 100644 index 000000000..80adef7d4 --- /dev/null +++ b/kernel/kernel/rcu/rcu.h @@ -0,0 +1,146 @@ +/* + * Read-Copy Update definitions shared among RCU implementations. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, you can access it online at + * http://www.gnu.org/licenses/gpl-2.0.html. + * + * Copyright IBM Corporation, 2011 + * + * Author: Paul E. McKenney + */ + +#ifndef __LINUX_RCU_H +#define __LINUX_RCU_H + +#include +#ifdef CONFIG_RCU_TRACE +#define RCU_TRACE(stmt) stmt +#else /* #ifdef CONFIG_RCU_TRACE */ +#define RCU_TRACE(stmt) +#endif /* #else #ifdef CONFIG_RCU_TRACE */ + +/* + * Process-level increment to ->dynticks_nesting field. This allows for + * architectures that use half-interrupts and half-exceptions from + * process context. + * + * DYNTICK_TASK_NEST_MASK defines a field of width DYNTICK_TASK_NEST_WIDTH + * that counts the number of process-based reasons why RCU cannot + * consider the corresponding CPU to be idle, and DYNTICK_TASK_NEST_VALUE + * is the value used to increment or decrement this field. + * + * The rest of the bits could in principle be used to count interrupts, + * but this would mean that a negative-one value in the interrupt + * field could incorrectly zero out the DYNTICK_TASK_NEST_MASK field. + * We therefore provide a two-bit guard field defined by DYNTICK_TASK_MASK + * that is set to DYNTICK_TASK_FLAG upon initial exit from idle. + * The DYNTICK_TASK_EXIT_IDLE value is thus the combined value used upon + * initial exit from idle. + */ +#define DYNTICK_TASK_NEST_WIDTH 7 +#define DYNTICK_TASK_NEST_VALUE ((LLONG_MAX >> DYNTICK_TASK_NEST_WIDTH) + 1) +#define DYNTICK_TASK_NEST_MASK (LLONG_MAX - DYNTICK_TASK_NEST_VALUE + 1) +#define DYNTICK_TASK_FLAG ((DYNTICK_TASK_NEST_VALUE / 8) * 2) +#define DYNTICK_TASK_MASK ((DYNTICK_TASK_NEST_VALUE / 8) * 3) +#define DYNTICK_TASK_EXIT_IDLE (DYNTICK_TASK_NEST_VALUE + \ + DYNTICK_TASK_FLAG) + +/* + * debug_rcu_head_queue()/debug_rcu_head_unqueue() are used internally + * by call_rcu() and rcu callback execution, and are therefore not part of the + * RCU API. Leaving in rcupdate.h because they are used by all RCU flavors. + */ + +#ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD +# define STATE_RCU_HEAD_READY 0 +# define STATE_RCU_HEAD_QUEUED 1 + +extern struct debug_obj_descr rcuhead_debug_descr; + +static inline int debug_rcu_head_queue(struct rcu_head *head) +{ + int r1; + + r1 = debug_object_activate(head, &rcuhead_debug_descr); + debug_object_active_state(head, &rcuhead_debug_descr, + STATE_RCU_HEAD_READY, + STATE_RCU_HEAD_QUEUED); + return r1; +} + +static inline void debug_rcu_head_unqueue(struct rcu_head *head) +{ + debug_object_active_state(head, &rcuhead_debug_descr, + STATE_RCU_HEAD_QUEUED, + STATE_RCU_HEAD_READY); + debug_object_deactivate(head, &rcuhead_debug_descr); +} +#else /* !CONFIG_DEBUG_OBJECTS_RCU_HEAD */ +static inline int debug_rcu_head_queue(struct rcu_head *head) +{ + return 0; +} + +static inline void debug_rcu_head_unqueue(struct rcu_head *head) +{ +} +#endif /* #else !CONFIG_DEBUG_OBJECTS_RCU_HEAD */ + +void kfree(const void *); + +/* + * Reclaim the specified callback, either by invoking it (non-lazy case) + * or freeing it directly (lazy case). Return true if lazy, false otherwise. + */ +static inline bool __rcu_reclaim(const char *rn, struct rcu_head *head) +{ + unsigned long offset = (unsigned long)head->func; + + rcu_lock_acquire(&rcu_callback_map); + if (__is_kfree_rcu_offset(offset)) { + RCU_TRACE(trace_rcu_invoke_kfree_callback(rn, head, offset)); + kfree((void *)head - offset); + rcu_lock_release(&rcu_callback_map); + return true; + } else { + RCU_TRACE(trace_rcu_invoke_callback(rn, head)); + head->func(head); + rcu_lock_release(&rcu_callback_map); + return false; + } +} + +#ifdef CONFIG_RCU_STALL_COMMON + +extern int rcu_cpu_stall_suppress; +int rcu_jiffies_till_stall_check(void); + +#endif /* #ifdef CONFIG_RCU_STALL_COMMON */ + +/* + * Strings used in tracepoints need to be exported via the + * tracing system such that tools like perf and trace-cmd can + * translate the string address pointers to actual text. + */ +#define TPS(x) tracepoint_string(x) + +void rcu_early_boot_tests(void); + +/* + * This function really isn't for public consumption, but RCU is special in + * that context switches can allow the state machine to make progress. + */ +extern void resched_cpu(int cpu); + +#endif /* __LINUX_RCU_H */ diff --git a/kernel/kernel/rcu/rcutorture.c b/kernel/kernel/rcu/rcutorture.c new file mode 100644 index 000000000..8dbe27611 --- /dev/null +++ b/kernel/kernel/rcu/rcutorture.c @@ -0,0 +1,1861 @@ +/* + * Read-Copy Update module-based torture test facility + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, you can access it online at + * http://www.gnu.org/licenses/gpl-2.0.html. + * + * Copyright (C) IBM Corporation, 2005, 2006 + * + * Authors: Paul E. McKenney + * Josh Triplett + * + * See also: Documentation/RCU/torture.txt + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Paul E. McKenney and Josh Triplett "); + + +torture_param(int, cbflood_inter_holdoff, HZ, + "Holdoff between floods (jiffies)"); +torture_param(int, cbflood_intra_holdoff, 1, + "Holdoff between bursts (jiffies)"); +torture_param(int, cbflood_n_burst, 3, "# bursts in flood, zero to disable"); +torture_param(int, cbflood_n_per_burst, 20000, + "# callbacks per burst in flood"); +torture_param(int, fqs_duration, 0, + "Duration of fqs bursts (us), 0 to disable"); +torture_param(int, fqs_holdoff, 0, "Holdoff time within fqs bursts (us)"); +torture_param(int, fqs_stutter, 3, "Wait time between fqs bursts (s)"); +torture_param(bool, gp_cond, false, "Use conditional/async GP wait primitives"); +torture_param(bool, gp_exp, false, "Use expedited GP wait primitives"); +torture_param(bool, gp_normal, false, + "Use normal (non-expedited) GP wait primitives"); +torture_param(bool, gp_sync, false, "Use synchronous GP wait primitives"); +torture_param(int, irqreader, 1, "Allow RCU readers from irq handlers"); +torture_param(int, n_barrier_cbs, 0, + "# of callbacks/kthreads for barrier testing"); +torture_param(int, nfakewriters, 4, "Number of RCU fake writer threads"); +torture_param(int, nreaders, -1, "Number of RCU reader threads"); +torture_param(int, object_debug, 0, + "Enable debug-object double call_rcu() testing"); +torture_param(int, onoff_holdoff, 0, "Time after boot before CPU hotplugs (s)"); +torture_param(int, onoff_interval, 0, + "Time between CPU hotplugs (s), 0=disable"); +torture_param(int, shuffle_interval, 3, "Number of seconds between shuffles"); +torture_param(int, shutdown_secs, 0, "Shutdown time (s), <= zero to disable."); +torture_param(int, stall_cpu, 0, "Stall duration (s), zero to disable."); +torture_param(int, stall_cpu_holdoff, 10, + "Time to wait before starting stall (s)."); +torture_param(int, stat_interval, 60, + "Number of seconds between stats printk()s"); +torture_param(int, stutter, 5, "Number of seconds to run/halt test"); +torture_param(int, test_boost, 1, "Test RCU prio boost: 0=no, 1=maybe, 2=yes."); +torture_param(int, test_boost_duration, 4, + "Duration of each boost test, seconds."); +torture_param(int, test_boost_interval, 7, + "Interval between boost tests, seconds."); +torture_param(bool, test_no_idle_hz, true, + "Test support for tickless idle CPUs"); +torture_param(bool, verbose, true, + "Enable verbose debugging printk()s"); + +static char *torture_type = "rcu"; +module_param(torture_type, charp, 0444); +MODULE_PARM_DESC(torture_type, "Type of RCU to torture (rcu, rcu_bh, ...)"); + +static int nrealreaders; +static int ncbflooders; +static struct task_struct *writer_task; +static struct task_struct **fakewriter_tasks; +static struct task_struct **reader_tasks; +static struct task_struct *stats_task; +static struct task_struct **cbflood_task; +static struct task_struct *fqs_task; +static struct task_struct *boost_tasks[NR_CPUS]; +static struct task_struct *stall_task; +static struct task_struct **barrier_cbs_tasks; +static struct task_struct *barrier_task; + +#define RCU_TORTURE_PIPE_LEN 10 + +struct rcu_torture { + struct rcu_head rtort_rcu; + int rtort_pipe_count; + struct list_head rtort_free; + int rtort_mbtest; +}; + +static LIST_HEAD(rcu_torture_freelist); +static struct rcu_torture __rcu *rcu_torture_current; +static unsigned long rcu_torture_current_version; +static struct rcu_torture rcu_tortures[10 * RCU_TORTURE_PIPE_LEN]; +static DEFINE_SPINLOCK(rcu_torture_lock); +static DEFINE_PER_CPU(long [RCU_TORTURE_PIPE_LEN + 1], + rcu_torture_count) = { 0 }; +static DEFINE_PER_CPU(long [RCU_TORTURE_PIPE_LEN + 1], + rcu_torture_batch) = { 0 }; +static atomic_t rcu_torture_wcount[RCU_TORTURE_PIPE_LEN + 1]; +static atomic_t n_rcu_torture_alloc; +static atomic_t n_rcu_torture_alloc_fail; +static atomic_t n_rcu_torture_free; +static atomic_t n_rcu_torture_mberror; +static atomic_t n_rcu_torture_error; +static long n_rcu_torture_barrier_error; +static long n_rcu_torture_boost_ktrerror; +static long n_rcu_torture_boost_rterror; +static long n_rcu_torture_boost_failure; +static long n_rcu_torture_boosts; +static long n_rcu_torture_timers; +static long n_barrier_attempts; +static long n_barrier_successes; +static atomic_long_t n_cbfloods; +static struct list_head rcu_torture_removed; + +static int rcu_torture_writer_state; +#define RTWS_FIXED_DELAY 0 +#define RTWS_DELAY 1 +#define RTWS_REPLACE 2 +#define RTWS_DEF_FREE 3 +#define RTWS_EXP_SYNC 4 +#define RTWS_COND_GET 5 +#define RTWS_COND_SYNC 6 +#define RTWS_SYNC 7 +#define RTWS_STUTTER 8 +#define RTWS_STOPPING 9 + +#if defined(MODULE) || defined(CONFIG_RCU_TORTURE_TEST_RUNNABLE) +#define RCUTORTURE_RUNNABLE_INIT 1 +#else +#define RCUTORTURE_RUNNABLE_INIT 0 +#endif +static int torture_runnable = RCUTORTURE_RUNNABLE_INIT; +module_param(torture_runnable, int, 0444); +MODULE_PARM_DESC(torture_runnable, "Start rcutorture at boot"); + +#if defined(CONFIG_RCU_BOOST) && !defined(CONFIG_HOTPLUG_CPU) +#define rcu_can_boost() 1 +#else /* #if defined(CONFIG_RCU_BOOST) && !defined(CONFIG_HOTPLUG_CPU) */ +#define rcu_can_boost() 0 +#endif /* #else #if defined(CONFIG_RCU_BOOST) && !defined(CONFIG_HOTPLUG_CPU) */ + +#ifdef CONFIG_RCU_TRACE +static u64 notrace rcu_trace_clock_local(void) +{ + u64 ts = trace_clock_local(); + unsigned long __maybe_unused ts_rem = do_div(ts, NSEC_PER_USEC); + return ts; +} +#else /* #ifdef CONFIG_RCU_TRACE */ +static u64 notrace rcu_trace_clock_local(void) +{ + return 0ULL; +} +#endif /* #else #ifdef CONFIG_RCU_TRACE */ + +static unsigned long boost_starttime; /* jiffies of next boost test start. */ +static DEFINE_MUTEX(boost_mutex); /* protect setting boost_starttime */ + /* and boost task create/destroy. */ +static atomic_t barrier_cbs_count; /* Barrier callbacks registered. */ +static bool barrier_phase; /* Test phase. */ +static atomic_t barrier_cbs_invoked; /* Barrier callbacks invoked. */ +static wait_queue_head_t *barrier_cbs_wq; /* Coordinate barrier testing. */ +static DECLARE_WAIT_QUEUE_HEAD(barrier_wq); + +/* + * Allocate an element from the rcu_tortures pool. + */ +static struct rcu_torture * +rcu_torture_alloc(void) +{ + struct list_head *p; + + spin_lock_bh(&rcu_torture_lock); + if (list_empty(&rcu_torture_freelist)) { + atomic_inc(&n_rcu_torture_alloc_fail); + spin_unlock_bh(&rcu_torture_lock); + return NULL; + } + atomic_inc(&n_rcu_torture_alloc); + p = rcu_torture_freelist.next; + list_del_init(p); + spin_unlock_bh(&rcu_torture_lock); + return container_of(p, struct rcu_torture, rtort_free); +} + +/* + * Free an element to the rcu_tortures pool. + */ +static void +rcu_torture_free(struct rcu_torture *p) +{ + atomic_inc(&n_rcu_torture_free); + spin_lock_bh(&rcu_torture_lock); + list_add_tail(&p->rtort_free, &rcu_torture_freelist); + spin_unlock_bh(&rcu_torture_lock); +} + +/* + * Operations vector for selecting different types of tests. + */ + +struct rcu_torture_ops { + int ttype; + void (*init)(void); + int (*readlock)(void); + void (*read_delay)(struct torture_random_state *rrsp); + void (*readunlock)(int idx); + unsigned long (*started)(void); + unsigned long (*completed)(void); + void (*deferred_free)(struct rcu_torture *p); + void (*sync)(void); + void (*exp_sync)(void); + unsigned long (*get_state)(void); + void (*cond_sync)(unsigned long oldstate); + void (*call)(struct rcu_head *head, void (*func)(struct rcu_head *rcu)); + void (*cb_barrier)(void); + void (*fqs)(void); + void (*stats)(void); + int irq_capable; + int can_boost; + const char *name; +}; + +static struct rcu_torture_ops *cur_ops; + +/* + * Definitions for rcu torture testing. + */ + +static int rcu_torture_read_lock(void) __acquires(RCU) +{ + rcu_read_lock(); + return 0; +} + +static void rcu_read_delay(struct torture_random_state *rrsp) +{ + const unsigned long shortdelay_us = 200; + const unsigned long longdelay_ms = 50; + + /* We want a short delay sometimes to make a reader delay the grace + * period, and we want a long delay occasionally to trigger + * force_quiescent_state. */ + + if (!(torture_random(rrsp) % (nrealreaders * 2000 * longdelay_ms))) + mdelay(longdelay_ms); + if (!(torture_random(rrsp) % (nrealreaders * 2 * shortdelay_us))) + udelay(shortdelay_us); +#ifdef CONFIG_PREEMPT + if (!preempt_count() && + !(torture_random(rrsp) % (nrealreaders * 20000))) + preempt_schedule(); /* No QS if preempt_disable() in effect */ +#endif +} + +static void rcu_torture_read_unlock(int idx) __releases(RCU) +{ + rcu_read_unlock(); +} + +/* + * Update callback in the pipe. This should be invoked after a grace period. + */ +static bool +rcu_torture_pipe_update_one(struct rcu_torture *rp) +{ + int i; + + i = rp->rtort_pipe_count; + if (i > RCU_TORTURE_PIPE_LEN) + i = RCU_TORTURE_PIPE_LEN; + atomic_inc(&rcu_torture_wcount[i]); + if (++rp->rtort_pipe_count >= RCU_TORTURE_PIPE_LEN) { + rp->rtort_mbtest = 0; + return true; + } + return false; +} + +/* + * Update all callbacks in the pipe. Suitable for synchronous grace-period + * primitives. + */ +static void +rcu_torture_pipe_update(struct rcu_torture *old_rp) +{ + struct rcu_torture *rp; + struct rcu_torture *rp1; + + if (old_rp) + list_add(&old_rp->rtort_free, &rcu_torture_removed); + list_for_each_entry_safe(rp, rp1, &rcu_torture_removed, rtort_free) { + if (rcu_torture_pipe_update_one(rp)) { + list_del(&rp->rtort_free); + rcu_torture_free(rp); + } + } +} + +static void +rcu_torture_cb(struct rcu_head *p) +{ + struct rcu_torture *rp = container_of(p, struct rcu_torture, rtort_rcu); + + if (torture_must_stop_irq()) { + /* Test is ending, just drop callbacks on the floor. */ + /* The next initialization will pick up the pieces. */ + return; + } + if (rcu_torture_pipe_update_one(rp)) + rcu_torture_free(rp); + else + cur_ops->deferred_free(rp); +} + +static unsigned long rcu_no_completed(void) +{ + return 0; +} + +static void rcu_torture_deferred_free(struct rcu_torture *p) +{ + call_rcu(&p->rtort_rcu, rcu_torture_cb); +} + +static void rcu_sync_torture_init(void) +{ + INIT_LIST_HEAD(&rcu_torture_removed); +} + +static struct rcu_torture_ops rcu_ops = { + .ttype = RCU_FLAVOR, + .init = rcu_sync_torture_init, + .readlock = rcu_torture_read_lock, + .read_delay = rcu_read_delay, + .readunlock = rcu_torture_read_unlock, + .started = rcu_batches_started, + .completed = rcu_batches_completed, + .deferred_free = rcu_torture_deferred_free, + .sync = synchronize_rcu, + .exp_sync = synchronize_rcu_expedited, + .get_state = get_state_synchronize_rcu, + .cond_sync = cond_synchronize_rcu, + .call = call_rcu, + .cb_barrier = rcu_barrier, + .fqs = rcu_force_quiescent_state, + .stats = NULL, + .irq_capable = 1, + .can_boost = rcu_can_boost(), + .name = "rcu" +}; + +/* + * Definitions for rcu_bh torture testing. + */ + +static int rcu_bh_torture_read_lock(void) __acquires(RCU_BH) +{ + rcu_read_lock_bh(); + return 0; +} + +static void rcu_bh_torture_read_unlock(int idx) __releases(RCU_BH) +{ + rcu_read_unlock_bh(); +} + +static void rcu_bh_torture_deferred_free(struct rcu_torture *p) +{ + call_rcu_bh(&p->rtort_rcu, rcu_torture_cb); +} + +static struct rcu_torture_ops rcu_bh_ops = { + .ttype = RCU_BH_FLAVOR, + .init = rcu_sync_torture_init, + .readlock = rcu_bh_torture_read_lock, + .read_delay = rcu_read_delay, /* just reuse rcu's version. */ + .readunlock = rcu_bh_torture_read_unlock, + .started = rcu_batches_started_bh, + .completed = rcu_batches_completed_bh, + .deferred_free = rcu_bh_torture_deferred_free, + .sync = synchronize_rcu_bh, + .exp_sync = synchronize_rcu_bh_expedited, + .call = call_rcu_bh, + .cb_barrier = rcu_barrier_bh, + .fqs = rcu_bh_force_quiescent_state, + .stats = NULL, + .irq_capable = 1, + .name = "rcu_bh" +}; + +/* + * Don't even think about trying any of these in real life!!! + * The names includes "busted", and they really means it! + * The only purpose of these functions is to provide a buggy RCU + * implementation to make sure that rcutorture correctly emits + * buggy-RCU error messages. + */ +static void rcu_busted_torture_deferred_free(struct rcu_torture *p) +{ + /* This is a deliberate bug for testing purposes only! */ + rcu_torture_cb(&p->rtort_rcu); +} + +static void synchronize_rcu_busted(void) +{ + /* This is a deliberate bug for testing purposes only! */ +} + +static void +call_rcu_busted(struct rcu_head *head, void (*func)(struct rcu_head *rcu)) +{ + /* This is a deliberate bug for testing purposes only! */ + func(head); +} + +static struct rcu_torture_ops rcu_busted_ops = { + .ttype = INVALID_RCU_FLAVOR, + .init = rcu_sync_torture_init, + .readlock = rcu_torture_read_lock, + .read_delay = rcu_read_delay, /* just reuse rcu's version. */ + .readunlock = rcu_torture_read_unlock, + .started = rcu_no_completed, + .completed = rcu_no_completed, + .deferred_free = rcu_busted_torture_deferred_free, + .sync = synchronize_rcu_busted, + .exp_sync = synchronize_rcu_busted, + .call = call_rcu_busted, + .cb_barrier = NULL, + .fqs = NULL, + .stats = NULL, + .irq_capable = 1, + .name = "rcu_busted" +}; + +/* + * Definitions for srcu torture testing. + */ + +DEFINE_STATIC_SRCU(srcu_ctl); + +static int srcu_torture_read_lock(void) __acquires(&srcu_ctl) +{ + return srcu_read_lock(&srcu_ctl); +} + +static void srcu_read_delay(struct torture_random_state *rrsp) +{ + long delay; + const long uspertick = 1000000 / HZ; + const long longdelay = 10; + + /* We want there to be long-running readers, but not all the time. */ + + delay = torture_random(rrsp) % + (nrealreaders * 2 * longdelay * uspertick); + if (!delay) + schedule_timeout_interruptible(longdelay); + else + rcu_read_delay(rrsp); +} + +static void srcu_torture_read_unlock(int idx) __releases(&srcu_ctl) +{ + srcu_read_unlock(&srcu_ctl, idx); +} + +static unsigned long srcu_torture_completed(void) +{ + return srcu_batches_completed(&srcu_ctl); +} + +static void srcu_torture_deferred_free(struct rcu_torture *rp) +{ + call_srcu(&srcu_ctl, &rp->rtort_rcu, rcu_torture_cb); +} + +static void srcu_torture_synchronize(void) +{ + synchronize_srcu(&srcu_ctl); +} + +static void srcu_torture_call(struct rcu_head *head, + void (*func)(struct rcu_head *head)) +{ + call_srcu(&srcu_ctl, head, func); +} + +static void srcu_torture_barrier(void) +{ + srcu_barrier(&srcu_ctl); +} + +static void srcu_torture_stats(void) +{ + int cpu; + int idx = srcu_ctl.completed & 0x1; + + pr_alert("%s%s per-CPU(idx=%d):", + torture_type, TORTURE_FLAG, idx); + for_each_possible_cpu(cpu) { + long c0, c1; + + c0 = (long)per_cpu_ptr(srcu_ctl.per_cpu_ref, cpu)->c[!idx]; + c1 = (long)per_cpu_ptr(srcu_ctl.per_cpu_ref, cpu)->c[idx]; + pr_cont(" %d(%ld,%ld)", cpu, c0, c1); + } + pr_cont("\n"); +} + +static void srcu_torture_synchronize_expedited(void) +{ + synchronize_srcu_expedited(&srcu_ctl); +} + +static struct rcu_torture_ops srcu_ops = { + .ttype = SRCU_FLAVOR, + .init = rcu_sync_torture_init, + .readlock = srcu_torture_read_lock, + .read_delay = srcu_read_delay, + .readunlock = srcu_torture_read_unlock, + .started = NULL, + .completed = srcu_torture_completed, + .deferred_free = srcu_torture_deferred_free, + .sync = srcu_torture_synchronize, + .exp_sync = srcu_torture_synchronize_expedited, + .call = srcu_torture_call, + .cb_barrier = srcu_torture_barrier, + .stats = srcu_torture_stats, + .name = "srcu" +}; + +/* + * Definitions for sched torture testing. + */ + +static int sched_torture_read_lock(void) +{ + preempt_disable(); + return 0; +} + +static void sched_torture_read_unlock(int idx) +{ + preempt_enable(); +} + +static void rcu_sched_torture_deferred_free(struct rcu_torture *p) +{ + call_rcu_sched(&p->rtort_rcu, rcu_torture_cb); +} + +static struct rcu_torture_ops sched_ops = { + .ttype = RCU_SCHED_FLAVOR, + .init = rcu_sync_torture_init, + .readlock = sched_torture_read_lock, + .read_delay = rcu_read_delay, /* just reuse rcu's version. */ + .readunlock = sched_torture_read_unlock, + .started = rcu_batches_started_sched, + .completed = rcu_batches_completed_sched, + .deferred_free = rcu_sched_torture_deferred_free, + .sync = synchronize_sched, + .exp_sync = synchronize_sched_expedited, + .call = call_rcu_sched, + .cb_barrier = rcu_barrier_sched, + .fqs = rcu_sched_force_quiescent_state, + .stats = NULL, + .irq_capable = 1, + .name = "sched" +}; + +#ifdef CONFIG_TASKS_RCU + +/* + * Definitions for RCU-tasks torture testing. + */ + +static int tasks_torture_read_lock(void) +{ + return 0; +} + +static void tasks_torture_read_unlock(int idx) +{ +} + +static void rcu_tasks_torture_deferred_free(struct rcu_torture *p) +{ + call_rcu_tasks(&p->rtort_rcu, rcu_torture_cb); +} + +static struct rcu_torture_ops tasks_ops = { + .ttype = RCU_TASKS_FLAVOR, + .init = rcu_sync_torture_init, + .readlock = tasks_torture_read_lock, + .read_delay = rcu_read_delay, /* just reuse rcu's version. */ + .readunlock = tasks_torture_read_unlock, + .started = rcu_no_completed, + .completed = rcu_no_completed, + .deferred_free = rcu_tasks_torture_deferred_free, + .sync = synchronize_rcu_tasks, + .exp_sync = synchronize_rcu_tasks, + .call = call_rcu_tasks, + .cb_barrier = rcu_barrier_tasks, + .fqs = NULL, + .stats = NULL, + .irq_capable = 1, + .name = "tasks" +}; + +#define RCUTORTURE_TASKS_OPS &tasks_ops, + +#else /* #ifdef CONFIG_TASKS_RCU */ + +#define RCUTORTURE_TASKS_OPS + +#endif /* #else #ifdef CONFIG_TASKS_RCU */ + +/* + * RCU torture priority-boost testing. Runs one real-time thread per + * CPU for moderate bursts, repeatedly registering RCU callbacks and + * spinning waiting for them to be invoked. If a given callback takes + * too long to be invoked, we assume that priority inversion has occurred. + */ + +struct rcu_boost_inflight { + struct rcu_head rcu; + int inflight; +}; + +static void rcu_torture_boost_cb(struct rcu_head *head) +{ + struct rcu_boost_inflight *rbip = + container_of(head, struct rcu_boost_inflight, rcu); + + smp_mb(); /* Ensure RCU-core accesses precede clearing ->inflight */ + rbip->inflight = 0; +} + +static int rcu_torture_boost(void *arg) +{ + unsigned long call_rcu_time; + unsigned long endtime; + unsigned long oldstarttime; + struct rcu_boost_inflight rbi = { .inflight = 0 }; + struct sched_param sp; + + VERBOSE_TOROUT_STRING("rcu_torture_boost started"); + + /* Set real-time priority. */ + sp.sched_priority = 1; + if (sched_setscheduler(current, SCHED_FIFO, &sp) < 0) { + VERBOSE_TOROUT_STRING("rcu_torture_boost RT prio failed!"); + n_rcu_torture_boost_rterror++; + } + + init_rcu_head_on_stack(&rbi.rcu); + /* Each pass through the following loop does one boost-test cycle. */ + do { + /* Wait for the next test interval. */ + oldstarttime = boost_starttime; + while (ULONG_CMP_LT(jiffies, oldstarttime)) { + schedule_timeout_interruptible(oldstarttime - jiffies); + stutter_wait("rcu_torture_boost"); + if (torture_must_stop()) + goto checkwait; + } + + /* Do one boost-test interval. */ + endtime = oldstarttime + test_boost_duration * HZ; + call_rcu_time = jiffies; + while (ULONG_CMP_LT(jiffies, endtime)) { + /* If we don't have a callback in flight, post one. */ + if (!rbi.inflight) { + smp_mb(); /* RCU core before ->inflight = 1. */ + rbi.inflight = 1; + call_rcu(&rbi.rcu, rcu_torture_boost_cb); + if (jiffies - call_rcu_time > + test_boost_duration * HZ - HZ / 2) { + VERBOSE_TOROUT_STRING("rcu_torture_boost boosting failed"); + n_rcu_torture_boost_failure++; + } + call_rcu_time = jiffies; + } + cond_resched_rcu_qs(); + stutter_wait("rcu_torture_boost"); + if (torture_must_stop()) + goto checkwait; + } + + /* + * Set the start time of the next test interval. + * Yes, this is vulnerable to long delays, but such + * delays simply cause a false negative for the next + * interval. Besides, we are running at RT priority, + * so delays should be relatively rare. + */ + while (oldstarttime == boost_starttime && + !kthread_should_stop()) { + if (mutex_trylock(&boost_mutex)) { + boost_starttime = jiffies + + test_boost_interval * HZ; + n_rcu_torture_boosts++; + mutex_unlock(&boost_mutex); + break; + } + schedule_timeout_uninterruptible(1); + } + + /* Go do the stutter. */ +checkwait: stutter_wait("rcu_torture_boost"); + } while (!torture_must_stop()); + + /* Clean up and exit. */ + while (!kthread_should_stop() || rbi.inflight) { + torture_shutdown_absorb("rcu_torture_boost"); + schedule_timeout_uninterruptible(1); + } + smp_mb(); /* order accesses to ->inflight before stack-frame death. */ + destroy_rcu_head_on_stack(&rbi.rcu); + torture_kthread_stopping("rcu_torture_boost"); + return 0; +} + +static void rcu_torture_cbflood_cb(struct rcu_head *rhp) +{ +} + +/* + * RCU torture callback-flood kthread. Repeatedly induces bursts of calls + * to call_rcu() or analogous, increasing the probability of occurrence + * of callback-overflow corner cases. + */ +static int +rcu_torture_cbflood(void *arg) +{ + int err = 1; + int i; + int j; + struct rcu_head *rhp; + + if (cbflood_n_per_burst > 0 && + cbflood_inter_holdoff > 0 && + cbflood_intra_holdoff > 0 && + cur_ops->call && + cur_ops->cb_barrier) { + rhp = vmalloc(sizeof(*rhp) * + cbflood_n_burst * cbflood_n_per_burst); + err = !rhp; + } + if (err) { + VERBOSE_TOROUT_STRING("rcu_torture_cbflood disabled: Bad args or OOM"); + while (!torture_must_stop()) + schedule_timeout_interruptible(HZ); + return 0; + } + VERBOSE_TOROUT_STRING("rcu_torture_cbflood task started"); + do { + schedule_timeout_interruptible(cbflood_inter_holdoff); + atomic_long_inc(&n_cbfloods); + WARN_ON(signal_pending(current)); + for (i = 0; i < cbflood_n_burst; i++) { + for (j = 0; j < cbflood_n_per_burst; j++) { + cur_ops->call(&rhp[i * cbflood_n_per_burst + j], + rcu_torture_cbflood_cb); + } + schedule_timeout_interruptible(cbflood_intra_holdoff); + WARN_ON(signal_pending(current)); + } + cur_ops->cb_barrier(); + stutter_wait("rcu_torture_cbflood"); + } while (!torture_must_stop()); + vfree(rhp); + torture_kthread_stopping("rcu_torture_cbflood"); + return 0; +} + +/* + * RCU torture force-quiescent-state kthread. Repeatedly induces + * bursts of calls to force_quiescent_state(), increasing the probability + * of occurrence of some important types of race conditions. + */ +static int +rcu_torture_fqs(void *arg) +{ + unsigned long fqs_resume_time; + int fqs_burst_remaining; + + VERBOSE_TOROUT_STRING("rcu_torture_fqs task started"); + do { + fqs_resume_time = jiffies + fqs_stutter * HZ; + while (ULONG_CMP_LT(jiffies, fqs_resume_time) && + !kthread_should_stop()) { + schedule_timeout_interruptible(1); + } + fqs_burst_remaining = fqs_duration; + while (fqs_burst_remaining > 0 && + !kthread_should_stop()) { + cur_ops->fqs(); + udelay(fqs_holdoff); + fqs_burst_remaining -= fqs_holdoff; + } + stutter_wait("rcu_torture_fqs"); + } while (!torture_must_stop()); + torture_kthread_stopping("rcu_torture_fqs"); + return 0; +} + +/* + * RCU torture writer kthread. Repeatedly substitutes a new structure + * for that pointed to by rcu_torture_current, freeing the old structure + * after a series of grace periods (the "pipeline"). + */ +static int +rcu_torture_writer(void *arg) +{ + bool can_expedite = !rcu_gp_is_expedited(); + int expediting = 0; + unsigned long gp_snap; + bool gp_cond1 = gp_cond, gp_exp1 = gp_exp, gp_normal1 = gp_normal; + bool gp_sync1 = gp_sync; + int i; + struct rcu_torture *rp; + struct rcu_torture *old_rp; + static DEFINE_TORTURE_RANDOM(rand); + int synctype[] = { RTWS_DEF_FREE, RTWS_EXP_SYNC, + RTWS_COND_GET, RTWS_SYNC }; + int nsynctypes = 0; + + VERBOSE_TOROUT_STRING("rcu_torture_writer task started"); + pr_alert("%s" TORTURE_FLAG + " Grace periods expedited from boot/sysfs for %s,\n", + torture_type, cur_ops->name); + pr_alert("%s" TORTURE_FLAG + " Testing of dynamic grace-period expediting diabled.\n", + torture_type); + + /* Initialize synctype[] array. If none set, take default. */ + if (!gp_cond1 && !gp_exp1 && !gp_normal1 && !gp_sync1) + gp_cond1 = gp_exp1 = gp_normal1 = gp_sync1 = true; + if (gp_cond1 && cur_ops->get_state && cur_ops->cond_sync) + synctype[nsynctypes++] = RTWS_COND_GET; + else if (gp_cond && (!cur_ops->get_state || !cur_ops->cond_sync)) + pr_alert("rcu_torture_writer: gp_cond without primitives.\n"); + if (gp_exp1 && cur_ops->exp_sync) + synctype[nsynctypes++] = RTWS_EXP_SYNC; + else if (gp_exp && !cur_ops->exp_sync) + pr_alert("rcu_torture_writer: gp_exp without primitives.\n"); + if (gp_normal1 && cur_ops->deferred_free) + synctype[nsynctypes++] = RTWS_DEF_FREE; + else if (gp_normal && !cur_ops->deferred_free) + pr_alert("rcu_torture_writer: gp_normal without primitives.\n"); + if (gp_sync1 && cur_ops->sync) + synctype[nsynctypes++] = RTWS_SYNC; + else if (gp_sync && !cur_ops->sync) + pr_alert("rcu_torture_writer: gp_sync without primitives.\n"); + if (WARN_ONCE(nsynctypes == 0, + "rcu_torture_writer: No update-side primitives.\n")) { + /* + * No updates primitives, so don't try updating. + * The resulting test won't be testing much, hence the + * above WARN_ONCE(). + */ + rcu_torture_writer_state = RTWS_STOPPING; + torture_kthread_stopping("rcu_torture_writer"); + } + + do { + rcu_torture_writer_state = RTWS_FIXED_DELAY; + schedule_timeout_uninterruptible(1); + rp = rcu_torture_alloc(); + if (rp == NULL) + continue; + rp->rtort_pipe_count = 0; + rcu_torture_writer_state = RTWS_DELAY; + udelay(torture_random(&rand) & 0x3ff); + rcu_torture_writer_state = RTWS_REPLACE; + old_rp = rcu_dereference_check(rcu_torture_current, + current == writer_task); + rp->rtort_mbtest = 1; + rcu_assign_pointer(rcu_torture_current, rp); + smp_wmb(); /* Mods to old_rp must follow rcu_assign_pointer() */ + if (old_rp) { + i = old_rp->rtort_pipe_count; + if (i > RCU_TORTURE_PIPE_LEN) + i = RCU_TORTURE_PIPE_LEN; + atomic_inc(&rcu_torture_wcount[i]); + old_rp->rtort_pipe_count++; + switch (synctype[torture_random(&rand) % nsynctypes]) { + case RTWS_DEF_FREE: + rcu_torture_writer_state = RTWS_DEF_FREE; + cur_ops->deferred_free(old_rp); + break; + case RTWS_EXP_SYNC: + rcu_torture_writer_state = RTWS_EXP_SYNC; + cur_ops->exp_sync(); + rcu_torture_pipe_update(old_rp); + break; + case RTWS_COND_GET: + rcu_torture_writer_state = RTWS_COND_GET; + gp_snap = cur_ops->get_state(); + i = torture_random(&rand) % 16; + if (i != 0) + schedule_timeout_interruptible(i); + udelay(torture_random(&rand) % 1000); + rcu_torture_writer_state = RTWS_COND_SYNC; + cur_ops->cond_sync(gp_snap); + rcu_torture_pipe_update(old_rp); + break; + case RTWS_SYNC: + rcu_torture_writer_state = RTWS_SYNC; + cur_ops->sync(); + rcu_torture_pipe_update(old_rp); + break; + default: + WARN_ON_ONCE(1); + break; + } + } + rcutorture_record_progress(++rcu_torture_current_version); + /* Cycle through nesting levels of rcu_expedite_gp() calls. */ + if (can_expedite && + !(torture_random(&rand) & 0xff & (!!expediting - 1))) { + WARN_ON_ONCE(expediting == 0 && rcu_gp_is_expedited()); + if (expediting >= 0) + rcu_expedite_gp(); + else + rcu_unexpedite_gp(); + if (++expediting > 3) + expediting = -expediting; + } + rcu_torture_writer_state = RTWS_STUTTER; + stutter_wait("rcu_torture_writer"); + } while (!torture_must_stop()); + /* Reset expediting back to unexpedited. */ + if (expediting > 0) + expediting = -expediting; + while (can_expedite && expediting++ < 0) + rcu_unexpedite_gp(); + WARN_ON_ONCE(can_expedite && rcu_gp_is_expedited()); + rcu_torture_writer_state = RTWS_STOPPING; + torture_kthread_stopping("rcu_torture_writer"); + return 0; +} + +/* + * RCU torture fake writer kthread. Repeatedly calls sync, with a random + * delay between calls. + */ +static int +rcu_torture_fakewriter(void *arg) +{ + DEFINE_TORTURE_RANDOM(rand); + + VERBOSE_TOROUT_STRING("rcu_torture_fakewriter task started"); + set_user_nice(current, MAX_NICE); + + do { + schedule_timeout_uninterruptible(1 + torture_random(&rand)%10); + udelay(torture_random(&rand) & 0x3ff); + if (cur_ops->cb_barrier != NULL && + torture_random(&rand) % (nfakewriters * 8) == 0) { + cur_ops->cb_barrier(); + } else if (gp_normal == gp_exp) { + if (torture_random(&rand) & 0x80) + cur_ops->sync(); + else + cur_ops->exp_sync(); + } else if (gp_normal) { + cur_ops->sync(); + } else { + cur_ops->exp_sync(); + } + stutter_wait("rcu_torture_fakewriter"); + } while (!torture_must_stop()); + + torture_kthread_stopping("rcu_torture_fakewriter"); + return 0; +} + +static void rcutorture_trace_dump(void) +{ + static atomic_t beenhere = ATOMIC_INIT(0); + + if (atomic_read(&beenhere)) + return; + if (atomic_xchg(&beenhere, 1) != 0) + return; + ftrace_dump(DUMP_ALL); +} + +/* + * RCU torture reader from timer handler. Dereferences rcu_torture_current, + * incrementing the corresponding element of the pipeline array. The + * counter in the element should never be greater than 1, otherwise, the + * RCU implementation is broken. + */ +static void rcu_torture_timer(unsigned long unused) +{ + int idx; + unsigned long started; + unsigned long completed; + static DEFINE_TORTURE_RANDOM(rand); + static DEFINE_SPINLOCK(rand_lock); + struct rcu_torture *p; + int pipe_count; + unsigned long long ts; + + idx = cur_ops->readlock(); + if (cur_ops->started) + started = cur_ops->started(); + else + started = cur_ops->completed(); + ts = rcu_trace_clock_local(); + p = rcu_dereference_check(rcu_torture_current, + rcu_read_lock_bh_held() || + rcu_read_lock_sched_held() || + srcu_read_lock_held(&srcu_ctl)); + if (p == NULL) { + /* Leave because rcu_torture_writer is not yet underway */ + cur_ops->readunlock(idx); + return; + } + if (p->rtort_mbtest == 0) + atomic_inc(&n_rcu_torture_mberror); + spin_lock(&rand_lock); + cur_ops->read_delay(&rand); + n_rcu_torture_timers++; + spin_unlock(&rand_lock); + preempt_disable(); + pipe_count = p->rtort_pipe_count; + if (pipe_count > RCU_TORTURE_PIPE_LEN) { + /* Should not happen, but... */ + pipe_count = RCU_TORTURE_PIPE_LEN; + } + completed = cur_ops->completed(); + if (pipe_count > 1) { + do_trace_rcu_torture_read(cur_ops->name, &p->rtort_rcu, ts, + started, completed); + rcutorture_trace_dump(); + } + __this_cpu_inc(rcu_torture_count[pipe_count]); + completed = completed - started; + if (cur_ops->started) + completed++; + if (completed > RCU_TORTURE_PIPE_LEN) { + /* Should not happen, but... */ + completed = RCU_TORTURE_PIPE_LEN; + } + __this_cpu_inc(rcu_torture_batch[completed]); + preempt_enable(); + cur_ops->readunlock(idx); +} + +/* + * RCU torture reader kthread. Repeatedly dereferences rcu_torture_current, + * incrementing the corresponding element of the pipeline array. The + * counter in the element should never be greater than 1, otherwise, the + * RCU implementation is broken. + */ +static int +rcu_torture_reader(void *arg) +{ + unsigned long started; + unsigned long completed; + int idx; + DEFINE_TORTURE_RANDOM(rand); + struct rcu_torture *p; + int pipe_count; + struct timer_list t; + unsigned long long ts; + + VERBOSE_TOROUT_STRING("rcu_torture_reader task started"); + set_user_nice(current, MAX_NICE); + if (irqreader && cur_ops->irq_capable) + setup_timer_on_stack(&t, rcu_torture_timer, 0); + + do { + if (irqreader && cur_ops->irq_capable) { + if (!timer_pending(&t)) + mod_timer(&t, jiffies + 1); + } + idx = cur_ops->readlock(); + if (cur_ops->started) + started = cur_ops->started(); + else + started = cur_ops->completed(); + ts = rcu_trace_clock_local(); + p = rcu_dereference_check(rcu_torture_current, + rcu_read_lock_bh_held() || + rcu_read_lock_sched_held() || + srcu_read_lock_held(&srcu_ctl)); + if (p == NULL) { + /* Wait for rcu_torture_writer to get underway */ + cur_ops->readunlock(idx); + schedule_timeout_interruptible(HZ); + continue; + } + if (p->rtort_mbtest == 0) + atomic_inc(&n_rcu_torture_mberror); + cur_ops->read_delay(&rand); + preempt_disable(); + pipe_count = p->rtort_pipe_count; + if (pipe_count > RCU_TORTURE_PIPE_LEN) { + /* Should not happen, but... */ + pipe_count = RCU_TORTURE_PIPE_LEN; + } + completed = cur_ops->completed(); + if (pipe_count > 1) { + do_trace_rcu_torture_read(cur_ops->name, &p->rtort_rcu, + ts, started, completed); + rcutorture_trace_dump(); + } + __this_cpu_inc(rcu_torture_count[pipe_count]); + completed = completed - started; + if (cur_ops->started) + completed++; + if (completed > RCU_TORTURE_PIPE_LEN) { + /* Should not happen, but... */ + completed = RCU_TORTURE_PIPE_LEN; + } + __this_cpu_inc(rcu_torture_batch[completed]); + preempt_enable(); + cur_ops->readunlock(idx); + cond_resched_rcu_qs(); + stutter_wait("rcu_torture_reader"); + } while (!torture_must_stop()); + if (irqreader && cur_ops->irq_capable) { + del_timer_sync(&t); + destroy_timer_on_stack(&t); + } + torture_kthread_stopping("rcu_torture_reader"); + return 0; +} + +/* + * Print torture statistics. Caller must ensure that there is only + * one call to this function at a given time!!! This is normally + * accomplished by relying on the module system to only have one copy + * of the module loaded, and then by giving the rcu_torture_stats + * kthread full control (or the init/cleanup functions when rcu_torture_stats + * thread is not running). + */ +static void +rcu_torture_stats_print(void) +{ + int cpu; + int i; + long pipesummary[RCU_TORTURE_PIPE_LEN + 1] = { 0 }; + long batchsummary[RCU_TORTURE_PIPE_LEN + 1] = { 0 }; + static unsigned long rtcv_snap = ULONG_MAX; + + for_each_possible_cpu(cpu) { + for (i = 0; i < RCU_TORTURE_PIPE_LEN + 1; i++) { + pipesummary[i] += per_cpu(rcu_torture_count, cpu)[i]; + batchsummary[i] += per_cpu(rcu_torture_batch, cpu)[i]; + } + } + for (i = RCU_TORTURE_PIPE_LEN - 1; i >= 0; i--) { + if (pipesummary[i] != 0) + break; + } + + pr_alert("%s%s ", torture_type, TORTURE_FLAG); + pr_cont("rtc: %p ver: %lu tfle: %d rta: %d rtaf: %d rtf: %d ", + rcu_torture_current, + rcu_torture_current_version, + list_empty(&rcu_torture_freelist), + atomic_read(&n_rcu_torture_alloc), + atomic_read(&n_rcu_torture_alloc_fail), + atomic_read(&n_rcu_torture_free)); + pr_cont("rtmbe: %d rtbke: %ld rtbre: %ld ", + atomic_read(&n_rcu_torture_mberror), + n_rcu_torture_boost_ktrerror, + n_rcu_torture_boost_rterror); + pr_cont("rtbf: %ld rtb: %ld nt: %ld ", + n_rcu_torture_boost_failure, + n_rcu_torture_boosts, + n_rcu_torture_timers); + torture_onoff_stats(); + pr_cont("barrier: %ld/%ld:%ld ", + n_barrier_successes, + n_barrier_attempts, + n_rcu_torture_barrier_error); + pr_cont("cbflood: %ld\n", atomic_long_read(&n_cbfloods)); + + pr_alert("%s%s ", torture_type, TORTURE_FLAG); + if (atomic_read(&n_rcu_torture_mberror) != 0 || + n_rcu_torture_barrier_error != 0 || + n_rcu_torture_boost_ktrerror != 0 || + n_rcu_torture_boost_rterror != 0 || + n_rcu_torture_boost_failure != 0 || + i > 1) { + pr_cont("%s", "!!! "); + atomic_inc(&n_rcu_torture_error); + WARN_ON_ONCE(1); + } + pr_cont("Reader Pipe: "); + for (i = 0; i < RCU_TORTURE_PIPE_LEN + 1; i++) + pr_cont(" %ld", pipesummary[i]); + pr_cont("\n"); + + pr_alert("%s%s ", torture_type, TORTURE_FLAG); + pr_cont("Reader Batch: "); + for (i = 0; i < RCU_TORTURE_PIPE_LEN + 1; i++) + pr_cont(" %ld", batchsummary[i]); + pr_cont("\n"); + + pr_alert("%s%s ", torture_type, TORTURE_FLAG); + pr_cont("Free-Block Circulation: "); + for (i = 0; i < RCU_TORTURE_PIPE_LEN + 1; i++) { + pr_cont(" %d", atomic_read(&rcu_torture_wcount[i])); + } + pr_cont("\n"); + + if (cur_ops->stats) + cur_ops->stats(); + if (rtcv_snap == rcu_torture_current_version && + rcu_torture_current != NULL) { + int __maybe_unused flags; + unsigned long __maybe_unused gpnum; + unsigned long __maybe_unused completed; + + rcutorture_get_gp_data(cur_ops->ttype, + &flags, &gpnum, &completed); + pr_alert("??? Writer stall state %d g%lu c%lu f%#x\n", + rcu_torture_writer_state, + gpnum, completed, flags); + show_rcu_gp_kthreads(); + rcutorture_trace_dump(); + } + rtcv_snap = rcu_torture_current_version; +} + +/* + * Periodically prints torture statistics, if periodic statistics printing + * was specified via the stat_interval module parameter. + */ +static int +rcu_torture_stats(void *arg) +{ + VERBOSE_TOROUT_STRING("rcu_torture_stats task started"); + do { + schedule_timeout_interruptible(stat_interval * HZ); + rcu_torture_stats_print(); + torture_shutdown_absorb("rcu_torture_stats"); + } while (!torture_must_stop()); + torture_kthread_stopping("rcu_torture_stats"); + return 0; +} + +static inline void +rcu_torture_print_module_parms(struct rcu_torture_ops *cur_ops, const char *tag) +{ + pr_alert("%s" TORTURE_FLAG + "--- %s: nreaders=%d nfakewriters=%d " + "stat_interval=%d verbose=%d test_no_idle_hz=%d " + "shuffle_interval=%d stutter=%d irqreader=%d " + "fqs_duration=%d fqs_holdoff=%d fqs_stutter=%d " + "test_boost=%d/%d test_boost_interval=%d " + "test_boost_duration=%d shutdown_secs=%d " + "stall_cpu=%d stall_cpu_holdoff=%d " + "n_barrier_cbs=%d " + "onoff_interval=%d onoff_holdoff=%d\n", + torture_type, tag, nrealreaders, nfakewriters, + stat_interval, verbose, test_no_idle_hz, shuffle_interval, + stutter, irqreader, fqs_duration, fqs_holdoff, fqs_stutter, + test_boost, cur_ops->can_boost, + test_boost_interval, test_boost_duration, shutdown_secs, + stall_cpu, stall_cpu_holdoff, + n_barrier_cbs, + onoff_interval, onoff_holdoff); +} + +static void rcutorture_booster_cleanup(int cpu) +{ + struct task_struct *t; + + if (boost_tasks[cpu] == NULL) + return; + mutex_lock(&boost_mutex); + t = boost_tasks[cpu]; + boost_tasks[cpu] = NULL; + mutex_unlock(&boost_mutex); + + /* This must be outside of the mutex, otherwise deadlock! */ + torture_stop_kthread(rcu_torture_boost, t); +} + +static int rcutorture_booster_init(int cpu) +{ + int retval; + + if (boost_tasks[cpu] != NULL) + return 0; /* Already created, nothing more to do. */ + + /* Don't allow time recalculation while creating a new task. */ + mutex_lock(&boost_mutex); + VERBOSE_TOROUT_STRING("Creating rcu_torture_boost task"); + boost_tasks[cpu] = kthread_create_on_node(rcu_torture_boost, NULL, + cpu_to_node(cpu), + "rcu_torture_boost"); + if (IS_ERR(boost_tasks[cpu])) { + retval = PTR_ERR(boost_tasks[cpu]); + VERBOSE_TOROUT_STRING("rcu_torture_boost task create failed"); + n_rcu_torture_boost_ktrerror++; + boost_tasks[cpu] = NULL; + mutex_unlock(&boost_mutex); + return retval; + } + kthread_bind(boost_tasks[cpu], cpu); + wake_up_process(boost_tasks[cpu]); + mutex_unlock(&boost_mutex); + return 0; +} + +/* + * CPU-stall kthread. It waits as specified by stall_cpu_holdoff, then + * induces a CPU stall for the time specified by stall_cpu. + */ +static int rcu_torture_stall(void *args) +{ + unsigned long stop_at; + + VERBOSE_TOROUT_STRING("rcu_torture_stall task started"); + if (stall_cpu_holdoff > 0) { + VERBOSE_TOROUT_STRING("rcu_torture_stall begin holdoff"); + schedule_timeout_interruptible(stall_cpu_holdoff * HZ); + VERBOSE_TOROUT_STRING("rcu_torture_stall end holdoff"); + } + if (!kthread_should_stop()) { + stop_at = get_seconds() + stall_cpu; + /* RCU CPU stall is expected behavior in following code. */ + pr_alert("rcu_torture_stall start.\n"); + rcu_read_lock(); + preempt_disable(); + while (ULONG_CMP_LT(get_seconds(), stop_at)) + continue; /* Induce RCU CPU stall warning. */ + preempt_enable(); + rcu_read_unlock(); + pr_alert("rcu_torture_stall end.\n"); + } + torture_shutdown_absorb("rcu_torture_stall"); + while (!kthread_should_stop()) + schedule_timeout_interruptible(10 * HZ); + return 0; +} + +/* Spawn CPU-stall kthread, if stall_cpu specified. */ +static int __init rcu_torture_stall_init(void) +{ + if (stall_cpu <= 0) + return 0; + return torture_create_kthread(rcu_torture_stall, NULL, stall_task); +} + +/* Callback function for RCU barrier testing. */ +static void rcu_torture_barrier_cbf(struct rcu_head *rcu) +{ + atomic_inc(&barrier_cbs_invoked); +} + +/* kthread function to register callbacks used to test RCU barriers. */ +static int rcu_torture_barrier_cbs(void *arg) +{ + long myid = (long)arg; + bool lastphase = 0; + bool newphase; + struct rcu_head rcu; + + init_rcu_head_on_stack(&rcu); + VERBOSE_TOROUT_STRING("rcu_torture_barrier_cbs task started"); + set_user_nice(current, MAX_NICE); + do { + wait_event(barrier_cbs_wq[myid], + (newphase = + ACCESS_ONCE(barrier_phase)) != lastphase || + torture_must_stop()); + lastphase = newphase; + smp_mb(); /* ensure barrier_phase load before ->call(). */ + if (torture_must_stop()) + break; + cur_ops->call(&rcu, rcu_torture_barrier_cbf); + if (atomic_dec_and_test(&barrier_cbs_count)) + wake_up(&barrier_wq); + } while (!torture_must_stop()); + if (cur_ops->cb_barrier != NULL) + cur_ops->cb_barrier(); + destroy_rcu_head_on_stack(&rcu); + torture_kthread_stopping("rcu_torture_barrier_cbs"); + return 0; +} + +/* kthread function to drive and coordinate RCU barrier testing. */ +static int rcu_torture_barrier(void *arg) +{ + int i; + + VERBOSE_TOROUT_STRING("rcu_torture_barrier task starting"); + do { + atomic_set(&barrier_cbs_invoked, 0); + atomic_set(&barrier_cbs_count, n_barrier_cbs); + smp_mb(); /* Ensure barrier_phase after prior assignments. */ + barrier_phase = !barrier_phase; + for (i = 0; i < n_barrier_cbs; i++) + wake_up(&barrier_cbs_wq[i]); + wait_event(barrier_wq, + atomic_read(&barrier_cbs_count) == 0 || + torture_must_stop()); + if (torture_must_stop()) + break; + n_barrier_attempts++; + cur_ops->cb_barrier(); /* Implies smp_mb() for wait_event(). */ + if (atomic_read(&barrier_cbs_invoked) != n_barrier_cbs) { + n_rcu_torture_barrier_error++; + pr_err("barrier_cbs_invoked = %d, n_barrier_cbs = %d\n", + atomic_read(&barrier_cbs_invoked), + n_barrier_cbs); + WARN_ON_ONCE(1); + } + n_barrier_successes++; + schedule_timeout_interruptible(HZ / 10); + } while (!torture_must_stop()); + torture_kthread_stopping("rcu_torture_barrier"); + return 0; +} + +/* Initialize RCU barrier testing. */ +static int rcu_torture_barrier_init(void) +{ + int i; + int ret; + + if (n_barrier_cbs == 0) + return 0; + if (cur_ops->call == NULL || cur_ops->cb_barrier == NULL) { + pr_alert("%s" TORTURE_FLAG + " Call or barrier ops missing for %s,\n", + torture_type, cur_ops->name); + pr_alert("%s" TORTURE_FLAG + " RCU barrier testing omitted from run.\n", + torture_type); + return 0; + } + atomic_set(&barrier_cbs_count, 0); + atomic_set(&barrier_cbs_invoked, 0); + barrier_cbs_tasks = + kzalloc(n_barrier_cbs * sizeof(barrier_cbs_tasks[0]), + GFP_KERNEL); + barrier_cbs_wq = + kzalloc(n_barrier_cbs * sizeof(barrier_cbs_wq[0]), + GFP_KERNEL); + if (barrier_cbs_tasks == NULL || !barrier_cbs_wq) + return -ENOMEM; + for (i = 0; i < n_barrier_cbs; i++) { + init_waitqueue_head(&barrier_cbs_wq[i]); + ret = torture_create_kthread(rcu_torture_barrier_cbs, + (void *)(long)i, + barrier_cbs_tasks[i]); + if (ret) + return ret; + } + return torture_create_kthread(rcu_torture_barrier, NULL, barrier_task); +} + +/* Clean up after RCU barrier testing. */ +static void rcu_torture_barrier_cleanup(void) +{ + int i; + + torture_stop_kthread(rcu_torture_barrier, barrier_task); + if (barrier_cbs_tasks != NULL) { + for (i = 0; i < n_barrier_cbs; i++) + torture_stop_kthread(rcu_torture_barrier_cbs, + barrier_cbs_tasks[i]); + kfree(barrier_cbs_tasks); + barrier_cbs_tasks = NULL; + } + if (barrier_cbs_wq != NULL) { + kfree(barrier_cbs_wq); + barrier_cbs_wq = NULL; + } +} + +static int rcutorture_cpu_notify(struct notifier_block *self, + unsigned long action, void *hcpu) +{ + long cpu = (long)hcpu; + + switch (action) { + case CPU_ONLINE: + case CPU_DOWN_FAILED: + (void)rcutorture_booster_init(cpu); + break; + case CPU_DOWN_PREPARE: + rcutorture_booster_cleanup(cpu); + break; + default: + break; + } + return NOTIFY_OK; +} + +static struct notifier_block rcutorture_cpu_nb = { + .notifier_call = rcutorture_cpu_notify, +}; + +static void +rcu_torture_cleanup(void) +{ + int i; + + rcutorture_record_test_transition(); + if (torture_cleanup_begin()) { + if (cur_ops->cb_barrier != NULL) + cur_ops->cb_barrier(); + return; + } + + rcu_torture_barrier_cleanup(); + torture_stop_kthread(rcu_torture_stall, stall_task); + torture_stop_kthread(rcu_torture_writer, writer_task); + + if (reader_tasks) { + for (i = 0; i < nrealreaders; i++) + torture_stop_kthread(rcu_torture_reader, + reader_tasks[i]); + kfree(reader_tasks); + } + rcu_torture_current = NULL; + + if (fakewriter_tasks) { + for (i = 0; i < nfakewriters; i++) { + torture_stop_kthread(rcu_torture_fakewriter, + fakewriter_tasks[i]); + } + kfree(fakewriter_tasks); + fakewriter_tasks = NULL; + } + + torture_stop_kthread(rcu_torture_stats, stats_task); + torture_stop_kthread(rcu_torture_fqs, fqs_task); + for (i = 0; i < ncbflooders; i++) + torture_stop_kthread(rcu_torture_cbflood, cbflood_task[i]); + if ((test_boost == 1 && cur_ops->can_boost) || + test_boost == 2) { + unregister_cpu_notifier(&rcutorture_cpu_nb); + for_each_possible_cpu(i) + rcutorture_booster_cleanup(i); + } + + /* Wait for all RCU callbacks to fire. */ + + if (cur_ops->cb_barrier != NULL) + cur_ops->cb_barrier(); + + rcu_torture_stats_print(); /* -After- the stats thread is stopped! */ + + if (atomic_read(&n_rcu_torture_error) || n_rcu_torture_barrier_error) + rcu_torture_print_module_parms(cur_ops, "End of test: FAILURE"); + else if (torture_onoff_failures()) + rcu_torture_print_module_parms(cur_ops, + "End of test: RCU_HOTPLUG"); + else + rcu_torture_print_module_parms(cur_ops, "End of test: SUCCESS"); + torture_cleanup_end(); +} + +#ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD +static void rcu_torture_leak_cb(struct rcu_head *rhp) +{ +} + +static void rcu_torture_err_cb(struct rcu_head *rhp) +{ + /* + * This -might- happen due to race conditions, but is unlikely. + * The scenario that leads to this happening is that the + * first of the pair of duplicate callbacks is queued, + * someone else starts a grace period that includes that + * callback, then the second of the pair must wait for the + * next grace period. Unlikely, but can happen. If it + * does happen, the debug-objects subsystem won't have splatted. + */ + pr_alert("rcutorture: duplicated callback was invoked.\n"); +} +#endif /* #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD */ + +/* + * Verify that double-free causes debug-objects to complain, but only + * if CONFIG_DEBUG_OBJECTS_RCU_HEAD=y. Otherwise, say that the test + * cannot be carried out. + */ +static void rcu_test_debug_objects(void) +{ +#ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD + struct rcu_head rh1; + struct rcu_head rh2; + + init_rcu_head_on_stack(&rh1); + init_rcu_head_on_stack(&rh2); + pr_alert("rcutorture: WARN: Duplicate call_rcu() test starting.\n"); + + /* Try to queue the rh2 pair of callbacks for the same grace period. */ + preempt_disable(); /* Prevent preemption from interrupting test. */ + rcu_read_lock(); /* Make it impossible to finish a grace period. */ + call_rcu(&rh1, rcu_torture_leak_cb); /* Start grace period. */ + local_irq_disable(); /* Make it harder to start a new grace period. */ + call_rcu(&rh2, rcu_torture_leak_cb); + call_rcu(&rh2, rcu_torture_err_cb); /* Duplicate callback. */ + local_irq_enable(); + rcu_read_unlock(); + preempt_enable(); + + /* Wait for them all to get done so we can safely return. */ + rcu_barrier(); + pr_alert("rcutorture: WARN: Duplicate call_rcu() test complete.\n"); + destroy_rcu_head_on_stack(&rh1); + destroy_rcu_head_on_stack(&rh2); +#else /* #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD */ + pr_alert("rcutorture: !CONFIG_DEBUG_OBJECTS_RCU_HEAD, not testing duplicate call_rcu()\n"); +#endif /* #else #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD */ +} + +static int __init +rcu_torture_init(void) +{ + int i; + int cpu; + int firsterr = 0; + static struct rcu_torture_ops *torture_ops[] = { + &rcu_ops, &rcu_bh_ops, &rcu_busted_ops, &srcu_ops, &sched_ops, + RCUTORTURE_TASKS_OPS + }; + + if (!torture_init_begin(torture_type, verbose, &torture_runnable)) + return -EBUSY; + + /* Process args and tell the world that the torturer is on the job. */ + for (i = 0; i < ARRAY_SIZE(torture_ops); i++) { + cur_ops = torture_ops[i]; + if (strcmp(torture_type, cur_ops->name) == 0) + break; + } + if (i == ARRAY_SIZE(torture_ops)) { + pr_alert("rcu-torture: invalid torture type: \"%s\"\n", + torture_type); + pr_alert("rcu-torture types:"); + for (i = 0; i < ARRAY_SIZE(torture_ops); i++) + pr_alert(" %s", torture_ops[i]->name); + pr_alert("\n"); + torture_init_end(); + return -EINVAL; + } + if (cur_ops->fqs == NULL && fqs_duration != 0) { + pr_alert("rcu-torture: ->fqs NULL and non-zero fqs_duration, fqs disabled.\n"); + fqs_duration = 0; + } + if (cur_ops->init) + cur_ops->init(); /* no "goto unwind" prior to this point!!! */ + + if (nreaders >= 0) { + nrealreaders = nreaders; + } else { + nrealreaders = num_online_cpus() - 1; + if (nrealreaders <= 0) + nrealreaders = 1; + } + rcu_torture_print_module_parms(cur_ops, "Start of test"); + + /* Set up the freelist. */ + + INIT_LIST_HEAD(&rcu_torture_freelist); + for (i = 0; i < ARRAY_SIZE(rcu_tortures); i++) { + rcu_tortures[i].rtort_mbtest = 0; + list_add_tail(&rcu_tortures[i].rtort_free, + &rcu_torture_freelist); + } + + /* Initialize the statistics so that each run gets its own numbers. */ + + rcu_torture_current = NULL; + rcu_torture_current_version = 0; + atomic_set(&n_rcu_torture_alloc, 0); + atomic_set(&n_rcu_torture_alloc_fail, 0); + atomic_set(&n_rcu_torture_free, 0); + atomic_set(&n_rcu_torture_mberror, 0); + atomic_set(&n_rcu_torture_error, 0); + n_rcu_torture_barrier_error = 0; + n_rcu_torture_boost_ktrerror = 0; + n_rcu_torture_boost_rterror = 0; + n_rcu_torture_boost_failure = 0; + n_rcu_torture_boosts = 0; + for (i = 0; i < RCU_TORTURE_PIPE_LEN + 1; i++) + atomic_set(&rcu_torture_wcount[i], 0); + for_each_possible_cpu(cpu) { + for (i = 0; i < RCU_TORTURE_PIPE_LEN + 1; i++) { + per_cpu(rcu_torture_count, cpu)[i] = 0; + per_cpu(rcu_torture_batch, cpu)[i] = 0; + } + } + + /* Start up the kthreads. */ + + firsterr = torture_create_kthread(rcu_torture_writer, NULL, + writer_task); + if (firsterr) + goto unwind; + fakewriter_tasks = kzalloc(nfakewriters * sizeof(fakewriter_tasks[0]), + GFP_KERNEL); + if (fakewriter_tasks == NULL) { + VERBOSE_TOROUT_ERRSTRING("out of memory"); + firsterr = -ENOMEM; + goto unwind; + } + for (i = 0; i < nfakewriters; i++) { + firsterr = torture_create_kthread(rcu_torture_fakewriter, + NULL, fakewriter_tasks[i]); + if (firsterr) + goto unwind; + } + reader_tasks = kzalloc(nrealreaders * sizeof(reader_tasks[0]), + GFP_KERNEL); + if (reader_tasks == NULL) { + VERBOSE_TOROUT_ERRSTRING("out of memory"); + firsterr = -ENOMEM; + goto unwind; + } + for (i = 0; i < nrealreaders; i++) { + firsterr = torture_create_kthread(rcu_torture_reader, NULL, + reader_tasks[i]); + if (firsterr) + goto unwind; + } + if (stat_interval > 0) { + firsterr = torture_create_kthread(rcu_torture_stats, NULL, + stats_task); + if (firsterr) + goto unwind; + } + if (test_no_idle_hz) { + firsterr = torture_shuffle_init(shuffle_interval * HZ); + if (firsterr) + goto unwind; + } + if (stutter < 0) + stutter = 0; + if (stutter) { + firsterr = torture_stutter_init(stutter * HZ); + if (firsterr) + goto unwind; + } + if (fqs_duration < 0) + fqs_duration = 0; + if (fqs_duration) { + /* Create the fqs thread */ + firsterr = torture_create_kthread(rcu_torture_fqs, NULL, + fqs_task); + if (firsterr) + goto unwind; + } + if (test_boost_interval < 1) + test_boost_interval = 1; + if (test_boost_duration < 2) + test_boost_duration = 2; + if ((test_boost == 1 && cur_ops->can_boost) || + test_boost == 2) { + + boost_starttime = jiffies + test_boost_interval * HZ; + register_cpu_notifier(&rcutorture_cpu_nb); + for_each_possible_cpu(i) { + if (cpu_is_offline(i)) + continue; /* Heuristic: CPU can go offline. */ + firsterr = rcutorture_booster_init(i); + if (firsterr) + goto unwind; + } + } + firsterr = torture_shutdown_init(shutdown_secs, rcu_torture_cleanup); + if (firsterr) + goto unwind; + firsterr = torture_onoff_init(onoff_holdoff * HZ, onoff_interval * HZ); + if (firsterr) + goto unwind; + firsterr = rcu_torture_stall_init(); + if (firsterr) + goto unwind; + firsterr = rcu_torture_barrier_init(); + if (firsterr) + goto unwind; + if (object_debug) + rcu_test_debug_objects(); + if (cbflood_n_burst > 0) { + /* Create the cbflood threads */ + ncbflooders = (num_online_cpus() + 3) / 4; + cbflood_task = kcalloc(ncbflooders, sizeof(*cbflood_task), + GFP_KERNEL); + if (!cbflood_task) { + VERBOSE_TOROUT_ERRSTRING("out of memory"); + firsterr = -ENOMEM; + goto unwind; + } + for (i = 0; i < ncbflooders; i++) { + firsterr = torture_create_kthread(rcu_torture_cbflood, + NULL, + cbflood_task[i]); + if (firsterr) + goto unwind; + } + } + rcutorture_record_test_transition(); + torture_init_end(); + return 0; + +unwind: + torture_init_end(); + rcu_torture_cleanup(); + return firsterr; +} + +module_init(rcu_torture_init); +module_exit(rcu_torture_cleanup); diff --git a/kernel/kernel/rcu/srcu.c b/kernel/kernel/rcu/srcu.c new file mode 100644 index 000000000..cad76e76b --- /dev/null +++ b/kernel/kernel/rcu/srcu.c @@ -0,0 +1,676 @@ +/* + * Sleepable Read-Copy Update mechanism for mutual exclusion. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, you can access it online at + * http://www.gnu.org/licenses/gpl-2.0.html. + * + * Copyright (C) IBM Corporation, 2006 + * Copyright (C) Fujitsu, 2012 + * + * Author: Paul McKenney + * Lai Jiangshan + * + * For detailed explanation of Read-Copy Update mechanism see - + * Documentation/RCU/ *.txt + * + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "rcu.h" + +/* + * Initialize an rcu_batch structure to empty. + */ +static inline void rcu_batch_init(struct rcu_batch *b) +{ + b->head = NULL; + b->tail = &b->head; +} + +/* + * Enqueue a callback onto the tail of the specified rcu_batch structure. + */ +static inline void rcu_batch_queue(struct rcu_batch *b, struct rcu_head *head) +{ + *b->tail = head; + b->tail = &head->next; +} + +/* + * Is the specified rcu_batch structure empty? + */ +static inline bool rcu_batch_empty(struct rcu_batch *b) +{ + return b->tail == &b->head; +} + +/* + * Remove the callback at the head of the specified rcu_batch structure + * and return a pointer to it, or return NULL if the structure is empty. + */ +static inline struct rcu_head *rcu_batch_dequeue(struct rcu_batch *b) +{ + struct rcu_head *head; + + if (rcu_batch_empty(b)) + return NULL; + + head = b->head; + b->head = head->next; + if (b->tail == &head->next) + rcu_batch_init(b); + + return head; +} + +/* + * Move all callbacks from the rcu_batch structure specified by "from" to + * the structure specified by "to". + */ +static inline void rcu_batch_move(struct rcu_batch *to, struct rcu_batch *from) +{ + if (!rcu_batch_empty(from)) { + *to->tail = from->head; + to->tail = from->tail; + rcu_batch_init(from); + } +} + +static int init_srcu_struct_fields(struct srcu_struct *sp) +{ + sp->completed = 0; + spin_lock_init(&sp->queue_lock); + sp->running = false; + rcu_batch_init(&sp->batch_queue); + rcu_batch_init(&sp->batch_check0); + rcu_batch_init(&sp->batch_check1); + rcu_batch_init(&sp->batch_done); + INIT_DELAYED_WORK(&sp->work, process_srcu); + sp->per_cpu_ref = alloc_percpu(struct srcu_struct_array); + return sp->per_cpu_ref ? 0 : -ENOMEM; +} + +#ifdef CONFIG_DEBUG_LOCK_ALLOC + +int __init_srcu_struct(struct srcu_struct *sp, const char *name, + struct lock_class_key *key) +{ + /* Don't re-initialize a lock while it is held. */ + debug_check_no_locks_freed((void *)sp, sizeof(*sp)); + lockdep_init_map(&sp->dep_map, name, key, 0); + return init_srcu_struct_fields(sp); +} +EXPORT_SYMBOL_GPL(__init_srcu_struct); + +#else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ + +/** + * init_srcu_struct - initialize a sleep-RCU structure + * @sp: structure to initialize. + * + * Must invoke this on a given srcu_struct before passing that srcu_struct + * to any other function. Each srcu_struct represents a separate domain + * of SRCU protection. + */ +int init_srcu_struct(struct srcu_struct *sp) +{ + return init_srcu_struct_fields(sp); +} +EXPORT_SYMBOL_GPL(init_srcu_struct); + +#endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */ + +/* + * Returns approximate total of the readers' ->seq[] values for the + * rank of per-CPU counters specified by idx. + */ +static unsigned long srcu_readers_seq_idx(struct srcu_struct *sp, int idx) +{ + int cpu; + unsigned long sum = 0; + unsigned long t; + + for_each_possible_cpu(cpu) { + t = ACCESS_ONCE(per_cpu_ptr(sp->per_cpu_ref, cpu)->seq[idx]); + sum += t; + } + return sum; +} + +/* + * Returns approximate number of readers active on the specified rank + * of the per-CPU ->c[] counters. + */ +static unsigned long srcu_readers_active_idx(struct srcu_struct *sp, int idx) +{ + int cpu; + unsigned long sum = 0; + unsigned long t; + + for_each_possible_cpu(cpu) { + t = ACCESS_ONCE(per_cpu_ptr(sp->per_cpu_ref, cpu)->c[idx]); + sum += t; + } + return sum; +} + +/* + * Return true if the number of pre-existing readers is determined to + * be stably zero. An example unstable zero can occur if the call + * to srcu_readers_active_idx() misses an __srcu_read_lock() increment, + * but due to task migration, sees the corresponding __srcu_read_unlock() + * decrement. This can happen because srcu_readers_active_idx() takes + * time to sum the array, and might in fact be interrupted or preempted + * partway through the summation. + */ +static bool srcu_readers_active_idx_check(struct srcu_struct *sp, int idx) +{ + unsigned long seq; + + seq = srcu_readers_seq_idx(sp, idx); + + /* + * The following smp_mb() A pairs with the smp_mb() B located in + * __srcu_read_lock(). This pairing ensures that if an + * __srcu_read_lock() increments its counter after the summation + * in srcu_readers_active_idx(), then the corresponding SRCU read-side + * critical section will see any changes made prior to the start + * of the current SRCU grace period. + * + * Also, if the above call to srcu_readers_seq_idx() saw the + * increment of ->seq[], then the call to srcu_readers_active_idx() + * must see the increment of ->c[]. + */ + smp_mb(); /* A */ + + /* + * Note that srcu_readers_active_idx() can incorrectly return + * zero even though there is a pre-existing reader throughout. + * To see this, suppose that task A is in a very long SRCU + * read-side critical section that started on CPU 0, and that + * no other reader exists, so that the sum of the counters + * is equal to one. Then suppose that task B starts executing + * srcu_readers_active_idx(), summing up to CPU 1, and then that + * task C starts reading on CPU 0, so that its increment is not + * summed, but finishes reading on CPU 2, so that its decrement + * -is- summed. Then when task B completes its sum, it will + * incorrectly get zero, despite the fact that task A has been + * in its SRCU read-side critical section the whole time. + * + * We therefore do a validation step should srcu_readers_active_idx() + * return zero. + */ + if (srcu_readers_active_idx(sp, idx) != 0) + return false; + + /* + * The remainder of this function is the validation step. + * The following smp_mb() D pairs with the smp_mb() C in + * __srcu_read_unlock(). If the __srcu_read_unlock() was seen + * by srcu_readers_active_idx() above, then any destructive + * operation performed after the grace period will happen after + * the corresponding SRCU read-side critical section. + * + * Note that there can be at most NR_CPUS worth of readers using + * the old index, which is not enough to overflow even a 32-bit + * integer. (Yes, this does mean that systems having more than + * a billion or so CPUs need to be 64-bit systems.) Therefore, + * the sum of the ->seq[] counters cannot possibly overflow. + * Therefore, the only way that the return values of the two + * calls to srcu_readers_seq_idx() can be equal is if there were + * no increments of the corresponding rank of ->seq[] counts + * in the interim. But the missed-increment scenario laid out + * above includes an increment of the ->seq[] counter by + * the corresponding __srcu_read_lock(). Therefore, if this + * scenario occurs, the return values from the two calls to + * srcu_readers_seq_idx() will differ, and thus the validation + * step below suffices. + */ + smp_mb(); /* D */ + + return srcu_readers_seq_idx(sp, idx) == seq; +} + +/** + * srcu_readers_active - returns approximate number of readers. + * @sp: which srcu_struct to count active readers (holding srcu_read_lock). + * + * Note that this is not an atomic primitive, and can therefore suffer + * severe errors when invoked on an active srcu_struct. That said, it + * can be useful as an error check at cleanup time. + */ +static int srcu_readers_active(struct srcu_struct *sp) +{ + int cpu; + unsigned long sum = 0; + + for_each_possible_cpu(cpu) { + sum += ACCESS_ONCE(per_cpu_ptr(sp->per_cpu_ref, cpu)->c[0]); + sum += ACCESS_ONCE(per_cpu_ptr(sp->per_cpu_ref, cpu)->c[1]); + } + return sum; +} + +/** + * cleanup_srcu_struct - deconstruct a sleep-RCU structure + * @sp: structure to clean up. + * + * Must invoke this after you are finished using a given srcu_struct that + * was initialized via init_srcu_struct(), else you leak memory. + */ +void cleanup_srcu_struct(struct srcu_struct *sp) +{ + if (WARN_ON(srcu_readers_active(sp))) + return; /* Leakage unless caller handles error. */ + free_percpu(sp->per_cpu_ref); + sp->per_cpu_ref = NULL; +} +EXPORT_SYMBOL_GPL(cleanup_srcu_struct); + +/* + * Counts the new reader in the appropriate per-CPU element of the + * srcu_struct. Must be called from process context. + * Returns an index that must be passed to the matching srcu_read_unlock(). + */ +int __srcu_read_lock(struct srcu_struct *sp) +{ + int idx; + + idx = ACCESS_ONCE(sp->completed) & 0x1; + preempt_disable(); + __this_cpu_inc(sp->per_cpu_ref->c[idx]); + smp_mb(); /* B */ /* Avoid leaking the critical section. */ + __this_cpu_inc(sp->per_cpu_ref->seq[idx]); + preempt_enable(); + return idx; +} +EXPORT_SYMBOL_GPL(__srcu_read_lock); + +/* + * Removes the count for the old reader from the appropriate per-CPU + * element of the srcu_struct. Note that this may well be a different + * CPU than that which was incremented by the corresponding srcu_read_lock(). + * Must be called from process context. + */ +void __srcu_read_unlock(struct srcu_struct *sp, int idx) +{ + smp_mb(); /* C */ /* Avoid leaking the critical section. */ + this_cpu_dec(sp->per_cpu_ref->c[idx]); +} +EXPORT_SYMBOL_GPL(__srcu_read_unlock); + +/* + * We use an adaptive strategy for synchronize_srcu() and especially for + * synchronize_srcu_expedited(). We spin for a fixed time period + * (defined below) to allow SRCU readers to exit their read-side critical + * sections. If there are still some readers after 10 microseconds, + * we repeatedly block for 1-millisecond time periods. This approach + * has done well in testing, so there is no need for a config parameter. + */ +#define SRCU_RETRY_CHECK_DELAY 5 +#define SYNCHRONIZE_SRCU_TRYCOUNT 2 +#define SYNCHRONIZE_SRCU_EXP_TRYCOUNT 12 + +/* + * @@@ Wait until all pre-existing readers complete. Such readers + * will have used the index specified by "idx". + * the caller should ensures the ->completed is not changed while checking + * and idx = (->completed & 1) ^ 1 + */ +static bool try_check_zero(struct srcu_struct *sp, int idx, int trycount) +{ + for (;;) { + if (srcu_readers_active_idx_check(sp, idx)) + return true; + if (--trycount <= 0) + return false; + udelay(SRCU_RETRY_CHECK_DELAY); + } +} + +/* + * Increment the ->completed counter so that future SRCU readers will + * use the other rank of the ->c[] and ->seq[] arrays. This allows + * us to wait for pre-existing readers in a starvation-free manner. + */ +static void srcu_flip(struct srcu_struct *sp) +{ + sp->completed++; +} + +/* + * Enqueue an SRCU callback on the specified srcu_struct structure, + * initiating grace-period processing if it is not already running. + * + * Note that all CPUs must agree that the grace period extended beyond + * all pre-existing SRCU read-side critical section. On systems with + * more than one CPU, this means that when "func()" is invoked, each CPU + * is guaranteed to have executed a full memory barrier since the end of + * its last corresponding SRCU read-side critical section whose beginning + * preceded the call to call_rcu(). It also means that each CPU executing + * an SRCU read-side critical section that continues beyond the start of + * "func()" must have executed a memory barrier after the call_rcu() + * but before the beginning of that SRCU read-side critical section. + * Note that these guarantees include CPUs that are offline, idle, or + * executing in user mode, as well as CPUs that are executing in the kernel. + * + * Furthermore, if CPU A invoked call_rcu() and CPU B invoked the + * resulting SRCU callback function "func()", then both CPU A and CPU + * B are guaranteed to execute a full memory barrier during the time + * interval between the call to call_rcu() and the invocation of "func()". + * This guarantee applies even if CPU A and CPU B are the same CPU (but + * again only if the system has more than one CPU). + * + * Of course, these guarantees apply only for invocations of call_srcu(), + * srcu_read_lock(), and srcu_read_unlock() that are all passed the same + * srcu_struct structure. + */ +void call_srcu(struct srcu_struct *sp, struct rcu_head *head, + void (*func)(struct rcu_head *head)) +{ + unsigned long flags; + + head->next = NULL; + head->func = func; + spin_lock_irqsave(&sp->queue_lock, flags); + rcu_batch_queue(&sp->batch_queue, head); + if (!sp->running) { + sp->running = true; + queue_delayed_work(system_power_efficient_wq, &sp->work, 0); + } + spin_unlock_irqrestore(&sp->queue_lock, flags); +} +EXPORT_SYMBOL_GPL(call_srcu); + +static void srcu_advance_batches(struct srcu_struct *sp, int trycount); +static void srcu_reschedule(struct srcu_struct *sp); + +/* + * Helper function for synchronize_srcu() and synchronize_srcu_expedited(). + */ +static void __synchronize_srcu(struct srcu_struct *sp, int trycount) +{ + struct rcu_synchronize rcu; + struct rcu_head *head = &rcu.head; + bool done = false; + + rcu_lockdep_assert(!lock_is_held(&sp->dep_map) && + !lock_is_held(&rcu_bh_lock_map) && + !lock_is_held(&rcu_lock_map) && + !lock_is_held(&rcu_sched_lock_map), + "Illegal synchronize_srcu() in same-type SRCU (or RCU) read-side critical section"); + + might_sleep(); + init_completion(&rcu.completion); + + head->next = NULL; + head->func = wakeme_after_rcu; + spin_lock_irq(&sp->queue_lock); + if (!sp->running) { + /* steal the processing owner */ + sp->running = true; + rcu_batch_queue(&sp->batch_check0, head); + spin_unlock_irq(&sp->queue_lock); + + srcu_advance_batches(sp, trycount); + if (!rcu_batch_empty(&sp->batch_done)) { + BUG_ON(sp->batch_done.head != head); + rcu_batch_dequeue(&sp->batch_done); + done = true; + } + /* give the processing owner to work_struct */ + srcu_reschedule(sp); + } else { + rcu_batch_queue(&sp->batch_queue, head); + spin_unlock_irq(&sp->queue_lock); + } + + if (!done) + wait_for_completion(&rcu.completion); +} + +/** + * synchronize_srcu - wait for prior SRCU read-side critical-section completion + * @sp: srcu_struct with which to synchronize. + * + * Wait for the count to drain to zero of both indexes. To avoid the + * possible starvation of synchronize_srcu(), it waits for the count of + * the index=((->completed & 1) ^ 1) to drain to zero at first, + * and then flip the completed and wait for the count of the other index. + * + * Can block; must be called from process context. + * + * Note that it is illegal to call synchronize_srcu() from the corresponding + * SRCU read-side critical section; doing so will result in deadlock. + * However, it is perfectly legal to call synchronize_srcu() on one + * srcu_struct from some other srcu_struct's read-side critical section, + * as long as the resulting graph of srcu_structs is acyclic. + * + * There are memory-ordering constraints implied by synchronize_srcu(). + * On systems with more than one CPU, when synchronize_srcu() returns, + * each CPU is guaranteed to have executed a full memory barrier since + * the end of its last corresponding SRCU-sched read-side critical section + * whose beginning preceded the call to synchronize_srcu(). In addition, + * each CPU having an SRCU read-side critical section that extends beyond + * the return from synchronize_srcu() is guaranteed to have executed a + * full memory barrier after the beginning of synchronize_srcu() and before + * the beginning of that SRCU read-side critical section. Note that these + * guarantees include CPUs that are offline, idle, or executing in user mode, + * as well as CPUs that are executing in the kernel. + * + * Furthermore, if CPU A invoked synchronize_srcu(), which returned + * to its caller on CPU B, then both CPU A and CPU B are guaranteed + * to have executed a full memory barrier during the execution of + * synchronize_srcu(). This guarantee applies even if CPU A and CPU B + * are the same CPU, but again only if the system has more than one CPU. + * + * Of course, these memory-ordering guarantees apply only when + * synchronize_srcu(), srcu_read_lock(), and srcu_read_unlock() are + * passed the same srcu_struct structure. + */ +void synchronize_srcu(struct srcu_struct *sp) +{ + __synchronize_srcu(sp, rcu_gp_is_expedited() + ? SYNCHRONIZE_SRCU_EXP_TRYCOUNT + : SYNCHRONIZE_SRCU_TRYCOUNT); +} +EXPORT_SYMBOL_GPL(synchronize_srcu); + +/** + * synchronize_srcu_expedited - Brute-force SRCU grace period + * @sp: srcu_struct with which to synchronize. + * + * Wait for an SRCU grace period to elapse, but be more aggressive about + * spinning rather than blocking when waiting. + * + * Note that synchronize_srcu_expedited() has the same deadlock and + * memory-ordering properties as does synchronize_srcu(). + */ +void synchronize_srcu_expedited(struct srcu_struct *sp) +{ + __synchronize_srcu(sp, SYNCHRONIZE_SRCU_EXP_TRYCOUNT); +} +EXPORT_SYMBOL_GPL(synchronize_srcu_expedited); + +/** + * srcu_barrier - Wait until all in-flight call_srcu() callbacks complete. + * @sp: srcu_struct on which to wait for in-flight callbacks. + */ +void srcu_barrier(struct srcu_struct *sp) +{ + synchronize_srcu(sp); +} +EXPORT_SYMBOL_GPL(srcu_barrier); + +/** + * srcu_batches_completed - return batches completed. + * @sp: srcu_struct on which to report batch completion. + * + * Report the number of batches, correlated with, but not necessarily + * precisely the same as, the number of grace periods that have elapsed. + */ +unsigned long srcu_batches_completed(struct srcu_struct *sp) +{ + return sp->completed; +} +EXPORT_SYMBOL_GPL(srcu_batches_completed); + +#define SRCU_CALLBACK_BATCH 10 +#define SRCU_INTERVAL 1 + +/* + * Move any new SRCU callbacks to the first stage of the SRCU grace + * period pipeline. + */ +static void srcu_collect_new(struct srcu_struct *sp) +{ + if (!rcu_batch_empty(&sp->batch_queue)) { + spin_lock_irq(&sp->queue_lock); + rcu_batch_move(&sp->batch_check0, &sp->batch_queue); + spin_unlock_irq(&sp->queue_lock); + } +} + +/* + * Core SRCU state machine. Advance callbacks from ->batch_check0 to + * ->batch_check1 and then to ->batch_done as readers drain. + */ +static void srcu_advance_batches(struct srcu_struct *sp, int trycount) +{ + int idx = 1 ^ (sp->completed & 1); + + /* + * Because readers might be delayed for an extended period after + * fetching ->completed for their index, at any point in time there + * might well be readers using both idx=0 and idx=1. We therefore + * need to wait for readers to clear from both index values before + * invoking a callback. + */ + + if (rcu_batch_empty(&sp->batch_check0) && + rcu_batch_empty(&sp->batch_check1)) + return; /* no callbacks need to be advanced */ + + if (!try_check_zero(sp, idx, trycount)) + return; /* failed to advance, will try after SRCU_INTERVAL */ + + /* + * The callbacks in ->batch_check1 have already done with their + * first zero check and flip back when they were enqueued on + * ->batch_check0 in a previous invocation of srcu_advance_batches(). + * (Presumably try_check_zero() returned false during that + * invocation, leaving the callbacks stranded on ->batch_check1.) + * They are therefore ready to invoke, so move them to ->batch_done. + */ + rcu_batch_move(&sp->batch_done, &sp->batch_check1); + + if (rcu_batch_empty(&sp->batch_check0)) + return; /* no callbacks need to be advanced */ + srcu_flip(sp); + + /* + * The callbacks in ->batch_check0 just finished their + * first check zero and flip, so move them to ->batch_check1 + * for future checking on the other idx. + */ + rcu_batch_move(&sp->batch_check1, &sp->batch_check0); + + /* + * SRCU read-side critical sections are normally short, so check + * at least twice in quick succession after a flip. + */ + trycount = trycount < 2 ? 2 : trycount; + if (!try_check_zero(sp, idx^1, trycount)) + return; /* failed to advance, will try after SRCU_INTERVAL */ + + /* + * The callbacks in ->batch_check1 have now waited for all + * pre-existing readers using both idx values. They are therefore + * ready to invoke, so move them to ->batch_done. + */ + rcu_batch_move(&sp->batch_done, &sp->batch_check1); +} + +/* + * Invoke a limited number of SRCU callbacks that have passed through + * their grace period. If there are more to do, SRCU will reschedule + * the workqueue. + */ +static void srcu_invoke_callbacks(struct srcu_struct *sp) +{ + int i; + struct rcu_head *head; + + for (i = 0; i < SRCU_CALLBACK_BATCH; i++) { + head = rcu_batch_dequeue(&sp->batch_done); + if (!head) + break; + local_bh_disable(); + head->func(head); + local_bh_enable(); + } +} + +/* + * Finished one round of SRCU grace period. Start another if there are + * more SRCU callbacks queued, otherwise put SRCU into not-running state. + */ +static void srcu_reschedule(struct srcu_struct *sp) +{ + bool pending = true; + + if (rcu_batch_empty(&sp->batch_done) && + rcu_batch_empty(&sp->batch_check1) && + rcu_batch_empty(&sp->batch_check0) && + rcu_batch_empty(&sp->batch_queue)) { + spin_lock_irq(&sp->queue_lock); + if (rcu_batch_empty(&sp->batch_done) && + rcu_batch_empty(&sp->batch_check1) && + rcu_batch_empty(&sp->batch_check0) && + rcu_batch_empty(&sp->batch_queue)) { + sp->running = false; + pending = false; + } + spin_unlock_irq(&sp->queue_lock); + } + + if (pending) + queue_delayed_work(system_power_efficient_wq, + &sp->work, SRCU_INTERVAL); +} + +/* + * This is the work-queue function that handles SRCU grace periods. + */ +void process_srcu(struct work_struct *work) +{ + struct srcu_struct *sp; + + sp = container_of(work, struct srcu_struct, work.work); + + srcu_collect_new(sp); + srcu_advance_batches(sp, 1); + srcu_invoke_callbacks(sp); + srcu_reschedule(sp); +} +EXPORT_SYMBOL_GPL(process_srcu); diff --git a/kernel/kernel/rcu/tiny.c b/kernel/kernel/rcu/tiny.c new file mode 100644 index 000000000..ec3086879 --- /dev/null +++ b/kernel/kernel/rcu/tiny.c @@ -0,0 +1,288 @@ +/* + * Read-Copy Update mechanism for mutual exclusion, the Bloatwatch edition. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, you can access it online at + * http://www.gnu.org/licenses/gpl-2.0.html. + * + * Copyright IBM Corporation, 2008 + * + * Author: Paul E. McKenney + * + * For detailed explanation of Read-Copy Update mechanism see - + * Documentation/RCU + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "rcu.h" + +/* Forward declarations for tiny_plugin.h. */ +struct rcu_ctrlblk; +static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp); +static void rcu_process_callbacks(struct softirq_action *unused); +static void __call_rcu(struct rcu_head *head, + void (*func)(struct rcu_head *rcu), + struct rcu_ctrlblk *rcp); + +#include "tiny_plugin.h" + +/* + * Enter idle, which is an extended quiescent state if we have fully + * entered that mode. + */ +void rcu_idle_enter(void) +{ +} +EXPORT_SYMBOL_GPL(rcu_idle_enter); + +/* + * Exit an interrupt handler towards idle. + */ +void rcu_irq_exit(void) +{ +} +EXPORT_SYMBOL_GPL(rcu_irq_exit); + +/* + * Exit idle, so that we are no longer in an extended quiescent state. + */ +void rcu_idle_exit(void) +{ +} +EXPORT_SYMBOL_GPL(rcu_idle_exit); + +/* + * Enter an interrupt handler, moving away from idle. + */ +void rcu_irq_enter(void) +{ +} +EXPORT_SYMBOL_GPL(rcu_irq_enter); + +#if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE) + +/* + * Test whether RCU thinks that the current CPU is idle. + */ +bool notrace __rcu_is_watching(void) +{ + return true; +} +EXPORT_SYMBOL(__rcu_is_watching); + +#endif /* defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE) */ + +/* + * Helper function for rcu_sched_qs() and rcu_bh_qs(). + * Also irqs are disabled to avoid confusion due to interrupt handlers + * invoking call_rcu(). + */ +static int rcu_qsctr_help(struct rcu_ctrlblk *rcp) +{ + RCU_TRACE(reset_cpu_stall_ticks(rcp)); + if (rcp->donetail != rcp->curtail) { + rcp->donetail = rcp->curtail; + return 1; + } + + return 0; +} + +/* + * Record an rcu quiescent state. And an rcu_bh quiescent state while we + * are at it, given that any rcu quiescent state is also an rcu_bh + * quiescent state. Use "+" instead of "||" to defeat short circuiting. + */ +void rcu_sched_qs(void) +{ + unsigned long flags; + + local_irq_save(flags); + if (rcu_qsctr_help(&rcu_sched_ctrlblk) + + rcu_qsctr_help(&rcu_bh_ctrlblk)) + raise_softirq(RCU_SOFTIRQ); + local_irq_restore(flags); +} + +/* + * Record an rcu_bh quiescent state. + */ +void rcu_bh_qs(void) +{ + unsigned long flags; + + local_irq_save(flags); + if (rcu_qsctr_help(&rcu_bh_ctrlblk)) + raise_softirq(RCU_SOFTIRQ); + local_irq_restore(flags); +} + +/* + * Check to see if the scheduling-clock interrupt came from an extended + * quiescent state, and, if so, tell RCU about it. This function must + * be called from hardirq context. It is normally called from the + * scheduling-clock interrupt. + */ +void rcu_check_callbacks(int user) +{ + RCU_TRACE(check_cpu_stalls()); + if (user) + rcu_sched_qs(); + else if (!in_softirq()) + rcu_bh_qs(); + if (user) + rcu_note_voluntary_context_switch(current); +} + +/* + * Invoke the RCU callbacks on the specified rcu_ctrlkblk structure + * whose grace period has elapsed. + */ +static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp) +{ + const char *rn = NULL; + struct rcu_head *next, *list; + unsigned long flags; + RCU_TRACE(int cb_count = 0); + + /* Move the ready-to-invoke callbacks to a local list. */ + local_irq_save(flags); + if (rcp->donetail == &rcp->rcucblist) { + /* No callbacks ready, so just leave. */ + local_irq_restore(flags); + return; + } + RCU_TRACE(trace_rcu_batch_start(rcp->name, 0, rcp->qlen, -1)); + list = rcp->rcucblist; + rcp->rcucblist = *rcp->donetail; + *rcp->donetail = NULL; + if (rcp->curtail == rcp->donetail) + rcp->curtail = &rcp->rcucblist; + rcp->donetail = &rcp->rcucblist; + local_irq_restore(flags); + + /* Invoke the callbacks on the local list. */ + RCU_TRACE(rn = rcp->name); + while (list) { + next = list->next; + prefetch(next); + debug_rcu_head_unqueue(list); + local_bh_disable(); + __rcu_reclaim(rn, list); + local_bh_enable(); + list = next; + RCU_TRACE(cb_count++); + } + RCU_TRACE(rcu_trace_sub_qlen(rcp, cb_count)); + RCU_TRACE(trace_rcu_batch_end(rcp->name, + cb_count, 0, need_resched(), + is_idle_task(current), + false)); +} + +static void rcu_process_callbacks(struct softirq_action *unused) +{ + __rcu_process_callbacks(&rcu_sched_ctrlblk); + __rcu_process_callbacks(&rcu_bh_ctrlblk); +} + +/* + * Wait for a grace period to elapse. But it is illegal to invoke + * synchronize_sched() from within an RCU read-side critical section. + * Therefore, any legal call to synchronize_sched() is a quiescent + * state, and so on a UP system, synchronize_sched() need do nothing. + * Ditto for synchronize_rcu_bh(). (But Lai Jiangshan points out the + * benefits of doing might_sleep() to reduce latency.) + * + * Cool, huh? (Due to Josh Triplett.) + * + * But we want to make this a static inline later. The cond_resched() + * currently makes this problematic. + */ +void synchronize_sched(void) +{ + rcu_lockdep_assert(!lock_is_held(&rcu_bh_lock_map) && + !lock_is_held(&rcu_lock_map) && + !lock_is_held(&rcu_sched_lock_map), + "Illegal synchronize_sched() in RCU read-side critical section"); + cond_resched(); +} +EXPORT_SYMBOL_GPL(synchronize_sched); + +/* + * Helper function for call_rcu() and call_rcu_bh(). + */ +static void __call_rcu(struct rcu_head *head, + void (*func)(struct rcu_head *rcu), + struct rcu_ctrlblk *rcp) +{ + unsigned long flags; + + debug_rcu_head_queue(head); + head->func = func; + head->next = NULL; + + local_irq_save(flags); + *rcp->curtail = head; + rcp->curtail = &head->next; + RCU_TRACE(rcp->qlen++); + local_irq_restore(flags); + + if (unlikely(is_idle_task(current))) { + /* force scheduling for rcu_sched_qs() */ + resched_cpu(0); + } +} + +/* + * Post an RCU callback to be invoked after the end of an RCU-sched grace + * period. But since we have but one CPU, that would be after any + * quiescent state. + */ +void call_rcu_sched(struct rcu_head *head, void (*func)(struct rcu_head *rcu)) +{ + __call_rcu(head, func, &rcu_sched_ctrlblk); +} +EXPORT_SYMBOL_GPL(call_rcu_sched); + +/* + * Post an RCU bottom-half callback to be invoked after any subsequent + * quiescent state. + */ +void call_rcu_bh(struct rcu_head *head, void (*func)(struct rcu_head *rcu)) +{ + __call_rcu(head, func, &rcu_bh_ctrlblk); +} +EXPORT_SYMBOL_GPL(call_rcu_bh); + +void __init rcu_init(void) +{ + open_softirq(RCU_SOFTIRQ, rcu_process_callbacks); + RCU_TRACE(reset_cpu_stall_ticks(&rcu_sched_ctrlblk)); + RCU_TRACE(reset_cpu_stall_ticks(&rcu_bh_ctrlblk)); + + rcu_early_boot_tests(); +} diff --git a/kernel/kernel/rcu/tiny_plugin.h b/kernel/kernel/rcu/tiny_plugin.h new file mode 100644 index 000000000..f94e209a1 --- /dev/null +++ b/kernel/kernel/rcu/tiny_plugin.h @@ -0,0 +1,173 @@ +/* + * Read-Copy Update mechanism for mutual exclusion, the Bloatwatch edition + * Internal non-public definitions that provide either classic + * or preemptible semantics. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, you can access it online at + * http://www.gnu.org/licenses/gpl-2.0.html. + * + * Copyright (c) 2010 Linaro + * + * Author: Paul E. McKenney + */ + +#include +#include +#include +#include + +/* Global control variables for rcupdate callback mechanism. */ +struct rcu_ctrlblk { + struct rcu_head *rcucblist; /* List of pending callbacks (CBs). */ + struct rcu_head **donetail; /* ->next pointer of last "done" CB. */ + struct rcu_head **curtail; /* ->next pointer of last CB. */ + RCU_TRACE(long qlen); /* Number of pending CBs. */ + RCU_TRACE(unsigned long gp_start); /* Start time for stalls. */ + RCU_TRACE(unsigned long ticks_this_gp); /* Statistic for stalls. */ + RCU_TRACE(unsigned long jiffies_stall); /* Jiffies at next stall. */ + RCU_TRACE(const char *name); /* Name of RCU type. */ +}; + +/* Definition for rcupdate control block. */ +static struct rcu_ctrlblk rcu_sched_ctrlblk = { + .donetail = &rcu_sched_ctrlblk.rcucblist, + .curtail = &rcu_sched_ctrlblk.rcucblist, + RCU_TRACE(.name = "rcu_sched") +}; + +static struct rcu_ctrlblk rcu_bh_ctrlblk = { + .donetail = &rcu_bh_ctrlblk.rcucblist, + .curtail = &rcu_bh_ctrlblk.rcucblist, + RCU_TRACE(.name = "rcu_bh") +}; + +#ifdef CONFIG_DEBUG_LOCK_ALLOC +#include + +int rcu_scheduler_active __read_mostly; +EXPORT_SYMBOL_GPL(rcu_scheduler_active); + +/* + * During boot, we forgive RCU lockdep issues. After this function is + * invoked, we start taking RCU lockdep issues seriously. + */ +void __init rcu_scheduler_starting(void) +{ + WARN_ON(nr_context_switches() > 0); + rcu_scheduler_active = 1; +} + +#endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ + +#ifdef CONFIG_RCU_TRACE + +static void rcu_trace_sub_qlen(struct rcu_ctrlblk *rcp, int n) +{ + unsigned long flags; + + local_irq_save(flags); + rcp->qlen -= n; + local_irq_restore(flags); +} + +/* + * Dump statistics for TINY_RCU, such as they are. + */ +static int show_tiny_stats(struct seq_file *m, void *unused) +{ + seq_printf(m, "rcu_sched: qlen: %ld\n", rcu_sched_ctrlblk.qlen); + seq_printf(m, "rcu_bh: qlen: %ld\n", rcu_bh_ctrlblk.qlen); + return 0; +} + +static int show_tiny_stats_open(struct inode *inode, struct file *file) +{ + return single_open(file, show_tiny_stats, NULL); +} + +static const struct file_operations show_tiny_stats_fops = { + .owner = THIS_MODULE, + .open = show_tiny_stats_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static struct dentry *rcudir; + +static int __init rcutiny_trace_init(void) +{ + struct dentry *retval; + + rcudir = debugfs_create_dir("rcu", NULL); + if (!rcudir) + goto free_out; + retval = debugfs_create_file("rcudata", 0444, rcudir, + NULL, &show_tiny_stats_fops); + if (!retval) + goto free_out; + return 0; +free_out: + debugfs_remove_recursive(rcudir); + return 1; +} + +static void __exit rcutiny_trace_cleanup(void) +{ + debugfs_remove_recursive(rcudir); +} + +module_init(rcutiny_trace_init); +module_exit(rcutiny_trace_cleanup); + +MODULE_AUTHOR("Paul E. McKenney"); +MODULE_DESCRIPTION("Read-Copy Update tracing for tiny implementation"); +MODULE_LICENSE("GPL"); + +static void check_cpu_stall(struct rcu_ctrlblk *rcp) +{ + unsigned long j; + unsigned long js; + + if (rcu_cpu_stall_suppress) + return; + rcp->ticks_this_gp++; + j = jiffies; + js = ACCESS_ONCE(rcp->jiffies_stall); + if (rcp->rcucblist && ULONG_CMP_GE(j, js)) { + pr_err("INFO: %s stall on CPU (%lu ticks this GP) idle=%llx (t=%lu jiffies q=%ld)\n", + rcp->name, rcp->ticks_this_gp, DYNTICK_TASK_EXIT_IDLE, + jiffies - rcp->gp_start, rcp->qlen); + dump_stack(); + ACCESS_ONCE(rcp->jiffies_stall) = jiffies + + 3 * rcu_jiffies_till_stall_check() + 3; + } else if (ULONG_CMP_GE(j, js)) { + ACCESS_ONCE(rcp->jiffies_stall) = jiffies + rcu_jiffies_till_stall_check(); + } +} + +static void reset_cpu_stall_ticks(struct rcu_ctrlblk *rcp) +{ + rcp->ticks_this_gp = 0; + rcp->gp_start = jiffies; + ACCESS_ONCE(rcp->jiffies_stall) = jiffies + rcu_jiffies_till_stall_check(); +} + +static void check_cpu_stalls(void) +{ + RCU_TRACE(check_cpu_stall(&rcu_bh_ctrlblk)); + RCU_TRACE(check_cpu_stall(&rcu_sched_ctrlblk)); +} + +#endif /* #ifdef CONFIG_RCU_TRACE */ diff --git a/kernel/kernel/rcu/tree.c b/kernel/kernel/rcu/tree.c new file mode 100644 index 000000000..965df22d9 --- /dev/null +++ b/kernel/kernel/rcu/tree.c @@ -0,0 +1,4254 @@ +/* + * Read-Copy Update mechanism for mutual exclusion + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, you can access it online at + * http://www.gnu.org/licenses/gpl-2.0.html. + * + * Copyright IBM Corporation, 2008 + * + * Authors: Dipankar Sarma + * Manfred Spraul + * Paul E. McKenney Hierarchical version + * + * Based on the original work by Paul McKenney + * and inputs from Rusty Russell, Andrea Arcangeli and Andi Kleen. + * + * For detailed explanation of Read-Copy Update mechanism see - + * Documentation/RCU + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include "../time/tick-internal.h" + +#include "tree.h" +#include "rcu.h" + +MODULE_ALIAS("rcutree"); +#ifdef MODULE_PARAM_PREFIX +#undef MODULE_PARAM_PREFIX +#endif +#define MODULE_PARAM_PREFIX "rcutree." + +/* Data structures. */ + +static struct lock_class_key rcu_node_class[RCU_NUM_LVLS]; +static struct lock_class_key rcu_fqs_class[RCU_NUM_LVLS]; + +/* + * In order to export the rcu_state name to the tracing tools, it + * needs to be added in the __tracepoint_string section. + * This requires defining a separate variable tp__varname + * that points to the string being used, and this will allow + * the tracing userspace tools to be able to decipher the string + * address to the matching string. + */ +#ifdef CONFIG_TRACING +# define DEFINE_RCU_TPS(sname) \ +static char sname##_varname[] = #sname; \ +static const char *tp_##sname##_varname __used __tracepoint_string = sname##_varname; +# define RCU_STATE_NAME(sname) sname##_varname +#else +# define DEFINE_RCU_TPS(sname) +# define RCU_STATE_NAME(sname) __stringify(sname) +#endif + +#define RCU_STATE_INITIALIZER(sname, sabbr, cr) \ +DEFINE_RCU_TPS(sname) \ +DEFINE_PER_CPU_SHARED_ALIGNED(struct rcu_data, sname##_data); \ +struct rcu_state sname##_state = { \ + .level = { &sname##_state.node[0] }, \ + .rda = &sname##_data, \ + .call = cr, \ + .fqs_state = RCU_GP_IDLE, \ + .gpnum = 0UL - 300UL, \ + .completed = 0UL - 300UL, \ + .orphan_lock = __RAW_SPIN_LOCK_UNLOCKED(&sname##_state.orphan_lock), \ + .orphan_nxttail = &sname##_state.orphan_nxtlist, \ + .orphan_donetail = &sname##_state.orphan_donelist, \ + .barrier_mutex = __MUTEX_INITIALIZER(sname##_state.barrier_mutex), \ + .name = RCU_STATE_NAME(sname), \ + .abbr = sabbr, \ +} + +RCU_STATE_INITIALIZER(rcu_sched, 's', call_rcu_sched); +RCU_STATE_INITIALIZER(rcu_bh, 'b', call_rcu_bh); + +static struct rcu_state *rcu_state_p; +LIST_HEAD(rcu_struct_flavors); + +/* Increase (but not decrease) the CONFIG_RCU_FANOUT_LEAF at boot time. */ +static int rcu_fanout_leaf = CONFIG_RCU_FANOUT_LEAF; +module_param(rcu_fanout_leaf, int, 0444); +int rcu_num_lvls __read_mostly = RCU_NUM_LVLS; +static int num_rcu_lvl[] = { /* Number of rcu_nodes at specified level. */ + NUM_RCU_LVL_0, + NUM_RCU_LVL_1, + NUM_RCU_LVL_2, + NUM_RCU_LVL_3, + NUM_RCU_LVL_4, +}; +int rcu_num_nodes __read_mostly = NUM_RCU_NODES; /* Total # rcu_nodes in use. */ + +/* + * The rcu_scheduler_active variable transitions from zero to one just + * before the first task is spawned. So when this variable is zero, RCU + * can assume that there is but one task, allowing RCU to (for example) + * optimize synchronize_sched() to a simple barrier(). When this variable + * is one, RCU must actually do all the hard work required to detect real + * grace periods. This variable is also used to suppress boot-time false + * positives from lockdep-RCU error checking. + */ +int rcu_scheduler_active __read_mostly; +EXPORT_SYMBOL_GPL(rcu_scheduler_active); + +/* + * The rcu_scheduler_fully_active variable transitions from zero to one + * during the early_initcall() processing, which is after the scheduler + * is capable of creating new tasks. So RCU processing (for example, + * creating tasks for RCU priority boosting) must be delayed until after + * rcu_scheduler_fully_active transitions from zero to one. We also + * currently delay invocation of any RCU callbacks until after this point. + * + * It might later prove better for people registering RCU callbacks during + * early boot to take responsibility for these callbacks, but one step at + * a time. + */ +static int rcu_scheduler_fully_active __read_mostly; + +static void rcu_init_new_rnp(struct rcu_node *rnp_leaf); +static void rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf); +static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu); +static void invoke_rcu_core(void); +static void invoke_rcu_callbacks(struct rcu_state *rsp, struct rcu_data *rdp); + +/* rcuc/rcub kthread realtime priority */ +static int kthread_prio = CONFIG_RCU_KTHREAD_PRIO; +module_param(kthread_prio, int, 0644); + +/* Delay in jiffies for grace-period initialization delays, debug only. */ +#ifdef CONFIG_RCU_TORTURE_TEST_SLOW_INIT +static int gp_init_delay = CONFIG_RCU_TORTURE_TEST_SLOW_INIT_DELAY; +module_param(gp_init_delay, int, 0644); +#else /* #ifdef CONFIG_RCU_TORTURE_TEST_SLOW_INIT */ +static const int gp_init_delay; +#endif /* #else #ifdef CONFIG_RCU_TORTURE_TEST_SLOW_INIT */ +#define PER_RCU_NODE_PERIOD 10 /* Number of grace periods between delays. */ + +/* + * Track the rcutorture test sequence number and the update version + * number within a given test. The rcutorture_testseq is incremented + * on every rcutorture module load and unload, so has an odd value + * when a test is running. The rcutorture_vernum is set to zero + * when rcutorture starts and is incremented on each rcutorture update. + * These variables enable correlating rcutorture output with the + * RCU tracing information. + */ +unsigned long rcutorture_testseq; +unsigned long rcutorture_vernum; + +/* + * Compute the mask of online CPUs for the specified rcu_node structure. + * This will not be stable unless the rcu_node structure's ->lock is + * held, but the bit corresponding to the current CPU will be stable + * in most contexts. + */ +unsigned long rcu_rnp_online_cpus(struct rcu_node *rnp) +{ + return ACCESS_ONCE(rnp->qsmaskinitnext); +} + +/* + * Return true if an RCU grace period is in progress. The ACCESS_ONCE()s + * permit this function to be invoked without holding the root rcu_node + * structure's ->lock, but of course results can be subject to change. + */ +static int rcu_gp_in_progress(struct rcu_state *rsp) +{ + return ACCESS_ONCE(rsp->completed) != ACCESS_ONCE(rsp->gpnum); +} + +/* + * Note a quiescent state. Because we do not need to know + * how many quiescent states passed, just if there was at least + * one since the start of the grace period, this just sets a flag. + * The caller must have disabled preemption. + */ +void rcu_sched_qs(void) +{ + if (!__this_cpu_read(rcu_sched_data.passed_quiesce)) { + trace_rcu_grace_period(TPS("rcu_sched"), + __this_cpu_read(rcu_sched_data.gpnum), + TPS("cpuqs")); + __this_cpu_write(rcu_sched_data.passed_quiesce, 1); + } +} + +#ifdef CONFIG_PREEMPT_RT_FULL +static void rcu_preempt_qs(void); + +void rcu_bh_qs(void) +{ + unsigned long flags; + + /* Callers to this function, rcu_preempt_qs(), must disable irqs. */ + local_irq_save(flags); + rcu_preempt_qs(); + local_irq_restore(flags); +} +#else +void rcu_bh_qs(void) +{ + if (!__this_cpu_read(rcu_bh_data.passed_quiesce)) { + trace_rcu_grace_period(TPS("rcu_bh"), + __this_cpu_read(rcu_bh_data.gpnum), + TPS("cpuqs")); + __this_cpu_write(rcu_bh_data.passed_quiesce, 1); + } +} +#endif + +static DEFINE_PER_CPU(int, rcu_sched_qs_mask); + +static DEFINE_PER_CPU(struct rcu_dynticks, rcu_dynticks) = { + .dynticks_nesting = DYNTICK_TASK_EXIT_IDLE, + .dynticks = ATOMIC_INIT(1), +#ifdef CONFIG_NO_HZ_FULL_SYSIDLE + .dynticks_idle_nesting = DYNTICK_TASK_NEST_VALUE, + .dynticks_idle = ATOMIC_INIT(1), +#endif /* #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */ +}; + +DEFINE_PER_CPU_SHARED_ALIGNED(unsigned long, rcu_qs_ctr); +EXPORT_PER_CPU_SYMBOL_GPL(rcu_qs_ctr); + +/* + * Let the RCU core know that this CPU has gone through the scheduler, + * which is a quiescent state. This is called when the need for a + * quiescent state is urgent, so we burn an atomic operation and full + * memory barriers to let the RCU core know about it, regardless of what + * this CPU might (or might not) do in the near future. + * + * We inform the RCU core by emulating a zero-duration dyntick-idle + * period, which we in turn do by incrementing the ->dynticks counter + * by two. + */ +static void rcu_momentary_dyntick_idle(void) +{ + unsigned long flags; + struct rcu_data *rdp; + struct rcu_dynticks *rdtp; + int resched_mask; + struct rcu_state *rsp; + + local_irq_save(flags); + + /* + * Yes, we can lose flag-setting operations. This is OK, because + * the flag will be set again after some delay. + */ + resched_mask = raw_cpu_read(rcu_sched_qs_mask); + raw_cpu_write(rcu_sched_qs_mask, 0); + + /* Find the flavor that needs a quiescent state. */ + for_each_rcu_flavor(rsp) { + rdp = raw_cpu_ptr(rsp->rda); + if (!(resched_mask & rsp->flavor_mask)) + continue; + smp_mb(); /* rcu_sched_qs_mask before cond_resched_completed. */ + if (ACCESS_ONCE(rdp->mynode->completed) != + ACCESS_ONCE(rdp->cond_resched_completed)) + continue; + + /* + * Pretend to be momentarily idle for the quiescent state. + * This allows the grace-period kthread to record the + * quiescent state, with no need for this CPU to do anything + * further. + */ + rdtp = this_cpu_ptr(&rcu_dynticks); + smp_mb__before_atomic(); /* Earlier stuff before QS. */ + atomic_add(2, &rdtp->dynticks); /* QS. */ + smp_mb__after_atomic(); /* Later stuff after QS. */ + break; + } + local_irq_restore(flags); +} + +/* + * Note a context switch. This is a quiescent state for RCU-sched, + * and requires special handling for preemptible RCU. + * The caller must have disabled preemption. + */ +void rcu_note_context_switch(void) +{ + trace_rcu_utilization(TPS("Start context switch")); + rcu_sched_qs(); + rcu_preempt_note_context_switch(); + if (unlikely(raw_cpu_read(rcu_sched_qs_mask))) + rcu_momentary_dyntick_idle(); + trace_rcu_utilization(TPS("End context switch")); +} +EXPORT_SYMBOL_GPL(rcu_note_context_switch); + +/* + * Register a quiescent state for all RCU flavors. If there is an + * emergency, invoke rcu_momentary_dyntick_idle() to do a heavy-weight + * dyntick-idle quiescent state visible to other CPUs (but only for those + * RCU flavors in desperate need of a quiescent state, which will normally + * be none of them). Either way, do a lightweight quiescent state for + * all RCU flavors. + */ +void rcu_all_qs(void) +{ + if (unlikely(raw_cpu_read(rcu_sched_qs_mask))) + rcu_momentary_dyntick_idle(); + this_cpu_inc(rcu_qs_ctr); +} +EXPORT_SYMBOL_GPL(rcu_all_qs); + +static long blimit = 10; /* Maximum callbacks per rcu_do_batch. */ +static long qhimark = 10000; /* If this many pending, ignore blimit. */ +static long qlowmark = 100; /* Once only this many pending, use blimit. */ + +module_param(blimit, long, 0444); +module_param(qhimark, long, 0444); +module_param(qlowmark, long, 0444); + +static ulong jiffies_till_first_fqs = ULONG_MAX; +static ulong jiffies_till_next_fqs = ULONG_MAX; + +module_param(jiffies_till_first_fqs, ulong, 0644); +module_param(jiffies_till_next_fqs, ulong, 0644); + +/* + * How long the grace period must be before we start recruiting + * quiescent-state help from rcu_note_context_switch(). + */ +static ulong jiffies_till_sched_qs = HZ / 20; +module_param(jiffies_till_sched_qs, ulong, 0644); + +static bool rcu_start_gp_advanced(struct rcu_state *rsp, struct rcu_node *rnp, + struct rcu_data *rdp); +static void force_qs_rnp(struct rcu_state *rsp, + int (*f)(struct rcu_data *rsp, bool *isidle, + unsigned long *maxj), + bool *isidle, unsigned long *maxj); +static void force_quiescent_state(struct rcu_state *rsp); +static int rcu_pending(void); + +/* + * Return the number of RCU batches started thus far for debug & stats. + */ +unsigned long rcu_batches_started(void) +{ + return rcu_state_p->gpnum; +} +EXPORT_SYMBOL_GPL(rcu_batches_started); + +/* + * Return the number of RCU-sched batches started thus far for debug & stats. + */ +unsigned long rcu_batches_started_sched(void) +{ + return rcu_sched_state.gpnum; +} +EXPORT_SYMBOL_GPL(rcu_batches_started_sched); + +/* + * Return the number of RCU BH batches started thus far for debug & stats. + */ +unsigned long rcu_batches_started_bh(void) +{ + return rcu_bh_state.gpnum; +} +EXPORT_SYMBOL_GPL(rcu_batches_started_bh); + +/* + * Return the number of RCU batches completed thus far for debug & stats. + */ +unsigned long rcu_batches_completed(void) +{ + return rcu_state_p->completed; +} +EXPORT_SYMBOL_GPL(rcu_batches_completed); + +/* + * Return the number of RCU-sched batches completed thus far for debug & stats. + */ +unsigned long rcu_batches_completed_sched(void) +{ + return rcu_sched_state.completed; +} +EXPORT_SYMBOL_GPL(rcu_batches_completed_sched); + +#ifndef CONFIG_PREEMPT_RT_FULL +/* + * Return the number of RCU BH batches completed thus far for debug & stats. + */ +unsigned long rcu_batches_completed_bh(void) +{ + return rcu_bh_state.completed; +} +EXPORT_SYMBOL_GPL(rcu_batches_completed_bh); + +/* + * Force a quiescent state. + */ +void rcu_force_quiescent_state(void) +{ + force_quiescent_state(rcu_state_p); +} +EXPORT_SYMBOL_GPL(rcu_force_quiescent_state); + +/* + * Force a quiescent state for RCU BH. + */ +void rcu_bh_force_quiescent_state(void) +{ + force_quiescent_state(&rcu_bh_state); +} +EXPORT_SYMBOL_GPL(rcu_bh_force_quiescent_state); + +#else +void rcu_force_quiescent_state(void) +{ +} +EXPORT_SYMBOL_GPL(rcu_force_quiescent_state); +#endif + +/* + * Force a quiescent state for RCU-sched. + */ +void rcu_sched_force_quiescent_state(void) +{ + force_quiescent_state(&rcu_sched_state); +} +EXPORT_SYMBOL_GPL(rcu_sched_force_quiescent_state); + +/* + * Show the state of the grace-period kthreads. + */ +void show_rcu_gp_kthreads(void) +{ + struct rcu_state *rsp; + + for_each_rcu_flavor(rsp) { + pr_info("%s: wait state: %d ->state: %#lx\n", + rsp->name, rsp->gp_state, rsp->gp_kthread->state); + /* sched_show_task(rsp->gp_kthread); */ + } +} +EXPORT_SYMBOL_GPL(show_rcu_gp_kthreads); + +/* + * Record the number of times rcutorture tests have been initiated and + * terminated. This information allows the debugfs tracing stats to be + * correlated to the rcutorture messages, even when the rcutorture module + * is being repeatedly loaded and unloaded. In other words, we cannot + * store this state in rcutorture itself. + */ +void rcutorture_record_test_transition(void) +{ + rcutorture_testseq++; + rcutorture_vernum = 0; +} +EXPORT_SYMBOL_GPL(rcutorture_record_test_transition); + +/* + * Send along grace-period-related data for rcutorture diagnostics. + */ +void rcutorture_get_gp_data(enum rcutorture_type test_type, int *flags, + unsigned long *gpnum, unsigned long *completed) +{ + struct rcu_state *rsp = NULL; + + switch (test_type) { + case RCU_FLAVOR: + rsp = rcu_state_p; + break; + case RCU_BH_FLAVOR: + rsp = &rcu_bh_state; + break; + case RCU_SCHED_FLAVOR: + rsp = &rcu_sched_state; + break; + default: + break; + } + if (rsp != NULL) { + *flags = ACCESS_ONCE(rsp->gp_flags); + *gpnum = ACCESS_ONCE(rsp->gpnum); + *completed = ACCESS_ONCE(rsp->completed); + return; + } + *flags = 0; + *gpnum = 0; + *completed = 0; +} +EXPORT_SYMBOL_GPL(rcutorture_get_gp_data); + +/* + * Record the number of writer passes through the current rcutorture test. + * This is also used to correlate debugfs tracing stats with the rcutorture + * messages. + */ +void rcutorture_record_progress(unsigned long vernum) +{ + rcutorture_vernum++; +} +EXPORT_SYMBOL_GPL(rcutorture_record_progress); + +/* + * Does the CPU have callbacks ready to be invoked? + */ +static int +cpu_has_callbacks_ready_to_invoke(struct rcu_data *rdp) +{ + return &rdp->nxtlist != rdp->nxttail[RCU_DONE_TAIL] && + rdp->nxttail[RCU_DONE_TAIL] != NULL; +} + +/* + * Return the root node of the specified rcu_state structure. + */ +static struct rcu_node *rcu_get_root(struct rcu_state *rsp) +{ + return &rsp->node[0]; +} + +/* + * Is there any need for future grace periods? + * Interrupts must be disabled. If the caller does not hold the root + * rnp_node structure's ->lock, the results are advisory only. + */ +static int rcu_future_needs_gp(struct rcu_state *rsp) +{ + struct rcu_node *rnp = rcu_get_root(rsp); + int idx = (ACCESS_ONCE(rnp->completed) + 1) & 0x1; + int *fp = &rnp->need_future_gp[idx]; + + return ACCESS_ONCE(*fp); +} + +/* + * Does the current CPU require a not-yet-started grace period? + * The caller must have disabled interrupts to prevent races with + * normal callback registry. + */ +static int +cpu_needs_another_gp(struct rcu_state *rsp, struct rcu_data *rdp) +{ + int i; + + if (rcu_gp_in_progress(rsp)) + return 0; /* No, a grace period is already in progress. */ + if (rcu_future_needs_gp(rsp)) + return 1; /* Yes, a no-CBs CPU needs one. */ + if (!rdp->nxttail[RCU_NEXT_TAIL]) + return 0; /* No, this is a no-CBs (or offline) CPU. */ + if (*rdp->nxttail[RCU_NEXT_READY_TAIL]) + return 1; /* Yes, this CPU has newly registered callbacks. */ + for (i = RCU_WAIT_TAIL; i < RCU_NEXT_TAIL; i++) + if (rdp->nxttail[i - 1] != rdp->nxttail[i] && + ULONG_CMP_LT(ACCESS_ONCE(rsp->completed), + rdp->nxtcompleted[i])) + return 1; /* Yes, CBs for future grace period. */ + return 0; /* No grace period needed. */ +} + +/* + * rcu_eqs_enter_common - current CPU is moving towards extended quiescent state + * + * If the new value of the ->dynticks_nesting counter now is zero, + * we really have entered idle, and must do the appropriate accounting. + * The caller must have disabled interrupts. + */ +static void rcu_eqs_enter_common(long long oldval, bool user) +{ + struct rcu_state *rsp; + struct rcu_data *rdp; + struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks); + + trace_rcu_dyntick(TPS("Start"), oldval, rdtp->dynticks_nesting); + if (!user && !is_idle_task(current)) { + struct task_struct *idle __maybe_unused = + idle_task(smp_processor_id()); + + trace_rcu_dyntick(TPS("Error on entry: not idle task"), oldval, 0); + ftrace_dump(DUMP_ORIG); + WARN_ONCE(1, "Current pid: %d comm: %s / Idle pid: %d comm: %s", + current->pid, current->comm, + idle->pid, idle->comm); /* must be idle task! */ + } + for_each_rcu_flavor(rsp) { + rdp = this_cpu_ptr(rsp->rda); + do_nocb_deferred_wakeup(rdp); + } + rcu_prepare_for_idle(); + /* CPUs seeing atomic_inc() must see prior RCU read-side crit sects */ + smp_mb__before_atomic(); /* See above. */ + atomic_inc(&rdtp->dynticks); + smp_mb__after_atomic(); /* Force ordering with next sojourn. */ + WARN_ON_ONCE(atomic_read(&rdtp->dynticks) & 0x1); + rcu_dynticks_task_enter(); + + /* + * It is illegal to enter an extended quiescent state while + * in an RCU read-side critical section. + */ + rcu_lockdep_assert(!lock_is_held(&rcu_lock_map), + "Illegal idle entry in RCU read-side critical section."); + rcu_lockdep_assert(!lock_is_held(&rcu_bh_lock_map), + "Illegal idle entry in RCU-bh read-side critical section."); + rcu_lockdep_assert(!lock_is_held(&rcu_sched_lock_map), + "Illegal idle entry in RCU-sched read-side critical section."); +} + +/* + * Enter an RCU extended quiescent state, which can be either the + * idle loop or adaptive-tickless usermode execution. + */ +static void rcu_eqs_enter(bool user) +{ + long long oldval; + struct rcu_dynticks *rdtp; + + rdtp = this_cpu_ptr(&rcu_dynticks); + oldval = rdtp->dynticks_nesting; + WARN_ON_ONCE((oldval & DYNTICK_TASK_NEST_MASK) == 0); + if ((oldval & DYNTICK_TASK_NEST_MASK) == DYNTICK_TASK_NEST_VALUE) { + rdtp->dynticks_nesting = 0; + rcu_eqs_enter_common(oldval, user); + } else { + rdtp->dynticks_nesting -= DYNTICK_TASK_NEST_VALUE; + } +} + +/** + * rcu_idle_enter - inform RCU that current CPU is entering idle + * + * Enter idle mode, in other words, -leave- the mode in which RCU + * read-side critical sections can occur. (Though RCU read-side + * critical sections can occur in irq handlers in idle, a possibility + * handled by irq_enter() and irq_exit().) + * + * We crowbar the ->dynticks_nesting field to zero to allow for + * the possibility of usermode upcalls having messed up our count + * of interrupt nesting level during the prior busy period. + */ +void rcu_idle_enter(void) +{ + unsigned long flags; + + local_irq_save(flags); + rcu_eqs_enter(false); + rcu_sysidle_enter(0); + local_irq_restore(flags); +} +EXPORT_SYMBOL_GPL(rcu_idle_enter); + +#ifdef CONFIG_RCU_USER_QS +/** + * rcu_user_enter - inform RCU that we are resuming userspace. + * + * Enter RCU idle mode right before resuming userspace. No use of RCU + * is permitted between this call and rcu_user_exit(). This way the + * CPU doesn't need to maintain the tick for RCU maintenance purposes + * when the CPU runs in userspace. + */ +void rcu_user_enter(void) +{ + rcu_eqs_enter(1); +} +#endif /* CONFIG_RCU_USER_QS */ + +/** + * rcu_irq_exit - inform RCU that current CPU is exiting irq towards idle + * + * Exit from an interrupt handler, which might possibly result in entering + * idle mode, in other words, leaving the mode in which read-side critical + * sections can occur. + * + * This code assumes that the idle loop never does anything that might + * result in unbalanced calls to irq_enter() and irq_exit(). If your + * architecture violates this assumption, RCU will give you what you + * deserve, good and hard. But very infrequently and irreproducibly. + * + * Use things like work queues to work around this limitation. + * + * You have been warned. + */ +void rcu_irq_exit(void) +{ + unsigned long flags; + long long oldval; + struct rcu_dynticks *rdtp; + + local_irq_save(flags); + rdtp = this_cpu_ptr(&rcu_dynticks); + oldval = rdtp->dynticks_nesting; + rdtp->dynticks_nesting--; + WARN_ON_ONCE(rdtp->dynticks_nesting < 0); + if (rdtp->dynticks_nesting) + trace_rcu_dyntick(TPS("--="), oldval, rdtp->dynticks_nesting); + else + rcu_eqs_enter_common(oldval, true); + rcu_sysidle_enter(1); + local_irq_restore(flags); +} + +/* + * rcu_eqs_exit_common - current CPU moving away from extended quiescent state + * + * If the new value of the ->dynticks_nesting counter was previously zero, + * we really have exited idle, and must do the appropriate accounting. + * The caller must have disabled interrupts. + */ +static void rcu_eqs_exit_common(long long oldval, int user) +{ + struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks); + + rcu_dynticks_task_exit(); + smp_mb__before_atomic(); /* Force ordering w/previous sojourn. */ + atomic_inc(&rdtp->dynticks); + /* CPUs seeing atomic_inc() must see later RCU read-side crit sects */ + smp_mb__after_atomic(); /* See above. */ + WARN_ON_ONCE(!(atomic_read(&rdtp->dynticks) & 0x1)); + rcu_cleanup_after_idle(); + trace_rcu_dyntick(TPS("End"), oldval, rdtp->dynticks_nesting); + if (!user && !is_idle_task(current)) { + struct task_struct *idle __maybe_unused = + idle_task(smp_processor_id()); + + trace_rcu_dyntick(TPS("Error on exit: not idle task"), + oldval, rdtp->dynticks_nesting); + ftrace_dump(DUMP_ORIG); + WARN_ONCE(1, "Current pid: %d comm: %s / Idle pid: %d comm: %s", + current->pid, current->comm, + idle->pid, idle->comm); /* must be idle task! */ + } +} + +/* + * Exit an RCU extended quiescent state, which can be either the + * idle loop or adaptive-tickless usermode execution. + */ +static void rcu_eqs_exit(bool user) +{ + struct rcu_dynticks *rdtp; + long long oldval; + + rdtp = this_cpu_ptr(&rcu_dynticks); + oldval = rdtp->dynticks_nesting; + WARN_ON_ONCE(oldval < 0); + if (oldval & DYNTICK_TASK_NEST_MASK) { + rdtp->dynticks_nesting += DYNTICK_TASK_NEST_VALUE; + } else { + rdtp->dynticks_nesting = DYNTICK_TASK_EXIT_IDLE; + rcu_eqs_exit_common(oldval, user); + } +} + +/** + * rcu_idle_exit - inform RCU that current CPU is leaving idle + * + * Exit idle mode, in other words, -enter- the mode in which RCU + * read-side critical sections can occur. + * + * We crowbar the ->dynticks_nesting field to DYNTICK_TASK_NEST to + * allow for the possibility of usermode upcalls messing up our count + * of interrupt nesting level during the busy period that is just + * now starting. + */ +void rcu_idle_exit(void) +{ + unsigned long flags; + + local_irq_save(flags); + rcu_eqs_exit(false); + rcu_sysidle_exit(0); + local_irq_restore(flags); +} +EXPORT_SYMBOL_GPL(rcu_idle_exit); + +#ifdef CONFIG_RCU_USER_QS +/** + * rcu_user_exit - inform RCU that we are exiting userspace. + * + * Exit RCU idle mode while entering the kernel because it can + * run a RCU read side critical section anytime. + */ +void rcu_user_exit(void) +{ + rcu_eqs_exit(1); +} +#endif /* CONFIG_RCU_USER_QS */ + +/** + * rcu_irq_enter - inform RCU that current CPU is entering irq away from idle + * + * Enter an interrupt handler, which might possibly result in exiting + * idle mode, in other words, entering the mode in which read-side critical + * sections can occur. + * + * Note that the Linux kernel is fully capable of entering an interrupt + * handler that it never exits, for example when doing upcalls to + * user mode! This code assumes that the idle loop never does upcalls to + * user mode. If your architecture does do upcalls from the idle loop (or + * does anything else that results in unbalanced calls to the irq_enter() + * and irq_exit() functions), RCU will give you what you deserve, good + * and hard. But very infrequently and irreproducibly. + * + * Use things like work queues to work around this limitation. + * + * You have been warned. + */ +void rcu_irq_enter(void) +{ + unsigned long flags; + struct rcu_dynticks *rdtp; + long long oldval; + + local_irq_save(flags); + rdtp = this_cpu_ptr(&rcu_dynticks); + oldval = rdtp->dynticks_nesting; + rdtp->dynticks_nesting++; + WARN_ON_ONCE(rdtp->dynticks_nesting == 0); + if (oldval) + trace_rcu_dyntick(TPS("++="), oldval, rdtp->dynticks_nesting); + else + rcu_eqs_exit_common(oldval, true); + rcu_sysidle_exit(1); + local_irq_restore(flags); +} + +/** + * rcu_nmi_enter - inform RCU of entry to NMI context + * + * If the CPU was idle from RCU's viewpoint, update rdtp->dynticks and + * rdtp->dynticks_nmi_nesting to let the RCU grace-period handling know + * that the CPU is active. This implementation permits nested NMIs, as + * long as the nesting level does not overflow an int. (You will probably + * run out of stack space first.) + */ +void rcu_nmi_enter(void) +{ + struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks); + int incby = 2; + + /* Complain about underflow. */ + WARN_ON_ONCE(rdtp->dynticks_nmi_nesting < 0); + + /* + * If idle from RCU viewpoint, atomically increment ->dynticks + * to mark non-idle and increment ->dynticks_nmi_nesting by one. + * Otherwise, increment ->dynticks_nmi_nesting by two. This means + * if ->dynticks_nmi_nesting is equal to one, we are guaranteed + * to be in the outermost NMI handler that interrupted an RCU-idle + * period (observation due to Andy Lutomirski). + */ + if (!(atomic_read(&rdtp->dynticks) & 0x1)) { + smp_mb__before_atomic(); /* Force delay from prior write. */ + atomic_inc(&rdtp->dynticks); + /* atomic_inc() before later RCU read-side crit sects */ + smp_mb__after_atomic(); /* See above. */ + WARN_ON_ONCE(!(atomic_read(&rdtp->dynticks) & 0x1)); + incby = 1; + } + rdtp->dynticks_nmi_nesting += incby; + barrier(); +} + +/** + * rcu_nmi_exit - inform RCU of exit from NMI context + * + * If we are returning from the outermost NMI handler that interrupted an + * RCU-idle period, update rdtp->dynticks and rdtp->dynticks_nmi_nesting + * to let the RCU grace-period handling know that the CPU is back to + * being RCU-idle. + */ +void rcu_nmi_exit(void) +{ + struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks); + + /* + * Check for ->dynticks_nmi_nesting underflow and bad ->dynticks. + * (We are exiting an NMI handler, so RCU better be paying attention + * to us!) + */ + WARN_ON_ONCE(rdtp->dynticks_nmi_nesting <= 0); + WARN_ON_ONCE(!(atomic_read(&rdtp->dynticks) & 0x1)); + + /* + * If the nesting level is not 1, the CPU wasn't RCU-idle, so + * leave it in non-RCU-idle state. + */ + if (rdtp->dynticks_nmi_nesting != 1) { + rdtp->dynticks_nmi_nesting -= 2; + return; + } + + /* This NMI interrupted an RCU-idle CPU, restore RCU-idleness. */ + rdtp->dynticks_nmi_nesting = 0; + /* CPUs seeing atomic_inc() must see prior RCU read-side crit sects */ + smp_mb__before_atomic(); /* See above. */ + atomic_inc(&rdtp->dynticks); + smp_mb__after_atomic(); /* Force delay to next write. */ + WARN_ON_ONCE(atomic_read(&rdtp->dynticks) & 0x1); +} + +/** + * __rcu_is_watching - are RCU read-side critical sections safe? + * + * Return true if RCU is watching the running CPU, which means that + * this CPU can safely enter RCU read-side critical sections. Unlike + * rcu_is_watching(), the caller of __rcu_is_watching() must have at + * least disabled preemption. + */ +bool notrace __rcu_is_watching(void) +{ + return atomic_read(this_cpu_ptr(&rcu_dynticks.dynticks)) & 0x1; +} + +/** + * rcu_is_watching - see if RCU thinks that the current CPU is idle + * + * If the current CPU is in its idle loop and is neither in an interrupt + * or NMI handler, return true. + */ +bool notrace rcu_is_watching(void) +{ + bool ret; + + preempt_disable(); + ret = __rcu_is_watching(); + preempt_enable(); + return ret; +} +EXPORT_SYMBOL_GPL(rcu_is_watching); + +#if defined(CONFIG_PROVE_RCU) && defined(CONFIG_HOTPLUG_CPU) + +/* + * Is the current CPU online? Disable preemption to avoid false positives + * that could otherwise happen due to the current CPU number being sampled, + * this task being preempted, its old CPU being taken offline, resuming + * on some other CPU, then determining that its old CPU is now offline. + * It is OK to use RCU on an offline processor during initial boot, hence + * the check for rcu_scheduler_fully_active. Note also that it is OK + * for a CPU coming online to use RCU for one jiffy prior to marking itself + * online in the cpu_online_mask. Similarly, it is OK for a CPU going + * offline to continue to use RCU for one jiffy after marking itself + * offline in the cpu_online_mask. This leniency is necessary given the + * non-atomic nature of the online and offline processing, for example, + * the fact that a CPU enters the scheduler after completing the CPU_DYING + * notifiers. + * + * This is also why RCU internally marks CPUs online during the + * CPU_UP_PREPARE phase and offline during the CPU_DEAD phase. + * + * Disable checking if in an NMI handler because we cannot safely report + * errors from NMI handlers anyway. + */ +bool rcu_lockdep_current_cpu_online(void) +{ + struct rcu_data *rdp; + struct rcu_node *rnp; + bool ret; + + if (in_nmi()) + return true; + preempt_disable(); + rdp = this_cpu_ptr(&rcu_sched_data); + rnp = rdp->mynode; + ret = (rdp->grpmask & rcu_rnp_online_cpus(rnp)) || + !rcu_scheduler_fully_active; + preempt_enable(); + return ret; +} +EXPORT_SYMBOL_GPL(rcu_lockdep_current_cpu_online); + +#endif /* #if defined(CONFIG_PROVE_RCU) && defined(CONFIG_HOTPLUG_CPU) */ + +/** + * rcu_is_cpu_rrupt_from_idle - see if idle or immediately interrupted from idle + * + * If the current CPU is idle or running at a first-level (not nested) + * interrupt from idle, return true. The caller must have at least + * disabled preemption. + */ +static int rcu_is_cpu_rrupt_from_idle(void) +{ + return __this_cpu_read(rcu_dynticks.dynticks_nesting) <= 1; +} + +/* + * Snapshot the specified CPU's dynticks counter so that we can later + * credit them with an implicit quiescent state. Return 1 if this CPU + * is in dynticks idle mode, which is an extended quiescent state. + */ +static int dyntick_save_progress_counter(struct rcu_data *rdp, + bool *isidle, unsigned long *maxj) +{ + rdp->dynticks_snap = atomic_add_return(0, &rdp->dynticks->dynticks); + rcu_sysidle_check_cpu(rdp, isidle, maxj); + if ((rdp->dynticks_snap & 0x1) == 0) { + trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, TPS("dti")); + return 1; + } else { + if (ULONG_CMP_LT(ACCESS_ONCE(rdp->gpnum) + ULONG_MAX / 4, + rdp->mynode->gpnum)) + ACCESS_ONCE(rdp->gpwrap) = true; + return 0; + } +} + +/* + * Return true if the specified CPU has passed through a quiescent + * state by virtue of being in or having passed through an dynticks + * idle state since the last call to dyntick_save_progress_counter() + * for this same CPU, or by virtue of having been offline. + */ +static int rcu_implicit_dynticks_qs(struct rcu_data *rdp, + bool *isidle, unsigned long *maxj) +{ + unsigned int curr; + int *rcrmp; + unsigned int snap; + + curr = (unsigned int)atomic_add_return(0, &rdp->dynticks->dynticks); + snap = (unsigned int)rdp->dynticks_snap; + + /* + * If the CPU passed through or entered a dynticks idle phase with + * no active irq/NMI handlers, then we can safely pretend that the CPU + * already acknowledged the request to pass through a quiescent + * state. Either way, that CPU cannot possibly be in an RCU + * read-side critical section that started before the beginning + * of the current RCU grace period. + */ + if ((curr & 0x1) == 0 || UINT_CMP_GE(curr, snap + 2)) { + trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, TPS("dti")); + rdp->dynticks_fqs++; + return 1; + } + + /* + * Check for the CPU being offline, but only if the grace period + * is old enough. We don't need to worry about the CPU changing + * state: If we see it offline even once, it has been through a + * quiescent state. + * + * The reason for insisting that the grace period be at least + * one jiffy old is that CPUs that are not quite online and that + * have just gone offline can still execute RCU read-side critical + * sections. + */ + if (ULONG_CMP_GE(rdp->rsp->gp_start + 2, jiffies)) + return 0; /* Grace period is not old enough. */ + barrier(); + if (cpu_is_offline(rdp->cpu)) { + trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, TPS("ofl")); + rdp->offline_fqs++; + return 1; + } + + /* + * A CPU running for an extended time within the kernel can + * delay RCU grace periods. When the CPU is in NO_HZ_FULL mode, + * even context-switching back and forth between a pair of + * in-kernel CPU-bound tasks cannot advance grace periods. + * So if the grace period is old enough, make the CPU pay attention. + * Note that the unsynchronized assignments to the per-CPU + * rcu_sched_qs_mask variable are safe. Yes, setting of + * bits can be lost, but they will be set again on the next + * force-quiescent-state pass. So lost bit sets do not result + * in incorrect behavior, merely in a grace period lasting + * a few jiffies longer than it might otherwise. Because + * there are at most four threads involved, and because the + * updates are only once every few jiffies, the probability of + * lossage (and thus of slight grace-period extension) is + * quite low. + * + * Note that if the jiffies_till_sched_qs boot/sysfs parameter + * is set too high, we override with half of the RCU CPU stall + * warning delay. + */ + rcrmp = &per_cpu(rcu_sched_qs_mask, rdp->cpu); + if (ULONG_CMP_GE(jiffies, + rdp->rsp->gp_start + jiffies_till_sched_qs) || + ULONG_CMP_GE(jiffies, rdp->rsp->jiffies_resched)) { + if (!(ACCESS_ONCE(*rcrmp) & rdp->rsp->flavor_mask)) { + ACCESS_ONCE(rdp->cond_resched_completed) = + ACCESS_ONCE(rdp->mynode->completed); + smp_mb(); /* ->cond_resched_completed before *rcrmp. */ + ACCESS_ONCE(*rcrmp) = + ACCESS_ONCE(*rcrmp) + rdp->rsp->flavor_mask; + resched_cpu(rdp->cpu); /* Force CPU into scheduler. */ + rdp->rsp->jiffies_resched += 5; /* Enable beating. */ + } else if (ULONG_CMP_GE(jiffies, rdp->rsp->jiffies_resched)) { + /* Time to beat on that CPU again! */ + resched_cpu(rdp->cpu); /* Force CPU into scheduler. */ + rdp->rsp->jiffies_resched += 5; /* Re-enable beating. */ + } + } + + return 0; +} + +static void record_gp_stall_check_time(struct rcu_state *rsp) +{ + unsigned long j = jiffies; + unsigned long j1; + + rsp->gp_start = j; + smp_wmb(); /* Record start time before stall time. */ + j1 = rcu_jiffies_till_stall_check(); + ACCESS_ONCE(rsp->jiffies_stall) = j + j1; + rsp->jiffies_resched = j + j1 / 2; + rsp->n_force_qs_gpstart = ACCESS_ONCE(rsp->n_force_qs); +} + +/* + * Complain about starvation of grace-period kthread. + */ +static void rcu_check_gp_kthread_starvation(struct rcu_state *rsp) +{ + unsigned long gpa; + unsigned long j; + + j = jiffies; + gpa = ACCESS_ONCE(rsp->gp_activity); + if (j - gpa > 2 * HZ) + pr_err("%s kthread starved for %ld jiffies!\n", + rsp->name, j - gpa); +} + +/* + * Dump stacks of all tasks running on stalled CPUs. + */ +static void rcu_dump_cpu_stacks(struct rcu_state *rsp) +{ + int cpu; + unsigned long flags; + struct rcu_node *rnp; + + rcu_for_each_leaf_node(rsp, rnp) { + raw_spin_lock_irqsave(&rnp->lock, flags); + if (rnp->qsmask != 0) { + for (cpu = 0; cpu <= rnp->grphi - rnp->grplo; cpu++) + if (rnp->qsmask & (1UL << cpu)) + dump_cpu_task(rnp->grplo + cpu); + } + raw_spin_unlock_irqrestore(&rnp->lock, flags); + } +} + +static void print_other_cpu_stall(struct rcu_state *rsp, unsigned long gpnum) +{ + int cpu; + long delta; + unsigned long flags; + unsigned long gpa; + unsigned long j; + int ndetected = 0; + struct rcu_node *rnp = rcu_get_root(rsp); + long totqlen = 0; + + /* Only let one CPU complain about others per time interval. */ + + raw_spin_lock_irqsave(&rnp->lock, flags); + delta = jiffies - ACCESS_ONCE(rsp->jiffies_stall); + if (delta < RCU_STALL_RAT_DELAY || !rcu_gp_in_progress(rsp)) { + raw_spin_unlock_irqrestore(&rnp->lock, flags); + return; + } + ACCESS_ONCE(rsp->jiffies_stall) = jiffies + 3 * rcu_jiffies_till_stall_check() + 3; + raw_spin_unlock_irqrestore(&rnp->lock, flags); + + /* + * OK, time to rat on our buddy... + * See Documentation/RCU/stallwarn.txt for info on how to debug + * RCU CPU stall warnings. + */ + pr_err("INFO: %s detected stalls on CPUs/tasks:", + rsp->name); + print_cpu_stall_info_begin(); + rcu_for_each_leaf_node(rsp, rnp) { + raw_spin_lock_irqsave(&rnp->lock, flags); + ndetected += rcu_print_task_stall(rnp); + if (rnp->qsmask != 0) { + for (cpu = 0; cpu <= rnp->grphi - rnp->grplo; cpu++) + if (rnp->qsmask & (1UL << cpu)) { + print_cpu_stall_info(rsp, + rnp->grplo + cpu); + ndetected++; + } + } + raw_spin_unlock_irqrestore(&rnp->lock, flags); + } + + print_cpu_stall_info_end(); + for_each_possible_cpu(cpu) + totqlen += per_cpu_ptr(rsp->rda, cpu)->qlen; + pr_cont("(detected by %d, t=%ld jiffies, g=%ld, c=%ld, q=%lu)\n", + smp_processor_id(), (long)(jiffies - rsp->gp_start), + (long)rsp->gpnum, (long)rsp->completed, totqlen); + if (ndetected) { + rcu_dump_cpu_stacks(rsp); + } else { + if (ACCESS_ONCE(rsp->gpnum) != gpnum || + ACCESS_ONCE(rsp->completed) == gpnum) { + pr_err("INFO: Stall ended before state dump start\n"); + } else { + j = jiffies; + gpa = ACCESS_ONCE(rsp->gp_activity); + pr_err("All QSes seen, last %s kthread activity %ld (%ld-%ld), jiffies_till_next_fqs=%ld, root ->qsmask %#lx\n", + rsp->name, j - gpa, j, gpa, + jiffies_till_next_fqs, + rcu_get_root(rsp)->qsmask); + /* In this case, the current CPU might be at fault. */ + sched_show_task(current); + } + } + + /* Complain about tasks blocking the grace period. */ + rcu_print_detail_task_stall(rsp); + + rcu_check_gp_kthread_starvation(rsp); + + force_quiescent_state(rsp); /* Kick them all. */ +} + +static void print_cpu_stall(struct rcu_state *rsp) +{ + int cpu; + unsigned long flags; + struct rcu_node *rnp = rcu_get_root(rsp); + long totqlen = 0; + + /* + * OK, time to rat on ourselves... + * See Documentation/RCU/stallwarn.txt for info on how to debug + * RCU CPU stall warnings. + */ + pr_err("INFO: %s self-detected stall on CPU", rsp->name); + print_cpu_stall_info_begin(); + print_cpu_stall_info(rsp, smp_processor_id()); + print_cpu_stall_info_end(); + for_each_possible_cpu(cpu) + totqlen += per_cpu_ptr(rsp->rda, cpu)->qlen; + pr_cont(" (t=%lu jiffies g=%ld c=%ld q=%lu)\n", + jiffies - rsp->gp_start, + (long)rsp->gpnum, (long)rsp->completed, totqlen); + + rcu_check_gp_kthread_starvation(rsp); + + rcu_dump_cpu_stacks(rsp); + + raw_spin_lock_irqsave(&rnp->lock, flags); + if (ULONG_CMP_GE(jiffies, ACCESS_ONCE(rsp->jiffies_stall))) + ACCESS_ONCE(rsp->jiffies_stall) = jiffies + + 3 * rcu_jiffies_till_stall_check() + 3; + raw_spin_unlock_irqrestore(&rnp->lock, flags); + + /* + * Attempt to revive the RCU machinery by forcing a context switch. + * + * A context switch would normally allow the RCU state machine to make + * progress and it could be we're stuck in kernel space without context + * switches for an entirely unreasonable amount of time. + */ + resched_cpu(smp_processor_id()); +} + +static void check_cpu_stall(struct rcu_state *rsp, struct rcu_data *rdp) +{ + unsigned long completed; + unsigned long gpnum; + unsigned long gps; + unsigned long j; + unsigned long js; + struct rcu_node *rnp; + + if (rcu_cpu_stall_suppress || !rcu_gp_in_progress(rsp)) + return; + j = jiffies; + + /* + * Lots of memory barriers to reject false positives. + * + * The idea is to pick up rsp->gpnum, then rsp->jiffies_stall, + * then rsp->gp_start, and finally rsp->completed. These values + * are updated in the opposite order with memory barriers (or + * equivalent) during grace-period initialization and cleanup. + * Now, a false positive can occur if we get an new value of + * rsp->gp_start and a old value of rsp->jiffies_stall. But given + * the memory barriers, the only way that this can happen is if one + * grace period ends and another starts between these two fetches. + * Detect this by comparing rsp->completed with the previous fetch + * from rsp->gpnum. + * + * Given this check, comparisons of jiffies, rsp->jiffies_stall, + * and rsp->gp_start suffice to forestall false positives. + */ + gpnum = ACCESS_ONCE(rsp->gpnum); + smp_rmb(); /* Pick up ->gpnum first... */ + js = ACCESS_ONCE(rsp->jiffies_stall); + smp_rmb(); /* ...then ->jiffies_stall before the rest... */ + gps = ACCESS_ONCE(rsp->gp_start); + smp_rmb(); /* ...and finally ->gp_start before ->completed. */ + completed = ACCESS_ONCE(rsp->completed); + if (ULONG_CMP_GE(completed, gpnum) || + ULONG_CMP_LT(j, js) || + ULONG_CMP_GE(gps, js)) + return; /* No stall or GP completed since entering function. */ + rnp = rdp->mynode; + if (rcu_gp_in_progress(rsp) && + (ACCESS_ONCE(rnp->qsmask) & rdp->grpmask)) { + + /* We haven't checked in, so go dump stack. */ + print_cpu_stall(rsp); + + } else if (rcu_gp_in_progress(rsp) && + ULONG_CMP_GE(j, js + RCU_STALL_RAT_DELAY)) { + + /* They had a few time units to dump stack, so complain. */ + print_other_cpu_stall(rsp, gpnum); + } +} + +/** + * rcu_cpu_stall_reset - prevent further stall warnings in current grace period + * + * Set the stall-warning timeout way off into the future, thus preventing + * any RCU CPU stall-warning messages from appearing in the current set of + * RCU grace periods. + * + * The caller must disable hard irqs. + */ +void rcu_cpu_stall_reset(void) +{ + struct rcu_state *rsp; + + for_each_rcu_flavor(rsp) + ACCESS_ONCE(rsp->jiffies_stall) = jiffies + ULONG_MAX / 2; +} + +/* + * Initialize the specified rcu_data structure's default callback list + * to empty. The default callback list is the one that is not used by + * no-callbacks CPUs. + */ +static void init_default_callback_list(struct rcu_data *rdp) +{ + int i; + + rdp->nxtlist = NULL; + for (i = 0; i < RCU_NEXT_SIZE; i++) + rdp->nxttail[i] = &rdp->nxtlist; +} + +/* + * Initialize the specified rcu_data structure's callback list to empty. + */ +static void init_callback_list(struct rcu_data *rdp) +{ + if (init_nocb_callback_list(rdp)) + return; + init_default_callback_list(rdp); +} + +/* + * Determine the value that ->completed will have at the end of the + * next subsequent grace period. This is used to tag callbacks so that + * a CPU can invoke callbacks in a timely fashion even if that CPU has + * been dyntick-idle for an extended period with callbacks under the + * influence of RCU_FAST_NO_HZ. + * + * The caller must hold rnp->lock with interrupts disabled. + */ +static unsigned long rcu_cbs_completed(struct rcu_state *rsp, + struct rcu_node *rnp) +{ + /* + * If RCU is idle, we just wait for the next grace period. + * But we can only be sure that RCU is idle if we are looking + * at the root rcu_node structure -- otherwise, a new grace + * period might have started, but just not yet gotten around + * to initializing the current non-root rcu_node structure. + */ + if (rcu_get_root(rsp) == rnp && rnp->gpnum == rnp->completed) + return rnp->completed + 1; + + /* + * Otherwise, wait for a possible partial grace period and + * then the subsequent full grace period. + */ + return rnp->completed + 2; +} + +/* + * Trace-event helper function for rcu_start_future_gp() and + * rcu_nocb_wait_gp(). + */ +static void trace_rcu_future_gp(struct rcu_node *rnp, struct rcu_data *rdp, + unsigned long c, const char *s) +{ + trace_rcu_future_grace_period(rdp->rsp->name, rnp->gpnum, + rnp->completed, c, rnp->level, + rnp->grplo, rnp->grphi, s); +} + +/* + * Start some future grace period, as needed to handle newly arrived + * callbacks. The required future grace periods are recorded in each + * rcu_node structure's ->need_future_gp field. Returns true if there + * is reason to awaken the grace-period kthread. + * + * The caller must hold the specified rcu_node structure's ->lock. + */ +static bool __maybe_unused +rcu_start_future_gp(struct rcu_node *rnp, struct rcu_data *rdp, + unsigned long *c_out) +{ + unsigned long c; + int i; + bool ret = false; + struct rcu_node *rnp_root = rcu_get_root(rdp->rsp); + + /* + * Pick up grace-period number for new callbacks. If this + * grace period is already marked as needed, return to the caller. + */ + c = rcu_cbs_completed(rdp->rsp, rnp); + trace_rcu_future_gp(rnp, rdp, c, TPS("Startleaf")); + if (rnp->need_future_gp[c & 0x1]) { + trace_rcu_future_gp(rnp, rdp, c, TPS("Prestartleaf")); + goto out; + } + + /* + * If either this rcu_node structure or the root rcu_node structure + * believe that a grace period is in progress, then we must wait + * for the one following, which is in "c". Because our request + * will be noticed at the end of the current grace period, we don't + * need to explicitly start one. We only do the lockless check + * of rnp_root's fields if the current rcu_node structure thinks + * there is no grace period in flight, and because we hold rnp->lock, + * the only possible change is when rnp_root's two fields are + * equal, in which case rnp_root->gpnum might be concurrently + * incremented. But that is OK, as it will just result in our + * doing some extra useless work. + */ + if (rnp->gpnum != rnp->completed || + ACCESS_ONCE(rnp_root->gpnum) != ACCESS_ONCE(rnp_root->completed)) { + rnp->need_future_gp[c & 0x1]++; + trace_rcu_future_gp(rnp, rdp, c, TPS("Startedleaf")); + goto out; + } + + /* + * There might be no grace period in progress. If we don't already + * hold it, acquire the root rcu_node structure's lock in order to + * start one (if needed). + */ + if (rnp != rnp_root) { + raw_spin_lock(&rnp_root->lock); + smp_mb__after_unlock_lock(); + } + + /* + * Get a new grace-period number. If there really is no grace + * period in progress, it will be smaller than the one we obtained + * earlier. Adjust callbacks as needed. Note that even no-CBs + * CPUs have a ->nxtcompleted[] array, so no no-CBs checks needed. + */ + c = rcu_cbs_completed(rdp->rsp, rnp_root); + for (i = RCU_DONE_TAIL; i < RCU_NEXT_TAIL; i++) + if (ULONG_CMP_LT(c, rdp->nxtcompleted[i])) + rdp->nxtcompleted[i] = c; + + /* + * If the needed for the required grace period is already + * recorded, trace and leave. + */ + if (rnp_root->need_future_gp[c & 0x1]) { + trace_rcu_future_gp(rnp, rdp, c, TPS("Prestartedroot")); + goto unlock_out; + } + + /* Record the need for the future grace period. */ + rnp_root->need_future_gp[c & 0x1]++; + + /* If a grace period is not already in progress, start one. */ + if (rnp_root->gpnum != rnp_root->completed) { + trace_rcu_future_gp(rnp, rdp, c, TPS("Startedleafroot")); + } else { + trace_rcu_future_gp(rnp, rdp, c, TPS("Startedroot")); + ret = rcu_start_gp_advanced(rdp->rsp, rnp_root, rdp); + } +unlock_out: + if (rnp != rnp_root) + raw_spin_unlock(&rnp_root->lock); +out: + if (c_out != NULL) + *c_out = c; + return ret; +} + +/* + * Clean up any old requests for the just-ended grace period. Also return + * whether any additional grace periods have been requested. Also invoke + * rcu_nocb_gp_cleanup() in order to wake up any no-callbacks kthreads + * waiting for this grace period to complete. + */ +static int rcu_future_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp) +{ + int c = rnp->completed; + int needmore; + struct rcu_data *rdp = this_cpu_ptr(rsp->rda); + + rcu_nocb_gp_cleanup(rsp, rnp); + rnp->need_future_gp[c & 0x1] = 0; + needmore = rnp->need_future_gp[(c + 1) & 0x1]; + trace_rcu_future_gp(rnp, rdp, c, + needmore ? TPS("CleanupMore") : TPS("Cleanup")); + return needmore; +} + +/* + * Awaken the grace-period kthread for the specified flavor of RCU. + * Don't do a self-awaken, and don't bother awakening when there is + * nothing for the grace-period kthread to do (as in several CPUs + * raced to awaken, and we lost), and finally don't try to awaken + * a kthread that has not yet been created. + */ +static void rcu_gp_kthread_wake(struct rcu_state *rsp) +{ + if (current == rsp->gp_kthread || + !ACCESS_ONCE(rsp->gp_flags) || + !rsp->gp_kthread) + return; + swait_wake(&rsp->gp_wq); +} + +/* + * If there is room, assign a ->completed number to any callbacks on + * this CPU that have not already been assigned. Also accelerate any + * callbacks that were previously assigned a ->completed number that has + * since proven to be too conservative, which can happen if callbacks get + * assigned a ->completed number while RCU is idle, but with reference to + * a non-root rcu_node structure. This function is idempotent, so it does + * not hurt to call it repeatedly. Returns an flag saying that we should + * awaken the RCU grace-period kthread. + * + * The caller must hold rnp->lock with interrupts disabled. + */ +static bool rcu_accelerate_cbs(struct rcu_state *rsp, struct rcu_node *rnp, + struct rcu_data *rdp) +{ + unsigned long c; + int i; + bool ret; + + /* If the CPU has no callbacks, nothing to do. */ + if (!rdp->nxttail[RCU_NEXT_TAIL] || !*rdp->nxttail[RCU_DONE_TAIL]) + return false; + + /* + * Starting from the sublist containing the callbacks most + * recently assigned a ->completed number and working down, find the + * first sublist that is not assignable to an upcoming grace period. + * Such a sublist has something in it (first two tests) and has + * a ->completed number assigned that will complete sooner than + * the ->completed number for newly arrived callbacks (last test). + * + * The key point is that any later sublist can be assigned the + * same ->completed number as the newly arrived callbacks, which + * means that the callbacks in any of these later sublist can be + * grouped into a single sublist, whether or not they have already + * been assigned a ->completed number. + */ + c = rcu_cbs_completed(rsp, rnp); + for (i = RCU_NEXT_TAIL - 1; i > RCU_DONE_TAIL; i--) + if (rdp->nxttail[i] != rdp->nxttail[i - 1] && + !ULONG_CMP_GE(rdp->nxtcompleted[i], c)) + break; + + /* + * If there are no sublist for unassigned callbacks, leave. + * At the same time, advance "i" one sublist, so that "i" will + * index into the sublist where all the remaining callbacks should + * be grouped into. + */ + if (++i >= RCU_NEXT_TAIL) + return false; + + /* + * Assign all subsequent callbacks' ->completed number to the next + * full grace period and group them all in the sublist initially + * indexed by "i". + */ + for (; i <= RCU_NEXT_TAIL; i++) { + rdp->nxttail[i] = rdp->nxttail[RCU_NEXT_TAIL]; + rdp->nxtcompleted[i] = c; + } + /* Record any needed additional grace periods. */ + ret = rcu_start_future_gp(rnp, rdp, NULL); + + /* Trace depending on how much we were able to accelerate. */ + if (!*rdp->nxttail[RCU_WAIT_TAIL]) + trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("AccWaitCB")); + else + trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("AccReadyCB")); + return ret; +} + +/* + * Move any callbacks whose grace period has completed to the + * RCU_DONE_TAIL sublist, then compact the remaining sublists and + * assign ->completed numbers to any callbacks in the RCU_NEXT_TAIL + * sublist. This function is idempotent, so it does not hurt to + * invoke it repeatedly. As long as it is not invoked -too- often... + * Returns true if the RCU grace-period kthread needs to be awakened. + * + * The caller must hold rnp->lock with interrupts disabled. + */ +static bool rcu_advance_cbs(struct rcu_state *rsp, struct rcu_node *rnp, + struct rcu_data *rdp) +{ + int i, j; + + /* If the CPU has no callbacks, nothing to do. */ + if (!rdp->nxttail[RCU_NEXT_TAIL] || !*rdp->nxttail[RCU_DONE_TAIL]) + return false; + + /* + * Find all callbacks whose ->completed numbers indicate that they + * are ready to invoke, and put them into the RCU_DONE_TAIL sublist. + */ + for (i = RCU_WAIT_TAIL; i < RCU_NEXT_TAIL; i++) { + if (ULONG_CMP_LT(rnp->completed, rdp->nxtcompleted[i])) + break; + rdp->nxttail[RCU_DONE_TAIL] = rdp->nxttail[i]; + } + /* Clean up any sublist tail pointers that were misordered above. */ + for (j = RCU_WAIT_TAIL; j < i; j++) + rdp->nxttail[j] = rdp->nxttail[RCU_DONE_TAIL]; + + /* Copy down callbacks to fill in empty sublists. */ + for (j = RCU_WAIT_TAIL; i < RCU_NEXT_TAIL; i++, j++) { + if (rdp->nxttail[j] == rdp->nxttail[RCU_NEXT_TAIL]) + break; + rdp->nxttail[j] = rdp->nxttail[i]; + rdp->nxtcompleted[j] = rdp->nxtcompleted[i]; + } + + /* Classify any remaining callbacks. */ + return rcu_accelerate_cbs(rsp, rnp, rdp); +} + +/* + * Update CPU-local rcu_data state to record the beginnings and ends of + * grace periods. The caller must hold the ->lock of the leaf rcu_node + * structure corresponding to the current CPU, and must have irqs disabled. + * Returns true if the grace-period kthread needs to be awakened. + */ +static bool __note_gp_changes(struct rcu_state *rsp, struct rcu_node *rnp, + struct rcu_data *rdp) +{ + bool ret; + + /* Handle the ends of any preceding grace periods first. */ + if (rdp->completed == rnp->completed && + !unlikely(ACCESS_ONCE(rdp->gpwrap))) { + + /* No grace period end, so just accelerate recent callbacks. */ + ret = rcu_accelerate_cbs(rsp, rnp, rdp); + + } else { + + /* Advance callbacks. */ + ret = rcu_advance_cbs(rsp, rnp, rdp); + + /* Remember that we saw this grace-period completion. */ + rdp->completed = rnp->completed; + trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("cpuend")); + } + + if (rdp->gpnum != rnp->gpnum || unlikely(ACCESS_ONCE(rdp->gpwrap))) { + /* + * If the current grace period is waiting for this CPU, + * set up to detect a quiescent state, otherwise don't + * go looking for one. + */ + rdp->gpnum = rnp->gpnum; + trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("cpustart")); + rdp->passed_quiesce = 0; + rdp->rcu_qs_ctr_snap = __this_cpu_read(rcu_qs_ctr); + rdp->qs_pending = !!(rnp->qsmask & rdp->grpmask); + zero_cpu_stall_ticks(rdp); + ACCESS_ONCE(rdp->gpwrap) = false; + } + return ret; +} + +static void note_gp_changes(struct rcu_state *rsp, struct rcu_data *rdp) +{ + unsigned long flags; + bool needwake; + struct rcu_node *rnp; + + local_irq_save(flags); + rnp = rdp->mynode; + if ((rdp->gpnum == ACCESS_ONCE(rnp->gpnum) && + rdp->completed == ACCESS_ONCE(rnp->completed) && + !unlikely(ACCESS_ONCE(rdp->gpwrap))) || /* w/out lock. */ + !raw_spin_trylock(&rnp->lock)) { /* irqs already off, so later. */ + local_irq_restore(flags); + return; + } + smp_mb__after_unlock_lock(); + needwake = __note_gp_changes(rsp, rnp, rdp); + raw_spin_unlock_irqrestore(&rnp->lock, flags); + if (needwake) + rcu_gp_kthread_wake(rsp); +} + +/* + * Initialize a new grace period. Return 0 if no grace period required. + */ +static int rcu_gp_init(struct rcu_state *rsp) +{ + unsigned long oldmask; + struct rcu_data *rdp; + struct rcu_node *rnp = rcu_get_root(rsp); + + ACCESS_ONCE(rsp->gp_activity) = jiffies; + raw_spin_lock_irq(&rnp->lock); + smp_mb__after_unlock_lock(); + if (!ACCESS_ONCE(rsp->gp_flags)) { + /* Spurious wakeup, tell caller to go back to sleep. */ + raw_spin_unlock_irq(&rnp->lock); + return 0; + } + ACCESS_ONCE(rsp->gp_flags) = 0; /* Clear all flags: New grace period. */ + + if (WARN_ON_ONCE(rcu_gp_in_progress(rsp))) { + /* + * Grace period already in progress, don't start another. + * Not supposed to be able to happen. + */ + raw_spin_unlock_irq(&rnp->lock); + return 0; + } + + /* Advance to a new grace period and initialize state. */ + record_gp_stall_check_time(rsp); + /* Record GP times before starting GP, hence smp_store_release(). */ + smp_store_release(&rsp->gpnum, rsp->gpnum + 1); + trace_rcu_grace_period(rsp->name, rsp->gpnum, TPS("start")); + raw_spin_unlock_irq(&rnp->lock); + + /* + * Apply per-leaf buffered online and offline operations to the + * rcu_node tree. Note that this new grace period need not wait + * for subsequent online CPUs, and that quiescent-state forcing + * will handle subsequent offline CPUs. + */ + rcu_for_each_leaf_node(rsp, rnp) { + raw_spin_lock_irq(&rnp->lock); + smp_mb__after_unlock_lock(); + if (rnp->qsmaskinit == rnp->qsmaskinitnext && + !rnp->wait_blkd_tasks) { + /* Nothing to do on this leaf rcu_node structure. */ + raw_spin_unlock_irq(&rnp->lock); + continue; + } + + /* Record old state, apply changes to ->qsmaskinit field. */ + oldmask = rnp->qsmaskinit; + rnp->qsmaskinit = rnp->qsmaskinitnext; + + /* If zero-ness of ->qsmaskinit changed, propagate up tree. */ + if (!oldmask != !rnp->qsmaskinit) { + if (!oldmask) /* First online CPU for this rcu_node. */ + rcu_init_new_rnp(rnp); + else if (rcu_preempt_has_tasks(rnp)) /* blocked tasks */ + rnp->wait_blkd_tasks = true; + else /* Last offline CPU and can propagate. */ + rcu_cleanup_dead_rnp(rnp); + } + + /* + * If all waited-on tasks from prior grace period are + * done, and if all this rcu_node structure's CPUs are + * still offline, propagate up the rcu_node tree and + * clear ->wait_blkd_tasks. Otherwise, if one of this + * rcu_node structure's CPUs has since come back online, + * simply clear ->wait_blkd_tasks (but rcu_cleanup_dead_rnp() + * checks for this, so just call it unconditionally). + */ + if (rnp->wait_blkd_tasks && + (!rcu_preempt_has_tasks(rnp) || + rnp->qsmaskinit)) { + rnp->wait_blkd_tasks = false; + rcu_cleanup_dead_rnp(rnp); + } + + raw_spin_unlock_irq(&rnp->lock); + } + + /* + * Set the quiescent-state-needed bits in all the rcu_node + * structures for all currently online CPUs in breadth-first order, + * starting from the root rcu_node structure, relying on the layout + * of the tree within the rsp->node[] array. Note that other CPUs + * will access only the leaves of the hierarchy, thus seeing that no + * grace period is in progress, at least until the corresponding + * leaf node has been initialized. In addition, we have excluded + * CPU-hotplug operations. + * + * The grace period cannot complete until the initialization + * process finishes, because this kthread handles both. + */ + rcu_for_each_node_breadth_first(rsp, rnp) { + raw_spin_lock_irq(&rnp->lock); + smp_mb__after_unlock_lock(); + rdp = this_cpu_ptr(rsp->rda); + rcu_preempt_check_blocked_tasks(rnp); + rnp->qsmask = rnp->qsmaskinit; + ACCESS_ONCE(rnp->gpnum) = rsp->gpnum; + if (WARN_ON_ONCE(rnp->completed != rsp->completed)) + ACCESS_ONCE(rnp->completed) = rsp->completed; + if (rnp == rdp->mynode) + (void)__note_gp_changes(rsp, rnp, rdp); + rcu_preempt_boost_start_gp(rnp); + trace_rcu_grace_period_init(rsp->name, rnp->gpnum, + rnp->level, rnp->grplo, + rnp->grphi, rnp->qsmask); + raw_spin_unlock_irq(&rnp->lock); + cond_resched_rcu_qs(); + ACCESS_ONCE(rsp->gp_activity) = jiffies; + if (gp_init_delay > 0 && + !(rsp->gpnum % (rcu_num_nodes * PER_RCU_NODE_PERIOD))) + schedule_timeout_uninterruptible(gp_init_delay); + } + + return 1; +} + +/* + * Do one round of quiescent-state forcing. + */ +static int rcu_gp_fqs(struct rcu_state *rsp, int fqs_state_in) +{ + int fqs_state = fqs_state_in; + bool isidle = false; + unsigned long maxj; + struct rcu_node *rnp = rcu_get_root(rsp); + + ACCESS_ONCE(rsp->gp_activity) = jiffies; + rsp->n_force_qs++; + if (fqs_state == RCU_SAVE_DYNTICK) { + /* Collect dyntick-idle snapshots. */ + if (is_sysidle_rcu_state(rsp)) { + isidle = true; + maxj = jiffies - ULONG_MAX / 4; + } + force_qs_rnp(rsp, dyntick_save_progress_counter, + &isidle, &maxj); + rcu_sysidle_report_gp(rsp, isidle, maxj); + fqs_state = RCU_FORCE_QS; + } else { + /* Handle dyntick-idle and offline CPUs. */ + isidle = true; + force_qs_rnp(rsp, rcu_implicit_dynticks_qs, &isidle, &maxj); + } + /* Clear flag to prevent immediate re-entry. */ + if (ACCESS_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) { + raw_spin_lock_irq(&rnp->lock); + smp_mb__after_unlock_lock(); + ACCESS_ONCE(rsp->gp_flags) = + ACCESS_ONCE(rsp->gp_flags) & ~RCU_GP_FLAG_FQS; + raw_spin_unlock_irq(&rnp->lock); + } + return fqs_state; +} + +/* + * Clean up after the old grace period. + */ +static void rcu_gp_cleanup(struct rcu_state *rsp) +{ + unsigned long gp_duration; + bool needgp = false; + int nocb = 0; + struct rcu_data *rdp; + struct rcu_node *rnp = rcu_get_root(rsp); + + ACCESS_ONCE(rsp->gp_activity) = jiffies; + raw_spin_lock_irq(&rnp->lock); + smp_mb__after_unlock_lock(); + gp_duration = jiffies - rsp->gp_start; + if (gp_duration > rsp->gp_max) + rsp->gp_max = gp_duration; + + /* + * We know the grace period is complete, but to everyone else + * it appears to still be ongoing. But it is also the case + * that to everyone else it looks like there is nothing that + * they can do to advance the grace period. It is therefore + * safe for us to drop the lock in order to mark the grace + * period as completed in all of the rcu_node structures. + */ + raw_spin_unlock_irq(&rnp->lock); + + /* + * Propagate new ->completed value to rcu_node structures so + * that other CPUs don't have to wait until the start of the next + * grace period to process their callbacks. This also avoids + * some nasty RCU grace-period initialization races by forcing + * the end of the current grace period to be completely recorded in + * all of the rcu_node structures before the beginning of the next + * grace period is recorded in any of the rcu_node structures. + */ + rcu_for_each_node_breadth_first(rsp, rnp) { + raw_spin_lock_irq(&rnp->lock); + smp_mb__after_unlock_lock(); + WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp)); + WARN_ON_ONCE(rnp->qsmask); + ACCESS_ONCE(rnp->completed) = rsp->gpnum; + rdp = this_cpu_ptr(rsp->rda); + if (rnp == rdp->mynode) + needgp = __note_gp_changes(rsp, rnp, rdp) || needgp; + /* smp_mb() provided by prior unlock-lock pair. */ + nocb += rcu_future_gp_cleanup(rsp, rnp); + raw_spin_unlock_irq(&rnp->lock); + cond_resched_rcu_qs(); + ACCESS_ONCE(rsp->gp_activity) = jiffies; + } + rnp = rcu_get_root(rsp); + raw_spin_lock_irq(&rnp->lock); + smp_mb__after_unlock_lock(); /* Order GP before ->completed update. */ + rcu_nocb_gp_set(rnp, nocb); + + /* Declare grace period done. */ + ACCESS_ONCE(rsp->completed) = rsp->gpnum; + trace_rcu_grace_period(rsp->name, rsp->completed, TPS("end")); + rsp->fqs_state = RCU_GP_IDLE; + rdp = this_cpu_ptr(rsp->rda); + /* Advance CBs to reduce false positives below. */ + needgp = rcu_advance_cbs(rsp, rnp, rdp) || needgp; + if (needgp || cpu_needs_another_gp(rsp, rdp)) { + ACCESS_ONCE(rsp->gp_flags) = RCU_GP_FLAG_INIT; + trace_rcu_grace_period(rsp->name, + ACCESS_ONCE(rsp->gpnum), + TPS("newreq")); + } + raw_spin_unlock_irq(&rnp->lock); +} + +/* + * Body of kthread that handles grace periods. + */ +static int __noreturn rcu_gp_kthread(void *arg) +{ + int fqs_state; + int gf; + unsigned long j; + int ret; + struct rcu_state *rsp = arg; + struct rcu_node *rnp = rcu_get_root(rsp); + + rcu_bind_gp_kthread(); + for (;;) { + + /* Handle grace-period start. */ + for (;;) { + trace_rcu_grace_period(rsp->name, + ACCESS_ONCE(rsp->gpnum), + TPS("reqwait")); + rsp->gp_state = RCU_GP_WAIT_GPS; + swait_event_interruptible(rsp->gp_wq, + ACCESS_ONCE(rsp->gp_flags) & + RCU_GP_FLAG_INIT); + /* Locking provides needed memory barrier. */ + if (rcu_gp_init(rsp)) + break; + cond_resched_rcu_qs(); + ACCESS_ONCE(rsp->gp_activity) = jiffies; + WARN_ON(signal_pending(current)); + trace_rcu_grace_period(rsp->name, + ACCESS_ONCE(rsp->gpnum), + TPS("reqwaitsig")); + } + + /* Handle quiescent-state forcing. */ + fqs_state = RCU_SAVE_DYNTICK; + j = jiffies_till_first_fqs; + if (j > HZ) { + j = HZ; + jiffies_till_first_fqs = HZ; + } + ret = 0; + for (;;) { + if (!ret) + rsp->jiffies_force_qs = jiffies + j; + trace_rcu_grace_period(rsp->name, + ACCESS_ONCE(rsp->gpnum), + TPS("fqswait")); + rsp->gp_state = RCU_GP_WAIT_FQS; + ret = swait_event_interruptible_timeout(rsp->gp_wq, + ((gf = ACCESS_ONCE(rsp->gp_flags)) & + RCU_GP_FLAG_FQS) || + (!ACCESS_ONCE(rnp->qsmask) && + !rcu_preempt_blocked_readers_cgp(rnp)), + j); + /* Locking provides needed memory barriers. */ + /* If grace period done, leave loop. */ + if (!ACCESS_ONCE(rnp->qsmask) && + !rcu_preempt_blocked_readers_cgp(rnp)) + break; + /* If time for quiescent-state forcing, do it. */ + if (ULONG_CMP_GE(jiffies, rsp->jiffies_force_qs) || + (gf & RCU_GP_FLAG_FQS)) { + trace_rcu_grace_period(rsp->name, + ACCESS_ONCE(rsp->gpnum), + TPS("fqsstart")); + fqs_state = rcu_gp_fqs(rsp, fqs_state); + trace_rcu_grace_period(rsp->name, + ACCESS_ONCE(rsp->gpnum), + TPS("fqsend")); + cond_resched_rcu_qs(); + ACCESS_ONCE(rsp->gp_activity) = jiffies; + } else { + /* Deal with stray signal. */ + cond_resched_rcu_qs(); + ACCESS_ONCE(rsp->gp_activity) = jiffies; + WARN_ON(signal_pending(current)); + trace_rcu_grace_period(rsp->name, + ACCESS_ONCE(rsp->gpnum), + TPS("fqswaitsig")); + } + j = jiffies_till_next_fqs; + if (j > HZ) { + j = HZ; + jiffies_till_next_fqs = HZ; + } else if (j < 1) { + j = 1; + jiffies_till_next_fqs = 1; + } + } + + /* Handle grace-period end. */ + rcu_gp_cleanup(rsp); + } +} + +/* + * Start a new RCU grace period if warranted, re-initializing the hierarchy + * in preparation for detecting the next grace period. The caller must hold + * the root node's ->lock and hard irqs must be disabled. + * + * Note that it is legal for a dying CPU (which is marked as offline) to + * invoke this function. This can happen when the dying CPU reports its + * quiescent state. + * + * Returns true if the grace-period kthread must be awakened. + */ +static bool +rcu_start_gp_advanced(struct rcu_state *rsp, struct rcu_node *rnp, + struct rcu_data *rdp) +{ + if (!rsp->gp_kthread || !cpu_needs_another_gp(rsp, rdp)) { + /* + * Either we have not yet spawned the grace-period + * task, this CPU does not need another grace period, + * or a grace period is already in progress. + * Either way, don't start a new grace period. + */ + return false; + } + ACCESS_ONCE(rsp->gp_flags) = RCU_GP_FLAG_INIT; + trace_rcu_grace_period(rsp->name, ACCESS_ONCE(rsp->gpnum), + TPS("newreq")); + + /* + * We can't do wakeups while holding the rnp->lock, as that + * could cause possible deadlocks with the rq->lock. Defer + * the wakeup to our caller. + */ + return true; +} + +/* + * Similar to rcu_start_gp_advanced(), but also advance the calling CPU's + * callbacks. Note that rcu_start_gp_advanced() cannot do this because it + * is invoked indirectly from rcu_advance_cbs(), which would result in + * endless recursion -- or would do so if it wasn't for the self-deadlock + * that is encountered beforehand. + * + * Returns true if the grace-period kthread needs to be awakened. + */ +static bool rcu_start_gp(struct rcu_state *rsp) +{ + struct rcu_data *rdp = this_cpu_ptr(rsp->rda); + struct rcu_node *rnp = rcu_get_root(rsp); + bool ret = false; + + /* + * If there is no grace period in progress right now, any + * callbacks we have up to this point will be satisfied by the + * next grace period. Also, advancing the callbacks reduces the + * probability of false positives from cpu_needs_another_gp() + * resulting in pointless grace periods. So, advance callbacks + * then start the grace period! + */ + ret = rcu_advance_cbs(rsp, rnp, rdp) || ret; + ret = rcu_start_gp_advanced(rsp, rnp, rdp) || ret; + return ret; +} + +/* + * Report a full set of quiescent states to the specified rcu_state + * data structure. This involves cleaning up after the prior grace + * period and letting rcu_start_gp() start up the next grace period + * if one is needed. Note that the caller must hold rnp->lock, which + * is released before return. + */ +static void rcu_report_qs_rsp(struct rcu_state *rsp, unsigned long flags) + __releases(rcu_get_root(rsp)->lock) +{ + WARN_ON_ONCE(!rcu_gp_in_progress(rsp)); + raw_spin_unlock_irqrestore(&rcu_get_root(rsp)->lock, flags); + rcu_gp_kthread_wake(rsp); +} + +/* + * Similar to rcu_report_qs_rdp(), for which it is a helper function. + * Allows quiescent states for a group of CPUs to be reported at one go + * to the specified rcu_node structure, though all the CPUs in the group + * must be represented by the same rcu_node structure (which need not be a + * leaf rcu_node structure, though it often will be). The gps parameter + * is the grace-period snapshot, which means that the quiescent states + * are valid only if rnp->gpnum is equal to gps. That structure's lock + * must be held upon entry, and it is released before return. + */ +static void +rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp, + struct rcu_node *rnp, unsigned long gps, unsigned long flags) + __releases(rnp->lock) +{ + unsigned long oldmask = 0; + struct rcu_node *rnp_c; + + /* Walk up the rcu_node hierarchy. */ + for (;;) { + if (!(rnp->qsmask & mask) || rnp->gpnum != gps) { + + /* + * Our bit has already been cleared, or the + * relevant grace period is already over, so done. + */ + raw_spin_unlock_irqrestore(&rnp->lock, flags); + return; + } + WARN_ON_ONCE(oldmask); /* Any child must be all zeroed! */ + rnp->qsmask &= ~mask; + trace_rcu_quiescent_state_report(rsp->name, rnp->gpnum, + mask, rnp->qsmask, rnp->level, + rnp->grplo, rnp->grphi, + !!rnp->gp_tasks); + if (rnp->qsmask != 0 || rcu_preempt_blocked_readers_cgp(rnp)) { + + /* Other bits still set at this level, so done. */ + raw_spin_unlock_irqrestore(&rnp->lock, flags); + return; + } + mask = rnp->grpmask; + if (rnp->parent == NULL) { + + /* No more levels. Exit loop holding root lock. */ + + break; + } + raw_spin_unlock_irqrestore(&rnp->lock, flags); + rnp_c = rnp; + rnp = rnp->parent; + raw_spin_lock_irqsave(&rnp->lock, flags); + smp_mb__after_unlock_lock(); + oldmask = rnp_c->qsmask; + } + + /* + * Get here if we are the last CPU to pass through a quiescent + * state for this grace period. Invoke rcu_report_qs_rsp() + * to clean up and start the next grace period if one is needed. + */ + rcu_report_qs_rsp(rsp, flags); /* releases rnp->lock. */ +} + +/* + * Record a quiescent state for all tasks that were previously queued + * on the specified rcu_node structure and that were blocking the current + * RCU grace period. The caller must hold the specified rnp->lock with + * irqs disabled, and this lock is released upon return, but irqs remain + * disabled. + */ +static void rcu_report_unblock_qs_rnp(struct rcu_state *rsp, + struct rcu_node *rnp, unsigned long flags) + __releases(rnp->lock) +{ + unsigned long gps; + unsigned long mask; + struct rcu_node *rnp_p; + + if (rcu_state_p == &rcu_sched_state || rsp != rcu_state_p || + rnp->qsmask != 0 || rcu_preempt_blocked_readers_cgp(rnp)) { + raw_spin_unlock_irqrestore(&rnp->lock, flags); + return; /* Still need more quiescent states! */ + } + + rnp_p = rnp->parent; + if (rnp_p == NULL) { + /* + * Only one rcu_node structure in the tree, so don't + * try to report up to its nonexistent parent! + */ + rcu_report_qs_rsp(rsp, flags); + return; + } + + /* Report up the rest of the hierarchy, tracking current ->gpnum. */ + gps = rnp->gpnum; + mask = rnp->grpmask; + raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */ + raw_spin_lock(&rnp_p->lock); /* irqs already disabled. */ + smp_mb__after_unlock_lock(); + rcu_report_qs_rnp(mask, rsp, rnp_p, gps, flags); +} + +/* + * Record a quiescent state for the specified CPU to that CPU's rcu_data + * structure. This must be either called from the specified CPU, or + * called when the specified CPU is known to be offline (and when it is + * also known that no other CPU is concurrently trying to help the offline + * CPU). The lastcomp argument is used to make sure we are still in the + * grace period of interest. We don't want to end the current grace period + * based on quiescent states detected in an earlier grace period! + */ +static void +rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp) +{ + unsigned long flags; + unsigned long mask; + bool needwake; + struct rcu_node *rnp; + + rnp = rdp->mynode; + raw_spin_lock_irqsave(&rnp->lock, flags); + smp_mb__after_unlock_lock(); + if ((rdp->passed_quiesce == 0 && + rdp->rcu_qs_ctr_snap == __this_cpu_read(rcu_qs_ctr)) || + rdp->gpnum != rnp->gpnum || rnp->completed == rnp->gpnum || + rdp->gpwrap) { + + /* + * The grace period in which this quiescent state was + * recorded has ended, so don't report it upwards. + * We will instead need a new quiescent state that lies + * within the current grace period. + */ + rdp->passed_quiesce = 0; /* need qs for new gp. */ + rdp->rcu_qs_ctr_snap = __this_cpu_read(rcu_qs_ctr); + raw_spin_unlock_irqrestore(&rnp->lock, flags); + return; + } + mask = rdp->grpmask; + if ((rnp->qsmask & mask) == 0) { + raw_spin_unlock_irqrestore(&rnp->lock, flags); + } else { + rdp->qs_pending = 0; + + /* + * This GP can't end until cpu checks in, so all of our + * callbacks can be processed during the next GP. + */ + needwake = rcu_accelerate_cbs(rsp, rnp, rdp); + + rcu_report_qs_rnp(mask, rsp, rnp, rnp->gpnum, flags); + /* ^^^ Released rnp->lock */ + if (needwake) + rcu_gp_kthread_wake(rsp); + } +} + +/* + * Check to see if there is a new grace period of which this CPU + * is not yet aware, and if so, set up local rcu_data state for it. + * Otherwise, see if this CPU has just passed through its first + * quiescent state for this grace period, and record that fact if so. + */ +static void +rcu_check_quiescent_state(struct rcu_state *rsp, struct rcu_data *rdp) +{ + /* Check for grace-period ends and beginnings. */ + note_gp_changes(rsp, rdp); + + /* + * Does this CPU still need to do its part for current grace period? + * If no, return and let the other CPUs do their part as well. + */ + if (!rdp->qs_pending) + return; + + /* + * Was there a quiescent state since the beginning of the grace + * period? If no, then exit and wait for the next call. + */ + if (!rdp->passed_quiesce && + rdp->rcu_qs_ctr_snap == __this_cpu_read(rcu_qs_ctr)) + return; + + /* + * Tell RCU we are done (but rcu_report_qs_rdp() will be the + * judge of that). + */ + rcu_report_qs_rdp(rdp->cpu, rsp, rdp); +} + +#ifdef CONFIG_HOTPLUG_CPU + +/* + * Send the specified CPU's RCU callbacks to the orphanage. The + * specified CPU must be offline, and the caller must hold the + * ->orphan_lock. + */ +static void +rcu_send_cbs_to_orphanage(int cpu, struct rcu_state *rsp, + struct rcu_node *rnp, struct rcu_data *rdp) +{ + /* No-CBs CPUs do not have orphanable callbacks. */ + if (rcu_is_nocb_cpu(rdp->cpu)) + return; + + /* + * Orphan the callbacks. First adjust the counts. This is safe + * because _rcu_barrier() excludes CPU-hotplug operations, so it + * cannot be running now. Thus no memory barrier is required. + */ + if (rdp->nxtlist != NULL) { + rsp->qlen_lazy += rdp->qlen_lazy; + rsp->qlen += rdp->qlen; + rdp->n_cbs_orphaned += rdp->qlen; + rdp->qlen_lazy = 0; + ACCESS_ONCE(rdp->qlen) = 0; + } + + /* + * Next, move those callbacks still needing a grace period to + * the orphanage, where some other CPU will pick them up. + * Some of the callbacks might have gone partway through a grace + * period, but that is too bad. They get to start over because we + * cannot assume that grace periods are synchronized across CPUs. + * We don't bother updating the ->nxttail[] array yet, instead + * we just reset the whole thing later on. + */ + if (*rdp->nxttail[RCU_DONE_TAIL] != NULL) { + *rsp->orphan_nxttail = *rdp->nxttail[RCU_DONE_TAIL]; + rsp->orphan_nxttail = rdp->nxttail[RCU_NEXT_TAIL]; + *rdp->nxttail[RCU_DONE_TAIL] = NULL; + } + + /* + * Then move the ready-to-invoke callbacks to the orphanage, + * where some other CPU will pick them up. These will not be + * required to pass though another grace period: They are done. + */ + if (rdp->nxtlist != NULL) { + *rsp->orphan_donetail = rdp->nxtlist; + rsp->orphan_donetail = rdp->nxttail[RCU_DONE_TAIL]; + } + + /* + * Finally, initialize the rcu_data structure's list to empty and + * disallow further callbacks on this CPU. + */ + init_callback_list(rdp); + rdp->nxttail[RCU_NEXT_TAIL] = NULL; +} + +/* + * Adopt the RCU callbacks from the specified rcu_state structure's + * orphanage. The caller must hold the ->orphan_lock. + */ +static void rcu_adopt_orphan_cbs(struct rcu_state *rsp, unsigned long flags) +{ + int i; + struct rcu_data *rdp = raw_cpu_ptr(rsp->rda); + + /* No-CBs CPUs are handled specially. */ + if (rcu_nocb_adopt_orphan_cbs(rsp, rdp, flags)) + return; + + /* Do the accounting first. */ + rdp->qlen_lazy += rsp->qlen_lazy; + rdp->qlen += rsp->qlen; + rdp->n_cbs_adopted += rsp->qlen; + if (rsp->qlen_lazy != rsp->qlen) + rcu_idle_count_callbacks_posted(); + rsp->qlen_lazy = 0; + rsp->qlen = 0; + + /* + * We do not need a memory barrier here because the only way we + * can get here if there is an rcu_barrier() in flight is if + * we are the task doing the rcu_barrier(). + */ + + /* First adopt the ready-to-invoke callbacks. */ + if (rsp->orphan_donelist != NULL) { + *rsp->orphan_donetail = *rdp->nxttail[RCU_DONE_TAIL]; + *rdp->nxttail[RCU_DONE_TAIL] = rsp->orphan_donelist; + for (i = RCU_NEXT_SIZE - 1; i >= RCU_DONE_TAIL; i--) + if (rdp->nxttail[i] == rdp->nxttail[RCU_DONE_TAIL]) + rdp->nxttail[i] = rsp->orphan_donetail; + rsp->orphan_donelist = NULL; + rsp->orphan_donetail = &rsp->orphan_donelist; + } + + /* And then adopt the callbacks that still need a grace period. */ + if (rsp->orphan_nxtlist != NULL) { + *rdp->nxttail[RCU_NEXT_TAIL] = rsp->orphan_nxtlist; + rdp->nxttail[RCU_NEXT_TAIL] = rsp->orphan_nxttail; + rsp->orphan_nxtlist = NULL; + rsp->orphan_nxttail = &rsp->orphan_nxtlist; + } +} + +/* + * Trace the fact that this CPU is going offline. + */ +static void rcu_cleanup_dying_cpu(struct rcu_state *rsp) +{ + RCU_TRACE(unsigned long mask); + RCU_TRACE(struct rcu_data *rdp = this_cpu_ptr(rsp->rda)); + RCU_TRACE(struct rcu_node *rnp = rdp->mynode); + + RCU_TRACE(mask = rdp->grpmask); + trace_rcu_grace_period(rsp->name, + rnp->gpnum + 1 - !!(rnp->qsmask & mask), + TPS("cpuofl")); +} + +/* + * All CPUs for the specified rcu_node structure have gone offline, + * and all tasks that were preempted within an RCU read-side critical + * section while running on one of those CPUs have since exited their RCU + * read-side critical section. Some other CPU is reporting this fact with + * the specified rcu_node structure's ->lock held and interrupts disabled. + * This function therefore goes up the tree of rcu_node structures, + * clearing the corresponding bits in the ->qsmaskinit fields. Note that + * the leaf rcu_node structure's ->qsmaskinit field has already been + * updated + * + * This function does check that the specified rcu_node structure has + * all CPUs offline and no blocked tasks, so it is OK to invoke it + * prematurely. That said, invoking it after the fact will cost you + * a needless lock acquisition. So once it has done its work, don't + * invoke it again. + */ +static void rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf) +{ + long mask; + struct rcu_node *rnp = rnp_leaf; + + if (rnp->qsmaskinit || rcu_preempt_has_tasks(rnp)) + return; + for (;;) { + mask = rnp->grpmask; + rnp = rnp->parent; + if (!rnp) + break; + raw_spin_lock(&rnp->lock); /* irqs already disabled. */ + smp_mb__after_unlock_lock(); /* GP memory ordering. */ + rnp->qsmaskinit &= ~mask; + rnp->qsmask &= ~mask; + if (rnp->qsmaskinit) { + raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */ + return; + } + raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */ + } +} + +/* + * The CPU is exiting the idle loop into the arch_cpu_idle_dead() + * function. We now remove it from the rcu_node tree's ->qsmaskinit + * bit masks. + */ +static void rcu_cleanup_dying_idle_cpu(int cpu, struct rcu_state *rsp) +{ + unsigned long flags; + unsigned long mask; + struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu); + struct rcu_node *rnp = rdp->mynode; /* Outgoing CPU's rdp & rnp. */ + + /* Remove outgoing CPU from mask in the leaf rcu_node structure. */ + mask = rdp->grpmask; + raw_spin_lock_irqsave(&rnp->lock, flags); + smp_mb__after_unlock_lock(); /* Enforce GP memory-order guarantee. */ + rnp->qsmaskinitnext &= ~mask; + raw_spin_unlock_irqrestore(&rnp->lock, flags); +} + +/* + * The CPU has been completely removed, and some other CPU is reporting + * this fact from process context. Do the remainder of the cleanup, + * including orphaning the outgoing CPU's RCU callbacks, and also + * adopting them. There can only be one CPU hotplug operation at a time, + * so no other CPU can be attempting to update rcu_cpu_kthread_task. + */ +static void rcu_cleanup_dead_cpu(int cpu, struct rcu_state *rsp) +{ + unsigned long flags; + struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu); + struct rcu_node *rnp = rdp->mynode; /* Outgoing CPU's rdp & rnp. */ + + /* Adjust any no-longer-needed kthreads. */ + rcu_boost_kthread_setaffinity(rnp, -1); + + /* Orphan the dead CPU's callbacks, and adopt them if appropriate. */ + raw_spin_lock_irqsave(&rsp->orphan_lock, flags); + rcu_send_cbs_to_orphanage(cpu, rsp, rnp, rdp); + rcu_adopt_orphan_cbs(rsp, flags); + raw_spin_unlock_irqrestore(&rsp->orphan_lock, flags); + + WARN_ONCE(rdp->qlen != 0 || rdp->nxtlist != NULL, + "rcu_cleanup_dead_cpu: Callbacks on offline CPU %d: qlen=%lu, nxtlist=%p\n", + cpu, rdp->qlen, rdp->nxtlist); +} + +#else /* #ifdef CONFIG_HOTPLUG_CPU */ + +static void rcu_cleanup_dying_cpu(struct rcu_state *rsp) +{ +} + +static void __maybe_unused rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf) +{ +} + +static void rcu_cleanup_dying_idle_cpu(int cpu, struct rcu_state *rsp) +{ +} + +static void rcu_cleanup_dead_cpu(int cpu, struct rcu_state *rsp) +{ +} + +#endif /* #else #ifdef CONFIG_HOTPLUG_CPU */ + +/* + * Invoke any RCU callbacks that have made it to the end of their grace + * period. Thottle as specified by rdp->blimit. + */ +static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp) +{ + unsigned long flags; + struct rcu_head *next, *list, **tail; + long bl, count, count_lazy; + int i; + + /* If no callbacks are ready, just return. */ + if (!cpu_has_callbacks_ready_to_invoke(rdp)) { + trace_rcu_batch_start(rsp->name, rdp->qlen_lazy, rdp->qlen, 0); + trace_rcu_batch_end(rsp->name, 0, !!ACCESS_ONCE(rdp->nxtlist), + need_resched(), is_idle_task(current), + rcu_is_callbacks_kthread()); + return; + } + + /* + * Extract the list of ready callbacks, disabling to prevent + * races with call_rcu() from interrupt handlers. + */ + local_irq_save(flags); + WARN_ON_ONCE(cpu_is_offline(smp_processor_id())); + bl = rdp->blimit; + trace_rcu_batch_start(rsp->name, rdp->qlen_lazy, rdp->qlen, bl); + list = rdp->nxtlist; + rdp->nxtlist = *rdp->nxttail[RCU_DONE_TAIL]; + *rdp->nxttail[RCU_DONE_TAIL] = NULL; + tail = rdp->nxttail[RCU_DONE_TAIL]; + for (i = RCU_NEXT_SIZE - 1; i >= 0; i--) + if (rdp->nxttail[i] == rdp->nxttail[RCU_DONE_TAIL]) + rdp->nxttail[i] = &rdp->nxtlist; + local_irq_restore(flags); + + /* Invoke callbacks. */ + count = count_lazy = 0; + while (list) { + next = list->next; + prefetch(next); + debug_rcu_head_unqueue(list); + if (__rcu_reclaim(rsp->name, list)) + count_lazy++; + list = next; + /* Stop only if limit reached and CPU has something to do. */ + if (++count >= bl && + (need_resched() || + (!is_idle_task(current) && !rcu_is_callbacks_kthread()))) + break; + } + + local_irq_save(flags); + trace_rcu_batch_end(rsp->name, count, !!list, need_resched(), + is_idle_task(current), + rcu_is_callbacks_kthread()); + + /* Update count, and requeue any remaining callbacks. */ + if (list != NULL) { + *tail = rdp->nxtlist; + rdp->nxtlist = list; + for (i = 0; i < RCU_NEXT_SIZE; i++) + if (&rdp->nxtlist == rdp->nxttail[i]) + rdp->nxttail[i] = tail; + else + break; + } + smp_mb(); /* List handling before counting for rcu_barrier(). */ + rdp->qlen_lazy -= count_lazy; + ACCESS_ONCE(rdp->qlen) = rdp->qlen - count; + rdp->n_cbs_invoked += count; + + /* Reinstate batch limit if we have worked down the excess. */ + if (rdp->blimit == LONG_MAX && rdp->qlen <= qlowmark) + rdp->blimit = blimit; + + /* Reset ->qlen_last_fqs_check trigger if enough CBs have drained. */ + if (rdp->qlen == 0 && rdp->qlen_last_fqs_check != 0) { + rdp->qlen_last_fqs_check = 0; + rdp->n_force_qs_snap = rsp->n_force_qs; + } else if (rdp->qlen < rdp->qlen_last_fqs_check - qhimark) + rdp->qlen_last_fqs_check = rdp->qlen; + WARN_ON_ONCE((rdp->nxtlist == NULL) != (rdp->qlen == 0)); + + local_irq_restore(flags); + + /* Re-invoke RCU core processing if there are callbacks remaining. */ + if (cpu_has_callbacks_ready_to_invoke(rdp)) + invoke_rcu_core(); +} + +/* + * Check to see if this CPU is in a non-context-switch quiescent state + * (user mode or idle loop for rcu, non-softirq execution for rcu_bh). + * Also schedule RCU core processing. + * + * This function must be called from hardirq context. It is normally + * invoked from the scheduling-clock interrupt. If rcu_pending returns + * false, there is no point in invoking rcu_check_callbacks(). + */ +void rcu_check_callbacks(int user) +{ + trace_rcu_utilization(TPS("Start scheduler-tick")); + increment_cpu_stall_ticks(); + if (user || rcu_is_cpu_rrupt_from_idle()) { + + /* + * Get here if this CPU took its interrupt from user + * mode or from the idle loop, and if this is not a + * nested interrupt. In this case, the CPU is in + * a quiescent state, so note it. + * + * No memory barrier is required here because both + * rcu_sched_qs() and rcu_bh_qs() reference only CPU-local + * variables that other CPUs neither access nor modify, + * at least not while the corresponding CPU is online. + */ + + rcu_sched_qs(); + rcu_bh_qs(); + + } else if (!in_softirq()) { + + /* + * Get here if this CPU did not take its interrupt from + * softirq, in other words, if it is not interrupting + * a rcu_bh read-side critical section. This is an _bh + * critical section, so note it. + */ + + rcu_bh_qs(); + } + rcu_preempt_check_callbacks(); + if (rcu_pending()) + invoke_rcu_core(); + if (user) + rcu_note_voluntary_context_switch(current); + trace_rcu_utilization(TPS("End scheduler-tick")); +} + +/* + * Scan the leaf rcu_node structures, processing dyntick state for any that + * have not yet encountered a quiescent state, using the function specified. + * Also initiate boosting for any threads blocked on the root rcu_node. + * + * The caller must have suppressed start of new grace periods. + */ +static void force_qs_rnp(struct rcu_state *rsp, + int (*f)(struct rcu_data *rsp, bool *isidle, + unsigned long *maxj), + bool *isidle, unsigned long *maxj) +{ + unsigned long bit; + int cpu; + unsigned long flags; + unsigned long mask; + struct rcu_node *rnp; + + rcu_for_each_leaf_node(rsp, rnp) { + cond_resched_rcu_qs(); + mask = 0; + raw_spin_lock_irqsave(&rnp->lock, flags); + smp_mb__after_unlock_lock(); + if (!rcu_gp_in_progress(rsp)) { + raw_spin_unlock_irqrestore(&rnp->lock, flags); + return; + } + if (rnp->qsmask == 0) { + if (rcu_state_p == &rcu_sched_state || + rsp != rcu_state_p || + rcu_preempt_blocked_readers_cgp(rnp)) { + /* + * No point in scanning bits because they + * are all zero. But we might need to + * priority-boost blocked readers. + */ + rcu_initiate_boost(rnp, flags); + /* rcu_initiate_boost() releases rnp->lock */ + continue; + } + if (rnp->parent && + (rnp->parent->qsmask & rnp->grpmask)) { + /* + * Race between grace-period + * initialization and task exiting RCU + * read-side critical section: Report. + */ + rcu_report_unblock_qs_rnp(rsp, rnp, flags); + /* rcu_report_unblock_qs_rnp() rlses ->lock */ + continue; + } + } + cpu = rnp->grplo; + bit = 1; + for (; cpu <= rnp->grphi; cpu++, bit <<= 1) { + if ((rnp->qsmask & bit) != 0) { + if ((rnp->qsmaskinit & bit) == 0) + *isidle = false; /* Pending hotplug. */ + if (f(per_cpu_ptr(rsp->rda, cpu), isidle, maxj)) + mask |= bit; + } + } + if (mask != 0) { + /* Idle/offline CPUs, report (releases rnp->lock. */ + rcu_report_qs_rnp(mask, rsp, rnp, rnp->gpnum, flags); + } else { + /* Nothing to do here, so just drop the lock. */ + raw_spin_unlock_irqrestore(&rnp->lock, flags); + } + } +} + +/* + * Force quiescent states on reluctant CPUs, and also detect which + * CPUs are in dyntick-idle mode. + */ +static void force_quiescent_state(struct rcu_state *rsp) +{ + unsigned long flags; + bool ret; + struct rcu_node *rnp; + struct rcu_node *rnp_old = NULL; + + /* Funnel through hierarchy to reduce memory contention. */ + rnp = __this_cpu_read(rsp->rda->mynode); + for (; rnp != NULL; rnp = rnp->parent) { + ret = (ACCESS_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) || + !raw_spin_trylock(&rnp->fqslock); + if (rnp_old != NULL) + raw_spin_unlock(&rnp_old->fqslock); + if (ret) { + rsp->n_force_qs_lh++; + return; + } + rnp_old = rnp; + } + /* rnp_old == rcu_get_root(rsp), rnp == NULL. */ + + /* Reached the root of the rcu_node tree, acquire lock. */ + raw_spin_lock_irqsave(&rnp_old->lock, flags); + smp_mb__after_unlock_lock(); + raw_spin_unlock(&rnp_old->fqslock); + if (ACCESS_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) { + rsp->n_force_qs_lh++; + raw_spin_unlock_irqrestore(&rnp_old->lock, flags); + return; /* Someone beat us to it. */ + } + ACCESS_ONCE(rsp->gp_flags) = + ACCESS_ONCE(rsp->gp_flags) | RCU_GP_FLAG_FQS; + raw_spin_unlock_irqrestore(&rnp_old->lock, flags); + rcu_gp_kthread_wake(rsp); +} + +/* + * This does the RCU core processing work for the specified rcu_state + * and rcu_data structures. This may be called only from the CPU to + * whom the rdp belongs. + */ +static void +__rcu_process_callbacks(struct rcu_state *rsp) +{ + unsigned long flags; + bool needwake; + struct rcu_data *rdp = raw_cpu_ptr(rsp->rda); + + WARN_ON_ONCE(rdp->beenonline == 0); + + /* Update RCU state based on any recent quiescent states. */ + rcu_check_quiescent_state(rsp, rdp); + + /* Does this CPU require a not-yet-started grace period? */ + local_irq_save(flags); + if (cpu_needs_another_gp(rsp, rdp)) { + raw_spin_lock(&rcu_get_root(rsp)->lock); /* irqs disabled. */ + needwake = rcu_start_gp(rsp); + raw_spin_unlock_irqrestore(&rcu_get_root(rsp)->lock, flags); + if (needwake) + rcu_gp_kthread_wake(rsp); + } else { + local_irq_restore(flags); + } + + /* If there are callbacks ready, invoke them. */ + if (cpu_has_callbacks_ready_to_invoke(rdp)) + invoke_rcu_callbacks(rsp, rdp); + + /* Do any needed deferred wakeups of rcuo kthreads. */ + do_nocb_deferred_wakeup(rdp); +} + +/* + * Do RCU core processing for the current CPU. + */ +static void rcu_process_callbacks(void) +{ + struct rcu_state *rsp; + + if (cpu_is_offline(smp_processor_id())) + return; + for_each_rcu_flavor(rsp) + __rcu_process_callbacks(rsp); +} + +static DEFINE_PER_CPU(struct task_struct *, rcu_cpu_kthread_task); +/* + * Schedule RCU callback invocation. If the specified type of RCU + * does not support RCU priority boosting, just do a direct call, + * otherwise wake up the per-CPU kernel kthread. Note that because we + * are running on the current CPU with softirqs disabled, the + * rcu_cpu_kthread_task cannot disappear out from under us. + */ +static void invoke_rcu_callbacks(struct rcu_state *rsp, struct rcu_data *rdp) +{ + if (unlikely(!ACCESS_ONCE(rcu_scheduler_fully_active))) + return; + rcu_do_batch(rsp, rdp); +} + +static void rcu_wake_cond(struct task_struct *t, int status) +{ + /* + * If the thread is yielding, only wake it when this + * is invoked from idle + */ + if (t && (status != RCU_KTHREAD_YIELDING || is_idle_task(current))) + wake_up_process(t); +} + +/* + * Wake up this CPU's rcuc kthread to do RCU core processing. + */ +static void invoke_rcu_core(void) +{ + unsigned long flags; + struct task_struct *t; + + if (!cpu_online(smp_processor_id())) + return; + local_irq_save(flags); + __this_cpu_write(rcu_cpu_has_work, 1); + t = __this_cpu_read(rcu_cpu_kthread_task); + if (t != NULL && current != t) + rcu_wake_cond(t, __this_cpu_read(rcu_cpu_kthread_status)); + local_irq_restore(flags); +} + +static void rcu_cpu_kthread_park(unsigned int cpu) +{ + per_cpu(rcu_cpu_kthread_status, cpu) = RCU_KTHREAD_OFFCPU; +} + +static int rcu_cpu_kthread_should_run(unsigned int cpu) +{ + return __this_cpu_read(rcu_cpu_has_work); +} + +/* + * Per-CPU kernel thread that invokes RCU callbacks. This replaces the + * RCU softirq used in flavors and configurations of RCU that do not + * support RCU priority boosting. + */ +static void rcu_cpu_kthread(unsigned int cpu) +{ + unsigned int *statusp = this_cpu_ptr(&rcu_cpu_kthread_status); + char work, *workp = this_cpu_ptr(&rcu_cpu_has_work); + int spincnt; + + for (spincnt = 0; spincnt < 10; spincnt++) { + trace_rcu_utilization(TPS("Start CPU kthread@rcu_wait")); + local_bh_disable(); + *statusp = RCU_KTHREAD_RUNNING; + this_cpu_inc(rcu_cpu_kthread_loops); + local_irq_disable(); + work = *workp; + *workp = 0; + local_irq_enable(); + if (work) + rcu_process_callbacks(); + local_bh_enable(); + if (*workp == 0) { + trace_rcu_utilization(TPS("End CPU kthread@rcu_wait")); + *statusp = RCU_KTHREAD_WAITING; + return; + } + } + *statusp = RCU_KTHREAD_YIELDING; + trace_rcu_utilization(TPS("Start CPU kthread@rcu_yield")); + schedule_timeout_interruptible(2); + trace_rcu_utilization(TPS("End CPU kthread@rcu_yield")); + *statusp = RCU_KTHREAD_WAITING; +} + +static struct smp_hotplug_thread rcu_cpu_thread_spec = { + .store = &rcu_cpu_kthread_task, + .thread_should_run = rcu_cpu_kthread_should_run, + .thread_fn = rcu_cpu_kthread, + .thread_comm = "rcuc/%u", + .setup = rcu_cpu_kthread_setup, + .park = rcu_cpu_kthread_park, +}; + +/* + * Spawn per-CPU RCU core processing kthreads. + */ +static int __init rcu_spawn_core_kthreads(void) +{ + int cpu; + + for_each_possible_cpu(cpu) + per_cpu(rcu_cpu_has_work, cpu) = 0; + BUG_ON(smpboot_register_percpu_thread(&rcu_cpu_thread_spec)); + return 0; +} +early_initcall(rcu_spawn_core_kthreads); + +/* + * Handle any core-RCU processing required by a call_rcu() invocation. + */ +static void __call_rcu_core(struct rcu_state *rsp, struct rcu_data *rdp, + struct rcu_head *head, unsigned long flags) +{ + bool needwake; + + /* + * If called from an extended quiescent state, invoke the RCU + * core in order to force a re-evaluation of RCU's idleness. + */ + if (!rcu_is_watching()) + invoke_rcu_core(); + + /* If interrupts were disabled or CPU offline, don't invoke RCU core. */ + if (irqs_disabled_flags(flags) || cpu_is_offline(smp_processor_id())) + return; + + /* + * Force the grace period if too many callbacks or too long waiting. + * Enforce hysteresis, and don't invoke force_quiescent_state() + * if some other CPU has recently done so. Also, don't bother + * invoking force_quiescent_state() if the newly enqueued callback + * is the only one waiting for a grace period to complete. + */ + if (unlikely(rdp->qlen > rdp->qlen_last_fqs_check + qhimark)) { + + /* Are we ignoring a completed grace period? */ + note_gp_changes(rsp, rdp); + + /* Start a new grace period if one not already started. */ + if (!rcu_gp_in_progress(rsp)) { + struct rcu_node *rnp_root = rcu_get_root(rsp); + + raw_spin_lock(&rnp_root->lock); + smp_mb__after_unlock_lock(); + needwake = rcu_start_gp(rsp); + raw_spin_unlock(&rnp_root->lock); + if (needwake) + rcu_gp_kthread_wake(rsp); + } else { + /* Give the grace period a kick. */ + rdp->blimit = LONG_MAX; + if (rsp->n_force_qs == rdp->n_force_qs_snap && + *rdp->nxttail[RCU_DONE_TAIL] != head) + force_quiescent_state(rsp); + rdp->n_force_qs_snap = rsp->n_force_qs; + rdp->qlen_last_fqs_check = rdp->qlen; + } + } +} + +/* + * RCU callback function to leak a callback. + */ +static void rcu_leak_callback(struct rcu_head *rhp) +{ +} + +/* + * Helper function for call_rcu() and friends. The cpu argument will + * normally be -1, indicating "currently running CPU". It may specify + * a CPU only if that CPU is a no-CBs CPU. Currently, only _rcu_barrier() + * is expected to specify a CPU. + */ +static void +__call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu), + struct rcu_state *rsp, int cpu, bool lazy) +{ + unsigned long flags; + struct rcu_data *rdp; + + WARN_ON_ONCE((unsigned long)head & 0x1); /* Misaligned rcu_head! */ + if (debug_rcu_head_queue(head)) { + /* Probable double call_rcu(), so leak the callback. */ + ACCESS_ONCE(head->func) = rcu_leak_callback; + WARN_ONCE(1, "__call_rcu(): Leaked duplicate callback\n"); + return; + } + head->func = func; + head->next = NULL; + + /* + * Opportunistically note grace-period endings and beginnings. + * Note that we might see a beginning right after we see an + * end, but never vice versa, since this CPU has to pass through + * a quiescent state betweentimes. + */ + local_irq_save(flags); + rdp = this_cpu_ptr(rsp->rda); + + /* Add the callback to our list. */ + if (unlikely(rdp->nxttail[RCU_NEXT_TAIL] == NULL) || cpu != -1) { + int offline; + + if (cpu != -1) + rdp = per_cpu_ptr(rsp->rda, cpu); + if (likely(rdp->mynode)) { + /* Post-boot, so this should be for a no-CBs CPU. */ + offline = !__call_rcu_nocb(rdp, head, lazy, flags); + WARN_ON_ONCE(offline); + /* Offline CPU, _call_rcu() illegal, leak callback. */ + local_irq_restore(flags); + return; + } + /* + * Very early boot, before rcu_init(). Initialize if needed + * and then drop through to queue the callback. + */ + BUG_ON(cpu != -1); + WARN_ON_ONCE(!rcu_is_watching()); + if (!likely(rdp->nxtlist)) + init_default_callback_list(rdp); + } + ACCESS_ONCE(rdp->qlen) = rdp->qlen + 1; + if (lazy) + rdp->qlen_lazy++; + else + rcu_idle_count_callbacks_posted(); + smp_mb(); /* Count before adding callback for rcu_barrier(). */ + *rdp->nxttail[RCU_NEXT_TAIL] = head; + rdp->nxttail[RCU_NEXT_TAIL] = &head->next; + + if (__is_kfree_rcu_offset((unsigned long)func)) + trace_rcu_kfree_callback(rsp->name, head, (unsigned long)func, + rdp->qlen_lazy, rdp->qlen); + else + trace_rcu_callback(rsp->name, head, rdp->qlen_lazy, rdp->qlen); + + /* Go handle any RCU core processing required. */ + __call_rcu_core(rsp, rdp, head, flags); + local_irq_restore(flags); +} + +/* + * Queue an RCU-sched callback for invocation after a grace period. + */ +void call_rcu_sched(struct rcu_head *head, void (*func)(struct rcu_head *rcu)) +{ + __call_rcu(head, func, &rcu_sched_state, -1, 0); +} +EXPORT_SYMBOL_GPL(call_rcu_sched); + +#ifndef CONFIG_PREEMPT_RT_FULL +/* + * Queue an RCU callback for invocation after a quicker grace period. + */ +void call_rcu_bh(struct rcu_head *head, void (*func)(struct rcu_head *rcu)) +{ + __call_rcu(head, func, &rcu_bh_state, -1, 0); +} +EXPORT_SYMBOL_GPL(call_rcu_bh); +#endif + +/* + * Queue an RCU callback for lazy invocation after a grace period. + * This will likely be later named something like "call_rcu_lazy()", + * but this change will require some way of tagging the lazy RCU + * callbacks in the list of pending callbacks. Until then, this + * function may only be called from __kfree_rcu(). + */ +void kfree_call_rcu(struct rcu_head *head, + void (*func)(struct rcu_head *rcu)) +{ + __call_rcu(head, func, rcu_state_p, -1, 1); +} +EXPORT_SYMBOL_GPL(kfree_call_rcu); + +/* + * Because a context switch is a grace period for RCU-sched and RCU-bh, + * any blocking grace-period wait automatically implies a grace period + * if there is only one CPU online at any point time during execution + * of either synchronize_sched() or synchronize_rcu_bh(). It is OK to + * occasionally incorrectly indicate that there are multiple CPUs online + * when there was in fact only one the whole time, as this just adds + * some overhead: RCU still operates correctly. + */ +static inline int rcu_blocking_is_gp(void) +{ + int ret; + + might_sleep(); /* Check for RCU read-side critical section. */ + preempt_disable(); + ret = num_online_cpus() <= 1; + preempt_enable(); + return ret; +} + +/** + * synchronize_sched - wait until an rcu-sched grace period has elapsed. + * + * Control will return to the caller some time after a full rcu-sched + * grace period has elapsed, in other words after all currently executing + * rcu-sched read-side critical sections have completed. These read-side + * critical sections are delimited by rcu_read_lock_sched() and + * rcu_read_unlock_sched(), and may be nested. Note that preempt_disable(), + * local_irq_disable(), and so on may be used in place of + * rcu_read_lock_sched(). + * + * This means that all preempt_disable code sequences, including NMI and + * non-threaded hardware-interrupt handlers, in progress on entry will + * have completed before this primitive returns. However, this does not + * guarantee that softirq handlers will have completed, since in some + * kernels, these handlers can run in process context, and can block. + * + * Note that this guarantee implies further memory-ordering guarantees. + * On systems with more than one CPU, when synchronize_sched() returns, + * each CPU is guaranteed to have executed a full memory barrier since the + * end of its last RCU-sched read-side critical section whose beginning + * preceded the call to synchronize_sched(). In addition, each CPU having + * an RCU read-side critical section that extends beyond the return from + * synchronize_sched() is guaranteed to have executed a full memory barrier + * after the beginning of synchronize_sched() and before the beginning of + * that RCU read-side critical section. Note that these guarantees include + * CPUs that are offline, idle, or executing in user mode, as well as CPUs + * that are executing in the kernel. + * + * Furthermore, if CPU A invoked synchronize_sched(), which returned + * to its caller on CPU B, then both CPU A and CPU B are guaranteed + * to have executed a full memory barrier during the execution of + * synchronize_sched() -- even if CPU A and CPU B are the same CPU (but + * again only if the system has more than one CPU). + * + * This primitive provides the guarantees made by the (now removed) + * synchronize_kernel() API. In contrast, synchronize_rcu() only + * guarantees that rcu_read_lock() sections will have completed. + * In "classic RCU", these two guarantees happen to be one and + * the same, but can differ in realtime RCU implementations. + */ +void synchronize_sched(void) +{ + rcu_lockdep_assert(!lock_is_held(&rcu_bh_lock_map) && + !lock_is_held(&rcu_lock_map) && + !lock_is_held(&rcu_sched_lock_map), + "Illegal synchronize_sched() in RCU-sched read-side critical section"); + if (rcu_blocking_is_gp()) + return; + if (rcu_gp_is_expedited()) + synchronize_sched_expedited(); + else + wait_rcu_gp(call_rcu_sched); +} +EXPORT_SYMBOL_GPL(synchronize_sched); + +#ifndef CONFIG_PREEMPT_RT_FULL +/** + * synchronize_rcu_bh - wait until an rcu_bh grace period has elapsed. + * + * Control will return to the caller some time after a full rcu_bh grace + * period has elapsed, in other words after all currently executing rcu_bh + * read-side critical sections have completed. RCU read-side critical + * sections are delimited by rcu_read_lock_bh() and rcu_read_unlock_bh(), + * and may be nested. + * + * See the description of synchronize_sched() for more detailed information + * on memory ordering guarantees. + */ +void synchronize_rcu_bh(void) +{ + rcu_lockdep_assert(!lock_is_held(&rcu_bh_lock_map) && + !lock_is_held(&rcu_lock_map) && + !lock_is_held(&rcu_sched_lock_map), + "Illegal synchronize_rcu_bh() in RCU-bh read-side critical section"); + if (rcu_blocking_is_gp()) + return; + if (rcu_gp_is_expedited()) + synchronize_rcu_bh_expedited(); + else + wait_rcu_gp(call_rcu_bh); +} +EXPORT_SYMBOL_GPL(synchronize_rcu_bh); +#endif + +/** + * get_state_synchronize_rcu - Snapshot current RCU state + * + * Returns a cookie that is used by a later call to cond_synchronize_rcu() + * to determine whether or not a full grace period has elapsed in the + * meantime. + */ +unsigned long get_state_synchronize_rcu(void) +{ + /* + * Any prior manipulation of RCU-protected data must happen + * before the load from ->gpnum. + */ + smp_mb(); /* ^^^ */ + + /* + * Make sure this load happens before the purportedly + * time-consuming work between get_state_synchronize_rcu() + * and cond_synchronize_rcu(). + */ + return smp_load_acquire(&rcu_state_p->gpnum); +} +EXPORT_SYMBOL_GPL(get_state_synchronize_rcu); + +/** + * cond_synchronize_rcu - Conditionally wait for an RCU grace period + * + * @oldstate: return value from earlier call to get_state_synchronize_rcu() + * + * If a full RCU grace period has elapsed since the earlier call to + * get_state_synchronize_rcu(), just return. Otherwise, invoke + * synchronize_rcu() to wait for a full grace period. + * + * Yes, this function does not take counter wrap into account. But + * counter wrap is harmless. If the counter wraps, we have waited for + * more than 2 billion grace periods (and way more on a 64-bit system!), + * so waiting for one additional grace period should be just fine. + */ +void cond_synchronize_rcu(unsigned long oldstate) +{ + unsigned long newstate; + + /* + * Ensure that this load happens before any RCU-destructive + * actions the caller might carry out after we return. + */ + newstate = smp_load_acquire(&rcu_state_p->completed); + if (ULONG_CMP_GE(oldstate, newstate)) + synchronize_rcu(); +} +EXPORT_SYMBOL_GPL(cond_synchronize_rcu); + +static int synchronize_sched_expedited_cpu_stop(void *data) +{ + /* + * There must be a full memory barrier on each affected CPU + * between the time that try_stop_cpus() is called and the + * time that it returns. + * + * In the current initial implementation of cpu_stop, the + * above condition is already met when the control reaches + * this point and the following smp_mb() is not strictly + * necessary. Do smp_mb() anyway for documentation and + * robustness against future implementation changes. + */ + smp_mb(); /* See above comment block. */ + return 0; +} + +/** + * synchronize_sched_expedited - Brute-force RCU-sched grace period + * + * Wait for an RCU-sched grace period to elapse, but use a "big hammer" + * approach to force the grace period to end quickly. This consumes + * significant time on all CPUs and is unfriendly to real-time workloads, + * so is thus not recommended for any sort of common-case code. In fact, + * if you are using synchronize_sched_expedited() in a loop, please + * restructure your code to batch your updates, and then use a single + * synchronize_sched() instead. + * + * This implementation can be thought of as an application of ticket + * locking to RCU, with sync_sched_expedited_started and + * sync_sched_expedited_done taking on the roles of the halves + * of the ticket-lock word. Each task atomically increments + * sync_sched_expedited_started upon entry, snapshotting the old value, + * then attempts to stop all the CPUs. If this succeeds, then each + * CPU will have executed a context switch, resulting in an RCU-sched + * grace period. We are then done, so we use atomic_cmpxchg() to + * update sync_sched_expedited_done to match our snapshot -- but + * only if someone else has not already advanced past our snapshot. + * + * On the other hand, if try_stop_cpus() fails, we check the value + * of sync_sched_expedited_done. If it has advanced past our + * initial snapshot, then someone else must have forced a grace period + * some time after we took our snapshot. In this case, our work is + * done for us, and we can simply return. Otherwise, we try again, + * but keep our initial snapshot for purposes of checking for someone + * doing our work for us. + * + * If we fail too many times in a row, we fall back to synchronize_sched(). + */ +void synchronize_sched_expedited(void) +{ + cpumask_var_t cm; + bool cma = false; + int cpu; + long firstsnap, s, snap; + int trycount = 0; + struct rcu_state *rsp = &rcu_sched_state; + + /* + * If we are in danger of counter wrap, just do synchronize_sched(). + * By allowing sync_sched_expedited_started to advance no more than + * ULONG_MAX/8 ahead of sync_sched_expedited_done, we are ensuring + * that more than 3.5 billion CPUs would be required to force a + * counter wrap on a 32-bit system. Quite a few more CPUs would of + * course be required on a 64-bit system. + */ + if (ULONG_CMP_GE((ulong)atomic_long_read(&rsp->expedited_start), + (ulong)atomic_long_read(&rsp->expedited_done) + + ULONG_MAX / 8)) { + synchronize_sched(); + atomic_long_inc(&rsp->expedited_wrap); + return; + } + + /* + * Take a ticket. Note that atomic_inc_return() implies a + * full memory barrier. + */ + snap = atomic_long_inc_return(&rsp->expedited_start); + firstsnap = snap; + if (!try_get_online_cpus()) { + /* CPU hotplug operation in flight, fall back to normal GP. */ + wait_rcu_gp(call_rcu_sched); + atomic_long_inc(&rsp->expedited_normal); + return; + } + WARN_ON_ONCE(cpu_is_offline(raw_smp_processor_id())); + + /* Offline CPUs, idle CPUs, and any CPU we run on are quiescent. */ + cma = zalloc_cpumask_var(&cm, GFP_KERNEL); + if (cma) { + cpumask_copy(cm, cpu_online_mask); + cpumask_clear_cpu(raw_smp_processor_id(), cm); + for_each_cpu(cpu, cm) { + struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu); + + if (!(atomic_add_return(0, &rdtp->dynticks) & 0x1)) + cpumask_clear_cpu(cpu, cm); + } + if (cpumask_weight(cm) == 0) + goto all_cpus_idle; + } + + /* + * Each pass through the following loop attempts to force a + * context switch on each CPU. + */ + while (try_stop_cpus(cma ? cm : cpu_online_mask, + synchronize_sched_expedited_cpu_stop, + NULL) == -EAGAIN) { + put_online_cpus(); + atomic_long_inc(&rsp->expedited_tryfail); + + /* Check to see if someone else did our work for us. */ + s = atomic_long_read(&rsp->expedited_done); + if (ULONG_CMP_GE((ulong)s, (ulong)firstsnap)) { + /* ensure test happens before caller kfree */ + smp_mb__before_atomic(); /* ^^^ */ + atomic_long_inc(&rsp->expedited_workdone1); + free_cpumask_var(cm); + return; + } + + /* No joy, try again later. Or just synchronize_sched(). */ + if (trycount++ < 10) { + udelay(trycount * num_online_cpus()); + } else { + wait_rcu_gp(call_rcu_sched); + atomic_long_inc(&rsp->expedited_normal); + free_cpumask_var(cm); + return; + } + + /* Recheck to see if someone else did our work for us. */ + s = atomic_long_read(&rsp->expedited_done); + if (ULONG_CMP_GE((ulong)s, (ulong)firstsnap)) { + /* ensure test happens before caller kfree */ + smp_mb__before_atomic(); /* ^^^ */ + atomic_long_inc(&rsp->expedited_workdone2); + free_cpumask_var(cm); + return; + } + + /* + * Refetching sync_sched_expedited_started allows later + * callers to piggyback on our grace period. We retry + * after they started, so our grace period works for them, + * and they started after our first try, so their grace + * period works for us. + */ + if (!try_get_online_cpus()) { + /* CPU hotplug operation in flight, use normal GP. */ + wait_rcu_gp(call_rcu_sched); + atomic_long_inc(&rsp->expedited_normal); + free_cpumask_var(cm); + return; + } + snap = atomic_long_read(&rsp->expedited_start); + smp_mb(); /* ensure read is before try_stop_cpus(). */ + } + atomic_long_inc(&rsp->expedited_stoppedcpus); + +all_cpus_idle: + free_cpumask_var(cm); + + /* + * Everyone up to our most recent fetch is covered by our grace + * period. Update the counter, but only if our work is still + * relevant -- which it won't be if someone who started later + * than we did already did their update. + */ + do { + atomic_long_inc(&rsp->expedited_done_tries); + s = atomic_long_read(&rsp->expedited_done); + if (ULONG_CMP_GE((ulong)s, (ulong)snap)) { + /* ensure test happens before caller kfree */ + smp_mb__before_atomic(); /* ^^^ */ + atomic_long_inc(&rsp->expedited_done_lost); + break; + } + } while (atomic_long_cmpxchg(&rsp->expedited_done, s, snap) != s); + atomic_long_inc(&rsp->expedited_done_exit); + + put_online_cpus(); +} +EXPORT_SYMBOL_GPL(synchronize_sched_expedited); + +/* + * Check to see if there is any immediate RCU-related work to be done + * by the current CPU, for the specified type of RCU, returning 1 if so. + * The checks are in order of increasing expense: checks that can be + * carried out against CPU-local state are performed first. However, + * we must check for CPU stalls first, else we might not get a chance. + */ +static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp) +{ + struct rcu_node *rnp = rdp->mynode; + + rdp->n_rcu_pending++; + + /* Check for CPU stalls, if enabled. */ + check_cpu_stall(rsp, rdp); + + /* Is this CPU a NO_HZ_FULL CPU that should ignore RCU? */ + if (rcu_nohz_full_cpu(rsp)) + return 0; + + /* Is the RCU core waiting for a quiescent state from this CPU? */ + if (rcu_scheduler_fully_active && + rdp->qs_pending && !rdp->passed_quiesce && + rdp->rcu_qs_ctr_snap == __this_cpu_read(rcu_qs_ctr)) { + rdp->n_rp_qs_pending++; + } else if (rdp->qs_pending && + (rdp->passed_quiesce || + rdp->rcu_qs_ctr_snap != __this_cpu_read(rcu_qs_ctr))) { + rdp->n_rp_report_qs++; + return 1; + } + + /* Does this CPU have callbacks ready to invoke? */ + if (cpu_has_callbacks_ready_to_invoke(rdp)) { + rdp->n_rp_cb_ready++; + return 1; + } + + /* Has RCU gone idle with this CPU needing another grace period? */ + if (cpu_needs_another_gp(rsp, rdp)) { + rdp->n_rp_cpu_needs_gp++; + return 1; + } + + /* Has another RCU grace period completed? */ + if (ACCESS_ONCE(rnp->completed) != rdp->completed) { /* outside lock */ + rdp->n_rp_gp_completed++; + return 1; + } + + /* Has a new RCU grace period started? */ + if (ACCESS_ONCE(rnp->gpnum) != rdp->gpnum || + unlikely(ACCESS_ONCE(rdp->gpwrap))) { /* outside lock */ + rdp->n_rp_gp_started++; + return 1; + } + + /* Does this CPU need a deferred NOCB wakeup? */ + if (rcu_nocb_need_deferred_wakeup(rdp)) { + rdp->n_rp_nocb_defer_wakeup++; + return 1; + } + + /* nothing to do */ + rdp->n_rp_need_nothing++; + return 0; +} + +/* + * Check to see if there is any immediate RCU-related work to be done + * by the current CPU, returning 1 if so. This function is part of the + * RCU implementation; it is -not- an exported member of the RCU API. + */ +static int rcu_pending(void) +{ + struct rcu_state *rsp; + + for_each_rcu_flavor(rsp) + if (__rcu_pending(rsp, this_cpu_ptr(rsp->rda))) + return 1; + return 0; +} + +/* + * Return true if the specified CPU has any callback. If all_lazy is + * non-NULL, store an indication of whether all callbacks are lazy. + * (If there are no callbacks, all of them are deemed to be lazy.) + */ +static int __maybe_unused rcu_cpu_has_callbacks(bool *all_lazy) +{ + bool al = true; + bool hc = false; + struct rcu_data *rdp; + struct rcu_state *rsp; + + for_each_rcu_flavor(rsp) { + rdp = this_cpu_ptr(rsp->rda); + if (!rdp->nxtlist) + continue; + hc = true; + if (rdp->qlen != rdp->qlen_lazy || !all_lazy) { + al = false; + break; + } + } + if (all_lazy) + *all_lazy = al; + return hc; +} + +/* + * Helper function for _rcu_barrier() tracing. If tracing is disabled, + * the compiler is expected to optimize this away. + */ +static void _rcu_barrier_trace(struct rcu_state *rsp, const char *s, + int cpu, unsigned long done) +{ + trace_rcu_barrier(rsp->name, s, cpu, + atomic_read(&rsp->barrier_cpu_count), done); +} + +/* + * RCU callback function for _rcu_barrier(). If we are last, wake + * up the task executing _rcu_barrier(). + */ +static void rcu_barrier_callback(struct rcu_head *rhp) +{ + struct rcu_data *rdp = container_of(rhp, struct rcu_data, barrier_head); + struct rcu_state *rsp = rdp->rsp; + + if (atomic_dec_and_test(&rsp->barrier_cpu_count)) { + _rcu_barrier_trace(rsp, "LastCB", -1, rsp->n_barrier_done); + complete(&rsp->barrier_completion); + } else { + _rcu_barrier_trace(rsp, "CB", -1, rsp->n_barrier_done); + } +} + +/* + * Called with preemption disabled, and from cross-cpu IRQ context. + */ +static void rcu_barrier_func(void *type) +{ + struct rcu_state *rsp = type; + struct rcu_data *rdp = raw_cpu_ptr(rsp->rda); + + _rcu_barrier_trace(rsp, "IRQ", -1, rsp->n_barrier_done); + atomic_inc(&rsp->barrier_cpu_count); + rsp->call(&rdp->barrier_head, rcu_barrier_callback); +} + +/* + * Orchestrate the specified type of RCU barrier, waiting for all + * RCU callbacks of the specified type to complete. + */ +static void _rcu_barrier(struct rcu_state *rsp) +{ + int cpu; + struct rcu_data *rdp; + unsigned long snap = ACCESS_ONCE(rsp->n_barrier_done); + unsigned long snap_done; + + _rcu_barrier_trace(rsp, "Begin", -1, snap); + + /* Take mutex to serialize concurrent rcu_barrier() requests. */ + mutex_lock(&rsp->barrier_mutex); + + /* + * Ensure that all prior references, including to ->n_barrier_done, + * are ordered before the _rcu_barrier() machinery. + */ + smp_mb(); /* See above block comment. */ + + /* + * Recheck ->n_barrier_done to see if others did our work for us. + * This means checking ->n_barrier_done for an even-to-odd-to-even + * transition. The "if" expression below therefore rounds the old + * value up to the next even number and adds two before comparing. + */ + snap_done = rsp->n_barrier_done; + _rcu_barrier_trace(rsp, "Check", -1, snap_done); + + /* + * If the value in snap is odd, we needed to wait for the current + * rcu_barrier() to complete, then wait for the next one, in other + * words, we need the value of snap_done to be three larger than + * the value of snap. On the other hand, if the value in snap is + * even, we only had to wait for the next rcu_barrier() to complete, + * in other words, we need the value of snap_done to be only two + * greater than the value of snap. The "(snap + 3) & ~0x1" computes + * this for us (thank you, Linus!). + */ + if (ULONG_CMP_GE(snap_done, (snap + 3) & ~0x1)) { + _rcu_barrier_trace(rsp, "EarlyExit", -1, snap_done); + smp_mb(); /* caller's subsequent code after above check. */ + mutex_unlock(&rsp->barrier_mutex); + return; + } + + /* + * Increment ->n_barrier_done to avoid duplicate work. Use + * ACCESS_ONCE() to prevent the compiler from speculating + * the increment to precede the early-exit check. + */ + ACCESS_ONCE(rsp->n_barrier_done) = rsp->n_barrier_done + 1; + WARN_ON_ONCE((rsp->n_barrier_done & 0x1) != 1); + _rcu_barrier_trace(rsp, "Inc1", -1, rsp->n_barrier_done); + smp_mb(); /* Order ->n_barrier_done increment with below mechanism. */ + + /* + * Initialize the count to one rather than to zero in order to + * avoid a too-soon return to zero in case of a short grace period + * (or preemption of this task). Exclude CPU-hotplug operations + * to ensure that no offline CPU has callbacks queued. + */ + init_completion(&rsp->barrier_completion); + atomic_set(&rsp->barrier_cpu_count, 1); + get_online_cpus(); + + /* + * Force each CPU with callbacks to register a new callback. + * When that callback is invoked, we will know that all of the + * corresponding CPU's preceding callbacks have been invoked. + */ + for_each_possible_cpu(cpu) { + if (!cpu_online(cpu) && !rcu_is_nocb_cpu(cpu)) + continue; + rdp = per_cpu_ptr(rsp->rda, cpu); + if (rcu_is_nocb_cpu(cpu)) { + if (!rcu_nocb_cpu_needs_barrier(rsp, cpu)) { + _rcu_barrier_trace(rsp, "OfflineNoCB", cpu, + rsp->n_barrier_done); + } else { + _rcu_barrier_trace(rsp, "OnlineNoCB", cpu, + rsp->n_barrier_done); + smp_mb__before_atomic(); + atomic_inc(&rsp->barrier_cpu_count); + __call_rcu(&rdp->barrier_head, + rcu_barrier_callback, rsp, cpu, 0); + } + } else if (ACCESS_ONCE(rdp->qlen)) { + _rcu_barrier_trace(rsp, "OnlineQ", cpu, + rsp->n_barrier_done); + smp_call_function_single(cpu, rcu_barrier_func, rsp, 1); + } else { + _rcu_barrier_trace(rsp, "OnlineNQ", cpu, + rsp->n_barrier_done); + } + } + put_online_cpus(); + + /* + * Now that we have an rcu_barrier_callback() callback on each + * CPU, and thus each counted, remove the initial count. + */ + if (atomic_dec_and_test(&rsp->barrier_cpu_count)) + complete(&rsp->barrier_completion); + + /* Increment ->n_barrier_done to prevent duplicate work. */ + smp_mb(); /* Keep increment after above mechanism. */ + ACCESS_ONCE(rsp->n_barrier_done) = rsp->n_barrier_done + 1; + WARN_ON_ONCE((rsp->n_barrier_done & 0x1) != 0); + _rcu_barrier_trace(rsp, "Inc2", -1, rsp->n_barrier_done); + smp_mb(); /* Keep increment before caller's subsequent code. */ + + /* Wait for all rcu_barrier_callback() callbacks to be invoked. */ + wait_for_completion(&rsp->barrier_completion); + + /* Other rcu_barrier() invocations can now safely proceed. */ + mutex_unlock(&rsp->barrier_mutex); +} + +#ifndef CONFIG_PREEMPT_RT_FULL +/** + * rcu_barrier_bh - Wait until all in-flight call_rcu_bh() callbacks complete. + */ +void rcu_barrier_bh(void) +{ + _rcu_barrier(&rcu_bh_state); +} +EXPORT_SYMBOL_GPL(rcu_barrier_bh); +#endif + +/** + * rcu_barrier_sched - Wait for in-flight call_rcu_sched() callbacks. + */ +void rcu_barrier_sched(void) +{ + _rcu_barrier(&rcu_sched_state); +} +EXPORT_SYMBOL_GPL(rcu_barrier_sched); + +/* + * Propagate ->qsinitmask bits up the rcu_node tree to account for the + * first CPU in a given leaf rcu_node structure coming online. The caller + * must hold the corresponding leaf rcu_node ->lock with interrrupts + * disabled. + */ +static void rcu_init_new_rnp(struct rcu_node *rnp_leaf) +{ + long mask; + struct rcu_node *rnp = rnp_leaf; + + for (;;) { + mask = rnp->grpmask; + rnp = rnp->parent; + if (rnp == NULL) + return; + raw_spin_lock(&rnp->lock); /* Interrupts already disabled. */ + rnp->qsmaskinit |= mask; + raw_spin_unlock(&rnp->lock); /* Interrupts remain disabled. */ + } +} + +/* + * Do boot-time initialization of a CPU's per-CPU RCU data. + */ +static void __init +rcu_boot_init_percpu_data(int cpu, struct rcu_state *rsp) +{ + unsigned long flags; + struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu); + struct rcu_node *rnp = rcu_get_root(rsp); + + /* Set up local state, ensuring consistent view of global state. */ + raw_spin_lock_irqsave(&rnp->lock, flags); + rdp->grpmask = 1UL << (cpu - rdp->mynode->grplo); + rdp->dynticks = &per_cpu(rcu_dynticks, cpu); + WARN_ON_ONCE(rdp->dynticks->dynticks_nesting != DYNTICK_TASK_EXIT_IDLE); + WARN_ON_ONCE(atomic_read(&rdp->dynticks->dynticks) != 1); + rdp->cpu = cpu; + rdp->rsp = rsp; + rcu_boot_init_nocb_percpu_data(rdp); + raw_spin_unlock_irqrestore(&rnp->lock, flags); +} + +/* + * Initialize a CPU's per-CPU RCU data. Note that only one online or + * offline event can be happening at a given time. Note also that we + * can accept some slop in the rsp->completed access due to the fact + * that this CPU cannot possibly have any RCU callbacks in flight yet. + */ +static void +rcu_init_percpu_data(int cpu, struct rcu_state *rsp) +{ + unsigned long flags; + unsigned long mask; + struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu); + struct rcu_node *rnp = rcu_get_root(rsp); + + /* Set up local state, ensuring consistent view of global state. */ + raw_spin_lock_irqsave(&rnp->lock, flags); + rdp->beenonline = 1; /* We have now been online. */ + rdp->qlen_last_fqs_check = 0; + rdp->n_force_qs_snap = rsp->n_force_qs; + rdp->blimit = blimit; + if (!rdp->nxtlist) + init_callback_list(rdp); /* Re-enable callbacks on this CPU. */ + rdp->dynticks->dynticks_nesting = DYNTICK_TASK_EXIT_IDLE; + rcu_sysidle_init_percpu_data(rdp->dynticks); + atomic_set(&rdp->dynticks->dynticks, + (atomic_read(&rdp->dynticks->dynticks) & ~0x1) + 1); + raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */ + + /* + * Add CPU to leaf rcu_node pending-online bitmask. Any needed + * propagation up the rcu_node tree will happen at the beginning + * of the next grace period. + */ + rnp = rdp->mynode; + mask = rdp->grpmask; + raw_spin_lock(&rnp->lock); /* irqs already disabled. */ + smp_mb__after_unlock_lock(); + rnp->qsmaskinitnext |= mask; + rdp->gpnum = rnp->completed; /* Make CPU later note any new GP. */ + rdp->completed = rnp->completed; + rdp->passed_quiesce = false; + rdp->rcu_qs_ctr_snap = __this_cpu_read(rcu_qs_ctr); + rdp->qs_pending = false; + trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("cpuonl")); + raw_spin_unlock_irqrestore(&rnp->lock, flags); +} + +static void rcu_prepare_cpu(int cpu) +{ + struct rcu_state *rsp; + + for_each_rcu_flavor(rsp) + rcu_init_percpu_data(cpu, rsp); +} + +/* + * Handle CPU online/offline notification events. + */ +int rcu_cpu_notify(struct notifier_block *self, + unsigned long action, void *hcpu) +{ + long cpu = (long)hcpu; + struct rcu_data *rdp = per_cpu_ptr(rcu_state_p->rda, cpu); + struct rcu_node *rnp = rdp->mynode; + struct rcu_state *rsp; + + switch (action) { + case CPU_UP_PREPARE: + case CPU_UP_PREPARE_FROZEN: + rcu_prepare_cpu(cpu); + rcu_prepare_kthreads(cpu); + rcu_spawn_all_nocb_kthreads(cpu); + break; + case CPU_ONLINE: + case CPU_DOWN_FAILED: + rcu_boost_kthread_setaffinity(rnp, -1); + break; + case CPU_DOWN_PREPARE: + rcu_boost_kthread_setaffinity(rnp, cpu); + break; + case CPU_DYING: + case CPU_DYING_FROZEN: + for_each_rcu_flavor(rsp) + rcu_cleanup_dying_cpu(rsp); + break; + case CPU_DYING_IDLE: + for_each_rcu_flavor(rsp) { + rcu_cleanup_dying_idle_cpu(cpu, rsp); + } + break; + case CPU_DEAD: + case CPU_DEAD_FROZEN: + case CPU_UP_CANCELED: + case CPU_UP_CANCELED_FROZEN: + for_each_rcu_flavor(rsp) { + rcu_cleanup_dead_cpu(cpu, rsp); + do_nocb_deferred_wakeup(per_cpu_ptr(rsp->rda, cpu)); + } + break; + default: + break; + } + return NOTIFY_OK; +} + +static int rcu_pm_notify(struct notifier_block *self, + unsigned long action, void *hcpu) +{ + switch (action) { + case PM_HIBERNATION_PREPARE: + case PM_SUSPEND_PREPARE: + if (nr_cpu_ids <= 256) /* Expediting bad for large systems. */ + rcu_expedite_gp(); + break; + case PM_POST_HIBERNATION: + case PM_POST_SUSPEND: + if (nr_cpu_ids <= 256) /* Expediting bad for large systems. */ + rcu_unexpedite_gp(); + break; + default: + break; + } + return NOTIFY_OK; +} + +/* + * Spawn the kthreads that handle each RCU flavor's grace periods. + */ +static int __init rcu_spawn_gp_kthread(void) +{ + unsigned long flags; + int kthread_prio_in = kthread_prio; + struct rcu_node *rnp; + struct rcu_state *rsp; + struct sched_param sp; + struct task_struct *t; + + /* Force priority into range. */ + if (IS_ENABLED(CONFIG_RCU_BOOST) && kthread_prio < 1) + kthread_prio = 1; + else if (kthread_prio < 0) + kthread_prio = 0; + else if (kthread_prio > 99) + kthread_prio = 99; + if (kthread_prio != kthread_prio_in) + pr_alert("rcu_spawn_gp_kthread(): Limited prio to %d from %d\n", + kthread_prio, kthread_prio_in); + + rcu_scheduler_fully_active = 1; + for_each_rcu_flavor(rsp) { + t = kthread_create(rcu_gp_kthread, rsp, "%s", rsp->name); + BUG_ON(IS_ERR(t)); + rnp = rcu_get_root(rsp); + raw_spin_lock_irqsave(&rnp->lock, flags); + rsp->gp_kthread = t; + if (kthread_prio) { + sp.sched_priority = kthread_prio; + sched_setscheduler_nocheck(t, SCHED_FIFO, &sp); + } + wake_up_process(t); + raw_spin_unlock_irqrestore(&rnp->lock, flags); + } + rcu_spawn_nocb_kthreads(); + rcu_spawn_boost_kthreads(); + return 0; +} +early_initcall(rcu_spawn_gp_kthread); + +/* + * This function is invoked towards the end of the scheduler's initialization + * process. Before this is called, the idle task might contain + * RCU read-side critical sections (during which time, this idle + * task is booting the system). After this function is called, the + * idle tasks are prohibited from containing RCU read-side critical + * sections. This function also enables RCU lockdep checking. + */ +void rcu_scheduler_starting(void) +{ + WARN_ON(num_online_cpus() != 1); + WARN_ON(nr_context_switches() > 0); + rcu_scheduler_active = 1; +} + +/* + * Compute the per-level fanout, either using the exact fanout specified + * or balancing the tree, depending on CONFIG_RCU_FANOUT_EXACT. + */ +static void __init rcu_init_levelspread(struct rcu_state *rsp) +{ + int i; + + if (IS_ENABLED(CONFIG_RCU_FANOUT_EXACT)) { + rsp->levelspread[rcu_num_lvls - 1] = rcu_fanout_leaf; + for (i = rcu_num_lvls - 2; i >= 0; i--) + rsp->levelspread[i] = CONFIG_RCU_FANOUT; + } else { + int ccur; + int cprv; + + cprv = nr_cpu_ids; + for (i = rcu_num_lvls - 1; i >= 0; i--) { + ccur = rsp->levelcnt[i]; + rsp->levelspread[i] = (cprv + ccur - 1) / ccur; + cprv = ccur; + } + } +} + +/* + * Helper function for rcu_init() that initializes one rcu_state structure. + */ +static void __init rcu_init_one(struct rcu_state *rsp, + struct rcu_data __percpu *rda) +{ + static const char * const buf[] = { + "rcu_node_0", + "rcu_node_1", + "rcu_node_2", + "rcu_node_3" }; /* Match MAX_RCU_LVLS */ + static const char * const fqs[] = { + "rcu_node_fqs_0", + "rcu_node_fqs_1", + "rcu_node_fqs_2", + "rcu_node_fqs_3" }; /* Match MAX_RCU_LVLS */ + static u8 fl_mask = 0x1; + int cpustride = 1; + int i; + int j; + struct rcu_node *rnp; + + BUILD_BUG_ON(MAX_RCU_LVLS > ARRAY_SIZE(buf)); /* Fix buf[] init! */ + + /* Silence gcc 4.8 warning about array index out of range. */ + if (rcu_num_lvls > RCU_NUM_LVLS) + panic("rcu_init_one: rcu_num_lvls overflow"); + + /* Initialize the level-tracking arrays. */ + + for (i = 0; i < rcu_num_lvls; i++) + rsp->levelcnt[i] = num_rcu_lvl[i]; + for (i = 1; i < rcu_num_lvls; i++) + rsp->level[i] = rsp->level[i - 1] + rsp->levelcnt[i - 1]; + rcu_init_levelspread(rsp); + rsp->flavor_mask = fl_mask; + fl_mask <<= 1; + + /* Initialize the elements themselves, starting from the leaves. */ + + for (i = rcu_num_lvls - 1; i >= 0; i--) { + cpustride *= rsp->levelspread[i]; + rnp = rsp->level[i]; + for (j = 0; j < rsp->levelcnt[i]; j++, rnp++) { + raw_spin_lock_init(&rnp->lock); + lockdep_set_class_and_name(&rnp->lock, + &rcu_node_class[i], buf[i]); + raw_spin_lock_init(&rnp->fqslock); + lockdep_set_class_and_name(&rnp->fqslock, + &rcu_fqs_class[i], fqs[i]); + rnp->gpnum = rsp->gpnum; + rnp->completed = rsp->completed; + rnp->qsmask = 0; + rnp->qsmaskinit = 0; + rnp->grplo = j * cpustride; + rnp->grphi = (j + 1) * cpustride - 1; + if (rnp->grphi >= nr_cpu_ids) + rnp->grphi = nr_cpu_ids - 1; + if (i == 0) { + rnp->grpnum = 0; + rnp->grpmask = 0; + rnp->parent = NULL; + } else { + rnp->grpnum = j % rsp->levelspread[i - 1]; + rnp->grpmask = 1UL << rnp->grpnum; + rnp->parent = rsp->level[i - 1] + + j / rsp->levelspread[i - 1]; + } + rnp->level = i; + INIT_LIST_HEAD(&rnp->blkd_tasks); + rcu_init_one_nocb(rnp); + } + } + + init_swait_head(&rsp->gp_wq); + rnp = rsp->level[rcu_num_lvls - 1]; + for_each_possible_cpu(i) { + while (i > rnp->grphi) + rnp++; + per_cpu_ptr(rsp->rda, i)->mynode = rnp; + rcu_boot_init_percpu_data(i, rsp); + } + list_add(&rsp->flavors, &rcu_struct_flavors); +} + +/* + * Compute the rcu_node tree geometry from kernel parameters. This cannot + * replace the definitions in tree.h because those are needed to size + * the ->node array in the rcu_state structure. + */ +static void __init rcu_init_geometry(void) +{ + ulong d; + int i; + int j; + int n = nr_cpu_ids; + int rcu_capacity[MAX_RCU_LVLS + 1]; + + /* + * Initialize any unspecified boot parameters. + * The default values of jiffies_till_first_fqs and + * jiffies_till_next_fqs are set to the RCU_JIFFIES_TILL_FORCE_QS + * value, which is a function of HZ, then adding one for each + * RCU_JIFFIES_FQS_DIV CPUs that might be on the system. + */ + d = RCU_JIFFIES_TILL_FORCE_QS + nr_cpu_ids / RCU_JIFFIES_FQS_DIV; + if (jiffies_till_first_fqs == ULONG_MAX) + jiffies_till_first_fqs = d; + if (jiffies_till_next_fqs == ULONG_MAX) + jiffies_till_next_fqs = d; + + /* If the compile-time values are accurate, just leave. */ + if (rcu_fanout_leaf == CONFIG_RCU_FANOUT_LEAF && + nr_cpu_ids == NR_CPUS) + return; + pr_info("RCU: Adjusting geometry for rcu_fanout_leaf=%d, nr_cpu_ids=%d\n", + rcu_fanout_leaf, nr_cpu_ids); + + /* + * Compute number of nodes that can be handled an rcu_node tree + * with the given number of levels. Setting rcu_capacity[0] makes + * some of the arithmetic easier. + */ + rcu_capacity[0] = 1; + rcu_capacity[1] = rcu_fanout_leaf; + for (i = 2; i <= MAX_RCU_LVLS; i++) + rcu_capacity[i] = rcu_capacity[i - 1] * CONFIG_RCU_FANOUT; + + /* + * The boot-time rcu_fanout_leaf parameter is only permitted + * to increase the leaf-level fanout, not decrease it. Of course, + * the leaf-level fanout cannot exceed the number of bits in + * the rcu_node masks. Finally, the tree must be able to accommodate + * the configured number of CPUs. Complain and fall back to the + * compile-time values if these limits are exceeded. + */ + if (rcu_fanout_leaf < CONFIG_RCU_FANOUT_LEAF || + rcu_fanout_leaf > sizeof(unsigned long) * 8 || + n > rcu_capacity[MAX_RCU_LVLS]) { + WARN_ON(1); + return; + } + + /* Calculate the number of rcu_nodes at each level of the tree. */ + for (i = 1; i <= MAX_RCU_LVLS; i++) + if (n <= rcu_capacity[i]) { + for (j = 0; j <= i; j++) + num_rcu_lvl[j] = + DIV_ROUND_UP(n, rcu_capacity[i - j]); + rcu_num_lvls = i; + for (j = i + 1; j <= MAX_RCU_LVLS; j++) + num_rcu_lvl[j] = 0; + break; + } + + /* Calculate the total number of rcu_node structures. */ + rcu_num_nodes = 0; + for (i = 0; i <= MAX_RCU_LVLS; i++) + rcu_num_nodes += num_rcu_lvl[i]; + rcu_num_nodes -= n; +} + +void __init rcu_init(void) +{ + int cpu; + + rcu_early_boot_tests(); + + rcu_bootup_announce(); + rcu_init_geometry(); + rcu_init_one(&rcu_bh_state, &rcu_bh_data); + rcu_init_one(&rcu_sched_state, &rcu_sched_data); + __rcu_init_preempt(); + + /* + * We don't need protection against CPU-hotplug here because + * this is called early in boot, before either interrupts + * or the scheduler are operational. + */ + cpu_notifier(rcu_cpu_notify, 0); + pm_notifier(rcu_pm_notify, 0); + for_each_online_cpu(cpu) + rcu_cpu_notify(NULL, CPU_UP_PREPARE, (void *)(long)cpu); +} + +#include "tree_plugin.h" diff --git a/kernel/kernel/rcu/tree.h b/kernel/kernel/rcu/tree.h new file mode 100644 index 000000000..8a9f0d364 --- /dev/null +++ b/kernel/kernel/rcu/tree.h @@ -0,0 +1,618 @@ +/* + * Read-Copy Update mechanism for mutual exclusion (tree-based version) + * Internal non-public definitions. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, you can access it online at + * http://www.gnu.org/licenses/gpl-2.0.html. + * + * Copyright IBM Corporation, 2008 + * + * Author: Ingo Molnar + * Paul E. McKenney + */ + +#include +#include +#include +#include +#include +#include + +/* + * Define shape of hierarchy based on NR_CPUS, CONFIG_RCU_FANOUT, and + * CONFIG_RCU_FANOUT_LEAF. + * In theory, it should be possible to add more levels straightforwardly. + * In practice, this did work well going from three levels to four. + * Of course, your mileage may vary. + */ +#define MAX_RCU_LVLS 4 +#define RCU_FANOUT_1 (CONFIG_RCU_FANOUT_LEAF) +#define RCU_FANOUT_2 (RCU_FANOUT_1 * CONFIG_RCU_FANOUT) +#define RCU_FANOUT_3 (RCU_FANOUT_2 * CONFIG_RCU_FANOUT) +#define RCU_FANOUT_4 (RCU_FANOUT_3 * CONFIG_RCU_FANOUT) + +#if NR_CPUS <= RCU_FANOUT_1 +# define RCU_NUM_LVLS 1 +# define NUM_RCU_LVL_0 1 +# define NUM_RCU_LVL_1 (NR_CPUS) +# define NUM_RCU_LVL_2 0 +# define NUM_RCU_LVL_3 0 +# define NUM_RCU_LVL_4 0 +#elif NR_CPUS <= RCU_FANOUT_2 +# define RCU_NUM_LVLS 2 +# define NUM_RCU_LVL_0 1 +# define NUM_RCU_LVL_1 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_1) +# define NUM_RCU_LVL_2 (NR_CPUS) +# define NUM_RCU_LVL_3 0 +# define NUM_RCU_LVL_4 0 +#elif NR_CPUS <= RCU_FANOUT_3 +# define RCU_NUM_LVLS 3 +# define NUM_RCU_LVL_0 1 +# define NUM_RCU_LVL_1 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_2) +# define NUM_RCU_LVL_2 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_1) +# define NUM_RCU_LVL_3 (NR_CPUS) +# define NUM_RCU_LVL_4 0 +#elif NR_CPUS <= RCU_FANOUT_4 +# define RCU_NUM_LVLS 4 +# define NUM_RCU_LVL_0 1 +# define NUM_RCU_LVL_1 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_3) +# define NUM_RCU_LVL_2 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_2) +# define NUM_RCU_LVL_3 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_1) +# define NUM_RCU_LVL_4 (NR_CPUS) +#else +# error "CONFIG_RCU_FANOUT insufficient for NR_CPUS" +#endif /* #if (NR_CPUS) <= RCU_FANOUT_1 */ + +#define RCU_SUM (NUM_RCU_LVL_0 + NUM_RCU_LVL_1 + NUM_RCU_LVL_2 + NUM_RCU_LVL_3 + NUM_RCU_LVL_4) +#define NUM_RCU_NODES (RCU_SUM - NR_CPUS) + +extern int rcu_num_lvls; +extern int rcu_num_nodes; + +/* + * Dynticks per-CPU state. + */ +struct rcu_dynticks { + long long dynticks_nesting; /* Track irq/process nesting level. */ + /* Process level is worth LLONG_MAX/2. */ + int dynticks_nmi_nesting; /* Track NMI nesting level. */ + atomic_t dynticks; /* Even value for idle, else odd. */ +#ifdef CONFIG_NO_HZ_FULL_SYSIDLE + long long dynticks_idle_nesting; + /* irq/process nesting level from idle. */ + atomic_t dynticks_idle; /* Even value for idle, else odd. */ + /* "Idle" excludes userspace execution. */ + unsigned long dynticks_idle_jiffies; + /* End of last non-NMI non-idle period. */ +#endif /* #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */ +#ifdef CONFIG_RCU_FAST_NO_HZ + bool all_lazy; /* Are all CPU's CBs lazy? */ + unsigned long nonlazy_posted; + /* # times non-lazy CBs posted to CPU. */ + unsigned long nonlazy_posted_snap; + /* idle-period nonlazy_posted snapshot. */ + unsigned long last_accelerate; + /* Last jiffy CBs were accelerated. */ + unsigned long last_advance_all; + /* Last jiffy CBs were all advanced. */ + int tick_nohz_enabled_snap; /* Previously seen value from sysfs. */ +#endif /* #ifdef CONFIG_RCU_FAST_NO_HZ */ +}; + +/* RCU's kthread states for tracing. */ +#define RCU_KTHREAD_STOPPED 0 +#define RCU_KTHREAD_RUNNING 1 +#define RCU_KTHREAD_WAITING 2 +#define RCU_KTHREAD_OFFCPU 3 +#define RCU_KTHREAD_YIELDING 4 +#define RCU_KTHREAD_MAX 4 + +/* + * Definition for node within the RCU grace-period-detection hierarchy. + */ +struct rcu_node { + raw_spinlock_t lock; /* Root rcu_node's lock protects some */ + /* rcu_state fields as well as following. */ + unsigned long gpnum; /* Current grace period for this node. */ + /* This will either be equal to or one */ + /* behind the root rcu_node's gpnum. */ + unsigned long completed; /* Last GP completed for this node. */ + /* This will either be equal to or one */ + /* behind the root rcu_node's gpnum. */ + unsigned long qsmask; /* CPUs or groups that need to switch in */ + /* order for current grace period to proceed.*/ + /* In leaf rcu_node, each bit corresponds to */ + /* an rcu_data structure, otherwise, each */ + /* bit corresponds to a child rcu_node */ + /* structure. */ + unsigned long expmask; /* Groups that have ->blkd_tasks */ + /* elements that need to drain to allow the */ + /* current expedited grace period to */ + /* complete (only for PREEMPT_RCU). */ + unsigned long qsmaskinit; + /* Per-GP initial value for qsmask & expmask. */ + /* Initialized from ->qsmaskinitnext at the */ + /* beginning of each grace period. */ + unsigned long qsmaskinitnext; + /* Online CPUs for next grace period. */ + unsigned long grpmask; /* Mask to apply to parent qsmask. */ + /* Only one bit will be set in this mask. */ + int grplo; /* lowest-numbered CPU or group here. */ + int grphi; /* highest-numbered CPU or group here. */ + u8 grpnum; /* CPU/group number for next level up. */ + u8 level; /* root is at level 0. */ + bool wait_blkd_tasks;/* Necessary to wait for blocked tasks to */ + /* exit RCU read-side critical sections */ + /* before propagating offline up the */ + /* rcu_node tree? */ + struct rcu_node *parent; + struct list_head blkd_tasks; + /* Tasks blocked in RCU read-side critical */ + /* section. Tasks are placed at the head */ + /* of this list and age towards the tail. */ + struct list_head *gp_tasks; + /* Pointer to the first task blocking the */ + /* current grace period, or NULL if there */ + /* is no such task. */ + struct list_head *exp_tasks; + /* Pointer to the first task blocking the */ + /* current expedited grace period, or NULL */ + /* if there is no such task. If there */ + /* is no current expedited grace period, */ + /* then there can cannot be any such task. */ +#ifdef CONFIG_RCU_BOOST + struct list_head *boost_tasks; + /* Pointer to first task that needs to be */ + /* priority boosted, or NULL if no priority */ + /* boosting is needed for this rcu_node */ + /* structure. If there are no tasks */ + /* queued on this rcu_node structure that */ + /* are blocking the current grace period, */ + /* there can be no such task. */ + struct rt_mutex boost_mtx; + /* Used only for the priority-boosting */ + /* side effect, not as a lock. */ + unsigned long boost_time; + /* When to start boosting (jiffies). */ + struct task_struct *boost_kthread_task; + /* kthread that takes care of priority */ + /* boosting for this rcu_node structure. */ + unsigned int boost_kthread_status; + /* State of boost_kthread_task for tracing. */ + unsigned long n_tasks_boosted; + /* Total number of tasks boosted. */ + unsigned long n_exp_boosts; + /* Number of tasks boosted for expedited GP. */ + unsigned long n_normal_boosts; + /* Number of tasks boosted for normal GP. */ + unsigned long n_balk_blkd_tasks; + /* Refused to boost: no blocked tasks. */ + unsigned long n_balk_exp_gp_tasks; + /* Refused to boost: nothing blocking GP. */ + unsigned long n_balk_boost_tasks; + /* Refused to boost: already boosting. */ + unsigned long n_balk_notblocked; + /* Refused to boost: RCU RS CS still running. */ + unsigned long n_balk_notyet; + /* Refused to boost: not yet time. */ + unsigned long n_balk_nos; + /* Refused to boost: not sure why, though. */ + /* This can happen due to race conditions. */ +#endif /* #ifdef CONFIG_RCU_BOOST */ +#ifdef CONFIG_RCU_NOCB_CPU + struct swait_head nocb_gp_wq[2]; + /* Place for rcu_nocb_kthread() to wait GP. */ +#endif /* #ifdef CONFIG_RCU_NOCB_CPU */ + int need_future_gp[2]; + /* Counts of upcoming no-CB GP requests. */ + raw_spinlock_t fqslock ____cacheline_internodealigned_in_smp; +} ____cacheline_internodealigned_in_smp; + +/* + * Do a full breadth-first scan of the rcu_node structures for the + * specified rcu_state structure. + */ +#define rcu_for_each_node_breadth_first(rsp, rnp) \ + for ((rnp) = &(rsp)->node[0]; \ + (rnp) < &(rsp)->node[rcu_num_nodes]; (rnp)++) + +/* + * Do a breadth-first scan of the non-leaf rcu_node structures for the + * specified rcu_state structure. Note that if there is a singleton + * rcu_node tree with but one rcu_node structure, this loop is a no-op. + */ +#define rcu_for_each_nonleaf_node_breadth_first(rsp, rnp) \ + for ((rnp) = &(rsp)->node[0]; \ + (rnp) < (rsp)->level[rcu_num_lvls - 1]; (rnp)++) + +/* + * Scan the leaves of the rcu_node hierarchy for the specified rcu_state + * structure. Note that if there is a singleton rcu_node tree with but + * one rcu_node structure, this loop -will- visit the rcu_node structure. + * It is still a leaf node, even if it is also the root node. + */ +#define rcu_for_each_leaf_node(rsp, rnp) \ + for ((rnp) = (rsp)->level[rcu_num_lvls - 1]; \ + (rnp) < &(rsp)->node[rcu_num_nodes]; (rnp)++) + +/* Index values for nxttail array in struct rcu_data. */ +#define RCU_DONE_TAIL 0 /* Also RCU_WAIT head. */ +#define RCU_WAIT_TAIL 1 /* Also RCU_NEXT_READY head. */ +#define RCU_NEXT_READY_TAIL 2 /* Also RCU_NEXT head. */ +#define RCU_NEXT_TAIL 3 +#define RCU_NEXT_SIZE 4 + +/* Per-CPU data for read-copy update. */ +struct rcu_data { + /* 1) quiescent-state and grace-period handling : */ + unsigned long completed; /* Track rsp->completed gp number */ + /* in order to detect GP end. */ + unsigned long gpnum; /* Highest gp number that this CPU */ + /* is aware of having started. */ + unsigned long rcu_qs_ctr_snap;/* Snapshot of rcu_qs_ctr to check */ + /* for rcu_all_qs() invocations. */ + bool passed_quiesce; /* User-mode/idle loop etc. */ + bool qs_pending; /* Core waits for quiesc state. */ + bool beenonline; /* CPU online at least once. */ + bool gpwrap; /* Possible gpnum/completed wrap. */ + struct rcu_node *mynode; /* This CPU's leaf of hierarchy */ + unsigned long grpmask; /* Mask to apply to leaf qsmask. */ +#ifdef CONFIG_RCU_CPU_STALL_INFO + unsigned long ticks_this_gp; /* The number of scheduling-clock */ + /* ticks this CPU has handled */ + /* during and after the last grace */ + /* period it is aware of. */ +#endif /* #ifdef CONFIG_RCU_CPU_STALL_INFO */ + + /* 2) batch handling */ + /* + * If nxtlist is not NULL, it is partitioned as follows. + * Any of the partitions might be empty, in which case the + * pointer to that partition will be equal to the pointer for + * the following partition. When the list is empty, all of + * the nxttail elements point to the ->nxtlist pointer itself, + * which in that case is NULL. + * + * [nxtlist, *nxttail[RCU_DONE_TAIL]): + * Entries that batch # <= ->completed + * The grace period for these entries has completed, and + * the other grace-period-completed entries may be moved + * here temporarily in rcu_process_callbacks(). + * [*nxttail[RCU_DONE_TAIL], *nxttail[RCU_WAIT_TAIL]): + * Entries that batch # <= ->completed - 1: waiting for current GP + * [*nxttail[RCU_WAIT_TAIL], *nxttail[RCU_NEXT_READY_TAIL]): + * Entries known to have arrived before current GP ended + * [*nxttail[RCU_NEXT_READY_TAIL], *nxttail[RCU_NEXT_TAIL]): + * Entries that might have arrived after current GP ended + * Note that the value of *nxttail[RCU_NEXT_TAIL] will + * always be NULL, as this is the end of the list. + */ + struct rcu_head *nxtlist; + struct rcu_head **nxttail[RCU_NEXT_SIZE]; + unsigned long nxtcompleted[RCU_NEXT_SIZE]; + /* grace periods for sublists. */ + long qlen_lazy; /* # of lazy queued callbacks */ + long qlen; /* # of queued callbacks, incl lazy */ + long qlen_last_fqs_check; + /* qlen at last check for QS forcing */ + unsigned long n_cbs_invoked; /* count of RCU cbs invoked. */ + unsigned long n_nocbs_invoked; /* count of no-CBs RCU cbs invoked. */ + unsigned long n_cbs_orphaned; /* RCU cbs orphaned by dying CPU */ + unsigned long n_cbs_adopted; /* RCU cbs adopted from dying CPU */ + unsigned long n_force_qs_snap; + /* did other CPU force QS recently? */ + long blimit; /* Upper limit on a processed batch */ + + /* 3) dynticks interface. */ + struct rcu_dynticks *dynticks; /* Shared per-CPU dynticks state. */ + int dynticks_snap; /* Per-GP tracking for dynticks. */ + + /* 4) reasons this CPU needed to be kicked by force_quiescent_state */ + unsigned long dynticks_fqs; /* Kicked due to dynticks idle. */ + unsigned long offline_fqs; /* Kicked due to being offline. */ + unsigned long cond_resched_completed; + /* Grace period that needs help */ + /* from cond_resched(). */ + + /* 5) __rcu_pending() statistics. */ + unsigned long n_rcu_pending; /* rcu_pending() calls since boot. */ + unsigned long n_rp_qs_pending; + unsigned long n_rp_report_qs; + unsigned long n_rp_cb_ready; + unsigned long n_rp_cpu_needs_gp; + unsigned long n_rp_gp_completed; + unsigned long n_rp_gp_started; + unsigned long n_rp_nocb_defer_wakeup; + unsigned long n_rp_need_nothing; + + /* 6) _rcu_barrier() and OOM callbacks. */ + struct rcu_head barrier_head; +#ifdef CONFIG_RCU_FAST_NO_HZ + struct rcu_head oom_head; +#endif /* #ifdef CONFIG_RCU_FAST_NO_HZ */ + + /* 7) Callback offloading. */ +#ifdef CONFIG_RCU_NOCB_CPU + struct rcu_head *nocb_head; /* CBs waiting for kthread. */ + struct rcu_head **nocb_tail; + atomic_long_t nocb_q_count; /* # CBs waiting for nocb */ + atomic_long_t nocb_q_count_lazy; /* invocation (all stages). */ + struct rcu_head *nocb_follower_head; /* CBs ready to invoke. */ + struct rcu_head **nocb_follower_tail; + struct swait_head nocb_wq; /* For nocb kthreads to sleep on. */ + struct task_struct *nocb_kthread; + int nocb_defer_wakeup; /* Defer wakeup of nocb_kthread. */ + + /* The following fields are used by the leader, hence own cacheline. */ + struct rcu_head *nocb_gp_head ____cacheline_internodealigned_in_smp; + /* CBs waiting for GP. */ + struct rcu_head **nocb_gp_tail; + bool nocb_leader_sleep; /* Is the nocb leader thread asleep? */ + struct rcu_data *nocb_next_follower; + /* Next follower in wakeup chain. */ + + /* The following fields are used by the follower, hence new cachline. */ + struct rcu_data *nocb_leader ____cacheline_internodealigned_in_smp; + /* Leader CPU takes GP-end wakeups. */ +#endif /* #ifdef CONFIG_RCU_NOCB_CPU */ + + /* 8) RCU CPU stall data. */ +#ifdef CONFIG_RCU_CPU_STALL_INFO + unsigned int softirq_snap; /* Snapshot of softirq activity. */ +#endif /* #ifdef CONFIG_RCU_CPU_STALL_INFO */ + + int cpu; + struct rcu_state *rsp; +}; + +/* Values for fqs_state field in struct rcu_state. */ +#define RCU_GP_IDLE 0 /* No grace period in progress. */ +#define RCU_GP_INIT 1 /* Grace period being initialized. */ +#define RCU_SAVE_DYNTICK 2 /* Need to scan dyntick state. */ +#define RCU_FORCE_QS 3 /* Need to force quiescent state. */ +#define RCU_SIGNAL_INIT RCU_SAVE_DYNTICK + +/* Values for nocb_defer_wakeup field in struct rcu_data. */ +#define RCU_NOGP_WAKE_NOT 0 +#define RCU_NOGP_WAKE 1 +#define RCU_NOGP_WAKE_FORCE 2 + +#define RCU_JIFFIES_TILL_FORCE_QS (1 + (HZ > 250) + (HZ > 500)) + /* For jiffies_till_first_fqs and */ + /* and jiffies_till_next_fqs. */ + +#define RCU_JIFFIES_FQS_DIV 256 /* Very large systems need more */ + /* delay between bouts of */ + /* quiescent-state forcing. */ + +#define RCU_STALL_RAT_DELAY 2 /* Allow other CPUs time to take */ + /* at least one scheduling clock */ + /* irq before ratting on them. */ + +#define rcu_wait(cond) \ +do { \ + for (;;) { \ + set_current_state(TASK_INTERRUPTIBLE); \ + if (cond) \ + break; \ + schedule(); \ + } \ + __set_current_state(TASK_RUNNING); \ +} while (0) + +/* + * RCU global state, including node hierarchy. This hierarchy is + * represented in "heap" form in a dense array. The root (first level) + * of the hierarchy is in ->node[0] (referenced by ->level[0]), the second + * level in ->node[1] through ->node[m] (->node[1] referenced by ->level[1]), + * and the third level in ->node[m+1] and following (->node[m+1] referenced + * by ->level[2]). The number of levels is determined by the number of + * CPUs and by CONFIG_RCU_FANOUT. Small systems will have a "hierarchy" + * consisting of a single rcu_node. + */ +struct rcu_state { + struct rcu_node node[NUM_RCU_NODES]; /* Hierarchy. */ + struct rcu_node *level[RCU_NUM_LVLS]; /* Hierarchy levels. */ + u32 levelcnt[MAX_RCU_LVLS + 1]; /* # nodes in each level. */ + u8 levelspread[RCU_NUM_LVLS]; /* kids/node in each level. */ + u8 flavor_mask; /* bit in flavor mask. */ + struct rcu_data __percpu *rda; /* pointer of percu rcu_data. */ + void (*call)(struct rcu_head *head, /* call_rcu() flavor. */ + void (*func)(struct rcu_head *head)); + + /* The following fields are guarded by the root rcu_node's lock. */ + + u8 fqs_state ____cacheline_internodealigned_in_smp; + /* Force QS state. */ + u8 boost; /* Subject to priority boost. */ + unsigned long gpnum; /* Current gp number. */ + unsigned long completed; /* # of last completed gp. */ + struct task_struct *gp_kthread; /* Task for grace periods. */ + struct swait_head gp_wq; /* Where GP task waits. */ + short gp_flags; /* Commands for GP task. */ + short gp_state; /* GP kthread sleep state. */ + + /* End of fields guarded by root rcu_node's lock. */ + + raw_spinlock_t orphan_lock ____cacheline_internodealigned_in_smp; + /* Protect following fields. */ + struct rcu_head *orphan_nxtlist; /* Orphaned callbacks that */ + /* need a grace period. */ + struct rcu_head **orphan_nxttail; /* Tail of above. */ + struct rcu_head *orphan_donelist; /* Orphaned callbacks that */ + /* are ready to invoke. */ + struct rcu_head **orphan_donetail; /* Tail of above. */ + long qlen_lazy; /* Number of lazy callbacks. */ + long qlen; /* Total number of callbacks. */ + /* End of fields guarded by orphan_lock. */ + + struct mutex barrier_mutex; /* Guards barrier fields. */ + atomic_t barrier_cpu_count; /* # CPUs waiting on. */ + struct completion barrier_completion; /* Wake at barrier end. */ + unsigned long n_barrier_done; /* ++ at start and end of */ + /* _rcu_barrier(). */ + /* End of fields guarded by barrier_mutex. */ + + atomic_long_t expedited_start; /* Starting ticket. */ + atomic_long_t expedited_done; /* Done ticket. */ + atomic_long_t expedited_wrap; /* # near-wrap incidents. */ + atomic_long_t expedited_tryfail; /* # acquisition failures. */ + atomic_long_t expedited_workdone1; /* # done by others #1. */ + atomic_long_t expedited_workdone2; /* # done by others #2. */ + atomic_long_t expedited_normal; /* # fallbacks to normal. */ + atomic_long_t expedited_stoppedcpus; /* # successful stop_cpus. */ + atomic_long_t expedited_done_tries; /* # tries to update _done. */ + atomic_long_t expedited_done_lost; /* # times beaten to _done. */ + atomic_long_t expedited_done_exit; /* # times exited _done loop. */ + + unsigned long jiffies_force_qs; /* Time at which to invoke */ + /* force_quiescent_state(). */ + unsigned long n_force_qs; /* Number of calls to */ + /* force_quiescent_state(). */ + unsigned long n_force_qs_lh; /* ~Number of calls leaving */ + /* due to lock unavailable. */ + unsigned long n_force_qs_ngp; /* Number of calls leaving */ + /* due to no GP active. */ + unsigned long gp_start; /* Time at which GP started, */ + /* but in jiffies. */ + unsigned long gp_activity; /* Time of last GP kthread */ + /* activity in jiffies. */ + unsigned long jiffies_stall; /* Time at which to check */ + /* for CPU stalls. */ + unsigned long jiffies_resched; /* Time at which to resched */ + /* a reluctant CPU. */ + unsigned long n_force_qs_gpstart; /* Snapshot of n_force_qs at */ + /* GP start. */ + unsigned long gp_max; /* Maximum GP duration in */ + /* jiffies. */ + const char *name; /* Name of structure. */ + char abbr; /* Abbreviated name. */ + struct list_head flavors; /* List of RCU flavors. */ +}; + +/* Values for rcu_state structure's gp_flags field. */ +#define RCU_GP_FLAG_INIT 0x1 /* Need grace-period initialization. */ +#define RCU_GP_FLAG_FQS 0x2 /* Need grace-period quiescent-state forcing. */ + +/* Values for rcu_state structure's gp_flags field. */ +#define RCU_GP_WAIT_INIT 0 /* Initial state. */ +#define RCU_GP_WAIT_GPS 1 /* Wait for grace-period start. */ +#define RCU_GP_WAIT_FQS 2 /* Wait for force-quiescent-state time. */ + +extern struct list_head rcu_struct_flavors; + +/* Sequence through rcu_state structures for each RCU flavor. */ +#define for_each_rcu_flavor(rsp) \ + list_for_each_entry((rsp), &rcu_struct_flavors, flavors) + +/* + * RCU implementation internal declarations: + */ +extern struct rcu_state rcu_sched_state; +DECLARE_PER_CPU(struct rcu_data, rcu_sched_data); + +extern struct rcu_state rcu_bh_state; +DECLARE_PER_CPU(struct rcu_data, rcu_bh_data); + +#ifdef CONFIG_PREEMPT_RCU +extern struct rcu_state rcu_preempt_state; +DECLARE_PER_CPU(struct rcu_data, rcu_preempt_data); +#endif /* #ifdef CONFIG_PREEMPT_RCU */ + +DECLARE_PER_CPU(unsigned int, rcu_cpu_kthread_status); +DECLARE_PER_CPU(int, rcu_cpu_kthread_cpu); +DECLARE_PER_CPU(unsigned int, rcu_cpu_kthread_loops); +DECLARE_PER_CPU(char, rcu_cpu_has_work); + +#ifndef RCU_TREE_NONCORE + +/* Forward declarations for rcutree_plugin.h */ +static void rcu_bootup_announce(void); +static void rcu_preempt_note_context_switch(void); +static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp); +#ifdef CONFIG_HOTPLUG_CPU +static bool rcu_preempt_has_tasks(struct rcu_node *rnp); +#endif /* #ifdef CONFIG_HOTPLUG_CPU */ +static void rcu_print_detail_task_stall(struct rcu_state *rsp); +static int rcu_print_task_stall(struct rcu_node *rnp); +static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp); +static void rcu_preempt_check_callbacks(void); +void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu)); +static void __init __rcu_init_preempt(void); +static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags); +static void rcu_preempt_boost_start_gp(struct rcu_node *rnp); +static bool rcu_is_callbacks_kthread(void); +static void rcu_cpu_kthread_setup(unsigned int cpu); +#ifdef CONFIG_RCU_BOOST +static int rcu_spawn_one_boost_kthread(struct rcu_state *rsp, + struct rcu_node *rnp); +#endif /* #ifdef CONFIG_RCU_BOOST */ +static void __init rcu_spawn_boost_kthreads(void); +static void rcu_prepare_kthreads(int cpu); +static void rcu_cleanup_after_idle(void); +static void rcu_prepare_for_idle(void); +static void rcu_idle_count_callbacks_posted(void); +static bool rcu_preempt_has_tasks(struct rcu_node *rnp); +static void print_cpu_stall_info_begin(void); +static void print_cpu_stall_info(struct rcu_state *rsp, int cpu); +static void print_cpu_stall_info_end(void); +static void zero_cpu_stall_ticks(struct rcu_data *rdp); +static void increment_cpu_stall_ticks(void); +static bool rcu_nocb_cpu_needs_barrier(struct rcu_state *rsp, int cpu); +static void rcu_nocb_gp_set(struct rcu_node *rnp, int nrq); +static void rcu_nocb_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp); +static void rcu_init_one_nocb(struct rcu_node *rnp); +static bool __call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *rhp, + bool lazy, unsigned long flags); +static bool rcu_nocb_adopt_orphan_cbs(struct rcu_state *rsp, + struct rcu_data *rdp, + unsigned long flags); +static int rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp); +static void do_nocb_deferred_wakeup(struct rcu_data *rdp); +static void rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp); +static void rcu_spawn_all_nocb_kthreads(int cpu); +static void __init rcu_spawn_nocb_kthreads(void); +#ifdef CONFIG_RCU_NOCB_CPU +static void __init rcu_organize_nocb_kthreads(struct rcu_state *rsp); +#endif /* #ifdef CONFIG_RCU_NOCB_CPU */ +static void __maybe_unused rcu_kick_nohz_cpu(int cpu); +static bool init_nocb_callback_list(struct rcu_data *rdp); +static void rcu_sysidle_enter(int irq); +static void rcu_sysidle_exit(int irq); +static void rcu_sysidle_check_cpu(struct rcu_data *rdp, bool *isidle, + unsigned long *maxj); +static bool is_sysidle_rcu_state(struct rcu_state *rsp); +static void rcu_sysidle_report_gp(struct rcu_state *rsp, int isidle, + unsigned long maxj); +static void rcu_bind_gp_kthread(void); +static void rcu_sysidle_init_percpu_data(struct rcu_dynticks *rdtp); +static bool rcu_nohz_full_cpu(struct rcu_state *rsp); +static void rcu_dynticks_task_enter(void); +static void rcu_dynticks_task_exit(void); + +#endif /* #ifndef RCU_TREE_NONCORE */ + +#ifdef CONFIG_RCU_TRACE +/* Read out queue lengths for tracing. */ +static inline void rcu_nocb_q_lengths(struct rcu_data *rdp, long *ql, long *qll) +{ +#ifdef CONFIG_RCU_NOCB_CPU + *ql = atomic_long_read(&rdp->nocb_q_count); + *qll = atomic_long_read(&rdp->nocb_q_count_lazy); +#else /* #ifdef CONFIG_RCU_NOCB_CPU */ + *ql = 0; + *qll = 0; +#endif /* #else #ifdef CONFIG_RCU_NOCB_CPU */ +} +#endif /* #ifdef CONFIG_RCU_TRACE */ diff --git a/kernel/kernel/rcu/tree_plugin.h b/kernel/kernel/rcu/tree_plugin.h new file mode 100644 index 000000000..54da8f44d --- /dev/null +++ b/kernel/kernel/rcu/tree_plugin.h @@ -0,0 +1,2984 @@ +/* + * Read-Copy Update mechanism for mutual exclusion (tree-based version) + * Internal non-public definitions that provide either classic + * or preemptible semantics. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, you can access it online at + * http://www.gnu.org/licenses/gpl-2.0.html. + * + * Copyright Red Hat, 2009 + * Copyright IBM Corporation, 2009 + * + * Author: Ingo Molnar + * Paul E. McKenney + */ + +#ifdef CONFIG_RCU_BOOST + +#include "../locking/rtmutex_common.h" + +#endif /* #ifdef CONFIG_RCU_BOOST */ + +/* + * Control variables for per-CPU and per-rcu_node kthreads. These + * handle all flavors of RCU. + */ +DEFINE_PER_CPU(unsigned int, rcu_cpu_kthread_status); +DEFINE_PER_CPU(unsigned int, rcu_cpu_kthread_loops); +DEFINE_PER_CPU(char, rcu_cpu_has_work); + +#ifdef CONFIG_RCU_NOCB_CPU +static cpumask_var_t rcu_nocb_mask; /* CPUs to have callbacks offloaded. */ +static bool have_rcu_nocb_mask; /* Was rcu_nocb_mask allocated? */ +static bool __read_mostly rcu_nocb_poll; /* Offload kthread are to poll. */ +#endif /* #ifdef CONFIG_RCU_NOCB_CPU */ + +/* + * Check the RCU kernel configuration parameters and print informative + * messages about anything out of the ordinary. If you like #ifdef, you + * will love this function. + */ +static void __init rcu_bootup_announce_oddness(void) +{ + if (IS_ENABLED(CONFIG_RCU_TRACE)) + pr_info("\tRCU debugfs-based tracing is enabled.\n"); + if ((IS_ENABLED(CONFIG_64BIT) && CONFIG_RCU_FANOUT != 64) || + (!IS_ENABLED(CONFIG_64BIT) && CONFIG_RCU_FANOUT != 32)) + pr_info("\tCONFIG_RCU_FANOUT set to non-default value of %d\n", + CONFIG_RCU_FANOUT); + if (IS_ENABLED(CONFIG_RCU_FANOUT_EXACT)) + pr_info("\tHierarchical RCU autobalancing is disabled.\n"); + if (IS_ENABLED(CONFIG_RCU_FAST_NO_HZ)) + pr_info("\tRCU dyntick-idle grace-period acceleration is enabled.\n"); + if (IS_ENABLED(CONFIG_PROVE_RCU)) + pr_info("\tRCU lockdep checking is enabled.\n"); + if (IS_ENABLED(CONFIG_RCU_TORTURE_TEST_RUNNABLE)) + pr_info("\tRCU torture testing starts during boot.\n"); + if (IS_ENABLED(CONFIG_RCU_CPU_STALL_INFO)) + pr_info("\tAdditional per-CPU info printed with stalls.\n"); + if (NUM_RCU_LVL_4 != 0) + pr_info("\tFour-level hierarchy is enabled.\n"); + if (CONFIG_RCU_FANOUT_LEAF != 16) + pr_info("\tBuild-time adjustment of leaf fanout to %d.\n", + CONFIG_RCU_FANOUT_LEAF); + if (rcu_fanout_leaf != CONFIG_RCU_FANOUT_LEAF) + pr_info("\tBoot-time adjustment of leaf fanout to %d.\n", rcu_fanout_leaf); + if (nr_cpu_ids != NR_CPUS) + pr_info("\tRCU restricting CPUs from NR_CPUS=%d to nr_cpu_ids=%d.\n", NR_CPUS, nr_cpu_ids); + if (IS_ENABLED(CONFIG_RCU_BOOST)) + pr_info("\tRCU kthread priority: %d.\n", kthread_prio); +} + +#ifdef CONFIG_PREEMPT_RCU + +RCU_STATE_INITIALIZER(rcu_preempt, 'p', call_rcu); +static struct rcu_state *rcu_state_p = &rcu_preempt_state; + +static int rcu_preempted_readers_exp(struct rcu_node *rnp); +static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp, + bool wake); + +/* + * Tell them what RCU they are running. + */ +static void __init rcu_bootup_announce(void) +{ + pr_info("Preemptible hierarchical RCU implementation.\n"); + rcu_bootup_announce_oddness(); +} + +/* + * Record a preemptible-RCU quiescent state for the specified CPU. Note + * that this just means that the task currently running on the CPU is + * not in a quiescent state. There might be any number of tasks blocked + * while in an RCU read-side critical section. + * + * As with the other rcu_*_qs() functions, callers to this function + * must disable preemption. + */ +static void rcu_preempt_qs(void) +{ + if (!__this_cpu_read(rcu_preempt_data.passed_quiesce)) { + trace_rcu_grace_period(TPS("rcu_preempt"), + __this_cpu_read(rcu_preempt_data.gpnum), + TPS("cpuqs")); + __this_cpu_write(rcu_preempt_data.passed_quiesce, 1); + barrier(); /* Coordinate with rcu_preempt_check_callbacks(). */ + current->rcu_read_unlock_special.b.need_qs = false; + } +} + +/* + * We have entered the scheduler, and the current task might soon be + * context-switched away from. If this task is in an RCU read-side + * critical section, we will no longer be able to rely on the CPU to + * record that fact, so we enqueue the task on the blkd_tasks list. + * The task will dequeue itself when it exits the outermost enclosing + * RCU read-side critical section. Therefore, the current grace period + * cannot be permitted to complete until the blkd_tasks list entries + * predating the current grace period drain, in other words, until + * rnp->gp_tasks becomes NULL. + * + * Caller must disable preemption. + */ +static void rcu_preempt_note_context_switch(void) +{ + struct task_struct *t = current; + unsigned long flags; + struct rcu_data *rdp; + struct rcu_node *rnp; + + if (t->rcu_read_lock_nesting > 0 && + !t->rcu_read_unlock_special.b.blocked) { + + /* Possibly blocking in an RCU read-side critical section. */ + rdp = this_cpu_ptr(rcu_preempt_state.rda); + rnp = rdp->mynode; + raw_spin_lock_irqsave(&rnp->lock, flags); + smp_mb__after_unlock_lock(); + t->rcu_read_unlock_special.b.blocked = true; + t->rcu_blocked_node = rnp; + + /* + * If this CPU has already checked in, then this task + * will hold up the next grace period rather than the + * current grace period. Queue the task accordingly. + * If the task is queued for the current grace period + * (i.e., this CPU has not yet passed through a quiescent + * state for the current grace period), then as long + * as that task remains queued, the current grace period + * cannot end. Note that there is some uncertainty as + * to exactly when the current grace period started. + * We take a conservative approach, which can result + * in unnecessarily waiting on tasks that started very + * slightly after the current grace period began. C'est + * la vie!!! + * + * But first, note that the current CPU must still be + * on line! + */ + WARN_ON_ONCE((rdp->grpmask & rcu_rnp_online_cpus(rnp)) == 0); + WARN_ON_ONCE(!list_empty(&t->rcu_node_entry)); + if ((rnp->qsmask & rdp->grpmask) && rnp->gp_tasks != NULL) { + list_add(&t->rcu_node_entry, rnp->gp_tasks->prev); + rnp->gp_tasks = &t->rcu_node_entry; +#ifdef CONFIG_RCU_BOOST + if (rnp->boost_tasks != NULL) + rnp->boost_tasks = rnp->gp_tasks; +#endif /* #ifdef CONFIG_RCU_BOOST */ + } else { + list_add(&t->rcu_node_entry, &rnp->blkd_tasks); + if (rnp->qsmask & rdp->grpmask) + rnp->gp_tasks = &t->rcu_node_entry; + } + trace_rcu_preempt_task(rdp->rsp->name, + t->pid, + (rnp->qsmask & rdp->grpmask) + ? rnp->gpnum + : rnp->gpnum + 1); + raw_spin_unlock_irqrestore(&rnp->lock, flags); + } else if (t->rcu_read_lock_nesting < 0 && + t->rcu_read_unlock_special.s) { + + /* + * Complete exit from RCU read-side critical section on + * behalf of preempted instance of __rcu_read_unlock(). + */ + rcu_read_unlock_special(t); + } + + /* + * Either we were not in an RCU read-side critical section to + * begin with, or we have now recorded that critical section + * globally. Either way, we can now note a quiescent state + * for this CPU. Again, if we were in an RCU read-side critical + * section, and if that critical section was blocking the current + * grace period, then the fact that the task has been enqueued + * means that we continue to block the current grace period. + */ + rcu_preempt_qs(); +} + +/* + * Check for preempted RCU readers blocking the current grace period + * for the specified rcu_node structure. If the caller needs a reliable + * answer, it must hold the rcu_node's ->lock. + */ +static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp) +{ + return rnp->gp_tasks != NULL; +} + +/* + * Advance a ->blkd_tasks-list pointer to the next entry, instead + * returning NULL if at the end of the list. + */ +static struct list_head *rcu_next_node_entry(struct task_struct *t, + struct rcu_node *rnp) +{ + struct list_head *np; + + np = t->rcu_node_entry.next; + if (np == &rnp->blkd_tasks) + np = NULL; + return np; +} + +/* + * Return true if the specified rcu_node structure has tasks that were + * preempted within an RCU read-side critical section. + */ +static bool rcu_preempt_has_tasks(struct rcu_node *rnp) +{ + return !list_empty(&rnp->blkd_tasks); +} + +/* + * Handle special cases during rcu_read_unlock(), such as needing to + * notify RCU core processing or task having blocked during the RCU + * read-side critical section. + */ +void rcu_read_unlock_special(struct task_struct *t) +{ + bool empty_exp; + bool empty_norm; + bool empty_exp_now; + unsigned long flags; + struct list_head *np; +#ifdef CONFIG_RCU_BOOST + bool drop_boost_mutex = false; +#endif /* #ifdef CONFIG_RCU_BOOST */ + struct rcu_node *rnp; + union rcu_special special; + + /* NMI handlers cannot block and cannot safely manipulate state. */ + if (in_nmi()) + return; + + local_irq_save(flags); + + /* + * If RCU core is waiting for this CPU to exit critical section, + * let it know that we have done so. Because irqs are disabled, + * t->rcu_read_unlock_special cannot change. + */ + special = t->rcu_read_unlock_special; + if (special.b.need_qs) { + rcu_preempt_qs(); + t->rcu_read_unlock_special.b.need_qs = false; + if (!t->rcu_read_unlock_special.s) { + local_irq_restore(flags); + return; + } + } + + /* Hardware IRQ handlers cannot block, complain if they get here. */ + if (preempt_count() & (HARDIRQ_MASK | SOFTIRQ_OFFSET)) { + lockdep_rcu_suspicious(__FILE__, __LINE__, + "rcu_read_unlock() from irq or softirq with blocking in critical section!!!\n"); + pr_alert("->rcu_read_unlock_special: %#x (b: %d, nq: %d)\n", + t->rcu_read_unlock_special.s, + t->rcu_read_unlock_special.b.blocked, + t->rcu_read_unlock_special.b.need_qs); + local_irq_restore(flags); + return; + } + + /* Clean up if blocked during RCU read-side critical section. */ + if (special.b.blocked) { + t->rcu_read_unlock_special.b.blocked = false; + + /* + * Remove this task from the list it blocked on. The + * task can migrate while we acquire the lock, but at + * most one time. So at most two passes through loop. + */ + for (;;) { + rnp = t->rcu_blocked_node; + raw_spin_lock(&rnp->lock); /* irqs already disabled. */ + smp_mb__after_unlock_lock(); + if (rnp == t->rcu_blocked_node) + break; + raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */ + } + empty_norm = !rcu_preempt_blocked_readers_cgp(rnp); + empty_exp = !rcu_preempted_readers_exp(rnp); + smp_mb(); /* ensure expedited fastpath sees end of RCU c-s. */ + np = rcu_next_node_entry(t, rnp); + list_del_init(&t->rcu_node_entry); + t->rcu_blocked_node = NULL; + trace_rcu_unlock_preempted_task(TPS("rcu_preempt"), + rnp->gpnum, t->pid); + if (&t->rcu_node_entry == rnp->gp_tasks) + rnp->gp_tasks = np; + if (&t->rcu_node_entry == rnp->exp_tasks) + rnp->exp_tasks = np; +#ifdef CONFIG_RCU_BOOST + if (&t->rcu_node_entry == rnp->boost_tasks) + rnp->boost_tasks = np; + /* Snapshot ->boost_mtx ownership with rcu_node lock held. */ + drop_boost_mutex = rt_mutex_owner(&rnp->boost_mtx) == t; +#endif /* #ifdef CONFIG_RCU_BOOST */ + + /* + * If this was the last task on the current list, and if + * we aren't waiting on any CPUs, report the quiescent state. + * Note that rcu_report_unblock_qs_rnp() releases rnp->lock, + * so we must take a snapshot of the expedited state. + */ + empty_exp_now = !rcu_preempted_readers_exp(rnp); + if (!empty_norm && !rcu_preempt_blocked_readers_cgp(rnp)) { + trace_rcu_quiescent_state_report(TPS("preempt_rcu"), + rnp->gpnum, + 0, rnp->qsmask, + rnp->level, + rnp->grplo, + rnp->grphi, + !!rnp->gp_tasks); + rcu_report_unblock_qs_rnp(&rcu_preempt_state, + rnp, flags); + } else { + raw_spin_unlock_irqrestore(&rnp->lock, flags); + } + +#ifdef CONFIG_RCU_BOOST + /* Unboost if we were boosted. */ + if (drop_boost_mutex) + rt_mutex_unlock(&rnp->boost_mtx); +#endif /* #ifdef CONFIG_RCU_BOOST */ + + /* + * If this was the last task on the expedited lists, + * then we need to report up the rcu_node hierarchy. + */ + if (!empty_exp && empty_exp_now) + rcu_report_exp_rnp(&rcu_preempt_state, rnp, true); + } else { + local_irq_restore(flags); + } +} + +/* + * Dump detailed information for all tasks blocking the current RCU + * grace period on the specified rcu_node structure. + */ +static void rcu_print_detail_task_stall_rnp(struct rcu_node *rnp) +{ + unsigned long flags; + struct task_struct *t; + + raw_spin_lock_irqsave(&rnp->lock, flags); + if (!rcu_preempt_blocked_readers_cgp(rnp)) { + raw_spin_unlock_irqrestore(&rnp->lock, flags); + return; + } + t = list_entry(rnp->gp_tasks, + struct task_struct, rcu_node_entry); + list_for_each_entry_continue(t, &rnp->blkd_tasks, rcu_node_entry) + sched_show_task(t); + raw_spin_unlock_irqrestore(&rnp->lock, flags); +} + +/* + * Dump detailed information for all tasks blocking the current RCU + * grace period. + */ +static void rcu_print_detail_task_stall(struct rcu_state *rsp) +{ + struct rcu_node *rnp = rcu_get_root(rsp); + + rcu_print_detail_task_stall_rnp(rnp); + rcu_for_each_leaf_node(rsp, rnp) + rcu_print_detail_task_stall_rnp(rnp); +} + +#ifdef CONFIG_RCU_CPU_STALL_INFO + +static void rcu_print_task_stall_begin(struct rcu_node *rnp) +{ + pr_err("\tTasks blocked on level-%d rcu_node (CPUs %d-%d):", + rnp->level, rnp->grplo, rnp->grphi); +} + +static void rcu_print_task_stall_end(void) +{ + pr_cont("\n"); +} + +#else /* #ifdef CONFIG_RCU_CPU_STALL_INFO */ + +static void rcu_print_task_stall_begin(struct rcu_node *rnp) +{ +} + +static void rcu_print_task_stall_end(void) +{ +} + +#endif /* #else #ifdef CONFIG_RCU_CPU_STALL_INFO */ + +/* + * Scan the current list of tasks blocked within RCU read-side critical + * sections, printing out the tid of each. + */ +static int rcu_print_task_stall(struct rcu_node *rnp) +{ + struct task_struct *t; + int ndetected = 0; + + if (!rcu_preempt_blocked_readers_cgp(rnp)) + return 0; + rcu_print_task_stall_begin(rnp); + t = list_entry(rnp->gp_tasks, + struct task_struct, rcu_node_entry); + list_for_each_entry_continue(t, &rnp->blkd_tasks, rcu_node_entry) { + pr_cont(" P%d", t->pid); + ndetected++; + } + rcu_print_task_stall_end(); + return ndetected; +} + +/* + * Check that the list of blocked tasks for the newly completed grace + * period is in fact empty. It is a serious bug to complete a grace + * period that still has RCU readers blocked! This function must be + * invoked -before- updating this rnp's ->gpnum, and the rnp's ->lock + * must be held by the caller. + * + * Also, if there are blocked tasks on the list, they automatically + * block the newly created grace period, so set up ->gp_tasks accordingly. + */ +static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp) +{ + WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp)); + if (rcu_preempt_has_tasks(rnp)) + rnp->gp_tasks = rnp->blkd_tasks.next; + WARN_ON_ONCE(rnp->qsmask); +} + +/* + * Check for a quiescent state from the current CPU. When a task blocks, + * the task is recorded in the corresponding CPU's rcu_node structure, + * which is checked elsewhere. + * + * Caller must disable hard irqs. + */ +static void rcu_preempt_check_callbacks(void) +{ + struct task_struct *t = current; + + if (t->rcu_read_lock_nesting == 0) { + rcu_preempt_qs(); + return; + } + if (t->rcu_read_lock_nesting > 0 && + __this_cpu_read(rcu_preempt_data.qs_pending) && + !__this_cpu_read(rcu_preempt_data.passed_quiesce)) + t->rcu_read_unlock_special.b.need_qs = true; +} + +/* + * Queue a preemptible-RCU callback for invocation after a grace period. + */ +void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu)) +{ + __call_rcu(head, func, &rcu_preempt_state, -1, 0); +} +EXPORT_SYMBOL_GPL(call_rcu); + +/** + * synchronize_rcu - wait until a grace period has elapsed. + * + * Control will return to the caller some time after a full grace + * period has elapsed, in other words after all currently executing RCU + * read-side critical sections have completed. Note, however, that + * upon return from synchronize_rcu(), the caller might well be executing + * concurrently with new RCU read-side critical sections that began while + * synchronize_rcu() was waiting. RCU read-side critical sections are + * delimited by rcu_read_lock() and rcu_read_unlock(), and may be nested. + * + * See the description of synchronize_sched() for more detailed information + * on memory ordering guarantees. + */ +void synchronize_rcu(void) +{ + rcu_lockdep_assert(!lock_is_held(&rcu_bh_lock_map) && + !lock_is_held(&rcu_lock_map) && + !lock_is_held(&rcu_sched_lock_map), + "Illegal synchronize_rcu() in RCU read-side critical section"); + if (!rcu_scheduler_active) + return; + if (rcu_gp_is_expedited()) + synchronize_rcu_expedited(); + else + wait_rcu_gp(call_rcu); +} +EXPORT_SYMBOL_GPL(synchronize_rcu); + +static DECLARE_WAIT_QUEUE_HEAD(sync_rcu_preempt_exp_wq); +static unsigned long sync_rcu_preempt_exp_count; +static DEFINE_MUTEX(sync_rcu_preempt_exp_mutex); + +/* + * Return non-zero if there are any tasks in RCU read-side critical + * sections blocking the current preemptible-RCU expedited grace period. + * If there is no preemptible-RCU expedited grace period currently in + * progress, returns zero unconditionally. + */ +static int rcu_preempted_readers_exp(struct rcu_node *rnp) +{ + return rnp->exp_tasks != NULL; +} + +/* + * return non-zero if there is no RCU expedited grace period in progress + * for the specified rcu_node structure, in other words, if all CPUs and + * tasks covered by the specified rcu_node structure have done their bit + * for the current expedited grace period. Works only for preemptible + * RCU -- other RCU implementation use other means. + * + * Caller must hold sync_rcu_preempt_exp_mutex. + */ +static int sync_rcu_preempt_exp_done(struct rcu_node *rnp) +{ + return !rcu_preempted_readers_exp(rnp) && + ACCESS_ONCE(rnp->expmask) == 0; +} + +/* + * Report the exit from RCU read-side critical section for the last task + * that queued itself during or before the current expedited preemptible-RCU + * grace period. This event is reported either to the rcu_node structure on + * which the task was queued or to one of that rcu_node structure's ancestors, + * recursively up the tree. (Calm down, calm down, we do the recursion + * iteratively!) + * + * Caller must hold sync_rcu_preempt_exp_mutex. + */ +static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp, + bool wake) +{ + unsigned long flags; + unsigned long mask; + + raw_spin_lock_irqsave(&rnp->lock, flags); + smp_mb__after_unlock_lock(); + for (;;) { + if (!sync_rcu_preempt_exp_done(rnp)) { + raw_spin_unlock_irqrestore(&rnp->lock, flags); + break; + } + if (rnp->parent == NULL) { + raw_spin_unlock_irqrestore(&rnp->lock, flags); + if (wake) { + smp_mb(); /* EGP done before wake_up(). */ + wake_up(&sync_rcu_preempt_exp_wq); + } + break; + } + mask = rnp->grpmask; + raw_spin_unlock(&rnp->lock); /* irqs remain disabled */ + rnp = rnp->parent; + raw_spin_lock(&rnp->lock); /* irqs already disabled */ + smp_mb__after_unlock_lock(); + rnp->expmask &= ~mask; + } +} + +/* + * Snapshot the tasks blocking the newly started preemptible-RCU expedited + * grace period for the specified rcu_node structure, phase 1. If there + * are such tasks, set the ->expmask bits up the rcu_node tree and also + * set the ->expmask bits on the leaf rcu_node structures to tell phase 2 + * that work is needed here. + * + * Caller must hold sync_rcu_preempt_exp_mutex. + */ +static void +sync_rcu_preempt_exp_init1(struct rcu_state *rsp, struct rcu_node *rnp) +{ + unsigned long flags; + unsigned long mask; + struct rcu_node *rnp_up; + + raw_spin_lock_irqsave(&rnp->lock, flags); + smp_mb__after_unlock_lock(); + WARN_ON_ONCE(rnp->expmask); + WARN_ON_ONCE(rnp->exp_tasks); + if (!rcu_preempt_has_tasks(rnp)) { + /* No blocked tasks, nothing to do. */ + raw_spin_unlock_irqrestore(&rnp->lock, flags); + return; + } + /* Call for Phase 2 and propagate ->expmask bits up the tree. */ + rnp->expmask = 1; + rnp_up = rnp; + while (rnp_up->parent) { + mask = rnp_up->grpmask; + rnp_up = rnp_up->parent; + if (rnp_up->expmask & mask) + break; + raw_spin_lock(&rnp_up->lock); /* irqs already off */ + smp_mb__after_unlock_lock(); + rnp_up->expmask |= mask; + raw_spin_unlock(&rnp_up->lock); /* irqs still off */ + } + raw_spin_unlock_irqrestore(&rnp->lock, flags); +} + +/* + * Snapshot the tasks blocking the newly started preemptible-RCU expedited + * grace period for the specified rcu_node structure, phase 2. If the + * leaf rcu_node structure has its ->expmask field set, check for tasks. + * If there are some, clear ->expmask and set ->exp_tasks accordingly, + * then initiate RCU priority boosting. Otherwise, clear ->expmask and + * invoke rcu_report_exp_rnp() to clear out the upper-level ->expmask bits, + * enabling rcu_read_unlock_special() to do the bit-clearing. + * + * Caller must hold sync_rcu_preempt_exp_mutex. + */ +static void +sync_rcu_preempt_exp_init2(struct rcu_state *rsp, struct rcu_node *rnp) +{ + unsigned long flags; + + raw_spin_lock_irqsave(&rnp->lock, flags); + smp_mb__after_unlock_lock(); + if (!rnp->expmask) { + /* Phase 1 didn't do anything, so Phase 2 doesn't either. */ + raw_spin_unlock_irqrestore(&rnp->lock, flags); + return; + } + + /* Phase 1 is over. */ + rnp->expmask = 0; + + /* + * If there are still blocked tasks, set up ->exp_tasks so that + * rcu_read_unlock_special() will wake us and then boost them. + */ + if (rcu_preempt_has_tasks(rnp)) { + rnp->exp_tasks = rnp->blkd_tasks.next; + rcu_initiate_boost(rnp, flags); /* releases rnp->lock */ + return; + } + + /* No longer any blocked tasks, so undo bit setting. */ + raw_spin_unlock_irqrestore(&rnp->lock, flags); + rcu_report_exp_rnp(rsp, rnp, false); +} + +/** + * synchronize_rcu_expedited - Brute-force RCU grace period + * + * Wait for an RCU-preempt grace period, but expedite it. The basic + * idea is to invoke synchronize_sched_expedited() to push all the tasks to + * the ->blkd_tasks lists and wait for this list to drain. This consumes + * significant time on all CPUs and is unfriendly to real-time workloads, + * so is thus not recommended for any sort of common-case code. + * In fact, if you are using synchronize_rcu_expedited() in a loop, + * please restructure your code to batch your updates, and then Use a + * single synchronize_rcu() instead. + */ +void synchronize_rcu_expedited(void) +{ + struct rcu_node *rnp; + struct rcu_state *rsp = &rcu_preempt_state; + unsigned long snap; + int trycount = 0; + + smp_mb(); /* Caller's modifications seen first by other CPUs. */ + snap = ACCESS_ONCE(sync_rcu_preempt_exp_count) + 1; + smp_mb(); /* Above access cannot bleed into critical section. */ + + /* + * Block CPU-hotplug operations. This means that any CPU-hotplug + * operation that finds an rcu_node structure with tasks in the + * process of being boosted will know that all tasks blocking + * this expedited grace period will already be in the process of + * being boosted. This simplifies the process of moving tasks + * from leaf to root rcu_node structures. + */ + if (!try_get_online_cpus()) { + /* CPU-hotplug operation in flight, fall back to normal GP. */ + wait_rcu_gp(call_rcu); + return; + } + + /* + * Acquire lock, falling back to synchronize_rcu() if too many + * lock-acquisition failures. Of course, if someone does the + * expedited grace period for us, just leave. + */ + while (!mutex_trylock(&sync_rcu_preempt_exp_mutex)) { + if (ULONG_CMP_LT(snap, + ACCESS_ONCE(sync_rcu_preempt_exp_count))) { + put_online_cpus(); + goto mb_ret; /* Others did our work for us. */ + } + if (trycount++ < 10) { + udelay(trycount * num_online_cpus()); + } else { + put_online_cpus(); + wait_rcu_gp(call_rcu); + return; + } + } + if (ULONG_CMP_LT(snap, ACCESS_ONCE(sync_rcu_preempt_exp_count))) { + put_online_cpus(); + goto unlock_mb_ret; /* Others did our work for us. */ + } + + /* force all RCU readers onto ->blkd_tasks lists. */ + synchronize_sched_expedited(); + + /* + * Snapshot current state of ->blkd_tasks lists into ->expmask. + * Phase 1 sets bits and phase 2 permits rcu_read_unlock_special() + * to start clearing them. Doing this in one phase leads to + * strange races between setting and clearing bits, so just say "no"! + */ + rcu_for_each_leaf_node(rsp, rnp) + sync_rcu_preempt_exp_init1(rsp, rnp); + rcu_for_each_leaf_node(rsp, rnp) + sync_rcu_preempt_exp_init2(rsp, rnp); + + put_online_cpus(); + + /* Wait for snapshotted ->blkd_tasks lists to drain. */ + rnp = rcu_get_root(rsp); + wait_event(sync_rcu_preempt_exp_wq, + sync_rcu_preempt_exp_done(rnp)); + + /* Clean up and exit. */ + smp_mb(); /* ensure expedited GP seen before counter increment. */ + ACCESS_ONCE(sync_rcu_preempt_exp_count) = + sync_rcu_preempt_exp_count + 1; +unlock_mb_ret: + mutex_unlock(&sync_rcu_preempt_exp_mutex); +mb_ret: + smp_mb(); /* ensure subsequent action seen after grace period. */ +} +EXPORT_SYMBOL_GPL(synchronize_rcu_expedited); + +/** + * rcu_barrier - Wait until all in-flight call_rcu() callbacks complete. + * + * Note that this primitive does not necessarily wait for an RCU grace period + * to complete. For example, if there are no RCU callbacks queued anywhere + * in the system, then rcu_barrier() is within its rights to return + * immediately, without waiting for anything, much less an RCU grace period. + */ +void rcu_barrier(void) +{ + _rcu_barrier(&rcu_preempt_state); +} +EXPORT_SYMBOL_GPL(rcu_barrier); + +/* + * Initialize preemptible RCU's state structures. + */ +static void __init __rcu_init_preempt(void) +{ + rcu_init_one(&rcu_preempt_state, &rcu_preempt_data); +} + +/* + * Check for a task exiting while in a preemptible-RCU read-side + * critical section, clean up if so. No need to issue warnings, + * as debug_check_no_locks_held() already does this if lockdep + * is enabled. + */ +void exit_rcu(void) +{ + struct task_struct *t = current; + + if (likely(list_empty(¤t->rcu_node_entry))) + return; + t->rcu_read_lock_nesting = 1; + barrier(); + t->rcu_read_unlock_special.b.blocked = true; + __rcu_read_unlock(); +} + +#else /* #ifdef CONFIG_PREEMPT_RCU */ + +static struct rcu_state *rcu_state_p = &rcu_sched_state; + +/* + * Tell them what RCU they are running. + */ +static void __init rcu_bootup_announce(void) +{ + pr_info("Hierarchical RCU implementation.\n"); + rcu_bootup_announce_oddness(); +} + +/* + * Because preemptible RCU does not exist, we never have to check for + * CPUs being in quiescent states. + */ +static void rcu_preempt_note_context_switch(void) +{ +} + +/* + * Because preemptible RCU does not exist, there are never any preempted + * RCU readers. + */ +static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp) +{ + return 0; +} + +/* + * Because there is no preemptible RCU, there can be no readers blocked. + */ +static bool rcu_preempt_has_tasks(struct rcu_node *rnp) +{ + return false; +} + +/* + * Because preemptible RCU does not exist, we never have to check for + * tasks blocked within RCU read-side critical sections. + */ +static void rcu_print_detail_task_stall(struct rcu_state *rsp) +{ +} + +/* + * Because preemptible RCU does not exist, we never have to check for + * tasks blocked within RCU read-side critical sections. + */ +static int rcu_print_task_stall(struct rcu_node *rnp) +{ + return 0; +} + +/* + * Because there is no preemptible RCU, there can be no readers blocked, + * so there is no need to check for blocked tasks. So check only for + * bogus qsmask values. + */ +static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp) +{ + WARN_ON_ONCE(rnp->qsmask); +} + +/* + * Because preemptible RCU does not exist, it never has any callbacks + * to check. + */ +static void rcu_preempt_check_callbacks(void) +{ +} + +/* + * Wait for an rcu-preempt grace period, but make it happen quickly. + * But because preemptible RCU does not exist, map to rcu-sched. + */ +void synchronize_rcu_expedited(void) +{ + synchronize_sched_expedited(); +} +EXPORT_SYMBOL_GPL(synchronize_rcu_expedited); + +/* + * Because preemptible RCU does not exist, rcu_barrier() is just + * another name for rcu_barrier_sched(). + */ +void rcu_barrier(void) +{ + rcu_barrier_sched(); +} +EXPORT_SYMBOL_GPL(rcu_barrier); + +/* + * Because preemptible RCU does not exist, it need not be initialized. + */ +static void __init __rcu_init_preempt(void) +{ +} + +/* + * Because preemptible RCU does not exist, tasks cannot possibly exit + * while in preemptible RCU read-side critical sections. + */ +void exit_rcu(void) +{ +} + +#endif /* #else #ifdef CONFIG_PREEMPT_RCU */ + +/* + * If boosting, set rcuc kthreads to realtime priority. + */ +static void rcu_cpu_kthread_setup(unsigned int cpu) +{ +#ifdef CONFIG_RCU_BOOST + struct sched_param sp; + + sp.sched_priority = kthread_prio; + sched_setscheduler_nocheck(current, SCHED_FIFO, &sp); +#endif /* #ifdef CONFIG_RCU_BOOST */ +} + +#ifdef CONFIG_RCU_BOOST + +#include "../locking/rtmutex_common.h" + +#ifdef CONFIG_RCU_TRACE + +static void rcu_initiate_boost_trace(struct rcu_node *rnp) +{ + if (!rcu_preempt_has_tasks(rnp)) + rnp->n_balk_blkd_tasks++; + else if (rnp->exp_tasks == NULL && rnp->gp_tasks == NULL) + rnp->n_balk_exp_gp_tasks++; + else if (rnp->gp_tasks != NULL && rnp->boost_tasks != NULL) + rnp->n_balk_boost_tasks++; + else if (rnp->gp_tasks != NULL && rnp->qsmask != 0) + rnp->n_balk_notblocked++; + else if (rnp->gp_tasks != NULL && + ULONG_CMP_LT(jiffies, rnp->boost_time)) + rnp->n_balk_notyet++; + else + rnp->n_balk_nos++; +} + +#else /* #ifdef CONFIG_RCU_TRACE */ + +static void rcu_initiate_boost_trace(struct rcu_node *rnp) +{ +} + +#endif /* #else #ifdef CONFIG_RCU_TRACE */ + +/* + * Carry out RCU priority boosting on the task indicated by ->exp_tasks + * or ->boost_tasks, advancing the pointer to the next task in the + * ->blkd_tasks list. + * + * Note that irqs must be enabled: boosting the task can block. + * Returns 1 if there are more tasks needing to be boosted. + */ +static int rcu_boost(struct rcu_node *rnp) +{ + unsigned long flags; + struct task_struct *t; + struct list_head *tb; + + if (ACCESS_ONCE(rnp->exp_tasks) == NULL && + ACCESS_ONCE(rnp->boost_tasks) == NULL) + return 0; /* Nothing left to boost. */ + + raw_spin_lock_irqsave(&rnp->lock, flags); + smp_mb__after_unlock_lock(); + + /* + * Recheck under the lock: all tasks in need of boosting + * might exit their RCU read-side critical sections on their own. + */ + if (rnp->exp_tasks == NULL && rnp->boost_tasks == NULL) { + raw_spin_unlock_irqrestore(&rnp->lock, flags); + return 0; + } + + /* + * Preferentially boost tasks blocking expedited grace periods. + * This cannot starve the normal grace periods because a second + * expedited grace period must boost all blocked tasks, including + * those blocking the pre-existing normal grace period. + */ + if (rnp->exp_tasks != NULL) { + tb = rnp->exp_tasks; + rnp->n_exp_boosts++; + } else { + tb = rnp->boost_tasks; + rnp->n_normal_boosts++; + } + rnp->n_tasks_boosted++; + + /* + * We boost task t by manufacturing an rt_mutex that appears to + * be held by task t. We leave a pointer to that rt_mutex where + * task t can find it, and task t will release the mutex when it + * exits its outermost RCU read-side critical section. Then + * simply acquiring this artificial rt_mutex will boost task + * t's priority. (Thanks to tglx for suggesting this approach!) + * + * Note that task t must acquire rnp->lock to remove itself from + * the ->blkd_tasks list, which it will do from exit() if from + * nowhere else. We therefore are guaranteed that task t will + * stay around at least until we drop rnp->lock. Note that + * rnp->lock also resolves races between our priority boosting + * and task t's exiting its outermost RCU read-side critical + * section. + */ + t = container_of(tb, struct task_struct, rcu_node_entry); + rt_mutex_init_proxy_locked(&rnp->boost_mtx, t); + raw_spin_unlock_irqrestore(&rnp->lock, flags); + /* Lock only for side effect: boosts task t's priority. */ + rt_mutex_lock(&rnp->boost_mtx); + rt_mutex_unlock(&rnp->boost_mtx); /* Then keep lockdep happy. */ + + return ACCESS_ONCE(rnp->exp_tasks) != NULL || + ACCESS_ONCE(rnp->boost_tasks) != NULL; +} + +/* + * Priority-boosting kthread. One per leaf rcu_node and one for the + * root rcu_node. + */ +static int rcu_boost_kthread(void *arg) +{ + struct rcu_node *rnp = (struct rcu_node *)arg; + int spincnt = 0; + int more2boost; + + trace_rcu_utilization(TPS("Start boost kthread@init")); + for (;;) { + rnp->boost_kthread_status = RCU_KTHREAD_WAITING; + trace_rcu_utilization(TPS("End boost kthread@rcu_wait")); + rcu_wait(rnp->boost_tasks || rnp->exp_tasks); + trace_rcu_utilization(TPS("Start boost kthread@rcu_wait")); + rnp->boost_kthread_status = RCU_KTHREAD_RUNNING; + more2boost = rcu_boost(rnp); + if (more2boost) + spincnt++; + else + spincnt = 0; + if (spincnt > 10) { + rnp->boost_kthread_status = RCU_KTHREAD_YIELDING; + trace_rcu_utilization(TPS("End boost kthread@rcu_yield")); + schedule_timeout_interruptible(2); + trace_rcu_utilization(TPS("Start boost kthread@rcu_yield")); + spincnt = 0; + } + } + /* NOTREACHED */ + trace_rcu_utilization(TPS("End boost kthread@notreached")); + return 0; +} + +/* + * Check to see if it is time to start boosting RCU readers that are + * blocking the current grace period, and, if so, tell the per-rcu_node + * kthread to start boosting them. If there is an expedited grace + * period in progress, it is always time to boost. + * + * The caller must hold rnp->lock, which this function releases. + * The ->boost_kthread_task is immortal, so we don't need to worry + * about it going away. + */ +static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags) + __releases(rnp->lock) +{ + struct task_struct *t; + + if (!rcu_preempt_blocked_readers_cgp(rnp) && rnp->exp_tasks == NULL) { + rnp->n_balk_exp_gp_tasks++; + raw_spin_unlock_irqrestore(&rnp->lock, flags); + return; + } + if (rnp->exp_tasks != NULL || + (rnp->gp_tasks != NULL && + rnp->boost_tasks == NULL && + rnp->qsmask == 0 && + ULONG_CMP_GE(jiffies, rnp->boost_time))) { + if (rnp->exp_tasks == NULL) + rnp->boost_tasks = rnp->gp_tasks; + raw_spin_unlock_irqrestore(&rnp->lock, flags); + t = rnp->boost_kthread_task; + if (t) + rcu_wake_cond(t, rnp->boost_kthread_status); + } else { + rcu_initiate_boost_trace(rnp); + raw_spin_unlock_irqrestore(&rnp->lock, flags); + } +} + +/* + * Is the current CPU running the RCU-callbacks kthread? + * Caller must have preemption disabled. + */ +static bool rcu_is_callbacks_kthread(void) +{ + return __this_cpu_read(rcu_cpu_kthread_task) == current; +} + +#define RCU_BOOST_DELAY_JIFFIES DIV_ROUND_UP(CONFIG_RCU_BOOST_DELAY * HZ, 1000) + +/* + * Do priority-boost accounting for the start of a new grace period. + */ +static void rcu_preempt_boost_start_gp(struct rcu_node *rnp) +{ + rnp->boost_time = jiffies + RCU_BOOST_DELAY_JIFFIES; +} + +/* + * Create an RCU-boost kthread for the specified node if one does not + * already exist. We only create this kthread for preemptible RCU. + * Returns zero if all is well, a negated errno otherwise. + */ +static int rcu_spawn_one_boost_kthread(struct rcu_state *rsp, + struct rcu_node *rnp) +{ + int rnp_index = rnp - &rsp->node[0]; + unsigned long flags; + struct sched_param sp; + struct task_struct *t; + + if (&rcu_preempt_state != rsp) + return 0; + + if (!rcu_scheduler_fully_active || rcu_rnp_online_cpus(rnp) == 0) + return 0; + + rsp->boost = 1; + if (rnp->boost_kthread_task != NULL) + return 0; + t = kthread_create(rcu_boost_kthread, (void *)rnp, + "rcub/%d", rnp_index); + if (IS_ERR(t)) + return PTR_ERR(t); + raw_spin_lock_irqsave(&rnp->lock, flags); + smp_mb__after_unlock_lock(); + rnp->boost_kthread_task = t; + raw_spin_unlock_irqrestore(&rnp->lock, flags); + sp.sched_priority = kthread_prio; + sched_setscheduler_nocheck(t, SCHED_FIFO, &sp); + wake_up_process(t); /* get to TASK_INTERRUPTIBLE quickly. */ + return 0; +} + +/* + * Set the per-rcu_node kthread's affinity to cover all CPUs that are + * served by the rcu_node in question. The CPU hotplug lock is still + * held, so the value of rnp->qsmaskinit will be stable. + * + * We don't include outgoingcpu in the affinity set, use -1 if there is + * no outgoing CPU. If there are no CPUs left in the affinity set, + * this function allows the kthread to execute on any CPU. + */ +static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu) +{ + struct task_struct *t = rnp->boost_kthread_task; + unsigned long mask = rcu_rnp_online_cpus(rnp); + cpumask_var_t cm; + int cpu; + + if (!t) + return; + if (!zalloc_cpumask_var(&cm, GFP_KERNEL)) + return; + for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++, mask >>= 1) + if ((mask & 0x1) && cpu != outgoingcpu) + cpumask_set_cpu(cpu, cm); + if (cpumask_weight(cm) == 0) + cpumask_setall(cm); + set_cpus_allowed_ptr(t, cm); + free_cpumask_var(cm); +} + +/* + * Spawn boost kthreads -- called as soon as the scheduler is running. + */ +static void __init rcu_spawn_boost_kthreads(void) +{ + struct rcu_node *rnp; + rcu_for_each_leaf_node(rcu_state_p, rnp) + (void)rcu_spawn_one_boost_kthread(rcu_state_p, rnp); +} + +static void rcu_prepare_kthreads(int cpu) +{ + struct rcu_data *rdp = per_cpu_ptr(rcu_state_p->rda, cpu); + struct rcu_node *rnp = rdp->mynode; + + /* Fire up the incoming CPU's kthread and leaf rcu_node kthread. */ + if (rcu_scheduler_fully_active) + (void)rcu_spawn_one_boost_kthread(rcu_state_p, rnp); +} + +#else /* #ifdef CONFIG_RCU_BOOST */ + +static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags) + __releases(rnp->lock) +{ + raw_spin_unlock_irqrestore(&rnp->lock, flags); +} + +static bool rcu_is_callbacks_kthread(void) +{ + return false; +} + +static void rcu_preempt_boost_start_gp(struct rcu_node *rnp) +{ +} + +static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu) +{ +} + +static void __init rcu_spawn_boost_kthreads(void) +{ +} + +static void rcu_prepare_kthreads(int cpu) +{ +} + +#endif /* #else #ifdef CONFIG_RCU_BOOST */ + +#if !defined(CONFIG_RCU_FAST_NO_HZ) || defined(CONFIG_PREEMPT_RT_FULL) + +/* + * Check to see if any future RCU-related work will need to be done + * by the current CPU, even if none need be done immediately, returning + * 1 if so. This function is part of the RCU implementation; it is -not- + * an exported member of the RCU API. + * + * Because we not have RCU_FAST_NO_HZ, just check whether this CPU needs + * any flavor of RCU. + */ +#ifndef CONFIG_RCU_NOCB_CPU_ALL +int rcu_needs_cpu(unsigned long *delta_jiffies) +{ + *delta_jiffies = ULONG_MAX; + return rcu_cpu_has_callbacks(NULL); +} +#endif /* #ifndef CONFIG_RCU_NOCB_CPU_ALL */ +#endif /* !defined(CONFIG_RCU_FAST_NO_HZ) || defined(CONFIG_PREEMPT_RT_FULL) */ + +#if !defined(CONFIG_RCU_FAST_NO_HZ) +/* + * Because we do not have RCU_FAST_NO_HZ, don't bother cleaning up + * after it. + */ +static void rcu_cleanup_after_idle(void) +{ +} + +/* + * Do the idle-entry grace-period work, which, because CONFIG_RCU_FAST_NO_HZ=n, + * is nothing. + */ +static void rcu_prepare_for_idle(void) +{ +} + +/* + * Don't bother keeping a running count of the number of RCU callbacks + * posted because CONFIG_RCU_FAST_NO_HZ=n. + */ +static void rcu_idle_count_callbacks_posted(void) +{ +} + +#else /* #if !defined(CONFIG_RCU_FAST_NO_HZ) */ + +/* + * This code is invoked when a CPU goes idle, at which point we want + * to have the CPU do everything required for RCU so that it can enter + * the energy-efficient dyntick-idle mode. This is handled by a + * state machine implemented by rcu_prepare_for_idle() below. + * + * The following three proprocessor symbols control this state machine: + * + * RCU_IDLE_GP_DELAY gives the number of jiffies that a CPU is permitted + * to sleep in dyntick-idle mode with RCU callbacks pending. This + * is sized to be roughly one RCU grace period. Those energy-efficiency + * benchmarkers who might otherwise be tempted to set this to a large + * number, be warned: Setting RCU_IDLE_GP_DELAY too high can hang your + * system. And if you are -that- concerned about energy efficiency, + * just power the system down and be done with it! + * RCU_IDLE_LAZY_GP_DELAY gives the number of jiffies that a CPU is + * permitted to sleep in dyntick-idle mode with only lazy RCU + * callbacks pending. Setting this too high can OOM your system. + * + * The values below work well in practice. If future workloads require + * adjustment, they can be converted into kernel config parameters, though + * making the state machine smarter might be a better option. + */ +#define RCU_IDLE_GP_DELAY 4 /* Roughly one grace period. */ +#define RCU_IDLE_LAZY_GP_DELAY (6 * HZ) /* Roughly six seconds. */ + +static int rcu_idle_gp_delay = RCU_IDLE_GP_DELAY; +module_param(rcu_idle_gp_delay, int, 0644); +static int rcu_idle_lazy_gp_delay = RCU_IDLE_LAZY_GP_DELAY; +module_param(rcu_idle_lazy_gp_delay, int, 0644); + +extern int tick_nohz_active; + +/* + * Try to advance callbacks for all flavors of RCU on the current CPU, but + * only if it has been awhile since the last time we did so. Afterwards, + * if there are any callbacks ready for immediate invocation, return true. + */ +static bool __maybe_unused rcu_try_advance_all_cbs(void) +{ + bool cbs_ready = false; + struct rcu_data *rdp; + struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks); + struct rcu_node *rnp; + struct rcu_state *rsp; + + /* Exit early if we advanced recently. */ + if (jiffies == rdtp->last_advance_all) + return false; + rdtp->last_advance_all = jiffies; + + for_each_rcu_flavor(rsp) { + rdp = this_cpu_ptr(rsp->rda); + rnp = rdp->mynode; + + /* + * Don't bother checking unless a grace period has + * completed since we last checked and there are + * callbacks not yet ready to invoke. + */ + if ((rdp->completed != rnp->completed || + unlikely(ACCESS_ONCE(rdp->gpwrap))) && + rdp->nxttail[RCU_DONE_TAIL] != rdp->nxttail[RCU_NEXT_TAIL]) + note_gp_changes(rsp, rdp); + + if (cpu_has_callbacks_ready_to_invoke(rdp)) + cbs_ready = true; + } + return cbs_ready; +} + +#ifndef CONFIG_PREEMPT_RT_FULL + +/* + * Allow the CPU to enter dyntick-idle mode unless it has callbacks ready + * to invoke. If the CPU has callbacks, try to advance them. Tell the + * caller to set the timeout based on whether or not there are non-lazy + * callbacks. + * + * The caller must have disabled interrupts. + */ +#ifndef CONFIG_RCU_NOCB_CPU_ALL +int rcu_needs_cpu(unsigned long *dj) +{ + struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks); + + /* Snapshot to detect later posting of non-lazy callback. */ + rdtp->nonlazy_posted_snap = rdtp->nonlazy_posted; + + /* If no callbacks, RCU doesn't need the CPU. */ + if (!rcu_cpu_has_callbacks(&rdtp->all_lazy)) { + *dj = ULONG_MAX; + return 0; + } + + /* Attempt to advance callbacks. */ + if (rcu_try_advance_all_cbs()) { + /* Some ready to invoke, so initiate later invocation. */ + invoke_rcu_core(); + return 1; + } + rdtp->last_accelerate = jiffies; + + /* Request timer delay depending on laziness, and round. */ + if (!rdtp->all_lazy) { + *dj = round_up(rcu_idle_gp_delay + jiffies, + rcu_idle_gp_delay) - jiffies; + } else { + *dj = round_jiffies(rcu_idle_lazy_gp_delay + jiffies) - jiffies; + } + return 0; +} +#endif /* #ifndef CONFIG_RCU_NOCB_CPU_ALL */ +#endif /* #ifndef CONFIG_PREEMPT_RT_FULL */ +/* + * Prepare a CPU for idle from an RCU perspective. The first major task + * is to sense whether nohz mode has been enabled or disabled via sysfs. + * The second major task is to check to see if a non-lazy callback has + * arrived at a CPU that previously had only lazy callbacks. The third + * major task is to accelerate (that is, assign grace-period numbers to) + * any recently arrived callbacks. + * + * The caller must have disabled interrupts. + */ +static void rcu_prepare_for_idle(void) +{ +#ifndef CONFIG_RCU_NOCB_CPU_ALL + bool needwake; + struct rcu_data *rdp; + struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks); + struct rcu_node *rnp; + struct rcu_state *rsp; + int tne; + + /* Handle nohz enablement switches conservatively. */ + tne = ACCESS_ONCE(tick_nohz_active); + if (tne != rdtp->tick_nohz_enabled_snap) { + if (rcu_cpu_has_callbacks(NULL)) + invoke_rcu_core(); /* force nohz to see update. */ + rdtp->tick_nohz_enabled_snap = tne; + return; + } + if (!tne) + return; + + /* If this is a no-CBs CPU, no callbacks, just return. */ + if (rcu_is_nocb_cpu(smp_processor_id())) + return; + + /* + * If a non-lazy callback arrived at a CPU having only lazy + * callbacks, invoke RCU core for the side-effect of recalculating + * idle duration on re-entry to idle. + */ + if (rdtp->all_lazy && + rdtp->nonlazy_posted != rdtp->nonlazy_posted_snap) { + rdtp->all_lazy = false; + rdtp->nonlazy_posted_snap = rdtp->nonlazy_posted; + invoke_rcu_core(); + return; + } + + /* + * If we have not yet accelerated this jiffy, accelerate all + * callbacks on this CPU. + */ + if (rdtp->last_accelerate == jiffies) + return; + rdtp->last_accelerate = jiffies; + for_each_rcu_flavor(rsp) { + rdp = this_cpu_ptr(rsp->rda); + if (!*rdp->nxttail[RCU_DONE_TAIL]) + continue; + rnp = rdp->mynode; + raw_spin_lock(&rnp->lock); /* irqs already disabled. */ + smp_mb__after_unlock_lock(); + needwake = rcu_accelerate_cbs(rsp, rnp, rdp); + raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */ + if (needwake) + rcu_gp_kthread_wake(rsp); + } +#endif /* #ifndef CONFIG_RCU_NOCB_CPU_ALL */ +} + +/* + * Clean up for exit from idle. Attempt to advance callbacks based on + * any grace periods that elapsed while the CPU was idle, and if any + * callbacks are now ready to invoke, initiate invocation. + */ +static void rcu_cleanup_after_idle(void) +{ +#ifndef CONFIG_RCU_NOCB_CPU_ALL + if (rcu_is_nocb_cpu(smp_processor_id())) + return; + if (rcu_try_advance_all_cbs()) + invoke_rcu_core(); +#endif /* #ifndef CONFIG_RCU_NOCB_CPU_ALL */ +} + +/* + * Keep a running count of the number of non-lazy callbacks posted + * on this CPU. This running counter (which is never decremented) allows + * rcu_prepare_for_idle() to detect when something out of the idle loop + * posts a callback, even if an equal number of callbacks are invoked. + * Of course, callbacks should only be posted from within a trace event + * designed to be called from idle or from within RCU_NONIDLE(). + */ +static void rcu_idle_count_callbacks_posted(void) +{ + __this_cpu_add(rcu_dynticks.nonlazy_posted, 1); +} + +/* + * Data for flushing lazy RCU callbacks at OOM time. + */ +static atomic_t oom_callback_count; +static DECLARE_WAIT_QUEUE_HEAD(oom_callback_wq); + +/* + * RCU OOM callback -- decrement the outstanding count and deliver the + * wake-up if we are the last one. + */ +static void rcu_oom_callback(struct rcu_head *rhp) +{ + if (atomic_dec_and_test(&oom_callback_count)) + wake_up(&oom_callback_wq); +} + +/* + * Post an rcu_oom_notify callback on the current CPU if it has at + * least one lazy callback. This will unnecessarily post callbacks + * to CPUs that already have a non-lazy callback at the end of their + * callback list, but this is an infrequent operation, so accept some + * extra overhead to keep things simple. + */ +static void rcu_oom_notify_cpu(void *unused) +{ + struct rcu_state *rsp; + struct rcu_data *rdp; + + for_each_rcu_flavor(rsp) { + rdp = raw_cpu_ptr(rsp->rda); + if (rdp->qlen_lazy != 0) { + atomic_inc(&oom_callback_count); + rsp->call(&rdp->oom_head, rcu_oom_callback); + } + } +} + +/* + * If low on memory, ensure that each CPU has a non-lazy callback. + * This will wake up CPUs that have only lazy callbacks, in turn + * ensuring that they free up the corresponding memory in a timely manner. + * Because an uncertain amount of memory will be freed in some uncertain + * timeframe, we do not claim to have freed anything. + */ +static int rcu_oom_notify(struct notifier_block *self, + unsigned long notused, void *nfreed) +{ + int cpu; + + /* Wait for callbacks from earlier instance to complete. */ + wait_event(oom_callback_wq, atomic_read(&oom_callback_count) == 0); + smp_mb(); /* Ensure callback reuse happens after callback invocation. */ + + /* + * Prevent premature wakeup: ensure that all increments happen + * before there is a chance of the counter reaching zero. + */ + atomic_set(&oom_callback_count, 1); + + get_online_cpus(); + for_each_online_cpu(cpu) { + smp_call_function_single(cpu, rcu_oom_notify_cpu, NULL, 1); + cond_resched_rcu_qs(); + } + put_online_cpus(); + + /* Unconditionally decrement: no need to wake ourselves up. */ + atomic_dec(&oom_callback_count); + + return NOTIFY_OK; +} + +static struct notifier_block rcu_oom_nb = { + .notifier_call = rcu_oom_notify +}; + +static int __init rcu_register_oom_notifier(void) +{ + register_oom_notifier(&rcu_oom_nb); + return 0; +} +early_initcall(rcu_register_oom_notifier); + +#endif /* #else #if !defined(CONFIG_RCU_FAST_NO_HZ) */ + +#ifdef CONFIG_RCU_CPU_STALL_INFO + +#ifdef CONFIG_RCU_FAST_NO_HZ + +static void print_cpu_stall_fast_no_hz(char *cp, int cpu) +{ + struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu); + unsigned long nlpd = rdtp->nonlazy_posted - rdtp->nonlazy_posted_snap; + + sprintf(cp, "last_accelerate: %04lx/%04lx, nonlazy_posted: %ld, %c%c", + rdtp->last_accelerate & 0xffff, jiffies & 0xffff, + ulong2long(nlpd), + rdtp->all_lazy ? 'L' : '.', + rdtp->tick_nohz_enabled_snap ? '.' : 'D'); +} + +#else /* #ifdef CONFIG_RCU_FAST_NO_HZ */ + +static void print_cpu_stall_fast_no_hz(char *cp, int cpu) +{ + *cp = '\0'; +} + +#endif /* #else #ifdef CONFIG_RCU_FAST_NO_HZ */ + +/* Initiate the stall-info list. */ +static void print_cpu_stall_info_begin(void) +{ + pr_cont("\n"); +} + +/* + * Print out diagnostic information for the specified stalled CPU. + * + * If the specified CPU is aware of the current RCU grace period + * (flavor specified by rsp), then print the number of scheduling + * clock interrupts the CPU has taken during the time that it has + * been aware. Otherwise, print the number of RCU grace periods + * that this CPU is ignorant of, for example, "1" if the CPU was + * aware of the previous grace period. + * + * Also print out idle and (if CONFIG_RCU_FAST_NO_HZ) idle-entry info. + */ +static void print_cpu_stall_info(struct rcu_state *rsp, int cpu) +{ + char fast_no_hz[72]; + struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu); + struct rcu_dynticks *rdtp = rdp->dynticks; + char *ticks_title; + unsigned long ticks_value; + + if (rsp->gpnum == rdp->gpnum) { + ticks_title = "ticks this GP"; + ticks_value = rdp->ticks_this_gp; + } else { + ticks_title = "GPs behind"; + ticks_value = rsp->gpnum - rdp->gpnum; + } + print_cpu_stall_fast_no_hz(fast_no_hz, cpu); + pr_err("\t%d: (%lu %s) idle=%03x/%llx/%d softirq=%u/%u fqs=%ld %s\n", + cpu, ticks_value, ticks_title, + atomic_read(&rdtp->dynticks) & 0xfff, + rdtp->dynticks_nesting, rdtp->dynticks_nmi_nesting, + rdp->softirq_snap, kstat_softirqs_cpu(RCU_SOFTIRQ, cpu), + ACCESS_ONCE(rsp->n_force_qs) - rsp->n_force_qs_gpstart, + fast_no_hz); +} + +/* Terminate the stall-info list. */ +static void print_cpu_stall_info_end(void) +{ + pr_err("\t"); +} + +/* Zero ->ticks_this_gp for all flavors of RCU. */ +static void zero_cpu_stall_ticks(struct rcu_data *rdp) +{ + rdp->ticks_this_gp = 0; + rdp->softirq_snap = kstat_softirqs_cpu(RCU_SOFTIRQ, smp_processor_id()); +} + +/* Increment ->ticks_this_gp for all flavors of RCU. */ +static void increment_cpu_stall_ticks(void) +{ + struct rcu_state *rsp; + + for_each_rcu_flavor(rsp) + raw_cpu_inc(rsp->rda->ticks_this_gp); +} + +#else /* #ifdef CONFIG_RCU_CPU_STALL_INFO */ + +static void print_cpu_stall_info_begin(void) +{ + pr_cont(" {"); +} + +static void print_cpu_stall_info(struct rcu_state *rsp, int cpu) +{ + pr_cont(" %d", cpu); +} + +static void print_cpu_stall_info_end(void) +{ + pr_cont("} "); +} + +static void zero_cpu_stall_ticks(struct rcu_data *rdp) +{ +} + +static void increment_cpu_stall_ticks(void) +{ +} + +#endif /* #else #ifdef CONFIG_RCU_CPU_STALL_INFO */ + +#ifdef CONFIG_RCU_NOCB_CPU + +/* + * Offload callback processing from the boot-time-specified set of CPUs + * specified by rcu_nocb_mask. For each CPU in the set, there is a + * kthread created that pulls the callbacks from the corresponding CPU, + * waits for a grace period to elapse, and invokes the callbacks. + * The no-CBs CPUs do a wake_up() on their kthread when they insert + * a callback into any empty list, unless the rcu_nocb_poll boot parameter + * has been specified, in which case each kthread actively polls its + * CPU. (Which isn't so great for energy efficiency, but which does + * reduce RCU's overhead on that CPU.) + * + * This is intended to be used in conjunction with Frederic Weisbecker's + * adaptive-idle work, which would seriously reduce OS jitter on CPUs + * running CPU-bound user-mode computations. + * + * Offloading of callback processing could also in theory be used as + * an energy-efficiency measure because CPUs with no RCU callbacks + * queued are more aggressive about entering dyntick-idle mode. + */ + + +/* Parse the boot-time rcu_nocb_mask CPU list from the kernel parameters. */ +static int __init rcu_nocb_setup(char *str) +{ + alloc_bootmem_cpumask_var(&rcu_nocb_mask); + have_rcu_nocb_mask = true; + cpulist_parse(str, rcu_nocb_mask); + return 1; +} +__setup("rcu_nocbs=", rcu_nocb_setup); + +static int __init parse_rcu_nocb_poll(char *arg) +{ + rcu_nocb_poll = 1; + return 0; +} +early_param("rcu_nocb_poll", parse_rcu_nocb_poll); + +/* + * Wake up any no-CBs CPUs' kthreads that were waiting on the just-ended + * grace period. + */ +static void rcu_nocb_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp) +{ + swait_wake_all(&rnp->nocb_gp_wq[rnp->completed & 0x1]); +} + +/* + * Set the root rcu_node structure's ->need_future_gp field + * based on the sum of those of all rcu_node structures. This does + * double-count the root rcu_node structure's requests, but this + * is necessary to handle the possibility of a rcu_nocb_kthread() + * having awakened during the time that the rcu_node structures + * were being updated for the end of the previous grace period. + */ +static void rcu_nocb_gp_set(struct rcu_node *rnp, int nrq) +{ + rnp->need_future_gp[(rnp->completed + 1) & 0x1] += nrq; +} + +static void rcu_init_one_nocb(struct rcu_node *rnp) +{ + init_swait_head(&rnp->nocb_gp_wq[0]); + init_swait_head(&rnp->nocb_gp_wq[1]); +} + +#ifndef CONFIG_RCU_NOCB_CPU_ALL +/* Is the specified CPU a no-CBs CPU? */ +bool rcu_is_nocb_cpu(int cpu) +{ + if (have_rcu_nocb_mask) + return cpumask_test_cpu(cpu, rcu_nocb_mask); + return false; +} +#endif /* #ifndef CONFIG_RCU_NOCB_CPU_ALL */ + +/* + * Kick the leader kthread for this NOCB group. + */ +static void wake_nocb_leader(struct rcu_data *rdp, bool force) +{ + struct rcu_data *rdp_leader = rdp->nocb_leader; + + if (!ACCESS_ONCE(rdp_leader->nocb_kthread)) + return; + if (ACCESS_ONCE(rdp_leader->nocb_leader_sleep) || force) { + /* Prior smp_mb__after_atomic() orders against prior enqueue. */ + ACCESS_ONCE(rdp_leader->nocb_leader_sleep) = false; + swait_wake(&rdp_leader->nocb_wq); + } +} + +/* + * Does the specified CPU need an RCU callback for the specified flavor + * of rcu_barrier()? + */ +static bool rcu_nocb_cpu_needs_barrier(struct rcu_state *rsp, int cpu) +{ + struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu); + unsigned long ret; +#ifdef CONFIG_PROVE_RCU + struct rcu_head *rhp; +#endif /* #ifdef CONFIG_PROVE_RCU */ + + /* + * Check count of all no-CBs callbacks awaiting invocation. + * There needs to be a barrier before this function is called, + * but associated with a prior determination that no more + * callbacks would be posted. In the worst case, the first + * barrier in _rcu_barrier() suffices (but the caller cannot + * necessarily rely on this, not a substitute for the caller + * getting the concurrency design right!). There must also be + * a barrier between the following load an posting of a callback + * (if a callback is in fact needed). This is associated with an + * atomic_inc() in the caller. + */ + ret = atomic_long_read(&rdp->nocb_q_count); + +#ifdef CONFIG_PROVE_RCU + rhp = ACCESS_ONCE(rdp->nocb_head); + if (!rhp) + rhp = ACCESS_ONCE(rdp->nocb_gp_head); + if (!rhp) + rhp = ACCESS_ONCE(rdp->nocb_follower_head); + + /* Having no rcuo kthread but CBs after scheduler starts is bad! */ + if (!ACCESS_ONCE(rdp->nocb_kthread) && rhp && + rcu_scheduler_fully_active) { + /* RCU callback enqueued before CPU first came online??? */ + pr_err("RCU: Never-onlined no-CBs CPU %d has CB %p\n", + cpu, rhp->func); + WARN_ON_ONCE(1); + } +#endif /* #ifdef CONFIG_PROVE_RCU */ + + return !!ret; +} + +/* + * Enqueue the specified string of rcu_head structures onto the specified + * CPU's no-CBs lists. The CPU is specified by rdp, the head of the + * string by rhp, and the tail of the string by rhtp. The non-lazy/lazy + * counts are supplied by rhcount and rhcount_lazy. + * + * If warranted, also wake up the kthread servicing this CPUs queues. + */ +static void __call_rcu_nocb_enqueue(struct rcu_data *rdp, + struct rcu_head *rhp, + struct rcu_head **rhtp, + int rhcount, int rhcount_lazy, + unsigned long flags) +{ + int len; + struct rcu_head **old_rhpp; + struct task_struct *t; + + /* Enqueue the callback on the nocb list and update counts. */ + atomic_long_add(rhcount, &rdp->nocb_q_count); + /* rcu_barrier() relies on ->nocb_q_count add before xchg. */ + old_rhpp = xchg(&rdp->nocb_tail, rhtp); + ACCESS_ONCE(*old_rhpp) = rhp; + atomic_long_add(rhcount_lazy, &rdp->nocb_q_count_lazy); + smp_mb__after_atomic(); /* Store *old_rhpp before _wake test. */ + + /* If we are not being polled and there is a kthread, awaken it ... */ + t = ACCESS_ONCE(rdp->nocb_kthread); + if (rcu_nocb_poll || !t) { + trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, + TPS("WakeNotPoll")); + return; + } + len = atomic_long_read(&rdp->nocb_q_count); + if (old_rhpp == &rdp->nocb_head) { + if (!irqs_disabled_flags(flags)) { + /* ... if queue was empty ... */ + wake_nocb_leader(rdp, false); + trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, + TPS("WakeEmpty")); + } else { + rdp->nocb_defer_wakeup = RCU_NOGP_WAKE; + trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, + TPS("WakeEmptyIsDeferred")); + } + rdp->qlen_last_fqs_check = 0; + } else if (len > rdp->qlen_last_fqs_check + qhimark) { + /* ... or if many callbacks queued. */ + if (!irqs_disabled_flags(flags)) { + wake_nocb_leader(rdp, true); + trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, + TPS("WakeOvf")); + } else { + rdp->nocb_defer_wakeup = RCU_NOGP_WAKE_FORCE; + trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, + TPS("WakeOvfIsDeferred")); + } + rdp->qlen_last_fqs_check = LONG_MAX / 2; + } else { + trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, TPS("WakeNot")); + } + return; +} + +/* + * This is a helper for __call_rcu(), which invokes this when the normal + * callback queue is inoperable. If this is not a no-CBs CPU, this + * function returns failure back to __call_rcu(), which can complain + * appropriately. + * + * Otherwise, this function queues the callback where the corresponding + * "rcuo" kthread can find it. + */ +static bool __call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *rhp, + bool lazy, unsigned long flags) +{ + + if (!rcu_is_nocb_cpu(rdp->cpu)) + return false; + __call_rcu_nocb_enqueue(rdp, rhp, &rhp->next, 1, lazy, flags); + if (__is_kfree_rcu_offset((unsigned long)rhp->func)) + trace_rcu_kfree_callback(rdp->rsp->name, rhp, + (unsigned long)rhp->func, + -atomic_long_read(&rdp->nocb_q_count_lazy), + -atomic_long_read(&rdp->nocb_q_count)); + else + trace_rcu_callback(rdp->rsp->name, rhp, + -atomic_long_read(&rdp->nocb_q_count_lazy), + -atomic_long_read(&rdp->nocb_q_count)); + + /* + * If called from an extended quiescent state with interrupts + * disabled, invoke the RCU core in order to allow the idle-entry + * deferred-wakeup check to function. + */ + if (irqs_disabled_flags(flags) && + !rcu_is_watching() && + cpu_online(smp_processor_id())) + invoke_rcu_core(); + + return true; +} + +/* + * Adopt orphaned callbacks on a no-CBs CPU, or return 0 if this is + * not a no-CBs CPU. + */ +static bool __maybe_unused rcu_nocb_adopt_orphan_cbs(struct rcu_state *rsp, + struct rcu_data *rdp, + unsigned long flags) +{ + long ql = rsp->qlen; + long qll = rsp->qlen_lazy; + + /* If this is not a no-CBs CPU, tell the caller to do it the old way. */ + if (!rcu_is_nocb_cpu(smp_processor_id())) + return false; + rsp->qlen = 0; + rsp->qlen_lazy = 0; + + /* First, enqueue the donelist, if any. This preserves CB ordering. */ + if (rsp->orphan_donelist != NULL) { + __call_rcu_nocb_enqueue(rdp, rsp->orphan_donelist, + rsp->orphan_donetail, ql, qll, flags); + ql = qll = 0; + rsp->orphan_donelist = NULL; + rsp->orphan_donetail = &rsp->orphan_donelist; + } + if (rsp->orphan_nxtlist != NULL) { + __call_rcu_nocb_enqueue(rdp, rsp->orphan_nxtlist, + rsp->orphan_nxttail, ql, qll, flags); + ql = qll = 0; + rsp->orphan_nxtlist = NULL; + rsp->orphan_nxttail = &rsp->orphan_nxtlist; + } + return true; +} + +/* + * If necessary, kick off a new grace period, and either way wait + * for a subsequent grace period to complete. + */ +static void rcu_nocb_wait_gp(struct rcu_data *rdp) +{ + unsigned long c; + bool d; + unsigned long flags; + bool needwake; + struct rcu_node *rnp = rdp->mynode; + + raw_spin_lock_irqsave(&rnp->lock, flags); + smp_mb__after_unlock_lock(); + needwake = rcu_start_future_gp(rnp, rdp, &c); + raw_spin_unlock_irqrestore(&rnp->lock, flags); + if (needwake) + rcu_gp_kthread_wake(rdp->rsp); + + /* + * Wait for the grace period. Do so interruptibly to avoid messing + * up the load average. + */ + trace_rcu_future_gp(rnp, rdp, c, TPS("StartWait")); + for (;;) { + swait_event_interruptible( + rnp->nocb_gp_wq[c & 0x1], + (d = ULONG_CMP_GE(ACCESS_ONCE(rnp->completed), c))); + if (likely(d)) + break; + WARN_ON(signal_pending(current)); + trace_rcu_future_gp(rnp, rdp, c, TPS("ResumeWait")); + } + trace_rcu_future_gp(rnp, rdp, c, TPS("EndWait")); + smp_mb(); /* Ensure that CB invocation happens after GP end. */ +} + +/* + * Leaders come here to wait for additional callbacks to show up. + * This function does not return until callbacks appear. + */ +static void nocb_leader_wait(struct rcu_data *my_rdp) +{ + bool firsttime = true; + bool gotcbs; + struct rcu_data *rdp; + struct rcu_head **tail; + +wait_again: + + /* Wait for callbacks to appear. */ + if (!rcu_nocb_poll) { + trace_rcu_nocb_wake(my_rdp->rsp->name, my_rdp->cpu, "Sleep"); + swait_event_interruptible(my_rdp->nocb_wq, + !ACCESS_ONCE(my_rdp->nocb_leader_sleep)); + /* Memory barrier handled by smp_mb() calls below and repoll. */ + } else if (firsttime) { + firsttime = false; /* Don't drown trace log with "Poll"! */ + trace_rcu_nocb_wake(my_rdp->rsp->name, my_rdp->cpu, "Poll"); + } + + /* + * Each pass through the following loop checks a follower for CBs. + * We are our own first follower. Any CBs found are moved to + * nocb_gp_head, where they await a grace period. + */ + gotcbs = false; + for (rdp = my_rdp; rdp; rdp = rdp->nocb_next_follower) { + rdp->nocb_gp_head = ACCESS_ONCE(rdp->nocb_head); + if (!rdp->nocb_gp_head) + continue; /* No CBs here, try next follower. */ + + /* Move callbacks to wait-for-GP list, which is empty. */ + ACCESS_ONCE(rdp->nocb_head) = NULL; + rdp->nocb_gp_tail = xchg(&rdp->nocb_tail, &rdp->nocb_head); + gotcbs = true; + } + + /* + * If there were no callbacks, sleep a bit, rescan after a + * memory barrier, and go retry. + */ + if (unlikely(!gotcbs)) { + if (!rcu_nocb_poll) + trace_rcu_nocb_wake(my_rdp->rsp->name, my_rdp->cpu, + "WokeEmpty"); + WARN_ON(signal_pending(current)); + schedule_timeout_interruptible(1); + + /* Rescan in case we were a victim of memory ordering. */ + my_rdp->nocb_leader_sleep = true; + smp_mb(); /* Ensure _sleep true before scan. */ + for (rdp = my_rdp; rdp; rdp = rdp->nocb_next_follower) + if (ACCESS_ONCE(rdp->nocb_head)) { + /* Found CB, so short-circuit next wait. */ + my_rdp->nocb_leader_sleep = false; + break; + } + goto wait_again; + } + + /* Wait for one grace period. */ + rcu_nocb_wait_gp(my_rdp); + + /* + * We left ->nocb_leader_sleep unset to reduce cache thrashing. + * We set it now, but recheck for new callbacks while + * traversing our follower list. + */ + my_rdp->nocb_leader_sleep = true; + smp_mb(); /* Ensure _sleep true before scan of ->nocb_head. */ + + /* Each pass through the following loop wakes a follower, if needed. */ + for (rdp = my_rdp; rdp; rdp = rdp->nocb_next_follower) { + if (ACCESS_ONCE(rdp->nocb_head)) + my_rdp->nocb_leader_sleep = false;/* No need to sleep.*/ + if (!rdp->nocb_gp_head) + continue; /* No CBs, so no need to wake follower. */ + + /* Append callbacks to follower's "done" list. */ + tail = xchg(&rdp->nocb_follower_tail, rdp->nocb_gp_tail); + *tail = rdp->nocb_gp_head; + smp_mb__after_atomic(); /* Store *tail before wakeup. */ + if (rdp != my_rdp && tail == &rdp->nocb_follower_head) { + /* + * List was empty, wake up the follower. + * Memory barriers supplied by atomic_long_add(). + */ + swait_wake(&rdp->nocb_wq); + } + } + + /* If we (the leader) don't have CBs, go wait some more. */ + if (!my_rdp->nocb_follower_head) + goto wait_again; +} + +/* + * Followers come here to wait for additional callbacks to show up. + * This function does not return until callbacks appear. + */ +static void nocb_follower_wait(struct rcu_data *rdp) +{ + bool firsttime = true; + + for (;;) { + if (!rcu_nocb_poll) { + trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, + "FollowerSleep"); + swait_event_interruptible(rdp->nocb_wq, + ACCESS_ONCE(rdp->nocb_follower_head)); + } else if (firsttime) { + /* Don't drown trace log with "Poll"! */ + firsttime = false; + trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, "Poll"); + } + if (smp_load_acquire(&rdp->nocb_follower_head)) { + /* ^^^ Ensure CB invocation follows _head test. */ + return; + } + if (!rcu_nocb_poll) + trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, + "WokeEmpty"); + WARN_ON(signal_pending(current)); + schedule_timeout_interruptible(1); + } +} + +/* + * Per-rcu_data kthread, but only for no-CBs CPUs. Each kthread invokes + * callbacks queued by the corresponding no-CBs CPU, however, there is + * an optional leader-follower relationship so that the grace-period + * kthreads don't have to do quite so many wakeups. + */ +static int rcu_nocb_kthread(void *arg) +{ + int c, cl; + struct rcu_head *list; + struct rcu_head *next; + struct rcu_head **tail; + struct rcu_data *rdp = arg; + + /* Each pass through this loop invokes one batch of callbacks */ + for (;;) { + /* Wait for callbacks. */ + if (rdp->nocb_leader == rdp) + nocb_leader_wait(rdp); + else + nocb_follower_wait(rdp); + + /* Pull the ready-to-invoke callbacks onto local list. */ + list = ACCESS_ONCE(rdp->nocb_follower_head); + BUG_ON(!list); + trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, "WokeNonEmpty"); + ACCESS_ONCE(rdp->nocb_follower_head) = NULL; + tail = xchg(&rdp->nocb_follower_tail, &rdp->nocb_follower_head); + + /* Each pass through the following loop invokes a callback. */ + trace_rcu_batch_start(rdp->rsp->name, + atomic_long_read(&rdp->nocb_q_count_lazy), + atomic_long_read(&rdp->nocb_q_count), -1); + c = cl = 0; + while (list) { + next = list->next; + /* Wait for enqueuing to complete, if needed. */ + while (next == NULL && &list->next != tail) { + trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, + TPS("WaitQueue")); + schedule_timeout_interruptible(1); + trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, + TPS("WokeQueue")); + next = list->next; + } + debug_rcu_head_unqueue(list); + local_bh_disable(); + if (__rcu_reclaim(rdp->rsp->name, list)) + cl++; + c++; + local_bh_enable(); + list = next; + } + trace_rcu_batch_end(rdp->rsp->name, c, !!list, 0, 0, 1); + smp_mb__before_atomic(); /* _add after CB invocation. */ + atomic_long_add(-c, &rdp->nocb_q_count); + atomic_long_add(-cl, &rdp->nocb_q_count_lazy); + rdp->n_nocbs_invoked += c; + } + return 0; +} + +/* Is a deferred wakeup of rcu_nocb_kthread() required? */ +static int rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp) +{ + return ACCESS_ONCE(rdp->nocb_defer_wakeup); +} + +/* Do a deferred wakeup of rcu_nocb_kthread(). */ +static void do_nocb_deferred_wakeup(struct rcu_data *rdp) +{ + int ndw; + + if (!rcu_nocb_need_deferred_wakeup(rdp)) + return; + ndw = ACCESS_ONCE(rdp->nocb_defer_wakeup); + ACCESS_ONCE(rdp->nocb_defer_wakeup) = RCU_NOGP_WAKE_NOT; + wake_nocb_leader(rdp, ndw == RCU_NOGP_WAKE_FORCE); + trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, TPS("DeferredWake")); +} + +void __init rcu_init_nohz(void) +{ + int cpu; + bool need_rcu_nocb_mask = true; + struct rcu_state *rsp; + +#ifdef CONFIG_RCU_NOCB_CPU_NONE + need_rcu_nocb_mask = false; +#endif /* #ifndef CONFIG_RCU_NOCB_CPU_NONE */ + +#if defined(CONFIG_NO_HZ_FULL) + if (tick_nohz_full_running && cpumask_weight(tick_nohz_full_mask)) + need_rcu_nocb_mask = true; +#endif /* #if defined(CONFIG_NO_HZ_FULL) */ + + if (!have_rcu_nocb_mask && need_rcu_nocb_mask) { + if (!zalloc_cpumask_var(&rcu_nocb_mask, GFP_KERNEL)) { + pr_info("rcu_nocb_mask allocation failed, callback offloading disabled.\n"); + return; + } + have_rcu_nocb_mask = true; + } + if (!have_rcu_nocb_mask) + return; + +#ifdef CONFIG_RCU_NOCB_CPU_ZERO + pr_info("\tOffload RCU callbacks from CPU 0\n"); + cpumask_set_cpu(0, rcu_nocb_mask); +#endif /* #ifdef CONFIG_RCU_NOCB_CPU_ZERO */ +#ifdef CONFIG_RCU_NOCB_CPU_ALL + pr_info("\tOffload RCU callbacks from all CPUs\n"); + cpumask_copy(rcu_nocb_mask, cpu_possible_mask); +#endif /* #ifdef CONFIG_RCU_NOCB_CPU_ALL */ +#if defined(CONFIG_NO_HZ_FULL) + if (tick_nohz_full_running) + cpumask_or(rcu_nocb_mask, rcu_nocb_mask, tick_nohz_full_mask); +#endif /* #if defined(CONFIG_NO_HZ_FULL) */ + + if (!cpumask_subset(rcu_nocb_mask, cpu_possible_mask)) { + pr_info("\tNote: kernel parameter 'rcu_nocbs=' contains nonexistent CPUs.\n"); + cpumask_and(rcu_nocb_mask, cpu_possible_mask, + rcu_nocb_mask); + } + pr_info("\tOffload RCU callbacks from CPUs: %*pbl.\n", + cpumask_pr_args(rcu_nocb_mask)); + if (rcu_nocb_poll) + pr_info("\tPoll for callbacks from no-CBs CPUs.\n"); + + for_each_rcu_flavor(rsp) { + for_each_cpu(cpu, rcu_nocb_mask) + init_nocb_callback_list(per_cpu_ptr(rsp->rda, cpu)); + rcu_organize_nocb_kthreads(rsp); + } +} + +/* Initialize per-rcu_data variables for no-CBs CPUs. */ +static void __init rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp) +{ + rdp->nocb_tail = &rdp->nocb_head; + init_swait_head(&rdp->nocb_wq); + rdp->nocb_follower_tail = &rdp->nocb_follower_head; +} + +/* + * If the specified CPU is a no-CBs CPU that does not already have its + * rcuo kthread for the specified RCU flavor, spawn it. If the CPUs are + * brought online out of order, this can require re-organizing the + * leader-follower relationships. + */ +static void rcu_spawn_one_nocb_kthread(struct rcu_state *rsp, int cpu) +{ + struct rcu_data *rdp; + struct rcu_data *rdp_last; + struct rcu_data *rdp_old_leader; + struct rcu_data *rdp_spawn = per_cpu_ptr(rsp->rda, cpu); + struct task_struct *t; + + /* + * If this isn't a no-CBs CPU or if it already has an rcuo kthread, + * then nothing to do. + */ + if (!rcu_is_nocb_cpu(cpu) || rdp_spawn->nocb_kthread) + return; + + /* If we didn't spawn the leader first, reorganize! */ + rdp_old_leader = rdp_spawn->nocb_leader; + if (rdp_old_leader != rdp_spawn && !rdp_old_leader->nocb_kthread) { + rdp_last = NULL; + rdp = rdp_old_leader; + do { + rdp->nocb_leader = rdp_spawn; + if (rdp_last && rdp != rdp_spawn) + rdp_last->nocb_next_follower = rdp; + if (rdp == rdp_spawn) { + rdp = rdp->nocb_next_follower; + } else { + rdp_last = rdp; + rdp = rdp->nocb_next_follower; + rdp_last->nocb_next_follower = NULL; + } + } while (rdp); + rdp_spawn->nocb_next_follower = rdp_old_leader; + } + + /* Spawn the kthread for this CPU and RCU flavor. */ + t = kthread_run(rcu_nocb_kthread, rdp_spawn, + "rcuo%c/%d", rsp->abbr, cpu); + BUG_ON(IS_ERR(t)); + ACCESS_ONCE(rdp_spawn->nocb_kthread) = t; +} + +/* + * If the specified CPU is a no-CBs CPU that does not already have its + * rcuo kthreads, spawn them. + */ +static void rcu_spawn_all_nocb_kthreads(int cpu) +{ + struct rcu_state *rsp; + + if (rcu_scheduler_fully_active) + for_each_rcu_flavor(rsp) + rcu_spawn_one_nocb_kthread(rsp, cpu); +} + +/* + * Once the scheduler is running, spawn rcuo kthreads for all online + * no-CBs CPUs. This assumes that the early_initcall()s happen before + * non-boot CPUs come online -- if this changes, we will need to add + * some mutual exclusion. + */ +static void __init rcu_spawn_nocb_kthreads(void) +{ + int cpu; + + for_each_online_cpu(cpu) + rcu_spawn_all_nocb_kthreads(cpu); +} + +/* How many follower CPU IDs per leader? Default of -1 for sqrt(nr_cpu_ids). */ +static int rcu_nocb_leader_stride = -1; +module_param(rcu_nocb_leader_stride, int, 0444); + +/* + * Initialize leader-follower relationships for all no-CBs CPU. + */ +static void __init rcu_organize_nocb_kthreads(struct rcu_state *rsp) +{ + int cpu; + int ls = rcu_nocb_leader_stride; + int nl = 0; /* Next leader. */ + struct rcu_data *rdp; + struct rcu_data *rdp_leader = NULL; /* Suppress misguided gcc warn. */ + struct rcu_data *rdp_prev = NULL; + + if (!have_rcu_nocb_mask) + return; + if (ls == -1) { + ls = int_sqrt(nr_cpu_ids); + rcu_nocb_leader_stride = ls; + } + + /* + * Each pass through this loop sets up one rcu_data structure and + * spawns one rcu_nocb_kthread(). + */ + for_each_cpu(cpu, rcu_nocb_mask) { + rdp = per_cpu_ptr(rsp->rda, cpu); + if (rdp->cpu >= nl) { + /* New leader, set up for followers & next leader. */ + nl = DIV_ROUND_UP(rdp->cpu + 1, ls) * ls; + rdp->nocb_leader = rdp; + rdp_leader = rdp; + } else { + /* Another follower, link to previous leader. */ + rdp->nocb_leader = rdp_leader; + rdp_prev->nocb_next_follower = rdp; + } + rdp_prev = rdp; + } +} + +/* Prevent __call_rcu() from enqueuing callbacks on no-CBs CPUs */ +static bool init_nocb_callback_list(struct rcu_data *rdp) +{ + if (!rcu_is_nocb_cpu(rdp->cpu)) + return false; + + /* If there are early-boot callbacks, move them to nocb lists. */ + if (rdp->nxtlist) { + rdp->nocb_head = rdp->nxtlist; + rdp->nocb_tail = rdp->nxttail[RCU_NEXT_TAIL]; + atomic_long_set(&rdp->nocb_q_count, rdp->qlen); + atomic_long_set(&rdp->nocb_q_count_lazy, rdp->qlen_lazy); + rdp->nxtlist = NULL; + rdp->qlen = 0; + rdp->qlen_lazy = 0; + } + rdp->nxttail[RCU_NEXT_TAIL] = NULL; + return true; +} + +#else /* #ifdef CONFIG_RCU_NOCB_CPU */ + +static bool rcu_nocb_cpu_needs_barrier(struct rcu_state *rsp, int cpu) +{ + WARN_ON_ONCE(1); /* Should be dead code. */ + return false; +} + +static void rcu_nocb_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp) +{ +} + +static void rcu_nocb_gp_set(struct rcu_node *rnp, int nrq) +{ +} + +static void rcu_init_one_nocb(struct rcu_node *rnp) +{ +} + +static bool __call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *rhp, + bool lazy, unsigned long flags) +{ + return false; +} + +static bool __maybe_unused rcu_nocb_adopt_orphan_cbs(struct rcu_state *rsp, + struct rcu_data *rdp, + unsigned long flags) +{ + return false; +} + +static void __init rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp) +{ +} + +static int rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp) +{ + return false; +} + +static void do_nocb_deferred_wakeup(struct rcu_data *rdp) +{ +} + +static void rcu_spawn_all_nocb_kthreads(int cpu) +{ +} + +static void __init rcu_spawn_nocb_kthreads(void) +{ +} + +static bool init_nocb_callback_list(struct rcu_data *rdp) +{ + return false; +} + +#endif /* #else #ifdef CONFIG_RCU_NOCB_CPU */ + +/* + * An adaptive-ticks CPU can potentially execute in kernel mode for an + * arbitrarily long period of time with the scheduling-clock tick turned + * off. RCU will be paying attention to this CPU because it is in the + * kernel, but the CPU cannot be guaranteed to be executing the RCU state + * machine because the scheduling-clock tick has been disabled. Therefore, + * if an adaptive-ticks CPU is failing to respond to the current grace + * period and has not be idle from an RCU perspective, kick it. + */ +static void __maybe_unused rcu_kick_nohz_cpu(int cpu) +{ +#ifdef CONFIG_NO_HZ_FULL + if (tick_nohz_full_cpu(cpu)) + smp_send_reschedule(cpu); +#endif /* #ifdef CONFIG_NO_HZ_FULL */ +} + + +#ifdef CONFIG_NO_HZ_FULL_SYSIDLE + +static int full_sysidle_state; /* Current system-idle state. */ +#define RCU_SYSIDLE_NOT 0 /* Some CPU is not idle. */ +#define RCU_SYSIDLE_SHORT 1 /* All CPUs idle for brief period. */ +#define RCU_SYSIDLE_LONG 2 /* All CPUs idle for long enough. */ +#define RCU_SYSIDLE_FULL 3 /* All CPUs idle, ready for sysidle. */ +#define RCU_SYSIDLE_FULL_NOTED 4 /* Actually entered sysidle state. */ + +/* + * Invoked to note exit from irq or task transition to idle. Note that + * usermode execution does -not- count as idle here! After all, we want + * to detect full-system idle states, not RCU quiescent states and grace + * periods. The caller must have disabled interrupts. + */ +static void rcu_sysidle_enter(int irq) +{ + unsigned long j; + struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks); + + /* If there are no nohz_full= CPUs, no need to track this. */ + if (!tick_nohz_full_enabled()) + return; + + /* Adjust nesting, check for fully idle. */ + if (irq) { + rdtp->dynticks_idle_nesting--; + WARN_ON_ONCE(rdtp->dynticks_idle_nesting < 0); + if (rdtp->dynticks_idle_nesting != 0) + return; /* Still not fully idle. */ + } else { + if ((rdtp->dynticks_idle_nesting & DYNTICK_TASK_NEST_MASK) == + DYNTICK_TASK_NEST_VALUE) { + rdtp->dynticks_idle_nesting = 0; + } else { + rdtp->dynticks_idle_nesting -= DYNTICK_TASK_NEST_VALUE; + WARN_ON_ONCE(rdtp->dynticks_idle_nesting < 0); + return; /* Still not fully idle. */ + } + } + + /* Record start of fully idle period. */ + j = jiffies; + ACCESS_ONCE(rdtp->dynticks_idle_jiffies) = j; + smp_mb__before_atomic(); + atomic_inc(&rdtp->dynticks_idle); + smp_mb__after_atomic(); + WARN_ON_ONCE(atomic_read(&rdtp->dynticks_idle) & 0x1); +} + +/* + * Unconditionally force exit from full system-idle state. This is + * invoked when a normal CPU exits idle, but must be called separately + * for the timekeeping CPU (tick_do_timer_cpu). The reason for this + * is that the timekeeping CPU is permitted to take scheduling-clock + * interrupts while the system is in system-idle state, and of course + * rcu_sysidle_exit() has no way of distinguishing a scheduling-clock + * interrupt from any other type of interrupt. + */ +void rcu_sysidle_force_exit(void) +{ + int oldstate = ACCESS_ONCE(full_sysidle_state); + int newoldstate; + + /* + * Each pass through the following loop attempts to exit full + * system-idle state. If contention proves to be a problem, + * a trylock-based contention tree could be used here. + */ + while (oldstate > RCU_SYSIDLE_SHORT) { + newoldstate = cmpxchg(&full_sysidle_state, + oldstate, RCU_SYSIDLE_NOT); + if (oldstate == newoldstate && + oldstate == RCU_SYSIDLE_FULL_NOTED) { + rcu_kick_nohz_cpu(tick_do_timer_cpu); + return; /* We cleared it, done! */ + } + oldstate = newoldstate; + } + smp_mb(); /* Order initial oldstate fetch vs. later non-idle work. */ +} + +/* + * Invoked to note entry to irq or task transition from idle. Note that + * usermode execution does -not- count as idle here! The caller must + * have disabled interrupts. + */ +static void rcu_sysidle_exit(int irq) +{ + struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks); + + /* If there are no nohz_full= CPUs, no need to track this. */ + if (!tick_nohz_full_enabled()) + return; + + /* Adjust nesting, check for already non-idle. */ + if (irq) { + rdtp->dynticks_idle_nesting++; + WARN_ON_ONCE(rdtp->dynticks_idle_nesting <= 0); + if (rdtp->dynticks_idle_nesting != 1) + return; /* Already non-idle. */ + } else { + /* + * Allow for irq misnesting. Yes, it really is possible + * to enter an irq handler then never leave it, and maybe + * also vice versa. Handle both possibilities. + */ + if (rdtp->dynticks_idle_nesting & DYNTICK_TASK_NEST_MASK) { + rdtp->dynticks_idle_nesting += DYNTICK_TASK_NEST_VALUE; + WARN_ON_ONCE(rdtp->dynticks_idle_nesting <= 0); + return; /* Already non-idle. */ + } else { + rdtp->dynticks_idle_nesting = DYNTICK_TASK_EXIT_IDLE; + } + } + + /* Record end of idle period. */ + smp_mb__before_atomic(); + atomic_inc(&rdtp->dynticks_idle); + smp_mb__after_atomic(); + WARN_ON_ONCE(!(atomic_read(&rdtp->dynticks_idle) & 0x1)); + + /* + * If we are the timekeeping CPU, we are permitted to be non-idle + * during a system-idle state. This must be the case, because + * the timekeeping CPU has to take scheduling-clock interrupts + * during the time that the system is transitioning to full + * system-idle state. This means that the timekeeping CPU must + * invoke rcu_sysidle_force_exit() directly if it does anything + * more than take a scheduling-clock interrupt. + */ + if (smp_processor_id() == tick_do_timer_cpu) + return; + + /* Update system-idle state: We are clearly no longer fully idle! */ + rcu_sysidle_force_exit(); +} + +/* + * Check to see if the current CPU is idle. Note that usermode execution + * does not count as idle. The caller must have disabled interrupts, + * and must be running on tick_do_timer_cpu. + */ +static void rcu_sysidle_check_cpu(struct rcu_data *rdp, bool *isidle, + unsigned long *maxj) +{ + int cur; + unsigned long j; + struct rcu_dynticks *rdtp = rdp->dynticks; + + /* If there are no nohz_full= CPUs, don't check system-wide idleness. */ + if (!tick_nohz_full_enabled()) + return; + + /* + * If some other CPU has already reported non-idle, if this is + * not the flavor of RCU that tracks sysidle state, or if this + * is an offline or the timekeeping CPU, nothing to do. + */ + if (!*isidle || rdp->rsp != rcu_state_p || + cpu_is_offline(rdp->cpu) || rdp->cpu == tick_do_timer_cpu) + return; + /* Verify affinity of current kthread. */ + WARN_ON_ONCE(smp_processor_id() != tick_do_timer_cpu); + + /* Pick up current idle and NMI-nesting counter and check. */ + cur = atomic_read(&rdtp->dynticks_idle); + if (cur & 0x1) { + *isidle = false; /* We are not idle! */ + return; + } + smp_mb(); /* Read counters before timestamps. */ + + /* Pick up timestamps. */ + j = ACCESS_ONCE(rdtp->dynticks_idle_jiffies); + /* If this CPU entered idle more recently, update maxj timestamp. */ + if (ULONG_CMP_LT(*maxj, j)) + *maxj = j; +} + +/* + * Is this the flavor of RCU that is handling full-system idle? + */ +static bool is_sysidle_rcu_state(struct rcu_state *rsp) +{ + return rsp == rcu_state_p; +} + +/* + * Return a delay in jiffies based on the number of CPUs, rcu_node + * leaf fanout, and jiffies tick rate. The idea is to allow larger + * systems more time to transition to full-idle state in order to + * avoid the cache thrashing that otherwise occur on the state variable. + * Really small systems (less than a couple of tens of CPUs) should + * instead use a single global atomically incremented counter, and later + * versions of this will automatically reconfigure themselves accordingly. + */ +static unsigned long rcu_sysidle_delay(void) +{ + if (nr_cpu_ids <= CONFIG_NO_HZ_FULL_SYSIDLE_SMALL) + return 0; + return DIV_ROUND_UP(nr_cpu_ids * HZ, rcu_fanout_leaf * 1000); +} + +/* + * Advance the full-system-idle state. This is invoked when all of + * the non-timekeeping CPUs are idle. + */ +static void rcu_sysidle(unsigned long j) +{ + /* Check the current state. */ + switch (ACCESS_ONCE(full_sysidle_state)) { + case RCU_SYSIDLE_NOT: + + /* First time all are idle, so note a short idle period. */ + ACCESS_ONCE(full_sysidle_state) = RCU_SYSIDLE_SHORT; + break; + + case RCU_SYSIDLE_SHORT: + + /* + * Idle for a bit, time to advance to next state? + * cmpxchg failure means race with non-idle, let them win. + */ + if (ULONG_CMP_GE(jiffies, j + rcu_sysidle_delay())) + (void)cmpxchg(&full_sysidle_state, + RCU_SYSIDLE_SHORT, RCU_SYSIDLE_LONG); + break; + + case RCU_SYSIDLE_LONG: + + /* + * Do an additional check pass before advancing to full. + * cmpxchg failure means race with non-idle, let them win. + */ + if (ULONG_CMP_GE(jiffies, j + rcu_sysidle_delay())) + (void)cmpxchg(&full_sysidle_state, + RCU_SYSIDLE_LONG, RCU_SYSIDLE_FULL); + break; + + default: + break; + } +} + +/* + * Found a non-idle non-timekeeping CPU, so kick the system-idle state + * back to the beginning. + */ +static void rcu_sysidle_cancel(void) +{ + smp_mb(); + if (full_sysidle_state > RCU_SYSIDLE_SHORT) + ACCESS_ONCE(full_sysidle_state) = RCU_SYSIDLE_NOT; +} + +/* + * Update the sysidle state based on the results of a force-quiescent-state + * scan of the CPUs' dyntick-idle state. + */ +static void rcu_sysidle_report(struct rcu_state *rsp, int isidle, + unsigned long maxj, bool gpkt) +{ + if (rsp != rcu_state_p) + return; /* Wrong flavor, ignore. */ + if (gpkt && nr_cpu_ids <= CONFIG_NO_HZ_FULL_SYSIDLE_SMALL) + return; /* Running state machine from timekeeping CPU. */ + if (isidle) + rcu_sysidle(maxj); /* More idle! */ + else + rcu_sysidle_cancel(); /* Idle is over. */ +} + +/* + * Wrapper for rcu_sysidle_report() when called from the grace-period + * kthread's context. + */ +static void rcu_sysidle_report_gp(struct rcu_state *rsp, int isidle, + unsigned long maxj) +{ + /* If there are no nohz_full= CPUs, no need to track this. */ + if (!tick_nohz_full_enabled()) + return; + + rcu_sysidle_report(rsp, isidle, maxj, true); +} + +/* Callback and function for forcing an RCU grace period. */ +struct rcu_sysidle_head { + struct rcu_head rh; + int inuse; +}; + +static void rcu_sysidle_cb(struct rcu_head *rhp) +{ + struct rcu_sysidle_head *rshp; + + /* + * The following memory barrier is needed to replace the + * memory barriers that would normally be in the memory + * allocator. + */ + smp_mb(); /* grace period precedes setting inuse. */ + + rshp = container_of(rhp, struct rcu_sysidle_head, rh); + ACCESS_ONCE(rshp->inuse) = 0; +} + +/* + * Check to see if the system is fully idle, other than the timekeeping CPU. + * The caller must have disabled interrupts. This is not intended to be + * called unless tick_nohz_full_enabled(). + */ +bool rcu_sys_is_idle(void) +{ + static struct rcu_sysidle_head rsh; + int rss = ACCESS_ONCE(full_sysidle_state); + + if (WARN_ON_ONCE(smp_processor_id() != tick_do_timer_cpu)) + return false; + + /* Handle small-system case by doing a full scan of CPUs. */ + if (nr_cpu_ids <= CONFIG_NO_HZ_FULL_SYSIDLE_SMALL) { + int oldrss = rss - 1; + + /* + * One pass to advance to each state up to _FULL. + * Give up if any pass fails to advance the state. + */ + while (rss < RCU_SYSIDLE_FULL && oldrss < rss) { + int cpu; + bool isidle = true; + unsigned long maxj = jiffies - ULONG_MAX / 4; + struct rcu_data *rdp; + + /* Scan all the CPUs looking for nonidle CPUs. */ + for_each_possible_cpu(cpu) { + rdp = per_cpu_ptr(rcu_state_p->rda, cpu); + rcu_sysidle_check_cpu(rdp, &isidle, &maxj); + if (!isidle) + break; + } + rcu_sysidle_report(rcu_state_p, isidle, maxj, false); + oldrss = rss; + rss = ACCESS_ONCE(full_sysidle_state); + } + } + + /* If this is the first observation of an idle period, record it. */ + if (rss == RCU_SYSIDLE_FULL) { + rss = cmpxchg(&full_sysidle_state, + RCU_SYSIDLE_FULL, RCU_SYSIDLE_FULL_NOTED); + return rss == RCU_SYSIDLE_FULL; + } + + smp_mb(); /* ensure rss load happens before later caller actions. */ + + /* If already fully idle, tell the caller (in case of races). */ + if (rss == RCU_SYSIDLE_FULL_NOTED) + return true; + + /* + * If we aren't there yet, and a grace period is not in flight, + * initiate a grace period. Either way, tell the caller that + * we are not there yet. We use an xchg() rather than an assignment + * to make up for the memory barriers that would otherwise be + * provided by the memory allocator. + */ + if (nr_cpu_ids > CONFIG_NO_HZ_FULL_SYSIDLE_SMALL && + !rcu_gp_in_progress(rcu_state_p) && + !rsh.inuse && xchg(&rsh.inuse, 1) == 0) + call_rcu(&rsh.rh, rcu_sysidle_cb); + return false; +} + +/* + * Initialize dynticks sysidle state for CPUs coming online. + */ +static void rcu_sysidle_init_percpu_data(struct rcu_dynticks *rdtp) +{ + rdtp->dynticks_idle_nesting = DYNTICK_TASK_NEST_VALUE; +} + +#else /* #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */ + +static void rcu_sysidle_enter(int irq) +{ +} + +static void rcu_sysidle_exit(int irq) +{ +} + +static void rcu_sysidle_check_cpu(struct rcu_data *rdp, bool *isidle, + unsigned long *maxj) +{ +} + +static bool is_sysidle_rcu_state(struct rcu_state *rsp) +{ + return false; +} + +static void rcu_sysidle_report_gp(struct rcu_state *rsp, int isidle, + unsigned long maxj) +{ +} + +static void rcu_sysidle_init_percpu_data(struct rcu_dynticks *rdtp) +{ +} + +#endif /* #else #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */ + +/* + * Is this CPU a NO_HZ_FULL CPU that should ignore RCU so that the + * grace-period kthread will do force_quiescent_state() processing? + * The idea is to avoid waking up RCU core processing on such a + * CPU unless the grace period has extended for too long. + * + * This code relies on the fact that all NO_HZ_FULL CPUs are also + * CONFIG_RCU_NOCB_CPU CPUs. + */ +static bool rcu_nohz_full_cpu(struct rcu_state *rsp) +{ +#ifdef CONFIG_NO_HZ_FULL + if (tick_nohz_full_cpu(smp_processor_id()) && + (!rcu_gp_in_progress(rsp) || + ULONG_CMP_LT(jiffies, ACCESS_ONCE(rsp->gp_start) + HZ))) + return 1; +#endif /* #ifdef CONFIG_NO_HZ_FULL */ + return 0; +} + +/* + * Bind the grace-period kthread for the sysidle flavor of RCU to the + * timekeeping CPU. + */ +static void rcu_bind_gp_kthread(void) +{ + int __maybe_unused cpu; + + if (!tick_nohz_full_enabled()) + return; +#ifdef CONFIG_NO_HZ_FULL_SYSIDLE + cpu = tick_do_timer_cpu; + if (cpu >= 0 && cpu < nr_cpu_ids) + set_cpus_allowed_ptr(current, cpumask_of(cpu)); +#else /* #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */ + housekeeping_affine(current); +#endif /* #else #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */ +} + +/* Record the current task on dyntick-idle entry. */ +static void rcu_dynticks_task_enter(void) +{ +#if defined(CONFIG_TASKS_RCU) && defined(CONFIG_NO_HZ_FULL) + ACCESS_ONCE(current->rcu_tasks_idle_cpu) = smp_processor_id(); +#endif /* #if defined(CONFIG_TASKS_RCU) && defined(CONFIG_NO_HZ_FULL) */ +} + +/* Record no current task on dyntick-idle exit. */ +static void rcu_dynticks_task_exit(void) +{ +#if defined(CONFIG_TASKS_RCU) && defined(CONFIG_NO_HZ_FULL) + ACCESS_ONCE(current->rcu_tasks_idle_cpu) = -1; +#endif /* #if defined(CONFIG_TASKS_RCU) && defined(CONFIG_NO_HZ_FULL) */ +} diff --git a/kernel/kernel/rcu/tree_trace.c b/kernel/kernel/rcu/tree_trace.c new file mode 100644 index 000000000..f92361efd --- /dev/null +++ b/kernel/kernel/rcu/tree_trace.c @@ -0,0 +1,505 @@ +/* + * Read-Copy Update tracing for classic implementation + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, you can access it online at + * http://www.gnu.org/licenses/gpl-2.0.html. + * + * Copyright IBM Corporation, 2008 + * + * Papers: http://www.rdrop.com/users/paulmck/RCU + * + * For detailed explanation of Read-Copy Update mechanism see - + * Documentation/RCU + * + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define RCU_TREE_NONCORE +#include "tree.h" + +DECLARE_PER_CPU_SHARED_ALIGNED(unsigned long, rcu_qs_ctr); + +static int r_open(struct inode *inode, struct file *file, + const struct seq_operations *op) +{ + int ret = seq_open(file, op); + if (!ret) { + struct seq_file *m = (struct seq_file *)file->private_data; + m->private = inode->i_private; + } + return ret; +} + +static void *r_start(struct seq_file *m, loff_t *pos) +{ + struct rcu_state *rsp = (struct rcu_state *)m->private; + *pos = cpumask_next(*pos - 1, cpu_possible_mask); + if ((*pos) < nr_cpu_ids) + return per_cpu_ptr(rsp->rda, *pos); + return NULL; +} + +static void *r_next(struct seq_file *m, void *v, loff_t *pos) +{ + (*pos)++; + return r_start(m, pos); +} + +static void r_stop(struct seq_file *m, void *v) +{ +} + +static int show_rcubarrier(struct seq_file *m, void *v) +{ + struct rcu_state *rsp = (struct rcu_state *)m->private; + seq_printf(m, "bcc: %d nbd: %lu\n", + atomic_read(&rsp->barrier_cpu_count), + rsp->n_barrier_done); + return 0; +} + +static int rcubarrier_open(struct inode *inode, struct file *file) +{ + return single_open(file, show_rcubarrier, inode->i_private); +} + +static const struct file_operations rcubarrier_fops = { + .owner = THIS_MODULE, + .open = rcubarrier_open, + .read = seq_read, + .llseek = no_llseek, + .release = single_release, +}; + +#ifdef CONFIG_RCU_BOOST + +static char convert_kthread_status(unsigned int kthread_status) +{ + if (kthread_status > RCU_KTHREAD_MAX) + return '?'; + return "SRWOY"[kthread_status]; +} + +#endif /* #ifdef CONFIG_RCU_BOOST */ + +static void print_one_rcu_data(struct seq_file *m, struct rcu_data *rdp) +{ + long ql, qll; + + if (!rdp->beenonline) + return; + seq_printf(m, "%3d%cc=%ld g=%ld pq=%d/%d qp=%d", + rdp->cpu, + cpu_is_offline(rdp->cpu) ? '!' : ' ', + ulong2long(rdp->completed), ulong2long(rdp->gpnum), + rdp->passed_quiesce, + rdp->rcu_qs_ctr_snap == per_cpu(rcu_qs_ctr, rdp->cpu), + rdp->qs_pending); + seq_printf(m, " dt=%d/%llx/%d df=%lu", + atomic_read(&rdp->dynticks->dynticks), + rdp->dynticks->dynticks_nesting, + rdp->dynticks->dynticks_nmi_nesting, + rdp->dynticks_fqs); + seq_printf(m, " of=%lu", rdp->offline_fqs); + rcu_nocb_q_lengths(rdp, &ql, &qll); + qll += rdp->qlen_lazy; + ql += rdp->qlen; + seq_printf(m, " ql=%ld/%ld qs=%c%c%c%c", + qll, ql, + ".N"[rdp->nxttail[RCU_NEXT_READY_TAIL] != + rdp->nxttail[RCU_NEXT_TAIL]], + ".R"[rdp->nxttail[RCU_WAIT_TAIL] != + rdp->nxttail[RCU_NEXT_READY_TAIL]], + ".W"[rdp->nxttail[RCU_DONE_TAIL] != + rdp->nxttail[RCU_WAIT_TAIL]], + ".D"[&rdp->nxtlist != rdp->nxttail[RCU_DONE_TAIL]]); +#ifdef CONFIG_RCU_BOOST + seq_printf(m, " kt=%d/%c ktl=%x", + per_cpu(rcu_cpu_has_work, rdp->cpu), + convert_kthread_status(per_cpu(rcu_cpu_kthread_status, + rdp->cpu)), + per_cpu(rcu_cpu_kthread_loops, rdp->cpu) & 0xffff); +#endif /* #ifdef CONFIG_RCU_BOOST */ + seq_printf(m, " b=%ld", rdp->blimit); + seq_printf(m, " ci=%lu nci=%lu co=%lu ca=%lu\n", + rdp->n_cbs_invoked, rdp->n_nocbs_invoked, + rdp->n_cbs_orphaned, rdp->n_cbs_adopted); +} + +static int show_rcudata(struct seq_file *m, void *v) +{ + print_one_rcu_data(m, (struct rcu_data *)v); + return 0; +} + +static const struct seq_operations rcudate_op = { + .start = r_start, + .next = r_next, + .stop = r_stop, + .show = show_rcudata, +}; + +static int rcudata_open(struct inode *inode, struct file *file) +{ + return r_open(inode, file, &rcudate_op); +} + +static const struct file_operations rcudata_fops = { + .owner = THIS_MODULE, + .open = rcudata_open, + .read = seq_read, + .llseek = no_llseek, + .release = seq_release, +}; + +static int show_rcuexp(struct seq_file *m, void *v) +{ + struct rcu_state *rsp = (struct rcu_state *)m->private; + + seq_printf(m, "s=%lu d=%lu w=%lu tf=%lu wd1=%lu wd2=%lu n=%lu sc=%lu dt=%lu dl=%lu dx=%lu\n", + atomic_long_read(&rsp->expedited_start), + atomic_long_read(&rsp->expedited_done), + atomic_long_read(&rsp->expedited_wrap), + atomic_long_read(&rsp->expedited_tryfail), + atomic_long_read(&rsp->expedited_workdone1), + atomic_long_read(&rsp->expedited_workdone2), + atomic_long_read(&rsp->expedited_normal), + atomic_long_read(&rsp->expedited_stoppedcpus), + atomic_long_read(&rsp->expedited_done_tries), + atomic_long_read(&rsp->expedited_done_lost), + atomic_long_read(&rsp->expedited_done_exit)); + return 0; +} + +static int rcuexp_open(struct inode *inode, struct file *file) +{ + return single_open(file, show_rcuexp, inode->i_private); +} + +static const struct file_operations rcuexp_fops = { + .owner = THIS_MODULE, + .open = rcuexp_open, + .read = seq_read, + .llseek = no_llseek, + .release = single_release, +}; + +#ifdef CONFIG_RCU_BOOST + +static void print_one_rcu_node_boost(struct seq_file *m, struct rcu_node *rnp) +{ + seq_printf(m, "%d:%d tasks=%c%c%c%c kt=%c ntb=%lu neb=%lu nnb=%lu ", + rnp->grplo, rnp->grphi, + "T."[list_empty(&rnp->blkd_tasks)], + "N."[!rnp->gp_tasks], + "E."[!rnp->exp_tasks], + "B."[!rnp->boost_tasks], + convert_kthread_status(rnp->boost_kthread_status), + rnp->n_tasks_boosted, rnp->n_exp_boosts, + rnp->n_normal_boosts); + seq_printf(m, "j=%04x bt=%04x\n", + (int)(jiffies & 0xffff), + (int)(rnp->boost_time & 0xffff)); + seq_printf(m, " balk: nt=%lu egt=%lu bt=%lu nb=%lu ny=%lu nos=%lu\n", + rnp->n_balk_blkd_tasks, + rnp->n_balk_exp_gp_tasks, + rnp->n_balk_boost_tasks, + rnp->n_balk_notblocked, + rnp->n_balk_notyet, + rnp->n_balk_nos); +} + +static int show_rcu_node_boost(struct seq_file *m, void *unused) +{ + struct rcu_node *rnp; + + rcu_for_each_leaf_node(&rcu_preempt_state, rnp) + print_one_rcu_node_boost(m, rnp); + return 0; +} + +static int rcu_node_boost_open(struct inode *inode, struct file *file) +{ + return single_open(file, show_rcu_node_boost, NULL); +} + +static const struct file_operations rcu_node_boost_fops = { + .owner = THIS_MODULE, + .open = rcu_node_boost_open, + .read = seq_read, + .llseek = no_llseek, + .release = single_release, +}; + +#endif /* #ifdef CONFIG_RCU_BOOST */ + +static void print_one_rcu_state(struct seq_file *m, struct rcu_state *rsp) +{ + unsigned long gpnum; + int level = 0; + struct rcu_node *rnp; + + gpnum = rsp->gpnum; + seq_printf(m, "c=%ld g=%ld s=%d jfq=%ld j=%x ", + ulong2long(rsp->completed), ulong2long(gpnum), + rsp->fqs_state, + (long)(rsp->jiffies_force_qs - jiffies), + (int)(jiffies & 0xffff)); + seq_printf(m, "nfqs=%lu/nfqsng=%lu(%lu) fqlh=%lu oqlen=%ld/%ld\n", + rsp->n_force_qs, rsp->n_force_qs_ngp, + rsp->n_force_qs - rsp->n_force_qs_ngp, + ACCESS_ONCE(rsp->n_force_qs_lh), rsp->qlen_lazy, rsp->qlen); + for (rnp = &rsp->node[0]; rnp - &rsp->node[0] < rcu_num_nodes; rnp++) { + if (rnp->level != level) { + seq_puts(m, "\n"); + level = rnp->level; + } + seq_printf(m, "%lx/%lx->%lx %c%c>%c %d:%d ^%d ", + rnp->qsmask, rnp->qsmaskinit, rnp->qsmaskinitnext, + ".G"[rnp->gp_tasks != NULL], + ".E"[rnp->exp_tasks != NULL], + ".T"[!list_empty(&rnp->blkd_tasks)], + rnp->grplo, rnp->grphi, rnp->grpnum); + } + seq_puts(m, "\n"); +} + +static int show_rcuhier(struct seq_file *m, void *v) +{ + struct rcu_state *rsp = (struct rcu_state *)m->private; + print_one_rcu_state(m, rsp); + return 0; +} + +static int rcuhier_open(struct inode *inode, struct file *file) +{ + return single_open(file, show_rcuhier, inode->i_private); +} + +static const struct file_operations rcuhier_fops = { + .owner = THIS_MODULE, + .open = rcuhier_open, + .read = seq_read, + .llseek = no_llseek, + .release = single_release, +}; + +static void show_one_rcugp(struct seq_file *m, struct rcu_state *rsp) +{ + unsigned long flags; + unsigned long completed; + unsigned long gpnum; + unsigned long gpage; + unsigned long gpmax; + struct rcu_node *rnp = &rsp->node[0]; + + raw_spin_lock_irqsave(&rnp->lock, flags); + completed = ACCESS_ONCE(rsp->completed); + gpnum = ACCESS_ONCE(rsp->gpnum); + if (completed == gpnum) + gpage = 0; + else + gpage = jiffies - rsp->gp_start; + gpmax = rsp->gp_max; + raw_spin_unlock_irqrestore(&rnp->lock, flags); + seq_printf(m, "completed=%ld gpnum=%ld age=%ld max=%ld\n", + ulong2long(completed), ulong2long(gpnum), gpage, gpmax); +} + +static int show_rcugp(struct seq_file *m, void *v) +{ + struct rcu_state *rsp = (struct rcu_state *)m->private; + show_one_rcugp(m, rsp); + return 0; +} + +static int rcugp_open(struct inode *inode, struct file *file) +{ + return single_open(file, show_rcugp, inode->i_private); +} + +static const struct file_operations rcugp_fops = { + .owner = THIS_MODULE, + .open = rcugp_open, + .read = seq_read, + .llseek = no_llseek, + .release = single_release, +}; + +static void print_one_rcu_pending(struct seq_file *m, struct rcu_data *rdp) +{ + if (!rdp->beenonline) + return; + seq_printf(m, "%3d%cnp=%ld ", + rdp->cpu, + cpu_is_offline(rdp->cpu) ? '!' : ' ', + rdp->n_rcu_pending); + seq_printf(m, "qsp=%ld rpq=%ld cbr=%ld cng=%ld ", + rdp->n_rp_qs_pending, + rdp->n_rp_report_qs, + rdp->n_rp_cb_ready, + rdp->n_rp_cpu_needs_gp); + seq_printf(m, "gpc=%ld gps=%ld nn=%ld ndw%ld\n", + rdp->n_rp_gp_completed, + rdp->n_rp_gp_started, + rdp->n_rp_nocb_defer_wakeup, + rdp->n_rp_need_nothing); +} + +static int show_rcu_pending(struct seq_file *m, void *v) +{ + print_one_rcu_pending(m, (struct rcu_data *)v); + return 0; +} + +static const struct seq_operations rcu_pending_op = { + .start = r_start, + .next = r_next, + .stop = r_stop, + .show = show_rcu_pending, +}; + +static int rcu_pending_open(struct inode *inode, struct file *file) +{ + return r_open(inode, file, &rcu_pending_op); +} + +static const struct file_operations rcu_pending_fops = { + .owner = THIS_MODULE, + .open = rcu_pending_open, + .read = seq_read, + .llseek = no_llseek, + .release = seq_release, +}; + +static int show_rcutorture(struct seq_file *m, void *unused) +{ + seq_printf(m, "rcutorture test sequence: %lu %s\n", + rcutorture_testseq >> 1, + (rcutorture_testseq & 0x1) ? "(test in progress)" : ""); + seq_printf(m, "rcutorture update version number: %lu\n", + rcutorture_vernum); + return 0; +} + +static int rcutorture_open(struct inode *inode, struct file *file) +{ + return single_open(file, show_rcutorture, NULL); +} + +static const struct file_operations rcutorture_fops = { + .owner = THIS_MODULE, + .open = rcutorture_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static struct dentry *rcudir; + +static int __init rcutree_trace_init(void) +{ + struct rcu_state *rsp; + struct dentry *retval; + struct dentry *rspdir; + + rcudir = debugfs_create_dir("rcu", NULL); + if (!rcudir) + goto free_out; + + for_each_rcu_flavor(rsp) { + rspdir = debugfs_create_dir(rsp->name, rcudir); + if (!rspdir) + goto free_out; + + retval = debugfs_create_file("rcudata", 0444, + rspdir, rsp, &rcudata_fops); + if (!retval) + goto free_out; + + retval = debugfs_create_file("rcuexp", 0444, + rspdir, rsp, &rcuexp_fops); + if (!retval) + goto free_out; + + retval = debugfs_create_file("rcu_pending", 0444, + rspdir, rsp, &rcu_pending_fops); + if (!retval) + goto free_out; + + retval = debugfs_create_file("rcubarrier", 0444, + rspdir, rsp, &rcubarrier_fops); + if (!retval) + goto free_out; + +#ifdef CONFIG_RCU_BOOST + if (rsp == &rcu_preempt_state) { + retval = debugfs_create_file("rcuboost", 0444, + rspdir, NULL, &rcu_node_boost_fops); + if (!retval) + goto free_out; + } +#endif + + retval = debugfs_create_file("rcugp", 0444, + rspdir, rsp, &rcugp_fops); + if (!retval) + goto free_out; + + retval = debugfs_create_file("rcuhier", 0444, + rspdir, rsp, &rcuhier_fops); + if (!retval) + goto free_out; + } + + retval = debugfs_create_file("rcutorture", 0444, rcudir, + NULL, &rcutorture_fops); + if (!retval) + goto free_out; + return 0; +free_out: + debugfs_remove_recursive(rcudir); + return 1; +} + +static void __exit rcutree_trace_cleanup(void) +{ + debugfs_remove_recursive(rcudir); +} + + +module_init(rcutree_trace_init); +module_exit(rcutree_trace_cleanup); + +MODULE_AUTHOR("Paul E. McKenney"); +MODULE_DESCRIPTION("Read-Copy Update tracing for hierarchical implementation"); +MODULE_LICENSE("GPL"); diff --git a/kernel/kernel/rcu/update.c b/kernel/kernel/rcu/update.c new file mode 100644 index 000000000..1718c4fe9 --- /dev/null +++ b/kernel/kernel/rcu/update.c @@ -0,0 +1,833 @@ +/* + * Read-Copy Update mechanism for mutual exclusion + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, you can access it online at + * http://www.gnu.org/licenses/gpl-2.0.html. + * + * Copyright IBM Corporation, 2001 + * + * Authors: Dipankar Sarma + * Manfred Spraul + * + * Based on the original work by Paul McKenney + * and inputs from Rusty Russell, Andrea Arcangeli and Andi Kleen. + * Papers: + * http://www.rdrop.com/users/paulmck/paper/rclockpdcsproof.pdf + * http://lse.sourceforge.net/locking/rclock_OLS.2001.05.01c.sc.pdf (OLS2001) + * + * For detailed explanation of Read-Copy Update mechanism see - + * http://lse.sourceforge.net/locking/rcupdate.html + * + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define CREATE_TRACE_POINTS + +#include "rcu.h" + +MODULE_ALIAS("rcupdate"); +#ifdef MODULE_PARAM_PREFIX +#undef MODULE_PARAM_PREFIX +#endif +#define MODULE_PARAM_PREFIX "rcupdate." + +module_param(rcu_expedited, int, 0); + +#ifndef CONFIG_TINY_RCU + +static atomic_t rcu_expedited_nesting = + ATOMIC_INIT(IS_ENABLED(CONFIG_RCU_EXPEDITE_BOOT) ? 1 : 0); + +/* + * Should normal grace-period primitives be expedited? Intended for + * use within RCU. Note that this function takes the rcu_expedited + * sysfs/boot variable into account as well as the rcu_expedite_gp() + * nesting. So looping on rcu_unexpedite_gp() until rcu_gp_is_expedited() + * returns false is a -really- bad idea. + */ +bool rcu_gp_is_expedited(void) +{ + return rcu_expedited || atomic_read(&rcu_expedited_nesting); +} +EXPORT_SYMBOL_GPL(rcu_gp_is_expedited); + +/** + * rcu_expedite_gp - Expedite future RCU grace periods + * + * After a call to this function, future calls to synchronize_rcu() and + * friends act as the corresponding synchronize_rcu_expedited() function + * had instead been called. + */ +void rcu_expedite_gp(void) +{ + atomic_inc(&rcu_expedited_nesting); +} +EXPORT_SYMBOL_GPL(rcu_expedite_gp); + +/** + * rcu_unexpedite_gp - Cancel prior rcu_expedite_gp() invocation + * + * Undo a prior call to rcu_expedite_gp(). If all prior calls to + * rcu_expedite_gp() are undone by a subsequent call to rcu_unexpedite_gp(), + * and if the rcu_expedited sysfs/boot parameter is not set, then all + * subsequent calls to synchronize_rcu() and friends will return to + * their normal non-expedited behavior. + */ +void rcu_unexpedite_gp(void) +{ + atomic_dec(&rcu_expedited_nesting); +} +EXPORT_SYMBOL_GPL(rcu_unexpedite_gp); + +#endif /* #ifndef CONFIG_TINY_RCU */ + +/* + * Inform RCU of the end of the in-kernel boot sequence. + */ +void rcu_end_inkernel_boot(void) +{ + if (IS_ENABLED(CONFIG_RCU_EXPEDITE_BOOT)) + rcu_unexpedite_gp(); +} + +#ifdef CONFIG_PREEMPT_RCU + +/* + * Preemptible RCU implementation for rcu_read_lock(). + * Just increment ->rcu_read_lock_nesting, shared state will be updated + * if we block. + */ +void __rcu_read_lock(void) +{ + current->rcu_read_lock_nesting++; + barrier(); /* critical section after entry code. */ +} +EXPORT_SYMBOL_GPL(__rcu_read_lock); + +/* + * Preemptible RCU implementation for rcu_read_unlock(). + * Decrement ->rcu_read_lock_nesting. If the result is zero (outermost + * rcu_read_unlock()) and ->rcu_read_unlock_special is non-zero, then + * invoke rcu_read_unlock_special() to clean up after a context switch + * in an RCU read-side critical section and other special cases. + */ +void __rcu_read_unlock(void) +{ + struct task_struct *t = current; + + if (t->rcu_read_lock_nesting != 1) { + --t->rcu_read_lock_nesting; + } else { + barrier(); /* critical section before exit code. */ + t->rcu_read_lock_nesting = INT_MIN; + barrier(); /* assign before ->rcu_read_unlock_special load */ + if (unlikely(ACCESS_ONCE(t->rcu_read_unlock_special.s))) + rcu_read_unlock_special(t); + barrier(); /* ->rcu_read_unlock_special load before assign */ + t->rcu_read_lock_nesting = 0; + } +#ifdef CONFIG_PROVE_LOCKING + { + int rrln = ACCESS_ONCE(t->rcu_read_lock_nesting); + + WARN_ON_ONCE(rrln < 0 && rrln > INT_MIN / 2); + } +#endif /* #ifdef CONFIG_PROVE_LOCKING */ +} +EXPORT_SYMBOL_GPL(__rcu_read_unlock); + +#endif /* #ifdef CONFIG_PREEMPT_RCU */ + +#ifdef CONFIG_DEBUG_LOCK_ALLOC +static struct lock_class_key rcu_lock_key; +struct lockdep_map rcu_lock_map = + STATIC_LOCKDEP_MAP_INIT("rcu_read_lock", &rcu_lock_key); +EXPORT_SYMBOL_GPL(rcu_lock_map); + +static struct lock_class_key rcu_bh_lock_key; +struct lockdep_map rcu_bh_lock_map = + STATIC_LOCKDEP_MAP_INIT("rcu_read_lock_bh", &rcu_bh_lock_key); +EXPORT_SYMBOL_GPL(rcu_bh_lock_map); + +static struct lock_class_key rcu_sched_lock_key; +struct lockdep_map rcu_sched_lock_map = + STATIC_LOCKDEP_MAP_INIT("rcu_read_lock_sched", &rcu_sched_lock_key); +EXPORT_SYMBOL_GPL(rcu_sched_lock_map); + +static struct lock_class_key rcu_callback_key; +struct lockdep_map rcu_callback_map = + STATIC_LOCKDEP_MAP_INIT("rcu_callback", &rcu_callback_key); +EXPORT_SYMBOL_GPL(rcu_callback_map); + +int notrace debug_lockdep_rcu_enabled(void) +{ + return rcu_scheduler_active && debug_locks && + current->lockdep_recursion == 0; +} +EXPORT_SYMBOL_GPL(debug_lockdep_rcu_enabled); + +/** + * rcu_read_lock_held() - might we be in RCU read-side critical section? + * + * If CONFIG_DEBUG_LOCK_ALLOC is selected, returns nonzero iff in an RCU + * read-side critical section. In absence of CONFIG_DEBUG_LOCK_ALLOC, + * this assumes we are in an RCU read-side critical section unless it can + * prove otherwise. This is useful for debug checks in functions that + * require that they be called within an RCU read-side critical section. + * + * Checks debug_lockdep_rcu_enabled() to prevent false positives during boot + * and while lockdep is disabled. + * + * Note that rcu_read_lock() and the matching rcu_read_unlock() must + * occur in the same context, for example, it is illegal to invoke + * rcu_read_unlock() in process context if the matching rcu_read_lock() + * was invoked from within an irq handler. + * + * Note that rcu_read_lock() is disallowed if the CPU is either idle or + * offline from an RCU perspective, so check for those as well. + */ +int rcu_read_lock_held(void) +{ + if (!debug_lockdep_rcu_enabled()) + return 1; + if (!rcu_is_watching()) + return 0; + if (!rcu_lockdep_current_cpu_online()) + return 0; + return lock_is_held(&rcu_lock_map); +} +EXPORT_SYMBOL_GPL(rcu_read_lock_held); + +#ifndef CONFIG_PREEMPT_RT_FULL +/** + * rcu_read_lock_bh_held() - might we be in RCU-bh read-side critical section? + * + * Check for bottom half being disabled, which covers both the + * CONFIG_PROVE_RCU and not cases. Note that if someone uses + * rcu_read_lock_bh(), but then later enables BH, lockdep (if enabled) + * will show the situation. This is useful for debug checks in functions + * that require that they be called within an RCU read-side critical + * section. + * + * Check debug_lockdep_rcu_enabled() to prevent false positives during boot. + * + * Note that rcu_read_lock() is disallowed if the CPU is either idle or + * offline from an RCU perspective, so check for those as well. + */ +int rcu_read_lock_bh_held(void) +{ + if (!debug_lockdep_rcu_enabled()) + return 1; + if (!rcu_is_watching()) + return 0; + if (!rcu_lockdep_current_cpu_online()) + return 0; + return in_softirq() || irqs_disabled(); +} +EXPORT_SYMBOL_GPL(rcu_read_lock_bh_held); +#endif + +#endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ + +/** + * wakeme_after_rcu() - Callback function to awaken a task after grace period + * @head: Pointer to rcu_head member within rcu_synchronize structure + * + * Awaken the corresponding task now that a grace period has elapsed. + */ +void wakeme_after_rcu(struct rcu_head *head) +{ + struct rcu_synchronize *rcu; + + rcu = container_of(head, struct rcu_synchronize, head); + complete(&rcu->completion); +} + +void wait_rcu_gp(call_rcu_func_t crf) +{ + struct rcu_synchronize rcu; + + init_rcu_head_on_stack(&rcu.head); + init_completion(&rcu.completion); + /* Will wake me after RCU finished. */ + crf(&rcu.head, wakeme_after_rcu); + /* Wait for it. */ + wait_for_completion(&rcu.completion); + destroy_rcu_head_on_stack(&rcu.head); +} +EXPORT_SYMBOL_GPL(wait_rcu_gp); + +#ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD +void init_rcu_head(struct rcu_head *head) +{ + debug_object_init(head, &rcuhead_debug_descr); +} + +void destroy_rcu_head(struct rcu_head *head) +{ + debug_object_free(head, &rcuhead_debug_descr); +} + +/* + * fixup_activate is called when: + * - an active object is activated + * - an unknown object is activated (might be a statically initialized object) + * Activation is performed internally by call_rcu(). + */ +static int rcuhead_fixup_activate(void *addr, enum debug_obj_state state) +{ + struct rcu_head *head = addr; + + switch (state) { + + case ODEBUG_STATE_NOTAVAILABLE: + /* + * This is not really a fixup. We just make sure that it is + * tracked in the object tracker. + */ + debug_object_init(head, &rcuhead_debug_descr); + debug_object_activate(head, &rcuhead_debug_descr); + return 0; + default: + return 1; + } +} + +/** + * init_rcu_head_on_stack() - initialize on-stack rcu_head for debugobjects + * @head: pointer to rcu_head structure to be initialized + * + * This function informs debugobjects of a new rcu_head structure that + * has been allocated as an auto variable on the stack. This function + * is not required for rcu_head structures that are statically defined or + * that are dynamically allocated on the heap. This function has no + * effect for !CONFIG_DEBUG_OBJECTS_RCU_HEAD kernel builds. + */ +void init_rcu_head_on_stack(struct rcu_head *head) +{ + debug_object_init_on_stack(head, &rcuhead_debug_descr); +} +EXPORT_SYMBOL_GPL(init_rcu_head_on_stack); + +/** + * destroy_rcu_head_on_stack() - destroy on-stack rcu_head for debugobjects + * @head: pointer to rcu_head structure to be initialized + * + * This function informs debugobjects that an on-stack rcu_head structure + * is about to go out of scope. As with init_rcu_head_on_stack(), this + * function is not required for rcu_head structures that are statically + * defined or that are dynamically allocated on the heap. Also as with + * init_rcu_head_on_stack(), this function has no effect for + * !CONFIG_DEBUG_OBJECTS_RCU_HEAD kernel builds. + */ +void destroy_rcu_head_on_stack(struct rcu_head *head) +{ + debug_object_free(head, &rcuhead_debug_descr); +} +EXPORT_SYMBOL_GPL(destroy_rcu_head_on_stack); + +struct debug_obj_descr rcuhead_debug_descr = { + .name = "rcu_head", + .fixup_activate = rcuhead_fixup_activate, +}; +EXPORT_SYMBOL_GPL(rcuhead_debug_descr); +#endif /* #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD */ + +#if defined(CONFIG_TREE_RCU) || defined(CONFIG_PREEMPT_RCU) || defined(CONFIG_RCU_TRACE) +void do_trace_rcu_torture_read(const char *rcutorturename, struct rcu_head *rhp, + unsigned long secs, + unsigned long c_old, unsigned long c) +{ + trace_rcu_torture_read(rcutorturename, rhp, secs, c_old, c); +} +EXPORT_SYMBOL_GPL(do_trace_rcu_torture_read); +#else +#define do_trace_rcu_torture_read(rcutorturename, rhp, secs, c_old, c) \ + do { } while (0) +#endif + +#ifdef CONFIG_RCU_STALL_COMMON + +#ifdef CONFIG_PROVE_RCU +#define RCU_STALL_DELAY_DELTA (5 * HZ) +#else +#define RCU_STALL_DELAY_DELTA 0 +#endif + +int rcu_cpu_stall_suppress __read_mostly; /* 1 = suppress stall warnings. */ +static int rcu_cpu_stall_timeout __read_mostly = CONFIG_RCU_CPU_STALL_TIMEOUT; + +module_param(rcu_cpu_stall_suppress, int, 0644); +module_param(rcu_cpu_stall_timeout, int, 0644); + +int rcu_jiffies_till_stall_check(void) +{ + int till_stall_check = ACCESS_ONCE(rcu_cpu_stall_timeout); + + /* + * Limit check must be consistent with the Kconfig limits + * for CONFIG_RCU_CPU_STALL_TIMEOUT. + */ + if (till_stall_check < 3) { + ACCESS_ONCE(rcu_cpu_stall_timeout) = 3; + till_stall_check = 3; + } else if (till_stall_check > 300) { + ACCESS_ONCE(rcu_cpu_stall_timeout) = 300; + till_stall_check = 300; + } + return till_stall_check * HZ + RCU_STALL_DELAY_DELTA; +} + +void rcu_sysrq_start(void) +{ + if (!rcu_cpu_stall_suppress) + rcu_cpu_stall_suppress = 2; +} + +void rcu_sysrq_end(void) +{ + if (rcu_cpu_stall_suppress == 2) + rcu_cpu_stall_suppress = 0; +} + +static int rcu_panic(struct notifier_block *this, unsigned long ev, void *ptr) +{ + rcu_cpu_stall_suppress = 1; + return NOTIFY_DONE; +} + +static struct notifier_block rcu_panic_block = { + .notifier_call = rcu_panic, +}; + +static int __init check_cpu_stall_init(void) +{ + atomic_notifier_chain_register(&panic_notifier_list, &rcu_panic_block); + return 0; +} +early_initcall(check_cpu_stall_init); + +#endif /* #ifdef CONFIG_RCU_STALL_COMMON */ + +#ifdef CONFIG_TASKS_RCU + +/* + * Simple variant of RCU whose quiescent states are voluntary context switch, + * user-space execution, and idle. As such, grace periods can take one good + * long time. There are no read-side primitives similar to rcu_read_lock() + * and rcu_read_unlock() because this implementation is intended to get + * the system into a safe state for some of the manipulations involved in + * tracing and the like. Finally, this implementation does not support + * high call_rcu_tasks() rates from multiple CPUs. If this is required, + * per-CPU callback lists will be needed. + */ + +/* Global list of callbacks and associated lock. */ +static struct rcu_head *rcu_tasks_cbs_head; +static struct rcu_head **rcu_tasks_cbs_tail = &rcu_tasks_cbs_head; +static DECLARE_WAIT_QUEUE_HEAD(rcu_tasks_cbs_wq); +static DEFINE_RAW_SPINLOCK(rcu_tasks_cbs_lock); + +/* Track exiting tasks in order to allow them to be waited for. */ +DEFINE_SRCU(tasks_rcu_exit_srcu); + +/* Control stall timeouts. Disable with <= 0, otherwise jiffies till stall. */ +static int rcu_task_stall_timeout __read_mostly = HZ * 60 * 10; +module_param(rcu_task_stall_timeout, int, 0644); + +static void rcu_spawn_tasks_kthread(void); + +/* + * Post an RCU-tasks callback. First call must be from process context + * after the scheduler if fully operational. + */ +void call_rcu_tasks(struct rcu_head *rhp, void (*func)(struct rcu_head *rhp)) +{ + unsigned long flags; + bool needwake; + + rhp->next = NULL; + rhp->func = func; + raw_spin_lock_irqsave(&rcu_tasks_cbs_lock, flags); + needwake = !rcu_tasks_cbs_head; + *rcu_tasks_cbs_tail = rhp; + rcu_tasks_cbs_tail = &rhp->next; + raw_spin_unlock_irqrestore(&rcu_tasks_cbs_lock, flags); + if (needwake) { + rcu_spawn_tasks_kthread(); + wake_up(&rcu_tasks_cbs_wq); + } +} +EXPORT_SYMBOL_GPL(call_rcu_tasks); + +/** + * synchronize_rcu_tasks - wait until an rcu-tasks grace period has elapsed. + * + * Control will return to the caller some time after a full rcu-tasks + * grace period has elapsed, in other words after all currently + * executing rcu-tasks read-side critical sections have elapsed. These + * read-side critical sections are delimited by calls to schedule(), + * cond_resched_rcu_qs(), idle execution, userspace execution, calls + * to synchronize_rcu_tasks(), and (in theory, anyway) cond_resched(). + * + * This is a very specialized primitive, intended only for a few uses in + * tracing and other situations requiring manipulation of function + * preambles and profiling hooks. The synchronize_rcu_tasks() function + * is not (yet) intended for heavy use from multiple CPUs. + * + * Note that this guarantee implies further memory-ordering guarantees. + * On systems with more than one CPU, when synchronize_rcu_tasks() returns, + * each CPU is guaranteed to have executed a full memory barrier since the + * end of its last RCU-tasks read-side critical section whose beginning + * preceded the call to synchronize_rcu_tasks(). In addition, each CPU + * having an RCU-tasks read-side critical section that extends beyond + * the return from synchronize_rcu_tasks() is guaranteed to have executed + * a full memory barrier after the beginning of synchronize_rcu_tasks() + * and before the beginning of that RCU-tasks read-side critical section. + * Note that these guarantees include CPUs that are offline, idle, or + * executing in user mode, as well as CPUs that are executing in the kernel. + * + * Furthermore, if CPU A invoked synchronize_rcu_tasks(), which returned + * to its caller on CPU B, then both CPU A and CPU B are guaranteed + * to have executed a full memory barrier during the execution of + * synchronize_rcu_tasks() -- even if CPU A and CPU B are the same CPU + * (but again only if the system has more than one CPU). + */ +void synchronize_rcu_tasks(void) +{ + /* Complain if the scheduler has not started. */ + rcu_lockdep_assert(!rcu_scheduler_active, + "synchronize_rcu_tasks called too soon"); + + /* Wait for the grace period. */ + wait_rcu_gp(call_rcu_tasks); +} +EXPORT_SYMBOL_GPL(synchronize_rcu_tasks); + +/** + * rcu_barrier_tasks - Wait for in-flight call_rcu_tasks() callbacks. + * + * Although the current implementation is guaranteed to wait, it is not + * obligated to, for example, if there are no pending callbacks. + */ +void rcu_barrier_tasks(void) +{ + /* There is only one callback queue, so this is easy. ;-) */ + synchronize_rcu_tasks(); +} +EXPORT_SYMBOL_GPL(rcu_barrier_tasks); + +/* See if tasks are still holding out, complain if so. */ +static void check_holdout_task(struct task_struct *t, + bool needreport, bool *firstreport) +{ + int cpu; + + if (!ACCESS_ONCE(t->rcu_tasks_holdout) || + t->rcu_tasks_nvcsw != ACCESS_ONCE(t->nvcsw) || + !ACCESS_ONCE(t->on_rq) || + (IS_ENABLED(CONFIG_NO_HZ_FULL) && + !is_idle_task(t) && t->rcu_tasks_idle_cpu >= 0)) { + ACCESS_ONCE(t->rcu_tasks_holdout) = false; + list_del_init(&t->rcu_tasks_holdout_list); + put_task_struct(t); + return; + } + if (!needreport) + return; + if (*firstreport) { + pr_err("INFO: rcu_tasks detected stalls on tasks:\n"); + *firstreport = false; + } + cpu = task_cpu(t); + pr_alert("%p: %c%c nvcsw: %lu/%lu holdout: %d idle_cpu: %d/%d\n", + t, ".I"[is_idle_task(t)], + "N."[cpu < 0 || !tick_nohz_full_cpu(cpu)], + t->rcu_tasks_nvcsw, t->nvcsw, t->rcu_tasks_holdout, + t->rcu_tasks_idle_cpu, cpu); + sched_show_task(t); +} + +/* RCU-tasks kthread that detects grace periods and invokes callbacks. */ +static int __noreturn rcu_tasks_kthread(void *arg) +{ + unsigned long flags; + struct task_struct *g, *t; + unsigned long lastreport; + struct rcu_head *list; + struct rcu_head *next; + LIST_HEAD(rcu_tasks_holdouts); + + /* Run on housekeeping CPUs by default. Sysadm can move if desired. */ + housekeeping_affine(current); + + /* + * Each pass through the following loop makes one check for + * newly arrived callbacks, and, if there are some, waits for + * one RCU-tasks grace period and then invokes the callbacks. + * This loop is terminated by the system going down. ;-) + */ + for (;;) { + + /* Pick up any new callbacks. */ + raw_spin_lock_irqsave(&rcu_tasks_cbs_lock, flags); + list = rcu_tasks_cbs_head; + rcu_tasks_cbs_head = NULL; + rcu_tasks_cbs_tail = &rcu_tasks_cbs_head; + raw_spin_unlock_irqrestore(&rcu_tasks_cbs_lock, flags); + + /* If there were none, wait a bit and start over. */ + if (!list) { + wait_event_interruptible(rcu_tasks_cbs_wq, + rcu_tasks_cbs_head); + if (!rcu_tasks_cbs_head) { + WARN_ON(signal_pending(current)); + schedule_timeout_interruptible(HZ/10); + } + continue; + } + + /* + * Wait for all pre-existing t->on_rq and t->nvcsw + * transitions to complete. Invoking synchronize_sched() + * suffices because all these transitions occur with + * interrupts disabled. Without this synchronize_sched(), + * a read-side critical section that started before the + * grace period might be incorrectly seen as having started + * after the grace period. + * + * This synchronize_sched() also dispenses with the + * need for a memory barrier on the first store to + * ->rcu_tasks_holdout, as it forces the store to happen + * after the beginning of the grace period. + */ + synchronize_sched(); + + /* + * There were callbacks, so we need to wait for an + * RCU-tasks grace period. Start off by scanning + * the task list for tasks that are not already + * voluntarily blocked. Mark these tasks and make + * a list of them in rcu_tasks_holdouts. + */ + rcu_read_lock(); + for_each_process_thread(g, t) { + if (t != current && ACCESS_ONCE(t->on_rq) && + !is_idle_task(t)) { + get_task_struct(t); + t->rcu_tasks_nvcsw = ACCESS_ONCE(t->nvcsw); + ACCESS_ONCE(t->rcu_tasks_holdout) = true; + list_add(&t->rcu_tasks_holdout_list, + &rcu_tasks_holdouts); + } + } + rcu_read_unlock(); + + /* + * Wait for tasks that are in the process of exiting. + * This does only part of the job, ensuring that all + * tasks that were previously exiting reach the point + * where they have disabled preemption, allowing the + * later synchronize_sched() to finish the job. + */ + synchronize_srcu(&tasks_rcu_exit_srcu); + + /* + * Each pass through the following loop scans the list + * of holdout tasks, removing any that are no longer + * holdouts. When the list is empty, we are done. + */ + lastreport = jiffies; + while (!list_empty(&rcu_tasks_holdouts)) { + bool firstreport; + bool needreport; + int rtst; + struct task_struct *t1; + + schedule_timeout_interruptible(HZ); + rtst = ACCESS_ONCE(rcu_task_stall_timeout); + needreport = rtst > 0 && + time_after(jiffies, lastreport + rtst); + if (needreport) + lastreport = jiffies; + firstreport = true; + WARN_ON(signal_pending(current)); + list_for_each_entry_safe(t, t1, &rcu_tasks_holdouts, + rcu_tasks_holdout_list) { + check_holdout_task(t, needreport, &firstreport); + cond_resched(); + } + } + + /* + * Because ->on_rq and ->nvcsw are not guaranteed + * to have a full memory barriers prior to them in the + * schedule() path, memory reordering on other CPUs could + * cause their RCU-tasks read-side critical sections to + * extend past the end of the grace period. However, + * because these ->nvcsw updates are carried out with + * interrupts disabled, we can use synchronize_sched() + * to force the needed ordering on all such CPUs. + * + * This synchronize_sched() also confines all + * ->rcu_tasks_holdout accesses to be within the grace + * period, avoiding the need for memory barriers for + * ->rcu_tasks_holdout accesses. + * + * In addition, this synchronize_sched() waits for exiting + * tasks to complete their final preempt_disable() region + * of execution, cleaning up after the synchronize_srcu() + * above. + */ + synchronize_sched(); + + /* Invoke the callbacks. */ + while (list) { + next = list->next; + local_bh_disable(); + list->func(list); + local_bh_enable(); + list = next; + cond_resched(); + } + schedule_timeout_uninterruptible(HZ/10); + } +} + +/* Spawn rcu_tasks_kthread() at first call to call_rcu_tasks(). */ +static void rcu_spawn_tasks_kthread(void) +{ + static DEFINE_MUTEX(rcu_tasks_kthread_mutex); + static struct task_struct *rcu_tasks_kthread_ptr; + struct task_struct *t; + + if (ACCESS_ONCE(rcu_tasks_kthread_ptr)) { + smp_mb(); /* Ensure caller sees full kthread. */ + return; + } + mutex_lock(&rcu_tasks_kthread_mutex); + if (rcu_tasks_kthread_ptr) { + mutex_unlock(&rcu_tasks_kthread_mutex); + return; + } + t = kthread_run(rcu_tasks_kthread, NULL, "rcu_tasks_kthread"); + BUG_ON(IS_ERR(t)); + smp_mb(); /* Ensure others see full kthread. */ + ACCESS_ONCE(rcu_tasks_kthread_ptr) = t; + mutex_unlock(&rcu_tasks_kthread_mutex); +} + +#endif /* #ifdef CONFIG_TASKS_RCU */ + +#ifdef CONFIG_PROVE_RCU + +/* + * Early boot self test parameters, one for each flavor + */ +static bool rcu_self_test; +static bool rcu_self_test_bh; +static bool rcu_self_test_sched; + +module_param(rcu_self_test, bool, 0444); +module_param(rcu_self_test_bh, bool, 0444); +module_param(rcu_self_test_sched, bool, 0444); + +static int rcu_self_test_counter; + +static void test_callback(struct rcu_head *r) +{ + rcu_self_test_counter++; + pr_info("RCU test callback executed %d\n", rcu_self_test_counter); +} + +static void early_boot_test_call_rcu(void) +{ + static struct rcu_head head; + + call_rcu(&head, test_callback); +} + +static void early_boot_test_call_rcu_bh(void) +{ + static struct rcu_head head; + + call_rcu_bh(&head, test_callback); +} + +static void early_boot_test_call_rcu_sched(void) +{ + static struct rcu_head head; + + call_rcu_sched(&head, test_callback); +} + +void rcu_early_boot_tests(void) +{ + pr_info("Running RCU self tests\n"); + + if (rcu_self_test) + early_boot_test_call_rcu(); + if (rcu_self_test_bh) + early_boot_test_call_rcu_bh(); + if (rcu_self_test_sched) + early_boot_test_call_rcu_sched(); +} + +static int rcu_verify_early_boot_tests(void) +{ + int ret = 0; + int early_boot_test_counter = 0; + + if (rcu_self_test) { + early_boot_test_counter++; + rcu_barrier(); + } + if (rcu_self_test_bh) { + early_boot_test_counter++; + rcu_barrier_bh(); + } + if (rcu_self_test_sched) { + early_boot_test_counter++; + rcu_barrier_sched(); + } + + if (rcu_self_test_counter != early_boot_test_counter) { + WARN_ON(1); + ret = -1; + } + + return ret; +} +late_initcall(rcu_verify_early_boot_tests); +#else +void rcu_early_boot_tests(void) {} +#endif /* CONFIG_PROVE_RCU */ diff --git a/kernel/kernel/reboot.c b/kernel/kernel/reboot.c new file mode 100644 index 000000000..d20c85d9f --- /dev/null +++ b/kernel/kernel/reboot.c @@ -0,0 +1,557 @@ +/* + * linux/kernel/reboot.c + * + * Copyright (C) 2013 Linus Torvalds + */ + +#define pr_fmt(fmt) "reboot: " fmt + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +/* + * this indicates whether you can reboot with ctrl-alt-del: the default is yes + */ + +int C_A_D = 1; +struct pid *cad_pid; +EXPORT_SYMBOL(cad_pid); + +#if defined(CONFIG_ARM) || defined(CONFIG_UNICORE32) +#define DEFAULT_REBOOT_MODE = REBOOT_HARD +#else +#define DEFAULT_REBOOT_MODE +#endif +enum reboot_mode reboot_mode DEFAULT_REBOOT_MODE; + +/* + * This variable is used privately to keep track of whether or not + * reboot_type is still set to its default value (i.e., reboot= hasn't + * been set on the command line). This is needed so that we can + * suppress DMI scanning for reboot quirks. Without it, it's + * impossible to override a faulty reboot quirk without recompiling. + */ +int reboot_default = 1; +int reboot_cpu; +enum reboot_type reboot_type = BOOT_ACPI; +int reboot_force; + +/* + * If set, this is used for preparing the system to power off. + */ + +void (*pm_power_off_prepare)(void); + +/** + * emergency_restart - reboot the system + * + * Without shutting down any hardware or taking any locks + * reboot the system. This is called when we know we are in + * trouble so this is our best effort to reboot. This is + * safe to call in interrupt context. + */ +void emergency_restart(void) +{ + kmsg_dump(KMSG_DUMP_EMERG); + machine_emergency_restart(); +} +EXPORT_SYMBOL_GPL(emergency_restart); + +void kernel_restart_prepare(char *cmd) +{ + blocking_notifier_call_chain(&reboot_notifier_list, SYS_RESTART, cmd); + system_state = SYSTEM_RESTART; + usermodehelper_disable(); + device_shutdown(); +} + +/** + * register_reboot_notifier - Register function to be called at reboot time + * @nb: Info about notifier function to be called + * + * Registers a function with the list of functions + * to be called at reboot time. + * + * Currently always returns zero, as blocking_notifier_chain_register() + * always returns zero. + */ +int register_reboot_notifier(struct notifier_block *nb) +{ + return blocking_notifier_chain_register(&reboot_notifier_list, nb); +} +EXPORT_SYMBOL(register_reboot_notifier); + +/** + * unregister_reboot_notifier - Unregister previously registered reboot notifier + * @nb: Hook to be unregistered + * + * Unregisters a previously registered reboot + * notifier function. + * + * Returns zero on success, or %-ENOENT on failure. + */ +int unregister_reboot_notifier(struct notifier_block *nb) +{ + return blocking_notifier_chain_unregister(&reboot_notifier_list, nb); +} +EXPORT_SYMBOL(unregister_reboot_notifier); + +/* + * Notifier list for kernel code which wants to be called + * to restart the system. + */ +static ATOMIC_NOTIFIER_HEAD(restart_handler_list); + +/** + * register_restart_handler - Register function to be called to reset + * the system + * @nb: Info about handler function to be called + * @nb->priority: Handler priority. Handlers should follow the + * following guidelines for setting priorities. + * 0: Restart handler of last resort, + * with limited restart capabilities + * 128: Default restart handler; use if no other + * restart handler is expected to be available, + * and/or if restart functionality is + * sufficient to restart the entire system + * 255: Highest priority restart handler, will + * preempt all other restart handlers + * + * Registers a function with code to be called to restart the + * system. + * + * Registered functions will be called from machine_restart as last + * step of the restart sequence (if the architecture specific + * machine_restart function calls do_kernel_restart - see below + * for details). + * Registered functions are expected to restart the system immediately. + * If more than one function is registered, the restart handler priority + * selects which function will be called first. + * + * Restart handlers are expected to be registered from non-architecture + * code, typically from drivers. A typical use case would be a system + * where restart functionality is provided through a watchdog. Multiple + * restart handlers may exist; for example, one restart handler might + * restart the entire system, while another only restarts the CPU. + * In such cases, the restart handler which only restarts part of the + * hardware is expected to register with low priority to ensure that + * it only runs if no other means to restart the system is available. + * + * Currently always returns zero, as atomic_notifier_chain_register() + * always returns zero. + */ +int register_restart_handler(struct notifier_block *nb) +{ + return atomic_notifier_chain_register(&restart_handler_list, nb); +} +EXPORT_SYMBOL(register_restart_handler); + +/** + * unregister_restart_handler - Unregister previously registered + * restart handler + * @nb: Hook to be unregistered + * + * Unregisters a previously registered restart handler function. + * + * Returns zero on success, or %-ENOENT on failure. + */ +int unregister_restart_handler(struct notifier_block *nb) +{ + return atomic_notifier_chain_unregister(&restart_handler_list, nb); +} +EXPORT_SYMBOL(unregister_restart_handler); + +/** + * do_kernel_restart - Execute kernel restart handler call chain + * + * Calls functions registered with register_restart_handler. + * + * Expected to be called from machine_restart as last step of the restart + * sequence. + * + * Restarts the system immediately if a restart handler function has been + * registered. Otherwise does nothing. + */ +void do_kernel_restart(char *cmd) +{ + atomic_notifier_call_chain(&restart_handler_list, reboot_mode, cmd); +} + +void migrate_to_reboot_cpu(void) +{ + /* The boot cpu is always logical cpu 0 */ + int cpu = reboot_cpu; + + cpu_hotplug_disable(); + + /* Make certain the cpu I'm about to reboot on is online */ + if (!cpu_online(cpu)) + cpu = cpumask_first(cpu_online_mask); + + /* Prevent races with other tasks migrating this task */ + current->flags |= PF_NO_SETAFFINITY; + + /* Make certain I only run on the appropriate processor */ + set_cpus_allowed_ptr(current, cpumask_of(cpu)); +} + +/** + * kernel_restart - reboot the system + * @cmd: pointer to buffer containing command to execute for restart + * or %NULL + * + * Shutdown everything and perform a clean reboot. + * This is not safe to call in interrupt context. + */ +void kernel_restart(char *cmd) +{ + kernel_restart_prepare(cmd); + migrate_to_reboot_cpu(); + syscore_shutdown(); + if (!cmd) + pr_emerg("Restarting system\n"); + else + pr_emerg("Restarting system with command '%s'\n", cmd); + kmsg_dump(KMSG_DUMP_RESTART); + machine_restart(cmd); +} +EXPORT_SYMBOL_GPL(kernel_restart); + +static void kernel_shutdown_prepare(enum system_states state) +{ + blocking_notifier_call_chain(&reboot_notifier_list, + (state == SYSTEM_HALT) ? SYS_HALT : SYS_POWER_OFF, NULL); + system_state = state; + usermodehelper_disable(); + device_shutdown(); +} +/** + * kernel_halt - halt the system + * + * Shutdown everything and perform a clean system halt. + */ +void kernel_halt(void) +{ + kernel_shutdown_prepare(SYSTEM_HALT); + migrate_to_reboot_cpu(); + syscore_shutdown(); + pr_emerg("System halted\n"); + kmsg_dump(KMSG_DUMP_HALT); + machine_halt(); +} +EXPORT_SYMBOL_GPL(kernel_halt); + +/** + * kernel_power_off - power_off the system + * + * Shutdown everything and perform a clean system power_off. + */ +void kernel_power_off(void) +{ + kernel_shutdown_prepare(SYSTEM_POWER_OFF); + if (pm_power_off_prepare) + pm_power_off_prepare(); + migrate_to_reboot_cpu(); + syscore_shutdown(); + pr_emerg("Power down\n"); + kmsg_dump(KMSG_DUMP_POWEROFF); + machine_power_off(); +} +EXPORT_SYMBOL_GPL(kernel_power_off); + +static DEFINE_MUTEX(reboot_mutex); + +/* + * Reboot system call: for obvious reasons only root may call it, + * and even root needs to set up some magic numbers in the registers + * so that some mistake won't make this reboot the whole machine. + * You can also set the meaning of the ctrl-alt-del-key here. + * + * reboot doesn't sync: do that yourself before calling this. + */ +SYSCALL_DEFINE4(reboot, int, magic1, int, magic2, unsigned int, cmd, + void __user *, arg) +{ + struct pid_namespace *pid_ns = task_active_pid_ns(current); + char buffer[256]; + int ret = 0; + + /* We only trust the superuser with rebooting the system. */ + if (!ns_capable(pid_ns->user_ns, CAP_SYS_BOOT)) + return -EPERM; + + /* For safety, we require "magic" arguments. */ + if (magic1 != LINUX_REBOOT_MAGIC1 || + (magic2 != LINUX_REBOOT_MAGIC2 && + magic2 != LINUX_REBOOT_MAGIC2A && + magic2 != LINUX_REBOOT_MAGIC2B && + magic2 != LINUX_REBOOT_MAGIC2C)) + return -EINVAL; + + /* + * If pid namespaces are enabled and the current task is in a child + * pid_namespace, the command is handled by reboot_pid_ns() which will + * call do_exit(). + */ + ret = reboot_pid_ns(pid_ns, cmd); + if (ret) + return ret; + + /* Instead of trying to make the power_off code look like + * halt when pm_power_off is not set do it the easy way. + */ + if ((cmd == LINUX_REBOOT_CMD_POWER_OFF) && !pm_power_off) + cmd = LINUX_REBOOT_CMD_HALT; + + mutex_lock(&reboot_mutex); + switch (cmd) { + case LINUX_REBOOT_CMD_RESTART: + kernel_restart(NULL); + break; + + case LINUX_REBOOT_CMD_CAD_ON: + C_A_D = 1; + break; + + case LINUX_REBOOT_CMD_CAD_OFF: + C_A_D = 0; + break; + + case LINUX_REBOOT_CMD_HALT: + kernel_halt(); + do_exit(0); + panic("cannot halt"); + + case LINUX_REBOOT_CMD_POWER_OFF: + kernel_power_off(); + do_exit(0); + break; + + case LINUX_REBOOT_CMD_RESTART2: + ret = strncpy_from_user(&buffer[0], arg, sizeof(buffer) - 1); + if (ret < 0) { + ret = -EFAULT; + break; + } + buffer[sizeof(buffer) - 1] = '\0'; + + kernel_restart(buffer); + break; + +#ifdef CONFIG_KEXEC + case LINUX_REBOOT_CMD_KEXEC: + ret = kernel_kexec(); + break; +#endif + +#ifdef CONFIG_HIBERNATION + case LINUX_REBOOT_CMD_SW_SUSPEND: + ret = hibernate(); + break; +#endif + + default: + ret = -EINVAL; + break; + } + mutex_unlock(&reboot_mutex); + return ret; +} + +static void deferred_cad(struct work_struct *dummy) +{ + kernel_restart(NULL); +} + +/* + * This function gets called by ctrl-alt-del - ie the keyboard interrupt. + * As it's called within an interrupt, it may NOT sync: the only choice + * is whether to reboot at once, or just ignore the ctrl-alt-del. + */ +void ctrl_alt_del(void) +{ + static DECLARE_WORK(cad_work, deferred_cad); + + if (C_A_D) + schedule_work(&cad_work); + else + kill_cad_pid(SIGINT, 1); +} + +char poweroff_cmd[POWEROFF_CMD_PATH_LEN] = "/sbin/poweroff"; +static const char reboot_cmd[] = "/sbin/reboot"; + +static int run_cmd(const char *cmd) +{ + char **argv; + static char *envp[] = { + "HOME=/", + "PATH=/sbin:/bin:/usr/sbin:/usr/bin", + NULL + }; + int ret; + argv = argv_split(GFP_KERNEL, cmd, NULL); + if (argv) { + ret = call_usermodehelper(argv[0], argv, envp, UMH_WAIT_EXEC); + argv_free(argv); + } else { + ret = -ENOMEM; + } + + return ret; +} + +static int __orderly_reboot(void) +{ + int ret; + + ret = run_cmd(reboot_cmd); + + if (ret) { + pr_warn("Failed to start orderly reboot: forcing the issue\n"); + emergency_sync(); + kernel_restart(NULL); + } + + return ret; +} + +static int __orderly_poweroff(bool force) +{ + int ret; + + ret = run_cmd(poweroff_cmd); + + if (ret && force) { + pr_warn("Failed to start orderly shutdown: forcing the issue\n"); + + /* + * I guess this should try to kick off some daemon to sync and + * poweroff asap. Or not even bother syncing if we're doing an + * emergency shutdown? + */ + emergency_sync(); + kernel_power_off(); + } + + return ret; +} + +static bool poweroff_force; + +static void poweroff_work_func(struct work_struct *work) +{ + __orderly_poweroff(poweroff_force); +} + +static DECLARE_WORK(poweroff_work, poweroff_work_func); + +/** + * orderly_poweroff - Trigger an orderly system poweroff + * @force: force poweroff if command execution fails + * + * This may be called from any context to trigger a system shutdown. + * If the orderly shutdown fails, it will force an immediate shutdown. + */ +void orderly_poweroff(bool force) +{ + if (force) /* do not override the pending "true" */ + poweroff_force = true; + schedule_work(&poweroff_work); +} +EXPORT_SYMBOL_GPL(orderly_poweroff); + +static void reboot_work_func(struct work_struct *work) +{ + __orderly_reboot(); +} + +static DECLARE_WORK(reboot_work, reboot_work_func); + +/** + * orderly_reboot - Trigger an orderly system reboot + * + * This may be called from any context to trigger a system reboot. + * If the orderly reboot fails, it will force an immediate reboot. + */ +void orderly_reboot(void) +{ + schedule_work(&reboot_work); +} +EXPORT_SYMBOL_GPL(orderly_reboot); + +static int __init reboot_setup(char *str) +{ + for (;;) { + /* + * Having anything passed on the command line via + * reboot= will cause us to disable DMI checking + * below. + */ + reboot_default = 0; + + switch (*str) { + case 'w': + reboot_mode = REBOOT_WARM; + break; + + case 'c': + reboot_mode = REBOOT_COLD; + break; + + case 'h': + reboot_mode = REBOOT_HARD; + break; + + case 's': + { + int rc; + + if (isdigit(*(str+1))) { + rc = kstrtoint(str+1, 0, &reboot_cpu); + if (rc) + return rc; + } else if (str[1] == 'm' && str[2] == 'p' && + isdigit(*(str+3))) { + rc = kstrtoint(str+3, 0, &reboot_cpu); + if (rc) + return rc; + } else + reboot_mode = REBOOT_SOFT; + break; + } + case 'g': + reboot_mode = REBOOT_GPIO; + break; + + case 'b': + case 'a': + case 'k': + case 't': + case 'e': + case 'p': + reboot_type = *str; + break; + + case 'f': + reboot_force = 1; + break; + } + + str = strchr(str, ','); + if (str) + str++; + else + break; + } + return 1; +} +__setup("reboot=", reboot_setup); diff --git a/kernel/kernel/relay.c b/kernel/kernel/relay.c new file mode 100644 index 000000000..509f68fb9 --- /dev/null +++ b/kernel/kernel/relay.c @@ -0,0 +1,1356 @@ +/* + * Public API and common code for kernel->userspace relay file support. + * + * See Documentation/filesystems/relay.txt for an overview. + * + * Copyright (C) 2002-2005 - Tom Zanussi (zanussi@us.ibm.com), IBM Corp + * Copyright (C) 1999-2005 - Karim Yaghmour (karim@opersys.com) + * + * Moved to kernel/relay.c by Paul Mundt, 2006. + * November 2006 - CPU hotplug support by Mathieu Desnoyers + * (mathieu.desnoyers@polymtl.ca) + * + * This file is released under the GPL. + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +/* list of open channels, for cpu hotplug */ +static DEFINE_MUTEX(relay_channels_mutex); +static LIST_HEAD(relay_channels); + +/* + * close() vm_op implementation for relay file mapping. + */ +static void relay_file_mmap_close(struct vm_area_struct *vma) +{ + struct rchan_buf *buf = vma->vm_private_data; + buf->chan->cb->buf_unmapped(buf, vma->vm_file); +} + +/* + * fault() vm_op implementation for relay file mapping. + */ +static int relay_buf_fault(struct vm_area_struct *vma, struct vm_fault *vmf) +{ + struct page *page; + struct rchan_buf *buf = vma->vm_private_data; + pgoff_t pgoff = vmf->pgoff; + + if (!buf) + return VM_FAULT_OOM; + + page = vmalloc_to_page(buf->start + (pgoff << PAGE_SHIFT)); + if (!page) + return VM_FAULT_SIGBUS; + get_page(page); + vmf->page = page; + + return 0; +} + +/* + * vm_ops for relay file mappings. + */ +static const struct vm_operations_struct relay_file_mmap_ops = { + .fault = relay_buf_fault, + .close = relay_file_mmap_close, +}; + +/* + * allocate an array of pointers of struct page + */ +static struct page **relay_alloc_page_array(unsigned int n_pages) +{ + const size_t pa_size = n_pages * sizeof(struct page *); + if (pa_size > PAGE_SIZE) + return vzalloc(pa_size); + return kzalloc(pa_size, GFP_KERNEL); +} + +/* + * free an array of pointers of struct page + */ +static void relay_free_page_array(struct page **array) +{ + if (is_vmalloc_addr(array)) + vfree(array); + else + kfree(array); +} + +/** + * relay_mmap_buf: - mmap channel buffer to process address space + * @buf: relay channel buffer + * @vma: vm_area_struct describing memory to be mapped + * + * Returns 0 if ok, negative on error + * + * Caller should already have grabbed mmap_sem. + */ +static int relay_mmap_buf(struct rchan_buf *buf, struct vm_area_struct *vma) +{ + unsigned long length = vma->vm_end - vma->vm_start; + struct file *filp = vma->vm_file; + + if (!buf) + return -EBADF; + + if (length != (unsigned long)buf->chan->alloc_size) + return -EINVAL; + + vma->vm_ops = &relay_file_mmap_ops; + vma->vm_flags |= VM_DONTEXPAND; + vma->vm_private_data = buf; + buf->chan->cb->buf_mapped(buf, filp); + + return 0; +} + +/** + * relay_alloc_buf - allocate a channel buffer + * @buf: the buffer struct + * @size: total size of the buffer + * + * Returns a pointer to the resulting buffer, %NULL if unsuccessful. The + * passed in size will get page aligned, if it isn't already. + */ +static void *relay_alloc_buf(struct rchan_buf *buf, size_t *size) +{ + void *mem; + unsigned int i, j, n_pages; + + *size = PAGE_ALIGN(*size); + n_pages = *size >> PAGE_SHIFT; + + buf->page_array = relay_alloc_page_array(n_pages); + if (!buf->page_array) + return NULL; + + for (i = 0; i < n_pages; i++) { + buf->page_array[i] = alloc_page(GFP_KERNEL); + if (unlikely(!buf->page_array[i])) + goto depopulate; + set_page_private(buf->page_array[i], (unsigned long)buf); + } + mem = vmap(buf->page_array, n_pages, VM_MAP, PAGE_KERNEL); + if (!mem) + goto depopulate; + + memset(mem, 0, *size); + buf->page_count = n_pages; + return mem; + +depopulate: + for (j = 0; j < i; j++) + __free_page(buf->page_array[j]); + relay_free_page_array(buf->page_array); + return NULL; +} + +/** + * relay_create_buf - allocate and initialize a channel buffer + * @chan: the relay channel + * + * Returns channel buffer if successful, %NULL otherwise. + */ +static struct rchan_buf *relay_create_buf(struct rchan *chan) +{ + struct rchan_buf *buf; + + if (chan->n_subbufs > UINT_MAX / sizeof(size_t *)) + return NULL; + + buf = kzalloc(sizeof(struct rchan_buf), GFP_KERNEL); + if (!buf) + return NULL; + buf->padding = kmalloc(chan->n_subbufs * sizeof(size_t *), GFP_KERNEL); + if (!buf->padding) + goto free_buf; + + buf->start = relay_alloc_buf(buf, &chan->alloc_size); + if (!buf->start) + goto free_buf; + + buf->chan = chan; + kref_get(&buf->chan->kref); + return buf; + +free_buf: + kfree(buf->padding); + kfree(buf); + return NULL; +} + +/** + * relay_destroy_channel - free the channel struct + * @kref: target kernel reference that contains the relay channel + * + * Should only be called from kref_put(). + */ +static void relay_destroy_channel(struct kref *kref) +{ + struct rchan *chan = container_of(kref, struct rchan, kref); + kfree(chan); +} + +/** + * relay_destroy_buf - destroy an rchan_buf struct and associated buffer + * @buf: the buffer struct + */ +static void relay_destroy_buf(struct rchan_buf *buf) +{ + struct rchan *chan = buf->chan; + unsigned int i; + + if (likely(buf->start)) { + vunmap(buf->start); + for (i = 0; i < buf->page_count; i++) + __free_page(buf->page_array[i]); + relay_free_page_array(buf->page_array); + } + chan->buf[buf->cpu] = NULL; + kfree(buf->padding); + kfree(buf); + kref_put(&chan->kref, relay_destroy_channel); +} + +/** + * relay_remove_buf - remove a channel buffer + * @kref: target kernel reference that contains the relay buffer + * + * Removes the file from the filesystem, which also frees the + * rchan_buf_struct and the channel buffer. Should only be called from + * kref_put(). + */ +static void relay_remove_buf(struct kref *kref) +{ + struct rchan_buf *buf = container_of(kref, struct rchan_buf, kref); + relay_destroy_buf(buf); +} + +/** + * relay_buf_empty - boolean, is the channel buffer empty? + * @buf: channel buffer + * + * Returns 1 if the buffer is empty, 0 otherwise. + */ +static int relay_buf_empty(struct rchan_buf *buf) +{ + return (buf->subbufs_produced - buf->subbufs_consumed) ? 0 : 1; +} + +/** + * relay_buf_full - boolean, is the channel buffer full? + * @buf: channel buffer + * + * Returns 1 if the buffer is full, 0 otherwise. + */ +int relay_buf_full(struct rchan_buf *buf) +{ + size_t ready = buf->subbufs_produced - buf->subbufs_consumed; + return (ready >= buf->chan->n_subbufs) ? 1 : 0; +} +EXPORT_SYMBOL_GPL(relay_buf_full); + +/* + * High-level relay kernel API and associated functions. + */ + +/* + * rchan_callback implementations defining default channel behavior. Used + * in place of corresponding NULL values in client callback struct. + */ + +/* + * subbuf_start() default callback. Does nothing. + */ +static int subbuf_start_default_callback (struct rchan_buf *buf, + void *subbuf, + void *prev_subbuf, + size_t prev_padding) +{ + if (relay_buf_full(buf)) + return 0; + + return 1; +} + +/* + * buf_mapped() default callback. Does nothing. + */ +static void buf_mapped_default_callback(struct rchan_buf *buf, + struct file *filp) +{ +} + +/* + * buf_unmapped() default callback. Does nothing. + */ +static void buf_unmapped_default_callback(struct rchan_buf *buf, + struct file *filp) +{ +} + +/* + * create_buf_file_create() default callback. Does nothing. + */ +static struct dentry *create_buf_file_default_callback(const char *filename, + struct dentry *parent, + umode_t mode, + struct rchan_buf *buf, + int *is_global) +{ + return NULL; +} + +/* + * remove_buf_file() default callback. Does nothing. + */ +static int remove_buf_file_default_callback(struct dentry *dentry) +{ + return -EINVAL; +} + +/* relay channel default callbacks */ +static struct rchan_callbacks default_channel_callbacks = { + .subbuf_start = subbuf_start_default_callback, + .buf_mapped = buf_mapped_default_callback, + .buf_unmapped = buf_unmapped_default_callback, + .create_buf_file = create_buf_file_default_callback, + .remove_buf_file = remove_buf_file_default_callback, +}; + +/** + * wakeup_readers - wake up readers waiting on a channel + * @data: contains the channel buffer + * + * This is the timer function used to defer reader waking. + */ +static void wakeup_readers(unsigned long data) +{ + struct rchan_buf *buf = (struct rchan_buf *)data; + wake_up_interruptible(&buf->read_wait); + /* + * Stupid polling for now: + */ + mod_timer(&buf->timer, jiffies + 1); +} + +/** + * __relay_reset - reset a channel buffer + * @buf: the channel buffer + * @init: 1 if this is a first-time initialization + * + * See relay_reset() for description of effect. + */ +static void __relay_reset(struct rchan_buf *buf, unsigned int init) +{ + size_t i; + + if (init) { + init_waitqueue_head(&buf->read_wait); + kref_init(&buf->kref); + setup_timer(&buf->timer, wakeup_readers, (unsigned long)buf); + mod_timer(&buf->timer, jiffies + 1); + } else + del_timer_sync(&buf->timer); + + buf->subbufs_produced = 0; + buf->subbufs_consumed = 0; + buf->bytes_consumed = 0; + buf->finalized = 0; + buf->data = buf->start; + buf->offset = 0; + + for (i = 0; i < buf->chan->n_subbufs; i++) + buf->padding[i] = 0; + + buf->chan->cb->subbuf_start(buf, buf->data, NULL, 0); +} + +/** + * relay_reset - reset the channel + * @chan: the channel + * + * This has the effect of erasing all data from all channel buffers + * and restarting the channel in its initial state. The buffers + * are not freed, so any mappings are still in effect. + * + * NOTE. Care should be taken that the channel isn't actually + * being used by anything when this call is made. + */ +void relay_reset(struct rchan *chan) +{ + unsigned int i; + + if (!chan) + return; + + if (chan->is_global && chan->buf[0]) { + __relay_reset(chan->buf[0], 0); + return; + } + + mutex_lock(&relay_channels_mutex); + for_each_possible_cpu(i) + if (chan->buf[i]) + __relay_reset(chan->buf[i], 0); + mutex_unlock(&relay_channels_mutex); +} +EXPORT_SYMBOL_GPL(relay_reset); + +static inline void relay_set_buf_dentry(struct rchan_buf *buf, + struct dentry *dentry) +{ + buf->dentry = dentry; + d_inode(buf->dentry)->i_size = buf->early_bytes; +} + +static struct dentry *relay_create_buf_file(struct rchan *chan, + struct rchan_buf *buf, + unsigned int cpu) +{ + struct dentry *dentry; + char *tmpname; + + tmpname = kzalloc(NAME_MAX + 1, GFP_KERNEL); + if (!tmpname) + return NULL; + snprintf(tmpname, NAME_MAX, "%s%d", chan->base_filename, cpu); + + /* Create file in fs */ + dentry = chan->cb->create_buf_file(tmpname, chan->parent, + S_IRUSR, buf, + &chan->is_global); + + kfree(tmpname); + + return dentry; +} + +/* + * relay_open_buf - create a new relay channel buffer + * + * used by relay_open() and CPU hotplug. + */ +static struct rchan_buf *relay_open_buf(struct rchan *chan, unsigned int cpu) +{ + struct rchan_buf *buf = NULL; + struct dentry *dentry; + + if (chan->is_global) + return chan->buf[0]; + + buf = relay_create_buf(chan); + if (!buf) + return NULL; + + if (chan->has_base_filename) { + dentry = relay_create_buf_file(chan, buf, cpu); + if (!dentry) + goto free_buf; + relay_set_buf_dentry(buf, dentry); + } + + buf->cpu = cpu; + __relay_reset(buf, 1); + + if(chan->is_global) { + chan->buf[0] = buf; + buf->cpu = 0; + } + + return buf; + +free_buf: + relay_destroy_buf(buf); + return NULL; +} + +/** + * relay_close_buf - close a channel buffer + * @buf: channel buffer + * + * Marks the buffer finalized and restores the default callbacks. + * The channel buffer and channel buffer data structure are then freed + * automatically when the last reference is given up. + */ +static void relay_close_buf(struct rchan_buf *buf) +{ + buf->finalized = 1; + del_timer_sync(&buf->timer); + buf->chan->cb->remove_buf_file(buf->dentry); + kref_put(&buf->kref, relay_remove_buf); +} + +static void setup_callbacks(struct rchan *chan, + struct rchan_callbacks *cb) +{ + if (!cb) { + chan->cb = &default_channel_callbacks; + return; + } + + if (!cb->subbuf_start) + cb->subbuf_start = subbuf_start_default_callback; + if (!cb->buf_mapped) + cb->buf_mapped = buf_mapped_default_callback; + if (!cb->buf_unmapped) + cb->buf_unmapped = buf_unmapped_default_callback; + if (!cb->create_buf_file) + cb->create_buf_file = create_buf_file_default_callback; + if (!cb->remove_buf_file) + cb->remove_buf_file = remove_buf_file_default_callback; + chan->cb = cb; +} + +/** + * relay_hotcpu_callback - CPU hotplug callback + * @nb: notifier block + * @action: hotplug action to take + * @hcpu: CPU number + * + * Returns the success/failure of the operation. (%NOTIFY_OK, %NOTIFY_BAD) + */ +static int relay_hotcpu_callback(struct notifier_block *nb, + unsigned long action, + void *hcpu) +{ + unsigned int hotcpu = (unsigned long)hcpu; + struct rchan *chan; + + switch(action) { + case CPU_UP_PREPARE: + case CPU_UP_PREPARE_FROZEN: + mutex_lock(&relay_channels_mutex); + list_for_each_entry(chan, &relay_channels, list) { + if (chan->buf[hotcpu]) + continue; + chan->buf[hotcpu] = relay_open_buf(chan, hotcpu); + if(!chan->buf[hotcpu]) { + printk(KERN_ERR + "relay_hotcpu_callback: cpu %d buffer " + "creation failed\n", hotcpu); + mutex_unlock(&relay_channels_mutex); + return notifier_from_errno(-ENOMEM); + } + } + mutex_unlock(&relay_channels_mutex); + break; + case CPU_DEAD: + case CPU_DEAD_FROZEN: + /* No need to flush the cpu : will be flushed upon + * final relay_flush() call. */ + break; + } + return NOTIFY_OK; +} + +/** + * relay_open - create a new relay channel + * @base_filename: base name of files to create, %NULL for buffering only + * @parent: dentry of parent directory, %NULL for root directory or buffer + * @subbuf_size: size of sub-buffers + * @n_subbufs: number of sub-buffers + * @cb: client callback functions + * @private_data: user-defined data + * + * Returns channel pointer if successful, %NULL otherwise. + * + * Creates a channel buffer for each cpu using the sizes and + * attributes specified. The created channel buffer files + * will be named base_filename0...base_filenameN-1. File + * permissions will be %S_IRUSR. + */ +struct rchan *relay_open(const char *base_filename, + struct dentry *parent, + size_t subbuf_size, + size_t n_subbufs, + struct rchan_callbacks *cb, + void *private_data) +{ + unsigned int i; + struct rchan *chan; + + if (!(subbuf_size && n_subbufs)) + return NULL; + if (subbuf_size > UINT_MAX / n_subbufs) + return NULL; + + chan = kzalloc(sizeof(struct rchan), GFP_KERNEL); + if (!chan) + return NULL; + + chan->version = RELAYFS_CHANNEL_VERSION; + chan->n_subbufs = n_subbufs; + chan->subbuf_size = subbuf_size; + chan->alloc_size = PAGE_ALIGN(subbuf_size * n_subbufs); + chan->parent = parent; + chan->private_data = private_data; + if (base_filename) { + chan->has_base_filename = 1; + strlcpy(chan->base_filename, base_filename, NAME_MAX); + } + setup_callbacks(chan, cb); + kref_init(&chan->kref); + + mutex_lock(&relay_channels_mutex); + for_each_online_cpu(i) { + chan->buf[i] = relay_open_buf(chan, i); + if (!chan->buf[i]) + goto free_bufs; + } + list_add(&chan->list, &relay_channels); + mutex_unlock(&relay_channels_mutex); + + return chan; + +free_bufs: + for_each_possible_cpu(i) { + if (chan->buf[i]) + relay_close_buf(chan->buf[i]); + } + + kref_put(&chan->kref, relay_destroy_channel); + mutex_unlock(&relay_channels_mutex); + return NULL; +} +EXPORT_SYMBOL_GPL(relay_open); + +struct rchan_percpu_buf_dispatcher { + struct rchan_buf *buf; + struct dentry *dentry; +}; + +/* Called in atomic context. */ +static void __relay_set_buf_dentry(void *info) +{ + struct rchan_percpu_buf_dispatcher *p = info; + + relay_set_buf_dentry(p->buf, p->dentry); +} + +/** + * relay_late_setup_files - triggers file creation + * @chan: channel to operate on + * @base_filename: base name of files to create + * @parent: dentry of parent directory, %NULL for root directory + * + * Returns 0 if successful, non-zero otherwise. + * + * Use to setup files for a previously buffer-only channel. + * Useful to do early tracing in kernel, before VFS is up, for example. + */ +int relay_late_setup_files(struct rchan *chan, + const char *base_filename, + struct dentry *parent) +{ + int err = 0; + unsigned int i, curr_cpu; + unsigned long flags; + struct dentry *dentry; + struct rchan_percpu_buf_dispatcher disp; + + if (!chan || !base_filename) + return -EINVAL; + + strlcpy(chan->base_filename, base_filename, NAME_MAX); + + mutex_lock(&relay_channels_mutex); + /* Is chan already set up? */ + if (unlikely(chan->has_base_filename)) { + mutex_unlock(&relay_channels_mutex); + return -EEXIST; + } + chan->has_base_filename = 1; + chan->parent = parent; + curr_cpu = get_cpu(); + /* + * The CPU hotplug notifier ran before us and created buffers with + * no files associated. So it's safe to call relay_setup_buf_file() + * on all currently online CPUs. + */ + for_each_online_cpu(i) { + if (unlikely(!chan->buf[i])) { + WARN_ONCE(1, KERN_ERR "CPU has no buffer!\n"); + err = -EINVAL; + break; + } + + dentry = relay_create_buf_file(chan, chan->buf[i], i); + if (unlikely(!dentry)) { + err = -EINVAL; + break; + } + + if (curr_cpu == i) { + local_irq_save(flags); + relay_set_buf_dentry(chan->buf[i], dentry); + local_irq_restore(flags); + } else { + disp.buf = chan->buf[i]; + disp.dentry = dentry; + smp_mb(); + /* relay_channels_mutex must be held, so wait. */ + err = smp_call_function_single(i, + __relay_set_buf_dentry, + &disp, 1); + } + if (unlikely(err)) + break; + } + put_cpu(); + mutex_unlock(&relay_channels_mutex); + + return err; +} + +/** + * relay_switch_subbuf - switch to a new sub-buffer + * @buf: channel buffer + * @length: size of current event + * + * Returns either the length passed in or 0 if full. + * + * Performs sub-buffer-switch tasks such as invoking callbacks, + * updating padding counts, waking up readers, etc. + */ +size_t relay_switch_subbuf(struct rchan_buf *buf, size_t length) +{ + void *old, *new; + size_t old_subbuf, new_subbuf; + + if (unlikely(length > buf->chan->subbuf_size)) + goto toobig; + + if (buf->offset != buf->chan->subbuf_size + 1) { + buf->prev_padding = buf->chan->subbuf_size - buf->offset; + old_subbuf = buf->subbufs_produced % buf->chan->n_subbufs; + buf->padding[old_subbuf] = buf->prev_padding; + buf->subbufs_produced++; + if (buf->dentry) + d_inode(buf->dentry)->i_size += + buf->chan->subbuf_size - + buf->padding[old_subbuf]; + else + buf->early_bytes += buf->chan->subbuf_size - + buf->padding[old_subbuf]; + } + + old = buf->data; + new_subbuf = buf->subbufs_produced % buf->chan->n_subbufs; + new = buf->start + new_subbuf * buf->chan->subbuf_size; + buf->offset = 0; + if (!buf->chan->cb->subbuf_start(buf, new, old, buf->prev_padding)) { + buf->offset = buf->chan->subbuf_size + 1; + return 0; + } + buf->data = new; + buf->padding[new_subbuf] = 0; + + if (unlikely(length + buf->offset > buf->chan->subbuf_size)) + goto toobig; + + return length; + +toobig: + buf->chan->last_toobig = length; + return 0; +} +EXPORT_SYMBOL_GPL(relay_switch_subbuf); + +/** + * relay_subbufs_consumed - update the buffer's sub-buffers-consumed count + * @chan: the channel + * @cpu: the cpu associated with the channel buffer to update + * @subbufs_consumed: number of sub-buffers to add to current buf's count + * + * Adds to the channel buffer's consumed sub-buffer count. + * subbufs_consumed should be the number of sub-buffers newly consumed, + * not the total consumed. + * + * NOTE. Kernel clients don't need to call this function if the channel + * mode is 'overwrite'. + */ +void relay_subbufs_consumed(struct rchan *chan, + unsigned int cpu, + size_t subbufs_consumed) +{ + struct rchan_buf *buf; + + if (!chan) + return; + + if (cpu >= NR_CPUS || !chan->buf[cpu] || + subbufs_consumed > chan->n_subbufs) + return; + + buf = chan->buf[cpu]; + if (subbufs_consumed > buf->subbufs_produced - buf->subbufs_consumed) + buf->subbufs_consumed = buf->subbufs_produced; + else + buf->subbufs_consumed += subbufs_consumed; +} +EXPORT_SYMBOL_GPL(relay_subbufs_consumed); + +/** + * relay_close - close the channel + * @chan: the channel + * + * Closes all channel buffers and frees the channel. + */ +void relay_close(struct rchan *chan) +{ + unsigned int i; + + if (!chan) + return; + + mutex_lock(&relay_channels_mutex); + if (chan->is_global && chan->buf[0]) + relay_close_buf(chan->buf[0]); + else + for_each_possible_cpu(i) + if (chan->buf[i]) + relay_close_buf(chan->buf[i]); + + if (chan->last_toobig) + printk(KERN_WARNING "relay: one or more items not logged " + "[item size (%Zd) > sub-buffer size (%Zd)]\n", + chan->last_toobig, chan->subbuf_size); + + list_del(&chan->list); + kref_put(&chan->kref, relay_destroy_channel); + mutex_unlock(&relay_channels_mutex); +} +EXPORT_SYMBOL_GPL(relay_close); + +/** + * relay_flush - close the channel + * @chan: the channel + * + * Flushes all channel buffers, i.e. forces buffer switch. + */ +void relay_flush(struct rchan *chan) +{ + unsigned int i; + + if (!chan) + return; + + if (chan->is_global && chan->buf[0]) { + relay_switch_subbuf(chan->buf[0], 0); + return; + } + + mutex_lock(&relay_channels_mutex); + for_each_possible_cpu(i) + if (chan->buf[i]) + relay_switch_subbuf(chan->buf[i], 0); + mutex_unlock(&relay_channels_mutex); +} +EXPORT_SYMBOL_GPL(relay_flush); + +/** + * relay_file_open - open file op for relay files + * @inode: the inode + * @filp: the file + * + * Increments the channel buffer refcount. + */ +static int relay_file_open(struct inode *inode, struct file *filp) +{ + struct rchan_buf *buf = inode->i_private; + kref_get(&buf->kref); + filp->private_data = buf; + + return nonseekable_open(inode, filp); +} + +/** + * relay_file_mmap - mmap file op for relay files + * @filp: the file + * @vma: the vma describing what to map + * + * Calls upon relay_mmap_buf() to map the file into user space. + */ +static int relay_file_mmap(struct file *filp, struct vm_area_struct *vma) +{ + struct rchan_buf *buf = filp->private_data; + return relay_mmap_buf(buf, vma); +} + +/** + * relay_file_poll - poll file op for relay files + * @filp: the file + * @wait: poll table + * + * Poll implemention. + */ +static unsigned int relay_file_poll(struct file *filp, poll_table *wait) +{ + unsigned int mask = 0; + struct rchan_buf *buf = filp->private_data; + + if (buf->finalized) + return POLLERR; + + if (filp->f_mode & FMODE_READ) { + poll_wait(filp, &buf->read_wait, wait); + if (!relay_buf_empty(buf)) + mask |= POLLIN | POLLRDNORM; + } + + return mask; +} + +/** + * relay_file_release - release file op for relay files + * @inode: the inode + * @filp: the file + * + * Decrements the channel refcount, as the filesystem is + * no longer using it. + */ +static int relay_file_release(struct inode *inode, struct file *filp) +{ + struct rchan_buf *buf = filp->private_data; + kref_put(&buf->kref, relay_remove_buf); + + return 0; +} + +/* + * relay_file_read_consume - update the consumed count for the buffer + */ +static void relay_file_read_consume(struct rchan_buf *buf, + size_t read_pos, + size_t bytes_consumed) +{ + size_t subbuf_size = buf->chan->subbuf_size; + size_t n_subbufs = buf->chan->n_subbufs; + size_t read_subbuf; + + if (buf->subbufs_produced == buf->subbufs_consumed && + buf->offset == buf->bytes_consumed) + return; + + if (buf->bytes_consumed + bytes_consumed > subbuf_size) { + relay_subbufs_consumed(buf->chan, buf->cpu, 1); + buf->bytes_consumed = 0; + } + + buf->bytes_consumed += bytes_consumed; + if (!read_pos) + read_subbuf = buf->subbufs_consumed % n_subbufs; + else + read_subbuf = read_pos / buf->chan->subbuf_size; + if (buf->bytes_consumed + buf->padding[read_subbuf] == subbuf_size) { + if ((read_subbuf == buf->subbufs_produced % n_subbufs) && + (buf->offset == subbuf_size)) + return; + relay_subbufs_consumed(buf->chan, buf->cpu, 1); + buf->bytes_consumed = 0; + } +} + +/* + * relay_file_read_avail - boolean, are there unconsumed bytes available? + */ +static int relay_file_read_avail(struct rchan_buf *buf, size_t read_pos) +{ + size_t subbuf_size = buf->chan->subbuf_size; + size_t n_subbufs = buf->chan->n_subbufs; + size_t produced = buf->subbufs_produced; + size_t consumed = buf->subbufs_consumed; + + relay_file_read_consume(buf, read_pos, 0); + + consumed = buf->subbufs_consumed; + + if (unlikely(buf->offset > subbuf_size)) { + if (produced == consumed) + return 0; + return 1; + } + + if (unlikely(produced - consumed >= n_subbufs)) { + consumed = produced - n_subbufs + 1; + buf->subbufs_consumed = consumed; + buf->bytes_consumed = 0; + } + + produced = (produced % n_subbufs) * subbuf_size + buf->offset; + consumed = (consumed % n_subbufs) * subbuf_size + buf->bytes_consumed; + + if (consumed > produced) + produced += n_subbufs * subbuf_size; + + if (consumed == produced) { + if (buf->offset == subbuf_size && + buf->subbufs_produced > buf->subbufs_consumed) + return 1; + return 0; + } + + return 1; +} + +/** + * relay_file_read_subbuf_avail - return bytes available in sub-buffer + * @read_pos: file read position + * @buf: relay channel buffer + */ +static size_t relay_file_read_subbuf_avail(size_t read_pos, + struct rchan_buf *buf) +{ + size_t padding, avail = 0; + size_t read_subbuf, read_offset, write_subbuf, write_offset; + size_t subbuf_size = buf->chan->subbuf_size; + + write_subbuf = (buf->data - buf->start) / subbuf_size; + write_offset = buf->offset > subbuf_size ? subbuf_size : buf->offset; + read_subbuf = read_pos / subbuf_size; + read_offset = read_pos % subbuf_size; + padding = buf->padding[read_subbuf]; + + if (read_subbuf == write_subbuf) { + if (read_offset + padding < write_offset) + avail = write_offset - (read_offset + padding); + } else + avail = (subbuf_size - padding) - read_offset; + + return avail; +} + +/** + * relay_file_read_start_pos - find the first available byte to read + * @read_pos: file read position + * @buf: relay channel buffer + * + * If the @read_pos is in the middle of padding, return the + * position of the first actually available byte, otherwise + * return the original value. + */ +static size_t relay_file_read_start_pos(size_t read_pos, + struct rchan_buf *buf) +{ + size_t read_subbuf, padding, padding_start, padding_end; + size_t subbuf_size = buf->chan->subbuf_size; + size_t n_subbufs = buf->chan->n_subbufs; + size_t consumed = buf->subbufs_consumed % n_subbufs; + + if (!read_pos) + read_pos = consumed * subbuf_size + buf->bytes_consumed; + read_subbuf = read_pos / subbuf_size; + padding = buf->padding[read_subbuf]; + padding_start = (read_subbuf + 1) * subbuf_size - padding; + padding_end = (read_subbuf + 1) * subbuf_size; + if (read_pos >= padding_start && read_pos < padding_end) { + read_subbuf = (read_subbuf + 1) % n_subbufs; + read_pos = read_subbuf * subbuf_size; + } + + return read_pos; +} + +/** + * relay_file_read_end_pos - return the new read position + * @read_pos: file read position + * @buf: relay channel buffer + * @count: number of bytes to be read + */ +static size_t relay_file_read_end_pos(struct rchan_buf *buf, + size_t read_pos, + size_t count) +{ + size_t read_subbuf, padding, end_pos; + size_t subbuf_size = buf->chan->subbuf_size; + size_t n_subbufs = buf->chan->n_subbufs; + + read_subbuf = read_pos / subbuf_size; + padding = buf->padding[read_subbuf]; + if (read_pos % subbuf_size + count + padding == subbuf_size) + end_pos = (read_subbuf + 1) * subbuf_size; + else + end_pos = read_pos + count; + if (end_pos >= subbuf_size * n_subbufs) + end_pos = 0; + + return end_pos; +} + +/* + * subbuf_read_actor - read up to one subbuf's worth of data + */ +static int subbuf_read_actor(size_t read_start, + struct rchan_buf *buf, + size_t avail, + read_descriptor_t *desc) +{ + void *from; + int ret = 0; + + from = buf->start + read_start; + ret = avail; + if (copy_to_user(desc->arg.buf, from, avail)) { + desc->error = -EFAULT; + ret = 0; + } + desc->arg.data += ret; + desc->written += ret; + desc->count -= ret; + + return ret; +} + +typedef int (*subbuf_actor_t) (size_t read_start, + struct rchan_buf *buf, + size_t avail, + read_descriptor_t *desc); + +/* + * relay_file_read_subbufs - read count bytes, bridging subbuf boundaries + */ +static ssize_t relay_file_read_subbufs(struct file *filp, loff_t *ppos, + subbuf_actor_t subbuf_actor, + read_descriptor_t *desc) +{ + struct rchan_buf *buf = filp->private_data; + size_t read_start, avail; + int ret; + + if (!desc->count) + return 0; + + mutex_lock(&file_inode(filp)->i_mutex); + do { + if (!relay_file_read_avail(buf, *ppos)) + break; + + read_start = relay_file_read_start_pos(*ppos, buf); + avail = relay_file_read_subbuf_avail(read_start, buf); + if (!avail) + break; + + avail = min(desc->count, avail); + ret = subbuf_actor(read_start, buf, avail, desc); + if (desc->error < 0) + break; + + if (ret) { + relay_file_read_consume(buf, read_start, ret); + *ppos = relay_file_read_end_pos(buf, read_start, ret); + } + } while (desc->count && ret); + mutex_unlock(&file_inode(filp)->i_mutex); + + return desc->written; +} + +static ssize_t relay_file_read(struct file *filp, + char __user *buffer, + size_t count, + loff_t *ppos) +{ + read_descriptor_t desc; + desc.written = 0; + desc.count = count; + desc.arg.buf = buffer; + desc.error = 0; + return relay_file_read_subbufs(filp, ppos, subbuf_read_actor, &desc); +} + +static void relay_consume_bytes(struct rchan_buf *rbuf, int bytes_consumed) +{ + rbuf->bytes_consumed += bytes_consumed; + + if (rbuf->bytes_consumed >= rbuf->chan->subbuf_size) { + relay_subbufs_consumed(rbuf->chan, rbuf->cpu, 1); + rbuf->bytes_consumed %= rbuf->chan->subbuf_size; + } +} + +static void relay_pipe_buf_release(struct pipe_inode_info *pipe, + struct pipe_buffer *buf) +{ + struct rchan_buf *rbuf; + + rbuf = (struct rchan_buf *)page_private(buf->page); + relay_consume_bytes(rbuf, buf->private); +} + +static const struct pipe_buf_operations relay_pipe_buf_ops = { + .can_merge = 0, + .confirm = generic_pipe_buf_confirm, + .release = relay_pipe_buf_release, + .steal = generic_pipe_buf_steal, + .get = generic_pipe_buf_get, +}; + +static void relay_page_release(struct splice_pipe_desc *spd, unsigned int i) +{ +} + +/* + * subbuf_splice_actor - splice up to one subbuf's worth of data + */ +static ssize_t subbuf_splice_actor(struct file *in, + loff_t *ppos, + struct pipe_inode_info *pipe, + size_t len, + unsigned int flags, + int *nonpad_ret) +{ + unsigned int pidx, poff, total_len, subbuf_pages, nr_pages; + struct rchan_buf *rbuf = in->private_data; + unsigned int subbuf_size = rbuf->chan->subbuf_size; + uint64_t pos = (uint64_t) *ppos; + uint32_t alloc_size = (uint32_t) rbuf->chan->alloc_size; + size_t read_start = (size_t) do_div(pos, alloc_size); + size_t read_subbuf = read_start / subbuf_size; + size_t padding = rbuf->padding[read_subbuf]; + size_t nonpad_end = read_subbuf * subbuf_size + subbuf_size - padding; + struct page *pages[PIPE_DEF_BUFFERS]; + struct partial_page partial[PIPE_DEF_BUFFERS]; + struct splice_pipe_desc spd = { + .pages = pages, + .nr_pages = 0, + .nr_pages_max = PIPE_DEF_BUFFERS, + .partial = partial, + .flags = flags, + .ops = &relay_pipe_buf_ops, + .spd_release = relay_page_release, + }; + ssize_t ret; + + if (rbuf->subbufs_produced == rbuf->subbufs_consumed) + return 0; + if (splice_grow_spd(pipe, &spd)) + return -ENOMEM; + + /* + * Adjust read len, if longer than what is available + */ + if (len > (subbuf_size - read_start % subbuf_size)) + len = subbuf_size - read_start % subbuf_size; + + subbuf_pages = rbuf->chan->alloc_size >> PAGE_SHIFT; + pidx = (read_start / PAGE_SIZE) % subbuf_pages; + poff = read_start & ~PAGE_MASK; + nr_pages = min_t(unsigned int, subbuf_pages, spd.nr_pages_max); + + for (total_len = 0; spd.nr_pages < nr_pages; spd.nr_pages++) { + unsigned int this_len, this_end, private; + unsigned int cur_pos = read_start + total_len; + + if (!len) + break; + + this_len = min_t(unsigned long, len, PAGE_SIZE - poff); + private = this_len; + + spd.pages[spd.nr_pages] = rbuf->page_array[pidx]; + spd.partial[spd.nr_pages].offset = poff; + + this_end = cur_pos + this_len; + if (this_end >= nonpad_end) { + this_len = nonpad_end - cur_pos; + private = this_len + padding; + } + spd.partial[spd.nr_pages].len = this_len; + spd.partial[spd.nr_pages].private = private; + + len -= this_len; + total_len += this_len; + poff = 0; + pidx = (pidx + 1) % subbuf_pages; + + if (this_end >= nonpad_end) { + spd.nr_pages++; + break; + } + } + + ret = 0; + if (!spd.nr_pages) + goto out; + + ret = *nonpad_ret = splice_to_pipe(pipe, &spd); + if (ret < 0 || ret < total_len) + goto out; + + if (read_start + ret == nonpad_end) + ret += padding; + +out: + splice_shrink_spd(&spd); + return ret; +} + +static ssize_t relay_file_splice_read(struct file *in, + loff_t *ppos, + struct pipe_inode_info *pipe, + size_t len, + unsigned int flags) +{ + ssize_t spliced; + int ret; + int nonpad_ret = 0; + + ret = 0; + spliced = 0; + + while (len && !spliced) { + ret = subbuf_splice_actor(in, ppos, pipe, len, flags, &nonpad_ret); + if (ret < 0) + break; + else if (!ret) { + if (flags & SPLICE_F_NONBLOCK) + ret = -EAGAIN; + break; + } + + *ppos += ret; + if (ret > len) + len = 0; + else + len -= ret; + spliced += nonpad_ret; + nonpad_ret = 0; + } + + if (spliced) + return spliced; + + return ret; +} + +const struct file_operations relay_file_operations = { + .open = relay_file_open, + .poll = relay_file_poll, + .mmap = relay_file_mmap, + .read = relay_file_read, + .llseek = no_llseek, + .release = relay_file_release, + .splice_read = relay_file_splice_read, +}; +EXPORT_SYMBOL_GPL(relay_file_operations); + +static __init int relay_init(void) +{ + + hotcpu_notifier(relay_hotcpu_callback, 0); + return 0; +} + +early_initcall(relay_init); diff --git a/kernel/kernel/resource.c b/kernel/kernel/resource.c new file mode 100644 index 000000000..90552aab5 --- /dev/null +++ b/kernel/kernel/resource.c @@ -0,0 +1,1534 @@ +/* + * linux/kernel/resource.c + * + * Copyright (C) 1999 Linus Torvalds + * Copyright (C) 1999 Martin Mares + * + * Arbitrary resource management. + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + +struct resource ioport_resource = { + .name = "PCI IO", + .start = 0, + .end = IO_SPACE_LIMIT, + .flags = IORESOURCE_IO, +}; +EXPORT_SYMBOL(ioport_resource); + +struct resource iomem_resource = { + .name = "PCI mem", + .start = 0, + .end = -1, + .flags = IORESOURCE_MEM, +}; +EXPORT_SYMBOL(iomem_resource); + +/* constraints to be met while allocating resources */ +struct resource_constraint { + resource_size_t min, max, align; + resource_size_t (*alignf)(void *, const struct resource *, + resource_size_t, resource_size_t); + void *alignf_data; +}; + +static DEFINE_RWLOCK(resource_lock); + +/* + * For memory hotplug, there is no way to free resource entries allocated + * by boot mem after the system is up. So for reusing the resource entry + * we need to remember the resource. + */ +static struct resource *bootmem_resource_free; +static DEFINE_SPINLOCK(bootmem_resource_lock); + +static struct resource *next_resource(struct resource *p, bool sibling_only) +{ + /* Caller wants to traverse through siblings only */ + if (sibling_only) + return p->sibling; + + if (p->child) + return p->child; + while (!p->sibling && p->parent) + p = p->parent; + return p->sibling; +} + +static void *r_next(struct seq_file *m, void *v, loff_t *pos) +{ + struct resource *p = v; + (*pos)++; + return (void *)next_resource(p, false); +} + +#ifdef CONFIG_PROC_FS + +enum { MAX_IORES_LEVEL = 5 }; + +static void *r_start(struct seq_file *m, loff_t *pos) + __acquires(resource_lock) +{ + struct resource *p = m->private; + loff_t l = 0; + read_lock(&resource_lock); + for (p = p->child; p && l < *pos; p = r_next(m, p, &l)) + ; + return p; +} + +static void r_stop(struct seq_file *m, void *v) + __releases(resource_lock) +{ + read_unlock(&resource_lock); +} + +static int r_show(struct seq_file *m, void *v) +{ + struct resource *root = m->private; + struct resource *r = v, *p; + int width = root->end < 0x10000 ? 4 : 8; + int depth; + + for (depth = 0, p = r; depth < MAX_IORES_LEVEL; depth++, p = p->parent) + if (p->parent == root) + break; + seq_printf(m, "%*s%0*llx-%0*llx : %s\n", + depth * 2, "", + width, (unsigned long long) r->start, + width, (unsigned long long) r->end, + r->name ? r->name : ""); + return 0; +} + +static const struct seq_operations resource_op = { + .start = r_start, + .next = r_next, + .stop = r_stop, + .show = r_show, +}; + +static int ioports_open(struct inode *inode, struct file *file) +{ + int res = seq_open(file, &resource_op); + if (!res) { + struct seq_file *m = file->private_data; + m->private = &ioport_resource; + } + return res; +} + +static int iomem_open(struct inode *inode, struct file *file) +{ + int res = seq_open(file, &resource_op); + if (!res) { + struct seq_file *m = file->private_data; + m->private = &iomem_resource; + } + return res; +} + +static const struct file_operations proc_ioports_operations = { + .open = ioports_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, +}; + +static const struct file_operations proc_iomem_operations = { + .open = iomem_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, +}; + +static int __init ioresources_init(void) +{ + proc_create("ioports", 0, NULL, &proc_ioports_operations); + proc_create("iomem", 0, NULL, &proc_iomem_operations); + return 0; +} +__initcall(ioresources_init); + +#endif /* CONFIG_PROC_FS */ + +static void free_resource(struct resource *res) +{ + if (!res) + return; + + if (!PageSlab(virt_to_head_page(res))) { + spin_lock(&bootmem_resource_lock); + res->sibling = bootmem_resource_free; + bootmem_resource_free = res; + spin_unlock(&bootmem_resource_lock); + } else { + kfree(res); + } +} + +static struct resource *alloc_resource(gfp_t flags) +{ + struct resource *res = NULL; + + spin_lock(&bootmem_resource_lock); + if (bootmem_resource_free) { + res = bootmem_resource_free; + bootmem_resource_free = res->sibling; + } + spin_unlock(&bootmem_resource_lock); + + if (res) + memset(res, 0, sizeof(struct resource)); + else + res = kzalloc(sizeof(struct resource), flags); + + return res; +} + +/* Return the conflict entry if you can't request it */ +static struct resource * __request_resource(struct resource *root, struct resource *new) +{ + resource_size_t start = new->start; + resource_size_t end = new->end; + struct resource *tmp, **p; + + if (end < start) + return root; + if (start < root->start) + return root; + if (end > root->end) + return root; + p = &root->child; + for (;;) { + tmp = *p; + if (!tmp || tmp->start > end) { + new->sibling = tmp; + *p = new; + new->parent = root; + return NULL; + } + p = &tmp->sibling; + if (tmp->end < start) + continue; + return tmp; + } +} + +static int __release_resource(struct resource *old) +{ + struct resource *tmp, **p; + + p = &old->parent->child; + for (;;) { + tmp = *p; + if (!tmp) + break; + if (tmp == old) { + *p = tmp->sibling; + old->parent = NULL; + return 0; + } + p = &tmp->sibling; + } + return -EINVAL; +} + +static void __release_child_resources(struct resource *r) +{ + struct resource *tmp, *p; + resource_size_t size; + + p = r->child; + r->child = NULL; + while (p) { + tmp = p; + p = p->sibling; + + tmp->parent = NULL; + tmp->sibling = NULL; + __release_child_resources(tmp); + + printk(KERN_DEBUG "release child resource %pR\n", tmp); + /* need to restore size, and keep flags */ + size = resource_size(tmp); + tmp->start = 0; + tmp->end = size - 1; + } +} + +void release_child_resources(struct resource *r) +{ + write_lock(&resource_lock); + __release_child_resources(r); + write_unlock(&resource_lock); +} + +/** + * request_resource_conflict - request and reserve an I/O or memory resource + * @root: root resource descriptor + * @new: resource descriptor desired by caller + * + * Returns 0 for success, conflict resource on error. + */ +struct resource *request_resource_conflict(struct resource *root, struct resource *new) +{ + struct resource *conflict; + + write_lock(&resource_lock); + conflict = __request_resource(root, new); + write_unlock(&resource_lock); + return conflict; +} + +/** + * request_resource - request and reserve an I/O or memory resource + * @root: root resource descriptor + * @new: resource descriptor desired by caller + * + * Returns 0 for success, negative error code on error. + */ +int request_resource(struct resource *root, struct resource *new) +{ + struct resource *conflict; + + conflict = request_resource_conflict(root, new); + return conflict ? -EBUSY : 0; +} + +EXPORT_SYMBOL(request_resource); + +/** + * release_resource - release a previously reserved resource + * @old: resource pointer + */ +int release_resource(struct resource *old) +{ + int retval; + + write_lock(&resource_lock); + retval = __release_resource(old); + write_unlock(&resource_lock); + return retval; +} + +EXPORT_SYMBOL(release_resource); + +/* + * Finds the lowest iomem reosurce exists with-in [res->start.res->end) + * the caller must specify res->start, res->end, res->flags and "name". + * If found, returns 0, res is overwritten, if not found, returns -1. + * This walks through whole tree and not just first level children + * until and unless first_level_children_only is true. + */ +static int find_next_iomem_res(struct resource *res, char *name, + bool first_level_children_only) +{ + resource_size_t start, end; + struct resource *p; + bool sibling_only = false; + + BUG_ON(!res); + + start = res->start; + end = res->end; + BUG_ON(start >= end); + + if (first_level_children_only) + sibling_only = true; + + read_lock(&resource_lock); + + for (p = iomem_resource.child; p; p = next_resource(p, sibling_only)) { + if (p->flags != res->flags) + continue; + if (name && strcmp(p->name, name)) + continue; + if (p->start > end) { + p = NULL; + break; + } + if ((p->end >= start) && (p->start < end)) + break; + } + + read_unlock(&resource_lock); + if (!p) + return -1; + /* copy data */ + if (res->start < p->start) + res->start = p->start; + if (res->end > p->end) + res->end = p->end; + return 0; +} + +/* + * Walks through iomem resources and calls func() with matching resource + * ranges. This walks through whole tree and not just first level children. + * All the memory ranges which overlap start,end and also match flags and + * name are valid candidates. + * + * @name: name of resource + * @flags: resource flags + * @start: start addr + * @end: end addr + */ +int walk_iomem_res(char *name, unsigned long flags, u64 start, u64 end, + void *arg, int (*func)(u64, u64, void *)) +{ + struct resource res; + u64 orig_end; + int ret = -1; + + res.start = start; + res.end = end; + res.flags = flags; + orig_end = res.end; + while ((res.start < res.end) && + (!find_next_iomem_res(&res, name, false))) { + ret = (*func)(res.start, res.end, arg); + if (ret) + break; + res.start = res.end + 1; + res.end = orig_end; + } + return ret; +} + +/* + * This function calls callback against all memory range of "System RAM" + * which are marked as IORESOURCE_MEM and IORESOUCE_BUSY. + * Now, this function is only for "System RAM". This function deals with + * full ranges and not pfn. If resources are not pfn aligned, dealing + * with pfn can truncate ranges. + */ +int walk_system_ram_res(u64 start, u64 end, void *arg, + int (*func)(u64, u64, void *)) +{ + struct resource res; + u64 orig_end; + int ret = -1; + + res.start = start; + res.end = end; + res.flags = IORESOURCE_MEM | IORESOURCE_BUSY; + orig_end = res.end; + while ((res.start < res.end) && + (!find_next_iomem_res(&res, "System RAM", true))) { + ret = (*func)(res.start, res.end, arg); + if (ret) + break; + res.start = res.end + 1; + res.end = orig_end; + } + return ret; +} + +#if !defined(CONFIG_ARCH_HAS_WALK_MEMORY) + +/* + * This function calls callback against all memory range of "System RAM" + * which are marked as IORESOURCE_MEM and IORESOUCE_BUSY. + * Now, this function is only for "System RAM". + */ +int walk_system_ram_range(unsigned long start_pfn, unsigned long nr_pages, + void *arg, int (*func)(unsigned long, unsigned long, void *)) +{ + struct resource res; + unsigned long pfn, end_pfn; + u64 orig_end; + int ret = -1; + + res.start = (u64) start_pfn << PAGE_SHIFT; + res.end = ((u64)(start_pfn + nr_pages) << PAGE_SHIFT) - 1; + res.flags = IORESOURCE_MEM | IORESOURCE_BUSY; + orig_end = res.end; + while ((res.start < res.end) && + (find_next_iomem_res(&res, "System RAM", true) >= 0)) { + pfn = (res.start + PAGE_SIZE - 1) >> PAGE_SHIFT; + end_pfn = (res.end + 1) >> PAGE_SHIFT; + if (end_pfn > pfn) + ret = (*func)(pfn, end_pfn - pfn, arg); + if (ret) + break; + res.start = res.end + 1; + res.end = orig_end; + } + return ret; +} + +#endif + +static int __is_ram(unsigned long pfn, unsigned long nr_pages, void *arg) +{ + return 1; +} +/* + * This generic page_is_ram() returns true if specified address is + * registered as "System RAM" in iomem_resource list. + */ +int __weak page_is_ram(unsigned long pfn) +{ + return walk_system_ram_range(pfn, 1, NULL, __is_ram) == 1; +} +EXPORT_SYMBOL_GPL(page_is_ram); + +/* + * Search for a resouce entry that fully contains the specified region. + * If found, return 1 if it is RAM, 0 if not. + * If not found, or region is not fully contained, return -1 + * + * Used by the ioremap functions to ensure the user is not remapping RAM and is + * a vast speed up over walking through the resource table page by page. + */ +int region_is_ram(resource_size_t start, unsigned long size) +{ + struct resource *p; + resource_size_t end = start + size - 1; + int flags = IORESOURCE_MEM | IORESOURCE_BUSY; + const char *name = "System RAM"; + int ret = -1; + + read_lock(&resource_lock); + for (p = iomem_resource.child; p ; p = p->sibling) { + if (end < p->start) + continue; + + if (p->start <= start && end <= p->end) { + /* resource fully contains region */ + if ((p->flags != flags) || strcmp(p->name, name)) + ret = 0; + else + ret = 1; + break; + } + if (p->end < start) + break; /* not found */ + } + read_unlock(&resource_lock); + return ret; +} + +void __weak arch_remove_reservations(struct resource *avail) +{ +} + +static resource_size_t simple_align_resource(void *data, + const struct resource *avail, + resource_size_t size, + resource_size_t align) +{ + return avail->start; +} + +static void resource_clip(struct resource *res, resource_size_t min, + resource_size_t max) +{ + if (res->start < min) + res->start = min; + if (res->end > max) + res->end = max; +} + +/* + * Find empty slot in the resource tree with the given range and + * alignment constraints + */ +static int __find_resource(struct resource *root, struct resource *old, + struct resource *new, + resource_size_t size, + struct resource_constraint *constraint) +{ + struct resource *this = root->child; + struct resource tmp = *new, avail, alloc; + + tmp.start = root->start; + /* + * Skip past an allocated resource that starts at 0, since the assignment + * of this->start - 1 to tmp->end below would cause an underflow. + */ + if (this && this->start == root->start) { + tmp.start = (this == old) ? old->start : this->end + 1; + this = this->sibling; + } + for(;;) { + if (this) + tmp.end = (this == old) ? this->end : this->start - 1; + else + tmp.end = root->end; + + if (tmp.end < tmp.start) + goto next; + + resource_clip(&tmp, constraint->min, constraint->max); + arch_remove_reservations(&tmp); + + /* Check for overflow after ALIGN() */ + avail.start = ALIGN(tmp.start, constraint->align); + avail.end = tmp.end; + avail.flags = new->flags & ~IORESOURCE_UNSET; + if (avail.start >= tmp.start) { + alloc.flags = avail.flags; + alloc.start = constraint->alignf(constraint->alignf_data, &avail, + size, constraint->align); + alloc.end = alloc.start + size - 1; + if (resource_contains(&avail, &alloc)) { + new->start = alloc.start; + new->end = alloc.end; + return 0; + } + } + +next: if (!this || this->end == root->end) + break; + + if (this != old) + tmp.start = this->end + 1; + this = this->sibling; + } + return -EBUSY; +} + +/* + * Find empty slot in the resource tree given range and alignment. + */ +static int find_resource(struct resource *root, struct resource *new, + resource_size_t size, + struct resource_constraint *constraint) +{ + return __find_resource(root, NULL, new, size, constraint); +} + +/** + * reallocate_resource - allocate a slot in the resource tree given range & alignment. + * The resource will be relocated if the new size cannot be reallocated in the + * current location. + * + * @root: root resource descriptor + * @old: resource descriptor desired by caller + * @newsize: new size of the resource descriptor + * @constraint: the size and alignment constraints to be met. + */ +static int reallocate_resource(struct resource *root, struct resource *old, + resource_size_t newsize, + struct resource_constraint *constraint) +{ + int err=0; + struct resource new = *old; + struct resource *conflict; + + write_lock(&resource_lock); + + if ((err = __find_resource(root, old, &new, newsize, constraint))) + goto out; + + if (resource_contains(&new, old)) { + old->start = new.start; + old->end = new.end; + goto out; + } + + if (old->child) { + err = -EBUSY; + goto out; + } + + if (resource_contains(old, &new)) { + old->start = new.start; + old->end = new.end; + } else { + __release_resource(old); + *old = new; + conflict = __request_resource(root, old); + BUG_ON(conflict); + } +out: + write_unlock(&resource_lock); + return err; +} + + +/** + * allocate_resource - allocate empty slot in the resource tree given range & alignment. + * The resource will be reallocated with a new size if it was already allocated + * @root: root resource descriptor + * @new: resource descriptor desired by caller + * @size: requested resource region size + * @min: minimum boundary to allocate + * @max: maximum boundary to allocate + * @align: alignment requested, in bytes + * @alignf: alignment function, optional, called if not NULL + * @alignf_data: arbitrary data to pass to the @alignf function + */ +int allocate_resource(struct resource *root, struct resource *new, + resource_size_t size, resource_size_t min, + resource_size_t max, resource_size_t align, + resource_size_t (*alignf)(void *, + const struct resource *, + resource_size_t, + resource_size_t), + void *alignf_data) +{ + int err; + struct resource_constraint constraint; + + if (!alignf) + alignf = simple_align_resource; + + constraint.min = min; + constraint.max = max; + constraint.align = align; + constraint.alignf = alignf; + constraint.alignf_data = alignf_data; + + if ( new->parent ) { + /* resource is already allocated, try reallocating with + the new constraints */ + return reallocate_resource(root, new, size, &constraint); + } + + write_lock(&resource_lock); + err = find_resource(root, new, size, &constraint); + if (err >= 0 && __request_resource(root, new)) + err = -EBUSY; + write_unlock(&resource_lock); + return err; +} + +EXPORT_SYMBOL(allocate_resource); + +/** + * lookup_resource - find an existing resource by a resource start address + * @root: root resource descriptor + * @start: resource start address + * + * Returns a pointer to the resource if found, NULL otherwise + */ +struct resource *lookup_resource(struct resource *root, resource_size_t start) +{ + struct resource *res; + + read_lock(&resource_lock); + for (res = root->child; res; res = res->sibling) { + if (res->start == start) + break; + } + read_unlock(&resource_lock); + + return res; +} + +/* + * Insert a resource into the resource tree. If successful, return NULL, + * otherwise return the conflicting resource (compare to __request_resource()) + */ +static struct resource * __insert_resource(struct resource *parent, struct resource *new) +{ + struct resource *first, *next; + + for (;; parent = first) { + first = __request_resource(parent, new); + if (!first) + return first; + + if (first == parent) + return first; + if (WARN_ON(first == new)) /* duplicated insertion */ + return first; + + if ((first->start > new->start) || (first->end < new->end)) + break; + if ((first->start == new->start) && (first->end == new->end)) + break; + } + + for (next = first; ; next = next->sibling) { + /* Partial overlap? Bad, and unfixable */ + if (next->start < new->start || next->end > new->end) + return next; + if (!next->sibling) + break; + if (next->sibling->start > new->end) + break; + } + + new->parent = parent; + new->sibling = next->sibling; + new->child = first; + + next->sibling = NULL; + for (next = first; next; next = next->sibling) + next->parent = new; + + if (parent->child == first) { + parent->child = new; + } else { + next = parent->child; + while (next->sibling != first) + next = next->sibling; + next->sibling = new; + } + return NULL; +} + +/** + * insert_resource_conflict - Inserts resource in the resource tree + * @parent: parent of the new resource + * @new: new resource to insert + * + * Returns 0 on success, conflict resource if the resource can't be inserted. + * + * This function is equivalent to request_resource_conflict when no conflict + * happens. If a conflict happens, and the conflicting resources + * entirely fit within the range of the new resource, then the new + * resource is inserted and the conflicting resources become children of + * the new resource. + */ +struct resource *insert_resource_conflict(struct resource *parent, struct resource *new) +{ + struct resource *conflict; + + write_lock(&resource_lock); + conflict = __insert_resource(parent, new); + write_unlock(&resource_lock); + return conflict; +} + +/** + * insert_resource - Inserts a resource in the resource tree + * @parent: parent of the new resource + * @new: new resource to insert + * + * Returns 0 on success, -EBUSY if the resource can't be inserted. + */ +int insert_resource(struct resource *parent, struct resource *new) +{ + struct resource *conflict; + + conflict = insert_resource_conflict(parent, new); + return conflict ? -EBUSY : 0; +} + +/** + * insert_resource_expand_to_fit - Insert a resource into the resource tree + * @root: root resource descriptor + * @new: new resource to insert + * + * Insert a resource into the resource tree, possibly expanding it in order + * to make it encompass any conflicting resources. + */ +void insert_resource_expand_to_fit(struct resource *root, struct resource *new) +{ + if (new->parent) + return; + + write_lock(&resource_lock); + for (;;) { + struct resource *conflict; + + conflict = __insert_resource(root, new); + if (!conflict) + break; + if (conflict == root) + break; + + /* Ok, expand resource to cover the conflict, then try again .. */ + if (conflict->start < new->start) + new->start = conflict->start; + if (conflict->end > new->end) + new->end = conflict->end; + + printk("Expanded resource %s due to conflict with %s\n", new->name, conflict->name); + } + write_unlock(&resource_lock); +} + +static int __adjust_resource(struct resource *res, resource_size_t start, + resource_size_t size) +{ + struct resource *tmp, *parent = res->parent; + resource_size_t end = start + size - 1; + int result = -EBUSY; + + if (!parent) + goto skip; + + if ((start < parent->start) || (end > parent->end)) + goto out; + + if (res->sibling && (res->sibling->start <= end)) + goto out; + + tmp = parent->child; + if (tmp != res) { + while (tmp->sibling != res) + tmp = tmp->sibling; + if (start <= tmp->end) + goto out; + } + +skip: + for (tmp = res->child; tmp; tmp = tmp->sibling) + if ((tmp->start < start) || (tmp->end > end)) + goto out; + + res->start = start; + res->end = end; + result = 0; + + out: + return result; +} + +/** + * adjust_resource - modify a resource's start and size + * @res: resource to modify + * @start: new start value + * @size: new size + * + * Given an existing resource, change its start and size to match the + * arguments. Returns 0 on success, -EBUSY if it can't fit. + * Existing children of the resource are assumed to be immutable. + */ +int adjust_resource(struct resource *res, resource_size_t start, + resource_size_t size) +{ + int result; + + write_lock(&resource_lock); + result = __adjust_resource(res, start, size); + write_unlock(&resource_lock); + return result; +} +EXPORT_SYMBOL(adjust_resource); + +static void __init __reserve_region_with_split(struct resource *root, + resource_size_t start, resource_size_t end, + const char *name) +{ + struct resource *parent = root; + struct resource *conflict; + struct resource *res = alloc_resource(GFP_ATOMIC); + struct resource *next_res = NULL; + + if (!res) + return; + + res->name = name; + res->start = start; + res->end = end; + res->flags = IORESOURCE_BUSY; + + while (1) { + + conflict = __request_resource(parent, res); + if (!conflict) { + if (!next_res) + break; + res = next_res; + next_res = NULL; + continue; + } + + /* conflict covered whole area */ + if (conflict->start <= res->start && + conflict->end >= res->end) { + free_resource(res); + WARN_ON(next_res); + break; + } + + /* failed, split and try again */ + if (conflict->start > res->start) { + end = res->end; + res->end = conflict->start - 1; + if (conflict->end < end) { + next_res = alloc_resource(GFP_ATOMIC); + if (!next_res) { + free_resource(res); + break; + } + next_res->name = name; + next_res->start = conflict->end + 1; + next_res->end = end; + next_res->flags = IORESOURCE_BUSY; + } + } else { + res->start = conflict->end + 1; + } + } + +} + +void __init reserve_region_with_split(struct resource *root, + resource_size_t start, resource_size_t end, + const char *name) +{ + int abort = 0; + + write_lock(&resource_lock); + if (root->start > start || root->end < end) { + pr_err("requested range [0x%llx-0x%llx] not in root %pr\n", + (unsigned long long)start, (unsigned long long)end, + root); + if (start > root->end || end < root->start) + abort = 1; + else { + if (end > root->end) + end = root->end; + if (start < root->start) + start = root->start; + pr_err("fixing request to [0x%llx-0x%llx]\n", + (unsigned long long)start, + (unsigned long long)end); + } + dump_stack(); + } + if (!abort) + __reserve_region_with_split(root, start, end, name); + write_unlock(&resource_lock); +} + +/** + * resource_alignment - calculate resource's alignment + * @res: resource pointer + * + * Returns alignment on success, 0 (invalid alignment) on failure. + */ +resource_size_t resource_alignment(struct resource *res) +{ + switch (res->flags & (IORESOURCE_SIZEALIGN | IORESOURCE_STARTALIGN)) { + case IORESOURCE_SIZEALIGN: + return resource_size(res); + case IORESOURCE_STARTALIGN: + return res->start; + default: + return 0; + } +} + +/* + * This is compatibility stuff for IO resources. + * + * Note how this, unlike the above, knows about + * the IO flag meanings (busy etc). + * + * request_region creates a new busy region. + * + * release_region releases a matching busy region. + */ + +static DECLARE_WAIT_QUEUE_HEAD(muxed_resource_wait); + +/** + * __request_region - create a new busy resource region + * @parent: parent resource descriptor + * @start: resource start address + * @n: resource region size + * @name: reserving caller's ID string + * @flags: IO resource flags + */ +struct resource * __request_region(struct resource *parent, + resource_size_t start, resource_size_t n, + const char *name, int flags) +{ + DECLARE_WAITQUEUE(wait, current); + struct resource *res = alloc_resource(GFP_KERNEL); + + if (!res) + return NULL; + + res->name = name; + res->start = start; + res->end = start + n - 1; + res->flags = resource_type(parent); + res->flags |= IORESOURCE_BUSY | flags; + + write_lock(&resource_lock); + + for (;;) { + struct resource *conflict; + + conflict = __request_resource(parent, res); + if (!conflict) + break; + if (conflict != parent) { + parent = conflict; + if (!(conflict->flags & IORESOURCE_BUSY)) + continue; + } + if (conflict->flags & flags & IORESOURCE_MUXED) { + add_wait_queue(&muxed_resource_wait, &wait); + write_unlock(&resource_lock); + set_current_state(TASK_UNINTERRUPTIBLE); + schedule(); + remove_wait_queue(&muxed_resource_wait, &wait); + write_lock(&resource_lock); + continue; + } + /* Uhhuh, that didn't work out.. */ + free_resource(res); + res = NULL; + break; + } + write_unlock(&resource_lock); + return res; +} +EXPORT_SYMBOL(__request_region); + +/** + * __release_region - release a previously reserved resource region + * @parent: parent resource descriptor + * @start: resource start address + * @n: resource region size + * + * The described resource region must match a currently busy region. + */ +void __release_region(struct resource *parent, resource_size_t start, + resource_size_t n) +{ + struct resource **p; + resource_size_t end; + + p = &parent->child; + end = start + n - 1; + + write_lock(&resource_lock); + + for (;;) { + struct resource *res = *p; + + if (!res) + break; + if (res->start <= start && res->end >= end) { + if (!(res->flags & IORESOURCE_BUSY)) { + p = &res->child; + continue; + } + if (res->start != start || res->end != end) + break; + *p = res->sibling; + write_unlock(&resource_lock); + if (res->flags & IORESOURCE_MUXED) + wake_up(&muxed_resource_wait); + free_resource(res); + return; + } + p = &res->sibling; + } + + write_unlock(&resource_lock); + + printk(KERN_WARNING "Trying to free nonexistent resource " + "<%016llx-%016llx>\n", (unsigned long long)start, + (unsigned long long)end); +} +EXPORT_SYMBOL(__release_region); + +#ifdef CONFIG_MEMORY_HOTREMOVE +/** + * release_mem_region_adjustable - release a previously reserved memory region + * @parent: parent resource descriptor + * @start: resource start address + * @size: resource region size + * + * This interface is intended for memory hot-delete. The requested region + * is released from a currently busy memory resource. The requested region + * must either match exactly or fit into a single busy resource entry. In + * the latter case, the remaining resource is adjusted accordingly. + * Existing children of the busy memory resource must be immutable in the + * request. + * + * Note: + * - Additional release conditions, such as overlapping region, can be + * supported after they are confirmed as valid cases. + * - When a busy memory resource gets split into two entries, the code + * assumes that all children remain in the lower address entry for + * simplicity. Enhance this logic when necessary. + */ +int release_mem_region_adjustable(struct resource *parent, + resource_size_t start, resource_size_t size) +{ + struct resource **p; + struct resource *res; + struct resource *new_res; + resource_size_t end; + int ret = -EINVAL; + + end = start + size - 1; + if ((start < parent->start) || (end > parent->end)) + return ret; + + /* The alloc_resource() result gets checked later */ + new_res = alloc_resource(GFP_KERNEL); + + p = &parent->child; + write_lock(&resource_lock); + + while ((res = *p)) { + if (res->start >= end) + break; + + /* look for the next resource if it does not fit into */ + if (res->start > start || res->end < end) { + p = &res->sibling; + continue; + } + + if (!(res->flags & IORESOURCE_MEM)) + break; + + if (!(res->flags & IORESOURCE_BUSY)) { + p = &res->child; + continue; + } + + /* found the target resource; let's adjust accordingly */ + if (res->start == start && res->end == end) { + /* free the whole entry */ + *p = res->sibling; + free_resource(res); + ret = 0; + } else if (res->start == start && res->end != end) { + /* adjust the start */ + ret = __adjust_resource(res, end + 1, + res->end - end); + } else if (res->start != start && res->end == end) { + /* adjust the end */ + ret = __adjust_resource(res, res->start, + start - res->start); + } else { + /* split into two entries */ + if (!new_res) { + ret = -ENOMEM; + break; + } + new_res->name = res->name; + new_res->start = end + 1; + new_res->end = res->end; + new_res->flags = res->flags; + new_res->parent = res->parent; + new_res->sibling = res->sibling; + new_res->child = NULL; + + ret = __adjust_resource(res, res->start, + start - res->start); + if (ret) + break; + res->sibling = new_res; + new_res = NULL; + } + + break; + } + + write_unlock(&resource_lock); + free_resource(new_res); + return ret; +} +#endif /* CONFIG_MEMORY_HOTREMOVE */ + +/* + * Managed region resource + */ +static void devm_resource_release(struct device *dev, void *ptr) +{ + struct resource **r = ptr; + + release_resource(*r); +} + +/** + * devm_request_resource() - request and reserve an I/O or memory resource + * @dev: device for which to request the resource + * @root: root of the resource tree from which to request the resource + * @new: descriptor of the resource to request + * + * This is a device-managed version of request_resource(). There is usually + * no need to release resources requested by this function explicitly since + * that will be taken care of when the device is unbound from its driver. + * If for some reason the resource needs to be released explicitly, because + * of ordering issues for example, drivers must call devm_release_resource() + * rather than the regular release_resource(). + * + * When a conflict is detected between any existing resources and the newly + * requested resource, an error message will be printed. + * + * Returns 0 on success or a negative error code on failure. + */ +int devm_request_resource(struct device *dev, struct resource *root, + struct resource *new) +{ + struct resource *conflict, **ptr; + + ptr = devres_alloc(devm_resource_release, sizeof(*ptr), GFP_KERNEL); + if (!ptr) + return -ENOMEM; + + *ptr = new; + + conflict = request_resource_conflict(root, new); + if (conflict) { + dev_err(dev, "resource collision: %pR conflicts with %s %pR\n", + new, conflict->name, conflict); + devres_free(ptr); + return -EBUSY; + } + + devres_add(dev, ptr); + return 0; +} +EXPORT_SYMBOL(devm_request_resource); + +static int devm_resource_match(struct device *dev, void *res, void *data) +{ + struct resource **ptr = res; + + return *ptr == data; +} + +/** + * devm_release_resource() - release a previously requested resource + * @dev: device for which to release the resource + * @new: descriptor of the resource to release + * + * Releases a resource previously requested using devm_request_resource(). + */ +void devm_release_resource(struct device *dev, struct resource *new) +{ + WARN_ON(devres_release(dev, devm_resource_release, devm_resource_match, + new)); +} +EXPORT_SYMBOL(devm_release_resource); + +struct region_devres { + struct resource *parent; + resource_size_t start; + resource_size_t n; +}; + +static void devm_region_release(struct device *dev, void *res) +{ + struct region_devres *this = res; + + __release_region(this->parent, this->start, this->n); +} + +static int devm_region_match(struct device *dev, void *res, void *match_data) +{ + struct region_devres *this = res, *match = match_data; + + return this->parent == match->parent && + this->start == match->start && this->n == match->n; +} + +struct resource * __devm_request_region(struct device *dev, + struct resource *parent, resource_size_t start, + resource_size_t n, const char *name) +{ + struct region_devres *dr = NULL; + struct resource *res; + + dr = devres_alloc(devm_region_release, sizeof(struct region_devres), + GFP_KERNEL); + if (!dr) + return NULL; + + dr->parent = parent; + dr->start = start; + dr->n = n; + + res = __request_region(parent, start, n, name, 0); + if (res) + devres_add(dev, dr); + else + devres_free(dr); + + return res; +} +EXPORT_SYMBOL(__devm_request_region); + +void __devm_release_region(struct device *dev, struct resource *parent, + resource_size_t start, resource_size_t n) +{ + struct region_devres match_data = { parent, start, n }; + + __release_region(parent, start, n); + WARN_ON(devres_destroy(dev, devm_region_release, devm_region_match, + &match_data)); +} +EXPORT_SYMBOL(__devm_release_region); + +/* + * Called from init/main.c to reserve IO ports. + */ +#define MAXRESERVE 4 +static int __init reserve_setup(char *str) +{ + static int reserved; + static struct resource reserve[MAXRESERVE]; + + for (;;) { + unsigned int io_start, io_num; + int x = reserved; + + if (get_option (&str, &io_start) != 2) + break; + if (get_option (&str, &io_num) == 0) + break; + if (x < MAXRESERVE) { + struct resource *res = reserve + x; + res->name = "reserved"; + res->start = io_start; + res->end = io_start + io_num - 1; + res->flags = IORESOURCE_BUSY; + res->child = NULL; + if (request_resource(res->start >= 0x10000 ? &iomem_resource : &ioport_resource, res) == 0) + reserved = x+1; + } + } + return 1; +} + +__setup("reserve=", reserve_setup); + +/* + * Check if the requested addr and size spans more than any slot in the + * iomem resource tree. + */ +int iomem_map_sanity_check(resource_size_t addr, unsigned long size) +{ + struct resource *p = &iomem_resource; + int err = 0; + loff_t l; + + read_lock(&resource_lock); + for (p = p->child; p ; p = r_next(NULL, p, &l)) { + /* + * We can probably skip the resources without + * IORESOURCE_IO attribute? + */ + if (p->start >= addr + size) + continue; + if (p->end < addr) + continue; + if (PFN_DOWN(p->start) <= PFN_DOWN(addr) && + PFN_DOWN(p->end) >= PFN_DOWN(addr + size - 1)) + continue; + /* + * if a resource is "BUSY", it's not a hardware resource + * but a driver mapping of such a resource; we don't want + * to warn for those; some drivers legitimately map only + * partial hardware resources. (example: vesafb) + */ + if (p->flags & IORESOURCE_BUSY) + continue; + + printk(KERN_WARNING "resource sanity check: requesting [mem %#010llx-%#010llx], which spans more than %s %pR\n", + (unsigned long long)addr, + (unsigned long long)(addr + size - 1), + p->name, p); + err = -1; + break; + } + read_unlock(&resource_lock); + + return err; +} + +#ifdef CONFIG_STRICT_DEVMEM +static int strict_iomem_checks = 1; +#else +static int strict_iomem_checks; +#endif + +/* + * check if an address is reserved in the iomem resource tree + * returns 1 if reserved, 0 if not reserved. + */ +int iomem_is_exclusive(u64 addr) +{ + struct resource *p = &iomem_resource; + int err = 0; + loff_t l; + int size = PAGE_SIZE; + + if (!strict_iomem_checks) + return 0; + + addr = addr & PAGE_MASK; + + read_lock(&resource_lock); + for (p = p->child; p ; p = r_next(NULL, p, &l)) { + /* + * We can probably skip the resources without + * IORESOURCE_IO attribute? + */ + if (p->start >= addr + size) + break; + if (p->end < addr) + continue; + if (p->flags & IORESOURCE_BUSY && + p->flags & IORESOURCE_EXCLUSIVE) { + err = 1; + break; + } + } + read_unlock(&resource_lock); + + return err; +} + +struct resource_entry *resource_list_create_entry(struct resource *res, + size_t extra_size) +{ + struct resource_entry *entry; + + entry = kzalloc(sizeof(*entry) + extra_size, GFP_KERNEL); + if (entry) { + INIT_LIST_HEAD(&entry->node); + entry->res = res ? res : &entry->__res; + } + + return entry; +} +EXPORT_SYMBOL(resource_list_create_entry); + +void resource_list_free(struct list_head *head) +{ + struct resource_entry *entry, *tmp; + + list_for_each_entry_safe(entry, tmp, head, node) + resource_list_destroy_entry(entry); +} +EXPORT_SYMBOL(resource_list_free); + +static int __init strict_iomem(char *str) +{ + if (strstr(str, "relaxed")) + strict_iomem_checks = 0; + if (strstr(str, "strict")) + strict_iomem_checks = 1; + return 1; +} + +__setup("iomem=", strict_iomem); diff --git a/kernel/kernel/sched/Makefile b/kernel/kernel/sched/Makefile new file mode 100644 index 000000000..3944d32a0 --- /dev/null +++ b/kernel/kernel/sched/Makefile @@ -0,0 +1,21 @@ +ifdef CONFIG_FUNCTION_TRACER +CFLAGS_REMOVE_clock.o = $(CC_FLAGS_FTRACE) +endif + +ifneq ($(CONFIG_SCHED_OMIT_FRAME_POINTER),y) +# According to Alan Modra , the -fno-omit-frame-pointer is +# needed for x86 only. Why this used to be enabled for all architectures is beyond +# me. I suspect most platforms don't need this, but until we know that for sure +# I turn this off for IA-64 only. Andreas Schwab says it's also needed on m68k +# to get a correct value for the wait-channel (WCHAN in ps). --davidm +CFLAGS_core.o := $(PROFILING) -fno-omit-frame-pointer +endif + +obj-y += core.o proc.o clock.o cputime.o +obj-y += idle_task.o fair.o rt.o deadline.o stop_task.o +obj-y += wait.o wait-simple.o work-simple.o completion.o idle.o +obj-$(CONFIG_SMP) += cpupri.o cpudeadline.o +obj-$(CONFIG_SCHED_AUTOGROUP) += auto_group.o +obj-$(CONFIG_SCHEDSTATS) += stats.o +obj-$(CONFIG_SCHED_DEBUG) += debug.o +obj-$(CONFIG_CGROUP_CPUACCT) += cpuacct.o diff --git a/kernel/kernel/sched/auto_group.c b/kernel/kernel/sched/auto_group.c new file mode 100644 index 000000000..eae160dd6 --- /dev/null +++ b/kernel/kernel/sched/auto_group.c @@ -0,0 +1,253 @@ +#ifdef CONFIG_SCHED_AUTOGROUP + +#include "sched.h" + +#include +#include +#include +#include +#include +#include + +unsigned int __read_mostly sysctl_sched_autogroup_enabled = 1; +static struct autogroup autogroup_default; +static atomic_t autogroup_seq_nr; + +void __init autogroup_init(struct task_struct *init_task) +{ + autogroup_default.tg = &root_task_group; + kref_init(&autogroup_default.kref); + init_rwsem(&autogroup_default.lock); + init_task->signal->autogroup = &autogroup_default; +} + +void autogroup_free(struct task_group *tg) +{ + kfree(tg->autogroup); +} + +static inline void autogroup_destroy(struct kref *kref) +{ + struct autogroup *ag = container_of(kref, struct autogroup, kref); + +#ifdef CONFIG_RT_GROUP_SCHED + /* We've redirected RT tasks to the root task group... */ + ag->tg->rt_se = NULL; + ag->tg->rt_rq = NULL; +#endif + sched_offline_group(ag->tg); + sched_destroy_group(ag->tg); +} + +static inline void autogroup_kref_put(struct autogroup *ag) +{ + kref_put(&ag->kref, autogroup_destroy); +} + +static inline struct autogroup *autogroup_kref_get(struct autogroup *ag) +{ + kref_get(&ag->kref); + return ag; +} + +static inline struct autogroup *autogroup_task_get(struct task_struct *p) +{ + struct autogroup *ag; + unsigned long flags; + + if (!lock_task_sighand(p, &flags)) + return autogroup_kref_get(&autogroup_default); + + ag = autogroup_kref_get(p->signal->autogroup); + unlock_task_sighand(p, &flags); + + return ag; +} + +static inline struct autogroup *autogroup_create(void) +{ + struct autogroup *ag = kzalloc(sizeof(*ag), GFP_KERNEL); + struct task_group *tg; + + if (!ag) + goto out_fail; + + tg = sched_create_group(&root_task_group); + + if (IS_ERR(tg)) + goto out_free; + + kref_init(&ag->kref); + init_rwsem(&ag->lock); + ag->id = atomic_inc_return(&autogroup_seq_nr); + ag->tg = tg; +#ifdef CONFIG_RT_GROUP_SCHED + /* + * Autogroup RT tasks are redirected to the root task group + * so we don't have to move tasks around upon policy change, + * or flail around trying to allocate bandwidth on the fly. + * A bandwidth exception in __sched_setscheduler() allows + * the policy change to proceed. + */ + free_rt_sched_group(tg); + tg->rt_se = root_task_group.rt_se; + tg->rt_rq = root_task_group.rt_rq; +#endif + tg->autogroup = ag; + + sched_online_group(tg, &root_task_group); + return ag; + +out_free: + kfree(ag); +out_fail: + if (printk_ratelimit()) { + printk(KERN_WARNING "autogroup_create: %s failure.\n", + ag ? "sched_create_group()" : "kmalloc()"); + } + + return autogroup_kref_get(&autogroup_default); +} + +bool task_wants_autogroup(struct task_struct *p, struct task_group *tg) +{ + if (tg != &root_task_group) + return false; + + /* + * We can only assume the task group can't go away on us if + * autogroup_move_group() can see us on ->thread_group list. + */ + if (p->flags & PF_EXITING) + return false; + + return true; +} + +static void +autogroup_move_group(struct task_struct *p, struct autogroup *ag) +{ + struct autogroup *prev; + struct task_struct *t; + unsigned long flags; + + BUG_ON(!lock_task_sighand(p, &flags)); + + prev = p->signal->autogroup; + if (prev == ag) { + unlock_task_sighand(p, &flags); + return; + } + + p->signal->autogroup = autogroup_kref_get(ag); + + if (!ACCESS_ONCE(sysctl_sched_autogroup_enabled)) + goto out; + + for_each_thread(p, t) + sched_move_task(t); +out: + unlock_task_sighand(p, &flags); + autogroup_kref_put(prev); +} + +/* Allocates GFP_KERNEL, cannot be called under any spinlock */ +void sched_autogroup_create_attach(struct task_struct *p) +{ + struct autogroup *ag = autogroup_create(); + + autogroup_move_group(p, ag); + /* drop extra reference added by autogroup_create() */ + autogroup_kref_put(ag); +} +EXPORT_SYMBOL(sched_autogroup_create_attach); + +/* Cannot be called under siglock. Currently has no users */ +void sched_autogroup_detach(struct task_struct *p) +{ + autogroup_move_group(p, &autogroup_default); +} +EXPORT_SYMBOL(sched_autogroup_detach); + +void sched_autogroup_fork(struct signal_struct *sig) +{ + sig->autogroup = autogroup_task_get(current); +} + +void sched_autogroup_exit(struct signal_struct *sig) +{ + autogroup_kref_put(sig->autogroup); +} + +static int __init setup_autogroup(char *str) +{ + sysctl_sched_autogroup_enabled = 0; + + return 1; +} + +__setup("noautogroup", setup_autogroup); + +#ifdef CONFIG_PROC_FS + +int proc_sched_autogroup_set_nice(struct task_struct *p, int nice) +{ + static unsigned long next = INITIAL_JIFFIES; + struct autogroup *ag; + int err; + + if (nice < MIN_NICE || nice > MAX_NICE) + return -EINVAL; + + err = security_task_setnice(current, nice); + if (err) + return err; + + if (nice < 0 && !can_nice(current, nice)) + return -EPERM; + + /* this is a heavy operation taking global locks.. */ + if (!capable(CAP_SYS_ADMIN) && time_before(jiffies, next)) + return -EAGAIN; + + next = HZ / 10 + jiffies; + ag = autogroup_task_get(p); + + down_write(&ag->lock); + err = sched_group_set_shares(ag->tg, prio_to_weight[nice + 20]); + if (!err) + ag->nice = nice; + up_write(&ag->lock); + + autogroup_kref_put(ag); + + return err; +} + +void proc_sched_autogroup_show_task(struct task_struct *p, struct seq_file *m) +{ + struct autogroup *ag = autogroup_task_get(p); + + if (!task_group_is_autogroup(ag->tg)) + goto out; + + down_read(&ag->lock); + seq_printf(m, "/autogroup-%ld nice %d\n", ag->id, ag->nice); + up_read(&ag->lock); + +out: + autogroup_kref_put(ag); +} +#endif /* CONFIG_PROC_FS */ + +#ifdef CONFIG_SCHED_DEBUG +int autogroup_path(struct task_group *tg, char *buf, int buflen) +{ + if (!task_group_is_autogroup(tg)) + return 0; + + return snprintf(buf, buflen, "%s-%ld", "/autogroup", tg->autogroup->id); +} +#endif /* CONFIG_SCHED_DEBUG */ + +#endif /* CONFIG_SCHED_AUTOGROUP */ diff --git a/kernel/kernel/sched/auto_group.h b/kernel/kernel/sched/auto_group.h new file mode 100644 index 000000000..8bd047142 --- /dev/null +++ b/kernel/kernel/sched/auto_group.h @@ -0,0 +1,64 @@ +#ifdef CONFIG_SCHED_AUTOGROUP + +#include +#include + +struct autogroup { + /* + * reference doesn't mean how many thread attach to this + * autogroup now. It just stands for the number of task + * could use this autogroup. + */ + struct kref kref; + struct task_group *tg; + struct rw_semaphore lock; + unsigned long id; + int nice; +}; + +extern void autogroup_init(struct task_struct *init_task); +extern void autogroup_free(struct task_group *tg); + +static inline bool task_group_is_autogroup(struct task_group *tg) +{ + return !!tg->autogroup; +} + +extern bool task_wants_autogroup(struct task_struct *p, struct task_group *tg); + +static inline struct task_group * +autogroup_task_group(struct task_struct *p, struct task_group *tg) +{ + int enabled = ACCESS_ONCE(sysctl_sched_autogroup_enabled); + + if (enabled && task_wants_autogroup(p, tg)) + return p->signal->autogroup->tg; + + return tg; +} + +extern int autogroup_path(struct task_group *tg, char *buf, int buflen); + +#else /* !CONFIG_SCHED_AUTOGROUP */ + +static inline void autogroup_init(struct task_struct *init_task) { } +static inline void autogroup_free(struct task_group *tg) { } +static inline bool task_group_is_autogroup(struct task_group *tg) +{ + return 0; +} + +static inline struct task_group * +autogroup_task_group(struct task_struct *p, struct task_group *tg) +{ + return tg; +} + +#ifdef CONFIG_SCHED_DEBUG +static inline int autogroup_path(struct task_group *tg, char *buf, int buflen) +{ + return 0; +} +#endif + +#endif /* CONFIG_SCHED_AUTOGROUP */ diff --git a/kernel/kernel/sched/clock.c b/kernel/kernel/sched/clock.c new file mode 100644 index 000000000..c0a205101 --- /dev/null +++ b/kernel/kernel/sched/clock.c @@ -0,0 +1,435 @@ +/* + * sched_clock for unstable cpu clocks + * + * Copyright (C) 2008 Red Hat, Inc., Peter Zijlstra + * + * Updates and enhancements: + * Copyright (C) 2008 Red Hat, Inc. Steven Rostedt + * + * Based on code by: + * Ingo Molnar + * Guillaume Chazarain + * + * + * What: + * + * cpu_clock(i) provides a fast (execution time) high resolution + * clock with bounded drift between CPUs. The value of cpu_clock(i) + * is monotonic for constant i. The timestamp returned is in nanoseconds. + * + * ######################### BIG FAT WARNING ########################## + * # when comparing cpu_clock(i) to cpu_clock(j) for i != j, time can # + * # go backwards !! # + * #################################################################### + * + * There is no strict promise about the base, although it tends to start + * at 0 on boot (but people really shouldn't rely on that). + * + * cpu_clock(i) -- can be used from any context, including NMI. + * local_clock() -- is cpu_clock() on the current cpu. + * + * sched_clock_cpu(i) + * + * How: + * + * The implementation either uses sched_clock() when + * !CONFIG_HAVE_UNSTABLE_SCHED_CLOCK, which means in that case the + * sched_clock() is assumed to provide these properties (mostly it means + * the architecture provides a globally synchronized highres time source). + * + * Otherwise it tries to create a semi stable clock from a mixture of other + * clocks, including: + * + * - GTOD (clock monotomic) + * - sched_clock() + * - explicit idle events + * + * We use GTOD as base and use sched_clock() deltas to improve resolution. The + * deltas are filtered to provide monotonicity and keeping it within an + * expected window. + * + * Furthermore, explicit sleep and wakeup hooks allow us to account for time + * that is otherwise invisible (TSC gets stopped). + * + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include + +/* + * Scheduler clock - returns current time in nanosec units. + * This is default implementation. + * Architectures and sub-architectures can override this. + */ +unsigned long long __weak sched_clock(void) +{ + return (unsigned long long)(jiffies - INITIAL_JIFFIES) + * (NSEC_PER_SEC / HZ); +} +EXPORT_SYMBOL_GPL(sched_clock); + +__read_mostly int sched_clock_running; + +#ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK +static struct static_key __sched_clock_stable = STATIC_KEY_INIT; +static int __sched_clock_stable_early; + +int sched_clock_stable(void) +{ + return static_key_false(&__sched_clock_stable); +} + +static void __set_sched_clock_stable(void) +{ + if (!sched_clock_stable()) + static_key_slow_inc(&__sched_clock_stable); +} + +void set_sched_clock_stable(void) +{ + __sched_clock_stable_early = 1; + + smp_mb(); /* matches sched_clock_init() */ + + if (!sched_clock_running) + return; + + __set_sched_clock_stable(); +} + +static void __clear_sched_clock_stable(struct work_struct *work) +{ + /* XXX worry about clock continuity */ + if (sched_clock_stable()) + static_key_slow_dec(&__sched_clock_stable); +} + +static DECLARE_WORK(sched_clock_work, __clear_sched_clock_stable); + +void clear_sched_clock_stable(void) +{ + __sched_clock_stable_early = 0; + + smp_mb(); /* matches sched_clock_init() */ + + if (!sched_clock_running) + return; + + schedule_work(&sched_clock_work); +} + +struct sched_clock_data { + u64 tick_raw; + u64 tick_gtod; + u64 clock; +}; + +static DEFINE_PER_CPU_SHARED_ALIGNED(struct sched_clock_data, sched_clock_data); + +static inline struct sched_clock_data *this_scd(void) +{ + return this_cpu_ptr(&sched_clock_data); +} + +static inline struct sched_clock_data *cpu_sdc(int cpu) +{ + return &per_cpu(sched_clock_data, cpu); +} + +void sched_clock_init(void) +{ + u64 ktime_now = ktime_to_ns(ktime_get()); + int cpu; + + for_each_possible_cpu(cpu) { + struct sched_clock_data *scd = cpu_sdc(cpu); + + scd->tick_raw = 0; + scd->tick_gtod = ktime_now; + scd->clock = ktime_now; + } + + sched_clock_running = 1; + + /* + * Ensure that it is impossible to not do a static_key update. + * + * Either {set,clear}_sched_clock_stable() must see sched_clock_running + * and do the update, or we must see their __sched_clock_stable_early + * and do the update, or both. + */ + smp_mb(); /* matches {set,clear}_sched_clock_stable() */ + + if (__sched_clock_stable_early) + __set_sched_clock_stable(); + else + __clear_sched_clock_stable(NULL); +} + +/* + * min, max except they take wrapping into account + */ + +static inline u64 wrap_min(u64 x, u64 y) +{ + return (s64)(x - y) < 0 ? x : y; +} + +static inline u64 wrap_max(u64 x, u64 y) +{ + return (s64)(x - y) > 0 ? x : y; +} + +/* + * update the percpu scd from the raw @now value + * + * - filter out backward motion + * - use the GTOD tick value to create a window to filter crazy TSC values + */ +static u64 sched_clock_local(struct sched_clock_data *scd) +{ + u64 now, clock, old_clock, min_clock, max_clock; + s64 delta; + +again: + now = sched_clock(); + delta = now - scd->tick_raw; + if (unlikely(delta < 0)) + delta = 0; + + old_clock = scd->clock; + + /* + * scd->clock = clamp(scd->tick_gtod + delta, + * max(scd->tick_gtod, scd->clock), + * scd->tick_gtod + TICK_NSEC); + */ + + clock = scd->tick_gtod + delta; + min_clock = wrap_max(scd->tick_gtod, old_clock); + max_clock = wrap_max(old_clock, scd->tick_gtod + TICK_NSEC); + + clock = wrap_max(clock, min_clock); + clock = wrap_min(clock, max_clock); + + if (cmpxchg64(&scd->clock, old_clock, clock) != old_clock) + goto again; + + return clock; +} + +static u64 sched_clock_remote(struct sched_clock_data *scd) +{ + struct sched_clock_data *my_scd = this_scd(); + u64 this_clock, remote_clock; + u64 *ptr, old_val, val; + +#if BITS_PER_LONG != 64 +again: + /* + * Careful here: The local and the remote clock values need to + * be read out atomic as we need to compare the values and + * then update either the local or the remote side. So the + * cmpxchg64 below only protects one readout. + * + * We must reread via sched_clock_local() in the retry case on + * 32bit as an NMI could use sched_clock_local() via the + * tracer and hit between the readout of + * the low32bit and the high 32bit portion. + */ + this_clock = sched_clock_local(my_scd); + /* + * We must enforce atomic readout on 32bit, otherwise the + * update on the remote cpu can hit inbetween the readout of + * the low32bit and the high 32bit portion. + */ + remote_clock = cmpxchg64(&scd->clock, 0, 0); +#else + /* + * On 64bit the read of [my]scd->clock is atomic versus the + * update, so we can avoid the above 32bit dance. + */ + sched_clock_local(my_scd); +again: + this_clock = my_scd->clock; + remote_clock = scd->clock; +#endif + + /* + * Use the opportunity that we have both locks + * taken to couple the two clocks: we take the + * larger time as the latest time for both + * runqueues. (this creates monotonic movement) + */ + if (likely((s64)(remote_clock - this_clock) < 0)) { + ptr = &scd->clock; + old_val = remote_clock; + val = this_clock; + } else { + /* + * Should be rare, but possible: + */ + ptr = &my_scd->clock; + old_val = this_clock; + val = remote_clock; + } + + if (cmpxchg64(ptr, old_val, val) != old_val) + goto again; + + return val; +} + +/* + * Similar to cpu_clock(), but requires local IRQs to be disabled. + * + * See cpu_clock(). + */ +u64 sched_clock_cpu(int cpu) +{ + struct sched_clock_data *scd; + u64 clock; + + if (sched_clock_stable()) + return sched_clock(); + + if (unlikely(!sched_clock_running)) + return 0ull; + + preempt_disable_notrace(); + scd = cpu_sdc(cpu); + + if (cpu != smp_processor_id()) + clock = sched_clock_remote(scd); + else + clock = sched_clock_local(scd); + preempt_enable_notrace(); + + return clock; +} + +void sched_clock_tick(void) +{ + struct sched_clock_data *scd; + u64 now, now_gtod; + + if (sched_clock_stable()) + return; + + if (unlikely(!sched_clock_running)) + return; + + WARN_ON_ONCE(!irqs_disabled()); + + scd = this_scd(); + now_gtod = ktime_to_ns(ktime_get()); + now = sched_clock(); + + scd->tick_raw = now; + scd->tick_gtod = now_gtod; + sched_clock_local(scd); +} + +/* + * We are going deep-idle (irqs are disabled): + */ +void sched_clock_idle_sleep_event(void) +{ + sched_clock_cpu(smp_processor_id()); +} +EXPORT_SYMBOL_GPL(sched_clock_idle_sleep_event); + +/* + * We just idled delta nanoseconds (called with irqs disabled): + */ +void sched_clock_idle_wakeup_event(u64 delta_ns) +{ + if (timekeeping_suspended) + return; + + sched_clock_tick(); + touch_softlockup_watchdog(); +} +EXPORT_SYMBOL_GPL(sched_clock_idle_wakeup_event); + +/* + * As outlined at the top, provides a fast, high resolution, nanosecond + * time source that is monotonic per cpu argument and has bounded drift + * between cpus. + * + * ######################### BIG FAT WARNING ########################## + * # when comparing cpu_clock(i) to cpu_clock(j) for i != j, time can # + * # go backwards !! # + * #################################################################### + */ +u64 cpu_clock(int cpu) +{ + if (!sched_clock_stable()) + return sched_clock_cpu(cpu); + + return sched_clock(); +} + +/* + * Similar to cpu_clock() for the current cpu. Time will only be observed + * to be monotonic if care is taken to only compare timestampt taken on the + * same CPU. + * + * See cpu_clock(). + */ +u64 local_clock(void) +{ + if (!sched_clock_stable()) + return sched_clock_cpu(raw_smp_processor_id()); + + return sched_clock(); +} + +#else /* CONFIG_HAVE_UNSTABLE_SCHED_CLOCK */ + +void sched_clock_init(void) +{ + sched_clock_running = 1; +} + +u64 sched_clock_cpu(int cpu) +{ + if (unlikely(!sched_clock_running)) + return 0; + + return sched_clock(); +} + +u64 cpu_clock(int cpu) +{ + return sched_clock(); +} + +u64 local_clock(void) +{ + return sched_clock(); +} + +#endif /* CONFIG_HAVE_UNSTABLE_SCHED_CLOCK */ + +EXPORT_SYMBOL_GPL(cpu_clock); +EXPORT_SYMBOL_GPL(local_clock); + +/* + * Running clock - returns the time that has elapsed while a guest has been + * running. + * On a guest this value should be local_clock minus the time the guest was + * suspended by the hypervisor (for any reason). + * On bare metal this function should return the same as local_clock. + * Architectures and sub-architectures can override this. + */ +u64 __weak running_clock(void) +{ + return local_clock(); +} diff --git a/kernel/kernel/sched/completion.c b/kernel/kernel/sched/completion.c new file mode 100644 index 000000000..45ebcffd9 --- /dev/null +++ b/kernel/kernel/sched/completion.c @@ -0,0 +1,317 @@ +/* + * Generic wait-for-completion handler; + * + * It differs from semaphores in that their default case is the opposite, + * wait_for_completion default blocks whereas semaphore default non-block. The + * interface also makes it easy to 'complete' multiple waiting threads, + * something which isn't entirely natural for semaphores. + * + * But more importantly, the primitive documents the usage. Semaphores would + * typically be used for exclusion which gives rise to priority inversion. + * Waiting for completion is a typically sync point, but not an exclusion point. + */ + +#include +#include + +/** + * complete: - signals a single thread waiting on this completion + * @x: holds the state of this particular completion + * + * This will wake up a single thread waiting on this completion. Threads will be + * awakened in the same order in which they were queued. + * + * See also complete_all(), wait_for_completion() and related routines. + * + * It may be assumed that this function implies a write memory barrier before + * changing the task state if and only if any tasks are woken up. + */ +void complete(struct completion *x) +{ + unsigned long flags; + + raw_spin_lock_irqsave(&x->wait.lock, flags); + x->done++; + __swait_wake_locked(&x->wait, TASK_NORMAL, 1); + raw_spin_unlock_irqrestore(&x->wait.lock, flags); +} +EXPORT_SYMBOL(complete); + +/** + * complete_all: - signals all threads waiting on this completion + * @x: holds the state of this particular completion + * + * This will wake up all threads waiting on this particular completion event. + * + * It may be assumed that this function implies a write memory barrier before + * changing the task state if and only if any tasks are woken up. + */ +void complete_all(struct completion *x) +{ + unsigned long flags; + + raw_spin_lock_irqsave(&x->wait.lock, flags); + x->done += UINT_MAX/2; + __swait_wake_locked(&x->wait, TASK_NORMAL, 0); + raw_spin_unlock_irqrestore(&x->wait.lock, flags); +} +EXPORT_SYMBOL(complete_all); + +static inline long __sched +do_wait_for_common(struct completion *x, + long (*action)(long), long timeout, int state) +{ + if (!x->done) { + DEFINE_SWAITER(wait); + + swait_prepare_locked(&x->wait, &wait); + do { + if (signal_pending_state(state, current)) { + timeout = -ERESTARTSYS; + break; + } + __set_current_state(state); + raw_spin_unlock_irq(&x->wait.lock); + timeout = action(timeout); + raw_spin_lock_irq(&x->wait.lock); + } while (!x->done && timeout); + swait_finish_locked(&x->wait, &wait); + if (!x->done) + return timeout; + } + x->done--; + return timeout ?: 1; +} + +static inline long __sched +__wait_for_common(struct completion *x, + long (*action)(long), long timeout, int state) +{ + might_sleep(); + + raw_spin_lock_irq(&x->wait.lock); + timeout = do_wait_for_common(x, action, timeout, state); + raw_spin_unlock_irq(&x->wait.lock); + return timeout; +} + +static long __sched +wait_for_common(struct completion *x, long timeout, int state) +{ + return __wait_for_common(x, schedule_timeout, timeout, state); +} + +static long __sched +wait_for_common_io(struct completion *x, long timeout, int state) +{ + return __wait_for_common(x, io_schedule_timeout, timeout, state); +} + +/** + * wait_for_completion: - waits for completion of a task + * @x: holds the state of this particular completion + * + * This waits to be signaled for completion of a specific task. It is NOT + * interruptible and there is no timeout. + * + * See also similar routines (i.e. wait_for_completion_timeout()) with timeout + * and interrupt capability. Also see complete(). + */ +void __sched wait_for_completion(struct completion *x) +{ + wait_for_common(x, MAX_SCHEDULE_TIMEOUT, TASK_UNINTERRUPTIBLE); +} +EXPORT_SYMBOL(wait_for_completion); + +/** + * wait_for_completion_timeout: - waits for completion of a task (w/timeout) + * @x: holds the state of this particular completion + * @timeout: timeout value in jiffies + * + * This waits for either a completion of a specific task to be signaled or for a + * specified timeout to expire. The timeout is in jiffies. It is not + * interruptible. + * + * Return: 0 if timed out, and positive (at least 1, or number of jiffies left + * till timeout) if completed. + */ +unsigned long __sched +wait_for_completion_timeout(struct completion *x, unsigned long timeout) +{ + return wait_for_common(x, timeout, TASK_UNINTERRUPTIBLE); +} +EXPORT_SYMBOL(wait_for_completion_timeout); + +/** + * wait_for_completion_io: - waits for completion of a task + * @x: holds the state of this particular completion + * + * This waits to be signaled for completion of a specific task. It is NOT + * interruptible and there is no timeout. The caller is accounted as waiting + * for IO (which traditionally means blkio only). + */ +void __sched wait_for_completion_io(struct completion *x) +{ + wait_for_common_io(x, MAX_SCHEDULE_TIMEOUT, TASK_UNINTERRUPTIBLE); +} +EXPORT_SYMBOL(wait_for_completion_io); + +/** + * wait_for_completion_io_timeout: - waits for completion of a task (w/timeout) + * @x: holds the state of this particular completion + * @timeout: timeout value in jiffies + * + * This waits for either a completion of a specific task to be signaled or for a + * specified timeout to expire. The timeout is in jiffies. It is not + * interruptible. The caller is accounted as waiting for IO (which traditionally + * means blkio only). + * + * Return: 0 if timed out, and positive (at least 1, or number of jiffies left + * till timeout) if completed. + */ +unsigned long __sched +wait_for_completion_io_timeout(struct completion *x, unsigned long timeout) +{ + return wait_for_common_io(x, timeout, TASK_UNINTERRUPTIBLE); +} +EXPORT_SYMBOL(wait_for_completion_io_timeout); + +/** + * wait_for_completion_interruptible: - waits for completion of a task (w/intr) + * @x: holds the state of this particular completion + * + * This waits for completion of a specific task to be signaled. It is + * interruptible. + * + * Return: -ERESTARTSYS if interrupted, 0 if completed. + */ +int __sched wait_for_completion_interruptible(struct completion *x) +{ + long t = wait_for_common(x, MAX_SCHEDULE_TIMEOUT, TASK_INTERRUPTIBLE); + if (t == -ERESTARTSYS) + return t; + return 0; +} +EXPORT_SYMBOL(wait_for_completion_interruptible); + +/** + * wait_for_completion_interruptible_timeout: - waits for completion (w/(to,intr)) + * @x: holds the state of this particular completion + * @timeout: timeout value in jiffies + * + * This waits for either a completion of a specific task to be signaled or for a + * specified timeout to expire. It is interruptible. The timeout is in jiffies. + * + * Return: -ERESTARTSYS if interrupted, 0 if timed out, positive (at least 1, + * or number of jiffies left till timeout) if completed. + */ +long __sched +wait_for_completion_interruptible_timeout(struct completion *x, + unsigned long timeout) +{ + return wait_for_common(x, timeout, TASK_INTERRUPTIBLE); +} +EXPORT_SYMBOL(wait_for_completion_interruptible_timeout); + +/** + * wait_for_completion_killable: - waits for completion of a task (killable) + * @x: holds the state of this particular completion + * + * This waits to be signaled for completion of a specific task. It can be + * interrupted by a kill signal. + * + * Return: -ERESTARTSYS if interrupted, 0 if completed. + */ +int __sched wait_for_completion_killable(struct completion *x) +{ + long t = wait_for_common(x, MAX_SCHEDULE_TIMEOUT, TASK_KILLABLE); + if (t == -ERESTARTSYS) + return t; + return 0; +} +EXPORT_SYMBOL(wait_for_completion_killable); + +/** + * wait_for_completion_killable_timeout: - waits for completion of a task (w/(to,killable)) + * @x: holds the state of this particular completion + * @timeout: timeout value in jiffies + * + * This waits for either a completion of a specific task to be + * signaled or for a specified timeout to expire. It can be + * interrupted by a kill signal. The timeout is in jiffies. + * + * Return: -ERESTARTSYS if interrupted, 0 if timed out, positive (at least 1, + * or number of jiffies left till timeout) if completed. + */ +long __sched +wait_for_completion_killable_timeout(struct completion *x, + unsigned long timeout) +{ + return wait_for_common(x, timeout, TASK_KILLABLE); +} +EXPORT_SYMBOL(wait_for_completion_killable_timeout); + +/** + * try_wait_for_completion - try to decrement a completion without blocking + * @x: completion structure + * + * Return: 0 if a decrement cannot be done without blocking + * 1 if a decrement succeeded. + * + * If a completion is being used as a counting completion, + * attempt to decrement the counter without blocking. This + * enables us to avoid waiting if the resource the completion + * is protecting is not available. + */ +bool try_wait_for_completion(struct completion *x) +{ + unsigned long flags; + int ret = 1; + + /* + * Since x->done will need to be locked only + * in the non-blocking case, we check x->done + * first without taking the lock so we can + * return early in the blocking case. + */ + if (!READ_ONCE(x->done)) + return 0; + + raw_spin_lock_irqsave(&x->wait.lock, flags); + if (!x->done) + ret = 0; + else + x->done--; + raw_spin_unlock_irqrestore(&x->wait.lock, flags); + return ret; +} +EXPORT_SYMBOL(try_wait_for_completion); + +/** + * completion_done - Test to see if a completion has any waiters + * @x: completion structure + * + * Return: 0 if there are waiters (wait_for_completion() in progress) + * 1 if there are no waiters. + * + */ +bool completion_done(struct completion *x) +{ + if (!READ_ONCE(x->done)) + return false; + + /* + * If ->done, we need to wait for complete() to release ->wait.lock + * otherwise we can end up freeing the completion before complete() + * is done referencing it. + * + * The RMB pairs with complete()'s RELEASE of ->wait.lock and orders + * the loads of ->done and ->wait.lock such that we cannot observe + * the lock before complete() acquires it while observing the ->done + * after it's acquired the lock. + */ + smp_rmb(); + raw_spin_unlock_wait(&x->wait.lock); + return true; +} +EXPORT_SYMBOL(completion_done); diff --git a/kernel/kernel/sched/core.c b/kernel/kernel/sched/core.c new file mode 100644 index 000000000..392aad4ec --- /dev/null +++ b/kernel/kernel/sched/core.c @@ -0,0 +1,8726 @@ +/* + * kernel/sched/core.c + * + * Kernel scheduler and related syscalls + * + * Copyright (C) 1991-2002 Linus Torvalds + * + * 1996-12-23 Modified by Dave Grothe to fix bugs in semaphores and + * make semaphores SMP safe + * 1998-11-19 Implemented schedule_timeout() and related stuff + * by Andrea Arcangeli + * 2002-01-04 New ultra-scalable O(1) scheduler by Ingo Molnar: + * hybrid priority-list and round-robin design with + * an array-switch method of distributing timeslices + * and per-CPU runqueues. Cleanups and useful suggestions + * by Davide Libenzi, preemptible kernel bits by Robert Love. + * 2003-09-03 Interactivity tuning by Con Kolivas. + * 2004-04-02 Scheduler domains code by Nick Piggin + * 2007-04-15 Work begun on replacing all interactivity tuning with a + * fair scheduling design by Con Kolivas. + * 2007-05-05 Load balancing (smp-nice) and other improvements + * by Peter Williams + * 2007-05-06 Interactivity improvements to CFS by Mike Galbraith + * 2007-07-01 Group scheduling enhancements by Srivatsa Vaddagiri + * 2007-11-29 RT balancing improvements by Steven Rostedt, Gregory Haskins, + * Thomas Gleixner, Mike Kravetz + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#ifdef CONFIG_PARAVIRT +#include +#endif + +#include "sched.h" +#include "../workqueue_internal.h" +#include "../smpboot.h" + +#define CREATE_TRACE_POINTS +#include + +void start_bandwidth_timer(struct hrtimer *period_timer, ktime_t period) +{ + unsigned long delta; + ktime_t soft, hard, now; + + for (;;) { + if (hrtimer_active(period_timer)) + break; + + now = hrtimer_cb_get_time(period_timer); + hrtimer_forward(period_timer, now, period); + + soft = hrtimer_get_softexpires(period_timer); + hard = hrtimer_get_expires(period_timer); + delta = ktime_to_ns(ktime_sub(hard, soft)); + __hrtimer_start_range_ns(period_timer, soft, delta, + HRTIMER_MODE_ABS_PINNED, 0); + } +} + +DEFINE_MUTEX(sched_domains_mutex); +DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues); + +static void update_rq_clock_task(struct rq *rq, s64 delta); + +void update_rq_clock(struct rq *rq) +{ + s64 delta; + + lockdep_assert_held(&rq->lock); + + if (rq->clock_skip_update & RQCF_ACT_SKIP) + return; + + delta = sched_clock_cpu(cpu_of(rq)) - rq->clock; + if (delta < 0) + return; + rq->clock += delta; + update_rq_clock_task(rq, delta); +} + +/* + * Debugging: various feature bits + */ + +#define SCHED_FEAT(name, enabled) \ + (1UL << __SCHED_FEAT_##name) * enabled | + +const_debug unsigned int sysctl_sched_features = +#include "features.h" + 0; + +#undef SCHED_FEAT + +#ifdef CONFIG_SCHED_DEBUG +#define SCHED_FEAT(name, enabled) \ + #name , + +static const char * const sched_feat_names[] = { +#include "features.h" +}; + +#undef SCHED_FEAT + +static int sched_feat_show(struct seq_file *m, void *v) +{ + int i; + + for (i = 0; i < __SCHED_FEAT_NR; i++) { + if (!(sysctl_sched_features & (1UL << i))) + seq_puts(m, "NO_"); + seq_printf(m, "%s ", sched_feat_names[i]); + } + seq_puts(m, "\n"); + + return 0; +} + +#ifdef HAVE_JUMP_LABEL + +#define jump_label_key__true STATIC_KEY_INIT_TRUE +#define jump_label_key__false STATIC_KEY_INIT_FALSE + +#define SCHED_FEAT(name, enabled) \ + jump_label_key__##enabled , + +struct static_key sched_feat_keys[__SCHED_FEAT_NR] = { +#include "features.h" +}; + +#undef SCHED_FEAT + +static void sched_feat_disable(int i) +{ + if (static_key_enabled(&sched_feat_keys[i])) + static_key_slow_dec(&sched_feat_keys[i]); +} + +static void sched_feat_enable(int i) +{ + if (!static_key_enabled(&sched_feat_keys[i])) + static_key_slow_inc(&sched_feat_keys[i]); +} +#else +static void sched_feat_disable(int i) { }; +static void sched_feat_enable(int i) { }; +#endif /* HAVE_JUMP_LABEL */ + +static int sched_feat_set(char *cmp) +{ + int i; + int neg = 0; + + if (strncmp(cmp, "NO_", 3) == 0) { + neg = 1; + cmp += 3; + } + + for (i = 0; i < __SCHED_FEAT_NR; i++) { + if (strcmp(cmp, sched_feat_names[i]) == 0) { + if (neg) { + sysctl_sched_features &= ~(1UL << i); + sched_feat_disable(i); + } else { + sysctl_sched_features |= (1UL << i); + sched_feat_enable(i); + } + break; + } + } + + return i; +} + +static ssize_t +sched_feat_write(struct file *filp, const char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + char buf[64]; + char *cmp; + int i; + struct inode *inode; + + if (cnt > 63) + cnt = 63; + + if (copy_from_user(&buf, ubuf, cnt)) + return -EFAULT; + + buf[cnt] = 0; + cmp = strstrip(buf); + + /* Ensure the static_key remains in a consistent state */ + inode = file_inode(filp); + mutex_lock(&inode->i_mutex); + i = sched_feat_set(cmp); + mutex_unlock(&inode->i_mutex); + if (i == __SCHED_FEAT_NR) + return -EINVAL; + + *ppos += cnt; + + return cnt; +} + +static int sched_feat_open(struct inode *inode, struct file *filp) +{ + return single_open(filp, sched_feat_show, NULL); +} + +static const struct file_operations sched_feat_fops = { + .open = sched_feat_open, + .write = sched_feat_write, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static __init int sched_init_debug(void) +{ + debugfs_create_file("sched_features", 0644, NULL, NULL, + &sched_feat_fops); + + return 0; +} +late_initcall(sched_init_debug); +#endif /* CONFIG_SCHED_DEBUG */ + +/* + * Number of tasks to iterate in a single balance run. + * Limited because this is done with IRQs disabled. + */ +#ifndef CONFIG_PREEMPT_RT_FULL +const_debug unsigned int sysctl_sched_nr_migrate = 32; +#else +const_debug unsigned int sysctl_sched_nr_migrate = 8; +#endif + +/* + * period over which we average the RT time consumption, measured + * in ms. + * + * default: 1s + */ +const_debug unsigned int sysctl_sched_time_avg = MSEC_PER_SEC; + +/* + * period over which we measure -rt task cpu usage in us. + * default: 1s + */ +unsigned int sysctl_sched_rt_period = 1000000; + +__read_mostly int scheduler_running; + +/* + * part of the period that we allow rt tasks to run in us. + * default: 0.95s + */ +int sysctl_sched_rt_runtime = 950000; + +/* cpus with isolated domains */ +cpumask_var_t cpu_isolated_map; + +/* + * this_rq_lock - lock this runqueue and disable interrupts. + */ +static struct rq *this_rq_lock(void) + __acquires(rq->lock) +{ + struct rq *rq; + + local_irq_disable(); + rq = this_rq(); + raw_spin_lock(&rq->lock); + + return rq; +} + +#ifdef CONFIG_SCHED_HRTICK +/* + * Use HR-timers to deliver accurate preemption points. + */ + +static void hrtick_clear(struct rq *rq) +{ + if (hrtimer_active(&rq->hrtick_timer)) + hrtimer_cancel(&rq->hrtick_timer); +} + +/* + * High-resolution timer tick. + * Runs from hardirq context with interrupts disabled. + */ +static enum hrtimer_restart hrtick(struct hrtimer *timer) +{ + struct rq *rq = container_of(timer, struct rq, hrtick_timer); + + WARN_ON_ONCE(cpu_of(rq) != smp_processor_id()); + + raw_spin_lock(&rq->lock); + update_rq_clock(rq); + rq->curr->sched_class->task_tick(rq, rq->curr, 1); + raw_spin_unlock(&rq->lock); + + return HRTIMER_NORESTART; +} + +#ifdef CONFIG_SMP + +static int __hrtick_restart(struct rq *rq) +{ + struct hrtimer *timer = &rq->hrtick_timer; + ktime_t time = hrtimer_get_softexpires(timer); + + return __hrtimer_start_range_ns(timer, time, 0, HRTIMER_MODE_ABS_PINNED, 0); +} + +/* + * called from hardirq (IPI) context + */ +static void __hrtick_start(void *arg) +{ + struct rq *rq = arg; + + raw_spin_lock(&rq->lock); + __hrtick_restart(rq); + rq->hrtick_csd_pending = 0; + raw_spin_unlock(&rq->lock); +} + +/* + * Called to set the hrtick timer state. + * + * called with rq->lock held and irqs disabled + */ +void hrtick_start(struct rq *rq, u64 delay) +{ + struct hrtimer *timer = &rq->hrtick_timer; + ktime_t time; + s64 delta; + + /* + * Don't schedule slices shorter than 10000ns, that just + * doesn't make sense and can cause timer DoS. + */ + delta = max_t(s64, delay, 10000LL); + time = ktime_add_ns(timer->base->get_time(), delta); + + hrtimer_set_expires(timer, time); + + if (rq == this_rq()) { + __hrtick_restart(rq); + } else if (!rq->hrtick_csd_pending) { + smp_call_function_single_async(cpu_of(rq), &rq->hrtick_csd); + rq->hrtick_csd_pending = 1; + } +} + +static int +hotplug_hrtick(struct notifier_block *nfb, unsigned long action, void *hcpu) +{ + int cpu = (int)(long)hcpu; + + switch (action) { + case CPU_UP_CANCELED: + case CPU_UP_CANCELED_FROZEN: + case CPU_DOWN_PREPARE: + case CPU_DOWN_PREPARE_FROZEN: + case CPU_DEAD: + case CPU_DEAD_FROZEN: + hrtick_clear(cpu_rq(cpu)); + return NOTIFY_OK; + } + + return NOTIFY_DONE; +} + +static __init void init_hrtick(void) +{ + hotcpu_notifier(hotplug_hrtick, 0); +} +#else +/* + * Called to set the hrtick timer state. + * + * called with rq->lock held and irqs disabled + */ +void hrtick_start(struct rq *rq, u64 delay) +{ + /* + * Don't schedule slices shorter than 10000ns, that just + * doesn't make sense. Rely on vruntime for fairness. + */ + delay = max_t(u64, delay, 10000LL); + __hrtimer_start_range_ns(&rq->hrtick_timer, ns_to_ktime(delay), 0, + HRTIMER_MODE_REL_PINNED, 0); +} + +static inline void init_hrtick(void) +{ +} +#endif /* CONFIG_SMP */ + +static void init_rq_hrtick(struct rq *rq) +{ +#ifdef CONFIG_SMP + rq->hrtick_csd_pending = 0; + + rq->hrtick_csd.flags = 0; + rq->hrtick_csd.func = __hrtick_start; + rq->hrtick_csd.info = rq; +#endif + + hrtimer_init(&rq->hrtick_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + rq->hrtick_timer.function = hrtick; + rq->hrtick_timer.irqsafe = 1; +} +#else /* CONFIG_SCHED_HRTICK */ +static inline void hrtick_clear(struct rq *rq) +{ +} + +static inline void init_rq_hrtick(struct rq *rq) +{ +} + +static inline void init_hrtick(void) +{ +} +#endif /* CONFIG_SCHED_HRTICK */ + +/* + * cmpxchg based fetch_or, macro so it works for different integer types + */ +#define fetch_or(ptr, val) \ +({ typeof(*(ptr)) __old, __val = *(ptr); \ + for (;;) { \ + __old = cmpxchg((ptr), __val, __val | (val)); \ + if (__old == __val) \ + break; \ + __val = __old; \ + } \ + __old; \ +}) + +#if defined(CONFIG_SMP) && defined(TIF_POLLING_NRFLAG) +/* + * Atomically set TIF_NEED_RESCHED and test for TIF_POLLING_NRFLAG, + * this avoids any races wrt polling state changes and thereby avoids + * spurious IPIs. + */ +static bool set_nr_and_not_polling(struct task_struct *p) +{ + struct thread_info *ti = task_thread_info(p); + return !(fetch_or(&ti->flags, _TIF_NEED_RESCHED) & _TIF_POLLING_NRFLAG); +} + +/* + * Atomically set TIF_NEED_RESCHED if TIF_POLLING_NRFLAG is set. + * + * If this returns true, then the idle task promises to call + * sched_ttwu_pending() and reschedule soon. + */ +static bool set_nr_if_polling(struct task_struct *p) +{ + struct thread_info *ti = task_thread_info(p); + typeof(ti->flags) old, val = ACCESS_ONCE(ti->flags); + + for (;;) { + if (!(val & _TIF_POLLING_NRFLAG)) + return false; + if (val & _TIF_NEED_RESCHED) + return true; + old = cmpxchg(&ti->flags, val, val | _TIF_NEED_RESCHED); + if (old == val) + break; + val = old; + } + return true; +} + +#else +static bool set_nr_and_not_polling(struct task_struct *p) +{ + set_tsk_need_resched(p); + return true; +} + +#ifdef CONFIG_SMP +static bool set_nr_if_polling(struct task_struct *p) +{ + return false; +} +#endif +#endif + +void wake_q_add(struct wake_q_head *head, struct task_struct *task) +{ + struct wake_q_node *node = &task->wake_q; + + /* + * Atomically grab the task, if ->wake_q is !nil already it means + * its already queued (either by us or someone else) and will get the + * wakeup due to that. + * + * This cmpxchg() implies a full barrier, which pairs with the write + * barrier implied by the wakeup in wake_up_list(). + */ + if (cmpxchg(&node->next, NULL, WAKE_Q_TAIL)) + return; + + get_task_struct(task); + + /* + * The head is context local, there can be no concurrency. + */ + *head->lastp = node; + head->lastp = &node->next; +} + +void wake_up_q(struct wake_q_head *head) +{ + struct wake_q_node *node = head->first; + + while (node != WAKE_Q_TAIL) { + struct task_struct *task; + + task = container_of(node, struct task_struct, wake_q); + BUG_ON(!task); + /* task can safely be re-inserted now */ + node = node->next; + task->wake_q.next = NULL; + + /* + * wake_up_process() implies a wmb() to pair with the queueing + * in wake_q_add() so as not to miss wakeups. + */ + wake_up_process(task); + put_task_struct(task); + } +} + +/* + * resched_curr - mark rq's current task 'to be rescheduled now'. + * + * On UP this means the setting of the need_resched flag, on SMP it + * might also involve a cross-CPU call to trigger the scheduler on + * the target CPU. + */ +void resched_curr(struct rq *rq) +{ + struct task_struct *curr = rq->curr; + int cpu; + + lockdep_assert_held(&rq->lock); + + if (test_tsk_need_resched(curr)) + return; + + cpu = cpu_of(rq); + + if (cpu == smp_processor_id()) { + set_tsk_need_resched(curr); + set_preempt_need_resched(); + return; + } + + if (set_nr_and_not_polling(curr)) + smp_send_reschedule(cpu); + else + trace_sched_wake_idle_without_ipi(cpu); +} + +#ifdef CONFIG_PREEMPT_LAZY +void resched_curr_lazy(struct rq *rq) +{ + struct task_struct *curr = rq->curr; + int cpu; + + if (!sched_feat(PREEMPT_LAZY)) { + resched_curr(rq); + return; + } + + lockdep_assert_held(&rq->lock); + + if (test_tsk_need_resched(curr)) + return; + + if (test_tsk_need_resched_lazy(curr)) + return; + + set_tsk_need_resched_lazy(curr); + + cpu = cpu_of(rq); + if (cpu == smp_processor_id()) + return; + + /* NEED_RESCHED_LAZY must be visible before we test polling */ + smp_mb(); + if (!tsk_is_polling(curr)) + smp_send_reschedule(cpu); +} +#endif + +void resched_cpu(int cpu) +{ + struct rq *rq = cpu_rq(cpu); + unsigned long flags; + + if (!raw_spin_trylock_irqsave(&rq->lock, flags)) + return; + resched_curr(rq); + raw_spin_unlock_irqrestore(&rq->lock, flags); +} + +#ifdef CONFIG_SMP +#ifdef CONFIG_NO_HZ_COMMON +/* + * In the semi idle case, use the nearest busy cpu for migrating timers + * from an idle cpu. This is good for power-savings. + * + * We don't do similar optimization for completely idle system, as + * selecting an idle cpu will add more delays to the timers than intended + * (as that cpu's timer base may not be uptodate wrt jiffies etc). + */ +int get_nohz_timer_target(int pinned) +{ + int cpu; + int i; + struct sched_domain *sd; + + preempt_disable_rt(); + cpu = smp_processor_id(); + if (pinned || !get_sysctl_timer_migration() || !idle_cpu(cpu)) + goto preempt_en_rt; + + rcu_read_lock(); + for_each_domain(cpu, sd) { + for_each_cpu(i, sched_domain_span(sd)) { + if (!idle_cpu(i)) { + cpu = i; + goto unlock; + } + } + } +unlock: + rcu_read_unlock(); +preempt_en_rt: + preempt_enable_rt(); + return cpu; +} +/* + * When add_timer_on() enqueues a timer into the timer wheel of an + * idle CPU then this timer might expire before the next timer event + * which is scheduled to wake up that CPU. In case of a completely + * idle system the next event might even be infinite time into the + * future. wake_up_idle_cpu() ensures that the CPU is woken up and + * leaves the inner idle loop so the newly added timer is taken into + * account when the CPU goes back to idle and evaluates the timer + * wheel for the next timer event. + */ +static void wake_up_idle_cpu(int cpu) +{ + struct rq *rq = cpu_rq(cpu); + + if (cpu == smp_processor_id()) + return; + + if (set_nr_and_not_polling(rq->idle)) + smp_send_reschedule(cpu); + else + trace_sched_wake_idle_without_ipi(cpu); +} + +static bool wake_up_full_nohz_cpu(int cpu) +{ + /* + * We just need the target to call irq_exit() and re-evaluate + * the next tick. The nohz full kick at least implies that. + * If needed we can still optimize that later with an + * empty IRQ. + */ + if (tick_nohz_full_cpu(cpu)) { + if (cpu != smp_processor_id() || + tick_nohz_tick_stopped()) + tick_nohz_full_kick_cpu(cpu); + return true; + } + + return false; +} + +void wake_up_nohz_cpu(int cpu) +{ + if (!wake_up_full_nohz_cpu(cpu)) + wake_up_idle_cpu(cpu); +} + +static inline bool got_nohz_idle_kick(void) +{ + int cpu = smp_processor_id(); + + if (!test_bit(NOHZ_BALANCE_KICK, nohz_flags(cpu))) + return false; + + if (idle_cpu(cpu) && !need_resched()) + return true; + + /* + * We can't run Idle Load Balance on this CPU for this time so we + * cancel it and clear NOHZ_BALANCE_KICK + */ + clear_bit(NOHZ_BALANCE_KICK, nohz_flags(cpu)); + return false; +} + +#else /* CONFIG_NO_HZ_COMMON */ + +static inline bool got_nohz_idle_kick(void) +{ + return false; +} + +#endif /* CONFIG_NO_HZ_COMMON */ + +#ifdef CONFIG_NO_HZ_FULL +bool sched_can_stop_tick(void) +{ + /* + * FIFO realtime policy runs the highest priority task. Other runnable + * tasks are of a lower priority. The scheduler tick does nothing. + */ + if (current->policy == SCHED_FIFO) + return true; + + /* + * Round-robin realtime tasks time slice with other tasks at the same + * realtime priority. Is this task the only one at this priority? + */ + if (current->policy == SCHED_RR) { + struct sched_rt_entity *rt_se = ¤t->rt; + + return rt_se->run_list.prev == rt_se->run_list.next; + } + + /* + * More than one running task need preemption. + * nr_running update is assumed to be visible + * after IPI is sent from wakers. + */ + if (this_rq()->nr_running > 1) + return false; + + return true; +} +#endif /* CONFIG_NO_HZ_FULL */ + +void sched_avg_update(struct rq *rq) +{ + s64 period = sched_avg_period(); + + while ((s64)(rq_clock(rq) - rq->age_stamp) > period) { + /* + * Inline assembly required to prevent the compiler + * optimising this loop into a divmod call. + * See __iter_div_u64_rem() for another example of this. + */ + asm("" : "+rm" (rq->age_stamp)); + rq->age_stamp += period; + rq->rt_avg /= 2; + } +} + +#endif /* CONFIG_SMP */ + +#if defined(CONFIG_RT_GROUP_SCHED) || (defined(CONFIG_FAIR_GROUP_SCHED) && \ + (defined(CONFIG_SMP) || defined(CONFIG_CFS_BANDWIDTH))) +/* + * Iterate task_group tree rooted at *from, calling @down when first entering a + * node and @up when leaving it for the final time. + * + * Caller must hold rcu_lock or sufficient equivalent. + */ +int walk_tg_tree_from(struct task_group *from, + tg_visitor down, tg_visitor up, void *data) +{ + struct task_group *parent, *child; + int ret; + + parent = from; + +down: + ret = (*down)(parent, data); + if (ret) + goto out; + list_for_each_entry_rcu(child, &parent->children, siblings) { + parent = child; + goto down; + +up: + continue; + } + ret = (*up)(parent, data); + if (ret || parent == from) + goto out; + + child = parent; + parent = parent->parent; + if (parent) + goto up; +out: + return ret; +} + +int tg_nop(struct task_group *tg, void *data) +{ + return 0; +} +#endif + +static void set_load_weight(struct task_struct *p) +{ + int prio = p->static_prio - MAX_RT_PRIO; + struct load_weight *load = &p->se.load; + + /* + * SCHED_IDLE tasks get minimal weight: + */ + if (p->policy == SCHED_IDLE) { + load->weight = scale_load(WEIGHT_IDLEPRIO); + load->inv_weight = WMULT_IDLEPRIO; + return; + } + + load->weight = scale_load(prio_to_weight[prio]); + load->inv_weight = prio_to_wmult[prio]; +} + +static void enqueue_task(struct rq *rq, struct task_struct *p, int flags) +{ + update_rq_clock(rq); + sched_info_queued(rq, p); + p->sched_class->enqueue_task(rq, p, flags); +} + +static void dequeue_task(struct rq *rq, struct task_struct *p, int flags) +{ + update_rq_clock(rq); + sched_info_dequeued(rq, p); + p->sched_class->dequeue_task(rq, p, flags); +} + +void activate_task(struct rq *rq, struct task_struct *p, int flags) +{ + if (task_contributes_to_load(p)) + rq->nr_uninterruptible--; + + enqueue_task(rq, p, flags); +} + +void deactivate_task(struct rq *rq, struct task_struct *p, int flags) +{ + if (task_contributes_to_load(p)) + rq->nr_uninterruptible++; + + dequeue_task(rq, p, flags); +} + +static void update_rq_clock_task(struct rq *rq, s64 delta) +{ +/* + * In theory, the compile should just see 0 here, and optimize out the call + * to sched_rt_avg_update. But I don't trust it... + */ +#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING) + s64 steal = 0, irq_delta = 0; +#endif +#ifdef CONFIG_IRQ_TIME_ACCOUNTING + irq_delta = irq_time_read(cpu_of(rq)) - rq->prev_irq_time; + + /* + * Since irq_time is only updated on {soft,}irq_exit, we might run into + * this case when a previous update_rq_clock() happened inside a + * {soft,}irq region. + * + * When this happens, we stop ->clock_task and only update the + * prev_irq_time stamp to account for the part that fit, so that a next + * update will consume the rest. This ensures ->clock_task is + * monotonic. + * + * It does however cause some slight miss-attribution of {soft,}irq + * time, a more accurate solution would be to update the irq_time using + * the current rq->clock timestamp, except that would require using + * atomic ops. + */ + if (irq_delta > delta) + irq_delta = delta; + + rq->prev_irq_time += irq_delta; + delta -= irq_delta; +#endif +#ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING + if (static_key_false((¶virt_steal_rq_enabled))) { + steal = paravirt_steal_clock(cpu_of(rq)); + steal -= rq->prev_steal_time_rq; + + if (unlikely(steal > delta)) + steal = delta; + + rq->prev_steal_time_rq += steal; + delta -= steal; + } +#endif + + rq->clock_task += delta; + +#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING) + if ((irq_delta + steal) && sched_feat(NONTASK_CAPACITY)) + sched_rt_avg_update(rq, irq_delta + steal); +#endif +} + +void sched_set_stop_task(int cpu, struct task_struct *stop) +{ + struct sched_param param = { .sched_priority = MAX_RT_PRIO - 1 }; + struct task_struct *old_stop = cpu_rq(cpu)->stop; + + if (stop) { + /* + * Make it appear like a SCHED_FIFO task, its something + * userspace knows about and won't get confused about. + * + * Also, it will make PI more or less work without too + * much confusion -- but then, stop work should not + * rely on PI working anyway. + */ + sched_setscheduler_nocheck(stop, SCHED_FIFO, ¶m); + + stop->sched_class = &stop_sched_class; + } + + cpu_rq(cpu)->stop = stop; + + if (old_stop) { + /* + * Reset it back to a normal scheduling class so that + * it can die in pieces. + */ + old_stop->sched_class = &rt_sched_class; + } +} + +/* + * __normal_prio - return the priority that is based on the static prio + */ +static inline int __normal_prio(struct task_struct *p) +{ + return p->static_prio; +} + +/* + * Calculate the expected normal priority: i.e. priority + * without taking RT-inheritance into account. Might be + * boosted by interactivity modifiers. Changes upon fork, + * setprio syscalls, and whenever the interactivity + * estimator recalculates. + */ +static inline int normal_prio(struct task_struct *p) +{ + int prio; + + if (task_has_dl_policy(p)) + prio = MAX_DL_PRIO-1; + else if (task_has_rt_policy(p)) + prio = MAX_RT_PRIO-1 - p->rt_priority; + else + prio = __normal_prio(p); + return prio; +} + +/* + * Calculate the current priority, i.e. the priority + * taken into account by the scheduler. This value might + * be boosted by RT tasks, or might be boosted by + * interactivity modifiers. Will be RT if the task got + * RT-boosted. If not then it returns p->normal_prio. + */ +static int effective_prio(struct task_struct *p) +{ + p->normal_prio = normal_prio(p); + /* + * If we are RT tasks or we were boosted to RT priority, + * keep the priority unchanged. Otherwise, update priority + * to the normal priority: + */ + if (!rt_prio(p->prio)) + return p->normal_prio; + return p->prio; +} + +/** + * task_curr - is this task currently executing on a CPU? + * @p: the task in question. + * + * Return: 1 if the task is currently executing. 0 otherwise. + */ +inline int task_curr(const struct task_struct *p) +{ + return cpu_curr(task_cpu(p)) == p; +} + +/* + * Can drop rq->lock because from sched_class::switched_from() methods drop it. + */ +static inline void check_class_changed(struct rq *rq, struct task_struct *p, + const struct sched_class *prev_class, + int oldprio) +{ + if (prev_class != p->sched_class) { + if (prev_class->switched_from) + prev_class->switched_from(rq, p); + /* Possble rq->lock 'hole'. */ + p->sched_class->switched_to(rq, p); + } else if (oldprio != p->prio || dl_task(p)) + p->sched_class->prio_changed(rq, p, oldprio); +} + +void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags) +{ + const struct sched_class *class; + + if (p->sched_class == rq->curr->sched_class) { + rq->curr->sched_class->check_preempt_curr(rq, p, flags); + } else { + for_each_class(class) { + if (class == rq->curr->sched_class) + break; + if (class == p->sched_class) { + resched_curr(rq); + break; + } + } + } + + /* + * A queue event has occurred, and we're going to schedule. In + * this case, we can save a useless back to back clock update. + */ + if (task_on_rq_queued(rq->curr) && test_tsk_need_resched(rq->curr)) + rq_clock_skip_update(rq, true); +} + +#ifdef CONFIG_SMP +void set_task_cpu(struct task_struct *p, unsigned int new_cpu) +{ +#ifdef CONFIG_SCHED_DEBUG + /* + * We should never call set_task_cpu() on a blocked task, + * ttwu() will sort out the placement. + */ + WARN_ON_ONCE(p->state != TASK_RUNNING && p->state != TASK_WAKING && + !p->on_rq); + +#ifdef CONFIG_LOCKDEP + /* + * The caller should hold either p->pi_lock or rq->lock, when changing + * a task's CPU. ->pi_lock for waking tasks, rq->lock for runnable tasks. + * + * sched_move_task() holds both and thus holding either pins the cgroup, + * see task_group(). + * + * Furthermore, all task_rq users should acquire both locks, see + * task_rq_lock(). + */ + WARN_ON_ONCE(debug_locks && !(lockdep_is_held(&p->pi_lock) || + lockdep_is_held(&task_rq(p)->lock))); +#endif +#endif + + trace_sched_migrate_task(p, new_cpu); + + if (task_cpu(p) != new_cpu) { + if (p->sched_class->migrate_task_rq) + p->sched_class->migrate_task_rq(p, new_cpu); + p->se.nr_migrations++; + perf_sw_event_sched(PERF_COUNT_SW_CPU_MIGRATIONS, 1, 0); + } + + __set_task_cpu(p, new_cpu); +} + +static void __migrate_swap_task(struct task_struct *p, int cpu) +{ + if (task_on_rq_queued(p)) { + struct rq *src_rq, *dst_rq; + + src_rq = task_rq(p); + dst_rq = cpu_rq(cpu); + + deactivate_task(src_rq, p, 0); + set_task_cpu(p, cpu); + activate_task(dst_rq, p, 0); + check_preempt_curr(dst_rq, p, 0); + } else { + /* + * Task isn't running anymore; make it appear like we migrated + * it before it went to sleep. This means on wakeup we make the + * previous cpu our targer instead of where it really is. + */ + p->wake_cpu = cpu; + } +} + +struct migration_swap_arg { + struct task_struct *src_task, *dst_task; + int src_cpu, dst_cpu; +}; + +static int migrate_swap_stop(void *data) +{ + struct migration_swap_arg *arg = data; + struct rq *src_rq, *dst_rq; + int ret = -EAGAIN; + + src_rq = cpu_rq(arg->src_cpu); + dst_rq = cpu_rq(arg->dst_cpu); + + double_raw_lock(&arg->src_task->pi_lock, + &arg->dst_task->pi_lock); + double_rq_lock(src_rq, dst_rq); + if (task_cpu(arg->dst_task) != arg->dst_cpu) + goto unlock; + + if (task_cpu(arg->src_task) != arg->src_cpu) + goto unlock; + + if (!cpumask_test_cpu(arg->dst_cpu, tsk_cpus_allowed(arg->src_task))) + goto unlock; + + if (!cpumask_test_cpu(arg->src_cpu, tsk_cpus_allowed(arg->dst_task))) + goto unlock; + + __migrate_swap_task(arg->src_task, arg->dst_cpu); + __migrate_swap_task(arg->dst_task, arg->src_cpu); + + ret = 0; + +unlock: + double_rq_unlock(src_rq, dst_rq); + raw_spin_unlock(&arg->dst_task->pi_lock); + raw_spin_unlock(&arg->src_task->pi_lock); + + return ret; +} + +/* + * Cross migrate two tasks + */ +int migrate_swap(struct task_struct *cur, struct task_struct *p) +{ + struct migration_swap_arg arg; + int ret = -EINVAL; + + arg = (struct migration_swap_arg){ + .src_task = cur, + .src_cpu = task_cpu(cur), + .dst_task = p, + .dst_cpu = task_cpu(p), + }; + + if (arg.src_cpu == arg.dst_cpu) + goto out; + + /* + * These three tests are all lockless; this is OK since all of them + * will be re-checked with proper locks held further down the line. + */ + if (!cpu_active(arg.src_cpu) || !cpu_active(arg.dst_cpu)) + goto out; + + if (!cpumask_test_cpu(arg.dst_cpu, tsk_cpus_allowed(arg.src_task))) + goto out; + + if (!cpumask_test_cpu(arg.src_cpu, tsk_cpus_allowed(arg.dst_task))) + goto out; + + trace_sched_swap_numa(cur, arg.src_cpu, p, arg.dst_cpu); + ret = stop_two_cpus(arg.dst_cpu, arg.src_cpu, migrate_swap_stop, &arg); + +out: + return ret; +} + +struct migration_arg { + struct task_struct *task; + int dest_cpu; +}; + +static int migration_cpu_stop(void *data); + +static bool check_task_state(struct task_struct *p, long match_state) +{ + bool match = false; + + raw_spin_lock_irq(&p->pi_lock); + if (p->state == match_state || p->saved_state == match_state) + match = true; + raw_spin_unlock_irq(&p->pi_lock); + + return match; +} + +/* + * wait_task_inactive - wait for a thread to unschedule. + * + * If @match_state is nonzero, it's the @p->state value just checked and + * not expected to change. If it changes, i.e. @p might have woken up, + * then return zero. When we succeed in waiting for @p to be off its CPU, + * we return a positive number (its total switch count). If a second call + * a short while later returns the same number, the caller can be sure that + * @p has remained unscheduled the whole time. + * + * The caller must ensure that the task *will* unschedule sometime soon, + * else this function might spin for a *long* time. This function can't + * be called with interrupts off, or it may introduce deadlock with + * smp_call_function() if an IPI is sent by the same process we are + * waiting to become inactive. + */ +unsigned long wait_task_inactive(struct task_struct *p, long match_state) +{ + unsigned long flags; + int running, queued; + unsigned long ncsw; + struct rq *rq; + + for (;;) { + /* + * We do the initial early heuristics without holding + * any task-queue locks at all. We'll only try to get + * the runqueue lock when things look like they will + * work out! + */ + rq = task_rq(p); + + /* + * If the task is actively running on another CPU + * still, just relax and busy-wait without holding + * any locks. + * + * NOTE! Since we don't hold any locks, it's not + * even sure that "rq" stays as the right runqueue! + * But we don't care, since "task_running()" will + * return false if the runqueue has changed and p + * is actually now running somewhere else! + */ + while (task_running(rq, p)) { + if (match_state && !check_task_state(p, match_state)) + return 0; + cpu_relax(); + } + + /* + * Ok, time to look more closely! We need the rq + * lock now, to be *sure*. If we're wrong, we'll + * just go back and repeat. + */ + rq = task_rq_lock(p, &flags); + trace_sched_wait_task(p); + running = task_running(rq, p); + queued = task_on_rq_queued(p); + ncsw = 0; + if (!match_state || p->state == match_state || + p->saved_state == match_state) + ncsw = p->nvcsw | LONG_MIN; /* sets MSB */ + task_rq_unlock(rq, p, &flags); + + /* + * If it changed from the expected state, bail out now. + */ + if (unlikely(!ncsw)) + break; + + /* + * Was it really running after all now that we + * checked with the proper locks actually held? + * + * Oops. Go back and try again.. + */ + if (unlikely(running)) { + cpu_relax(); + continue; + } + + /* + * It's not enough that it's not actively running, + * it must be off the runqueue _entirely_, and not + * preempted! + * + * So if it was still runnable (but just not actively + * running right now), it's preempted, and we should + * yield - it could be a while. + */ + if (unlikely(queued)) { + ktime_t to = ktime_set(0, NSEC_PER_SEC/HZ); + + set_current_state(TASK_UNINTERRUPTIBLE); + schedule_hrtimeout(&to, HRTIMER_MODE_REL); + continue; + } + + /* + * Ahh, all good. It wasn't running, and it wasn't + * runnable, which means that it will never become + * running in the future either. We're all done! + */ + break; + } + + return ncsw; +} + +/*** + * kick_process - kick a running thread to enter/exit the kernel + * @p: the to-be-kicked thread + * + * Cause a process which is running on another CPU to enter + * kernel-mode, without any delay. (to get signals handled.) + * + * NOTE: this function doesn't have to take the runqueue lock, + * because all it wants to ensure is that the remote task enters + * the kernel. If the IPI races and the task has been migrated + * to another CPU then no harm is done and the purpose has been + * achieved as well. + */ +void kick_process(struct task_struct *p) +{ + int cpu; + + preempt_disable(); + cpu = task_cpu(p); + if ((cpu != smp_processor_id()) && task_curr(p)) + smp_send_reschedule(cpu); + preempt_enable(); +} +EXPORT_SYMBOL_GPL(kick_process); +#endif /* CONFIG_SMP */ + +#ifdef CONFIG_SMP +/* + * ->cpus_allowed is protected by both rq->lock and p->pi_lock + */ +static int select_fallback_rq(int cpu, struct task_struct *p) +{ + int nid = cpu_to_node(cpu); + const struct cpumask *nodemask = NULL; + enum { cpuset, possible, fail } state = cpuset; + int dest_cpu; + + /* + * If the node that the cpu is on has been offlined, cpu_to_node() + * will return -1. There is no cpu on the node, and we should + * select the cpu on the other node. + */ + if (nid != -1) { + nodemask = cpumask_of_node(nid); + + /* Look for allowed, online CPU in same node. */ + for_each_cpu(dest_cpu, nodemask) { + if (!cpu_online(dest_cpu)) + continue; + if (!cpu_active(dest_cpu)) + continue; + if (cpumask_test_cpu(dest_cpu, tsk_cpus_allowed(p))) + return dest_cpu; + } + } + + for (;;) { + /* Any allowed, online CPU? */ + for_each_cpu(dest_cpu, tsk_cpus_allowed(p)) { + if (!cpu_online(dest_cpu)) + continue; + if (!cpu_active(dest_cpu)) + continue; + goto out; + } + + switch (state) { + case cpuset: + /* No more Mr. Nice Guy. */ + cpuset_cpus_allowed_fallback(p); + state = possible; + break; + + case possible: + do_set_cpus_allowed(p, cpu_possible_mask); + state = fail; + break; + + case fail: + BUG(); + break; + } + } + +out: + if (state != cpuset) { + /* + * Don't tell them about moving exiting tasks or + * kernel threads (both mm NULL), since they never + * leave kernel. + */ + if (p->mm && printk_ratelimit()) { + printk_deferred("process %d (%s) no longer affine to cpu%d\n", + task_pid_nr(p), p->comm, cpu); + } + } + + return dest_cpu; +} + +/* + * The caller (fork, wakeup) owns p->pi_lock, ->cpus_allowed is stable. + */ +static inline +int select_task_rq(struct task_struct *p, int cpu, int sd_flags, int wake_flags) +{ + if (p->nr_cpus_allowed > 1) + cpu = p->sched_class->select_task_rq(p, cpu, sd_flags, wake_flags); + + /* + * In order not to call set_task_cpu() on a blocking task we need + * to rely on ttwu() to place the task on a valid ->cpus_allowed + * cpu. + * + * Since this is common to all placement strategies, this lives here. + * + * [ this allows ->select_task() to simply return task_cpu(p) and + * not worry about this generic constraint ] + */ + if (unlikely(!cpumask_test_cpu(cpu, tsk_cpus_allowed(p)) || + !cpu_online(cpu))) + cpu = select_fallback_rq(task_cpu(p), p); + + return cpu; +} + +static void update_avg(u64 *avg, u64 sample) +{ + s64 diff = sample - *avg; + *avg += diff >> 3; +} +#endif + +static void +ttwu_stat(struct task_struct *p, int cpu, int wake_flags) +{ +#ifdef CONFIG_SCHEDSTATS + struct rq *rq = this_rq(); + +#ifdef CONFIG_SMP + int this_cpu = smp_processor_id(); + + if (cpu == this_cpu) { + schedstat_inc(rq, ttwu_local); + schedstat_inc(p, se.statistics.nr_wakeups_local); + } else { + struct sched_domain *sd; + + schedstat_inc(p, se.statistics.nr_wakeups_remote); + rcu_read_lock(); + for_each_domain(this_cpu, sd) { + if (cpumask_test_cpu(cpu, sched_domain_span(sd))) { + schedstat_inc(sd, ttwu_wake_remote); + break; + } + } + rcu_read_unlock(); + } + + if (wake_flags & WF_MIGRATED) + schedstat_inc(p, se.statistics.nr_wakeups_migrate); + +#endif /* CONFIG_SMP */ + + schedstat_inc(rq, ttwu_count); + schedstat_inc(p, se.statistics.nr_wakeups); + + if (wake_flags & WF_SYNC) + schedstat_inc(p, se.statistics.nr_wakeups_sync); + +#endif /* CONFIG_SCHEDSTATS */ +} + +static void ttwu_activate(struct rq *rq, struct task_struct *p, int en_flags) +{ + activate_task(rq, p, en_flags); + p->on_rq = TASK_ON_RQ_QUEUED; +} + +/* + * Mark the task runnable and perform wakeup-preemption. + */ +static void +ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags) +{ + check_preempt_curr(rq, p, wake_flags); + trace_sched_wakeup(p, true); + + p->state = TASK_RUNNING; +#ifdef CONFIG_SMP + if (p->sched_class->task_woken) + p->sched_class->task_woken(rq, p); + + if (rq->idle_stamp) { + u64 delta = rq_clock(rq) - rq->idle_stamp; + u64 max = 2*rq->max_idle_balance_cost; + + update_avg(&rq->avg_idle, delta); + + if (rq->avg_idle > max) + rq->avg_idle = max; + + rq->idle_stamp = 0; + } +#endif +} + +static void +ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags) +{ +#ifdef CONFIG_SMP + if (p->sched_contributes_to_load) + rq->nr_uninterruptible--; +#endif + + ttwu_activate(rq, p, ENQUEUE_WAKEUP | ENQUEUE_WAKING); + ttwu_do_wakeup(rq, p, wake_flags); +} + +/* + * Called in case the task @p isn't fully descheduled from its runqueue, + * in this case we must do a remote wakeup. Its a 'light' wakeup though, + * since all we need to do is flip p->state to TASK_RUNNING, since + * the task is still ->on_rq. + */ +static int ttwu_remote(struct task_struct *p, int wake_flags) +{ + struct rq *rq; + int ret = 0; + + rq = __task_rq_lock(p); + if (task_on_rq_queued(p)) { + /* check_preempt_curr() may use rq clock */ + update_rq_clock(rq); + ttwu_do_wakeup(rq, p, wake_flags); + ret = 1; + } + __task_rq_unlock(rq); + + return ret; +} + +#ifdef CONFIG_SMP +void sched_ttwu_pending(void) +{ + struct rq *rq = this_rq(); + struct llist_node *llist = llist_del_all(&rq->wake_list); + struct task_struct *p; + unsigned long flags; + + if (!llist) + return; + + raw_spin_lock_irqsave(&rq->lock, flags); + + while (llist) { + p = llist_entry(llist, struct task_struct, wake_entry); + llist = llist_next(llist); + ttwu_do_activate(rq, p, 0); + } + + raw_spin_unlock_irqrestore(&rq->lock, flags); +} + +void scheduler_ipi(void) +{ + /* + * Fold TIF_NEED_RESCHED into the preempt_count; anybody setting + * TIF_NEED_RESCHED remotely (for the first time) will also send + * this IPI. + */ + preempt_fold_need_resched(); + + if (llist_empty(&this_rq()->wake_list) && !got_nohz_idle_kick()) + return; + + /* + * Not all reschedule IPI handlers call irq_enter/irq_exit, since + * traditionally all their work was done from the interrupt return + * path. Now that we actually do some work, we need to make sure + * we do call them. + * + * Some archs already do call them, luckily irq_enter/exit nest + * properly. + * + * Arguably we should visit all archs and update all handlers, + * however a fair share of IPIs are still resched only so this would + * somewhat pessimize the simple resched case. + */ + irq_enter(); + sched_ttwu_pending(); + + /* + * Check if someone kicked us for doing the nohz idle load balance. + */ + if (unlikely(got_nohz_idle_kick())) { + this_rq()->idle_balance = 1; + raise_softirq_irqoff(SCHED_SOFTIRQ); + } + irq_exit(); +} + +static void ttwu_queue_remote(struct task_struct *p, int cpu) +{ + struct rq *rq = cpu_rq(cpu); + + if (llist_add(&p->wake_entry, &cpu_rq(cpu)->wake_list)) { + if (!set_nr_if_polling(rq->idle)) + smp_send_reschedule(cpu); + else + trace_sched_wake_idle_without_ipi(cpu); + } +} + +void wake_up_if_idle(int cpu) +{ + struct rq *rq = cpu_rq(cpu); + unsigned long flags; + + rcu_read_lock(); + + if (!is_idle_task(rcu_dereference(rq->curr))) + goto out; + + if (set_nr_if_polling(rq->idle)) { + trace_sched_wake_idle_without_ipi(cpu); + } else { + raw_spin_lock_irqsave(&rq->lock, flags); + if (is_idle_task(rq->curr)) + smp_send_reschedule(cpu); + /* Else cpu is not in idle, do nothing here */ + raw_spin_unlock_irqrestore(&rq->lock, flags); + } + +out: + rcu_read_unlock(); +} + +bool cpus_share_cache(int this_cpu, int that_cpu) +{ + return per_cpu(sd_llc_id, this_cpu) == per_cpu(sd_llc_id, that_cpu); +} +#endif /* CONFIG_SMP */ + +static void ttwu_queue(struct task_struct *p, int cpu) +{ + struct rq *rq = cpu_rq(cpu); + +#if defined(CONFIG_SMP) + if (sched_feat(TTWU_QUEUE) && !cpus_share_cache(smp_processor_id(), cpu)) { + sched_clock_cpu(cpu); /* sync clocks x-cpu */ + ttwu_queue_remote(p, cpu); + return; + } +#endif + + raw_spin_lock(&rq->lock); + ttwu_do_activate(rq, p, 0); + raw_spin_unlock(&rq->lock); +} + +/** + * try_to_wake_up - wake up a thread + * @p: the thread to be awakened + * @state: the mask of task states that can be woken + * @wake_flags: wake modifier flags (WF_*) + * + * Put it on the run-queue if it's not already there. The "current" + * thread is always on the run-queue (except when the actual + * re-schedule is in progress), and as such you're allowed to do + * the simpler "current->state = TASK_RUNNING" to mark yourself + * runnable without the overhead of this. + * + * Return: %true if @p was woken up, %false if it was already running. + * or @state didn't match @p's state. + */ +static int +try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) +{ + unsigned long flags; + int cpu, success = 0; + + /* + * If we are going to wake up a thread waiting for CONDITION we + * need to ensure that CONDITION=1 done by the caller can not be + * reordered with p->state check below. This pairs with mb() in + * set_current_state() the waiting thread does. + */ + smp_mb__before_spinlock(); + raw_spin_lock_irqsave(&p->pi_lock, flags); + if (!(p->state & state)) { + /* + * The task might be running due to a spinlock sleeper + * wakeup. Check the saved state and set it to running + * if the wakeup condition is true. + */ + if (!(wake_flags & WF_LOCK_SLEEPER)) { + if (p->saved_state & state) { + p->saved_state = TASK_RUNNING; + success = 1; + } + } + goto out; + } + + /* + * If this is a regular wakeup, then we can unconditionally + * clear the saved state of a "lock sleeper". + */ + if (!(wake_flags & WF_LOCK_SLEEPER)) + p->saved_state = TASK_RUNNING; + + success = 1; /* we're going to change ->state */ + cpu = task_cpu(p); + + if (p->on_rq && ttwu_remote(p, wake_flags)) + goto stat; + +#ifdef CONFIG_SMP + /* + * If the owning (remote) cpu is still in the middle of schedule() with + * this task as prev, wait until its done referencing the task. + */ + while (p->on_cpu) + cpu_relax(); + /* + * Pairs with the smp_wmb() in finish_lock_switch(). + */ + smp_rmb(); + + p->sched_contributes_to_load = !!task_contributes_to_load(p); + p->state = TASK_WAKING; + + if (p->sched_class->task_waking) + p->sched_class->task_waking(p); + + cpu = select_task_rq(p, p->wake_cpu, SD_BALANCE_WAKE, wake_flags); + if (task_cpu(p) != cpu) { + wake_flags |= WF_MIGRATED; + set_task_cpu(p, cpu); + } +#endif /* CONFIG_SMP */ + + ttwu_queue(p, cpu); +stat: + ttwu_stat(p, cpu, wake_flags); +out: + raw_spin_unlock_irqrestore(&p->pi_lock, flags); + + return success; +} + +/** + * wake_up_process - Wake up a specific process + * @p: The process to be woken up. + * + * Attempt to wake up the nominated process and move it to the set of runnable + * processes. + * + * Return: 1 if the process was woken up, 0 if it was already running. + * + * It may be assumed that this function implies a write memory barrier before + * changing the task state if and only if any tasks are woken up. + */ +int wake_up_process(struct task_struct *p) +{ + WARN_ON(__task_is_stopped_or_traced(p)); + return try_to_wake_up(p, TASK_NORMAL, 0); +} +EXPORT_SYMBOL(wake_up_process); + +/** + * wake_up_lock_sleeper - Wake up a specific process blocked on a "sleeping lock" + * @p: The process to be woken up. + * + * Same as wake_up_process() above, but wake_flags=WF_LOCK_SLEEPER to indicate + * the nature of the wakeup. + */ +int wake_up_lock_sleeper(struct task_struct *p) +{ + return try_to_wake_up(p, TASK_ALL, WF_LOCK_SLEEPER); +} + +int wake_up_state(struct task_struct *p, unsigned int state) +{ + return try_to_wake_up(p, state, 0); +} + +/* + * This function clears the sched_dl_entity static params. + */ +void __dl_clear_params(struct task_struct *p) +{ + struct sched_dl_entity *dl_se = &p->dl; + + dl_se->dl_runtime = 0; + dl_se->dl_deadline = 0; + dl_se->dl_period = 0; + dl_se->flags = 0; + dl_se->dl_bw = 0; + + dl_se->dl_throttled = 0; + dl_se->dl_new = 1; + dl_se->dl_yielded = 0; +} + +/* + * Perform scheduler related setup for a newly forked process p. + * p is forked by current. + * + * __sched_fork() is basic setup used by init_idle() too: + */ +static void __sched_fork(unsigned long clone_flags, struct task_struct *p) +{ + p->on_rq = 0; + + p->se.on_rq = 0; + p->se.exec_start = 0; + p->se.sum_exec_runtime = 0; + p->se.prev_sum_exec_runtime = 0; + p->se.nr_migrations = 0; + p->se.vruntime = 0; +#ifdef CONFIG_SMP + p->se.avg.decay_count = 0; +#endif + INIT_LIST_HEAD(&p->se.group_node); + +#ifdef CONFIG_SCHEDSTATS + memset(&p->se.statistics, 0, sizeof(p->se.statistics)); +#endif + + RB_CLEAR_NODE(&p->dl.rb_node); + init_dl_task_timer(&p->dl); + __dl_clear_params(p); + + INIT_LIST_HEAD(&p->rt.run_list); + +#ifdef CONFIG_PREEMPT_NOTIFIERS + INIT_HLIST_HEAD(&p->preempt_notifiers); +#endif + +#ifdef CONFIG_NUMA_BALANCING + if (p->mm && atomic_read(&p->mm->mm_users) == 1) { + p->mm->numa_next_scan = jiffies + msecs_to_jiffies(sysctl_numa_balancing_scan_delay); + p->mm->numa_scan_seq = 0; + } + + if (clone_flags & CLONE_VM) + p->numa_preferred_nid = current->numa_preferred_nid; + else + p->numa_preferred_nid = -1; + + p->node_stamp = 0ULL; + p->numa_scan_seq = p->mm ? p->mm->numa_scan_seq : 0; + p->numa_scan_period = sysctl_numa_balancing_scan_delay; + p->numa_work.next = &p->numa_work; + p->numa_faults = NULL; + p->last_task_numa_placement = 0; + p->last_sum_exec_runtime = 0; + + p->numa_group = NULL; +#endif /* CONFIG_NUMA_BALANCING */ +} + +#ifdef CONFIG_NUMA_BALANCING +#ifdef CONFIG_SCHED_DEBUG +void set_numabalancing_state(bool enabled) +{ + if (enabled) + sched_feat_set("NUMA"); + else + sched_feat_set("NO_NUMA"); +} +#else +__read_mostly bool numabalancing_enabled; + +void set_numabalancing_state(bool enabled) +{ + numabalancing_enabled = enabled; +} +#endif /* CONFIG_SCHED_DEBUG */ + +#ifdef CONFIG_PROC_SYSCTL +int sysctl_numa_balancing(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + struct ctl_table t; + int err; + int state = numabalancing_enabled; + + if (write && !capable(CAP_SYS_ADMIN)) + return -EPERM; + + t = *table; + t.data = &state; + err = proc_dointvec_minmax(&t, write, buffer, lenp, ppos); + if (err < 0) + return err; + if (write) + set_numabalancing_state(state); + return err; +} +#endif +#endif + +/* + * fork()/clone()-time setup: + */ +int sched_fork(unsigned long clone_flags, struct task_struct *p) +{ + unsigned long flags; + int cpu = get_cpu(); + + __sched_fork(clone_flags, p); + /* + * We mark the process as running here. This guarantees that + * nobody will actually run it, and a signal or other external + * event cannot wake it up and insert it on the runqueue either. + */ + p->state = TASK_RUNNING; + + /* + * Make sure we do not leak PI boosting priority to the child. + */ + p->prio = current->normal_prio; + + /* + * Revert to default priority/policy on fork if requested. + */ + if (unlikely(p->sched_reset_on_fork)) { + if (task_has_dl_policy(p) || task_has_rt_policy(p)) { + p->policy = SCHED_NORMAL; + p->static_prio = NICE_TO_PRIO(0); + p->rt_priority = 0; + } else if (PRIO_TO_NICE(p->static_prio) < 0) + p->static_prio = NICE_TO_PRIO(0); + + p->prio = p->normal_prio = __normal_prio(p); + set_load_weight(p); + + /* + * We don't need the reset flag anymore after the fork. It has + * fulfilled its duty: + */ + p->sched_reset_on_fork = 0; + } + + if (dl_prio(p->prio)) { + put_cpu(); + return -EAGAIN; + } else if (rt_prio(p->prio)) { + p->sched_class = &rt_sched_class; + } else { + p->sched_class = &fair_sched_class; + } + + if (p->sched_class->task_fork) + p->sched_class->task_fork(p); + + /* + * The child is not yet in the pid-hash so no cgroup attach races, + * and the cgroup is pinned to this child due to cgroup_fork() + * is ran before sched_fork(). + * + * Silence PROVE_RCU. + */ + raw_spin_lock_irqsave(&p->pi_lock, flags); + set_task_cpu(p, cpu); + raw_spin_unlock_irqrestore(&p->pi_lock, flags); + +#if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT) + if (likely(sched_info_on())) + memset(&p->sched_info, 0, sizeof(p->sched_info)); +#endif +#if defined(CONFIG_SMP) + p->on_cpu = 0; +#endif + init_task_preempt_count(p); +#ifdef CONFIG_HAVE_PREEMPT_LAZY + task_thread_info(p)->preempt_lazy_count = 0; +#endif +#ifdef CONFIG_SMP + plist_node_init(&p->pushable_tasks, MAX_PRIO); + RB_CLEAR_NODE(&p->pushable_dl_tasks); +#endif + + put_cpu(); + return 0; +} + +unsigned long to_ratio(u64 period, u64 runtime) +{ + if (runtime == RUNTIME_INF) + return 1ULL << 20; + + /* + * Doing this here saves a lot of checks in all + * the calling paths, and returning zero seems + * safe for them anyway. + */ + if (period == 0) + return 0; + + return div64_u64(runtime << 20, period); +} + +#ifdef CONFIG_SMP +inline struct dl_bw *dl_bw_of(int i) +{ + rcu_lockdep_assert(rcu_read_lock_sched_held(), + "sched RCU must be held"); + return &cpu_rq(i)->rd->dl_bw; +} + +static inline int dl_bw_cpus(int i) +{ + struct root_domain *rd = cpu_rq(i)->rd; + int cpus = 0; + + rcu_lockdep_assert(rcu_read_lock_sched_held(), + "sched RCU must be held"); + for_each_cpu_and(i, rd->span, cpu_active_mask) + cpus++; + + return cpus; +} +#else +inline struct dl_bw *dl_bw_of(int i) +{ + return &cpu_rq(i)->dl.dl_bw; +} + +static inline int dl_bw_cpus(int i) +{ + return 1; +} +#endif + +/* + * We must be sure that accepting a new task (or allowing changing the + * parameters of an existing one) is consistent with the bandwidth + * constraints. If yes, this function also accordingly updates the currently + * allocated bandwidth to reflect the new situation. + * + * This function is called while holding p's rq->lock. + * + * XXX we should delay bw change until the task's 0-lag point, see + * __setparam_dl(). + */ +static int dl_overflow(struct task_struct *p, int policy, + const struct sched_attr *attr) +{ + + struct dl_bw *dl_b = dl_bw_of(task_cpu(p)); + u64 period = attr->sched_period ?: attr->sched_deadline; + u64 runtime = attr->sched_runtime; + u64 new_bw = dl_policy(policy) ? to_ratio(period, runtime) : 0; + int cpus, err = -1; + + if (new_bw == p->dl.dl_bw) + return 0; + + /* + * Either if a task, enters, leave, or stays -deadline but changes + * its parameters, we may need to update accordingly the total + * allocated bandwidth of the container. + */ + raw_spin_lock(&dl_b->lock); + cpus = dl_bw_cpus(task_cpu(p)); + if (dl_policy(policy) && !task_has_dl_policy(p) && + !__dl_overflow(dl_b, cpus, 0, new_bw)) { + __dl_add(dl_b, new_bw); + err = 0; + } else if (dl_policy(policy) && task_has_dl_policy(p) && + !__dl_overflow(dl_b, cpus, p->dl.dl_bw, new_bw)) { + __dl_clear(dl_b, p->dl.dl_bw); + __dl_add(dl_b, new_bw); + err = 0; + } else if (!dl_policy(policy) && task_has_dl_policy(p)) { + __dl_clear(dl_b, p->dl.dl_bw); + err = 0; + } + raw_spin_unlock(&dl_b->lock); + + return err; +} + +extern void init_dl_bw(struct dl_bw *dl_b); + +/* + * wake_up_new_task - wake up a newly created task for the first time. + * + * This function will do some initial scheduler statistics housekeeping + * that must be done for every newly created context, then puts the task + * on the runqueue and wakes it. + */ +void wake_up_new_task(struct task_struct *p) +{ + unsigned long flags; + struct rq *rq; + + raw_spin_lock_irqsave(&p->pi_lock, flags); +#ifdef CONFIG_SMP + /* + * Fork balancing, do it here and not earlier because: + * - cpus_allowed can change in the fork path + * - any previously selected cpu might disappear through hotplug + */ + set_task_cpu(p, select_task_rq(p, task_cpu(p), SD_BALANCE_FORK, 0)); +#endif + + /* Initialize new task's runnable average */ + init_task_runnable_average(p); + rq = __task_rq_lock(p); + activate_task(rq, p, 0); + p->on_rq = TASK_ON_RQ_QUEUED; + trace_sched_wakeup_new(p, true); + check_preempt_curr(rq, p, WF_FORK); +#ifdef CONFIG_SMP + if (p->sched_class->task_woken) + p->sched_class->task_woken(rq, p); +#endif + task_rq_unlock(rq, p, &flags); +} + +#ifdef CONFIG_PREEMPT_NOTIFIERS + +/** + * preempt_notifier_register - tell me when current is being preempted & rescheduled + * @notifier: notifier struct to register + */ +void preempt_notifier_register(struct preempt_notifier *notifier) +{ + hlist_add_head(¬ifier->link, ¤t->preempt_notifiers); +} +EXPORT_SYMBOL_GPL(preempt_notifier_register); + +/** + * preempt_notifier_unregister - no longer interested in preemption notifications + * @notifier: notifier struct to unregister + * + * This is safe to call from within a preemption notifier. + */ +void preempt_notifier_unregister(struct preempt_notifier *notifier) +{ + hlist_del(¬ifier->link); +} +EXPORT_SYMBOL_GPL(preempt_notifier_unregister); + +static void fire_sched_in_preempt_notifiers(struct task_struct *curr) +{ + struct preempt_notifier *notifier; + + hlist_for_each_entry(notifier, &curr->preempt_notifiers, link) + notifier->ops->sched_in(notifier, raw_smp_processor_id()); +} + +static void +fire_sched_out_preempt_notifiers(struct task_struct *curr, + struct task_struct *next) +{ + struct preempt_notifier *notifier; + + hlist_for_each_entry(notifier, &curr->preempt_notifiers, link) + notifier->ops->sched_out(notifier, next); +} + +#else /* !CONFIG_PREEMPT_NOTIFIERS */ + +static void fire_sched_in_preempt_notifiers(struct task_struct *curr) +{ +} + +static void +fire_sched_out_preempt_notifiers(struct task_struct *curr, + struct task_struct *next) +{ +} + +#endif /* CONFIG_PREEMPT_NOTIFIERS */ + +/** + * prepare_task_switch - prepare to switch tasks + * @rq: the runqueue preparing to switch + * @prev: the current task that is being switched out + * @next: the task we are going to switch to. + * + * This is called with the rq lock held and interrupts off. It must + * be paired with a subsequent finish_task_switch after the context + * switch. + * + * prepare_task_switch sets up locking and calls architecture specific + * hooks. + */ +static inline void +prepare_task_switch(struct rq *rq, struct task_struct *prev, + struct task_struct *next) +{ + trace_sched_switch(prev, next); + sched_info_switch(rq, prev, next); + perf_event_task_sched_out(prev, next); + fire_sched_out_preempt_notifiers(prev, next); + prepare_lock_switch(rq, next); + prepare_arch_switch(next); +} + +/** + * finish_task_switch - clean up after a task-switch + * @prev: the thread we just switched away from. + * + * finish_task_switch must be called after the context switch, paired + * with a prepare_task_switch call before the context switch. + * finish_task_switch will reconcile locking set up by prepare_task_switch, + * and do any other architecture-specific cleanup actions. + * + * Note that we may have delayed dropping an mm in context_switch(). If + * so, we finish that here outside of the runqueue lock. (Doing it + * with the lock held can cause deadlocks; see schedule() for + * details.) + * + * The context switch have flipped the stack from under us and restored the + * local variables which were saved when this task called schedule() in the + * past. prev == current is still correct but we need to recalculate this_rq + * because prev may have moved to another CPU. + */ +static struct rq *finish_task_switch(struct task_struct *prev) + __releases(rq->lock) +{ + struct rq *rq = this_rq(); + struct mm_struct *mm = rq->prev_mm; + long prev_state; + + rq->prev_mm = NULL; + + /* + * A task struct has one reference for the use as "current". + * If a task dies, then it sets TASK_DEAD in tsk->state and calls + * schedule one last time. The schedule call will never return, and + * the scheduled task must drop that reference. + * The test for TASK_DEAD must occur while the runqueue locks are + * still held, otherwise prev could be scheduled on another cpu, die + * there before we look at prev->state, and then the reference would + * be dropped twice. + * Manfred Spraul + */ + prev_state = prev->state; + vtime_task_switch(prev); + finish_arch_switch(prev); + perf_event_task_sched_in(prev, current); + finish_lock_switch(rq, prev); + finish_arch_post_lock_switch(); + + fire_sched_in_preempt_notifiers(current); + /* + * We use mmdrop_delayed() here so we don't have to do the + * full __mmdrop() when we are the last user. + */ + if (mm) + mmdrop_delayed(mm); + if (unlikely(prev_state == TASK_DEAD)) { + if (prev->sched_class->task_dead) + prev->sched_class->task_dead(prev); + + /* + * Remove function-return probe instances associated with this + * task and put them back on the free list. + */ + kprobe_flush_task(prev); + put_task_struct(prev); + } + + tick_nohz_task_switch(current); + return rq; +} + +#ifdef CONFIG_SMP + +/* rq->lock is NOT held, but preemption is disabled */ +static inline void post_schedule(struct rq *rq) +{ + if (rq->post_schedule) { + unsigned long flags; + + raw_spin_lock_irqsave(&rq->lock, flags); + if (rq->curr->sched_class->post_schedule) + rq->curr->sched_class->post_schedule(rq); + raw_spin_unlock_irqrestore(&rq->lock, flags); + + rq->post_schedule = 0; + } +} + +#else + +static inline void post_schedule(struct rq *rq) +{ +} + +#endif + +/** + * schedule_tail - first thing a freshly forked thread must call. + * @prev: the thread we just switched away from. + */ +asmlinkage __visible void schedule_tail(struct task_struct *prev) + __releases(rq->lock) +{ + struct rq *rq; + + /* finish_task_switch() drops rq->lock and enables preemtion */ + preempt_disable(); + rq = finish_task_switch(prev); + post_schedule(rq); + preempt_enable(); + + if (current->set_child_tid) + put_user(task_pid_vnr(current), current->set_child_tid); +} + +/* + * context_switch - switch to the new MM and the new thread's register state. + */ +static inline struct rq * +context_switch(struct rq *rq, struct task_struct *prev, + struct task_struct *next) +{ + struct mm_struct *mm, *oldmm; + + prepare_task_switch(rq, prev, next); + + mm = next->mm; + oldmm = prev->active_mm; + /* + * For paravirt, this is coupled with an exit in switch_to to + * combine the page table reload and the switch backend into + * one hypercall. + */ + arch_start_context_switch(prev); + + if (!mm) { + next->active_mm = oldmm; + atomic_inc(&oldmm->mm_count); + enter_lazy_tlb(oldmm, next); + } else + switch_mm(oldmm, mm, next); + + if (!prev->mm) { + prev->active_mm = NULL; + rq->prev_mm = oldmm; + } + /* + * Since the runqueue lock will be released by the next + * task (which is an invalid locking op but in the case + * of the scheduler it's an obvious special-case), so we + * do an early lockdep release here: + */ + spin_release(&rq->lock.dep_map, 1, _THIS_IP_); + + context_tracking_task_switch(prev, next); + /* Here we just switch the register state and the stack. */ + switch_to(prev, next, prev); + barrier(); + + return finish_task_switch(prev); +} + +/* + * nr_running and nr_context_switches: + * + * externally visible scheduler statistics: current number of runnable + * threads, total number of context switches performed since bootup. + */ +unsigned long nr_running(void) +{ + unsigned long i, sum = 0; + + for_each_online_cpu(i) + sum += cpu_rq(i)->nr_running; + + return sum; +} + +/* + * Check if only the current task is running on the cpu. + */ +bool single_task_running(void) +{ + if (cpu_rq(smp_processor_id())->nr_running == 1) + return true; + else + return false; +} +EXPORT_SYMBOL(single_task_running); + +unsigned long long nr_context_switches(void) +{ + int i; + unsigned long long sum = 0; + + for_each_possible_cpu(i) + sum += cpu_rq(i)->nr_switches; + + return sum; +} + +unsigned long nr_iowait(void) +{ + unsigned long i, sum = 0; + + for_each_possible_cpu(i) + sum += atomic_read(&cpu_rq(i)->nr_iowait); + + return sum; +} + +unsigned long nr_iowait_cpu(int cpu) +{ + struct rq *this = cpu_rq(cpu); + return atomic_read(&this->nr_iowait); +} + +void get_iowait_load(unsigned long *nr_waiters, unsigned long *load) +{ + struct rq *this = this_rq(); + *nr_waiters = atomic_read(&this->nr_iowait); + *load = this->cpu_load[0]; +} + +#ifdef CONFIG_SMP + +/* + * sched_exec - execve() is a valuable balancing opportunity, because at + * this point the task has the smallest effective memory and cache footprint. + */ +void sched_exec(void) +{ + struct task_struct *p = current; + unsigned long flags; + int dest_cpu; + + raw_spin_lock_irqsave(&p->pi_lock, flags); + dest_cpu = p->sched_class->select_task_rq(p, task_cpu(p), SD_BALANCE_EXEC, 0); + if (dest_cpu == smp_processor_id()) + goto unlock; + + if (likely(cpu_active(dest_cpu))) { + struct migration_arg arg = { p, dest_cpu }; + + raw_spin_unlock_irqrestore(&p->pi_lock, flags); + stop_one_cpu(task_cpu(p), migration_cpu_stop, &arg); + return; + } +unlock: + raw_spin_unlock_irqrestore(&p->pi_lock, flags); +} + +#endif + +DEFINE_PER_CPU(struct kernel_stat, kstat); +DEFINE_PER_CPU(struct kernel_cpustat, kernel_cpustat); + +EXPORT_PER_CPU_SYMBOL(kstat); +EXPORT_PER_CPU_SYMBOL(kernel_cpustat); + +/* + * Return accounted runtime for the task. + * In case the task is currently running, return the runtime plus current's + * pending runtime that have not been accounted yet. + */ +unsigned long long task_sched_runtime(struct task_struct *p) +{ + unsigned long flags; + struct rq *rq; + u64 ns; + +#if defined(CONFIG_64BIT) && defined(CONFIG_SMP) + /* + * 64-bit doesn't need locks to atomically read a 64bit value. + * So we have a optimization chance when the task's delta_exec is 0. + * Reading ->on_cpu is racy, but this is ok. + * + * If we race with it leaving cpu, we'll take a lock. So we're correct. + * If we race with it entering cpu, unaccounted time is 0. This is + * indistinguishable from the read occurring a few cycles earlier. + * If we see ->on_cpu without ->on_rq, the task is leaving, and has + * been accounted, so we're correct here as well. + */ + if (!p->on_cpu || !task_on_rq_queued(p)) + return p->se.sum_exec_runtime; +#endif + + rq = task_rq_lock(p, &flags); + /* + * Must be ->curr _and_ ->on_rq. If dequeued, we would + * project cycles that may never be accounted to this + * thread, breaking clock_gettime(). + */ + if (task_current(rq, p) && task_on_rq_queued(p)) { + update_rq_clock(rq); + p->sched_class->update_curr(rq); + } + ns = p->se.sum_exec_runtime; + task_rq_unlock(rq, p, &flags); + + return ns; +} + +/* + * This function gets called by the timer code, with HZ frequency. + * We call it with interrupts disabled. + */ +void scheduler_tick(void) +{ + int cpu = smp_processor_id(); + struct rq *rq = cpu_rq(cpu); + struct task_struct *curr = rq->curr; + + sched_clock_tick(); + + raw_spin_lock(&rq->lock); + update_rq_clock(rq); + curr->sched_class->task_tick(rq, curr, 0); + update_cpu_load_active(rq); + raw_spin_unlock(&rq->lock); + + perf_event_task_tick(); + +#ifdef CONFIG_SMP + rq->idle_balance = idle_cpu(cpu); + trigger_load_balance(rq); +#endif + rq_last_tick_reset(rq); +} + +#ifdef CONFIG_NO_HZ_FULL +/** + * scheduler_tick_max_deferment + * + * Keep at least one tick per second when a single + * active task is running because the scheduler doesn't + * yet completely support full dynticks environment. + * + * This makes sure that uptime, CFS vruntime, load + * balancing, etc... continue to move forward, even + * with a very low granularity. + * + * Return: Maximum deferment in nanoseconds. + */ +u64 scheduler_tick_max_deferment(void) +{ + struct rq *rq = this_rq(); + unsigned long next, now = ACCESS_ONCE(jiffies); + + next = rq->last_sched_tick + HZ; + + if (time_before_eq(next, now)) + return 0; + + return jiffies_to_nsecs(next - now); +} +#endif + +notrace unsigned long get_parent_ip(unsigned long addr) +{ + if (in_lock_functions(addr)) { + addr = CALLER_ADDR2; + if (in_lock_functions(addr)) + addr = CALLER_ADDR3; + } + return addr; +} + +#if defined(CONFIG_PREEMPT) && (defined(CONFIG_DEBUG_PREEMPT) || \ + defined(CONFIG_PREEMPT_TRACER)) + +void preempt_count_add(int val) +{ +#ifdef CONFIG_DEBUG_PREEMPT + /* + * Underflow? + */ + if (DEBUG_LOCKS_WARN_ON((preempt_count() < 0))) + return; +#endif + __preempt_count_add(val); +#ifdef CONFIG_DEBUG_PREEMPT + /* + * Spinlock count overflowing soon? + */ + DEBUG_LOCKS_WARN_ON((preempt_count() & PREEMPT_MASK) >= + PREEMPT_MASK - 10); +#endif + if (preempt_count() == val) { + unsigned long ip = get_parent_ip(CALLER_ADDR1); +#ifdef CONFIG_DEBUG_PREEMPT + current->preempt_disable_ip = ip; +#endif + trace_preempt_off(CALLER_ADDR0, ip); + } +} +EXPORT_SYMBOL(preempt_count_add); +NOKPROBE_SYMBOL(preempt_count_add); + +void preempt_count_sub(int val) +{ +#ifdef CONFIG_DEBUG_PREEMPT + /* + * Underflow? + */ + if (DEBUG_LOCKS_WARN_ON(val > preempt_count())) + return; + /* + * Is the spinlock portion underflowing? + */ + if (DEBUG_LOCKS_WARN_ON((val < PREEMPT_MASK) && + !(preempt_count() & PREEMPT_MASK))) + return; +#endif + + if (preempt_count() == val) + trace_preempt_on(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1)); + __preempt_count_sub(val); +} +EXPORT_SYMBOL(preempt_count_sub); +NOKPROBE_SYMBOL(preempt_count_sub); + +#endif + +/* + * Print scheduling while atomic bug: + */ +static noinline void __schedule_bug(struct task_struct *prev) +{ + if (oops_in_progress) + return; + + printk(KERN_ERR "BUG: scheduling while atomic: %s/%d/0x%08x\n", + prev->comm, prev->pid, preempt_count()); + + debug_show_held_locks(prev); + print_modules(); + if (irqs_disabled()) + print_irqtrace_events(prev); +#ifdef CONFIG_DEBUG_PREEMPT + if (in_atomic_preempt_off()) { + pr_err("Preemption disabled at:"); + print_ip_sym(current->preempt_disable_ip); + pr_cont("\n"); + } +#endif + dump_stack(); + add_taint(TAINT_WARN, LOCKDEP_STILL_OK); +} + +/* + * Various schedule()-time debugging checks and statistics: + */ +static inline void schedule_debug(struct task_struct *prev) +{ +#ifdef CONFIG_SCHED_STACK_END_CHECK + BUG_ON(unlikely(task_stack_end_corrupted(prev))); +#endif + /* + * Test if we are atomic. Since do_exit() needs to call into + * schedule() atomically, we ignore that path. Otherwise whine + * if we are scheduling when we should not. + */ + if (unlikely(in_atomic_preempt_off() && prev->state != TASK_DEAD)) + __schedule_bug(prev); + rcu_sleep_check(); + + profile_hit(SCHED_PROFILING, __builtin_return_address(0)); + + schedstat_inc(this_rq(), sched_count); +} + +#if defined(CONFIG_PREEMPT_RT_FULL) && defined(CONFIG_SMP) +#define MIGRATE_DISABLE_SET_AFFIN (1<<30) /* Can't make a negative */ +#define migrate_disabled_updated(p) ((p)->migrate_disable & MIGRATE_DISABLE_SET_AFFIN) +#define migrate_disable_count(p) ((p)->migrate_disable & ~MIGRATE_DISABLE_SET_AFFIN) + +static inline void update_migrate_disable(struct task_struct *p) +{ + const struct cpumask *mask; + + if (likely(!p->migrate_disable)) + return; + + /* Did we already update affinity? */ + if (unlikely(migrate_disabled_updated(p))) + return; + + /* + * Since this is always current we can get away with only locking + * rq->lock, the ->cpus_allowed value can normally only be changed + * while holding both p->pi_lock and rq->lock, but seeing that this + * is current, we cannot actually be waking up, so all code that + * relies on serialization against p->pi_lock is out of scope. + * + * Having rq->lock serializes us against things like + * set_cpus_allowed_ptr() that can still happen concurrently. + */ + mask = tsk_cpus_allowed(p); + + if (p->sched_class->set_cpus_allowed) + p->sched_class->set_cpus_allowed(p, mask); + /* mask==cpumask_of(task_cpu(p)) which has a cpumask_weight==1 */ + p->nr_cpus_allowed = 1; + + /* Let migrate_enable know to fix things back up */ + p->migrate_disable |= MIGRATE_DISABLE_SET_AFFIN; +} + +void migrate_disable(void) +{ + struct task_struct *p = current; + + if (in_atomic()) { +#ifdef CONFIG_SCHED_DEBUG + p->migrate_disable_atomic++; +#endif + return; + } + +#ifdef CONFIG_SCHED_DEBUG + if (unlikely(p->migrate_disable_atomic)) { + tracing_off(); + WARN_ON_ONCE(1); + } +#endif + + if (p->migrate_disable) { + p->migrate_disable++; + return; + } + + preempt_disable(); + preempt_lazy_disable(); + pin_current_cpu(); + p->migrate_disable = 1; + preempt_enable(); +} +EXPORT_SYMBOL(migrate_disable); + +void migrate_enable(void) +{ + struct task_struct *p = current; + const struct cpumask *mask; + unsigned long flags; + struct rq *rq; + + if (in_atomic()) { +#ifdef CONFIG_SCHED_DEBUG + p->migrate_disable_atomic--; +#endif + return; + } + +#ifdef CONFIG_SCHED_DEBUG + if (unlikely(p->migrate_disable_atomic)) { + tracing_off(); + WARN_ON_ONCE(1); + } +#endif + WARN_ON_ONCE(p->migrate_disable <= 0); + + if (migrate_disable_count(p) > 1) { + p->migrate_disable--; + return; + } + + preempt_disable(); + if (unlikely(migrate_disabled_updated(p))) { + /* + * Undo whatever update_migrate_disable() did, also see there + * about locking. + */ + rq = this_rq(); + raw_spin_lock_irqsave(&rq->lock, flags); + + /* + * Clearing migrate_disable causes tsk_cpus_allowed to + * show the tasks original cpu affinity. + */ + p->migrate_disable = 0; + mask = tsk_cpus_allowed(p); + if (p->sched_class->set_cpus_allowed) + p->sched_class->set_cpus_allowed(p, mask); + p->nr_cpus_allowed = cpumask_weight(mask); + raw_spin_unlock_irqrestore(&rq->lock, flags); + } else + p->migrate_disable = 0; + + unpin_current_cpu(); + preempt_enable(); + preempt_lazy_enable(); +} +EXPORT_SYMBOL(migrate_enable); +#else +static inline void update_migrate_disable(struct task_struct *p) { } +#define migrate_disabled_updated(p) 0 +#endif + +/* + * Pick up the highest-prio task: + */ +static inline struct task_struct * +pick_next_task(struct rq *rq, struct task_struct *prev) +{ + const struct sched_class *class = &fair_sched_class; + struct task_struct *p; + + /* + * Optimization: we know that if all tasks are in + * the fair class we can call that function directly: + */ + if (likely(prev->sched_class == class && + rq->nr_running == rq->cfs.h_nr_running)) { + p = fair_sched_class.pick_next_task(rq, prev); + if (unlikely(p == RETRY_TASK)) + goto again; + + /* assumes fair_sched_class->next == idle_sched_class */ + if (unlikely(!p)) + p = idle_sched_class.pick_next_task(rq, prev); + + return p; + } + +again: + for_each_class(class) { + p = class->pick_next_task(rq, prev); + if (p) { + if (unlikely(p == RETRY_TASK)) + goto again; + return p; + } + } + + BUG(); /* the idle class will always have a runnable task */ +} + +/* + * __schedule() is the main scheduler function. + * + * The main means of driving the scheduler and thus entering this function are: + * + * 1. Explicit blocking: mutex, semaphore, waitqueue, etc. + * + * 2. TIF_NEED_RESCHED flag is checked on interrupt and userspace return + * paths. For example, see arch/x86/entry_64.S. + * + * To drive preemption between tasks, the scheduler sets the flag in timer + * interrupt handler scheduler_tick(). + * + * 3. Wakeups don't really cause entry into schedule(). They add a + * task to the run-queue and that's it. + * + * Now, if the new task added to the run-queue preempts the current + * task, then the wakeup sets TIF_NEED_RESCHED and schedule() gets + * called on the nearest possible occasion: + * + * - If the kernel is preemptible (CONFIG_PREEMPT=y): + * + * - in syscall or exception context, at the next outmost + * preempt_enable(). (this might be as soon as the wake_up()'s + * spin_unlock()!) + * + * - in IRQ context, return from interrupt-handler to + * preemptible context + * + * - If the kernel is not preemptible (CONFIG_PREEMPT is not set) + * then at the next: + * + * - cond_resched() call + * - explicit schedule() call + * - return from syscall or exception to user-space + * - return from interrupt-handler to user-space + * + * WARNING: all callers must re-check need_resched() afterward and reschedule + * accordingly in case an event triggered the need for rescheduling (such as + * an interrupt waking up a task) while preemption was disabled in __schedule(). + */ +static void __sched __schedule(void) +{ + struct task_struct *prev, *next; + unsigned long *switch_count; + struct rq *rq; + int cpu; + + preempt_disable(); + cpu = smp_processor_id(); + rq = cpu_rq(cpu); + rcu_note_context_switch(); + prev = rq->curr; + + schedule_debug(prev); + + if (sched_feat(HRTICK)) + hrtick_clear(rq); + + /* + * Make sure that signal_pending_state()->signal_pending() below + * can't be reordered with __set_current_state(TASK_INTERRUPTIBLE) + * done by the caller to avoid the race with signal_wake_up(). + */ + smp_mb__before_spinlock(); + raw_spin_lock_irq(&rq->lock); + + update_migrate_disable(prev); + + rq->clock_skip_update <<= 1; /* promote REQ to ACT */ + + switch_count = &prev->nivcsw; + if (prev->state && !(preempt_count() & PREEMPT_ACTIVE)) { + if (unlikely(signal_pending_state(prev->state, prev))) { + prev->state = TASK_RUNNING; + } else { + deactivate_task(rq, prev, DEQUEUE_SLEEP); + prev->on_rq = 0; + } + switch_count = &prev->nvcsw; + } + + if (task_on_rq_queued(prev)) + update_rq_clock(rq); + + next = pick_next_task(rq, prev); + clear_tsk_need_resched(prev); + clear_tsk_need_resched_lazy(prev); + clear_preempt_need_resched(); + rq->clock_skip_update = 0; + + if (likely(prev != next)) { + rq->nr_switches++; + rq->curr = next; + ++*switch_count; + + rq = context_switch(rq, prev, next); /* unlocks the rq */ + cpu = cpu_of(rq); + } else + raw_spin_unlock_irq(&rq->lock); + + post_schedule(rq); + + sched_preempt_enable_no_resched(); +} + +static inline void sched_submit_work(struct task_struct *tsk) +{ + if (!tsk->state) + return; + /* + * If a worker went to sleep, notify and ask workqueue whether + * it wants to wake up a task to maintain concurrency. + */ + if (tsk->flags & PF_WQ_WORKER) + wq_worker_sleeping(tsk); + + + if (tsk_is_pi_blocked(tsk)) + return; + + /* + * If we are going to sleep and we have plugged IO queued, + * make sure to submit it to avoid deadlocks. + */ + if (blk_needs_flush_plug(tsk)) + blk_schedule_flush_plug(tsk); +} + +static void sched_update_worker(struct task_struct *tsk) +{ + if (tsk->flags & PF_WQ_WORKER) + wq_worker_running(tsk); +} + +asmlinkage __visible void __sched schedule(void) +{ + struct task_struct *tsk = current; + + sched_submit_work(tsk); + do { + __schedule(); + } while (need_resched()); + sched_update_worker(tsk); +} +EXPORT_SYMBOL(schedule); + +#ifdef CONFIG_CONTEXT_TRACKING +asmlinkage __visible void __sched schedule_user(void) +{ + /* + * If we come here after a random call to set_need_resched(), + * or we have been woken up remotely but the IPI has not yet arrived, + * we haven't yet exited the RCU idle mode. Do it here manually until + * we find a better solution. + * + * NB: There are buggy callers of this function. Ideally we + * should warn if prev_state != CONTEXT_USER, but that will trigger + * too frequently to make sense yet. + */ + enum ctx_state prev_state = exception_enter(); + schedule(); + exception_exit(prev_state); +} +#endif + +/** + * schedule_preempt_disabled - called with preemption disabled + * + * Returns with preemption disabled. Note: preempt_count must be 1 + */ +void __sched schedule_preempt_disabled(void) +{ + sched_preempt_enable_no_resched(); + schedule(); + preempt_disable(); +} + +static void __sched notrace preempt_schedule_common(void) +{ + do { + __preempt_count_add(PREEMPT_ACTIVE); + __schedule(); + __preempt_count_sub(PREEMPT_ACTIVE); + + /* + * Check again in case we missed a preemption opportunity + * between schedule and now. + */ + barrier(); + } while (need_resched()); +} + +#ifdef CONFIG_PREEMPT +/* + * this is the entry point to schedule() from in-kernel preemption + * off of preempt_enable. Kernel preemptions off return from interrupt + * occur there and call schedule directly. + */ +asmlinkage __visible void __sched notrace preempt_schedule(void) +{ + /* + * If there is a non-zero preempt_count or interrupts are disabled, + * we do not want to preempt the current task. Just return.. + */ + if (likely(!preemptible())) + return; + + preempt_schedule_common(); +} +NOKPROBE_SYMBOL(preempt_schedule); +EXPORT_SYMBOL(preempt_schedule); + +#ifdef CONFIG_CONTEXT_TRACKING +/** + * preempt_schedule_context - preempt_schedule called by tracing + * + * The tracing infrastructure uses preempt_enable_notrace to prevent + * recursion and tracing preempt enabling caused by the tracing + * infrastructure itself. But as tracing can happen in areas coming + * from userspace or just about to enter userspace, a preempt enable + * can occur before user_exit() is called. This will cause the scheduler + * to be called when the system is still in usermode. + * + * To prevent this, the preempt_enable_notrace will use this function + * instead of preempt_schedule() to exit user context if needed before + * calling the scheduler. + */ +asmlinkage __visible void __sched notrace preempt_schedule_context(void) +{ + enum ctx_state prev_ctx; + + if (likely(!preemptible())) + return; + +#ifdef CONFIG_PREEMPT_LAZY + /* + * Check for lazy preemption + */ + if (current_thread_info()->preempt_lazy_count && + !test_thread_flag(TIF_NEED_RESCHED)) + return; +#endif + do { + __preempt_count_add(PREEMPT_ACTIVE); + /* + * Needs preempt disabled in case user_exit() is traced + * and the tracer calls preempt_enable_notrace() causing + * an infinite recursion. + */ + prev_ctx = exception_enter(); + /* + * The add/subtract must not be traced by the function + * tracer. But we still want to account for the + * preempt off latency tracer. Since the _notrace versions + * of add/subtract skip the accounting for latency tracer + * we must force it manually. + */ + start_critical_timings(); + __schedule(); + stop_critical_timings(); + exception_exit(prev_ctx); + + __preempt_count_sub(PREEMPT_ACTIVE); + barrier(); + } while (need_resched()); +} +EXPORT_SYMBOL_GPL(preempt_schedule_context); +#endif /* CONFIG_CONTEXT_TRACKING */ + +#endif /* CONFIG_PREEMPT */ + +/* + * this is the entry point to schedule() from kernel preemption + * off of irq context. + * Note, that this is called and return with irqs disabled. This will + * protect us against recursive calling from irq. + */ +asmlinkage __visible void __sched preempt_schedule_irq(void) +{ + enum ctx_state prev_state; + + /* Catch callers which need to be fixed */ + BUG_ON(preempt_count() || !irqs_disabled()); + + prev_state = exception_enter(); + + do { + __preempt_count_add(PREEMPT_ACTIVE); + local_irq_enable(); + __schedule(); + local_irq_disable(); + __preempt_count_sub(PREEMPT_ACTIVE); + + /* + * Check again in case we missed a preemption opportunity + * between schedule and now. + */ + barrier(); + } while (need_resched()); + + exception_exit(prev_state); +} + +int default_wake_function(wait_queue_t *curr, unsigned mode, int wake_flags, + void *key) +{ + return try_to_wake_up(curr->private, mode, wake_flags); +} +EXPORT_SYMBOL(default_wake_function); + +#ifdef CONFIG_RT_MUTEXES + +/* + * rt_mutex_setprio - set the current priority of a task + * @p: task + * @prio: prio value (kernel-internal form) + * + * This function changes the 'effective' priority of a task. It does + * not touch ->normal_prio like __setscheduler(). + * + * Used by the rt_mutex code to implement priority inheritance + * logic. Call site only calls if the priority of the task changed. + */ +void rt_mutex_setprio(struct task_struct *p, int prio) +{ + int oldprio, queued, running, enqueue_flag = 0; + struct rq *rq; + const struct sched_class *prev_class; + + BUG_ON(prio > MAX_PRIO); + + rq = __task_rq_lock(p); + + /* + * Idle task boosting is a nono in general. There is one + * exception, when PREEMPT_RT and NOHZ is active: + * + * The idle task calls get_next_timer_interrupt() and holds + * the timer wheel base->lock on the CPU and another CPU wants + * to access the timer (probably to cancel it). We can safely + * ignore the boosting request, as the idle CPU runs this code + * with interrupts disabled and will complete the lock + * protected section without being interrupted. So there is no + * real need to boost. + */ + if (unlikely(p == rq->idle)) { + WARN_ON(p != rq->curr); + WARN_ON(p->pi_blocked_on); + goto out_unlock; + } + + trace_sched_pi_setprio(p, prio); + oldprio = p->prio; + prev_class = p->sched_class; + queued = task_on_rq_queued(p); + running = task_current(rq, p); + if (queued) + dequeue_task(rq, p, 0); + if (running) + put_prev_task(rq, p); + + /* + * Boosting condition are: + * 1. -rt task is running and holds mutex A + * --> -dl task blocks on mutex A + * + * 2. -dl task is running and holds mutex A + * --> -dl task blocks on mutex A and could preempt the + * running task + */ + if (dl_prio(prio)) { + struct task_struct *pi_task = rt_mutex_get_top_task(p); + if (!dl_prio(p->normal_prio) || + (pi_task && dl_entity_preempt(&pi_task->dl, &p->dl))) { + p->dl.dl_boosted = 1; + p->dl.dl_throttled = 0; + enqueue_flag = ENQUEUE_REPLENISH; + } else + p->dl.dl_boosted = 0; + p->sched_class = &dl_sched_class; + } else if (rt_prio(prio)) { + if (dl_prio(oldprio)) + p->dl.dl_boosted = 0; + if (oldprio < prio) + enqueue_flag = ENQUEUE_HEAD; + p->sched_class = &rt_sched_class; + } else { + if (dl_prio(oldprio)) + p->dl.dl_boosted = 0; + if (rt_prio(oldprio)) + p->rt.timeout = 0; + p->sched_class = &fair_sched_class; + } + + p->prio = prio; + + if (running) + p->sched_class->set_curr_task(rq); + if (queued) + enqueue_task(rq, p, enqueue_flag); + + check_class_changed(rq, p, prev_class, oldprio); +out_unlock: + __task_rq_unlock(rq); +} +#endif + +void set_user_nice(struct task_struct *p, long nice) +{ + int old_prio, delta, queued; + unsigned long flags; + struct rq *rq; + + if (task_nice(p) == nice || nice < MIN_NICE || nice > MAX_NICE) + return; + /* + * We have to be careful, if called from sys_setpriority(), + * the task might be in the middle of scheduling on another CPU. + */ + rq = task_rq_lock(p, &flags); + /* + * The RT priorities are set via sched_setscheduler(), but we still + * allow the 'normal' nice value to be set - but as expected + * it wont have any effect on scheduling until the task is + * SCHED_DEADLINE, SCHED_FIFO or SCHED_RR: + */ + if (task_has_dl_policy(p) || task_has_rt_policy(p)) { + p->static_prio = NICE_TO_PRIO(nice); + goto out_unlock; + } + queued = task_on_rq_queued(p); + if (queued) + dequeue_task(rq, p, 0); + + p->static_prio = NICE_TO_PRIO(nice); + set_load_weight(p); + old_prio = p->prio; + p->prio = effective_prio(p); + delta = p->prio - old_prio; + + if (queued) { + enqueue_task(rq, p, 0); + /* + * If the task increased its priority or is running and + * lowered its priority, then reschedule its CPU: + */ + if (delta < 0 || (delta > 0 && task_running(rq, p))) + resched_curr(rq); + } +out_unlock: + task_rq_unlock(rq, p, &flags); +} +EXPORT_SYMBOL(set_user_nice); + +/* + * can_nice - check if a task can reduce its nice value + * @p: task + * @nice: nice value + */ +int can_nice(const struct task_struct *p, const int nice) +{ + /* convert nice value [19,-20] to rlimit style value [1,40] */ + int nice_rlim = nice_to_rlimit(nice); + + return (nice_rlim <= task_rlimit(p, RLIMIT_NICE) || + capable(CAP_SYS_NICE)); +} + +#ifdef __ARCH_WANT_SYS_NICE + +/* + * sys_nice - change the priority of the current process. + * @increment: priority increment + * + * sys_setpriority is a more generic, but much slower function that + * does similar things. + */ +SYSCALL_DEFINE1(nice, int, increment) +{ + long nice, retval; + + /* + * Setpriority might change our priority at the same moment. + * We don't have to worry. Conceptually one call occurs first + * and we have a single winner. + */ + increment = clamp(increment, -NICE_WIDTH, NICE_WIDTH); + nice = task_nice(current) + increment; + + nice = clamp_val(nice, MIN_NICE, MAX_NICE); + if (increment < 0 && !can_nice(current, nice)) + return -EPERM; + + retval = security_task_setnice(current, nice); + if (retval) + return retval; + + set_user_nice(current, nice); + return 0; +} + +#endif + +/** + * task_prio - return the priority value of a given task. + * @p: the task in question. + * + * Return: The priority value as seen by users in /proc. + * RT tasks are offset by -200. Normal tasks are centered + * around 0, value goes from -16 to +15. + */ +int task_prio(const struct task_struct *p) +{ + return p->prio - MAX_RT_PRIO; +} + +/** + * idle_cpu - is a given cpu idle currently? + * @cpu: the processor in question. + * + * Return: 1 if the CPU is currently idle. 0 otherwise. + */ +int idle_cpu(int cpu) +{ + struct rq *rq = cpu_rq(cpu); + + if (rq->curr != rq->idle) + return 0; + + if (rq->nr_running) + return 0; + +#ifdef CONFIG_SMP + if (!llist_empty(&rq->wake_list)) + return 0; +#endif + + return 1; +} + +/** + * idle_task - return the idle task for a given cpu. + * @cpu: the processor in question. + * + * Return: The idle task for the cpu @cpu. + */ +struct task_struct *idle_task(int cpu) +{ + return cpu_rq(cpu)->idle; +} + +/** + * find_process_by_pid - find a process with a matching PID value. + * @pid: the pid in question. + * + * The task of @pid, if found. %NULL otherwise. + */ +static struct task_struct *find_process_by_pid(pid_t pid) +{ + return pid ? find_task_by_vpid(pid) : current; +} + +/* + * This function initializes the sched_dl_entity of a newly becoming + * SCHED_DEADLINE task. + * + * Only the static values are considered here, the actual runtime and the + * absolute deadline will be properly calculated when the task is enqueued + * for the first time with its new policy. + */ +static void +__setparam_dl(struct task_struct *p, const struct sched_attr *attr) +{ + struct sched_dl_entity *dl_se = &p->dl; + + dl_se->dl_runtime = attr->sched_runtime; + dl_se->dl_deadline = attr->sched_deadline; + dl_se->dl_period = attr->sched_period ?: dl_se->dl_deadline; + dl_se->flags = attr->sched_flags; + dl_se->dl_bw = to_ratio(dl_se->dl_period, dl_se->dl_runtime); + + /* + * Changing the parameters of a task is 'tricky' and we're not doing + * the correct thing -- also see task_dead_dl() and switched_from_dl(). + * + * What we SHOULD do is delay the bandwidth release until the 0-lag + * point. This would include retaining the task_struct until that time + * and change dl_overflow() to not immediately decrement the current + * amount. + * + * Instead we retain the current runtime/deadline and let the new + * parameters take effect after the current reservation period lapses. + * This is safe (albeit pessimistic) because the 0-lag point is always + * before the current scheduling deadline. + * + * We can still have temporary overloads because we do not delay the + * change in bandwidth until that time; so admission control is + * not on the safe side. It does however guarantee tasks will never + * consume more than promised. + */ +} + +/* + * sched_setparam() passes in -1 for its policy, to let the functions + * it calls know not to change it. + */ +#define SETPARAM_POLICY -1 + +static void __setscheduler_params(struct task_struct *p, + const struct sched_attr *attr) +{ + int policy = attr->sched_policy; + + if (policy == SETPARAM_POLICY) + policy = p->policy; + + p->policy = policy; + + if (dl_policy(policy)) + __setparam_dl(p, attr); + else if (fair_policy(policy)) + p->static_prio = NICE_TO_PRIO(attr->sched_nice); + + /* + * __sched_setscheduler() ensures attr->sched_priority == 0 when + * !rt_policy. Always setting this ensures that things like + * getparam()/getattr() don't report silly values for !rt tasks. + */ + p->rt_priority = attr->sched_priority; + p->normal_prio = normal_prio(p); + set_load_weight(p); +} + +/* Actually do priority change: must hold pi & rq lock. */ +static void __setscheduler(struct rq *rq, struct task_struct *p, + const struct sched_attr *attr, bool keep_boost) +{ + __setscheduler_params(p, attr); + + /* + * Keep a potential priority boosting if called from + * sched_setscheduler(). + */ + if (keep_boost) + p->prio = rt_mutex_get_effective_prio(p, normal_prio(p)); + else + p->prio = normal_prio(p); + + if (dl_prio(p->prio)) + p->sched_class = &dl_sched_class; + else if (rt_prio(p->prio)) + p->sched_class = &rt_sched_class; + else + p->sched_class = &fair_sched_class; +} + +static void +__getparam_dl(struct task_struct *p, struct sched_attr *attr) +{ + struct sched_dl_entity *dl_se = &p->dl; + + attr->sched_priority = p->rt_priority; + attr->sched_runtime = dl_se->dl_runtime; + attr->sched_deadline = dl_se->dl_deadline; + attr->sched_period = dl_se->dl_period; + attr->sched_flags = dl_se->flags; +} + +/* + * This function validates the new parameters of a -deadline task. + * We ask for the deadline not being zero, and greater or equal + * than the runtime, as well as the period of being zero or + * greater than deadline. Furthermore, we have to be sure that + * user parameters are above the internal resolution of 1us (we + * check sched_runtime only since it is always the smaller one) and + * below 2^63 ns (we have to check both sched_deadline and + * sched_period, as the latter can be zero). + */ +static bool +__checkparam_dl(const struct sched_attr *attr) +{ + /* deadline != 0 */ + if (attr->sched_deadline == 0) + return false; + + /* + * Since we truncate DL_SCALE bits, make sure we're at least + * that big. + */ + if (attr->sched_runtime < (1ULL << DL_SCALE)) + return false; + + /* + * Since we use the MSB for wrap-around and sign issues, make + * sure it's not set (mind that period can be equal to zero). + */ + if (attr->sched_deadline & (1ULL << 63) || + attr->sched_period & (1ULL << 63)) + return false; + + /* runtime <= deadline <= period (if period != 0) */ + if ((attr->sched_period != 0 && + attr->sched_period < attr->sched_deadline) || + attr->sched_deadline < attr->sched_runtime) + return false; + + return true; +} + +/* + * check the target process has a UID that matches the current process's + */ +static bool check_same_owner(struct task_struct *p) +{ + const struct cred *cred = current_cred(), *pcred; + bool match; + + rcu_read_lock(); + pcred = __task_cred(p); + match = (uid_eq(cred->euid, pcred->euid) || + uid_eq(cred->euid, pcred->uid)); + rcu_read_unlock(); + return match; +} + +static bool dl_param_changed(struct task_struct *p, + const struct sched_attr *attr) +{ + struct sched_dl_entity *dl_se = &p->dl; + + if (dl_se->dl_runtime != attr->sched_runtime || + dl_se->dl_deadline != attr->sched_deadline || + dl_se->dl_period != attr->sched_period || + dl_se->flags != attr->sched_flags) + return true; + + return false; +} + +static int __sched_setscheduler(struct task_struct *p, + const struct sched_attr *attr, + bool user) +{ + int newprio = dl_policy(attr->sched_policy) ? MAX_DL_PRIO - 1 : + MAX_RT_PRIO - 1 - attr->sched_priority; + int retval, oldprio, oldpolicy = -1, queued, running; + int new_effective_prio, policy = attr->sched_policy; + unsigned long flags; + const struct sched_class *prev_class; + struct rq *rq; + int reset_on_fork; + + /* may grab non-irq protected spin_locks */ + BUG_ON(in_interrupt()); +recheck: + /* double check policy once rq lock held */ + if (policy < 0) { + reset_on_fork = p->sched_reset_on_fork; + policy = oldpolicy = p->policy; + } else { + reset_on_fork = !!(attr->sched_flags & SCHED_FLAG_RESET_ON_FORK); + + if (policy != SCHED_DEADLINE && + policy != SCHED_FIFO && policy != SCHED_RR && + policy != SCHED_NORMAL && policy != SCHED_BATCH && + policy != SCHED_IDLE) + return -EINVAL; + } + + if (attr->sched_flags & ~(SCHED_FLAG_RESET_ON_FORK)) + return -EINVAL; + + /* + * Valid priorities for SCHED_FIFO and SCHED_RR are + * 1..MAX_USER_RT_PRIO-1, valid priority for SCHED_NORMAL, + * SCHED_BATCH and SCHED_IDLE is 0. + */ + if ((p->mm && attr->sched_priority > MAX_USER_RT_PRIO-1) || + (!p->mm && attr->sched_priority > MAX_RT_PRIO-1)) + return -EINVAL; + if ((dl_policy(policy) && !__checkparam_dl(attr)) || + (rt_policy(policy) != (attr->sched_priority != 0))) + return -EINVAL; + + /* + * Allow unprivileged RT tasks to decrease priority: + */ + if (user && !capable(CAP_SYS_NICE)) { + if (fair_policy(policy)) { + if (attr->sched_nice < task_nice(p) && + !can_nice(p, attr->sched_nice)) + return -EPERM; + } + + if (rt_policy(policy)) { + unsigned long rlim_rtprio = + task_rlimit(p, RLIMIT_RTPRIO); + + /* can't set/change the rt policy */ + if (policy != p->policy && !rlim_rtprio) + return -EPERM; + + /* can't increase priority */ + if (attr->sched_priority > p->rt_priority && + attr->sched_priority > rlim_rtprio) + return -EPERM; + } + + /* + * Can't set/change SCHED_DEADLINE policy at all for now + * (safest behavior); in the future we would like to allow + * unprivileged DL tasks to increase their relative deadline + * or reduce their runtime (both ways reducing utilization) + */ + if (dl_policy(policy)) + return -EPERM; + + /* + * Treat SCHED_IDLE as nice 20. Only allow a switch to + * SCHED_NORMAL if the RLIMIT_NICE would normally permit it. + */ + if (p->policy == SCHED_IDLE && policy != SCHED_IDLE) { + if (!can_nice(p, task_nice(p))) + return -EPERM; + } + + /* can't change other user's priorities */ + if (!check_same_owner(p)) + return -EPERM; + + /* Normal users shall not reset the sched_reset_on_fork flag */ + if (p->sched_reset_on_fork && !reset_on_fork) + return -EPERM; + } + + if (user) { + retval = security_task_setscheduler(p); + if (retval) + return retval; + } + + /* + * make sure no PI-waiters arrive (or leave) while we are + * changing the priority of the task: + * + * To be able to change p->policy safely, the appropriate + * runqueue lock must be held. + */ + rq = task_rq_lock(p, &flags); + + /* + * Changing the policy of the stop threads its a very bad idea + */ + if (p == rq->stop) { + task_rq_unlock(rq, p, &flags); + return -EINVAL; + } + + /* + * If not changing anything there's no need to proceed further, + * but store a possible modification of reset_on_fork. + */ + if (unlikely(policy == p->policy)) { + if (fair_policy(policy) && attr->sched_nice != task_nice(p)) + goto change; + if (rt_policy(policy) && attr->sched_priority != p->rt_priority) + goto change; + if (dl_policy(policy) && dl_param_changed(p, attr)) + goto change; + + p->sched_reset_on_fork = reset_on_fork; + task_rq_unlock(rq, p, &flags); + return 0; + } +change: + + if (user) { +#ifdef CONFIG_RT_GROUP_SCHED + /* + * Do not allow realtime tasks into groups that have no runtime + * assigned. + */ + if (rt_bandwidth_enabled() && rt_policy(policy) && + task_group(p)->rt_bandwidth.rt_runtime == 0 && + !task_group_is_autogroup(task_group(p))) { + task_rq_unlock(rq, p, &flags); + return -EPERM; + } +#endif +#ifdef CONFIG_SMP + if (dl_bandwidth_enabled() && dl_policy(policy)) { + cpumask_t *span = rq->rd->span; + + /* + * Don't allow tasks with an affinity mask smaller than + * the entire root_domain to become SCHED_DEADLINE. We + * will also fail if there's no bandwidth available. + */ + if (!cpumask_subset(span, &p->cpus_allowed) || + rq->rd->dl_bw.bw == 0) { + task_rq_unlock(rq, p, &flags); + return -EPERM; + } + } +#endif + } + + /* recheck policy now with rq lock held */ + if (unlikely(oldpolicy != -1 && oldpolicy != p->policy)) { + policy = oldpolicy = -1; + task_rq_unlock(rq, p, &flags); + goto recheck; + } + + /* + * If setscheduling to SCHED_DEADLINE (or changing the parameters + * of a SCHED_DEADLINE task) we need to check if enough bandwidth + * is available. + */ + if ((dl_policy(policy) || dl_task(p)) && dl_overflow(p, policy, attr)) { + task_rq_unlock(rq, p, &flags); + return -EBUSY; + } + + p->sched_reset_on_fork = reset_on_fork; + oldprio = p->prio; + + /* + * Take priority boosted tasks into account. If the new + * effective priority is unchanged, we just store the new + * normal parameters and do not touch the scheduler class and + * the runqueue. This will be done when the task deboost + * itself. + */ + new_effective_prio = rt_mutex_get_effective_prio(p, newprio); + if (new_effective_prio == oldprio) { + __setscheduler_params(p, attr); + task_rq_unlock(rq, p, &flags); + return 0; + } + + queued = task_on_rq_queued(p); + running = task_current(rq, p); + if (queued) + dequeue_task(rq, p, 0); + if (running) + put_prev_task(rq, p); + + prev_class = p->sched_class; + __setscheduler(rq, p, attr, true); + + if (running) + p->sched_class->set_curr_task(rq); + if (queued) { + /* + * We enqueue to tail when the priority of a task is + * increased (user space view). + */ + enqueue_task(rq, p, oldprio <= p->prio ? ENQUEUE_HEAD : 0); + } + + check_class_changed(rq, p, prev_class, oldprio); + task_rq_unlock(rq, p, &flags); + + rt_mutex_adjust_pi(p); + + return 0; +} + +static int _sched_setscheduler(struct task_struct *p, int policy, + const struct sched_param *param, bool check) +{ + struct sched_attr attr = { + .sched_policy = policy, + .sched_priority = param->sched_priority, + .sched_nice = PRIO_TO_NICE(p->static_prio), + }; + + /* Fixup the legacy SCHED_RESET_ON_FORK hack. */ + if ((policy != SETPARAM_POLICY) && (policy & SCHED_RESET_ON_FORK)) { + attr.sched_flags |= SCHED_FLAG_RESET_ON_FORK; + policy &= ~SCHED_RESET_ON_FORK; + attr.sched_policy = policy; + } + + return __sched_setscheduler(p, &attr, check); +} +/** + * sched_setscheduler - change the scheduling policy and/or RT priority of a thread. + * @p: the task in question. + * @policy: new policy. + * @param: structure containing the new RT priority. + * + * Return: 0 on success. An error code otherwise. + * + * NOTE that the task may be already dead. + */ +int sched_setscheduler(struct task_struct *p, int policy, + const struct sched_param *param) +{ + return _sched_setscheduler(p, policy, param, true); +} +EXPORT_SYMBOL_GPL(sched_setscheduler); + +int sched_setattr(struct task_struct *p, const struct sched_attr *attr) +{ + return __sched_setscheduler(p, attr, true); +} +EXPORT_SYMBOL_GPL(sched_setattr); + +/** + * sched_setscheduler_nocheck - change the scheduling policy and/or RT priority of a thread from kernelspace. + * @p: the task in question. + * @policy: new policy. + * @param: structure containing the new RT priority. + * + * Just like sched_setscheduler, only don't bother checking if the + * current context has permission. For example, this is needed in + * stop_machine(): we create temporary high priority worker threads, + * but our caller might not have that capability. + * + * Return: 0 on success. An error code otherwise. + */ +int sched_setscheduler_nocheck(struct task_struct *p, int policy, + const struct sched_param *param) +{ + return _sched_setscheduler(p, policy, param, false); +} + +static int +do_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param) +{ + struct sched_param lparam; + struct task_struct *p; + int retval; + + if (!param || pid < 0) + return -EINVAL; + if (copy_from_user(&lparam, param, sizeof(struct sched_param))) + return -EFAULT; + + rcu_read_lock(); + retval = -ESRCH; + p = find_process_by_pid(pid); + if (p != NULL) + retval = sched_setscheduler(p, policy, &lparam); + rcu_read_unlock(); + + return retval; +} + +/* + * Mimics kernel/events/core.c perf_copy_attr(). + */ +static int sched_copy_attr(struct sched_attr __user *uattr, + struct sched_attr *attr) +{ + u32 size; + int ret; + + if (!access_ok(VERIFY_WRITE, uattr, SCHED_ATTR_SIZE_VER0)) + return -EFAULT; + + /* + * zero the full structure, so that a short copy will be nice. + */ + memset(attr, 0, sizeof(*attr)); + + ret = get_user(size, &uattr->size); + if (ret) + return ret; + + if (size > PAGE_SIZE) /* silly large */ + goto err_size; + + if (!size) /* abi compat */ + size = SCHED_ATTR_SIZE_VER0; + + if (size < SCHED_ATTR_SIZE_VER0) + goto err_size; + + /* + * If we're handed a bigger struct than we know of, + * ensure all the unknown bits are 0 - i.e. new + * user-space does not rely on any kernel feature + * extensions we dont know about yet. + */ + if (size > sizeof(*attr)) { + unsigned char __user *addr; + unsigned char __user *end; + unsigned char val; + + addr = (void __user *)uattr + sizeof(*attr); + end = (void __user *)uattr + size; + + for (; addr < end; addr++) { + ret = get_user(val, addr); + if (ret) + return ret; + if (val) + goto err_size; + } + size = sizeof(*attr); + } + + ret = copy_from_user(attr, uattr, size); + if (ret) + return -EFAULT; + + /* + * XXX: do we want to be lenient like existing syscalls; or do we want + * to be strict and return an error on out-of-bounds values? + */ + attr->sched_nice = clamp(attr->sched_nice, MIN_NICE, MAX_NICE); + + return 0; + +err_size: + put_user(sizeof(*attr), &uattr->size); + return -E2BIG; +} + +/** + * sys_sched_setscheduler - set/change the scheduler policy and RT priority + * @pid: the pid in question. + * @policy: new policy. + * @param: structure containing the new RT priority. + * + * Return: 0 on success. An error code otherwise. + */ +SYSCALL_DEFINE3(sched_setscheduler, pid_t, pid, int, policy, + struct sched_param __user *, param) +{ + /* negative values for policy are not valid */ + if (policy < 0) + return -EINVAL; + + return do_sched_setscheduler(pid, policy, param); +} + +/** + * sys_sched_setparam - set/change the RT priority of a thread + * @pid: the pid in question. + * @param: structure containing the new RT priority. + * + * Return: 0 on success. An error code otherwise. + */ +SYSCALL_DEFINE2(sched_setparam, pid_t, pid, struct sched_param __user *, param) +{ + return do_sched_setscheduler(pid, SETPARAM_POLICY, param); +} + +/** + * sys_sched_setattr - same as above, but with extended sched_attr + * @pid: the pid in question. + * @uattr: structure containing the extended parameters. + * @flags: for future extension. + */ +SYSCALL_DEFINE3(sched_setattr, pid_t, pid, struct sched_attr __user *, uattr, + unsigned int, flags) +{ + struct sched_attr attr; + struct task_struct *p; + int retval; + + if (!uattr || pid < 0 || flags) + return -EINVAL; + + retval = sched_copy_attr(uattr, &attr); + if (retval) + return retval; + + if ((int)attr.sched_policy < 0) + return -EINVAL; + + rcu_read_lock(); + retval = -ESRCH; + p = find_process_by_pid(pid); + if (p != NULL) + retval = sched_setattr(p, &attr); + rcu_read_unlock(); + + return retval; +} + +/** + * sys_sched_getscheduler - get the policy (scheduling class) of a thread + * @pid: the pid in question. + * + * Return: On success, the policy of the thread. Otherwise, a negative error + * code. + */ +SYSCALL_DEFINE1(sched_getscheduler, pid_t, pid) +{ + struct task_struct *p; + int retval; + + if (pid < 0) + return -EINVAL; + + retval = -ESRCH; + rcu_read_lock(); + p = find_process_by_pid(pid); + if (p) { + retval = security_task_getscheduler(p); + if (!retval) + retval = p->policy + | (p->sched_reset_on_fork ? SCHED_RESET_ON_FORK : 0); + } + rcu_read_unlock(); + return retval; +} + +/** + * sys_sched_getparam - get the RT priority of a thread + * @pid: the pid in question. + * @param: structure containing the RT priority. + * + * Return: On success, 0 and the RT priority is in @param. Otherwise, an error + * code. + */ +SYSCALL_DEFINE2(sched_getparam, pid_t, pid, struct sched_param __user *, param) +{ + struct sched_param lp = { .sched_priority = 0 }; + struct task_struct *p; + int retval; + + if (!param || pid < 0) + return -EINVAL; + + rcu_read_lock(); + p = find_process_by_pid(pid); + retval = -ESRCH; + if (!p) + goto out_unlock; + + retval = security_task_getscheduler(p); + if (retval) + goto out_unlock; + + if (task_has_rt_policy(p)) + lp.sched_priority = p->rt_priority; + rcu_read_unlock(); + + /* + * This one might sleep, we cannot do it with a spinlock held ... + */ + retval = copy_to_user(param, &lp, sizeof(*param)) ? -EFAULT : 0; + + return retval; + +out_unlock: + rcu_read_unlock(); + return retval; +} + +static int sched_read_attr(struct sched_attr __user *uattr, + struct sched_attr *attr, + unsigned int usize) +{ + int ret; + + if (!access_ok(VERIFY_WRITE, uattr, usize)) + return -EFAULT; + + /* + * If we're handed a smaller struct than we know of, + * ensure all the unknown bits are 0 - i.e. old + * user-space does not get uncomplete information. + */ + if (usize < sizeof(*attr)) { + unsigned char *addr; + unsigned char *end; + + addr = (void *)attr + usize; + end = (void *)attr + sizeof(*attr); + + for (; addr < end; addr++) { + if (*addr) + return -EFBIG; + } + + attr->size = usize; + } + + ret = copy_to_user(uattr, attr, attr->size); + if (ret) + return -EFAULT; + + return 0; +} + +/** + * sys_sched_getattr - similar to sched_getparam, but with sched_attr + * @pid: the pid in question. + * @uattr: structure containing the extended parameters. + * @size: sizeof(attr) for fwd/bwd comp. + * @flags: for future extension. + */ +SYSCALL_DEFINE4(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr, + unsigned int, size, unsigned int, flags) +{ + struct sched_attr attr = { + .size = sizeof(struct sched_attr), + }; + struct task_struct *p; + int retval; + + if (!uattr || pid < 0 || size > PAGE_SIZE || + size < SCHED_ATTR_SIZE_VER0 || flags) + return -EINVAL; + + rcu_read_lock(); + p = find_process_by_pid(pid); + retval = -ESRCH; + if (!p) + goto out_unlock; + + retval = security_task_getscheduler(p); + if (retval) + goto out_unlock; + + attr.sched_policy = p->policy; + if (p->sched_reset_on_fork) + attr.sched_flags |= SCHED_FLAG_RESET_ON_FORK; + if (task_has_dl_policy(p)) + __getparam_dl(p, &attr); + else if (task_has_rt_policy(p)) + attr.sched_priority = p->rt_priority; + else + attr.sched_nice = task_nice(p); + + rcu_read_unlock(); + + retval = sched_read_attr(uattr, &attr, size); + return retval; + +out_unlock: + rcu_read_unlock(); + return retval; +} + +long sched_setaffinity(pid_t pid, const struct cpumask *in_mask) +{ + cpumask_var_t cpus_allowed, new_mask; + struct task_struct *p; + int retval; + + rcu_read_lock(); + + p = find_process_by_pid(pid); + if (!p) { + rcu_read_unlock(); + return -ESRCH; + } + + /* Prevent p going away */ + get_task_struct(p); + rcu_read_unlock(); + + if (p->flags & PF_NO_SETAFFINITY) { + retval = -EINVAL; + goto out_put_task; + } + if (!alloc_cpumask_var(&cpus_allowed, GFP_KERNEL)) { + retval = -ENOMEM; + goto out_put_task; + } + if (!alloc_cpumask_var(&new_mask, GFP_KERNEL)) { + retval = -ENOMEM; + goto out_free_cpus_allowed; + } + retval = -EPERM; + if (!check_same_owner(p)) { + rcu_read_lock(); + if (!ns_capable(__task_cred(p)->user_ns, CAP_SYS_NICE)) { + rcu_read_unlock(); + goto out_free_new_mask; + } + rcu_read_unlock(); + } + + retval = security_task_setscheduler(p); + if (retval) + goto out_free_new_mask; + + + cpuset_cpus_allowed(p, cpus_allowed); + cpumask_and(new_mask, in_mask, cpus_allowed); + + /* + * Since bandwidth control happens on root_domain basis, + * if admission test is enabled, we only admit -deadline + * tasks allowed to run on all the CPUs in the task's + * root_domain. + */ +#ifdef CONFIG_SMP + if (task_has_dl_policy(p) && dl_bandwidth_enabled()) { + rcu_read_lock(); + if (!cpumask_subset(task_rq(p)->rd->span, new_mask)) { + retval = -EBUSY; + rcu_read_unlock(); + goto out_free_new_mask; + } + rcu_read_unlock(); + } +#endif +again: + retval = set_cpus_allowed_ptr(p, new_mask); + + if (!retval) { + cpuset_cpus_allowed(p, cpus_allowed); + if (!cpumask_subset(new_mask, cpus_allowed)) { + /* + * We must have raced with a concurrent cpuset + * update. Just reset the cpus_allowed to the + * cpuset's cpus_allowed + */ + cpumask_copy(new_mask, cpus_allowed); + goto again; + } + } +out_free_new_mask: + free_cpumask_var(new_mask); +out_free_cpus_allowed: + free_cpumask_var(cpus_allowed); +out_put_task: + put_task_struct(p); + return retval; +} + +static int get_user_cpu_mask(unsigned long __user *user_mask_ptr, unsigned len, + struct cpumask *new_mask) +{ + if (len < cpumask_size()) + cpumask_clear(new_mask); + else if (len > cpumask_size()) + len = cpumask_size(); + + return copy_from_user(new_mask, user_mask_ptr, len) ? -EFAULT : 0; +} + +/** + * sys_sched_setaffinity - set the cpu affinity of a process + * @pid: pid of the process + * @len: length in bytes of the bitmask pointed to by user_mask_ptr + * @user_mask_ptr: user-space pointer to the new cpu mask + * + * Return: 0 on success. An error code otherwise. + */ +SYSCALL_DEFINE3(sched_setaffinity, pid_t, pid, unsigned int, len, + unsigned long __user *, user_mask_ptr) +{ + cpumask_var_t new_mask; + int retval; + + if (!alloc_cpumask_var(&new_mask, GFP_KERNEL)) + return -ENOMEM; + + retval = get_user_cpu_mask(user_mask_ptr, len, new_mask); + if (retval == 0) + retval = sched_setaffinity(pid, new_mask); + free_cpumask_var(new_mask); + return retval; +} + +long sched_getaffinity(pid_t pid, struct cpumask *mask) +{ + struct task_struct *p; + unsigned long flags; + int retval; + + rcu_read_lock(); + + retval = -ESRCH; + p = find_process_by_pid(pid); + if (!p) + goto out_unlock; + + retval = security_task_getscheduler(p); + if (retval) + goto out_unlock; + + raw_spin_lock_irqsave(&p->pi_lock, flags); + cpumask_and(mask, &p->cpus_allowed, cpu_active_mask); + raw_spin_unlock_irqrestore(&p->pi_lock, flags); + +out_unlock: + rcu_read_unlock(); + + return retval; +} + +/** + * sys_sched_getaffinity - get the cpu affinity of a process + * @pid: pid of the process + * @len: length in bytes of the bitmask pointed to by user_mask_ptr + * @user_mask_ptr: user-space pointer to hold the current cpu mask + * + * Return: 0 on success. An error code otherwise. + */ +SYSCALL_DEFINE3(sched_getaffinity, pid_t, pid, unsigned int, len, + unsigned long __user *, user_mask_ptr) +{ + int ret; + cpumask_var_t mask; + + if ((len * BITS_PER_BYTE) < nr_cpu_ids) + return -EINVAL; + if (len & (sizeof(unsigned long)-1)) + return -EINVAL; + + if (!alloc_cpumask_var(&mask, GFP_KERNEL)) + return -ENOMEM; + + ret = sched_getaffinity(pid, mask); + if (ret == 0) { + size_t retlen = min_t(size_t, len, cpumask_size()); + + if (copy_to_user(user_mask_ptr, mask, retlen)) + ret = -EFAULT; + else + ret = retlen; + } + free_cpumask_var(mask); + + return ret; +} + +/** + * sys_sched_yield - yield the current processor to other threads. + * + * This function yields the current CPU to other tasks. If there are no + * other threads running on this CPU then this function will return. + * + * Return: 0. + */ +SYSCALL_DEFINE0(sched_yield) +{ + struct rq *rq = this_rq_lock(); + + schedstat_inc(rq, yld_count); + current->sched_class->yield_task(rq); + + /* + * Since we are going to call schedule() anyway, there's + * no need to preempt or enable interrupts: + */ + __release(rq->lock); + spin_release(&rq->lock.dep_map, 1, _THIS_IP_); + do_raw_spin_unlock(&rq->lock); + sched_preempt_enable_no_resched(); + + schedule(); + + return 0; +} + +int __sched _cond_resched(void) +{ + if (should_resched()) { + preempt_schedule_common(); + return 1; + } + return 0; +} +EXPORT_SYMBOL(_cond_resched); + +/* + * __cond_resched_lock() - if a reschedule is pending, drop the given lock, + * call schedule, and on return reacquire the lock. + * + * This works OK both with and without CONFIG_PREEMPT. We do strange low-level + * operations here to prevent schedule() from being called twice (once via + * spin_unlock(), once by hand). + */ +int __cond_resched_lock(spinlock_t *lock) +{ + int resched = should_resched(); + int ret = 0; + + lockdep_assert_held(lock); + + if (spin_needbreak(lock) || resched) { + spin_unlock(lock); + if (resched) + preempt_schedule_common(); + else + cpu_relax(); + ret = 1; + spin_lock(lock); + } + return ret; +} +EXPORT_SYMBOL(__cond_resched_lock); + +#ifndef CONFIG_PREEMPT_RT_FULL +int __sched __cond_resched_softirq(void) +{ + BUG_ON(!in_softirq()); + + if (should_resched()) { + local_bh_enable(); + preempt_schedule_common(); + local_bh_disable(); + return 1; + } + return 0; +} +EXPORT_SYMBOL(__cond_resched_softirq); +#endif + +/** + * yield - yield the current processor to other threads. + * + * Do not ever use this function, there's a 99% chance you're doing it wrong. + * + * The scheduler is at all times free to pick the calling task as the most + * eligible task to run, if removing the yield() call from your code breaks + * it, its already broken. + * + * Typical broken usage is: + * + * while (!event) + * yield(); + * + * where one assumes that yield() will let 'the other' process run that will + * make event true. If the current task is a SCHED_FIFO task that will never + * happen. Never use yield() as a progress guarantee!! + * + * If you want to use yield() to wait for something, use wait_event(). + * If you want to use yield() to be 'nice' for others, use cond_resched(). + * If you still want to use yield(), do not! + */ +void __sched yield(void) +{ + set_current_state(TASK_RUNNING); + sys_sched_yield(); +} +EXPORT_SYMBOL(yield); + +/** + * yield_to - yield the current processor to another thread in + * your thread group, or accelerate that thread toward the + * processor it's on. + * @p: target task + * @preempt: whether task preemption is allowed or not + * + * It's the caller's job to ensure that the target task struct + * can't go away on us before we can do any checks. + * + * Return: + * true (>0) if we indeed boosted the target task. + * false (0) if we failed to boost the target. + * -ESRCH if there's no task to yield to. + */ +int __sched yield_to(struct task_struct *p, bool preempt) +{ + struct task_struct *curr = current; + struct rq *rq, *p_rq; + unsigned long flags; + int yielded = 0; + + local_irq_save(flags); + rq = this_rq(); + +again: + p_rq = task_rq(p); + /* + * If we're the only runnable task on the rq and target rq also + * has only one task, there's absolutely no point in yielding. + */ + if (rq->nr_running == 1 && p_rq->nr_running == 1) { + yielded = -ESRCH; + goto out_irq; + } + + double_rq_lock(rq, p_rq); + if (task_rq(p) != p_rq) { + double_rq_unlock(rq, p_rq); + goto again; + } + + if (!curr->sched_class->yield_to_task) + goto out_unlock; + + if (curr->sched_class != p->sched_class) + goto out_unlock; + + if (task_running(p_rq, p) || p->state) + goto out_unlock; + + yielded = curr->sched_class->yield_to_task(rq, p, preempt); + if (yielded) { + schedstat_inc(rq, yld_count); + /* + * Make p's CPU reschedule; pick_next_entity takes care of + * fairness. + */ + if (preempt && rq != p_rq) + resched_curr(p_rq); + } + +out_unlock: + double_rq_unlock(rq, p_rq); +out_irq: + local_irq_restore(flags); + + if (yielded > 0) + schedule(); + + return yielded; +} +EXPORT_SYMBOL_GPL(yield_to); + +/* + * This task is about to go to sleep on IO. Increment rq->nr_iowait so + * that process accounting knows that this is a task in IO wait state. + */ +long __sched io_schedule_timeout(long timeout) +{ + int old_iowait = current->in_iowait; + struct rq *rq; + long ret; + + current->in_iowait = 1; + blk_schedule_flush_plug(current); + + delayacct_blkio_start(); + rq = raw_rq(); + atomic_inc(&rq->nr_iowait); + ret = schedule_timeout(timeout); + current->in_iowait = old_iowait; + atomic_dec(&rq->nr_iowait); + delayacct_blkio_end(); + + return ret; +} +EXPORT_SYMBOL(io_schedule_timeout); + +/** + * sys_sched_get_priority_max - return maximum RT priority. + * @policy: scheduling class. + * + * Return: On success, this syscall returns the maximum + * rt_priority that can be used by a given scheduling class. + * On failure, a negative error code is returned. + */ +SYSCALL_DEFINE1(sched_get_priority_max, int, policy) +{ + int ret = -EINVAL; + + switch (policy) { + case SCHED_FIFO: + case SCHED_RR: + ret = MAX_USER_RT_PRIO-1; + break; + case SCHED_DEADLINE: + case SCHED_NORMAL: + case SCHED_BATCH: + case SCHED_IDLE: + ret = 0; + break; + } + return ret; +} + +/** + * sys_sched_get_priority_min - return minimum RT priority. + * @policy: scheduling class. + * + * Return: On success, this syscall returns the minimum + * rt_priority that can be used by a given scheduling class. + * On failure, a negative error code is returned. + */ +SYSCALL_DEFINE1(sched_get_priority_min, int, policy) +{ + int ret = -EINVAL; + + switch (policy) { + case SCHED_FIFO: + case SCHED_RR: + ret = 1; + break; + case SCHED_DEADLINE: + case SCHED_NORMAL: + case SCHED_BATCH: + case SCHED_IDLE: + ret = 0; + } + return ret; +} + +/** + * sys_sched_rr_get_interval - return the default timeslice of a process. + * @pid: pid of the process. + * @interval: userspace pointer to the timeslice value. + * + * this syscall writes the default timeslice value of a given process + * into the user-space timespec buffer. A value of '0' means infinity. + * + * Return: On success, 0 and the timeslice is in @interval. Otherwise, + * an error code. + */ +SYSCALL_DEFINE2(sched_rr_get_interval, pid_t, pid, + struct timespec __user *, interval) +{ + struct task_struct *p; + unsigned int time_slice; + unsigned long flags; + struct rq *rq; + int retval; + struct timespec t; + + if (pid < 0) + return -EINVAL; + + retval = -ESRCH; + rcu_read_lock(); + p = find_process_by_pid(pid); + if (!p) + goto out_unlock; + + retval = security_task_getscheduler(p); + if (retval) + goto out_unlock; + + rq = task_rq_lock(p, &flags); + time_slice = 0; + if (p->sched_class->get_rr_interval) + time_slice = p->sched_class->get_rr_interval(rq, p); + task_rq_unlock(rq, p, &flags); + + rcu_read_unlock(); + jiffies_to_timespec(time_slice, &t); + retval = copy_to_user(interval, &t, sizeof(t)) ? -EFAULT : 0; + return retval; + +out_unlock: + rcu_read_unlock(); + return retval; +} + +static const char stat_nam[] = TASK_STATE_TO_CHAR_STR; + +void sched_show_task(struct task_struct *p) +{ + unsigned long free = 0; + int ppid; + unsigned long state = p->state; + + if (state) + state = __ffs(state) + 1; + printk(KERN_INFO "%-15.15s %c", p->comm, + state < sizeof(stat_nam) - 1 ? stat_nam[state] : '?'); +#if BITS_PER_LONG == 32 + if (state == TASK_RUNNING) + printk(KERN_CONT " running "); + else + printk(KERN_CONT " %08lx ", thread_saved_pc(p)); +#else + if (state == TASK_RUNNING) + printk(KERN_CONT " running task "); + else + printk(KERN_CONT " %016lx ", thread_saved_pc(p)); +#endif +#ifdef CONFIG_DEBUG_STACK_USAGE + free = stack_not_used(p); +#endif + ppid = 0; + rcu_read_lock(); + if (pid_alive(p)) + ppid = task_pid_nr(rcu_dereference(p->real_parent)); + rcu_read_unlock(); + printk(KERN_CONT "%5lu %5d %6d 0x%08lx\n", free, + task_pid_nr(p), ppid, + (unsigned long)task_thread_info(p)->flags); + + print_worker_info(KERN_INFO, p); + show_stack(p, NULL); +} + +void show_state_filter(unsigned long state_filter) +{ + struct task_struct *g, *p; + +#if BITS_PER_LONG == 32 + printk(KERN_INFO + " task PC stack pid father\n"); +#else + printk(KERN_INFO + " task PC stack pid father\n"); +#endif + rcu_read_lock(); + for_each_process_thread(g, p) { + /* + * reset the NMI-timeout, listing all files on a slow + * console might take a lot of time: + */ + touch_nmi_watchdog(); + if (!state_filter || (p->state & state_filter)) + sched_show_task(p); + } + + touch_all_softlockup_watchdogs(); + +#ifdef CONFIG_SCHED_DEBUG + sysrq_sched_debug_show(); +#endif + rcu_read_unlock(); + /* + * Only show locks if all tasks are dumped: + */ + if (!state_filter) + debug_show_all_locks(); +} + +void init_idle_bootup_task(struct task_struct *idle) +{ + idle->sched_class = &idle_sched_class; +} + +/** + * init_idle - set up an idle thread for a given CPU + * @idle: task in question + * @cpu: cpu the idle task belongs to + * + * NOTE: this function does not set the idle thread's NEED_RESCHED + * flag, to make booting more robust. + */ +void init_idle(struct task_struct *idle, int cpu) +{ + struct rq *rq = cpu_rq(cpu); + unsigned long flags; + + raw_spin_lock_irqsave(&rq->lock, flags); + + __sched_fork(0, idle); + idle->state = TASK_RUNNING; + idle->se.exec_start = sched_clock(); + + do_set_cpus_allowed(idle, cpumask_of(cpu)); + /* + * We're having a chicken and egg problem, even though we are + * holding rq->lock, the cpu isn't yet set to this cpu so the + * lockdep check in task_group() will fail. + * + * Similar case to sched_fork(). / Alternatively we could + * use task_rq_lock() here and obtain the other rq->lock. + * + * Silence PROVE_RCU + */ + rcu_read_lock(); + __set_task_cpu(idle, cpu); + rcu_read_unlock(); + + rq->curr = rq->idle = idle; + idle->on_rq = TASK_ON_RQ_QUEUED; +#if defined(CONFIG_SMP) + idle->on_cpu = 1; +#endif + raw_spin_unlock_irqrestore(&rq->lock, flags); + + /* Set the preempt count _outside_ the spinlocks! */ + init_idle_preempt_count(idle, cpu); +#ifdef CONFIG_HAVE_PREEMPT_LAZY + task_thread_info(idle)->preempt_lazy_count = 0; +#endif + /* + * The idle tasks have their own, simple scheduling class: + */ + idle->sched_class = &idle_sched_class; + ftrace_graph_init_idle_task(idle, cpu); + vtime_init_idle(idle, cpu); +#if defined(CONFIG_SMP) + sprintf(idle->comm, "%s/%d", INIT_TASK_COMM, cpu); +#endif +} + +int cpuset_cpumask_can_shrink(const struct cpumask *cur, + const struct cpumask *trial) +{ + int ret = 1, trial_cpus; + struct dl_bw *cur_dl_b; + unsigned long flags; + + if (!cpumask_weight(cur)) + return ret; + + rcu_read_lock_sched(); + cur_dl_b = dl_bw_of(cpumask_any(cur)); + trial_cpus = cpumask_weight(trial); + + raw_spin_lock_irqsave(&cur_dl_b->lock, flags); + if (cur_dl_b->bw != -1 && + cur_dl_b->bw * trial_cpus < cur_dl_b->total_bw) + ret = 0; + raw_spin_unlock_irqrestore(&cur_dl_b->lock, flags); + rcu_read_unlock_sched(); + + return ret; +} + +int task_can_attach(struct task_struct *p, + const struct cpumask *cs_cpus_allowed) +{ + int ret = 0; + + /* + * Kthreads which disallow setaffinity shouldn't be moved + * to a new cpuset; we don't want to change their cpu + * affinity and isolating such threads by their set of + * allowed nodes is unnecessary. Thus, cpusets are not + * applicable for such threads. This prevents checking for + * success of set_cpus_allowed_ptr() on all attached tasks + * before cpus_allowed may be changed. + */ + if (p->flags & PF_NO_SETAFFINITY) { + ret = -EINVAL; + goto out; + } + +#ifdef CONFIG_SMP + if (dl_task(p) && !cpumask_intersects(task_rq(p)->rd->span, + cs_cpus_allowed)) { + unsigned int dest_cpu = cpumask_any_and(cpu_active_mask, + cs_cpus_allowed); + struct dl_bw *dl_b; + bool overflow; + int cpus; + unsigned long flags; + + rcu_read_lock_sched(); + dl_b = dl_bw_of(dest_cpu); + raw_spin_lock_irqsave(&dl_b->lock, flags); + cpus = dl_bw_cpus(dest_cpu); + overflow = __dl_overflow(dl_b, cpus, 0, p->dl.dl_bw); + if (overflow) + ret = -EBUSY; + else { + /* + * We reserve space for this task in the destination + * root_domain, as we can't fail after this point. + * We will free resources in the source root_domain + * later on (see set_cpus_allowed_dl()). + */ + __dl_add(dl_b, p->dl.dl_bw); + } + raw_spin_unlock_irqrestore(&dl_b->lock, flags); + rcu_read_unlock_sched(); + + } +#endif +out: + return ret; +} + +#ifdef CONFIG_SMP +/* + * move_queued_task - move a queued task to new rq. + * + * Returns (locked) new rq. Old rq's lock is released. + */ +static struct rq *move_queued_task(struct task_struct *p, int new_cpu) +{ + struct rq *rq = task_rq(p); + + lockdep_assert_held(&rq->lock); + + dequeue_task(rq, p, 0); + p->on_rq = TASK_ON_RQ_MIGRATING; + set_task_cpu(p, new_cpu); + raw_spin_unlock(&rq->lock); + + rq = cpu_rq(new_cpu); + + raw_spin_lock(&rq->lock); + BUG_ON(task_cpu(p) != new_cpu); + p->on_rq = TASK_ON_RQ_QUEUED; + enqueue_task(rq, p, 0); + check_preempt_curr(rq, p, 0); + + return rq; +} + +void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask) +{ + if (!migrate_disabled_updated(p)) { + if (p->sched_class->set_cpus_allowed) + p->sched_class->set_cpus_allowed(p, new_mask); + p->nr_cpus_allowed = cpumask_weight(new_mask); + } + + cpumask_copy(&p->cpus_allowed, new_mask); +} + +static DEFINE_PER_CPU(struct cpumask, sched_cpumasks); +static DEFINE_MUTEX(sched_down_mutex); +static cpumask_t sched_down_cpumask; + +void tell_sched_cpu_down_begin(int cpu) +{ + mutex_lock(&sched_down_mutex); + cpumask_set_cpu(cpu, &sched_down_cpumask); + mutex_unlock(&sched_down_mutex); +} + +void tell_sched_cpu_down_done(int cpu) +{ + mutex_lock(&sched_down_mutex); + cpumask_clear_cpu(cpu, &sched_down_cpumask); + mutex_unlock(&sched_down_mutex); +} + +/** + * migrate_me - try to move the current task off this cpu + * + * Used by the pin_current_cpu() code to try to get tasks + * to move off the current CPU as it is going down. + * It will only move the task if the task isn't pinned to + * the CPU (with migrate_disable, affinity or NO_SETAFFINITY) + * and the task has to be in a RUNNING state. Otherwise the + * movement of the task will wake it up (change its state + * to running) when the task did not expect it. + * + * Returns 1 if it succeeded in moving the current task + * 0 otherwise. + */ +int migrate_me(void) +{ + struct task_struct *p = current; + struct migration_arg arg; + struct cpumask *cpumask; + struct cpumask *mask; + unsigned long flags; + unsigned int dest_cpu; + struct rq *rq; + + /* + * We can not migrate tasks bounded to a CPU or tasks not + * running. The movement of the task will wake it up. + */ + if (p->flags & PF_NO_SETAFFINITY || p->state) + return 0; + + mutex_lock(&sched_down_mutex); + rq = task_rq_lock(p, &flags); + + cpumask = this_cpu_ptr(&sched_cpumasks); + mask = &p->cpus_allowed; + + cpumask_andnot(cpumask, mask, &sched_down_cpumask); + + if (!cpumask_weight(cpumask)) { + /* It's only on this CPU? */ + task_rq_unlock(rq, p, &flags); + mutex_unlock(&sched_down_mutex); + return 0; + } + + dest_cpu = cpumask_any_and(cpu_active_mask, cpumask); + + arg.task = p; + arg.dest_cpu = dest_cpu; + + task_rq_unlock(rq, p, &flags); + + stop_one_cpu(cpu_of(rq), migration_cpu_stop, &arg); + tlb_migrate_finish(p->mm); + mutex_unlock(&sched_down_mutex); + + return 1; +} + +/* + * This is how migration works: + * + * 1) we invoke migration_cpu_stop() on the target CPU using + * stop_one_cpu(). + * 2) stopper starts to run (implicitly forcing the migrated thread + * off the CPU) + * 3) it checks whether the migrated task is still in the wrong runqueue. + * 4) if it's in the wrong runqueue then the migration thread removes + * it and puts it into the right queue. + * 5) stopper completes and stop_one_cpu() returns and the migration + * is done. + */ + +/* + * Change a given task's CPU affinity. Migrate the thread to a + * proper CPU and schedule it away if the CPU it's executing on + * is removed from the allowed bitmask. + * + * NOTE: the caller must have a valid reference to the task, the + * task must not exit() & deallocate itself prematurely. The + * call is not atomic; no spinlocks may be held. + */ +int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask) +{ + unsigned long flags; + struct rq *rq; + unsigned int dest_cpu; + int ret = 0; + + rq = task_rq_lock(p, &flags); + + if (cpumask_equal(&p->cpus_allowed, new_mask)) + goto out; + + if (!cpumask_intersects(new_mask, cpu_active_mask)) { + ret = -EINVAL; + goto out; + } + + do_set_cpus_allowed(p, new_mask); + + /* Can the task run on the task's current CPU? If so, we're done */ + if (cpumask_test_cpu(task_cpu(p), new_mask) || __migrate_disabled(p)) + goto out; + + dest_cpu = cpumask_any_and(cpu_active_mask, new_mask); + if (task_running(rq, p) || p->state == TASK_WAKING) { + struct migration_arg arg = { p, dest_cpu }; + /* Need help from migration thread: drop lock and wait. */ + task_rq_unlock(rq, p, &flags); + stop_one_cpu(cpu_of(rq), migration_cpu_stop, &arg); + tlb_migrate_finish(p->mm); + return 0; + } else if (task_on_rq_queued(p)) + rq = move_queued_task(p, dest_cpu); +out: + task_rq_unlock(rq, p, &flags); + + return ret; +} +EXPORT_SYMBOL_GPL(set_cpus_allowed_ptr); + +/* + * Move (not current) task off this cpu, onto dest cpu. We're doing + * this because either it can't run here any more (set_cpus_allowed() + * away from this CPU, or CPU going down), or because we're + * attempting to rebalance this task on exec (sched_exec). + * + * So we race with normal scheduler movements, but that's OK, as long + * as the task is no longer on this CPU. + * + * Returns non-zero if task was successfully migrated. + */ +static int __migrate_task(struct task_struct *p, int src_cpu, int dest_cpu) +{ + struct rq *rq; + int ret = 0; + + if (unlikely(!cpu_active(dest_cpu))) + return ret; + + rq = cpu_rq(src_cpu); + + raw_spin_lock(&p->pi_lock); + raw_spin_lock(&rq->lock); + /* Already moved. */ + if (task_cpu(p) != src_cpu) + goto done; + + /* Affinity changed (again). */ + if (!cpumask_test_cpu(dest_cpu, tsk_cpus_allowed(p))) + goto fail; + + /* + * If we're not on a rq, the next wake-up will ensure we're + * placed properly. + */ + if (task_on_rq_queued(p)) + rq = move_queued_task(p, dest_cpu); +done: + ret = 1; +fail: + raw_spin_unlock(&rq->lock); + raw_spin_unlock(&p->pi_lock); + return ret; +} + +#ifdef CONFIG_NUMA_BALANCING +/* Migrate current task p to target_cpu */ +int migrate_task_to(struct task_struct *p, int target_cpu) +{ + struct migration_arg arg = { p, target_cpu }; + int curr_cpu = task_cpu(p); + + if (curr_cpu == target_cpu) + return 0; + + if (!cpumask_test_cpu(target_cpu, tsk_cpus_allowed(p))) + return -EINVAL; + + /* TODO: This is not properly updating schedstats */ + + trace_sched_move_numa(p, curr_cpu, target_cpu); + return stop_one_cpu(curr_cpu, migration_cpu_stop, &arg); +} + +/* + * Requeue a task on a given node and accurately track the number of NUMA + * tasks on the runqueues + */ +void sched_setnuma(struct task_struct *p, int nid) +{ + struct rq *rq; + unsigned long flags; + bool queued, running; + + rq = task_rq_lock(p, &flags); + queued = task_on_rq_queued(p); + running = task_current(rq, p); + + if (queued) + dequeue_task(rq, p, 0); + if (running) + put_prev_task(rq, p); + + p->numa_preferred_nid = nid; + + if (running) + p->sched_class->set_curr_task(rq); + if (queued) + enqueue_task(rq, p, 0); + task_rq_unlock(rq, p, &flags); +} +#endif + +/* + * migration_cpu_stop - this will be executed by a highprio stopper thread + * and performs thread migration by bumping thread off CPU then + * 'pushing' onto another runqueue. + */ +static int migration_cpu_stop(void *data) +{ + struct migration_arg *arg = data; + + /* + * The original target cpu might have gone down and we might + * be on another cpu but it doesn't matter. + */ + local_irq_disable(); + /* + * We need to explicitly wake pending tasks before running + * __migrate_task() such that we will not miss enforcing cpus_allowed + * during wakeups, see set_cpus_allowed_ptr()'s TASK_WAKING test. + */ + sched_ttwu_pending(); + __migrate_task(arg->task, raw_smp_processor_id(), arg->dest_cpu); + local_irq_enable(); + return 0; +} + +#ifdef CONFIG_HOTPLUG_CPU + +static DEFINE_PER_CPU(struct mm_struct *, idle_last_mm); + +/* + * Ensures that the idle task is using init_mm right before its cpu goes + * offline. + */ +void idle_task_exit(void) +{ + struct mm_struct *mm = current->active_mm; + + BUG_ON(cpu_online(smp_processor_id())); + + if (mm != &init_mm) { + switch_mm(mm, &init_mm, current); + finish_arch_post_lock_switch(); + } + /* + * Defer the cleanup to an alive cpu. On RT we can neither + * call mmdrop() nor mmdrop_delayed() from here. + */ + per_cpu(idle_last_mm, smp_processor_id()) = mm; +} + +/* + * Since this CPU is going 'away' for a while, fold any nr_active delta + * we might have. Assumes we're called after migrate_tasks() so that the + * nr_active count is stable. + * + * Also see the comment "Global load-average calculations". + */ +static void calc_load_migrate(struct rq *rq) +{ + long delta = calc_load_fold_active(rq); + if (delta) + atomic_long_add(delta, &calc_load_tasks); +} + +static void put_prev_task_fake(struct rq *rq, struct task_struct *prev) +{ +} + +static const struct sched_class fake_sched_class = { + .put_prev_task = put_prev_task_fake, +}; + +static struct task_struct fake_task = { + /* + * Avoid pull_{rt,dl}_task() + */ + .prio = MAX_PRIO + 1, + .sched_class = &fake_sched_class, +}; + +/* + * Migrate all tasks from the rq, sleeping tasks will be migrated by + * try_to_wake_up()->select_task_rq(). + * + * Called with rq->lock held even though we'er in stop_machine() and + * there's no concurrency possible, we hold the required locks anyway + * because of lock validation efforts. + */ +static void migrate_tasks(unsigned int dead_cpu) +{ + struct rq *rq = cpu_rq(dead_cpu); + struct task_struct *next, *stop = rq->stop; + int dest_cpu; + + /* + * Fudge the rq selection such that the below task selection loop + * doesn't get stuck on the currently eligible stop task. + * + * We're currently inside stop_machine() and the rq is either stuck + * in the stop_machine_cpu_stop() loop, or we're executing this code, + * either way we should never end up calling schedule() until we're + * done here. + */ + rq->stop = NULL; + + /* + * put_prev_task() and pick_next_task() sched + * class method both need to have an up-to-date + * value of rq->clock[_task] + */ + update_rq_clock(rq); + + for ( ; ; ) { + /* + * There's this thread running, bail when that's the only + * remaining thread. + */ + if (rq->nr_running == 1) + break; + + next = pick_next_task(rq, &fake_task); + BUG_ON(!next); + next->sched_class->put_prev_task(rq, next); + + /* Find suitable destination for @next, with force if needed. */ + dest_cpu = select_fallback_rq(dead_cpu, next); + raw_spin_unlock(&rq->lock); + + __migrate_task(next, dead_cpu, dest_cpu); + + raw_spin_lock(&rq->lock); + } + + rq->stop = stop; +} + +#endif /* CONFIG_HOTPLUG_CPU */ + +#if defined(CONFIG_SCHED_DEBUG) && defined(CONFIG_SYSCTL) + +static struct ctl_table sd_ctl_dir[] = { + { + .procname = "sched_domain", + .mode = 0555, + }, + {} +}; + +static struct ctl_table sd_ctl_root[] = { + { + .procname = "kernel", + .mode = 0555, + .child = sd_ctl_dir, + }, + {} +}; + +static struct ctl_table *sd_alloc_ctl_entry(int n) +{ + struct ctl_table *entry = + kcalloc(n, sizeof(struct ctl_table), GFP_KERNEL); + + return entry; +} + +static void sd_free_ctl_entry(struct ctl_table **tablep) +{ + struct ctl_table *entry; + + /* + * In the intermediate directories, both the child directory and + * procname are dynamically allocated and could fail but the mode + * will always be set. In the lowest directory the names are + * static strings and all have proc handlers. + */ + for (entry = *tablep; entry->mode; entry++) { + if (entry->child) + sd_free_ctl_entry(&entry->child); + if (entry->proc_handler == NULL) + kfree(entry->procname); + } + + kfree(*tablep); + *tablep = NULL; +} + +static int min_load_idx = 0; +static int max_load_idx = CPU_LOAD_IDX_MAX-1; + +static void +set_table_entry(struct ctl_table *entry, + const char *procname, void *data, int maxlen, + umode_t mode, proc_handler *proc_handler, + bool load_idx) +{ + entry->procname = procname; + entry->data = data; + entry->maxlen = maxlen; + entry->mode = mode; + entry->proc_handler = proc_handler; + + if (load_idx) { + entry->extra1 = &min_load_idx; + entry->extra2 = &max_load_idx; + } +} + +static struct ctl_table * +sd_alloc_ctl_domain_table(struct sched_domain *sd) +{ + struct ctl_table *table = sd_alloc_ctl_entry(14); + + if (table == NULL) + return NULL; + + set_table_entry(&table[0], "min_interval", &sd->min_interval, + sizeof(long), 0644, proc_doulongvec_minmax, false); + set_table_entry(&table[1], "max_interval", &sd->max_interval, + sizeof(long), 0644, proc_doulongvec_minmax, false); + set_table_entry(&table[2], "busy_idx", &sd->busy_idx, + sizeof(int), 0644, proc_dointvec_minmax, true); + set_table_entry(&table[3], "idle_idx", &sd->idle_idx, + sizeof(int), 0644, proc_dointvec_minmax, true); + set_table_entry(&table[4], "newidle_idx", &sd->newidle_idx, + sizeof(int), 0644, proc_dointvec_minmax, true); + set_table_entry(&table[5], "wake_idx", &sd->wake_idx, + sizeof(int), 0644, proc_dointvec_minmax, true); + set_table_entry(&table[6], "forkexec_idx", &sd->forkexec_idx, + sizeof(int), 0644, proc_dointvec_minmax, true); + set_table_entry(&table[7], "busy_factor", &sd->busy_factor, + sizeof(int), 0644, proc_dointvec_minmax, false); + set_table_entry(&table[8], "imbalance_pct", &sd->imbalance_pct, + sizeof(int), 0644, proc_dointvec_minmax, false); + set_table_entry(&table[9], "cache_nice_tries", + &sd->cache_nice_tries, + sizeof(int), 0644, proc_dointvec_minmax, false); + set_table_entry(&table[10], "flags", &sd->flags, + sizeof(int), 0644, proc_dointvec_minmax, false); + set_table_entry(&table[11], "max_newidle_lb_cost", + &sd->max_newidle_lb_cost, + sizeof(long), 0644, proc_doulongvec_minmax, false); + set_table_entry(&table[12], "name", sd->name, + CORENAME_MAX_SIZE, 0444, proc_dostring, false); + /* &table[13] is terminator */ + + return table; +} + +static struct ctl_table *sd_alloc_ctl_cpu_table(int cpu) +{ + struct ctl_table *entry, *table; + struct sched_domain *sd; + int domain_num = 0, i; + char buf[32]; + + for_each_domain(cpu, sd) + domain_num++; + entry = table = sd_alloc_ctl_entry(domain_num + 1); + if (table == NULL) + return NULL; + + i = 0; + for_each_domain(cpu, sd) { + snprintf(buf, 32, "domain%d", i); + entry->procname = kstrdup(buf, GFP_KERNEL); + entry->mode = 0555; + entry->child = sd_alloc_ctl_domain_table(sd); + entry++; + i++; + } + return table; +} + +static struct ctl_table_header *sd_sysctl_header; +static void register_sched_domain_sysctl(void) +{ + int i, cpu_num = num_possible_cpus(); + struct ctl_table *entry = sd_alloc_ctl_entry(cpu_num + 1); + char buf[32]; + + WARN_ON(sd_ctl_dir[0].child); + sd_ctl_dir[0].child = entry; + + if (entry == NULL) + return; + + for_each_possible_cpu(i) { + snprintf(buf, 32, "cpu%d", i); + entry->procname = kstrdup(buf, GFP_KERNEL); + entry->mode = 0555; + entry->child = sd_alloc_ctl_cpu_table(i); + entry++; + } + + WARN_ON(sd_sysctl_header); + sd_sysctl_header = register_sysctl_table(sd_ctl_root); +} + +/* may be called multiple times per register */ +static void unregister_sched_domain_sysctl(void) +{ + if (sd_sysctl_header) + unregister_sysctl_table(sd_sysctl_header); + sd_sysctl_header = NULL; + if (sd_ctl_dir[0].child) + sd_free_ctl_entry(&sd_ctl_dir[0].child); +} +#else +static void register_sched_domain_sysctl(void) +{ +} +static void unregister_sched_domain_sysctl(void) +{ +} +#endif + +static void set_rq_online(struct rq *rq) +{ + if (!rq->online) { + const struct sched_class *class; + + cpumask_set_cpu(rq->cpu, rq->rd->online); + rq->online = 1; + + for_each_class(class) { + if (class->rq_online) + class->rq_online(rq); + } + } +} + +static void set_rq_offline(struct rq *rq) +{ + if (rq->online) { + const struct sched_class *class; + + for_each_class(class) { + if (class->rq_offline) + class->rq_offline(rq); + } + + cpumask_clear_cpu(rq->cpu, rq->rd->online); + rq->online = 0; + } +} + +/* + * migration_call - callback that gets triggered when a CPU is added. + * Here we can start up the necessary migration thread for the new CPU. + */ +static int +migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu) +{ + int cpu = (long)hcpu; + unsigned long flags; + struct rq *rq = cpu_rq(cpu); + + switch (action & ~CPU_TASKS_FROZEN) { + + case CPU_UP_PREPARE: + rq->calc_load_update = calc_load_update; + break; + + case CPU_ONLINE: + /* Update our root-domain */ + raw_spin_lock_irqsave(&rq->lock, flags); + if (rq->rd) { + BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span)); + + set_rq_online(rq); + } + raw_spin_unlock_irqrestore(&rq->lock, flags); + break; + +#ifdef CONFIG_HOTPLUG_CPU + case CPU_DYING: + sched_ttwu_pending(); + /* Update our root-domain */ + raw_spin_lock_irqsave(&rq->lock, flags); + if (rq->rd) { + BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span)); + set_rq_offline(rq); + } + migrate_tasks(cpu); + BUG_ON(rq->nr_running != 1); /* the migration thread */ + raw_spin_unlock_irqrestore(&rq->lock, flags); + break; + + case CPU_DEAD: + calc_load_migrate(rq); + if (per_cpu(idle_last_mm, cpu)) { + mmdrop(per_cpu(idle_last_mm, cpu)); + per_cpu(idle_last_mm, cpu) = NULL; + } + break; +#endif + } + + update_max_interval(); + + return NOTIFY_OK; +} + +/* + * Register at high priority so that task migration (migrate_all_tasks) + * happens before everything else. This has to be lower priority than + * the notifier in the perf_event subsystem, though. + */ +static struct notifier_block migration_notifier = { + .notifier_call = migration_call, + .priority = CPU_PRI_MIGRATION, +}; + +static void __cpuinit set_cpu_rq_start_time(void) +{ + int cpu = smp_processor_id(); + struct rq *rq = cpu_rq(cpu); + rq->age_stamp = sched_clock_cpu(cpu); +} + +static int sched_cpu_active(struct notifier_block *nfb, + unsigned long action, void *hcpu) +{ + switch (action & ~CPU_TASKS_FROZEN) { + case CPU_STARTING: + set_cpu_rq_start_time(); + return NOTIFY_OK; + case CPU_DOWN_FAILED: + set_cpu_active((long)hcpu, true); + return NOTIFY_OK; + default: + return NOTIFY_DONE; + } +} + +static int sched_cpu_inactive(struct notifier_block *nfb, + unsigned long action, void *hcpu) +{ + switch (action & ~CPU_TASKS_FROZEN) { + case CPU_DOWN_PREPARE: + set_cpu_active((long)hcpu, false); + return NOTIFY_OK; + default: + return NOTIFY_DONE; + } +} + +static int __init migration_init(void) +{ + void *cpu = (void *)(long)smp_processor_id(); + int err; + + /* Initialize migration for the boot CPU */ + err = migration_call(&migration_notifier, CPU_UP_PREPARE, cpu); + BUG_ON(err == NOTIFY_BAD); + migration_call(&migration_notifier, CPU_ONLINE, cpu); + register_cpu_notifier(&migration_notifier); + + /* Register cpu active notifiers */ + cpu_notifier(sched_cpu_active, CPU_PRI_SCHED_ACTIVE); + cpu_notifier(sched_cpu_inactive, CPU_PRI_SCHED_INACTIVE); + + return 0; +} +early_initcall(migration_init); +#endif + +#ifdef CONFIG_SMP + +static cpumask_var_t sched_domains_tmpmask; /* sched_domains_mutex */ + +#ifdef CONFIG_SCHED_DEBUG + +static __read_mostly int sched_debug_enabled; + +static int __init sched_debug_setup(char *str) +{ + sched_debug_enabled = 1; + + return 0; +} +early_param("sched_debug", sched_debug_setup); + +static inline bool sched_debug(void) +{ + return sched_debug_enabled; +} + +static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level, + struct cpumask *groupmask) +{ + struct sched_group *group = sd->groups; + + cpumask_clear(groupmask); + + printk(KERN_DEBUG "%*s domain %d: ", level, "", level); + + if (!(sd->flags & SD_LOAD_BALANCE)) { + printk("does not load-balance\n"); + if (sd->parent) + printk(KERN_ERR "ERROR: !SD_LOAD_BALANCE domain" + " has parent"); + return -1; + } + + printk(KERN_CONT "span %*pbl level %s\n", + cpumask_pr_args(sched_domain_span(sd)), sd->name); + + if (!cpumask_test_cpu(cpu, sched_domain_span(sd))) { + printk(KERN_ERR "ERROR: domain->span does not contain " + "CPU%d\n", cpu); + } + if (!cpumask_test_cpu(cpu, sched_group_cpus(group))) { + printk(KERN_ERR "ERROR: domain->groups does not contain" + " CPU%d\n", cpu); + } + + printk(KERN_DEBUG "%*s groups:", level + 1, ""); + do { + if (!group) { + printk("\n"); + printk(KERN_ERR "ERROR: group is NULL\n"); + break; + } + + if (!cpumask_weight(sched_group_cpus(group))) { + printk(KERN_CONT "\n"); + printk(KERN_ERR "ERROR: empty group\n"); + break; + } + + if (!(sd->flags & SD_OVERLAP) && + cpumask_intersects(groupmask, sched_group_cpus(group))) { + printk(KERN_CONT "\n"); + printk(KERN_ERR "ERROR: repeated CPUs\n"); + break; + } + + cpumask_or(groupmask, groupmask, sched_group_cpus(group)); + + printk(KERN_CONT " %*pbl", + cpumask_pr_args(sched_group_cpus(group))); + if (group->sgc->capacity != SCHED_CAPACITY_SCALE) { + printk(KERN_CONT " (cpu_capacity = %d)", + group->sgc->capacity); + } + + group = group->next; + } while (group != sd->groups); + printk(KERN_CONT "\n"); + + if (!cpumask_equal(sched_domain_span(sd), groupmask)) + printk(KERN_ERR "ERROR: groups don't span domain->span\n"); + + if (sd->parent && + !cpumask_subset(groupmask, sched_domain_span(sd->parent))) + printk(KERN_ERR "ERROR: parent span is not a superset " + "of domain->span\n"); + return 0; +} + +static void sched_domain_debug(struct sched_domain *sd, int cpu) +{ + int level = 0; + + if (!sched_debug_enabled) + return; + + if (!sd) { + printk(KERN_DEBUG "CPU%d attaching NULL sched-domain.\n", cpu); + return; + } + + printk(KERN_DEBUG "CPU%d attaching sched-domain:\n", cpu); + + for (;;) { + if (sched_domain_debug_one(sd, cpu, level, sched_domains_tmpmask)) + break; + level++; + sd = sd->parent; + if (!sd) + break; + } +} +#else /* !CONFIG_SCHED_DEBUG */ +# define sched_domain_debug(sd, cpu) do { } while (0) +static inline bool sched_debug(void) +{ + return false; +} +#endif /* CONFIG_SCHED_DEBUG */ + +static int sd_degenerate(struct sched_domain *sd) +{ + if (cpumask_weight(sched_domain_span(sd)) == 1) + return 1; + + /* Following flags need at least 2 groups */ + if (sd->flags & (SD_LOAD_BALANCE | + SD_BALANCE_NEWIDLE | + SD_BALANCE_FORK | + SD_BALANCE_EXEC | + SD_SHARE_CPUCAPACITY | + SD_SHARE_PKG_RESOURCES | + SD_SHARE_POWERDOMAIN)) { + if (sd->groups != sd->groups->next) + return 0; + } + + /* Following flags don't use groups */ + if (sd->flags & (SD_WAKE_AFFINE)) + return 0; + + return 1; +} + +static int +sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent) +{ + unsigned long cflags = sd->flags, pflags = parent->flags; + + if (sd_degenerate(parent)) + return 1; + + if (!cpumask_equal(sched_domain_span(sd), sched_domain_span(parent))) + return 0; + + /* Flags needing groups don't count if only 1 group in parent */ + if (parent->groups == parent->groups->next) { + pflags &= ~(SD_LOAD_BALANCE | + SD_BALANCE_NEWIDLE | + SD_BALANCE_FORK | + SD_BALANCE_EXEC | + SD_SHARE_CPUCAPACITY | + SD_SHARE_PKG_RESOURCES | + SD_PREFER_SIBLING | + SD_SHARE_POWERDOMAIN); + if (nr_node_ids == 1) + pflags &= ~SD_SERIALIZE; + } + if (~cflags & pflags) + return 0; + + return 1; +} + +static void free_rootdomain(struct rcu_head *rcu) +{ + struct root_domain *rd = container_of(rcu, struct root_domain, rcu); + + cpupri_cleanup(&rd->cpupri); + cpudl_cleanup(&rd->cpudl); + free_cpumask_var(rd->dlo_mask); + free_cpumask_var(rd->rto_mask); + free_cpumask_var(rd->online); + free_cpumask_var(rd->span); + kfree(rd); +} + +static void rq_attach_root(struct rq *rq, struct root_domain *rd) +{ + struct root_domain *old_rd = NULL; + unsigned long flags; + + raw_spin_lock_irqsave(&rq->lock, flags); + + if (rq->rd) { + old_rd = rq->rd; + + if (cpumask_test_cpu(rq->cpu, old_rd->online)) + set_rq_offline(rq); + + cpumask_clear_cpu(rq->cpu, old_rd->span); + + /* + * If we dont want to free the old_rd yet then + * set old_rd to NULL to skip the freeing later + * in this function: + */ + if (!atomic_dec_and_test(&old_rd->refcount)) + old_rd = NULL; + } + + atomic_inc(&rd->refcount); + rq->rd = rd; + + cpumask_set_cpu(rq->cpu, rd->span); + if (cpumask_test_cpu(rq->cpu, cpu_active_mask)) + set_rq_online(rq); + + raw_spin_unlock_irqrestore(&rq->lock, flags); + + if (old_rd) + call_rcu_sched(&old_rd->rcu, free_rootdomain); +} + +static int init_rootdomain(struct root_domain *rd) +{ + memset(rd, 0, sizeof(*rd)); + + if (!alloc_cpumask_var(&rd->span, GFP_KERNEL)) + goto out; + if (!alloc_cpumask_var(&rd->online, GFP_KERNEL)) + goto free_span; + if (!alloc_cpumask_var(&rd->dlo_mask, GFP_KERNEL)) + goto free_online; + if (!alloc_cpumask_var(&rd->rto_mask, GFP_KERNEL)) + goto free_dlo_mask; + + init_dl_bw(&rd->dl_bw); + if (cpudl_init(&rd->cpudl) != 0) + goto free_dlo_mask; + + if (cpupri_init(&rd->cpupri) != 0) + goto free_rto_mask; + return 0; + +free_rto_mask: + free_cpumask_var(rd->rto_mask); +free_dlo_mask: + free_cpumask_var(rd->dlo_mask); +free_online: + free_cpumask_var(rd->online); +free_span: + free_cpumask_var(rd->span); +out: + return -ENOMEM; +} + +/* + * By default the system creates a single root-domain with all cpus as + * members (mimicking the global state we have today). + */ +struct root_domain def_root_domain; + +static void init_defrootdomain(void) +{ + init_rootdomain(&def_root_domain); + + atomic_set(&def_root_domain.refcount, 1); +} + +static struct root_domain *alloc_rootdomain(void) +{ + struct root_domain *rd; + + rd = kmalloc(sizeof(*rd), GFP_KERNEL); + if (!rd) + return NULL; + + if (init_rootdomain(rd) != 0) { + kfree(rd); + return NULL; + } + + return rd; +} + +static void free_sched_groups(struct sched_group *sg, int free_sgc) +{ + struct sched_group *tmp, *first; + + if (!sg) + return; + + first = sg; + do { + tmp = sg->next; + + if (free_sgc && atomic_dec_and_test(&sg->sgc->ref)) + kfree(sg->sgc); + + kfree(sg); + sg = tmp; + } while (sg != first); +} + +static void free_sched_domain(struct rcu_head *rcu) +{ + struct sched_domain *sd = container_of(rcu, struct sched_domain, rcu); + + /* + * If its an overlapping domain it has private groups, iterate and + * nuke them all. + */ + if (sd->flags & SD_OVERLAP) { + free_sched_groups(sd->groups, 1); + } else if (atomic_dec_and_test(&sd->groups->ref)) { + kfree(sd->groups->sgc); + kfree(sd->groups); + } + kfree(sd); +} + +static void destroy_sched_domain(struct sched_domain *sd, int cpu) +{ + call_rcu(&sd->rcu, free_sched_domain); +} + +static void destroy_sched_domains(struct sched_domain *sd, int cpu) +{ + for (; sd; sd = sd->parent) + destroy_sched_domain(sd, cpu); +} + +/* + * Keep a special pointer to the highest sched_domain that has + * SD_SHARE_PKG_RESOURCE set (Last Level Cache Domain) for this + * allows us to avoid some pointer chasing select_idle_sibling(). + * + * Also keep a unique ID per domain (we use the first cpu number in + * the cpumask of the domain), this allows us to quickly tell if + * two cpus are in the same cache domain, see cpus_share_cache(). + */ +DEFINE_PER_CPU(struct sched_domain *, sd_llc); +DEFINE_PER_CPU(int, sd_llc_size); +DEFINE_PER_CPU(int, sd_llc_id); +DEFINE_PER_CPU(struct sched_domain *, sd_numa); +DEFINE_PER_CPU(struct sched_domain *, sd_busy); +DEFINE_PER_CPU(struct sched_domain *, sd_asym); + +static void update_top_cache_domain(int cpu) +{ + struct sched_domain *sd; + struct sched_domain *busy_sd = NULL; + int id = cpu; + int size = 1; + + sd = highest_flag_domain(cpu, SD_SHARE_PKG_RESOURCES); + if (sd) { + id = cpumask_first(sched_domain_span(sd)); + size = cpumask_weight(sched_domain_span(sd)); + busy_sd = sd->parent; /* sd_busy */ + } + rcu_assign_pointer(per_cpu(sd_busy, cpu), busy_sd); + + rcu_assign_pointer(per_cpu(sd_llc, cpu), sd); + per_cpu(sd_llc_size, cpu) = size; + per_cpu(sd_llc_id, cpu) = id; + + sd = lowest_flag_domain(cpu, SD_NUMA); + rcu_assign_pointer(per_cpu(sd_numa, cpu), sd); + + sd = highest_flag_domain(cpu, SD_ASYM_PACKING); + rcu_assign_pointer(per_cpu(sd_asym, cpu), sd); +} + +/* + * Attach the domain 'sd' to 'cpu' as its base domain. Callers must + * hold the hotplug lock. + */ +static void +cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu) +{ + struct rq *rq = cpu_rq(cpu); + struct sched_domain *tmp; + + /* Remove the sched domains which do not contribute to scheduling. */ + for (tmp = sd; tmp; ) { + struct sched_domain *parent = tmp->parent; + if (!parent) + break; + + if (sd_parent_degenerate(tmp, parent)) { + tmp->parent = parent->parent; + if (parent->parent) + parent->parent->child = tmp; + /* + * Transfer SD_PREFER_SIBLING down in case of a + * degenerate parent; the spans match for this + * so the property transfers. + */ + if (parent->flags & SD_PREFER_SIBLING) + tmp->flags |= SD_PREFER_SIBLING; + destroy_sched_domain(parent, cpu); + } else + tmp = tmp->parent; + } + + if (sd && sd_degenerate(sd)) { + tmp = sd; + sd = sd->parent; + destroy_sched_domain(tmp, cpu); + if (sd) + sd->child = NULL; + } + + sched_domain_debug(sd, cpu); + + rq_attach_root(rq, rd); + tmp = rq->sd; + rcu_assign_pointer(rq->sd, sd); + destroy_sched_domains(tmp, cpu); + + update_top_cache_domain(cpu); +} + +/* Setup the mask of cpus configured for isolated domains */ +static int __init isolated_cpu_setup(char *str) +{ + alloc_bootmem_cpumask_var(&cpu_isolated_map); + cpulist_parse(str, cpu_isolated_map); + return 1; +} + +__setup("isolcpus=", isolated_cpu_setup); + +struct s_data { + struct sched_domain ** __percpu sd; + struct root_domain *rd; +}; + +enum s_alloc { + sa_rootdomain, + sa_sd, + sa_sd_storage, + sa_none, +}; + +/* + * Build an iteration mask that can exclude certain CPUs from the upwards + * domain traversal. + * + * Asymmetric node setups can result in situations where the domain tree is of + * unequal depth, make sure to skip domains that already cover the entire + * range. + * + * In that case build_sched_domains() will have terminated the iteration early + * and our sibling sd spans will be empty. Domains should always include the + * cpu they're built on, so check that. + * + */ +static void build_group_mask(struct sched_domain *sd, struct sched_group *sg) +{ + const struct cpumask *span = sched_domain_span(sd); + struct sd_data *sdd = sd->private; + struct sched_domain *sibling; + int i; + + for_each_cpu(i, span) { + sibling = *per_cpu_ptr(sdd->sd, i); + if (!cpumask_test_cpu(i, sched_domain_span(sibling))) + continue; + + cpumask_set_cpu(i, sched_group_mask(sg)); + } +} + +/* + * Return the canonical balance cpu for this group, this is the first cpu + * of this group that's also in the iteration mask. + */ +int group_balance_cpu(struct sched_group *sg) +{ + return cpumask_first_and(sched_group_cpus(sg), sched_group_mask(sg)); +} + +static int +build_overlap_sched_groups(struct sched_domain *sd, int cpu) +{ + struct sched_group *first = NULL, *last = NULL, *groups = NULL, *sg; + const struct cpumask *span = sched_domain_span(sd); + struct cpumask *covered = sched_domains_tmpmask; + struct sd_data *sdd = sd->private; + struct sched_domain *sibling; + int i; + + cpumask_clear(covered); + + for_each_cpu(i, span) { + struct cpumask *sg_span; + + if (cpumask_test_cpu(i, covered)) + continue; + + sibling = *per_cpu_ptr(sdd->sd, i); + + /* See the comment near build_group_mask(). */ + if (!cpumask_test_cpu(i, sched_domain_span(sibling))) + continue; + + sg = kzalloc_node(sizeof(struct sched_group) + cpumask_size(), + GFP_KERNEL, cpu_to_node(cpu)); + + if (!sg) + goto fail; + + sg_span = sched_group_cpus(sg); + if (sibling->child) + cpumask_copy(sg_span, sched_domain_span(sibling->child)); + else + cpumask_set_cpu(i, sg_span); + + cpumask_or(covered, covered, sg_span); + + sg->sgc = *per_cpu_ptr(sdd->sgc, i); + if (atomic_inc_return(&sg->sgc->ref) == 1) + build_group_mask(sd, sg); + + /* + * Initialize sgc->capacity such that even if we mess up the + * domains and no possible iteration will get us here, we won't + * die on a /0 trap. + */ + sg->sgc->capacity = SCHED_CAPACITY_SCALE * cpumask_weight(sg_span); + + /* + * Make sure the first group of this domain contains the + * canonical balance cpu. Otherwise the sched_domain iteration + * breaks. See update_sg_lb_stats(). + */ + if ((!groups && cpumask_test_cpu(cpu, sg_span)) || + group_balance_cpu(sg) == cpu) + groups = sg; + + if (!first) + first = sg; + if (last) + last->next = sg; + last = sg; + last->next = first; + } + sd->groups = groups; + + return 0; + +fail: + free_sched_groups(first, 0); + + return -ENOMEM; +} + +static int get_group(int cpu, struct sd_data *sdd, struct sched_group **sg) +{ + struct sched_domain *sd = *per_cpu_ptr(sdd->sd, cpu); + struct sched_domain *child = sd->child; + + if (child) + cpu = cpumask_first(sched_domain_span(child)); + + if (sg) { + *sg = *per_cpu_ptr(sdd->sg, cpu); + (*sg)->sgc = *per_cpu_ptr(sdd->sgc, cpu); + atomic_set(&(*sg)->sgc->ref, 1); /* for claim_allocations */ + } + + return cpu; +} + +/* + * build_sched_groups will build a circular linked list of the groups + * covered by the given span, and will set each group's ->cpumask correctly, + * and ->cpu_capacity to 0. + * + * Assumes the sched_domain tree is fully constructed + */ +static int +build_sched_groups(struct sched_domain *sd, int cpu) +{ + struct sched_group *first = NULL, *last = NULL; + struct sd_data *sdd = sd->private; + const struct cpumask *span = sched_domain_span(sd); + struct cpumask *covered; + int i; + + get_group(cpu, sdd, &sd->groups); + atomic_inc(&sd->groups->ref); + + if (cpu != cpumask_first(span)) + return 0; + + lockdep_assert_held(&sched_domains_mutex); + covered = sched_domains_tmpmask; + + cpumask_clear(covered); + + for_each_cpu(i, span) { + struct sched_group *sg; + int group, j; + + if (cpumask_test_cpu(i, covered)) + continue; + + group = get_group(i, sdd, &sg); + cpumask_setall(sched_group_mask(sg)); + + for_each_cpu(j, span) { + if (get_group(j, sdd, NULL) != group) + continue; + + cpumask_set_cpu(j, covered); + cpumask_set_cpu(j, sched_group_cpus(sg)); + } + + if (!first) + first = sg; + if (last) + last->next = sg; + last = sg; + } + last->next = first; + + return 0; +} + +/* + * Initialize sched groups cpu_capacity. + * + * cpu_capacity indicates the capacity of sched group, which is used while + * distributing the load between different sched groups in a sched domain. + * Typically cpu_capacity for all the groups in a sched domain will be same + * unless there are asymmetries in the topology. If there are asymmetries, + * group having more cpu_capacity will pickup more load compared to the + * group having less cpu_capacity. + */ +static void init_sched_groups_capacity(int cpu, struct sched_domain *sd) +{ + struct sched_group *sg = sd->groups; + + WARN_ON(!sg); + + do { + sg->group_weight = cpumask_weight(sched_group_cpus(sg)); + sg = sg->next; + } while (sg != sd->groups); + + if (cpu != group_balance_cpu(sg)) + return; + + update_group_capacity(sd, cpu); + atomic_set(&sg->sgc->nr_busy_cpus, sg->group_weight); +} + +/* + * Initializers for schedule domains + * Non-inlined to reduce accumulated stack pressure in build_sched_domains() + */ + +static int default_relax_domain_level = -1; +int sched_domain_level_max; + +static int __init setup_relax_domain_level(char *str) +{ + if (kstrtoint(str, 0, &default_relax_domain_level)) + pr_warn("Unable to set relax_domain_level\n"); + + return 1; +} +__setup("relax_domain_level=", setup_relax_domain_level); + +static void set_domain_attribute(struct sched_domain *sd, + struct sched_domain_attr *attr) +{ + int request; + + if (!attr || attr->relax_domain_level < 0) { + if (default_relax_domain_level < 0) + return; + else + request = default_relax_domain_level; + } else + request = attr->relax_domain_level; + if (request < sd->level) { + /* turn off idle balance on this domain */ + sd->flags &= ~(SD_BALANCE_WAKE|SD_BALANCE_NEWIDLE); + } else { + /* turn on idle balance on this domain */ + sd->flags |= (SD_BALANCE_WAKE|SD_BALANCE_NEWIDLE); + } +} + +static void __sdt_free(const struct cpumask *cpu_map); +static int __sdt_alloc(const struct cpumask *cpu_map); + +static void __free_domain_allocs(struct s_data *d, enum s_alloc what, + const struct cpumask *cpu_map) +{ + switch (what) { + case sa_rootdomain: + if (!atomic_read(&d->rd->refcount)) + free_rootdomain(&d->rd->rcu); /* fall through */ + case sa_sd: + free_percpu(d->sd); /* fall through */ + case sa_sd_storage: + __sdt_free(cpu_map); /* fall through */ + case sa_none: + break; + } +} + +static enum s_alloc __visit_domain_allocation_hell(struct s_data *d, + const struct cpumask *cpu_map) +{ + memset(d, 0, sizeof(*d)); + + if (__sdt_alloc(cpu_map)) + return sa_sd_storage; + d->sd = alloc_percpu(struct sched_domain *); + if (!d->sd) + return sa_sd_storage; + d->rd = alloc_rootdomain(); + if (!d->rd) + return sa_sd; + return sa_rootdomain; +} + +/* + * NULL the sd_data elements we've used to build the sched_domain and + * sched_group structure so that the subsequent __free_domain_allocs() + * will not free the data we're using. + */ +static void claim_allocations(int cpu, struct sched_domain *sd) +{ + struct sd_data *sdd = sd->private; + + WARN_ON_ONCE(*per_cpu_ptr(sdd->sd, cpu) != sd); + *per_cpu_ptr(sdd->sd, cpu) = NULL; + + if (atomic_read(&(*per_cpu_ptr(sdd->sg, cpu))->ref)) + *per_cpu_ptr(sdd->sg, cpu) = NULL; + + if (atomic_read(&(*per_cpu_ptr(sdd->sgc, cpu))->ref)) + *per_cpu_ptr(sdd->sgc, cpu) = NULL; +} + +#ifdef CONFIG_NUMA +static int sched_domains_numa_levels; +enum numa_topology_type sched_numa_topology_type; +static int *sched_domains_numa_distance; +int sched_max_numa_distance; +static struct cpumask ***sched_domains_numa_masks; +static int sched_domains_curr_level; +#endif + +/* + * SD_flags allowed in topology descriptions. + * + * SD_SHARE_CPUCAPACITY - describes SMT topologies + * SD_SHARE_PKG_RESOURCES - describes shared caches + * SD_NUMA - describes NUMA topologies + * SD_SHARE_POWERDOMAIN - describes shared power domain + * + * Odd one out: + * SD_ASYM_PACKING - describes SMT quirks + */ +#define TOPOLOGY_SD_FLAGS \ + (SD_SHARE_CPUCAPACITY | \ + SD_SHARE_PKG_RESOURCES | \ + SD_NUMA | \ + SD_ASYM_PACKING | \ + SD_SHARE_POWERDOMAIN) + +static struct sched_domain * +sd_init(struct sched_domain_topology_level *tl, int cpu) +{ + struct sched_domain *sd = *per_cpu_ptr(tl->data.sd, cpu); + int sd_weight, sd_flags = 0; + +#ifdef CONFIG_NUMA + /* + * Ugly hack to pass state to sd_numa_mask()... + */ + sched_domains_curr_level = tl->numa_level; +#endif + + sd_weight = cpumask_weight(tl->mask(cpu)); + + if (tl->sd_flags) + sd_flags = (*tl->sd_flags)(); + if (WARN_ONCE(sd_flags & ~TOPOLOGY_SD_FLAGS, + "wrong sd_flags in topology description\n")) + sd_flags &= ~TOPOLOGY_SD_FLAGS; + + *sd = (struct sched_domain){ + .min_interval = sd_weight, + .max_interval = 2*sd_weight, + .busy_factor = 32, + .imbalance_pct = 125, + + .cache_nice_tries = 0, + .busy_idx = 0, + .idle_idx = 0, + .newidle_idx = 0, + .wake_idx = 0, + .forkexec_idx = 0, + + .flags = 1*SD_LOAD_BALANCE + | 1*SD_BALANCE_NEWIDLE + | 1*SD_BALANCE_EXEC + | 1*SD_BALANCE_FORK + | 0*SD_BALANCE_WAKE + | 1*SD_WAKE_AFFINE + | 0*SD_SHARE_CPUCAPACITY + | 0*SD_SHARE_PKG_RESOURCES + | 0*SD_SERIALIZE + | 0*SD_PREFER_SIBLING + | 0*SD_NUMA + | sd_flags + , + + .last_balance = jiffies, + .balance_interval = sd_weight, + .smt_gain = 0, + .max_newidle_lb_cost = 0, + .next_decay_max_lb_cost = jiffies, +#ifdef CONFIG_SCHED_DEBUG + .name = tl->name, +#endif + }; + + /* + * Convert topological properties into behaviour. + */ + + if (sd->flags & SD_SHARE_CPUCAPACITY) { + sd->flags |= SD_PREFER_SIBLING; + sd->imbalance_pct = 110; + sd->smt_gain = 1178; /* ~15% */ + + } else if (sd->flags & SD_SHARE_PKG_RESOURCES) { + sd->imbalance_pct = 117; + sd->cache_nice_tries = 1; + sd->busy_idx = 2; + +#ifdef CONFIG_NUMA + } else if (sd->flags & SD_NUMA) { + sd->cache_nice_tries = 2; + sd->busy_idx = 3; + sd->idle_idx = 2; + + sd->flags |= SD_SERIALIZE; + if (sched_domains_numa_distance[tl->numa_level] > RECLAIM_DISTANCE) { + sd->flags &= ~(SD_BALANCE_EXEC | + SD_BALANCE_FORK | + SD_WAKE_AFFINE); + } + +#endif + } else { + sd->flags |= SD_PREFER_SIBLING; + sd->cache_nice_tries = 1; + sd->busy_idx = 2; + sd->idle_idx = 1; + } + + sd->private = &tl->data; + + return sd; +} + +/* + * Topology list, bottom-up. + */ +static struct sched_domain_topology_level default_topology[] = { +#ifdef CONFIG_SCHED_SMT + { cpu_smt_mask, cpu_smt_flags, SD_INIT_NAME(SMT) }, +#endif +#ifdef CONFIG_SCHED_MC + { cpu_coregroup_mask, cpu_core_flags, SD_INIT_NAME(MC) }, +#endif + { cpu_cpu_mask, SD_INIT_NAME(DIE) }, + { NULL, }, +}; + +struct sched_domain_topology_level *sched_domain_topology = default_topology; + +#define for_each_sd_topology(tl) \ + for (tl = sched_domain_topology; tl->mask; tl++) + +void set_sched_topology(struct sched_domain_topology_level *tl) +{ + sched_domain_topology = tl; +} + +#ifdef CONFIG_NUMA + +static const struct cpumask *sd_numa_mask(int cpu) +{ + return sched_domains_numa_masks[sched_domains_curr_level][cpu_to_node(cpu)]; +} + +static void sched_numa_warn(const char *str) +{ + static int done = false; + int i,j; + + if (done) + return; + + done = true; + + printk(KERN_WARNING "ERROR: %s\n\n", str); + + for (i = 0; i < nr_node_ids; i++) { + printk(KERN_WARNING " "); + for (j = 0; j < nr_node_ids; j++) + printk(KERN_CONT "%02d ", node_distance(i,j)); + printk(KERN_CONT "\n"); + } + printk(KERN_WARNING "\n"); +} + +bool find_numa_distance(int distance) +{ + int i; + + if (distance == node_distance(0, 0)) + return true; + + for (i = 0; i < sched_domains_numa_levels; i++) { + if (sched_domains_numa_distance[i] == distance) + return true; + } + + return false; +} + +/* + * A system can have three types of NUMA topology: + * NUMA_DIRECT: all nodes are directly connected, or not a NUMA system + * NUMA_GLUELESS_MESH: some nodes reachable through intermediary nodes + * NUMA_BACKPLANE: nodes can reach other nodes through a backplane + * + * The difference between a glueless mesh topology and a backplane + * topology lies in whether communication between not directly + * connected nodes goes through intermediary nodes (where programs + * could run), or through backplane controllers. This affects + * placement of programs. + * + * The type of topology can be discerned with the following tests: + * - If the maximum distance between any nodes is 1 hop, the system + * is directly connected. + * - If for two nodes A and B, located N > 1 hops away from each other, + * there is an intermediary node C, which is < N hops away from both + * nodes A and B, the system is a glueless mesh. + */ +static void init_numa_topology_type(void) +{ + int a, b, c, n; + + n = sched_max_numa_distance; + + if (n <= 1) + sched_numa_topology_type = NUMA_DIRECT; + + for_each_online_node(a) { + for_each_online_node(b) { + /* Find two nodes furthest removed from each other. */ + if (node_distance(a, b) < n) + continue; + + /* Is there an intermediary node between a and b? */ + for_each_online_node(c) { + if (node_distance(a, c) < n && + node_distance(b, c) < n) { + sched_numa_topology_type = + NUMA_GLUELESS_MESH; + return; + } + } + + sched_numa_topology_type = NUMA_BACKPLANE; + return; + } + } +} + +static void sched_init_numa(void) +{ + int next_distance, curr_distance = node_distance(0, 0); + struct sched_domain_topology_level *tl; + int level = 0; + int i, j, k; + + sched_domains_numa_distance = kzalloc(sizeof(int) * nr_node_ids, GFP_KERNEL); + if (!sched_domains_numa_distance) + return; + + /* + * O(nr_nodes^2) deduplicating selection sort -- in order to find the + * unique distances in the node_distance() table. + * + * Assumes node_distance(0,j) includes all distances in + * node_distance(i,j) in order to avoid cubic time. + */ + next_distance = curr_distance; + for (i = 0; i < nr_node_ids; i++) { + for (j = 0; j < nr_node_ids; j++) { + for (k = 0; k < nr_node_ids; k++) { + int distance = node_distance(i, k); + + if (distance > curr_distance && + (distance < next_distance || + next_distance == curr_distance)) + next_distance = distance; + + /* + * While not a strong assumption it would be nice to know + * about cases where if node A is connected to B, B is not + * equally connected to A. + */ + if (sched_debug() && node_distance(k, i) != distance) + sched_numa_warn("Node-distance not symmetric"); + + if (sched_debug() && i && !find_numa_distance(distance)) + sched_numa_warn("Node-0 not representative"); + } + if (next_distance != curr_distance) { + sched_domains_numa_distance[level++] = next_distance; + sched_domains_numa_levels = level; + curr_distance = next_distance; + } else break; + } + + /* + * In case of sched_debug() we verify the above assumption. + */ + if (!sched_debug()) + break; + } + + if (!level) + return; + + /* + * 'level' contains the number of unique distances, excluding the + * identity distance node_distance(i,i). + * + * The sched_domains_numa_distance[] array includes the actual distance + * numbers. + */ + + /* + * Here, we should temporarily reset sched_domains_numa_levels to 0. + * If it fails to allocate memory for array sched_domains_numa_masks[][], + * the array will contain less then 'level' members. This could be + * dangerous when we use it to iterate array sched_domains_numa_masks[][] + * in other functions. + * + * We reset it to 'level' at the end of this function. + */ + sched_domains_numa_levels = 0; + + sched_domains_numa_masks = kzalloc(sizeof(void *) * level, GFP_KERNEL); + if (!sched_domains_numa_masks) + return; + + /* + * Now for each level, construct a mask per node which contains all + * cpus of nodes that are that many hops away from us. + */ + for (i = 0; i < level; i++) { + sched_domains_numa_masks[i] = + kzalloc(nr_node_ids * sizeof(void *), GFP_KERNEL); + if (!sched_domains_numa_masks[i]) + return; + + for (j = 0; j < nr_node_ids; j++) { + struct cpumask *mask = kzalloc(cpumask_size(), GFP_KERNEL); + if (!mask) + return; + + sched_domains_numa_masks[i][j] = mask; + + for (k = 0; k < nr_node_ids; k++) { + if (node_distance(j, k) > sched_domains_numa_distance[i]) + continue; + + cpumask_or(mask, mask, cpumask_of_node(k)); + } + } + } + + /* Compute default topology size */ + for (i = 0; sched_domain_topology[i].mask; i++); + + tl = kzalloc((i + level + 1) * + sizeof(struct sched_domain_topology_level), GFP_KERNEL); + if (!tl) + return; + + /* + * Copy the default topology bits.. + */ + for (i = 0; sched_domain_topology[i].mask; i++) + tl[i] = sched_domain_topology[i]; + + /* + * .. and append 'j' levels of NUMA goodness. + */ + for (j = 0; j < level; i++, j++) { + tl[i] = (struct sched_domain_topology_level){ + .mask = sd_numa_mask, + .sd_flags = cpu_numa_flags, + .flags = SDTL_OVERLAP, + .numa_level = j, + SD_INIT_NAME(NUMA) + }; + } + + sched_domain_topology = tl; + + sched_domains_numa_levels = level; + sched_max_numa_distance = sched_domains_numa_distance[level - 1]; + + init_numa_topology_type(); +} + +static void sched_domains_numa_masks_set(int cpu) +{ + int i, j; + int node = cpu_to_node(cpu); + + for (i = 0; i < sched_domains_numa_levels; i++) { + for (j = 0; j < nr_node_ids; j++) { + if (node_distance(j, node) <= sched_domains_numa_distance[i]) + cpumask_set_cpu(cpu, sched_domains_numa_masks[i][j]); + } + } +} + +static void sched_domains_numa_masks_clear(int cpu) +{ + int i, j; + for (i = 0; i < sched_domains_numa_levels; i++) { + for (j = 0; j < nr_node_ids; j++) + cpumask_clear_cpu(cpu, sched_domains_numa_masks[i][j]); + } +} + +/* + * Update sched_domains_numa_masks[level][node] array when new cpus + * are onlined. + */ +static int sched_domains_numa_masks_update(struct notifier_block *nfb, + unsigned long action, + void *hcpu) +{ + int cpu = (long)hcpu; + + switch (action & ~CPU_TASKS_FROZEN) { + case CPU_ONLINE: + sched_domains_numa_masks_set(cpu); + break; + + case CPU_DEAD: + sched_domains_numa_masks_clear(cpu); + break; + + default: + return NOTIFY_DONE; + } + + return NOTIFY_OK; +} +#else +static inline void sched_init_numa(void) +{ +} + +static int sched_domains_numa_masks_update(struct notifier_block *nfb, + unsigned long action, + void *hcpu) +{ + return 0; +} +#endif /* CONFIG_NUMA */ + +static int __sdt_alloc(const struct cpumask *cpu_map) +{ + struct sched_domain_topology_level *tl; + int j; + + for_each_sd_topology(tl) { + struct sd_data *sdd = &tl->data; + + sdd->sd = alloc_percpu(struct sched_domain *); + if (!sdd->sd) + return -ENOMEM; + + sdd->sg = alloc_percpu(struct sched_group *); + if (!sdd->sg) + return -ENOMEM; + + sdd->sgc = alloc_percpu(struct sched_group_capacity *); + if (!sdd->sgc) + return -ENOMEM; + + for_each_cpu(j, cpu_map) { + struct sched_domain *sd; + struct sched_group *sg; + struct sched_group_capacity *sgc; + + sd = kzalloc_node(sizeof(struct sched_domain) + cpumask_size(), + GFP_KERNEL, cpu_to_node(j)); + if (!sd) + return -ENOMEM; + + *per_cpu_ptr(sdd->sd, j) = sd; + + sg = kzalloc_node(sizeof(struct sched_group) + cpumask_size(), + GFP_KERNEL, cpu_to_node(j)); + if (!sg) + return -ENOMEM; + + sg->next = sg; + + *per_cpu_ptr(sdd->sg, j) = sg; + + sgc = kzalloc_node(sizeof(struct sched_group_capacity) + cpumask_size(), + GFP_KERNEL, cpu_to_node(j)); + if (!sgc) + return -ENOMEM; + + *per_cpu_ptr(sdd->sgc, j) = sgc; + } + } + + return 0; +} + +static void __sdt_free(const struct cpumask *cpu_map) +{ + struct sched_domain_topology_level *tl; + int j; + + for_each_sd_topology(tl) { + struct sd_data *sdd = &tl->data; + + for_each_cpu(j, cpu_map) { + struct sched_domain *sd; + + if (sdd->sd) { + sd = *per_cpu_ptr(sdd->sd, j); + if (sd && (sd->flags & SD_OVERLAP)) + free_sched_groups(sd->groups, 0); + kfree(*per_cpu_ptr(sdd->sd, j)); + } + + if (sdd->sg) + kfree(*per_cpu_ptr(sdd->sg, j)); + if (sdd->sgc) + kfree(*per_cpu_ptr(sdd->sgc, j)); + } + free_percpu(sdd->sd); + sdd->sd = NULL; + free_percpu(sdd->sg); + sdd->sg = NULL; + free_percpu(sdd->sgc); + sdd->sgc = NULL; + } +} + +struct sched_domain *build_sched_domain(struct sched_domain_topology_level *tl, + const struct cpumask *cpu_map, struct sched_domain_attr *attr, + struct sched_domain *child, int cpu) +{ + struct sched_domain *sd = sd_init(tl, cpu); + if (!sd) + return child; + + cpumask_and(sched_domain_span(sd), cpu_map, tl->mask(cpu)); + if (child) { + sd->level = child->level + 1; + sched_domain_level_max = max(sched_domain_level_max, sd->level); + child->parent = sd; + sd->child = child; + + if (!cpumask_subset(sched_domain_span(child), + sched_domain_span(sd))) { + pr_err("BUG: arch topology borken\n"); +#ifdef CONFIG_SCHED_DEBUG + pr_err(" the %s domain not a subset of the %s domain\n", + child->name, sd->name); +#endif + /* Fixup, ensure @sd has at least @child cpus. */ + cpumask_or(sched_domain_span(sd), + sched_domain_span(sd), + sched_domain_span(child)); + } + + } + set_domain_attribute(sd, attr); + + return sd; +} + +/* + * Build sched domains for a given set of cpus and attach the sched domains + * to the individual cpus + */ +static int build_sched_domains(const struct cpumask *cpu_map, + struct sched_domain_attr *attr) +{ + enum s_alloc alloc_state; + struct sched_domain *sd; + struct s_data d; + int i, ret = -ENOMEM; + + alloc_state = __visit_domain_allocation_hell(&d, cpu_map); + if (alloc_state != sa_rootdomain) + goto error; + + /* Set up domains for cpus specified by the cpu_map. */ + for_each_cpu(i, cpu_map) { + struct sched_domain_topology_level *tl; + + sd = NULL; + for_each_sd_topology(tl) { + sd = build_sched_domain(tl, cpu_map, attr, sd, i); + if (tl == sched_domain_topology) + *per_cpu_ptr(d.sd, i) = sd; + if (tl->flags & SDTL_OVERLAP || sched_feat(FORCE_SD_OVERLAP)) + sd->flags |= SD_OVERLAP; + if (cpumask_equal(cpu_map, sched_domain_span(sd))) + break; + } + } + + /* Build the groups for the domains */ + for_each_cpu(i, cpu_map) { + for (sd = *per_cpu_ptr(d.sd, i); sd; sd = sd->parent) { + sd->span_weight = cpumask_weight(sched_domain_span(sd)); + if (sd->flags & SD_OVERLAP) { + if (build_overlap_sched_groups(sd, i)) + goto error; + } else { + if (build_sched_groups(sd, i)) + goto error; + } + } + } + + /* Calculate CPU capacity for physical packages and nodes */ + for (i = nr_cpumask_bits-1; i >= 0; i--) { + if (!cpumask_test_cpu(i, cpu_map)) + continue; + + for (sd = *per_cpu_ptr(d.sd, i); sd; sd = sd->parent) { + claim_allocations(i, sd); + init_sched_groups_capacity(i, sd); + } + } + + /* Attach the domains */ + rcu_read_lock(); + for_each_cpu(i, cpu_map) { + sd = *per_cpu_ptr(d.sd, i); + cpu_attach_domain(sd, d.rd, i); + } + rcu_read_unlock(); + + ret = 0; +error: + __free_domain_allocs(&d, alloc_state, cpu_map); + return ret; +} + +static cpumask_var_t *doms_cur; /* current sched domains */ +static int ndoms_cur; /* number of sched domains in 'doms_cur' */ +static struct sched_domain_attr *dattr_cur; + /* attribues of custom domains in 'doms_cur' */ + +/* + * Special case: If a kmalloc of a doms_cur partition (array of + * cpumask) fails, then fallback to a single sched domain, + * as determined by the single cpumask fallback_doms. + */ +static cpumask_var_t fallback_doms; + +/* + * arch_update_cpu_topology lets virtualized architectures update the + * cpu core maps. It is supposed to return 1 if the topology changed + * or 0 if it stayed the same. + */ +int __weak arch_update_cpu_topology(void) +{ + return 0; +} + +cpumask_var_t *alloc_sched_domains(unsigned int ndoms) +{ + int i; + cpumask_var_t *doms; + + doms = kmalloc(sizeof(*doms) * ndoms, GFP_KERNEL); + if (!doms) + return NULL; + for (i = 0; i < ndoms; i++) { + if (!alloc_cpumask_var(&doms[i], GFP_KERNEL)) { + free_sched_domains(doms, i); + return NULL; + } + } + return doms; +} + +void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms) +{ + unsigned int i; + for (i = 0; i < ndoms; i++) + free_cpumask_var(doms[i]); + kfree(doms); +} + +/* + * Set up scheduler domains and groups. Callers must hold the hotplug lock. + * For now this just excludes isolated cpus, but could be used to + * exclude other special cases in the future. + */ +static int init_sched_domains(const struct cpumask *cpu_map) +{ + int err; + + arch_update_cpu_topology(); + ndoms_cur = 1; + doms_cur = alloc_sched_domains(ndoms_cur); + if (!doms_cur) + doms_cur = &fallback_doms; + cpumask_andnot(doms_cur[0], cpu_map, cpu_isolated_map); + err = build_sched_domains(doms_cur[0], NULL); + register_sched_domain_sysctl(); + + return err; +} + +/* + * Detach sched domains from a group of cpus specified in cpu_map + * These cpus will now be attached to the NULL domain + */ +static void detach_destroy_domains(const struct cpumask *cpu_map) +{ + int i; + + rcu_read_lock(); + for_each_cpu(i, cpu_map) + cpu_attach_domain(NULL, &def_root_domain, i); + rcu_read_unlock(); +} + +/* handle null as "default" */ +static int dattrs_equal(struct sched_domain_attr *cur, int idx_cur, + struct sched_domain_attr *new, int idx_new) +{ + struct sched_domain_attr tmp; + + /* fast path */ + if (!new && !cur) + return 1; + + tmp = SD_ATTR_INIT; + return !memcmp(cur ? (cur + idx_cur) : &tmp, + new ? (new + idx_new) : &tmp, + sizeof(struct sched_domain_attr)); +} + +/* + * Partition sched domains as specified by the 'ndoms_new' + * cpumasks in the array doms_new[] of cpumasks. This compares + * doms_new[] to the current sched domain partitioning, doms_cur[]. + * It destroys each deleted domain and builds each new domain. + * + * 'doms_new' is an array of cpumask_var_t's of length 'ndoms_new'. + * The masks don't intersect (don't overlap.) We should setup one + * sched domain for each mask. CPUs not in any of the cpumasks will + * not be load balanced. If the same cpumask appears both in the + * current 'doms_cur' domains and in the new 'doms_new', we can leave + * it as it is. + * + * The passed in 'doms_new' should be allocated using + * alloc_sched_domains. This routine takes ownership of it and will + * free_sched_domains it when done with it. If the caller failed the + * alloc call, then it can pass in doms_new == NULL && ndoms_new == 1, + * and partition_sched_domains() will fallback to the single partition + * 'fallback_doms', it also forces the domains to be rebuilt. + * + * If doms_new == NULL it will be replaced with cpu_online_mask. + * ndoms_new == 0 is a special case for destroying existing domains, + * and it will not create the default domain. + * + * Call with hotplug lock held + */ +void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[], + struct sched_domain_attr *dattr_new) +{ + int i, j, n; + int new_topology; + + mutex_lock(&sched_domains_mutex); + + /* always unregister in case we don't destroy any domains */ + unregister_sched_domain_sysctl(); + + /* Let architecture update cpu core mappings. */ + new_topology = arch_update_cpu_topology(); + + n = doms_new ? ndoms_new : 0; + + /* Destroy deleted domains */ + for (i = 0; i < ndoms_cur; i++) { + for (j = 0; j < n && !new_topology; j++) { + if (cpumask_equal(doms_cur[i], doms_new[j]) + && dattrs_equal(dattr_cur, i, dattr_new, j)) + goto match1; + } + /* no match - a current sched domain not in new doms_new[] */ + detach_destroy_domains(doms_cur[i]); +match1: + ; + } + + n = ndoms_cur; + if (doms_new == NULL) { + n = 0; + doms_new = &fallback_doms; + cpumask_andnot(doms_new[0], cpu_active_mask, cpu_isolated_map); + WARN_ON_ONCE(dattr_new); + } + + /* Build new domains */ + for (i = 0; i < ndoms_new; i++) { + for (j = 0; j < n && !new_topology; j++) { + if (cpumask_equal(doms_new[i], doms_cur[j]) + && dattrs_equal(dattr_new, i, dattr_cur, j)) + goto match2; + } + /* no match - add a new doms_new */ + build_sched_domains(doms_new[i], dattr_new ? dattr_new + i : NULL); +match2: + ; + } + + /* Remember the new sched domains */ + if (doms_cur != &fallback_doms) + free_sched_domains(doms_cur, ndoms_cur); + kfree(dattr_cur); /* kfree(NULL) is safe */ + doms_cur = doms_new; + dattr_cur = dattr_new; + ndoms_cur = ndoms_new; + + register_sched_domain_sysctl(); + + mutex_unlock(&sched_domains_mutex); +} + +static int num_cpus_frozen; /* used to mark begin/end of suspend/resume */ + +/* + * Update cpusets according to cpu_active mask. If cpusets are + * disabled, cpuset_update_active_cpus() becomes a simple wrapper + * around partition_sched_domains(). + * + * If we come here as part of a suspend/resume, don't touch cpusets because we + * want to restore it back to its original state upon resume anyway. + */ +static int cpuset_cpu_active(struct notifier_block *nfb, unsigned long action, + void *hcpu) +{ + switch (action) { + case CPU_ONLINE_FROZEN: + case CPU_DOWN_FAILED_FROZEN: + + /* + * num_cpus_frozen tracks how many CPUs are involved in suspend + * resume sequence. As long as this is not the last online + * operation in the resume sequence, just build a single sched + * domain, ignoring cpusets. + */ + num_cpus_frozen--; + if (likely(num_cpus_frozen)) { + partition_sched_domains(1, NULL, NULL); + break; + } + + /* + * This is the last CPU online operation. So fall through and + * restore the original sched domains by considering the + * cpuset configurations. + */ + + case CPU_ONLINE: + cpuset_update_active_cpus(true); + break; + default: + return NOTIFY_DONE; + } + return NOTIFY_OK; +} + +static int cpuset_cpu_inactive(struct notifier_block *nfb, unsigned long action, + void *hcpu) +{ + unsigned long flags; + long cpu = (long)hcpu; + struct dl_bw *dl_b; + bool overflow; + int cpus; + + switch (action) { + case CPU_DOWN_PREPARE: + rcu_read_lock_sched(); + dl_b = dl_bw_of(cpu); + + raw_spin_lock_irqsave(&dl_b->lock, flags); + cpus = dl_bw_cpus(cpu); + overflow = __dl_overflow(dl_b, cpus, 0, 0); + raw_spin_unlock_irqrestore(&dl_b->lock, flags); + + rcu_read_unlock_sched(); + + if (overflow) + return notifier_from_errno(-EBUSY); + cpuset_update_active_cpus(false); + break; + case CPU_DOWN_PREPARE_FROZEN: + num_cpus_frozen++; + partition_sched_domains(1, NULL, NULL); + break; + default: + return NOTIFY_DONE; + } + return NOTIFY_OK; +} + +void __init sched_init_smp(void) +{ + cpumask_var_t non_isolated_cpus; + + alloc_cpumask_var(&non_isolated_cpus, GFP_KERNEL); + alloc_cpumask_var(&fallback_doms, GFP_KERNEL); + + sched_init_numa(); + + /* + * There's no userspace yet to cause hotplug operations; hence all the + * cpu masks are stable and all blatant races in the below code cannot + * happen. + */ + mutex_lock(&sched_domains_mutex); + init_sched_domains(cpu_active_mask); + cpumask_andnot(non_isolated_cpus, cpu_possible_mask, cpu_isolated_map); + if (cpumask_empty(non_isolated_cpus)) + cpumask_set_cpu(smp_processor_id(), non_isolated_cpus); + mutex_unlock(&sched_domains_mutex); + + hotcpu_notifier(sched_domains_numa_masks_update, CPU_PRI_SCHED_ACTIVE); + hotcpu_notifier(cpuset_cpu_active, CPU_PRI_CPUSET_ACTIVE); + hotcpu_notifier(cpuset_cpu_inactive, CPU_PRI_CPUSET_INACTIVE); + + init_hrtick(); + + /* Move init over to a non-isolated CPU */ + if (set_cpus_allowed_ptr(current, non_isolated_cpus) < 0) + BUG(); + sched_init_granularity(); + free_cpumask_var(non_isolated_cpus); + + init_sched_rt_class(); + init_sched_dl_class(); +} +#else +void __init sched_init_smp(void) +{ + sched_init_granularity(); +} +#endif /* CONFIG_SMP */ + +const_debug unsigned int sysctl_timer_migration = 1; + +int in_sched_functions(unsigned long addr) +{ + return in_lock_functions(addr) || + (addr >= (unsigned long)__sched_text_start + && addr < (unsigned long)__sched_text_end); +} + +#ifdef CONFIG_CGROUP_SCHED +/* + * Default task group. + * Every task in system belongs to this group at bootup. + */ +struct task_group root_task_group; +LIST_HEAD(task_groups); +#endif + +DECLARE_PER_CPU(cpumask_var_t, load_balance_mask); + +void __init sched_init(void) +{ + int i, j; + unsigned long alloc_size = 0, ptr; + +#ifdef CONFIG_FAIR_GROUP_SCHED + alloc_size += 2 * nr_cpu_ids * sizeof(void **); +#endif +#ifdef CONFIG_RT_GROUP_SCHED + alloc_size += 2 * nr_cpu_ids * sizeof(void **); +#endif + if (alloc_size) { + ptr = (unsigned long)kzalloc(alloc_size, GFP_NOWAIT); + +#ifdef CONFIG_FAIR_GROUP_SCHED + root_task_group.se = (struct sched_entity **)ptr; + ptr += nr_cpu_ids * sizeof(void **); + + root_task_group.cfs_rq = (struct cfs_rq **)ptr; + ptr += nr_cpu_ids * sizeof(void **); + +#endif /* CONFIG_FAIR_GROUP_SCHED */ +#ifdef CONFIG_RT_GROUP_SCHED + root_task_group.rt_se = (struct sched_rt_entity **)ptr; + ptr += nr_cpu_ids * sizeof(void **); + + root_task_group.rt_rq = (struct rt_rq **)ptr; + ptr += nr_cpu_ids * sizeof(void **); + +#endif /* CONFIG_RT_GROUP_SCHED */ + } +#ifdef CONFIG_CPUMASK_OFFSTACK + for_each_possible_cpu(i) { + per_cpu(load_balance_mask, i) = (cpumask_var_t)kzalloc_node( + cpumask_size(), GFP_KERNEL, cpu_to_node(i)); + } +#endif /* CONFIG_CPUMASK_OFFSTACK */ + + init_rt_bandwidth(&def_rt_bandwidth, + global_rt_period(), global_rt_runtime()); + init_dl_bandwidth(&def_dl_bandwidth, + global_rt_period(), global_rt_runtime()); + +#ifdef CONFIG_SMP + init_defrootdomain(); +#endif + +#ifdef CONFIG_RT_GROUP_SCHED + init_rt_bandwidth(&root_task_group.rt_bandwidth, + global_rt_period(), global_rt_runtime()); +#endif /* CONFIG_RT_GROUP_SCHED */ + +#ifdef CONFIG_CGROUP_SCHED + list_add(&root_task_group.list, &task_groups); + INIT_LIST_HEAD(&root_task_group.children); + INIT_LIST_HEAD(&root_task_group.siblings); + autogroup_init(&init_task); + +#endif /* CONFIG_CGROUP_SCHED */ + + for_each_possible_cpu(i) { + struct rq *rq; + + rq = cpu_rq(i); + raw_spin_lock_init(&rq->lock); + rq->nr_running = 0; + rq->calc_load_active = 0; + rq->calc_load_update = jiffies + LOAD_FREQ; + init_cfs_rq(&rq->cfs); + init_rt_rq(&rq->rt); + init_dl_rq(&rq->dl); +#ifdef CONFIG_FAIR_GROUP_SCHED + root_task_group.shares = ROOT_TASK_GROUP_LOAD; + INIT_LIST_HEAD(&rq->leaf_cfs_rq_list); + /* + * How much cpu bandwidth does root_task_group get? + * + * In case of task-groups formed thr' the cgroup filesystem, it + * gets 100% of the cpu resources in the system. This overall + * system cpu resource is divided among the tasks of + * root_task_group and its child task-groups in a fair manner, + * based on each entity's (task or task-group's) weight + * (se->load.weight). + * + * In other words, if root_task_group has 10 tasks of weight + * 1024) and two child groups A0 and A1 (of weight 1024 each), + * then A0's share of the cpu resource is: + * + * A0's bandwidth = 1024 / (10*1024 + 1024 + 1024) = 8.33% + * + * We achieve this by letting root_task_group's tasks sit + * directly in rq->cfs (i.e root_task_group->se[] = NULL). + */ + init_cfs_bandwidth(&root_task_group.cfs_bandwidth); + init_tg_cfs_entry(&root_task_group, &rq->cfs, NULL, i, NULL); +#endif /* CONFIG_FAIR_GROUP_SCHED */ + + rq->rt.rt_runtime = def_rt_bandwidth.rt_runtime; +#ifdef CONFIG_RT_GROUP_SCHED + init_tg_rt_entry(&root_task_group, &rq->rt, NULL, i, NULL); +#endif + + for (j = 0; j < CPU_LOAD_IDX_MAX; j++) + rq->cpu_load[j] = 0; + + rq->last_load_update_tick = jiffies; + +#ifdef CONFIG_SMP + rq->sd = NULL; + rq->rd = NULL; + rq->cpu_capacity = rq->cpu_capacity_orig = SCHED_CAPACITY_SCALE; + rq->post_schedule = 0; + rq->active_balance = 0; + rq->next_balance = jiffies; + rq->push_cpu = 0; + rq->cpu = i; + rq->online = 0; + rq->idle_stamp = 0; + rq->avg_idle = 2*sysctl_sched_migration_cost; + rq->max_idle_balance_cost = sysctl_sched_migration_cost; + + INIT_LIST_HEAD(&rq->cfs_tasks); + + rq_attach_root(rq, &def_root_domain); +#ifdef CONFIG_NO_HZ_COMMON + rq->nohz_flags = 0; +#endif +#ifdef CONFIG_NO_HZ_FULL + rq->last_sched_tick = 0; +#endif +#endif + init_rq_hrtick(rq); + atomic_set(&rq->nr_iowait, 0); + } + + set_load_weight(&init_task); + +#ifdef CONFIG_PREEMPT_NOTIFIERS + INIT_HLIST_HEAD(&init_task.preempt_notifiers); +#endif + + /* + * The boot idle thread does lazy MMU switching as well: + */ + atomic_inc(&init_mm.mm_count); + enter_lazy_tlb(&init_mm, current); + + /* + * During early bootup we pretend to be a normal task: + */ + current->sched_class = &fair_sched_class; + + /* + * Make us the idle thread. Technically, schedule() should not be + * called from this thread, however somewhere below it might be, + * but because we are the idle thread, we just pick up running again + * when this runqueue becomes "idle". + */ + init_idle(current, smp_processor_id()); + + calc_load_update = jiffies + LOAD_FREQ; + +#ifdef CONFIG_SMP + zalloc_cpumask_var(&sched_domains_tmpmask, GFP_NOWAIT); + /* May be allocated at isolcpus cmdline parse time */ + if (cpu_isolated_map == NULL) + zalloc_cpumask_var(&cpu_isolated_map, GFP_NOWAIT); + idle_thread_set_boot_cpu(); + set_cpu_rq_start_time(); +#endif + init_sched_fair_class(); + + scheduler_running = 1; +} + +#ifdef CONFIG_DEBUG_ATOMIC_SLEEP +static inline int preempt_count_equals(int preempt_offset) +{ + int nested = (preempt_count() & ~PREEMPT_ACTIVE) + + sched_rcu_preempt_depth(); + + return (nested == preempt_offset); +} + +void __might_sleep(const char *file, int line, int preempt_offset) +{ + /* + * Blocking primitives will set (and therefore destroy) current->state, + * since we will exit with TASK_RUNNING make sure we enter with it, + * otherwise we will destroy state. + */ + WARN_ONCE(current->state != TASK_RUNNING && current->task_state_change, + "do not call blocking ops when !TASK_RUNNING; " + "state=%lx set at [<%p>] %pS\n", + current->state, + (void *)current->task_state_change, + (void *)current->task_state_change); + + ___might_sleep(file, line, preempt_offset); +} +EXPORT_SYMBOL(__might_sleep); + +void ___might_sleep(const char *file, int line, int preempt_offset) +{ + static unsigned long prev_jiffy; /* ratelimiting */ + + rcu_sleep_check(); /* WARN_ON_ONCE() by default, no rate limit reqd. */ + if ((preempt_count_equals(preempt_offset) && !irqs_disabled() && + !is_idle_task(current)) || + system_state != SYSTEM_RUNNING || oops_in_progress) + return; + if (time_before(jiffies, prev_jiffy + HZ) && prev_jiffy) + return; + prev_jiffy = jiffies; + + printk(KERN_ERR + "BUG: sleeping function called from invalid context at %s:%d\n", + file, line); + printk(KERN_ERR + "in_atomic(): %d, irqs_disabled(): %d, pid: %d, name: %s\n", + in_atomic(), irqs_disabled(), + current->pid, current->comm); + + if (task_stack_end_corrupted(current)) + printk(KERN_EMERG "Thread overran stack, or stack corrupted\n"); + + debug_show_held_locks(current); + if (irqs_disabled()) + print_irqtrace_events(current); +#ifdef CONFIG_DEBUG_PREEMPT + if (!preempt_count_equals(preempt_offset)) { + pr_err("Preemption disabled at:"); + print_ip_sym(current->preempt_disable_ip); + pr_cont("\n"); + } +#endif + dump_stack(); +} +EXPORT_SYMBOL(___might_sleep); +#endif + +#ifdef CONFIG_MAGIC_SYSRQ +static void normalize_task(struct rq *rq, struct task_struct *p) +{ + const struct sched_class *prev_class = p->sched_class; + struct sched_attr attr = { + .sched_policy = SCHED_NORMAL, + }; + int old_prio = p->prio; + int queued; + + queued = task_on_rq_queued(p); + if (queued) + dequeue_task(rq, p, 0); + __setscheduler(rq, p, &attr, false); + if (queued) { + enqueue_task(rq, p, 0); + resched_curr(rq); + } + + check_class_changed(rq, p, prev_class, old_prio); +} + +void normalize_rt_tasks(void) +{ + struct task_struct *g, *p; + unsigned long flags; + struct rq *rq; + + read_lock(&tasklist_lock); + for_each_process_thread(g, p) { + /* + * Only normalize user tasks: + */ + if (p->flags & PF_KTHREAD) + continue; + + p->se.exec_start = 0; +#ifdef CONFIG_SCHEDSTATS + p->se.statistics.wait_start = 0; + p->se.statistics.sleep_start = 0; + p->se.statistics.block_start = 0; +#endif + + if (!dl_task(p) && !rt_task(p)) { + /* + * Renice negative nice level userspace + * tasks back to 0: + */ + if (task_nice(p) < 0) + set_user_nice(p, 0); + continue; + } + + rq = task_rq_lock(p, &flags); + normalize_task(rq, p); + task_rq_unlock(rq, p, &flags); + } + read_unlock(&tasklist_lock); +} + +#endif /* CONFIG_MAGIC_SYSRQ */ + +#if defined(CONFIG_IA64) || defined(CONFIG_KGDB_KDB) +/* + * These functions are only useful for the IA64 MCA handling, or kdb. + * + * They can only be called when the whole system has been + * stopped - every CPU needs to be quiescent, and no scheduling + * activity can take place. Using them for anything else would + * be a serious bug, and as a result, they aren't even visible + * under any other configuration. + */ + +/** + * curr_task - return the current task for a given cpu. + * @cpu: the processor in question. + * + * ONLY VALID WHEN THE WHOLE SYSTEM IS STOPPED! + * + * Return: The current task for @cpu. + */ +struct task_struct *curr_task(int cpu) +{ + return cpu_curr(cpu); +} + +#endif /* defined(CONFIG_IA64) || defined(CONFIG_KGDB_KDB) */ + +#ifdef CONFIG_IA64 +/** + * set_curr_task - set the current task for a given cpu. + * @cpu: the processor in question. + * @p: the task pointer to set. + * + * Description: This function must only be used when non-maskable interrupts + * are serviced on a separate stack. It allows the architecture to switch the + * notion of the current task on a cpu in a non-blocking manner. This function + * must be called with all CPU's synchronized, and interrupts disabled, the + * and caller must save the original value of the current task (see + * curr_task() above) and restore that value before reenabling interrupts and + * re-starting the system. + * + * ONLY VALID WHEN THE WHOLE SYSTEM IS STOPPED! + */ +void set_curr_task(int cpu, struct task_struct *p) +{ + cpu_curr(cpu) = p; +} + +#endif + +#ifdef CONFIG_CGROUP_SCHED +/* task_group_lock serializes the addition/removal of task groups */ +static DEFINE_SPINLOCK(task_group_lock); + +static void free_sched_group(struct task_group *tg) +{ + free_fair_sched_group(tg); + free_rt_sched_group(tg); + autogroup_free(tg); + kfree(tg); +} + +/* allocate runqueue etc for a new task group */ +struct task_group *sched_create_group(struct task_group *parent) +{ + struct task_group *tg; + + tg = kzalloc(sizeof(*tg), GFP_KERNEL); + if (!tg) + return ERR_PTR(-ENOMEM); + + if (!alloc_fair_sched_group(tg, parent)) + goto err; + + if (!alloc_rt_sched_group(tg, parent)) + goto err; + + return tg; + +err: + free_sched_group(tg); + return ERR_PTR(-ENOMEM); +} + +void sched_online_group(struct task_group *tg, struct task_group *parent) +{ + unsigned long flags; + + spin_lock_irqsave(&task_group_lock, flags); + list_add_rcu(&tg->list, &task_groups); + + WARN_ON(!parent); /* root should already exist */ + + tg->parent = parent; + INIT_LIST_HEAD(&tg->children); + list_add_rcu(&tg->siblings, &parent->children); + spin_unlock_irqrestore(&task_group_lock, flags); +} + +/* rcu callback to free various structures associated with a task group */ +static void free_sched_group_rcu(struct rcu_head *rhp) +{ + /* now it should be safe to free those cfs_rqs */ + free_sched_group(container_of(rhp, struct task_group, rcu)); +} + +/* Destroy runqueue etc associated with a task group */ +void sched_destroy_group(struct task_group *tg) +{ + /* wait for possible concurrent references to cfs_rqs complete */ + call_rcu(&tg->rcu, free_sched_group_rcu); +} + +void sched_offline_group(struct task_group *tg) +{ + unsigned long flags; + int i; + + /* end participation in shares distribution */ + for_each_possible_cpu(i) + unregister_fair_sched_group(tg, i); + + spin_lock_irqsave(&task_group_lock, flags); + list_del_rcu(&tg->list); + list_del_rcu(&tg->siblings); + spin_unlock_irqrestore(&task_group_lock, flags); +} + +/* change task's runqueue when it moves between groups. + * The caller of this function should have put the task in its new group + * by now. This function just updates tsk->se.cfs_rq and tsk->se.parent to + * reflect its new group. + */ +void sched_move_task(struct task_struct *tsk) +{ + struct task_group *tg; + int queued, running; + unsigned long flags; + struct rq *rq; + + rq = task_rq_lock(tsk, &flags); + + running = task_current(rq, tsk); + queued = task_on_rq_queued(tsk); + + if (queued) + dequeue_task(rq, tsk, 0); + if (unlikely(running)) + put_prev_task(rq, tsk); + + /* + * All callers are synchronized by task_rq_lock(); we do not use RCU + * which is pointless here. Thus, we pass "true" to task_css_check() + * to prevent lockdep warnings. + */ + tg = container_of(task_css_check(tsk, cpu_cgrp_id, true), + struct task_group, css); + tg = autogroup_task_group(tsk, tg); + tsk->sched_task_group = tg; + +#ifdef CONFIG_FAIR_GROUP_SCHED + if (tsk->sched_class->task_move_group) + tsk->sched_class->task_move_group(tsk, queued); + else +#endif + set_task_rq(tsk, task_cpu(tsk)); + + if (unlikely(running)) + tsk->sched_class->set_curr_task(rq); + if (queued) + enqueue_task(rq, tsk, 0); + + task_rq_unlock(rq, tsk, &flags); +} +#endif /* CONFIG_CGROUP_SCHED */ + +#ifdef CONFIG_RT_GROUP_SCHED +/* + * Ensure that the real time constraints are schedulable. + */ +static DEFINE_MUTEX(rt_constraints_mutex); + +/* Must be called with tasklist_lock held */ +static inline int tg_has_rt_tasks(struct task_group *tg) +{ + struct task_struct *g, *p; + + /* + * Autogroups do not have RT tasks; see autogroup_create(). + */ + if (task_group_is_autogroup(tg)) + return 0; + + for_each_process_thread(g, p) { + if (rt_task(p) && task_group(p) == tg) + return 1; + } + + return 0; +} + +struct rt_schedulable_data { + struct task_group *tg; + u64 rt_period; + u64 rt_runtime; +}; + +static int tg_rt_schedulable(struct task_group *tg, void *data) +{ + struct rt_schedulable_data *d = data; + struct task_group *child; + unsigned long total, sum = 0; + u64 period, runtime; + + period = ktime_to_ns(tg->rt_bandwidth.rt_period); + runtime = tg->rt_bandwidth.rt_runtime; + + if (tg == d->tg) { + period = d->rt_period; + runtime = d->rt_runtime; + } + + /* + * Cannot have more runtime than the period. + */ + if (runtime > period && runtime != RUNTIME_INF) + return -EINVAL; + + /* + * Ensure we don't starve existing RT tasks. + */ + if (rt_bandwidth_enabled() && !runtime && tg_has_rt_tasks(tg)) + return -EBUSY; + + total = to_ratio(period, runtime); + + /* + * Nobody can have more than the global setting allows. + */ + if (total > to_ratio(global_rt_period(), global_rt_runtime())) + return -EINVAL; + + /* + * The sum of our children's runtime should not exceed our own. + */ + list_for_each_entry_rcu(child, &tg->children, siblings) { + period = ktime_to_ns(child->rt_bandwidth.rt_period); + runtime = child->rt_bandwidth.rt_runtime; + + if (child == d->tg) { + period = d->rt_period; + runtime = d->rt_runtime; + } + + sum += to_ratio(period, runtime); + } + + if (sum > total) + return -EINVAL; + + return 0; +} + +static int __rt_schedulable(struct task_group *tg, u64 period, u64 runtime) +{ + int ret; + + struct rt_schedulable_data data = { + .tg = tg, + .rt_period = period, + .rt_runtime = runtime, + }; + + rcu_read_lock(); + ret = walk_tg_tree(tg_rt_schedulable, tg_nop, &data); + rcu_read_unlock(); + + return ret; +} + +static int tg_set_rt_bandwidth(struct task_group *tg, + u64 rt_period, u64 rt_runtime) +{ + int i, err = 0; + + /* + * Disallowing the root group RT runtime is BAD, it would disallow the + * kernel creating (and or operating) RT threads. + */ + if (tg == &root_task_group && rt_runtime == 0) + return -EINVAL; + + /* No period doesn't make any sense. */ + if (rt_period == 0) + return -EINVAL; + + mutex_lock(&rt_constraints_mutex); + read_lock(&tasklist_lock); + err = __rt_schedulable(tg, rt_period, rt_runtime); + if (err) + goto unlock; + + raw_spin_lock_irq(&tg->rt_bandwidth.rt_runtime_lock); + tg->rt_bandwidth.rt_period = ns_to_ktime(rt_period); + tg->rt_bandwidth.rt_runtime = rt_runtime; + + for_each_possible_cpu(i) { + struct rt_rq *rt_rq = tg->rt_rq[i]; + + raw_spin_lock(&rt_rq->rt_runtime_lock); + rt_rq->rt_runtime = rt_runtime; + raw_spin_unlock(&rt_rq->rt_runtime_lock); + } + raw_spin_unlock_irq(&tg->rt_bandwidth.rt_runtime_lock); +unlock: + read_unlock(&tasklist_lock); + mutex_unlock(&rt_constraints_mutex); + + return err; +} + +static int sched_group_set_rt_runtime(struct task_group *tg, long rt_runtime_us) +{ + u64 rt_runtime, rt_period; + + rt_period = ktime_to_ns(tg->rt_bandwidth.rt_period); + rt_runtime = (u64)rt_runtime_us * NSEC_PER_USEC; + if (rt_runtime_us < 0) + rt_runtime = RUNTIME_INF; + + return tg_set_rt_bandwidth(tg, rt_period, rt_runtime); +} + +static long sched_group_rt_runtime(struct task_group *tg) +{ + u64 rt_runtime_us; + + if (tg->rt_bandwidth.rt_runtime == RUNTIME_INF) + return -1; + + rt_runtime_us = tg->rt_bandwidth.rt_runtime; + do_div(rt_runtime_us, NSEC_PER_USEC); + return rt_runtime_us; +} + +static int sched_group_set_rt_period(struct task_group *tg, long rt_period_us) +{ + u64 rt_runtime, rt_period; + + rt_period = (u64)rt_period_us * NSEC_PER_USEC; + rt_runtime = tg->rt_bandwidth.rt_runtime; + + return tg_set_rt_bandwidth(tg, rt_period, rt_runtime); +} + +static long sched_group_rt_period(struct task_group *tg) +{ + u64 rt_period_us; + + rt_period_us = ktime_to_ns(tg->rt_bandwidth.rt_period); + do_div(rt_period_us, NSEC_PER_USEC); + return rt_period_us; +} +#endif /* CONFIG_RT_GROUP_SCHED */ + +#ifdef CONFIG_RT_GROUP_SCHED +static int sched_rt_global_constraints(void) +{ + int ret = 0; + + mutex_lock(&rt_constraints_mutex); + read_lock(&tasklist_lock); + ret = __rt_schedulable(NULL, 0, 0); + read_unlock(&tasklist_lock); + mutex_unlock(&rt_constraints_mutex); + + return ret; +} + +static int sched_rt_can_attach(struct task_group *tg, struct task_struct *tsk) +{ + /* Don't accept realtime tasks when there is no way for them to run */ + if (rt_task(tsk) && tg->rt_bandwidth.rt_runtime == 0) + return 0; + + return 1; +} + +#else /* !CONFIG_RT_GROUP_SCHED */ +static int sched_rt_global_constraints(void) +{ + unsigned long flags; + int i, ret = 0; + + raw_spin_lock_irqsave(&def_rt_bandwidth.rt_runtime_lock, flags); + for_each_possible_cpu(i) { + struct rt_rq *rt_rq = &cpu_rq(i)->rt; + + raw_spin_lock(&rt_rq->rt_runtime_lock); + rt_rq->rt_runtime = global_rt_runtime(); + raw_spin_unlock(&rt_rq->rt_runtime_lock); + } + raw_spin_unlock_irqrestore(&def_rt_bandwidth.rt_runtime_lock, flags); + + return ret; +} +#endif /* CONFIG_RT_GROUP_SCHED */ + +static int sched_dl_global_validate(void) +{ + u64 runtime = global_rt_runtime(); + u64 period = global_rt_period(); + u64 new_bw = to_ratio(period, runtime); + struct dl_bw *dl_b; + int cpu, ret = 0; + unsigned long flags; + + /* + * Here we want to check the bandwidth not being set to some + * value smaller than the currently allocated bandwidth in + * any of the root_domains. + * + * FIXME: Cycling on all the CPUs is overdoing, but simpler than + * cycling on root_domains... Discussion on different/better + * solutions is welcome! + */ + for_each_possible_cpu(cpu) { + rcu_read_lock_sched(); + dl_b = dl_bw_of(cpu); + + raw_spin_lock_irqsave(&dl_b->lock, flags); + if (new_bw < dl_b->total_bw) + ret = -EBUSY; + raw_spin_unlock_irqrestore(&dl_b->lock, flags); + + rcu_read_unlock_sched(); + + if (ret) + break; + } + + return ret; +} + +static void sched_dl_do_global(void) +{ + u64 new_bw = -1; + struct dl_bw *dl_b; + int cpu; + unsigned long flags; + + def_dl_bandwidth.dl_period = global_rt_period(); + def_dl_bandwidth.dl_runtime = global_rt_runtime(); + + if (global_rt_runtime() != RUNTIME_INF) + new_bw = to_ratio(global_rt_period(), global_rt_runtime()); + + /* + * FIXME: As above... + */ + for_each_possible_cpu(cpu) { + rcu_read_lock_sched(); + dl_b = dl_bw_of(cpu); + + raw_spin_lock_irqsave(&dl_b->lock, flags); + dl_b->bw = new_bw; + raw_spin_unlock_irqrestore(&dl_b->lock, flags); + + rcu_read_unlock_sched(); + } +} + +static int sched_rt_global_validate(void) +{ + if (sysctl_sched_rt_period <= 0) + return -EINVAL; + + if ((sysctl_sched_rt_runtime != RUNTIME_INF) && + (sysctl_sched_rt_runtime > sysctl_sched_rt_period)) + return -EINVAL; + + return 0; +} + +static void sched_rt_do_global(void) +{ + def_rt_bandwidth.rt_runtime = global_rt_runtime(); + def_rt_bandwidth.rt_period = ns_to_ktime(global_rt_period()); +} + +int sched_rt_handler(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos) +{ + int old_period, old_runtime; + static DEFINE_MUTEX(mutex); + int ret; + + mutex_lock(&mutex); + old_period = sysctl_sched_rt_period; + old_runtime = sysctl_sched_rt_runtime; + + ret = proc_dointvec(table, write, buffer, lenp, ppos); + + if (!ret && write) { + ret = sched_rt_global_validate(); + if (ret) + goto undo; + + ret = sched_dl_global_validate(); + if (ret) + goto undo; + + ret = sched_rt_global_constraints(); + if (ret) + goto undo; + + sched_rt_do_global(); + sched_dl_do_global(); + } + if (0) { +undo: + sysctl_sched_rt_period = old_period; + sysctl_sched_rt_runtime = old_runtime; + } + mutex_unlock(&mutex); + + return ret; +} + +int sched_rr_handler(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos) +{ + int ret; + static DEFINE_MUTEX(mutex); + + mutex_lock(&mutex); + ret = proc_dointvec(table, write, buffer, lenp, ppos); + /* make sure that internally we keep jiffies */ + /* also, writing zero resets timeslice to default */ + if (!ret && write) { + sched_rr_timeslice = sched_rr_timeslice <= 0 ? + RR_TIMESLICE : msecs_to_jiffies(sched_rr_timeslice); + } + mutex_unlock(&mutex); + return ret; +} + +#ifdef CONFIG_CGROUP_SCHED + +static inline struct task_group *css_tg(struct cgroup_subsys_state *css) +{ + return css ? container_of(css, struct task_group, css) : NULL; +} + +static struct cgroup_subsys_state * +cpu_cgroup_css_alloc(struct cgroup_subsys_state *parent_css) +{ + struct task_group *parent = css_tg(parent_css); + struct task_group *tg; + + if (!parent) { + /* This is early initialization for the top cgroup */ + return &root_task_group.css; + } + + tg = sched_create_group(parent); + if (IS_ERR(tg)) + return ERR_PTR(-ENOMEM); + + return &tg->css; +} + +static int cpu_cgroup_css_online(struct cgroup_subsys_state *css) +{ + struct task_group *tg = css_tg(css); + struct task_group *parent = css_tg(css->parent); + + if (parent) + sched_online_group(tg, parent); + return 0; +} + +static void cpu_cgroup_css_free(struct cgroup_subsys_state *css) +{ + struct task_group *tg = css_tg(css); + + sched_destroy_group(tg); +} + +static void cpu_cgroup_css_offline(struct cgroup_subsys_state *css) +{ + struct task_group *tg = css_tg(css); + + sched_offline_group(tg); +} + +static void cpu_cgroup_fork(struct task_struct *task) +{ + sched_move_task(task); +} + +static int cpu_cgroup_can_attach(struct cgroup_subsys_state *css, + struct cgroup_taskset *tset) +{ + struct task_struct *task; + + cgroup_taskset_for_each(task, tset) { +#ifdef CONFIG_RT_GROUP_SCHED + if (!sched_rt_can_attach(css_tg(css), task)) + return -EINVAL; +#else + /* We don't support RT-tasks being in separate groups */ + if (task->sched_class != &fair_sched_class) + return -EINVAL; +#endif + } + return 0; +} + +static void cpu_cgroup_attach(struct cgroup_subsys_state *css, + struct cgroup_taskset *tset) +{ + struct task_struct *task; + + cgroup_taskset_for_each(task, tset) + sched_move_task(task); +} + +static void cpu_cgroup_exit(struct cgroup_subsys_state *css, + struct cgroup_subsys_state *old_css, + struct task_struct *task) +{ + /* + * cgroup_exit() is called in the copy_process() failure path. + * Ignore this case since the task hasn't ran yet, this avoids + * trying to poke a half freed task state from generic code. + */ + if (!(task->flags & PF_EXITING)) + return; + + sched_move_task(task); +} + +#ifdef CONFIG_FAIR_GROUP_SCHED +static int cpu_shares_write_u64(struct cgroup_subsys_state *css, + struct cftype *cftype, u64 shareval) +{ + return sched_group_set_shares(css_tg(css), scale_load(shareval)); +} + +static u64 cpu_shares_read_u64(struct cgroup_subsys_state *css, + struct cftype *cft) +{ + struct task_group *tg = css_tg(css); + + return (u64) scale_load_down(tg->shares); +} + +#ifdef CONFIG_CFS_BANDWIDTH +static DEFINE_MUTEX(cfs_constraints_mutex); + +const u64 max_cfs_quota_period = 1 * NSEC_PER_SEC; /* 1s */ +const u64 min_cfs_quota_period = 1 * NSEC_PER_MSEC; /* 1ms */ + +static int __cfs_schedulable(struct task_group *tg, u64 period, u64 runtime); + +static int tg_set_cfs_bandwidth(struct task_group *tg, u64 period, u64 quota) +{ + int i, ret = 0, runtime_enabled, runtime_was_enabled; + struct cfs_bandwidth *cfs_b = &tg->cfs_bandwidth; + + if (tg == &root_task_group) + return -EINVAL; + + /* + * Ensure we have at some amount of bandwidth every period. This is + * to prevent reaching a state of large arrears when throttled via + * entity_tick() resulting in prolonged exit starvation. + */ + if (quota < min_cfs_quota_period || period < min_cfs_quota_period) + return -EINVAL; + + /* + * Likewise, bound things on the otherside by preventing insane quota + * periods. This also allows us to normalize in computing quota + * feasibility. + */ + if (period > max_cfs_quota_period) + return -EINVAL; + + /* + * Prevent race between setting of cfs_rq->runtime_enabled and + * unthrottle_offline_cfs_rqs(). + */ + get_online_cpus(); + mutex_lock(&cfs_constraints_mutex); + ret = __cfs_schedulable(tg, period, quota); + if (ret) + goto out_unlock; + + runtime_enabled = quota != RUNTIME_INF; + runtime_was_enabled = cfs_b->quota != RUNTIME_INF; + /* + * If we need to toggle cfs_bandwidth_used, off->on must occur + * before making related changes, and on->off must occur afterwards + */ + if (runtime_enabled && !runtime_was_enabled) + cfs_bandwidth_usage_inc(); + raw_spin_lock_irq(&cfs_b->lock); + cfs_b->period = ns_to_ktime(period); + cfs_b->quota = quota; + + __refill_cfs_bandwidth_runtime(cfs_b); + /* restart the period timer (if active) to handle new period expiry */ + if (runtime_enabled && cfs_b->timer_active) { + /* force a reprogram */ + __start_cfs_bandwidth(cfs_b, true); + } + raw_spin_unlock_irq(&cfs_b->lock); + + for_each_online_cpu(i) { + struct cfs_rq *cfs_rq = tg->cfs_rq[i]; + struct rq *rq = cfs_rq->rq; + + raw_spin_lock_irq(&rq->lock); + cfs_rq->runtime_enabled = runtime_enabled; + cfs_rq->runtime_remaining = 0; + + if (cfs_rq->throttled) + unthrottle_cfs_rq(cfs_rq); + raw_spin_unlock_irq(&rq->lock); + } + if (runtime_was_enabled && !runtime_enabled) + cfs_bandwidth_usage_dec(); +out_unlock: + mutex_unlock(&cfs_constraints_mutex); + put_online_cpus(); + + return ret; +} + +int tg_set_cfs_quota(struct task_group *tg, long cfs_quota_us) +{ + u64 quota, period; + + period = ktime_to_ns(tg->cfs_bandwidth.period); + if (cfs_quota_us < 0) + quota = RUNTIME_INF; + else + quota = (u64)cfs_quota_us * NSEC_PER_USEC; + + return tg_set_cfs_bandwidth(tg, period, quota); +} + +long tg_get_cfs_quota(struct task_group *tg) +{ + u64 quota_us; + + if (tg->cfs_bandwidth.quota == RUNTIME_INF) + return -1; + + quota_us = tg->cfs_bandwidth.quota; + do_div(quota_us, NSEC_PER_USEC); + + return quota_us; +} + +int tg_set_cfs_period(struct task_group *tg, long cfs_period_us) +{ + u64 quota, period; + + period = (u64)cfs_period_us * NSEC_PER_USEC; + quota = tg->cfs_bandwidth.quota; + + return tg_set_cfs_bandwidth(tg, period, quota); +} + +long tg_get_cfs_period(struct task_group *tg) +{ + u64 cfs_period_us; + + cfs_period_us = ktime_to_ns(tg->cfs_bandwidth.period); + do_div(cfs_period_us, NSEC_PER_USEC); + + return cfs_period_us; +} + +static s64 cpu_cfs_quota_read_s64(struct cgroup_subsys_state *css, + struct cftype *cft) +{ + return tg_get_cfs_quota(css_tg(css)); +} + +static int cpu_cfs_quota_write_s64(struct cgroup_subsys_state *css, + struct cftype *cftype, s64 cfs_quota_us) +{ + return tg_set_cfs_quota(css_tg(css), cfs_quota_us); +} + +static u64 cpu_cfs_period_read_u64(struct cgroup_subsys_state *css, + struct cftype *cft) +{ + return tg_get_cfs_period(css_tg(css)); +} + +static int cpu_cfs_period_write_u64(struct cgroup_subsys_state *css, + struct cftype *cftype, u64 cfs_period_us) +{ + return tg_set_cfs_period(css_tg(css), cfs_period_us); +} + +struct cfs_schedulable_data { + struct task_group *tg; + u64 period, quota; +}; + +/* + * normalize group quota/period to be quota/max_period + * note: units are usecs + */ +static u64 normalize_cfs_quota(struct task_group *tg, + struct cfs_schedulable_data *d) +{ + u64 quota, period; + + if (tg == d->tg) { + period = d->period; + quota = d->quota; + } else { + period = tg_get_cfs_period(tg); + quota = tg_get_cfs_quota(tg); + } + + /* note: these should typically be equivalent */ + if (quota == RUNTIME_INF || quota == -1) + return RUNTIME_INF; + + return to_ratio(period, quota); +} + +static int tg_cfs_schedulable_down(struct task_group *tg, void *data) +{ + struct cfs_schedulable_data *d = data; + struct cfs_bandwidth *cfs_b = &tg->cfs_bandwidth; + s64 quota = 0, parent_quota = -1; + + if (!tg->parent) { + quota = RUNTIME_INF; + } else { + struct cfs_bandwidth *parent_b = &tg->parent->cfs_bandwidth; + + quota = normalize_cfs_quota(tg, d); + parent_quota = parent_b->hierarchical_quota; + + /* + * ensure max(child_quota) <= parent_quota, inherit when no + * limit is set + */ + if (quota == RUNTIME_INF) + quota = parent_quota; + else if (parent_quota != RUNTIME_INF && quota > parent_quota) + return -EINVAL; + } + cfs_b->hierarchical_quota = quota; + + return 0; +} + +static int __cfs_schedulable(struct task_group *tg, u64 period, u64 quota) +{ + int ret; + struct cfs_schedulable_data data = { + .tg = tg, + .period = period, + .quota = quota, + }; + + if (quota != RUNTIME_INF) { + do_div(data.period, NSEC_PER_USEC); + do_div(data.quota, NSEC_PER_USEC); + } + + rcu_read_lock(); + ret = walk_tg_tree(tg_cfs_schedulable_down, tg_nop, &data); + rcu_read_unlock(); + + return ret; +} + +static int cpu_stats_show(struct seq_file *sf, void *v) +{ + struct task_group *tg = css_tg(seq_css(sf)); + struct cfs_bandwidth *cfs_b = &tg->cfs_bandwidth; + + seq_printf(sf, "nr_periods %d\n", cfs_b->nr_periods); + seq_printf(sf, "nr_throttled %d\n", cfs_b->nr_throttled); + seq_printf(sf, "throttled_time %llu\n", cfs_b->throttled_time); + + return 0; +} +#endif /* CONFIG_CFS_BANDWIDTH */ +#endif /* CONFIG_FAIR_GROUP_SCHED */ + +#ifdef CONFIG_RT_GROUP_SCHED +static int cpu_rt_runtime_write(struct cgroup_subsys_state *css, + struct cftype *cft, s64 val) +{ + return sched_group_set_rt_runtime(css_tg(css), val); +} + +static s64 cpu_rt_runtime_read(struct cgroup_subsys_state *css, + struct cftype *cft) +{ + return sched_group_rt_runtime(css_tg(css)); +} + +static int cpu_rt_period_write_uint(struct cgroup_subsys_state *css, + struct cftype *cftype, u64 rt_period_us) +{ + return sched_group_set_rt_period(css_tg(css), rt_period_us); +} + +static u64 cpu_rt_period_read_uint(struct cgroup_subsys_state *css, + struct cftype *cft) +{ + return sched_group_rt_period(css_tg(css)); +} +#endif /* CONFIG_RT_GROUP_SCHED */ + +static struct cftype cpu_files[] = { +#ifdef CONFIG_FAIR_GROUP_SCHED + { + .name = "shares", + .read_u64 = cpu_shares_read_u64, + .write_u64 = cpu_shares_write_u64, + }, +#endif +#ifdef CONFIG_CFS_BANDWIDTH + { + .name = "cfs_quota_us", + .read_s64 = cpu_cfs_quota_read_s64, + .write_s64 = cpu_cfs_quota_write_s64, + }, + { + .name = "cfs_period_us", + .read_u64 = cpu_cfs_period_read_u64, + .write_u64 = cpu_cfs_period_write_u64, + }, + { + .name = "stat", + .seq_show = cpu_stats_show, + }, +#endif +#ifdef CONFIG_RT_GROUP_SCHED + { + .name = "rt_runtime_us", + .read_s64 = cpu_rt_runtime_read, + .write_s64 = cpu_rt_runtime_write, + }, + { + .name = "rt_period_us", + .read_u64 = cpu_rt_period_read_uint, + .write_u64 = cpu_rt_period_write_uint, + }, +#endif + { } /* terminate */ +}; + +struct cgroup_subsys cpu_cgrp_subsys = { + .css_alloc = cpu_cgroup_css_alloc, + .css_free = cpu_cgroup_css_free, + .css_online = cpu_cgroup_css_online, + .css_offline = cpu_cgroup_css_offline, + .fork = cpu_cgroup_fork, + .can_attach = cpu_cgroup_can_attach, + .attach = cpu_cgroup_attach, + .exit = cpu_cgroup_exit, + .legacy_cftypes = cpu_files, + .early_init = 1, +}; + +#endif /* CONFIG_CGROUP_SCHED */ + +void dump_cpu_task(int cpu) +{ + pr_info("Task dump for CPU %d:\n", cpu); + sched_show_task(cpu_curr(cpu)); +} diff --git a/kernel/kernel/sched/cpuacct.c b/kernel/kernel/sched/cpuacct.c new file mode 100644 index 000000000..dd7cbb55b --- /dev/null +++ b/kernel/kernel/sched/cpuacct.c @@ -0,0 +1,283 @@ +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "sched.h" + +/* + * CPU accounting code for task groups. + * + * Based on the work by Paul Menage (menage@google.com) and Balbir Singh + * (balbir@in.ibm.com). + */ + +/* Time spent by the tasks of the cpu accounting group executing in ... */ +enum cpuacct_stat_index { + CPUACCT_STAT_USER, /* ... user mode */ + CPUACCT_STAT_SYSTEM, /* ... kernel mode */ + + CPUACCT_STAT_NSTATS, +}; + +/* track cpu usage of a group of tasks and its child groups */ +struct cpuacct { + struct cgroup_subsys_state css; + /* cpuusage holds pointer to a u64-type object on every cpu */ + u64 __percpu *cpuusage; + struct kernel_cpustat __percpu *cpustat; +}; + +static inline struct cpuacct *css_ca(struct cgroup_subsys_state *css) +{ + return css ? container_of(css, struct cpuacct, css) : NULL; +} + +/* return cpu accounting group to which this task belongs */ +static inline struct cpuacct *task_ca(struct task_struct *tsk) +{ + return css_ca(task_css(tsk, cpuacct_cgrp_id)); +} + +static inline struct cpuacct *parent_ca(struct cpuacct *ca) +{ + return css_ca(ca->css.parent); +} + +static DEFINE_PER_CPU(u64, root_cpuacct_cpuusage); +static struct cpuacct root_cpuacct = { + .cpustat = &kernel_cpustat, + .cpuusage = &root_cpuacct_cpuusage, +}; + +/* create a new cpu accounting group */ +static struct cgroup_subsys_state * +cpuacct_css_alloc(struct cgroup_subsys_state *parent_css) +{ + struct cpuacct *ca; + + if (!parent_css) + return &root_cpuacct.css; + + ca = kzalloc(sizeof(*ca), GFP_KERNEL); + if (!ca) + goto out; + + ca->cpuusage = alloc_percpu(u64); + if (!ca->cpuusage) + goto out_free_ca; + + ca->cpustat = alloc_percpu(struct kernel_cpustat); + if (!ca->cpustat) + goto out_free_cpuusage; + + return &ca->css; + +out_free_cpuusage: + free_percpu(ca->cpuusage); +out_free_ca: + kfree(ca); +out: + return ERR_PTR(-ENOMEM); +} + +/* destroy an existing cpu accounting group */ +static void cpuacct_css_free(struct cgroup_subsys_state *css) +{ + struct cpuacct *ca = css_ca(css); + + free_percpu(ca->cpustat); + free_percpu(ca->cpuusage); + kfree(ca); +} + +static u64 cpuacct_cpuusage_read(struct cpuacct *ca, int cpu) +{ + u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu); + u64 data; + +#ifndef CONFIG_64BIT + /* + * Take rq->lock to make 64-bit read safe on 32-bit platforms. + */ + raw_spin_lock_irq(&cpu_rq(cpu)->lock); + data = *cpuusage; + raw_spin_unlock_irq(&cpu_rq(cpu)->lock); +#else + data = *cpuusage; +#endif + + return data; +} + +static void cpuacct_cpuusage_write(struct cpuacct *ca, int cpu, u64 val) +{ + u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu); + +#ifndef CONFIG_64BIT + /* + * Take rq->lock to make 64-bit write safe on 32-bit platforms. + */ + raw_spin_lock_irq(&cpu_rq(cpu)->lock); + *cpuusage = val; + raw_spin_unlock_irq(&cpu_rq(cpu)->lock); +#else + *cpuusage = val; +#endif +} + +/* return total cpu usage (in nanoseconds) of a group */ +static u64 cpuusage_read(struct cgroup_subsys_state *css, struct cftype *cft) +{ + struct cpuacct *ca = css_ca(css); + u64 totalcpuusage = 0; + int i; + + for_each_present_cpu(i) + totalcpuusage += cpuacct_cpuusage_read(ca, i); + + return totalcpuusage; +} + +static int cpuusage_write(struct cgroup_subsys_state *css, struct cftype *cft, + u64 reset) +{ + struct cpuacct *ca = css_ca(css); + int err = 0; + int i; + + if (reset) { + err = -EINVAL; + goto out; + } + + for_each_present_cpu(i) + cpuacct_cpuusage_write(ca, i, 0); + +out: + return err; +} + +static int cpuacct_percpu_seq_show(struct seq_file *m, void *V) +{ + struct cpuacct *ca = css_ca(seq_css(m)); + u64 percpu; + int i; + + for_each_present_cpu(i) { + percpu = cpuacct_cpuusage_read(ca, i); + seq_printf(m, "%llu ", (unsigned long long) percpu); + } + seq_printf(m, "\n"); + return 0; +} + +static const char * const cpuacct_stat_desc[] = { + [CPUACCT_STAT_USER] = "user", + [CPUACCT_STAT_SYSTEM] = "system", +}; + +static int cpuacct_stats_show(struct seq_file *sf, void *v) +{ + struct cpuacct *ca = css_ca(seq_css(sf)); + int cpu; + s64 val = 0; + + for_each_online_cpu(cpu) { + struct kernel_cpustat *kcpustat = per_cpu_ptr(ca->cpustat, cpu); + val += kcpustat->cpustat[CPUTIME_USER]; + val += kcpustat->cpustat[CPUTIME_NICE]; + } + val = cputime64_to_clock_t(val); + seq_printf(sf, "%s %lld\n", cpuacct_stat_desc[CPUACCT_STAT_USER], val); + + val = 0; + for_each_online_cpu(cpu) { + struct kernel_cpustat *kcpustat = per_cpu_ptr(ca->cpustat, cpu); + val += kcpustat->cpustat[CPUTIME_SYSTEM]; + val += kcpustat->cpustat[CPUTIME_IRQ]; + val += kcpustat->cpustat[CPUTIME_SOFTIRQ]; + } + + val = cputime64_to_clock_t(val); + seq_printf(sf, "%s %lld\n", cpuacct_stat_desc[CPUACCT_STAT_SYSTEM], val); + + return 0; +} + +static struct cftype files[] = { + { + .name = "usage", + .read_u64 = cpuusage_read, + .write_u64 = cpuusage_write, + }, + { + .name = "usage_percpu", + .seq_show = cpuacct_percpu_seq_show, + }, + { + .name = "stat", + .seq_show = cpuacct_stats_show, + }, + { } /* terminate */ +}; + +/* + * charge this task's execution time to its accounting group. + * + * called with rq->lock held. + */ +void cpuacct_charge(struct task_struct *tsk, u64 cputime) +{ + struct cpuacct *ca; + int cpu; + + cpu = task_cpu(tsk); + + rcu_read_lock(); + + ca = task_ca(tsk); + + while (true) { + u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu); + *cpuusage += cputime; + + ca = parent_ca(ca); + if (!ca) + break; + } + + rcu_read_unlock(); +} + +/* + * Add user/system time to cpuacct. + * + * Note: it's the caller that updates the account of the root cgroup. + */ +void cpuacct_account_field(struct task_struct *p, int index, u64 val) +{ + struct kernel_cpustat *kcpustat; + struct cpuacct *ca; + + rcu_read_lock(); + ca = task_ca(p); + while (ca != &root_cpuacct) { + kcpustat = this_cpu_ptr(ca->cpustat); + kcpustat->cpustat[index] += val; + ca = parent_ca(ca); + } + rcu_read_unlock(); +} + +struct cgroup_subsys cpuacct_cgrp_subsys = { + .css_alloc = cpuacct_css_alloc, + .css_free = cpuacct_css_free, + .legacy_cftypes = files, + .early_init = 1, +}; diff --git a/kernel/kernel/sched/cpuacct.h b/kernel/kernel/sched/cpuacct.h new file mode 100644 index 000000000..ed605624a --- /dev/null +++ b/kernel/kernel/sched/cpuacct.h @@ -0,0 +1,17 @@ +#ifdef CONFIG_CGROUP_CPUACCT + +extern void cpuacct_charge(struct task_struct *tsk, u64 cputime); +extern void cpuacct_account_field(struct task_struct *p, int index, u64 val); + +#else + +static inline void cpuacct_charge(struct task_struct *tsk, u64 cputime) +{ +} + +static inline void +cpuacct_account_field(struct task_struct *p, int index, u64 val) +{ +} + +#endif diff --git a/kernel/kernel/sched/cpudeadline.c b/kernel/kernel/sched/cpudeadline.c new file mode 100644 index 000000000..c6acb0746 --- /dev/null +++ b/kernel/kernel/sched/cpudeadline.c @@ -0,0 +1,246 @@ +/* + * kernel/sched/cpudl.c + * + * Global CPU deadline management + * + * Author: Juri Lelli + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; version 2 + * of the License. + */ + +#include +#include +#include +#include "cpudeadline.h" + +static inline int parent(int i) +{ + return (i - 1) >> 1; +} + +static inline int left_child(int i) +{ + return (i << 1) + 1; +} + +static inline int right_child(int i) +{ + return (i << 1) + 2; +} + +static inline int dl_time_before(u64 a, u64 b) +{ + return (s64)(a - b) < 0; +} + +static void cpudl_exchange(struct cpudl *cp, int a, int b) +{ + int cpu_a = cp->elements[a].cpu, cpu_b = cp->elements[b].cpu; + + swap(cp->elements[a].cpu, cp->elements[b].cpu); + swap(cp->elements[a].dl , cp->elements[b].dl ); + + swap(cp->elements[cpu_a].idx, cp->elements[cpu_b].idx); +} + +static void cpudl_heapify(struct cpudl *cp, int idx) +{ + int l, r, largest; + + /* adapted from lib/prio_heap.c */ + while(1) { + l = left_child(idx); + r = right_child(idx); + largest = idx; + + if ((l < cp->size) && dl_time_before(cp->elements[idx].dl, + cp->elements[l].dl)) + largest = l; + if ((r < cp->size) && dl_time_before(cp->elements[largest].dl, + cp->elements[r].dl)) + largest = r; + if (largest == idx) + break; + + /* Push idx down the heap one level and bump one up */ + cpudl_exchange(cp, largest, idx); + idx = largest; + } +} + +static void cpudl_change_key(struct cpudl *cp, int idx, u64 new_dl) +{ + WARN_ON(idx == IDX_INVALID || !cpu_present(idx)); + + if (dl_time_before(new_dl, cp->elements[idx].dl)) { + cp->elements[idx].dl = new_dl; + cpudl_heapify(cp, idx); + } else { + cp->elements[idx].dl = new_dl; + while (idx > 0 && dl_time_before(cp->elements[parent(idx)].dl, + cp->elements[idx].dl)) { + cpudl_exchange(cp, idx, parent(idx)); + idx = parent(idx); + } + } +} + +static inline int cpudl_maximum(struct cpudl *cp) +{ + return cp->elements[0].cpu; +} + +/* + * cpudl_find - find the best (later-dl) CPU in the system + * @cp: the cpudl max-heap context + * @p: the task + * @later_mask: a mask to fill in with the selected CPUs (or NULL) + * + * Returns: int - best CPU (heap maximum if suitable) + */ +int cpudl_find(struct cpudl *cp, struct task_struct *p, + struct cpumask *later_mask) +{ + int best_cpu = -1; + const struct sched_dl_entity *dl_se = &p->dl; + + if (later_mask && + cpumask_and(later_mask, cp->free_cpus, &p->cpus_allowed)) { + best_cpu = cpumask_any(later_mask); + goto out; + } else if (cpumask_test_cpu(cpudl_maximum(cp), &p->cpus_allowed) && + dl_time_before(dl_se->deadline, cp->elements[0].dl)) { + best_cpu = cpudl_maximum(cp); + if (later_mask) + cpumask_set_cpu(best_cpu, later_mask); + } + +out: + WARN_ON(best_cpu != -1 && !cpu_present(best_cpu)); + + return best_cpu; +} + +/* + * cpudl_set - update the cpudl max-heap + * @cp: the cpudl max-heap context + * @cpu: the target cpu + * @dl: the new earliest deadline for this cpu + * + * Notes: assumes cpu_rq(cpu)->lock is locked + * + * Returns: (void) + */ +void cpudl_set(struct cpudl *cp, int cpu, u64 dl, int is_valid) +{ + int old_idx, new_cpu; + unsigned long flags; + + WARN_ON(!cpu_present(cpu)); + + raw_spin_lock_irqsave(&cp->lock, flags); + old_idx = cp->elements[cpu].idx; + if (!is_valid) { + /* remove item */ + if (old_idx == IDX_INVALID) { + /* + * Nothing to remove if old_idx was invalid. + * This could happen if a rq_offline_dl is + * called for a CPU without -dl tasks running. + */ + goto out; + } + new_cpu = cp->elements[cp->size - 1].cpu; + cp->elements[old_idx].dl = cp->elements[cp->size - 1].dl; + cp->elements[old_idx].cpu = new_cpu; + cp->size--; + cp->elements[new_cpu].idx = old_idx; + cp->elements[cpu].idx = IDX_INVALID; + while (old_idx > 0 && dl_time_before( + cp->elements[parent(old_idx)].dl, + cp->elements[old_idx].dl)) { + cpudl_exchange(cp, old_idx, parent(old_idx)); + old_idx = parent(old_idx); + } + cpumask_set_cpu(cpu, cp->free_cpus); + cpudl_heapify(cp, old_idx); + + goto out; + } + + if (old_idx == IDX_INVALID) { + cp->size++; + cp->elements[cp->size - 1].dl = 0; + cp->elements[cp->size - 1].cpu = cpu; + cp->elements[cpu].idx = cp->size - 1; + cpudl_change_key(cp, cp->size - 1, dl); + cpumask_clear_cpu(cpu, cp->free_cpus); + } else { + cpudl_change_key(cp, old_idx, dl); + } + +out: + raw_spin_unlock_irqrestore(&cp->lock, flags); +} + +/* + * cpudl_set_freecpu - Set the cpudl.free_cpus + * @cp: the cpudl max-heap context + * @cpu: rd attached cpu + */ +void cpudl_set_freecpu(struct cpudl *cp, int cpu) +{ + cpumask_set_cpu(cpu, cp->free_cpus); +} + +/* + * cpudl_clear_freecpu - Clear the cpudl.free_cpus + * @cp: the cpudl max-heap context + * @cpu: rd attached cpu + */ +void cpudl_clear_freecpu(struct cpudl *cp, int cpu) +{ + cpumask_clear_cpu(cpu, cp->free_cpus); +} + +/* + * cpudl_init - initialize the cpudl structure + * @cp: the cpudl max-heap context + */ +int cpudl_init(struct cpudl *cp) +{ + int i; + + memset(cp, 0, sizeof(*cp)); + raw_spin_lock_init(&cp->lock); + cp->size = 0; + + cp->elements = kcalloc(nr_cpu_ids, + sizeof(struct cpudl_item), + GFP_KERNEL); + if (!cp->elements) + return -ENOMEM; + + if (!zalloc_cpumask_var(&cp->free_cpus, GFP_KERNEL)) { + kfree(cp->elements); + return -ENOMEM; + } + + for_each_possible_cpu(i) + cp->elements[i].idx = IDX_INVALID; + + return 0; +} + +/* + * cpudl_cleanup - clean up the cpudl structure + * @cp: the cpudl max-heap context + */ +void cpudl_cleanup(struct cpudl *cp) +{ + free_cpumask_var(cp->free_cpus); + kfree(cp->elements); +} diff --git a/kernel/kernel/sched/cpudeadline.h b/kernel/kernel/sched/cpudeadline.h new file mode 100644 index 000000000..1a0a6ef2f --- /dev/null +++ b/kernel/kernel/sched/cpudeadline.h @@ -0,0 +1,32 @@ +#ifndef _LINUX_CPUDL_H +#define _LINUX_CPUDL_H + +#include + +#define IDX_INVALID -1 + +struct cpudl_item { + u64 dl; + int cpu; + int idx; +}; + +struct cpudl { + raw_spinlock_t lock; + int size; + cpumask_var_t free_cpus; + struct cpudl_item *elements; +}; + + +#ifdef CONFIG_SMP +int cpudl_find(struct cpudl *cp, struct task_struct *p, + struct cpumask *later_mask); +void cpudl_set(struct cpudl *cp, int cpu, u64 dl, int is_valid); +int cpudl_init(struct cpudl *cp); +void cpudl_set_freecpu(struct cpudl *cp, int cpu); +void cpudl_clear_freecpu(struct cpudl *cp, int cpu); +void cpudl_cleanup(struct cpudl *cp); +#endif /* CONFIG_SMP */ + +#endif /* _LINUX_CPUDL_H */ diff --git a/kernel/kernel/sched/cpupri.c b/kernel/kernel/sched/cpupri.c new file mode 100644 index 000000000..981fcd7dc --- /dev/null +++ b/kernel/kernel/sched/cpupri.c @@ -0,0 +1,248 @@ +/* + * kernel/sched/cpupri.c + * + * CPU priority management + * + * Copyright (C) 2007-2008 Novell + * + * Author: Gregory Haskins + * + * This code tracks the priority of each CPU so that global migration + * decisions are easy to calculate. Each CPU can be in a state as follows: + * + * (INVALID), IDLE, NORMAL, RT1, ... RT99 + * + * going from the lowest priority to the highest. CPUs in the INVALID state + * are not eligible for routing. The system maintains this state with + * a 2 dimensional bitmap (the first for priority class, the second for cpus + * in that class). Therefore a typical application without affinity + * restrictions can find a suitable CPU with O(1) complexity (e.g. two bit + * searches). For tasks with affinity restrictions, the algorithm has a + * worst case complexity of O(min(102, nr_domcpus)), though the scenario that + * yields the worst case search is fairly contrived. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; version 2 + * of the License. + */ + +#include +#include +#include +#include +#include "cpupri.h" + +/* Convert between a 140 based task->prio, and our 102 based cpupri */ +static int convert_prio(int prio) +{ + int cpupri; + + if (prio == CPUPRI_INVALID) + cpupri = CPUPRI_INVALID; + else if (prio == MAX_PRIO) + cpupri = CPUPRI_IDLE; + else if (prio >= MAX_RT_PRIO) + cpupri = CPUPRI_NORMAL; + else + cpupri = MAX_RT_PRIO - prio + 1; + + return cpupri; +} + +/** + * cpupri_find - find the best (lowest-pri) CPU in the system + * @cp: The cpupri context + * @p: The task + * @lowest_mask: A mask to fill in with selected CPUs (or NULL) + * + * Note: This function returns the recommended CPUs as calculated during the + * current invocation. By the time the call returns, the CPUs may have in + * fact changed priorities any number of times. While not ideal, it is not + * an issue of correctness since the normal rebalancer logic will correct + * any discrepancies created by racing against the uncertainty of the current + * priority configuration. + * + * Return: (int)bool - CPUs were found + */ +int cpupri_find(struct cpupri *cp, struct task_struct *p, + struct cpumask *lowest_mask) +{ + int idx = 0; + int task_pri = convert_prio(p->prio); + + BUG_ON(task_pri >= CPUPRI_NR_PRIORITIES); + + for (idx = 0; idx < task_pri; idx++) { + struct cpupri_vec *vec = &cp->pri_to_cpu[idx]; + int skip = 0; + + if (!atomic_read(&(vec)->count)) + skip = 1; + /* + * When looking at the vector, we need to read the counter, + * do a memory barrier, then read the mask. + * + * Note: This is still all racey, but we can deal with it. + * Ideally, we only want to look at masks that are set. + * + * If a mask is not set, then the only thing wrong is that we + * did a little more work than necessary. + * + * If we read a zero count but the mask is set, because of the + * memory barriers, that can only happen when the highest prio + * task for a run queue has left the run queue, in which case, + * it will be followed by a pull. If the task we are processing + * fails to find a proper place to go, that pull request will + * pull this task if the run queue is running at a lower + * priority. + */ + smp_rmb(); + + /* Need to do the rmb for every iteration */ + if (skip) + continue; + + if (cpumask_any_and(&p->cpus_allowed, vec->mask) >= nr_cpu_ids) + continue; + + if (lowest_mask) { + cpumask_and(lowest_mask, &p->cpus_allowed, vec->mask); + + /* + * We have to ensure that we have at least one bit + * still set in the array, since the map could have + * been concurrently emptied between the first and + * second reads of vec->mask. If we hit this + * condition, simply act as though we never hit this + * priority level and continue on. + */ + if (cpumask_any(lowest_mask) >= nr_cpu_ids) + continue; + } + + return 1; + } + + return 0; +} + +/** + * cpupri_set - update the cpu priority setting + * @cp: The cpupri context + * @cpu: The target cpu + * @newpri: The priority (INVALID-RT99) to assign to this CPU + * + * Note: Assumes cpu_rq(cpu)->lock is locked + * + * Returns: (void) + */ +void cpupri_set(struct cpupri *cp, int cpu, int newpri) +{ + int *currpri = &cp->cpu_to_pri[cpu]; + int oldpri = *currpri; + int do_mb = 0; + + newpri = convert_prio(newpri); + + BUG_ON(newpri >= CPUPRI_NR_PRIORITIES); + + if (newpri == oldpri) + return; + + /* + * If the cpu was currently mapped to a different value, we + * need to map it to the new value then remove the old value. + * Note, we must add the new value first, otherwise we risk the + * cpu being missed by the priority loop in cpupri_find. + */ + if (likely(newpri != CPUPRI_INVALID)) { + struct cpupri_vec *vec = &cp->pri_to_cpu[newpri]; + + cpumask_set_cpu(cpu, vec->mask); + /* + * When adding a new vector, we update the mask first, + * do a write memory barrier, and then update the count, to + * make sure the vector is visible when count is set. + */ + smp_mb__before_atomic(); + atomic_inc(&(vec)->count); + do_mb = 1; + } + if (likely(oldpri != CPUPRI_INVALID)) { + struct cpupri_vec *vec = &cp->pri_to_cpu[oldpri]; + + /* + * Because the order of modification of the vec->count + * is important, we must make sure that the update + * of the new prio is seen before we decrement the + * old prio. This makes sure that the loop sees + * one or the other when we raise the priority of + * the run queue. We don't care about when we lower the + * priority, as that will trigger an rt pull anyway. + * + * We only need to do a memory barrier if we updated + * the new priority vec. + */ + if (do_mb) + smp_mb__after_atomic(); + + /* + * When removing from the vector, we decrement the counter first + * do a memory barrier and then clear the mask. + */ + atomic_dec(&(vec)->count); + smp_mb__after_atomic(); + cpumask_clear_cpu(cpu, vec->mask); + } + + *currpri = newpri; +} + +/** + * cpupri_init - initialize the cpupri structure + * @cp: The cpupri context + * + * Return: -ENOMEM on memory allocation failure. + */ +int cpupri_init(struct cpupri *cp) +{ + int i; + + memset(cp, 0, sizeof(*cp)); + + for (i = 0; i < CPUPRI_NR_PRIORITIES; i++) { + struct cpupri_vec *vec = &cp->pri_to_cpu[i]; + + atomic_set(&vec->count, 0); + if (!zalloc_cpumask_var(&vec->mask, GFP_KERNEL)) + goto cleanup; + } + + cp->cpu_to_pri = kcalloc(nr_cpu_ids, sizeof(int), GFP_KERNEL); + if (!cp->cpu_to_pri) + goto cleanup; + + for_each_possible_cpu(i) + cp->cpu_to_pri[i] = CPUPRI_INVALID; + + return 0; + +cleanup: + for (i--; i >= 0; i--) + free_cpumask_var(cp->pri_to_cpu[i].mask); + return -ENOMEM; +} + +/** + * cpupri_cleanup - clean up the cpupri structure + * @cp: The cpupri context + */ +void cpupri_cleanup(struct cpupri *cp) +{ + int i; + + kfree(cp->cpu_to_pri); + for (i = 0; i < CPUPRI_NR_PRIORITIES; i++) + free_cpumask_var(cp->pri_to_cpu[i].mask); +} diff --git a/kernel/kernel/sched/cpupri.h b/kernel/kernel/sched/cpupri.h new file mode 100644 index 000000000..63cbb9ca0 --- /dev/null +++ b/kernel/kernel/sched/cpupri.h @@ -0,0 +1,31 @@ +#ifndef _LINUX_CPUPRI_H +#define _LINUX_CPUPRI_H + +#include + +#define CPUPRI_NR_PRIORITIES (MAX_RT_PRIO + 2) + +#define CPUPRI_INVALID -1 +#define CPUPRI_IDLE 0 +#define CPUPRI_NORMAL 1 +/* values 2-101 are RT priorities 0-99 */ + +struct cpupri_vec { + atomic_t count; + cpumask_var_t mask; +}; + +struct cpupri { + struct cpupri_vec pri_to_cpu[CPUPRI_NR_PRIORITIES]; + int *cpu_to_pri; +}; + +#ifdef CONFIG_SMP +int cpupri_find(struct cpupri *cp, + struct task_struct *p, struct cpumask *lowest_mask); +void cpupri_set(struct cpupri *cp, int cpu, int pri); +int cpupri_init(struct cpupri *cp); +void cpupri_cleanup(struct cpupri *cp); +#endif + +#endif /* _LINUX_CPUPRI_H */ diff --git a/kernel/kernel/sched/cputime.c b/kernel/kernel/sched/cputime.c new file mode 100644 index 000000000..2da134c9b --- /dev/null +++ b/kernel/kernel/sched/cputime.c @@ -0,0 +1,870 @@ +#include +#include +#include +#include +#include +#include +#include "sched.h" + + +#ifdef CONFIG_IRQ_TIME_ACCOUNTING + +/* + * There are no locks covering percpu hardirq/softirq time. + * They are only modified in vtime_account, on corresponding CPU + * with interrupts disabled. So, writes are safe. + * They are read and saved off onto struct rq in update_rq_clock(). + * This may result in other CPU reading this CPU's irq time and can + * race with irq/vtime_account on this CPU. We would either get old + * or new value with a side effect of accounting a slice of irq time to wrong + * task when irq is in progress while we read rq->clock. That is a worthy + * compromise in place of having locks on each irq in account_system_time. + */ +DEFINE_PER_CPU(u64, cpu_hardirq_time); +DEFINE_PER_CPU(u64, cpu_softirq_time); + +static DEFINE_PER_CPU(u64, irq_start_time); +static int sched_clock_irqtime; + +void enable_sched_clock_irqtime(void) +{ + sched_clock_irqtime = 1; +} + +void disable_sched_clock_irqtime(void) +{ + sched_clock_irqtime = 0; +} + +#ifndef CONFIG_64BIT +DEFINE_PER_CPU(seqcount_t, irq_time_seq); +#endif /* CONFIG_64BIT */ + +/* + * Called before incrementing preempt_count on {soft,}irq_enter + * and before decrementing preempt_count on {soft,}irq_exit. + */ +void irqtime_account_irq(struct task_struct *curr) +{ + unsigned long flags; + s64 delta; + int cpu; + + if (!sched_clock_irqtime) + return; + + local_irq_save(flags); + + cpu = smp_processor_id(); + delta = sched_clock_cpu(cpu) - __this_cpu_read(irq_start_time); + __this_cpu_add(irq_start_time, delta); + + irq_time_write_begin(); + /* + * We do not account for softirq time from ksoftirqd here. + * We want to continue accounting softirq time to ksoftirqd thread + * in that case, so as not to confuse scheduler with a special task + * that do not consume any time, but still wants to run. + */ + if (hardirq_count()) + __this_cpu_add(cpu_hardirq_time, delta); + else if (in_serving_softirq() && curr != this_cpu_ksoftirqd()) + __this_cpu_add(cpu_softirq_time, delta); + + irq_time_write_end(); + local_irq_restore(flags); +} +EXPORT_SYMBOL_GPL(irqtime_account_irq); + +static int irqtime_account_hi_update(void) +{ + u64 *cpustat = kcpustat_this_cpu->cpustat; + unsigned long flags; + u64 latest_ns; + int ret = 0; + + local_irq_save(flags); + latest_ns = this_cpu_read(cpu_hardirq_time); + if (nsecs_to_cputime64(latest_ns) > cpustat[CPUTIME_IRQ]) + ret = 1; + local_irq_restore(flags); + return ret; +} + +static int irqtime_account_si_update(void) +{ + u64 *cpustat = kcpustat_this_cpu->cpustat; + unsigned long flags; + u64 latest_ns; + int ret = 0; + + local_irq_save(flags); + latest_ns = this_cpu_read(cpu_softirq_time); + if (nsecs_to_cputime64(latest_ns) > cpustat[CPUTIME_SOFTIRQ]) + ret = 1; + local_irq_restore(flags); + return ret; +} + +#else /* CONFIG_IRQ_TIME_ACCOUNTING */ + +#define sched_clock_irqtime (0) + +#endif /* !CONFIG_IRQ_TIME_ACCOUNTING */ + +static inline void task_group_account_field(struct task_struct *p, int index, + u64 tmp) +{ + /* + * Since all updates are sure to touch the root cgroup, we + * get ourselves ahead and touch it first. If the root cgroup + * is the only cgroup, then nothing else should be necessary. + * + */ + __this_cpu_add(kernel_cpustat.cpustat[index], tmp); + + cpuacct_account_field(p, index, tmp); +} + +/* + * Account user cpu time to a process. + * @p: the process that the cpu time gets accounted to + * @cputime: the cpu time spent in user space since the last update + * @cputime_scaled: cputime scaled by cpu frequency + */ +void account_user_time(struct task_struct *p, cputime_t cputime, + cputime_t cputime_scaled) +{ + int index; + + /* Add user time to process. */ + p->utime += cputime; + p->utimescaled += cputime_scaled; + account_group_user_time(p, cputime); + + index = (task_nice(p) > 0) ? CPUTIME_NICE : CPUTIME_USER; + + /* Add user time to cpustat. */ + task_group_account_field(p, index, (__force u64) cputime); + + /* Account for user time used */ + acct_account_cputime(p); +} + +/* + * Account guest cpu time to a process. + * @p: the process that the cpu time gets accounted to + * @cputime: the cpu time spent in virtual machine since the last update + * @cputime_scaled: cputime scaled by cpu frequency + */ +static void account_guest_time(struct task_struct *p, cputime_t cputime, + cputime_t cputime_scaled) +{ + u64 *cpustat = kcpustat_this_cpu->cpustat; + + /* Add guest time to process. */ + p->utime += cputime; + p->utimescaled += cputime_scaled; + account_group_user_time(p, cputime); + p->gtime += cputime; + + /* Add guest time to cpustat. */ + if (task_nice(p) > 0) { + cpustat[CPUTIME_NICE] += (__force u64) cputime; + cpustat[CPUTIME_GUEST_NICE] += (__force u64) cputime; + } else { + cpustat[CPUTIME_USER] += (__force u64) cputime; + cpustat[CPUTIME_GUEST] += (__force u64) cputime; + } +} + +/* + * Account system cpu time to a process and desired cpustat field + * @p: the process that the cpu time gets accounted to + * @cputime: the cpu time spent in kernel space since the last update + * @cputime_scaled: cputime scaled by cpu frequency + * @target_cputime64: pointer to cpustat field that has to be updated + */ +static inline +void __account_system_time(struct task_struct *p, cputime_t cputime, + cputime_t cputime_scaled, int index) +{ + /* Add system time to process. */ + p->stime += cputime; + p->stimescaled += cputime_scaled; + account_group_system_time(p, cputime); + + /* Add system time to cpustat. */ + task_group_account_field(p, index, (__force u64) cputime); + + /* Account for system time used */ + acct_account_cputime(p); +} + +/* + * Account system cpu time to a process. + * @p: the process that the cpu time gets accounted to + * @hardirq_offset: the offset to subtract from hardirq_count() + * @cputime: the cpu time spent in kernel space since the last update + * @cputime_scaled: cputime scaled by cpu frequency + */ +void account_system_time(struct task_struct *p, int hardirq_offset, + cputime_t cputime, cputime_t cputime_scaled) +{ + int index; + + if ((p->flags & PF_VCPU) && (irq_count() - hardirq_offset == 0)) { + account_guest_time(p, cputime, cputime_scaled); + return; + } + + if (hardirq_count() - hardirq_offset) + index = CPUTIME_IRQ; + else if (in_serving_softirq()) + index = CPUTIME_SOFTIRQ; + else + index = CPUTIME_SYSTEM; + + __account_system_time(p, cputime, cputime_scaled, index); +} + +/* + * Account for involuntary wait time. + * @cputime: the cpu time spent in involuntary wait + */ +void account_steal_time(cputime_t cputime) +{ + u64 *cpustat = kcpustat_this_cpu->cpustat; + + cpustat[CPUTIME_STEAL] += (__force u64) cputime; +} + +/* + * Account for idle time. + * @cputime: the cpu time spent in idle wait + */ +void account_idle_time(cputime_t cputime) +{ + u64 *cpustat = kcpustat_this_cpu->cpustat; + struct rq *rq = this_rq(); + + if (atomic_read(&rq->nr_iowait) > 0) + cpustat[CPUTIME_IOWAIT] += (__force u64) cputime; + else + cpustat[CPUTIME_IDLE] += (__force u64) cputime; +} + +static __always_inline bool steal_account_process_tick(void) +{ +#ifdef CONFIG_PARAVIRT + if (static_key_false(¶virt_steal_enabled)) { + u64 steal; + cputime_t steal_ct; + + steal = paravirt_steal_clock(smp_processor_id()); + steal -= this_rq()->prev_steal_time; + + /* + * cputime_t may be less precise than nsecs (eg: if it's + * based on jiffies). Lets cast the result to cputime + * granularity and account the rest on the next rounds. + */ + steal_ct = nsecs_to_cputime(steal); + this_rq()->prev_steal_time += cputime_to_nsecs(steal_ct); + + account_steal_time(steal_ct); + return steal_ct; + } +#endif + return false; +} + +/* + * Accumulate raw cputime values of dead tasks (sig->[us]time) and live + * tasks (sum on group iteration) belonging to @tsk's group. + */ +void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times) +{ + struct signal_struct *sig = tsk->signal; + cputime_t utime, stime; + struct task_struct *t; + unsigned int seq, nextseq; + unsigned long flags; + + rcu_read_lock(); + /* Attempt a lockless read on the first round. */ + nextseq = 0; + do { + seq = nextseq; + flags = read_seqbegin_or_lock_irqsave(&sig->stats_lock, &seq); + times->utime = sig->utime; + times->stime = sig->stime; + times->sum_exec_runtime = sig->sum_sched_runtime; + + for_each_thread(tsk, t) { + task_cputime(t, &utime, &stime); + times->utime += utime; + times->stime += stime; + times->sum_exec_runtime += task_sched_runtime(t); + } + /* If lockless access failed, take the lock. */ + nextseq = 1; + } while (need_seqretry(&sig->stats_lock, seq)); + done_seqretry_irqrestore(&sig->stats_lock, seq, flags); + rcu_read_unlock(); +} + +#ifdef CONFIG_IRQ_TIME_ACCOUNTING +/* + * Account a tick to a process and cpustat + * @p: the process that the cpu time gets accounted to + * @user_tick: is the tick from userspace + * @rq: the pointer to rq + * + * Tick demultiplexing follows the order + * - pending hardirq update + * - pending softirq update + * - user_time + * - idle_time + * - system time + * - check for guest_time + * - else account as system_time + * + * Check for hardirq is done both for system and user time as there is + * no timer going off while we are on hardirq and hence we may never get an + * opportunity to update it solely in system time. + * p->stime and friends are only updated on system time and not on irq + * softirq as those do not count in task exec_runtime any more. + */ +static void irqtime_account_process_tick(struct task_struct *p, int user_tick, + struct rq *rq, int ticks) +{ + cputime_t scaled = cputime_to_scaled(cputime_one_jiffy); + u64 cputime = (__force u64) cputime_one_jiffy; + u64 *cpustat = kcpustat_this_cpu->cpustat; + + if (steal_account_process_tick()) + return; + + cputime *= ticks; + scaled *= ticks; + + if (irqtime_account_hi_update()) { + cpustat[CPUTIME_IRQ] += cputime; + } else if (irqtime_account_si_update()) { + cpustat[CPUTIME_SOFTIRQ] += cputime; + } else if (this_cpu_ksoftirqd() == p) { + /* + * ksoftirqd time do not get accounted in cpu_softirq_time. + * So, we have to handle it separately here. + * Also, p->stime needs to be updated for ksoftirqd. + */ + __account_system_time(p, cputime, scaled, CPUTIME_SOFTIRQ); + } else if (user_tick) { + account_user_time(p, cputime, scaled); + } else if (p == rq->idle) { + account_idle_time(cputime); + } else if (p->flags & PF_VCPU) { /* System time or guest time */ + account_guest_time(p, cputime, scaled); + } else { + __account_system_time(p, cputime, scaled, CPUTIME_SYSTEM); + } +} + +static void irqtime_account_idle_ticks(int ticks) +{ + struct rq *rq = this_rq(); + + irqtime_account_process_tick(current, 0, rq, ticks); +} +#else /* CONFIG_IRQ_TIME_ACCOUNTING */ +static inline void irqtime_account_idle_ticks(int ticks) {} +static inline void irqtime_account_process_tick(struct task_struct *p, int user_tick, + struct rq *rq, int nr_ticks) {} +#endif /* CONFIG_IRQ_TIME_ACCOUNTING */ + +/* + * Use precise platform statistics if available: + */ +#ifdef CONFIG_VIRT_CPU_ACCOUNTING + +#ifndef __ARCH_HAS_VTIME_TASK_SWITCH +void vtime_common_task_switch(struct task_struct *prev) +{ + if (is_idle_task(prev)) + vtime_account_idle(prev); + else + vtime_account_system(prev); + +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE + vtime_account_user(prev); +#endif + arch_vtime_task_switch(prev); +} +#endif + +/* + * Archs that account the whole time spent in the idle task + * (outside irq) as idle time can rely on this and just implement + * vtime_account_system() and vtime_account_idle(). Archs that + * have other meaning of the idle time (s390 only includes the + * time spent by the CPU when it's in low power mode) must override + * vtime_account(). + */ +#ifndef __ARCH_HAS_VTIME_ACCOUNT +void vtime_common_account_irq_enter(struct task_struct *tsk) +{ + if (!in_interrupt()) { + /* + * If we interrupted user, context_tracking_in_user() + * is 1 because the context tracking don't hook + * on irq entry/exit. This way we know if + * we need to flush user time on kernel entry. + */ + if (context_tracking_in_user()) { + vtime_account_user(tsk); + return; + } + + if (is_idle_task(tsk)) { + vtime_account_idle(tsk); + return; + } + } + vtime_account_system(tsk); +} +EXPORT_SYMBOL_GPL(vtime_common_account_irq_enter); +#endif /* __ARCH_HAS_VTIME_ACCOUNT */ +#endif /* CONFIG_VIRT_CPU_ACCOUNTING */ + + +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE +void task_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st) +{ + *ut = p->utime; + *st = p->stime; +} + +void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st) +{ + struct task_cputime cputime; + + thread_group_cputime(p, &cputime); + + *ut = cputime.utime; + *st = cputime.stime; +} +#else /* !CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */ +/* + * Account a single tick of cpu time. + * @p: the process that the cpu time gets accounted to + * @user_tick: indicates if the tick is a user or a system tick + */ +void account_process_tick(struct task_struct *p, int user_tick) +{ + cputime_t one_jiffy_scaled = cputime_to_scaled(cputime_one_jiffy); + struct rq *rq = this_rq(); + + if (vtime_accounting_enabled()) + return; + + if (sched_clock_irqtime) { + irqtime_account_process_tick(p, user_tick, rq, 1); + return; + } + + if (steal_account_process_tick()) + return; + + if (user_tick) + account_user_time(p, cputime_one_jiffy, one_jiffy_scaled); + else if ((p != rq->idle) || (irq_count() != HARDIRQ_OFFSET)) + account_system_time(p, HARDIRQ_OFFSET, cputime_one_jiffy, + one_jiffy_scaled); + else + account_idle_time(cputime_one_jiffy); +} + +/* + * Account multiple ticks of steal time. + * @p: the process from which the cpu time has been stolen + * @ticks: number of stolen ticks + */ +void account_steal_ticks(unsigned long ticks) +{ + account_steal_time(jiffies_to_cputime(ticks)); +} + +/* + * Account multiple ticks of idle time. + * @ticks: number of stolen ticks + */ +void account_idle_ticks(unsigned long ticks) +{ + + if (sched_clock_irqtime) { + irqtime_account_idle_ticks(ticks); + return; + } + + account_idle_time(jiffies_to_cputime(ticks)); +} + +/* + * Perform (stime * rtime) / total, but avoid multiplication overflow by + * loosing precision when the numbers are big. + */ +static cputime_t scale_stime(u64 stime, u64 rtime, u64 total) +{ + u64 scaled; + + for (;;) { + /* Make sure "rtime" is the bigger of stime/rtime */ + if (stime > rtime) + swap(rtime, stime); + + /* Make sure 'total' fits in 32 bits */ + if (total >> 32) + goto drop_precision; + + /* Does rtime (and thus stime) fit in 32 bits? */ + if (!(rtime >> 32)) + break; + + /* Can we just balance rtime/stime rather than dropping bits? */ + if (stime >> 31) + goto drop_precision; + + /* We can grow stime and shrink rtime and try to make them both fit */ + stime <<= 1; + rtime >>= 1; + continue; + +drop_precision: + /* We drop from rtime, it has more bits than stime */ + rtime >>= 1; + total >>= 1; + } + + /* + * Make sure gcc understands that this is a 32x32->64 multiply, + * followed by a 64/32->64 divide. + */ + scaled = div_u64((u64) (u32) stime * (u64) (u32) rtime, (u32)total); + return (__force cputime_t) scaled; +} + +/* + * Atomically advance counter to the new value. Interrupts, vcpu + * scheduling, and scaling inaccuracies can cause cputime_advance + * to be occasionally called with a new value smaller than counter. + * Let's enforce atomicity. + * + * Normally a caller will only go through this loop once, or not + * at all in case a previous caller updated counter the same jiffy. + */ +static void cputime_advance(cputime_t *counter, cputime_t new) +{ + cputime_t old; + + while (new > (old = ACCESS_ONCE(*counter))) + cmpxchg_cputime(counter, old, new); +} + +/* + * Adjust tick based cputime random precision against scheduler + * runtime accounting. + */ +static void cputime_adjust(struct task_cputime *curr, + struct cputime *prev, + cputime_t *ut, cputime_t *st) +{ + cputime_t rtime, stime, utime; + + /* + * Tick based cputime accounting depend on random scheduling + * timeslices of a task to be interrupted or not by the timer. + * Depending on these circumstances, the number of these interrupts + * may be over or under-optimistic, matching the real user and system + * cputime with a variable precision. + * + * Fix this by scaling these tick based values against the total + * runtime accounted by the CFS scheduler. + */ + rtime = nsecs_to_cputime(curr->sum_exec_runtime); + + /* + * Update userspace visible utime/stime values only if actual execution + * time is bigger than already exported. Note that can happen, that we + * provided bigger values due to scaling inaccuracy on big numbers. + */ + if (prev->stime + prev->utime >= rtime) + goto out; + + stime = curr->stime; + utime = curr->utime; + + if (utime == 0) { + stime = rtime; + } else if (stime == 0) { + utime = rtime; + } else { + cputime_t total = stime + utime; + + stime = scale_stime((__force u64)stime, + (__force u64)rtime, (__force u64)total); + utime = rtime - stime; + } + + cputime_advance(&prev->stime, stime); + cputime_advance(&prev->utime, utime); + +out: + *ut = prev->utime; + *st = prev->stime; +} + +void task_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st) +{ + struct task_cputime cputime = { + .sum_exec_runtime = p->se.sum_exec_runtime, + }; + + task_cputime(p, &cputime.utime, &cputime.stime); + cputime_adjust(&cputime, &p->prev_cputime, ut, st); +} + +void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st) +{ + struct task_cputime cputime; + + thread_group_cputime(p, &cputime); + cputime_adjust(&cputime, &p->signal->prev_cputime, ut, st); +} +#endif /* !CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */ + +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN +static unsigned long long vtime_delta(struct task_struct *tsk) +{ + unsigned long long clock; + + clock = local_clock(); + if (clock < tsk->vtime_snap) + return 0; + + return clock - tsk->vtime_snap; +} + +static cputime_t get_vtime_delta(struct task_struct *tsk) +{ + unsigned long long delta = vtime_delta(tsk); + + WARN_ON_ONCE(tsk->vtime_snap_whence == VTIME_SLEEPING); + tsk->vtime_snap += delta; + + /* CHECKME: always safe to convert nsecs to cputime? */ + return nsecs_to_cputime(delta); +} + +static void __vtime_account_system(struct task_struct *tsk) +{ + cputime_t delta_cpu = get_vtime_delta(tsk); + + account_system_time(tsk, irq_count(), delta_cpu, cputime_to_scaled(delta_cpu)); +} + +void vtime_account_system(struct task_struct *tsk) +{ + raw_spin_lock(&tsk->vtime_lock); + write_seqcount_begin(&tsk->vtime_seq); + __vtime_account_system(tsk); + write_seqcount_end(&tsk->vtime_seq); + raw_spin_unlock(&tsk->vtime_lock); +} + +void vtime_gen_account_irq_exit(struct task_struct *tsk) +{ + raw_spin_lock(&tsk->vtime_lock); + write_seqcount_begin(&tsk->vtime_seq); + __vtime_account_system(tsk); + if (context_tracking_in_user()) + tsk->vtime_snap_whence = VTIME_USER; + write_seqcount_end(&tsk->vtime_seq); + raw_spin_unlock(&tsk->vtime_lock); +} + +void vtime_account_user(struct task_struct *tsk) +{ + cputime_t delta_cpu; + + raw_spin_lock(&tsk->vtime_lock); + write_seqcount_begin(&tsk->vtime_seq); + delta_cpu = get_vtime_delta(tsk); + tsk->vtime_snap_whence = VTIME_SYS; + account_user_time(tsk, delta_cpu, cputime_to_scaled(delta_cpu)); + write_seqcount_end(&tsk->vtime_seq); + raw_spin_unlock(&tsk->vtime_lock); +} + +void vtime_user_enter(struct task_struct *tsk) +{ + raw_spin_lock(&tsk->vtime_lock); + write_seqcount_begin(&tsk->vtime_seq); + __vtime_account_system(tsk); + tsk->vtime_snap_whence = VTIME_USER; + write_seqcount_end(&tsk->vtime_seq); + raw_spin_unlock(&tsk->vtime_lock); +} + +void vtime_guest_enter(struct task_struct *tsk) +{ + /* + * The flags must be updated under the lock with + * the vtime_snap flush and update. + * That enforces a right ordering and update sequence + * synchronization against the reader (task_gtime()) + * that can thus safely catch up with a tickless delta. + */ + raw_spin_lock(&tsk->vtime_lock); + write_seqcount_begin(&tsk->vtime_seq); + __vtime_account_system(tsk); + current->flags |= PF_VCPU; + write_seqcount_end(&tsk->vtime_seq); + raw_spin_unlock(&tsk->vtime_lock); +} +EXPORT_SYMBOL_GPL(vtime_guest_enter); + +void vtime_guest_exit(struct task_struct *tsk) +{ + raw_spin_lock(&tsk->vtime_lock); + write_seqcount_begin(&tsk->vtime_seq); + __vtime_account_system(tsk); + current->flags &= ~PF_VCPU; + write_seqcount_end(&tsk->vtime_seq); + raw_spin_unlock(&tsk->vtime_lock); +} +EXPORT_SYMBOL_GPL(vtime_guest_exit); + +void vtime_account_idle(struct task_struct *tsk) +{ + cputime_t delta_cpu = get_vtime_delta(tsk); + + account_idle_time(delta_cpu); +} + +void arch_vtime_task_switch(struct task_struct *prev) +{ + raw_spin_lock(&prev->vtime_lock); + write_seqcount_begin(&prev->vtime_seq); + prev->vtime_snap_whence = VTIME_SLEEPING; + write_seqcount_end(&prev->vtime_seq); + raw_spin_unlock(&prev->vtime_lock); + + raw_spin_lock(¤t->vtime_lock); + write_seqcount_begin(¤t->vtime_seq); + current->vtime_snap_whence = VTIME_SYS; + current->vtime_snap = sched_clock_cpu(smp_processor_id()); + write_seqcount_end(¤t->vtime_seq); + raw_spin_unlock(¤t->vtime_lock); +} + +void vtime_init_idle(struct task_struct *t, int cpu) +{ + unsigned long flags; + + raw_spin_lock_irqsave(&t->vtime_lock, flags); + write_seqcount_begin(&t->vtime_seq); + t->vtime_snap_whence = VTIME_SYS; + t->vtime_snap = sched_clock_cpu(cpu); + write_seqcount_end(&t->vtime_seq); + raw_spin_unlock_irqrestore(&t->vtime_lock, flags); +} + +cputime_t task_gtime(struct task_struct *t) +{ + unsigned int seq; + cputime_t gtime; + + do { + seq = read_seqcount_begin(&t->vtime_seq); + + gtime = t->gtime; + if (t->flags & PF_VCPU) + gtime += vtime_delta(t); + + } while (read_seqcount_retry(&t->vtime_seq, seq)); + + return gtime; +} + +/* + * Fetch cputime raw values from fields of task_struct and + * add up the pending nohz execution time since the last + * cputime snapshot. + */ +static void +fetch_task_cputime(struct task_struct *t, + cputime_t *u_dst, cputime_t *s_dst, + cputime_t *u_src, cputime_t *s_src, + cputime_t *udelta, cputime_t *sdelta) +{ + unsigned int seq; + unsigned long long delta; + + do { + *udelta = 0; + *sdelta = 0; + + seq = read_seqcount_begin(&t->vtime_seq); + + if (u_dst) + *u_dst = *u_src; + if (s_dst) + *s_dst = *s_src; + + /* Task is sleeping, nothing to add */ + if (t->vtime_snap_whence == VTIME_SLEEPING || + is_idle_task(t)) + continue; + + delta = vtime_delta(t); + + /* + * Task runs either in user or kernel space, add pending nohz time to + * the right place. + */ + if (t->vtime_snap_whence == VTIME_USER || t->flags & PF_VCPU) { + *udelta = delta; + } else { + if (t->vtime_snap_whence == VTIME_SYS) + *sdelta = delta; + } + } while (read_seqcount_retry(&t->vtime_seq, seq)); +} + + +void task_cputime(struct task_struct *t, cputime_t *utime, cputime_t *stime) +{ + cputime_t udelta, sdelta; + + fetch_task_cputime(t, utime, stime, &t->utime, + &t->stime, &udelta, &sdelta); + if (utime) + *utime += udelta; + if (stime) + *stime += sdelta; +} + +void task_cputime_scaled(struct task_struct *t, + cputime_t *utimescaled, cputime_t *stimescaled) +{ + cputime_t udelta, sdelta; + + fetch_task_cputime(t, utimescaled, stimescaled, + &t->utimescaled, &t->stimescaled, &udelta, &sdelta); + if (utimescaled) + *utimescaled += cputime_to_scaled(udelta); + if (stimescaled) + *stimescaled += cputime_to_scaled(sdelta); +} +#endif /* CONFIG_VIRT_CPU_ACCOUNTING_GEN */ diff --git a/kernel/kernel/sched/deadline.c b/kernel/kernel/sched/deadline.c new file mode 100644 index 000000000..0c261c511 --- /dev/null +++ b/kernel/kernel/sched/deadline.c @@ -0,0 +1,1819 @@ +/* + * Deadline Scheduling Class (SCHED_DEADLINE) + * + * Earliest Deadline First (EDF) + Constant Bandwidth Server (CBS). + * + * Tasks that periodically executes their instances for less than their + * runtime won't miss any of their deadlines. + * Tasks that are not periodic or sporadic or that tries to execute more + * than their reserved bandwidth will be slowed down (and may potentially + * miss some of their deadlines), and won't affect any other task. + * + * Copyright (C) 2012 Dario Faggioli , + * Juri Lelli , + * Michael Trimarchi , + * Fabio Checconi + */ +#include "sched.h" + +#include + +struct dl_bandwidth def_dl_bandwidth; + +static inline struct task_struct *dl_task_of(struct sched_dl_entity *dl_se) +{ + return container_of(dl_se, struct task_struct, dl); +} + +static inline struct rq *rq_of_dl_rq(struct dl_rq *dl_rq) +{ + return container_of(dl_rq, struct rq, dl); +} + +static inline struct dl_rq *dl_rq_of_se(struct sched_dl_entity *dl_se) +{ + struct task_struct *p = dl_task_of(dl_se); + struct rq *rq = task_rq(p); + + return &rq->dl; +} + +static inline int on_dl_rq(struct sched_dl_entity *dl_se) +{ + return !RB_EMPTY_NODE(&dl_se->rb_node); +} + +static inline int is_leftmost(struct task_struct *p, struct dl_rq *dl_rq) +{ + struct sched_dl_entity *dl_se = &p->dl; + + return dl_rq->rb_leftmost == &dl_se->rb_node; +} + +void init_dl_bandwidth(struct dl_bandwidth *dl_b, u64 period, u64 runtime) +{ + raw_spin_lock_init(&dl_b->dl_runtime_lock); + dl_b->dl_period = period; + dl_b->dl_runtime = runtime; +} + +void init_dl_bw(struct dl_bw *dl_b) +{ + raw_spin_lock_init(&dl_b->lock); + raw_spin_lock(&def_dl_bandwidth.dl_runtime_lock); + if (global_rt_runtime() == RUNTIME_INF) + dl_b->bw = -1; + else + dl_b->bw = to_ratio(global_rt_period(), global_rt_runtime()); + raw_spin_unlock(&def_dl_bandwidth.dl_runtime_lock); + dl_b->total_bw = 0; +} + +void init_dl_rq(struct dl_rq *dl_rq) +{ + dl_rq->rb_root = RB_ROOT; + +#ifdef CONFIG_SMP + /* zero means no -deadline tasks */ + dl_rq->earliest_dl.curr = dl_rq->earliest_dl.next = 0; + + dl_rq->dl_nr_migratory = 0; + dl_rq->overloaded = 0; + dl_rq->pushable_dl_tasks_root = RB_ROOT; +#else + init_dl_bw(&dl_rq->dl_bw); +#endif +} + +#ifdef CONFIG_SMP + +static inline int dl_overloaded(struct rq *rq) +{ + return atomic_read(&rq->rd->dlo_count); +} + +static inline void dl_set_overload(struct rq *rq) +{ + if (!rq->online) + return; + + cpumask_set_cpu(rq->cpu, rq->rd->dlo_mask); + /* + * Must be visible before the overload count is + * set (as in sched_rt.c). + * + * Matched by the barrier in pull_dl_task(). + */ + smp_wmb(); + atomic_inc(&rq->rd->dlo_count); +} + +static inline void dl_clear_overload(struct rq *rq) +{ + if (!rq->online) + return; + + atomic_dec(&rq->rd->dlo_count); + cpumask_clear_cpu(rq->cpu, rq->rd->dlo_mask); +} + +static void update_dl_migration(struct dl_rq *dl_rq) +{ + if (dl_rq->dl_nr_migratory && dl_rq->dl_nr_running > 1) { + if (!dl_rq->overloaded) { + dl_set_overload(rq_of_dl_rq(dl_rq)); + dl_rq->overloaded = 1; + } + } else if (dl_rq->overloaded) { + dl_clear_overload(rq_of_dl_rq(dl_rq)); + dl_rq->overloaded = 0; + } +} + +static void inc_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq) +{ + struct task_struct *p = dl_task_of(dl_se); + + if (p->nr_cpus_allowed > 1) + dl_rq->dl_nr_migratory++; + + update_dl_migration(dl_rq); +} + +static void dec_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq) +{ + struct task_struct *p = dl_task_of(dl_se); + + if (p->nr_cpus_allowed > 1) + dl_rq->dl_nr_migratory--; + + update_dl_migration(dl_rq); +} + +/* + * The list of pushable -deadline task is not a plist, like in + * sched_rt.c, it is an rb-tree with tasks ordered by deadline. + */ +static void enqueue_pushable_dl_task(struct rq *rq, struct task_struct *p) +{ + struct dl_rq *dl_rq = &rq->dl; + struct rb_node **link = &dl_rq->pushable_dl_tasks_root.rb_node; + struct rb_node *parent = NULL; + struct task_struct *entry; + int leftmost = 1; + + BUG_ON(!RB_EMPTY_NODE(&p->pushable_dl_tasks)); + + while (*link) { + parent = *link; + entry = rb_entry(parent, struct task_struct, + pushable_dl_tasks); + if (dl_entity_preempt(&p->dl, &entry->dl)) + link = &parent->rb_left; + else { + link = &parent->rb_right; + leftmost = 0; + } + } + + if (leftmost) + dl_rq->pushable_dl_tasks_leftmost = &p->pushable_dl_tasks; + + rb_link_node(&p->pushable_dl_tasks, parent, link); + rb_insert_color(&p->pushable_dl_tasks, &dl_rq->pushable_dl_tasks_root); +} + +static void dequeue_pushable_dl_task(struct rq *rq, struct task_struct *p) +{ + struct dl_rq *dl_rq = &rq->dl; + + if (RB_EMPTY_NODE(&p->pushable_dl_tasks)) + return; + + if (dl_rq->pushable_dl_tasks_leftmost == &p->pushable_dl_tasks) { + struct rb_node *next_node; + + next_node = rb_next(&p->pushable_dl_tasks); + dl_rq->pushable_dl_tasks_leftmost = next_node; + } + + rb_erase(&p->pushable_dl_tasks, &dl_rq->pushable_dl_tasks_root); + RB_CLEAR_NODE(&p->pushable_dl_tasks); +} + +static inline int has_pushable_dl_tasks(struct rq *rq) +{ + return !RB_EMPTY_ROOT(&rq->dl.pushable_dl_tasks_root); +} + +static int push_dl_task(struct rq *rq); + +static inline bool need_pull_dl_task(struct rq *rq, struct task_struct *prev) +{ + return dl_task(prev); +} + +static inline void set_post_schedule(struct rq *rq) +{ + rq->post_schedule = has_pushable_dl_tasks(rq); +} + +static struct rq *find_lock_later_rq(struct task_struct *task, struct rq *rq); + +static void dl_task_offline_migration(struct rq *rq, struct task_struct *p) +{ + struct rq *later_rq = NULL; + bool fallback = false; + + later_rq = find_lock_later_rq(p, rq); + + if (!later_rq) { + int cpu; + + /* + * If we cannot preempt any rq, fall back to pick any + * online cpu. + */ + fallback = true; + cpu = cpumask_any_and(cpu_active_mask, tsk_cpus_allowed(p)); + if (cpu >= nr_cpu_ids) { + /* + * Fail to find any suitable cpu. + * The task will never come back! + */ + BUG_ON(dl_bandwidth_enabled()); + + /* + * If admission control is disabled we + * try a little harder to let the task + * run. + */ + cpu = cpumask_any(cpu_active_mask); + } + later_rq = cpu_rq(cpu); + double_lock_balance(rq, later_rq); + } + + deactivate_task(rq, p, 0); + set_task_cpu(p, later_rq->cpu); + activate_task(later_rq, p, ENQUEUE_REPLENISH); + + if (!fallback) + resched_curr(later_rq); + + double_unlock_balance(rq, later_rq); +} + +#else + +static inline +void enqueue_pushable_dl_task(struct rq *rq, struct task_struct *p) +{ +} + +static inline +void dequeue_pushable_dl_task(struct rq *rq, struct task_struct *p) +{ +} + +static inline +void inc_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq) +{ +} + +static inline +void dec_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq) +{ +} + +static inline bool need_pull_dl_task(struct rq *rq, struct task_struct *prev) +{ + return false; +} + +static inline int pull_dl_task(struct rq *rq) +{ + return 0; +} + +static inline void set_post_schedule(struct rq *rq) +{ +} +#endif /* CONFIG_SMP */ + +static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags); +static void __dequeue_task_dl(struct rq *rq, struct task_struct *p, int flags); +static void check_preempt_curr_dl(struct rq *rq, struct task_struct *p, + int flags); + +/* + * We are being explicitly informed that a new instance is starting, + * and this means that: + * - the absolute deadline of the entity has to be placed at + * current time + relative deadline; + * - the runtime of the entity has to be set to the maximum value. + * + * The capability of specifying such event is useful whenever a -deadline + * entity wants to (try to!) synchronize its behaviour with the scheduler's + * one, and to (try to!) reconcile itself with its own scheduling + * parameters. + */ +static inline void setup_new_dl_entity(struct sched_dl_entity *dl_se, + struct sched_dl_entity *pi_se) +{ + struct dl_rq *dl_rq = dl_rq_of_se(dl_se); + struct rq *rq = rq_of_dl_rq(dl_rq); + + WARN_ON(!dl_se->dl_new || dl_se->dl_throttled); + + /* + * We use the regular wall clock time to set deadlines in the + * future; in fact, we must consider execution overheads (time + * spent on hardirq context, etc.). + */ + dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline; + dl_se->runtime = pi_se->dl_runtime; + dl_se->dl_new = 0; +} + +/* + * Pure Earliest Deadline First (EDF) scheduling does not deal with the + * possibility of a entity lasting more than what it declared, and thus + * exhausting its runtime. + * + * Here we are interested in making runtime overrun possible, but we do + * not want a entity which is misbehaving to affect the scheduling of all + * other entities. + * Therefore, a budgeting strategy called Constant Bandwidth Server (CBS) + * is used, in order to confine each entity within its own bandwidth. + * + * This function deals exactly with that, and ensures that when the runtime + * of a entity is replenished, its deadline is also postponed. That ensures + * the overrunning entity can't interfere with other entity in the system and + * can't make them miss their deadlines. Reasons why this kind of overruns + * could happen are, typically, a entity voluntarily trying to overcome its + * runtime, or it just underestimated it during sched_setattr(). + */ +static void replenish_dl_entity(struct sched_dl_entity *dl_se, + struct sched_dl_entity *pi_se) +{ + struct dl_rq *dl_rq = dl_rq_of_se(dl_se); + struct rq *rq = rq_of_dl_rq(dl_rq); + + BUG_ON(pi_se->dl_runtime <= 0); + + /* + * This could be the case for a !-dl task that is boosted. + * Just go with full inherited parameters. + */ + if (dl_se->dl_deadline == 0) { + dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline; + dl_se->runtime = pi_se->dl_runtime; + } + + /* + * We keep moving the deadline away until we get some + * available runtime for the entity. This ensures correct + * handling of situations where the runtime overrun is + * arbitrary large. + */ + while (dl_se->runtime <= 0) { + dl_se->deadline += pi_se->dl_period; + dl_se->runtime += pi_se->dl_runtime; + } + + /* + * At this point, the deadline really should be "in + * the future" with respect to rq->clock. If it's + * not, we are, for some reason, lagging too much! + * Anyway, after having warn userspace abut that, + * we still try to keep the things running by + * resetting the deadline and the budget of the + * entity. + */ + if (dl_time_before(dl_se->deadline, rq_clock(rq))) { + printk_deferred_once("sched: DL replenish lagged to much\n"); + dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline; + dl_se->runtime = pi_se->dl_runtime; + } + + if (dl_se->dl_yielded) + dl_se->dl_yielded = 0; + if (dl_se->dl_throttled) + dl_se->dl_throttled = 0; +} + +/* + * Here we check if --at time t-- an entity (which is probably being + * [re]activated or, in general, enqueued) can use its remaining runtime + * and its current deadline _without_ exceeding the bandwidth it is + * assigned (function returns true if it can't). We are in fact applying + * one of the CBS rules: when a task wakes up, if the residual runtime + * over residual deadline fits within the allocated bandwidth, then we + * can keep the current (absolute) deadline and residual budget without + * disrupting the schedulability of the system. Otherwise, we should + * refill the runtime and set the deadline a period in the future, + * because keeping the current (absolute) deadline of the task would + * result in breaking guarantees promised to other tasks (refer to + * Documentation/scheduler/sched-deadline.txt for more informations). + * + * This function returns true if: + * + * runtime / (deadline - t) > dl_runtime / dl_period , + * + * IOW we can't recycle current parameters. + * + * Notice that the bandwidth check is done against the period. For + * task with deadline equal to period this is the same of using + * dl_deadline instead of dl_period in the equation above. + */ +static bool dl_entity_overflow(struct sched_dl_entity *dl_se, + struct sched_dl_entity *pi_se, u64 t) +{ + u64 left, right; + + /* + * left and right are the two sides of the equation above, + * after a bit of shuffling to use multiplications instead + * of divisions. + * + * Note that none of the time values involved in the two + * multiplications are absolute: dl_deadline and dl_runtime + * are the relative deadline and the maximum runtime of each + * instance, runtime is the runtime left for the last instance + * and (deadline - t), since t is rq->clock, is the time left + * to the (absolute) deadline. Even if overflowing the u64 type + * is very unlikely to occur in both cases, here we scale down + * as we want to avoid that risk at all. Scaling down by 10 + * means that we reduce granularity to 1us. We are fine with it, + * since this is only a true/false check and, anyway, thinking + * of anything below microseconds resolution is actually fiction + * (but still we want to give the user that illusion >;). + */ + left = (pi_se->dl_period >> DL_SCALE) * (dl_se->runtime >> DL_SCALE); + right = ((dl_se->deadline - t) >> DL_SCALE) * + (pi_se->dl_runtime >> DL_SCALE); + + return dl_time_before(right, left); +} + +/* + * When a -deadline entity is queued back on the runqueue, its runtime and + * deadline might need updating. + * + * The policy here is that we update the deadline of the entity only if: + * - the current deadline is in the past, + * - using the remaining runtime with the current deadline would make + * the entity exceed its bandwidth. + */ +static void update_dl_entity(struct sched_dl_entity *dl_se, + struct sched_dl_entity *pi_se) +{ + struct dl_rq *dl_rq = dl_rq_of_se(dl_se); + struct rq *rq = rq_of_dl_rq(dl_rq); + + /* + * The arrival of a new instance needs special treatment, i.e., + * the actual scheduling parameters have to be "renewed". + */ + if (dl_se->dl_new) { + setup_new_dl_entity(dl_se, pi_se); + return; + } + + if (dl_time_before(dl_se->deadline, rq_clock(rq)) || + dl_entity_overflow(dl_se, pi_se, rq_clock(rq))) { + dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline; + dl_se->runtime = pi_se->dl_runtime; + } +} + +/* + * If the entity depleted all its runtime, and if we want it to sleep + * while waiting for some new execution time to become available, we + * set the bandwidth enforcement timer to the replenishment instant + * and try to activate it. + * + * Notice that it is important for the caller to know if the timer + * actually started or not (i.e., the replenishment instant is in + * the future or in the past). + */ +static int start_dl_timer(struct sched_dl_entity *dl_se, bool boosted) +{ + struct dl_rq *dl_rq = dl_rq_of_se(dl_se); + struct rq *rq = rq_of_dl_rq(dl_rq); + ktime_t now, act; + ktime_t soft, hard; + unsigned long range; + s64 delta; + + if (boosted) + return 0; + /* + * We want the timer to fire at the deadline, but considering + * that it is actually coming from rq->clock and not from + * hrtimer's time base reading. + */ + act = ns_to_ktime(dl_se->deadline); + now = hrtimer_cb_get_time(&dl_se->dl_timer); + delta = ktime_to_ns(now) - rq_clock(rq); + act = ktime_add_ns(act, delta); + + /* + * If the expiry time already passed, e.g., because the value + * chosen as the deadline is too small, don't even try to + * start the timer in the past! + */ + if (ktime_us_delta(act, now) < 0) + return 0; + + hrtimer_set_expires(&dl_se->dl_timer, act); + + soft = hrtimer_get_softexpires(&dl_se->dl_timer); + hard = hrtimer_get_expires(&dl_se->dl_timer); + range = ktime_to_ns(ktime_sub(hard, soft)); + __hrtimer_start_range_ns(&dl_se->dl_timer, soft, + range, HRTIMER_MODE_ABS, 0); + + return hrtimer_active(&dl_se->dl_timer); +} + +/* + * This is the bandwidth enforcement timer callback. If here, we know + * a task is not on its dl_rq, since the fact that the timer was running + * means the task is throttled and needs a runtime replenishment. + * + * However, what we actually do depends on the fact the task is active, + * (it is on its rq) or has been removed from there by a call to + * dequeue_task_dl(). In the former case we must issue the runtime + * replenishment and add the task back to the dl_rq; in the latter, we just + * do nothing but clearing dl_throttled, so that runtime and deadline + * updating (and the queueing back to dl_rq) will be done by the + * next call to enqueue_task_dl(). + */ +static enum hrtimer_restart dl_task_timer(struct hrtimer *timer) +{ + struct sched_dl_entity *dl_se = container_of(timer, + struct sched_dl_entity, + dl_timer); + struct task_struct *p = dl_task_of(dl_se); + unsigned long flags; + struct rq *rq; + + rq = task_rq_lock(p, &flags); + + /* + * We need to take care of several possible races here: + * + * - the task might have changed its scheduling policy + * to something different than SCHED_DEADLINE + * - the task might have changed its reservation parameters + * (through sched_setattr()) + * - the task might have been boosted by someone else and + * might be in the boosting/deboosting path + * + * In all this cases we bail out, as the task is already + * in the runqueue or is going to be enqueued back anyway. + */ + if (!dl_task(p) || dl_se->dl_new || + dl_se->dl_boosted || !dl_se->dl_throttled) + goto unlock; + + sched_clock_tick(); + update_rq_clock(rq); + +#ifdef CONFIG_SMP + /* + * If we find that the rq the task was on is no longer + * available, we need to select a new rq. + */ + if (unlikely(!rq->online)) { + dl_task_offline_migration(rq, p); + goto unlock; + } +#endif + + /* + * If the throttle happened during sched-out; like: + * + * schedule() + * deactivate_task() + * dequeue_task_dl() + * update_curr_dl() + * start_dl_timer() + * __dequeue_task_dl() + * prev->on_rq = 0; + * + * We can be both throttled and !queued. Replenish the counter + * but do not enqueue -- wait for our wakeup to do that. + */ + if (!task_on_rq_queued(p)) { + replenish_dl_entity(dl_se, dl_se); + goto unlock; + } + + enqueue_task_dl(rq, p, ENQUEUE_REPLENISH); + if (dl_task(rq->curr)) + check_preempt_curr_dl(rq, p, 0); + else + resched_curr(rq); +#ifdef CONFIG_SMP + /* + * Queueing this task back might have overloaded rq, + * check if we need to kick someone away. + */ + if (has_pushable_dl_tasks(rq)) + push_dl_task(rq); +#endif +unlock: + task_rq_unlock(rq, p, &flags); + + return HRTIMER_NORESTART; +} + +void init_dl_task_timer(struct sched_dl_entity *dl_se) +{ + struct hrtimer *timer = &dl_se->dl_timer; + + hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + timer->function = dl_task_timer; + timer->irqsafe = 1; +} + +static +int dl_runtime_exceeded(struct rq *rq, struct sched_dl_entity *dl_se) +{ + return (dl_se->runtime <= 0); +} + +extern bool sched_rt_bandwidth_account(struct rt_rq *rt_rq); + +/* + * Update the current task's runtime statistics (provided it is still + * a -deadline task and has not been removed from the dl_rq). + */ +static void update_curr_dl(struct rq *rq) +{ + struct task_struct *curr = rq->curr; + struct sched_dl_entity *dl_se = &curr->dl; + u64 delta_exec; + + if (!dl_task(curr) || !on_dl_rq(dl_se)) + return; + + /* + * Consumed budget is computed considering the time as + * observed by schedulable tasks (excluding time spent + * in hardirq context, etc.). Deadlines are instead + * computed using hard walltime. This seems to be the more + * natural solution, but the full ramifications of this + * approach need further study. + */ + delta_exec = rq_clock_task(rq) - curr->se.exec_start; + if (unlikely((s64)delta_exec <= 0)) + return; + + schedstat_set(curr->se.statistics.exec_max, + max(curr->se.statistics.exec_max, delta_exec)); + + curr->se.sum_exec_runtime += delta_exec; + account_group_exec_runtime(curr, delta_exec); + + curr->se.exec_start = rq_clock_task(rq); + cpuacct_charge(curr, delta_exec); + + sched_rt_avg_update(rq, delta_exec); + + dl_se->runtime -= dl_se->dl_yielded ? 0 : delta_exec; + if (dl_runtime_exceeded(rq, dl_se)) { + dl_se->dl_throttled = 1; + __dequeue_task_dl(rq, curr, 0); + if (unlikely(!start_dl_timer(dl_se, curr->dl.dl_boosted))) + enqueue_task_dl(rq, curr, ENQUEUE_REPLENISH); + + if (!is_leftmost(curr, &rq->dl)) + resched_curr(rq); + } + + /* + * Because -- for now -- we share the rt bandwidth, we need to + * account our runtime there too, otherwise actual rt tasks + * would be able to exceed the shared quota. + * + * Account to the root rt group for now. + * + * The solution we're working towards is having the RT groups scheduled + * using deadline servers -- however there's a few nasties to figure + * out before that can happen. + */ + if (rt_bandwidth_enabled()) { + struct rt_rq *rt_rq = &rq->rt; + + raw_spin_lock(&rt_rq->rt_runtime_lock); + /* + * We'll let actual RT tasks worry about the overflow here, we + * have our own CBS to keep us inline; only account when RT + * bandwidth is relevant. + */ + if (sched_rt_bandwidth_account(rt_rq)) + rt_rq->rt_time += delta_exec; + raw_spin_unlock(&rt_rq->rt_runtime_lock); + } +} + +#ifdef CONFIG_SMP + +static struct task_struct *pick_next_earliest_dl_task(struct rq *rq, int cpu); + +static inline u64 next_deadline(struct rq *rq) +{ + struct task_struct *next = pick_next_earliest_dl_task(rq, rq->cpu); + + if (next && dl_prio(next->prio)) + return next->dl.deadline; + else + return 0; +} + +static void inc_dl_deadline(struct dl_rq *dl_rq, u64 deadline) +{ + struct rq *rq = rq_of_dl_rq(dl_rq); + + if (dl_rq->earliest_dl.curr == 0 || + dl_time_before(deadline, dl_rq->earliest_dl.curr)) { + /* + * If the dl_rq had no -deadline tasks, or if the new task + * has shorter deadline than the current one on dl_rq, we + * know that the previous earliest becomes our next earliest, + * as the new task becomes the earliest itself. + */ + dl_rq->earliest_dl.next = dl_rq->earliest_dl.curr; + dl_rq->earliest_dl.curr = deadline; + cpudl_set(&rq->rd->cpudl, rq->cpu, deadline, 1); + } else if (dl_rq->earliest_dl.next == 0 || + dl_time_before(deadline, dl_rq->earliest_dl.next)) { + /* + * On the other hand, if the new -deadline task has a + * a later deadline than the earliest one on dl_rq, but + * it is earlier than the next (if any), we must + * recompute the next-earliest. + */ + dl_rq->earliest_dl.next = next_deadline(rq); + } +} + +static void dec_dl_deadline(struct dl_rq *dl_rq, u64 deadline) +{ + struct rq *rq = rq_of_dl_rq(dl_rq); + + /* + * Since we may have removed our earliest (and/or next earliest) + * task we must recompute them. + */ + if (!dl_rq->dl_nr_running) { + dl_rq->earliest_dl.curr = 0; + dl_rq->earliest_dl.next = 0; + cpudl_set(&rq->rd->cpudl, rq->cpu, 0, 0); + } else { + struct rb_node *leftmost = dl_rq->rb_leftmost; + struct sched_dl_entity *entry; + + entry = rb_entry(leftmost, struct sched_dl_entity, rb_node); + dl_rq->earliest_dl.curr = entry->deadline; + dl_rq->earliest_dl.next = next_deadline(rq); + cpudl_set(&rq->rd->cpudl, rq->cpu, entry->deadline, 1); + } +} + +#else + +static inline void inc_dl_deadline(struct dl_rq *dl_rq, u64 deadline) {} +static inline void dec_dl_deadline(struct dl_rq *dl_rq, u64 deadline) {} + +#endif /* CONFIG_SMP */ + +static inline +void inc_dl_tasks(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq) +{ + int prio = dl_task_of(dl_se)->prio; + u64 deadline = dl_se->deadline; + + WARN_ON(!dl_prio(prio)); + dl_rq->dl_nr_running++; + add_nr_running(rq_of_dl_rq(dl_rq), 1); + + inc_dl_deadline(dl_rq, deadline); + inc_dl_migration(dl_se, dl_rq); +} + +static inline +void dec_dl_tasks(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq) +{ + int prio = dl_task_of(dl_se)->prio; + + WARN_ON(!dl_prio(prio)); + WARN_ON(!dl_rq->dl_nr_running); + dl_rq->dl_nr_running--; + sub_nr_running(rq_of_dl_rq(dl_rq), 1); + + dec_dl_deadline(dl_rq, dl_se->deadline); + dec_dl_migration(dl_se, dl_rq); +} + +static void __enqueue_dl_entity(struct sched_dl_entity *dl_se) +{ + struct dl_rq *dl_rq = dl_rq_of_se(dl_se); + struct rb_node **link = &dl_rq->rb_root.rb_node; + struct rb_node *parent = NULL; + struct sched_dl_entity *entry; + int leftmost = 1; + + BUG_ON(!RB_EMPTY_NODE(&dl_se->rb_node)); + + while (*link) { + parent = *link; + entry = rb_entry(parent, struct sched_dl_entity, rb_node); + if (dl_time_before(dl_se->deadline, entry->deadline)) + link = &parent->rb_left; + else { + link = &parent->rb_right; + leftmost = 0; + } + } + + if (leftmost) + dl_rq->rb_leftmost = &dl_se->rb_node; + + rb_link_node(&dl_se->rb_node, parent, link); + rb_insert_color(&dl_se->rb_node, &dl_rq->rb_root); + + inc_dl_tasks(dl_se, dl_rq); +} + +static void __dequeue_dl_entity(struct sched_dl_entity *dl_se) +{ + struct dl_rq *dl_rq = dl_rq_of_se(dl_se); + + if (RB_EMPTY_NODE(&dl_se->rb_node)) + return; + + if (dl_rq->rb_leftmost == &dl_se->rb_node) { + struct rb_node *next_node; + + next_node = rb_next(&dl_se->rb_node); + dl_rq->rb_leftmost = next_node; + } + + rb_erase(&dl_se->rb_node, &dl_rq->rb_root); + RB_CLEAR_NODE(&dl_se->rb_node); + + dec_dl_tasks(dl_se, dl_rq); +} + +static void +enqueue_dl_entity(struct sched_dl_entity *dl_se, + struct sched_dl_entity *pi_se, int flags) +{ + BUG_ON(on_dl_rq(dl_se)); + + /* + * If this is a wakeup or a new instance, the scheduling + * parameters of the task might need updating. Otherwise, + * we want a replenishment of its runtime. + */ + if (dl_se->dl_new || flags & ENQUEUE_WAKEUP) + update_dl_entity(dl_se, pi_se); + else if (flags & ENQUEUE_REPLENISH) + replenish_dl_entity(dl_se, pi_se); + + __enqueue_dl_entity(dl_se); +} + +static void dequeue_dl_entity(struct sched_dl_entity *dl_se) +{ + __dequeue_dl_entity(dl_se); +} + +static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags) +{ + struct task_struct *pi_task = rt_mutex_get_top_task(p); + struct sched_dl_entity *pi_se = &p->dl; + + /* + * Use the scheduling parameters of the top pi-waiter + * task if we have one and its (relative) deadline is + * smaller than our one... OTW we keep our runtime and + * deadline. + */ + if (pi_task && p->dl.dl_boosted && dl_prio(pi_task->normal_prio)) { + pi_se = &pi_task->dl; + } else if (!dl_prio(p->normal_prio)) { + /* + * Special case in which we have a !SCHED_DEADLINE task + * that is going to be deboosted, but exceedes its + * runtime while doing so. No point in replenishing + * it, as it's going to return back to its original + * scheduling class after this. + */ + BUG_ON(!p->dl.dl_boosted || flags != ENQUEUE_REPLENISH); + return; + } + + /* + * If p is throttled, we do nothing. In fact, if it exhausted + * its budget it needs a replenishment and, since it now is on + * its rq, the bandwidth timer callback (which clearly has not + * run yet) will take care of this. + */ + if (p->dl.dl_throttled && !(flags & ENQUEUE_REPLENISH)) + return; + + enqueue_dl_entity(&p->dl, pi_se, flags); + + if (!task_current(rq, p) && p->nr_cpus_allowed > 1) + enqueue_pushable_dl_task(rq, p); +} + +static void __dequeue_task_dl(struct rq *rq, struct task_struct *p, int flags) +{ + dequeue_dl_entity(&p->dl); + dequeue_pushable_dl_task(rq, p); +} + +static void dequeue_task_dl(struct rq *rq, struct task_struct *p, int flags) +{ + update_curr_dl(rq); + __dequeue_task_dl(rq, p, flags); +} + +/* + * Yield task semantic for -deadline tasks is: + * + * get off from the CPU until our next instance, with + * a new runtime. This is of little use now, since we + * don't have a bandwidth reclaiming mechanism. Anyway, + * bandwidth reclaiming is planned for the future, and + * yield_task_dl will indicate that some spare budget + * is available for other task instances to use it. + */ +static void yield_task_dl(struct rq *rq) +{ + struct task_struct *p = rq->curr; + + /* + * We make the task go to sleep until its current deadline by + * forcing its runtime to zero. This way, update_curr_dl() stops + * it and the bandwidth timer will wake it up and will give it + * new scheduling parameters (thanks to dl_yielded=1). + */ + if (p->dl.runtime > 0) { + rq->curr->dl.dl_yielded = 1; + p->dl.runtime = 0; + } + update_rq_clock(rq); + update_curr_dl(rq); + /* + * Tell update_rq_clock() that we've just updated, + * so we don't do microscopic update in schedule() + * and double the fastpath cost. + */ + rq_clock_skip_update(rq, true); +} + +#ifdef CONFIG_SMP + +static int find_later_rq(struct task_struct *task); + +static int +select_task_rq_dl(struct task_struct *p, int cpu, int sd_flag, int flags) +{ + struct task_struct *curr; + struct rq *rq; + + if (sd_flag != SD_BALANCE_WAKE) + goto out; + + rq = cpu_rq(cpu); + + rcu_read_lock(); + curr = ACCESS_ONCE(rq->curr); /* unlocked access */ + + /* + * If we are dealing with a -deadline task, we must + * decide where to wake it up. + * If it has a later deadline and the current task + * on this rq can't move (provided the waking task + * can!) we prefer to send it somewhere else. On the + * other hand, if it has a shorter deadline, we + * try to make it stay here, it might be important. + */ + if (unlikely(dl_task(curr)) && + (curr->nr_cpus_allowed < 2 || + !dl_entity_preempt(&p->dl, &curr->dl)) && + (p->nr_cpus_allowed > 1)) { + int target = find_later_rq(p); + + if (target != -1) + cpu = target; + } + rcu_read_unlock(); + +out: + return cpu; +} + +static void check_preempt_equal_dl(struct rq *rq, struct task_struct *p) +{ + /* + * Current can't be migrated, useless to reschedule, + * let's hope p can move out. + */ + if (rq->curr->nr_cpus_allowed == 1 || + cpudl_find(&rq->rd->cpudl, rq->curr, NULL) == -1) + return; + + /* + * p is migratable, so let's not schedule it and + * see if it is pushed or pulled somewhere else. + */ + if (p->nr_cpus_allowed != 1 && + cpudl_find(&rq->rd->cpudl, p, NULL) != -1) + return; + + resched_curr(rq); +} + +static int pull_dl_task(struct rq *this_rq); + +#endif /* CONFIG_SMP */ + +/* + * Only called when both the current and waking task are -deadline + * tasks. + */ +static void check_preempt_curr_dl(struct rq *rq, struct task_struct *p, + int flags) +{ + if (dl_entity_preempt(&p->dl, &rq->curr->dl)) { + resched_curr(rq); + return; + } + +#ifdef CONFIG_SMP + /* + * In the unlikely case current and p have the same deadline + * let us try to decide what's the best thing to do... + */ + if ((p->dl.deadline == rq->curr->dl.deadline) && + !test_tsk_need_resched(rq->curr)) + check_preempt_equal_dl(rq, p); +#endif /* CONFIG_SMP */ +} + +#ifdef CONFIG_SCHED_HRTICK +static void start_hrtick_dl(struct rq *rq, struct task_struct *p) +{ + hrtick_start(rq, p->dl.runtime); +} +#else /* !CONFIG_SCHED_HRTICK */ +static void start_hrtick_dl(struct rq *rq, struct task_struct *p) +{ +} +#endif + +static struct sched_dl_entity *pick_next_dl_entity(struct rq *rq, + struct dl_rq *dl_rq) +{ + struct rb_node *left = dl_rq->rb_leftmost; + + if (!left) + return NULL; + + return rb_entry(left, struct sched_dl_entity, rb_node); +} + +struct task_struct *pick_next_task_dl(struct rq *rq, struct task_struct *prev) +{ + struct sched_dl_entity *dl_se; + struct task_struct *p; + struct dl_rq *dl_rq; + + dl_rq = &rq->dl; + + if (need_pull_dl_task(rq, prev)) { + pull_dl_task(rq); + /* + * pull_rt_task() can drop (and re-acquire) rq->lock; this + * means a stop task can slip in, in which case we need to + * re-start task selection. + */ + if (rq->stop && task_on_rq_queued(rq->stop)) + return RETRY_TASK; + } + + /* + * When prev is DL, we may throttle it in put_prev_task(). + * So, we update time before we check for dl_nr_running. + */ + if (prev->sched_class == &dl_sched_class) + update_curr_dl(rq); + + if (unlikely(!dl_rq->dl_nr_running)) + return NULL; + + put_prev_task(rq, prev); + + dl_se = pick_next_dl_entity(rq, dl_rq); + BUG_ON(!dl_se); + + p = dl_task_of(dl_se); + p->se.exec_start = rq_clock_task(rq); + + /* Running task will never be pushed. */ + dequeue_pushable_dl_task(rq, p); + + if (hrtick_enabled(rq)) + start_hrtick_dl(rq, p); + + set_post_schedule(rq); + + return p; +} + +static void put_prev_task_dl(struct rq *rq, struct task_struct *p) +{ + update_curr_dl(rq); + + if (on_dl_rq(&p->dl) && p->nr_cpus_allowed > 1) + enqueue_pushable_dl_task(rq, p); +} + +static void task_tick_dl(struct rq *rq, struct task_struct *p, int queued) +{ + update_curr_dl(rq); + + /* + * Even when we have runtime, update_curr_dl() might have resulted in us + * not being the leftmost task anymore. In that case NEED_RESCHED will + * be set and schedule() will start a new hrtick for the next task. + */ + if (hrtick_enabled(rq) && queued && p->dl.runtime > 0 && + is_leftmost(p, &rq->dl)) + start_hrtick_dl(rq, p); +} + +static void task_fork_dl(struct task_struct *p) +{ + /* + * SCHED_DEADLINE tasks cannot fork and this is achieved through + * sched_fork() + */ +} + +static void task_dead_dl(struct task_struct *p) +{ + struct hrtimer *timer = &p->dl.dl_timer; + struct dl_bw *dl_b = dl_bw_of(task_cpu(p)); + + /* + * Since we are TASK_DEAD we won't slip out of the domain! + */ + raw_spin_lock_irq(&dl_b->lock); + /* XXX we should retain the bw until 0-lag */ + dl_b->total_bw -= p->dl.dl_bw; + raw_spin_unlock_irq(&dl_b->lock); + + hrtimer_cancel(timer); +} + +static void set_curr_task_dl(struct rq *rq) +{ + struct task_struct *p = rq->curr; + + p->se.exec_start = rq_clock_task(rq); + + /* You can't push away the running task */ + dequeue_pushable_dl_task(rq, p); +} + +#ifdef CONFIG_SMP + +/* Only try algorithms three times */ +#define DL_MAX_TRIES 3 + +static int pick_dl_task(struct rq *rq, struct task_struct *p, int cpu) +{ + if (!task_running(rq, p) && + cpumask_test_cpu(cpu, tsk_cpus_allowed(p))) + return 1; + return 0; +} + +/* Returns the second earliest -deadline task, NULL otherwise */ +static struct task_struct *pick_next_earliest_dl_task(struct rq *rq, int cpu) +{ + struct rb_node *next_node = rq->dl.rb_leftmost; + struct sched_dl_entity *dl_se; + struct task_struct *p = NULL; + +next_node: + next_node = rb_next(next_node); + if (next_node) { + dl_se = rb_entry(next_node, struct sched_dl_entity, rb_node); + p = dl_task_of(dl_se); + + if (pick_dl_task(rq, p, cpu)) + return p; + + goto next_node; + } + + return NULL; +} + +static DEFINE_PER_CPU(cpumask_var_t, local_cpu_mask_dl); + +static int find_later_rq(struct task_struct *task) +{ + struct sched_domain *sd; + struct cpumask *later_mask = this_cpu_cpumask_var_ptr(local_cpu_mask_dl); + int this_cpu = smp_processor_id(); + int best_cpu, cpu = task_cpu(task); + + /* Make sure the mask is initialized first */ + if (unlikely(!later_mask)) + return -1; + + if (task->nr_cpus_allowed == 1) + return -1; + + /* + * We have to consider system topology and task affinity + * first, then we can look for a suitable cpu. + */ + best_cpu = cpudl_find(&task_rq(task)->rd->cpudl, + task, later_mask); + if (best_cpu == -1) + return -1; + + /* + * If we are here, some target has been found, + * the most suitable of which is cached in best_cpu. + * This is, among the runqueues where the current tasks + * have later deadlines than the task's one, the rq + * with the latest possible one. + * + * Now we check how well this matches with task's + * affinity and system topology. + * + * The last cpu where the task run is our first + * guess, since it is most likely cache-hot there. + */ + if (cpumask_test_cpu(cpu, later_mask)) + return cpu; + /* + * Check if this_cpu is to be skipped (i.e., it is + * not in the mask) or not. + */ + if (!cpumask_test_cpu(this_cpu, later_mask)) + this_cpu = -1; + + rcu_read_lock(); + for_each_domain(cpu, sd) { + if (sd->flags & SD_WAKE_AFFINE) { + + /* + * If possible, preempting this_cpu is + * cheaper than migrating. + */ + if (this_cpu != -1 && + cpumask_test_cpu(this_cpu, sched_domain_span(sd))) { + rcu_read_unlock(); + return this_cpu; + } + + /* + * Last chance: if best_cpu is valid and is + * in the mask, that becomes our choice. + */ + if (best_cpu < nr_cpu_ids && + cpumask_test_cpu(best_cpu, sched_domain_span(sd))) { + rcu_read_unlock(); + return best_cpu; + } + } + } + rcu_read_unlock(); + + /* + * At this point, all our guesses failed, we just return + * 'something', and let the caller sort the things out. + */ + if (this_cpu != -1) + return this_cpu; + + cpu = cpumask_any(later_mask); + if (cpu < nr_cpu_ids) + return cpu; + + return -1; +} + +/* Locks the rq it finds */ +static struct rq *find_lock_later_rq(struct task_struct *task, struct rq *rq) +{ + struct rq *later_rq = NULL; + int tries; + int cpu; + + for (tries = 0; tries < DL_MAX_TRIES; tries++) { + cpu = find_later_rq(task); + + if ((cpu == -1) || (cpu == rq->cpu)) + break; + + later_rq = cpu_rq(cpu); + + /* Retry if something changed. */ + if (double_lock_balance(rq, later_rq)) { + if (unlikely(task_rq(task) != rq || + !cpumask_test_cpu(later_rq->cpu, + &task->cpus_allowed) || + task_running(rq, task) || + !task_on_rq_queued(task))) { + double_unlock_balance(rq, later_rq); + later_rq = NULL; + break; + } + } + + /* + * If the rq we found has no -deadline task, or + * its earliest one has a later deadline than our + * task, the rq is a good one. + */ + if (!later_rq->dl.dl_nr_running || + dl_time_before(task->dl.deadline, + later_rq->dl.earliest_dl.curr)) + break; + + /* Otherwise we try again. */ + double_unlock_balance(rq, later_rq); + later_rq = NULL; + } + + return later_rq; +} + +static struct task_struct *pick_next_pushable_dl_task(struct rq *rq) +{ + struct task_struct *p; + + if (!has_pushable_dl_tasks(rq)) + return NULL; + + p = rb_entry(rq->dl.pushable_dl_tasks_leftmost, + struct task_struct, pushable_dl_tasks); + + BUG_ON(rq->cpu != task_cpu(p)); + BUG_ON(task_current(rq, p)); + BUG_ON(p->nr_cpus_allowed <= 1); + + BUG_ON(!task_on_rq_queued(p)); + BUG_ON(!dl_task(p)); + + return p; +} + +/* + * See if the non running -deadline tasks on this rq + * can be sent to some other CPU where they can preempt + * and start executing. + */ +static int push_dl_task(struct rq *rq) +{ + struct task_struct *next_task; + struct rq *later_rq; + int ret = 0; + + if (!rq->dl.overloaded) + return 0; + + next_task = pick_next_pushable_dl_task(rq); + if (!next_task) + return 0; + +retry: + if (unlikely(next_task == rq->curr)) { + WARN_ON(1); + return 0; + } + + /* + * If next_task preempts rq->curr, and rq->curr + * can move away, it makes sense to just reschedule + * without going further in pushing next_task. + */ + if (dl_task(rq->curr) && + dl_time_before(next_task->dl.deadline, rq->curr->dl.deadline) && + rq->curr->nr_cpus_allowed > 1) { + resched_curr(rq); + return 0; + } + + /* We might release rq lock */ + get_task_struct(next_task); + + /* Will lock the rq it'll find */ + later_rq = find_lock_later_rq(next_task, rq); + if (!later_rq) { + struct task_struct *task; + + /* + * We must check all this again, since + * find_lock_later_rq releases rq->lock and it is + * then possible that next_task has migrated. + */ + task = pick_next_pushable_dl_task(rq); + if (task_cpu(next_task) == rq->cpu && task == next_task) { + /* + * The task is still there. We don't try + * again, some other cpu will pull it when ready. + */ + goto out; + } + + if (!task) + /* No more tasks */ + goto out; + + put_task_struct(next_task); + next_task = task; + goto retry; + } + + deactivate_task(rq, next_task, 0); + set_task_cpu(next_task, later_rq->cpu); + activate_task(later_rq, next_task, 0); + ret = 1; + + resched_curr(later_rq); + + double_unlock_balance(rq, later_rq); + +out: + put_task_struct(next_task); + + return ret; +} + +static void push_dl_tasks(struct rq *rq) +{ + /* Terminates as it moves a -deadline task */ + while (push_dl_task(rq)) + ; +} + +static int pull_dl_task(struct rq *this_rq) +{ + int this_cpu = this_rq->cpu, ret = 0, cpu; + struct task_struct *p; + struct rq *src_rq; + u64 dmin = LONG_MAX; + + if (likely(!dl_overloaded(this_rq))) + return 0; + + /* + * Match the barrier from dl_set_overloaded; this guarantees that if we + * see overloaded we must also see the dlo_mask bit. + */ + smp_rmb(); + + for_each_cpu(cpu, this_rq->rd->dlo_mask) { + if (this_cpu == cpu) + continue; + + src_rq = cpu_rq(cpu); + + /* + * It looks racy, abd it is! However, as in sched_rt.c, + * we are fine with this. + */ + if (this_rq->dl.dl_nr_running && + dl_time_before(this_rq->dl.earliest_dl.curr, + src_rq->dl.earliest_dl.next)) + continue; + + /* Might drop this_rq->lock */ + double_lock_balance(this_rq, src_rq); + + /* + * If there are no more pullable tasks on the + * rq, we're done with it. + */ + if (src_rq->dl.dl_nr_running <= 1) + goto skip; + + p = pick_next_earliest_dl_task(src_rq, this_cpu); + + /* + * We found a task to be pulled if: + * - it preempts our current (if there's one), + * - it will preempt the last one we pulled (if any). + */ + if (p && dl_time_before(p->dl.deadline, dmin) && + (!this_rq->dl.dl_nr_running || + dl_time_before(p->dl.deadline, + this_rq->dl.earliest_dl.curr))) { + WARN_ON(p == src_rq->curr); + WARN_ON(!task_on_rq_queued(p)); + + /* + * Then we pull iff p has actually an earlier + * deadline than the current task of its runqueue. + */ + if (dl_time_before(p->dl.deadline, + src_rq->curr->dl.deadline)) + goto skip; + + ret = 1; + + deactivate_task(src_rq, p, 0); + set_task_cpu(p, this_cpu); + activate_task(this_rq, p, 0); + dmin = p->dl.deadline; + + /* Is there any other task even earlier? */ + } +skip: + double_unlock_balance(this_rq, src_rq); + } + + return ret; +} + +static void post_schedule_dl(struct rq *rq) +{ + push_dl_tasks(rq); +} + +/* + * Since the task is not running and a reschedule is not going to happen + * anytime soon on its runqueue, we try pushing it away now. + */ +static void task_woken_dl(struct rq *rq, struct task_struct *p) +{ + if (!task_running(rq, p) && + !test_tsk_need_resched(rq->curr) && + has_pushable_dl_tasks(rq) && + p->nr_cpus_allowed > 1 && + dl_task(rq->curr) && + (rq->curr->nr_cpus_allowed < 2 || + !dl_entity_preempt(&p->dl, &rq->curr->dl))) { + push_dl_tasks(rq); + } +} + +static void set_cpus_allowed_dl(struct task_struct *p, + const struct cpumask *new_mask) +{ + struct rq *rq; + struct root_domain *src_rd; + int weight; + + BUG_ON(!dl_task(p)); + + rq = task_rq(p); + src_rd = rq->rd; + /* + * Migrating a SCHED_DEADLINE task between exclusive + * cpusets (different root_domains) entails a bandwidth + * update. We already made space for us in the destination + * domain (see cpuset_can_attach()). + */ + if (!cpumask_intersects(src_rd->span, new_mask)) { + struct dl_bw *src_dl_b; + + src_dl_b = dl_bw_of(cpu_of(rq)); + /* + * We now free resources of the root_domain we are migrating + * off. In the worst case, sched_setattr() may temporary fail + * until we complete the update. + */ + raw_spin_lock(&src_dl_b->lock); + __dl_clear(src_dl_b, p->dl.dl_bw); + raw_spin_unlock(&src_dl_b->lock); + } + + /* + * Update only if the task is actually running (i.e., + * it is on the rq AND it is not throttled). + */ + if (!on_dl_rq(&p->dl)) + return; + + weight = cpumask_weight(new_mask); + + /* + * Only update if the process changes its state from whether it + * can migrate or not. + */ + if ((p->nr_cpus_allowed > 1) == (weight > 1)) + return; + + /* + * The process used to be able to migrate OR it can now migrate + */ + if (weight <= 1) { + if (!task_current(rq, p)) + dequeue_pushable_dl_task(rq, p); + BUG_ON(!rq->dl.dl_nr_migratory); + rq->dl.dl_nr_migratory--; + } else { + if (!task_current(rq, p)) + enqueue_pushable_dl_task(rq, p); + rq->dl.dl_nr_migratory++; + } + + update_dl_migration(&rq->dl); +} + +/* Assumes rq->lock is held */ +static void rq_online_dl(struct rq *rq) +{ + if (rq->dl.overloaded) + dl_set_overload(rq); + + cpudl_set_freecpu(&rq->rd->cpudl, rq->cpu); + if (rq->dl.dl_nr_running > 0) + cpudl_set(&rq->rd->cpudl, rq->cpu, rq->dl.earliest_dl.curr, 1); +} + +/* Assumes rq->lock is held */ +static void rq_offline_dl(struct rq *rq) +{ + if (rq->dl.overloaded) + dl_clear_overload(rq); + + cpudl_set(&rq->rd->cpudl, rq->cpu, 0, 0); + cpudl_clear_freecpu(&rq->rd->cpudl, rq->cpu); +} + +void init_sched_dl_class(void) +{ + unsigned int i; + + for_each_possible_cpu(i) + zalloc_cpumask_var_node(&per_cpu(local_cpu_mask_dl, i), + GFP_KERNEL, cpu_to_node(i)); +} + +#endif /* CONFIG_SMP */ + +/* + * Ensure p's dl_timer is cancelled. May drop rq->lock for a while. + */ +static void cancel_dl_timer(struct rq *rq, struct task_struct *p) +{ + struct hrtimer *dl_timer = &p->dl.dl_timer; + + /* Nobody will change task's class if pi_lock is held */ + lockdep_assert_held(&p->pi_lock); + + if (hrtimer_active(dl_timer)) { + int ret = hrtimer_try_to_cancel(dl_timer); + + if (unlikely(ret == -1)) { + /* + * Note, p may migrate OR new deadline tasks + * may appear in rq when we are unlocking it. + * A caller of us must be fine with that. + */ + raw_spin_unlock(&rq->lock); + hrtimer_cancel(dl_timer); + raw_spin_lock(&rq->lock); + } + } +} + +static void switched_from_dl(struct rq *rq, struct task_struct *p) +{ + /* XXX we should retain the bw until 0-lag */ + cancel_dl_timer(rq, p); + __dl_clear_params(p); + + /* + * Since this might be the only -deadline task on the rq, + * this is the right place to try to pull some other one + * from an overloaded cpu, if any. + */ + if (!task_on_rq_queued(p) || rq->dl.dl_nr_running) + return; + + if (pull_dl_task(rq)) + resched_curr(rq); +} + +/* + * When switching to -deadline, we may overload the rq, then + * we try to push someone off, if possible. + */ +static void switched_to_dl(struct rq *rq, struct task_struct *p) +{ + int check_resched = 1; + + if (task_on_rq_queued(p) && rq->curr != p) { +#ifdef CONFIG_SMP + if (p->nr_cpus_allowed > 1 && rq->dl.overloaded && + push_dl_task(rq) && rq != task_rq(p)) + /* Only reschedule if pushing failed */ + check_resched = 0; +#endif /* CONFIG_SMP */ + if (check_resched) { + if (dl_task(rq->curr)) + check_preempt_curr_dl(rq, p, 0); + else + resched_curr(rq); + } + } +} + +/* + * If the scheduling parameters of a -deadline task changed, + * a push or pull operation might be needed. + */ +static void prio_changed_dl(struct rq *rq, struct task_struct *p, + int oldprio) +{ + if (task_on_rq_queued(p) || rq->curr == p) { +#ifdef CONFIG_SMP + /* + * This might be too much, but unfortunately + * we don't have the old deadline value, and + * we can't argue if the task is increasing + * or lowering its prio, so... + */ + if (!rq->dl.overloaded) + pull_dl_task(rq); + + /* + * If we now have a earlier deadline task than p, + * then reschedule, provided p is still on this + * runqueue. + */ + if (dl_time_before(rq->dl.earliest_dl.curr, p->dl.deadline) && + rq->curr == p) + resched_curr(rq); +#else + /* + * Again, we don't know if p has a earlier + * or later deadline, so let's blindly set a + * (maybe not needed) rescheduling point. + */ + resched_curr(rq); +#endif /* CONFIG_SMP */ + } else + switched_to_dl(rq, p); +} + +const struct sched_class dl_sched_class = { + .next = &rt_sched_class, + .enqueue_task = enqueue_task_dl, + .dequeue_task = dequeue_task_dl, + .yield_task = yield_task_dl, + + .check_preempt_curr = check_preempt_curr_dl, + + .pick_next_task = pick_next_task_dl, + .put_prev_task = put_prev_task_dl, + +#ifdef CONFIG_SMP + .select_task_rq = select_task_rq_dl, + .set_cpus_allowed = set_cpus_allowed_dl, + .rq_online = rq_online_dl, + .rq_offline = rq_offline_dl, + .post_schedule = post_schedule_dl, + .task_woken = task_woken_dl, +#endif + + .set_curr_task = set_curr_task_dl, + .task_tick = task_tick_dl, + .task_fork = task_fork_dl, + .task_dead = task_dead_dl, + + .prio_changed = prio_changed_dl, + .switched_from = switched_from_dl, + .switched_to = switched_to_dl, + + .update_curr = update_curr_dl, +}; + +#ifdef CONFIG_SCHED_DEBUG +extern void print_dl_rq(struct seq_file *m, int cpu, struct dl_rq *dl_rq); + +void print_dl_stats(struct seq_file *m, int cpu) +{ + print_dl_rq(m, cpu, &cpu_rq(cpu)->dl); +} +#endif /* CONFIG_SCHED_DEBUG */ diff --git a/kernel/kernel/sched/debug.c b/kernel/kernel/sched/debug.c new file mode 100644 index 000000000..34b00001b --- /dev/null +++ b/kernel/kernel/sched/debug.c @@ -0,0 +1,681 @@ +/* + * kernel/sched/debug.c + * + * Print the CFS rbtree + * + * Copyright(C) 2007, Red Hat, Inc., Ingo Molnar + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include +#include +#include +#include +#include +#include + +#include "sched.h" + +static DEFINE_SPINLOCK(sched_debug_lock); + +/* + * This allows printing both to /proc/sched_debug and + * to the console + */ +#define SEQ_printf(m, x...) \ + do { \ + if (m) \ + seq_printf(m, x); \ + else \ + printk(x); \ + } while (0) + +/* + * Ease the printing of nsec fields: + */ +static long long nsec_high(unsigned long long nsec) +{ + if ((long long)nsec < 0) { + nsec = -nsec; + do_div(nsec, 1000000); + return -nsec; + } + do_div(nsec, 1000000); + + return nsec; +} + +static unsigned long nsec_low(unsigned long long nsec) +{ + if ((long long)nsec < 0) + nsec = -nsec; + + return do_div(nsec, 1000000); +} + +#define SPLIT_NS(x) nsec_high(x), nsec_low(x) + +#ifdef CONFIG_FAIR_GROUP_SCHED +static void print_cfs_group_stats(struct seq_file *m, int cpu, struct task_group *tg) +{ + struct sched_entity *se = tg->se[cpu]; + +#define P(F) \ + SEQ_printf(m, " .%-30s: %lld\n", #F, (long long)F) +#define PN(F) \ + SEQ_printf(m, " .%-30s: %lld.%06ld\n", #F, SPLIT_NS((long long)F)) + + if (!se) { + struct sched_avg *avg = &cpu_rq(cpu)->avg; + P(avg->runnable_avg_sum); + P(avg->avg_period); + return; + } + + + PN(se->exec_start); + PN(se->vruntime); + PN(se->sum_exec_runtime); +#ifdef CONFIG_SCHEDSTATS + PN(se->statistics.wait_start); + PN(se->statistics.sleep_start); + PN(se->statistics.block_start); + PN(se->statistics.sleep_max); + PN(se->statistics.block_max); + PN(se->statistics.exec_max); + PN(se->statistics.slice_max); + PN(se->statistics.wait_max); + PN(se->statistics.wait_sum); + P(se->statistics.wait_count); +#endif + P(se->load.weight); +#ifdef CONFIG_SMP + P(se->avg.runnable_avg_sum); + P(se->avg.running_avg_sum); + P(se->avg.avg_period); + P(se->avg.load_avg_contrib); + P(se->avg.utilization_avg_contrib); + P(se->avg.decay_count); +#endif +#undef PN +#undef P +} +#endif + +#ifdef CONFIG_CGROUP_SCHED +static char group_path[PATH_MAX]; + +static char *task_group_path(struct task_group *tg) +{ + if (autogroup_path(tg, group_path, PATH_MAX)) + return group_path; + + return cgroup_path(tg->css.cgroup, group_path, PATH_MAX); +} +#endif + +static void +print_task(struct seq_file *m, struct rq *rq, struct task_struct *p) +{ + if (rq->curr == p) + SEQ_printf(m, "R"); + else + SEQ_printf(m, " "); + + SEQ_printf(m, "%15s %5d %9Ld.%06ld %9Ld %5d ", + p->comm, task_pid_nr(p), + SPLIT_NS(p->se.vruntime), + (long long)(p->nvcsw + p->nivcsw), + p->prio); +#ifdef CONFIG_SCHEDSTATS + SEQ_printf(m, "%9Ld.%06ld %9Ld.%06ld %9Ld.%06ld", + SPLIT_NS(p->se.vruntime), + SPLIT_NS(p->se.sum_exec_runtime), + SPLIT_NS(p->se.statistics.sum_sleep_runtime)); +#else + SEQ_printf(m, "%15Ld %15Ld %15Ld.%06ld %15Ld.%06ld %15Ld.%06ld", + 0LL, 0LL, 0LL, 0L, 0LL, 0L, 0LL, 0L); +#endif +#ifdef CONFIG_NUMA_BALANCING + SEQ_printf(m, " %d", task_node(p)); +#endif +#ifdef CONFIG_CGROUP_SCHED + SEQ_printf(m, " %s", task_group_path(task_group(p))); +#endif + + SEQ_printf(m, "\n"); +} + +static void print_rq(struct seq_file *m, struct rq *rq, int rq_cpu) +{ + struct task_struct *g, *p; + + SEQ_printf(m, + "\nrunnable tasks:\n" + " task PID tree-key switches prio" + " exec-runtime sum-exec sum-sleep\n" + "------------------------------------------------------" + "----------------------------------------------------\n"); + + rcu_read_lock(); + for_each_process_thread(g, p) { + if (task_cpu(p) != rq_cpu) + continue; + + print_task(m, rq, p); + } + rcu_read_unlock(); +} + +void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq) +{ + s64 MIN_vruntime = -1, min_vruntime, max_vruntime = -1, + spread, rq0_min_vruntime, spread0; + struct rq *rq = cpu_rq(cpu); + struct sched_entity *last; + unsigned long flags; + +#ifdef CONFIG_FAIR_GROUP_SCHED + SEQ_printf(m, "\ncfs_rq[%d]:%s\n", cpu, task_group_path(cfs_rq->tg)); +#else + SEQ_printf(m, "\ncfs_rq[%d]:\n", cpu); +#endif + SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "exec_clock", + SPLIT_NS(cfs_rq->exec_clock)); + + raw_spin_lock_irqsave(&rq->lock, flags); + if (cfs_rq->rb_leftmost) + MIN_vruntime = (__pick_first_entity(cfs_rq))->vruntime; + last = __pick_last_entity(cfs_rq); + if (last) + max_vruntime = last->vruntime; + min_vruntime = cfs_rq->min_vruntime; + rq0_min_vruntime = cpu_rq(0)->cfs.min_vruntime; + raw_spin_unlock_irqrestore(&rq->lock, flags); + SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "MIN_vruntime", + SPLIT_NS(MIN_vruntime)); + SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "min_vruntime", + SPLIT_NS(min_vruntime)); + SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "max_vruntime", + SPLIT_NS(max_vruntime)); + spread = max_vruntime - MIN_vruntime; + SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "spread", + SPLIT_NS(spread)); + spread0 = min_vruntime - rq0_min_vruntime; + SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "spread0", + SPLIT_NS(spread0)); + SEQ_printf(m, " .%-30s: %d\n", "nr_spread_over", + cfs_rq->nr_spread_over); + SEQ_printf(m, " .%-30s: %d\n", "nr_running", cfs_rq->nr_running); + SEQ_printf(m, " .%-30s: %ld\n", "load", cfs_rq->load.weight); +#ifdef CONFIG_SMP + SEQ_printf(m, " .%-30s: %ld\n", "runnable_load_avg", + cfs_rq->runnable_load_avg); + SEQ_printf(m, " .%-30s: %ld\n", "blocked_load_avg", + cfs_rq->blocked_load_avg); + SEQ_printf(m, " .%-30s: %ld\n", "utilization_load_avg", + cfs_rq->utilization_load_avg); +#ifdef CONFIG_FAIR_GROUP_SCHED + SEQ_printf(m, " .%-30s: %ld\n", "tg_load_contrib", + cfs_rq->tg_load_contrib); + SEQ_printf(m, " .%-30s: %d\n", "tg_runnable_contrib", + cfs_rq->tg_runnable_contrib); + SEQ_printf(m, " .%-30s: %ld\n", "tg_load_avg", + atomic_long_read(&cfs_rq->tg->load_avg)); + SEQ_printf(m, " .%-30s: %d\n", "tg->runnable_avg", + atomic_read(&cfs_rq->tg->runnable_avg)); +#endif +#endif +#ifdef CONFIG_CFS_BANDWIDTH + SEQ_printf(m, " .%-30s: %d\n", "tg->cfs_bandwidth.timer_active", + cfs_rq->tg->cfs_bandwidth.timer_active); + SEQ_printf(m, " .%-30s: %d\n", "throttled", + cfs_rq->throttled); + SEQ_printf(m, " .%-30s: %d\n", "throttle_count", + cfs_rq->throttle_count); +#endif + +#ifdef CONFIG_FAIR_GROUP_SCHED + print_cfs_group_stats(m, cpu, cfs_rq->tg); +#endif +} + +void print_rt_rq(struct seq_file *m, int cpu, struct rt_rq *rt_rq) +{ +#ifdef CONFIG_RT_GROUP_SCHED + SEQ_printf(m, "\nrt_rq[%d]:%s\n", cpu, task_group_path(rt_rq->tg)); +#else + SEQ_printf(m, "\nrt_rq[%d]:\n", cpu); +#endif + +#define P(x) \ + SEQ_printf(m, " .%-30s: %Ld\n", #x, (long long)(rt_rq->x)) +#define PN(x) \ + SEQ_printf(m, " .%-30s: %Ld.%06ld\n", #x, SPLIT_NS(rt_rq->x)) + + P(rt_nr_running); + P(rt_throttled); + PN(rt_time); + PN(rt_runtime); +#ifdef CONFIG_SMP + P(rt_nr_migratory); +#endif + +#undef PN +#undef P +} + +void print_dl_rq(struct seq_file *m, int cpu, struct dl_rq *dl_rq) +{ + SEQ_printf(m, "\ndl_rq[%d]:\n", cpu); + SEQ_printf(m, " .%-30s: %ld\n", "dl_nr_running", dl_rq->dl_nr_running); +} + +extern __read_mostly int sched_clock_running; + +static void print_cpu(struct seq_file *m, int cpu) +{ + struct rq *rq = cpu_rq(cpu); + unsigned long flags; + +#ifdef CONFIG_X86 + { + unsigned int freq = cpu_khz ? : 1; + + SEQ_printf(m, "cpu#%d, %u.%03u MHz\n", + cpu, freq / 1000, (freq % 1000)); + } +#else + SEQ_printf(m, "cpu#%d\n", cpu); +#endif + +#define P(x) \ +do { \ + if (sizeof(rq->x) == 4) \ + SEQ_printf(m, " .%-30s: %ld\n", #x, (long)(rq->x)); \ + else \ + SEQ_printf(m, " .%-30s: %Ld\n", #x, (long long)(rq->x));\ +} while (0) + +#define PN(x) \ + SEQ_printf(m, " .%-30s: %Ld.%06ld\n", #x, SPLIT_NS(rq->x)) + + P(nr_running); + SEQ_printf(m, " .%-30s: %lu\n", "load", + rq->load.weight); + P(nr_switches); + P(nr_load_updates); + P(nr_uninterruptible); + PN(next_balance); + SEQ_printf(m, " .%-30s: %ld\n", "curr->pid", (long)(task_pid_nr(rq->curr))); + PN(clock); + PN(clock_task); + P(cpu_load[0]); + P(cpu_load[1]); + P(cpu_load[2]); + P(cpu_load[3]); + P(cpu_load[4]); +#undef P +#undef PN + +#ifdef CONFIG_SCHEDSTATS +#define P(n) SEQ_printf(m, " .%-30s: %d\n", #n, rq->n); +#define P64(n) SEQ_printf(m, " .%-30s: %Ld\n", #n, rq->n); + + P(yld_count); + + P(sched_count); + P(sched_goidle); +#ifdef CONFIG_SMP + P64(avg_idle); + P64(max_idle_balance_cost); +#endif + + P(ttwu_count); + P(ttwu_local); + +#undef P +#undef P64 +#endif + spin_lock_irqsave(&sched_debug_lock, flags); + print_cfs_stats(m, cpu); + print_rt_stats(m, cpu); + print_dl_stats(m, cpu); + + print_rq(m, rq, cpu); + spin_unlock_irqrestore(&sched_debug_lock, flags); + SEQ_printf(m, "\n"); +} + +static const char *sched_tunable_scaling_names[] = { + "none", + "logaritmic", + "linear" +}; + +static void sched_debug_header(struct seq_file *m) +{ + u64 ktime, sched_clk, cpu_clk; + unsigned long flags; + + local_irq_save(flags); + ktime = ktime_to_ns(ktime_get()); + sched_clk = sched_clock(); + cpu_clk = local_clock(); + local_irq_restore(flags); + + SEQ_printf(m, "Sched Debug Version: v0.11, %s %.*s\n", + init_utsname()->release, + (int)strcspn(init_utsname()->version, " "), + init_utsname()->version); + +#define P(x) \ + SEQ_printf(m, "%-40s: %Ld\n", #x, (long long)(x)) +#define PN(x) \ + SEQ_printf(m, "%-40s: %Ld.%06ld\n", #x, SPLIT_NS(x)) + PN(ktime); + PN(sched_clk); + PN(cpu_clk); + P(jiffies); +#ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK + P(sched_clock_stable()); +#endif +#undef PN +#undef P + + SEQ_printf(m, "\n"); + SEQ_printf(m, "sysctl_sched\n"); + +#define P(x) \ + SEQ_printf(m, " .%-40s: %Ld\n", #x, (long long)(x)) +#define PN(x) \ + SEQ_printf(m, " .%-40s: %Ld.%06ld\n", #x, SPLIT_NS(x)) + PN(sysctl_sched_latency); + PN(sysctl_sched_min_granularity); + PN(sysctl_sched_wakeup_granularity); + P(sysctl_sched_child_runs_first); + P(sysctl_sched_features); +#undef PN +#undef P + + SEQ_printf(m, " .%-40s: %d (%s)\n", + "sysctl_sched_tunable_scaling", + sysctl_sched_tunable_scaling, + sched_tunable_scaling_names[sysctl_sched_tunable_scaling]); + SEQ_printf(m, "\n"); +} + +static int sched_debug_show(struct seq_file *m, void *v) +{ + int cpu = (unsigned long)(v - 2); + + if (cpu != -1) + print_cpu(m, cpu); + else + sched_debug_header(m); + + return 0; +} + +void sysrq_sched_debug_show(void) +{ + int cpu; + + sched_debug_header(NULL); + for_each_online_cpu(cpu) + print_cpu(NULL, cpu); + +} + +/* + * This itererator needs some explanation. + * It returns 1 for the header position. + * This means 2 is cpu 0. + * In a hotplugged system some cpus, including cpu 0, may be missing so we have + * to use cpumask_* to iterate over the cpus. + */ +static void *sched_debug_start(struct seq_file *file, loff_t *offset) +{ + unsigned long n = *offset; + + if (n == 0) + return (void *) 1; + + n--; + + if (n > 0) + n = cpumask_next(n - 1, cpu_online_mask); + else + n = cpumask_first(cpu_online_mask); + + *offset = n + 1; + + if (n < nr_cpu_ids) + return (void *)(unsigned long)(n + 2); + return NULL; +} + +static void *sched_debug_next(struct seq_file *file, void *data, loff_t *offset) +{ + (*offset)++; + return sched_debug_start(file, offset); +} + +static void sched_debug_stop(struct seq_file *file, void *data) +{ +} + +static const struct seq_operations sched_debug_sops = { + .start = sched_debug_start, + .next = sched_debug_next, + .stop = sched_debug_stop, + .show = sched_debug_show, +}; + +static int sched_debug_release(struct inode *inode, struct file *file) +{ + seq_release(inode, file); + + return 0; +} + +static int sched_debug_open(struct inode *inode, struct file *filp) +{ + int ret = 0; + + ret = seq_open(filp, &sched_debug_sops); + + return ret; +} + +static const struct file_operations sched_debug_fops = { + .open = sched_debug_open, + .read = seq_read, + .llseek = seq_lseek, + .release = sched_debug_release, +}; + +static int __init init_sched_debug_procfs(void) +{ + struct proc_dir_entry *pe; + + pe = proc_create("sched_debug", 0444, NULL, &sched_debug_fops); + if (!pe) + return -ENOMEM; + return 0; +} + +__initcall(init_sched_debug_procfs); + +#define __P(F) \ + SEQ_printf(m, "%-45s:%21Ld\n", #F, (long long)F) +#define P(F) \ + SEQ_printf(m, "%-45s:%21Ld\n", #F, (long long)p->F) +#define __PN(F) \ + SEQ_printf(m, "%-45s:%14Ld.%06ld\n", #F, SPLIT_NS((long long)F)) +#define PN(F) \ + SEQ_printf(m, "%-45s:%14Ld.%06ld\n", #F, SPLIT_NS((long long)p->F)) + + +static void sched_show_numa(struct task_struct *p, struct seq_file *m) +{ +#ifdef CONFIG_NUMA_BALANCING + struct mempolicy *pol; + int node, i; + + if (p->mm) + P(mm->numa_scan_seq); + + task_lock(p); + pol = p->mempolicy; + if (pol && !(pol->flags & MPOL_F_MORON)) + pol = NULL; + mpol_get(pol); + task_unlock(p); + + SEQ_printf(m, "numa_migrations, %ld\n", xchg(&p->numa_pages_migrated, 0)); + + for_each_online_node(node) { + for (i = 0; i < 2; i++) { + unsigned long nr_faults = -1; + int cpu_current, home_node; + + if (p->numa_faults) + nr_faults = p->numa_faults[2*node + i]; + + cpu_current = !i ? (task_node(p) == node) : + (pol && node_isset(node, pol->v.nodes)); + + home_node = (p->numa_preferred_nid == node); + + SEQ_printf(m, "numa_faults_memory, %d, %d, %d, %d, %ld\n", + i, node, cpu_current, home_node, nr_faults); + } + } + + mpol_put(pol); +#endif +} + +void proc_sched_show_task(struct task_struct *p, struct seq_file *m) +{ + unsigned long nr_switches; + + SEQ_printf(m, "%s (%d, #threads: %d)\n", p->comm, task_pid_nr(p), + get_nr_threads(p)); + SEQ_printf(m, + "---------------------------------------------------------" + "----------\n"); +#define __P(F) \ + SEQ_printf(m, "%-45s:%21Ld\n", #F, (long long)F) +#define P(F) \ + SEQ_printf(m, "%-45s:%21Ld\n", #F, (long long)p->F) +#define __PN(F) \ + SEQ_printf(m, "%-45s:%14Ld.%06ld\n", #F, SPLIT_NS((long long)F)) +#define PN(F) \ + SEQ_printf(m, "%-45s:%14Ld.%06ld\n", #F, SPLIT_NS((long long)p->F)) + + PN(se.exec_start); + PN(se.vruntime); + PN(se.sum_exec_runtime); + + nr_switches = p->nvcsw + p->nivcsw; + +#ifdef CONFIG_SCHEDSTATS + PN(se.statistics.wait_start); + PN(se.statistics.sleep_start); + PN(se.statistics.block_start); + PN(se.statistics.sleep_max); + PN(se.statistics.block_max); + PN(se.statistics.exec_max); + PN(se.statistics.slice_max); + PN(se.statistics.wait_max); + PN(se.statistics.wait_sum); + P(se.statistics.wait_count); + PN(se.statistics.iowait_sum); + P(se.statistics.iowait_count); + P(se.nr_migrations); + P(se.statistics.nr_migrations_cold); + P(se.statistics.nr_failed_migrations_affine); + P(se.statistics.nr_failed_migrations_running); + P(se.statistics.nr_failed_migrations_hot); + P(se.statistics.nr_forced_migrations); + P(se.statistics.nr_wakeups); + P(se.statistics.nr_wakeups_sync); + P(se.statistics.nr_wakeups_migrate); + P(se.statistics.nr_wakeups_local); + P(se.statistics.nr_wakeups_remote); + P(se.statistics.nr_wakeups_affine); + P(se.statistics.nr_wakeups_affine_attempts); + P(se.statistics.nr_wakeups_passive); + P(se.statistics.nr_wakeups_idle); + + { + u64 avg_atom, avg_per_cpu; + + avg_atom = p->se.sum_exec_runtime; + if (nr_switches) + avg_atom = div64_ul(avg_atom, nr_switches); + else + avg_atom = -1LL; + + avg_per_cpu = p->se.sum_exec_runtime; + if (p->se.nr_migrations) { + avg_per_cpu = div64_u64(avg_per_cpu, + p->se.nr_migrations); + } else { + avg_per_cpu = -1LL; + } + + __PN(avg_atom); + __PN(avg_per_cpu); + } +#endif + __P(nr_switches); + SEQ_printf(m, "%-45s:%21Ld\n", + "nr_voluntary_switches", (long long)p->nvcsw); + SEQ_printf(m, "%-45s:%21Ld\n", + "nr_involuntary_switches", (long long)p->nivcsw); + + P(se.load.weight); +#ifdef CONFIG_SMP + P(se.avg.runnable_avg_sum); + P(se.avg.running_avg_sum); + P(se.avg.avg_period); + P(se.avg.load_avg_contrib); + P(se.avg.utilization_avg_contrib); + P(se.avg.decay_count); +#endif + P(policy); + P(prio); +#ifdef CONFIG_PREEMPT_RT_FULL + P(migrate_disable); +#endif + P(nr_cpus_allowed); +#undef PN +#undef __PN +#undef P +#undef __P + + { + unsigned int this_cpu = raw_smp_processor_id(); + u64 t0, t1; + + t0 = cpu_clock(this_cpu); + t1 = cpu_clock(this_cpu); + SEQ_printf(m, "%-45s:%21Ld\n", + "clock-delta", (long long)(t1-t0)); + } + + sched_show_numa(p, m); +} + +void proc_sched_set_task(struct task_struct *p) +{ +#ifdef CONFIG_SCHEDSTATS + memset(&p->se.statistics, 0, sizeof(p->se.statistics)); +#endif +} diff --git a/kernel/kernel/sched/fair.c b/kernel/kernel/sched/fair.c new file mode 100644 index 000000000..92c53d074 --- /dev/null +++ b/kernel/kernel/sched/fair.c @@ -0,0 +1,8285 @@ +/* + * Completely Fair Scheduling (CFS) Class (SCHED_NORMAL/SCHED_BATCH) + * + * Copyright (C) 2007 Red Hat, Inc., Ingo Molnar + * + * Interactivity improvements by Mike Galbraith + * (C) 2007 Mike Galbraith + * + * Various enhancements by Dmitry Adamushko. + * (C) 2007 Dmitry Adamushko + * + * Group scheduling enhancements by Srivatsa Vaddagiri + * Copyright IBM Corporation, 2007 + * Author: Srivatsa Vaddagiri + * + * Scaled math optimizations by Thomas Gleixner + * Copyright (C) 2007, Thomas Gleixner + * + * Adaptive scheduling granularity, math enhancements by Peter Zijlstra + * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +#include "sched.h" + +/* + * Targeted preemption latency for CPU-bound tasks: + * (default: 6ms * (1 + ilog(ncpus)), units: nanoseconds) + * + * NOTE: this latency value is not the same as the concept of + * 'timeslice length' - timeslices in CFS are of variable length + * and have no persistent notion like in traditional, time-slice + * based scheduling concepts. + * + * (to see the precise effective timeslice length of your workload, + * run vmstat and monitor the context-switches (cs) field) + */ +unsigned int sysctl_sched_latency = 6000000ULL; +unsigned int normalized_sysctl_sched_latency = 6000000ULL; + +/* + * The initial- and re-scaling of tunables is configurable + * (default SCHED_TUNABLESCALING_LOG = *(1+ilog(ncpus)) + * + * Options are: + * SCHED_TUNABLESCALING_NONE - unscaled, always *1 + * SCHED_TUNABLESCALING_LOG - scaled logarithmical, *1+ilog(ncpus) + * SCHED_TUNABLESCALING_LINEAR - scaled linear, *ncpus + */ +enum sched_tunable_scaling sysctl_sched_tunable_scaling + = SCHED_TUNABLESCALING_LOG; + +/* + * Minimal preemption granularity for CPU-bound tasks: + * (default: 0.75 msec * (1 + ilog(ncpus)), units: nanoseconds) + */ +unsigned int sysctl_sched_min_granularity = 750000ULL; +unsigned int normalized_sysctl_sched_min_granularity = 750000ULL; + +/* + * is kept at sysctl_sched_latency / sysctl_sched_min_granularity + */ +static unsigned int sched_nr_latency = 8; + +/* + * After fork, child runs first. If set to 0 (default) then + * parent will (try to) run first. + */ +unsigned int sysctl_sched_child_runs_first __read_mostly; + +/* + * SCHED_OTHER wake-up granularity. + * (default: 1 msec * (1 + ilog(ncpus)), units: nanoseconds) + * + * This option delays the preemption effects of decoupled workloads + * and reduces their over-scheduling. Synchronous workloads will still + * have immediate wakeup/sleep latencies. + */ +unsigned int sysctl_sched_wakeup_granularity = 1000000UL; +unsigned int normalized_sysctl_sched_wakeup_granularity = 1000000UL; + +const_debug unsigned int sysctl_sched_migration_cost = 500000UL; + +/* + * The exponential sliding window over which load is averaged for shares + * distribution. + * (default: 10msec) + */ +unsigned int __read_mostly sysctl_sched_shares_window = 10000000UL; + +#ifdef CONFIG_CFS_BANDWIDTH +/* + * Amount of runtime to allocate from global (tg) to local (per-cfs_rq) pool + * each time a cfs_rq requests quota. + * + * Note: in the case that the slice exceeds the runtime remaining (either due + * to consumption or the quota being specified to be smaller than the slice) + * we will always only issue the remaining available time. + * + * default: 5 msec, units: microseconds + */ +unsigned int sysctl_sched_cfs_bandwidth_slice = 5000UL; +#endif + +static inline void update_load_add(struct load_weight *lw, unsigned long inc) +{ + lw->weight += inc; + lw->inv_weight = 0; +} + +static inline void update_load_sub(struct load_weight *lw, unsigned long dec) +{ + lw->weight -= dec; + lw->inv_weight = 0; +} + +static inline void update_load_set(struct load_weight *lw, unsigned long w) +{ + lw->weight = w; + lw->inv_weight = 0; +} + +/* + * Increase the granularity value when there are more CPUs, + * because with more CPUs the 'effective latency' as visible + * to users decreases. But the relationship is not linear, + * so pick a second-best guess by going with the log2 of the + * number of CPUs. + * + * This idea comes from the SD scheduler of Con Kolivas: + */ +static int get_update_sysctl_factor(void) +{ + unsigned int cpus = min_t(int, num_online_cpus(), 8); + unsigned int factor; + + switch (sysctl_sched_tunable_scaling) { + case SCHED_TUNABLESCALING_NONE: + factor = 1; + break; + case SCHED_TUNABLESCALING_LINEAR: + factor = cpus; + break; + case SCHED_TUNABLESCALING_LOG: + default: + factor = 1 + ilog2(cpus); + break; + } + + return factor; +} + +static void update_sysctl(void) +{ + unsigned int factor = get_update_sysctl_factor(); + +#define SET_SYSCTL(name) \ + (sysctl_##name = (factor) * normalized_sysctl_##name) + SET_SYSCTL(sched_min_granularity); + SET_SYSCTL(sched_latency); + SET_SYSCTL(sched_wakeup_granularity); +#undef SET_SYSCTL +} + +void sched_init_granularity(void) +{ + update_sysctl(); +} + +#define WMULT_CONST (~0U) +#define WMULT_SHIFT 32 + +static void __update_inv_weight(struct load_weight *lw) +{ + unsigned long w; + + if (likely(lw->inv_weight)) + return; + + w = scale_load_down(lw->weight); + + if (BITS_PER_LONG > 32 && unlikely(w >= WMULT_CONST)) + lw->inv_weight = 1; + else if (unlikely(!w)) + lw->inv_weight = WMULT_CONST; + else + lw->inv_weight = WMULT_CONST / w; +} + +/* + * delta_exec * weight / lw.weight + * OR + * (delta_exec * (weight * lw->inv_weight)) >> WMULT_SHIFT + * + * Either weight := NICE_0_LOAD and lw \e prio_to_wmult[], in which case + * we're guaranteed shift stays positive because inv_weight is guaranteed to + * fit 32 bits, and NICE_0_LOAD gives another 10 bits; therefore shift >= 22. + * + * Or, weight =< lw.weight (because lw.weight is the runqueue weight), thus + * weight/lw.weight <= 1, and therefore our shift will also be positive. + */ +static u64 __calc_delta(u64 delta_exec, unsigned long weight, struct load_weight *lw) +{ + u64 fact = scale_load_down(weight); + int shift = WMULT_SHIFT; + + __update_inv_weight(lw); + + if (unlikely(fact >> 32)) { + while (fact >> 32) { + fact >>= 1; + shift--; + } + } + + /* hint to use a 32x32->64 mul */ + fact = (u64)(u32)fact * lw->inv_weight; + + while (fact >> 32) { + fact >>= 1; + shift--; + } + + return mul_u64_u32_shr(delta_exec, fact, shift); +} + + +const struct sched_class fair_sched_class; + +/************************************************************** + * CFS operations on generic schedulable entities: + */ + +#ifdef CONFIG_FAIR_GROUP_SCHED + +/* cpu runqueue to which this cfs_rq is attached */ +static inline struct rq *rq_of(struct cfs_rq *cfs_rq) +{ + return cfs_rq->rq; +} + +/* An entity is a task if it doesn't "own" a runqueue */ +#define entity_is_task(se) (!se->my_q) + +static inline struct task_struct *task_of(struct sched_entity *se) +{ +#ifdef CONFIG_SCHED_DEBUG + WARN_ON_ONCE(!entity_is_task(se)); +#endif + return container_of(se, struct task_struct, se); +} + +/* Walk up scheduling entities hierarchy */ +#define for_each_sched_entity(se) \ + for (; se; se = se->parent) + +static inline struct cfs_rq *task_cfs_rq(struct task_struct *p) +{ + return p->se.cfs_rq; +} + +/* runqueue on which this entity is (to be) queued */ +static inline struct cfs_rq *cfs_rq_of(struct sched_entity *se) +{ + return se->cfs_rq; +} + +/* runqueue "owned" by this group */ +static inline struct cfs_rq *group_cfs_rq(struct sched_entity *grp) +{ + return grp->my_q; +} + +static void update_cfs_rq_blocked_load(struct cfs_rq *cfs_rq, + int force_update); + +static inline void list_add_leaf_cfs_rq(struct cfs_rq *cfs_rq) +{ + if (!cfs_rq->on_list) { + /* + * Ensure we either appear before our parent (if already + * enqueued) or force our parent to appear after us when it is + * enqueued. The fact that we always enqueue bottom-up + * reduces this to two cases. + */ + if (cfs_rq->tg->parent && + cfs_rq->tg->parent->cfs_rq[cpu_of(rq_of(cfs_rq))]->on_list) { + list_add_rcu(&cfs_rq->leaf_cfs_rq_list, + &rq_of(cfs_rq)->leaf_cfs_rq_list); + } else { + list_add_tail_rcu(&cfs_rq->leaf_cfs_rq_list, + &rq_of(cfs_rq)->leaf_cfs_rq_list); + } + + cfs_rq->on_list = 1; + /* We should have no load, but we need to update last_decay. */ + update_cfs_rq_blocked_load(cfs_rq, 0); + } +} + +static inline void list_del_leaf_cfs_rq(struct cfs_rq *cfs_rq) +{ + if (cfs_rq->on_list) { + list_del_rcu(&cfs_rq->leaf_cfs_rq_list); + cfs_rq->on_list = 0; + } +} + +/* Iterate thr' all leaf cfs_rq's on a runqueue */ +#define for_each_leaf_cfs_rq(rq, cfs_rq) \ + list_for_each_entry_rcu(cfs_rq, &rq->leaf_cfs_rq_list, leaf_cfs_rq_list) + +/* Do the two (enqueued) entities belong to the same group ? */ +static inline struct cfs_rq * +is_same_group(struct sched_entity *se, struct sched_entity *pse) +{ + if (se->cfs_rq == pse->cfs_rq) + return se->cfs_rq; + + return NULL; +} + +static inline struct sched_entity *parent_entity(struct sched_entity *se) +{ + return se->parent; +} + +static void +find_matching_se(struct sched_entity **se, struct sched_entity **pse) +{ + int se_depth, pse_depth; + + /* + * preemption test can be made between sibling entities who are in the + * same cfs_rq i.e who have a common parent. Walk up the hierarchy of + * both tasks until we find their ancestors who are siblings of common + * parent. + */ + + /* First walk up until both entities are at same depth */ + se_depth = (*se)->depth; + pse_depth = (*pse)->depth; + + while (se_depth > pse_depth) { + se_depth--; + *se = parent_entity(*se); + } + + while (pse_depth > se_depth) { + pse_depth--; + *pse = parent_entity(*pse); + } + + while (!is_same_group(*se, *pse)) { + *se = parent_entity(*se); + *pse = parent_entity(*pse); + } +} + +#else /* !CONFIG_FAIR_GROUP_SCHED */ + +static inline struct task_struct *task_of(struct sched_entity *se) +{ + return container_of(se, struct task_struct, se); +} + +static inline struct rq *rq_of(struct cfs_rq *cfs_rq) +{ + return container_of(cfs_rq, struct rq, cfs); +} + +#define entity_is_task(se) 1 + +#define for_each_sched_entity(se) \ + for (; se; se = NULL) + +static inline struct cfs_rq *task_cfs_rq(struct task_struct *p) +{ + return &task_rq(p)->cfs; +} + +static inline struct cfs_rq *cfs_rq_of(struct sched_entity *se) +{ + struct task_struct *p = task_of(se); + struct rq *rq = task_rq(p); + + return &rq->cfs; +} + +/* runqueue "owned" by this group */ +static inline struct cfs_rq *group_cfs_rq(struct sched_entity *grp) +{ + return NULL; +} + +static inline void list_add_leaf_cfs_rq(struct cfs_rq *cfs_rq) +{ +} + +static inline void list_del_leaf_cfs_rq(struct cfs_rq *cfs_rq) +{ +} + +#define for_each_leaf_cfs_rq(rq, cfs_rq) \ + for (cfs_rq = &rq->cfs; cfs_rq; cfs_rq = NULL) + +static inline struct sched_entity *parent_entity(struct sched_entity *se) +{ + return NULL; +} + +static inline void +find_matching_se(struct sched_entity **se, struct sched_entity **pse) +{ +} + +#endif /* CONFIG_FAIR_GROUP_SCHED */ + +static __always_inline +void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec); + +/************************************************************** + * Scheduling class tree data structure manipulation methods: + */ + +static inline u64 max_vruntime(u64 max_vruntime, u64 vruntime) +{ + s64 delta = (s64)(vruntime - max_vruntime); + if (delta > 0) + max_vruntime = vruntime; + + return max_vruntime; +} + +static inline u64 min_vruntime(u64 min_vruntime, u64 vruntime) +{ + s64 delta = (s64)(vruntime - min_vruntime); + if (delta < 0) + min_vruntime = vruntime; + + return min_vruntime; +} + +static inline int entity_before(struct sched_entity *a, + struct sched_entity *b) +{ + return (s64)(a->vruntime - b->vruntime) < 0; +} + +static void update_min_vruntime(struct cfs_rq *cfs_rq) +{ + u64 vruntime = cfs_rq->min_vruntime; + + if (cfs_rq->curr) + vruntime = cfs_rq->curr->vruntime; + + if (cfs_rq->rb_leftmost) { + struct sched_entity *se = rb_entry(cfs_rq->rb_leftmost, + struct sched_entity, + run_node); + + if (!cfs_rq->curr) + vruntime = se->vruntime; + else + vruntime = min_vruntime(vruntime, se->vruntime); + } + + /* ensure we never gain time by being placed backwards. */ + cfs_rq->min_vruntime = max_vruntime(cfs_rq->min_vruntime, vruntime); +#ifndef CONFIG_64BIT + smp_wmb(); + cfs_rq->min_vruntime_copy = cfs_rq->min_vruntime; +#endif +} + +/* + * Enqueue an entity into the rb-tree: + */ +static void __enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se) +{ + struct rb_node **link = &cfs_rq->tasks_timeline.rb_node; + struct rb_node *parent = NULL; + struct sched_entity *entry; + int leftmost = 1; + + /* + * Find the right place in the rbtree: + */ + while (*link) { + parent = *link; + entry = rb_entry(parent, struct sched_entity, run_node); + /* + * We dont care about collisions. Nodes with + * the same key stay together. + */ + if (entity_before(se, entry)) { + link = &parent->rb_left; + } else { + link = &parent->rb_right; + leftmost = 0; + } + } + + /* + * Maintain a cache of leftmost tree entries (it is frequently + * used): + */ + if (leftmost) + cfs_rq->rb_leftmost = &se->run_node; + + rb_link_node(&se->run_node, parent, link); + rb_insert_color(&se->run_node, &cfs_rq->tasks_timeline); +} + +static void __dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se) +{ + if (cfs_rq->rb_leftmost == &se->run_node) { + struct rb_node *next_node; + + next_node = rb_next(&se->run_node); + cfs_rq->rb_leftmost = next_node; + } + + rb_erase(&se->run_node, &cfs_rq->tasks_timeline); +} + +struct sched_entity *__pick_first_entity(struct cfs_rq *cfs_rq) +{ + struct rb_node *left = cfs_rq->rb_leftmost; + + if (!left) + return NULL; + + return rb_entry(left, struct sched_entity, run_node); +} + +static struct sched_entity *__pick_next_entity(struct sched_entity *se) +{ + struct rb_node *next = rb_next(&se->run_node); + + if (!next) + return NULL; + + return rb_entry(next, struct sched_entity, run_node); +} + +#ifdef CONFIG_SCHED_DEBUG +struct sched_entity *__pick_last_entity(struct cfs_rq *cfs_rq) +{ + struct rb_node *last = rb_last(&cfs_rq->tasks_timeline); + + if (!last) + return NULL; + + return rb_entry(last, struct sched_entity, run_node); +} + +/************************************************************** + * Scheduling class statistics methods: + */ + +int sched_proc_update_handler(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos) +{ + int ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); + int factor = get_update_sysctl_factor(); + + if (ret || !write) + return ret; + + sched_nr_latency = DIV_ROUND_UP(sysctl_sched_latency, + sysctl_sched_min_granularity); + +#define WRT_SYSCTL(name) \ + (normalized_sysctl_##name = sysctl_##name / (factor)) + WRT_SYSCTL(sched_min_granularity); + WRT_SYSCTL(sched_latency); + WRT_SYSCTL(sched_wakeup_granularity); +#undef WRT_SYSCTL + + return 0; +} +#endif + +/* + * delta /= w + */ +static inline u64 calc_delta_fair(u64 delta, struct sched_entity *se) +{ + if (unlikely(se->load.weight != NICE_0_LOAD)) + delta = __calc_delta(delta, NICE_0_LOAD, &se->load); + + return delta; +} + +/* + * The idea is to set a period in which each task runs once. + * + * When there are too many tasks (sched_nr_latency) we have to stretch + * this period because otherwise the slices get too small. + * + * p = (nr <= nl) ? l : l*nr/nl + */ +static u64 __sched_period(unsigned long nr_running) +{ + u64 period = sysctl_sched_latency; + unsigned long nr_latency = sched_nr_latency; + + if (unlikely(nr_running > nr_latency)) { + period = sysctl_sched_min_granularity; + period *= nr_running; + } + + return period; +} + +/* + * We calculate the wall-time slice from the period by taking a part + * proportional to the weight. + * + * s = p*P[w/rw] + */ +static u64 sched_slice(struct cfs_rq *cfs_rq, struct sched_entity *se) +{ + u64 slice = __sched_period(cfs_rq->nr_running + !se->on_rq); + + for_each_sched_entity(se) { + struct load_weight *load; + struct load_weight lw; + + cfs_rq = cfs_rq_of(se); + load = &cfs_rq->load; + + if (unlikely(!se->on_rq)) { + lw = cfs_rq->load; + + update_load_add(&lw, se->load.weight); + load = &lw; + } + slice = __calc_delta(slice, se->load.weight, load); + } + return slice; +} + +/* + * We calculate the vruntime slice of a to-be-inserted task. + * + * vs = s/w + */ +static u64 sched_vslice(struct cfs_rq *cfs_rq, struct sched_entity *se) +{ + return calc_delta_fair(sched_slice(cfs_rq, se), se); +} + +#ifdef CONFIG_SMP +static int select_idle_sibling(struct task_struct *p, int cpu); +static unsigned long task_h_load(struct task_struct *p); + +static inline void __update_task_entity_contrib(struct sched_entity *se); +static inline void __update_task_entity_utilization(struct sched_entity *se); + +/* Give new task start runnable values to heavy its load in infant time */ +void init_task_runnable_average(struct task_struct *p) +{ + u32 slice; + + slice = sched_slice(task_cfs_rq(p), &p->se) >> 10; + p->se.avg.runnable_avg_sum = p->se.avg.running_avg_sum = slice; + p->se.avg.avg_period = slice; + __update_task_entity_contrib(&p->se); + __update_task_entity_utilization(&p->se); +} +#else +void init_task_runnable_average(struct task_struct *p) +{ +} +#endif + +/* + * Update the current task's runtime statistics. + */ +static void update_curr(struct cfs_rq *cfs_rq) +{ + struct sched_entity *curr = cfs_rq->curr; + u64 now = rq_clock_task(rq_of(cfs_rq)); + u64 delta_exec; + + if (unlikely(!curr)) + return; + + delta_exec = now - curr->exec_start; + if (unlikely((s64)delta_exec <= 0)) + return; + + curr->exec_start = now; + + schedstat_set(curr->statistics.exec_max, + max(delta_exec, curr->statistics.exec_max)); + + curr->sum_exec_runtime += delta_exec; + schedstat_add(cfs_rq, exec_clock, delta_exec); + + curr->vruntime += calc_delta_fair(delta_exec, curr); + update_min_vruntime(cfs_rq); + + if (entity_is_task(curr)) { + struct task_struct *curtask = task_of(curr); + + trace_sched_stat_runtime(curtask, delta_exec, curr->vruntime); + cpuacct_charge(curtask, delta_exec); + account_group_exec_runtime(curtask, delta_exec); + } + + account_cfs_rq_runtime(cfs_rq, delta_exec); +} + +static void update_curr_fair(struct rq *rq) +{ + update_curr(cfs_rq_of(&rq->curr->se)); +} + +static inline void +update_stats_wait_start(struct cfs_rq *cfs_rq, struct sched_entity *se) +{ + schedstat_set(se->statistics.wait_start, rq_clock(rq_of(cfs_rq))); +} + +/* + * Task is being enqueued - update stats: + */ +static void update_stats_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se) +{ + /* + * Are we enqueueing a waiting task? (for current tasks + * a dequeue/enqueue event is a NOP) + */ + if (se != cfs_rq->curr) + update_stats_wait_start(cfs_rq, se); +} + +static void +update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se) +{ + schedstat_set(se->statistics.wait_max, max(se->statistics.wait_max, + rq_clock(rq_of(cfs_rq)) - se->statistics.wait_start)); + schedstat_set(se->statistics.wait_count, se->statistics.wait_count + 1); + schedstat_set(se->statistics.wait_sum, se->statistics.wait_sum + + rq_clock(rq_of(cfs_rq)) - se->statistics.wait_start); +#ifdef CONFIG_SCHEDSTATS + if (entity_is_task(se)) { + trace_sched_stat_wait(task_of(se), + rq_clock(rq_of(cfs_rq)) - se->statistics.wait_start); + } +#endif + schedstat_set(se->statistics.wait_start, 0); +} + +static inline void +update_stats_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se) +{ + /* + * Mark the end of the wait period if dequeueing a + * waiting task: + */ + if (se != cfs_rq->curr) + update_stats_wait_end(cfs_rq, se); +} + +/* + * We are picking a new current task - update its stats: + */ +static inline void +update_stats_curr_start(struct cfs_rq *cfs_rq, struct sched_entity *se) +{ + /* + * We are starting a new run period: + */ + se->exec_start = rq_clock_task(rq_of(cfs_rq)); +} + +/************************************************** + * Scheduling class queueing methods: + */ + +#ifdef CONFIG_NUMA_BALANCING +/* + * Approximate time to scan a full NUMA task in ms. The task scan period is + * calculated based on the tasks virtual memory size and + * numa_balancing_scan_size. + */ +unsigned int sysctl_numa_balancing_scan_period_min = 1000; +unsigned int sysctl_numa_balancing_scan_period_max = 60000; + +/* Portion of address space to scan in MB */ +unsigned int sysctl_numa_balancing_scan_size = 256; + +/* Scan @scan_size MB every @scan_period after an initial @scan_delay in ms */ +unsigned int sysctl_numa_balancing_scan_delay = 1000; + +static unsigned int task_nr_scan_windows(struct task_struct *p) +{ + unsigned long rss = 0; + unsigned long nr_scan_pages; + + /* + * Calculations based on RSS as non-present and empty pages are skipped + * by the PTE scanner and NUMA hinting faults should be trapped based + * on resident pages + */ + nr_scan_pages = sysctl_numa_balancing_scan_size << (20 - PAGE_SHIFT); + rss = get_mm_rss(p->mm); + if (!rss) + rss = nr_scan_pages; + + rss = round_up(rss, nr_scan_pages); + return rss / nr_scan_pages; +} + +/* For sanitys sake, never scan more PTEs than MAX_SCAN_WINDOW MB/sec. */ +#define MAX_SCAN_WINDOW 2560 + +static unsigned int task_scan_min(struct task_struct *p) +{ + unsigned int scan_size = ACCESS_ONCE(sysctl_numa_balancing_scan_size); + unsigned int scan, floor; + unsigned int windows = 1; + + if (scan_size < MAX_SCAN_WINDOW) + windows = MAX_SCAN_WINDOW / scan_size; + floor = 1000 / windows; + + scan = sysctl_numa_balancing_scan_period_min / task_nr_scan_windows(p); + return max_t(unsigned int, floor, scan); +} + +static unsigned int task_scan_max(struct task_struct *p) +{ + unsigned int smin = task_scan_min(p); + unsigned int smax; + + /* Watch for min being lower than max due to floor calculations */ + smax = sysctl_numa_balancing_scan_period_max / task_nr_scan_windows(p); + return max(smin, smax); +} + +static void account_numa_enqueue(struct rq *rq, struct task_struct *p) +{ + rq->nr_numa_running += (p->numa_preferred_nid != -1); + rq->nr_preferred_running += (p->numa_preferred_nid == task_node(p)); +} + +static void account_numa_dequeue(struct rq *rq, struct task_struct *p) +{ + rq->nr_numa_running -= (p->numa_preferred_nid != -1); + rq->nr_preferred_running -= (p->numa_preferred_nid == task_node(p)); +} + +struct numa_group { + atomic_t refcount; + + spinlock_t lock; /* nr_tasks, tasks */ + int nr_tasks; + pid_t gid; + + struct rcu_head rcu; + nodemask_t active_nodes; + unsigned long total_faults; + /* + * Faults_cpu is used to decide whether memory should move + * towards the CPU. As a consequence, these stats are weighted + * more by CPU use than by memory faults. + */ + unsigned long *faults_cpu; + unsigned long faults[0]; +}; + +/* Shared or private faults. */ +#define NR_NUMA_HINT_FAULT_TYPES 2 + +/* Memory and CPU locality */ +#define NR_NUMA_HINT_FAULT_STATS (NR_NUMA_HINT_FAULT_TYPES * 2) + +/* Averaged statistics, and temporary buffers. */ +#define NR_NUMA_HINT_FAULT_BUCKETS (NR_NUMA_HINT_FAULT_STATS * 2) + +pid_t task_numa_group_id(struct task_struct *p) +{ + return p->numa_group ? p->numa_group->gid : 0; +} + +/* + * The averaged statistics, shared & private, memory & cpu, + * occupy the first half of the array. The second half of the + * array is for current counters, which are averaged into the + * first set by task_numa_placement. + */ +static inline int task_faults_idx(enum numa_faults_stats s, int nid, int priv) +{ + return NR_NUMA_HINT_FAULT_TYPES * (s * nr_node_ids + nid) + priv; +} + +static inline unsigned long task_faults(struct task_struct *p, int nid) +{ + if (!p->numa_faults) + return 0; + + return p->numa_faults[task_faults_idx(NUMA_MEM, nid, 0)] + + p->numa_faults[task_faults_idx(NUMA_MEM, nid, 1)]; +} + +static inline unsigned long group_faults(struct task_struct *p, int nid) +{ + if (!p->numa_group) + return 0; + + return p->numa_group->faults[task_faults_idx(NUMA_MEM, nid, 0)] + + p->numa_group->faults[task_faults_idx(NUMA_MEM, nid, 1)]; +} + +static inline unsigned long group_faults_cpu(struct numa_group *group, int nid) +{ + return group->faults_cpu[task_faults_idx(NUMA_MEM, nid, 0)] + + group->faults_cpu[task_faults_idx(NUMA_MEM, nid, 1)]; +} + +/* Handle placement on systems where not all nodes are directly connected. */ +static unsigned long score_nearby_nodes(struct task_struct *p, int nid, + int maxdist, bool task) +{ + unsigned long score = 0; + int node; + + /* + * All nodes are directly connected, and the same distance + * from each other. No need for fancy placement algorithms. + */ + if (sched_numa_topology_type == NUMA_DIRECT) + return 0; + + /* + * This code is called for each node, introducing N^2 complexity, + * which should be ok given the number of nodes rarely exceeds 8. + */ + for_each_online_node(node) { + unsigned long faults; + int dist = node_distance(nid, node); + + /* + * The furthest away nodes in the system are not interesting + * for placement; nid was already counted. + */ + if (dist == sched_max_numa_distance || node == nid) + continue; + + /* + * On systems with a backplane NUMA topology, compare groups + * of nodes, and move tasks towards the group with the most + * memory accesses. When comparing two nodes at distance + * "hoplimit", only nodes closer by than "hoplimit" are part + * of each group. Skip other nodes. + */ + if (sched_numa_topology_type == NUMA_BACKPLANE && + dist > maxdist) + continue; + + /* Add up the faults from nearby nodes. */ + if (task) + faults = task_faults(p, node); + else + faults = group_faults(p, node); + + /* + * On systems with a glueless mesh NUMA topology, there are + * no fixed "groups of nodes". Instead, nodes that are not + * directly connected bounce traffic through intermediate + * nodes; a numa_group can occupy any set of nodes. + * The further away a node is, the less the faults count. + * This seems to result in good task placement. + */ + if (sched_numa_topology_type == NUMA_GLUELESS_MESH) { + faults *= (sched_max_numa_distance - dist); + faults /= (sched_max_numa_distance - LOCAL_DISTANCE); + } + + score += faults; + } + + return score; +} + +/* + * These return the fraction of accesses done by a particular task, or + * task group, on a particular numa node. The group weight is given a + * larger multiplier, in order to group tasks together that are almost + * evenly spread out between numa nodes. + */ +static inline unsigned long task_weight(struct task_struct *p, int nid, + int dist) +{ + unsigned long faults, total_faults; + + if (!p->numa_faults) + return 0; + + total_faults = p->total_numa_faults; + + if (!total_faults) + return 0; + + faults = task_faults(p, nid); + faults += score_nearby_nodes(p, nid, dist, true); + + return 1000 * faults / total_faults; +} + +static inline unsigned long group_weight(struct task_struct *p, int nid, + int dist) +{ + unsigned long faults, total_faults; + + if (!p->numa_group) + return 0; + + total_faults = p->numa_group->total_faults; + + if (!total_faults) + return 0; + + faults = group_faults(p, nid); + faults += score_nearby_nodes(p, nid, dist, false); + + return 1000 * faults / total_faults; +} + +bool should_numa_migrate_memory(struct task_struct *p, struct page * page, + int src_nid, int dst_cpu) +{ + struct numa_group *ng = p->numa_group; + int dst_nid = cpu_to_node(dst_cpu); + int last_cpupid, this_cpupid; + + this_cpupid = cpu_pid_to_cpupid(dst_cpu, current->pid); + + /* + * Multi-stage node selection is used in conjunction with a periodic + * migration fault to build a temporal task<->page relation. By using + * a two-stage filter we remove short/unlikely relations. + * + * Using P(p) ~ n_p / n_t as per frequentist probability, we can equate + * a task's usage of a particular page (n_p) per total usage of this + * page (n_t) (in a given time-span) to a probability. + * + * Our periodic faults will sample this probability and getting the + * same result twice in a row, given these samples are fully + * independent, is then given by P(n)^2, provided our sample period + * is sufficiently short compared to the usage pattern. + * + * This quadric squishes small probabilities, making it less likely we + * act on an unlikely task<->page relation. + */ + last_cpupid = page_cpupid_xchg_last(page, this_cpupid); + if (!cpupid_pid_unset(last_cpupid) && + cpupid_to_nid(last_cpupid) != dst_nid) + return false; + + /* Always allow migrate on private faults */ + if (cpupid_match_pid(p, last_cpupid)) + return true; + + /* A shared fault, but p->numa_group has not been set up yet. */ + if (!ng) + return true; + + /* + * Do not migrate if the destination is not a node that + * is actively used by this numa group. + */ + if (!node_isset(dst_nid, ng->active_nodes)) + return false; + + /* + * Source is a node that is not actively used by this + * numa group, while the destination is. Migrate. + */ + if (!node_isset(src_nid, ng->active_nodes)) + return true; + + /* + * Both source and destination are nodes in active + * use by this numa group. Maximize memory bandwidth + * by migrating from more heavily used groups, to less + * heavily used ones, spreading the load around. + * Use a 1/4 hysteresis to avoid spurious page movement. + */ + return group_faults(p, dst_nid) < (group_faults(p, src_nid) * 3 / 4); +} + +static unsigned long weighted_cpuload(const int cpu); +static unsigned long source_load(int cpu, int type); +static unsigned long target_load(int cpu, int type); +static unsigned long capacity_of(int cpu); +static long effective_load(struct task_group *tg, int cpu, long wl, long wg); + +/* Cached statistics for all CPUs within a node */ +struct numa_stats { + unsigned long nr_running; + unsigned long load; + + /* Total compute capacity of CPUs on a node */ + unsigned long compute_capacity; + + /* Approximate capacity in terms of runnable tasks on a node */ + unsigned long task_capacity; + int has_free_capacity; +}; + +/* + * XXX borrowed from update_sg_lb_stats + */ +static void update_numa_stats(struct numa_stats *ns, int nid) +{ + int smt, cpu, cpus = 0; + unsigned long capacity; + + memset(ns, 0, sizeof(*ns)); + for_each_cpu(cpu, cpumask_of_node(nid)) { + struct rq *rq = cpu_rq(cpu); + + ns->nr_running += rq->nr_running; + ns->load += weighted_cpuload(cpu); + ns->compute_capacity += capacity_of(cpu); + + cpus++; + } + + /* + * If we raced with hotplug and there are no CPUs left in our mask + * the @ns structure is NULL'ed and task_numa_compare() will + * not find this node attractive. + * + * We'll either bail at !has_free_capacity, or we'll detect a huge + * imbalance and bail there. + */ + if (!cpus) + return; + + /* smt := ceil(cpus / capacity), assumes: 1 < smt_power < 2 */ + smt = DIV_ROUND_UP(SCHED_CAPACITY_SCALE * cpus, ns->compute_capacity); + capacity = cpus / smt; /* cores */ + + ns->task_capacity = min_t(unsigned, capacity, + DIV_ROUND_CLOSEST(ns->compute_capacity, SCHED_CAPACITY_SCALE)); + ns->has_free_capacity = (ns->nr_running < ns->task_capacity); +} + +struct task_numa_env { + struct task_struct *p; + + int src_cpu, src_nid; + int dst_cpu, dst_nid; + + struct numa_stats src_stats, dst_stats; + + int imbalance_pct; + int dist; + + struct task_struct *best_task; + long best_imp; + int best_cpu; +}; + +static void task_numa_assign(struct task_numa_env *env, + struct task_struct *p, long imp) +{ + if (env->best_task) + put_task_struct(env->best_task); + if (p) + get_task_struct(p); + + env->best_task = p; + env->best_imp = imp; + env->best_cpu = env->dst_cpu; +} + +static bool load_too_imbalanced(long src_load, long dst_load, + struct task_numa_env *env) +{ + long src_capacity, dst_capacity; + long orig_src_load; + long load_a, load_b; + long moved_load; + long imb; + + /* + * The load is corrected for the CPU capacity available on each node. + * + * src_load dst_load + * ------------ vs --------- + * src_capacity dst_capacity + */ + src_capacity = env->src_stats.compute_capacity; + dst_capacity = env->dst_stats.compute_capacity; + + /* We care about the slope of the imbalance, not the direction. */ + load_a = dst_load; + load_b = src_load; + if (load_a < load_b) + swap(load_a, load_b); + + /* Is the difference below the threshold? */ + imb = load_a * src_capacity * 100 - + load_b * dst_capacity * env->imbalance_pct; + if (imb <= 0) + return false; + + /* + * The imbalance is above the allowed threshold. + * Allow a move that brings us closer to a balanced situation, + * without moving things past the point of balance. + */ + orig_src_load = env->src_stats.load; + + /* + * In a task swap, there will be one load moving from src to dst, + * and another moving back. This is the net sum of both moves. + * A simple task move will always have a positive value. + * Allow the move if it brings the system closer to a balanced + * situation, without crossing over the balance point. + */ + moved_load = orig_src_load - src_load; + + if (moved_load > 0) + /* Moving src -> dst. Did we overshoot balance? */ + return src_load * dst_capacity < dst_load * src_capacity; + else + /* Moving dst -> src. Did we overshoot balance? */ + return dst_load * src_capacity < src_load * dst_capacity; +} + +/* + * This checks if the overall compute and NUMA accesses of the system would + * be improved if the source tasks was migrated to the target dst_cpu taking + * into account that it might be best if task running on the dst_cpu should + * be exchanged with the source task + */ +static void task_numa_compare(struct task_numa_env *env, + long taskimp, long groupimp) +{ + struct rq *src_rq = cpu_rq(env->src_cpu); + struct rq *dst_rq = cpu_rq(env->dst_cpu); + struct task_struct *cur; + long src_load, dst_load; + long load; + long imp = env->p->numa_group ? groupimp : taskimp; + long moveimp = imp; + int dist = env->dist; + + rcu_read_lock(); + + raw_spin_lock_irq(&dst_rq->lock); + cur = dst_rq->curr; + /* + * No need to move the exiting task, and this ensures that ->curr + * wasn't reaped and thus get_task_struct() in task_numa_assign() + * is safe under RCU read lock. + * Note that rcu_read_lock() itself can't protect from the final + * put_task_struct() after the last schedule(). + */ + if ((cur->flags & PF_EXITING) || is_idle_task(cur)) + cur = NULL; + raw_spin_unlock_irq(&dst_rq->lock); + + /* + * Because we have preemption enabled we can get migrated around and + * end try selecting ourselves (current == env->p) as a swap candidate. + */ + if (cur == env->p) + goto unlock; + + /* + * "imp" is the fault differential for the source task between the + * source and destination node. Calculate the total differential for + * the source task and potential destination task. The more negative + * the value is, the more rmeote accesses that would be expected to + * be incurred if the tasks were swapped. + */ + if (cur) { + /* Skip this swap candidate if cannot move to the source cpu */ + if (!cpumask_test_cpu(env->src_cpu, tsk_cpus_allowed(cur))) + goto unlock; + + /* + * If dst and source tasks are in the same NUMA group, or not + * in any group then look only at task weights. + */ + if (cur->numa_group == env->p->numa_group) { + imp = taskimp + task_weight(cur, env->src_nid, dist) - + task_weight(cur, env->dst_nid, dist); + /* + * Add some hysteresis to prevent swapping the + * tasks within a group over tiny differences. + */ + if (cur->numa_group) + imp -= imp/16; + } else { + /* + * Compare the group weights. If a task is all by + * itself (not part of a group), use the task weight + * instead. + */ + if (cur->numa_group) + imp += group_weight(cur, env->src_nid, dist) - + group_weight(cur, env->dst_nid, dist); + else + imp += task_weight(cur, env->src_nid, dist) - + task_weight(cur, env->dst_nid, dist); + } + } + + if (imp <= env->best_imp && moveimp <= env->best_imp) + goto unlock; + + if (!cur) { + /* Is there capacity at our destination? */ + if (env->src_stats.nr_running <= env->src_stats.task_capacity && + !env->dst_stats.has_free_capacity) + goto unlock; + + goto balance; + } + + /* Balance doesn't matter much if we're running a task per cpu */ + if (imp > env->best_imp && src_rq->nr_running == 1 && + dst_rq->nr_running == 1) + goto assign; + + /* + * In the overloaded case, try and keep the load balanced. + */ +balance: + load = task_h_load(env->p); + dst_load = env->dst_stats.load + load; + src_load = env->src_stats.load - load; + + if (moveimp > imp && moveimp > env->best_imp) { + /* + * If the improvement from just moving env->p direction is + * better than swapping tasks around, check if a move is + * possible. Store a slightly smaller score than moveimp, + * so an actually idle CPU will win. + */ + if (!load_too_imbalanced(src_load, dst_load, env)) { + imp = moveimp - 1; + cur = NULL; + goto assign; + } + } + + if (imp <= env->best_imp) + goto unlock; + + if (cur) { + load = task_h_load(cur); + dst_load -= load; + src_load += load; + } + + if (load_too_imbalanced(src_load, dst_load, env)) + goto unlock; + + /* + * One idle CPU per node is evaluated for a task numa move. + * Call select_idle_sibling to maybe find a better one. + */ + if (!cur) + env->dst_cpu = select_idle_sibling(env->p, env->dst_cpu); + +assign: + task_numa_assign(env, cur, imp); +unlock: + rcu_read_unlock(); +} + +static void task_numa_find_cpu(struct task_numa_env *env, + long taskimp, long groupimp) +{ + int cpu; + + for_each_cpu(cpu, cpumask_of_node(env->dst_nid)) { + /* Skip this CPU if the source task cannot migrate */ + if (!cpumask_test_cpu(cpu, tsk_cpus_allowed(env->p))) + continue; + + env->dst_cpu = cpu; + task_numa_compare(env, taskimp, groupimp); + } +} + +static int task_numa_migrate(struct task_struct *p) +{ + struct task_numa_env env = { + .p = p, + + .src_cpu = task_cpu(p), + .src_nid = task_node(p), + + .imbalance_pct = 112, + + .best_task = NULL, + .best_imp = 0, + .best_cpu = -1 + }; + struct sched_domain *sd; + unsigned long taskweight, groupweight; + int nid, ret, dist; + long taskimp, groupimp; + + /* + * Pick the lowest SD_NUMA domain, as that would have the smallest + * imbalance and would be the first to start moving tasks about. + * + * And we want to avoid any moving of tasks about, as that would create + * random movement of tasks -- counter the numa conditions we're trying + * to satisfy here. + */ + rcu_read_lock(); + sd = rcu_dereference(per_cpu(sd_numa, env.src_cpu)); + if (sd) + env.imbalance_pct = 100 + (sd->imbalance_pct - 100) / 2; + rcu_read_unlock(); + + /* + * Cpusets can break the scheduler domain tree into smaller + * balance domains, some of which do not cross NUMA boundaries. + * Tasks that are "trapped" in such domains cannot be migrated + * elsewhere, so there is no point in (re)trying. + */ + if (unlikely(!sd)) { + p->numa_preferred_nid = task_node(p); + return -EINVAL; + } + + env.dst_nid = p->numa_preferred_nid; + dist = env.dist = node_distance(env.src_nid, env.dst_nid); + taskweight = task_weight(p, env.src_nid, dist); + groupweight = group_weight(p, env.src_nid, dist); + update_numa_stats(&env.src_stats, env.src_nid); + taskimp = task_weight(p, env.dst_nid, dist) - taskweight; + groupimp = group_weight(p, env.dst_nid, dist) - groupweight; + update_numa_stats(&env.dst_stats, env.dst_nid); + + /* Try to find a spot on the preferred nid. */ + task_numa_find_cpu(&env, taskimp, groupimp); + + /* + * Look at other nodes in these cases: + * - there is no space available on the preferred_nid + * - the task is part of a numa_group that is interleaved across + * multiple NUMA nodes; in order to better consolidate the group, + * we need to check other locations. + */ + if (env.best_cpu == -1 || (p->numa_group && + nodes_weight(p->numa_group->active_nodes) > 1)) { + for_each_online_node(nid) { + if (nid == env.src_nid || nid == p->numa_preferred_nid) + continue; + + dist = node_distance(env.src_nid, env.dst_nid); + if (sched_numa_topology_type == NUMA_BACKPLANE && + dist != env.dist) { + taskweight = task_weight(p, env.src_nid, dist); + groupweight = group_weight(p, env.src_nid, dist); + } + + /* Only consider nodes where both task and groups benefit */ + taskimp = task_weight(p, nid, dist) - taskweight; + groupimp = group_weight(p, nid, dist) - groupweight; + if (taskimp < 0 && groupimp < 0) + continue; + + env.dist = dist; + env.dst_nid = nid; + update_numa_stats(&env.dst_stats, env.dst_nid); + task_numa_find_cpu(&env, taskimp, groupimp); + } + } + + /* + * If the task is part of a workload that spans multiple NUMA nodes, + * and is migrating into one of the workload's active nodes, remember + * this node as the task's preferred numa node, so the workload can + * settle down. + * A task that migrated to a second choice node will be better off + * trying for a better one later. Do not set the preferred node here. + */ + if (p->numa_group) { + if (env.best_cpu == -1) + nid = env.src_nid; + else + nid = env.dst_nid; + + if (node_isset(nid, p->numa_group->active_nodes)) + sched_setnuma(p, env.dst_nid); + } + + /* No better CPU than the current one was found. */ + if (env.best_cpu == -1) + return -EAGAIN; + + /* + * Reset the scan period if the task is being rescheduled on an + * alternative node to recheck if the tasks is now properly placed. + */ + p->numa_scan_period = task_scan_min(p); + + if (env.best_task == NULL) { + ret = migrate_task_to(p, env.best_cpu); + if (ret != 0) + trace_sched_stick_numa(p, env.src_cpu, env.best_cpu); + return ret; + } + + ret = migrate_swap(p, env.best_task); + if (ret != 0) + trace_sched_stick_numa(p, env.src_cpu, task_cpu(env.best_task)); + put_task_struct(env.best_task); + return ret; +} + +/* Attempt to migrate a task to a CPU on the preferred node. */ +static void numa_migrate_preferred(struct task_struct *p) +{ + unsigned long interval = HZ; + + /* This task has no NUMA fault statistics yet */ + if (unlikely(p->numa_preferred_nid == -1 || !p->numa_faults)) + return; + + /* Periodically retry migrating the task to the preferred node */ + interval = min(interval, msecs_to_jiffies(p->numa_scan_period) / 16); + p->numa_migrate_retry = jiffies + interval; + + /* Success if task is already running on preferred CPU */ + if (task_node(p) == p->numa_preferred_nid) + return; + + /* Otherwise, try migrate to a CPU on the preferred node */ + task_numa_migrate(p); +} + +/* + * Find the nodes on which the workload is actively running. We do this by + * tracking the nodes from which NUMA hinting faults are triggered. This can + * be different from the set of nodes where the workload's memory is currently + * located. + * + * The bitmask is used to make smarter decisions on when to do NUMA page + * migrations, To prevent flip-flopping, and excessive page migrations, nodes + * are added when they cause over 6/16 of the maximum number of faults, but + * only removed when they drop below 3/16. + */ +static void update_numa_active_node_mask(struct numa_group *numa_group) +{ + unsigned long faults, max_faults = 0; + int nid; + + for_each_online_node(nid) { + faults = group_faults_cpu(numa_group, nid); + if (faults > max_faults) + max_faults = faults; + } + + for_each_online_node(nid) { + faults = group_faults_cpu(numa_group, nid); + if (!node_isset(nid, numa_group->active_nodes)) { + if (faults > max_faults * 6 / 16) + node_set(nid, numa_group->active_nodes); + } else if (faults < max_faults * 3 / 16) + node_clear(nid, numa_group->active_nodes); + } +} + +/* + * When adapting the scan rate, the period is divided into NUMA_PERIOD_SLOTS + * increments. The more local the fault statistics are, the higher the scan + * period will be for the next scan window. If local/(local+remote) ratio is + * below NUMA_PERIOD_THRESHOLD (where range of ratio is 1..NUMA_PERIOD_SLOTS) + * the scan period will decrease. Aim for 70% local accesses. + */ +#define NUMA_PERIOD_SLOTS 10 +#define NUMA_PERIOD_THRESHOLD 7 + +/* + * Increase the scan period (slow down scanning) if the majority of + * our memory is already on our local node, or if the majority of + * the page accesses are shared with other processes. + * Otherwise, decrease the scan period. + */ +static void update_task_scan_period(struct task_struct *p, + unsigned long shared, unsigned long private) +{ + unsigned int period_slot; + int ratio; + int diff; + + unsigned long remote = p->numa_faults_locality[0]; + unsigned long local = p->numa_faults_locality[1]; + + /* + * If there were no record hinting faults then either the task is + * completely idle or all activity is areas that are not of interest + * to automatic numa balancing. Related to that, if there were failed + * migration then it implies we are migrating too quickly or the local + * node is overloaded. In either case, scan slower + */ + if (local + shared == 0 || p->numa_faults_locality[2]) { + p->numa_scan_period = min(p->numa_scan_period_max, + p->numa_scan_period << 1); + + p->mm->numa_next_scan = jiffies + + msecs_to_jiffies(p->numa_scan_period); + + return; + } + + /* + * Prepare to scale scan period relative to the current period. + * == NUMA_PERIOD_THRESHOLD scan period stays the same + * < NUMA_PERIOD_THRESHOLD scan period decreases (scan faster) + * >= NUMA_PERIOD_THRESHOLD scan period increases (scan slower) + */ + period_slot = DIV_ROUND_UP(p->numa_scan_period, NUMA_PERIOD_SLOTS); + ratio = (local * NUMA_PERIOD_SLOTS) / (local + remote); + if (ratio >= NUMA_PERIOD_THRESHOLD) { + int slot = ratio - NUMA_PERIOD_THRESHOLD; + if (!slot) + slot = 1; + diff = slot * period_slot; + } else { + diff = -(NUMA_PERIOD_THRESHOLD - ratio) * period_slot; + + /* + * Scale scan rate increases based on sharing. There is an + * inverse relationship between the degree of sharing and + * the adjustment made to the scanning period. Broadly + * speaking the intent is that there is little point + * scanning faster if shared accesses dominate as it may + * simply bounce migrations uselessly + */ + ratio = DIV_ROUND_UP(private * NUMA_PERIOD_SLOTS, (private + shared + 1)); + diff = (diff * ratio) / NUMA_PERIOD_SLOTS; + } + + p->numa_scan_period = clamp(p->numa_scan_period + diff, + task_scan_min(p), task_scan_max(p)); + memset(p->numa_faults_locality, 0, sizeof(p->numa_faults_locality)); +} + +/* + * Get the fraction of time the task has been running since the last + * NUMA placement cycle. The scheduler keeps similar statistics, but + * decays those on a 32ms period, which is orders of magnitude off + * from the dozens-of-seconds NUMA balancing period. Use the scheduler + * stats only if the task is so new there are no NUMA statistics yet. + */ +static u64 numa_get_avg_runtime(struct task_struct *p, u64 *period) +{ + u64 runtime, delta, now; + /* Use the start of this time slice to avoid calculations. */ + now = p->se.exec_start; + runtime = p->se.sum_exec_runtime; + + if (p->last_task_numa_placement) { + delta = runtime - p->last_sum_exec_runtime; + *period = now - p->last_task_numa_placement; + } else { + delta = p->se.avg.runnable_avg_sum; + *period = p->se.avg.avg_period; + } + + p->last_sum_exec_runtime = runtime; + p->last_task_numa_placement = now; + + return delta; +} + +/* + * Determine the preferred nid for a task in a numa_group. This needs to + * be done in a way that produces consistent results with group_weight, + * otherwise workloads might not converge. + */ +static int preferred_group_nid(struct task_struct *p, int nid) +{ + nodemask_t nodes; + int dist; + + /* Direct connections between all NUMA nodes. */ + if (sched_numa_topology_type == NUMA_DIRECT) + return nid; + + /* + * On a system with glueless mesh NUMA topology, group_weight + * scores nodes according to the number of NUMA hinting faults on + * both the node itself, and on nearby nodes. + */ + if (sched_numa_topology_type == NUMA_GLUELESS_MESH) { + unsigned long score, max_score = 0; + int node, max_node = nid; + + dist = sched_max_numa_distance; + + for_each_online_node(node) { + score = group_weight(p, node, dist); + if (score > max_score) { + max_score = score; + max_node = node; + } + } + return max_node; + } + + /* + * Finding the preferred nid in a system with NUMA backplane + * interconnect topology is more involved. The goal is to locate + * tasks from numa_groups near each other in the system, and + * untangle workloads from different sides of the system. This requires + * searching down the hierarchy of node groups, recursively searching + * inside the highest scoring group of nodes. The nodemask tricks + * keep the complexity of the search down. + */ + nodes = node_online_map; + for (dist = sched_max_numa_distance; dist > LOCAL_DISTANCE; dist--) { + unsigned long max_faults = 0; + nodemask_t max_group = NODE_MASK_NONE; + int a, b; + + /* Are there nodes at this distance from each other? */ + if (!find_numa_distance(dist)) + continue; + + for_each_node_mask(a, nodes) { + unsigned long faults = 0; + nodemask_t this_group; + nodes_clear(this_group); + + /* Sum group's NUMA faults; includes a==b case. */ + for_each_node_mask(b, nodes) { + if (node_distance(a, b) < dist) { + faults += group_faults(p, b); + node_set(b, this_group); + node_clear(b, nodes); + } + } + + /* Remember the top group. */ + if (faults > max_faults) { + max_faults = faults; + max_group = this_group; + /* + * subtle: at the smallest distance there is + * just one node left in each "group", the + * winner is the preferred nid. + */ + nid = a; + } + } + /* Next round, evaluate the nodes within max_group. */ + if (!max_faults) + break; + nodes = max_group; + } + return nid; +} + +static void task_numa_placement(struct task_struct *p) +{ + int seq, nid, max_nid = -1, max_group_nid = -1; + unsigned long max_faults = 0, max_group_faults = 0; + unsigned long fault_types[2] = { 0, 0 }; + unsigned long total_faults; + u64 runtime, period; + spinlock_t *group_lock = NULL; + + seq = ACCESS_ONCE(p->mm->numa_scan_seq); + if (p->numa_scan_seq == seq) + return; + p->numa_scan_seq = seq; + p->numa_scan_period_max = task_scan_max(p); + + total_faults = p->numa_faults_locality[0] + + p->numa_faults_locality[1]; + runtime = numa_get_avg_runtime(p, &period); + + /* If the task is part of a group prevent parallel updates to group stats */ + if (p->numa_group) { + group_lock = &p->numa_group->lock; + spin_lock_irq(group_lock); + } + + /* Find the node with the highest number of faults */ + for_each_online_node(nid) { + /* Keep track of the offsets in numa_faults array */ + int mem_idx, membuf_idx, cpu_idx, cpubuf_idx; + unsigned long faults = 0, group_faults = 0; + int priv; + + for (priv = 0; priv < NR_NUMA_HINT_FAULT_TYPES; priv++) { + long diff, f_diff, f_weight; + + mem_idx = task_faults_idx(NUMA_MEM, nid, priv); + membuf_idx = task_faults_idx(NUMA_MEMBUF, nid, priv); + cpu_idx = task_faults_idx(NUMA_CPU, nid, priv); + cpubuf_idx = task_faults_idx(NUMA_CPUBUF, nid, priv); + + /* Decay existing window, copy faults since last scan */ + diff = p->numa_faults[membuf_idx] - p->numa_faults[mem_idx] / 2; + fault_types[priv] += p->numa_faults[membuf_idx]; + p->numa_faults[membuf_idx] = 0; + + /* + * Normalize the faults_from, so all tasks in a group + * count according to CPU use, instead of by the raw + * number of faults. Tasks with little runtime have + * little over-all impact on throughput, and thus their + * faults are less important. + */ + f_weight = div64_u64(runtime << 16, period + 1); + f_weight = (f_weight * p->numa_faults[cpubuf_idx]) / + (total_faults + 1); + f_diff = f_weight - p->numa_faults[cpu_idx] / 2; + p->numa_faults[cpubuf_idx] = 0; + + p->numa_faults[mem_idx] += diff; + p->numa_faults[cpu_idx] += f_diff; + faults += p->numa_faults[mem_idx]; + p->total_numa_faults += diff; + if (p->numa_group) { + /* + * safe because we can only change our own group + * + * mem_idx represents the offset for a given + * nid and priv in a specific region because it + * is at the beginning of the numa_faults array. + */ + p->numa_group->faults[mem_idx] += diff; + p->numa_group->faults_cpu[mem_idx] += f_diff; + p->numa_group->total_faults += diff; + group_faults += p->numa_group->faults[mem_idx]; + } + } + + if (faults > max_faults) { + max_faults = faults; + max_nid = nid; + } + + if (group_faults > max_group_faults) { + max_group_faults = group_faults; + max_group_nid = nid; + } + } + + update_task_scan_period(p, fault_types[0], fault_types[1]); + + if (p->numa_group) { + update_numa_active_node_mask(p->numa_group); + spin_unlock_irq(group_lock); + max_nid = preferred_group_nid(p, max_group_nid); + } + + if (max_faults) { + /* Set the new preferred node */ + if (max_nid != p->numa_preferred_nid) + sched_setnuma(p, max_nid); + + if (task_node(p) != p->numa_preferred_nid) + numa_migrate_preferred(p); + } +} + +static inline int get_numa_group(struct numa_group *grp) +{ + return atomic_inc_not_zero(&grp->refcount); +} + +static inline void put_numa_group(struct numa_group *grp) +{ + if (atomic_dec_and_test(&grp->refcount)) + kfree_rcu(grp, rcu); +} + +static void task_numa_group(struct task_struct *p, int cpupid, int flags, + int *priv) +{ + struct numa_group *grp, *my_grp; + struct task_struct *tsk; + bool join = false; + int cpu = cpupid_to_cpu(cpupid); + int i; + + if (unlikely(!p->numa_group)) { + unsigned int size = sizeof(struct numa_group) + + 4*nr_node_ids*sizeof(unsigned long); + + grp = kzalloc(size, GFP_KERNEL | __GFP_NOWARN); + if (!grp) + return; + + atomic_set(&grp->refcount, 1); + spin_lock_init(&grp->lock); + grp->gid = p->pid; + /* Second half of the array tracks nids where faults happen */ + grp->faults_cpu = grp->faults + NR_NUMA_HINT_FAULT_TYPES * + nr_node_ids; + + node_set(task_node(current), grp->active_nodes); + + for (i = 0; i < NR_NUMA_HINT_FAULT_STATS * nr_node_ids; i++) + grp->faults[i] = p->numa_faults[i]; + + grp->total_faults = p->total_numa_faults; + + grp->nr_tasks++; + rcu_assign_pointer(p->numa_group, grp); + } + + rcu_read_lock(); + tsk = ACCESS_ONCE(cpu_rq(cpu)->curr); + + if (!cpupid_match_pid(tsk, cpupid)) + goto no_join; + + grp = rcu_dereference(tsk->numa_group); + if (!grp) + goto no_join; + + my_grp = p->numa_group; + if (grp == my_grp) + goto no_join; + + /* + * Only join the other group if its bigger; if we're the bigger group, + * the other task will join us. + */ + if (my_grp->nr_tasks > grp->nr_tasks) + goto no_join; + + /* + * Tie-break on the grp address. + */ + if (my_grp->nr_tasks == grp->nr_tasks && my_grp > grp) + goto no_join; + + /* Always join threads in the same process. */ + if (tsk->mm == current->mm) + join = true; + + /* Simple filter to avoid false positives due to PID collisions */ + if (flags & TNF_SHARED) + join = true; + + /* Update priv based on whether false sharing was detected */ + *priv = !join; + + if (join && !get_numa_group(grp)) + goto no_join; + + rcu_read_unlock(); + + if (!join) + return; + + BUG_ON(irqs_disabled()); + double_lock_irq(&my_grp->lock, &grp->lock); + + for (i = 0; i < NR_NUMA_HINT_FAULT_STATS * nr_node_ids; i++) { + my_grp->faults[i] -= p->numa_faults[i]; + grp->faults[i] += p->numa_faults[i]; + } + my_grp->total_faults -= p->total_numa_faults; + grp->total_faults += p->total_numa_faults; + + my_grp->nr_tasks--; + grp->nr_tasks++; + + spin_unlock(&my_grp->lock); + spin_unlock_irq(&grp->lock); + + rcu_assign_pointer(p->numa_group, grp); + + put_numa_group(my_grp); + return; + +no_join: + rcu_read_unlock(); + return; +} + +void task_numa_free(struct task_struct *p) +{ + struct numa_group *grp = p->numa_group; + void *numa_faults = p->numa_faults; + unsigned long flags; + int i; + + if (grp) { + spin_lock_irqsave(&grp->lock, flags); + for (i = 0; i < NR_NUMA_HINT_FAULT_STATS * nr_node_ids; i++) + grp->faults[i] -= p->numa_faults[i]; + grp->total_faults -= p->total_numa_faults; + + grp->nr_tasks--; + spin_unlock_irqrestore(&grp->lock, flags); + RCU_INIT_POINTER(p->numa_group, NULL); + put_numa_group(grp); + } + + p->numa_faults = NULL; + kfree(numa_faults); +} + +/* + * Got a PROT_NONE fault for a page on @node. + */ +void task_numa_fault(int last_cpupid, int mem_node, int pages, int flags) +{ + struct task_struct *p = current; + bool migrated = flags & TNF_MIGRATED; + int cpu_node = task_node(current); + int local = !!(flags & TNF_FAULT_LOCAL); + int priv; + + if (!numabalancing_enabled) + return; + + /* for example, ksmd faulting in a user's mm */ + if (!p->mm) + return; + + /* Allocate buffer to track faults on a per-node basis */ + if (unlikely(!p->numa_faults)) { + int size = sizeof(*p->numa_faults) * + NR_NUMA_HINT_FAULT_BUCKETS * nr_node_ids; + + p->numa_faults = kzalloc(size, GFP_KERNEL|__GFP_NOWARN); + if (!p->numa_faults) + return; + + p->total_numa_faults = 0; + memset(p->numa_faults_locality, 0, sizeof(p->numa_faults_locality)); + } + + /* + * First accesses are treated as private, otherwise consider accesses + * to be private if the accessing pid has not changed + */ + if (unlikely(last_cpupid == (-1 & LAST_CPUPID_MASK))) { + priv = 1; + } else { + priv = cpupid_match_pid(p, last_cpupid); + if (!priv && !(flags & TNF_NO_GROUP)) + task_numa_group(p, last_cpupid, flags, &priv); + } + + /* + * If a workload spans multiple NUMA nodes, a shared fault that + * occurs wholly within the set of nodes that the workload is + * actively using should be counted as local. This allows the + * scan rate to slow down when a workload has settled down. + */ + if (!priv && !local && p->numa_group && + node_isset(cpu_node, p->numa_group->active_nodes) && + node_isset(mem_node, p->numa_group->active_nodes)) + local = 1; + + task_numa_placement(p); + + /* + * Retry task to preferred node migration periodically, in case it + * case it previously failed, or the scheduler moved us. + */ + if (time_after(jiffies, p->numa_migrate_retry)) + numa_migrate_preferred(p); + + if (migrated) + p->numa_pages_migrated += pages; + if (flags & TNF_MIGRATE_FAIL) + p->numa_faults_locality[2] += pages; + + p->numa_faults[task_faults_idx(NUMA_MEMBUF, mem_node, priv)] += pages; + p->numa_faults[task_faults_idx(NUMA_CPUBUF, cpu_node, priv)] += pages; + p->numa_faults_locality[local] += pages; +} + +static void reset_ptenuma_scan(struct task_struct *p) +{ + ACCESS_ONCE(p->mm->numa_scan_seq)++; + p->mm->numa_scan_offset = 0; +} + +/* + * The expensive part of numa migration is done from task_work context. + * Triggered from task_tick_numa(). + */ +void task_numa_work(struct callback_head *work) +{ + unsigned long migrate, next_scan, now = jiffies; + struct task_struct *p = current; + struct mm_struct *mm = p->mm; + struct vm_area_struct *vma; + unsigned long start, end; + unsigned long nr_pte_updates = 0; + long pages; + + WARN_ON_ONCE(p != container_of(work, struct task_struct, numa_work)); + + work->next = work; /* protect against double add */ + /* + * Who cares about NUMA placement when they're dying. + * + * NOTE: make sure not to dereference p->mm before this check, + * exit_task_work() happens _after_ exit_mm() so we could be called + * without p->mm even though we still had it when we enqueued this + * work. + */ + if (p->flags & PF_EXITING) + return; + + if (!mm->numa_next_scan) { + mm->numa_next_scan = now + + msecs_to_jiffies(sysctl_numa_balancing_scan_delay); + } + + /* + * Enforce maximal scan/migration frequency.. + */ + migrate = mm->numa_next_scan; + if (time_before(now, migrate)) + return; + + if (p->numa_scan_period == 0) { + p->numa_scan_period_max = task_scan_max(p); + p->numa_scan_period = task_scan_min(p); + } + + next_scan = now + msecs_to_jiffies(p->numa_scan_period); + if (cmpxchg(&mm->numa_next_scan, migrate, next_scan) != migrate) + return; + + /* + * Delay this task enough that another task of this mm will likely win + * the next time around. + */ + p->node_stamp += 2 * TICK_NSEC; + + start = mm->numa_scan_offset; + pages = sysctl_numa_balancing_scan_size; + pages <<= 20 - PAGE_SHIFT; /* MB in pages */ + if (!pages) + return; + + down_read(&mm->mmap_sem); + vma = find_vma(mm, start); + if (!vma) { + reset_ptenuma_scan(p); + start = 0; + vma = mm->mmap; + } + for (; vma; vma = vma->vm_next) { + if (!vma_migratable(vma) || !vma_policy_mof(vma) || + is_vm_hugetlb_page(vma) || (vma->vm_flags & VM_MIXEDMAP)) { + continue; + } + + /* + * Shared library pages mapped by multiple processes are not + * migrated as it is expected they are cache replicated. Avoid + * hinting faults in read-only file-backed mappings or the vdso + * as migrating the pages will be of marginal benefit. + */ + if (!vma->vm_mm || + (vma->vm_file && (vma->vm_flags & (VM_READ|VM_WRITE)) == (VM_READ))) + continue; + + /* + * Skip inaccessible VMAs to avoid any confusion between + * PROT_NONE and NUMA hinting ptes + */ + if (!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE))) + continue; + + do { + start = max(start, vma->vm_start); + end = ALIGN(start + (pages << PAGE_SHIFT), HPAGE_SIZE); + end = min(end, vma->vm_end); + nr_pte_updates += change_prot_numa(vma, start, end); + + /* + * Scan sysctl_numa_balancing_scan_size but ensure that + * at least one PTE is updated so that unused virtual + * address space is quickly skipped. + */ + if (nr_pte_updates) + pages -= (end - start) >> PAGE_SHIFT; + + start = end; + if (pages <= 0) + goto out; + + cond_resched(); + } while (end != vma->vm_end); + } + +out: + /* + * It is possible to reach the end of the VMA list but the last few + * VMAs are not guaranteed to the vma_migratable. If they are not, we + * would find the !migratable VMA on the next scan but not reset the + * scanner to the start so check it now. + */ + if (vma) + mm->numa_scan_offset = start; + else + reset_ptenuma_scan(p); + up_read(&mm->mmap_sem); +} + +/* + * Drive the periodic memory faults.. + */ +void task_tick_numa(struct rq *rq, struct task_struct *curr) +{ + struct callback_head *work = &curr->numa_work; + u64 period, now; + + /* + * We don't care about NUMA placement if we don't have memory. + */ + if (!curr->mm || (curr->flags & PF_EXITING) || work->next != work) + return; + + /* + * Using runtime rather than walltime has the dual advantage that + * we (mostly) drive the selection from busy threads and that the + * task needs to have done some actual work before we bother with + * NUMA placement. + */ + now = curr->se.sum_exec_runtime; + period = (u64)curr->numa_scan_period * NSEC_PER_MSEC; + + if (now - curr->node_stamp > period) { + if (!curr->node_stamp) + curr->numa_scan_period = task_scan_min(curr); + curr->node_stamp += period; + + if (!time_before(jiffies, curr->mm->numa_next_scan)) { + init_task_work(work, task_numa_work); /* TODO: move this into sched_fork() */ + task_work_add(curr, work, true); + } + } +} +#else +static void task_tick_numa(struct rq *rq, struct task_struct *curr) +{ +} + +static inline void account_numa_enqueue(struct rq *rq, struct task_struct *p) +{ +} + +static inline void account_numa_dequeue(struct rq *rq, struct task_struct *p) +{ +} +#endif /* CONFIG_NUMA_BALANCING */ + +static void +account_entity_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se) +{ + update_load_add(&cfs_rq->load, se->load.weight); + if (!parent_entity(se)) + update_load_add(&rq_of(cfs_rq)->load, se->load.weight); +#ifdef CONFIG_SMP + if (entity_is_task(se)) { + struct rq *rq = rq_of(cfs_rq); + + account_numa_enqueue(rq, task_of(se)); + list_add(&se->group_node, &rq->cfs_tasks); + } +#endif + cfs_rq->nr_running++; +} + +static void +account_entity_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se) +{ + update_load_sub(&cfs_rq->load, se->load.weight); + if (!parent_entity(se)) + update_load_sub(&rq_of(cfs_rq)->load, se->load.weight); + if (entity_is_task(se)) { + account_numa_dequeue(rq_of(cfs_rq), task_of(se)); + list_del_init(&se->group_node); + } + cfs_rq->nr_running--; +} + +#ifdef CONFIG_FAIR_GROUP_SCHED +# ifdef CONFIG_SMP +static inline long calc_tg_weight(struct task_group *tg, struct cfs_rq *cfs_rq) +{ + long tg_weight; + + /* + * Use this CPU's actual weight instead of the last load_contribution + * to gain a more accurate current total weight. See + * update_cfs_rq_load_contribution(). + */ + tg_weight = atomic_long_read(&tg->load_avg); + tg_weight -= cfs_rq->tg_load_contrib; + tg_weight += cfs_rq->load.weight; + + return tg_weight; +} + +static long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg) +{ + long tg_weight, load, shares; + + tg_weight = calc_tg_weight(tg, cfs_rq); + load = cfs_rq->load.weight; + + shares = (tg->shares * load); + if (tg_weight) + shares /= tg_weight; + + if (shares < MIN_SHARES) + shares = MIN_SHARES; + if (shares > tg->shares) + shares = tg->shares; + + return shares; +} +# else /* CONFIG_SMP */ +static inline long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg) +{ + return tg->shares; +} +# endif /* CONFIG_SMP */ +static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, + unsigned long weight) +{ + if (se->on_rq) { + /* commit outstanding execution time */ + if (cfs_rq->curr == se) + update_curr(cfs_rq); + account_entity_dequeue(cfs_rq, se); + } + + update_load_set(&se->load, weight); + + if (se->on_rq) + account_entity_enqueue(cfs_rq, se); +} + +static inline int throttled_hierarchy(struct cfs_rq *cfs_rq); + +static void update_cfs_shares(struct cfs_rq *cfs_rq) +{ + struct task_group *tg; + struct sched_entity *se; + long shares; + + tg = cfs_rq->tg; + se = tg->se[cpu_of(rq_of(cfs_rq))]; + if (!se || throttled_hierarchy(cfs_rq)) + return; +#ifndef CONFIG_SMP + if (likely(se->load.weight == tg->shares)) + return; +#endif + shares = calc_cfs_shares(cfs_rq, tg); + + reweight_entity(cfs_rq_of(se), se, shares); +} +#else /* CONFIG_FAIR_GROUP_SCHED */ +static inline void update_cfs_shares(struct cfs_rq *cfs_rq) +{ +} +#endif /* CONFIG_FAIR_GROUP_SCHED */ + +#ifdef CONFIG_SMP +/* + * We choose a half-life close to 1 scheduling period. + * Note: The tables below are dependent on this value. + */ +#define LOAD_AVG_PERIOD 32 +#define LOAD_AVG_MAX 47742 /* maximum possible load avg */ +#define LOAD_AVG_MAX_N 345 /* number of full periods to produce LOAD_MAX_AVG */ + +/* Precomputed fixed inverse multiplies for multiplication by y^n */ +static const u32 runnable_avg_yN_inv[] = { + 0xffffffff, 0xfa83b2da, 0xf5257d14, 0xefe4b99a, 0xeac0c6e6, 0xe5b906e6, + 0xe0ccdeeb, 0xdbfbb796, 0xd744fcc9, 0xd2a81d91, 0xce248c14, 0xc9b9bd85, + 0xc5672a10, 0xc12c4cc9, 0xbd08a39e, 0xb8fbaf46, 0xb504f333, 0xb123f581, + 0xad583ee9, 0xa9a15ab4, 0xa5fed6a9, 0xa2704302, 0x9ef5325f, 0x9b8d39b9, + 0x9837f050, 0x94f4efa8, 0x91c3d373, 0x8ea4398a, 0x8b95c1e3, 0x88980e80, + 0x85aac367, 0x82cd8698, +}; + +/* + * Precomputed \Sum y^k { 1<=k<=n }. These are floor(true_value) to prevent + * over-estimates when re-combining. + */ +static const u32 runnable_avg_yN_sum[] = { + 0, 1002, 1982, 2941, 3880, 4798, 5697, 6576, 7437, 8279, 9103, + 9909,10698,11470,12226,12966,13690,14398,15091,15769,16433,17082, + 17718,18340,18949,19545,20128,20698,21256,21802,22336,22859,23371, +}; + +/* + * Approximate: + * val * y^n, where y^32 ~= 0.5 (~1 scheduling period) + */ +static __always_inline u64 decay_load(u64 val, u64 n) +{ + unsigned int local_n; + + if (!n) + return val; + else if (unlikely(n > LOAD_AVG_PERIOD * 63)) + return 0; + + /* after bounds checking we can collapse to 32-bit */ + local_n = n; + + /* + * As y^PERIOD = 1/2, we can combine + * y^n = 1/2^(n/PERIOD) * y^(n%PERIOD) + * With a look-up table which covers y^n (n= LOAD_AVG_PERIOD)) { + val >>= local_n / LOAD_AVG_PERIOD; + local_n %= LOAD_AVG_PERIOD; + } + + val *= runnable_avg_yN_inv[local_n]; + /* We don't use SRR here since we always want to round down. */ + return val >> 32; +} + +/* + * For updates fully spanning n periods, the contribution to runnable + * average will be: \Sum 1024*y^n + * + * We can compute this reasonably efficiently by combining: + * y^PERIOD = 1/2 with precomputed \Sum 1024*y^n {for n = LOAD_AVG_MAX_N)) + return LOAD_AVG_MAX; + + /* Compute \Sum k^n combining precomputed values for k^i, \Sum k^j */ + do { + contrib /= 2; /* y^LOAD_AVG_PERIOD = 1/2 */ + contrib += runnable_avg_yN_sum[LOAD_AVG_PERIOD]; + + n -= LOAD_AVG_PERIOD; + } while (n > LOAD_AVG_PERIOD); + + contrib = decay_load(contrib, n); + return contrib + runnable_avg_yN_sum[n]; +} + +/* + * We can represent the historical contribution to runnable average as the + * coefficients of a geometric series. To do this we sub-divide our runnable + * history into segments of approximately 1ms (1024us); label the segment that + * occurred N-ms ago p_N, with p_0 corresponding to the current period, e.g. + * + * [<- 1024us ->|<- 1024us ->|<- 1024us ->| ... + * p0 p1 p2 + * (now) (~1ms ago) (~2ms ago) + * + * Let u_i denote the fraction of p_i that the entity was runnable. + * + * We then designate the fractions u_i as our co-efficients, yielding the + * following representation of historical load: + * u_0 + u_1*y + u_2*y^2 + u_3*y^3 + ... + * + * We choose y based on the with of a reasonably scheduling period, fixing: + * y^32 = 0.5 + * + * This means that the contribution to load ~32ms ago (u_32) will be weighted + * approximately half as much as the contribution to load within the last ms + * (u_0). + * + * When a period "rolls over" and we have new u_0`, multiplying the previous + * sum again by y is sufficient to update: + * load_avg = u_0` + y*(u_0 + u_1*y + u_2*y^2 + ... ) + * = u_0 + u_1*y + u_2*y^2 + ... [re-labeling u_i --> u_{i+1}] + */ +static __always_inline int __update_entity_runnable_avg(u64 now, int cpu, + struct sched_avg *sa, + int runnable, + int running) +{ + u64 delta, periods; + u32 runnable_contrib; + int delta_w, decayed = 0; + unsigned long scale_freq = arch_scale_freq_capacity(NULL, cpu); + + delta = now - sa->last_runnable_update; + /* + * This should only happen when time goes backwards, which it + * unfortunately does during sched clock init when we swap over to TSC. + */ + if ((s64)delta < 0) { + sa->last_runnable_update = now; + return 0; + } + + /* + * Use 1024ns as the unit of measurement since it's a reasonable + * approximation of 1us and fast to compute. + */ + delta >>= 10; + if (!delta) + return 0; + sa->last_runnable_update = now; + + /* delta_w is the amount already accumulated against our next period */ + delta_w = sa->avg_period % 1024; + if (delta + delta_w >= 1024) { + /* period roll-over */ + decayed = 1; + + /* + * Now that we know we're crossing a period boundary, figure + * out how much from delta we need to complete the current + * period and accrue it. + */ + delta_w = 1024 - delta_w; + if (runnable) + sa->runnable_avg_sum += delta_w; + if (running) + sa->running_avg_sum += delta_w * scale_freq + >> SCHED_CAPACITY_SHIFT; + sa->avg_period += delta_w; + + delta -= delta_w; + + /* Figure out how many additional periods this update spans */ + periods = delta / 1024; + delta %= 1024; + + sa->runnable_avg_sum = decay_load(sa->runnable_avg_sum, + periods + 1); + sa->running_avg_sum = decay_load(sa->running_avg_sum, + periods + 1); + sa->avg_period = decay_load(sa->avg_period, + periods + 1); + + /* Efficiently calculate \sum (1..n_period) 1024*y^i */ + runnable_contrib = __compute_runnable_contrib(periods); + if (runnable) + sa->runnable_avg_sum += runnable_contrib; + if (running) + sa->running_avg_sum += runnable_contrib * scale_freq + >> SCHED_CAPACITY_SHIFT; + sa->avg_period += runnable_contrib; + } + + /* Remainder of delta accrued against u_0` */ + if (runnable) + sa->runnable_avg_sum += delta; + if (running) + sa->running_avg_sum += delta * scale_freq + >> SCHED_CAPACITY_SHIFT; + sa->avg_period += delta; + + return decayed; +} + +/* Synchronize an entity's decay with its parenting cfs_rq.*/ +static inline u64 __synchronize_entity_decay(struct sched_entity *se) +{ + struct cfs_rq *cfs_rq = cfs_rq_of(se); + u64 decays = atomic64_read(&cfs_rq->decay_counter); + + decays -= se->avg.decay_count; + se->avg.decay_count = 0; + if (!decays) + return 0; + + se->avg.load_avg_contrib = decay_load(se->avg.load_avg_contrib, decays); + se->avg.utilization_avg_contrib = + decay_load(se->avg.utilization_avg_contrib, decays); + + return decays; +} + +#ifdef CONFIG_FAIR_GROUP_SCHED +static inline void __update_cfs_rq_tg_load_contrib(struct cfs_rq *cfs_rq, + int force_update) +{ + struct task_group *tg = cfs_rq->tg; + long tg_contrib; + + tg_contrib = cfs_rq->runnable_load_avg + cfs_rq->blocked_load_avg; + tg_contrib -= cfs_rq->tg_load_contrib; + + if (!tg_contrib) + return; + + if (force_update || abs(tg_contrib) > cfs_rq->tg_load_contrib / 8) { + atomic_long_add(tg_contrib, &tg->load_avg); + cfs_rq->tg_load_contrib += tg_contrib; + } +} + +/* + * Aggregate cfs_rq runnable averages into an equivalent task_group + * representation for computing load contributions. + */ +static inline void __update_tg_runnable_avg(struct sched_avg *sa, + struct cfs_rq *cfs_rq) +{ + struct task_group *tg = cfs_rq->tg; + long contrib; + + /* The fraction of a cpu used by this cfs_rq */ + contrib = div_u64((u64)sa->runnable_avg_sum << NICE_0_SHIFT, + sa->avg_period + 1); + contrib -= cfs_rq->tg_runnable_contrib; + + if (abs(contrib) > cfs_rq->tg_runnable_contrib / 64) { + atomic_add(contrib, &tg->runnable_avg); + cfs_rq->tg_runnable_contrib += contrib; + } +} + +static inline void __update_group_entity_contrib(struct sched_entity *se) +{ + struct cfs_rq *cfs_rq = group_cfs_rq(se); + struct task_group *tg = cfs_rq->tg; + int runnable_avg; + + u64 contrib; + + contrib = cfs_rq->tg_load_contrib * tg->shares; + se->avg.load_avg_contrib = div_u64(contrib, + atomic_long_read(&tg->load_avg) + 1); + + /* + * For group entities we need to compute a correction term in the case + * that they are consuming <1 cpu so that we would contribute the same + * load as a task of equal weight. + * + * Explicitly co-ordinating this measurement would be expensive, but + * fortunately the sum of each cpus contribution forms a usable + * lower-bound on the true value. + * + * Consider the aggregate of 2 contributions. Either they are disjoint + * (and the sum represents true value) or they are disjoint and we are + * understating by the aggregate of their overlap. + * + * Extending this to N cpus, for a given overlap, the maximum amount we + * understand is then n_i(n_i+1)/2 * w_i where n_i is the number of + * cpus that overlap for this interval and w_i is the interval width. + * + * On a small machine; the first term is well-bounded which bounds the + * total error since w_i is a subset of the period. Whereas on a + * larger machine, while this first term can be larger, if w_i is the + * of consequential size guaranteed to see n_i*w_i quickly converge to + * our upper bound of 1-cpu. + */ + runnable_avg = atomic_read(&tg->runnable_avg); + if (runnable_avg < NICE_0_LOAD) { + se->avg.load_avg_contrib *= runnable_avg; + se->avg.load_avg_contrib >>= NICE_0_SHIFT; + } +} + +static inline void update_rq_runnable_avg(struct rq *rq, int runnable) +{ + __update_entity_runnable_avg(rq_clock_task(rq), cpu_of(rq), &rq->avg, + runnable, runnable); + __update_tg_runnable_avg(&rq->avg, &rq->cfs); +} +#else /* CONFIG_FAIR_GROUP_SCHED */ +static inline void __update_cfs_rq_tg_load_contrib(struct cfs_rq *cfs_rq, + int force_update) {} +static inline void __update_tg_runnable_avg(struct sched_avg *sa, + struct cfs_rq *cfs_rq) {} +static inline void __update_group_entity_contrib(struct sched_entity *se) {} +static inline void update_rq_runnable_avg(struct rq *rq, int runnable) {} +#endif /* CONFIG_FAIR_GROUP_SCHED */ + +static inline void __update_task_entity_contrib(struct sched_entity *se) +{ + u32 contrib; + + /* avoid overflowing a 32-bit type w/ SCHED_LOAD_SCALE */ + contrib = se->avg.runnable_avg_sum * scale_load_down(se->load.weight); + contrib /= (se->avg.avg_period + 1); + se->avg.load_avg_contrib = scale_load(contrib); +} + +/* Compute the current contribution to load_avg by se, return any delta */ +static long __update_entity_load_avg_contrib(struct sched_entity *se) +{ + long old_contrib = se->avg.load_avg_contrib; + + if (entity_is_task(se)) { + __update_task_entity_contrib(se); + } else { + __update_tg_runnable_avg(&se->avg, group_cfs_rq(se)); + __update_group_entity_contrib(se); + } + + return se->avg.load_avg_contrib - old_contrib; +} + + +static inline void __update_task_entity_utilization(struct sched_entity *se) +{ + u32 contrib; + + /* avoid overflowing a 32-bit type w/ SCHED_LOAD_SCALE */ + contrib = se->avg.running_avg_sum * scale_load_down(SCHED_LOAD_SCALE); + contrib /= (se->avg.avg_period + 1); + se->avg.utilization_avg_contrib = scale_load(contrib); +} + +static long __update_entity_utilization_avg_contrib(struct sched_entity *se) +{ + long old_contrib = se->avg.utilization_avg_contrib; + + if (entity_is_task(se)) + __update_task_entity_utilization(se); + else + se->avg.utilization_avg_contrib = + group_cfs_rq(se)->utilization_load_avg; + + return se->avg.utilization_avg_contrib - old_contrib; +} + +static inline void subtract_blocked_load_contrib(struct cfs_rq *cfs_rq, + long load_contrib) +{ + if (likely(load_contrib < cfs_rq->blocked_load_avg)) + cfs_rq->blocked_load_avg -= load_contrib; + else + cfs_rq->blocked_load_avg = 0; +} + +static inline u64 cfs_rq_clock_task(struct cfs_rq *cfs_rq); + +/* Update a sched_entity's runnable average */ +static inline void update_entity_load_avg(struct sched_entity *se, + int update_cfs_rq) +{ + struct cfs_rq *cfs_rq = cfs_rq_of(se); + long contrib_delta, utilization_delta; + int cpu = cpu_of(rq_of(cfs_rq)); + u64 now; + + /* + * For a group entity we need to use their owned cfs_rq_clock_task() in + * case they are the parent of a throttled hierarchy. + */ + if (entity_is_task(se)) + now = cfs_rq_clock_task(cfs_rq); + else + now = cfs_rq_clock_task(group_cfs_rq(se)); + + if (!__update_entity_runnable_avg(now, cpu, &se->avg, se->on_rq, + cfs_rq->curr == se)) + return; + + contrib_delta = __update_entity_load_avg_contrib(se); + utilization_delta = __update_entity_utilization_avg_contrib(se); + + if (!update_cfs_rq) + return; + + if (se->on_rq) { + cfs_rq->runnable_load_avg += contrib_delta; + cfs_rq->utilization_load_avg += utilization_delta; + } else { + subtract_blocked_load_contrib(cfs_rq, -contrib_delta); + } +} + +/* + * Decay the load contributed by all blocked children and account this so that + * their contribution may appropriately discounted when they wake up. + */ +static void update_cfs_rq_blocked_load(struct cfs_rq *cfs_rq, int force_update) +{ + u64 now = cfs_rq_clock_task(cfs_rq) >> 20; + u64 decays; + + decays = now - cfs_rq->last_decay; + if (!decays && !force_update) + return; + + if (atomic_long_read(&cfs_rq->removed_load)) { + unsigned long removed_load; + removed_load = atomic_long_xchg(&cfs_rq->removed_load, 0); + subtract_blocked_load_contrib(cfs_rq, removed_load); + } + + if (decays) { + cfs_rq->blocked_load_avg = decay_load(cfs_rq->blocked_load_avg, + decays); + atomic64_add(decays, &cfs_rq->decay_counter); + cfs_rq->last_decay = now; + } + + __update_cfs_rq_tg_load_contrib(cfs_rq, force_update); +} + +/* Add the load generated by se into cfs_rq's child load-average */ +static inline void enqueue_entity_load_avg(struct cfs_rq *cfs_rq, + struct sched_entity *se, + int wakeup) +{ + /* + * We track migrations using entity decay_count <= 0, on a wake-up + * migration we use a negative decay count to track the remote decays + * accumulated while sleeping. + * + * Newly forked tasks are enqueued with se->avg.decay_count == 0, they + * are seen by enqueue_entity_load_avg() as a migration with an already + * constructed load_avg_contrib. + */ + if (unlikely(se->avg.decay_count <= 0)) { + se->avg.last_runnable_update = rq_clock_task(rq_of(cfs_rq)); + if (se->avg.decay_count) { + /* + * In a wake-up migration we have to approximate the + * time sleeping. This is because we can't synchronize + * clock_task between the two cpus, and it is not + * guaranteed to be read-safe. Instead, we can + * approximate this using our carried decays, which are + * explicitly atomically readable. + */ + se->avg.last_runnable_update -= (-se->avg.decay_count) + << 20; + update_entity_load_avg(se, 0); + /* Indicate that we're now synchronized and on-rq */ + se->avg.decay_count = 0; + } + wakeup = 0; + } else { + __synchronize_entity_decay(se); + } + + /* migrated tasks did not contribute to our blocked load */ + if (wakeup) { + subtract_blocked_load_contrib(cfs_rq, se->avg.load_avg_contrib); + update_entity_load_avg(se, 0); + } + + cfs_rq->runnable_load_avg += se->avg.load_avg_contrib; + cfs_rq->utilization_load_avg += se->avg.utilization_avg_contrib; + /* we force update consideration on load-balancer moves */ + update_cfs_rq_blocked_load(cfs_rq, !wakeup); +} + +/* + * Remove se's load from this cfs_rq child load-average, if the entity is + * transitioning to a blocked state we track its projected decay using + * blocked_load_avg. + */ +static inline void dequeue_entity_load_avg(struct cfs_rq *cfs_rq, + struct sched_entity *se, + int sleep) +{ + update_entity_load_avg(se, 1); + /* we force update consideration on load-balancer moves */ + update_cfs_rq_blocked_load(cfs_rq, !sleep); + + cfs_rq->runnable_load_avg -= se->avg.load_avg_contrib; + cfs_rq->utilization_load_avg -= se->avg.utilization_avg_contrib; + if (sleep) { + cfs_rq->blocked_load_avg += se->avg.load_avg_contrib; + se->avg.decay_count = atomic64_read(&cfs_rq->decay_counter); + } /* migrations, e.g. sleep=0 leave decay_count == 0 */ +} + +/* + * Update the rq's load with the elapsed running time before entering + * idle. if the last scheduled task is not a CFS task, idle_enter will + * be the only way to update the runnable statistic. + */ +void idle_enter_fair(struct rq *this_rq) +{ + update_rq_runnable_avg(this_rq, 1); +} + +/* + * Update the rq's load with the elapsed idle time before a task is + * scheduled. if the newly scheduled task is not a CFS task, idle_exit will + * be the only way to update the runnable statistic. + */ +void idle_exit_fair(struct rq *this_rq) +{ + update_rq_runnable_avg(this_rq, 0); +} + +static int idle_balance(struct rq *this_rq); + +#else /* CONFIG_SMP */ + +static inline void update_entity_load_avg(struct sched_entity *se, + int update_cfs_rq) {} +static inline void update_rq_runnable_avg(struct rq *rq, int runnable) {} +static inline void enqueue_entity_load_avg(struct cfs_rq *cfs_rq, + struct sched_entity *se, + int wakeup) {} +static inline void dequeue_entity_load_avg(struct cfs_rq *cfs_rq, + struct sched_entity *se, + int sleep) {} +static inline void update_cfs_rq_blocked_load(struct cfs_rq *cfs_rq, + int force_update) {} + +static inline int idle_balance(struct rq *rq) +{ + return 0; +} + +#endif /* CONFIG_SMP */ + +static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se) +{ +#ifdef CONFIG_SCHEDSTATS + struct task_struct *tsk = NULL; + + if (entity_is_task(se)) + tsk = task_of(se); + + if (se->statistics.sleep_start) { + u64 delta = rq_clock(rq_of(cfs_rq)) - se->statistics.sleep_start; + + if ((s64)delta < 0) + delta = 0; + + if (unlikely(delta > se->statistics.sleep_max)) + se->statistics.sleep_max = delta; + + se->statistics.sleep_start = 0; + se->statistics.sum_sleep_runtime += delta; + + if (tsk) { + account_scheduler_latency(tsk, delta >> 10, 1); + trace_sched_stat_sleep(tsk, delta); + } + } + if (se->statistics.block_start) { + u64 delta = rq_clock(rq_of(cfs_rq)) - se->statistics.block_start; + + if ((s64)delta < 0) + delta = 0; + + if (unlikely(delta > se->statistics.block_max)) + se->statistics.block_max = delta; + + se->statistics.block_start = 0; + se->statistics.sum_sleep_runtime += delta; + + if (tsk) { + if (tsk->in_iowait) { + se->statistics.iowait_sum += delta; + se->statistics.iowait_count++; + trace_sched_stat_iowait(tsk, delta); + } + + trace_sched_stat_blocked(tsk, delta); + + /* + * Blocking time is in units of nanosecs, so shift by + * 20 to get a milliseconds-range estimation of the + * amount of time that the task spent sleeping: + */ + if (unlikely(prof_on == SLEEP_PROFILING)) { + profile_hits(SLEEP_PROFILING, + (void *)get_wchan(tsk), + delta >> 20); + } + account_scheduler_latency(tsk, delta >> 10, 0); + } + } +#endif +} + +static void check_spread(struct cfs_rq *cfs_rq, struct sched_entity *se) +{ +#ifdef CONFIG_SCHED_DEBUG + s64 d = se->vruntime - cfs_rq->min_vruntime; + + if (d < 0) + d = -d; + + if (d > 3*sysctl_sched_latency) + schedstat_inc(cfs_rq, nr_spread_over); +#endif +} + +static void +place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial) +{ + u64 vruntime = cfs_rq->min_vruntime; + + /* + * The 'current' period is already promised to the current tasks, + * however the extra weight of the new task will slow them down a + * little, place the new task so that it fits in the slot that + * stays open at the end. + */ + if (initial && sched_feat(START_DEBIT)) + vruntime += sched_vslice(cfs_rq, se); + + /* sleeps up to a single latency don't count. */ + if (!initial) { + unsigned long thresh = sysctl_sched_latency; + + /* + * Halve their sleep time's effect, to allow + * for a gentler effect of sleepers: + */ + if (sched_feat(GENTLE_FAIR_SLEEPERS)) + thresh >>= 1; + + vruntime -= thresh; + } + + /* ensure we never gain time by being placed backwards. */ + se->vruntime = max_vruntime(se->vruntime, vruntime); +} + +static void check_enqueue_throttle(struct cfs_rq *cfs_rq); + +static void +enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) +{ + /* + * Update the normalized vruntime before updating min_vruntime + * through calling update_curr(). + */ + if (!(flags & ENQUEUE_WAKEUP) || (flags & ENQUEUE_WAKING)) + se->vruntime += cfs_rq->min_vruntime; + + /* + * Update run-time statistics of the 'current'. + */ + update_curr(cfs_rq); + enqueue_entity_load_avg(cfs_rq, se, flags & ENQUEUE_WAKEUP); + account_entity_enqueue(cfs_rq, se); + update_cfs_shares(cfs_rq); + + if (flags & ENQUEUE_WAKEUP) { + place_entity(cfs_rq, se, 0); + enqueue_sleeper(cfs_rq, se); + } + + update_stats_enqueue(cfs_rq, se); + check_spread(cfs_rq, se); + if (se != cfs_rq->curr) + __enqueue_entity(cfs_rq, se); + se->on_rq = 1; + + if (cfs_rq->nr_running == 1) { + list_add_leaf_cfs_rq(cfs_rq); + check_enqueue_throttle(cfs_rq); + } +} + +static void __clear_buddies_last(struct sched_entity *se) +{ + for_each_sched_entity(se) { + struct cfs_rq *cfs_rq = cfs_rq_of(se); + if (cfs_rq->last != se) + break; + + cfs_rq->last = NULL; + } +} + +static void __clear_buddies_next(struct sched_entity *se) +{ + for_each_sched_entity(se) { + struct cfs_rq *cfs_rq = cfs_rq_of(se); + if (cfs_rq->next != se) + break; + + cfs_rq->next = NULL; + } +} + +static void __clear_buddies_skip(struct sched_entity *se) +{ + for_each_sched_entity(se) { + struct cfs_rq *cfs_rq = cfs_rq_of(se); + if (cfs_rq->skip != se) + break; + + cfs_rq->skip = NULL; + } +} + +static void clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se) +{ + if (cfs_rq->last == se) + __clear_buddies_last(se); + + if (cfs_rq->next == se) + __clear_buddies_next(se); + + if (cfs_rq->skip == se) + __clear_buddies_skip(se); +} + +static __always_inline void return_cfs_rq_runtime(struct cfs_rq *cfs_rq); + +static void +dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) +{ + /* + * Update run-time statistics of the 'current'. + */ + update_curr(cfs_rq); + dequeue_entity_load_avg(cfs_rq, se, flags & DEQUEUE_SLEEP); + + update_stats_dequeue(cfs_rq, se); + if (flags & DEQUEUE_SLEEP) { +#ifdef CONFIG_SCHEDSTATS + if (entity_is_task(se)) { + struct task_struct *tsk = task_of(se); + + if (tsk->state & TASK_INTERRUPTIBLE) + se->statistics.sleep_start = rq_clock(rq_of(cfs_rq)); + if (tsk->state & TASK_UNINTERRUPTIBLE) + se->statistics.block_start = rq_clock(rq_of(cfs_rq)); + } +#endif + } + + clear_buddies(cfs_rq, se); + + if (se != cfs_rq->curr) + __dequeue_entity(cfs_rq, se); + se->on_rq = 0; + account_entity_dequeue(cfs_rq, se); + + /* + * Normalize the entity after updating the min_vruntime because the + * update can refer to the ->curr item and we need to reflect this + * movement in our normalized position. + */ + if (!(flags & DEQUEUE_SLEEP)) + se->vruntime -= cfs_rq->min_vruntime; + + /* return excess runtime on last dequeue */ + return_cfs_rq_runtime(cfs_rq); + + update_min_vruntime(cfs_rq); + update_cfs_shares(cfs_rq); +} + +/* + * Preempt the current task with a newly woken task if needed: + */ +static void +check_preempt_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr) +{ + unsigned long ideal_runtime, delta_exec; + struct sched_entity *se; + s64 delta; + + ideal_runtime = sched_slice(cfs_rq, curr); + delta_exec = curr->sum_exec_runtime - curr->prev_sum_exec_runtime; + if (delta_exec > ideal_runtime) { + resched_curr_lazy(rq_of(cfs_rq)); + /* + * The current task ran long enough, ensure it doesn't get + * re-elected due to buddy favours. + */ + clear_buddies(cfs_rq, curr); + return; + } + + /* + * Ensure that a task that missed wakeup preemption by a + * narrow margin doesn't have to wait for a full slice. + * This also mitigates buddy induced latencies under load. + */ + if (delta_exec < sysctl_sched_min_granularity) + return; + + se = __pick_first_entity(cfs_rq); + delta = curr->vruntime - se->vruntime; + + if (delta < 0) + return; + + if (delta > ideal_runtime) + resched_curr_lazy(rq_of(cfs_rq)); +} + +static void +set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se) +{ + /* 'current' is not kept within the tree. */ + if (se->on_rq) { + /* + * Any task has to be enqueued before it get to execute on + * a CPU. So account for the time it spent waiting on the + * runqueue. + */ + update_stats_wait_end(cfs_rq, se); + __dequeue_entity(cfs_rq, se); + update_entity_load_avg(se, 1); + } + + update_stats_curr_start(cfs_rq, se); + cfs_rq->curr = se; +#ifdef CONFIG_SCHEDSTATS + /* + * Track our maximum slice length, if the CPU's load is at + * least twice that of our own weight (i.e. dont track it + * when there are only lesser-weight tasks around): + */ + if (rq_of(cfs_rq)->load.weight >= 2*se->load.weight) { + se->statistics.slice_max = max(se->statistics.slice_max, + se->sum_exec_runtime - se->prev_sum_exec_runtime); + } +#endif + se->prev_sum_exec_runtime = se->sum_exec_runtime; +} + +static int +wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se); + +/* + * Pick the next process, keeping these things in mind, in this order: + * 1) keep things fair between processes/task groups + * 2) pick the "next" process, since someone really wants that to run + * 3) pick the "last" process, for cache locality + * 4) do not run the "skip" process, if something else is available + */ +static struct sched_entity * +pick_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *curr) +{ + struct sched_entity *left = __pick_first_entity(cfs_rq); + struct sched_entity *se; + + /* + * If curr is set we have to see if its left of the leftmost entity + * still in the tree, provided there was anything in the tree at all. + */ + if (!left || (curr && entity_before(curr, left))) + left = curr; + + se = left; /* ideally we run the leftmost entity */ + + /* + * Avoid running the skip buddy, if running something else can + * be done without getting too unfair. + */ + if (cfs_rq->skip == se) { + struct sched_entity *second; + + if (se == curr) { + second = __pick_first_entity(cfs_rq); + } else { + second = __pick_next_entity(se); + if (!second || (curr && entity_before(curr, second))) + second = curr; + } + + if (second && wakeup_preempt_entity(second, left) < 1) + se = second; + } + + /* + * Prefer last buddy, try to return the CPU to a preempted task. + */ + if (cfs_rq->last && wakeup_preempt_entity(cfs_rq->last, left) < 1) + se = cfs_rq->last; + + /* + * Someone really wants this to run. If it's not unfair, run it. + */ + if (cfs_rq->next && wakeup_preempt_entity(cfs_rq->next, left) < 1) + se = cfs_rq->next; + + clear_buddies(cfs_rq, se); + + return se; +} + +static bool check_cfs_rq_runtime(struct cfs_rq *cfs_rq); + +static void put_prev_entity(struct cfs_rq *cfs_rq, struct sched_entity *prev) +{ + /* + * If still on the runqueue then deactivate_task() + * was not called and update_curr() has to be done: + */ + if (prev->on_rq) + update_curr(cfs_rq); + + /* throttle cfs_rqs exceeding runtime */ + check_cfs_rq_runtime(cfs_rq); + + check_spread(cfs_rq, prev); + if (prev->on_rq) { + update_stats_wait_start(cfs_rq, prev); + /* Put 'current' back into the tree. */ + __enqueue_entity(cfs_rq, prev); + /* in !on_rq case, update occurred at dequeue */ + update_entity_load_avg(prev, 1); + } + cfs_rq->curr = NULL; +} + +static void +entity_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr, int queued) +{ + /* + * Update run-time statistics of the 'current'. + */ + update_curr(cfs_rq); + + /* + * Ensure that runnable average is periodically updated. + */ + update_entity_load_avg(curr, 1); + update_cfs_rq_blocked_load(cfs_rq, 1); + update_cfs_shares(cfs_rq); + +#ifdef CONFIG_SCHED_HRTICK + /* + * queued ticks are scheduled to match the slice, so don't bother + * validating it and just reschedule. + */ + if (queued) { + resched_curr_lazy(rq_of(cfs_rq)); + return; + } + /* + * don't let the period tick interfere with the hrtick preemption + */ + if (!sched_feat(DOUBLE_TICK) && + hrtimer_active(&rq_of(cfs_rq)->hrtick_timer)) + return; +#endif + + if (cfs_rq->nr_running > 1) + check_preempt_tick(cfs_rq, curr); +} + + +/************************************************** + * CFS bandwidth control machinery + */ + +#ifdef CONFIG_CFS_BANDWIDTH + +#ifdef HAVE_JUMP_LABEL +static struct static_key __cfs_bandwidth_used; + +static inline bool cfs_bandwidth_used(void) +{ + return static_key_false(&__cfs_bandwidth_used); +} + +void cfs_bandwidth_usage_inc(void) +{ + static_key_slow_inc(&__cfs_bandwidth_used); +} + +void cfs_bandwidth_usage_dec(void) +{ + static_key_slow_dec(&__cfs_bandwidth_used); +} +#else /* HAVE_JUMP_LABEL */ +static bool cfs_bandwidth_used(void) +{ + return true; +} + +void cfs_bandwidth_usage_inc(void) {} +void cfs_bandwidth_usage_dec(void) {} +#endif /* HAVE_JUMP_LABEL */ + +/* + * default period for cfs group bandwidth. + * default: 0.1s, units: nanoseconds + */ +static inline u64 default_cfs_period(void) +{ + return 100000000ULL; +} + +static inline u64 sched_cfs_bandwidth_slice(void) +{ + return (u64)sysctl_sched_cfs_bandwidth_slice * NSEC_PER_USEC; +} + +/* + * Replenish runtime according to assigned quota and update expiration time. + * We use sched_clock_cpu directly instead of rq->clock to avoid adding + * additional synchronization around rq->lock. + * + * requires cfs_b->lock + */ +void __refill_cfs_bandwidth_runtime(struct cfs_bandwidth *cfs_b) +{ + u64 now; + + if (cfs_b->quota == RUNTIME_INF) + return; + + now = sched_clock_cpu(smp_processor_id()); + cfs_b->runtime = cfs_b->quota; + cfs_b->runtime_expires = now + ktime_to_ns(cfs_b->period); +} + +static inline struct cfs_bandwidth *tg_cfs_bandwidth(struct task_group *tg) +{ + return &tg->cfs_bandwidth; +} + +/* rq->task_clock normalized against any time this cfs_rq has spent throttled */ +static inline u64 cfs_rq_clock_task(struct cfs_rq *cfs_rq) +{ + if (unlikely(cfs_rq->throttle_count)) + return cfs_rq->throttled_clock_task; + + return rq_clock_task(rq_of(cfs_rq)) - cfs_rq->throttled_clock_task_time; +} + +/* returns 0 on failure to allocate runtime */ +static int assign_cfs_rq_runtime(struct cfs_rq *cfs_rq) +{ + struct task_group *tg = cfs_rq->tg; + struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(tg); + u64 amount = 0, min_amount, expires; + + /* note: this is a positive sum as runtime_remaining <= 0 */ + min_amount = sched_cfs_bandwidth_slice() - cfs_rq->runtime_remaining; + + raw_spin_lock(&cfs_b->lock); + if (cfs_b->quota == RUNTIME_INF) + amount = min_amount; + else { + /* + * If the bandwidth pool has become inactive, then at least one + * period must have elapsed since the last consumption. + * Refresh the global state and ensure bandwidth timer becomes + * active. + */ + if (!cfs_b->timer_active) { + __refill_cfs_bandwidth_runtime(cfs_b); + __start_cfs_bandwidth(cfs_b, false); + } + + if (cfs_b->runtime > 0) { + amount = min(cfs_b->runtime, min_amount); + cfs_b->runtime -= amount; + cfs_b->idle = 0; + } + } + expires = cfs_b->runtime_expires; + raw_spin_unlock(&cfs_b->lock); + + cfs_rq->runtime_remaining += amount; + /* + * we may have advanced our local expiration to account for allowed + * spread between our sched_clock and the one on which runtime was + * issued. + */ + if ((s64)(expires - cfs_rq->runtime_expires) > 0) + cfs_rq->runtime_expires = expires; + + return cfs_rq->runtime_remaining > 0; +} + +/* + * Note: This depends on the synchronization provided by sched_clock and the + * fact that rq->clock snapshots this value. + */ +static void expire_cfs_rq_runtime(struct cfs_rq *cfs_rq) +{ + struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg); + + /* if the deadline is ahead of our clock, nothing to do */ + if (likely((s64)(rq_clock(rq_of(cfs_rq)) - cfs_rq->runtime_expires) < 0)) + return; + + if (cfs_rq->runtime_remaining < 0) + return; + + /* + * If the local deadline has passed we have to consider the + * possibility that our sched_clock is 'fast' and the global deadline + * has not truly expired. + * + * Fortunately we can check determine whether this the case by checking + * whether the global deadline has advanced. It is valid to compare + * cfs_b->runtime_expires without any locks since we only care about + * exact equality, so a partial write will still work. + */ + + if (cfs_rq->runtime_expires != cfs_b->runtime_expires) { + /* extend local deadline, drift is bounded above by 2 ticks */ + cfs_rq->runtime_expires += TICK_NSEC; + } else { + /* global deadline is ahead, expiration has passed */ + cfs_rq->runtime_remaining = 0; + } +} + +static void __account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec) +{ + /* dock delta_exec before expiring quota (as it could span periods) */ + cfs_rq->runtime_remaining -= delta_exec; + expire_cfs_rq_runtime(cfs_rq); + + if (likely(cfs_rq->runtime_remaining > 0)) + return; + + /* + * if we're unable to extend our runtime we resched so that the active + * hierarchy can be throttled + */ + if (!assign_cfs_rq_runtime(cfs_rq) && likely(cfs_rq->curr)) + resched_curr_lazy(rq_of(cfs_rq)); +} + +static __always_inline +void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec) +{ + if (!cfs_bandwidth_used() || !cfs_rq->runtime_enabled) + return; + + __account_cfs_rq_runtime(cfs_rq, delta_exec); +} + +static inline int cfs_rq_throttled(struct cfs_rq *cfs_rq) +{ + return cfs_bandwidth_used() && cfs_rq->throttled; +} + +/* check whether cfs_rq, or any parent, is throttled */ +static inline int throttled_hierarchy(struct cfs_rq *cfs_rq) +{ + return cfs_bandwidth_used() && cfs_rq->throttle_count; +} + +/* + * Ensure that neither of the group entities corresponding to src_cpu or + * dest_cpu are members of a throttled hierarchy when performing group + * load-balance operations. + */ +static inline int throttled_lb_pair(struct task_group *tg, + int src_cpu, int dest_cpu) +{ + struct cfs_rq *src_cfs_rq, *dest_cfs_rq; + + src_cfs_rq = tg->cfs_rq[src_cpu]; + dest_cfs_rq = tg->cfs_rq[dest_cpu]; + + return throttled_hierarchy(src_cfs_rq) || + throttled_hierarchy(dest_cfs_rq); +} + +/* updated child weight may affect parent so we have to do this bottom up */ +static int tg_unthrottle_up(struct task_group *tg, void *data) +{ + struct rq *rq = data; + struct cfs_rq *cfs_rq = tg->cfs_rq[cpu_of(rq)]; + + cfs_rq->throttle_count--; +#ifdef CONFIG_SMP + if (!cfs_rq->throttle_count) { + /* adjust cfs_rq_clock_task() */ + cfs_rq->throttled_clock_task_time += rq_clock_task(rq) - + cfs_rq->throttled_clock_task; + } +#endif + + return 0; +} + +static int tg_throttle_down(struct task_group *tg, void *data) +{ + struct rq *rq = data; + struct cfs_rq *cfs_rq = tg->cfs_rq[cpu_of(rq)]; + + /* group is entering throttled state, stop time */ + if (!cfs_rq->throttle_count) + cfs_rq->throttled_clock_task = rq_clock_task(rq); + cfs_rq->throttle_count++; + + return 0; +} + +static void throttle_cfs_rq(struct cfs_rq *cfs_rq) +{ + struct rq *rq = rq_of(cfs_rq); + struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg); + struct sched_entity *se; + long task_delta, dequeue = 1; + + se = cfs_rq->tg->se[cpu_of(rq_of(cfs_rq))]; + + /* freeze hierarchy runnable averages while throttled */ + rcu_read_lock(); + walk_tg_tree_from(cfs_rq->tg, tg_throttle_down, tg_nop, (void *)rq); + rcu_read_unlock(); + + task_delta = cfs_rq->h_nr_running; + for_each_sched_entity(se) { + struct cfs_rq *qcfs_rq = cfs_rq_of(se); + /* throttled entity or throttle-on-deactivate */ + if (!se->on_rq) + break; + + if (dequeue) + dequeue_entity(qcfs_rq, se, DEQUEUE_SLEEP); + qcfs_rq->h_nr_running -= task_delta; + + if (qcfs_rq->load.weight) + dequeue = 0; + } + + if (!se) + sub_nr_running(rq, task_delta); + + cfs_rq->throttled = 1; + cfs_rq->throttled_clock = rq_clock(rq); + raw_spin_lock(&cfs_b->lock); + /* + * Add to the _head_ of the list, so that an already-started + * distribute_cfs_runtime will not see us + */ + list_add_rcu(&cfs_rq->throttled_list, &cfs_b->throttled_cfs_rq); + if (!cfs_b->timer_active) + __start_cfs_bandwidth(cfs_b, false); + raw_spin_unlock(&cfs_b->lock); +} + +void unthrottle_cfs_rq(struct cfs_rq *cfs_rq) +{ + struct rq *rq = rq_of(cfs_rq); + struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg); + struct sched_entity *se; + int enqueue = 1; + long task_delta; + + se = cfs_rq->tg->se[cpu_of(rq)]; + + cfs_rq->throttled = 0; + + update_rq_clock(rq); + + raw_spin_lock(&cfs_b->lock); + cfs_b->throttled_time += rq_clock(rq) - cfs_rq->throttled_clock; + list_del_rcu(&cfs_rq->throttled_list); + raw_spin_unlock(&cfs_b->lock); + + /* update hierarchical throttle state */ + walk_tg_tree_from(cfs_rq->tg, tg_nop, tg_unthrottle_up, (void *)rq); + + if (!cfs_rq->load.weight) + return; + + task_delta = cfs_rq->h_nr_running; + for_each_sched_entity(se) { + if (se->on_rq) + enqueue = 0; + + cfs_rq = cfs_rq_of(se); + if (enqueue) + enqueue_entity(cfs_rq, se, ENQUEUE_WAKEUP); + cfs_rq->h_nr_running += task_delta; + + if (cfs_rq_throttled(cfs_rq)) + break; + } + + if (!se) + add_nr_running(rq, task_delta); + + /* determine whether we need to wake up potentially idle cpu */ + if (rq->curr == rq->idle && rq->cfs.nr_running) + resched_curr(rq); +} + +static u64 distribute_cfs_runtime(struct cfs_bandwidth *cfs_b, + u64 remaining, u64 expires) +{ + struct cfs_rq *cfs_rq; + u64 runtime; + u64 starting_runtime = remaining; + + rcu_read_lock(); + list_for_each_entry_rcu(cfs_rq, &cfs_b->throttled_cfs_rq, + throttled_list) { + struct rq *rq = rq_of(cfs_rq); + + raw_spin_lock(&rq->lock); + if (!cfs_rq_throttled(cfs_rq)) + goto next; + + runtime = -cfs_rq->runtime_remaining + 1; + if (runtime > remaining) + runtime = remaining; + remaining -= runtime; + + cfs_rq->runtime_remaining += runtime; + cfs_rq->runtime_expires = expires; + + /* we check whether we're throttled above */ + if (cfs_rq->runtime_remaining > 0) + unthrottle_cfs_rq(cfs_rq); + +next: + raw_spin_unlock(&rq->lock); + + if (!remaining) + break; + } + rcu_read_unlock(); + + return starting_runtime - remaining; +} + +/* + * Responsible for refilling a task_group's bandwidth and unthrottling its + * cfs_rqs as appropriate. If there has been no activity within the last + * period the timer is deactivated until scheduling resumes; cfs_b->idle is + * used to track this state. + */ +static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun) +{ + u64 runtime, runtime_expires; + int throttled; + + /* no need to continue the timer with no bandwidth constraint */ + if (cfs_b->quota == RUNTIME_INF) + goto out_deactivate; + + throttled = !list_empty(&cfs_b->throttled_cfs_rq); + cfs_b->nr_periods += overrun; + + /* + * idle depends on !throttled (for the case of a large deficit), and if + * we're going inactive then everything else can be deferred + */ + if (cfs_b->idle && !throttled) + goto out_deactivate; + + /* + * if we have relooped after returning idle once, we need to update our + * status as actually running, so that other cpus doing + * __start_cfs_bandwidth will stop trying to cancel us. + */ + cfs_b->timer_active = 1; + + __refill_cfs_bandwidth_runtime(cfs_b); + + if (!throttled) { + /* mark as potentially idle for the upcoming period */ + cfs_b->idle = 1; + return 0; + } + + /* account preceding periods in which throttling occurred */ + cfs_b->nr_throttled += overrun; + + runtime_expires = cfs_b->runtime_expires; + + /* + * This check is repeated as we are holding onto the new bandwidth while + * we unthrottle. This can potentially race with an unthrottled group + * trying to acquire new bandwidth from the global pool. This can result + * in us over-using our runtime if it is all used during this loop, but + * only by limited amounts in that extreme case. + */ + while (throttled && cfs_b->runtime > 0) { + runtime = cfs_b->runtime; + raw_spin_unlock(&cfs_b->lock); + /* we can't nest cfs_b->lock while distributing bandwidth */ + runtime = distribute_cfs_runtime(cfs_b, runtime, + runtime_expires); + raw_spin_lock(&cfs_b->lock); + + throttled = !list_empty(&cfs_b->throttled_cfs_rq); + + cfs_b->runtime -= min(runtime, cfs_b->runtime); + } + + /* + * While we are ensured activity in the period following an + * unthrottle, this also covers the case in which the new bandwidth is + * insufficient to cover the existing bandwidth deficit. (Forcing the + * timer to remain active while there are any throttled entities.) + */ + cfs_b->idle = 0; + + return 0; + +out_deactivate: + cfs_b->timer_active = 0; + return 1; +} + +/* a cfs_rq won't donate quota below this amount */ +static const u64 min_cfs_rq_runtime = 1 * NSEC_PER_MSEC; +/* minimum remaining period time to redistribute slack quota */ +static const u64 min_bandwidth_expiration = 2 * NSEC_PER_MSEC; +/* how long we wait to gather additional slack before distributing */ +static const u64 cfs_bandwidth_slack_period = 5 * NSEC_PER_MSEC; + +/* + * Are we near the end of the current quota period? + * + * Requires cfs_b->lock for hrtimer_expires_remaining to be safe against the + * hrtimer base being cleared by __hrtimer_start_range_ns. In the case of + * migrate_hrtimers, base is never cleared, so we are fine. + */ +static int runtime_refresh_within(struct cfs_bandwidth *cfs_b, u64 min_expire) +{ + struct hrtimer *refresh_timer = &cfs_b->period_timer; + u64 remaining; + + /* if the call-back is running a quota refresh is already occurring */ + if (hrtimer_callback_running(refresh_timer)) + return 1; + + /* is a quota refresh about to occur? */ + remaining = ktime_to_ns(hrtimer_expires_remaining(refresh_timer)); + if (remaining < min_expire) + return 1; + + return 0; +} + +static void start_cfs_slack_bandwidth(struct cfs_bandwidth *cfs_b) +{ + u64 min_left = cfs_bandwidth_slack_period + min_bandwidth_expiration; + + /* if there's a quota refresh soon don't bother with slack */ + if (runtime_refresh_within(cfs_b, min_left)) + return; + + start_bandwidth_timer(&cfs_b->slack_timer, + ns_to_ktime(cfs_bandwidth_slack_period)); +} + +/* we know any runtime found here is valid as update_curr() precedes return */ +static void __return_cfs_rq_runtime(struct cfs_rq *cfs_rq) +{ + struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg); + s64 slack_runtime = cfs_rq->runtime_remaining - min_cfs_rq_runtime; + + if (slack_runtime <= 0) + return; + + raw_spin_lock(&cfs_b->lock); + if (cfs_b->quota != RUNTIME_INF && + cfs_rq->runtime_expires == cfs_b->runtime_expires) { + cfs_b->runtime += slack_runtime; + + /* we are under rq->lock, defer unthrottling using a timer */ + if (cfs_b->runtime > sched_cfs_bandwidth_slice() && + !list_empty(&cfs_b->throttled_cfs_rq)) + start_cfs_slack_bandwidth(cfs_b); + } + raw_spin_unlock(&cfs_b->lock); + + /* even if it's not valid for return we don't want to try again */ + cfs_rq->runtime_remaining -= slack_runtime; +} + +static __always_inline void return_cfs_rq_runtime(struct cfs_rq *cfs_rq) +{ + if (!cfs_bandwidth_used()) + return; + + if (!cfs_rq->runtime_enabled || cfs_rq->nr_running) + return; + + __return_cfs_rq_runtime(cfs_rq); +} + +/* + * This is done with a timer (instead of inline with bandwidth return) since + * it's necessary to juggle rq->locks to unthrottle their respective cfs_rqs. + */ +static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b) +{ + u64 runtime = 0, slice = sched_cfs_bandwidth_slice(); + u64 expires; + + /* confirm we're still not at a refresh boundary */ + raw_spin_lock(&cfs_b->lock); + if (runtime_refresh_within(cfs_b, min_bandwidth_expiration)) { + raw_spin_unlock(&cfs_b->lock); + return; + } + + if (cfs_b->quota != RUNTIME_INF && cfs_b->runtime > slice) + runtime = cfs_b->runtime; + + expires = cfs_b->runtime_expires; + raw_spin_unlock(&cfs_b->lock); + + if (!runtime) + return; + + runtime = distribute_cfs_runtime(cfs_b, runtime, expires); + + raw_spin_lock(&cfs_b->lock); + if (expires == cfs_b->runtime_expires) + cfs_b->runtime -= min(runtime, cfs_b->runtime); + raw_spin_unlock(&cfs_b->lock); +} + +/* + * When a group wakes up we want to make sure that its quota is not already + * expired/exceeded, otherwise it may be allowed to steal additional ticks of + * runtime as update_curr() throttling can not not trigger until it's on-rq. + */ +static void check_enqueue_throttle(struct cfs_rq *cfs_rq) +{ + if (!cfs_bandwidth_used()) + return; + + /* an active group must be handled by the update_curr()->put() path */ + if (!cfs_rq->runtime_enabled || cfs_rq->curr) + return; + + /* ensure the group is not already throttled */ + if (cfs_rq_throttled(cfs_rq)) + return; + + /* update runtime allocation */ + account_cfs_rq_runtime(cfs_rq, 0); + if (cfs_rq->runtime_remaining <= 0) + throttle_cfs_rq(cfs_rq); +} + +/* conditionally throttle active cfs_rq's from put_prev_entity() */ +static bool check_cfs_rq_runtime(struct cfs_rq *cfs_rq) +{ + if (!cfs_bandwidth_used()) + return false; + + if (likely(!cfs_rq->runtime_enabled || cfs_rq->runtime_remaining > 0)) + return false; + + /* + * it's possible for a throttled entity to be forced into a running + * state (e.g. set_curr_task), in this case we're finished. + */ + if (cfs_rq_throttled(cfs_rq)) + return true; + + throttle_cfs_rq(cfs_rq); + return true; +} + +static enum hrtimer_restart sched_cfs_slack_timer(struct hrtimer *timer) +{ + struct cfs_bandwidth *cfs_b = + container_of(timer, struct cfs_bandwidth, slack_timer); + do_sched_cfs_slack_timer(cfs_b); + + return HRTIMER_NORESTART; +} + +static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer) +{ + struct cfs_bandwidth *cfs_b = + container_of(timer, struct cfs_bandwidth, period_timer); + ktime_t now; + int overrun; + int idle = 0; + + raw_spin_lock(&cfs_b->lock); + for (;;) { + now = hrtimer_cb_get_time(timer); + overrun = hrtimer_forward(timer, now, cfs_b->period); + + if (!overrun) + break; + + idle = do_sched_cfs_period_timer(cfs_b, overrun); + } + raw_spin_unlock(&cfs_b->lock); + + return idle ? HRTIMER_NORESTART : HRTIMER_RESTART; +} + +void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b) +{ + raw_spin_lock_init(&cfs_b->lock); + cfs_b->runtime = 0; + cfs_b->quota = RUNTIME_INF; + cfs_b->period = ns_to_ktime(default_cfs_period()); + + INIT_LIST_HEAD(&cfs_b->throttled_cfs_rq); + hrtimer_init(&cfs_b->period_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + cfs_b->period_timer.function = sched_cfs_period_timer; + hrtimer_init(&cfs_b->slack_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + cfs_b->slack_timer.function = sched_cfs_slack_timer; +} + +static void init_cfs_rq_runtime(struct cfs_rq *cfs_rq) +{ + cfs_rq->runtime_enabled = 0; + INIT_LIST_HEAD(&cfs_rq->throttled_list); +} + +/* requires cfs_b->lock, may release to reprogram timer */ +void __start_cfs_bandwidth(struct cfs_bandwidth *cfs_b, bool force) +{ + /* + * The timer may be active because we're trying to set a new bandwidth + * period or because we're racing with the tear-down path + * (timer_active==0 becomes visible before the hrtimer call-back + * terminates). In either case we ensure that it's re-programmed + */ + while (unlikely(hrtimer_active(&cfs_b->period_timer)) && + hrtimer_try_to_cancel(&cfs_b->period_timer) < 0) { + /* bounce the lock to allow do_sched_cfs_period_timer to run */ + raw_spin_unlock(&cfs_b->lock); + cpu_relax(); + raw_spin_lock(&cfs_b->lock); + /* if someone else restarted the timer then we're done */ + if (!force && cfs_b->timer_active) + return; + } + + cfs_b->timer_active = 1; + start_bandwidth_timer(&cfs_b->period_timer, cfs_b->period); +} + +static void destroy_cfs_bandwidth(struct cfs_bandwidth *cfs_b) +{ + /* init_cfs_bandwidth() was not called */ + if (!cfs_b->throttled_cfs_rq.next) + return; + + hrtimer_cancel(&cfs_b->period_timer); + hrtimer_cancel(&cfs_b->slack_timer); +} + +static void __maybe_unused update_runtime_enabled(struct rq *rq) +{ + struct cfs_rq *cfs_rq; + + for_each_leaf_cfs_rq(rq, cfs_rq) { + struct cfs_bandwidth *cfs_b = &cfs_rq->tg->cfs_bandwidth; + + raw_spin_lock(&cfs_b->lock); + cfs_rq->runtime_enabled = cfs_b->quota != RUNTIME_INF; + raw_spin_unlock(&cfs_b->lock); + } +} + +static void __maybe_unused unthrottle_offline_cfs_rqs(struct rq *rq) +{ + struct cfs_rq *cfs_rq; + + for_each_leaf_cfs_rq(rq, cfs_rq) { + if (!cfs_rq->runtime_enabled) + continue; + + /* + * clock_task is not advancing so we just need to make sure + * there's some valid quota amount + */ + cfs_rq->runtime_remaining = 1; + /* + * Offline rq is schedulable till cpu is completely disabled + * in take_cpu_down(), so we prevent new cfs throttling here. + */ + cfs_rq->runtime_enabled = 0; + + if (cfs_rq_throttled(cfs_rq)) + unthrottle_cfs_rq(cfs_rq); + } +} + +#else /* CONFIG_CFS_BANDWIDTH */ +static inline u64 cfs_rq_clock_task(struct cfs_rq *cfs_rq) +{ + return rq_clock_task(rq_of(cfs_rq)); +} + +static void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec) {} +static bool check_cfs_rq_runtime(struct cfs_rq *cfs_rq) { return false; } +static void check_enqueue_throttle(struct cfs_rq *cfs_rq) {} +static __always_inline void return_cfs_rq_runtime(struct cfs_rq *cfs_rq) {} + +static inline int cfs_rq_throttled(struct cfs_rq *cfs_rq) +{ + return 0; +} + +static inline int throttled_hierarchy(struct cfs_rq *cfs_rq) +{ + return 0; +} + +static inline int throttled_lb_pair(struct task_group *tg, + int src_cpu, int dest_cpu) +{ + return 0; +} + +void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b) {} + +#ifdef CONFIG_FAIR_GROUP_SCHED +static void init_cfs_rq_runtime(struct cfs_rq *cfs_rq) {} +#endif + +static inline struct cfs_bandwidth *tg_cfs_bandwidth(struct task_group *tg) +{ + return NULL; +} +static inline void destroy_cfs_bandwidth(struct cfs_bandwidth *cfs_b) {} +static inline void update_runtime_enabled(struct rq *rq) {} +static inline void unthrottle_offline_cfs_rqs(struct rq *rq) {} + +#endif /* CONFIG_CFS_BANDWIDTH */ + +/************************************************** + * CFS operations on tasks: + */ + +#ifdef CONFIG_SCHED_HRTICK +static void hrtick_start_fair(struct rq *rq, struct task_struct *p) +{ + struct sched_entity *se = &p->se; + struct cfs_rq *cfs_rq = cfs_rq_of(se); + + WARN_ON(task_rq(p) != rq); + + if (cfs_rq->nr_running > 1) { + u64 slice = sched_slice(cfs_rq, se); + u64 ran = se->sum_exec_runtime - se->prev_sum_exec_runtime; + s64 delta = slice - ran; + + if (delta < 0) { + if (rq->curr == p) + resched_curr_lazy(rq); + return; + } + hrtick_start(rq, delta); + } +} + +/* + * called from enqueue/dequeue and updates the hrtick when the + * current task is from our class and nr_running is low enough + * to matter. + */ +static void hrtick_update(struct rq *rq) +{ + struct task_struct *curr = rq->curr; + + if (!hrtick_enabled(rq) || curr->sched_class != &fair_sched_class) + return; + + if (cfs_rq_of(&curr->se)->nr_running < sched_nr_latency) + hrtick_start_fair(rq, curr); +} +#else /* !CONFIG_SCHED_HRTICK */ +static inline void +hrtick_start_fair(struct rq *rq, struct task_struct *p) +{ +} + +static inline void hrtick_update(struct rq *rq) +{ +} +#endif + +/* + * The enqueue_task method is called before nr_running is + * increased. Here we update the fair scheduling stats and + * then put the task into the rbtree: + */ +static void +enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags) +{ + struct cfs_rq *cfs_rq; + struct sched_entity *se = &p->se; + + for_each_sched_entity(se) { + if (se->on_rq) + break; + cfs_rq = cfs_rq_of(se); + enqueue_entity(cfs_rq, se, flags); + + /* + * end evaluation on encountering a throttled cfs_rq + * + * note: in the case of encountering a throttled cfs_rq we will + * post the final h_nr_running increment below. + */ + if (cfs_rq_throttled(cfs_rq)) + break; + cfs_rq->h_nr_running++; + + flags = ENQUEUE_WAKEUP; + } + + for_each_sched_entity(se) { + cfs_rq = cfs_rq_of(se); + cfs_rq->h_nr_running++; + + if (cfs_rq_throttled(cfs_rq)) + break; + + update_cfs_shares(cfs_rq); + update_entity_load_avg(se, 1); + } + + if (!se) { + update_rq_runnable_avg(rq, rq->nr_running); + add_nr_running(rq, 1); + } + hrtick_update(rq); +} + +static void set_next_buddy(struct sched_entity *se); + +/* + * The dequeue_task method is called before nr_running is + * decreased. We remove the task from the rbtree and + * update the fair scheduling stats: + */ +static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags) +{ + struct cfs_rq *cfs_rq; + struct sched_entity *se = &p->se; + int task_sleep = flags & DEQUEUE_SLEEP; + + for_each_sched_entity(se) { + cfs_rq = cfs_rq_of(se); + dequeue_entity(cfs_rq, se, flags); + + /* + * end evaluation on encountering a throttled cfs_rq + * + * note: in the case of encountering a throttled cfs_rq we will + * post the final h_nr_running decrement below. + */ + if (cfs_rq_throttled(cfs_rq)) + break; + cfs_rq->h_nr_running--; + + /* Don't dequeue parent if it has other entities besides us */ + if (cfs_rq->load.weight) { + /* + * Bias pick_next to pick a task from this cfs_rq, as + * p is sleeping when it is within its sched_slice. + */ + if (task_sleep && parent_entity(se)) + set_next_buddy(parent_entity(se)); + + /* avoid re-evaluating load for this entity */ + se = parent_entity(se); + break; + } + flags |= DEQUEUE_SLEEP; + } + + for_each_sched_entity(se) { + cfs_rq = cfs_rq_of(se); + cfs_rq->h_nr_running--; + + if (cfs_rq_throttled(cfs_rq)) + break; + + update_cfs_shares(cfs_rq); + update_entity_load_avg(se, 1); + } + + if (!se) { + sub_nr_running(rq, 1); + update_rq_runnable_avg(rq, 1); + } + hrtick_update(rq); +} + +#ifdef CONFIG_SMP +/* Used instead of source_load when we know the type == 0 */ +static unsigned long weighted_cpuload(const int cpu) +{ + return cpu_rq(cpu)->cfs.runnable_load_avg; +} + +/* + * Return a low guess at the load of a migration-source cpu weighted + * according to the scheduling class and "nice" value. + * + * We want to under-estimate the load of migration sources, to + * balance conservatively. + */ +static unsigned long source_load(int cpu, int type) +{ + struct rq *rq = cpu_rq(cpu); + unsigned long total = weighted_cpuload(cpu); + + if (type == 0 || !sched_feat(LB_BIAS)) + return total; + + return min(rq->cpu_load[type-1], total); +} + +/* + * Return a high guess at the load of a migration-target cpu weighted + * according to the scheduling class and "nice" value. + */ +static unsigned long target_load(int cpu, int type) +{ + struct rq *rq = cpu_rq(cpu); + unsigned long total = weighted_cpuload(cpu); + + if (type == 0 || !sched_feat(LB_BIAS)) + return total; + + return max(rq->cpu_load[type-1], total); +} + +static unsigned long capacity_of(int cpu) +{ + return cpu_rq(cpu)->cpu_capacity; +} + +static unsigned long capacity_orig_of(int cpu) +{ + return cpu_rq(cpu)->cpu_capacity_orig; +} + +static unsigned long cpu_avg_load_per_task(int cpu) +{ + struct rq *rq = cpu_rq(cpu); + unsigned long nr_running = ACCESS_ONCE(rq->cfs.h_nr_running); + unsigned long load_avg = rq->cfs.runnable_load_avg; + + if (nr_running) + return load_avg / nr_running; + + return 0; +} + +static void record_wakee(struct task_struct *p) +{ + /* + * Rough decay (wiping) for cost saving, don't worry + * about the boundary, really active task won't care + * about the loss. + */ + if (time_after(jiffies, current->wakee_flip_decay_ts + HZ)) { + current->wakee_flips >>= 1; + current->wakee_flip_decay_ts = jiffies; + } + + if (current->last_wakee != p) { + current->last_wakee = p; + current->wakee_flips++; + } +} + +static void task_waking_fair(struct task_struct *p) +{ + struct sched_entity *se = &p->se; + struct cfs_rq *cfs_rq = cfs_rq_of(se); + u64 min_vruntime; + +#ifndef CONFIG_64BIT + u64 min_vruntime_copy; + + do { + min_vruntime_copy = cfs_rq->min_vruntime_copy; + smp_rmb(); + min_vruntime = cfs_rq->min_vruntime; + } while (min_vruntime != min_vruntime_copy); +#else + min_vruntime = cfs_rq->min_vruntime; +#endif + + se->vruntime -= min_vruntime; + record_wakee(p); +} + +#ifdef CONFIG_FAIR_GROUP_SCHED +/* + * effective_load() calculates the load change as seen from the root_task_group + * + * Adding load to a group doesn't make a group heavier, but can cause movement + * of group shares between cpus. Assuming the shares were perfectly aligned one + * can calculate the shift in shares. + * + * Calculate the effective load difference if @wl is added (subtracted) to @tg + * on this @cpu and results in a total addition (subtraction) of @wg to the + * total group weight. + * + * Given a runqueue weight distribution (rw_i) we can compute a shares + * distribution (s_i) using: + * + * s_i = rw_i / \Sum rw_j (1) + * + * Suppose we have 4 CPUs and our @tg is a direct child of the root group and + * has 7 equal weight tasks, distributed as below (rw_i), with the resulting + * shares distribution (s_i): + * + * rw_i = { 2, 4, 1, 0 } + * s_i = { 2/7, 4/7, 1/7, 0 } + * + * As per wake_affine() we're interested in the load of two CPUs (the CPU the + * task used to run on and the CPU the waker is running on), we need to + * compute the effect of waking a task on either CPU and, in case of a sync + * wakeup, compute the effect of the current task going to sleep. + * + * So for a change of @wl to the local @cpu with an overall group weight change + * of @wl we can compute the new shares distribution (s'_i) using: + * + * s'_i = (rw_i + @wl) / (@wg + \Sum rw_j) (2) + * + * Suppose we're interested in CPUs 0 and 1, and want to compute the load + * differences in waking a task to CPU 0. The additional task changes the + * weight and shares distributions like: + * + * rw'_i = { 3, 4, 1, 0 } + * s'_i = { 3/8, 4/8, 1/8, 0 } + * + * We can then compute the difference in effective weight by using: + * + * dw_i = S * (s'_i - s_i) (3) + * + * Where 'S' is the group weight as seen by its parent. + * + * Therefore the effective change in loads on CPU 0 would be 5/56 (3/8 - 2/7) + * times the weight of the group. The effect on CPU 1 would be -4/56 (4/8 - + * 4/7) times the weight of the group. + */ +static long effective_load(struct task_group *tg, int cpu, long wl, long wg) +{ + struct sched_entity *se = tg->se[cpu]; + + if (!tg->parent) /* the trivial, non-cgroup case */ + return wl; + + for_each_sched_entity(se) { + long w, W; + + tg = se->my_q->tg; + + /* + * W = @wg + \Sum rw_j + */ + W = wg + calc_tg_weight(tg, se->my_q); + + /* + * w = rw_i + @wl + */ + w = se->my_q->load.weight + wl; + + /* + * wl = S * s'_i; see (2) + */ + if (W > 0 && w < W) + wl = (w * (long)tg->shares) / W; + else + wl = tg->shares; + + /* + * Per the above, wl is the new se->load.weight value; since + * those are clipped to [MIN_SHARES, ...) do so now. See + * calc_cfs_shares(). + */ + if (wl < MIN_SHARES) + wl = MIN_SHARES; + + /* + * wl = dw_i = S * (s'_i - s_i); see (3) + */ + wl -= se->load.weight; + + /* + * Recursively apply this logic to all parent groups to compute + * the final effective load change on the root group. Since + * only the @tg group gets extra weight, all parent groups can + * only redistribute existing shares. @wl is the shift in shares + * resulting from this level per the above. + */ + wg = 0; + } + + return wl; +} +#else + +static long effective_load(struct task_group *tg, int cpu, long wl, long wg) +{ + return wl; +} + +#endif + +static int wake_wide(struct task_struct *p) +{ + int factor = this_cpu_read(sd_llc_size); + + /* + * Yeah, it's the switching-frequency, could means many wakee or + * rapidly switch, use factor here will just help to automatically + * adjust the loose-degree, so bigger node will lead to more pull. + */ + if (p->wakee_flips > factor) { + /* + * wakee is somewhat hot, it needs certain amount of cpu + * resource, so if waker is far more hot, prefer to leave + * it alone. + */ + if (current->wakee_flips > (factor * p->wakee_flips)) + return 1; + } + + return 0; +} + +static int wake_affine(struct sched_domain *sd, struct task_struct *p, int sync) +{ + s64 this_load, load; + s64 this_eff_load, prev_eff_load; + int idx, this_cpu, prev_cpu; + struct task_group *tg; + unsigned long weight; + int balanced; + + /* + * If we wake multiple tasks be careful to not bounce + * ourselves around too much. + */ + if (wake_wide(p)) + return 0; + + idx = sd->wake_idx; + this_cpu = smp_processor_id(); + prev_cpu = task_cpu(p); + load = source_load(prev_cpu, idx); + this_load = target_load(this_cpu, idx); + + /* + * If sync wakeup then subtract the (maximum possible) + * effect of the currently running task from the load + * of the current CPU: + */ + if (sync) { + tg = task_group(current); + weight = current->se.load.weight; + + this_load += effective_load(tg, this_cpu, -weight, -weight); + load += effective_load(tg, prev_cpu, 0, -weight); + } + + tg = task_group(p); + weight = p->se.load.weight; + + /* + * In low-load situations, where prev_cpu is idle and this_cpu is idle + * due to the sync cause above having dropped this_load to 0, we'll + * always have an imbalance, but there's really nothing you can do + * about that, so that's good too. + * + * Otherwise check if either cpus are near enough in load to allow this + * task to be woken on this_cpu. + */ + this_eff_load = 100; + this_eff_load *= capacity_of(prev_cpu); + + prev_eff_load = 100 + (sd->imbalance_pct - 100) / 2; + prev_eff_load *= capacity_of(this_cpu); + + if (this_load > 0) { + this_eff_load *= this_load + + effective_load(tg, this_cpu, weight, weight); + + prev_eff_load *= load + effective_load(tg, prev_cpu, 0, weight); + } + + balanced = this_eff_load <= prev_eff_load; + + schedstat_inc(p, se.statistics.nr_wakeups_affine_attempts); + + if (!balanced) + return 0; + + schedstat_inc(sd, ttwu_move_affine); + schedstat_inc(p, se.statistics.nr_wakeups_affine); + + return 1; +} + +/* + * find_idlest_group finds and returns the least busy CPU group within the + * domain. + */ +static struct sched_group * +find_idlest_group(struct sched_domain *sd, struct task_struct *p, + int this_cpu, int sd_flag) +{ + struct sched_group *idlest = NULL, *group = sd->groups; + unsigned long min_load = ULONG_MAX, this_load = 0; + int load_idx = sd->forkexec_idx; + int imbalance = 100 + (sd->imbalance_pct-100)/2; + + if (sd_flag & SD_BALANCE_WAKE) + load_idx = sd->wake_idx; + + do { + unsigned long load, avg_load; + int local_group; + int i; + + /* Skip over this group if it has no CPUs allowed */ + if (!cpumask_intersects(sched_group_cpus(group), + tsk_cpus_allowed(p))) + continue; + + local_group = cpumask_test_cpu(this_cpu, + sched_group_cpus(group)); + + /* Tally up the load of all CPUs in the group */ + avg_load = 0; + + for_each_cpu(i, sched_group_cpus(group)) { + /* Bias balancing toward cpus of our domain */ + if (local_group) + load = source_load(i, load_idx); + else + load = target_load(i, load_idx); + + avg_load += load; + } + + /* Adjust by relative CPU capacity of the group */ + avg_load = (avg_load * SCHED_CAPACITY_SCALE) / group->sgc->capacity; + + if (local_group) { + this_load = avg_load; + } else if (avg_load < min_load) { + min_load = avg_load; + idlest = group; + } + } while (group = group->next, group != sd->groups); + + if (!idlest || 100*this_load < imbalance*min_load) + return NULL; + return idlest; +} + +/* + * find_idlest_cpu - find the idlest cpu among the cpus in group. + */ +static int +find_idlest_cpu(struct sched_group *group, struct task_struct *p, int this_cpu) +{ + unsigned long load, min_load = ULONG_MAX; + unsigned int min_exit_latency = UINT_MAX; + u64 latest_idle_timestamp = 0; + int least_loaded_cpu = this_cpu; + int shallowest_idle_cpu = -1; + int i; + + /* Traverse only the allowed CPUs */ + for_each_cpu_and(i, sched_group_cpus(group), tsk_cpus_allowed(p)) { + if (idle_cpu(i)) { + struct rq *rq = cpu_rq(i); + struct cpuidle_state *idle = idle_get_state(rq); + if (idle && idle->exit_latency < min_exit_latency) { + /* + * We give priority to a CPU whose idle state + * has the smallest exit latency irrespective + * of any idle timestamp. + */ + min_exit_latency = idle->exit_latency; + latest_idle_timestamp = rq->idle_stamp; + shallowest_idle_cpu = i; + } else if ((!idle || idle->exit_latency == min_exit_latency) && + rq->idle_stamp > latest_idle_timestamp) { + /* + * If equal or no active idle state, then + * the most recently idled CPU might have + * a warmer cache. + */ + latest_idle_timestamp = rq->idle_stamp; + shallowest_idle_cpu = i; + } + } else if (shallowest_idle_cpu == -1) { + load = weighted_cpuload(i); + if (load < min_load || (load == min_load && i == this_cpu)) { + min_load = load; + least_loaded_cpu = i; + } + } + } + + return shallowest_idle_cpu != -1 ? shallowest_idle_cpu : least_loaded_cpu; +} + +/* + * Try and locate an idle CPU in the sched_domain. + */ +static int select_idle_sibling(struct task_struct *p, int target) +{ + struct sched_domain *sd; + struct sched_group *sg; + int i = task_cpu(p); + + if (idle_cpu(target)) + return target; + + /* + * If the prevous cpu is cache affine and idle, don't be stupid. + */ + if (i != target && cpus_share_cache(i, target) && idle_cpu(i)) + return i; + + /* + * Otherwise, iterate the domains and find an elegible idle cpu. + */ + sd = rcu_dereference(per_cpu(sd_llc, target)); + for_each_lower_domain(sd) { + sg = sd->groups; + do { + if (!cpumask_intersects(sched_group_cpus(sg), + tsk_cpus_allowed(p))) + goto next; + + for_each_cpu(i, sched_group_cpus(sg)) { + if (i == target || !idle_cpu(i)) + goto next; + } + + target = cpumask_first_and(sched_group_cpus(sg), + tsk_cpus_allowed(p)); + goto done; +next: + sg = sg->next; + } while (sg != sd->groups); + } +done: + return target; +} +/* + * get_cpu_usage returns the amount of capacity of a CPU that is used by CFS + * tasks. The unit of the return value must be the one of capacity so we can + * compare the usage with the capacity of the CPU that is available for CFS + * task (ie cpu_capacity). + * cfs.utilization_load_avg is the sum of running time of runnable tasks on a + * CPU. It represents the amount of utilization of a CPU in the range + * [0..SCHED_LOAD_SCALE]. The usage of a CPU can't be higher than the full + * capacity of the CPU because it's about the running time on this CPU. + * Nevertheless, cfs.utilization_load_avg can be higher than SCHED_LOAD_SCALE + * because of unfortunate rounding in avg_period and running_load_avg or just + * after migrating tasks until the average stabilizes with the new running + * time. So we need to check that the usage stays into the range + * [0..cpu_capacity_orig] and cap if necessary. + * Without capping the usage, a group could be seen as overloaded (CPU0 usage + * at 121% + CPU1 usage at 80%) whereas CPU1 has 20% of available capacity + */ +static int get_cpu_usage(int cpu) +{ + unsigned long usage = cpu_rq(cpu)->cfs.utilization_load_avg; + unsigned long capacity = capacity_orig_of(cpu); + + if (usage >= SCHED_LOAD_SCALE) + return capacity; + + return (usage * capacity) >> SCHED_LOAD_SHIFT; +} + +/* + * select_task_rq_fair: Select target runqueue for the waking task in domains + * that have the 'sd_flag' flag set. In practice, this is SD_BALANCE_WAKE, + * SD_BALANCE_FORK, or SD_BALANCE_EXEC. + * + * Balances load by selecting the idlest cpu in the idlest group, or under + * certain conditions an idle sibling cpu if the domain has SD_WAKE_AFFINE set. + * + * Returns the target cpu number. + * + * preempt must be disabled. + */ +static int +select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_flags) +{ + struct sched_domain *tmp, *affine_sd = NULL, *sd = NULL; + int cpu = smp_processor_id(); + int new_cpu = cpu; + int want_affine = 0; + int sync = wake_flags & WF_SYNC; + + if (sd_flag & SD_BALANCE_WAKE) + want_affine = cpumask_test_cpu(cpu, tsk_cpus_allowed(p)); + + rcu_read_lock(); + for_each_domain(cpu, tmp) { + if (!(tmp->flags & SD_LOAD_BALANCE)) + continue; + + /* + * If both cpu and prev_cpu are part of this domain, + * cpu is a valid SD_WAKE_AFFINE target. + */ + if (want_affine && (tmp->flags & SD_WAKE_AFFINE) && + cpumask_test_cpu(prev_cpu, sched_domain_span(tmp))) { + affine_sd = tmp; + break; + } + + if (tmp->flags & sd_flag) + sd = tmp; + } + + if (affine_sd && cpu != prev_cpu && wake_affine(affine_sd, p, sync)) + prev_cpu = cpu; + + if (sd_flag & SD_BALANCE_WAKE) { + new_cpu = select_idle_sibling(p, prev_cpu); + goto unlock; + } + + while (sd) { + struct sched_group *group; + int weight; + + if (!(sd->flags & sd_flag)) { + sd = sd->child; + continue; + } + + group = find_idlest_group(sd, p, cpu, sd_flag); + if (!group) { + sd = sd->child; + continue; + } + + new_cpu = find_idlest_cpu(group, p, cpu); + if (new_cpu == -1 || new_cpu == cpu) { + /* Now try balancing at a lower domain level of cpu */ + sd = sd->child; + continue; + } + + /* Now try balancing at a lower domain level of new_cpu */ + cpu = new_cpu; + weight = sd->span_weight; + sd = NULL; + for_each_domain(cpu, tmp) { + if (weight <= tmp->span_weight) + break; + if (tmp->flags & sd_flag) + sd = tmp; + } + /* while loop will break here if sd == NULL */ + } +unlock: + rcu_read_unlock(); + + return new_cpu; +} + +/* + * Called immediately before a task is migrated to a new cpu; task_cpu(p) and + * cfs_rq_of(p) references at time of call are still valid and identify the + * previous cpu. However, the caller only guarantees p->pi_lock is held; no + * other assumptions, including the state of rq->lock, should be made. + */ +static void +migrate_task_rq_fair(struct task_struct *p, int next_cpu) +{ + struct sched_entity *se = &p->se; + struct cfs_rq *cfs_rq = cfs_rq_of(se); + + /* + * Load tracking: accumulate removed load so that it can be processed + * when we next update owning cfs_rq under rq->lock. Tasks contribute + * to blocked load iff they have a positive decay-count. It can never + * be negative here since on-rq tasks have decay-count == 0. + */ + if (se->avg.decay_count) { + se->avg.decay_count = -__synchronize_entity_decay(se); + atomic_long_add(se->avg.load_avg_contrib, + &cfs_rq->removed_load); + } + + /* We have migrated, no longer consider this task hot */ + se->exec_start = 0; +} +#endif /* CONFIG_SMP */ + +static unsigned long +wakeup_gran(struct sched_entity *curr, struct sched_entity *se) +{ + unsigned long gran = sysctl_sched_wakeup_granularity; + + /* + * Since its curr running now, convert the gran from real-time + * to virtual-time in his units. + * + * By using 'se' instead of 'curr' we penalize light tasks, so + * they get preempted easier. That is, if 'se' < 'curr' then + * the resulting gran will be larger, therefore penalizing the + * lighter, if otoh 'se' > 'curr' then the resulting gran will + * be smaller, again penalizing the lighter task. + * + * This is especially important for buddies when the leftmost + * task is higher priority than the buddy. + */ + return calc_delta_fair(gran, se); +} + +/* + * Should 'se' preempt 'curr'. + * + * |s1 + * |s2 + * |s3 + * g + * |<--->|c + * + * w(c, s1) = -1 + * w(c, s2) = 0 + * w(c, s3) = 1 + * + */ +static int +wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se) +{ + s64 gran, vdiff = curr->vruntime - se->vruntime; + + if (vdiff <= 0) + return -1; + + gran = wakeup_gran(curr, se); + if (vdiff > gran) + return 1; + + return 0; +} + +static void set_last_buddy(struct sched_entity *se) +{ + if (entity_is_task(se) && unlikely(task_of(se)->policy == SCHED_IDLE)) + return; + + for_each_sched_entity(se) + cfs_rq_of(se)->last = se; +} + +static void set_next_buddy(struct sched_entity *se) +{ + if (entity_is_task(se) && unlikely(task_of(se)->policy == SCHED_IDLE)) + return; + + for_each_sched_entity(se) + cfs_rq_of(se)->next = se; +} + +static void set_skip_buddy(struct sched_entity *se) +{ + for_each_sched_entity(se) + cfs_rq_of(se)->skip = se; +} + +/* + * Preempt the current task with a newly woken task if needed: + */ +static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_flags) +{ + struct task_struct *curr = rq->curr; + struct sched_entity *se = &curr->se, *pse = &p->se; + struct cfs_rq *cfs_rq = task_cfs_rq(curr); + int scale = cfs_rq->nr_running >= sched_nr_latency; + int next_buddy_marked = 0; + + if (unlikely(se == pse)) + return; + + /* + * This is possible from callers such as attach_tasks(), in which we + * unconditionally check_prempt_curr() after an enqueue (which may have + * lead to a throttle). This both saves work and prevents false + * next-buddy nomination below. + */ + if (unlikely(throttled_hierarchy(cfs_rq_of(pse)))) + return; + + if (sched_feat(NEXT_BUDDY) && scale && !(wake_flags & WF_FORK)) { + set_next_buddy(pse); + next_buddy_marked = 1; + } + + /* + * We can come here with TIF_NEED_RESCHED already set from new task + * wake up path. + * + * Note: this also catches the edge-case of curr being in a throttled + * group (e.g. via set_curr_task), since update_curr() (in the + * enqueue of curr) will have resulted in resched being set. This + * prevents us from potentially nominating it as a false LAST_BUDDY + * below. + */ + if (test_tsk_need_resched(curr)) + return; + + /* Idle tasks are by definition preempted by non-idle tasks. */ + if (unlikely(curr->policy == SCHED_IDLE) && + likely(p->policy != SCHED_IDLE)) + goto preempt; + + /* + * Batch and idle tasks do not preempt non-idle tasks (their preemption + * is driven by the tick): + */ + if (unlikely(p->policy != SCHED_NORMAL) || !sched_feat(WAKEUP_PREEMPTION)) + return; + + find_matching_se(&se, &pse); + update_curr(cfs_rq_of(se)); + BUG_ON(!pse); + if (wakeup_preempt_entity(se, pse) == 1) { + /* + * Bias pick_next to pick the sched entity that is + * triggering this preemption. + */ + if (!next_buddy_marked) + set_next_buddy(pse); + goto preempt; + } + + return; + +preempt: + resched_curr_lazy(rq); + /* + * Only set the backward buddy when the current task is still + * on the rq. This can happen when a wakeup gets interleaved + * with schedule on the ->pre_schedule() or idle_balance() + * point, either of which can * drop the rq lock. + * + * Also, during early boot the idle thread is in the fair class, + * for obvious reasons its a bad idea to schedule back to it. + */ + if (unlikely(!se->on_rq || curr == rq->idle)) + return; + + if (sched_feat(LAST_BUDDY) && scale && entity_is_task(se)) + set_last_buddy(se); +} + +static struct task_struct * +pick_next_task_fair(struct rq *rq, struct task_struct *prev) +{ + struct cfs_rq *cfs_rq = &rq->cfs; + struct sched_entity *se; + struct task_struct *p; + int new_tasks; + +again: +#ifdef CONFIG_FAIR_GROUP_SCHED + if (!cfs_rq->nr_running) + goto idle; + + if (prev->sched_class != &fair_sched_class) + goto simple; + + /* + * Because of the set_next_buddy() in dequeue_task_fair() it is rather + * likely that a next task is from the same cgroup as the current. + * + * Therefore attempt to avoid putting and setting the entire cgroup + * hierarchy, only change the part that actually changes. + */ + + do { + struct sched_entity *curr = cfs_rq->curr; + + /* + * Since we got here without doing put_prev_entity() we also + * have to consider cfs_rq->curr. If it is still a runnable + * entity, update_curr() will update its vruntime, otherwise + * forget we've ever seen it. + */ + if (curr && curr->on_rq) + update_curr(cfs_rq); + else + curr = NULL; + + /* + * This call to check_cfs_rq_runtime() will do the throttle and + * dequeue its entity in the parent(s). Therefore the 'simple' + * nr_running test will indeed be correct. + */ + if (unlikely(check_cfs_rq_runtime(cfs_rq))) + goto simple; + + se = pick_next_entity(cfs_rq, curr); + cfs_rq = group_cfs_rq(se); + } while (cfs_rq); + + p = task_of(se); + + /* + * Since we haven't yet done put_prev_entity and if the selected task + * is a different task than we started out with, try and touch the + * least amount of cfs_rqs. + */ + if (prev != p) { + struct sched_entity *pse = &prev->se; + + while (!(cfs_rq = is_same_group(se, pse))) { + int se_depth = se->depth; + int pse_depth = pse->depth; + + if (se_depth <= pse_depth) { + put_prev_entity(cfs_rq_of(pse), pse); + pse = parent_entity(pse); + } + if (se_depth >= pse_depth) { + set_next_entity(cfs_rq_of(se), se); + se = parent_entity(se); + } + } + + put_prev_entity(cfs_rq, pse); + set_next_entity(cfs_rq, se); + } + + if (hrtick_enabled(rq)) + hrtick_start_fair(rq, p); + + return p; +simple: + cfs_rq = &rq->cfs; +#endif + + if (!cfs_rq->nr_running) + goto idle; + + put_prev_task(rq, prev); + + do { + se = pick_next_entity(cfs_rq, NULL); + set_next_entity(cfs_rq, se); + cfs_rq = group_cfs_rq(se); + } while (cfs_rq); + + p = task_of(se); + + if (hrtick_enabled(rq)) + hrtick_start_fair(rq, p); + + return p; + +idle: + new_tasks = idle_balance(rq); + /* + * Because idle_balance() releases (and re-acquires) rq->lock, it is + * possible for any higher priority task to appear. In that case we + * must re-start the pick_next_entity() loop. + */ + if (new_tasks < 0) + return RETRY_TASK; + + if (new_tasks > 0) + goto again; + + return NULL; +} + +/* + * Account for a descheduled task: + */ +static void put_prev_task_fair(struct rq *rq, struct task_struct *prev) +{ + struct sched_entity *se = &prev->se; + struct cfs_rq *cfs_rq; + + for_each_sched_entity(se) { + cfs_rq = cfs_rq_of(se); + put_prev_entity(cfs_rq, se); + } +} + +/* + * sched_yield() is very simple + * + * The magic of dealing with the ->skip buddy is in pick_next_entity. + */ +static void yield_task_fair(struct rq *rq) +{ + struct task_struct *curr = rq->curr; + struct cfs_rq *cfs_rq = task_cfs_rq(curr); + struct sched_entity *se = &curr->se; + + /* + * Are we the only task in the tree? + */ + if (unlikely(rq->nr_running == 1)) + return; + + clear_buddies(cfs_rq, se); + + if (curr->policy != SCHED_BATCH) { + update_rq_clock(rq); + /* + * Update run-time statistics of the 'current'. + */ + update_curr(cfs_rq); + /* + * Tell update_rq_clock() that we've just updated, + * so we don't do microscopic update in schedule() + * and double the fastpath cost. + */ + rq_clock_skip_update(rq, true); + } + + set_skip_buddy(se); +} + +static bool yield_to_task_fair(struct rq *rq, struct task_struct *p, bool preempt) +{ + struct sched_entity *se = &p->se; + + /* throttled hierarchies are not runnable */ + if (!se->on_rq || throttled_hierarchy(cfs_rq_of(se))) + return false; + + /* Tell the scheduler that we'd really like pse to run next. */ + set_next_buddy(se); + + yield_task_fair(rq); + + return true; +} + +#ifdef CONFIG_SMP +/************************************************** + * Fair scheduling class load-balancing methods. + * + * BASICS + * + * The purpose of load-balancing is to achieve the same basic fairness the + * per-cpu scheduler provides, namely provide a proportional amount of compute + * time to each task. This is expressed in the following equation: + * + * W_i,n/P_i == W_j,n/P_j for all i,j (1) + * + * Where W_i,n is the n-th weight average for cpu i. The instantaneous weight + * W_i,0 is defined as: + * + * W_i,0 = \Sum_j w_i,j (2) + * + * Where w_i,j is the weight of the j-th runnable task on cpu i. This weight + * is derived from the nice value as per prio_to_weight[]. + * + * The weight average is an exponential decay average of the instantaneous + * weight: + * + * W'_i,n = (2^n - 1) / 2^n * W_i,n + 1 / 2^n * W_i,0 (3) + * + * C_i is the compute capacity of cpu i, typically it is the + * fraction of 'recent' time available for SCHED_OTHER task execution. But it + * can also include other factors [XXX]. + * + * To achieve this balance we define a measure of imbalance which follows + * directly from (1): + * + * imb_i,j = max{ avg(W/C), W_i/C_i } - min{ avg(W/C), W_j/C_j } (4) + * + * We them move tasks around to minimize the imbalance. In the continuous + * function space it is obvious this converges, in the discrete case we get + * a few fun cases generally called infeasible weight scenarios. + * + * [XXX expand on: + * - infeasible weights; + * - local vs global optima in the discrete case. ] + * + * + * SCHED DOMAINS + * + * In order to solve the imbalance equation (4), and avoid the obvious O(n^2) + * for all i,j solution, we create a tree of cpus that follows the hardware + * topology where each level pairs two lower groups (or better). This results + * in O(log n) layers. Furthermore we reduce the number of cpus going up the + * tree to only the first of the previous level and we decrease the frequency + * of load-balance at each level inv. proportional to the number of cpus in + * the groups. + * + * This yields: + * + * log_2 n 1 n + * \Sum { --- * --- * 2^i } = O(n) (5) + * i = 0 2^i 2^i + * `- size of each group + * | | `- number of cpus doing load-balance + * | `- freq + * `- sum over all levels + * + * Coupled with a limit on how many tasks we can migrate every balance pass, + * this makes (5) the runtime complexity of the balancer. + * + * An important property here is that each CPU is still (indirectly) connected + * to every other cpu in at most O(log n) steps: + * + * The adjacency matrix of the resulting graph is given by: + * + * log_2 n + * A_i,j = \Union (i % 2^k == 0) && i / 2^(k+1) == j / 2^(k+1) (6) + * k = 0 + * + * And you'll find that: + * + * A^(log_2 n)_i,j != 0 for all i,j (7) + * + * Showing there's indeed a path between every cpu in at most O(log n) steps. + * The task movement gives a factor of O(m), giving a convergence complexity + * of: + * + * O(nm log n), n := nr_cpus, m := nr_tasks (8) + * + * + * WORK CONSERVING + * + * In order to avoid CPUs going idle while there's still work to do, new idle + * balancing is more aggressive and has the newly idle cpu iterate up the domain + * tree itself instead of relying on other CPUs to bring it work. + * + * This adds some complexity to both (5) and (8) but it reduces the total idle + * time. + * + * [XXX more?] + * + * + * CGROUPS + * + * Cgroups make a horror show out of (2), instead of a simple sum we get: + * + * s_k,i + * W_i,0 = \Sum_j \Prod_k w_k * ----- (9) + * S_k + * + * Where + * + * s_k,i = \Sum_j w_i,j,k and S_k = \Sum_i s_k,i (10) + * + * w_i,j,k is the weight of the j-th runnable task in the k-th cgroup on cpu i. + * + * The big problem is S_k, its a global sum needed to compute a local (W_i) + * property. + * + * [XXX write more on how we solve this.. _after_ merging pjt's patches that + * rewrite all of this once again.] + */ + +static unsigned long __read_mostly max_load_balance_interval = HZ/10; + +enum fbq_type { regular, remote, all }; + +#define LBF_ALL_PINNED 0x01 +#define LBF_NEED_BREAK 0x02 +#define LBF_DST_PINNED 0x04 +#define LBF_SOME_PINNED 0x08 + +struct lb_env { + struct sched_domain *sd; + + struct rq *src_rq; + int src_cpu; + + int dst_cpu; + struct rq *dst_rq; + + struct cpumask *dst_grpmask; + int new_dst_cpu; + enum cpu_idle_type idle; + long imbalance; + /* The set of CPUs under consideration for load-balancing */ + struct cpumask *cpus; + + unsigned int flags; + + unsigned int loop; + unsigned int loop_break; + unsigned int loop_max; + + enum fbq_type fbq_type; + struct list_head tasks; +}; + +/* + * Is this task likely cache-hot: + */ +static int task_hot(struct task_struct *p, struct lb_env *env) +{ + s64 delta; + + lockdep_assert_held(&env->src_rq->lock); + + if (p->sched_class != &fair_sched_class) + return 0; + + if (unlikely(p->policy == SCHED_IDLE)) + return 0; + + /* + * Buddy candidates are cache hot: + */ + if (sched_feat(CACHE_HOT_BUDDY) && env->dst_rq->nr_running && + (&p->se == cfs_rq_of(&p->se)->next || + &p->se == cfs_rq_of(&p->se)->last)) + return 1; + + if (sysctl_sched_migration_cost == -1) + return 1; + if (sysctl_sched_migration_cost == 0) + return 0; + + delta = rq_clock_task(env->src_rq) - p->se.exec_start; + + return delta < (s64)sysctl_sched_migration_cost; +} + +#ifdef CONFIG_NUMA_BALANCING +/* Returns true if the destination node has incurred more faults */ +static bool migrate_improves_locality(struct task_struct *p, struct lb_env *env) +{ + struct numa_group *numa_group = rcu_dereference(p->numa_group); + int src_nid, dst_nid; + + if (!sched_feat(NUMA_FAVOUR_HIGHER) || !p->numa_faults || + !(env->sd->flags & SD_NUMA)) { + return false; + } + + src_nid = cpu_to_node(env->src_cpu); + dst_nid = cpu_to_node(env->dst_cpu); + + if (src_nid == dst_nid) + return false; + + if (numa_group) { + /* Task is already in the group's interleave set. */ + if (node_isset(src_nid, numa_group->active_nodes)) + return false; + + /* Task is moving into the group's interleave set. */ + if (node_isset(dst_nid, numa_group->active_nodes)) + return true; + + return group_faults(p, dst_nid) > group_faults(p, src_nid); + } + + /* Encourage migration to the preferred node. */ + if (dst_nid == p->numa_preferred_nid) + return true; + + return task_faults(p, dst_nid) > task_faults(p, src_nid); +} + + +static bool migrate_degrades_locality(struct task_struct *p, struct lb_env *env) +{ + struct numa_group *numa_group = rcu_dereference(p->numa_group); + int src_nid, dst_nid; + + if (!sched_feat(NUMA) || !sched_feat(NUMA_RESIST_LOWER)) + return false; + + if (!p->numa_faults || !(env->sd->flags & SD_NUMA)) + return false; + + src_nid = cpu_to_node(env->src_cpu); + dst_nid = cpu_to_node(env->dst_cpu); + + if (src_nid == dst_nid) + return false; + + if (numa_group) { + /* Task is moving within/into the group's interleave set. */ + if (node_isset(dst_nid, numa_group->active_nodes)) + return false; + + /* Task is moving out of the group's interleave set. */ + if (node_isset(src_nid, numa_group->active_nodes)) + return true; + + return group_faults(p, dst_nid) < group_faults(p, src_nid); + } + + /* Migrating away from the preferred node is always bad. */ + if (src_nid == p->numa_preferred_nid) + return true; + + return task_faults(p, dst_nid) < task_faults(p, src_nid); +} + +#else +static inline bool migrate_improves_locality(struct task_struct *p, + struct lb_env *env) +{ + return false; +} + +static inline bool migrate_degrades_locality(struct task_struct *p, + struct lb_env *env) +{ + return false; +} +#endif + +/* + * can_migrate_task - may task p from runqueue rq be migrated to this_cpu? + */ +static +int can_migrate_task(struct task_struct *p, struct lb_env *env) +{ + int tsk_cache_hot = 0; + + lockdep_assert_held(&env->src_rq->lock); + + /* + * We do not migrate tasks that are: + * 1) throttled_lb_pair, or + * 2) cannot be migrated to this CPU due to cpus_allowed, or + * 3) running (obviously), or + * 4) are cache-hot on their current CPU. + */ + if (throttled_lb_pair(task_group(p), env->src_cpu, env->dst_cpu)) + return 0; + + if (!cpumask_test_cpu(env->dst_cpu, tsk_cpus_allowed(p))) { + int cpu; + + schedstat_inc(p, se.statistics.nr_failed_migrations_affine); + + env->flags |= LBF_SOME_PINNED; + + /* + * Remember if this task can be migrated to any other cpu in + * our sched_group. We may want to revisit it if we couldn't + * meet load balance goals by pulling other tasks on src_cpu. + * + * Also avoid computing new_dst_cpu if we have already computed + * one in current iteration. + */ + if (!env->dst_grpmask || (env->flags & LBF_DST_PINNED)) + return 0; + + /* Prevent to re-select dst_cpu via env's cpus */ + for_each_cpu_and(cpu, env->dst_grpmask, env->cpus) { + if (cpumask_test_cpu(cpu, tsk_cpus_allowed(p))) { + env->flags |= LBF_DST_PINNED; + env->new_dst_cpu = cpu; + break; + } + } + + return 0; + } + + /* Record that we found atleast one task that could run on dst_cpu */ + env->flags &= ~LBF_ALL_PINNED; + + if (task_running(env->src_rq, p)) { + schedstat_inc(p, se.statistics.nr_failed_migrations_running); + return 0; + } + + /* + * Aggressive migration if: + * 1) destination numa is preferred + * 2) task is cache cold, or + * 3) too many balance attempts have failed. + */ + tsk_cache_hot = task_hot(p, env); + if (!tsk_cache_hot) + tsk_cache_hot = migrate_degrades_locality(p, env); + + if (migrate_improves_locality(p, env) || !tsk_cache_hot || + env->sd->nr_balance_failed > env->sd->cache_nice_tries) { + if (tsk_cache_hot) { + schedstat_inc(env->sd, lb_hot_gained[env->idle]); + schedstat_inc(p, se.statistics.nr_forced_migrations); + } + return 1; + } + + schedstat_inc(p, se.statistics.nr_failed_migrations_hot); + return 0; +} + +/* + * detach_task() -- detach the task for the migration specified in env + */ +static void detach_task(struct task_struct *p, struct lb_env *env) +{ + lockdep_assert_held(&env->src_rq->lock); + + deactivate_task(env->src_rq, p, 0); + p->on_rq = TASK_ON_RQ_MIGRATING; + set_task_cpu(p, env->dst_cpu); +} + +/* + * detach_one_task() -- tries to dequeue exactly one task from env->src_rq, as + * part of active balancing operations within "domain". + * + * Returns a task if successful and NULL otherwise. + */ +static struct task_struct *detach_one_task(struct lb_env *env) +{ + struct task_struct *p, *n; + + lockdep_assert_held(&env->src_rq->lock); + + list_for_each_entry_safe(p, n, &env->src_rq->cfs_tasks, se.group_node) { + if (!can_migrate_task(p, env)) + continue; + + detach_task(p, env); + + /* + * Right now, this is only the second place where + * lb_gained[env->idle] is updated (other is detach_tasks) + * so we can safely collect stats here rather than + * inside detach_tasks(). + */ + schedstat_inc(env->sd, lb_gained[env->idle]); + return p; + } + return NULL; +} + +static const unsigned int sched_nr_migrate_break = 32; + +/* + * detach_tasks() -- tries to detach up to imbalance weighted load from + * busiest_rq, as part of a balancing operation within domain "sd". + * + * Returns number of detached tasks if successful and 0 otherwise. + */ +static int detach_tasks(struct lb_env *env) +{ + struct list_head *tasks = &env->src_rq->cfs_tasks; + struct task_struct *p; + unsigned long load; + int detached = 0; + + lockdep_assert_held(&env->src_rq->lock); + + if (env->imbalance <= 0) + return 0; + + while (!list_empty(tasks)) { + p = list_first_entry(tasks, struct task_struct, se.group_node); + + env->loop++; + /* We've more or less seen every task there is, call it quits */ + if (env->loop > env->loop_max) + break; + + /* take a breather every nr_migrate tasks */ + if (env->loop > env->loop_break) { + env->loop_break += sched_nr_migrate_break; + env->flags |= LBF_NEED_BREAK; + break; + } + + if (!can_migrate_task(p, env)) + goto next; + + load = task_h_load(p); + + if (sched_feat(LB_MIN) && load < 16 && !env->sd->nr_balance_failed) + goto next; + + if ((load / 2) > env->imbalance) + goto next; + + detach_task(p, env); + list_add(&p->se.group_node, &env->tasks); + + detached++; + env->imbalance -= load; + +#ifdef CONFIG_PREEMPT + /* + * NEWIDLE balancing is a source of latency, so preemptible + * kernels will stop after the first task is detached to minimize + * the critical section. + */ + if (env->idle == CPU_NEWLY_IDLE) + break; +#endif + + /* + * We only want to steal up to the prescribed amount of + * weighted load. + */ + if (env->imbalance <= 0) + break; + + continue; +next: + list_move_tail(&p->se.group_node, tasks); + } + + /* + * Right now, this is one of only two places we collect this stat + * so we can safely collect detach_one_task() stats here rather + * than inside detach_one_task(). + */ + schedstat_add(env->sd, lb_gained[env->idle], detached); + + return detached; +} + +/* + * attach_task() -- attach the task detached by detach_task() to its new rq. + */ +static void attach_task(struct rq *rq, struct task_struct *p) +{ + lockdep_assert_held(&rq->lock); + + BUG_ON(task_rq(p) != rq); + p->on_rq = TASK_ON_RQ_QUEUED; + activate_task(rq, p, 0); + check_preempt_curr(rq, p, 0); +} + +/* + * attach_one_task() -- attaches the task returned from detach_one_task() to + * its new rq. + */ +static void attach_one_task(struct rq *rq, struct task_struct *p) +{ + raw_spin_lock(&rq->lock); + attach_task(rq, p); + raw_spin_unlock(&rq->lock); +} + +/* + * attach_tasks() -- attaches all tasks detached by detach_tasks() to their + * new rq. + */ +static void attach_tasks(struct lb_env *env) +{ + struct list_head *tasks = &env->tasks; + struct task_struct *p; + + raw_spin_lock(&env->dst_rq->lock); + + while (!list_empty(tasks)) { + p = list_first_entry(tasks, struct task_struct, se.group_node); + list_del_init(&p->se.group_node); + + attach_task(env->dst_rq, p); + } + + raw_spin_unlock(&env->dst_rq->lock); +} + +#ifdef CONFIG_FAIR_GROUP_SCHED +/* + * update tg->load_weight by folding this cpu's load_avg + */ +static void __update_blocked_averages_cpu(struct task_group *tg, int cpu) +{ + struct sched_entity *se = tg->se[cpu]; + struct cfs_rq *cfs_rq = tg->cfs_rq[cpu]; + + /* throttled entities do not contribute to load */ + if (throttled_hierarchy(cfs_rq)) + return; + + update_cfs_rq_blocked_load(cfs_rq, 1); + + if (se) { + update_entity_load_avg(se, 1); + /* + * We pivot on our runnable average having decayed to zero for + * list removal. This generally implies that all our children + * have also been removed (modulo rounding error or bandwidth + * control); however, such cases are rare and we can fix these + * at enqueue. + * + * TODO: fix up out-of-order children on enqueue. + */ + if (!se->avg.runnable_avg_sum && !cfs_rq->nr_running) + list_del_leaf_cfs_rq(cfs_rq); + } else { + struct rq *rq = rq_of(cfs_rq); + update_rq_runnable_avg(rq, rq->nr_running); + } +} + +static void update_blocked_averages(int cpu) +{ + struct rq *rq = cpu_rq(cpu); + struct cfs_rq *cfs_rq; + unsigned long flags; + + raw_spin_lock_irqsave(&rq->lock, flags); + update_rq_clock(rq); + /* + * Iterates the task_group tree in a bottom up fashion, see + * list_add_leaf_cfs_rq() for details. + */ + for_each_leaf_cfs_rq(rq, cfs_rq) { + /* + * Note: We may want to consider periodically releasing + * rq->lock about these updates so that creating many task + * groups does not result in continually extending hold time. + */ + __update_blocked_averages_cpu(cfs_rq->tg, rq->cpu); + } + + raw_spin_unlock_irqrestore(&rq->lock, flags); +} + +/* + * Compute the hierarchical load factor for cfs_rq and all its ascendants. + * This needs to be done in a top-down fashion because the load of a child + * group is a fraction of its parents load. + */ +static void update_cfs_rq_h_load(struct cfs_rq *cfs_rq) +{ + struct rq *rq = rq_of(cfs_rq); + struct sched_entity *se = cfs_rq->tg->se[cpu_of(rq)]; + unsigned long now = jiffies; + unsigned long load; + + if (cfs_rq->last_h_load_update == now) + return; + + cfs_rq->h_load_next = NULL; + for_each_sched_entity(se) { + cfs_rq = cfs_rq_of(se); + cfs_rq->h_load_next = se; + if (cfs_rq->last_h_load_update == now) + break; + } + + if (!se) { + cfs_rq->h_load = cfs_rq->runnable_load_avg; + cfs_rq->last_h_load_update = now; + } + + while ((se = cfs_rq->h_load_next) != NULL) { + load = cfs_rq->h_load; + load = div64_ul(load * se->avg.load_avg_contrib, + cfs_rq->runnable_load_avg + 1); + cfs_rq = group_cfs_rq(se); + cfs_rq->h_load = load; + cfs_rq->last_h_load_update = now; + } +} + +static unsigned long task_h_load(struct task_struct *p) +{ + struct cfs_rq *cfs_rq = task_cfs_rq(p); + + update_cfs_rq_h_load(cfs_rq); + return div64_ul(p->se.avg.load_avg_contrib * cfs_rq->h_load, + cfs_rq->runnable_load_avg + 1); +} +#else +static inline void update_blocked_averages(int cpu) +{ +} + +static unsigned long task_h_load(struct task_struct *p) +{ + return p->se.avg.load_avg_contrib; +} +#endif + +/********** Helpers for find_busiest_group ************************/ + +enum group_type { + group_other = 0, + group_imbalanced, + group_overloaded, +}; + +/* + * sg_lb_stats - stats of a sched_group required for load_balancing + */ +struct sg_lb_stats { + unsigned long avg_load; /*Avg load across the CPUs of the group */ + unsigned long group_load; /* Total load over the CPUs of the group */ + unsigned long sum_weighted_load; /* Weighted load of group's tasks */ + unsigned long load_per_task; + unsigned long group_capacity; + unsigned long group_usage; /* Total usage of the group */ + unsigned int sum_nr_running; /* Nr tasks running in the group */ + unsigned int idle_cpus; + unsigned int group_weight; + enum group_type group_type; + int group_no_capacity; +#ifdef CONFIG_NUMA_BALANCING + unsigned int nr_numa_running; + unsigned int nr_preferred_running; +#endif +}; + +/* + * sd_lb_stats - Structure to store the statistics of a sched_domain + * during load balancing. + */ +struct sd_lb_stats { + struct sched_group *busiest; /* Busiest group in this sd */ + struct sched_group *local; /* Local group in this sd */ + unsigned long total_load; /* Total load of all groups in sd */ + unsigned long total_capacity; /* Total capacity of all groups in sd */ + unsigned long avg_load; /* Average load across all groups in sd */ + + struct sg_lb_stats busiest_stat;/* Statistics of the busiest group */ + struct sg_lb_stats local_stat; /* Statistics of the local group */ +}; + +static inline void init_sd_lb_stats(struct sd_lb_stats *sds) +{ + /* + * Skimp on the clearing to avoid duplicate work. We can avoid clearing + * local_stat because update_sg_lb_stats() does a full clear/assignment. + * We must however clear busiest_stat::avg_load because + * update_sd_pick_busiest() reads this before assignment. + */ + *sds = (struct sd_lb_stats){ + .busiest = NULL, + .local = NULL, + .total_load = 0UL, + .total_capacity = 0UL, + .busiest_stat = { + .avg_load = 0UL, + .sum_nr_running = 0, + .group_type = group_other, + }, + }; +} + +/** + * get_sd_load_idx - Obtain the load index for a given sched domain. + * @sd: The sched_domain whose load_idx is to be obtained. + * @idle: The idle status of the CPU for whose sd load_idx is obtained. + * + * Return: The load index. + */ +static inline int get_sd_load_idx(struct sched_domain *sd, + enum cpu_idle_type idle) +{ + int load_idx; + + switch (idle) { + case CPU_NOT_IDLE: + load_idx = sd->busy_idx; + break; + + case CPU_NEWLY_IDLE: + load_idx = sd->newidle_idx; + break; + default: + load_idx = sd->idle_idx; + break; + } + + return load_idx; +} + +static unsigned long default_scale_cpu_capacity(struct sched_domain *sd, int cpu) +{ + if ((sd->flags & SD_SHARE_CPUCAPACITY) && (sd->span_weight > 1)) + return sd->smt_gain / sd->span_weight; + + return SCHED_CAPACITY_SCALE; +} + +unsigned long __weak arch_scale_cpu_capacity(struct sched_domain *sd, int cpu) +{ + return default_scale_cpu_capacity(sd, cpu); +} + +static unsigned long scale_rt_capacity(int cpu) +{ + struct rq *rq = cpu_rq(cpu); + u64 total, used, age_stamp, avg; + s64 delta; + + /* + * Since we're reading these variables without serialization make sure + * we read them once before doing sanity checks on them. + */ + age_stamp = ACCESS_ONCE(rq->age_stamp); + avg = ACCESS_ONCE(rq->rt_avg); + delta = __rq_clock_broken(rq) - age_stamp; + + if (unlikely(delta < 0)) + delta = 0; + + total = sched_avg_period() + delta; + + used = div_u64(avg, total); + + if (likely(used < SCHED_CAPACITY_SCALE)) + return SCHED_CAPACITY_SCALE - used; + + return 1; +} + +static void update_cpu_capacity(struct sched_domain *sd, int cpu) +{ + unsigned long capacity = SCHED_CAPACITY_SCALE; + struct sched_group *sdg = sd->groups; + + if (sched_feat(ARCH_CAPACITY)) + capacity *= arch_scale_cpu_capacity(sd, cpu); + else + capacity *= default_scale_cpu_capacity(sd, cpu); + + capacity >>= SCHED_CAPACITY_SHIFT; + + cpu_rq(cpu)->cpu_capacity_orig = capacity; + + capacity *= scale_rt_capacity(cpu); + capacity >>= SCHED_CAPACITY_SHIFT; + + if (!capacity) + capacity = 1; + + cpu_rq(cpu)->cpu_capacity = capacity; + sdg->sgc->capacity = capacity; +} + +void update_group_capacity(struct sched_domain *sd, int cpu) +{ + struct sched_domain *child = sd->child; + struct sched_group *group, *sdg = sd->groups; + unsigned long capacity; + unsigned long interval; + + interval = msecs_to_jiffies(sd->balance_interval); + interval = clamp(interval, 1UL, max_load_balance_interval); + sdg->sgc->next_update = jiffies + interval; + + if (!child) { + update_cpu_capacity(sd, cpu); + return; + } + + capacity = 0; + + if (child->flags & SD_OVERLAP) { + /* + * SD_OVERLAP domains cannot assume that child groups + * span the current group. + */ + + for_each_cpu(cpu, sched_group_cpus(sdg)) { + struct sched_group_capacity *sgc; + struct rq *rq = cpu_rq(cpu); + + /* + * build_sched_domains() -> init_sched_groups_capacity() + * gets here before we've attached the domains to the + * runqueues. + * + * Use capacity_of(), which is set irrespective of domains + * in update_cpu_capacity(). + * + * This avoids capacity from being 0 and + * causing divide-by-zero issues on boot. + */ + if (unlikely(!rq->sd)) { + capacity += capacity_of(cpu); + continue; + } + + sgc = rq->sd->groups->sgc; + capacity += sgc->capacity; + } + } else { + /* + * !SD_OVERLAP domains can assume that child groups + * span the current group. + */ + + group = child->groups; + do { + capacity += group->sgc->capacity; + group = group->next; + } while (group != child->groups); + } + + sdg->sgc->capacity = capacity; +} + +/* + * Check whether the capacity of the rq has been noticeably reduced by side + * activity. The imbalance_pct is used for the threshold. + * Return true is the capacity is reduced + */ +static inline int +check_cpu_capacity(struct rq *rq, struct sched_domain *sd) +{ + return ((rq->cpu_capacity * sd->imbalance_pct) < + (rq->cpu_capacity_orig * 100)); +} + +/* + * Group imbalance indicates (and tries to solve) the problem where balancing + * groups is inadequate due to tsk_cpus_allowed() constraints. + * + * Imagine a situation of two groups of 4 cpus each and 4 tasks each with a + * cpumask covering 1 cpu of the first group and 3 cpus of the second group. + * Something like: + * + * { 0 1 2 3 } { 4 5 6 7 } + * * * * * + * + * If we were to balance group-wise we'd place two tasks in the first group and + * two tasks in the second group. Clearly this is undesired as it will overload + * cpu 3 and leave one of the cpus in the second group unused. + * + * The current solution to this issue is detecting the skew in the first group + * by noticing the lower domain failed to reach balance and had difficulty + * moving tasks due to affinity constraints. + * + * When this is so detected; this group becomes a candidate for busiest; see + * update_sd_pick_busiest(). And calculate_imbalance() and + * find_busiest_group() avoid some of the usual balance conditions to allow it + * to create an effective group imbalance. + * + * This is a somewhat tricky proposition since the next run might not find the + * group imbalance and decide the groups need to be balanced again. A most + * subtle and fragile situation. + */ + +static inline int sg_imbalanced(struct sched_group *group) +{ + return group->sgc->imbalance; +} + +/* + * group_has_capacity returns true if the group has spare capacity that could + * be used by some tasks. + * We consider that a group has spare capacity if the * number of task is + * smaller than the number of CPUs or if the usage is lower than the available + * capacity for CFS tasks. + * For the latter, we use a threshold to stabilize the state, to take into + * account the variance of the tasks' load and to return true if the available + * capacity in meaningful for the load balancer. + * As an example, an available capacity of 1% can appear but it doesn't make + * any benefit for the load balance. + */ +static inline bool +group_has_capacity(struct lb_env *env, struct sg_lb_stats *sgs) +{ + if (sgs->sum_nr_running < sgs->group_weight) + return true; + + if ((sgs->group_capacity * 100) > + (sgs->group_usage * env->sd->imbalance_pct)) + return true; + + return false; +} + +/* + * group_is_overloaded returns true if the group has more tasks than it can + * handle. + * group_is_overloaded is not equals to !group_has_capacity because a group + * with the exact right number of tasks, has no more spare capacity but is not + * overloaded so both group_has_capacity and group_is_overloaded return + * false. + */ +static inline bool +group_is_overloaded(struct lb_env *env, struct sg_lb_stats *sgs) +{ + if (sgs->sum_nr_running <= sgs->group_weight) + return false; + + if ((sgs->group_capacity * 100) < + (sgs->group_usage * env->sd->imbalance_pct)) + return true; + + return false; +} + +static enum group_type group_classify(struct lb_env *env, + struct sched_group *group, + struct sg_lb_stats *sgs) +{ + if (sgs->group_no_capacity) + return group_overloaded; + + if (sg_imbalanced(group)) + return group_imbalanced; + + return group_other; +} + +/** + * update_sg_lb_stats - Update sched_group's statistics for load balancing. + * @env: The load balancing environment. + * @group: sched_group whose statistics are to be updated. + * @load_idx: Load index of sched_domain of this_cpu for load calc. + * @local_group: Does group contain this_cpu. + * @sgs: variable to hold the statistics for this group. + * @overload: Indicate more than one runnable task for any CPU. + */ +static inline void update_sg_lb_stats(struct lb_env *env, + struct sched_group *group, int load_idx, + int local_group, struct sg_lb_stats *sgs, + bool *overload) +{ + unsigned long load; + int i; + + memset(sgs, 0, sizeof(*sgs)); + + for_each_cpu_and(i, sched_group_cpus(group), env->cpus) { + struct rq *rq = cpu_rq(i); + + /* Bias balancing toward cpus of our domain */ + if (local_group) + load = target_load(i, load_idx); + else + load = source_load(i, load_idx); + + sgs->group_load += load; + sgs->group_usage += get_cpu_usage(i); + sgs->sum_nr_running += rq->cfs.h_nr_running; + + if (rq->nr_running > 1) + *overload = true; + +#ifdef CONFIG_NUMA_BALANCING + sgs->nr_numa_running += rq->nr_numa_running; + sgs->nr_preferred_running += rq->nr_preferred_running; +#endif + sgs->sum_weighted_load += weighted_cpuload(i); + if (idle_cpu(i)) + sgs->idle_cpus++; + } + + /* Adjust by relative CPU capacity of the group */ + sgs->group_capacity = group->sgc->capacity; + sgs->avg_load = (sgs->group_load*SCHED_CAPACITY_SCALE) / sgs->group_capacity; + + if (sgs->sum_nr_running) + sgs->load_per_task = sgs->sum_weighted_load / sgs->sum_nr_running; + + sgs->group_weight = group->group_weight; + + sgs->group_no_capacity = group_is_overloaded(env, sgs); + sgs->group_type = group_classify(env, group, sgs); +} + +/** + * update_sd_pick_busiest - return 1 on busiest group + * @env: The load balancing environment. + * @sds: sched_domain statistics + * @sg: sched_group candidate to be checked for being the busiest + * @sgs: sched_group statistics + * + * Determine if @sg is a busier group than the previously selected + * busiest group. + * + * Return: %true if @sg is a busier group than the previously selected + * busiest group. %false otherwise. + */ +static bool update_sd_pick_busiest(struct lb_env *env, + struct sd_lb_stats *sds, + struct sched_group *sg, + struct sg_lb_stats *sgs) +{ + struct sg_lb_stats *busiest = &sds->busiest_stat; + + if (sgs->group_type > busiest->group_type) + return true; + + if (sgs->group_type < busiest->group_type) + return false; + + if (sgs->avg_load <= busiest->avg_load) + return false; + + /* This is the busiest node in its class. */ + if (!(env->sd->flags & SD_ASYM_PACKING)) + return true; + + /* + * ASYM_PACKING needs to move all the work to the lowest + * numbered CPUs in the group, therefore mark all groups + * higher than ourself as busy. + */ + if (sgs->sum_nr_running && env->dst_cpu < group_first_cpu(sg)) { + if (!sds->busiest) + return true; + + if (group_first_cpu(sds->busiest) > group_first_cpu(sg)) + return true; + } + + return false; +} + +#ifdef CONFIG_NUMA_BALANCING +static inline enum fbq_type fbq_classify_group(struct sg_lb_stats *sgs) +{ + if (sgs->sum_nr_running > sgs->nr_numa_running) + return regular; + if (sgs->sum_nr_running > sgs->nr_preferred_running) + return remote; + return all; +} + +static inline enum fbq_type fbq_classify_rq(struct rq *rq) +{ + if (rq->nr_running > rq->nr_numa_running) + return regular; + if (rq->nr_running > rq->nr_preferred_running) + return remote; + return all; +} +#else +static inline enum fbq_type fbq_classify_group(struct sg_lb_stats *sgs) +{ + return all; +} + +static inline enum fbq_type fbq_classify_rq(struct rq *rq) +{ + return regular; +} +#endif /* CONFIG_NUMA_BALANCING */ + +/** + * update_sd_lb_stats - Update sched_domain's statistics for load balancing. + * @env: The load balancing environment. + * @sds: variable to hold the statistics for this sched_domain. + */ +static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sds) +{ + struct sched_domain *child = env->sd->child; + struct sched_group *sg = env->sd->groups; + struct sg_lb_stats tmp_sgs; + int load_idx, prefer_sibling = 0; + bool overload = false; + + if (child && child->flags & SD_PREFER_SIBLING) + prefer_sibling = 1; + + load_idx = get_sd_load_idx(env->sd, env->idle); + + do { + struct sg_lb_stats *sgs = &tmp_sgs; + int local_group; + + local_group = cpumask_test_cpu(env->dst_cpu, sched_group_cpus(sg)); + if (local_group) { + sds->local = sg; + sgs = &sds->local_stat; + + if (env->idle != CPU_NEWLY_IDLE || + time_after_eq(jiffies, sg->sgc->next_update)) + update_group_capacity(env->sd, env->dst_cpu); + } + + update_sg_lb_stats(env, sg, load_idx, local_group, sgs, + &overload); + + if (local_group) + goto next_group; + + /* + * In case the child domain prefers tasks go to siblings + * first, lower the sg capacity so that we'll try + * and move all the excess tasks away. We lower the capacity + * of a group only if the local group has the capacity to fit + * these excess tasks. The extra check prevents the case where + * you always pull from the heaviest group when it is already + * under-utilized (possible with a large weight task outweighs + * the tasks on the system). + */ + if (prefer_sibling && sds->local && + group_has_capacity(env, &sds->local_stat) && + (sgs->sum_nr_running > 1)) { + sgs->group_no_capacity = 1; + sgs->group_type = group_overloaded; + } + + if (update_sd_pick_busiest(env, sds, sg, sgs)) { + sds->busiest = sg; + sds->busiest_stat = *sgs; + } + +next_group: + /* Now, start updating sd_lb_stats */ + sds->total_load += sgs->group_load; + sds->total_capacity += sgs->group_capacity; + + sg = sg->next; + } while (sg != env->sd->groups); + + if (env->sd->flags & SD_NUMA) + env->fbq_type = fbq_classify_group(&sds->busiest_stat); + + if (!env->sd->parent) { + /* update overload indicator if we are at root domain */ + if (env->dst_rq->rd->overload != overload) + env->dst_rq->rd->overload = overload; + } + +} + +/** + * check_asym_packing - Check to see if the group is packed into the + * sched doman. + * + * This is primarily intended to used at the sibling level. Some + * cores like POWER7 prefer to use lower numbered SMT threads. In the + * case of POWER7, it can move to lower SMT modes only when higher + * threads are idle. When in lower SMT modes, the threads will + * perform better since they share less core resources. Hence when we + * have idle threads, we want them to be the higher ones. + * + * This packing function is run on idle threads. It checks to see if + * the busiest CPU in this domain (core in the P7 case) has a higher + * CPU number than the packing function is being run on. Here we are + * assuming lower CPU number will be equivalent to lower a SMT thread + * number. + * + * Return: 1 when packing is required and a task should be moved to + * this CPU. The amount of the imbalance is returned in *imbalance. + * + * @env: The load balancing environment. + * @sds: Statistics of the sched_domain which is to be packed + */ +static int check_asym_packing(struct lb_env *env, struct sd_lb_stats *sds) +{ + int busiest_cpu; + + if (!(env->sd->flags & SD_ASYM_PACKING)) + return 0; + + if (!sds->busiest) + return 0; + + busiest_cpu = group_first_cpu(sds->busiest); + if (env->dst_cpu > busiest_cpu) + return 0; + + env->imbalance = DIV_ROUND_CLOSEST( + sds->busiest_stat.avg_load * sds->busiest_stat.group_capacity, + SCHED_CAPACITY_SCALE); + + return 1; +} + +/** + * fix_small_imbalance - Calculate the minor imbalance that exists + * amongst the groups of a sched_domain, during + * load balancing. + * @env: The load balancing environment. + * @sds: Statistics of the sched_domain whose imbalance is to be calculated. + */ +static inline +void fix_small_imbalance(struct lb_env *env, struct sd_lb_stats *sds) +{ + unsigned long tmp, capa_now = 0, capa_move = 0; + unsigned int imbn = 2; + unsigned long scaled_busy_load_per_task; + struct sg_lb_stats *local, *busiest; + + local = &sds->local_stat; + busiest = &sds->busiest_stat; + + if (!local->sum_nr_running) + local->load_per_task = cpu_avg_load_per_task(env->dst_cpu); + else if (busiest->load_per_task > local->load_per_task) + imbn = 1; + + scaled_busy_load_per_task = + (busiest->load_per_task * SCHED_CAPACITY_SCALE) / + busiest->group_capacity; + + if (busiest->avg_load + scaled_busy_load_per_task >= + local->avg_load + (scaled_busy_load_per_task * imbn)) { + env->imbalance = busiest->load_per_task; + return; + } + + /* + * OK, we don't have enough imbalance to justify moving tasks, + * however we may be able to increase total CPU capacity used by + * moving them. + */ + + capa_now += busiest->group_capacity * + min(busiest->load_per_task, busiest->avg_load); + capa_now += local->group_capacity * + min(local->load_per_task, local->avg_load); + capa_now /= SCHED_CAPACITY_SCALE; + + /* Amount of load we'd subtract */ + if (busiest->avg_load > scaled_busy_load_per_task) { + capa_move += busiest->group_capacity * + min(busiest->load_per_task, + busiest->avg_load - scaled_busy_load_per_task); + } + + /* Amount of load we'd add */ + if (busiest->avg_load * busiest->group_capacity < + busiest->load_per_task * SCHED_CAPACITY_SCALE) { + tmp = (busiest->avg_load * busiest->group_capacity) / + local->group_capacity; + } else { + tmp = (busiest->load_per_task * SCHED_CAPACITY_SCALE) / + local->group_capacity; + } + capa_move += local->group_capacity * + min(local->load_per_task, local->avg_load + tmp); + capa_move /= SCHED_CAPACITY_SCALE; + + /* Move if we gain throughput */ + if (capa_move > capa_now) + env->imbalance = busiest->load_per_task; +} + +/** + * calculate_imbalance - Calculate the amount of imbalance present within the + * groups of a given sched_domain during load balance. + * @env: load balance environment + * @sds: statistics of the sched_domain whose imbalance is to be calculated. + */ +static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *sds) +{ + unsigned long max_pull, load_above_capacity = ~0UL; + struct sg_lb_stats *local, *busiest; + + local = &sds->local_stat; + busiest = &sds->busiest_stat; + + if (busiest->group_type == group_imbalanced) { + /* + * In the group_imb case we cannot rely on group-wide averages + * to ensure cpu-load equilibrium, look at wider averages. XXX + */ + busiest->load_per_task = + min(busiest->load_per_task, sds->avg_load); + } + + /* + * In the presence of smp nice balancing, certain scenarios can have + * max load less than avg load(as we skip the groups at or below + * its cpu_capacity, while calculating max_load..) + */ + if (busiest->avg_load <= sds->avg_load || + local->avg_load >= sds->avg_load) { + env->imbalance = 0; + return fix_small_imbalance(env, sds); + } + + /* + * If there aren't any idle cpus, avoid creating some. + */ + if (busiest->group_type == group_overloaded && + local->group_type == group_overloaded) { + load_above_capacity = busiest->sum_nr_running * + SCHED_LOAD_SCALE; + if (load_above_capacity > busiest->group_capacity) + load_above_capacity -= busiest->group_capacity; + else + load_above_capacity = ~0UL; + } + + /* + * We're trying to get all the cpus to the average_load, so we don't + * want to push ourselves above the average load, nor do we wish to + * reduce the max loaded cpu below the average load. At the same time, + * we also don't want to reduce the group load below the group capacity + * (so that we can implement power-savings policies etc). Thus we look + * for the minimum possible imbalance. + */ + max_pull = min(busiest->avg_load - sds->avg_load, load_above_capacity); + + /* How much load to actually move to equalise the imbalance */ + env->imbalance = min( + max_pull * busiest->group_capacity, + (sds->avg_load - local->avg_load) * local->group_capacity + ) / SCHED_CAPACITY_SCALE; + + /* + * if *imbalance is less than the average load per runnable task + * there is no guarantee that any tasks will be moved so we'll have + * a think about bumping its value to force at least one task to be + * moved + */ + if (env->imbalance < busiest->load_per_task) + return fix_small_imbalance(env, sds); +} + +/******* find_busiest_group() helpers end here *********************/ + +/** + * find_busiest_group - Returns the busiest group within the sched_domain + * if there is an imbalance. If there isn't an imbalance, and + * the user has opted for power-savings, it returns a group whose + * CPUs can be put to idle by rebalancing those tasks elsewhere, if + * such a group exists. + * + * Also calculates the amount of weighted load which should be moved + * to restore balance. + * + * @env: The load balancing environment. + * + * Return: - The busiest group if imbalance exists. + * - If no imbalance and user has opted for power-savings balance, + * return the least loaded group whose CPUs can be + * put to idle by rebalancing its tasks onto our group. + */ +static struct sched_group *find_busiest_group(struct lb_env *env) +{ + struct sg_lb_stats *local, *busiest; + struct sd_lb_stats sds; + + init_sd_lb_stats(&sds); + + /* + * Compute the various statistics relavent for load balancing at + * this level. + */ + update_sd_lb_stats(env, &sds); + local = &sds.local_stat; + busiest = &sds.busiest_stat; + + /* ASYM feature bypasses nice load balance check */ + if ((env->idle == CPU_IDLE || env->idle == CPU_NEWLY_IDLE) && + check_asym_packing(env, &sds)) + return sds.busiest; + + /* There is no busy sibling group to pull tasks from */ + if (!sds.busiest || busiest->sum_nr_running == 0) + goto out_balanced; + + sds.avg_load = (SCHED_CAPACITY_SCALE * sds.total_load) + / sds.total_capacity; + + /* + * If the busiest group is imbalanced the below checks don't + * work because they assume all things are equal, which typically + * isn't true due to cpus_allowed constraints and the like. + */ + if (busiest->group_type == group_imbalanced) + goto force_balance; + + /* SD_BALANCE_NEWIDLE trumps SMP nice when underutilized */ + if (env->idle == CPU_NEWLY_IDLE && group_has_capacity(env, local) && + busiest->group_no_capacity) + goto force_balance; + + /* + * If the local group is busier than the selected busiest group + * don't try and pull any tasks. + */ + if (local->avg_load >= busiest->avg_load) + goto out_balanced; + + /* + * Don't pull any tasks if this group is already above the domain + * average load. + */ + if (local->avg_load >= sds.avg_load) + goto out_balanced; + + if (env->idle == CPU_IDLE) { + /* + * This cpu is idle. If the busiest group is not overloaded + * and there is no imbalance between this and busiest group + * wrt idle cpus, it is balanced. The imbalance becomes + * significant if the diff is greater than 1 otherwise we + * might end up to just move the imbalance on another group + */ + if ((busiest->group_type != group_overloaded) && + (local->idle_cpus <= (busiest->idle_cpus + 1))) + goto out_balanced; + } else { + /* + * In the CPU_NEWLY_IDLE, CPU_NOT_IDLE cases, use + * imbalance_pct to be conservative. + */ + if (100 * busiest->avg_load <= + env->sd->imbalance_pct * local->avg_load) + goto out_balanced; + } + +force_balance: + /* Looks like there is an imbalance. Compute it */ + calculate_imbalance(env, &sds); + return sds.busiest; + +out_balanced: + env->imbalance = 0; + return NULL; +} + +/* + * find_busiest_queue - find the busiest runqueue among the cpus in group. + */ +static struct rq *find_busiest_queue(struct lb_env *env, + struct sched_group *group) +{ + struct rq *busiest = NULL, *rq; + unsigned long busiest_load = 0, busiest_capacity = 1; + int i; + + for_each_cpu_and(i, sched_group_cpus(group), env->cpus) { + unsigned long capacity, wl; + enum fbq_type rt; + + rq = cpu_rq(i); + rt = fbq_classify_rq(rq); + + /* + * We classify groups/runqueues into three groups: + * - regular: there are !numa tasks + * - remote: there are numa tasks that run on the 'wrong' node + * - all: there is no distinction + * + * In order to avoid migrating ideally placed numa tasks, + * ignore those when there's better options. + * + * If we ignore the actual busiest queue to migrate another + * task, the next balance pass can still reduce the busiest + * queue by moving tasks around inside the node. + * + * If we cannot move enough load due to this classification + * the next pass will adjust the group classification and + * allow migration of more tasks. + * + * Both cases only affect the total convergence complexity. + */ + if (rt > env->fbq_type) + continue; + + capacity = capacity_of(i); + + wl = weighted_cpuload(i); + + /* + * When comparing with imbalance, use weighted_cpuload() + * which is not scaled with the cpu capacity. + */ + + if (rq->nr_running == 1 && wl > env->imbalance && + !check_cpu_capacity(rq, env->sd)) + continue; + + /* + * For the load comparisons with the other cpu's, consider + * the weighted_cpuload() scaled with the cpu capacity, so + * that the load can be moved away from the cpu that is + * potentially running at a lower capacity. + * + * Thus we're looking for max(wl_i / capacity_i), crosswise + * multiplication to rid ourselves of the division works out + * to: wl_i * capacity_j > wl_j * capacity_i; where j is + * our previous maximum. + */ + if (wl * busiest_capacity > busiest_load * capacity) { + busiest_load = wl; + busiest_capacity = capacity; + busiest = rq; + } + } + + return busiest; +} + +/* + * Max backoff if we encounter pinned tasks. Pretty arbitrary value, but + * so long as it is large enough. + */ +#define MAX_PINNED_INTERVAL 512 + +/* Working cpumask for load_balance and load_balance_newidle. */ +DEFINE_PER_CPU(cpumask_var_t, load_balance_mask); + +static int need_active_balance(struct lb_env *env) +{ + struct sched_domain *sd = env->sd; + + if (env->idle == CPU_NEWLY_IDLE) { + + /* + * ASYM_PACKING needs to force migrate tasks from busy but + * higher numbered CPUs in order to pack all tasks in the + * lowest numbered CPUs. + */ + if ((sd->flags & SD_ASYM_PACKING) && env->src_cpu > env->dst_cpu) + return 1; + } + + /* + * The dst_cpu is idle and the src_cpu CPU has only 1 CFS task. + * It's worth migrating the task if the src_cpu's capacity is reduced + * because of other sched_class or IRQs if more capacity stays + * available on dst_cpu. + */ + if ((env->idle != CPU_NOT_IDLE) && + (env->src_rq->cfs.h_nr_running == 1)) { + if ((check_cpu_capacity(env->src_rq, sd)) && + (capacity_of(env->src_cpu)*sd->imbalance_pct < capacity_of(env->dst_cpu)*100)) + return 1; + } + + return unlikely(sd->nr_balance_failed > sd->cache_nice_tries+2); +} + +static int active_load_balance_cpu_stop(void *data); + +static int should_we_balance(struct lb_env *env) +{ + struct sched_group *sg = env->sd->groups; + struct cpumask *sg_cpus, *sg_mask; + int cpu, balance_cpu = -1; + + /* + * In the newly idle case, we will allow all the cpu's + * to do the newly idle load balance. + */ + if (env->idle == CPU_NEWLY_IDLE) + return 1; + + sg_cpus = sched_group_cpus(sg); + sg_mask = sched_group_mask(sg); + /* Try to find first idle cpu */ + for_each_cpu_and(cpu, sg_cpus, env->cpus) { + if (!cpumask_test_cpu(cpu, sg_mask) || !idle_cpu(cpu)) + continue; + + balance_cpu = cpu; + break; + } + + if (balance_cpu == -1) + balance_cpu = group_balance_cpu(sg); + + /* + * First idle cpu or the first cpu(busiest) in this sched group + * is eligible for doing load balancing at this and above domains. + */ + return balance_cpu == env->dst_cpu; +} + +/* + * Check this_cpu to ensure it is balanced within domain. Attempt to move + * tasks if there is an imbalance. + */ +static int load_balance(int this_cpu, struct rq *this_rq, + struct sched_domain *sd, enum cpu_idle_type idle, + int *continue_balancing) +{ + int ld_moved, cur_ld_moved, active_balance = 0; + struct sched_domain *sd_parent = sd->parent; + struct sched_group *group; + struct rq *busiest; + unsigned long flags; + struct cpumask *cpus = this_cpu_cpumask_var_ptr(load_balance_mask); + + struct lb_env env = { + .sd = sd, + .dst_cpu = this_cpu, + .dst_rq = this_rq, + .dst_grpmask = sched_group_cpus(sd->groups), + .idle = idle, + .loop_break = sched_nr_migrate_break, + .cpus = cpus, + .fbq_type = all, + .tasks = LIST_HEAD_INIT(env.tasks), + }; + + /* + * For NEWLY_IDLE load_balancing, we don't need to consider + * other cpus in our group + */ + if (idle == CPU_NEWLY_IDLE) + env.dst_grpmask = NULL; + + cpumask_copy(cpus, cpu_active_mask); + + schedstat_inc(sd, lb_count[idle]); + +redo: + if (!should_we_balance(&env)) { + *continue_balancing = 0; + goto out_balanced; + } + + group = find_busiest_group(&env); + if (!group) { + schedstat_inc(sd, lb_nobusyg[idle]); + goto out_balanced; + } + + busiest = find_busiest_queue(&env, group); + if (!busiest) { + schedstat_inc(sd, lb_nobusyq[idle]); + goto out_balanced; + } + + BUG_ON(busiest == env.dst_rq); + + schedstat_add(sd, lb_imbalance[idle], env.imbalance); + + env.src_cpu = busiest->cpu; + env.src_rq = busiest; + + ld_moved = 0; + if (busiest->nr_running > 1) { + /* + * Attempt to move tasks. If find_busiest_group has found + * an imbalance but busiest->nr_running <= 1, the group is + * still unbalanced. ld_moved simply stays zero, so it is + * correctly treated as an imbalance. + */ + env.flags |= LBF_ALL_PINNED; + env.loop_max = min(sysctl_sched_nr_migrate, busiest->nr_running); + +more_balance: + raw_spin_lock_irqsave(&busiest->lock, flags); + + /* + * cur_ld_moved - load moved in current iteration + * ld_moved - cumulative load moved across iterations + */ + cur_ld_moved = detach_tasks(&env); + + /* + * We've detached some tasks from busiest_rq. Every + * task is masked "TASK_ON_RQ_MIGRATING", so we can safely + * unlock busiest->lock, and we are able to be sure + * that nobody can manipulate the tasks in parallel. + * See task_rq_lock() family for the details. + */ + + raw_spin_unlock(&busiest->lock); + + if (cur_ld_moved) { + attach_tasks(&env); + ld_moved += cur_ld_moved; + } + + local_irq_restore(flags); + + if (env.flags & LBF_NEED_BREAK) { + env.flags &= ~LBF_NEED_BREAK; + goto more_balance; + } + + /* + * Revisit (affine) tasks on src_cpu that couldn't be moved to + * us and move them to an alternate dst_cpu in our sched_group + * where they can run. The upper limit on how many times we + * iterate on same src_cpu is dependent on number of cpus in our + * sched_group. + * + * This changes load balance semantics a bit on who can move + * load to a given_cpu. In addition to the given_cpu itself + * (or a ilb_cpu acting on its behalf where given_cpu is + * nohz-idle), we now have balance_cpu in a position to move + * load to given_cpu. In rare situations, this may cause + * conflicts (balance_cpu and given_cpu/ilb_cpu deciding + * _independently_ and at _same_ time to move some load to + * given_cpu) causing exceess load to be moved to given_cpu. + * This however should not happen so much in practice and + * moreover subsequent load balance cycles should correct the + * excess load moved. + */ + if ((env.flags & LBF_DST_PINNED) && env.imbalance > 0) { + + /* Prevent to re-select dst_cpu via env's cpus */ + cpumask_clear_cpu(env.dst_cpu, env.cpus); + + env.dst_rq = cpu_rq(env.new_dst_cpu); + env.dst_cpu = env.new_dst_cpu; + env.flags &= ~LBF_DST_PINNED; + env.loop = 0; + env.loop_break = sched_nr_migrate_break; + + /* + * Go back to "more_balance" rather than "redo" since we + * need to continue with same src_cpu. + */ + goto more_balance; + } + + /* + * We failed to reach balance because of affinity. + */ + if (sd_parent) { + int *group_imbalance = &sd_parent->groups->sgc->imbalance; + + if ((env.flags & LBF_SOME_PINNED) && env.imbalance > 0) + *group_imbalance = 1; + } + + /* All tasks on this runqueue were pinned by CPU affinity */ + if (unlikely(env.flags & LBF_ALL_PINNED)) { + cpumask_clear_cpu(cpu_of(busiest), cpus); + if (!cpumask_empty(cpus)) { + env.loop = 0; + env.loop_break = sched_nr_migrate_break; + goto redo; + } + goto out_all_pinned; + } + } + + if (!ld_moved) { + schedstat_inc(sd, lb_failed[idle]); + /* + * Increment the failure counter only on periodic balance. + * We do not want newidle balance, which can be very + * frequent, pollute the failure counter causing + * excessive cache_hot migrations and active balances. + */ + if (idle != CPU_NEWLY_IDLE) + sd->nr_balance_failed++; + + if (need_active_balance(&env)) { + raw_spin_lock_irqsave(&busiest->lock, flags); + + /* don't kick the active_load_balance_cpu_stop, + * if the curr task on busiest cpu can't be + * moved to this_cpu + */ + if (!cpumask_test_cpu(this_cpu, + tsk_cpus_allowed(busiest->curr))) { + raw_spin_unlock_irqrestore(&busiest->lock, + flags); + env.flags |= LBF_ALL_PINNED; + goto out_one_pinned; + } + + /* + * ->active_balance synchronizes accesses to + * ->active_balance_work. Once set, it's cleared + * only after active load balance is finished. + */ + if (!busiest->active_balance) { + busiest->active_balance = 1; + busiest->push_cpu = this_cpu; + active_balance = 1; + } + raw_spin_unlock_irqrestore(&busiest->lock, flags); + + if (active_balance) { + stop_one_cpu_nowait(cpu_of(busiest), + active_load_balance_cpu_stop, busiest, + &busiest->active_balance_work); + } + + /* + * We've kicked active balancing, reset the failure + * counter. + */ + sd->nr_balance_failed = sd->cache_nice_tries+1; + } + } else + sd->nr_balance_failed = 0; + + if (likely(!active_balance)) { + /* We were unbalanced, so reset the balancing interval */ + sd->balance_interval = sd->min_interval; + } else { + /* + * If we've begun active balancing, start to back off. This + * case may not be covered by the all_pinned logic if there + * is only 1 task on the busy runqueue (because we don't call + * detach_tasks). + */ + if (sd->balance_interval < sd->max_interval) + sd->balance_interval *= 2; + } + + goto out; + +out_balanced: + /* + * We reach balance although we may have faced some affinity + * constraints. Clear the imbalance flag if it was set. + */ + if (sd_parent) { + int *group_imbalance = &sd_parent->groups->sgc->imbalance; + + if (*group_imbalance) + *group_imbalance = 0; + } + +out_all_pinned: + /* + * We reach balance because all tasks are pinned at this level so + * we can't migrate them. Let the imbalance flag set so parent level + * can try to migrate them. + */ + schedstat_inc(sd, lb_balanced[idle]); + + sd->nr_balance_failed = 0; + +out_one_pinned: + /* tune up the balancing interval */ + if (((env.flags & LBF_ALL_PINNED) && + sd->balance_interval < MAX_PINNED_INTERVAL) || + (sd->balance_interval < sd->max_interval)) + sd->balance_interval *= 2; + + ld_moved = 0; +out: + return ld_moved; +} + +static inline unsigned long +get_sd_balance_interval(struct sched_domain *sd, int cpu_busy) +{ + unsigned long interval = sd->balance_interval; + + if (cpu_busy) + interval *= sd->busy_factor; + + /* scale ms to jiffies */ + interval = msecs_to_jiffies(interval); + interval = clamp(interval, 1UL, max_load_balance_interval); + + return interval; +} + +static inline void +update_next_balance(struct sched_domain *sd, int cpu_busy, unsigned long *next_balance) +{ + unsigned long interval, next; + + interval = get_sd_balance_interval(sd, cpu_busy); + next = sd->last_balance + interval; + + if (time_after(*next_balance, next)) + *next_balance = next; +} + +/* + * idle_balance is called by schedule() if this_cpu is about to become + * idle. Attempts to pull tasks from other CPUs. + */ +static int idle_balance(struct rq *this_rq) +{ + unsigned long next_balance = jiffies + HZ; + int this_cpu = this_rq->cpu; + struct sched_domain *sd; + int pulled_task = 0; + u64 curr_cost = 0; + + idle_enter_fair(this_rq); + + /* + * We must set idle_stamp _before_ calling idle_balance(), such that we + * measure the duration of idle_balance() as idle time. + */ + this_rq->idle_stamp = rq_clock(this_rq); + + if (this_rq->avg_idle < sysctl_sched_migration_cost || + !this_rq->rd->overload) { + rcu_read_lock(); + sd = rcu_dereference_check_sched_domain(this_rq->sd); + if (sd) + update_next_balance(sd, 0, &next_balance); + rcu_read_unlock(); + + goto out; + } + + /* + * Drop the rq->lock, but keep IRQ/preempt disabled. + */ + raw_spin_unlock(&this_rq->lock); + + update_blocked_averages(this_cpu); + rcu_read_lock(); + for_each_domain(this_cpu, sd) { + int continue_balancing = 1; + u64 t0, domain_cost; + + if (!(sd->flags & SD_LOAD_BALANCE)) + continue; + + if (this_rq->avg_idle < curr_cost + sd->max_newidle_lb_cost) { + update_next_balance(sd, 0, &next_balance); + break; + } + + if (sd->flags & SD_BALANCE_NEWIDLE) { + t0 = sched_clock_cpu(this_cpu); + + pulled_task = load_balance(this_cpu, this_rq, + sd, CPU_NEWLY_IDLE, + &continue_balancing); + + domain_cost = sched_clock_cpu(this_cpu) - t0; + if (domain_cost > sd->max_newidle_lb_cost) + sd->max_newidle_lb_cost = domain_cost; + + curr_cost += domain_cost; + } + + update_next_balance(sd, 0, &next_balance); + + /* + * Stop searching for tasks to pull if there are + * now runnable tasks on this rq. + */ + if (pulled_task || this_rq->nr_running > 0) + break; + } + rcu_read_unlock(); + + raw_spin_lock(&this_rq->lock); + + if (curr_cost > this_rq->max_idle_balance_cost) + this_rq->max_idle_balance_cost = curr_cost; + + /* + * While browsing the domains, we released the rq lock, a task could + * have been enqueued in the meantime. Since we're not going idle, + * pretend we pulled a task. + */ + if (this_rq->cfs.h_nr_running && !pulled_task) + pulled_task = 1; + +out: + /* Move the next balance forward */ + if (time_after(this_rq->next_balance, next_balance)) + this_rq->next_balance = next_balance; + + /* Is there a task of a high priority class? */ + if (this_rq->nr_running != this_rq->cfs.h_nr_running) + pulled_task = -1; + + if (pulled_task) { + idle_exit_fair(this_rq); + this_rq->idle_stamp = 0; + } + + return pulled_task; +} + +/* + * active_load_balance_cpu_stop is run by cpu stopper. It pushes + * running tasks off the busiest CPU onto idle CPUs. It requires at + * least 1 task to be running on each physical CPU where possible, and + * avoids physical / logical imbalances. + */ +static int active_load_balance_cpu_stop(void *data) +{ + struct rq *busiest_rq = data; + int busiest_cpu = cpu_of(busiest_rq); + int target_cpu = busiest_rq->push_cpu; + struct rq *target_rq = cpu_rq(target_cpu); + struct sched_domain *sd; + struct task_struct *p = NULL; + + raw_spin_lock_irq(&busiest_rq->lock); + + /* make sure the requested cpu hasn't gone down in the meantime */ + if (unlikely(busiest_cpu != smp_processor_id() || + !busiest_rq->active_balance)) + goto out_unlock; + + /* Is there any task to move? */ + if (busiest_rq->nr_running <= 1) + goto out_unlock; + + /* + * This condition is "impossible", if it occurs + * we need to fix it. Originally reported by + * Bjorn Helgaas on a 128-cpu setup. + */ + BUG_ON(busiest_rq == target_rq); + + /* Search for an sd spanning us and the target CPU. */ + rcu_read_lock(); + for_each_domain(target_cpu, sd) { + if ((sd->flags & SD_LOAD_BALANCE) && + cpumask_test_cpu(busiest_cpu, sched_domain_span(sd))) + break; + } + + if (likely(sd)) { + struct lb_env env = { + .sd = sd, + .dst_cpu = target_cpu, + .dst_rq = target_rq, + .src_cpu = busiest_rq->cpu, + .src_rq = busiest_rq, + .idle = CPU_IDLE, + }; + + schedstat_inc(sd, alb_count); + + p = detach_one_task(&env); + if (p) + schedstat_inc(sd, alb_pushed); + else + schedstat_inc(sd, alb_failed); + } + rcu_read_unlock(); +out_unlock: + busiest_rq->active_balance = 0; + raw_spin_unlock(&busiest_rq->lock); + + if (p) + attach_one_task(target_rq, p); + + local_irq_enable(); + + return 0; +} + +static inline int on_null_domain(struct rq *rq) +{ + return unlikely(!rcu_dereference_sched(rq->sd)); +} + +#ifdef CONFIG_NO_HZ_COMMON +/* + * idle load balancing details + * - When one of the busy CPUs notice that there may be an idle rebalancing + * needed, they will kick the idle load balancer, which then does idle + * load balancing for all the idle CPUs. + */ +static struct { + cpumask_var_t idle_cpus_mask; + atomic_t nr_cpus; + unsigned long next_balance; /* in jiffy units */ +} nohz ____cacheline_aligned; + +static inline int find_new_ilb(void) +{ + int ilb = cpumask_first(nohz.idle_cpus_mask); + + if (ilb < nr_cpu_ids && idle_cpu(ilb)) + return ilb; + + return nr_cpu_ids; +} + +/* + * Kick a CPU to do the nohz balancing, if it is time for it. We pick the + * nohz_load_balancer CPU (if there is one) otherwise fallback to any idle + * CPU (if there is one). + */ +static void nohz_balancer_kick(void) +{ + int ilb_cpu; + + nohz.next_balance++; + + ilb_cpu = find_new_ilb(); + + if (ilb_cpu >= nr_cpu_ids) + return; + + if (test_and_set_bit(NOHZ_BALANCE_KICK, nohz_flags(ilb_cpu))) + return; + /* + * Use smp_send_reschedule() instead of resched_cpu(). + * This way we generate a sched IPI on the target cpu which + * is idle. And the softirq performing nohz idle load balance + * will be run before returning from the IPI. + */ + smp_send_reschedule(ilb_cpu); + return; +} + +static inline void nohz_balance_exit_idle(int cpu) +{ + if (unlikely(test_bit(NOHZ_TICK_STOPPED, nohz_flags(cpu)))) { + /* + * Completely isolated CPUs don't ever set, so we must test. + */ + if (likely(cpumask_test_cpu(cpu, nohz.idle_cpus_mask))) { + cpumask_clear_cpu(cpu, nohz.idle_cpus_mask); + atomic_dec(&nohz.nr_cpus); + } + clear_bit(NOHZ_TICK_STOPPED, nohz_flags(cpu)); + } +} + +static inline void set_cpu_sd_state_busy(void) +{ + struct sched_domain *sd; + int cpu = smp_processor_id(); + + rcu_read_lock(); + sd = rcu_dereference(per_cpu(sd_busy, cpu)); + + if (!sd || !sd->nohz_idle) + goto unlock; + sd->nohz_idle = 0; + + atomic_inc(&sd->groups->sgc->nr_busy_cpus); +unlock: + rcu_read_unlock(); +} + +void set_cpu_sd_state_idle(void) +{ + struct sched_domain *sd; + int cpu = smp_processor_id(); + + rcu_read_lock(); + sd = rcu_dereference(per_cpu(sd_busy, cpu)); + + if (!sd || sd->nohz_idle) + goto unlock; + sd->nohz_idle = 1; + + atomic_dec(&sd->groups->sgc->nr_busy_cpus); +unlock: + rcu_read_unlock(); +} + +/* + * This routine will record that the cpu is going idle with tick stopped. + * This info will be used in performing idle load balancing in the future. + */ +void nohz_balance_enter_idle(int cpu) +{ + /* + * If this cpu is going down, then nothing needs to be done. + */ + if (!cpu_active(cpu)) + return; + + if (test_bit(NOHZ_TICK_STOPPED, nohz_flags(cpu))) + return; + + /* + * If we're a completely isolated CPU, we don't play. + */ + if (on_null_domain(cpu_rq(cpu))) + return; + + cpumask_set_cpu(cpu, nohz.idle_cpus_mask); + atomic_inc(&nohz.nr_cpus); + set_bit(NOHZ_TICK_STOPPED, nohz_flags(cpu)); +} + +static int sched_ilb_notifier(struct notifier_block *nfb, + unsigned long action, void *hcpu) +{ + switch (action & ~CPU_TASKS_FROZEN) { + case CPU_DYING: + nohz_balance_exit_idle(smp_processor_id()); + return NOTIFY_OK; + default: + return NOTIFY_DONE; + } +} +#endif + +static DEFINE_SPINLOCK(balancing); + +/* + * Scale the max load_balance interval with the number of CPUs in the system. + * This trades load-balance latency on larger machines for less cross talk. + */ +void update_max_interval(void) +{ + max_load_balance_interval = HZ*num_online_cpus()/10; +} + +/* + * It checks each scheduling domain to see if it is due to be balanced, + * and initiates a balancing operation if so. + * + * Balancing parameters are set up in init_sched_domains. + */ +static void rebalance_domains(struct rq *rq, enum cpu_idle_type idle) +{ + int continue_balancing = 1; + int cpu = rq->cpu; + unsigned long interval; + struct sched_domain *sd; + /* Earliest time when we have to do rebalance again */ + unsigned long next_balance = jiffies + 60*HZ; + int update_next_balance = 0; + int need_serialize, need_decay = 0; + u64 max_cost = 0; + + update_blocked_averages(cpu); + + rcu_read_lock(); + for_each_domain(cpu, sd) { + /* + * Decay the newidle max times here because this is a regular + * visit to all the domains. Decay ~1% per second. + */ + if (time_after(jiffies, sd->next_decay_max_lb_cost)) { + sd->max_newidle_lb_cost = + (sd->max_newidle_lb_cost * 253) / 256; + sd->next_decay_max_lb_cost = jiffies + HZ; + need_decay = 1; + } + max_cost += sd->max_newidle_lb_cost; + + if (!(sd->flags & SD_LOAD_BALANCE)) + continue; + + /* + * Stop the load balance at this level. There is another + * CPU in our sched group which is doing load balancing more + * actively. + */ + if (!continue_balancing) { + if (need_decay) + continue; + break; + } + + interval = get_sd_balance_interval(sd, idle != CPU_IDLE); + + need_serialize = sd->flags & SD_SERIALIZE; + if (need_serialize) { + if (!spin_trylock(&balancing)) + goto out; + } + + if (time_after_eq(jiffies, sd->last_balance + interval)) { + if (load_balance(cpu, rq, sd, idle, &continue_balancing)) { + /* + * The LBF_DST_PINNED logic could have changed + * env->dst_cpu, so we can't know our idle + * state even if we migrated tasks. Update it. + */ + idle = idle_cpu(cpu) ? CPU_IDLE : CPU_NOT_IDLE; + } + sd->last_balance = jiffies; + interval = get_sd_balance_interval(sd, idle != CPU_IDLE); + } + if (need_serialize) + spin_unlock(&balancing); +out: + if (time_after(next_balance, sd->last_balance + interval)) { + next_balance = sd->last_balance + interval; + update_next_balance = 1; + } + } + if (need_decay) { + /* + * Ensure the rq-wide value also decays but keep it at a + * reasonable floor to avoid funnies with rq->avg_idle. + */ + rq->max_idle_balance_cost = + max((u64)sysctl_sched_migration_cost, max_cost); + } + rcu_read_unlock(); + + /* + * next_balance will be updated only when there is a need. + * When the cpu is attached to null domain for ex, it will not be + * updated. + */ + if (likely(update_next_balance)) + rq->next_balance = next_balance; +} + +#ifdef CONFIG_NO_HZ_COMMON +/* + * In CONFIG_NO_HZ_COMMON case, the idle balance kickee will do the + * rebalancing for all the cpus for whom scheduler ticks are stopped. + */ +static void nohz_idle_balance(struct rq *this_rq, enum cpu_idle_type idle) +{ + int this_cpu = this_rq->cpu; + struct rq *rq; + int balance_cpu; + + if (idle != CPU_IDLE || + !test_bit(NOHZ_BALANCE_KICK, nohz_flags(this_cpu))) + goto end; + + for_each_cpu(balance_cpu, nohz.idle_cpus_mask) { + if (balance_cpu == this_cpu || !idle_cpu(balance_cpu)) + continue; + + /* + * If this cpu gets work to do, stop the load balancing + * work being done for other cpus. Next load + * balancing owner will pick it up. + */ + if (need_resched()) + break; + + rq = cpu_rq(balance_cpu); + + /* + * If time for next balance is due, + * do the balance. + */ + if (time_after_eq(jiffies, rq->next_balance)) { + raw_spin_lock_irq(&rq->lock); + update_rq_clock(rq); + update_idle_cpu_load(rq); + raw_spin_unlock_irq(&rq->lock); + rebalance_domains(rq, CPU_IDLE); + } + + if (time_after(this_rq->next_balance, rq->next_balance)) + this_rq->next_balance = rq->next_balance; + } + nohz.next_balance = this_rq->next_balance; +end: + clear_bit(NOHZ_BALANCE_KICK, nohz_flags(this_cpu)); +} + +/* + * Current heuristic for kicking the idle load balancer in the presence + * of an idle cpu in the system. + * - This rq has more than one task. + * - This rq has at least one CFS task and the capacity of the CPU is + * significantly reduced because of RT tasks or IRQs. + * - At parent of LLC scheduler domain level, this cpu's scheduler group has + * multiple busy cpu. + * - For SD_ASYM_PACKING, if the lower numbered cpu's in the scheduler + * domain span are idle. + */ +static inline bool nohz_kick_needed(struct rq *rq) +{ + unsigned long now = jiffies; + struct sched_domain *sd; + struct sched_group_capacity *sgc; + int nr_busy, cpu = rq->cpu; + bool kick = false; + + if (unlikely(rq->idle_balance)) + return false; + + /* + * We may be recently in ticked or tickless idle mode. At the first + * busy tick after returning from idle, we will update the busy stats. + */ + set_cpu_sd_state_busy(); + nohz_balance_exit_idle(cpu); + + /* + * None are in tickless mode and hence no need for NOHZ idle load + * balancing. + */ + if (likely(!atomic_read(&nohz.nr_cpus))) + return false; + + if (time_before(now, nohz.next_balance)) + return false; + + if (rq->nr_running >= 2) + return true; + + rcu_read_lock(); + sd = rcu_dereference(per_cpu(sd_busy, cpu)); + if (sd) { + sgc = sd->groups->sgc; + nr_busy = atomic_read(&sgc->nr_busy_cpus); + + if (nr_busy > 1) { + kick = true; + goto unlock; + } + + } + + sd = rcu_dereference(rq->sd); + if (sd) { + if ((rq->cfs.h_nr_running >= 1) && + check_cpu_capacity(rq, sd)) { + kick = true; + goto unlock; + } + } + + sd = rcu_dereference(per_cpu(sd_asym, cpu)); + if (sd && (cpumask_first_and(nohz.idle_cpus_mask, + sched_domain_span(sd)) < cpu)) { + kick = true; + goto unlock; + } + +unlock: + rcu_read_unlock(); + return kick; +} +#else +static void nohz_idle_balance(struct rq *this_rq, enum cpu_idle_type idle) { } +#endif + +/* + * run_rebalance_domains is triggered when needed from the scheduler tick. + * Also triggered for nohz idle balancing (with nohz_balancing_kick set). + */ +static void run_rebalance_domains(struct softirq_action *h) +{ + struct rq *this_rq = this_rq(); + enum cpu_idle_type idle = this_rq->idle_balance ? + CPU_IDLE : CPU_NOT_IDLE; + + /* + * If this cpu has a pending nohz_balance_kick, then do the + * balancing on behalf of the other idle cpus whose ticks are + * stopped. Do nohz_idle_balance *before* rebalance_domains to + * give the idle cpus a chance to load balance. Else we may + * load balance only within the local sched_domain hierarchy + * and abort nohz_idle_balance altogether if we pull some load. + */ + nohz_idle_balance(this_rq, idle); + rebalance_domains(this_rq, idle); +} + +/* + * Trigger the SCHED_SOFTIRQ if it is time to do periodic load balancing. + */ +void trigger_load_balance(struct rq *rq) +{ + /* Don't need to rebalance while attached to NULL domain */ + if (unlikely(on_null_domain(rq))) + return; + + if (time_after_eq(jiffies, rq->next_balance)) + raise_softirq(SCHED_SOFTIRQ); +#ifdef CONFIG_NO_HZ_COMMON + if (nohz_kick_needed(rq)) + nohz_balancer_kick(); +#endif +} + +static void rq_online_fair(struct rq *rq) +{ + update_sysctl(); + + update_runtime_enabled(rq); +} + +static void rq_offline_fair(struct rq *rq) +{ + update_sysctl(); + + /* Ensure any throttled groups are reachable by pick_next_task */ + unthrottle_offline_cfs_rqs(rq); +} + +#endif /* CONFIG_SMP */ + +/* + * scheduler tick hitting a task of our scheduling class: + */ +static void task_tick_fair(struct rq *rq, struct task_struct *curr, int queued) +{ + struct cfs_rq *cfs_rq; + struct sched_entity *se = &curr->se; + + for_each_sched_entity(se) { + cfs_rq = cfs_rq_of(se); + entity_tick(cfs_rq, se, queued); + } + + if (numabalancing_enabled) + task_tick_numa(rq, curr); + + update_rq_runnable_avg(rq, 1); +} + +/* + * called on fork with the child task as argument from the parent's context + * - child not yet on the tasklist + * - preemption disabled + */ +static void task_fork_fair(struct task_struct *p) +{ + struct cfs_rq *cfs_rq; + struct sched_entity *se = &p->se, *curr; + int this_cpu = smp_processor_id(); + struct rq *rq = this_rq(); + unsigned long flags; + + raw_spin_lock_irqsave(&rq->lock, flags); + + update_rq_clock(rq); + + cfs_rq = task_cfs_rq(current); + curr = cfs_rq->curr; + + /* + * Not only the cpu but also the task_group of the parent might have + * been changed after parent->se.parent,cfs_rq were copied to + * child->se.parent,cfs_rq. So call __set_task_cpu() to make those + * of child point to valid ones. + */ + rcu_read_lock(); + __set_task_cpu(p, this_cpu); + rcu_read_unlock(); + + update_curr(cfs_rq); + + if (curr) + se->vruntime = curr->vruntime; + place_entity(cfs_rq, se, 1); + + if (sysctl_sched_child_runs_first && curr && entity_before(curr, se)) { + /* + * Upon rescheduling, sched_class::put_prev_task() will place + * 'current' within the tree based on its new key value. + */ + swap(curr->vruntime, se->vruntime); + resched_curr_lazy(rq); + } + + se->vruntime -= cfs_rq->min_vruntime; + + raw_spin_unlock_irqrestore(&rq->lock, flags); +} + +/* + * Priority of the task has changed. Check to see if we preempt + * the current task. + */ +static void +prio_changed_fair(struct rq *rq, struct task_struct *p, int oldprio) +{ + if (!task_on_rq_queued(p)) + return; + + /* + * Reschedule if we are currently running on this runqueue and + * our priority decreased, or if we are not currently running on + * this runqueue and our priority is higher than the current's + */ + if (rq->curr == p) { + if (p->prio > oldprio) + resched_curr_lazy(rq); + } else + check_preempt_curr(rq, p, 0); +} + +static void switched_from_fair(struct rq *rq, struct task_struct *p) +{ + struct sched_entity *se = &p->se; + struct cfs_rq *cfs_rq = cfs_rq_of(se); + + /* + * Ensure the task's vruntime is normalized, so that when it's + * switched back to the fair class the enqueue_entity(.flags=0) will + * do the right thing. + * + * If it's queued, then the dequeue_entity(.flags=0) will already + * have normalized the vruntime, if it's !queued, then only when + * the task is sleeping will it still have non-normalized vruntime. + */ + if (!task_on_rq_queued(p) && p->state != TASK_RUNNING) { + /* + * Fix up our vruntime so that the current sleep doesn't + * cause 'unlimited' sleep bonus. + */ + place_entity(cfs_rq, se, 0); + se->vruntime -= cfs_rq->min_vruntime; + } + +#ifdef CONFIG_SMP + /* + * Remove our load from contribution when we leave sched_fair + * and ensure we don't carry in an old decay_count if we + * switch back. + */ + if (se->avg.decay_count) { + __synchronize_entity_decay(se); + subtract_blocked_load_contrib(cfs_rq, se->avg.load_avg_contrib); + } +#endif +} + +/* + * We switched to the sched_fair class. + */ +static void switched_to_fair(struct rq *rq, struct task_struct *p) +{ +#ifdef CONFIG_FAIR_GROUP_SCHED + struct sched_entity *se = &p->se; + /* + * Since the real-depth could have been changed (only FAIR + * class maintain depth value), reset depth properly. + */ + se->depth = se->parent ? se->parent->depth + 1 : 0; +#endif + if (!task_on_rq_queued(p)) + return; + + /* + * We were most likely switched from sched_rt, so + * kick off the schedule if running, otherwise just see + * if we can still preempt the current task. + */ + if (rq->curr == p) + resched_curr(rq); + else + check_preempt_curr(rq, p, 0); +} + +/* Account for a task changing its policy or group. + * + * This routine is mostly called to set cfs_rq->curr field when a task + * migrates between groups/classes. + */ +static void set_curr_task_fair(struct rq *rq) +{ + struct sched_entity *se = &rq->curr->se; + + for_each_sched_entity(se) { + struct cfs_rq *cfs_rq = cfs_rq_of(se); + + set_next_entity(cfs_rq, se); + /* ensure bandwidth has been allocated on our new cfs_rq */ + account_cfs_rq_runtime(cfs_rq, 0); + } +} + +void init_cfs_rq(struct cfs_rq *cfs_rq) +{ + cfs_rq->tasks_timeline = RB_ROOT; + cfs_rq->min_vruntime = (u64)(-(1LL << 20)); +#ifndef CONFIG_64BIT + cfs_rq->min_vruntime_copy = cfs_rq->min_vruntime; +#endif +#ifdef CONFIG_SMP + atomic64_set(&cfs_rq->decay_counter, 1); + atomic_long_set(&cfs_rq->removed_load, 0); +#endif +} + +#ifdef CONFIG_FAIR_GROUP_SCHED +static void task_move_group_fair(struct task_struct *p, int queued) +{ + struct sched_entity *se = &p->se; + struct cfs_rq *cfs_rq; + + /* + * If the task was not on the rq at the time of this cgroup movement + * it must have been asleep, sleeping tasks keep their ->vruntime + * absolute on their old rq until wakeup (needed for the fair sleeper + * bonus in place_entity()). + * + * If it was on the rq, we've just 'preempted' it, which does convert + * ->vruntime to a relative base. + * + * Make sure both cases convert their relative position when migrating + * to another cgroup's rq. This does somewhat interfere with the + * fair sleeper stuff for the first placement, but who cares. + */ + /* + * When !queued, vruntime of the task has usually NOT been normalized. + * But there are some cases where it has already been normalized: + * + * - Moving a forked child which is waiting for being woken up by + * wake_up_new_task(). + * - Moving a task which has been woken up by try_to_wake_up() and + * waiting for actually being woken up by sched_ttwu_pending(). + * + * To prevent boost or penalty in the new cfs_rq caused by delta + * min_vruntime between the two cfs_rqs, we skip vruntime adjustment. + */ + if (!queued && (!se->sum_exec_runtime || p->state == TASK_WAKING)) + queued = 1; + + if (!queued) + se->vruntime -= cfs_rq_of(se)->min_vruntime; + set_task_rq(p, task_cpu(p)); + se->depth = se->parent ? se->parent->depth + 1 : 0; + if (!queued) { + cfs_rq = cfs_rq_of(se); + se->vruntime += cfs_rq->min_vruntime; +#ifdef CONFIG_SMP + /* + * migrate_task_rq_fair() will have removed our previous + * contribution, but we must synchronize for ongoing future + * decay. + */ + se->avg.decay_count = atomic64_read(&cfs_rq->decay_counter); + cfs_rq->blocked_load_avg += se->avg.load_avg_contrib; +#endif + } +} + +void free_fair_sched_group(struct task_group *tg) +{ + int i; + + destroy_cfs_bandwidth(tg_cfs_bandwidth(tg)); + + for_each_possible_cpu(i) { + if (tg->cfs_rq) + kfree(tg->cfs_rq[i]); + if (tg->se) + kfree(tg->se[i]); + } + + kfree(tg->cfs_rq); + kfree(tg->se); +} + +int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent) +{ + struct cfs_rq *cfs_rq; + struct sched_entity *se; + int i; + + tg->cfs_rq = kzalloc(sizeof(cfs_rq) * nr_cpu_ids, GFP_KERNEL); + if (!tg->cfs_rq) + goto err; + tg->se = kzalloc(sizeof(se) * nr_cpu_ids, GFP_KERNEL); + if (!tg->se) + goto err; + + tg->shares = NICE_0_LOAD; + + init_cfs_bandwidth(tg_cfs_bandwidth(tg)); + + for_each_possible_cpu(i) { + cfs_rq = kzalloc_node(sizeof(struct cfs_rq), + GFP_KERNEL, cpu_to_node(i)); + if (!cfs_rq) + goto err; + + se = kzalloc_node(sizeof(struct sched_entity), + GFP_KERNEL, cpu_to_node(i)); + if (!se) + goto err_free_rq; + + init_cfs_rq(cfs_rq); + init_tg_cfs_entry(tg, cfs_rq, se, i, parent->se[i]); + } + + return 1; + +err_free_rq: + kfree(cfs_rq); +err: + return 0; +} + +void unregister_fair_sched_group(struct task_group *tg, int cpu) +{ + struct rq *rq = cpu_rq(cpu); + unsigned long flags; + + /* + * Only empty task groups can be destroyed; so we can speculatively + * check on_list without danger of it being re-added. + */ + if (!tg->cfs_rq[cpu]->on_list) + return; + + raw_spin_lock_irqsave(&rq->lock, flags); + list_del_leaf_cfs_rq(tg->cfs_rq[cpu]); + raw_spin_unlock_irqrestore(&rq->lock, flags); +} + +void init_tg_cfs_entry(struct task_group *tg, struct cfs_rq *cfs_rq, + struct sched_entity *se, int cpu, + struct sched_entity *parent) +{ + struct rq *rq = cpu_rq(cpu); + + cfs_rq->tg = tg; + cfs_rq->rq = rq; + init_cfs_rq_runtime(cfs_rq); + + tg->cfs_rq[cpu] = cfs_rq; + tg->se[cpu] = se; + + /* se could be NULL for root_task_group */ + if (!se) + return; + + if (!parent) { + se->cfs_rq = &rq->cfs; + se->depth = 0; + } else { + se->cfs_rq = parent->my_q; + se->depth = parent->depth + 1; + } + + se->my_q = cfs_rq; + /* guarantee group entities always have weight */ + update_load_set(&se->load, NICE_0_LOAD); + se->parent = parent; +} + +static DEFINE_MUTEX(shares_mutex); + +int sched_group_set_shares(struct task_group *tg, unsigned long shares) +{ + int i; + unsigned long flags; + + /* + * We can't change the weight of the root cgroup. + */ + if (!tg->se[0]) + return -EINVAL; + + shares = clamp(shares, scale_load(MIN_SHARES), scale_load(MAX_SHARES)); + + mutex_lock(&shares_mutex); + if (tg->shares == shares) + goto done; + + tg->shares = shares; + for_each_possible_cpu(i) { + struct rq *rq = cpu_rq(i); + struct sched_entity *se; + + se = tg->se[i]; + /* Propagate contribution to hierarchy */ + raw_spin_lock_irqsave(&rq->lock, flags); + + /* Possible calls to update_curr() need rq clock */ + update_rq_clock(rq); + for_each_sched_entity(se) + update_cfs_shares(group_cfs_rq(se)); + raw_spin_unlock_irqrestore(&rq->lock, flags); + } + +done: + mutex_unlock(&shares_mutex); + return 0; +} +#else /* CONFIG_FAIR_GROUP_SCHED */ + +void free_fair_sched_group(struct task_group *tg) { } + +int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent) +{ + return 1; +} + +void unregister_fair_sched_group(struct task_group *tg, int cpu) { } + +#endif /* CONFIG_FAIR_GROUP_SCHED */ + + +static unsigned int get_rr_interval_fair(struct rq *rq, struct task_struct *task) +{ + struct sched_entity *se = &task->se; + unsigned int rr_interval = 0; + + /* + * Time slice is 0 for SCHED_OTHER tasks that are on an otherwise + * idle runqueue: + */ + if (rq->cfs.load.weight) + rr_interval = NS_TO_JIFFIES(sched_slice(cfs_rq_of(se), se)); + + return rr_interval; +} + +/* + * All the scheduling class methods: + */ +const struct sched_class fair_sched_class = { + .next = &idle_sched_class, + .enqueue_task = enqueue_task_fair, + .dequeue_task = dequeue_task_fair, + .yield_task = yield_task_fair, + .yield_to_task = yield_to_task_fair, + + .check_preempt_curr = check_preempt_wakeup, + + .pick_next_task = pick_next_task_fair, + .put_prev_task = put_prev_task_fair, + +#ifdef CONFIG_SMP + .select_task_rq = select_task_rq_fair, + .migrate_task_rq = migrate_task_rq_fair, + + .rq_online = rq_online_fair, + .rq_offline = rq_offline_fair, + + .task_waking = task_waking_fair, +#endif + + .set_curr_task = set_curr_task_fair, + .task_tick = task_tick_fair, + .task_fork = task_fork_fair, + + .prio_changed = prio_changed_fair, + .switched_from = switched_from_fair, + .switched_to = switched_to_fair, + + .get_rr_interval = get_rr_interval_fair, + + .update_curr = update_curr_fair, + +#ifdef CONFIG_FAIR_GROUP_SCHED + .task_move_group = task_move_group_fair, +#endif +}; + +#ifdef CONFIG_SCHED_DEBUG +void print_cfs_stats(struct seq_file *m, int cpu) +{ + struct cfs_rq *cfs_rq; + + rcu_read_lock(); + for_each_leaf_cfs_rq(cpu_rq(cpu), cfs_rq) + print_cfs_rq(m, cpu, cfs_rq); + rcu_read_unlock(); +} +#endif + +__init void init_sched_fair_class(void) +{ +#ifdef CONFIG_SMP + open_softirq(SCHED_SOFTIRQ, run_rebalance_domains); + +#ifdef CONFIG_NO_HZ_COMMON + nohz.next_balance = jiffies; + zalloc_cpumask_var(&nohz.idle_cpus_mask, GFP_NOWAIT); + cpu_notifier(sched_ilb_notifier, 0); +#endif +#endif /* SMP */ + +} diff --git a/kernel/kernel/sched/features.h b/kernel/kernel/sched/features.h new file mode 100644 index 000000000..0ea4e3775 --- /dev/null +++ b/kernel/kernel/sched/features.h @@ -0,0 +1,106 @@ +/* + * Only give sleepers 50% of their service deficit. This allows + * them to run sooner, but does not allow tons of sleepers to + * rip the spread apart. + */ +SCHED_FEAT(GENTLE_FAIR_SLEEPERS, true) + +/* + * Place new tasks ahead so that they do not starve already running + * tasks + */ +SCHED_FEAT(START_DEBIT, true) + +/* + * Prefer to schedule the task we woke last (assuming it failed + * wakeup-preemption), since its likely going to consume data we + * touched, increases cache locality. + */ +SCHED_FEAT(NEXT_BUDDY, false) + +/* + * Prefer to schedule the task that ran last (when we did + * wake-preempt) as that likely will touch the same data, increases + * cache locality. + */ +SCHED_FEAT(LAST_BUDDY, true) + +/* + * Consider buddies to be cache hot, decreases the likelyness of a + * cache buddy being migrated away, increases cache locality. + */ +SCHED_FEAT(CACHE_HOT_BUDDY, true) + +/* + * Allow wakeup-time preemption of the current task: + */ +SCHED_FEAT(WAKEUP_PREEMPTION, true) + +/* + * Use arch dependent cpu capacity functions + */ +SCHED_FEAT(ARCH_CAPACITY, true) + +SCHED_FEAT(HRTICK, false) +SCHED_FEAT(DOUBLE_TICK, false) +SCHED_FEAT(LB_BIAS, true) + +/* + * Decrement CPU capacity based on time not spent running tasks + */ +SCHED_FEAT(NONTASK_CAPACITY, true) + +#ifdef CONFIG_PREEMPT_RT_FULL +SCHED_FEAT(TTWU_QUEUE, false) +# ifdef CONFIG_PREEMPT_LAZY +SCHED_FEAT(PREEMPT_LAZY, true) +# endif +#else + +/* + * Queue remote wakeups on the target CPU and process them + * using the scheduler IPI. Reduces rq->lock contention/bounces. + */ +SCHED_FEAT(TTWU_QUEUE, true) +#endif + +#ifdef HAVE_RT_PUSH_IPI +/* + * In order to avoid a thundering herd attack of CPUs that are + * lowering their priorities at the same time, and there being + * a single CPU that has an RT task that can migrate and is waiting + * to run, where the other CPUs will try to take that CPUs + * rq lock and possibly create a large contention, sending an + * IPI to that CPU and let that CPU push the RT task to where + * it should go may be a better scenario. + */ +SCHED_FEAT(RT_PUSH_IPI, true) +#endif + +SCHED_FEAT(FORCE_SD_OVERLAP, false) +SCHED_FEAT(RT_RUNTIME_SHARE, true) +SCHED_FEAT(LB_MIN, false) + +/* + * Apply the automatic NUMA scheduling policy. Enabled automatically + * at runtime if running on a NUMA machine. Can be controlled via + * numa_balancing= + */ +#ifdef CONFIG_NUMA_BALANCING +SCHED_FEAT(NUMA, false) + +/* + * NUMA_FAVOUR_HIGHER will favor moving tasks towards nodes where a + * higher number of hinting faults are recorded during active load + * balancing. + */ +SCHED_FEAT(NUMA_FAVOUR_HIGHER, true) + +/* + * NUMA_RESIST_LOWER will resist moving tasks towards nodes where a + * lower number of hinting faults have been recorded. As this has + * the potential to prevent a task ever migrating to a new node + * due to CPU overload it is disabled by default. + */ +SCHED_FEAT(NUMA_RESIST_LOWER, false) +#endif diff --git a/kernel/kernel/sched/idle.c b/kernel/kernel/sched/idle.c new file mode 100644 index 000000000..fefcb1fa5 --- /dev/null +++ b/kernel/kernel/sched/idle.c @@ -0,0 +1,298 @@ +/* + * Generic entry point for the idle threads + */ +#include +#include +#include +#include +#include +#include +#include + +#include + +#include + +#include "sched.h" + +static int __read_mostly cpu_idle_force_poll; + +void cpu_idle_poll_ctrl(bool enable) +{ + if (enable) { + cpu_idle_force_poll++; + } else { + cpu_idle_force_poll--; + WARN_ON_ONCE(cpu_idle_force_poll < 0); + } +} + +#ifdef CONFIG_GENERIC_IDLE_POLL_SETUP +static int __init cpu_idle_poll_setup(char *__unused) +{ + cpu_idle_force_poll = 1; + return 1; +} +__setup("nohlt", cpu_idle_poll_setup); + +static int __init cpu_idle_nopoll_setup(char *__unused) +{ + cpu_idle_force_poll = 0; + return 1; +} +__setup("hlt", cpu_idle_nopoll_setup); +#endif + +static inline int cpu_idle_poll(void) +{ + rcu_idle_enter(); + trace_cpu_idle_rcuidle(0, smp_processor_id()); + local_irq_enable(); + while (!tif_need_resched() && + (cpu_idle_force_poll || tick_check_broadcast_expired())) + cpu_relax(); + trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id()); + rcu_idle_exit(); + return 1; +} + +/* Weak implementations for optional arch specific functions */ +void __weak arch_cpu_idle_prepare(void) { } +void __weak arch_cpu_idle_enter(void) { } +void __weak arch_cpu_idle_exit(void) { } +void __weak arch_cpu_idle_dead(void) { } +void __weak arch_cpu_idle(void) +{ + cpu_idle_force_poll = 1; + local_irq_enable(); +} + +/** + * cpuidle_idle_call - the main idle function + * + * NOTE: no locks or semaphores should be used here + * + * On archs that support TIF_POLLING_NRFLAG, is called with polling + * set, and it returns with polling set. If it ever stops polling, it + * must clear the polling bit. + */ +static void cpuidle_idle_call(void) +{ + struct cpuidle_device *dev = __this_cpu_read(cpuidle_devices); + struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev); + int next_state, entered_state; + bool reflect; + + /* + * Check if the idle task must be rescheduled. If it is the + * case, exit the function after re-enabling the local irq. + */ + if (need_resched()) { + local_irq_enable(); + return; + } + + /* + * During the idle period, stop measuring the disabled irqs + * critical sections latencies + */ + stop_critical_timings(); + + /* + * Tell the RCU framework we are entering an idle section, + * so no more rcu read side critical sections and one more + * step to the grace period + */ + rcu_idle_enter(); + + if (cpuidle_not_available(drv, dev)) + goto use_default; + + /* + * Suspend-to-idle ("freeze") is a system state in which all user space + * has been frozen, all I/O devices have been suspended and the only + * activity happens here and in iterrupts (if any). In that case bypass + * the cpuidle governor and go stratight for the deepest idle state + * available. Possibly also suspend the local tick and the entire + * timekeeping to prevent timer interrupts from kicking us out of idle + * until a proper wakeup interrupt happens. + */ + if (idle_should_freeze()) { + entered_state = cpuidle_enter_freeze(drv, dev); + if (entered_state >= 0) { + local_irq_enable(); + goto exit_idle; + } + + reflect = false; + next_state = cpuidle_find_deepest_state(drv, dev); + } else { + reflect = true; + /* + * Ask the cpuidle framework to choose a convenient idle state. + */ + next_state = cpuidle_select(drv, dev); + } + /* Fall back to the default arch idle method on errors. */ + if (next_state < 0) + goto use_default; + + /* + * The idle task must be scheduled, it is pointless to + * go to idle, just update no idle residency and get + * out of this function + */ + if (current_clr_polling_and_test()) { + dev->last_residency = 0; + entered_state = next_state; + local_irq_enable(); + goto exit_idle; + } + + /* Take note of the planned idle state. */ + idle_set_state(this_rq(), &drv->states[next_state]); + + /* + * Enter the idle state previously returned by the governor decision. + * This function will block until an interrupt occurs and will take + * care of re-enabling the local interrupts + */ + entered_state = cpuidle_enter(drv, dev, next_state); + + /* The cpu is no longer idle or about to enter idle. */ + idle_set_state(this_rq(), NULL); + + if (entered_state == -EBUSY) + goto use_default; + + /* + * Give the governor an opportunity to reflect on the outcome + */ + if (reflect) + cpuidle_reflect(dev, entered_state); + +exit_idle: + __current_set_polling(); + + /* + * It is up to the idle functions to reenable local interrupts + */ + if (WARN_ON_ONCE(irqs_disabled())) + local_irq_enable(); + + rcu_idle_exit(); + start_critical_timings(); + return; + +use_default: + /* + * We can't use the cpuidle framework, let's use the default + * idle routine. + */ + if (current_clr_polling_and_test()) + local_irq_enable(); + else + arch_cpu_idle(); + + goto exit_idle; +} + +DEFINE_PER_CPU(bool, cpu_dead_idle); + +/* + * Generic idle loop implementation + * + * Called with polling cleared. + */ +static void cpu_idle_loop(void) +{ + while (1) { + /* + * If the arch has a polling bit, we maintain an invariant: + * + * Our polling bit is clear if we're not scheduled (i.e. if + * rq->curr != rq->idle). This means that, if rq->idle has + * the polling bit set, then setting need_resched is + * guaranteed to cause the cpu to reschedule. + */ + + __current_set_polling(); + tick_nohz_idle_enter(); + + while (!need_resched()) { + check_pgt_cache(); + rmb(); + + if (cpu_is_offline(smp_processor_id())) { + rcu_cpu_notify(NULL, CPU_DYING_IDLE, + (void *)(long)smp_processor_id()); + smp_mb(); /* all activity before dead. */ + this_cpu_write(cpu_dead_idle, true); + arch_cpu_idle_dead(); + } + + local_irq_disable(); + arch_cpu_idle_enter(); + + /* + * In poll mode we reenable interrupts and spin. + * + * Also if we detected in the wakeup from idle + * path that the tick broadcast device expired + * for us, we don't want to go deep idle as we + * know that the IPI is going to arrive right + * away + */ + if (cpu_idle_force_poll || tick_check_broadcast_expired()) + cpu_idle_poll(); + else + cpuidle_idle_call(); + + arch_cpu_idle_exit(); + } + + /* + * Since we fell out of the loop above, we know + * TIF_NEED_RESCHED must be set, propagate it into + * PREEMPT_NEED_RESCHED. + * + * This is required because for polling idle loops we will + * not have had an IPI to fold the state for us. + */ + preempt_set_need_resched(); + tick_nohz_idle_exit(); + __current_clr_polling(); + + /* + * We promise to call sched_ttwu_pending and reschedule + * if need_resched is set while polling is set. That + * means that clearing polling needs to be visible + * before doing these things. + */ + smp_mb__after_atomic(); + + sched_ttwu_pending(); + schedule_preempt_disabled(); + } +} + +void cpu_startup_entry(enum cpuhp_state state) +{ + /* + * This #ifdef needs to die, but it's too late in the cycle to + * make this generic (arm and sh have never invoked the canary + * init for the non boot cpus!). Will be fixed in 3.11 + */ +#ifdef CONFIG_X86 + /* + * If we're the non-boot CPU, nothing set the stack canary up + * for us. The boot CPU already has it initialized but no harm + * in doing it again. This is a good place for updating it, as + * we wont ever return from this function (so the invalid + * canaries already on the stack wont ever trigger). + */ + boot_init_stack_canary(); +#endif + arch_cpu_idle_prepare(); + cpu_idle_loop(); +} diff --git a/kernel/kernel/sched/idle_task.c b/kernel/kernel/sched/idle_task.c new file mode 100644 index 000000000..c65dac8c9 --- /dev/null +++ b/kernel/kernel/sched/idle_task.c @@ -0,0 +1,109 @@ +#include "sched.h" + +/* + * idle-task scheduling class. + * + * (NOTE: these are not related to SCHED_IDLE tasks which are + * handled in sched/fair.c) + */ + +#ifdef CONFIG_SMP +static int +select_task_rq_idle(struct task_struct *p, int cpu, int sd_flag, int flags) +{ + return task_cpu(p); /* IDLE tasks as never migrated */ +} +#endif /* CONFIG_SMP */ + +/* + * Idle tasks are unconditionally rescheduled: + */ +static void check_preempt_curr_idle(struct rq *rq, struct task_struct *p, int flags) +{ + resched_curr(rq); +} + +static struct task_struct * +pick_next_task_idle(struct rq *rq, struct task_struct *prev) +{ + put_prev_task(rq, prev); + + schedstat_inc(rq, sched_goidle); + return rq->idle; +} + +/* + * It is not legal to sleep in the idle task - print a warning + * message if some code attempts to do it: + */ +static void +dequeue_task_idle(struct rq *rq, struct task_struct *p, int flags) +{ + raw_spin_unlock_irq(&rq->lock); + printk(KERN_ERR "bad: scheduling from the idle thread!\n"); + dump_stack(); + raw_spin_lock_irq(&rq->lock); +} + +static void put_prev_task_idle(struct rq *rq, struct task_struct *prev) +{ + idle_exit_fair(rq); + rq_last_tick_reset(rq); +} + +static void task_tick_idle(struct rq *rq, struct task_struct *curr, int queued) +{ +} + +static void set_curr_task_idle(struct rq *rq) +{ +} + +static void switched_to_idle(struct rq *rq, struct task_struct *p) +{ + BUG(); +} + +static void +prio_changed_idle(struct rq *rq, struct task_struct *p, int oldprio) +{ + BUG(); +} + +static unsigned int get_rr_interval_idle(struct rq *rq, struct task_struct *task) +{ + return 0; +} + +static void update_curr_idle(struct rq *rq) +{ +} + +/* + * Simple, special scheduling class for the per-CPU idle tasks: + */ +const struct sched_class idle_sched_class = { + /* .next is NULL */ + /* no enqueue/yield_task for idle tasks */ + + /* dequeue is not valid, we print a debug message there: */ + .dequeue_task = dequeue_task_idle, + + .check_preempt_curr = check_preempt_curr_idle, + + .pick_next_task = pick_next_task_idle, + .put_prev_task = put_prev_task_idle, + +#ifdef CONFIG_SMP + .select_task_rq = select_task_rq_idle, +#endif + + .set_curr_task = set_curr_task_idle, + .task_tick = task_tick_idle, + + .get_rr_interval = get_rr_interval_idle, + + .prio_changed = prio_changed_idle, + .switched_to = switched_to_idle, + .update_curr = update_curr_idle, +}; diff --git a/kernel/kernel/sched/proc.c b/kernel/kernel/sched/proc.c new file mode 100644 index 000000000..8ecd552fe --- /dev/null +++ b/kernel/kernel/sched/proc.c @@ -0,0 +1,584 @@ +/* + * kernel/sched/proc.c + * + * Kernel load calculations, forked from sched/core.c + */ + +#include + +#include "sched.h" + +/* + * Global load-average calculations + * + * We take a distributed and async approach to calculating the global load-avg + * in order to minimize overhead. + * + * The global load average is an exponentially decaying average of nr_running + + * nr_uninterruptible. + * + * Once every LOAD_FREQ: + * + * nr_active = 0; + * for_each_possible_cpu(cpu) + * nr_active += cpu_of(cpu)->nr_running + cpu_of(cpu)->nr_uninterruptible; + * + * avenrun[n] = avenrun[0] * exp_n + nr_active * (1 - exp_n) + * + * Due to a number of reasons the above turns in the mess below: + * + * - for_each_possible_cpu() is prohibitively expensive on machines with + * serious number of cpus, therefore we need to take a distributed approach + * to calculating nr_active. + * + * \Sum_i x_i(t) = \Sum_i x_i(t) - x_i(t_0) | x_i(t_0) := 0 + * = \Sum_i { \Sum_j=1 x_i(t_j) - x_i(t_j-1) } + * + * So assuming nr_active := 0 when we start out -- true per definition, we + * can simply take per-cpu deltas and fold those into a global accumulate + * to obtain the same result. See calc_load_fold_active(). + * + * Furthermore, in order to avoid synchronizing all per-cpu delta folding + * across the machine, we assume 10 ticks is sufficient time for every + * cpu to have completed this task. + * + * This places an upper-bound on the IRQ-off latency of the machine. Then + * again, being late doesn't loose the delta, just wrecks the sample. + * + * - cpu_rq()->nr_uninterruptible isn't accurately tracked per-cpu because + * this would add another cross-cpu cacheline miss and atomic operation + * to the wakeup path. Instead we increment on whatever cpu the task ran + * when it went into uninterruptible state and decrement on whatever cpu + * did the wakeup. This means that only the sum of nr_uninterruptible over + * all cpus yields the correct result. + * + * This covers the NO_HZ=n code, for extra head-aches, see the comment below. + */ + +/* Variables and functions for calc_load */ +atomic_long_t calc_load_tasks; +unsigned long calc_load_update; +unsigned long avenrun[3]; +EXPORT_SYMBOL(avenrun); /* should be removed */ + +/** + * get_avenrun - get the load average array + * @loads: pointer to dest load array + * @offset: offset to add + * @shift: shift count to shift the result left + * + * These values are estimates at best, so no need for locking. + */ +void get_avenrun(unsigned long *loads, unsigned long offset, int shift) +{ + loads[0] = (avenrun[0] + offset) << shift; + loads[1] = (avenrun[1] + offset) << shift; + loads[2] = (avenrun[2] + offset) << shift; +} + +long calc_load_fold_active(struct rq *this_rq) +{ + long nr_active, delta = 0; + + nr_active = this_rq->nr_running; + nr_active += (long) this_rq->nr_uninterruptible; + + if (nr_active != this_rq->calc_load_active) { + delta = nr_active - this_rq->calc_load_active; + this_rq->calc_load_active = nr_active; + } + + return delta; +} + +/* + * a1 = a0 * e + a * (1 - e) + */ +static unsigned long +calc_load(unsigned long load, unsigned long exp, unsigned long active) +{ + load *= exp; + load += active * (FIXED_1 - exp); + load += 1UL << (FSHIFT - 1); + return load >> FSHIFT; +} + +#ifdef CONFIG_NO_HZ_COMMON +/* + * Handle NO_HZ for the global load-average. + * + * Since the above described distributed algorithm to compute the global + * load-average relies on per-cpu sampling from the tick, it is affected by + * NO_HZ. + * + * The basic idea is to fold the nr_active delta into a global idle-delta upon + * entering NO_HZ state such that we can include this as an 'extra' cpu delta + * when we read the global state. + * + * Obviously reality has to ruin such a delightfully simple scheme: + * + * - When we go NO_HZ idle during the window, we can negate our sample + * contribution, causing under-accounting. + * + * We avoid this by keeping two idle-delta counters and flipping them + * when the window starts, thus separating old and new NO_HZ load. + * + * The only trick is the slight shift in index flip for read vs write. + * + * 0s 5s 10s 15s + * +10 +10 +10 +10 + * |-|-----------|-|-----------|-|-----------|-| + * r:0 0 1 1 0 0 1 1 0 + * w:0 1 1 0 0 1 1 0 0 + * + * This ensures we'll fold the old idle contribution in this window while + * accumlating the new one. + * + * - When we wake up from NO_HZ idle during the window, we push up our + * contribution, since we effectively move our sample point to a known + * busy state. + * + * This is solved by pushing the window forward, and thus skipping the + * sample, for this cpu (effectively using the idle-delta for this cpu which + * was in effect at the time the window opened). This also solves the issue + * of having to deal with a cpu having been in NOHZ idle for multiple + * LOAD_FREQ intervals. + * + * When making the ILB scale, we should try to pull this in as well. + */ +static atomic_long_t calc_load_idle[2]; +static int calc_load_idx; + +static inline int calc_load_write_idx(void) +{ + int idx = calc_load_idx; + + /* + * See calc_global_nohz(), if we observe the new index, we also + * need to observe the new update time. + */ + smp_rmb(); + + /* + * If the folding window started, make sure we start writing in the + * next idle-delta. + */ + if (!time_before(jiffies, calc_load_update)) + idx++; + + return idx & 1; +} + +static inline int calc_load_read_idx(void) +{ + return calc_load_idx & 1; +} + +void calc_load_enter_idle(void) +{ + struct rq *this_rq = this_rq(); + long delta; + + /* + * We're going into NOHZ mode, if there's any pending delta, fold it + * into the pending idle delta. + */ + delta = calc_load_fold_active(this_rq); + if (delta) { + int idx = calc_load_write_idx(); + atomic_long_add(delta, &calc_load_idle[idx]); + } +} + +void calc_load_exit_idle(void) +{ + struct rq *this_rq = this_rq(); + + /* + * If we're still before the sample window, we're done. + */ + if (time_before(jiffies, this_rq->calc_load_update)) + return; + + /* + * We woke inside or after the sample window, this means we're already + * accounted through the nohz accounting, so skip the entire deal and + * sync up for the next window. + */ + this_rq->calc_load_update = calc_load_update; + if (time_before(jiffies, this_rq->calc_load_update + 10)) + this_rq->calc_load_update += LOAD_FREQ; +} + +static long calc_load_fold_idle(void) +{ + int idx = calc_load_read_idx(); + long delta = 0; + + if (atomic_long_read(&calc_load_idle[idx])) + delta = atomic_long_xchg(&calc_load_idle[idx], 0); + + return delta; +} + +/** + * fixed_power_int - compute: x^n, in O(log n) time + * + * @x: base of the power + * @frac_bits: fractional bits of @x + * @n: power to raise @x to. + * + * By exploiting the relation between the definition of the natural power + * function: x^n := x*x*...*x (x multiplied by itself for n times), and + * the binary encoding of numbers used by computers: n := \Sum n_i * 2^i, + * (where: n_i \elem {0, 1}, the binary vector representing n), + * we find: x^n := x^(\Sum n_i * 2^i) := \Prod x^(n_i * 2^i), which is + * of course trivially computable in O(log_2 n), the length of our binary + * vector. + */ +static unsigned long +fixed_power_int(unsigned long x, unsigned int frac_bits, unsigned int n) +{ + unsigned long result = 1UL << frac_bits; + + if (n) for (;;) { + if (n & 1) { + result *= x; + result += 1UL << (frac_bits - 1); + result >>= frac_bits; + } + n >>= 1; + if (!n) + break; + x *= x; + x += 1UL << (frac_bits - 1); + x >>= frac_bits; + } + + return result; +} + +/* + * a1 = a0 * e + a * (1 - e) + * + * a2 = a1 * e + a * (1 - e) + * = (a0 * e + a * (1 - e)) * e + a * (1 - e) + * = a0 * e^2 + a * (1 - e) * (1 + e) + * + * a3 = a2 * e + a * (1 - e) + * = (a0 * e^2 + a * (1 - e) * (1 + e)) * e + a * (1 - e) + * = a0 * e^3 + a * (1 - e) * (1 + e + e^2) + * + * ... + * + * an = a0 * e^n + a * (1 - e) * (1 + e + ... + e^n-1) [1] + * = a0 * e^n + a * (1 - e) * (1 - e^n)/(1 - e) + * = a0 * e^n + a * (1 - e^n) + * + * [1] application of the geometric series: + * + * n 1 - x^(n+1) + * S_n := \Sum x^i = ------------- + * i=0 1 - x + */ +static unsigned long +calc_load_n(unsigned long load, unsigned long exp, + unsigned long active, unsigned int n) +{ + + return calc_load(load, fixed_power_int(exp, FSHIFT, n), active); +} + +/* + * NO_HZ can leave us missing all per-cpu ticks calling + * calc_load_account_active(), but since an idle CPU folds its delta into + * calc_load_tasks_idle per calc_load_account_idle(), all we need to do is fold + * in the pending idle delta if our idle period crossed a load cycle boundary. + * + * Once we've updated the global active value, we need to apply the exponential + * weights adjusted to the number of cycles missed. + */ +static void calc_global_nohz(void) +{ + long delta, active, n; + + if (!time_before(jiffies, calc_load_update + 10)) { + /* + * Catch-up, fold however many we are behind still + */ + delta = jiffies - calc_load_update - 10; + n = 1 + (delta / LOAD_FREQ); + + active = atomic_long_read(&calc_load_tasks); + active = active > 0 ? active * FIXED_1 : 0; + + avenrun[0] = calc_load_n(avenrun[0], EXP_1, active, n); + avenrun[1] = calc_load_n(avenrun[1], EXP_5, active, n); + avenrun[2] = calc_load_n(avenrun[2], EXP_15, active, n); + + calc_load_update += n * LOAD_FREQ; + } + + /* + * Flip the idle index... + * + * Make sure we first write the new time then flip the index, so that + * calc_load_write_idx() will see the new time when it reads the new + * index, this avoids a double flip messing things up. + */ + smp_wmb(); + calc_load_idx++; +} +#else /* !CONFIG_NO_HZ_COMMON */ + +static inline long calc_load_fold_idle(void) { return 0; } +static inline void calc_global_nohz(void) { } + +#endif /* CONFIG_NO_HZ_COMMON */ + +/* + * calc_load - update the avenrun load estimates 10 ticks after the + * CPUs have updated calc_load_tasks. + */ +void calc_global_load(unsigned long ticks) +{ + long active, delta; + + if (time_before(jiffies, calc_load_update + 10)) + return; + + /* + * Fold the 'old' idle-delta to include all NO_HZ cpus. + */ + delta = calc_load_fold_idle(); + if (delta) + atomic_long_add(delta, &calc_load_tasks); + + active = atomic_long_read(&calc_load_tasks); + active = active > 0 ? active * FIXED_1 : 0; + + avenrun[0] = calc_load(avenrun[0], EXP_1, active); + avenrun[1] = calc_load(avenrun[1], EXP_5, active); + avenrun[2] = calc_load(avenrun[2], EXP_15, active); + + calc_load_update += LOAD_FREQ; + + /* + * In case we idled for multiple LOAD_FREQ intervals, catch up in bulk. + */ + calc_global_nohz(); +} + +/* + * Called from update_cpu_load() to periodically update this CPU's + * active count. + */ +static void calc_load_account_active(struct rq *this_rq) +{ + long delta; + + if (time_before(jiffies, this_rq->calc_load_update)) + return; + + delta = calc_load_fold_active(this_rq); + if (delta) + atomic_long_add(delta, &calc_load_tasks); + + this_rq->calc_load_update += LOAD_FREQ; +} + +/* + * End of global load-average stuff + */ + +/* + * The exact cpuload at various idx values, calculated at every tick would be + * load = (2^idx - 1) / 2^idx * load + 1 / 2^idx * cur_load + * + * If a cpu misses updates for n-1 ticks (as it was idle) and update gets called + * on nth tick when cpu may be busy, then we have: + * load = ((2^idx - 1) / 2^idx)^(n-1) * load + * load = (2^idx - 1) / 2^idx) * load + 1 / 2^idx * cur_load + * + * decay_load_missed() below does efficient calculation of + * load = ((2^idx - 1) / 2^idx)^(n-1) * load + * avoiding 0..n-1 loop doing load = ((2^idx - 1) / 2^idx) * load + * + * The calculation is approximated on a 128 point scale. + * degrade_zero_ticks is the number of ticks after which load at any + * particular idx is approximated to be zero. + * degrade_factor is a precomputed table, a row for each load idx. + * Each column corresponds to degradation factor for a power of two ticks, + * based on 128 point scale. + * Example: + * row 2, col 3 (=12) says that the degradation at load idx 2 after + * 8 ticks is 12/128 (which is an approximation of exact factor 3^8/4^8). + * + * With this power of 2 load factors, we can degrade the load n times + * by looking at 1 bits in n and doing as many mult/shift instead of + * n mult/shifts needed by the exact degradation. + */ +#define DEGRADE_SHIFT 7 +static const unsigned char + degrade_zero_ticks[CPU_LOAD_IDX_MAX] = {0, 8, 32, 64, 128}; +static const unsigned char + degrade_factor[CPU_LOAD_IDX_MAX][DEGRADE_SHIFT + 1] = { + {0, 0, 0, 0, 0, 0, 0, 0}, + {64, 32, 8, 0, 0, 0, 0, 0}, + {96, 72, 40, 12, 1, 0, 0}, + {112, 98, 75, 43, 15, 1, 0}, + {120, 112, 98, 76, 45, 16, 2} }; + +/* + * Update cpu_load for any missed ticks, due to tickless idle. The backlog + * would be when CPU is idle and so we just decay the old load without + * adding any new load. + */ +static unsigned long +decay_load_missed(unsigned long load, unsigned long missed_updates, int idx) +{ + int j = 0; + + if (!missed_updates) + return load; + + if (missed_updates >= degrade_zero_ticks[idx]) + return 0; + + if (idx == 1) + return load >> missed_updates; + + while (missed_updates) { + if (missed_updates % 2) + load = (load * degrade_factor[idx][j]) >> DEGRADE_SHIFT; + + missed_updates >>= 1; + j++; + } + return load; +} + +/* + * Update rq->cpu_load[] statistics. This function is usually called every + * scheduler tick (TICK_NSEC). With tickless idle this will not be called + * every tick. We fix it up based on jiffies. + */ +static void __update_cpu_load(struct rq *this_rq, unsigned long this_load, + unsigned long pending_updates) +{ + int i, scale; + + this_rq->nr_load_updates++; + + /* Update our load: */ + this_rq->cpu_load[0] = this_load; /* Fasttrack for idx 0 */ + for (i = 1, scale = 2; i < CPU_LOAD_IDX_MAX; i++, scale += scale) { + unsigned long old_load, new_load; + + /* scale is effectively 1 << i now, and >> i divides by scale */ + + old_load = this_rq->cpu_load[i]; + old_load = decay_load_missed(old_load, pending_updates - 1, i); + new_load = this_load; + /* + * Round up the averaging division if load is increasing. This + * prevents us from getting stuck on 9 if the load is 10, for + * example. + */ + if (new_load > old_load) + new_load += scale - 1; + + this_rq->cpu_load[i] = (old_load * (scale - 1) + new_load) >> i; + } + + sched_avg_update(this_rq); +} + +#ifdef CONFIG_SMP +static inline unsigned long get_rq_runnable_load(struct rq *rq) +{ + return rq->cfs.runnable_load_avg; +} +#else +static inline unsigned long get_rq_runnable_load(struct rq *rq) +{ + return rq->load.weight; +} +#endif + +#ifdef CONFIG_NO_HZ_COMMON +/* + * There is no sane way to deal with nohz on smp when using jiffies because the + * cpu doing the jiffies update might drift wrt the cpu doing the jiffy reading + * causing off-by-one errors in observed deltas; {0,2} instead of {1,1}. + * + * Therefore we cannot use the delta approach from the regular tick since that + * would seriously skew the load calculation. However we'll make do for those + * updates happening while idle (nohz_idle_balance) or coming out of idle + * (tick_nohz_idle_exit). + * + * This means we might still be one tick off for nohz periods. + */ + +/* + * Called from nohz_idle_balance() to update the load ratings before doing the + * idle balance. + */ +void update_idle_cpu_load(struct rq *this_rq) +{ + unsigned long curr_jiffies = ACCESS_ONCE(jiffies); + unsigned long load = get_rq_runnable_load(this_rq); + unsigned long pending_updates; + + /* + * bail if there's load or we're actually up-to-date. + */ + if (load || curr_jiffies == this_rq->last_load_update_tick) + return; + + pending_updates = curr_jiffies - this_rq->last_load_update_tick; + this_rq->last_load_update_tick = curr_jiffies; + + __update_cpu_load(this_rq, load, pending_updates); +} + +/* + * Called from tick_nohz_idle_exit() -- try and fix up the ticks we missed. + */ +void update_cpu_load_nohz(void) +{ + struct rq *this_rq = this_rq(); + unsigned long curr_jiffies = ACCESS_ONCE(jiffies); + unsigned long pending_updates; + + if (curr_jiffies == this_rq->last_load_update_tick) + return; + + raw_spin_lock(&this_rq->lock); + pending_updates = curr_jiffies - this_rq->last_load_update_tick; + if (pending_updates) { + this_rq->last_load_update_tick = curr_jiffies; + /* + * We were idle, this means load 0, the current load might be + * !0 due to remote wakeups and the sort. + */ + __update_cpu_load(this_rq, 0, pending_updates); + } + raw_spin_unlock(&this_rq->lock); +} +#endif /* CONFIG_NO_HZ */ + +/* + * Called from scheduler_tick() + */ +void update_cpu_load_active(struct rq *this_rq) +{ + unsigned long load = get_rq_runnable_load(this_rq); + /* + * See the mess around update_idle_cpu_load() / update_cpu_load_nohz(). + */ + this_rq->last_load_update_tick = jiffies; + __update_cpu_load(this_rq, load, 1); + + calc_load_account_active(this_rq); +} diff --git a/kernel/kernel/sched/rt.c b/kernel/kernel/sched/rt.c new file mode 100644 index 000000000..637aa208a --- /dev/null +++ b/kernel/kernel/sched/rt.c @@ -0,0 +1,2348 @@ +/* + * Real-Time Scheduling Class (mapped to the SCHED_FIFO and SCHED_RR + * policies) + */ + +#include "sched.h" + +#include +#include + +int sched_rr_timeslice = RR_TIMESLICE; + +static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun); + +struct rt_bandwidth def_rt_bandwidth; + +static enum hrtimer_restart sched_rt_period_timer(struct hrtimer *timer) +{ + struct rt_bandwidth *rt_b = + container_of(timer, struct rt_bandwidth, rt_period_timer); + ktime_t now; + int overrun; + int idle = 0; + + for (;;) { + now = hrtimer_cb_get_time(timer); + overrun = hrtimer_forward(timer, now, rt_b->rt_period); + + if (!overrun) + break; + + idle = do_sched_rt_period_timer(rt_b, overrun); + } + + return idle ? HRTIMER_NORESTART : HRTIMER_RESTART; +} + +void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime) +{ + rt_b->rt_period = ns_to_ktime(period); + rt_b->rt_runtime = runtime; + + raw_spin_lock_init(&rt_b->rt_runtime_lock); + + hrtimer_init(&rt_b->rt_period_timer, + CLOCK_MONOTONIC, HRTIMER_MODE_REL); + rt_b->rt_period_timer.irqsafe = 1; + rt_b->rt_period_timer.function = sched_rt_period_timer; +} + +static void start_rt_bandwidth(struct rt_bandwidth *rt_b) +{ + if (!rt_bandwidth_enabled() || rt_b->rt_runtime == RUNTIME_INF) + return; + + if (hrtimer_active(&rt_b->rt_period_timer)) + return; + + raw_spin_lock(&rt_b->rt_runtime_lock); + start_bandwidth_timer(&rt_b->rt_period_timer, rt_b->rt_period); + raw_spin_unlock(&rt_b->rt_runtime_lock); +} + +#ifdef CONFIG_SMP +static void push_irq_work_func(struct irq_work *work); +#endif + +void init_rt_rq(struct rt_rq *rt_rq) +{ + struct rt_prio_array *array; + int i; + + array = &rt_rq->active; + for (i = 0; i < MAX_RT_PRIO; i++) { + INIT_LIST_HEAD(array->queue + i); + __clear_bit(i, array->bitmap); + } + /* delimiter for bitsearch: */ + __set_bit(MAX_RT_PRIO, array->bitmap); + +#if defined CONFIG_SMP + rt_rq->highest_prio.curr = MAX_RT_PRIO; + rt_rq->highest_prio.next = MAX_RT_PRIO; + rt_rq->rt_nr_migratory = 0; + rt_rq->overloaded = 0; + plist_head_init(&rt_rq->pushable_tasks); + +#ifdef HAVE_RT_PUSH_IPI + rt_rq->push_flags = 0; + rt_rq->push_cpu = nr_cpu_ids; + raw_spin_lock_init(&rt_rq->push_lock); + init_irq_work(&rt_rq->push_work, push_irq_work_func); + rt_rq->push_work.flags |= IRQ_WORK_HARD_IRQ; +#endif +#endif /* CONFIG_SMP */ + /* We start is dequeued state, because no RT tasks are queued */ + rt_rq->rt_queued = 0; + + rt_rq->rt_time = 0; + rt_rq->rt_throttled = 0; + rt_rq->rt_runtime = 0; + raw_spin_lock_init(&rt_rq->rt_runtime_lock); +} + +#ifdef CONFIG_RT_GROUP_SCHED +static void destroy_rt_bandwidth(struct rt_bandwidth *rt_b) +{ + hrtimer_cancel(&rt_b->rt_period_timer); +} + +#define rt_entity_is_task(rt_se) (!(rt_se)->my_q) + +static inline struct task_struct *rt_task_of(struct sched_rt_entity *rt_se) +{ +#ifdef CONFIG_SCHED_DEBUG + WARN_ON_ONCE(!rt_entity_is_task(rt_se)); +#endif + return container_of(rt_se, struct task_struct, rt); +} + +static inline struct rq *rq_of_rt_rq(struct rt_rq *rt_rq) +{ + return rt_rq->rq; +} + +static inline struct rt_rq *rt_rq_of_se(struct sched_rt_entity *rt_se) +{ + return rt_se->rt_rq; +} + +static inline struct rq *rq_of_rt_se(struct sched_rt_entity *rt_se) +{ + struct rt_rq *rt_rq = rt_se->rt_rq; + + return rt_rq->rq; +} + +void free_rt_sched_group(struct task_group *tg) +{ + int i; + + if (tg->rt_se) + destroy_rt_bandwidth(&tg->rt_bandwidth); + + for_each_possible_cpu(i) { + if (tg->rt_rq) + kfree(tg->rt_rq[i]); + if (tg->rt_se) + kfree(tg->rt_se[i]); + } + + kfree(tg->rt_rq); + kfree(tg->rt_se); +} + +void init_tg_rt_entry(struct task_group *tg, struct rt_rq *rt_rq, + struct sched_rt_entity *rt_se, int cpu, + struct sched_rt_entity *parent) +{ + struct rq *rq = cpu_rq(cpu); + + rt_rq->highest_prio.curr = MAX_RT_PRIO; + rt_rq->rt_nr_boosted = 0; + rt_rq->rq = rq; + rt_rq->tg = tg; + + tg->rt_rq[cpu] = rt_rq; + tg->rt_se[cpu] = rt_se; + + if (!rt_se) + return; + + if (!parent) + rt_se->rt_rq = &rq->rt; + else + rt_se->rt_rq = parent->my_q; + + rt_se->my_q = rt_rq; + rt_se->parent = parent; + INIT_LIST_HEAD(&rt_se->run_list); +} + +int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent) +{ + struct rt_rq *rt_rq; + struct sched_rt_entity *rt_se; + int i; + + tg->rt_rq = kzalloc(sizeof(rt_rq) * nr_cpu_ids, GFP_KERNEL); + if (!tg->rt_rq) + goto err; + tg->rt_se = kzalloc(sizeof(rt_se) * nr_cpu_ids, GFP_KERNEL); + if (!tg->rt_se) + goto err; + + init_rt_bandwidth(&tg->rt_bandwidth, + ktime_to_ns(def_rt_bandwidth.rt_period), 0); + + for_each_possible_cpu(i) { + rt_rq = kzalloc_node(sizeof(struct rt_rq), + GFP_KERNEL, cpu_to_node(i)); + if (!rt_rq) + goto err; + + rt_se = kzalloc_node(sizeof(struct sched_rt_entity), + GFP_KERNEL, cpu_to_node(i)); + if (!rt_se) + goto err_free_rq; + + init_rt_rq(rt_rq); + rt_rq->rt_runtime = tg->rt_bandwidth.rt_runtime; + init_tg_rt_entry(tg, rt_rq, rt_se, i, parent->rt_se[i]); + } + + return 1; + +err_free_rq: + kfree(rt_rq); +err: + return 0; +} + +#else /* CONFIG_RT_GROUP_SCHED */ + +#define rt_entity_is_task(rt_se) (1) + +static inline struct task_struct *rt_task_of(struct sched_rt_entity *rt_se) +{ + return container_of(rt_se, struct task_struct, rt); +} + +static inline struct rq *rq_of_rt_rq(struct rt_rq *rt_rq) +{ + return container_of(rt_rq, struct rq, rt); +} + +static inline struct rq *rq_of_rt_se(struct sched_rt_entity *rt_se) +{ + struct task_struct *p = rt_task_of(rt_se); + + return task_rq(p); +} + +static inline struct rt_rq *rt_rq_of_se(struct sched_rt_entity *rt_se) +{ + struct rq *rq = rq_of_rt_se(rt_se); + + return &rq->rt; +} + +void free_rt_sched_group(struct task_group *tg) { } + +int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent) +{ + return 1; +} +#endif /* CONFIG_RT_GROUP_SCHED */ + +#ifdef CONFIG_SMP + +static int pull_rt_task(struct rq *this_rq); + +static inline bool need_pull_rt_task(struct rq *rq, struct task_struct *prev) +{ + /* Try to pull RT tasks here if we lower this rq's prio */ + return rq->rt.highest_prio.curr > prev->prio; +} + +static inline int rt_overloaded(struct rq *rq) +{ + return atomic_read(&rq->rd->rto_count); +} + +static inline void rt_set_overload(struct rq *rq) +{ + if (!rq->online) + return; + + cpumask_set_cpu(rq->cpu, rq->rd->rto_mask); + /* + * Make sure the mask is visible before we set + * the overload count. That is checked to determine + * if we should look at the mask. It would be a shame + * if we looked at the mask, but the mask was not + * updated yet. + * + * Matched by the barrier in pull_rt_task(). + */ + smp_wmb(); + atomic_inc(&rq->rd->rto_count); +} + +static inline void rt_clear_overload(struct rq *rq) +{ + if (!rq->online) + return; + + /* the order here really doesn't matter */ + atomic_dec(&rq->rd->rto_count); + cpumask_clear_cpu(rq->cpu, rq->rd->rto_mask); +} + +static void update_rt_migration(struct rt_rq *rt_rq) +{ + if (rt_rq->rt_nr_migratory && rt_rq->rt_nr_total > 1) { + if (!rt_rq->overloaded) { + rt_set_overload(rq_of_rt_rq(rt_rq)); + rt_rq->overloaded = 1; + } + } else if (rt_rq->overloaded) { + rt_clear_overload(rq_of_rt_rq(rt_rq)); + rt_rq->overloaded = 0; + } +} + +static void inc_rt_migration(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq) +{ + struct task_struct *p; + + if (!rt_entity_is_task(rt_se)) + return; + + p = rt_task_of(rt_se); + rt_rq = &rq_of_rt_rq(rt_rq)->rt; + + rt_rq->rt_nr_total++; + if (p->nr_cpus_allowed > 1) + rt_rq->rt_nr_migratory++; + + update_rt_migration(rt_rq); +} + +static void dec_rt_migration(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq) +{ + struct task_struct *p; + + if (!rt_entity_is_task(rt_se)) + return; + + p = rt_task_of(rt_se); + rt_rq = &rq_of_rt_rq(rt_rq)->rt; + + rt_rq->rt_nr_total--; + if (p->nr_cpus_allowed > 1) + rt_rq->rt_nr_migratory--; + + update_rt_migration(rt_rq); +} + +static inline int has_pushable_tasks(struct rq *rq) +{ + return !plist_head_empty(&rq->rt.pushable_tasks); +} + +static inline void set_post_schedule(struct rq *rq) +{ + /* + * We detect this state here so that we can avoid taking the RQ + * lock again later if there is no need to push + */ + rq->post_schedule = has_pushable_tasks(rq); +} + +static void enqueue_pushable_task(struct rq *rq, struct task_struct *p) +{ + plist_del(&p->pushable_tasks, &rq->rt.pushable_tasks); + plist_node_init(&p->pushable_tasks, p->prio); + plist_add(&p->pushable_tasks, &rq->rt.pushable_tasks); + + /* Update the highest prio pushable task */ + if (p->prio < rq->rt.highest_prio.next) + rq->rt.highest_prio.next = p->prio; +} + +static void dequeue_pushable_task(struct rq *rq, struct task_struct *p) +{ + plist_del(&p->pushable_tasks, &rq->rt.pushable_tasks); + + /* Update the new highest prio pushable task */ + if (has_pushable_tasks(rq)) { + p = plist_first_entry(&rq->rt.pushable_tasks, + struct task_struct, pushable_tasks); + rq->rt.highest_prio.next = p->prio; + } else + rq->rt.highest_prio.next = MAX_RT_PRIO; +} + +#else + +static inline void enqueue_pushable_task(struct rq *rq, struct task_struct *p) +{ +} + +static inline void dequeue_pushable_task(struct rq *rq, struct task_struct *p) +{ +} + +static inline +void inc_rt_migration(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq) +{ +} + +static inline +void dec_rt_migration(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq) +{ +} + +static inline bool need_pull_rt_task(struct rq *rq, struct task_struct *prev) +{ + return false; +} + +static inline int pull_rt_task(struct rq *this_rq) +{ + return 0; +} + +static inline void set_post_schedule(struct rq *rq) +{ +} +#endif /* CONFIG_SMP */ + +static void enqueue_top_rt_rq(struct rt_rq *rt_rq); +static void dequeue_top_rt_rq(struct rt_rq *rt_rq); + +static inline int on_rt_rq(struct sched_rt_entity *rt_se) +{ + return !list_empty(&rt_se->run_list); +} + +#ifdef CONFIG_RT_GROUP_SCHED + +static inline u64 sched_rt_runtime(struct rt_rq *rt_rq) +{ + if (!rt_rq->tg) + return RUNTIME_INF; + + return rt_rq->rt_runtime; +} + +static inline u64 sched_rt_period(struct rt_rq *rt_rq) +{ + return ktime_to_ns(rt_rq->tg->rt_bandwidth.rt_period); +} + +typedef struct task_group *rt_rq_iter_t; + +static inline struct task_group *next_task_group(struct task_group *tg) +{ + do { + tg = list_entry_rcu(tg->list.next, + typeof(struct task_group), list); + } while (&tg->list != &task_groups && task_group_is_autogroup(tg)); + + if (&tg->list == &task_groups) + tg = NULL; + + return tg; +} + +#define for_each_rt_rq(rt_rq, iter, rq) \ + for (iter = container_of(&task_groups, typeof(*iter), list); \ + (iter = next_task_group(iter)) && \ + (rt_rq = iter->rt_rq[cpu_of(rq)]);) + +#define for_each_sched_rt_entity(rt_se) \ + for (; rt_se; rt_se = rt_se->parent) + +static inline struct rt_rq *group_rt_rq(struct sched_rt_entity *rt_se) +{ + return rt_se->my_q; +} + +static void enqueue_rt_entity(struct sched_rt_entity *rt_se, bool head); +static void dequeue_rt_entity(struct sched_rt_entity *rt_se); + +static void sched_rt_rq_enqueue(struct rt_rq *rt_rq) +{ + struct task_struct *curr = rq_of_rt_rq(rt_rq)->curr; + struct rq *rq = rq_of_rt_rq(rt_rq); + struct sched_rt_entity *rt_se; + + int cpu = cpu_of(rq); + + rt_se = rt_rq->tg->rt_se[cpu]; + + if (rt_rq->rt_nr_running) { + if (!rt_se) + enqueue_top_rt_rq(rt_rq); + else if (!on_rt_rq(rt_se)) + enqueue_rt_entity(rt_se, false); + + if (rt_rq->highest_prio.curr < curr->prio) + resched_curr(rq); + } +} + +static void sched_rt_rq_dequeue(struct rt_rq *rt_rq) +{ + struct sched_rt_entity *rt_se; + int cpu = cpu_of(rq_of_rt_rq(rt_rq)); + + rt_se = rt_rq->tg->rt_se[cpu]; + + if (!rt_se) + dequeue_top_rt_rq(rt_rq); + else if (on_rt_rq(rt_se)) + dequeue_rt_entity(rt_se); +} + +static inline int rt_rq_throttled(struct rt_rq *rt_rq) +{ + return rt_rq->rt_throttled && !rt_rq->rt_nr_boosted; +} + +static int rt_se_boosted(struct sched_rt_entity *rt_se) +{ + struct rt_rq *rt_rq = group_rt_rq(rt_se); + struct task_struct *p; + + if (rt_rq) + return !!rt_rq->rt_nr_boosted; + + p = rt_task_of(rt_se); + return p->prio != p->normal_prio; +} + +#ifdef CONFIG_SMP +static inline const struct cpumask *sched_rt_period_mask(void) +{ + return this_rq()->rd->span; +} +#else +static inline const struct cpumask *sched_rt_period_mask(void) +{ + return cpu_online_mask; +} +#endif + +static inline +struct rt_rq *sched_rt_period_rt_rq(struct rt_bandwidth *rt_b, int cpu) +{ + return container_of(rt_b, struct task_group, rt_bandwidth)->rt_rq[cpu]; +} + +static inline struct rt_bandwidth *sched_rt_bandwidth(struct rt_rq *rt_rq) +{ + return &rt_rq->tg->rt_bandwidth; +} + +#else /* !CONFIG_RT_GROUP_SCHED */ + +static inline u64 sched_rt_runtime(struct rt_rq *rt_rq) +{ + return rt_rq->rt_runtime; +} + +static inline u64 sched_rt_period(struct rt_rq *rt_rq) +{ + return ktime_to_ns(def_rt_bandwidth.rt_period); +} + +typedef struct rt_rq *rt_rq_iter_t; + +#define for_each_rt_rq(rt_rq, iter, rq) \ + for ((void) iter, rt_rq = &rq->rt; rt_rq; rt_rq = NULL) + +#define for_each_sched_rt_entity(rt_se) \ + for (; rt_se; rt_se = NULL) + +static inline struct rt_rq *group_rt_rq(struct sched_rt_entity *rt_se) +{ + return NULL; +} + +static inline void sched_rt_rq_enqueue(struct rt_rq *rt_rq) +{ + struct rq *rq = rq_of_rt_rq(rt_rq); + + if (!rt_rq->rt_nr_running) + return; + + enqueue_top_rt_rq(rt_rq); + resched_curr(rq); +} + +static inline void sched_rt_rq_dequeue(struct rt_rq *rt_rq) +{ + dequeue_top_rt_rq(rt_rq); +} + +static inline int rt_rq_throttled(struct rt_rq *rt_rq) +{ + return rt_rq->rt_throttled; +} + +static inline const struct cpumask *sched_rt_period_mask(void) +{ + return cpu_online_mask; +} + +static inline +struct rt_rq *sched_rt_period_rt_rq(struct rt_bandwidth *rt_b, int cpu) +{ + return &cpu_rq(cpu)->rt; +} + +static inline struct rt_bandwidth *sched_rt_bandwidth(struct rt_rq *rt_rq) +{ + return &def_rt_bandwidth; +} + +#endif /* CONFIG_RT_GROUP_SCHED */ + +bool sched_rt_bandwidth_account(struct rt_rq *rt_rq) +{ + struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq); + + return (hrtimer_active(&rt_b->rt_period_timer) || + rt_rq->rt_time < rt_b->rt_runtime); +} + +#ifdef CONFIG_SMP +/* + * We ran out of runtime, see if we can borrow some from our neighbours. + */ +static int do_balance_runtime(struct rt_rq *rt_rq) +{ + struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq); + struct root_domain *rd = rq_of_rt_rq(rt_rq)->rd; + int i, weight, more = 0; + u64 rt_period; + + weight = cpumask_weight(rd->span); + + raw_spin_lock(&rt_b->rt_runtime_lock); + rt_period = ktime_to_ns(rt_b->rt_period); + for_each_cpu(i, rd->span) { + struct rt_rq *iter = sched_rt_period_rt_rq(rt_b, i); + s64 diff; + + if (iter == rt_rq) + continue; + + raw_spin_lock(&iter->rt_runtime_lock); + /* + * Either all rqs have inf runtime and there's nothing to steal + * or __disable_runtime() below sets a specific rq to inf to + * indicate its been disabled and disalow stealing. + */ + if (iter->rt_runtime == RUNTIME_INF) + goto next; + + /* + * From runqueues with spare time, take 1/n part of their + * spare time, but no more than our period. + */ + diff = iter->rt_runtime - iter->rt_time; + if (diff > 0) { + diff = div_u64((u64)diff, weight); + if (rt_rq->rt_runtime + diff > rt_period) + diff = rt_period - rt_rq->rt_runtime; + iter->rt_runtime -= diff; + rt_rq->rt_runtime += diff; + more = 1; + if (rt_rq->rt_runtime == rt_period) { + raw_spin_unlock(&iter->rt_runtime_lock); + break; + } + } +next: + raw_spin_unlock(&iter->rt_runtime_lock); + } + raw_spin_unlock(&rt_b->rt_runtime_lock); + + return more; +} + +/* + * Ensure this RQ takes back all the runtime it lend to its neighbours. + */ +static void __disable_runtime(struct rq *rq) +{ + struct root_domain *rd = rq->rd; + rt_rq_iter_t iter; + struct rt_rq *rt_rq; + + if (unlikely(!scheduler_running)) + return; + + for_each_rt_rq(rt_rq, iter, rq) { + struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq); + s64 want; + int i; + + raw_spin_lock(&rt_b->rt_runtime_lock); + raw_spin_lock(&rt_rq->rt_runtime_lock); + /* + * Either we're all inf and nobody needs to borrow, or we're + * already disabled and thus have nothing to do, or we have + * exactly the right amount of runtime to take out. + */ + if (rt_rq->rt_runtime == RUNTIME_INF || + rt_rq->rt_runtime == rt_b->rt_runtime) + goto balanced; + raw_spin_unlock(&rt_rq->rt_runtime_lock); + + /* + * Calculate the difference between what we started out with + * and what we current have, that's the amount of runtime + * we lend and now have to reclaim. + */ + want = rt_b->rt_runtime - rt_rq->rt_runtime; + + /* + * Greedy reclaim, take back as much as we can. + */ + for_each_cpu(i, rd->span) { + struct rt_rq *iter = sched_rt_period_rt_rq(rt_b, i); + s64 diff; + + /* + * Can't reclaim from ourselves or disabled runqueues. + */ + if (iter == rt_rq || iter->rt_runtime == RUNTIME_INF) + continue; + + raw_spin_lock(&iter->rt_runtime_lock); + if (want > 0) { + diff = min_t(s64, iter->rt_runtime, want); + iter->rt_runtime -= diff; + want -= diff; + } else { + iter->rt_runtime -= want; + want -= want; + } + raw_spin_unlock(&iter->rt_runtime_lock); + + if (!want) + break; + } + + raw_spin_lock(&rt_rq->rt_runtime_lock); + /* + * We cannot be left wanting - that would mean some runtime + * leaked out of the system. + */ + BUG_ON(want); +balanced: + /* + * Disable all the borrow logic by pretending we have inf + * runtime - in which case borrowing doesn't make sense. + */ + rt_rq->rt_runtime = RUNTIME_INF; + rt_rq->rt_throttled = 0; + raw_spin_unlock(&rt_rq->rt_runtime_lock); + raw_spin_unlock(&rt_b->rt_runtime_lock); + + /* Make rt_rq available for pick_next_task() */ + sched_rt_rq_enqueue(rt_rq); + } +} + +static void __enable_runtime(struct rq *rq) +{ + rt_rq_iter_t iter; + struct rt_rq *rt_rq; + + if (unlikely(!scheduler_running)) + return; + + /* + * Reset each runqueue's bandwidth settings + */ + for_each_rt_rq(rt_rq, iter, rq) { + struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq); + + raw_spin_lock(&rt_b->rt_runtime_lock); + raw_spin_lock(&rt_rq->rt_runtime_lock); + rt_rq->rt_runtime = rt_b->rt_runtime; + rt_rq->rt_time = 0; + rt_rq->rt_throttled = 0; + raw_spin_unlock(&rt_rq->rt_runtime_lock); + raw_spin_unlock(&rt_b->rt_runtime_lock); + } +} + +static int balance_runtime(struct rt_rq *rt_rq) +{ + int more = 0; + + if (!sched_feat(RT_RUNTIME_SHARE)) + return more; + + if (rt_rq->rt_time > rt_rq->rt_runtime) { + raw_spin_unlock(&rt_rq->rt_runtime_lock); + more = do_balance_runtime(rt_rq); + raw_spin_lock(&rt_rq->rt_runtime_lock); + } + + return more; +} +#else /* !CONFIG_SMP */ +static inline int balance_runtime(struct rt_rq *rt_rq) +{ + return 0; +} +#endif /* CONFIG_SMP */ + +static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun) +{ + int i, idle = 1, throttled = 0; + const struct cpumask *span; + + span = sched_rt_period_mask(); +#ifdef CONFIG_RT_GROUP_SCHED + /* + * FIXME: isolated CPUs should really leave the root task group, + * whether they are isolcpus or were isolated via cpusets, lest + * the timer run on a CPU which does not service all runqueues, + * potentially leaving other CPUs indefinitely throttled. If + * isolation is really required, the user will turn the throttle + * off to kill the perturbations it causes anyway. Meanwhile, + * this maintains functionality for boot and/or troubleshooting. + */ + if (rt_b == &root_task_group.rt_bandwidth) + span = cpu_online_mask; +#endif + for_each_cpu(i, span) { + int enqueue = 0; + struct rt_rq *rt_rq = sched_rt_period_rt_rq(rt_b, i); + struct rq *rq = rq_of_rt_rq(rt_rq); + + raw_spin_lock(&rq->lock); + if (rt_rq->rt_time) { + u64 runtime; + + raw_spin_lock(&rt_rq->rt_runtime_lock); + if (rt_rq->rt_throttled) + balance_runtime(rt_rq); + runtime = rt_rq->rt_runtime; + rt_rq->rt_time -= min(rt_rq->rt_time, overrun*runtime); + if (rt_rq->rt_throttled && rt_rq->rt_time < runtime) { + rt_rq->rt_throttled = 0; + enqueue = 1; + + /* + * When we're idle and a woken (rt) task is + * throttled check_preempt_curr() will set + * skip_update and the time between the wakeup + * and this unthrottle will get accounted as + * 'runtime'. + */ + if (rt_rq->rt_nr_running && rq->curr == rq->idle) + rq_clock_skip_update(rq, false); + } + if (rt_rq->rt_time || rt_rq->rt_nr_running) + idle = 0; + raw_spin_unlock(&rt_rq->rt_runtime_lock); + } else if (rt_rq->rt_nr_running) { + idle = 0; + if (!rt_rq_throttled(rt_rq)) + enqueue = 1; + } + if (rt_rq->rt_throttled) + throttled = 1; + + if (enqueue) + sched_rt_rq_enqueue(rt_rq); + raw_spin_unlock(&rq->lock); + } + + if (!throttled && (!rt_bandwidth_enabled() || rt_b->rt_runtime == RUNTIME_INF)) + return 1; + + return idle; +} + +static inline int rt_se_prio(struct sched_rt_entity *rt_se) +{ +#ifdef CONFIG_RT_GROUP_SCHED + struct rt_rq *rt_rq = group_rt_rq(rt_se); + + if (rt_rq) + return rt_rq->highest_prio.curr; +#endif + + return rt_task_of(rt_se)->prio; +} + +static int sched_rt_runtime_exceeded(struct rt_rq *rt_rq) +{ + u64 runtime = sched_rt_runtime(rt_rq); + + if (rt_rq->rt_throttled) + return rt_rq_throttled(rt_rq); + + if (runtime >= sched_rt_period(rt_rq)) + return 0; + + balance_runtime(rt_rq); + runtime = sched_rt_runtime(rt_rq); + if (runtime == RUNTIME_INF) + return 0; + + if (rt_rq->rt_time > runtime) { + struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq); + + /* + * Don't actually throttle groups that have no runtime assigned + * but accrue some time due to boosting. + */ + if (likely(rt_b->rt_runtime)) { + rt_rq->rt_throttled = 1; + printk_deferred_once("sched: RT throttling activated\n"); + } else { + /* + * In case we did anyway, make it go away, + * replenishment is a joke, since it will replenish us + * with exactly 0 ns. + */ + rt_rq->rt_time = 0; + } + + if (rt_rq_throttled(rt_rq)) { + sched_rt_rq_dequeue(rt_rq); + return 1; + } + } + + return 0; +} + +/* + * Update the current task's runtime statistics. Skip current tasks that + * are not in our scheduling class. + */ +static void update_curr_rt(struct rq *rq) +{ + struct task_struct *curr = rq->curr; + struct sched_rt_entity *rt_se = &curr->rt; + u64 delta_exec; + + if (curr->sched_class != &rt_sched_class) + return; + + delta_exec = rq_clock_task(rq) - curr->se.exec_start; + if (unlikely((s64)delta_exec <= 0)) + return; + + schedstat_set(curr->se.statistics.exec_max, + max(curr->se.statistics.exec_max, delta_exec)); + + curr->se.sum_exec_runtime += delta_exec; + account_group_exec_runtime(curr, delta_exec); + + curr->se.exec_start = rq_clock_task(rq); + cpuacct_charge(curr, delta_exec); + + sched_rt_avg_update(rq, delta_exec); + + if (!rt_bandwidth_enabled()) + return; + + for_each_sched_rt_entity(rt_se) { + struct rt_rq *rt_rq = rt_rq_of_se(rt_se); + + if (sched_rt_runtime(rt_rq) != RUNTIME_INF) { + raw_spin_lock(&rt_rq->rt_runtime_lock); + rt_rq->rt_time += delta_exec; + if (sched_rt_runtime_exceeded(rt_rq)) + resched_curr(rq); + raw_spin_unlock(&rt_rq->rt_runtime_lock); + } + } +} + +static void +dequeue_top_rt_rq(struct rt_rq *rt_rq) +{ + struct rq *rq = rq_of_rt_rq(rt_rq); + + BUG_ON(&rq->rt != rt_rq); + + if (!rt_rq->rt_queued) + return; + + BUG_ON(!rq->nr_running); + + sub_nr_running(rq, rt_rq->rt_nr_running); + rt_rq->rt_queued = 0; +} + +static void +enqueue_top_rt_rq(struct rt_rq *rt_rq) +{ + struct rq *rq = rq_of_rt_rq(rt_rq); + + BUG_ON(&rq->rt != rt_rq); + + if (rt_rq->rt_queued) + return; + if (rt_rq_throttled(rt_rq) || !rt_rq->rt_nr_running) + return; + + add_nr_running(rq, rt_rq->rt_nr_running); + rt_rq->rt_queued = 1; +} + +#if defined CONFIG_SMP + +static void +inc_rt_prio_smp(struct rt_rq *rt_rq, int prio, int prev_prio) +{ + struct rq *rq = rq_of_rt_rq(rt_rq); + +#ifdef CONFIG_RT_GROUP_SCHED + /* + * Change rq's cpupri only if rt_rq is the top queue. + */ + if (&rq->rt != rt_rq) + return; +#endif + if (rq->online && prio < prev_prio) + cpupri_set(&rq->rd->cpupri, rq->cpu, prio); +} + +static void +dec_rt_prio_smp(struct rt_rq *rt_rq, int prio, int prev_prio) +{ + struct rq *rq = rq_of_rt_rq(rt_rq); + +#ifdef CONFIG_RT_GROUP_SCHED + /* + * Change rq's cpupri only if rt_rq is the top queue. + */ + if (&rq->rt != rt_rq) + return; +#endif + if (rq->online && rt_rq->highest_prio.curr != prev_prio) + cpupri_set(&rq->rd->cpupri, rq->cpu, rt_rq->highest_prio.curr); +} + +#else /* CONFIG_SMP */ + +static inline +void inc_rt_prio_smp(struct rt_rq *rt_rq, int prio, int prev_prio) {} +static inline +void dec_rt_prio_smp(struct rt_rq *rt_rq, int prio, int prev_prio) {} + +#endif /* CONFIG_SMP */ + +#if defined CONFIG_SMP || defined CONFIG_RT_GROUP_SCHED +static void +inc_rt_prio(struct rt_rq *rt_rq, int prio) +{ + int prev_prio = rt_rq->highest_prio.curr; + + if (prio < prev_prio) + rt_rq->highest_prio.curr = prio; + + inc_rt_prio_smp(rt_rq, prio, prev_prio); +} + +static void +dec_rt_prio(struct rt_rq *rt_rq, int prio) +{ + int prev_prio = rt_rq->highest_prio.curr; + + if (rt_rq->rt_nr_running) { + + WARN_ON(prio < prev_prio); + + /* + * This may have been our highest task, and therefore + * we may have some recomputation to do + */ + if (prio == prev_prio) { + struct rt_prio_array *array = &rt_rq->active; + + rt_rq->highest_prio.curr = + sched_find_first_bit(array->bitmap); + } + + } else + rt_rq->highest_prio.curr = MAX_RT_PRIO; + + dec_rt_prio_smp(rt_rq, prio, prev_prio); +} + +#else + +static inline void inc_rt_prio(struct rt_rq *rt_rq, int prio) {} +static inline void dec_rt_prio(struct rt_rq *rt_rq, int prio) {} + +#endif /* CONFIG_SMP || CONFIG_RT_GROUP_SCHED */ + +#ifdef CONFIG_RT_GROUP_SCHED + +static void +inc_rt_group(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq) +{ + if (rt_se_boosted(rt_se)) + rt_rq->rt_nr_boosted++; + + if (rt_rq->tg) + start_rt_bandwidth(&rt_rq->tg->rt_bandwidth); +} + +static void +dec_rt_group(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq) +{ + if (rt_se_boosted(rt_se)) + rt_rq->rt_nr_boosted--; + + WARN_ON(!rt_rq->rt_nr_running && rt_rq->rt_nr_boosted); +} + +#else /* CONFIG_RT_GROUP_SCHED */ + +static void +inc_rt_group(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq) +{ + start_rt_bandwidth(&def_rt_bandwidth); +} + +static inline +void dec_rt_group(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq) {} + +#endif /* CONFIG_RT_GROUP_SCHED */ + +static inline +unsigned int rt_se_nr_running(struct sched_rt_entity *rt_se) +{ + struct rt_rq *group_rq = group_rt_rq(rt_se); + + if (group_rq) + return group_rq->rt_nr_running; + else + return 1; +} + +static inline +void inc_rt_tasks(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq) +{ + int prio = rt_se_prio(rt_se); + + WARN_ON(!rt_prio(prio)); + rt_rq->rt_nr_running += rt_se_nr_running(rt_se); + + inc_rt_prio(rt_rq, prio); + inc_rt_migration(rt_se, rt_rq); + inc_rt_group(rt_se, rt_rq); +} + +static inline +void dec_rt_tasks(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq) +{ + WARN_ON(!rt_prio(rt_se_prio(rt_se))); + WARN_ON(!rt_rq->rt_nr_running); + rt_rq->rt_nr_running -= rt_se_nr_running(rt_se); + + dec_rt_prio(rt_rq, rt_se_prio(rt_se)); + dec_rt_migration(rt_se, rt_rq); + dec_rt_group(rt_se, rt_rq); +} + +static void __enqueue_rt_entity(struct sched_rt_entity *rt_se, bool head) +{ + struct rt_rq *rt_rq = rt_rq_of_se(rt_se); + struct rt_prio_array *array = &rt_rq->active; + struct rt_rq *group_rq = group_rt_rq(rt_se); + struct list_head *queue = array->queue + rt_se_prio(rt_se); + + /* + * Don't enqueue the group if its throttled, or when empty. + * The latter is a consequence of the former when a child group + * get throttled and the current group doesn't have any other + * active members. + */ + if (group_rq && (rt_rq_throttled(group_rq) || !group_rq->rt_nr_running)) + return; + + if (head) + list_add(&rt_se->run_list, queue); + else + list_add_tail(&rt_se->run_list, queue); + __set_bit(rt_se_prio(rt_se), array->bitmap); + + inc_rt_tasks(rt_se, rt_rq); +} + +static void __dequeue_rt_entity(struct sched_rt_entity *rt_se) +{ + struct rt_rq *rt_rq = rt_rq_of_se(rt_se); + struct rt_prio_array *array = &rt_rq->active; + + list_del_init(&rt_se->run_list); + if (list_empty(array->queue + rt_se_prio(rt_se))) + __clear_bit(rt_se_prio(rt_se), array->bitmap); + + dec_rt_tasks(rt_se, rt_rq); +} + +/* + * Because the prio of an upper entry depends on the lower + * entries, we must remove entries top - down. + */ +static void dequeue_rt_stack(struct sched_rt_entity *rt_se) +{ + struct sched_rt_entity *back = NULL; + + for_each_sched_rt_entity(rt_se) { + rt_se->back = back; + back = rt_se; + } + + dequeue_top_rt_rq(rt_rq_of_se(back)); + + for (rt_se = back; rt_se; rt_se = rt_se->back) { + if (on_rt_rq(rt_se)) + __dequeue_rt_entity(rt_se); + } +} + +static void enqueue_rt_entity(struct sched_rt_entity *rt_se, bool head) +{ + struct rq *rq = rq_of_rt_se(rt_se); + + dequeue_rt_stack(rt_se); + for_each_sched_rt_entity(rt_se) + __enqueue_rt_entity(rt_se, head); + enqueue_top_rt_rq(&rq->rt); +} + +static void dequeue_rt_entity(struct sched_rt_entity *rt_se) +{ + struct rq *rq = rq_of_rt_se(rt_se); + + dequeue_rt_stack(rt_se); + + for_each_sched_rt_entity(rt_se) { + struct rt_rq *rt_rq = group_rt_rq(rt_se); + + if (rt_rq && rt_rq->rt_nr_running) + __enqueue_rt_entity(rt_se, false); + } + enqueue_top_rt_rq(&rq->rt); +} + +/* + * Adding/removing a task to/from a priority array: + */ +static void +enqueue_task_rt(struct rq *rq, struct task_struct *p, int flags) +{ + struct sched_rt_entity *rt_se = &p->rt; + + if (flags & ENQUEUE_WAKEUP) + rt_se->timeout = 0; + + enqueue_rt_entity(rt_se, flags & ENQUEUE_HEAD); + + if (!task_current(rq, p) && p->nr_cpus_allowed > 1) + enqueue_pushable_task(rq, p); +} + +static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int flags) +{ + struct sched_rt_entity *rt_se = &p->rt; + + update_curr_rt(rq); + dequeue_rt_entity(rt_se); + + dequeue_pushable_task(rq, p); +} + +/* + * Put task to the head or the end of the run list without the overhead of + * dequeue followed by enqueue. + */ +static void +requeue_rt_entity(struct rt_rq *rt_rq, struct sched_rt_entity *rt_se, int head) +{ + if (on_rt_rq(rt_se)) { + struct rt_prio_array *array = &rt_rq->active; + struct list_head *queue = array->queue + rt_se_prio(rt_se); + + if (head) + list_move(&rt_se->run_list, queue); + else + list_move_tail(&rt_se->run_list, queue); + } +} + +static void requeue_task_rt(struct rq *rq, struct task_struct *p, int head) +{ + struct sched_rt_entity *rt_se = &p->rt; + struct rt_rq *rt_rq; + + for_each_sched_rt_entity(rt_se) { + rt_rq = rt_rq_of_se(rt_se); + requeue_rt_entity(rt_rq, rt_se, head); + } +} + +static void yield_task_rt(struct rq *rq) +{ + requeue_task_rt(rq, rq->curr, 0); +} + +#ifdef CONFIG_SMP +static int find_lowest_rq(struct task_struct *task); + +static int +select_task_rq_rt(struct task_struct *p, int cpu, int sd_flag, int flags) +{ + struct task_struct *curr; + struct rq *rq; + + /* For anything but wake ups, just return the task_cpu */ + if (sd_flag != SD_BALANCE_WAKE && sd_flag != SD_BALANCE_FORK) + goto out; + + rq = cpu_rq(cpu); + + rcu_read_lock(); + curr = ACCESS_ONCE(rq->curr); /* unlocked access */ + + /* + * If the current task on @p's runqueue is an RT task, then + * try to see if we can wake this RT task up on another + * runqueue. Otherwise simply start this RT task + * on its current runqueue. + * + * We want to avoid overloading runqueues. If the woken + * task is a higher priority, then it will stay on this CPU + * and the lower prio task should be moved to another CPU. + * Even though this will probably make the lower prio task + * lose its cache, we do not want to bounce a higher task + * around just because it gave up its CPU, perhaps for a + * lock? + * + * For equal prio tasks, we just let the scheduler sort it out. + * + * Otherwise, just let it ride on the affined RQ and the + * post-schedule router will push the preempted task away + * + * This test is optimistic, if we get it wrong the load-balancer + * will have to sort it out. + */ + if (curr && unlikely(rt_task(curr)) && + (curr->nr_cpus_allowed < 2 || + curr->prio <= p->prio)) { + int target = find_lowest_rq(p); + + /* + * Don't bother moving it if the destination CPU is + * not running a lower priority task. + */ + if (target != -1 && + p->prio < cpu_rq(target)->rt.highest_prio.curr) + cpu = target; + } + rcu_read_unlock(); + +out: + return cpu; +} + +static void check_preempt_equal_prio(struct rq *rq, struct task_struct *p) +{ + /* + * Current can't be migrated, useless to reschedule, + * let's hope p can move out. + */ + if (rq->curr->nr_cpus_allowed == 1 || + !cpupri_find(&rq->rd->cpupri, rq->curr, NULL)) + return; + + /* + * p is migratable, so let's not schedule it and + * see if it is pushed or pulled somewhere else. + */ + if (p->nr_cpus_allowed != 1 + && cpupri_find(&rq->rd->cpupri, p, NULL)) + return; + + /* + * There appears to be other cpus that can accept + * current and none to run 'p', so lets reschedule + * to try and push current away: + */ + requeue_task_rt(rq, p, 1); + resched_curr(rq); +} + +#endif /* CONFIG_SMP */ + +/* + * Preempt the current task with a newly woken task if needed: + */ +static void check_preempt_curr_rt(struct rq *rq, struct task_struct *p, int flags) +{ + if (p->prio < rq->curr->prio) { + resched_curr(rq); + return; + } + +#ifdef CONFIG_SMP + /* + * If: + * + * - the newly woken task is of equal priority to the current task + * - the newly woken task is non-migratable while current is migratable + * - current will be preempted on the next reschedule + * + * we should check to see if current can readily move to a different + * cpu. If so, we will reschedule to allow the push logic to try + * to move current somewhere else, making room for our non-migratable + * task. + */ + if (p->prio == rq->curr->prio && !test_tsk_need_resched(rq->curr)) + check_preempt_equal_prio(rq, p); +#endif +} + +static struct sched_rt_entity *pick_next_rt_entity(struct rq *rq, + struct rt_rq *rt_rq) +{ + struct rt_prio_array *array = &rt_rq->active; + struct sched_rt_entity *next = NULL; + struct list_head *queue; + int idx; + + idx = sched_find_first_bit(array->bitmap); + BUG_ON(idx >= MAX_RT_PRIO); + + queue = array->queue + idx; + next = list_entry(queue->next, struct sched_rt_entity, run_list); + + return next; +} + +static struct task_struct *_pick_next_task_rt(struct rq *rq) +{ + struct sched_rt_entity *rt_se; + struct task_struct *p; + struct rt_rq *rt_rq = &rq->rt; + + do { + rt_se = pick_next_rt_entity(rq, rt_rq); + BUG_ON(!rt_se); + rt_rq = group_rt_rq(rt_se); + } while (rt_rq); + + p = rt_task_of(rt_se); + p->se.exec_start = rq_clock_task(rq); + + return p; +} + +static struct task_struct * +pick_next_task_rt(struct rq *rq, struct task_struct *prev) +{ + struct task_struct *p; + struct rt_rq *rt_rq = &rq->rt; + + if (need_pull_rt_task(rq, prev)) { + pull_rt_task(rq); + /* + * pull_rt_task() can drop (and re-acquire) rq->lock; this + * means a dl or stop task can slip in, in which case we need + * to re-start task selection. + */ + if (unlikely((rq->stop && task_on_rq_queued(rq->stop)) || + rq->dl.dl_nr_running)) + return RETRY_TASK; + } + + /* + * We may dequeue prev's rt_rq in put_prev_task(). + * So, we update time before rt_nr_running check. + */ + if (prev->sched_class == &rt_sched_class) + update_curr_rt(rq); + + if (!rt_rq->rt_queued) + return NULL; + + put_prev_task(rq, prev); + + p = _pick_next_task_rt(rq); + + /* The running task is never eligible for pushing */ + dequeue_pushable_task(rq, p); + + set_post_schedule(rq); + + return p; +} + +static void put_prev_task_rt(struct rq *rq, struct task_struct *p) +{ + update_curr_rt(rq); + + /* + * The previous task needs to be made eligible for pushing + * if it is still active + */ + if (on_rt_rq(&p->rt) && p->nr_cpus_allowed > 1) + enqueue_pushable_task(rq, p); +} + +#ifdef CONFIG_SMP + +/* Only try algorithms three times */ +#define RT_MAX_TRIES 3 + +static int pick_rt_task(struct rq *rq, struct task_struct *p, int cpu) +{ + if (!task_running(rq, p) && + cpumask_test_cpu(cpu, tsk_cpus_allowed(p))) + return 1; + return 0; +} + +/* + * Return the highest pushable rq's task, which is suitable to be executed + * on the cpu, NULL otherwise + */ +static struct task_struct *pick_highest_pushable_task(struct rq *rq, int cpu) +{ + struct plist_head *head = &rq->rt.pushable_tasks; + struct task_struct *p; + + if (!has_pushable_tasks(rq)) + return NULL; + + plist_for_each_entry(p, head, pushable_tasks) { + if (pick_rt_task(rq, p, cpu)) + return p; + } + + return NULL; +} + +static DEFINE_PER_CPU(cpumask_var_t, local_cpu_mask); + +static int find_lowest_rq(struct task_struct *task) +{ + struct sched_domain *sd; + struct cpumask *lowest_mask = this_cpu_cpumask_var_ptr(local_cpu_mask); + int this_cpu = smp_processor_id(); + int cpu = task_cpu(task); + + /* Make sure the mask is initialized first */ + if (unlikely(!lowest_mask)) + return -1; + + if (task->nr_cpus_allowed == 1) + return -1; /* No other targets possible */ + + if (!cpupri_find(&task_rq(task)->rd->cpupri, task, lowest_mask)) + return -1; /* No targets found */ + + /* + * At this point we have built a mask of cpus representing the + * lowest priority tasks in the system. Now we want to elect + * the best one based on our affinity and topology. + * + * We prioritize the last cpu that the task executed on since + * it is most likely cache-hot in that location. + */ + if (cpumask_test_cpu(cpu, lowest_mask)) + return cpu; + + /* + * Otherwise, we consult the sched_domains span maps to figure + * out which cpu is logically closest to our hot cache data. + */ + if (!cpumask_test_cpu(this_cpu, lowest_mask)) + this_cpu = -1; /* Skip this_cpu opt if not among lowest */ + + rcu_read_lock(); + for_each_domain(cpu, sd) { + if (sd->flags & SD_WAKE_AFFINE) { + int best_cpu; + + /* + * "this_cpu" is cheaper to preempt than a + * remote processor. + */ + if (this_cpu != -1 && + cpumask_test_cpu(this_cpu, sched_domain_span(sd))) { + rcu_read_unlock(); + return this_cpu; + } + + best_cpu = cpumask_first_and(lowest_mask, + sched_domain_span(sd)); + if (best_cpu < nr_cpu_ids) { + rcu_read_unlock(); + return best_cpu; + } + } + } + rcu_read_unlock(); + + /* + * And finally, if there were no matches within the domains + * just give the caller *something* to work with from the compatible + * locations. + */ + if (this_cpu != -1) + return this_cpu; + + cpu = cpumask_any(lowest_mask); + if (cpu < nr_cpu_ids) + return cpu; + return -1; +} + +/* Will lock the rq it finds */ +static struct rq *find_lock_lowest_rq(struct task_struct *task, struct rq *rq) +{ + struct rq *lowest_rq = NULL; + int tries; + int cpu; + + for (tries = 0; tries < RT_MAX_TRIES; tries++) { + cpu = find_lowest_rq(task); + + if ((cpu == -1) || (cpu == rq->cpu)) + break; + + lowest_rq = cpu_rq(cpu); + + if (lowest_rq->rt.highest_prio.curr <= task->prio) { + /* + * Target rq has tasks of equal or higher priority, + * retrying does not release any lock and is unlikely + * to yield a different result. + */ + lowest_rq = NULL; + break; + } + + /* if the prio of this runqueue changed, try again */ + if (double_lock_balance(rq, lowest_rq)) { + /* + * We had to unlock the run queue. In + * the mean time, task could have + * migrated already or had its affinity changed. + * Also make sure that it wasn't scheduled on its rq. + */ + if (unlikely(task_rq(task) != rq || + !cpumask_test_cpu(lowest_rq->cpu, + tsk_cpus_allowed(task)) || + task_running(rq, task) || + !task_on_rq_queued(task))) { + + double_unlock_balance(rq, lowest_rq); + lowest_rq = NULL; + break; + } + } + + /* If this rq is still suitable use it. */ + if (lowest_rq->rt.highest_prio.curr > task->prio) + break; + + /* try again */ + double_unlock_balance(rq, lowest_rq); + lowest_rq = NULL; + } + + return lowest_rq; +} + +static struct task_struct *pick_next_pushable_task(struct rq *rq) +{ + struct task_struct *p; + + if (!has_pushable_tasks(rq)) + return NULL; + + p = plist_first_entry(&rq->rt.pushable_tasks, + struct task_struct, pushable_tasks); + + BUG_ON(rq->cpu != task_cpu(p)); + BUG_ON(task_current(rq, p)); + BUG_ON(p->nr_cpus_allowed <= 1); + + BUG_ON(!task_on_rq_queued(p)); + BUG_ON(!rt_task(p)); + + return p; +} + +/* + * If the current CPU has more than one RT task, see if the non + * running task can migrate over to a CPU that is running a task + * of lesser priority. + */ +static int push_rt_task(struct rq *rq) +{ + struct task_struct *next_task; + struct rq *lowest_rq; + int ret = 0; + + if (!rq->rt.overloaded) + return 0; + + next_task = pick_next_pushable_task(rq); + if (!next_task) + return 0; + +retry: + if (unlikely(next_task == rq->curr)) { + WARN_ON(1); + return 0; + } + + /* + * It's possible that the next_task slipped in of + * higher priority than current. If that's the case + * just reschedule current. + */ + if (unlikely(next_task->prio < rq->curr->prio)) { + resched_curr(rq); + return 0; + } + + /* We might release rq lock */ + get_task_struct(next_task); + + /* find_lock_lowest_rq locks the rq if found */ + lowest_rq = find_lock_lowest_rq(next_task, rq); + if (!lowest_rq) { + struct task_struct *task; + /* + * find_lock_lowest_rq releases rq->lock + * so it is possible that next_task has migrated. + * + * We need to make sure that the task is still on the same + * run-queue and is also still the next task eligible for + * pushing. + */ + task = pick_next_pushable_task(rq); + if (task_cpu(next_task) == rq->cpu && task == next_task) { + /* + * The task hasn't migrated, and is still the next + * eligible task, but we failed to find a run-queue + * to push it to. Do not retry in this case, since + * other cpus will pull from us when ready. + */ + goto out; + } + + if (!task) + /* No more tasks, just exit */ + goto out; + + /* + * Something has shifted, try again. + */ + put_task_struct(next_task); + next_task = task; + goto retry; + } + + deactivate_task(rq, next_task, 0); + set_task_cpu(next_task, lowest_rq->cpu); + activate_task(lowest_rq, next_task, 0); + ret = 1; + + resched_curr(lowest_rq); + + double_unlock_balance(rq, lowest_rq); + +out: + put_task_struct(next_task); + + return ret; +} + +static void push_rt_tasks(struct rq *rq) +{ + /* push_rt_task will return true if it moved an RT */ + while (push_rt_task(rq)) + ; +} + +#ifdef HAVE_RT_PUSH_IPI +/* + * The search for the next cpu always starts at rq->cpu and ends + * when we reach rq->cpu again. It will never return rq->cpu. + * This returns the next cpu to check, or nr_cpu_ids if the loop + * is complete. + * + * rq->rt.push_cpu holds the last cpu returned by this function, + * or if this is the first instance, it must hold rq->cpu. + */ +static int rto_next_cpu(struct rq *rq) +{ + int prev_cpu = rq->rt.push_cpu; + int cpu; + + cpu = cpumask_next(prev_cpu, rq->rd->rto_mask); + + /* + * If the previous cpu is less than the rq's CPU, then it already + * passed the end of the mask, and has started from the beginning. + * We end if the next CPU is greater or equal to rq's CPU. + */ + if (prev_cpu < rq->cpu) { + if (cpu >= rq->cpu) + return nr_cpu_ids; + + } else if (cpu >= nr_cpu_ids) { + /* + * We passed the end of the mask, start at the beginning. + * If the result is greater or equal to the rq's CPU, then + * the loop is finished. + */ + cpu = cpumask_first(rq->rd->rto_mask); + if (cpu >= rq->cpu) + return nr_cpu_ids; + } + rq->rt.push_cpu = cpu; + + /* Return cpu to let the caller know if the loop is finished or not */ + return cpu; +} + +static int find_next_push_cpu(struct rq *rq) +{ + struct rq *next_rq; + int cpu; + + while (1) { + cpu = rto_next_cpu(rq); + if (cpu >= nr_cpu_ids) + break; + next_rq = cpu_rq(cpu); + + /* Make sure the next rq can push to this rq */ + if (next_rq->rt.highest_prio.next < rq->rt.highest_prio.curr) + break; + } + + return cpu; +} + +#define RT_PUSH_IPI_EXECUTING 1 +#define RT_PUSH_IPI_RESTART 2 + +static void tell_cpu_to_push(struct rq *rq) +{ + int cpu; + + if (rq->rt.push_flags & RT_PUSH_IPI_EXECUTING) { + raw_spin_lock(&rq->rt.push_lock); + /* Make sure it's still executing */ + if (rq->rt.push_flags & RT_PUSH_IPI_EXECUTING) { + /* + * Tell the IPI to restart the loop as things have + * changed since it started. + */ + rq->rt.push_flags |= RT_PUSH_IPI_RESTART; + raw_spin_unlock(&rq->rt.push_lock); + return; + } + raw_spin_unlock(&rq->rt.push_lock); + } + + /* When here, there's no IPI going around */ + + rq->rt.push_cpu = rq->cpu; + cpu = find_next_push_cpu(rq); + if (cpu >= nr_cpu_ids) + return; + + rq->rt.push_flags = RT_PUSH_IPI_EXECUTING; + + irq_work_queue_on(&rq->rt.push_work, cpu); +} + +/* Called from hardirq context */ +static void try_to_push_tasks(void *arg) +{ + struct rt_rq *rt_rq = arg; + struct rq *rq, *src_rq; + int this_cpu; + int cpu; + + this_cpu = rt_rq->push_cpu; + + /* Paranoid check */ + BUG_ON(this_cpu != smp_processor_id()); + + rq = cpu_rq(this_cpu); + src_rq = rq_of_rt_rq(rt_rq); + +again: + if (has_pushable_tasks(rq)) { + raw_spin_lock(&rq->lock); + push_rt_task(rq); + raw_spin_unlock(&rq->lock); + } + + /* Pass the IPI to the next rt overloaded queue */ + raw_spin_lock(&rt_rq->push_lock); + /* + * If the source queue changed since the IPI went out, + * we need to restart the search from that CPU again. + */ + if (rt_rq->push_flags & RT_PUSH_IPI_RESTART) { + rt_rq->push_flags &= ~RT_PUSH_IPI_RESTART; + rt_rq->push_cpu = src_rq->cpu; + } + + cpu = find_next_push_cpu(src_rq); + + if (cpu >= nr_cpu_ids) + rt_rq->push_flags &= ~RT_PUSH_IPI_EXECUTING; + raw_spin_unlock(&rt_rq->push_lock); + + if (cpu >= nr_cpu_ids) + return; + + /* + * It is possible that a restart caused this CPU to be + * chosen again. Don't bother with an IPI, just see if we + * have more to push. + */ + if (unlikely(cpu == rq->cpu)) + goto again; + + /* Try the next RT overloaded CPU */ + irq_work_queue_on(&rt_rq->push_work, cpu); +} + +static void push_irq_work_func(struct irq_work *work) +{ + struct rt_rq *rt_rq = container_of(work, struct rt_rq, push_work); + + try_to_push_tasks(rt_rq); +} +#endif /* HAVE_RT_PUSH_IPI */ + +static int pull_rt_task(struct rq *this_rq) +{ + int this_cpu = this_rq->cpu, ret = 0, cpu; + struct task_struct *p; + struct rq *src_rq; + + if (likely(!rt_overloaded(this_rq))) + return 0; + + /* + * Match the barrier from rt_set_overloaded; this guarantees that if we + * see overloaded we must also see the rto_mask bit. + */ + smp_rmb(); + +#ifdef HAVE_RT_PUSH_IPI + if (sched_feat(RT_PUSH_IPI)) { + tell_cpu_to_push(this_rq); + return 0; + } +#endif + + for_each_cpu(cpu, this_rq->rd->rto_mask) { + if (this_cpu == cpu) + continue; + + src_rq = cpu_rq(cpu); + + /* + * Don't bother taking the src_rq->lock if the next highest + * task is known to be lower-priority than our current task. + * This may look racy, but if this value is about to go + * logically higher, the src_rq will push this task away. + * And if its going logically lower, we do not care + */ + if (src_rq->rt.highest_prio.next >= + this_rq->rt.highest_prio.curr) + continue; + + /* + * We can potentially drop this_rq's lock in + * double_lock_balance, and another CPU could + * alter this_rq + */ + double_lock_balance(this_rq, src_rq); + + /* + * We can pull only a task, which is pushable + * on its rq, and no others. + */ + p = pick_highest_pushable_task(src_rq, this_cpu); + + /* + * Do we have an RT task that preempts + * the to-be-scheduled task? + */ + if (p && (p->prio < this_rq->rt.highest_prio.curr)) { + WARN_ON(p == src_rq->curr); + WARN_ON(!task_on_rq_queued(p)); + + /* + * There's a chance that p is higher in priority + * than what's currently running on its cpu. + * This is just that p is wakeing up and hasn't + * had a chance to schedule. We only pull + * p if it is lower in priority than the + * current task on the run queue + */ + if (p->prio < src_rq->curr->prio) + goto skip; + + ret = 1; + + deactivate_task(src_rq, p, 0); + set_task_cpu(p, this_cpu); + activate_task(this_rq, p, 0); + /* + * We continue with the search, just in + * case there's an even higher prio task + * in another runqueue. (low likelihood + * but possible) + */ + } +skip: + double_unlock_balance(this_rq, src_rq); + } + + return ret; +} + +static void post_schedule_rt(struct rq *rq) +{ + push_rt_tasks(rq); +} + +/* + * If we are not running and we are not going to reschedule soon, we should + * try to push tasks away now + */ +static void task_woken_rt(struct rq *rq, struct task_struct *p) +{ + if (!task_running(rq, p) && + !test_tsk_need_resched(rq->curr) && + has_pushable_tasks(rq) && + p->nr_cpus_allowed > 1 && + (dl_task(rq->curr) || rt_task(rq->curr)) && + (rq->curr->nr_cpus_allowed < 2 || + rq->curr->prio <= p->prio)) + push_rt_tasks(rq); +} + +static void set_cpus_allowed_rt(struct task_struct *p, + const struct cpumask *new_mask) +{ + struct rq *rq; + int weight; + + BUG_ON(!rt_task(p)); + + if (!task_on_rq_queued(p)) + return; + + weight = cpumask_weight(new_mask); + + /* + * Only update if the process changes its state from whether it + * can migrate or not. + */ + if ((p->nr_cpus_allowed > 1) == (weight > 1)) + return; + + rq = task_rq(p); + + /* + * The process used to be able to migrate OR it can now migrate + */ + if (weight <= 1) { + if (!task_current(rq, p)) + dequeue_pushable_task(rq, p); + BUG_ON(!rq->rt.rt_nr_migratory); + rq->rt.rt_nr_migratory--; + } else { + if (!task_current(rq, p)) + enqueue_pushable_task(rq, p); + rq->rt.rt_nr_migratory++; + } + + update_rt_migration(&rq->rt); +} + +/* Assumes rq->lock is held */ +static void rq_online_rt(struct rq *rq) +{ + if (rq->rt.overloaded) + rt_set_overload(rq); + + __enable_runtime(rq); + + cpupri_set(&rq->rd->cpupri, rq->cpu, rq->rt.highest_prio.curr); +} + +/* Assumes rq->lock is held */ +static void rq_offline_rt(struct rq *rq) +{ + if (rq->rt.overloaded) + rt_clear_overload(rq); + + __disable_runtime(rq); + + cpupri_set(&rq->rd->cpupri, rq->cpu, CPUPRI_INVALID); +} + +/* + * When switch from the rt queue, we bring ourselves to a position + * that we might want to pull RT tasks from other runqueues. + */ +static void switched_from_rt(struct rq *rq, struct task_struct *p) +{ + /* + * If there are other RT tasks then we will reschedule + * and the scheduling of the other RT tasks will handle + * the balancing. But if we are the last RT task + * we may need to handle the pulling of RT tasks + * now. + */ + if (!task_on_rq_queued(p) || rq->rt.rt_nr_running) + return; + + if (pull_rt_task(rq)) + resched_curr(rq); +} + +void __init init_sched_rt_class(void) +{ + unsigned int i; + + for_each_possible_cpu(i) { + zalloc_cpumask_var_node(&per_cpu(local_cpu_mask, i), + GFP_KERNEL, cpu_to_node(i)); + } +} +#endif /* CONFIG_SMP */ + +/* + * When switching a task to RT, we may overload the runqueue + * with RT tasks. In this case we try to push them off to + * other runqueues. + */ +static void switched_to_rt(struct rq *rq, struct task_struct *p) +{ + int check_resched = 1; + + /* + * If we are already running, then there's nothing + * that needs to be done. But if we are not running + * we may need to preempt the current running task. + * If that current running task is also an RT task + * then see if we can move to another run queue. + */ + if (task_on_rq_queued(p) && rq->curr != p) { +#ifdef CONFIG_SMP + if (p->nr_cpus_allowed > 1 && rq->rt.overloaded && + /* Don't resched if we changed runqueues */ + push_rt_task(rq) && rq != task_rq(p)) + check_resched = 0; +#endif /* CONFIG_SMP */ + if (check_resched && p->prio < rq->curr->prio) + resched_curr(rq); + } +} + +/* + * Priority of the task has changed. This may cause + * us to initiate a push or pull. + */ +static void +prio_changed_rt(struct rq *rq, struct task_struct *p, int oldprio) +{ + if (!task_on_rq_queued(p)) + return; + + if (rq->curr == p) { +#ifdef CONFIG_SMP + /* + * If our priority decreases while running, we + * may need to pull tasks to this runqueue. + */ + if (oldprio < p->prio) + pull_rt_task(rq); + /* + * If there's a higher priority task waiting to run + * then reschedule. Note, the above pull_rt_task + * can release the rq lock and p could migrate. + * Only reschedule if p is still on the same runqueue. + */ + if (p->prio > rq->rt.highest_prio.curr && rq->curr == p) + resched_curr(rq); +#else + /* For UP simply resched on drop of prio */ + if (oldprio < p->prio) + resched_curr(rq); +#endif /* CONFIG_SMP */ + } else { + /* + * This task is not running, but if it is + * greater than the current running task + * then reschedule. + */ + if (p->prio < rq->curr->prio) + resched_curr(rq); + } +} + +static void watchdog(struct rq *rq, struct task_struct *p) +{ + unsigned long soft, hard; + + /* max may change after cur was read, this will be fixed next tick */ + soft = task_rlimit(p, RLIMIT_RTTIME); + hard = task_rlimit_max(p, RLIMIT_RTTIME); + + if (soft != RLIM_INFINITY) { + unsigned long next; + + if (p->rt.watchdog_stamp != jiffies) { + p->rt.timeout++; + p->rt.watchdog_stamp = jiffies; + } + + next = DIV_ROUND_UP(min(soft, hard), USEC_PER_SEC/HZ); + if (p->rt.timeout > next) + p->cputime_expires.sched_exp = p->se.sum_exec_runtime; + } +} + +static void task_tick_rt(struct rq *rq, struct task_struct *p, int queued) +{ + struct sched_rt_entity *rt_se = &p->rt; + + update_curr_rt(rq); + + watchdog(rq, p); + + /* + * RR tasks need a special form of timeslice management. + * FIFO tasks have no timeslices. + */ + if (p->policy != SCHED_RR) + return; + + if (--p->rt.time_slice) + return; + + p->rt.time_slice = sched_rr_timeslice; + + /* + * Requeue to the end of queue if we (and all of our ancestors) are not + * the only element on the queue + */ + for_each_sched_rt_entity(rt_se) { + if (rt_se->run_list.prev != rt_se->run_list.next) { + requeue_task_rt(rq, p, 0); + resched_curr(rq); + return; + } + } +} + +static void set_curr_task_rt(struct rq *rq) +{ + struct task_struct *p = rq->curr; + + p->se.exec_start = rq_clock_task(rq); + + /* The running task is never eligible for pushing */ + dequeue_pushable_task(rq, p); +} + +static unsigned int get_rr_interval_rt(struct rq *rq, struct task_struct *task) +{ + /* + * Time slice is 0 for SCHED_FIFO tasks + */ + if (task->policy == SCHED_RR) + return sched_rr_timeslice; + else + return 0; +} + +const struct sched_class rt_sched_class = { + .next = &fair_sched_class, + .enqueue_task = enqueue_task_rt, + .dequeue_task = dequeue_task_rt, + .yield_task = yield_task_rt, + + .check_preempt_curr = check_preempt_curr_rt, + + .pick_next_task = pick_next_task_rt, + .put_prev_task = put_prev_task_rt, + +#ifdef CONFIG_SMP + .select_task_rq = select_task_rq_rt, + + .set_cpus_allowed = set_cpus_allowed_rt, + .rq_online = rq_online_rt, + .rq_offline = rq_offline_rt, + .post_schedule = post_schedule_rt, + .task_woken = task_woken_rt, + .switched_from = switched_from_rt, +#endif + + .set_curr_task = set_curr_task_rt, + .task_tick = task_tick_rt, + + .get_rr_interval = get_rr_interval_rt, + + .prio_changed = prio_changed_rt, + .switched_to = switched_to_rt, + + .update_curr = update_curr_rt, +}; + +#ifdef CONFIG_SCHED_DEBUG +extern void print_rt_rq(struct seq_file *m, int cpu, struct rt_rq *rt_rq); + +void print_rt_stats(struct seq_file *m, int cpu) +{ + rt_rq_iter_t iter; + struct rt_rq *rt_rq; + + rcu_read_lock(); + for_each_rt_rq(rt_rq, iter, cpu_rq(cpu)) + print_rt_rq(m, cpu, rt_rq); + rcu_read_unlock(); +} +#endif /* CONFIG_SCHED_DEBUG */ diff --git a/kernel/kernel/sched/sched.h b/kernel/kernel/sched/sched.h new file mode 100644 index 000000000..308f66454 --- /dev/null +++ b/kernel/kernel/sched/sched.h @@ -0,0 +1,1746 @@ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "cpupri.h" +#include "cpudeadline.h" +#include "cpuacct.h" + +struct rq; +struct cpuidle_state; + +/* task_struct::on_rq states: */ +#define TASK_ON_RQ_QUEUED 1 +#define TASK_ON_RQ_MIGRATING 2 + +extern __read_mostly int scheduler_running; + +extern unsigned long calc_load_update; +extern atomic_long_t calc_load_tasks; + +extern long calc_load_fold_active(struct rq *this_rq); +extern void update_cpu_load_active(struct rq *this_rq); + +/* + * Helpers for converting nanosecond timing to jiffy resolution + */ +#define NS_TO_JIFFIES(TIME) ((unsigned long)(TIME) / (NSEC_PER_SEC / HZ)) + +/* + * Increase resolution of nice-level calculations for 64-bit architectures. + * The extra resolution improves shares distribution and load balancing of + * low-weight task groups (eg. nice +19 on an autogroup), deeper taskgroup + * hierarchies, especially on larger systems. This is not a user-visible change + * and does not change the user-interface for setting shares/weights. + * + * We increase resolution only if we have enough bits to allow this increased + * resolution (i.e. BITS_PER_LONG > 32). The costs for increasing resolution + * when BITS_PER_LONG <= 32 are pretty high and the returns do not justify the + * increased costs. + */ +#if 0 /* BITS_PER_LONG > 32 -- currently broken: it increases power usage under light load */ +# define SCHED_LOAD_RESOLUTION 10 +# define scale_load(w) ((w) << SCHED_LOAD_RESOLUTION) +# define scale_load_down(w) ((w) >> SCHED_LOAD_RESOLUTION) +#else +# define SCHED_LOAD_RESOLUTION 0 +# define scale_load(w) (w) +# define scale_load_down(w) (w) +#endif + +#define SCHED_LOAD_SHIFT (10 + SCHED_LOAD_RESOLUTION) +#define SCHED_LOAD_SCALE (1L << SCHED_LOAD_SHIFT) + +#define NICE_0_LOAD SCHED_LOAD_SCALE +#define NICE_0_SHIFT SCHED_LOAD_SHIFT + +/* + * Single value that decides SCHED_DEADLINE internal math precision. + * 10 -> just above 1us + * 9 -> just above 0.5us + */ +#define DL_SCALE (10) + +/* + * These are the 'tuning knobs' of the scheduler: + */ + +/* + * single value that denotes runtime == period, ie unlimited time. + */ +#define RUNTIME_INF ((u64)~0ULL) + +static inline int fair_policy(int policy) +{ + return policy == SCHED_NORMAL || policy == SCHED_BATCH; +} + +static inline int rt_policy(int policy) +{ + return policy == SCHED_FIFO || policy == SCHED_RR; +} + +static inline int dl_policy(int policy) +{ + return policy == SCHED_DEADLINE; +} + +static inline int task_has_rt_policy(struct task_struct *p) +{ + return rt_policy(p->policy); +} + +static inline int task_has_dl_policy(struct task_struct *p) +{ + return dl_policy(p->policy); +} + +static inline bool dl_time_before(u64 a, u64 b) +{ + return (s64)(a - b) < 0; +} + +/* + * Tells if entity @a should preempt entity @b. + */ +static inline bool +dl_entity_preempt(struct sched_dl_entity *a, struct sched_dl_entity *b) +{ + return dl_time_before(a->deadline, b->deadline); +} + +/* + * This is the priority-queue data structure of the RT scheduling class: + */ +struct rt_prio_array { + DECLARE_BITMAP(bitmap, MAX_RT_PRIO+1); /* include 1 bit for delimiter */ + struct list_head queue[MAX_RT_PRIO]; +}; + +struct rt_bandwidth { + /* nests inside the rq lock: */ + raw_spinlock_t rt_runtime_lock; + ktime_t rt_period; + u64 rt_runtime; + struct hrtimer rt_period_timer; +}; + +void __dl_clear_params(struct task_struct *p); + +/* + * To keep the bandwidth of -deadline tasks and groups under control + * we need some place where: + * - store the maximum -deadline bandwidth of the system (the group); + * - cache the fraction of that bandwidth that is currently allocated. + * + * This is all done in the data structure below. It is similar to the + * one used for RT-throttling (rt_bandwidth), with the main difference + * that, since here we are only interested in admission control, we + * do not decrease any runtime while the group "executes", neither we + * need a timer to replenish it. + * + * With respect to SMP, the bandwidth is given on a per-CPU basis, + * meaning that: + * - dl_bw (< 100%) is the bandwidth of the system (group) on each CPU; + * - dl_total_bw array contains, in the i-eth element, the currently + * allocated bandwidth on the i-eth CPU. + * Moreover, groups consume bandwidth on each CPU, while tasks only + * consume bandwidth on the CPU they're running on. + * Finally, dl_total_bw_cpu is used to cache the index of dl_total_bw + * that will be shown the next time the proc or cgroup controls will + * be red. It on its turn can be changed by writing on its own + * control. + */ +struct dl_bandwidth { + raw_spinlock_t dl_runtime_lock; + u64 dl_runtime; + u64 dl_period; +}; + +static inline int dl_bandwidth_enabled(void) +{ + return sysctl_sched_rt_runtime >= 0; +} + +extern struct dl_bw *dl_bw_of(int i); + +struct dl_bw { + raw_spinlock_t lock; + u64 bw, total_bw; +}; + +static inline +void __dl_clear(struct dl_bw *dl_b, u64 tsk_bw) +{ + dl_b->total_bw -= tsk_bw; +} + +static inline +void __dl_add(struct dl_bw *dl_b, u64 tsk_bw) +{ + dl_b->total_bw += tsk_bw; +} + +static inline +bool __dl_overflow(struct dl_bw *dl_b, int cpus, u64 old_bw, u64 new_bw) +{ + return dl_b->bw != -1 && + dl_b->bw * cpus < dl_b->total_bw - old_bw + new_bw; +} + +extern struct mutex sched_domains_mutex; + +#ifdef CONFIG_CGROUP_SCHED + +#include + +struct cfs_rq; +struct rt_rq; + +extern struct list_head task_groups; + +struct cfs_bandwidth { +#ifdef CONFIG_CFS_BANDWIDTH + raw_spinlock_t lock; + ktime_t period; + u64 quota, runtime; + s64 hierarchical_quota; + u64 runtime_expires; + + int idle, timer_active; + struct hrtimer period_timer, slack_timer; + struct list_head throttled_cfs_rq; + + /* statistics */ + int nr_periods, nr_throttled; + u64 throttled_time; +#endif +}; + +/* task group related information */ +struct task_group { + struct cgroup_subsys_state css; + +#ifdef CONFIG_FAIR_GROUP_SCHED + /* schedulable entities of this group on each cpu */ + struct sched_entity **se; + /* runqueue "owned" by this group on each cpu */ + struct cfs_rq **cfs_rq; + unsigned long shares; + +#ifdef CONFIG_SMP + atomic_long_t load_avg; + atomic_t runnable_avg; +#endif +#endif + +#ifdef CONFIG_RT_GROUP_SCHED + struct sched_rt_entity **rt_se; + struct rt_rq **rt_rq; + + struct rt_bandwidth rt_bandwidth; +#endif + + struct rcu_head rcu; + struct list_head list; + + struct task_group *parent; + struct list_head siblings; + struct list_head children; + +#ifdef CONFIG_SCHED_AUTOGROUP + struct autogroup *autogroup; +#endif + + struct cfs_bandwidth cfs_bandwidth; +}; + +#ifdef CONFIG_FAIR_GROUP_SCHED +#define ROOT_TASK_GROUP_LOAD NICE_0_LOAD + +/* + * A weight of 0 or 1 can cause arithmetics problems. + * A weight of a cfs_rq is the sum of weights of which entities + * are queued on this cfs_rq, so a weight of a entity should not be + * too large, so as the shares value of a task group. + * (The default weight is 1024 - so there's no practical + * limitation from this.) + */ +#define MIN_SHARES (1UL << 1) +#define MAX_SHARES (1UL << 18) +#endif + +typedef int (*tg_visitor)(struct task_group *, void *); + +extern int walk_tg_tree_from(struct task_group *from, + tg_visitor down, tg_visitor up, void *data); + +/* + * Iterate the full tree, calling @down when first entering a node and @up when + * leaving it for the final time. + * + * Caller must hold rcu_lock or sufficient equivalent. + */ +static inline int walk_tg_tree(tg_visitor down, tg_visitor up, void *data) +{ + return walk_tg_tree_from(&root_task_group, down, up, data); +} + +extern int tg_nop(struct task_group *tg, void *data); + +extern void free_fair_sched_group(struct task_group *tg); +extern int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent); +extern void unregister_fair_sched_group(struct task_group *tg, int cpu); +extern void init_tg_cfs_entry(struct task_group *tg, struct cfs_rq *cfs_rq, + struct sched_entity *se, int cpu, + struct sched_entity *parent); +extern void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b); +extern int sched_group_set_shares(struct task_group *tg, unsigned long shares); + +extern void __refill_cfs_bandwidth_runtime(struct cfs_bandwidth *cfs_b); +extern void __start_cfs_bandwidth(struct cfs_bandwidth *cfs_b, bool force); +extern void unthrottle_cfs_rq(struct cfs_rq *cfs_rq); + +extern void free_rt_sched_group(struct task_group *tg); +extern int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent); +extern void init_tg_rt_entry(struct task_group *tg, struct rt_rq *rt_rq, + struct sched_rt_entity *rt_se, int cpu, + struct sched_rt_entity *parent); + +extern struct task_group *sched_create_group(struct task_group *parent); +extern void sched_online_group(struct task_group *tg, + struct task_group *parent); +extern void sched_destroy_group(struct task_group *tg); +extern void sched_offline_group(struct task_group *tg); + +extern void sched_move_task(struct task_struct *tsk); + +#ifdef CONFIG_FAIR_GROUP_SCHED +extern int sched_group_set_shares(struct task_group *tg, unsigned long shares); +#endif + +#else /* CONFIG_CGROUP_SCHED */ + +struct cfs_bandwidth { }; + +#endif /* CONFIG_CGROUP_SCHED */ + +/* CFS-related fields in a runqueue */ +struct cfs_rq { + struct load_weight load; + unsigned int nr_running, h_nr_running; + + u64 exec_clock; + u64 min_vruntime; +#ifndef CONFIG_64BIT + u64 min_vruntime_copy; +#endif + + struct rb_root tasks_timeline; + struct rb_node *rb_leftmost; + + /* + * 'curr' points to currently running entity on this cfs_rq. + * It is set to NULL otherwise (i.e when none are currently running). + */ + struct sched_entity *curr, *next, *last, *skip; + +#ifdef CONFIG_SCHED_DEBUG + unsigned int nr_spread_over; +#endif + +#ifdef CONFIG_SMP + /* + * CFS Load tracking + * Under CFS, load is tracked on a per-entity basis and aggregated up. + * This allows for the description of both thread and group usage (in + * the FAIR_GROUP_SCHED case). + * runnable_load_avg is the sum of the load_avg_contrib of the + * sched_entities on the rq. + * blocked_load_avg is similar to runnable_load_avg except that its + * the blocked sched_entities on the rq. + * utilization_load_avg is the sum of the average running time of the + * sched_entities on the rq. + */ + unsigned long runnable_load_avg, blocked_load_avg, utilization_load_avg; + atomic64_t decay_counter; + u64 last_decay; + atomic_long_t removed_load; + +#ifdef CONFIG_FAIR_GROUP_SCHED + /* Required to track per-cpu representation of a task_group */ + u32 tg_runnable_contrib; + unsigned long tg_load_contrib; + + /* + * h_load = weight * f(tg) + * + * Where f(tg) is the recursive weight fraction assigned to + * this group. + */ + unsigned long h_load; + u64 last_h_load_update; + struct sched_entity *h_load_next; +#endif /* CONFIG_FAIR_GROUP_SCHED */ +#endif /* CONFIG_SMP */ + +#ifdef CONFIG_FAIR_GROUP_SCHED + struct rq *rq; /* cpu runqueue to which this cfs_rq is attached */ + + /* + * leaf cfs_rqs are those that hold tasks (lowest schedulable entity in + * a hierarchy). Non-leaf lrqs hold other higher schedulable entities + * (like users, containers etc.) + * + * leaf_cfs_rq_list ties together list of leaf cfs_rq's in a cpu. This + * list is used during load balance. + */ + int on_list; + struct list_head leaf_cfs_rq_list; + struct task_group *tg; /* group that "owns" this runqueue */ + +#ifdef CONFIG_CFS_BANDWIDTH + int runtime_enabled; + u64 runtime_expires; + s64 runtime_remaining; + + u64 throttled_clock, throttled_clock_task; + u64 throttled_clock_task_time; + int throttled, throttle_count; + struct list_head throttled_list; +#endif /* CONFIG_CFS_BANDWIDTH */ +#endif /* CONFIG_FAIR_GROUP_SCHED */ +}; + +static inline int rt_bandwidth_enabled(void) +{ + return sysctl_sched_rt_runtime >= 0; +} + +/* RT IPI pull logic requires IRQ_WORK */ +#ifdef CONFIG_IRQ_WORK +# define HAVE_RT_PUSH_IPI +#endif + +/* Real-Time classes' related field in a runqueue: */ +struct rt_rq { + struct rt_prio_array active; + unsigned int rt_nr_running; +#if defined CONFIG_SMP || defined CONFIG_RT_GROUP_SCHED + struct { + int curr; /* highest queued rt task prio */ +#ifdef CONFIG_SMP + int next; /* next highest */ +#endif + } highest_prio; +#endif +#ifdef CONFIG_SMP + unsigned long rt_nr_migratory; + unsigned long rt_nr_total; + int overloaded; + struct plist_head pushable_tasks; +#ifdef HAVE_RT_PUSH_IPI + int push_flags; + int push_cpu; + struct irq_work push_work; + raw_spinlock_t push_lock; +#endif +#endif /* CONFIG_SMP */ + int rt_queued; + + int rt_throttled; + u64 rt_time; + u64 rt_runtime; + /* Nests inside the rq lock: */ + raw_spinlock_t rt_runtime_lock; + +#ifdef CONFIG_RT_GROUP_SCHED + unsigned long rt_nr_boosted; + + struct rq *rq; + struct task_group *tg; +#endif +}; + +/* Deadline class' related fields in a runqueue */ +struct dl_rq { + /* runqueue is an rbtree, ordered by deadline */ + struct rb_root rb_root; + struct rb_node *rb_leftmost; + + unsigned long dl_nr_running; + +#ifdef CONFIG_SMP + /* + * Deadline values of the currently executing and the + * earliest ready task on this rq. Caching these facilitates + * the decision wether or not a ready but not running task + * should migrate somewhere else. + */ + struct { + u64 curr; + u64 next; + } earliest_dl; + + unsigned long dl_nr_migratory; + int overloaded; + + /* + * Tasks on this rq that can be pushed away. They are kept in + * an rb-tree, ordered by tasks' deadlines, with caching + * of the leftmost (earliest deadline) element. + */ + struct rb_root pushable_dl_tasks_root; + struct rb_node *pushable_dl_tasks_leftmost; +#else + struct dl_bw dl_bw; +#endif +}; + +#ifdef CONFIG_SMP + +/* + * We add the notion of a root-domain which will be used to define per-domain + * variables. Each exclusive cpuset essentially defines an island domain by + * fully partitioning the member cpus from any other cpuset. Whenever a new + * exclusive cpuset is created, we also create and attach a new root-domain + * object. + * + */ +struct root_domain { + atomic_t refcount; + atomic_t rto_count; + struct rcu_head rcu; + cpumask_var_t span; + cpumask_var_t online; + + /* Indicate more than one runnable task for any CPU */ + bool overload; + + /* + * The bit corresponding to a CPU gets set here if such CPU has more + * than one runnable -deadline task (as it is below for RT tasks). + */ + cpumask_var_t dlo_mask; + atomic_t dlo_count; + struct dl_bw dl_bw; + struct cpudl cpudl; + + /* + * The "RT overload" flag: it gets set if a CPU has more than + * one runnable RT task. + */ + cpumask_var_t rto_mask; + struct cpupri cpupri; +}; + +extern struct root_domain def_root_domain; + +#endif /* CONFIG_SMP */ + +/* + * This is the main, per-CPU runqueue data structure. + * + * Locking rule: those places that want to lock multiple runqueues + * (such as the load balancing or the thread migration code), lock + * acquire operations must be ordered by ascending &runqueue. + */ +struct rq { + /* runqueue lock: */ + raw_spinlock_t lock; + + /* + * nr_running and cpu_load should be in the same cacheline because + * remote CPUs use both these fields when doing load calculation. + */ + unsigned int nr_running; +#ifdef CONFIG_NUMA_BALANCING + unsigned int nr_numa_running; + unsigned int nr_preferred_running; +#endif + #define CPU_LOAD_IDX_MAX 5 + unsigned long cpu_load[CPU_LOAD_IDX_MAX]; + unsigned long last_load_update_tick; +#ifdef CONFIG_NO_HZ_COMMON + u64 nohz_stamp; + unsigned long nohz_flags; +#endif +#ifdef CONFIG_NO_HZ_FULL + unsigned long last_sched_tick; +#endif + /* capture load from *all* tasks on this cpu: */ + struct load_weight load; + unsigned long nr_load_updates; + u64 nr_switches; + + struct cfs_rq cfs; + struct rt_rq rt; + struct dl_rq dl; + +#ifdef CONFIG_FAIR_GROUP_SCHED + /* list of leaf cfs_rq on this cpu: */ + struct list_head leaf_cfs_rq_list; + + struct sched_avg avg; +#endif /* CONFIG_FAIR_GROUP_SCHED */ + + /* + * This is part of a global counter where only the total sum + * over all CPUs matters. A task can increase this counter on + * one CPU and if it got migrated afterwards it may decrease + * it on another CPU. Always updated under the runqueue lock: + */ + unsigned long nr_uninterruptible; + + struct task_struct *curr, *idle, *stop; + unsigned long next_balance; + struct mm_struct *prev_mm; + + unsigned int clock_skip_update; + u64 clock; + u64 clock_task; + + atomic_t nr_iowait; + +#ifdef CONFIG_SMP + struct root_domain *rd; + struct sched_domain *sd; + + unsigned long cpu_capacity; + unsigned long cpu_capacity_orig; + + unsigned char idle_balance; + /* For active balancing */ + int post_schedule; + int active_balance; + int push_cpu; + struct cpu_stop_work active_balance_work; + /* cpu of this runqueue: */ + int cpu; + int online; + + struct list_head cfs_tasks; + + u64 rt_avg; + u64 age_stamp; + u64 idle_stamp; + u64 avg_idle; + + /* This is used to determine avg_idle's max value */ + u64 max_idle_balance_cost; +#endif + +#ifdef CONFIG_IRQ_TIME_ACCOUNTING + u64 prev_irq_time; +#endif +#ifdef CONFIG_PARAVIRT + u64 prev_steal_time; +#endif +#ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING + u64 prev_steal_time_rq; +#endif + + /* calc_load related fields */ + unsigned long calc_load_update; + long calc_load_active; + +#ifdef CONFIG_SCHED_HRTICK +#ifdef CONFIG_SMP + int hrtick_csd_pending; + struct call_single_data hrtick_csd; +#endif + struct hrtimer hrtick_timer; +#endif + +#ifdef CONFIG_SCHEDSTATS + /* latency stats */ + struct sched_info rq_sched_info; + unsigned long long rq_cpu_time; + /* could above be rq->cfs_rq.exec_clock + rq->rt_rq.rt_runtime ? */ + + /* sys_sched_yield() stats */ + unsigned int yld_count; + + /* schedule() stats */ + unsigned int sched_count; + unsigned int sched_goidle; + + /* try_to_wake_up() stats */ + unsigned int ttwu_count; + unsigned int ttwu_local; +#endif + +#ifdef CONFIG_SMP + struct llist_head wake_list; +#endif + +#ifdef CONFIG_CPU_IDLE + /* Must be inspected within a rcu lock section */ + struct cpuidle_state *idle_state; +#endif +}; + +static inline int cpu_of(struct rq *rq) +{ +#ifdef CONFIG_SMP + return rq->cpu; +#else + return 0; +#endif +} + +DECLARE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues); + +#define cpu_rq(cpu) (&per_cpu(runqueues, (cpu))) +#define this_rq() this_cpu_ptr(&runqueues) +#define task_rq(p) cpu_rq(task_cpu(p)) +#define cpu_curr(cpu) (cpu_rq(cpu)->curr) +#define raw_rq() raw_cpu_ptr(&runqueues) + +static inline u64 __rq_clock_broken(struct rq *rq) +{ + return ACCESS_ONCE(rq->clock); +} + +static inline u64 rq_clock(struct rq *rq) +{ + lockdep_assert_held(&rq->lock); + return rq->clock; +} + +static inline u64 rq_clock_task(struct rq *rq) +{ + lockdep_assert_held(&rq->lock); + return rq->clock_task; +} + +#define RQCF_REQ_SKIP 0x01 +#define RQCF_ACT_SKIP 0x02 + +static inline void rq_clock_skip_update(struct rq *rq, bool skip) +{ + lockdep_assert_held(&rq->lock); + if (skip) + rq->clock_skip_update |= RQCF_REQ_SKIP; + else + rq->clock_skip_update &= ~RQCF_REQ_SKIP; +} + +#ifdef CONFIG_NUMA +enum numa_topology_type { + NUMA_DIRECT, + NUMA_GLUELESS_MESH, + NUMA_BACKPLANE, +}; +extern enum numa_topology_type sched_numa_topology_type; +extern int sched_max_numa_distance; +extern bool find_numa_distance(int distance); +#endif + +#ifdef CONFIG_NUMA_BALANCING +/* The regions in numa_faults array from task_struct */ +enum numa_faults_stats { + NUMA_MEM = 0, + NUMA_CPU, + NUMA_MEMBUF, + NUMA_CPUBUF +}; +extern void sched_setnuma(struct task_struct *p, int node); +extern int migrate_task_to(struct task_struct *p, int cpu); +extern int migrate_swap(struct task_struct *, struct task_struct *); +#endif /* CONFIG_NUMA_BALANCING */ + +#ifdef CONFIG_SMP + +extern void sched_ttwu_pending(void); + +#define rcu_dereference_check_sched_domain(p) \ + rcu_dereference_check((p), \ + lockdep_is_held(&sched_domains_mutex)) + +/* + * The domain tree (rq->sd) is protected by RCU's quiescent state transition. + * See detach_destroy_domains: synchronize_sched for details. + * + * The domain tree of any CPU may only be accessed from within + * preempt-disabled sections. + */ +#define for_each_domain(cpu, __sd) \ + for (__sd = rcu_dereference_check_sched_domain(cpu_rq(cpu)->sd); \ + __sd; __sd = __sd->parent) + +#define for_each_lower_domain(sd) for (; sd; sd = sd->child) + +/** + * highest_flag_domain - Return highest sched_domain containing flag. + * @cpu: The cpu whose highest level of sched domain is to + * be returned. + * @flag: The flag to check for the highest sched_domain + * for the given cpu. + * + * Returns the highest sched_domain of a cpu which contains the given flag. + */ +static inline struct sched_domain *highest_flag_domain(int cpu, int flag) +{ + struct sched_domain *sd, *hsd = NULL; + + for_each_domain(cpu, sd) { + if (!(sd->flags & flag)) + break; + hsd = sd; + } + + return hsd; +} + +static inline struct sched_domain *lowest_flag_domain(int cpu, int flag) +{ + struct sched_domain *sd; + + for_each_domain(cpu, sd) { + if (sd->flags & flag) + break; + } + + return sd; +} + +DECLARE_PER_CPU(struct sched_domain *, sd_llc); +DECLARE_PER_CPU(int, sd_llc_size); +DECLARE_PER_CPU(int, sd_llc_id); +DECLARE_PER_CPU(struct sched_domain *, sd_numa); +DECLARE_PER_CPU(struct sched_domain *, sd_busy); +DECLARE_PER_CPU(struct sched_domain *, sd_asym); + +struct sched_group_capacity { + atomic_t ref; + /* + * CPU capacity of this group, SCHED_LOAD_SCALE being max capacity + * for a single CPU. + */ + unsigned int capacity; + unsigned long next_update; + int imbalance; /* XXX unrelated to capacity but shared group state */ + /* + * Number of busy cpus in this group. + */ + atomic_t nr_busy_cpus; + + unsigned long cpumask[0]; /* iteration mask */ +}; + +struct sched_group { + struct sched_group *next; /* Must be a circular list */ + atomic_t ref; + + unsigned int group_weight; + struct sched_group_capacity *sgc; + + /* + * The CPUs this group covers. + * + * NOTE: this field is variable length. (Allocated dynamically + * by attaching extra space to the end of the structure, + * depending on how many CPUs the kernel has booted up with) + */ + unsigned long cpumask[0]; +}; + +static inline struct cpumask *sched_group_cpus(struct sched_group *sg) +{ + return to_cpumask(sg->cpumask); +} + +/* + * cpumask masking which cpus in the group are allowed to iterate up the domain + * tree. + */ +static inline struct cpumask *sched_group_mask(struct sched_group *sg) +{ + return to_cpumask(sg->sgc->cpumask); +} + +/** + * group_first_cpu - Returns the first cpu in the cpumask of a sched_group. + * @group: The group whose first cpu is to be returned. + */ +static inline unsigned int group_first_cpu(struct sched_group *group) +{ + return cpumask_first(sched_group_cpus(group)); +} + +extern int group_balance_cpu(struct sched_group *sg); + +#else + +static inline void sched_ttwu_pending(void) { } + +#endif /* CONFIG_SMP */ + +#include "stats.h" +#include "auto_group.h" + +#ifdef CONFIG_CGROUP_SCHED + +/* + * Return the group to which this tasks belongs. + * + * We cannot use task_css() and friends because the cgroup subsystem + * changes that value before the cgroup_subsys::attach() method is called, + * therefore we cannot pin it and might observe the wrong value. + * + * The same is true for autogroup's p->signal->autogroup->tg, the autogroup + * core changes this before calling sched_move_task(). + * + * Instead we use a 'copy' which is updated from sched_move_task() while + * holding both task_struct::pi_lock and rq::lock. + */ +static inline struct task_group *task_group(struct task_struct *p) +{ + return p->sched_task_group; +} + +/* Change a task's cfs_rq and parent entity if it moves across CPUs/groups */ +static inline void set_task_rq(struct task_struct *p, unsigned int cpu) +{ +#if defined(CONFIG_FAIR_GROUP_SCHED) || defined(CONFIG_RT_GROUP_SCHED) + struct task_group *tg = task_group(p); +#endif + +#ifdef CONFIG_FAIR_GROUP_SCHED + p->se.cfs_rq = tg->cfs_rq[cpu]; + p->se.parent = tg->se[cpu]; +#endif + +#ifdef CONFIG_RT_GROUP_SCHED + p->rt.rt_rq = tg->rt_rq[cpu]; + p->rt.parent = tg->rt_se[cpu]; +#endif +} + +#else /* CONFIG_CGROUP_SCHED */ + +static inline void set_task_rq(struct task_struct *p, unsigned int cpu) { } +static inline struct task_group *task_group(struct task_struct *p) +{ + return NULL; +} + +#endif /* CONFIG_CGROUP_SCHED */ + +static inline void __set_task_cpu(struct task_struct *p, unsigned int cpu) +{ + set_task_rq(p, cpu); +#ifdef CONFIG_SMP + /* + * After ->cpu is set up to a new value, task_rq_lock(p, ...) can be + * successfuly executed on another CPU. We must ensure that updates of + * per-task data have been completed by this moment. + */ + smp_wmb(); + task_thread_info(p)->cpu = cpu; + p->wake_cpu = cpu; +#endif +} + +/* + * Tunables that become constants when CONFIG_SCHED_DEBUG is off: + */ +#ifdef CONFIG_SCHED_DEBUG +# include +# define const_debug __read_mostly +#else +# define const_debug const +#endif + +extern const_debug unsigned int sysctl_sched_features; + +#define SCHED_FEAT(name, enabled) \ + __SCHED_FEAT_##name , + +enum { +#include "features.h" + __SCHED_FEAT_NR, +}; + +#undef SCHED_FEAT + +#if defined(CONFIG_SCHED_DEBUG) && defined(HAVE_JUMP_LABEL) +#define SCHED_FEAT(name, enabled) \ +static __always_inline bool static_branch_##name(struct static_key *key) \ +{ \ + return static_key_##enabled(key); \ +} + +#include "features.h" + +#undef SCHED_FEAT + +extern struct static_key sched_feat_keys[__SCHED_FEAT_NR]; +#define sched_feat(x) (static_branch_##x(&sched_feat_keys[__SCHED_FEAT_##x])) +#else /* !(SCHED_DEBUG && HAVE_JUMP_LABEL) */ +#define sched_feat(x) (sysctl_sched_features & (1UL << __SCHED_FEAT_##x)) +#endif /* SCHED_DEBUG && HAVE_JUMP_LABEL */ + +#ifdef CONFIG_NUMA_BALANCING +#define sched_feat_numa(x) sched_feat(x) +#ifdef CONFIG_SCHED_DEBUG +#define numabalancing_enabled sched_feat_numa(NUMA) +#else +extern bool numabalancing_enabled; +#endif /* CONFIG_SCHED_DEBUG */ +#else +#define sched_feat_numa(x) (0) +#define numabalancing_enabled (0) +#endif /* CONFIG_NUMA_BALANCING */ + +static inline u64 global_rt_period(void) +{ + return (u64)sysctl_sched_rt_period * NSEC_PER_USEC; +} + +static inline u64 global_rt_runtime(void) +{ + if (sysctl_sched_rt_runtime < 0) + return RUNTIME_INF; + + return (u64)sysctl_sched_rt_runtime * NSEC_PER_USEC; +} + +static inline int task_current(struct rq *rq, struct task_struct *p) +{ + return rq->curr == p; +} + +static inline int task_running(struct rq *rq, struct task_struct *p) +{ +#ifdef CONFIG_SMP + return p->on_cpu; +#else + return task_current(rq, p); +#endif +} + +static inline int task_on_rq_queued(struct task_struct *p) +{ + return p->on_rq == TASK_ON_RQ_QUEUED; +} + +static inline int task_on_rq_migrating(struct task_struct *p) +{ + return p->on_rq == TASK_ON_RQ_MIGRATING; +} + +#ifndef prepare_arch_switch +# define prepare_arch_switch(next) do { } while (0) +#endif +#ifndef finish_arch_switch +# define finish_arch_switch(prev) do { } while (0) +#endif +#ifndef finish_arch_post_lock_switch +# define finish_arch_post_lock_switch() do { } while (0) +#endif + +static inline void prepare_lock_switch(struct rq *rq, struct task_struct *next) +{ +#ifdef CONFIG_SMP + /* + * We can optimise this out completely for !SMP, because the + * SMP rebalancing from interrupt is the only thing that cares + * here. + */ + next->on_cpu = 1; +#endif +} + +static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev) +{ +#ifdef CONFIG_SMP + /* + * After ->on_cpu is cleared, the task can be moved to a different CPU. + * We must ensure this doesn't happen until the switch is completely + * finished. + */ + smp_wmb(); + prev->on_cpu = 0; +#endif +#ifdef CONFIG_DEBUG_SPINLOCK + /* this is a valid case when another task releases the spinlock */ + rq->lock.owner = current; +#endif + /* + * If we are tracking spinlock dependencies then we have to + * fix up the runqueue lock - which gets 'carried over' from + * prev into current: + */ + spin_acquire(&rq->lock.dep_map, 0, 0, _THIS_IP_); + + raw_spin_unlock_irq(&rq->lock); +} + +/* + * wake flags + */ +#define WF_SYNC 0x01 /* waker goes to sleep after wakeup */ +#define WF_FORK 0x02 /* child wakeup after fork */ +#define WF_MIGRATED 0x4 /* internal use, task got migrated */ +#define WF_LOCK_SLEEPER 0x08 /* wakeup spinlock "sleeper" */ + +/* + * To aid in avoiding the subversion of "niceness" due to uneven distribution + * of tasks with abnormal "nice" values across CPUs the contribution that + * each task makes to its run queue's load is weighted according to its + * scheduling class and "nice" value. For SCHED_NORMAL tasks this is just a + * scaled version of the new time slice allocation that they receive on time + * slice expiry etc. + */ + +#define WEIGHT_IDLEPRIO 3 +#define WMULT_IDLEPRIO 1431655765 + +/* + * Nice levels are multiplicative, with a gentle 10% change for every + * nice level changed. I.e. when a CPU-bound task goes from nice 0 to + * nice 1, it will get ~10% less CPU time than another CPU-bound task + * that remained on nice 0. + * + * The "10% effect" is relative and cumulative: from _any_ nice level, + * if you go up 1 level, it's -10% CPU usage, if you go down 1 level + * it's +10% CPU usage. (to achieve that we use a multiplier of 1.25. + * If a task goes up by ~10% and another task goes down by ~10% then + * the relative distance between them is ~25%.) + */ +static const int prio_to_weight[40] = { + /* -20 */ 88761, 71755, 56483, 46273, 36291, + /* -15 */ 29154, 23254, 18705, 14949, 11916, + /* -10 */ 9548, 7620, 6100, 4904, 3906, + /* -5 */ 3121, 2501, 1991, 1586, 1277, + /* 0 */ 1024, 820, 655, 526, 423, + /* 5 */ 335, 272, 215, 172, 137, + /* 10 */ 110, 87, 70, 56, 45, + /* 15 */ 36, 29, 23, 18, 15, +}; + +/* + * Inverse (2^32/x) values of the prio_to_weight[] array, precalculated. + * + * In cases where the weight does not change often, we can use the + * precalculated inverse to speed up arithmetics by turning divisions + * into multiplications: + */ +static const u32 prio_to_wmult[40] = { + /* -20 */ 48388, 59856, 76040, 92818, 118348, + /* -15 */ 147320, 184698, 229616, 287308, 360437, + /* -10 */ 449829, 563644, 704093, 875809, 1099582, + /* -5 */ 1376151, 1717300, 2157191, 2708050, 3363326, + /* 0 */ 4194304, 5237765, 6557202, 8165337, 10153587, + /* 5 */ 12820798, 15790321, 19976592, 24970740, 31350126, + /* 10 */ 39045157, 49367440, 61356676, 76695844, 95443717, + /* 15 */ 119304647, 148102320, 186737708, 238609294, 286331153, +}; + +#define ENQUEUE_WAKEUP 1 +#define ENQUEUE_HEAD 2 +#ifdef CONFIG_SMP +#define ENQUEUE_WAKING 4 /* sched_class::task_waking was called */ +#else +#define ENQUEUE_WAKING 0 +#endif +#define ENQUEUE_REPLENISH 8 + +#define DEQUEUE_SLEEP 1 + +#define RETRY_TASK ((void *)-1UL) + +struct sched_class { + const struct sched_class *next; + + void (*enqueue_task) (struct rq *rq, struct task_struct *p, int flags); + void (*dequeue_task) (struct rq *rq, struct task_struct *p, int flags); + void (*yield_task) (struct rq *rq); + bool (*yield_to_task) (struct rq *rq, struct task_struct *p, bool preempt); + + void (*check_preempt_curr) (struct rq *rq, struct task_struct *p, int flags); + + /* + * It is the responsibility of the pick_next_task() method that will + * return the next task to call put_prev_task() on the @prev task or + * something equivalent. + * + * May return RETRY_TASK when it finds a higher prio class has runnable + * tasks. + */ + struct task_struct * (*pick_next_task) (struct rq *rq, + struct task_struct *prev); + void (*put_prev_task) (struct rq *rq, struct task_struct *p); + +#ifdef CONFIG_SMP + int (*select_task_rq)(struct task_struct *p, int task_cpu, int sd_flag, int flags); + void (*migrate_task_rq)(struct task_struct *p, int next_cpu); + + void (*post_schedule) (struct rq *this_rq); + void (*task_waking) (struct task_struct *task); + void (*task_woken) (struct rq *this_rq, struct task_struct *task); + + void (*set_cpus_allowed)(struct task_struct *p, + const struct cpumask *newmask); + + void (*rq_online)(struct rq *rq); + void (*rq_offline)(struct rq *rq); +#endif + + void (*set_curr_task) (struct rq *rq); + void (*task_tick) (struct rq *rq, struct task_struct *p, int queued); + void (*task_fork) (struct task_struct *p); + void (*task_dead) (struct task_struct *p); + + /* + * The switched_from() call is allowed to drop rq->lock, therefore we + * cannot assume the switched_from/switched_to pair is serliazed by + * rq->lock. They are however serialized by p->pi_lock. + */ + void (*switched_from) (struct rq *this_rq, struct task_struct *task); + void (*switched_to) (struct rq *this_rq, struct task_struct *task); + void (*prio_changed) (struct rq *this_rq, struct task_struct *task, + int oldprio); + + unsigned int (*get_rr_interval) (struct rq *rq, + struct task_struct *task); + + void (*update_curr) (struct rq *rq); + +#ifdef CONFIG_FAIR_GROUP_SCHED + void (*task_move_group) (struct task_struct *p, int on_rq); +#endif +}; + +static inline void put_prev_task(struct rq *rq, struct task_struct *prev) +{ + prev->sched_class->put_prev_task(rq, prev); +} + +#define sched_class_highest (&stop_sched_class) +#define for_each_class(class) \ + for (class = sched_class_highest; class; class = class->next) + +extern const struct sched_class stop_sched_class; +extern const struct sched_class dl_sched_class; +extern const struct sched_class rt_sched_class; +extern const struct sched_class fair_sched_class; +extern const struct sched_class idle_sched_class; + + +#ifdef CONFIG_SMP + +extern void update_group_capacity(struct sched_domain *sd, int cpu); + +extern void trigger_load_balance(struct rq *rq); + +extern void idle_enter_fair(struct rq *this_rq); +extern void idle_exit_fair(struct rq *this_rq); + +#else + +static inline void idle_enter_fair(struct rq *rq) { } +static inline void idle_exit_fair(struct rq *rq) { } + +#endif + +#ifdef CONFIG_CPU_IDLE +static inline void idle_set_state(struct rq *rq, + struct cpuidle_state *idle_state) +{ + rq->idle_state = idle_state; +} + +static inline struct cpuidle_state *idle_get_state(struct rq *rq) +{ + WARN_ON(!rcu_read_lock_held()); + return rq->idle_state; +} +#else +static inline void idle_set_state(struct rq *rq, + struct cpuidle_state *idle_state) +{ +} + +static inline struct cpuidle_state *idle_get_state(struct rq *rq) +{ + return NULL; +} +#endif + +extern void sysrq_sched_debug_show(void); +extern void sched_init_granularity(void); +extern void update_max_interval(void); + +extern void init_sched_dl_class(void); +extern void init_sched_rt_class(void); +extern void init_sched_fair_class(void); +extern void init_sched_dl_class(void); + +extern void resched_curr(struct rq *rq); +extern void resched_cpu(int cpu); + +#ifdef CONFIG_PREEMPT_LAZY +extern void resched_curr_lazy(struct rq *rq); +#else +static inline void resched_curr_lazy(struct rq *rq) +{ + resched_curr(rq); +} +#endif + +extern struct rt_bandwidth def_rt_bandwidth; +extern void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime); + +extern struct dl_bandwidth def_dl_bandwidth; +extern void init_dl_bandwidth(struct dl_bandwidth *dl_b, u64 period, u64 runtime); +extern void init_dl_task_timer(struct sched_dl_entity *dl_se); + +unsigned long to_ratio(u64 period, u64 runtime); + +extern void update_idle_cpu_load(struct rq *this_rq); + +extern void init_task_runnable_average(struct task_struct *p); + +static inline void add_nr_running(struct rq *rq, unsigned count) +{ + unsigned prev_nr = rq->nr_running; + + rq->nr_running = prev_nr + count; + + if (prev_nr < 2 && rq->nr_running >= 2) { +#ifdef CONFIG_SMP + if (!rq->rd->overload) + rq->rd->overload = true; +#endif + +#ifdef CONFIG_NO_HZ_FULL + if (tick_nohz_full_cpu(rq->cpu)) { + /* + * Tick is needed if more than one task runs on a CPU. + * Send the target an IPI to kick it out of nohz mode. + * + * We assume that IPI implies full memory barrier and the + * new value of rq->nr_running is visible on reception + * from the target. + */ + tick_nohz_full_kick_cpu(rq->cpu); + } +#endif + } +} + +static inline void sub_nr_running(struct rq *rq, unsigned count) +{ + rq->nr_running -= count; +} + +static inline void rq_last_tick_reset(struct rq *rq) +{ +#ifdef CONFIG_NO_HZ_FULL + rq->last_sched_tick = jiffies; +#endif +} + +extern void update_rq_clock(struct rq *rq); + +extern void activate_task(struct rq *rq, struct task_struct *p, int flags); +extern void deactivate_task(struct rq *rq, struct task_struct *p, int flags); + +extern void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags); + +extern const_debug unsigned int sysctl_sched_time_avg; +extern const_debug unsigned int sysctl_sched_nr_migrate; +extern const_debug unsigned int sysctl_sched_migration_cost; + +static inline u64 sched_avg_period(void) +{ + return (u64)sysctl_sched_time_avg * NSEC_PER_MSEC / 2; +} + +#ifdef CONFIG_SCHED_HRTICK + +/* + * Use hrtick when: + * - enabled by features + * - hrtimer is actually high res + */ +static inline int hrtick_enabled(struct rq *rq) +{ + if (!sched_feat(HRTICK)) + return 0; + if (!cpu_active(cpu_of(rq))) + return 0; + return hrtimer_is_hres_active(&rq->hrtick_timer); +} + +void hrtick_start(struct rq *rq, u64 delay); + +#else + +static inline int hrtick_enabled(struct rq *rq) +{ + return 0; +} + +#endif /* CONFIG_SCHED_HRTICK */ + +#ifdef CONFIG_SMP +extern void sched_avg_update(struct rq *rq); + +#ifndef arch_scale_freq_capacity +static __always_inline +unsigned long arch_scale_freq_capacity(struct sched_domain *sd, int cpu) +{ + return SCHED_CAPACITY_SCALE; +} +#endif + +static inline void sched_rt_avg_update(struct rq *rq, u64 rt_delta) +{ + rq->rt_avg += rt_delta * arch_scale_freq_capacity(NULL, cpu_of(rq)); + sched_avg_update(rq); +} +#else +static inline void sched_rt_avg_update(struct rq *rq, u64 rt_delta) { } +static inline void sched_avg_update(struct rq *rq) { } +#endif + +extern void start_bandwidth_timer(struct hrtimer *period_timer, ktime_t period); + +/* + * __task_rq_lock - lock the rq @p resides on. + */ +static inline struct rq *__task_rq_lock(struct task_struct *p) + __acquires(rq->lock) +{ + struct rq *rq; + + lockdep_assert_held(&p->pi_lock); + + for (;;) { + rq = task_rq(p); + raw_spin_lock(&rq->lock); + if (likely(rq == task_rq(p) && !task_on_rq_migrating(p))) + return rq; + raw_spin_unlock(&rq->lock); + + while (unlikely(task_on_rq_migrating(p))) + cpu_relax(); + } +} + +/* + * task_rq_lock - lock p->pi_lock and lock the rq @p resides on. + */ +static inline struct rq *task_rq_lock(struct task_struct *p, unsigned long *flags) + __acquires(p->pi_lock) + __acquires(rq->lock) +{ + struct rq *rq; + + for (;;) { + raw_spin_lock_irqsave(&p->pi_lock, *flags); + rq = task_rq(p); + raw_spin_lock(&rq->lock); + /* + * move_queued_task() task_rq_lock() + * + * ACQUIRE (rq->lock) + * [S] ->on_rq = MIGRATING [L] rq = task_rq() + * WMB (__set_task_cpu()) ACQUIRE (rq->lock); + * [S] ->cpu = new_cpu [L] task_rq() + * [L] ->on_rq + * RELEASE (rq->lock) + * + * If we observe the old cpu in task_rq_lock, the acquire of + * the old rq->lock will fully serialize against the stores. + * + * If we observe the new cpu in task_rq_lock, the acquire will + * pair with the WMB to ensure we must then also see migrating. + */ + if (likely(rq == task_rq(p) && !task_on_rq_migrating(p))) + return rq; + raw_spin_unlock(&rq->lock); + raw_spin_unlock_irqrestore(&p->pi_lock, *flags); + + while (unlikely(task_on_rq_migrating(p))) + cpu_relax(); + } +} + +static inline void __task_rq_unlock(struct rq *rq) + __releases(rq->lock) +{ + raw_spin_unlock(&rq->lock); +} + +static inline void +task_rq_unlock(struct rq *rq, struct task_struct *p, unsigned long *flags) + __releases(rq->lock) + __releases(p->pi_lock) +{ + raw_spin_unlock(&rq->lock); + raw_spin_unlock_irqrestore(&p->pi_lock, *flags); +} + +#ifdef CONFIG_SMP +#ifdef CONFIG_PREEMPT + +static inline void double_rq_lock(struct rq *rq1, struct rq *rq2); + +/* + * fair double_lock_balance: Safely acquires both rq->locks in a fair + * way at the expense of forcing extra atomic operations in all + * invocations. This assures that the double_lock is acquired using the + * same underlying policy as the spinlock_t on this architecture, which + * reduces latency compared to the unfair variant below. However, it + * also adds more overhead and therefore may reduce throughput. + */ +static inline int _double_lock_balance(struct rq *this_rq, struct rq *busiest) + __releases(this_rq->lock) + __acquires(busiest->lock) + __acquires(this_rq->lock) +{ + raw_spin_unlock(&this_rq->lock); + double_rq_lock(this_rq, busiest); + + return 1; +} + +#else +/* + * Unfair double_lock_balance: Optimizes throughput at the expense of + * latency by eliminating extra atomic operations when the locks are + * already in proper order on entry. This favors lower cpu-ids and will + * grant the double lock to lower cpus over higher ids under contention, + * regardless of entry order into the function. + */ +static inline int _double_lock_balance(struct rq *this_rq, struct rq *busiest) + __releases(this_rq->lock) + __acquires(busiest->lock) + __acquires(this_rq->lock) +{ + int ret = 0; + + if (unlikely(!raw_spin_trylock(&busiest->lock))) { + if (busiest < this_rq) { + raw_spin_unlock(&this_rq->lock); + raw_spin_lock(&busiest->lock); + raw_spin_lock_nested(&this_rq->lock, + SINGLE_DEPTH_NESTING); + ret = 1; + } else + raw_spin_lock_nested(&busiest->lock, + SINGLE_DEPTH_NESTING); + } + return ret; +} + +#endif /* CONFIG_PREEMPT */ + +/* + * double_lock_balance - lock the busiest runqueue, this_rq is locked already. + */ +static inline int double_lock_balance(struct rq *this_rq, struct rq *busiest) +{ + if (unlikely(!irqs_disabled())) { + /* printk() doesn't work good under rq->lock */ + raw_spin_unlock(&this_rq->lock); + BUG_ON(1); + } + + return _double_lock_balance(this_rq, busiest); +} + +static inline void double_unlock_balance(struct rq *this_rq, struct rq *busiest) + __releases(busiest->lock) +{ + raw_spin_unlock(&busiest->lock); + lock_set_subclass(&this_rq->lock.dep_map, 0, _RET_IP_); +} + +static inline void double_lock(spinlock_t *l1, spinlock_t *l2) +{ + if (l1 > l2) + swap(l1, l2); + + spin_lock(l1); + spin_lock_nested(l2, SINGLE_DEPTH_NESTING); +} + +static inline void double_lock_irq(spinlock_t *l1, spinlock_t *l2) +{ + if (l1 > l2) + swap(l1, l2); + + spin_lock_irq(l1); + spin_lock_nested(l2, SINGLE_DEPTH_NESTING); +} + +static inline void double_raw_lock(raw_spinlock_t *l1, raw_spinlock_t *l2) +{ + if (l1 > l2) + swap(l1, l2); + + raw_spin_lock(l1); + raw_spin_lock_nested(l2, SINGLE_DEPTH_NESTING); +} + +/* + * double_rq_lock - safely lock two runqueues + * + * Note this does not disable interrupts like task_rq_lock, + * you need to do so manually before calling. + */ +static inline void double_rq_lock(struct rq *rq1, struct rq *rq2) + __acquires(rq1->lock) + __acquires(rq2->lock) +{ + BUG_ON(!irqs_disabled()); + if (rq1 == rq2) { + raw_spin_lock(&rq1->lock); + __acquire(rq2->lock); /* Fake it out ;) */ + } else { + if (rq1 < rq2) { + raw_spin_lock(&rq1->lock); + raw_spin_lock_nested(&rq2->lock, SINGLE_DEPTH_NESTING); + } else { + raw_spin_lock(&rq2->lock); + raw_spin_lock_nested(&rq1->lock, SINGLE_DEPTH_NESTING); + } + } +} + +/* + * double_rq_unlock - safely unlock two runqueues + * + * Note this does not restore interrupts like task_rq_unlock, + * you need to do so manually after calling. + */ +static inline void double_rq_unlock(struct rq *rq1, struct rq *rq2) + __releases(rq1->lock) + __releases(rq2->lock) +{ + raw_spin_unlock(&rq1->lock); + if (rq1 != rq2) + raw_spin_unlock(&rq2->lock); + else + __release(rq2->lock); +} + +#else /* CONFIG_SMP */ + +/* + * double_rq_lock - safely lock two runqueues + * + * Note this does not disable interrupts like task_rq_lock, + * you need to do so manually before calling. + */ +static inline void double_rq_lock(struct rq *rq1, struct rq *rq2) + __acquires(rq1->lock) + __acquires(rq2->lock) +{ + BUG_ON(!irqs_disabled()); + BUG_ON(rq1 != rq2); + raw_spin_lock(&rq1->lock); + __acquire(rq2->lock); /* Fake it out ;) */ +} + +/* + * double_rq_unlock - safely unlock two runqueues + * + * Note this does not restore interrupts like task_rq_unlock, + * you need to do so manually after calling. + */ +static inline void double_rq_unlock(struct rq *rq1, struct rq *rq2) + __releases(rq1->lock) + __releases(rq2->lock) +{ + BUG_ON(rq1 != rq2); + raw_spin_unlock(&rq1->lock); + __release(rq2->lock); +} + +#endif + +extern struct sched_entity *__pick_first_entity(struct cfs_rq *cfs_rq); +extern struct sched_entity *__pick_last_entity(struct cfs_rq *cfs_rq); +extern void print_cfs_stats(struct seq_file *m, int cpu); +extern void print_rt_stats(struct seq_file *m, int cpu); +extern void print_dl_stats(struct seq_file *m, int cpu); + +extern void init_cfs_rq(struct cfs_rq *cfs_rq); +extern void init_rt_rq(struct rt_rq *rt_rq); +extern void init_dl_rq(struct dl_rq *dl_rq); + +extern void cfs_bandwidth_usage_inc(void); +extern void cfs_bandwidth_usage_dec(void); + +#ifdef CONFIG_NO_HZ_COMMON +enum rq_nohz_flag_bits { + NOHZ_TICK_STOPPED, + NOHZ_BALANCE_KICK, +}; + +#define nohz_flags(cpu) (&cpu_rq(cpu)->nohz_flags) +#endif + +#ifdef CONFIG_IRQ_TIME_ACCOUNTING + +DECLARE_PER_CPU(u64, cpu_hardirq_time); +DECLARE_PER_CPU(u64, cpu_softirq_time); + +#ifndef CONFIG_64BIT +DECLARE_PER_CPU(seqcount_t, irq_time_seq); + +static inline void irq_time_write_begin(void) +{ + __this_cpu_inc(irq_time_seq.sequence); + smp_wmb(); +} + +static inline void irq_time_write_end(void) +{ + smp_wmb(); + __this_cpu_inc(irq_time_seq.sequence); +} + +static inline u64 irq_time_read(int cpu) +{ + u64 irq_time; + unsigned seq; + + do { + seq = read_seqcount_begin(&per_cpu(irq_time_seq, cpu)); + irq_time = per_cpu(cpu_softirq_time, cpu) + + per_cpu(cpu_hardirq_time, cpu); + } while (read_seqcount_retry(&per_cpu(irq_time_seq, cpu), seq)); + + return irq_time; +} +#else /* CONFIG_64BIT */ +static inline void irq_time_write_begin(void) +{ +} + +static inline void irq_time_write_end(void) +{ +} + +static inline u64 irq_time_read(int cpu) +{ + return per_cpu(cpu_softirq_time, cpu) + per_cpu(cpu_hardirq_time, cpu); +} +#endif /* CONFIG_64BIT */ +#endif /* CONFIG_IRQ_TIME_ACCOUNTING */ diff --git a/kernel/kernel/sched/stats.c b/kernel/kernel/sched/stats.c new file mode 100644 index 000000000..87e2c9f0c --- /dev/null +++ b/kernel/kernel/sched/stats.c @@ -0,0 +1,138 @@ + +#include +#include +#include +#include + +#include "sched.h" + +/* + * bump this up when changing the output format or the meaning of an existing + * format, so that tools can adapt (or abort) + */ +#define SCHEDSTAT_VERSION 15 + +static int show_schedstat(struct seq_file *seq, void *v) +{ + int cpu; + + if (v == (void *)1) { + seq_printf(seq, "version %d\n", SCHEDSTAT_VERSION); + seq_printf(seq, "timestamp %lu\n", jiffies); + } else { + struct rq *rq; +#ifdef CONFIG_SMP + struct sched_domain *sd; + int dcount = 0; +#endif + cpu = (unsigned long)(v - 2); + rq = cpu_rq(cpu); + + /* runqueue-specific stats */ + seq_printf(seq, + "cpu%d %u 0 %u %u %u %u %llu %llu %lu", + cpu, rq->yld_count, + rq->sched_count, rq->sched_goidle, + rq->ttwu_count, rq->ttwu_local, + rq->rq_cpu_time, + rq->rq_sched_info.run_delay, rq->rq_sched_info.pcount); + + seq_printf(seq, "\n"); + +#ifdef CONFIG_SMP + /* domain-specific stats */ + rcu_read_lock(); + for_each_domain(cpu, sd) { + enum cpu_idle_type itype; + + seq_printf(seq, "domain%d %*pb", dcount++, + cpumask_pr_args(sched_domain_span(sd))); + for (itype = CPU_IDLE; itype < CPU_MAX_IDLE_TYPES; + itype++) { + seq_printf(seq, " %u %u %u %u %u %u %u %u", + sd->lb_count[itype], + sd->lb_balanced[itype], + sd->lb_failed[itype], + sd->lb_imbalance[itype], + sd->lb_gained[itype], + sd->lb_hot_gained[itype], + sd->lb_nobusyq[itype], + sd->lb_nobusyg[itype]); + } + seq_printf(seq, + " %u %u %u %u %u %u %u %u %u %u %u %u\n", + sd->alb_count, sd->alb_failed, sd->alb_pushed, + sd->sbe_count, sd->sbe_balanced, sd->sbe_pushed, + sd->sbf_count, sd->sbf_balanced, sd->sbf_pushed, + sd->ttwu_wake_remote, sd->ttwu_move_affine, + sd->ttwu_move_balance); + } + rcu_read_unlock(); +#endif + } + return 0; +} + +/* + * This itererator needs some explanation. + * It returns 1 for the header position. + * This means 2 is cpu 0. + * In a hotplugged system some cpus, including cpu 0, may be missing so we have + * to use cpumask_* to iterate over the cpus. + */ +static void *schedstat_start(struct seq_file *file, loff_t *offset) +{ + unsigned long n = *offset; + + if (n == 0) + return (void *) 1; + + n--; + + if (n > 0) + n = cpumask_next(n - 1, cpu_online_mask); + else + n = cpumask_first(cpu_online_mask); + + *offset = n + 1; + + if (n < nr_cpu_ids) + return (void *)(unsigned long)(n + 2); + return NULL; +} + +static void *schedstat_next(struct seq_file *file, void *data, loff_t *offset) +{ + (*offset)++; + return schedstat_start(file, offset); +} + +static void schedstat_stop(struct seq_file *file, void *data) +{ +} + +static const struct seq_operations schedstat_sops = { + .start = schedstat_start, + .next = schedstat_next, + .stop = schedstat_stop, + .show = show_schedstat, +}; + +static int schedstat_open(struct inode *inode, struct file *file) +{ + return seq_open(file, &schedstat_sops); +} + +static const struct file_operations proc_schedstat_operations = { + .open = schedstat_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, +}; + +static int __init proc_schedstat_init(void) +{ + proc_create("schedstat", 0, NULL, &proc_schedstat_operations); + return 0; +} +subsys_initcall(proc_schedstat_init); diff --git a/kernel/kernel/sched/stats.h b/kernel/kernel/sched/stats.h new file mode 100644 index 000000000..4ab704339 --- /dev/null +++ b/kernel/kernel/sched/stats.h @@ -0,0 +1,267 @@ + +#ifdef CONFIG_SCHEDSTATS + +/* + * Expects runqueue lock to be held for atomicity of update + */ +static inline void +rq_sched_info_arrive(struct rq *rq, unsigned long long delta) +{ + if (rq) { + rq->rq_sched_info.run_delay += delta; + rq->rq_sched_info.pcount++; + } +} + +/* + * Expects runqueue lock to be held for atomicity of update + */ +static inline void +rq_sched_info_depart(struct rq *rq, unsigned long long delta) +{ + if (rq) + rq->rq_cpu_time += delta; +} + +static inline void +rq_sched_info_dequeued(struct rq *rq, unsigned long long delta) +{ + if (rq) + rq->rq_sched_info.run_delay += delta; +} +# define schedstat_inc(rq, field) do { (rq)->field++; } while (0) +# define schedstat_add(rq, field, amt) do { (rq)->field += (amt); } while (0) +# define schedstat_set(var, val) do { var = (val); } while (0) +#else /* !CONFIG_SCHEDSTATS */ +static inline void +rq_sched_info_arrive(struct rq *rq, unsigned long long delta) +{} +static inline void +rq_sched_info_dequeued(struct rq *rq, unsigned long long delta) +{} +static inline void +rq_sched_info_depart(struct rq *rq, unsigned long long delta) +{} +# define schedstat_inc(rq, field) do { } while (0) +# define schedstat_add(rq, field, amt) do { } while (0) +# define schedstat_set(var, val) do { } while (0) +#endif + +#if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT) +static inline void sched_info_reset_dequeued(struct task_struct *t) +{ + t->sched_info.last_queued = 0; +} + +/* + * We are interested in knowing how long it was from the *first* time a + * task was queued to the time that it finally hit a cpu, we call this routine + * from dequeue_task() to account for possible rq->clock skew across cpus. The + * delta taken on each cpu would annul the skew. + */ +static inline void sched_info_dequeued(struct rq *rq, struct task_struct *t) +{ + unsigned long long now = rq_clock(rq), delta = 0; + + if (unlikely(sched_info_on())) + if (t->sched_info.last_queued) + delta = now - t->sched_info.last_queued; + sched_info_reset_dequeued(t); + t->sched_info.run_delay += delta; + + rq_sched_info_dequeued(rq, delta); +} + +/* + * Called when a task finally hits the cpu. We can now calculate how + * long it was waiting to run. We also note when it began so that we + * can keep stats on how long its timeslice is. + */ +static void sched_info_arrive(struct rq *rq, struct task_struct *t) +{ + unsigned long long now = rq_clock(rq), delta = 0; + + if (t->sched_info.last_queued) + delta = now - t->sched_info.last_queued; + sched_info_reset_dequeued(t); + t->sched_info.run_delay += delta; + t->sched_info.last_arrival = now; + t->sched_info.pcount++; + + rq_sched_info_arrive(rq, delta); +} + +/* + * This function is only called from enqueue_task(), but also only updates + * the timestamp if it is already not set. It's assumed that + * sched_info_dequeued() will clear that stamp when appropriate. + */ +static inline void sched_info_queued(struct rq *rq, struct task_struct *t) +{ + if (unlikely(sched_info_on())) + if (!t->sched_info.last_queued) + t->sched_info.last_queued = rq_clock(rq); +} + +/* + * Called when a process ceases being the active-running process involuntarily + * due, typically, to expiring its time slice (this may also be called when + * switching to the idle task). Now we can calculate how long we ran. + * Also, if the process is still in the TASK_RUNNING state, call + * sched_info_queued() to mark that it has now again started waiting on + * the runqueue. + */ +static inline void sched_info_depart(struct rq *rq, struct task_struct *t) +{ + unsigned long long delta = rq_clock(rq) - + t->sched_info.last_arrival; + + rq_sched_info_depart(rq, delta); + + if (t->state == TASK_RUNNING) + sched_info_queued(rq, t); +} + +/* + * Called when tasks are switched involuntarily due, typically, to expiring + * their time slice. (This may also be called when switching to or from + * the idle task.) We are only called when prev != next. + */ +static inline void +__sched_info_switch(struct rq *rq, + struct task_struct *prev, struct task_struct *next) +{ + /* + * prev now departs the cpu. It's not interesting to record + * stats about how efficient we were at scheduling the idle + * process, however. + */ + if (prev != rq->idle) + sched_info_depart(rq, prev); + + if (next != rq->idle) + sched_info_arrive(rq, next); +} +static inline void +sched_info_switch(struct rq *rq, + struct task_struct *prev, struct task_struct *next) +{ + if (unlikely(sched_info_on())) + __sched_info_switch(rq, prev, next); +} +#else +#define sched_info_queued(rq, t) do { } while (0) +#define sched_info_reset_dequeued(t) do { } while (0) +#define sched_info_dequeued(rq, t) do { } while (0) +#define sched_info_depart(rq, t) do { } while (0) +#define sched_info_arrive(rq, next) do { } while (0) +#define sched_info_switch(rq, t, next) do { } while (0) +#endif /* CONFIG_SCHEDSTATS || CONFIG_TASK_DELAY_ACCT */ + +/* + * The following are functions that support scheduler-internal time accounting. + * These functions are generally called at the timer tick. None of this depends + * on CONFIG_SCHEDSTATS. + */ + +/** + * cputimer_running - return true if cputimer is running + * + * @tsk: Pointer to target task. + */ +static inline bool cputimer_running(struct task_struct *tsk) + +{ + struct thread_group_cputimer *cputimer = &tsk->signal->cputimer; + + if (!cputimer->running) + return false; + + /* + * After we flush the task's sum_exec_runtime to sig->sum_sched_runtime + * in __exit_signal(), we won't account to the signal struct further + * cputime consumed by that task, even though the task can still be + * ticking after __exit_signal(). + * + * In order to keep a consistent behaviour between thread group cputime + * and thread group cputimer accounting, lets also ignore the cputime + * elapsing after __exit_signal() in any thread group timer running. + * + * This makes sure that POSIX CPU clocks and timers are synchronized, so + * that a POSIX CPU timer won't expire while the corresponding POSIX CPU + * clock delta is behind the expiring timer value. + */ + if (unlikely(!tsk->sighand)) + return false; + + return true; +} + +/** + * account_group_user_time - Maintain utime for a thread group. + * + * @tsk: Pointer to task structure. + * @cputime: Time value by which to increment the utime field of the + * thread_group_cputime structure. + * + * If thread group time is being maintained, get the structure for the + * running CPU and update the utime field there. + */ +static inline void account_group_user_time(struct task_struct *tsk, + cputime_t cputime) +{ + struct thread_group_cputimer *cputimer = &tsk->signal->cputimer; + + if (!cputimer_running(tsk)) + return; + + raw_spin_lock(&cputimer->lock); + cputimer->cputime.utime += cputime; + raw_spin_unlock(&cputimer->lock); +} + +/** + * account_group_system_time - Maintain stime for a thread group. + * + * @tsk: Pointer to task structure. + * @cputime: Time value by which to increment the stime field of the + * thread_group_cputime structure. + * + * If thread group time is being maintained, get the structure for the + * running CPU and update the stime field there. + */ +static inline void account_group_system_time(struct task_struct *tsk, + cputime_t cputime) +{ + struct thread_group_cputimer *cputimer = &tsk->signal->cputimer; + + if (!cputimer_running(tsk)) + return; + + raw_spin_lock(&cputimer->lock); + cputimer->cputime.stime += cputime; + raw_spin_unlock(&cputimer->lock); +} + +/** + * account_group_exec_runtime - Maintain exec runtime for a thread group. + * + * @tsk: Pointer to task structure. + * @ns: Time value by which to increment the sum_exec_runtime field + * of the thread_group_cputime structure. + * + * If thread group time is being maintained, get the structure for the + * running CPU and update the sum_exec_runtime field there. + */ +static inline void account_group_exec_runtime(struct task_struct *tsk, + unsigned long long ns) +{ + struct thread_group_cputimer *cputimer = &tsk->signal->cputimer; + + if (!cputimer_running(tsk)) + return; + + raw_spin_lock(&cputimer->lock); + cputimer->cputime.sum_exec_runtime += ns; + raw_spin_unlock(&cputimer->lock); +} diff --git a/kernel/kernel/sched/stop_task.c b/kernel/kernel/sched/stop_task.c new file mode 100644 index 000000000..79ffec45a --- /dev/null +++ b/kernel/kernel/sched/stop_task.c @@ -0,0 +1,136 @@ +#include "sched.h" + +/* + * stop-task scheduling class. + * + * The stop task is the highest priority task in the system, it preempts + * everything and will be preempted by nothing. + * + * See kernel/stop_machine.c + */ + +#ifdef CONFIG_SMP +static int +select_task_rq_stop(struct task_struct *p, int cpu, int sd_flag, int flags) +{ + return task_cpu(p); /* stop tasks as never migrate */ +} +#endif /* CONFIG_SMP */ + +static void +check_preempt_curr_stop(struct rq *rq, struct task_struct *p, int flags) +{ + /* we're never preempted */ +} + +static struct task_struct * +pick_next_task_stop(struct rq *rq, struct task_struct *prev) +{ + struct task_struct *stop = rq->stop; + + if (!stop || !task_on_rq_queued(stop)) + return NULL; + + put_prev_task(rq, prev); + + stop->se.exec_start = rq_clock_task(rq); + + return stop; +} + +static void +enqueue_task_stop(struct rq *rq, struct task_struct *p, int flags) +{ + add_nr_running(rq, 1); +} + +static void +dequeue_task_stop(struct rq *rq, struct task_struct *p, int flags) +{ + sub_nr_running(rq, 1); +} + +static void yield_task_stop(struct rq *rq) +{ + BUG(); /* the stop task should never yield, its pointless. */ +} + +static void put_prev_task_stop(struct rq *rq, struct task_struct *prev) +{ + struct task_struct *curr = rq->curr; + u64 delta_exec; + + delta_exec = rq_clock_task(rq) - curr->se.exec_start; + if (unlikely((s64)delta_exec < 0)) + delta_exec = 0; + + schedstat_set(curr->se.statistics.exec_max, + max(curr->se.statistics.exec_max, delta_exec)); + + curr->se.sum_exec_runtime += delta_exec; + account_group_exec_runtime(curr, delta_exec); + + curr->se.exec_start = rq_clock_task(rq); + cpuacct_charge(curr, delta_exec); +} + +static void task_tick_stop(struct rq *rq, struct task_struct *curr, int queued) +{ +} + +static void set_curr_task_stop(struct rq *rq) +{ + struct task_struct *stop = rq->stop; + + stop->se.exec_start = rq_clock_task(rq); +} + +static void switched_to_stop(struct rq *rq, struct task_struct *p) +{ + BUG(); /* its impossible to change to this class */ +} + +static void +prio_changed_stop(struct rq *rq, struct task_struct *p, int oldprio) +{ + BUG(); /* how!?, what priority? */ +} + +static unsigned int +get_rr_interval_stop(struct rq *rq, struct task_struct *task) +{ + return 0; +} + +static void update_curr_stop(struct rq *rq) +{ +} + +/* + * Simple, special scheduling class for the per-CPU stop tasks: + */ +const struct sched_class stop_sched_class = { + .next = &dl_sched_class, + + .enqueue_task = enqueue_task_stop, + .dequeue_task = dequeue_task_stop, + .yield_task = yield_task_stop, + + .check_preempt_curr = check_preempt_curr_stop, + + .pick_next_task = pick_next_task_stop, + .put_prev_task = put_prev_task_stop, + +#ifdef CONFIG_SMP + .select_task_rq = select_task_rq_stop, +#endif + + .set_curr_task = set_curr_task_stop, + .task_tick = task_tick_stop, + + .get_rr_interval = get_rr_interval_stop, + + .prio_changed = prio_changed_stop, + .switched_to = switched_to_stop, + .update_curr = update_curr_stop, +}; diff --git a/kernel/kernel/sched/wait-simple.c b/kernel/kernel/sched/wait-simple.c new file mode 100644 index 000000000..7dfa86d1f --- /dev/null +++ b/kernel/kernel/sched/wait-simple.c @@ -0,0 +1,115 @@ +/* + * Simple waitqueues without fancy flags and callbacks + * + * (C) 2011 Thomas Gleixner + * + * Based on kernel/wait.c + * + * For licencing details see kernel-base/COPYING + */ +#include +#include +#include +#include + +/* Adds w to head->list. Must be called with head->lock locked. */ +static inline void __swait_enqueue(struct swait_head *head, struct swaiter *w) +{ + list_add(&w->node, &head->list); + /* We can't let the condition leak before the setting of head */ + smp_mb(); +} + +/* Removes w from head->list. Must be called with head->lock locked. */ +static inline void __swait_dequeue(struct swaiter *w) +{ + list_del_init(&w->node); +} + +void __init_swait_head(struct swait_head *head, struct lock_class_key *key) +{ + raw_spin_lock_init(&head->lock); + lockdep_set_class(&head->lock, key); + INIT_LIST_HEAD(&head->list); +} +EXPORT_SYMBOL(__init_swait_head); + +void swait_prepare_locked(struct swait_head *head, struct swaiter *w) +{ + w->task = current; + if (list_empty(&w->node)) + __swait_enqueue(head, w); +} + +void swait_prepare(struct swait_head *head, struct swaiter *w, int state) +{ + unsigned long flags; + + raw_spin_lock_irqsave(&head->lock, flags); + swait_prepare_locked(head, w); + __set_current_state(state); + raw_spin_unlock_irqrestore(&head->lock, flags); +} +EXPORT_SYMBOL(swait_prepare); + +void swait_finish_locked(struct swait_head *head, struct swaiter *w) +{ + __set_current_state(TASK_RUNNING); + if (w->task) + __swait_dequeue(w); +} + +void swait_finish(struct swait_head *head, struct swaiter *w) +{ + unsigned long flags; + + __set_current_state(TASK_RUNNING); + if (w->task) { + raw_spin_lock_irqsave(&head->lock, flags); + __swait_dequeue(w); + raw_spin_unlock_irqrestore(&head->lock, flags); + } +} +EXPORT_SYMBOL(swait_finish); + +unsigned int +__swait_wake_locked(struct swait_head *head, unsigned int state, unsigned int num) +{ + struct swaiter *curr, *next; + int woken = 0; + + list_for_each_entry_safe(curr, next, &head->list, node) { + if (wake_up_state(curr->task, state)) { + __swait_dequeue(curr); + /* + * The waiting task can free the waiter as + * soon as curr->task = NULL is written, + * without taking any locks. A memory barrier + * is required here to prevent the following + * store to curr->task from getting ahead of + * the dequeue operation. + */ + smp_wmb(); + curr->task = NULL; + if (++woken == num) + break; + } + } + return woken; +} + +unsigned int +__swait_wake(struct swait_head *head, unsigned int state, unsigned int num) +{ + unsigned long flags; + int woken; + + if (!swaitqueue_active(head)) + return 0; + + raw_spin_lock_irqsave(&head->lock, flags); + woken = __swait_wake_locked(head, state, num); + raw_spin_unlock_irqrestore(&head->lock, flags); + return woken; +} +EXPORT_SYMBOL(__swait_wake); diff --git a/kernel/kernel/sched/wait.c b/kernel/kernel/sched/wait.c new file mode 100644 index 000000000..852143a79 --- /dev/null +++ b/kernel/kernel/sched/wait.c @@ -0,0 +1,624 @@ +/* + * Generic waiting primitives. + * + * (C) 2004 Nadia Yvette Chambers, Oracle + */ +#include +#include +#include +#include +#include +#include +#include + +void __init_waitqueue_head(wait_queue_head_t *q, const char *name, struct lock_class_key *key) +{ + spin_lock_init(&q->lock); + lockdep_set_class_and_name(&q->lock, key, name); + INIT_LIST_HEAD(&q->task_list); +} + +EXPORT_SYMBOL(__init_waitqueue_head); + +void add_wait_queue(wait_queue_head_t *q, wait_queue_t *wait) +{ + unsigned long flags; + + wait->flags &= ~WQ_FLAG_EXCLUSIVE; + spin_lock_irqsave(&q->lock, flags); + __add_wait_queue(q, wait); + spin_unlock_irqrestore(&q->lock, flags); +} +EXPORT_SYMBOL(add_wait_queue); + +void add_wait_queue_exclusive(wait_queue_head_t *q, wait_queue_t *wait) +{ + unsigned long flags; + + wait->flags |= WQ_FLAG_EXCLUSIVE; + spin_lock_irqsave(&q->lock, flags); + __add_wait_queue_tail(q, wait); + spin_unlock_irqrestore(&q->lock, flags); +} +EXPORT_SYMBOL(add_wait_queue_exclusive); + +void remove_wait_queue(wait_queue_head_t *q, wait_queue_t *wait) +{ + unsigned long flags; + + spin_lock_irqsave(&q->lock, flags); + __remove_wait_queue(q, wait); + spin_unlock_irqrestore(&q->lock, flags); +} +EXPORT_SYMBOL(remove_wait_queue); + + +/* + * The core wakeup function. Non-exclusive wakeups (nr_exclusive == 0) just + * wake everything up. If it's an exclusive wakeup (nr_exclusive == small +ve + * number) then we wake all the non-exclusive tasks and one exclusive task. + * + * There are circumstances in which we can try to wake a task which has already + * started to run but is not in state TASK_RUNNING. try_to_wake_up() returns + * zero in this (rare) case, and we handle it by continuing to scan the queue. + */ +static void __wake_up_common(wait_queue_head_t *q, unsigned int mode, + int nr_exclusive, int wake_flags, void *key) +{ + wait_queue_t *curr, *next; + + list_for_each_entry_safe(curr, next, &q->task_list, task_list) { + unsigned flags = curr->flags; + + if (curr->func(curr, mode, wake_flags, key) && + (flags & WQ_FLAG_EXCLUSIVE) && !--nr_exclusive) + break; + } +} + +/** + * __wake_up - wake up threads blocked on a waitqueue. + * @q: the waitqueue + * @mode: which threads + * @nr_exclusive: how many wake-one or wake-many threads to wake up + * @key: is directly passed to the wakeup function + * + * It may be assumed that this function implies a write memory barrier before + * changing the task state if and only if any tasks are woken up. + */ +void __wake_up(wait_queue_head_t *q, unsigned int mode, + int nr_exclusive, void *key) +{ + unsigned long flags; + + spin_lock_irqsave(&q->lock, flags); + __wake_up_common(q, mode, nr_exclusive, 0, key); + spin_unlock_irqrestore(&q->lock, flags); +} +EXPORT_SYMBOL(__wake_up); + +/* + * Same as __wake_up but called with the spinlock in wait_queue_head_t held. + */ +void __wake_up_locked(wait_queue_head_t *q, unsigned int mode, int nr) +{ + __wake_up_common(q, mode, nr, 0, NULL); +} +EXPORT_SYMBOL_GPL(__wake_up_locked); + +void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, void *key) +{ + __wake_up_common(q, mode, 1, 0, key); +} +EXPORT_SYMBOL_GPL(__wake_up_locked_key); + +/** + * __wake_up_sync_key - wake up threads blocked on a waitqueue. + * @q: the waitqueue + * @mode: which threads + * @nr_exclusive: how many wake-one or wake-many threads to wake up + * @key: opaque value to be passed to wakeup targets + * + * The sync wakeup differs that the waker knows that it will schedule + * away soon, so while the target thread will be woken up, it will not + * be migrated to another CPU - ie. the two threads are 'synchronized' + * with each other. This can prevent needless bouncing between CPUs. + * + * On UP it can prevent extra preemption. + * + * It may be assumed that this function implies a write memory barrier before + * changing the task state if and only if any tasks are woken up. + */ +void __wake_up_sync_key(wait_queue_head_t *q, unsigned int mode, + int nr_exclusive, void *key) +{ + unsigned long flags; + int wake_flags = 1; /* XXX WF_SYNC */ + + if (unlikely(!q)) + return; + + if (unlikely(nr_exclusive != 1)) + wake_flags = 0; + + spin_lock_irqsave(&q->lock, flags); + __wake_up_common(q, mode, nr_exclusive, wake_flags, key); + spin_unlock_irqrestore(&q->lock, flags); +} +EXPORT_SYMBOL_GPL(__wake_up_sync_key); + +/* + * __wake_up_sync - see __wake_up_sync_key() + */ +void __wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr_exclusive) +{ + __wake_up_sync_key(q, mode, nr_exclusive, NULL); +} +EXPORT_SYMBOL_GPL(__wake_up_sync); /* For internal use only */ + +/* + * Note: we use "set_current_state()" _after_ the wait-queue add, + * because we need a memory barrier there on SMP, so that any + * wake-function that tests for the wait-queue being active + * will be guaranteed to see waitqueue addition _or_ subsequent + * tests in this thread will see the wakeup having taken place. + * + * The spin_unlock() itself is semi-permeable and only protects + * one way (it only protects stuff inside the critical region and + * stops them from bleeding out - it would still allow subsequent + * loads to move into the critical region). + */ +void +prepare_to_wait(wait_queue_head_t *q, wait_queue_t *wait, int state) +{ + unsigned long flags; + + wait->flags &= ~WQ_FLAG_EXCLUSIVE; + spin_lock_irqsave(&q->lock, flags); + if (list_empty(&wait->task_list)) + __add_wait_queue(q, wait); + set_current_state(state); + spin_unlock_irqrestore(&q->lock, flags); +} +EXPORT_SYMBOL(prepare_to_wait); + +void +prepare_to_wait_exclusive(wait_queue_head_t *q, wait_queue_t *wait, int state) +{ + unsigned long flags; + + wait->flags |= WQ_FLAG_EXCLUSIVE; + spin_lock_irqsave(&q->lock, flags); + if (list_empty(&wait->task_list)) + __add_wait_queue_tail(q, wait); + set_current_state(state); + spin_unlock_irqrestore(&q->lock, flags); +} +EXPORT_SYMBOL(prepare_to_wait_exclusive); + +long prepare_to_wait_event(wait_queue_head_t *q, wait_queue_t *wait, int state) +{ + unsigned long flags; + + if (signal_pending_state(state, current)) + return -ERESTARTSYS; + + wait->private = current; + wait->func = autoremove_wake_function; + + spin_lock_irqsave(&q->lock, flags); + if (list_empty(&wait->task_list)) { + if (wait->flags & WQ_FLAG_EXCLUSIVE) + __add_wait_queue_tail(q, wait); + else + __add_wait_queue(q, wait); + } + set_current_state(state); + spin_unlock_irqrestore(&q->lock, flags); + + return 0; +} +EXPORT_SYMBOL(prepare_to_wait_event); + +/** + * finish_wait - clean up after waiting in a queue + * @q: waitqueue waited on + * @wait: wait descriptor + * + * Sets current thread back to running state and removes + * the wait descriptor from the given waitqueue if still + * queued. + */ +void finish_wait(wait_queue_head_t *q, wait_queue_t *wait) +{ + unsigned long flags; + + __set_current_state(TASK_RUNNING); + /* + * We can check for list emptiness outside the lock + * IFF: + * - we use the "careful" check that verifies both + * the next and prev pointers, so that there cannot + * be any half-pending updates in progress on other + * CPU's that we haven't seen yet (and that might + * still change the stack area. + * and + * - all other users take the lock (ie we can only + * have _one_ other CPU that looks at or modifies + * the list). + */ + if (!list_empty_careful(&wait->task_list)) { + spin_lock_irqsave(&q->lock, flags); + list_del_init(&wait->task_list); + spin_unlock_irqrestore(&q->lock, flags); + } +} +EXPORT_SYMBOL(finish_wait); + +/** + * abort_exclusive_wait - abort exclusive waiting in a queue + * @q: waitqueue waited on + * @wait: wait descriptor + * @mode: runstate of the waiter to be woken + * @key: key to identify a wait bit queue or %NULL + * + * Sets current thread back to running state and removes + * the wait descriptor from the given waitqueue if still + * queued. + * + * Wakes up the next waiter if the caller is concurrently + * woken up through the queue. + * + * This prevents waiter starvation where an exclusive waiter + * aborts and is woken up concurrently and no one wakes up + * the next waiter. + */ +void abort_exclusive_wait(wait_queue_head_t *q, wait_queue_t *wait, + unsigned int mode, void *key) +{ + unsigned long flags; + + __set_current_state(TASK_RUNNING); + spin_lock_irqsave(&q->lock, flags); + if (!list_empty(&wait->task_list)) + list_del_init(&wait->task_list); + else if (waitqueue_active(q)) + __wake_up_locked_key(q, mode, key); + spin_unlock_irqrestore(&q->lock, flags); +} +EXPORT_SYMBOL(abort_exclusive_wait); + +int autoremove_wake_function(wait_queue_t *wait, unsigned mode, int sync, void *key) +{ + int ret = default_wake_function(wait, mode, sync, key); + + if (ret) + list_del_init(&wait->task_list); + return ret; +} +EXPORT_SYMBOL(autoremove_wake_function); + +static inline bool is_kthread_should_stop(void) +{ + return (current->flags & PF_KTHREAD) && kthread_should_stop(); +} + +/* + * DEFINE_WAIT_FUNC(wait, woken_wake_func); + * + * add_wait_queue(&wq, &wait); + * for (;;) { + * if (condition) + * break; + * + * p->state = mode; condition = true; + * smp_mb(); // A smp_wmb(); // C + * if (!wait->flags & WQ_FLAG_WOKEN) wait->flags |= WQ_FLAG_WOKEN; + * schedule() try_to_wake_up(); + * p->state = TASK_RUNNING; ~~~~~~~~~~~~~~~~~~ + * wait->flags &= ~WQ_FLAG_WOKEN; condition = true; + * smp_mb() // B smp_wmb(); // C + * wait->flags |= WQ_FLAG_WOKEN; + * } + * remove_wait_queue(&wq, &wait); + * + */ +long wait_woken(wait_queue_t *wait, unsigned mode, long timeout) +{ + set_current_state(mode); /* A */ + /* + * The above implies an smp_mb(), which matches with the smp_wmb() from + * woken_wake_function() such that if we observe WQ_FLAG_WOKEN we must + * also observe all state before the wakeup. + */ + if (!(wait->flags & WQ_FLAG_WOKEN) && !is_kthread_should_stop()) + timeout = schedule_timeout(timeout); + __set_current_state(TASK_RUNNING); + + /* + * The below implies an smp_mb(), it too pairs with the smp_wmb() from + * woken_wake_function() such that we must either observe the wait + * condition being true _OR_ WQ_FLAG_WOKEN such that we will not miss + * an event. + */ + set_mb(wait->flags, wait->flags & ~WQ_FLAG_WOKEN); /* B */ + + return timeout; +} +EXPORT_SYMBOL(wait_woken); + +int woken_wake_function(wait_queue_t *wait, unsigned mode, int sync, void *key) +{ + /* + * Although this function is called under waitqueue lock, LOCK + * doesn't imply write barrier and the users expects write + * barrier semantics on wakeup functions. The following + * smp_wmb() is equivalent to smp_wmb() in try_to_wake_up() + * and is paired with set_mb() in wait_woken(). + */ + smp_wmb(); /* C */ + wait->flags |= WQ_FLAG_WOKEN; + + return default_wake_function(wait, mode, sync, key); +} +EXPORT_SYMBOL(woken_wake_function); + +int wake_bit_function(wait_queue_t *wait, unsigned mode, int sync, void *arg) +{ + struct wait_bit_key *key = arg; + struct wait_bit_queue *wait_bit + = container_of(wait, struct wait_bit_queue, wait); + + if (wait_bit->key.flags != key->flags || + wait_bit->key.bit_nr != key->bit_nr || + test_bit(key->bit_nr, key->flags)) + return 0; + else + return autoremove_wake_function(wait, mode, sync, key); +} +EXPORT_SYMBOL(wake_bit_function); + +/* + * To allow interruptible waiting and asynchronous (i.e. nonblocking) + * waiting, the actions of __wait_on_bit() and __wait_on_bit_lock() are + * permitted return codes. Nonzero return codes halt waiting and return. + */ +int __sched +__wait_on_bit(wait_queue_head_t *wq, struct wait_bit_queue *q, + wait_bit_action_f *action, unsigned mode) +{ + int ret = 0; + + do { + prepare_to_wait(wq, &q->wait, mode); + if (test_bit(q->key.bit_nr, q->key.flags)) + ret = (*action)(&q->key); + } while (test_bit(q->key.bit_nr, q->key.flags) && !ret); + finish_wait(wq, &q->wait); + return ret; +} +EXPORT_SYMBOL(__wait_on_bit); + +int __sched out_of_line_wait_on_bit(void *word, int bit, + wait_bit_action_f *action, unsigned mode) +{ + wait_queue_head_t *wq = bit_waitqueue(word, bit); + DEFINE_WAIT_BIT(wait, word, bit); + + return __wait_on_bit(wq, &wait, action, mode); +} +EXPORT_SYMBOL(out_of_line_wait_on_bit); + +int __sched out_of_line_wait_on_bit_timeout( + void *word, int bit, wait_bit_action_f *action, + unsigned mode, unsigned long timeout) +{ + wait_queue_head_t *wq = bit_waitqueue(word, bit); + DEFINE_WAIT_BIT(wait, word, bit); + + wait.key.timeout = jiffies + timeout; + return __wait_on_bit(wq, &wait, action, mode); +} +EXPORT_SYMBOL_GPL(out_of_line_wait_on_bit_timeout); + +int __sched +__wait_on_bit_lock(wait_queue_head_t *wq, struct wait_bit_queue *q, + wait_bit_action_f *action, unsigned mode) +{ + do { + int ret; + + prepare_to_wait_exclusive(wq, &q->wait, mode); + if (!test_bit(q->key.bit_nr, q->key.flags)) + continue; + ret = action(&q->key); + if (!ret) + continue; + abort_exclusive_wait(wq, &q->wait, mode, &q->key); + return ret; + } while (test_and_set_bit(q->key.bit_nr, q->key.flags)); + finish_wait(wq, &q->wait); + return 0; +} +EXPORT_SYMBOL(__wait_on_bit_lock); + +int __sched out_of_line_wait_on_bit_lock(void *word, int bit, + wait_bit_action_f *action, unsigned mode) +{ + wait_queue_head_t *wq = bit_waitqueue(word, bit); + DEFINE_WAIT_BIT(wait, word, bit); + + return __wait_on_bit_lock(wq, &wait, action, mode); +} +EXPORT_SYMBOL(out_of_line_wait_on_bit_lock); + +void __wake_up_bit(wait_queue_head_t *wq, void *word, int bit) +{ + struct wait_bit_key key = __WAIT_BIT_KEY_INITIALIZER(word, bit); + if (waitqueue_active(wq)) + __wake_up(wq, TASK_NORMAL, 1, &key); +} +EXPORT_SYMBOL(__wake_up_bit); + +/** + * wake_up_bit - wake up a waiter on a bit + * @word: the word being waited on, a kernel virtual address + * @bit: the bit of the word being waited on + * + * There is a standard hashed waitqueue table for generic use. This + * is the part of the hashtable's accessor API that wakes up waiters + * on a bit. For instance, if one were to have waiters on a bitflag, + * one would call wake_up_bit() after clearing the bit. + * + * In order for this to function properly, as it uses waitqueue_active() + * internally, some kind of memory barrier must be done prior to calling + * this. Typically, this will be smp_mb__after_atomic(), but in some + * cases where bitflags are manipulated non-atomically under a lock, one + * may need to use a less regular barrier, such fs/inode.c's smp_mb(), + * because spin_unlock() does not guarantee a memory barrier. + */ +void wake_up_bit(void *word, int bit) +{ + __wake_up_bit(bit_waitqueue(word, bit), word, bit); +} +EXPORT_SYMBOL(wake_up_bit); + +wait_queue_head_t *bit_waitqueue(void *word, int bit) +{ + const int shift = BITS_PER_LONG == 32 ? 5 : 6; + const struct zone *zone = page_zone(virt_to_page(word)); + unsigned long val = (unsigned long)word << shift | bit; + + return &zone->wait_table[hash_long(val, zone->wait_table_bits)]; +} +EXPORT_SYMBOL(bit_waitqueue); + +/* + * Manipulate the atomic_t address to produce a better bit waitqueue table hash + * index (we're keying off bit -1, but that would produce a horrible hash + * value). + */ +static inline wait_queue_head_t *atomic_t_waitqueue(atomic_t *p) +{ + if (BITS_PER_LONG == 64) { + unsigned long q = (unsigned long)p; + return bit_waitqueue((void *)(q & ~1), q & 1); + } + return bit_waitqueue(p, 0); +} + +static int wake_atomic_t_function(wait_queue_t *wait, unsigned mode, int sync, + void *arg) +{ + struct wait_bit_key *key = arg; + struct wait_bit_queue *wait_bit + = container_of(wait, struct wait_bit_queue, wait); + atomic_t *val = key->flags; + + if (wait_bit->key.flags != key->flags || + wait_bit->key.bit_nr != key->bit_nr || + atomic_read(val) != 0) + return 0; + return autoremove_wake_function(wait, mode, sync, key); +} + +/* + * To allow interruptible waiting and asynchronous (i.e. nonblocking) waiting, + * the actions of __wait_on_atomic_t() are permitted return codes. Nonzero + * return codes halt waiting and return. + */ +static __sched +int __wait_on_atomic_t(wait_queue_head_t *wq, struct wait_bit_queue *q, + int (*action)(atomic_t *), unsigned mode) +{ + atomic_t *val; + int ret = 0; + + do { + prepare_to_wait(wq, &q->wait, mode); + val = q->key.flags; + if (atomic_read(val) == 0) + break; + ret = (*action)(val); + } while (!ret && atomic_read(val) != 0); + finish_wait(wq, &q->wait); + return ret; +} + +#define DEFINE_WAIT_ATOMIC_T(name, p) \ + struct wait_bit_queue name = { \ + .key = __WAIT_ATOMIC_T_KEY_INITIALIZER(p), \ + .wait = { \ + .private = current, \ + .func = wake_atomic_t_function, \ + .task_list = \ + LIST_HEAD_INIT((name).wait.task_list), \ + }, \ + } + +__sched int out_of_line_wait_on_atomic_t(atomic_t *p, int (*action)(atomic_t *), + unsigned mode) +{ + wait_queue_head_t *wq = atomic_t_waitqueue(p); + DEFINE_WAIT_ATOMIC_T(wait, p); + + return __wait_on_atomic_t(wq, &wait, action, mode); +} +EXPORT_SYMBOL(out_of_line_wait_on_atomic_t); + +/** + * wake_up_atomic_t - Wake up a waiter on a atomic_t + * @p: The atomic_t being waited on, a kernel virtual address + * + * Wake up anyone waiting for the atomic_t to go to zero. + * + * Abuse the bit-waker function and its waitqueue hash table set (the atomic_t + * check is done by the waiter's wake function, not the by the waker itself). + */ +void wake_up_atomic_t(atomic_t *p) +{ + __wake_up_bit(atomic_t_waitqueue(p), p, WAIT_ATOMIC_T_BIT_NR); +} +EXPORT_SYMBOL(wake_up_atomic_t); + +__sched int bit_wait(struct wait_bit_key *word) +{ + if (signal_pending_state(current->state, current)) + return 1; + schedule(); + return 0; +} +EXPORT_SYMBOL(bit_wait); + +__sched int bit_wait_io(struct wait_bit_key *word) +{ + if (signal_pending_state(current->state, current)) + return 1; + io_schedule(); + return 0; +} +EXPORT_SYMBOL(bit_wait_io); + +__sched int bit_wait_timeout(struct wait_bit_key *word) +{ + unsigned long now = ACCESS_ONCE(jiffies); + if (signal_pending_state(current->state, current)) + return 1; + if (time_after_eq(now, word->timeout)) + return -EAGAIN; + schedule_timeout(word->timeout - now); + return 0; +} +EXPORT_SYMBOL_GPL(bit_wait_timeout); + +__sched int bit_wait_io_timeout(struct wait_bit_key *word) +{ + unsigned long now = ACCESS_ONCE(jiffies); + if (signal_pending_state(current->state, current)) + return 1; + if (time_after_eq(now, word->timeout)) + return -EAGAIN; + io_schedule_timeout(word->timeout - now); + return 0; +} +EXPORT_SYMBOL_GPL(bit_wait_io_timeout); diff --git a/kernel/kernel/sched/work-simple.c b/kernel/kernel/sched/work-simple.c new file mode 100644 index 000000000..c996f755d --- /dev/null +++ b/kernel/kernel/sched/work-simple.c @@ -0,0 +1,172 @@ +/* + * Copyright (C) 2014 BMW Car IT GmbH, Daniel Wagner daniel.wagner@bmw-carit.de + * + * Provides a framework for enqueuing callbacks from irq context + * PREEMPT_RT_FULL safe. The callbacks are executed in kthread context. + */ + +#include +#include +#include +#include +#include + +#define SWORK_EVENT_PENDING (1 << 0) + +static DEFINE_MUTEX(worker_mutex); +static struct sworker *glob_worker; + +struct sworker { + struct list_head events; + struct swait_head wq; + + raw_spinlock_t lock; + + struct task_struct *task; + int refs; +}; + +static bool swork_readable(struct sworker *worker) +{ + bool r; + + if (kthread_should_stop()) + return true; + + raw_spin_lock_irq(&worker->lock); + r = !list_empty(&worker->events); + raw_spin_unlock_irq(&worker->lock); + + return r; +} + +static int swork_kthread(void *arg) +{ + struct sworker *worker = arg; + + for (;;) { + swait_event_interruptible(worker->wq, + swork_readable(worker)); + if (kthread_should_stop()) + break; + + raw_spin_lock_irq(&worker->lock); + while (!list_empty(&worker->events)) { + struct swork_event *sev; + + sev = list_first_entry(&worker->events, + struct swork_event, item); + list_del(&sev->item); + raw_spin_unlock_irq(&worker->lock); + + WARN_ON_ONCE(!test_and_clear_bit(SWORK_EVENT_PENDING, + &sev->flags)); + sev->func(sev); + raw_spin_lock_irq(&worker->lock); + } + raw_spin_unlock_irq(&worker->lock); + } + return 0; +} + +static struct sworker *swork_create(void) +{ + struct sworker *worker; + + worker = kzalloc(sizeof(*worker), GFP_KERNEL); + if (!worker) + return ERR_PTR(-ENOMEM); + + INIT_LIST_HEAD(&worker->events); + raw_spin_lock_init(&worker->lock); + init_swait_head(&worker->wq); + + worker->task = kthread_run(swork_kthread, worker, "kswork"); + if (IS_ERR(worker->task)) { + kfree(worker); + return ERR_PTR(-ENOMEM); + } + + return worker; +} + +static void swork_destroy(struct sworker *worker) +{ + kthread_stop(worker->task); + + WARN_ON(!list_empty(&worker->events)); + kfree(worker); +} + +/** + * swork_queue - queue swork + * + * Returns %false if @work was already on a queue, %true otherwise. + * + * The work is queued and processed on a random CPU + */ +bool swork_queue(struct swork_event *sev) +{ + unsigned long flags; + + if (test_and_set_bit(SWORK_EVENT_PENDING, &sev->flags)) + return false; + + raw_spin_lock_irqsave(&glob_worker->lock, flags); + list_add_tail(&sev->item, &glob_worker->events); + raw_spin_unlock_irqrestore(&glob_worker->lock, flags); + + swait_wake(&glob_worker->wq); + return true; +} +EXPORT_SYMBOL_GPL(swork_queue); + +/** + * swork_get - get an instance of the sworker + * + * Returns an negative error code if the initialization if the worker did not + * work, %0 otherwise. + * + */ +int swork_get(void) +{ + struct sworker *worker; + + mutex_lock(&worker_mutex); + if (!glob_worker) { + worker = swork_create(); + if (IS_ERR(worker)) { + mutex_unlock(&worker_mutex); + return -ENOMEM; + } + + glob_worker = worker; + } + + glob_worker->refs++; + mutex_unlock(&worker_mutex); + + return 0; +} +EXPORT_SYMBOL_GPL(swork_get); + +/** + * swork_put - puts an instance of the sworker + * + * Will destroy the sworker thread. This function must not be called until all + * queued events have been completed. + */ +void swork_put(void) +{ + mutex_lock(&worker_mutex); + + glob_worker->refs--; + if (glob_worker->refs > 0) + goto out; + + swork_destroy(glob_worker); + glob_worker = NULL; +out: + mutex_unlock(&worker_mutex); +} +EXPORT_SYMBOL_GPL(swork_put); diff --git a/kernel/kernel/seccomp.c b/kernel/kernel/seccomp.c new file mode 100644 index 000000000..4f4402894 --- /dev/null +++ b/kernel/kernel/seccomp.c @@ -0,0 +1,904 @@ +/* + * linux/kernel/seccomp.c + * + * Copyright 2004-2005 Andrea Arcangeli + * + * Copyright (C) 2012 Google, Inc. + * Will Drewry + * + * This defines a simple but solid secure-computing facility. + * + * Mode 1 uses a fixed list of allowed system calls. + * Mode 2 allows user-defined system call filters in the form + * of Berkeley Packet Filters/Linux Socket Filters. + */ + +#include +#include +#include +#include +#include +#include +#include + +#ifdef CONFIG_HAVE_ARCH_SECCOMP_FILTER +#include +#endif + +#ifdef CONFIG_SECCOMP_FILTER +#include +#include +#include +#include +#include +#include + +/** + * struct seccomp_filter - container for seccomp BPF programs + * + * @usage: reference count to manage the object lifetime. + * get/put helpers should be used when accessing an instance + * outside of a lifetime-guarded section. In general, this + * is only needed for handling filters shared across tasks. + * @prev: points to a previously installed, or inherited, filter + * @len: the number of instructions in the program + * @insnsi: the BPF program instructions to evaluate + * + * seccomp_filter objects are organized in a tree linked via the @prev + * pointer. For any task, it appears to be a singly-linked list starting + * with current->seccomp.filter, the most recently attached or inherited filter. + * However, multiple filters may share a @prev node, by way of fork(), which + * results in a unidirectional tree existing in memory. This is similar to + * how namespaces work. + * + * seccomp_filter objects should never be modified after being attached + * to a task_struct (other than @usage). + */ +struct seccomp_filter { + atomic_t usage; + struct seccomp_filter *prev; + struct bpf_prog *prog; +}; + +/* Limit any path through the tree to 256KB worth of instructions. */ +#define MAX_INSNS_PER_PATH ((1 << 18) / sizeof(struct sock_filter)) + +/* + * Endianness is explicitly ignored and left for BPF program authors to manage + * as per the specific architecture. + */ +static void populate_seccomp_data(struct seccomp_data *sd) +{ + struct task_struct *task = current; + struct pt_regs *regs = task_pt_regs(task); + unsigned long args[6]; + + sd->nr = syscall_get_nr(task, regs); + sd->arch = syscall_get_arch(); + syscall_get_arguments(task, regs, 0, 6, args); + sd->args[0] = args[0]; + sd->args[1] = args[1]; + sd->args[2] = args[2]; + sd->args[3] = args[3]; + sd->args[4] = args[4]; + sd->args[5] = args[5]; + sd->instruction_pointer = KSTK_EIP(task); +} + +/** + * seccomp_check_filter - verify seccomp filter code + * @filter: filter to verify + * @flen: length of filter + * + * Takes a previously checked filter (by bpf_check_classic) and + * redirects all filter code that loads struct sk_buff data + * and related data through seccomp_bpf_load. It also + * enforces length and alignment checking of those loads. + * + * Returns 0 if the rule set is legal or -EINVAL if not. + */ +static int seccomp_check_filter(struct sock_filter *filter, unsigned int flen) +{ + int pc; + for (pc = 0; pc < flen; pc++) { + struct sock_filter *ftest = &filter[pc]; + u16 code = ftest->code; + u32 k = ftest->k; + + switch (code) { + case BPF_LD | BPF_W | BPF_ABS: + ftest->code = BPF_LDX | BPF_W | BPF_ABS; + /* 32-bit aligned and not out of bounds. */ + if (k >= sizeof(struct seccomp_data) || k & 3) + return -EINVAL; + continue; + case BPF_LD | BPF_W | BPF_LEN: + ftest->code = BPF_LD | BPF_IMM; + ftest->k = sizeof(struct seccomp_data); + continue; + case BPF_LDX | BPF_W | BPF_LEN: + ftest->code = BPF_LDX | BPF_IMM; + ftest->k = sizeof(struct seccomp_data); + continue; + /* Explicitly include allowed calls. */ + case BPF_RET | BPF_K: + case BPF_RET | BPF_A: + case BPF_ALU | BPF_ADD | BPF_K: + case BPF_ALU | BPF_ADD | BPF_X: + case BPF_ALU | BPF_SUB | BPF_K: + case BPF_ALU | BPF_SUB | BPF_X: + case BPF_ALU | BPF_MUL | BPF_K: + case BPF_ALU | BPF_MUL | BPF_X: + case BPF_ALU | BPF_DIV | BPF_K: + case BPF_ALU | BPF_DIV | BPF_X: + case BPF_ALU | BPF_AND | BPF_K: + case BPF_ALU | BPF_AND | BPF_X: + case BPF_ALU | BPF_OR | BPF_K: + case BPF_ALU | BPF_OR | BPF_X: + case BPF_ALU | BPF_XOR | BPF_K: + case BPF_ALU | BPF_XOR | BPF_X: + case BPF_ALU | BPF_LSH | BPF_K: + case BPF_ALU | BPF_LSH | BPF_X: + case BPF_ALU | BPF_RSH | BPF_K: + case BPF_ALU | BPF_RSH | BPF_X: + case BPF_ALU | BPF_NEG: + case BPF_LD | BPF_IMM: + case BPF_LDX | BPF_IMM: + case BPF_MISC | BPF_TAX: + case BPF_MISC | BPF_TXA: + case BPF_LD | BPF_MEM: + case BPF_LDX | BPF_MEM: + case BPF_ST: + case BPF_STX: + case BPF_JMP | BPF_JA: + case BPF_JMP | BPF_JEQ | BPF_K: + case BPF_JMP | BPF_JEQ | BPF_X: + case BPF_JMP | BPF_JGE | BPF_K: + case BPF_JMP | BPF_JGE | BPF_X: + case BPF_JMP | BPF_JGT | BPF_K: + case BPF_JMP | BPF_JGT | BPF_X: + case BPF_JMP | BPF_JSET | BPF_K: + case BPF_JMP | BPF_JSET | BPF_X: + continue; + default: + return -EINVAL; + } + } + return 0; +} + +/** + * seccomp_run_filters - evaluates all seccomp filters against @syscall + * @syscall: number of the current system call + * + * Returns valid seccomp BPF response codes. + */ +static u32 seccomp_run_filters(struct seccomp_data *sd) +{ + struct seccomp_filter *f = ACCESS_ONCE(current->seccomp.filter); + struct seccomp_data sd_local; + u32 ret = SECCOMP_RET_ALLOW; + + /* Ensure unexpected behavior doesn't result in failing open. */ + if (unlikely(WARN_ON(f == NULL))) + return SECCOMP_RET_KILL; + + /* Make sure cross-thread synced filter points somewhere sane. */ + smp_read_barrier_depends(); + + if (!sd) { + populate_seccomp_data(&sd_local); + sd = &sd_local; + } + + /* + * All filters in the list are evaluated and the lowest BPF return + * value always takes priority (ignoring the DATA). + */ + for (; f; f = f->prev) { + u32 cur_ret = BPF_PROG_RUN(f->prog, (void *)sd); + + if ((cur_ret & SECCOMP_RET_ACTION) < (ret & SECCOMP_RET_ACTION)) + ret = cur_ret; + } + return ret; +} +#endif /* CONFIG_SECCOMP_FILTER */ + +static inline bool seccomp_may_assign_mode(unsigned long seccomp_mode) +{ + assert_spin_locked(¤t->sighand->siglock); + + if (current->seccomp.mode && current->seccomp.mode != seccomp_mode) + return false; + + return true; +} + +static inline void seccomp_assign_mode(struct task_struct *task, + unsigned long seccomp_mode) +{ + assert_spin_locked(&task->sighand->siglock); + + task->seccomp.mode = seccomp_mode; + /* + * Make sure TIF_SECCOMP cannot be set before the mode (and + * filter) is set. + */ + smp_mb__before_atomic(); + set_tsk_thread_flag(task, TIF_SECCOMP); +} + +#ifdef CONFIG_SECCOMP_FILTER +/* Returns 1 if the parent is an ancestor of the child. */ +static int is_ancestor(struct seccomp_filter *parent, + struct seccomp_filter *child) +{ + /* NULL is the root ancestor. */ + if (parent == NULL) + return 1; + for (; child; child = child->prev) + if (child == parent) + return 1; + return 0; +} + +/** + * seccomp_can_sync_threads: checks if all threads can be synchronized + * + * Expects sighand and cred_guard_mutex locks to be held. + * + * Returns 0 on success, -ve on error, or the pid of a thread which was + * either not in the correct seccomp mode or it did not have an ancestral + * seccomp filter. + */ +static inline pid_t seccomp_can_sync_threads(void) +{ + struct task_struct *thread, *caller; + + BUG_ON(!mutex_is_locked(¤t->signal->cred_guard_mutex)); + assert_spin_locked(¤t->sighand->siglock); + + /* Validate all threads being eligible for synchronization. */ + caller = current; + for_each_thread(caller, thread) { + pid_t failed; + + /* Skip current, since it is initiating the sync. */ + if (thread == caller) + continue; + + if (thread->seccomp.mode == SECCOMP_MODE_DISABLED || + (thread->seccomp.mode == SECCOMP_MODE_FILTER && + is_ancestor(thread->seccomp.filter, + caller->seccomp.filter))) + continue; + + /* Return the first thread that cannot be synchronized. */ + failed = task_pid_vnr(thread); + /* If the pid cannot be resolved, then return -ESRCH */ + if (unlikely(WARN_ON(failed == 0))) + failed = -ESRCH; + return failed; + } + + return 0; +} + +/** + * seccomp_sync_threads: sets all threads to use current's filter + * + * Expects sighand and cred_guard_mutex locks to be held, and for + * seccomp_can_sync_threads() to have returned success already + * without dropping the locks. + * + */ +static inline void seccomp_sync_threads(void) +{ + struct task_struct *thread, *caller; + + BUG_ON(!mutex_is_locked(¤t->signal->cred_guard_mutex)); + assert_spin_locked(¤t->sighand->siglock); + + /* Synchronize all threads. */ + caller = current; + for_each_thread(caller, thread) { + /* Skip current, since it needs no changes. */ + if (thread == caller) + continue; + + /* Get a task reference for the new leaf node. */ + get_seccomp_filter(caller); + /* + * Drop the task reference to the shared ancestor since + * current's path will hold a reference. (This also + * allows a put before the assignment.) + */ + put_seccomp_filter(thread); + smp_store_release(&thread->seccomp.filter, + caller->seccomp.filter); + /* + * Opt the other thread into seccomp if needed. + * As threads are considered to be trust-realm + * equivalent (see ptrace_may_access), it is safe to + * allow one thread to transition the other. + */ + if (thread->seccomp.mode == SECCOMP_MODE_DISABLED) { + /* + * Don't let an unprivileged task work around + * the no_new_privs restriction by creating + * a thread that sets it up, enters seccomp, + * then dies. + */ + if (task_no_new_privs(caller)) + task_set_no_new_privs(thread); + + seccomp_assign_mode(thread, SECCOMP_MODE_FILTER); + } + } +} + +/** + * seccomp_prepare_filter: Prepares a seccomp filter for use. + * @fprog: BPF program to install + * + * Returns filter on success or an ERR_PTR on failure. + */ +static struct seccomp_filter *seccomp_prepare_filter(struct sock_fprog *fprog) +{ + struct seccomp_filter *filter; + unsigned long fp_size; + struct sock_filter *fp; + int new_len; + long ret; + + if (fprog->len == 0 || fprog->len > BPF_MAXINSNS) + return ERR_PTR(-EINVAL); + BUG_ON(INT_MAX / fprog->len < sizeof(struct sock_filter)); + fp_size = fprog->len * sizeof(struct sock_filter); + + /* + * Installing a seccomp filter requires that the task has + * CAP_SYS_ADMIN in its namespace or be running with no_new_privs. + * This avoids scenarios where unprivileged tasks can affect the + * behavior of privileged children. + */ + if (!task_no_new_privs(current) && + security_capable_noaudit(current_cred(), current_user_ns(), + CAP_SYS_ADMIN) != 0) + return ERR_PTR(-EACCES); + + fp = kzalloc(fp_size, GFP_KERNEL|__GFP_NOWARN); + if (!fp) + return ERR_PTR(-ENOMEM); + + /* Copy the instructions from fprog. */ + ret = -EFAULT; + if (copy_from_user(fp, fprog->filter, fp_size)) + goto free_prog; + + /* Check and rewrite the fprog via the skb checker */ + ret = bpf_check_classic(fp, fprog->len); + if (ret) + goto free_prog; + + /* Check and rewrite the fprog for seccomp use */ + ret = seccomp_check_filter(fp, fprog->len); + if (ret) + goto free_prog; + + /* Convert 'sock_filter' insns to 'bpf_insn' insns */ + ret = bpf_convert_filter(fp, fprog->len, NULL, &new_len); + if (ret) + goto free_prog; + + /* Allocate a new seccomp_filter */ + ret = -ENOMEM; + filter = kzalloc(sizeof(struct seccomp_filter), + GFP_KERNEL|__GFP_NOWARN); + if (!filter) + goto free_prog; + + filter->prog = bpf_prog_alloc(bpf_prog_size(new_len), __GFP_NOWARN); + if (!filter->prog) + goto free_filter; + + ret = bpf_convert_filter(fp, fprog->len, filter->prog->insnsi, &new_len); + if (ret) + goto free_filter_prog; + + kfree(fp); + atomic_set(&filter->usage, 1); + filter->prog->len = new_len; + + bpf_prog_select_runtime(filter->prog); + + return filter; + +free_filter_prog: + __bpf_prog_free(filter->prog); +free_filter: + kfree(filter); +free_prog: + kfree(fp); + return ERR_PTR(ret); +} + +/** + * seccomp_prepare_user_filter - prepares a user-supplied sock_fprog + * @user_filter: pointer to the user data containing a sock_fprog. + * + * Returns 0 on success and non-zero otherwise. + */ +static struct seccomp_filter * +seccomp_prepare_user_filter(const char __user *user_filter) +{ + struct sock_fprog fprog; + struct seccomp_filter *filter = ERR_PTR(-EFAULT); + +#ifdef CONFIG_COMPAT + if (is_compat_task()) { + struct compat_sock_fprog fprog32; + if (copy_from_user(&fprog32, user_filter, sizeof(fprog32))) + goto out; + fprog.len = fprog32.len; + fprog.filter = compat_ptr(fprog32.filter); + } else /* falls through to the if below. */ +#endif + if (copy_from_user(&fprog, user_filter, sizeof(fprog))) + goto out; + filter = seccomp_prepare_filter(&fprog); +out: + return filter; +} + +/** + * seccomp_attach_filter: validate and attach filter + * @flags: flags to change filter behavior + * @filter: seccomp filter to add to the current process + * + * Caller must be holding current->sighand->siglock lock. + * + * Returns 0 on success, -ve on error. + */ +static long seccomp_attach_filter(unsigned int flags, + struct seccomp_filter *filter) +{ + unsigned long total_insns; + struct seccomp_filter *walker; + + assert_spin_locked(¤t->sighand->siglock); + + /* Validate resulting filter length. */ + total_insns = filter->prog->len; + for (walker = current->seccomp.filter; walker; walker = walker->prev) + total_insns += walker->prog->len + 4; /* 4 instr penalty */ + if (total_insns > MAX_INSNS_PER_PATH) + return -ENOMEM; + + /* If thread sync has been requested, check that it is possible. */ + if (flags & SECCOMP_FILTER_FLAG_TSYNC) { + int ret; + + ret = seccomp_can_sync_threads(); + if (ret) + return ret; + } + + /* + * If there is an existing filter, make it the prev and don't drop its + * task reference. + */ + filter->prev = current->seccomp.filter; + current->seccomp.filter = filter; + + /* Now that the new filter is in place, synchronize to all threads. */ + if (flags & SECCOMP_FILTER_FLAG_TSYNC) + seccomp_sync_threads(); + + return 0; +} + +/* get_seccomp_filter - increments the reference count of the filter on @tsk */ +void get_seccomp_filter(struct task_struct *tsk) +{ + struct seccomp_filter *orig = tsk->seccomp.filter; + if (!orig) + return; + /* Reference count is bounded by the number of total processes. */ + atomic_inc(&orig->usage); +} + +static inline void seccomp_filter_free(struct seccomp_filter *filter) +{ + if (filter) { + bpf_prog_free(filter->prog); + kfree(filter); + } +} + +/* put_seccomp_filter - decrements the ref count of tsk->seccomp.filter */ +void put_seccomp_filter(struct task_struct *tsk) +{ + struct seccomp_filter *orig = tsk->seccomp.filter; + /* Clean up single-reference branches iteratively. */ + while (orig && atomic_dec_and_test(&orig->usage)) { + struct seccomp_filter *freeme = orig; + orig = orig->prev; + seccomp_filter_free(freeme); + } +} + +/** + * seccomp_send_sigsys - signals the task to allow in-process syscall emulation + * @syscall: syscall number to send to userland + * @reason: filter-supplied reason code to send to userland (via si_errno) + * + * Forces a SIGSYS with a code of SYS_SECCOMP and related sigsys info. + */ +static void seccomp_send_sigsys(int syscall, int reason) +{ + struct siginfo info; + memset(&info, 0, sizeof(info)); + info.si_signo = SIGSYS; + info.si_code = SYS_SECCOMP; + info.si_call_addr = (void __user *)KSTK_EIP(current); + info.si_errno = reason; + info.si_arch = syscall_get_arch(); + info.si_syscall = syscall; + force_sig_info(SIGSYS, &info, current); +} +#endif /* CONFIG_SECCOMP_FILTER */ + +/* + * Secure computing mode 1 allows only read/write/exit/sigreturn. + * To be fully secure this must be combined with rlimit + * to limit the stack allocations too. + */ +static int mode1_syscalls[] = { + __NR_seccomp_read, __NR_seccomp_write, __NR_seccomp_exit, __NR_seccomp_sigreturn, + 0, /* null terminated */ +}; + +#ifdef CONFIG_COMPAT +static int mode1_syscalls_32[] = { + __NR_seccomp_read_32, __NR_seccomp_write_32, __NR_seccomp_exit_32, __NR_seccomp_sigreturn_32, + 0, /* null terminated */ +}; +#endif + +static void __secure_computing_strict(int this_syscall) +{ + int *syscall_whitelist = mode1_syscalls; +#ifdef CONFIG_COMPAT + if (is_compat_task()) + syscall_whitelist = mode1_syscalls_32; +#endif + do { + if (*syscall_whitelist == this_syscall) + return; + } while (*++syscall_whitelist); + +#ifdef SECCOMP_DEBUG + dump_stack(); +#endif + audit_seccomp(this_syscall, SIGKILL, SECCOMP_RET_KILL); + do_exit(SIGKILL); +} + +#ifndef CONFIG_HAVE_ARCH_SECCOMP_FILTER +void secure_computing_strict(int this_syscall) +{ + int mode = current->seccomp.mode; + + if (mode == 0) + return; + else if (mode == SECCOMP_MODE_STRICT) + __secure_computing_strict(this_syscall); + else + BUG(); +} +#else +int __secure_computing(void) +{ + u32 phase1_result = seccomp_phase1(NULL); + + if (likely(phase1_result == SECCOMP_PHASE1_OK)) + return 0; + else if (likely(phase1_result == SECCOMP_PHASE1_SKIP)) + return -1; + else + return seccomp_phase2(phase1_result); +} + +#ifdef CONFIG_SECCOMP_FILTER +static u32 __seccomp_phase1_filter(int this_syscall, struct seccomp_data *sd) +{ + u32 filter_ret, action; + int data; + + /* + * Make sure that any changes to mode from another thread have + * been seen after TIF_SECCOMP was seen. + */ + rmb(); + + filter_ret = seccomp_run_filters(sd); + data = filter_ret & SECCOMP_RET_DATA; + action = filter_ret & SECCOMP_RET_ACTION; + + switch (action) { + case SECCOMP_RET_ERRNO: + /* Set low-order bits as an errno, capped at MAX_ERRNO. */ + if (data > MAX_ERRNO) + data = MAX_ERRNO; + syscall_set_return_value(current, task_pt_regs(current), + -data, 0); + goto skip; + + case SECCOMP_RET_TRAP: + /* Show the handler the original registers. */ + syscall_rollback(current, task_pt_regs(current)); + /* Let the filter pass back 16 bits of data. */ + seccomp_send_sigsys(this_syscall, data); + goto skip; + + case SECCOMP_RET_TRACE: + return filter_ret; /* Save the rest for phase 2. */ + + case SECCOMP_RET_ALLOW: + return SECCOMP_PHASE1_OK; + + case SECCOMP_RET_KILL: + default: + audit_seccomp(this_syscall, SIGSYS, action); + do_exit(SIGSYS); + } + + unreachable(); + +skip: + audit_seccomp(this_syscall, 0, action); + return SECCOMP_PHASE1_SKIP; +} +#endif + +/** + * seccomp_phase1() - run fast path seccomp checks on the current syscall + * @arg sd: The seccomp_data or NULL + * + * This only reads pt_regs via the syscall_xyz helpers. The only change + * it will make to pt_regs is via syscall_set_return_value, and it will + * only do that if it returns SECCOMP_PHASE1_SKIP. + * + * If sd is provided, it will not read pt_regs at all. + * + * It may also call do_exit or force a signal; these actions must be + * safe. + * + * If it returns SECCOMP_PHASE1_OK, the syscall passes checks and should + * be processed normally. + * + * If it returns SECCOMP_PHASE1_SKIP, then the syscall should not be + * invoked. In this case, seccomp_phase1 will have set the return value + * using syscall_set_return_value. + * + * If it returns anything else, then the return value should be passed + * to seccomp_phase2 from a context in which ptrace hooks are safe. + */ +u32 seccomp_phase1(struct seccomp_data *sd) +{ + int mode = current->seccomp.mode; + int this_syscall = sd ? sd->nr : + syscall_get_nr(current, task_pt_regs(current)); + + switch (mode) { + case SECCOMP_MODE_STRICT: + __secure_computing_strict(this_syscall); /* may call do_exit */ + return SECCOMP_PHASE1_OK; +#ifdef CONFIG_SECCOMP_FILTER + case SECCOMP_MODE_FILTER: + return __seccomp_phase1_filter(this_syscall, sd); +#endif + default: + BUG(); + } +} + +/** + * seccomp_phase2() - finish slow path seccomp work for the current syscall + * @phase1_result: The return value from seccomp_phase1() + * + * This must be called from a context in which ptrace hooks can be used. + * + * Returns 0 if the syscall should be processed or -1 to skip the syscall. + */ +int seccomp_phase2(u32 phase1_result) +{ + struct pt_regs *regs = task_pt_regs(current); + u32 action = phase1_result & SECCOMP_RET_ACTION; + int data = phase1_result & SECCOMP_RET_DATA; + + BUG_ON(action != SECCOMP_RET_TRACE); + + audit_seccomp(syscall_get_nr(current, regs), 0, action); + + /* Skip these calls if there is no tracer. */ + if (!ptrace_event_enabled(current, PTRACE_EVENT_SECCOMP)) { + syscall_set_return_value(current, regs, + -ENOSYS, 0); + return -1; + } + + /* Allow the BPF to provide the event message */ + ptrace_event(PTRACE_EVENT_SECCOMP, data); + /* + * The delivery of a fatal signal during event + * notification may silently skip tracer notification. + * Terminating the task now avoids executing a system + * call that may not be intended. + */ + if (fatal_signal_pending(current)) + do_exit(SIGSYS); + if (syscall_get_nr(current, regs) < 0) + return -1; /* Explicit request to skip. */ + + return 0; +} +#endif /* CONFIG_HAVE_ARCH_SECCOMP_FILTER */ + +long prctl_get_seccomp(void) +{ + return current->seccomp.mode; +} + +/** + * seccomp_set_mode_strict: internal function for setting strict seccomp + * + * Once current->seccomp.mode is non-zero, it may not be changed. + * + * Returns 0 on success or -EINVAL on failure. + */ +static long seccomp_set_mode_strict(void) +{ + const unsigned long seccomp_mode = SECCOMP_MODE_STRICT; + long ret = -EINVAL; + + spin_lock_irq(¤t->sighand->siglock); + + if (!seccomp_may_assign_mode(seccomp_mode)) + goto out; + +#ifdef TIF_NOTSC + disable_TSC(); +#endif + seccomp_assign_mode(current, seccomp_mode); + ret = 0; + +out: + spin_unlock_irq(¤t->sighand->siglock); + + return ret; +} + +#ifdef CONFIG_SECCOMP_FILTER +/** + * seccomp_set_mode_filter: internal function for setting seccomp filter + * @flags: flags to change filter behavior + * @filter: struct sock_fprog containing filter + * + * This function may be called repeatedly to install additional filters. + * Every filter successfully installed will be evaluated (in reverse order) + * for each system call the task makes. + * + * Once current->seccomp.mode is non-zero, it may not be changed. + * + * Returns 0 on success or -EINVAL on failure. + */ +static long seccomp_set_mode_filter(unsigned int flags, + const char __user *filter) +{ + const unsigned long seccomp_mode = SECCOMP_MODE_FILTER; + struct seccomp_filter *prepared = NULL; + long ret = -EINVAL; + + /* Validate flags. */ + if (flags & ~SECCOMP_FILTER_FLAG_MASK) + return -EINVAL; + + /* Prepare the new filter before holding any locks. */ + prepared = seccomp_prepare_user_filter(filter); + if (IS_ERR(prepared)) + return PTR_ERR(prepared); + + /* + * Make sure we cannot change seccomp or nnp state via TSYNC + * while another thread is in the middle of calling exec. + */ + if (flags & SECCOMP_FILTER_FLAG_TSYNC && + mutex_lock_killable(¤t->signal->cred_guard_mutex)) + goto out_free; + + spin_lock_irq(¤t->sighand->siglock); + + if (!seccomp_may_assign_mode(seccomp_mode)) + goto out; + + ret = seccomp_attach_filter(flags, prepared); + if (ret) + goto out; + /* Do not free the successfully attached filter. */ + prepared = NULL; + + seccomp_assign_mode(current, seccomp_mode); +out: + spin_unlock_irq(¤t->sighand->siglock); + if (flags & SECCOMP_FILTER_FLAG_TSYNC) + mutex_unlock(¤t->signal->cred_guard_mutex); +out_free: + seccomp_filter_free(prepared); + return ret; +} +#else +static inline long seccomp_set_mode_filter(unsigned int flags, + const char __user *filter) +{ + return -EINVAL; +} +#endif + +/* Common entry point for both prctl and syscall. */ +static long do_seccomp(unsigned int op, unsigned int flags, + const char __user *uargs) +{ + switch (op) { + case SECCOMP_SET_MODE_STRICT: + if (flags != 0 || uargs != NULL) + return -EINVAL; + return seccomp_set_mode_strict(); + case SECCOMP_SET_MODE_FILTER: + return seccomp_set_mode_filter(flags, uargs); + default: + return -EINVAL; + } +} + +SYSCALL_DEFINE3(seccomp, unsigned int, op, unsigned int, flags, + const char __user *, uargs) +{ + return do_seccomp(op, flags, uargs); +} + +/** + * prctl_set_seccomp: configures current->seccomp.mode + * @seccomp_mode: requested mode to use + * @filter: optional struct sock_fprog for use with SECCOMP_MODE_FILTER + * + * Returns 0 on success or -EINVAL on failure. + */ +long prctl_set_seccomp(unsigned long seccomp_mode, char __user *filter) +{ + unsigned int op; + char __user *uargs; + + switch (seccomp_mode) { + case SECCOMP_MODE_STRICT: + op = SECCOMP_SET_MODE_STRICT; + /* + * Setting strict mode through prctl always ignored filter, + * so make sure it is always NULL here to pass the internal + * check in do_seccomp(). + */ + uargs = NULL; + break; + case SECCOMP_MODE_FILTER: + op = SECCOMP_SET_MODE_FILTER; + uargs = filter; + break; + default: + return -EINVAL; + } + + /* prctl interface doesn't have flags, so they are always zero. */ + return do_seccomp(op, 0, uargs); +} diff --git a/kernel/kernel/signal.c b/kernel/kernel/signal.c new file mode 100644 index 000000000..7dc2ebee3 --- /dev/null +++ b/kernel/kernel/signal.c @@ -0,0 +1,3775 @@ +/* + * linux/kernel/signal.c + * + * Copyright (C) 1991, 1992 Linus Torvalds + * + * 1997-11-02 Modified for POSIX.1b signals by Richard Henderson + * + * 2003-06-02 Jim Houston - Concurrent Computer Corp. + * Changes to use preallocated sigqueue structures + * to allow signals to be sent reliably. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define CREATE_TRACE_POINTS +#include + +#include +#include +#include +#include +#include +#include "audit.h" /* audit_signal_info() */ + +/* + * SLAB caches for signal bits. + */ + +static struct kmem_cache *sigqueue_cachep; + +int print_fatal_signals __read_mostly; + +static void __user *sig_handler(struct task_struct *t, int sig) +{ + return t->sighand->action[sig - 1].sa.sa_handler; +} + +static int sig_handler_ignored(void __user *handler, int sig) +{ + /* Is it explicitly or implicitly ignored? */ + return handler == SIG_IGN || + (handler == SIG_DFL && sig_kernel_ignore(sig)); +} + +static int sig_task_ignored(struct task_struct *t, int sig, bool force) +{ + void __user *handler; + + handler = sig_handler(t, sig); + + if (unlikely(t->signal->flags & SIGNAL_UNKILLABLE) && + handler == SIG_DFL && !force) + return 1; + + return sig_handler_ignored(handler, sig); +} + +static int sig_ignored(struct task_struct *t, int sig, bool force) +{ + /* + * Blocked signals are never ignored, since the + * signal handler may change by the time it is + * unblocked. + */ + if (sigismember(&t->blocked, sig) || sigismember(&t->real_blocked, sig)) + return 0; + + if (!sig_task_ignored(t, sig, force)) + return 0; + + /* + * Tracers may want to know about even ignored signals. + */ + return !t->ptrace; +} + +/* + * Re-calculate pending state from the set of locally pending + * signals, globally pending signals, and blocked signals. + */ +static inline int has_pending_signals(sigset_t *signal, sigset_t *blocked) +{ + unsigned long ready; + long i; + + switch (_NSIG_WORDS) { + default: + for (i = _NSIG_WORDS, ready = 0; --i >= 0 ;) + ready |= signal->sig[i] &~ blocked->sig[i]; + break; + + case 4: ready = signal->sig[3] &~ blocked->sig[3]; + ready |= signal->sig[2] &~ blocked->sig[2]; + ready |= signal->sig[1] &~ blocked->sig[1]; + ready |= signal->sig[0] &~ blocked->sig[0]; + break; + + case 2: ready = signal->sig[1] &~ blocked->sig[1]; + ready |= signal->sig[0] &~ blocked->sig[0]; + break; + + case 1: ready = signal->sig[0] &~ blocked->sig[0]; + } + return ready != 0; +} + +#define PENDING(p,b) has_pending_signals(&(p)->signal, (b)) + +static int recalc_sigpending_tsk(struct task_struct *t) +{ + if ((t->jobctl & JOBCTL_PENDING_MASK) || + PENDING(&t->pending, &t->blocked) || + PENDING(&t->signal->shared_pending, &t->blocked)) { + set_tsk_thread_flag(t, TIF_SIGPENDING); + return 1; + } + /* + * We must never clear the flag in another thread, or in current + * when it's possible the current syscall is returning -ERESTART*. + * So we don't clear it here, and only callers who know they should do. + */ + return 0; +} + +/* + * After recalculating TIF_SIGPENDING, we need to make sure the task wakes up. + * This is superfluous when called on current, the wakeup is a harmless no-op. + */ +void recalc_sigpending_and_wake(struct task_struct *t) +{ + if (recalc_sigpending_tsk(t)) + signal_wake_up(t, 0); +} + +void recalc_sigpending(void) +{ + if (!recalc_sigpending_tsk(current) && !freezing(current)) + clear_thread_flag(TIF_SIGPENDING); + +} + +/* Given the mask, find the first available signal that should be serviced. */ + +#define SYNCHRONOUS_MASK \ + (sigmask(SIGSEGV) | sigmask(SIGBUS) | sigmask(SIGILL) | \ + sigmask(SIGTRAP) | sigmask(SIGFPE) | sigmask(SIGSYS)) + +int next_signal(struct sigpending *pending, sigset_t *mask) +{ + unsigned long i, *s, *m, x; + int sig = 0; + + s = pending->signal.sig; + m = mask->sig; + + /* + * Handle the first word specially: it contains the + * synchronous signals that need to be dequeued first. + */ + x = *s &~ *m; + if (x) { + if (x & SYNCHRONOUS_MASK) + x &= SYNCHRONOUS_MASK; + sig = ffz(~x) + 1; + return sig; + } + + switch (_NSIG_WORDS) { + default: + for (i = 1; i < _NSIG_WORDS; ++i) { + x = *++s &~ *++m; + if (!x) + continue; + sig = ffz(~x) + i*_NSIG_BPW + 1; + break; + } + break; + + case 2: + x = s[1] &~ m[1]; + if (!x) + break; + sig = ffz(~x) + _NSIG_BPW + 1; + break; + + case 1: + /* Nothing to do */ + break; + } + + return sig; +} + +static inline void print_dropped_signal(int sig) +{ + static DEFINE_RATELIMIT_STATE(ratelimit_state, 5 * HZ, 10); + + if (!print_fatal_signals) + return; + + if (!__ratelimit(&ratelimit_state)) + return; + + printk(KERN_INFO "%s/%d: reached RLIMIT_SIGPENDING, dropped signal %d\n", + current->comm, current->pid, sig); +} + +/** + * task_set_jobctl_pending - set jobctl pending bits + * @task: target task + * @mask: pending bits to set + * + * Clear @mask from @task->jobctl. @mask must be subset of + * %JOBCTL_PENDING_MASK | %JOBCTL_STOP_CONSUME | %JOBCTL_STOP_SIGMASK | + * %JOBCTL_TRAPPING. If stop signo is being set, the existing signo is + * cleared. If @task is already being killed or exiting, this function + * becomes noop. + * + * CONTEXT: + * Must be called with @task->sighand->siglock held. + * + * RETURNS: + * %true if @mask is set, %false if made noop because @task was dying. + */ +bool task_set_jobctl_pending(struct task_struct *task, unsigned int mask) +{ + BUG_ON(mask & ~(JOBCTL_PENDING_MASK | JOBCTL_STOP_CONSUME | + JOBCTL_STOP_SIGMASK | JOBCTL_TRAPPING)); + BUG_ON((mask & JOBCTL_TRAPPING) && !(mask & JOBCTL_PENDING_MASK)); + + if (unlikely(fatal_signal_pending(task) || (task->flags & PF_EXITING))) + return false; + + if (mask & JOBCTL_STOP_SIGMASK) + task->jobctl &= ~JOBCTL_STOP_SIGMASK; + + task->jobctl |= mask; + return true; +} + +/** + * task_clear_jobctl_trapping - clear jobctl trapping bit + * @task: target task + * + * If JOBCTL_TRAPPING is set, a ptracer is waiting for us to enter TRACED. + * Clear it and wake up the ptracer. Note that we don't need any further + * locking. @task->siglock guarantees that @task->parent points to the + * ptracer. + * + * CONTEXT: + * Must be called with @task->sighand->siglock held. + */ +void task_clear_jobctl_trapping(struct task_struct *task) +{ + if (unlikely(task->jobctl & JOBCTL_TRAPPING)) { + task->jobctl &= ~JOBCTL_TRAPPING; + smp_mb(); /* advised by wake_up_bit() */ + wake_up_bit(&task->jobctl, JOBCTL_TRAPPING_BIT); + } +} + +/** + * task_clear_jobctl_pending - clear jobctl pending bits + * @task: target task + * @mask: pending bits to clear + * + * Clear @mask from @task->jobctl. @mask must be subset of + * %JOBCTL_PENDING_MASK. If %JOBCTL_STOP_PENDING is being cleared, other + * STOP bits are cleared together. + * + * If clearing of @mask leaves no stop or trap pending, this function calls + * task_clear_jobctl_trapping(). + * + * CONTEXT: + * Must be called with @task->sighand->siglock held. + */ +void task_clear_jobctl_pending(struct task_struct *task, unsigned int mask) +{ + BUG_ON(mask & ~JOBCTL_PENDING_MASK); + + if (mask & JOBCTL_STOP_PENDING) + mask |= JOBCTL_STOP_CONSUME | JOBCTL_STOP_DEQUEUED; + + task->jobctl &= ~mask; + + if (!(task->jobctl & JOBCTL_PENDING_MASK)) + task_clear_jobctl_trapping(task); +} + +/** + * task_participate_group_stop - participate in a group stop + * @task: task participating in a group stop + * + * @task has %JOBCTL_STOP_PENDING set and is participating in a group stop. + * Group stop states are cleared and the group stop count is consumed if + * %JOBCTL_STOP_CONSUME was set. If the consumption completes the group + * stop, the appropriate %SIGNAL_* flags are set. + * + * CONTEXT: + * Must be called with @task->sighand->siglock held. + * + * RETURNS: + * %true if group stop completion should be notified to the parent, %false + * otherwise. + */ +static bool task_participate_group_stop(struct task_struct *task) +{ + struct signal_struct *sig = task->signal; + bool consume = task->jobctl & JOBCTL_STOP_CONSUME; + + WARN_ON_ONCE(!(task->jobctl & JOBCTL_STOP_PENDING)); + + task_clear_jobctl_pending(task, JOBCTL_STOP_PENDING); + + if (!consume) + return false; + + if (!WARN_ON_ONCE(sig->group_stop_count == 0)) + sig->group_stop_count--; + + /* + * Tell the caller to notify completion iff we are entering into a + * fresh group stop. Read comment in do_signal_stop() for details. + */ + if (!sig->group_stop_count && !(sig->flags & SIGNAL_STOP_STOPPED)) { + sig->flags = SIGNAL_STOP_STOPPED; + return true; + } + return false; +} + +#ifdef __HAVE_ARCH_CMPXCHG +static inline struct sigqueue *get_task_cache(struct task_struct *t) +{ + struct sigqueue *q = t->sigqueue_cache; + + if (cmpxchg(&t->sigqueue_cache, q, NULL) != q) + return NULL; + return q; +} + +static inline int put_task_cache(struct task_struct *t, struct sigqueue *q) +{ + if (cmpxchg(&t->sigqueue_cache, NULL, q) == NULL) + return 0; + return 1; +} + +#else + +static inline struct sigqueue *get_task_cache(struct task_struct *t) +{ + return NULL; +} + +static inline int put_task_cache(struct task_struct *t, struct sigqueue *q) +{ + return 1; +} + +#endif + +/* + * allocate a new signal queue record + * - this may be called without locks if and only if t == current, otherwise an + * appropriate lock must be held to stop the target task from exiting + */ +static struct sigqueue * +__sigqueue_do_alloc(int sig, struct task_struct *t, gfp_t flags, + int override_rlimit, int fromslab) +{ + struct sigqueue *q = NULL; + struct user_struct *user; + + /* + * Protect access to @t credentials. This can go away when all + * callers hold rcu read lock. + */ + rcu_read_lock(); + user = get_uid(__task_cred(t)->user); + atomic_inc(&user->sigpending); + rcu_read_unlock(); + + if (override_rlimit || + atomic_read(&user->sigpending) <= + task_rlimit(t, RLIMIT_SIGPENDING)) { + if (!fromslab) + q = get_task_cache(t); + if (!q) + q = kmem_cache_alloc(sigqueue_cachep, flags); + } else { + print_dropped_signal(sig); + } + + if (unlikely(q == NULL)) { + atomic_dec(&user->sigpending); + free_uid(user); + } else { + INIT_LIST_HEAD(&q->list); + q->flags = 0; + q->user = user; + } + + return q; +} + +static struct sigqueue * +__sigqueue_alloc(int sig, struct task_struct *t, gfp_t flags, + int override_rlimit) +{ + return __sigqueue_do_alloc(sig, t, flags, override_rlimit, 0); +} + +static void __sigqueue_free(struct sigqueue *q) +{ + if (q->flags & SIGQUEUE_PREALLOC) + return; + atomic_dec(&q->user->sigpending); + free_uid(q->user); + kmem_cache_free(sigqueue_cachep, q); +} + +static void sigqueue_free_current(struct sigqueue *q) +{ + struct user_struct *up; + + if (q->flags & SIGQUEUE_PREALLOC) + return; + + up = q->user; + if (rt_prio(current->normal_prio) && !put_task_cache(current, q)) { + atomic_dec(&up->sigpending); + free_uid(up); + } else + __sigqueue_free(q); +} + +void flush_sigqueue(struct sigpending *queue) +{ + struct sigqueue *q; + + sigemptyset(&queue->signal); + while (!list_empty(&queue->list)) { + q = list_entry(queue->list.next, struct sigqueue , list); + list_del_init(&q->list); + __sigqueue_free(q); + } +} + +/* + * Called from __exit_signal. Flush tsk->pending and + * tsk->sigqueue_cache + */ +void flush_task_sigqueue(struct task_struct *tsk) +{ + struct sigqueue *q; + + flush_sigqueue(&tsk->pending); + + q = get_task_cache(tsk); + if (q) + kmem_cache_free(sigqueue_cachep, q); +} + +/* + * Flush all pending signals for a task. + */ +void __flush_signals(struct task_struct *t) +{ + clear_tsk_thread_flag(t, TIF_SIGPENDING); + flush_sigqueue(&t->pending); + flush_sigqueue(&t->signal->shared_pending); +} + +void flush_signals(struct task_struct *t) +{ + unsigned long flags; + + spin_lock_irqsave(&t->sighand->siglock, flags); + __flush_signals(t); + spin_unlock_irqrestore(&t->sighand->siglock, flags); +} + +static void __flush_itimer_signals(struct sigpending *pending) +{ + sigset_t signal, retain; + struct sigqueue *q, *n; + + signal = pending->signal; + sigemptyset(&retain); + + list_for_each_entry_safe(q, n, &pending->list, list) { + int sig = q->info.si_signo; + + if (likely(q->info.si_code != SI_TIMER)) { + sigaddset(&retain, sig); + } else { + sigdelset(&signal, sig); + list_del_init(&q->list); + __sigqueue_free(q); + } + } + + sigorsets(&pending->signal, &signal, &retain); +} + +void flush_itimer_signals(void) +{ + struct task_struct *tsk = current; + unsigned long flags; + + spin_lock_irqsave(&tsk->sighand->siglock, flags); + __flush_itimer_signals(&tsk->pending); + __flush_itimer_signals(&tsk->signal->shared_pending); + spin_unlock_irqrestore(&tsk->sighand->siglock, flags); +} + +void ignore_signals(struct task_struct *t) +{ + int i; + + for (i = 0; i < _NSIG; ++i) + t->sighand->action[i].sa.sa_handler = SIG_IGN; + + flush_signals(t); +} + +/* + * Flush all handlers for a task. + */ + +void +flush_signal_handlers(struct task_struct *t, int force_default) +{ + int i; + struct k_sigaction *ka = &t->sighand->action[0]; + for (i = _NSIG ; i != 0 ; i--) { + if (force_default || ka->sa.sa_handler != SIG_IGN) + ka->sa.sa_handler = SIG_DFL; + ka->sa.sa_flags = 0; +#ifdef __ARCH_HAS_SA_RESTORER + ka->sa.sa_restorer = NULL; +#endif + sigemptyset(&ka->sa.sa_mask); + ka++; + } +} + +int unhandled_signal(struct task_struct *tsk, int sig) +{ + void __user *handler = tsk->sighand->action[sig-1].sa.sa_handler; + if (is_global_init(tsk)) + return 1; + if (handler != SIG_IGN && handler != SIG_DFL) + return 0; + /* if ptraced, let the tracer determine */ + return !tsk->ptrace; +} + +/* + * Notify the system that a driver wants to block all signals for this + * process, and wants to be notified if any signals at all were to be + * sent/acted upon. If the notifier routine returns non-zero, then the + * signal will be acted upon after all. If the notifier routine returns 0, + * then then signal will be blocked. Only one block per process is + * allowed. priv is a pointer to private data that the notifier routine + * can use to determine if the signal should be blocked or not. + */ +void +block_all_signals(int (*notifier)(void *priv), void *priv, sigset_t *mask) +{ + unsigned long flags; + + spin_lock_irqsave(¤t->sighand->siglock, flags); + current->notifier_mask = mask; + current->notifier_data = priv; + current->notifier = notifier; + spin_unlock_irqrestore(¤t->sighand->siglock, flags); +} + +/* Notify the system that blocking has ended. */ + +void +unblock_all_signals(void) +{ + unsigned long flags; + + spin_lock_irqsave(¤t->sighand->siglock, flags); + current->notifier = NULL; + current->notifier_data = NULL; + recalc_sigpending(); + spin_unlock_irqrestore(¤t->sighand->siglock, flags); +} + +static void collect_signal(int sig, struct sigpending *list, siginfo_t *info) +{ + struct sigqueue *q, *first = NULL; + + /* + * Collect the siginfo appropriate to this signal. Check if + * there is another siginfo for the same signal. + */ + list_for_each_entry(q, &list->list, list) { + if (q->info.si_signo == sig) { + if (first) + goto still_pending; + first = q; + } + } + + sigdelset(&list->signal, sig); + + if (first) { +still_pending: + list_del_init(&first->list); + copy_siginfo(info, &first->info); + sigqueue_free_current(first); + } else { + /* + * Ok, it wasn't in the queue. This must be + * a fast-pathed signal or we must have been + * out of queue space. So zero out the info. + */ + info->si_signo = sig; + info->si_errno = 0; + info->si_code = SI_USER; + info->si_pid = 0; + info->si_uid = 0; + } +} + +static int __dequeue_signal(struct sigpending *pending, sigset_t *mask, + siginfo_t *info) +{ + int sig = next_signal(pending, mask); + + if (sig) { + if (current->notifier) { + if (sigismember(current->notifier_mask, sig)) { + if (!(current->notifier)(current->notifier_data)) { + clear_thread_flag(TIF_SIGPENDING); + return 0; + } + } + } + + collect_signal(sig, pending, info); + } + + return sig; +} + +/* + * Dequeue a signal and return the element to the caller, which is + * expected to free it. + * + * All callers have to hold the siglock. + */ +int dequeue_signal(struct task_struct *tsk, sigset_t *mask, siginfo_t *info) +{ + int signr; + + WARN_ON_ONCE(tsk != current); + + /* We only dequeue private signals from ourselves, we don't let + * signalfd steal them + */ + signr = __dequeue_signal(&tsk->pending, mask, info); + if (!signr) { + signr = __dequeue_signal(&tsk->signal->shared_pending, + mask, info); + /* + * itimer signal ? + * + * itimers are process shared and we restart periodic + * itimers in the signal delivery path to prevent DoS + * attacks in the high resolution timer case. This is + * compliant with the old way of self-restarting + * itimers, as the SIGALRM is a legacy signal and only + * queued once. Changing the restart behaviour to + * restart the timer in the signal dequeue path is + * reducing the timer noise on heavy loaded !highres + * systems too. + */ + if (unlikely(signr == SIGALRM)) { + struct hrtimer *tmr = &tsk->signal->real_timer; + + if (!hrtimer_is_queued(tmr) && + tsk->signal->it_real_incr.tv64 != 0) { + hrtimer_forward(tmr, tmr->base->get_time(), + tsk->signal->it_real_incr); + hrtimer_restart(tmr); + } + } + } + + recalc_sigpending(); + if (!signr) + return 0; + + if (unlikely(sig_kernel_stop(signr))) { + /* + * Set a marker that we have dequeued a stop signal. Our + * caller might release the siglock and then the pending + * stop signal it is about to process is no longer in the + * pending bitmasks, but must still be cleared by a SIGCONT + * (and overruled by a SIGKILL). So those cases clear this + * shared flag after we've set it. Note that this flag may + * remain set after the signal we return is ignored or + * handled. That doesn't matter because its only purpose + * is to alert stop-signal processing code when another + * processor has come along and cleared the flag. + */ + current->jobctl |= JOBCTL_STOP_DEQUEUED; + } + if ((info->si_code & __SI_MASK) == __SI_TIMER && info->si_sys_private) { + /* + * Release the siglock to ensure proper locking order + * of timer locks outside of siglocks. Note, we leave + * irqs disabled here, since the posix-timers code is + * about to disable them again anyway. + */ + spin_unlock(&tsk->sighand->siglock); + do_schedule_next_timer(info); + spin_lock(&tsk->sighand->siglock); + } + return signr; +} + +/* + * Tell a process that it has a new active signal.. + * + * NOTE! we rely on the previous spin_lock to + * lock interrupts for us! We can only be called with + * "siglock" held, and the local interrupt must + * have been disabled when that got acquired! + * + * No need to set need_resched since signal event passing + * goes through ->blocked + */ +void signal_wake_up_state(struct task_struct *t, unsigned int state) +{ + set_tsk_thread_flag(t, TIF_SIGPENDING); + /* + * TASK_WAKEKILL also means wake it up in the stopped/traced/killable + * case. We don't check t->state here because there is a race with it + * executing another processor and just now entering stopped state. + * By using wake_up_state, we ensure the process will wake up and + * handle its death signal. + */ + if (!wake_up_state(t, state | TASK_INTERRUPTIBLE)) + kick_process(t); +} + +/* + * Remove signals in mask from the pending set and queue. + * Returns 1 if any signals were found. + * + * All callers must be holding the siglock. + */ +static int flush_sigqueue_mask(sigset_t *mask, struct sigpending *s) +{ + struct sigqueue *q, *n; + sigset_t m; + + sigandsets(&m, mask, &s->signal); + if (sigisemptyset(&m)) + return 0; + + sigandnsets(&s->signal, &s->signal, mask); + list_for_each_entry_safe(q, n, &s->list, list) { + if (sigismember(mask, q->info.si_signo)) { + list_del_init(&q->list); + __sigqueue_free(q); + } + } + return 1; +} + +static inline int is_si_special(const struct siginfo *info) +{ + return info <= SEND_SIG_FORCED; +} + +static inline bool si_fromuser(const struct siginfo *info) +{ + return info == SEND_SIG_NOINFO || + (!is_si_special(info) && SI_FROMUSER(info)); +} + +/* + * called with RCU read lock from check_kill_permission() + */ +static int kill_ok_by_cred(struct task_struct *t) +{ + const struct cred *cred = current_cred(); + const struct cred *tcred = __task_cred(t); + + if (uid_eq(cred->euid, tcred->suid) || + uid_eq(cred->euid, tcred->uid) || + uid_eq(cred->uid, tcred->suid) || + uid_eq(cred->uid, tcred->uid)) + return 1; + + if (ns_capable(tcred->user_ns, CAP_KILL)) + return 1; + + return 0; +} + +/* + * Bad permissions for sending the signal + * - the caller must hold the RCU read lock + */ +static int check_kill_permission(int sig, struct siginfo *info, + struct task_struct *t) +{ + struct pid *sid; + int error; + + if (!valid_signal(sig)) + return -EINVAL; + + if (!si_fromuser(info)) + return 0; + + error = audit_signal_info(sig, t); /* Let audit system see the signal */ + if (error) + return error; + + if (!same_thread_group(current, t) && + !kill_ok_by_cred(t)) { + switch (sig) { + case SIGCONT: + sid = task_session(t); + /* + * We don't return the error if sid == NULL. The + * task was unhashed, the caller must notice this. + */ + if (!sid || sid == task_session(current)) + break; + default: + return -EPERM; + } + } + + return security_task_kill(t, info, sig, 0); +} + +/** + * ptrace_trap_notify - schedule trap to notify ptracer + * @t: tracee wanting to notify tracer + * + * This function schedules sticky ptrace trap which is cleared on the next + * TRAP_STOP to notify ptracer of an event. @t must have been seized by + * ptracer. + * + * If @t is running, STOP trap will be taken. If trapped for STOP and + * ptracer is listening for events, tracee is woken up so that it can + * re-trap for the new event. If trapped otherwise, STOP trap will be + * eventually taken without returning to userland after the existing traps + * are finished by PTRACE_CONT. + * + * CONTEXT: + * Must be called with @task->sighand->siglock held. + */ +static void ptrace_trap_notify(struct task_struct *t) +{ + WARN_ON_ONCE(!(t->ptrace & PT_SEIZED)); + assert_spin_locked(&t->sighand->siglock); + + task_set_jobctl_pending(t, JOBCTL_TRAP_NOTIFY); + ptrace_signal_wake_up(t, t->jobctl & JOBCTL_LISTENING); +} + +/* + * Handle magic process-wide effects of stop/continue signals. Unlike + * the signal actions, these happen immediately at signal-generation + * time regardless of blocking, ignoring, or handling. This does the + * actual continuing for SIGCONT, but not the actual stopping for stop + * signals. The process stop is done as a signal action for SIG_DFL. + * + * Returns true if the signal should be actually delivered, otherwise + * it should be dropped. + */ +static bool prepare_signal(int sig, struct task_struct *p, bool force) +{ + struct signal_struct *signal = p->signal; + struct task_struct *t; + sigset_t flush; + + if (signal->flags & (SIGNAL_GROUP_EXIT | SIGNAL_GROUP_COREDUMP)) { + if (signal->flags & SIGNAL_GROUP_COREDUMP) + return sig == SIGKILL; + /* + * The process is in the middle of dying, nothing to do. + */ + } else if (sig_kernel_stop(sig)) { + /* + * This is a stop signal. Remove SIGCONT from all queues. + */ + siginitset(&flush, sigmask(SIGCONT)); + flush_sigqueue_mask(&flush, &signal->shared_pending); + for_each_thread(p, t) + flush_sigqueue_mask(&flush, &t->pending); + } else if (sig == SIGCONT) { + unsigned int why; + /* + * Remove all stop signals from all queues, wake all threads. + */ + siginitset(&flush, SIG_KERNEL_STOP_MASK); + flush_sigqueue_mask(&flush, &signal->shared_pending); + for_each_thread(p, t) { + flush_sigqueue_mask(&flush, &t->pending); + task_clear_jobctl_pending(t, JOBCTL_STOP_PENDING); + if (likely(!(t->ptrace & PT_SEIZED))) + wake_up_state(t, __TASK_STOPPED); + else + ptrace_trap_notify(t); + } + + /* + * Notify the parent with CLD_CONTINUED if we were stopped. + * + * If we were in the middle of a group stop, we pretend it + * was already finished, and then continued. Since SIGCHLD + * doesn't queue we report only CLD_STOPPED, as if the next + * CLD_CONTINUED was dropped. + */ + why = 0; + if (signal->flags & SIGNAL_STOP_STOPPED) + why |= SIGNAL_CLD_CONTINUED; + else if (signal->group_stop_count) + why |= SIGNAL_CLD_STOPPED; + + if (why) { + /* + * The first thread which returns from do_signal_stop() + * will take ->siglock, notice SIGNAL_CLD_MASK, and + * notify its parent. See get_signal_to_deliver(). + */ + signal->flags = why | SIGNAL_STOP_CONTINUED; + signal->group_stop_count = 0; + signal->group_exit_code = 0; + } + } + + return !sig_ignored(p, sig, force); +} + +/* + * Test if P wants to take SIG. After we've checked all threads with this, + * it's equivalent to finding no threads not blocking SIG. Any threads not + * blocking SIG were ruled out because they are not running and already + * have pending signals. Such threads will dequeue from the shared queue + * as soon as they're available, so putting the signal on the shared queue + * will be equivalent to sending it to one such thread. + */ +static inline int wants_signal(int sig, struct task_struct *p) +{ + if (sigismember(&p->blocked, sig)) + return 0; + if (p->flags & PF_EXITING) + return 0; + if (sig == SIGKILL) + return 1; + if (task_is_stopped_or_traced(p)) + return 0; + return task_curr(p) || !signal_pending(p); +} + +static void complete_signal(int sig, struct task_struct *p, int group) +{ + struct signal_struct *signal = p->signal; + struct task_struct *t; + + /* + * Now find a thread we can wake up to take the signal off the queue. + * + * If the main thread wants the signal, it gets first crack. + * Probably the least surprising to the average bear. + */ + if (wants_signal(sig, p)) + t = p; + else if (!group || thread_group_empty(p)) + /* + * There is just one thread and it does not need to be woken. + * It will dequeue unblocked signals before it runs again. + */ + return; + else { + /* + * Otherwise try to find a suitable thread. + */ + t = signal->curr_target; + while (!wants_signal(sig, t)) { + t = next_thread(t); + if (t == signal->curr_target) + /* + * No thread needs to be woken. + * Any eligible threads will see + * the signal in the queue soon. + */ + return; + } + signal->curr_target = t; + } + + /* + * Found a killable thread. If the signal will be fatal, + * then start taking the whole group down immediately. + */ + if (sig_fatal(p, sig) && + !(signal->flags & (SIGNAL_UNKILLABLE | SIGNAL_GROUP_EXIT)) && + !sigismember(&t->real_blocked, sig) && + (sig == SIGKILL || !t->ptrace)) { + /* + * This signal will be fatal to the whole group. + */ + if (!sig_kernel_coredump(sig)) { + /* + * Start a group exit and wake everybody up. + * This way we don't have other threads + * running and doing things after a slower + * thread has the fatal signal pending. + */ + signal->flags = SIGNAL_GROUP_EXIT; + signal->group_exit_code = sig; + signal->group_stop_count = 0; + t = p; + do { + task_clear_jobctl_pending(t, JOBCTL_PENDING_MASK); + sigaddset(&t->pending.signal, SIGKILL); + signal_wake_up(t, 1); + } while_each_thread(p, t); + return; + } + } + + /* + * The signal is already in the shared-pending queue. + * Tell the chosen thread to wake up and dequeue it. + */ + signal_wake_up(t, sig == SIGKILL); + return; +} + +static inline int legacy_queue(struct sigpending *signals, int sig) +{ + return (sig < SIGRTMIN) && sigismember(&signals->signal, sig); +} + +#ifdef CONFIG_USER_NS +static inline void userns_fixup_signal_uid(struct siginfo *info, struct task_struct *t) +{ + if (current_user_ns() == task_cred_xxx(t, user_ns)) + return; + + if (SI_FROMKERNEL(info)) + return; + + rcu_read_lock(); + info->si_uid = from_kuid_munged(task_cred_xxx(t, user_ns), + make_kuid(current_user_ns(), info->si_uid)); + rcu_read_unlock(); +} +#else +static inline void userns_fixup_signal_uid(struct siginfo *info, struct task_struct *t) +{ + return; +} +#endif + +static int __send_signal(int sig, struct siginfo *info, struct task_struct *t, + int group, int from_ancestor_ns) +{ + struct sigpending *pending; + struct sigqueue *q; + int override_rlimit; + int ret = 0, result; + + assert_spin_locked(&t->sighand->siglock); + + result = TRACE_SIGNAL_IGNORED; + if (!prepare_signal(sig, t, + from_ancestor_ns || (info == SEND_SIG_FORCED))) + goto ret; + + pending = group ? &t->signal->shared_pending : &t->pending; + /* + * Short-circuit ignored signals and support queuing + * exactly one non-rt signal, so that we can get more + * detailed information about the cause of the signal. + */ + result = TRACE_SIGNAL_ALREADY_PENDING; + if (legacy_queue(pending, sig)) + goto ret; + + result = TRACE_SIGNAL_DELIVERED; + /* + * fast-pathed signals for kernel-internal things like SIGSTOP + * or SIGKILL. + */ + if (info == SEND_SIG_FORCED) + goto out_set; + + /* + * Real-time signals must be queued if sent by sigqueue, or + * some other real-time mechanism. It is implementation + * defined whether kill() does so. We attempt to do so, on + * the principle of least surprise, but since kill is not + * allowed to fail with EAGAIN when low on memory we just + * make sure at least one signal gets delivered and don't + * pass on the info struct. + */ + if (sig < SIGRTMIN) + override_rlimit = (is_si_special(info) || info->si_code >= 0); + else + override_rlimit = 0; + + q = __sigqueue_alloc(sig, t, GFP_ATOMIC | __GFP_NOTRACK_FALSE_POSITIVE, + override_rlimit); + if (q) { + list_add_tail(&q->list, &pending->list); + switch ((unsigned long) info) { + case (unsigned long) SEND_SIG_NOINFO: + q->info.si_signo = sig; + q->info.si_errno = 0; + q->info.si_code = SI_USER; + q->info.si_pid = task_tgid_nr_ns(current, + task_active_pid_ns(t)); + q->info.si_uid = from_kuid_munged(current_user_ns(), current_uid()); + break; + case (unsigned long) SEND_SIG_PRIV: + q->info.si_signo = sig; + q->info.si_errno = 0; + q->info.si_code = SI_KERNEL; + q->info.si_pid = 0; + q->info.si_uid = 0; + break; + default: + copy_siginfo(&q->info, info); + if (from_ancestor_ns) + q->info.si_pid = 0; + break; + } + + userns_fixup_signal_uid(&q->info, t); + + } else if (!is_si_special(info)) { + if (sig >= SIGRTMIN && info->si_code != SI_USER) { + /* + * Queue overflow, abort. We may abort if the + * signal was rt and sent by user using something + * other than kill(). + */ + result = TRACE_SIGNAL_OVERFLOW_FAIL; + ret = -EAGAIN; + goto ret; + } else { + /* + * This is a silent loss of information. We still + * send the signal, but the *info bits are lost. + */ + result = TRACE_SIGNAL_LOSE_INFO; + } + } + +out_set: + signalfd_notify(t, sig); + sigaddset(&pending->signal, sig); + complete_signal(sig, t, group); +ret: + trace_signal_generate(sig, info, t, group, result); + return ret; +} + +static int send_signal(int sig, struct siginfo *info, struct task_struct *t, + int group) +{ + int from_ancestor_ns = 0; + +#ifdef CONFIG_PID_NS + from_ancestor_ns = si_fromuser(info) && + !task_pid_nr_ns(current, task_active_pid_ns(t)); +#endif + + return __send_signal(sig, info, t, group, from_ancestor_ns); +} + +static void print_fatal_signal(int signr) +{ + struct pt_regs *regs = signal_pt_regs(); + printk(KERN_INFO "potentially unexpected fatal signal %d.\n", signr); + +#if defined(__i386__) && !defined(__arch_um__) + printk(KERN_INFO "code at %08lx: ", regs->ip); + { + int i; + for (i = 0; i < 16; i++) { + unsigned char insn; + + if (get_user(insn, (unsigned char *)(regs->ip + i))) + break; + printk(KERN_CONT "%02x ", insn); + } + } + printk(KERN_CONT "\n"); +#endif + preempt_disable(); + show_regs(regs); + preempt_enable(); +} + +static int __init setup_print_fatal_signals(char *str) +{ + get_option (&str, &print_fatal_signals); + + return 1; +} + +__setup("print-fatal-signals=", setup_print_fatal_signals); + +int +__group_send_sig_info(int sig, struct siginfo *info, struct task_struct *p) +{ + return send_signal(sig, info, p, 1); +} + +static int +specific_send_sig_info(int sig, struct siginfo *info, struct task_struct *t) +{ + return send_signal(sig, info, t, 0); +} + +int do_send_sig_info(int sig, struct siginfo *info, struct task_struct *p, + bool group) +{ + unsigned long flags; + int ret = -ESRCH; + + if (lock_task_sighand(p, &flags)) { + ret = send_signal(sig, info, p, group); + unlock_task_sighand(p, &flags); + } + + return ret; +} + +/* + * Force a signal that the process can't ignore: if necessary + * we unblock the signal and change any SIG_IGN to SIG_DFL. + * + * Note: If we unblock the signal, we always reset it to SIG_DFL, + * since we do not want to have a signal handler that was blocked + * be invoked when user space had explicitly blocked it. + * + * We don't want to have recursive SIGSEGV's etc, for example, + * that is why we also clear SIGNAL_UNKILLABLE. + */ +static int +do_force_sig_info(int sig, struct siginfo *info, struct task_struct *t) +{ + unsigned long int flags; + int ret, blocked, ignored; + struct k_sigaction *action; + + spin_lock_irqsave(&t->sighand->siglock, flags); + action = &t->sighand->action[sig-1]; + ignored = action->sa.sa_handler == SIG_IGN; + blocked = sigismember(&t->blocked, sig); + if (blocked || ignored) { + action->sa.sa_handler = SIG_DFL; + if (blocked) { + sigdelset(&t->blocked, sig); + recalc_sigpending_and_wake(t); + } + } + if (action->sa.sa_handler == SIG_DFL) + t->signal->flags &= ~SIGNAL_UNKILLABLE; + ret = specific_send_sig_info(sig, info, t); + spin_unlock_irqrestore(&t->sighand->siglock, flags); + + return ret; +} + +int force_sig_info(int sig, struct siginfo *info, struct task_struct *t) +{ +/* + * On some archs, PREEMPT_RT has to delay sending a signal from a trap + * since it can not enable preemption, and the signal code's spin_locks + * turn into mutexes. Instead, it must set TIF_NOTIFY_RESUME which will + * send the signal on exit of the trap. + */ +#ifdef ARCH_RT_DELAYS_SIGNAL_SEND + if (in_atomic()) { + if (WARN_ON_ONCE(t != current)) + return 0; + if (WARN_ON_ONCE(t->forced_info.si_signo)) + return 0; + + if (is_si_special(info)) { + WARN_ON_ONCE(info != SEND_SIG_PRIV); + t->forced_info.si_signo = sig; + t->forced_info.si_errno = 0; + t->forced_info.si_code = SI_KERNEL; + t->forced_info.si_pid = 0; + t->forced_info.si_uid = 0; + } else { + t->forced_info = *info; + } + + set_tsk_thread_flag(t, TIF_NOTIFY_RESUME); + return 0; + } +#endif + return do_force_sig_info(sig, info, t); +} + +/* + * Nuke all other threads in the group. + */ +int zap_other_threads(struct task_struct *p) +{ + struct task_struct *t = p; + int count = 0; + + p->signal->group_stop_count = 0; + + while_each_thread(p, t) { + task_clear_jobctl_pending(t, JOBCTL_PENDING_MASK); + count++; + + /* Don't bother with already dead threads */ + if (t->exit_state) + continue; + sigaddset(&t->pending.signal, SIGKILL); + signal_wake_up(t, 1); + } + + return count; +} + +struct sighand_struct *__lock_task_sighand(struct task_struct *tsk, + unsigned long *flags) +{ + struct sighand_struct *sighand; + + for (;;) { + /* + * Disable interrupts early to avoid deadlocks. + * See rcu_read_unlock() comment header for details. + */ + local_irq_save_nort(*flags); + rcu_read_lock(); + sighand = rcu_dereference(tsk->sighand); + if (unlikely(sighand == NULL)) { + rcu_read_unlock(); + local_irq_restore_nort(*flags); + break; + } + /* + * This sighand can be already freed and even reused, but + * we rely on SLAB_DESTROY_BY_RCU and sighand_ctor() which + * initializes ->siglock: this slab can't go away, it has + * the same object type, ->siglock can't be reinitialized. + * + * We need to ensure that tsk->sighand is still the same + * after we take the lock, we can race with de_thread() or + * __exit_signal(). In the latter case the next iteration + * must see ->sighand == NULL. + */ + spin_lock(&sighand->siglock); + if (likely(sighand == tsk->sighand)) { + rcu_read_unlock(); + break; + } + spin_unlock(&sighand->siglock); + rcu_read_unlock(); + local_irq_restore_nort(*flags); + } + + return sighand; +} + +/* + * send signal info to all the members of a group + */ +int group_send_sig_info(int sig, struct siginfo *info, struct task_struct *p) +{ + int ret; + + rcu_read_lock(); + ret = check_kill_permission(sig, info, p); + rcu_read_unlock(); + + if (!ret && sig) + ret = do_send_sig_info(sig, info, p, true); + + return ret; +} + +/* + * __kill_pgrp_info() sends a signal to a process group: this is what the tty + * control characters do (^C, ^Z etc) + * - the caller must hold at least a readlock on tasklist_lock + */ +int __kill_pgrp_info(int sig, struct siginfo *info, struct pid *pgrp) +{ + struct task_struct *p = NULL; + int retval, success; + + success = 0; + retval = -ESRCH; + do_each_pid_task(pgrp, PIDTYPE_PGID, p) { + int err = group_send_sig_info(sig, info, p); + success |= !err; + retval = err; + } while_each_pid_task(pgrp, PIDTYPE_PGID, p); + return success ? 0 : retval; +} + +int kill_pid_info(int sig, struct siginfo *info, struct pid *pid) +{ + int error = -ESRCH; + struct task_struct *p; + + for (;;) { + rcu_read_lock(); + p = pid_task(pid, PIDTYPE_PID); + if (p) + error = group_send_sig_info(sig, info, p); + rcu_read_unlock(); + if (likely(!p || error != -ESRCH)) + return error; + + /* + * The task was unhashed in between, try again. If it + * is dead, pid_task() will return NULL, if we race with + * de_thread() it will find the new leader. + */ + } +} + +int kill_proc_info(int sig, struct siginfo *info, pid_t pid) +{ + int error; + rcu_read_lock(); + error = kill_pid_info(sig, info, find_vpid(pid)); + rcu_read_unlock(); + return error; +} + +static int kill_as_cred_perm(const struct cred *cred, + struct task_struct *target) +{ + const struct cred *pcred = __task_cred(target); + if (!uid_eq(cred->euid, pcred->suid) && !uid_eq(cred->euid, pcred->uid) && + !uid_eq(cred->uid, pcred->suid) && !uid_eq(cred->uid, pcred->uid)) + return 0; + return 1; +} + +/* like kill_pid_info(), but doesn't use uid/euid of "current" */ +int kill_pid_info_as_cred(int sig, struct siginfo *info, struct pid *pid, + const struct cred *cred, u32 secid) +{ + int ret = -EINVAL; + struct task_struct *p; + unsigned long flags; + + if (!valid_signal(sig)) + return ret; + + rcu_read_lock(); + p = pid_task(pid, PIDTYPE_PID); + if (!p) { + ret = -ESRCH; + goto out_unlock; + } + if (si_fromuser(info) && !kill_as_cred_perm(cred, p)) { + ret = -EPERM; + goto out_unlock; + } + ret = security_task_kill(p, info, sig, secid); + if (ret) + goto out_unlock; + + if (sig) { + if (lock_task_sighand(p, &flags)) { + ret = __send_signal(sig, info, p, 1, 0); + unlock_task_sighand(p, &flags); + } else + ret = -ESRCH; + } +out_unlock: + rcu_read_unlock(); + return ret; +} +EXPORT_SYMBOL_GPL(kill_pid_info_as_cred); + +/* + * kill_something_info() interprets pid in interesting ways just like kill(2). + * + * POSIX specifies that kill(-1,sig) is unspecified, but what we have + * is probably wrong. Should make it like BSD or SYSV. + */ + +static int kill_something_info(int sig, struct siginfo *info, pid_t pid) +{ + int ret; + + if (pid > 0) { + rcu_read_lock(); + ret = kill_pid_info(sig, info, find_vpid(pid)); + rcu_read_unlock(); + return ret; + } + + read_lock(&tasklist_lock); + if (pid != -1) { + ret = __kill_pgrp_info(sig, info, + pid ? find_vpid(-pid) : task_pgrp(current)); + } else { + int retval = 0, count = 0; + struct task_struct * p; + + for_each_process(p) { + if (task_pid_vnr(p) > 1 && + !same_thread_group(p, current)) { + int err = group_send_sig_info(sig, info, p); + ++count; + if (err != -EPERM) + retval = err; + } + } + ret = count ? retval : -ESRCH; + } + read_unlock(&tasklist_lock); + + return ret; +} + +/* + * These are for backward compatibility with the rest of the kernel source. + */ + +int send_sig_info(int sig, struct siginfo *info, struct task_struct *p) +{ + /* + * Make sure legacy kernel users don't send in bad values + * (normal paths check this in check_kill_permission). + */ + if (!valid_signal(sig)) + return -EINVAL; + + return do_send_sig_info(sig, info, p, false); +} + +#define __si_special(priv) \ + ((priv) ? SEND_SIG_PRIV : SEND_SIG_NOINFO) + +int +send_sig(int sig, struct task_struct *p, int priv) +{ + return send_sig_info(sig, __si_special(priv), p); +} + +void +force_sig(int sig, struct task_struct *p) +{ + force_sig_info(sig, SEND_SIG_PRIV, p); +} + +/* + * When things go south during signal handling, we + * will force a SIGSEGV. And if the signal that caused + * the problem was already a SIGSEGV, we'll want to + * make sure we don't even try to deliver the signal.. + */ +int +force_sigsegv(int sig, struct task_struct *p) +{ + if (sig == SIGSEGV) { + unsigned long flags; + spin_lock_irqsave(&p->sighand->siglock, flags); + p->sighand->action[sig - 1].sa.sa_handler = SIG_DFL; + spin_unlock_irqrestore(&p->sighand->siglock, flags); + } + force_sig(SIGSEGV, p); + return 0; +} + +int kill_pgrp(struct pid *pid, int sig, int priv) +{ + int ret; + + read_lock(&tasklist_lock); + ret = __kill_pgrp_info(sig, __si_special(priv), pid); + read_unlock(&tasklist_lock); + + return ret; +} +EXPORT_SYMBOL(kill_pgrp); + +int kill_pid(struct pid *pid, int sig, int priv) +{ + return kill_pid_info(sig, __si_special(priv), pid); +} +EXPORT_SYMBOL(kill_pid); + +/* + * These functions support sending signals using preallocated sigqueue + * structures. This is needed "because realtime applications cannot + * afford to lose notifications of asynchronous events, like timer + * expirations or I/O completions". In the case of POSIX Timers + * we allocate the sigqueue structure from the timer_create. If this + * allocation fails we are able to report the failure to the application + * with an EAGAIN error. + */ +struct sigqueue *sigqueue_alloc(void) +{ + /* Preallocated sigqueue objects always from the slabcache ! */ + struct sigqueue *q = __sigqueue_do_alloc(-1, current, GFP_KERNEL, 0, 1); + + if (q) + q->flags |= SIGQUEUE_PREALLOC; + + return q; +} + +void sigqueue_free(struct sigqueue *q) +{ + unsigned long flags; + spinlock_t *lock = ¤t->sighand->siglock; + + BUG_ON(!(q->flags & SIGQUEUE_PREALLOC)); + /* + * We must hold ->siglock while testing q->list + * to serialize with collect_signal() or with + * __exit_signal()->flush_sigqueue(). + */ + spin_lock_irqsave(lock, flags); + q->flags &= ~SIGQUEUE_PREALLOC; + /* + * If it is queued it will be freed when dequeued, + * like the "regular" sigqueue. + */ + if (!list_empty(&q->list)) + q = NULL; + spin_unlock_irqrestore(lock, flags); + + if (q) + __sigqueue_free(q); +} + +int send_sigqueue(struct sigqueue *q, struct task_struct *t, int group) +{ + int sig = q->info.si_signo; + struct sigpending *pending; + unsigned long flags; + int ret, result; + + BUG_ON(!(q->flags & SIGQUEUE_PREALLOC)); + + ret = -1; + if (!likely(lock_task_sighand(t, &flags))) + goto ret; + + ret = 1; /* the signal is ignored */ + result = TRACE_SIGNAL_IGNORED; + if (!prepare_signal(sig, t, false)) + goto out; + + ret = 0; + if (unlikely(!list_empty(&q->list))) { + /* + * If an SI_TIMER entry is already queue just increment + * the overrun count. + */ + BUG_ON(q->info.si_code != SI_TIMER); + q->info.si_overrun++; + result = TRACE_SIGNAL_ALREADY_PENDING; + goto out; + } + q->info.si_overrun = 0; + + signalfd_notify(t, sig); + pending = group ? &t->signal->shared_pending : &t->pending; + list_add_tail(&q->list, &pending->list); + sigaddset(&pending->signal, sig); + complete_signal(sig, t, group); + result = TRACE_SIGNAL_DELIVERED; +out: + trace_signal_generate(sig, &q->info, t, group, result); + unlock_task_sighand(t, &flags); +ret: + return ret; +} + +/* + * Let a parent know about the death of a child. + * For a stopped/continued status change, use do_notify_parent_cldstop instead. + * + * Returns true if our parent ignored us and so we've switched to + * self-reaping. + */ +bool do_notify_parent(struct task_struct *tsk, int sig) +{ + struct siginfo info; + unsigned long flags; + struct sighand_struct *psig; + bool autoreap = false; + cputime_t utime, stime; + + BUG_ON(sig == -1); + + /* do_notify_parent_cldstop should have been called instead. */ + BUG_ON(task_is_stopped_or_traced(tsk)); + + BUG_ON(!tsk->ptrace && + (tsk->group_leader != tsk || !thread_group_empty(tsk))); + + if (sig != SIGCHLD) { + /* + * This is only possible if parent == real_parent. + * Check if it has changed security domain. + */ + if (tsk->parent_exec_id != tsk->parent->self_exec_id) + sig = SIGCHLD; + } + + info.si_signo = sig; + info.si_errno = 0; + /* + * We are under tasklist_lock here so our parent is tied to + * us and cannot change. + * + * task_active_pid_ns will always return the same pid namespace + * until a task passes through release_task. + * + * write_lock() currently calls preempt_disable() which is the + * same as rcu_read_lock(), but according to Oleg, this is not + * correct to rely on this + */ + rcu_read_lock(); + info.si_pid = task_pid_nr_ns(tsk, task_active_pid_ns(tsk->parent)); + info.si_uid = from_kuid_munged(task_cred_xxx(tsk->parent, user_ns), + task_uid(tsk)); + rcu_read_unlock(); + + task_cputime(tsk, &utime, &stime); + info.si_utime = cputime_to_clock_t(utime + tsk->signal->utime); + info.si_stime = cputime_to_clock_t(stime + tsk->signal->stime); + + info.si_status = tsk->exit_code & 0x7f; + if (tsk->exit_code & 0x80) + info.si_code = CLD_DUMPED; + else if (tsk->exit_code & 0x7f) + info.si_code = CLD_KILLED; + else { + info.si_code = CLD_EXITED; + info.si_status = tsk->exit_code >> 8; + } + + psig = tsk->parent->sighand; + spin_lock_irqsave(&psig->siglock, flags); + if (!tsk->ptrace && sig == SIGCHLD && + (psig->action[SIGCHLD-1].sa.sa_handler == SIG_IGN || + (psig->action[SIGCHLD-1].sa.sa_flags & SA_NOCLDWAIT))) { + /* + * We are exiting and our parent doesn't care. POSIX.1 + * defines special semantics for setting SIGCHLD to SIG_IGN + * or setting the SA_NOCLDWAIT flag: we should be reaped + * automatically and not left for our parent's wait4 call. + * Rather than having the parent do it as a magic kind of + * signal handler, we just set this to tell do_exit that we + * can be cleaned up without becoming a zombie. Note that + * we still call __wake_up_parent in this case, because a + * blocked sys_wait4 might now return -ECHILD. + * + * Whether we send SIGCHLD or not for SA_NOCLDWAIT + * is implementation-defined: we do (if you don't want + * it, just use SIG_IGN instead). + */ + autoreap = true; + if (psig->action[SIGCHLD-1].sa.sa_handler == SIG_IGN) + sig = 0; + } + if (valid_signal(sig) && sig) + __group_send_sig_info(sig, &info, tsk->parent); + __wake_up_parent(tsk, tsk->parent); + spin_unlock_irqrestore(&psig->siglock, flags); + + return autoreap; +} + +/** + * do_notify_parent_cldstop - notify parent of stopped/continued state change + * @tsk: task reporting the state change + * @for_ptracer: the notification is for ptracer + * @why: CLD_{CONTINUED|STOPPED|TRAPPED} to report + * + * Notify @tsk's parent that the stopped/continued state has changed. If + * @for_ptracer is %false, @tsk's group leader notifies to its real parent. + * If %true, @tsk reports to @tsk->parent which should be the ptracer. + * + * CONTEXT: + * Must be called with tasklist_lock at least read locked. + */ +static void do_notify_parent_cldstop(struct task_struct *tsk, + bool for_ptracer, int why) +{ + struct siginfo info; + unsigned long flags; + struct task_struct *parent; + struct sighand_struct *sighand; + cputime_t utime, stime; + + if (for_ptracer) { + parent = tsk->parent; + } else { + tsk = tsk->group_leader; + parent = tsk->real_parent; + } + + info.si_signo = SIGCHLD; + info.si_errno = 0; + /* + * see comment in do_notify_parent() about the following 4 lines + */ + rcu_read_lock(); + info.si_pid = task_pid_nr_ns(tsk, task_active_pid_ns(parent)); + info.si_uid = from_kuid_munged(task_cred_xxx(parent, user_ns), task_uid(tsk)); + rcu_read_unlock(); + + task_cputime(tsk, &utime, &stime); + info.si_utime = cputime_to_clock_t(utime); + info.si_stime = cputime_to_clock_t(stime); + + info.si_code = why; + switch (why) { + case CLD_CONTINUED: + info.si_status = SIGCONT; + break; + case CLD_STOPPED: + info.si_status = tsk->signal->group_exit_code & 0x7f; + break; + case CLD_TRAPPED: + info.si_status = tsk->exit_code & 0x7f; + break; + default: + BUG(); + } + + sighand = parent->sighand; + spin_lock_irqsave(&sighand->siglock, flags); + if (sighand->action[SIGCHLD-1].sa.sa_handler != SIG_IGN && + !(sighand->action[SIGCHLD-1].sa.sa_flags & SA_NOCLDSTOP)) + __group_send_sig_info(SIGCHLD, &info, parent); + /* + * Even if SIGCHLD is not generated, we must wake up wait4 calls. + */ + __wake_up_parent(tsk, parent); + spin_unlock_irqrestore(&sighand->siglock, flags); +} + +static inline int may_ptrace_stop(void) +{ + if (!likely(current->ptrace)) + return 0; + /* + * Are we in the middle of do_coredump? + * If so and our tracer is also part of the coredump stopping + * is a deadlock situation, and pointless because our tracer + * is dead so don't allow us to stop. + * If SIGKILL was already sent before the caller unlocked + * ->siglock we must see ->core_state != NULL. Otherwise it + * is safe to enter schedule(). + * + * This is almost outdated, a task with the pending SIGKILL can't + * block in TASK_TRACED. But PTRACE_EVENT_EXIT can be reported + * after SIGKILL was already dequeued. + */ + if (unlikely(current->mm->core_state) && + unlikely(current->mm == current->parent->mm)) + return 0; + + return 1; +} + +/* + * Return non-zero if there is a SIGKILL that should be waking us up. + * Called with the siglock held. + */ +static int sigkill_pending(struct task_struct *tsk) +{ + return sigismember(&tsk->pending.signal, SIGKILL) || + sigismember(&tsk->signal->shared_pending.signal, SIGKILL); +} + +/* + * This must be called with current->sighand->siglock held. + * + * This should be the path for all ptrace stops. + * We always set current->last_siginfo while stopped here. + * That makes it a way to test a stopped process for + * being ptrace-stopped vs being job-control-stopped. + * + * If we actually decide not to stop at all because the tracer + * is gone, we keep current->exit_code unless clear_code. + */ +static void ptrace_stop(int exit_code, int why, int clear_code, siginfo_t *info) + __releases(¤t->sighand->siglock) + __acquires(¤t->sighand->siglock) +{ + bool gstop_done = false; + + if (arch_ptrace_stop_needed(exit_code, info)) { + /* + * The arch code has something special to do before a + * ptrace stop. This is allowed to block, e.g. for faults + * on user stack pages. We can't keep the siglock while + * calling arch_ptrace_stop, so we must release it now. + * To preserve proper semantics, we must do this before + * any signal bookkeeping like checking group_stop_count. + * Meanwhile, a SIGKILL could come in before we retake the + * siglock. That must prevent us from sleeping in TASK_TRACED. + * So after regaining the lock, we must check for SIGKILL. + */ + spin_unlock_irq(¤t->sighand->siglock); + arch_ptrace_stop(exit_code, info); + spin_lock_irq(¤t->sighand->siglock); + if (sigkill_pending(current)) + return; + } + + /* + * We're committing to trapping. TRACED should be visible before + * TRAPPING is cleared; otherwise, the tracer might fail do_wait(). + * Also, transition to TRACED and updates to ->jobctl should be + * atomic with respect to siglock and should be done after the arch + * hook as siglock is released and regrabbed across it. + */ + set_current_state(TASK_TRACED); + + current->last_siginfo = info; + current->exit_code = exit_code; + + /* + * If @why is CLD_STOPPED, we're trapping to participate in a group + * stop. Do the bookkeeping. Note that if SIGCONT was delievered + * across siglock relocks since INTERRUPT was scheduled, PENDING + * could be clear now. We act as if SIGCONT is received after + * TASK_TRACED is entered - ignore it. + */ + if (why == CLD_STOPPED && (current->jobctl & JOBCTL_STOP_PENDING)) + gstop_done = task_participate_group_stop(current); + + /* any trap clears pending STOP trap, STOP trap clears NOTIFY */ + task_clear_jobctl_pending(current, JOBCTL_TRAP_STOP); + if (info && info->si_code >> 8 == PTRACE_EVENT_STOP) + task_clear_jobctl_pending(current, JOBCTL_TRAP_NOTIFY); + + /* entering a trap, clear TRAPPING */ + task_clear_jobctl_trapping(current); + + spin_unlock_irq(¤t->sighand->siglock); + read_lock(&tasklist_lock); + if (may_ptrace_stop()) { + /* + * Notify parents of the stop. + * + * While ptraced, there are two parents - the ptracer and + * the real_parent of the group_leader. The ptracer should + * know about every stop while the real parent is only + * interested in the completion of group stop. The states + * for the two don't interact with each other. Notify + * separately unless they're gonna be duplicates. + */ + do_notify_parent_cldstop(current, true, why); + if (gstop_done && ptrace_reparented(current)) + do_notify_parent_cldstop(current, false, why); + + read_unlock(&tasklist_lock); + freezable_schedule(); + } else { + /* + * By the time we got the lock, our tracer went away. + * Don't drop the lock yet, another tracer may come. + * + * If @gstop_done, the ptracer went away between group stop + * completion and here. During detach, it would have set + * JOBCTL_STOP_PENDING on us and we'll re-enter + * TASK_STOPPED in do_signal_stop() on return, so notifying + * the real parent of the group stop completion is enough. + */ + if (gstop_done) + do_notify_parent_cldstop(current, false, why); + + /* tasklist protects us from ptrace_freeze_traced() */ + __set_current_state(TASK_RUNNING); + if (clear_code) + current->exit_code = 0; + read_unlock(&tasklist_lock); + } + + /* + * We are back. Now reacquire the siglock before touching + * last_siginfo, so that we are sure to have synchronized with + * any signal-sending on another CPU that wants to examine it. + */ + spin_lock_irq(¤t->sighand->siglock); + current->last_siginfo = NULL; + + /* LISTENING can be set only during STOP traps, clear it */ + current->jobctl &= ~JOBCTL_LISTENING; + + /* + * Queued signals ignored us while we were stopped for tracing. + * So check for any that we should take before resuming user mode. + * This sets TIF_SIGPENDING, but never clears it. + */ + recalc_sigpending_tsk(current); +} + +static void ptrace_do_notify(int signr, int exit_code, int why) +{ + siginfo_t info; + + memset(&info, 0, sizeof info); + info.si_signo = signr; + info.si_code = exit_code; + info.si_pid = task_pid_vnr(current); + info.si_uid = from_kuid_munged(current_user_ns(), current_uid()); + + /* Let the debugger run. */ + ptrace_stop(exit_code, why, 1, &info); +} + +void ptrace_notify(int exit_code) +{ + BUG_ON((exit_code & (0x7f | ~0xffff)) != SIGTRAP); + if (unlikely(current->task_works)) + task_work_run(); + + spin_lock_irq(¤t->sighand->siglock); + ptrace_do_notify(SIGTRAP, exit_code, CLD_TRAPPED); + spin_unlock_irq(¤t->sighand->siglock); +} + +/** + * do_signal_stop - handle group stop for SIGSTOP and other stop signals + * @signr: signr causing group stop if initiating + * + * If %JOBCTL_STOP_PENDING is not set yet, initiate group stop with @signr + * and participate in it. If already set, participate in the existing + * group stop. If participated in a group stop (and thus slept), %true is + * returned with siglock released. + * + * If ptraced, this function doesn't handle stop itself. Instead, + * %JOBCTL_TRAP_STOP is scheduled and %false is returned with siglock + * untouched. The caller must ensure that INTERRUPT trap handling takes + * places afterwards. + * + * CONTEXT: + * Must be called with @current->sighand->siglock held, which is released + * on %true return. + * + * RETURNS: + * %false if group stop is already cancelled or ptrace trap is scheduled. + * %true if participated in group stop. + */ +static bool do_signal_stop(int signr) + __releases(¤t->sighand->siglock) +{ + struct signal_struct *sig = current->signal; + + if (!(current->jobctl & JOBCTL_STOP_PENDING)) { + unsigned int gstop = JOBCTL_STOP_PENDING | JOBCTL_STOP_CONSUME; + struct task_struct *t; + + /* signr will be recorded in task->jobctl for retries */ + WARN_ON_ONCE(signr & ~JOBCTL_STOP_SIGMASK); + + if (!likely(current->jobctl & JOBCTL_STOP_DEQUEUED) || + unlikely(signal_group_exit(sig))) + return false; + /* + * There is no group stop already in progress. We must + * initiate one now. + * + * While ptraced, a task may be resumed while group stop is + * still in effect and then receive a stop signal and + * initiate another group stop. This deviates from the + * usual behavior as two consecutive stop signals can't + * cause two group stops when !ptraced. That is why we + * also check !task_is_stopped(t) below. + * + * The condition can be distinguished by testing whether + * SIGNAL_STOP_STOPPED is already set. Don't generate + * group_exit_code in such case. + * + * This is not necessary for SIGNAL_STOP_CONTINUED because + * an intervening stop signal is required to cause two + * continued events regardless of ptrace. + */ + if (!(sig->flags & SIGNAL_STOP_STOPPED)) + sig->group_exit_code = signr; + + sig->group_stop_count = 0; + + if (task_set_jobctl_pending(current, signr | gstop)) + sig->group_stop_count++; + + t = current; + while_each_thread(current, t) { + /* + * Setting state to TASK_STOPPED for a group + * stop is always done with the siglock held, + * so this check has no races. + */ + if (!task_is_stopped(t) && + task_set_jobctl_pending(t, signr | gstop)) { + sig->group_stop_count++; + if (likely(!(t->ptrace & PT_SEIZED))) + signal_wake_up(t, 0); + else + ptrace_trap_notify(t); + } + } + } + + if (likely(!current->ptrace)) { + int notify = 0; + + /* + * If there are no other threads in the group, or if there + * is a group stop in progress and we are the last to stop, + * report to the parent. + */ + if (task_participate_group_stop(current)) + notify = CLD_STOPPED; + + __set_current_state(TASK_STOPPED); + spin_unlock_irq(¤t->sighand->siglock); + + /* + * Notify the parent of the group stop completion. Because + * we're not holding either the siglock or tasklist_lock + * here, ptracer may attach inbetween; however, this is for + * group stop and should always be delivered to the real + * parent of the group leader. The new ptracer will get + * its notification when this task transitions into + * TASK_TRACED. + */ + if (notify) { + read_lock(&tasklist_lock); + do_notify_parent_cldstop(current, false, notify); + read_unlock(&tasklist_lock); + } + + /* Now we don't run again until woken by SIGCONT or SIGKILL */ + freezable_schedule(); + return true; + } else { + /* + * While ptraced, group stop is handled by STOP trap. + * Schedule it and let the caller deal with it. + */ + task_set_jobctl_pending(current, JOBCTL_TRAP_STOP); + return false; + } +} + +/** + * do_jobctl_trap - take care of ptrace jobctl traps + * + * When PT_SEIZED, it's used for both group stop and explicit + * SEIZE/INTERRUPT traps. Both generate PTRACE_EVENT_STOP trap with + * accompanying siginfo. If stopped, lower eight bits of exit_code contain + * the stop signal; otherwise, %SIGTRAP. + * + * When !PT_SEIZED, it's used only for group stop trap with stop signal + * number as exit_code and no siginfo. + * + * CONTEXT: + * Must be called with @current->sighand->siglock held, which may be + * released and re-acquired before returning with intervening sleep. + */ +static void do_jobctl_trap(void) +{ + struct signal_struct *signal = current->signal; + int signr = current->jobctl & JOBCTL_STOP_SIGMASK; + + if (current->ptrace & PT_SEIZED) { + if (!signal->group_stop_count && + !(signal->flags & SIGNAL_STOP_STOPPED)) + signr = SIGTRAP; + WARN_ON_ONCE(!signr); + ptrace_do_notify(signr, signr | (PTRACE_EVENT_STOP << 8), + CLD_STOPPED); + } else { + WARN_ON_ONCE(!signr); + ptrace_stop(signr, CLD_STOPPED, 0, NULL); + current->exit_code = 0; + } +} + +static int ptrace_signal(int signr, siginfo_t *info) +{ + ptrace_signal_deliver(); + /* + * We do not check sig_kernel_stop(signr) but set this marker + * unconditionally because we do not know whether debugger will + * change signr. This flag has no meaning unless we are going + * to stop after return from ptrace_stop(). In this case it will + * be checked in do_signal_stop(), we should only stop if it was + * not cleared by SIGCONT while we were sleeping. See also the + * comment in dequeue_signal(). + */ + current->jobctl |= JOBCTL_STOP_DEQUEUED; + ptrace_stop(signr, CLD_TRAPPED, 0, info); + + /* We're back. Did the debugger cancel the sig? */ + signr = current->exit_code; + if (signr == 0) + return signr; + + current->exit_code = 0; + + /* + * Update the siginfo structure if the signal has + * changed. If the debugger wanted something + * specific in the siginfo structure then it should + * have updated *info via PTRACE_SETSIGINFO. + */ + if (signr != info->si_signo) { + info->si_signo = signr; + info->si_errno = 0; + info->si_code = SI_USER; + rcu_read_lock(); + info->si_pid = task_pid_vnr(current->parent); + info->si_uid = from_kuid_munged(current_user_ns(), + task_uid(current->parent)); + rcu_read_unlock(); + } + + /* If the (new) signal is now blocked, requeue it. */ + if (sigismember(¤t->blocked, signr)) { + specific_send_sig_info(signr, info, current); + signr = 0; + } + + return signr; +} + +int get_signal(struct ksignal *ksig) +{ + struct sighand_struct *sighand = current->sighand; + struct signal_struct *signal = current->signal; + int signr; + + if (unlikely(current->task_works)) + task_work_run(); + + if (unlikely(uprobe_deny_signal())) + return 0; + + /* + * Do this once, we can't return to user-mode if freezing() == T. + * do_signal_stop() and ptrace_stop() do freezable_schedule() and + * thus do not need another check after return. + */ + try_to_freeze(); + +relock: + spin_lock_irq(&sighand->siglock); + /* + * Every stopped thread goes here after wakeup. Check to see if + * we should notify the parent, prepare_signal(SIGCONT) encodes + * the CLD_ si_code into SIGNAL_CLD_MASK bits. + */ + if (unlikely(signal->flags & SIGNAL_CLD_MASK)) { + int why; + + if (signal->flags & SIGNAL_CLD_CONTINUED) + why = CLD_CONTINUED; + else + why = CLD_STOPPED; + + signal->flags &= ~SIGNAL_CLD_MASK; + + spin_unlock_irq(&sighand->siglock); + + /* + * Notify the parent that we're continuing. This event is + * always per-process and doesn't make whole lot of sense + * for ptracers, who shouldn't consume the state via + * wait(2) either, but, for backward compatibility, notify + * the ptracer of the group leader too unless it's gonna be + * a duplicate. + */ + read_lock(&tasklist_lock); + do_notify_parent_cldstop(current, false, why); + + if (ptrace_reparented(current->group_leader)) + do_notify_parent_cldstop(current->group_leader, + true, why); + read_unlock(&tasklist_lock); + + goto relock; + } + + for (;;) { + struct k_sigaction *ka; + + if (unlikely(current->jobctl & JOBCTL_STOP_PENDING) && + do_signal_stop(0)) + goto relock; + + if (unlikely(current->jobctl & JOBCTL_TRAP_MASK)) { + do_jobctl_trap(); + spin_unlock_irq(&sighand->siglock); + goto relock; + } + + signr = dequeue_signal(current, ¤t->blocked, &ksig->info); + + if (!signr) + break; /* will return 0 */ + + if (unlikely(current->ptrace) && signr != SIGKILL) { + signr = ptrace_signal(signr, &ksig->info); + if (!signr) + continue; + } + + ka = &sighand->action[signr-1]; + + /* Trace actually delivered signals. */ + trace_signal_deliver(signr, &ksig->info, ka); + + if (ka->sa.sa_handler == SIG_IGN) /* Do nothing. */ + continue; + if (ka->sa.sa_handler != SIG_DFL) { + /* Run the handler. */ + ksig->ka = *ka; + + if (ka->sa.sa_flags & SA_ONESHOT) + ka->sa.sa_handler = SIG_DFL; + + break; /* will return non-zero "signr" value */ + } + + /* + * Now we are doing the default action for this signal. + */ + if (sig_kernel_ignore(signr)) /* Default is nothing. */ + continue; + + /* + * Global init gets no signals it doesn't want. + * Container-init gets no signals it doesn't want from same + * container. + * + * Note that if global/container-init sees a sig_kernel_only() + * signal here, the signal must have been generated internally + * or must have come from an ancestor namespace. In either + * case, the signal cannot be dropped. + */ + if (unlikely(signal->flags & SIGNAL_UNKILLABLE) && + !sig_kernel_only(signr)) + continue; + + if (sig_kernel_stop(signr)) { + /* + * The default action is to stop all threads in + * the thread group. The job control signals + * do nothing in an orphaned pgrp, but SIGSTOP + * always works. Note that siglock needs to be + * dropped during the call to is_orphaned_pgrp() + * because of lock ordering with tasklist_lock. + * This allows an intervening SIGCONT to be posted. + * We need to check for that and bail out if necessary. + */ + if (signr != SIGSTOP) { + spin_unlock_irq(&sighand->siglock); + + /* signals can be posted during this window */ + + if (is_current_pgrp_orphaned()) + goto relock; + + spin_lock_irq(&sighand->siglock); + } + + if (likely(do_signal_stop(ksig->info.si_signo))) { + /* It released the siglock. */ + goto relock; + } + + /* + * We didn't actually stop, due to a race + * with SIGCONT or something like that. + */ + continue; + } + + spin_unlock_irq(&sighand->siglock); + + /* + * Anything else is fatal, maybe with a core dump. + */ + current->flags |= PF_SIGNALED; + + if (sig_kernel_coredump(signr)) { + if (print_fatal_signals) + print_fatal_signal(ksig->info.si_signo); + proc_coredump_connector(current); + /* + * If it was able to dump core, this kills all + * other threads in the group and synchronizes with + * their demise. If we lost the race with another + * thread getting here, it set group_exit_code + * first and our do_group_exit call below will use + * that value and ignore the one we pass it. + */ + do_coredump(&ksig->info); + } + + /* + * Death signals, no core dump. + */ + do_group_exit(ksig->info.si_signo); + /* NOTREACHED */ + } + spin_unlock_irq(&sighand->siglock); + + ksig->sig = signr; + return ksig->sig > 0; +} + +/** + * signal_delivered - + * @ksig: kernel signal struct + * @stepping: nonzero if debugger single-step or block-step in use + * + * This function should be called when a signal has successfully been + * delivered. It updates the blocked signals accordingly (@ksig->ka.sa.sa_mask + * is always blocked, and the signal itself is blocked unless %SA_NODEFER + * is set in @ksig->ka.sa.sa_flags. Tracing is notified. + */ +static void signal_delivered(struct ksignal *ksig, int stepping) +{ + sigset_t blocked; + + /* A signal was successfully delivered, and the + saved sigmask was stored on the signal frame, + and will be restored by sigreturn. So we can + simply clear the restore sigmask flag. */ + clear_restore_sigmask(); + + sigorsets(&blocked, ¤t->blocked, &ksig->ka.sa.sa_mask); + if (!(ksig->ka.sa.sa_flags & SA_NODEFER)) + sigaddset(&blocked, ksig->sig); + set_current_blocked(&blocked); + tracehook_signal_handler(stepping); +} + +void signal_setup_done(int failed, struct ksignal *ksig, int stepping) +{ + if (failed) + force_sigsegv(ksig->sig, current); + else + signal_delivered(ksig, stepping); +} + +/* + * It could be that complete_signal() picked us to notify about the + * group-wide signal. Other threads should be notified now to take + * the shared signals in @which since we will not. + */ +static void retarget_shared_pending(struct task_struct *tsk, sigset_t *which) +{ + sigset_t retarget; + struct task_struct *t; + + sigandsets(&retarget, &tsk->signal->shared_pending.signal, which); + if (sigisemptyset(&retarget)) + return; + + t = tsk; + while_each_thread(tsk, t) { + if (t->flags & PF_EXITING) + continue; + + if (!has_pending_signals(&retarget, &t->blocked)) + continue; + /* Remove the signals this thread can handle. */ + sigandsets(&retarget, &retarget, &t->blocked); + + if (!signal_pending(t)) + signal_wake_up(t, 0); + + if (sigisemptyset(&retarget)) + break; + } +} + +void exit_signals(struct task_struct *tsk) +{ + int group_stop = 0; + sigset_t unblocked; + + /* + * @tsk is about to have PF_EXITING set - lock out users which + * expect stable threadgroup. + */ + threadgroup_change_begin(tsk); + + if (thread_group_empty(tsk) || signal_group_exit(tsk->signal)) { + tsk->flags |= PF_EXITING; + threadgroup_change_end(tsk); + return; + } + + spin_lock_irq(&tsk->sighand->siglock); + /* + * From now this task is not visible for group-wide signals, + * see wants_signal(), do_signal_stop(). + */ + tsk->flags |= PF_EXITING; + + threadgroup_change_end(tsk); + + if (!signal_pending(tsk)) + goto out; + + unblocked = tsk->blocked; + signotset(&unblocked); + retarget_shared_pending(tsk, &unblocked); + + if (unlikely(tsk->jobctl & JOBCTL_STOP_PENDING) && + task_participate_group_stop(tsk)) + group_stop = CLD_STOPPED; +out: + spin_unlock_irq(&tsk->sighand->siglock); + + /* + * If group stop has completed, deliver the notification. This + * should always go to the real parent of the group leader. + */ + if (unlikely(group_stop)) { + read_lock(&tasklist_lock); + do_notify_parent_cldstop(tsk, false, group_stop); + read_unlock(&tasklist_lock); + } +} + +EXPORT_SYMBOL(recalc_sigpending); +EXPORT_SYMBOL_GPL(dequeue_signal); +EXPORT_SYMBOL(flush_signals); +EXPORT_SYMBOL(force_sig); +EXPORT_SYMBOL(send_sig); +EXPORT_SYMBOL(send_sig_info); +EXPORT_SYMBOL(sigprocmask); +EXPORT_SYMBOL(block_all_signals); +EXPORT_SYMBOL(unblock_all_signals); + + +/* + * System call entry points. + */ + +/** + * sys_restart_syscall - restart a system call + */ +SYSCALL_DEFINE0(restart_syscall) +{ + struct restart_block *restart = ¤t->restart_block; + return restart->fn(restart); +} + +long do_no_restart_syscall(struct restart_block *param) +{ + return -EINTR; +} + +static void __set_task_blocked(struct task_struct *tsk, const sigset_t *newset) +{ + if (signal_pending(tsk) && !thread_group_empty(tsk)) { + sigset_t newblocked; + /* A set of now blocked but previously unblocked signals. */ + sigandnsets(&newblocked, newset, ¤t->blocked); + retarget_shared_pending(tsk, &newblocked); + } + tsk->blocked = *newset; + recalc_sigpending(); +} + +/** + * set_current_blocked - change current->blocked mask + * @newset: new mask + * + * It is wrong to change ->blocked directly, this helper should be used + * to ensure the process can't miss a shared signal we are going to block. + */ +void set_current_blocked(sigset_t *newset) +{ + sigdelsetmask(newset, sigmask(SIGKILL) | sigmask(SIGSTOP)); + __set_current_blocked(newset); +} + +void __set_current_blocked(const sigset_t *newset) +{ + struct task_struct *tsk = current; + + spin_lock_irq(&tsk->sighand->siglock); + __set_task_blocked(tsk, newset); + spin_unlock_irq(&tsk->sighand->siglock); +} + +/* + * This is also useful for kernel threads that want to temporarily + * (or permanently) block certain signals. + * + * NOTE! Unlike the user-mode sys_sigprocmask(), the kernel + * interface happily blocks "unblockable" signals like SIGKILL + * and friends. + */ +int sigprocmask(int how, sigset_t *set, sigset_t *oldset) +{ + struct task_struct *tsk = current; + sigset_t newset; + + /* Lockless, only current can change ->blocked, never from irq */ + if (oldset) + *oldset = tsk->blocked; + + switch (how) { + case SIG_BLOCK: + sigorsets(&newset, &tsk->blocked, set); + break; + case SIG_UNBLOCK: + sigandnsets(&newset, &tsk->blocked, set); + break; + case SIG_SETMASK: + newset = *set; + break; + default: + return -EINVAL; + } + + __set_current_blocked(&newset); + return 0; +} + +/** + * sys_rt_sigprocmask - change the list of currently blocked signals + * @how: whether to add, remove, or set signals + * @nset: stores pending signals + * @oset: previous value of signal mask if non-null + * @sigsetsize: size of sigset_t type + */ +SYSCALL_DEFINE4(rt_sigprocmask, int, how, sigset_t __user *, nset, + sigset_t __user *, oset, size_t, sigsetsize) +{ + sigset_t old_set, new_set; + int error; + + /* XXX: Don't preclude handling different sized sigset_t's. */ + if (sigsetsize != sizeof(sigset_t)) + return -EINVAL; + + old_set = current->blocked; + + if (nset) { + if (copy_from_user(&new_set, nset, sizeof(sigset_t))) + return -EFAULT; + sigdelsetmask(&new_set, sigmask(SIGKILL)|sigmask(SIGSTOP)); + + error = sigprocmask(how, &new_set, NULL); + if (error) + return error; + } + + if (oset) { + if (copy_to_user(oset, &old_set, sizeof(sigset_t))) + return -EFAULT; + } + + return 0; +} + +#ifdef CONFIG_COMPAT +COMPAT_SYSCALL_DEFINE4(rt_sigprocmask, int, how, compat_sigset_t __user *, nset, + compat_sigset_t __user *, oset, compat_size_t, sigsetsize) +{ +#ifdef __BIG_ENDIAN + sigset_t old_set = current->blocked; + + /* XXX: Don't preclude handling different sized sigset_t's. */ + if (sigsetsize != sizeof(sigset_t)) + return -EINVAL; + + if (nset) { + compat_sigset_t new32; + sigset_t new_set; + int error; + if (copy_from_user(&new32, nset, sizeof(compat_sigset_t))) + return -EFAULT; + + sigset_from_compat(&new_set, &new32); + sigdelsetmask(&new_set, sigmask(SIGKILL)|sigmask(SIGSTOP)); + + error = sigprocmask(how, &new_set, NULL); + if (error) + return error; + } + if (oset) { + compat_sigset_t old32; + sigset_to_compat(&old32, &old_set); + if (copy_to_user(oset, &old32, sizeof(compat_sigset_t))) + return -EFAULT; + } + return 0; +#else + return sys_rt_sigprocmask(how, (sigset_t __user *)nset, + (sigset_t __user *)oset, sigsetsize); +#endif +} +#endif + +static int do_sigpending(void *set, unsigned long sigsetsize) +{ + if (sigsetsize > sizeof(sigset_t)) + return -EINVAL; + + spin_lock_irq(¤t->sighand->siglock); + sigorsets(set, ¤t->pending.signal, + ¤t->signal->shared_pending.signal); + spin_unlock_irq(¤t->sighand->siglock); + + /* Outside the lock because only this thread touches it. */ + sigandsets(set, ¤t->blocked, set); + return 0; +} + +/** + * sys_rt_sigpending - examine a pending signal that has been raised + * while blocked + * @uset: stores pending signals + * @sigsetsize: size of sigset_t type or larger + */ +SYSCALL_DEFINE2(rt_sigpending, sigset_t __user *, uset, size_t, sigsetsize) +{ + sigset_t set; + int err = do_sigpending(&set, sigsetsize); + if (!err && copy_to_user(uset, &set, sigsetsize)) + err = -EFAULT; + return err; +} + +#ifdef CONFIG_COMPAT +COMPAT_SYSCALL_DEFINE2(rt_sigpending, compat_sigset_t __user *, uset, + compat_size_t, sigsetsize) +{ +#ifdef __BIG_ENDIAN + sigset_t set; + int err = do_sigpending(&set, sigsetsize); + if (!err) { + compat_sigset_t set32; + sigset_to_compat(&set32, &set); + /* we can get here only if sigsetsize <= sizeof(set) */ + if (copy_to_user(uset, &set32, sigsetsize)) + err = -EFAULT; + } + return err; +#else + return sys_rt_sigpending((sigset_t __user *)uset, sigsetsize); +#endif +} +#endif + +#ifndef HAVE_ARCH_COPY_SIGINFO_TO_USER + +int copy_siginfo_to_user(siginfo_t __user *to, const siginfo_t *from) +{ + int err; + + if (!access_ok (VERIFY_WRITE, to, sizeof(siginfo_t))) + return -EFAULT; + if (from->si_code < 0) + return __copy_to_user(to, from, sizeof(siginfo_t)) + ? -EFAULT : 0; + /* + * If you change siginfo_t structure, please be sure + * this code is fixed accordingly. + * Please remember to update the signalfd_copyinfo() function + * inside fs/signalfd.c too, in case siginfo_t changes. + * It should never copy any pad contained in the structure + * to avoid security leaks, but must copy the generic + * 3 ints plus the relevant union member. + */ + err = __put_user(from->si_signo, &to->si_signo); + err |= __put_user(from->si_errno, &to->si_errno); + err |= __put_user((short)from->si_code, &to->si_code); + switch (from->si_code & __SI_MASK) { + case __SI_KILL: + err |= __put_user(from->si_pid, &to->si_pid); + err |= __put_user(from->si_uid, &to->si_uid); + break; + case __SI_TIMER: + err |= __put_user(from->si_tid, &to->si_tid); + err |= __put_user(from->si_overrun, &to->si_overrun); + err |= __put_user(from->si_ptr, &to->si_ptr); + break; + case __SI_POLL: + err |= __put_user(from->si_band, &to->si_band); + err |= __put_user(from->si_fd, &to->si_fd); + break; + case __SI_FAULT: + err |= __put_user(from->si_addr, &to->si_addr); +#ifdef __ARCH_SI_TRAPNO + err |= __put_user(from->si_trapno, &to->si_trapno); +#endif +#ifdef BUS_MCEERR_AO + /* + * Other callers might not initialize the si_lsb field, + * so check explicitly for the right codes here. + */ + if (from->si_code == BUS_MCEERR_AR || from->si_code == BUS_MCEERR_AO) + err |= __put_user(from->si_addr_lsb, &to->si_addr_lsb); +#endif +#ifdef SEGV_BNDERR + err |= __put_user(from->si_lower, &to->si_lower); + err |= __put_user(from->si_upper, &to->si_upper); +#endif + break; + case __SI_CHLD: + err |= __put_user(from->si_pid, &to->si_pid); + err |= __put_user(from->si_uid, &to->si_uid); + err |= __put_user(from->si_status, &to->si_status); + err |= __put_user(from->si_utime, &to->si_utime); + err |= __put_user(from->si_stime, &to->si_stime); + break; + case __SI_RT: /* This is not generated by the kernel as of now. */ + case __SI_MESGQ: /* But this is */ + err |= __put_user(from->si_pid, &to->si_pid); + err |= __put_user(from->si_uid, &to->si_uid); + err |= __put_user(from->si_ptr, &to->si_ptr); + break; +#ifdef __ARCH_SIGSYS + case __SI_SYS: + err |= __put_user(from->si_call_addr, &to->si_call_addr); + err |= __put_user(from->si_syscall, &to->si_syscall); + err |= __put_user(from->si_arch, &to->si_arch); + break; +#endif + default: /* this is just in case for now ... */ + err |= __put_user(from->si_pid, &to->si_pid); + err |= __put_user(from->si_uid, &to->si_uid); + break; + } + return err; +} + +#endif + +/** + * do_sigtimedwait - wait for queued signals specified in @which + * @which: queued signals to wait for + * @info: if non-null, the signal's siginfo is returned here + * @ts: upper bound on process time suspension + */ +int do_sigtimedwait(const sigset_t *which, siginfo_t *info, + const struct timespec *ts) +{ + struct task_struct *tsk = current; + long timeout = MAX_SCHEDULE_TIMEOUT; + sigset_t mask = *which; + int sig; + + if (ts) { + if (!timespec_valid(ts)) + return -EINVAL; + timeout = timespec_to_jiffies(ts); + /* + * We can be close to the next tick, add another one + * to ensure we will wait at least the time asked for. + */ + if (ts->tv_sec || ts->tv_nsec) + timeout++; + } + + /* + * Invert the set of allowed signals to get those we want to block. + */ + sigdelsetmask(&mask, sigmask(SIGKILL) | sigmask(SIGSTOP)); + signotset(&mask); + + spin_lock_irq(&tsk->sighand->siglock); + sig = dequeue_signal(tsk, &mask, info); + if (!sig && timeout) { + /* + * None ready, temporarily unblock those we're interested + * while we are sleeping in so that we'll be awakened when + * they arrive. Unblocking is always fine, we can avoid + * set_current_blocked(). + */ + tsk->real_blocked = tsk->blocked; + sigandsets(&tsk->blocked, &tsk->blocked, &mask); + recalc_sigpending(); + spin_unlock_irq(&tsk->sighand->siglock); + + timeout = freezable_schedule_timeout_interruptible(timeout); + + spin_lock_irq(&tsk->sighand->siglock); + __set_task_blocked(tsk, &tsk->real_blocked); + sigemptyset(&tsk->real_blocked); + sig = dequeue_signal(tsk, &mask, info); + } + spin_unlock_irq(&tsk->sighand->siglock); + + if (sig) + return sig; + return timeout ? -EINTR : -EAGAIN; +} + +/** + * sys_rt_sigtimedwait - synchronously wait for queued signals specified + * in @uthese + * @uthese: queued signals to wait for + * @uinfo: if non-null, the signal's siginfo is returned here + * @uts: upper bound on process time suspension + * @sigsetsize: size of sigset_t type + */ +SYSCALL_DEFINE4(rt_sigtimedwait, const sigset_t __user *, uthese, + siginfo_t __user *, uinfo, const struct timespec __user *, uts, + size_t, sigsetsize) +{ + sigset_t these; + struct timespec ts; + siginfo_t info; + int ret; + + /* XXX: Don't preclude handling different sized sigset_t's. */ + if (sigsetsize != sizeof(sigset_t)) + return -EINVAL; + + if (copy_from_user(&these, uthese, sizeof(these))) + return -EFAULT; + + if (uts) { + if (copy_from_user(&ts, uts, sizeof(ts))) + return -EFAULT; + } + + ret = do_sigtimedwait(&these, &info, uts ? &ts : NULL); + + if (ret > 0 && uinfo) { + if (copy_siginfo_to_user(uinfo, &info)) + ret = -EFAULT; + } + + return ret; +} + +/** + * sys_kill - send a signal to a process + * @pid: the PID of the process + * @sig: signal to be sent + */ +SYSCALL_DEFINE2(kill, pid_t, pid, int, sig) +{ + struct siginfo info; + + info.si_signo = sig; + info.si_errno = 0; + info.si_code = SI_USER; + info.si_pid = task_tgid_vnr(current); + info.si_uid = from_kuid_munged(current_user_ns(), current_uid()); + + return kill_something_info(sig, &info, pid); +} + +static int +do_send_specific(pid_t tgid, pid_t pid, int sig, struct siginfo *info) +{ + struct task_struct *p; + int error = -ESRCH; + + rcu_read_lock(); + p = find_task_by_vpid(pid); + if (p && (tgid <= 0 || task_tgid_vnr(p) == tgid)) { + error = check_kill_permission(sig, info, p); + /* + * The null signal is a permissions and process existence + * probe. No signal is actually delivered. + */ + if (!error && sig) { + error = do_send_sig_info(sig, info, p, false); + /* + * If lock_task_sighand() failed we pretend the task + * dies after receiving the signal. The window is tiny, + * and the signal is private anyway. + */ + if (unlikely(error == -ESRCH)) + error = 0; + } + } + rcu_read_unlock(); + + return error; +} + +static int do_tkill(pid_t tgid, pid_t pid, int sig) +{ + struct siginfo info = {}; + + info.si_signo = sig; + info.si_errno = 0; + info.si_code = SI_TKILL; + info.si_pid = task_tgid_vnr(current); + info.si_uid = from_kuid_munged(current_user_ns(), current_uid()); + + return do_send_specific(tgid, pid, sig, &info); +} + +/** + * sys_tgkill - send signal to one specific thread + * @tgid: the thread group ID of the thread + * @pid: the PID of the thread + * @sig: signal to be sent + * + * This syscall also checks the @tgid and returns -ESRCH even if the PID + * exists but it's not belonging to the target process anymore. This + * method solves the problem of threads exiting and PIDs getting reused. + */ +SYSCALL_DEFINE3(tgkill, pid_t, tgid, pid_t, pid, int, sig) +{ + /* This is only valid for single tasks */ + if (pid <= 0 || tgid <= 0) + return -EINVAL; + + return do_tkill(tgid, pid, sig); +} + +/** + * sys_tkill - send signal to one specific task + * @pid: the PID of the task + * @sig: signal to be sent + * + * Send a signal to only one task, even if it's a CLONE_THREAD task. + */ +SYSCALL_DEFINE2(tkill, pid_t, pid, int, sig) +{ + /* This is only valid for single tasks */ + if (pid <= 0) + return -EINVAL; + + return do_tkill(0, pid, sig); +} + +static int do_rt_sigqueueinfo(pid_t pid, int sig, siginfo_t *info) +{ + /* Not even root can pretend to send signals from the kernel. + * Nor can they impersonate a kill()/tgkill(), which adds source info. + */ + if ((info->si_code >= 0 || info->si_code == SI_TKILL) && + (task_pid_vnr(current) != pid)) + return -EPERM; + + info->si_signo = sig; + + /* POSIX.1b doesn't mention process groups. */ + return kill_proc_info(sig, info, pid); +} + +/** + * sys_rt_sigqueueinfo - send signal information to a signal + * @pid: the PID of the thread + * @sig: signal to be sent + * @uinfo: signal info to be sent + */ +SYSCALL_DEFINE3(rt_sigqueueinfo, pid_t, pid, int, sig, + siginfo_t __user *, uinfo) +{ + siginfo_t info; + if (copy_from_user(&info, uinfo, sizeof(siginfo_t))) + return -EFAULT; + return do_rt_sigqueueinfo(pid, sig, &info); +} + +#ifdef CONFIG_COMPAT +COMPAT_SYSCALL_DEFINE3(rt_sigqueueinfo, + compat_pid_t, pid, + int, sig, + struct compat_siginfo __user *, uinfo) +{ + siginfo_t info; + int ret = copy_siginfo_from_user32(&info, uinfo); + if (unlikely(ret)) + return ret; + return do_rt_sigqueueinfo(pid, sig, &info); +} +#endif + +static int do_rt_tgsigqueueinfo(pid_t tgid, pid_t pid, int sig, siginfo_t *info) +{ + /* This is only valid for single tasks */ + if (pid <= 0 || tgid <= 0) + return -EINVAL; + + /* Not even root can pretend to send signals from the kernel. + * Nor can they impersonate a kill()/tgkill(), which adds source info. + */ + if ((info->si_code >= 0 || info->si_code == SI_TKILL) && + (task_pid_vnr(current) != pid)) + return -EPERM; + + info->si_signo = sig; + + return do_send_specific(tgid, pid, sig, info); +} + +SYSCALL_DEFINE4(rt_tgsigqueueinfo, pid_t, tgid, pid_t, pid, int, sig, + siginfo_t __user *, uinfo) +{ + siginfo_t info; + + if (copy_from_user(&info, uinfo, sizeof(siginfo_t))) + return -EFAULT; + + return do_rt_tgsigqueueinfo(tgid, pid, sig, &info); +} + +#ifdef CONFIG_COMPAT +COMPAT_SYSCALL_DEFINE4(rt_tgsigqueueinfo, + compat_pid_t, tgid, + compat_pid_t, pid, + int, sig, + struct compat_siginfo __user *, uinfo) +{ + siginfo_t info; + + if (copy_siginfo_from_user32(&info, uinfo)) + return -EFAULT; + return do_rt_tgsigqueueinfo(tgid, pid, sig, &info); +} +#endif + +/* + * For kthreads only, must not be used if cloned with CLONE_SIGHAND + */ +void kernel_sigaction(int sig, __sighandler_t action) +{ + spin_lock_irq(¤t->sighand->siglock); + current->sighand->action[sig - 1].sa.sa_handler = action; + if (action == SIG_IGN) { + sigset_t mask; + + sigemptyset(&mask); + sigaddset(&mask, sig); + + flush_sigqueue_mask(&mask, ¤t->signal->shared_pending); + flush_sigqueue_mask(&mask, ¤t->pending); + recalc_sigpending(); + } + spin_unlock_irq(¤t->sighand->siglock); +} +EXPORT_SYMBOL(kernel_sigaction); + +int do_sigaction(int sig, struct k_sigaction *act, struct k_sigaction *oact) +{ + struct task_struct *p = current, *t; + struct k_sigaction *k; + sigset_t mask; + + if (!valid_signal(sig) || sig < 1 || (act && sig_kernel_only(sig))) + return -EINVAL; + + k = &p->sighand->action[sig-1]; + + spin_lock_irq(&p->sighand->siglock); + if (oact) + *oact = *k; + + if (act) { + sigdelsetmask(&act->sa.sa_mask, + sigmask(SIGKILL) | sigmask(SIGSTOP)); + *k = *act; + /* + * POSIX 3.3.1.3: + * "Setting a signal action to SIG_IGN for a signal that is + * pending shall cause the pending signal to be discarded, + * whether or not it is blocked." + * + * "Setting a signal action to SIG_DFL for a signal that is + * pending and whose default action is to ignore the signal + * (for example, SIGCHLD), shall cause the pending signal to + * be discarded, whether or not it is blocked" + */ + if (sig_handler_ignored(sig_handler(p, sig), sig)) { + sigemptyset(&mask); + sigaddset(&mask, sig); + flush_sigqueue_mask(&mask, &p->signal->shared_pending); + for_each_thread(p, t) + flush_sigqueue_mask(&mask, &t->pending); + } + } + + spin_unlock_irq(&p->sighand->siglock); + return 0; +} + +static int +do_sigaltstack (const stack_t __user *uss, stack_t __user *uoss, unsigned long sp) +{ + stack_t oss; + int error; + + oss.ss_sp = (void __user *) current->sas_ss_sp; + oss.ss_size = current->sas_ss_size; + oss.ss_flags = sas_ss_flags(sp); + + if (uss) { + void __user *ss_sp; + size_t ss_size; + int ss_flags; + + error = -EFAULT; + if (!access_ok(VERIFY_READ, uss, sizeof(*uss))) + goto out; + error = __get_user(ss_sp, &uss->ss_sp) | + __get_user(ss_flags, &uss->ss_flags) | + __get_user(ss_size, &uss->ss_size); + if (error) + goto out; + + error = -EPERM; + if (on_sig_stack(sp)) + goto out; + + error = -EINVAL; + /* + * Note - this code used to test ss_flags incorrectly: + * old code may have been written using ss_flags==0 + * to mean ss_flags==SS_ONSTACK (as this was the only + * way that worked) - this fix preserves that older + * mechanism. + */ + if (ss_flags != SS_DISABLE && ss_flags != SS_ONSTACK && ss_flags != 0) + goto out; + + if (ss_flags == SS_DISABLE) { + ss_size = 0; + ss_sp = NULL; + } else { + error = -ENOMEM; + if (ss_size < MINSIGSTKSZ) + goto out; + } + + current->sas_ss_sp = (unsigned long) ss_sp; + current->sas_ss_size = ss_size; + } + + error = 0; + if (uoss) { + error = -EFAULT; + if (!access_ok(VERIFY_WRITE, uoss, sizeof(*uoss))) + goto out; + error = __put_user(oss.ss_sp, &uoss->ss_sp) | + __put_user(oss.ss_size, &uoss->ss_size) | + __put_user(oss.ss_flags, &uoss->ss_flags); + } + +out: + return error; +} +SYSCALL_DEFINE2(sigaltstack,const stack_t __user *,uss, stack_t __user *,uoss) +{ + return do_sigaltstack(uss, uoss, current_user_stack_pointer()); +} + +int restore_altstack(const stack_t __user *uss) +{ + int err = do_sigaltstack(uss, NULL, current_user_stack_pointer()); + /* squash all but EFAULT for now */ + return err == -EFAULT ? err : 0; +} + +int __save_altstack(stack_t __user *uss, unsigned long sp) +{ + struct task_struct *t = current; + return __put_user((void __user *)t->sas_ss_sp, &uss->ss_sp) | + __put_user(sas_ss_flags(sp), &uss->ss_flags) | + __put_user(t->sas_ss_size, &uss->ss_size); +} + +#ifdef CONFIG_COMPAT +COMPAT_SYSCALL_DEFINE2(sigaltstack, + const compat_stack_t __user *, uss_ptr, + compat_stack_t __user *, uoss_ptr) +{ + stack_t uss, uoss; + int ret; + mm_segment_t seg; + + if (uss_ptr) { + compat_stack_t uss32; + + memset(&uss, 0, sizeof(stack_t)); + if (copy_from_user(&uss32, uss_ptr, sizeof(compat_stack_t))) + return -EFAULT; + uss.ss_sp = compat_ptr(uss32.ss_sp); + uss.ss_flags = uss32.ss_flags; + uss.ss_size = uss32.ss_size; + } + seg = get_fs(); + set_fs(KERNEL_DS); + ret = do_sigaltstack((stack_t __force __user *) (uss_ptr ? &uss : NULL), + (stack_t __force __user *) &uoss, + compat_user_stack_pointer()); + set_fs(seg); + if (ret >= 0 && uoss_ptr) { + if (!access_ok(VERIFY_WRITE, uoss_ptr, sizeof(compat_stack_t)) || + __put_user(ptr_to_compat(uoss.ss_sp), &uoss_ptr->ss_sp) || + __put_user(uoss.ss_flags, &uoss_ptr->ss_flags) || + __put_user(uoss.ss_size, &uoss_ptr->ss_size)) + ret = -EFAULT; + } + return ret; +} + +int compat_restore_altstack(const compat_stack_t __user *uss) +{ + int err = compat_sys_sigaltstack(uss, NULL); + /* squash all but -EFAULT for now */ + return err == -EFAULT ? err : 0; +} + +int __compat_save_altstack(compat_stack_t __user *uss, unsigned long sp) +{ + struct task_struct *t = current; + return __put_user(ptr_to_compat((void __user *)t->sas_ss_sp), &uss->ss_sp) | + __put_user(sas_ss_flags(sp), &uss->ss_flags) | + __put_user(t->sas_ss_size, &uss->ss_size); +} +#endif + +#ifdef __ARCH_WANT_SYS_SIGPENDING + +/** + * sys_sigpending - examine pending signals + * @set: where mask of pending signal is returned + */ +SYSCALL_DEFINE1(sigpending, old_sigset_t __user *, set) +{ + return sys_rt_sigpending((sigset_t __user *)set, sizeof(old_sigset_t)); +} + +#endif + +#ifdef __ARCH_WANT_SYS_SIGPROCMASK +/** + * sys_sigprocmask - examine and change blocked signals + * @how: whether to add, remove, or set signals + * @nset: signals to add or remove (if non-null) + * @oset: previous value of signal mask if non-null + * + * Some platforms have their own version with special arguments; + * others support only sys_rt_sigprocmask. + */ + +SYSCALL_DEFINE3(sigprocmask, int, how, old_sigset_t __user *, nset, + old_sigset_t __user *, oset) +{ + old_sigset_t old_set, new_set; + sigset_t new_blocked; + + old_set = current->blocked.sig[0]; + + if (nset) { + if (copy_from_user(&new_set, nset, sizeof(*nset))) + return -EFAULT; + + new_blocked = current->blocked; + + switch (how) { + case SIG_BLOCK: + sigaddsetmask(&new_blocked, new_set); + break; + case SIG_UNBLOCK: + sigdelsetmask(&new_blocked, new_set); + break; + case SIG_SETMASK: + new_blocked.sig[0] = new_set; + break; + default: + return -EINVAL; + } + + set_current_blocked(&new_blocked); + } + + if (oset) { + if (copy_to_user(oset, &old_set, sizeof(*oset))) + return -EFAULT; + } + + return 0; +} +#endif /* __ARCH_WANT_SYS_SIGPROCMASK */ + +#ifndef CONFIG_ODD_RT_SIGACTION +/** + * sys_rt_sigaction - alter an action taken by a process + * @sig: signal to be sent + * @act: new sigaction + * @oact: used to save the previous sigaction + * @sigsetsize: size of sigset_t type + */ +SYSCALL_DEFINE4(rt_sigaction, int, sig, + const struct sigaction __user *, act, + struct sigaction __user *, oact, + size_t, sigsetsize) +{ + struct k_sigaction new_sa, old_sa; + int ret = -EINVAL; + + /* XXX: Don't preclude handling different sized sigset_t's. */ + if (sigsetsize != sizeof(sigset_t)) + goto out; + + if (act) { + if (copy_from_user(&new_sa.sa, act, sizeof(new_sa.sa))) + return -EFAULT; + } + + ret = do_sigaction(sig, act ? &new_sa : NULL, oact ? &old_sa : NULL); + + if (!ret && oact) { + if (copy_to_user(oact, &old_sa.sa, sizeof(old_sa.sa))) + return -EFAULT; + } +out: + return ret; +} +#ifdef CONFIG_COMPAT +COMPAT_SYSCALL_DEFINE4(rt_sigaction, int, sig, + const struct compat_sigaction __user *, act, + struct compat_sigaction __user *, oact, + compat_size_t, sigsetsize) +{ + struct k_sigaction new_ka, old_ka; + compat_sigset_t mask; +#ifdef __ARCH_HAS_SA_RESTORER + compat_uptr_t restorer; +#endif + int ret; + + /* XXX: Don't preclude handling different sized sigset_t's. */ + if (sigsetsize != sizeof(compat_sigset_t)) + return -EINVAL; + + if (act) { + compat_uptr_t handler; + ret = get_user(handler, &act->sa_handler); + new_ka.sa.sa_handler = compat_ptr(handler); +#ifdef __ARCH_HAS_SA_RESTORER + ret |= get_user(restorer, &act->sa_restorer); + new_ka.sa.sa_restorer = compat_ptr(restorer); +#endif + ret |= copy_from_user(&mask, &act->sa_mask, sizeof(mask)); + ret |= get_user(new_ka.sa.sa_flags, &act->sa_flags); + if (ret) + return -EFAULT; + sigset_from_compat(&new_ka.sa.sa_mask, &mask); + } + + ret = do_sigaction(sig, act ? &new_ka : NULL, oact ? &old_ka : NULL); + if (!ret && oact) { + sigset_to_compat(&mask, &old_ka.sa.sa_mask); + ret = put_user(ptr_to_compat(old_ka.sa.sa_handler), + &oact->sa_handler); + ret |= copy_to_user(&oact->sa_mask, &mask, sizeof(mask)); + ret |= put_user(old_ka.sa.sa_flags, &oact->sa_flags); +#ifdef __ARCH_HAS_SA_RESTORER + ret |= put_user(ptr_to_compat(old_ka.sa.sa_restorer), + &oact->sa_restorer); +#endif + } + return ret; +} +#endif +#endif /* !CONFIG_ODD_RT_SIGACTION */ + +#ifdef CONFIG_OLD_SIGACTION +SYSCALL_DEFINE3(sigaction, int, sig, + const struct old_sigaction __user *, act, + struct old_sigaction __user *, oact) +{ + struct k_sigaction new_ka, old_ka; + int ret; + + if (act) { + old_sigset_t mask; + if (!access_ok(VERIFY_READ, act, sizeof(*act)) || + __get_user(new_ka.sa.sa_handler, &act->sa_handler) || + __get_user(new_ka.sa.sa_restorer, &act->sa_restorer) || + __get_user(new_ka.sa.sa_flags, &act->sa_flags) || + __get_user(mask, &act->sa_mask)) + return -EFAULT; +#ifdef __ARCH_HAS_KA_RESTORER + new_ka.ka_restorer = NULL; +#endif + siginitset(&new_ka.sa.sa_mask, mask); + } + + ret = do_sigaction(sig, act ? &new_ka : NULL, oact ? &old_ka : NULL); + + if (!ret && oact) { + if (!access_ok(VERIFY_WRITE, oact, sizeof(*oact)) || + __put_user(old_ka.sa.sa_handler, &oact->sa_handler) || + __put_user(old_ka.sa.sa_restorer, &oact->sa_restorer) || + __put_user(old_ka.sa.sa_flags, &oact->sa_flags) || + __put_user(old_ka.sa.sa_mask.sig[0], &oact->sa_mask)) + return -EFAULT; + } + + return ret; +} +#endif +#ifdef CONFIG_COMPAT_OLD_SIGACTION +COMPAT_SYSCALL_DEFINE3(sigaction, int, sig, + const struct compat_old_sigaction __user *, act, + struct compat_old_sigaction __user *, oact) +{ + struct k_sigaction new_ka, old_ka; + int ret; + compat_old_sigset_t mask; + compat_uptr_t handler, restorer; + + if (act) { + if (!access_ok(VERIFY_READ, act, sizeof(*act)) || + __get_user(handler, &act->sa_handler) || + __get_user(restorer, &act->sa_restorer) || + __get_user(new_ka.sa.sa_flags, &act->sa_flags) || + __get_user(mask, &act->sa_mask)) + return -EFAULT; + +#ifdef __ARCH_HAS_KA_RESTORER + new_ka.ka_restorer = NULL; +#endif + new_ka.sa.sa_handler = compat_ptr(handler); + new_ka.sa.sa_restorer = compat_ptr(restorer); + siginitset(&new_ka.sa.sa_mask, mask); + } + + ret = do_sigaction(sig, act ? &new_ka : NULL, oact ? &old_ka : NULL); + + if (!ret && oact) { + if (!access_ok(VERIFY_WRITE, oact, sizeof(*oact)) || + __put_user(ptr_to_compat(old_ka.sa.sa_handler), + &oact->sa_handler) || + __put_user(ptr_to_compat(old_ka.sa.sa_restorer), + &oact->sa_restorer) || + __put_user(old_ka.sa.sa_flags, &oact->sa_flags) || + __put_user(old_ka.sa.sa_mask.sig[0], &oact->sa_mask)) + return -EFAULT; + } + return ret; +} +#endif + +#ifdef CONFIG_SGETMASK_SYSCALL + +/* + * For backwards compatibility. Functionality superseded by sigprocmask. + */ +SYSCALL_DEFINE0(sgetmask) +{ + /* SMP safe */ + return current->blocked.sig[0]; +} + +SYSCALL_DEFINE1(ssetmask, int, newmask) +{ + int old = current->blocked.sig[0]; + sigset_t newset; + + siginitset(&newset, newmask); + set_current_blocked(&newset); + + return old; +} +#endif /* CONFIG_SGETMASK_SYSCALL */ + +#ifdef __ARCH_WANT_SYS_SIGNAL +/* + * For backwards compatibility. Functionality superseded by sigaction. + */ +SYSCALL_DEFINE2(signal, int, sig, __sighandler_t, handler) +{ + struct k_sigaction new_sa, old_sa; + int ret; + + new_sa.sa.sa_handler = handler; + new_sa.sa.sa_flags = SA_ONESHOT | SA_NOMASK; + sigemptyset(&new_sa.sa.sa_mask); + + ret = do_sigaction(sig, &new_sa, &old_sa); + + return ret ? ret : (unsigned long)old_sa.sa.sa_handler; +} +#endif /* __ARCH_WANT_SYS_SIGNAL */ + +#ifdef __ARCH_WANT_SYS_PAUSE + +SYSCALL_DEFINE0(pause) +{ + while (!signal_pending(current)) { + __set_current_state(TASK_INTERRUPTIBLE); + schedule(); + } + return -ERESTARTNOHAND; +} + +#endif + +int sigsuspend(sigset_t *set) +{ + current->saved_sigmask = current->blocked; + set_current_blocked(set); + + __set_current_state(TASK_INTERRUPTIBLE); + schedule(); + set_restore_sigmask(); + return -ERESTARTNOHAND; +} + +/** + * sys_rt_sigsuspend - replace the signal mask for a value with the + * @unewset value until a signal is received + * @unewset: new signal mask value + * @sigsetsize: size of sigset_t type + */ +SYSCALL_DEFINE2(rt_sigsuspend, sigset_t __user *, unewset, size_t, sigsetsize) +{ + sigset_t newset; + + /* XXX: Don't preclude handling different sized sigset_t's. */ + if (sigsetsize != sizeof(sigset_t)) + return -EINVAL; + + if (copy_from_user(&newset, unewset, sizeof(newset))) + return -EFAULT; + return sigsuspend(&newset); +} + +#ifdef CONFIG_COMPAT +COMPAT_SYSCALL_DEFINE2(rt_sigsuspend, compat_sigset_t __user *, unewset, compat_size_t, sigsetsize) +{ +#ifdef __BIG_ENDIAN + sigset_t newset; + compat_sigset_t newset32; + + /* XXX: Don't preclude handling different sized sigset_t's. */ + if (sigsetsize != sizeof(sigset_t)) + return -EINVAL; + + if (copy_from_user(&newset32, unewset, sizeof(compat_sigset_t))) + return -EFAULT; + sigset_from_compat(&newset, &newset32); + return sigsuspend(&newset); +#else + /* on little-endian bitmaps don't care about granularity */ + return sys_rt_sigsuspend((sigset_t __user *)unewset, sigsetsize); +#endif +} +#endif + +#ifdef CONFIG_OLD_SIGSUSPEND +SYSCALL_DEFINE1(sigsuspend, old_sigset_t, mask) +{ + sigset_t blocked; + siginitset(&blocked, mask); + return sigsuspend(&blocked); +} +#endif +#ifdef CONFIG_OLD_SIGSUSPEND3 +SYSCALL_DEFINE3(sigsuspend, int, unused1, int, unused2, old_sigset_t, mask) +{ + sigset_t blocked; + siginitset(&blocked, mask); + return sigsuspend(&blocked); +} +#endif + +__weak const char *arch_vma_name(struct vm_area_struct *vma) +{ + return NULL; +} + +void __init signals_init(void) +{ + sigqueue_cachep = KMEM_CACHE(sigqueue, SLAB_PANIC); +} + +#ifdef CONFIG_KGDB_KDB +#include +/* + * kdb_send_sig_info - Allows kdb to send signals without exposing + * signal internals. This function checks if the required locks are + * available before calling the main signal code, to avoid kdb + * deadlocks. + */ +void +kdb_send_sig_info(struct task_struct *t, struct siginfo *info) +{ + static struct task_struct *kdb_prev_t; + int sig, new_t; + if (!spin_trylock(&t->sighand->siglock)) { + kdb_printf("Can't do kill command now.\n" + "The sigmask lock is held somewhere else in " + "kernel, try again later\n"); + return; + } + spin_unlock(&t->sighand->siglock); + new_t = kdb_prev_t != t; + kdb_prev_t = t; + if (t->state != TASK_RUNNING && new_t) { + kdb_printf("Process is not RUNNING, sending a signal from " + "kdb risks deadlock\n" + "on the run queue locks. " + "The signal has _not_ been sent.\n" + "Reissue the kill command if you want to risk " + "the deadlock.\n"); + return; + } + sig = info->si_signo; + if (send_sig_info(sig, info, t)) + kdb_printf("Fail to deliver Signal %d to process %d.\n", + sig, t->pid); + else + kdb_printf("Signal %d is sent to process %d.\n", sig, t->pid); +} +#endif /* CONFIG_KGDB_KDB */ diff --git a/kernel/kernel/smp.c b/kernel/kernel/smp.c new file mode 100644 index 000000000..07854477c --- /dev/null +++ b/kernel/kernel/smp.c @@ -0,0 +1,741 @@ +/* + * Generic helpers for smp ipi calls + * + * (C) Jens Axboe 2008 + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "smpboot.h" + +enum { + CSD_FLAG_LOCK = 0x01, + CSD_FLAG_SYNCHRONOUS = 0x02, +}; + +struct call_function_data { + struct call_single_data __percpu *csd; + cpumask_var_t cpumask; +}; + +static DEFINE_PER_CPU_SHARED_ALIGNED(struct call_function_data, cfd_data); + +static DEFINE_PER_CPU_SHARED_ALIGNED(struct llist_head, call_single_queue); + +static void flush_smp_call_function_queue(bool warn_cpu_offline); + +static int +hotplug_cfd(struct notifier_block *nfb, unsigned long action, void *hcpu) +{ + long cpu = (long)hcpu; + struct call_function_data *cfd = &per_cpu(cfd_data, cpu); + + switch (action) { + case CPU_UP_PREPARE: + case CPU_UP_PREPARE_FROZEN: + if (!zalloc_cpumask_var_node(&cfd->cpumask, GFP_KERNEL, + cpu_to_node(cpu))) + return notifier_from_errno(-ENOMEM); + cfd->csd = alloc_percpu(struct call_single_data); + if (!cfd->csd) { + free_cpumask_var(cfd->cpumask); + return notifier_from_errno(-ENOMEM); + } + break; + +#ifdef CONFIG_HOTPLUG_CPU + case CPU_UP_CANCELED: + case CPU_UP_CANCELED_FROZEN: + /* Fall-through to the CPU_DEAD[_FROZEN] case. */ + + case CPU_DEAD: + case CPU_DEAD_FROZEN: + free_cpumask_var(cfd->cpumask); + free_percpu(cfd->csd); + break; + + case CPU_DYING: + case CPU_DYING_FROZEN: + /* + * The IPIs for the smp-call-function callbacks queued by other + * CPUs might arrive late, either due to hardware latencies or + * because this CPU disabled interrupts (inside stop-machine) + * before the IPIs were sent. So flush out any pending callbacks + * explicitly (without waiting for the IPIs to arrive), to + * ensure that the outgoing CPU doesn't go offline with work + * still pending. + */ + flush_smp_call_function_queue(false); + break; +#endif + }; + + return NOTIFY_OK; +} + +static struct notifier_block hotplug_cfd_notifier = { + .notifier_call = hotplug_cfd, +}; + +void __init call_function_init(void) +{ + void *cpu = (void *)(long)smp_processor_id(); + int i; + + for_each_possible_cpu(i) + init_llist_head(&per_cpu(call_single_queue, i)); + + hotplug_cfd(&hotplug_cfd_notifier, CPU_UP_PREPARE, cpu); + register_cpu_notifier(&hotplug_cfd_notifier); +} + +/* + * csd_lock/csd_unlock used to serialize access to per-cpu csd resources + * + * For non-synchronous ipi calls the csd can still be in use by the + * previous function call. For multi-cpu calls its even more interesting + * as we'll have to ensure no other cpu is observing our csd. + */ +static void csd_lock_wait(struct call_single_data *csd) +{ + while (smp_load_acquire(&csd->flags) & CSD_FLAG_LOCK) + cpu_relax(); +} + +static void csd_lock(struct call_single_data *csd) +{ + csd_lock_wait(csd); + csd->flags |= CSD_FLAG_LOCK; + + /* + * prevent CPU from reordering the above assignment + * to ->flags with any subsequent assignments to other + * fields of the specified call_single_data structure: + */ + smp_wmb(); +} + +static void csd_unlock(struct call_single_data *csd) +{ + WARN_ON(!(csd->flags & CSD_FLAG_LOCK)); + + /* + * ensure we're all done before releasing data: + */ + smp_store_release(&csd->flags, 0); +} + +static DEFINE_PER_CPU_SHARED_ALIGNED(struct call_single_data, csd_data); + +/* + * Insert a previously allocated call_single_data element + * for execution on the given CPU. data must already have + * ->func, ->info, and ->flags set. + */ +static int generic_exec_single(int cpu, struct call_single_data *csd, + smp_call_func_t func, void *info) +{ + if (cpu == smp_processor_id()) { + unsigned long flags; + + /* + * We can unlock early even for the synchronous on-stack case, + * since we're doing this from the same CPU.. + */ + csd_unlock(csd); + local_irq_save(flags); + func(info); + local_irq_restore(flags); + return 0; + } + + + if ((unsigned)cpu >= nr_cpu_ids || !cpu_online(cpu)) { + csd_unlock(csd); + return -ENXIO; + } + + csd->func = func; + csd->info = info; + + /* + * The list addition should be visible before sending the IPI + * handler locks the list to pull the entry off it because of + * normal cache coherency rules implied by spinlocks. + * + * If IPIs can go out of order to the cache coherency protocol + * in an architecture, sufficient synchronisation should be added + * to arch code to make it appear to obey cache coherency WRT + * locking and barrier primitives. Generic code isn't really + * equipped to do the right thing... + */ + if (llist_add(&csd->llist, &per_cpu(call_single_queue, cpu))) + arch_send_call_function_single_ipi(cpu); + + return 0; +} + +/** + * generic_smp_call_function_single_interrupt - Execute SMP IPI callbacks + * + * Invoked by arch to handle an IPI for call function single. + * Must be called with interrupts disabled. + */ +void generic_smp_call_function_single_interrupt(void) +{ + flush_smp_call_function_queue(true); +} + +/** + * flush_smp_call_function_queue - Flush pending smp-call-function callbacks + * + * @warn_cpu_offline: If set to 'true', warn if callbacks were queued on an + * offline CPU. Skip this check if set to 'false'. + * + * Flush any pending smp-call-function callbacks queued on this CPU. This is + * invoked by the generic IPI handler, as well as by a CPU about to go offline, + * to ensure that all pending IPI callbacks are run before it goes completely + * offline. + * + * Loop through the call_single_queue and run all the queued callbacks. + * Must be called with interrupts disabled. + */ +static void flush_smp_call_function_queue(bool warn_cpu_offline) +{ + struct llist_head *head; + struct llist_node *entry; + struct call_single_data *csd, *csd_next; + static bool warned; + + WARN_ON(!irqs_disabled()); + + head = this_cpu_ptr(&call_single_queue); + entry = llist_del_all(head); + entry = llist_reverse_order(entry); + + /* There shouldn't be any pending callbacks on an offline CPU. */ + if (unlikely(warn_cpu_offline && !cpu_online(smp_processor_id()) && + !warned && !llist_empty(head))) { + warned = true; + WARN(1, "IPI on offline CPU %d\n", smp_processor_id()); + + /* + * We don't have to use the _safe() variant here + * because we are not invoking the IPI handlers yet. + */ + llist_for_each_entry(csd, entry, llist) + pr_warn("IPI callback %pS sent to offline CPU\n", + csd->func); + } + + llist_for_each_entry_safe(csd, csd_next, entry, llist) { + smp_call_func_t func = csd->func; + void *info = csd->info; + + /* Do we wait until *after* callback? */ + if (csd->flags & CSD_FLAG_SYNCHRONOUS) { + func(info); + csd_unlock(csd); + } else { + csd_unlock(csd); + func(info); + } + } + + /* + * Handle irq works queued remotely by irq_work_queue_on(). + * Smp functions above are typically synchronous so they + * better run first since some other CPUs may be busy waiting + * for them. + */ + irq_work_run(); +} + +/* + * smp_call_function_single - Run a function on a specific CPU + * @func: The function to run. This must be fast and non-blocking. + * @info: An arbitrary pointer to pass to the function. + * @wait: If true, wait until function has completed on other CPUs. + * + * Returns 0 on success, else a negative status code. + */ +int smp_call_function_single(int cpu, smp_call_func_t func, void *info, + int wait) +{ + struct call_single_data *csd; + struct call_single_data csd_stack = { .flags = CSD_FLAG_LOCK | CSD_FLAG_SYNCHRONOUS }; + int this_cpu; + int err; + + /* + * prevent preemption and reschedule on another processor, + * as well as CPU removal + */ + this_cpu = get_cpu(); + + /* + * Can deadlock when called with interrupts disabled. + * We allow cpu's that are not yet online though, as no one else can + * send smp call function interrupt to this cpu and as such deadlocks + * can't happen. + */ + WARN_ON_ONCE(cpu_online(this_cpu) && irqs_disabled() + && !oops_in_progress); + + csd = &csd_stack; + if (!wait) { + csd = this_cpu_ptr(&csd_data); + csd_lock(csd); + } + + err = generic_exec_single(cpu, csd, func, info); + + if (wait) + csd_lock_wait(csd); + + put_cpu(); + + return err; +} +EXPORT_SYMBOL(smp_call_function_single); + +/** + * smp_call_function_single_async(): Run an asynchronous function on a + * specific CPU. + * @cpu: The CPU to run on. + * @csd: Pre-allocated and setup data structure + * + * Like smp_call_function_single(), but the call is asynchonous and + * can thus be done from contexts with disabled interrupts. + * + * The caller passes his own pre-allocated data structure + * (ie: embedded in an object) and is responsible for synchronizing it + * such that the IPIs performed on the @csd are strictly serialized. + * + * NOTE: Be careful, there is unfortunately no current debugging facility to + * validate the correctness of this serialization. + */ +int smp_call_function_single_async(int cpu, struct call_single_data *csd) +{ + int err = 0; + + preempt_disable(); + + /* We could deadlock if we have to wait here with interrupts disabled! */ + if (WARN_ON_ONCE(csd->flags & CSD_FLAG_LOCK)) + csd_lock_wait(csd); + + csd->flags = CSD_FLAG_LOCK; + smp_wmb(); + + err = generic_exec_single(cpu, csd, csd->func, csd->info); + preempt_enable(); + + return err; +} +EXPORT_SYMBOL_GPL(smp_call_function_single_async); + +/* + * smp_call_function_any - Run a function on any of the given cpus + * @mask: The mask of cpus it can run on. + * @func: The function to run. This must be fast and non-blocking. + * @info: An arbitrary pointer to pass to the function. + * @wait: If true, wait until function has completed. + * + * Returns 0 on success, else a negative status code (if no cpus were online). + * + * Selection preference: + * 1) current cpu if in @mask + * 2) any cpu of current node if in @mask + * 3) any other online cpu in @mask + */ +int smp_call_function_any(const struct cpumask *mask, + smp_call_func_t func, void *info, int wait) +{ + unsigned int cpu; + const struct cpumask *nodemask; + int ret; + + /* Try for same CPU (cheapest) */ + cpu = get_cpu(); + if (cpumask_test_cpu(cpu, mask)) + goto call; + + /* Try for same node. */ + nodemask = cpumask_of_node(cpu_to_node(cpu)); + for (cpu = cpumask_first_and(nodemask, mask); cpu < nr_cpu_ids; + cpu = cpumask_next_and(cpu, nodemask, mask)) { + if (cpu_online(cpu)) + goto call; + } + + /* Any online will do: smp_call_function_single handles nr_cpu_ids. */ + cpu = cpumask_any_and(mask, cpu_online_mask); +call: + ret = smp_call_function_single(cpu, func, info, wait); + put_cpu(); + return ret; +} +EXPORT_SYMBOL_GPL(smp_call_function_any); + +/** + * smp_call_function_many(): Run a function on a set of other CPUs. + * @mask: The set of cpus to run on (only runs on online subset). + * @func: The function to run. This must be fast and non-blocking. + * @info: An arbitrary pointer to pass to the function. + * @wait: If true, wait (atomically) until function has completed + * on other CPUs. + * + * If @wait is true, then returns once @func has returned. + * + * You must not call this function with disabled interrupts or from a + * hardware interrupt handler or from a bottom half handler. Preemption + * must be disabled when calling this function. + */ +void smp_call_function_many(const struct cpumask *mask, + smp_call_func_t func, void *info, bool wait) +{ + struct call_function_data *cfd; + int cpu, next_cpu, this_cpu = smp_processor_id(); + + /* + * Can deadlock when called with interrupts disabled. + * We allow cpu's that are not yet online though, as no one else can + * send smp call function interrupt to this cpu and as such deadlocks + * can't happen. + */ + WARN_ON_ONCE(cpu_online(this_cpu) && irqs_disabled() + && !oops_in_progress && !early_boot_irqs_disabled); + + /* Try to fastpath. So, what's a CPU they want? Ignoring this one. */ + cpu = cpumask_first_and(mask, cpu_online_mask); + if (cpu == this_cpu) + cpu = cpumask_next_and(cpu, mask, cpu_online_mask); + + /* No online cpus? We're done. */ + if (cpu >= nr_cpu_ids) + return; + + /* Do we have another CPU which isn't us? */ + next_cpu = cpumask_next_and(cpu, mask, cpu_online_mask); + if (next_cpu == this_cpu) + next_cpu = cpumask_next_and(next_cpu, mask, cpu_online_mask); + + /* Fastpath: do that cpu by itself. */ + if (next_cpu >= nr_cpu_ids) { + smp_call_function_single(cpu, func, info, wait); + return; + } + + cfd = this_cpu_ptr(&cfd_data); + + cpumask_and(cfd->cpumask, mask, cpu_online_mask); + cpumask_clear_cpu(this_cpu, cfd->cpumask); + + /* Some callers race with other cpus changing the passed mask */ + if (unlikely(!cpumask_weight(cfd->cpumask))) + return; + + for_each_cpu(cpu, cfd->cpumask) { + struct call_single_data *csd = per_cpu_ptr(cfd->csd, cpu); + + csd_lock(csd); + if (wait) + csd->flags |= CSD_FLAG_SYNCHRONOUS; + csd->func = func; + csd->info = info; + llist_add(&csd->llist, &per_cpu(call_single_queue, cpu)); + } + + /* Send a message to all CPUs in the map */ + arch_send_call_function_ipi_mask(cfd->cpumask); + + if (wait) { + for_each_cpu(cpu, cfd->cpumask) { + struct call_single_data *csd; + + csd = per_cpu_ptr(cfd->csd, cpu); + csd_lock_wait(csd); + } + } +} +EXPORT_SYMBOL(smp_call_function_many); + +/** + * smp_call_function(): Run a function on all other CPUs. + * @func: The function to run. This must be fast and non-blocking. + * @info: An arbitrary pointer to pass to the function. + * @wait: If true, wait (atomically) until function has completed + * on other CPUs. + * + * Returns 0. + * + * If @wait is true, then returns once @func has returned; otherwise + * it returns just before the target cpu calls @func. + * + * You must not call this function with disabled interrupts or from a + * hardware interrupt handler or from a bottom half handler. + */ +int smp_call_function(smp_call_func_t func, void *info, int wait) +{ + preempt_disable(); + smp_call_function_many(cpu_online_mask, func, info, wait); + preempt_enable(); + + return 0; +} +EXPORT_SYMBOL(smp_call_function); + +/* Setup configured maximum number of CPUs to activate */ +unsigned int setup_max_cpus = NR_CPUS; +EXPORT_SYMBOL(setup_max_cpus); + + +/* + * Setup routine for controlling SMP activation + * + * Command-line option of "nosmp" or "maxcpus=0" will disable SMP + * activation entirely (the MPS table probe still happens, though). + * + * Command-line option of "maxcpus=", where is an integer + * greater than 0, limits the maximum number of CPUs activated in + * SMP mode to . + */ + +void __weak arch_disable_smp_support(void) { } + +static int __init nosmp(char *str) +{ + setup_max_cpus = 0; + arch_disable_smp_support(); + + return 0; +} + +early_param("nosmp", nosmp); + +/* this is hard limit */ +static int __init nrcpus(char *str) +{ + int nr_cpus; + + get_option(&str, &nr_cpus); + if (nr_cpus > 0 && nr_cpus < nr_cpu_ids) + nr_cpu_ids = nr_cpus; + + return 0; +} + +early_param("nr_cpus", nrcpus); + +static int __init maxcpus(char *str) +{ + get_option(&str, &setup_max_cpus); + if (setup_max_cpus == 0) + arch_disable_smp_support(); + + return 0; +} + +early_param("maxcpus", maxcpus); + +/* Setup number of possible processor ids */ +int nr_cpu_ids __read_mostly = NR_CPUS; +EXPORT_SYMBOL(nr_cpu_ids); + +/* An arch may set nr_cpu_ids earlier if needed, so this would be redundant */ +void __init setup_nr_cpu_ids(void) +{ + nr_cpu_ids = find_last_bit(cpumask_bits(cpu_possible_mask),NR_CPUS) + 1; +} + +void __weak smp_announce(void) +{ + printk(KERN_INFO "Brought up %d CPUs\n", num_online_cpus()); +} + +/* Called by boot processor to activate the rest. */ +void __init smp_init(void) +{ + unsigned int cpu; + + idle_threads_init(); + + /* FIXME: This should be done in userspace --RR */ + for_each_present_cpu(cpu) { + if (num_online_cpus() >= setup_max_cpus) + break; + if (!cpu_online(cpu)) + cpu_up(cpu); + } + + /* Any cleanup work */ + smp_announce(); + smp_cpus_done(setup_max_cpus); +} + +/* + * Call a function on all processors. May be used during early boot while + * early_boot_irqs_disabled is set. Use local_irq_save/restore() instead + * of local_irq_disable/enable(). + */ +int on_each_cpu(void (*func) (void *info), void *info, int wait) +{ + unsigned long flags; + int ret = 0; + + preempt_disable(); + ret = smp_call_function(func, info, wait); + local_irq_save(flags); + func(info); + local_irq_restore(flags); + preempt_enable(); + return ret; +} +EXPORT_SYMBOL(on_each_cpu); + +/** + * on_each_cpu_mask(): Run a function on processors specified by + * cpumask, which may include the local processor. + * @mask: The set of cpus to run on (only runs on online subset). + * @func: The function to run. This must be fast and non-blocking. + * @info: An arbitrary pointer to pass to the function. + * @wait: If true, wait (atomically) until function has completed + * on other CPUs. + * + * If @wait is true, then returns once @func has returned. + * + * You must not call this function with disabled interrupts or from a + * hardware interrupt handler or from a bottom half handler. The + * exception is that it may be used during early boot while + * early_boot_irqs_disabled is set. + */ +void on_each_cpu_mask(const struct cpumask *mask, smp_call_func_t func, + void *info, bool wait) +{ + int cpu = get_cpu(); + + smp_call_function_many(mask, func, info, wait); + if (cpumask_test_cpu(cpu, mask)) { + unsigned long flags; + local_irq_save(flags); + func(info); + local_irq_restore(flags); + } + put_cpu(); +} +EXPORT_SYMBOL(on_each_cpu_mask); + +/* + * on_each_cpu_cond(): Call a function on each processor for which + * the supplied function cond_func returns true, optionally waiting + * for all the required CPUs to finish. This may include the local + * processor. + * @cond_func: A callback function that is passed a cpu id and + * the the info parameter. The function is called + * with preemption disabled. The function should + * return a blooean value indicating whether to IPI + * the specified CPU. + * @func: The function to run on all applicable CPUs. + * This must be fast and non-blocking. + * @info: An arbitrary pointer to pass to both functions. + * @wait: If true, wait (atomically) until function has + * completed on other CPUs. + * @gfp_flags: GFP flags to use when allocating the cpumask + * used internally by the function. + * + * The function might sleep if the GFP flags indicates a non + * atomic allocation is allowed. + * + * Preemption is disabled to protect against CPUs going offline but not online. + * CPUs going online during the call will not be seen or sent an IPI. + * + * You must not call this function with disabled interrupts or + * from a hardware interrupt handler or from a bottom half handler. + */ +void on_each_cpu_cond(bool (*cond_func)(int cpu, void *info), + smp_call_func_t func, void *info, bool wait, + gfp_t gfp_flags) +{ + cpumask_var_t cpus; + int cpu, ret; + + might_sleep_if(gfp_flags & __GFP_WAIT); + + if (likely(zalloc_cpumask_var(&cpus, (gfp_flags|__GFP_NOWARN)))) { + preempt_disable(); + for_each_online_cpu(cpu) + if (cond_func(cpu, info)) + cpumask_set_cpu(cpu, cpus); + on_each_cpu_mask(cpus, func, info, wait); + preempt_enable(); + free_cpumask_var(cpus); + } else { + /* + * No free cpumask, bother. No matter, we'll + * just have to IPI them one by one. + */ + preempt_disable(); + for_each_online_cpu(cpu) + if (cond_func(cpu, info)) { + ret = smp_call_function_single(cpu, func, + info, wait); + WARN_ON_ONCE(ret); + } + preempt_enable(); + } +} +EXPORT_SYMBOL(on_each_cpu_cond); + +static void do_nothing(void *unused) +{ +} + +/** + * kick_all_cpus_sync - Force all cpus out of idle + * + * Used to synchronize the update of pm_idle function pointer. It's + * called after the pointer is updated and returns after the dummy + * callback function has been executed on all cpus. The execution of + * the function can only happen on the remote cpus after they have + * left the idle function which had been called via pm_idle function + * pointer. So it's guaranteed that nothing uses the previous pointer + * anymore. + */ +void kick_all_cpus_sync(void) +{ + /* Make sure the change is visible before we kick the cpus */ + smp_mb(); + smp_call_function(do_nothing, NULL, 1); +} +EXPORT_SYMBOL_GPL(kick_all_cpus_sync); + +/** + * wake_up_all_idle_cpus - break all cpus out of idle + * wake_up_all_idle_cpus try to break all cpus which is in idle state even + * including idle polling cpus, for non-idle cpus, we will do nothing + * for them. + */ +void wake_up_all_idle_cpus(void) +{ + int cpu; + + preempt_disable(); + for_each_online_cpu(cpu) { + if (cpu == smp_processor_id()) + continue; + + wake_up_if_idle(cpu); + } + preempt_enable(); +} +EXPORT_SYMBOL_GPL(wake_up_all_idle_cpus); diff --git a/kernel/kernel/smpboot.c b/kernel/kernel/smpboot.c new file mode 100644 index 000000000..c697f73d8 --- /dev/null +++ b/kernel/kernel/smpboot.c @@ -0,0 +1,472 @@ +/* + * Common SMP CPU bringup/teardown functions + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "smpboot.h" + +#ifdef CONFIG_SMP + +#ifdef CONFIG_GENERIC_SMP_IDLE_THREAD +/* + * For the hotplug case we keep the task structs around and reuse + * them. + */ +static DEFINE_PER_CPU(struct task_struct *, idle_threads); + +struct task_struct *idle_thread_get(unsigned int cpu) +{ + struct task_struct *tsk = per_cpu(idle_threads, cpu); + + if (!tsk) + return ERR_PTR(-ENOMEM); + init_idle(tsk, cpu); + return tsk; +} + +void __init idle_thread_set_boot_cpu(void) +{ + per_cpu(idle_threads, smp_processor_id()) = current; +} + +/** + * idle_init - Initialize the idle thread for a cpu + * @cpu: The cpu for which the idle thread should be initialized + * + * Creates the thread if it does not exist. + */ +static inline void idle_init(unsigned int cpu) +{ + struct task_struct *tsk = per_cpu(idle_threads, cpu); + + if (!tsk) { + tsk = fork_idle(cpu); + if (IS_ERR(tsk)) + pr_err("SMP: fork_idle() failed for CPU %u\n", cpu); + else + per_cpu(idle_threads, cpu) = tsk; + } +} + +/** + * idle_threads_init - Initialize idle threads for all cpus + */ +void __init idle_threads_init(void) +{ + unsigned int cpu, boot_cpu; + + boot_cpu = smp_processor_id(); + + for_each_possible_cpu(cpu) { + if (cpu != boot_cpu) + idle_init(cpu); + } +} +#endif + +#endif /* #ifdef CONFIG_SMP */ + +static LIST_HEAD(hotplug_threads); +static DEFINE_MUTEX(smpboot_threads_lock); + +struct smpboot_thread_data { + unsigned int cpu; + unsigned int status; + struct smp_hotplug_thread *ht; +}; + +enum { + HP_THREAD_NONE = 0, + HP_THREAD_ACTIVE, + HP_THREAD_PARKED, +}; + +/** + * smpboot_thread_fn - percpu hotplug thread loop function + * @data: thread data pointer + * + * Checks for thread stop and park conditions. Calls the necessary + * setup, cleanup, park and unpark functions for the registered + * thread. + * + * Returns 1 when the thread should exit, 0 otherwise. + */ +static int smpboot_thread_fn(void *data) +{ + struct smpboot_thread_data *td = data; + struct smp_hotplug_thread *ht = td->ht; + + while (1) { + set_current_state(TASK_INTERRUPTIBLE); + preempt_disable(); + if (kthread_should_stop()) { + __set_current_state(TASK_RUNNING); + preempt_enable(); + if (ht->cleanup) + ht->cleanup(td->cpu, cpu_online(td->cpu)); + kfree(td); + return 0; + } + + if (kthread_should_park()) { + __set_current_state(TASK_RUNNING); + preempt_enable(); + if (ht->park && td->status == HP_THREAD_ACTIVE) { + BUG_ON(td->cpu != smp_processor_id()); + ht->park(td->cpu); + td->status = HP_THREAD_PARKED; + } + kthread_parkme(); + /* We might have been woken for stop */ + continue; + } + + BUG_ON(td->cpu != smp_processor_id()); + + /* Check for state change setup */ + switch (td->status) { + case HP_THREAD_NONE: + __set_current_state(TASK_RUNNING); + preempt_enable(); + if (ht->setup) + ht->setup(td->cpu); + td->status = HP_THREAD_ACTIVE; + continue; + + case HP_THREAD_PARKED: + __set_current_state(TASK_RUNNING); + preempt_enable(); + if (ht->unpark) + ht->unpark(td->cpu); + td->status = HP_THREAD_ACTIVE; + continue; + } + + if (!ht->thread_should_run(td->cpu)) { + preempt_enable_no_resched(); + schedule(); + } else { + __set_current_state(TASK_RUNNING); + preempt_enable(); + ht->thread_fn(td->cpu); + } + } +} + +static int +__smpboot_create_thread(struct smp_hotplug_thread *ht, unsigned int cpu) +{ + struct task_struct *tsk = *per_cpu_ptr(ht->store, cpu); + struct smpboot_thread_data *td; + + if (tsk) + return 0; + + td = kzalloc_node(sizeof(*td), GFP_KERNEL, cpu_to_node(cpu)); + if (!td) + return -ENOMEM; + td->cpu = cpu; + td->ht = ht; + + tsk = kthread_create_on_cpu(smpboot_thread_fn, td, cpu, + ht->thread_comm); + if (IS_ERR(tsk)) { + kfree(td); + return PTR_ERR(tsk); + } + get_task_struct(tsk); + *per_cpu_ptr(ht->store, cpu) = tsk; + if (ht->create) { + /* + * Make sure that the task has actually scheduled out + * into park position, before calling the create + * callback. At least the migration thread callback + * requires that the task is off the runqueue. + */ + if (!wait_task_inactive(tsk, TASK_PARKED)) + WARN_ON(1); + else + ht->create(cpu); + } + return 0; +} + +int smpboot_create_threads(unsigned int cpu) +{ + struct smp_hotplug_thread *cur; + int ret = 0; + + mutex_lock(&smpboot_threads_lock); + list_for_each_entry(cur, &hotplug_threads, list) { + ret = __smpboot_create_thread(cur, cpu); + if (ret) + break; + } + mutex_unlock(&smpboot_threads_lock); + return ret; +} + +static void smpboot_unpark_thread(struct smp_hotplug_thread *ht, unsigned int cpu) +{ + struct task_struct *tsk = *per_cpu_ptr(ht->store, cpu); + + if (ht->pre_unpark) + ht->pre_unpark(cpu); + kthread_unpark(tsk); +} + +void smpboot_unpark_threads(unsigned int cpu) +{ + struct smp_hotplug_thread *cur; + + mutex_lock(&smpboot_threads_lock); + list_for_each_entry(cur, &hotplug_threads, list) + smpboot_unpark_thread(cur, cpu); + mutex_unlock(&smpboot_threads_lock); +} + +static void smpboot_park_thread(struct smp_hotplug_thread *ht, unsigned int cpu) +{ + struct task_struct *tsk = *per_cpu_ptr(ht->store, cpu); + + if (tsk && !ht->selfparking) + kthread_park(tsk); +} + +void smpboot_park_threads(unsigned int cpu) +{ + struct smp_hotplug_thread *cur; + + mutex_lock(&smpboot_threads_lock); + list_for_each_entry_reverse(cur, &hotplug_threads, list) + smpboot_park_thread(cur, cpu); + mutex_unlock(&smpboot_threads_lock); +} + +static void smpboot_destroy_threads(struct smp_hotplug_thread *ht) +{ + unsigned int cpu; + + /* We need to destroy also the parked threads of offline cpus */ + for_each_possible_cpu(cpu) { + struct task_struct *tsk = *per_cpu_ptr(ht->store, cpu); + + if (tsk) { + kthread_stop(tsk); + put_task_struct(tsk); + *per_cpu_ptr(ht->store, cpu) = NULL; + } + } +} + +/** + * smpboot_register_percpu_thread - Register a per_cpu thread related to hotplug + * @plug_thread: Hotplug thread descriptor + * + * Creates and starts the threads on all online cpus. + */ +int smpboot_register_percpu_thread(struct smp_hotplug_thread *plug_thread) +{ + unsigned int cpu; + int ret = 0; + + get_online_cpus(); + mutex_lock(&smpboot_threads_lock); + for_each_online_cpu(cpu) { + ret = __smpboot_create_thread(plug_thread, cpu); + if (ret) { + smpboot_destroy_threads(plug_thread); + goto out; + } + smpboot_unpark_thread(plug_thread, cpu); + } + list_add(&plug_thread->list, &hotplug_threads); +out: + mutex_unlock(&smpboot_threads_lock); + put_online_cpus(); + return ret; +} +EXPORT_SYMBOL_GPL(smpboot_register_percpu_thread); + +/** + * smpboot_unregister_percpu_thread - Unregister a per_cpu thread related to hotplug + * @plug_thread: Hotplug thread descriptor + * + * Stops all threads on all possible cpus. + */ +void smpboot_unregister_percpu_thread(struct smp_hotplug_thread *plug_thread) +{ + get_online_cpus(); + mutex_lock(&smpboot_threads_lock); + list_del(&plug_thread->list); + smpboot_destroy_threads(plug_thread); + mutex_unlock(&smpboot_threads_lock); + put_online_cpus(); +} +EXPORT_SYMBOL_GPL(smpboot_unregister_percpu_thread); + +static DEFINE_PER_CPU(atomic_t, cpu_hotplug_state) = ATOMIC_INIT(CPU_POST_DEAD); + +/* + * Called to poll specified CPU's state, for example, when waiting for + * a CPU to come online. + */ +int cpu_report_state(int cpu) +{ + return atomic_read(&per_cpu(cpu_hotplug_state, cpu)); +} + +/* + * If CPU has died properly, set its state to CPU_UP_PREPARE and + * return success. Otherwise, return -EBUSY if the CPU died after + * cpu_wait_death() timed out. And yet otherwise again, return -EAGAIN + * if cpu_wait_death() timed out and the CPU still hasn't gotten around + * to dying. In the latter two cases, the CPU might not be set up + * properly, but it is up to the arch-specific code to decide. + * Finally, -EIO indicates an unanticipated problem. + * + * Note that it is permissible to omit this call entirely, as is + * done in architectures that do no CPU-hotplug error checking. + */ +int cpu_check_up_prepare(int cpu) +{ + if (!IS_ENABLED(CONFIG_HOTPLUG_CPU)) { + atomic_set(&per_cpu(cpu_hotplug_state, cpu), CPU_UP_PREPARE); + return 0; + } + + switch (atomic_read(&per_cpu(cpu_hotplug_state, cpu))) { + + case CPU_POST_DEAD: + + /* The CPU died properly, so just start it up again. */ + atomic_set(&per_cpu(cpu_hotplug_state, cpu), CPU_UP_PREPARE); + return 0; + + case CPU_DEAD_FROZEN: + + /* + * Timeout during CPU death, so let caller know. + * The outgoing CPU completed its processing, but after + * cpu_wait_death() timed out and reported the error. The + * caller is free to proceed, in which case the state + * will be reset properly by cpu_set_state_online(). + * Proceeding despite this -EBUSY return makes sense + * for systems where the outgoing CPUs take themselves + * offline, with no post-death manipulation required from + * a surviving CPU. + */ + return -EBUSY; + + case CPU_BROKEN: + + /* + * The most likely reason we got here is that there was + * a timeout during CPU death, and the outgoing CPU never + * did complete its processing. This could happen on + * a virtualized system if the outgoing VCPU gets preempted + * for more than five seconds, and the user attempts to + * immediately online that same CPU. Trying again later + * might return -EBUSY above, hence -EAGAIN. + */ + return -EAGAIN; + + default: + + /* Should not happen. Famous last words. */ + return -EIO; + } +} + +/* + * Mark the specified CPU online. + * + * Note that it is permissible to omit this call entirely, as is + * done in architectures that do no CPU-hotplug error checking. + */ +void cpu_set_state_online(int cpu) +{ + (void)atomic_xchg(&per_cpu(cpu_hotplug_state, cpu), CPU_ONLINE); +} + +#ifdef CONFIG_HOTPLUG_CPU + +/* + * Wait for the specified CPU to exit the idle loop and die. + */ +bool cpu_wait_death(unsigned int cpu, int seconds) +{ + int jf_left = seconds * HZ; + int oldstate; + bool ret = true; + int sleep_jf = 1; + + might_sleep(); + + /* The outgoing CPU will normally get done quite quickly. */ + if (atomic_read(&per_cpu(cpu_hotplug_state, cpu)) == CPU_DEAD) + goto update_state; + udelay(5); + + /* But if the outgoing CPU dawdles, wait increasingly long times. */ + while (atomic_read(&per_cpu(cpu_hotplug_state, cpu)) != CPU_DEAD) { + schedule_timeout_uninterruptible(sleep_jf); + jf_left -= sleep_jf; + if (jf_left <= 0) + break; + sleep_jf = DIV_ROUND_UP(sleep_jf * 11, 10); + } +update_state: + oldstate = atomic_read(&per_cpu(cpu_hotplug_state, cpu)); + if (oldstate == CPU_DEAD) { + /* Outgoing CPU died normally, update state. */ + smp_mb(); /* atomic_read() before update. */ + atomic_set(&per_cpu(cpu_hotplug_state, cpu), CPU_POST_DEAD); + } else { + /* Outgoing CPU still hasn't died, set state accordingly. */ + if (atomic_cmpxchg(&per_cpu(cpu_hotplug_state, cpu), + oldstate, CPU_BROKEN) != oldstate) + goto update_state; + ret = false; + } + return ret; +} + +/* + * Called by the outgoing CPU to report its successful death. Return + * false if this report follows the surviving CPU's timing out. + * + * A separate "CPU_DEAD_FROZEN" is used when the surviving CPU + * timed out. This approach allows architectures to omit calls to + * cpu_check_up_prepare() and cpu_set_state_online() without defeating + * the next cpu_wait_death()'s polling loop. + */ +bool cpu_report_death(void) +{ + int oldstate; + int newstate; + int cpu = smp_processor_id(); + + do { + oldstate = atomic_read(&per_cpu(cpu_hotplug_state, cpu)); + if (oldstate != CPU_BROKEN) + newstate = CPU_DEAD; + else + newstate = CPU_DEAD_FROZEN; + } while (atomic_cmpxchg(&per_cpu(cpu_hotplug_state, cpu), + oldstate, newstate) != oldstate); + return newstate == CPU_DEAD; +} + +#endif /* #ifdef CONFIG_HOTPLUG_CPU */ diff --git a/kernel/kernel/smpboot.h b/kernel/kernel/smpboot.h new file mode 100644 index 000000000..72415a0eb --- /dev/null +++ b/kernel/kernel/smpboot.h @@ -0,0 +1,20 @@ +#ifndef SMPBOOT_H +#define SMPBOOT_H + +struct task_struct; + +#ifdef CONFIG_GENERIC_SMP_IDLE_THREAD +struct task_struct *idle_thread_get(unsigned int cpu); +void idle_thread_set_boot_cpu(void); +void idle_threads_init(void); +#else +static inline struct task_struct *idle_thread_get(unsigned int cpu) { return NULL; } +static inline void idle_thread_set_boot_cpu(void) { } +static inline void idle_threads_init(void) { } +#endif + +int smpboot_create_threads(unsigned int cpu); +void smpboot_park_threads(unsigned int cpu); +void smpboot_unpark_threads(unsigned int cpu); + +#endif diff --git a/kernel/kernel/softirq.c b/kernel/kernel/softirq.c new file mode 100644 index 000000000..49baf8184 --- /dev/null +++ b/kernel/kernel/softirq.c @@ -0,0 +1,1245 @@ +/* + * linux/kernel/softirq.c + * + * Copyright (C) 1992 Linus Torvalds + * + * Distribute under GPLv2. + * + * Rewritten. Old one was good in 2.2, but in 2.3 it was immoral. --ANK (990903) + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define CREATE_TRACE_POINTS +#include + +/* + - No shared variables, all the data are CPU local. + - If a softirq needs serialization, let it serialize itself + by its own spinlocks. + - Even if softirq is serialized, only local cpu is marked for + execution. Hence, we get something sort of weak cpu binding. + Though it is still not clear, will it result in better locality + or will not. + + Examples: + - NET RX softirq. It is multithreaded and does not require + any global serialization. + - NET TX softirq. It kicks software netdevice queues, hence + it is logically serialized per device, but this serialization + is invisible to common code. + - Tasklets: serialized wrt itself. + */ + +#ifndef __ARCH_IRQ_STAT +irq_cpustat_t irq_stat[NR_CPUS] ____cacheline_aligned; +EXPORT_SYMBOL(irq_stat); +#endif + +static struct softirq_action softirq_vec[NR_SOFTIRQS] __cacheline_aligned_in_smp; + +DEFINE_PER_CPU(struct task_struct *, ksoftirqd); + +const char * const softirq_to_name[NR_SOFTIRQS] = { + "HI", "TIMER", "NET_TX", "NET_RX", "BLOCK", "BLOCK_IOPOLL", + "TASKLET", "SCHED", "HRTIMER", "RCU" +}; + +#ifdef CONFIG_NO_HZ_COMMON +# ifdef CONFIG_PREEMPT_RT_FULL + +struct softirq_runner { + struct task_struct *runner[NR_SOFTIRQS]; +}; + +static DEFINE_PER_CPU(struct softirq_runner, softirq_runners); + +static inline void softirq_set_runner(unsigned int sirq) +{ + struct softirq_runner *sr = this_cpu_ptr(&softirq_runners); + + sr->runner[sirq] = current; +} + +static inline void softirq_clr_runner(unsigned int sirq) +{ + struct softirq_runner *sr = this_cpu_ptr(&softirq_runners); + + sr->runner[sirq] = NULL; +} + +/* + * On preempt-rt a softirq running context might be blocked on a + * lock. There might be no other runnable task on this CPU because the + * lock owner runs on some other CPU. So we have to go into idle with + * the pending bit set. Therefor we need to check this otherwise we + * warn about false positives which confuses users and defeats the + * whole purpose of this test. + * + * This code is called with interrupts disabled. + */ +void softirq_check_pending_idle(void) +{ + static int rate_limit; + struct softirq_runner *sr = this_cpu_ptr(&softirq_runners); + u32 warnpending; + int i; + + if (rate_limit >= 10) + return; + + warnpending = local_softirq_pending() & SOFTIRQ_STOP_IDLE_MASK; + for (i = 0; i < NR_SOFTIRQS; i++) { + struct task_struct *tsk = sr->runner[i]; + + /* + * The wakeup code in rtmutex.c wakes up the task + * _before_ it sets pi_blocked_on to NULL under + * tsk->pi_lock. So we need to check for both: state + * and pi_blocked_on. + */ + if (tsk) { + raw_spin_lock(&tsk->pi_lock); + if (tsk->pi_blocked_on || tsk->state == TASK_RUNNING) { + /* Clear all bits pending in that task */ + warnpending &= ~(tsk->softirqs_raised); + warnpending &= ~(1 << i); + } + raw_spin_unlock(&tsk->pi_lock); + } + } + + if (warnpending) { + printk(KERN_ERR "NOHZ: local_softirq_pending %02x\n", + warnpending); + rate_limit++; + } +} +# else +/* + * On !PREEMPT_RT we just printk rate limited: + */ +void softirq_check_pending_idle(void) +{ + static int rate_limit; + + if (rate_limit < 10 && + (local_softirq_pending() & SOFTIRQ_STOP_IDLE_MASK)) { + printk(KERN_ERR "NOHZ: local_softirq_pending %02x\n", + local_softirq_pending()); + rate_limit++; + } +} +# endif + +#else /* !CONFIG_NO_HZ_COMMON */ +static inline void softirq_set_runner(unsigned int sirq) { } +static inline void softirq_clr_runner(unsigned int sirq) { } +#endif + +/* + * we cannot loop indefinitely here to avoid userspace starvation, + * but we also don't want to introduce a worst case 1/HZ latency + * to the pending events, so lets the scheduler to balance + * the softirq load for us. + */ +static void wakeup_softirqd(void) +{ + /* Interrupts are disabled: no need to stop preemption */ + struct task_struct *tsk = __this_cpu_read(ksoftirqd); + + if (tsk && tsk->state != TASK_RUNNING) + wake_up_process(tsk); +} + +static void handle_softirq(unsigned int vec_nr) +{ + struct softirq_action *h = softirq_vec + vec_nr; + int prev_count; + + prev_count = preempt_count(); + + kstat_incr_softirqs_this_cpu(vec_nr); + + trace_softirq_entry(vec_nr); + h->action(h); + trace_softirq_exit(vec_nr); + if (unlikely(prev_count != preempt_count())) { + pr_err("huh, entered softirq %u %s %p with preempt_count %08x, exited with %08x?\n", + vec_nr, softirq_to_name[vec_nr], h->action, + prev_count, preempt_count()); + preempt_count_set(prev_count); + } +} + +#ifndef CONFIG_PREEMPT_RT_FULL +static inline int ksoftirqd_softirq_pending(void) +{ + return local_softirq_pending(); +} + +static void handle_pending_softirqs(u32 pending) +{ + struct softirq_action *h = softirq_vec; + int softirq_bit; + + local_irq_enable(); + + h = softirq_vec; + + while ((softirq_bit = ffs(pending))) { + unsigned int vec_nr; + + h += softirq_bit - 1; + vec_nr = h - softirq_vec; + handle_softirq(vec_nr); + + h++; + pending >>= softirq_bit; + } + + rcu_bh_qs(); + local_irq_disable(); +} + +static void run_ksoftirqd(unsigned int cpu) +{ + local_irq_disable(); + if (ksoftirqd_softirq_pending()) { + __do_softirq(); + local_irq_enable(); + cond_resched_rcu_qs(); + return; + } + local_irq_enable(); +} + +/* + * preempt_count and SOFTIRQ_OFFSET usage: + * - preempt_count is changed by SOFTIRQ_OFFSET on entering or leaving + * softirq processing. + * - preempt_count is changed by SOFTIRQ_DISABLE_OFFSET (= 2 * SOFTIRQ_OFFSET) + * on local_bh_disable or local_bh_enable. + * This lets us distinguish between whether we are currently processing + * softirq and whether we just have bh disabled. + */ + +/* + * This one is for softirq.c-internal use, + * where hardirqs are disabled legitimately: + */ +#ifdef CONFIG_TRACE_IRQFLAGS +void __local_bh_disable_ip(unsigned long ip, unsigned int cnt) +{ + unsigned long flags; + + WARN_ON_ONCE(in_irq()); + + raw_local_irq_save(flags); + /* + * The preempt tracer hooks into preempt_count_add and will break + * lockdep because it calls back into lockdep after SOFTIRQ_OFFSET + * is set and before current->softirq_enabled is cleared. + * We must manually increment preempt_count here and manually + * call the trace_preempt_off later. + */ + __preempt_count_add(cnt); + /* + * Were softirqs turned off above: + */ + if (softirq_count() == (cnt & SOFTIRQ_MASK)) + trace_softirqs_off(ip); + raw_local_irq_restore(flags); + + if (preempt_count() == cnt) { +#ifdef CONFIG_DEBUG_PREEMPT + current->preempt_disable_ip = get_parent_ip(CALLER_ADDR1); +#endif + trace_preempt_off(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1)); + } +} +EXPORT_SYMBOL(__local_bh_disable_ip); +#endif /* CONFIG_TRACE_IRQFLAGS */ + +static void __local_bh_enable(unsigned int cnt) +{ + WARN_ON_ONCE(!irqs_disabled()); + + if (softirq_count() == (cnt & SOFTIRQ_MASK)) + trace_softirqs_on(_RET_IP_); + preempt_count_sub(cnt); +} + +/* + * Special-case - softirqs can safely be enabled in + * cond_resched_softirq(), or by __do_softirq(), + * without processing still-pending softirqs: + */ +void _local_bh_enable(void) +{ + WARN_ON_ONCE(in_irq()); + __local_bh_enable(SOFTIRQ_DISABLE_OFFSET); +} +EXPORT_SYMBOL(_local_bh_enable); + +void __local_bh_enable_ip(unsigned long ip, unsigned int cnt) +{ + WARN_ON_ONCE(in_irq() || irqs_disabled()); +#ifdef CONFIG_TRACE_IRQFLAGS + local_irq_disable(); +#endif + /* + * Are softirqs going to be turned on now: + */ + if (softirq_count() == SOFTIRQ_DISABLE_OFFSET) + trace_softirqs_on(ip); + /* + * Keep preemption disabled until we are done with + * softirq processing: + */ + preempt_count_sub(cnt - 1); + + if (unlikely(!in_interrupt() && local_softirq_pending())) { + /* + * Run softirq if any pending. And do it in its own stack + * as we may be calling this deep in a task call stack already. + */ + do_softirq(); + } + + preempt_count_dec(); +#ifdef CONFIG_TRACE_IRQFLAGS + local_irq_enable(); +#endif + preempt_check_resched(); +} +EXPORT_SYMBOL(__local_bh_enable_ip); + +/* + * We restart softirq processing for at most MAX_SOFTIRQ_RESTART times, + * but break the loop if need_resched() is set or after 2 ms. + * The MAX_SOFTIRQ_TIME provides a nice upper bound in most cases, but in + * certain cases, such as stop_machine(), jiffies may cease to + * increment and so we need the MAX_SOFTIRQ_RESTART limit as + * well to make sure we eventually return from this method. + * + * These limits have been established via experimentation. + * The two things to balance is latency against fairness - + * we want to handle softirqs as soon as possible, but they + * should not be able to lock up the box. + */ +#define MAX_SOFTIRQ_TIME msecs_to_jiffies(2) +#define MAX_SOFTIRQ_RESTART 10 + +#ifdef CONFIG_TRACE_IRQFLAGS +/* + * When we run softirqs from irq_exit() and thus on the hardirq stack we need + * to keep the lockdep irq context tracking as tight as possible in order to + * not miss-qualify lock contexts and miss possible deadlocks. + */ + +static inline bool lockdep_softirq_start(void) +{ + bool in_hardirq = false; + + if (trace_hardirq_context(current)) { + in_hardirq = true; + trace_hardirq_exit(); + } + + lockdep_softirq_enter(); + + return in_hardirq; +} + +static inline void lockdep_softirq_end(bool in_hardirq) +{ + lockdep_softirq_exit(); + + if (in_hardirq) + trace_hardirq_enter(); +} +#else +static inline bool lockdep_softirq_start(void) { return false; } +static inline void lockdep_softirq_end(bool in_hardirq) { } +#endif + +asmlinkage __visible void __do_softirq(void) +{ + unsigned long end = jiffies + MAX_SOFTIRQ_TIME; + unsigned long old_flags = current->flags; + int max_restart = MAX_SOFTIRQ_RESTART; + bool in_hardirq; + __u32 pending; + + /* + * Mask out PF_MEMALLOC s current task context is borrowed for the + * softirq. A softirq handled such as network RX might set PF_MEMALLOC + * again if the socket is related to swap + */ + current->flags &= ~PF_MEMALLOC; + + pending = local_softirq_pending(); + account_irq_enter_time(current); + + __local_bh_disable_ip(_RET_IP_, SOFTIRQ_OFFSET); + in_hardirq = lockdep_softirq_start(); + +restart: + /* Reset the pending bitmask before enabling irqs */ + set_softirq_pending(0); + + handle_pending_softirqs(pending); + + pending = local_softirq_pending(); + if (pending) { + if (time_before(jiffies, end) && !need_resched() && + --max_restart) + goto restart; + + wakeup_softirqd(); + } + + lockdep_softirq_end(in_hardirq); + account_irq_exit_time(current); + __local_bh_enable(SOFTIRQ_OFFSET); + WARN_ON_ONCE(in_interrupt()); + tsk_restore_flags(current, old_flags, PF_MEMALLOC); +} + +asmlinkage __visible void do_softirq(void) +{ + __u32 pending; + unsigned long flags; + + if (in_interrupt()) + return; + + local_irq_save(flags); + + pending = local_softirq_pending(); + + if (pending) + do_softirq_own_stack(); + + local_irq_restore(flags); +} + +/* + * This function must run with irqs disabled! + */ +void raise_softirq_irqoff(unsigned int nr) +{ + __raise_softirq_irqoff(nr); + + /* + * If we're in an interrupt or softirq, we're done + * (this also catches softirq-disabled code). We will + * actually run the softirq once we return from + * the irq or softirq. + * + * Otherwise we wake up ksoftirqd to make sure we + * schedule the softirq soon. + */ + if (!in_interrupt()) + wakeup_softirqd(); +} + +void __raise_softirq_irqoff(unsigned int nr) +{ + trace_softirq_raise(nr); + or_softirq_pending(1UL << nr); +} + +static inline void local_bh_disable_nort(void) { local_bh_disable(); } +static inline void _local_bh_enable_nort(void) { _local_bh_enable(); } +static void ksoftirqd_set_sched_params(unsigned int cpu) { } +static void ksoftirqd_clr_sched_params(unsigned int cpu, bool online) { } + +#else /* !PREEMPT_RT_FULL */ + +/* + * On RT we serialize softirq execution with a cpu local lock per softirq + */ +static DEFINE_PER_CPU(struct local_irq_lock [NR_SOFTIRQS], local_softirq_locks); + +void __init softirq_early_init(void) +{ + int i; + + for (i = 0; i < NR_SOFTIRQS; i++) + local_irq_lock_init(local_softirq_locks[i]); +} + +static void lock_softirq(int which) +{ + local_lock(local_softirq_locks[which]); +} + +static void unlock_softirq(int which) +{ + local_unlock(local_softirq_locks[which]); +} + +static void do_single_softirq(int which) +{ + unsigned long old_flags = current->flags; + + current->flags &= ~PF_MEMALLOC; + vtime_account_irq_enter(current); + current->flags |= PF_IN_SOFTIRQ; + lockdep_softirq_enter(); + local_irq_enable(); + handle_softirq(which); + local_irq_disable(); + lockdep_softirq_exit(); + current->flags &= ~PF_IN_SOFTIRQ; + vtime_account_irq_enter(current); + tsk_restore_flags(current, old_flags, PF_MEMALLOC); +} + +/* + * Called with interrupts disabled. Process softirqs which were raised + * in current context (or on behalf of ksoftirqd). + */ +static void do_current_softirqs(void) +{ + while (current->softirqs_raised) { + int i = __ffs(current->softirqs_raised); + unsigned int pending, mask = (1U << i); + + current->softirqs_raised &= ~mask; + local_irq_enable(); + + /* + * If the lock is contended, we boost the owner to + * process the softirq or leave the critical section + * now. + */ + lock_softirq(i); + local_irq_disable(); + softirq_set_runner(i); + /* + * Check with the local_softirq_pending() bits, + * whether we need to process this still or if someone + * else took care of it. + */ + pending = local_softirq_pending(); + if (pending & mask) { + set_softirq_pending(pending & ~mask); + do_single_softirq(i); + } + softirq_clr_runner(i); + unlock_softirq(i); + WARN_ON(current->softirq_nestcnt != 1); + } +} + +static void __local_bh_disable(void) +{ + if (++current->softirq_nestcnt == 1) + migrate_disable(); +} + +void local_bh_disable(void) +{ + __local_bh_disable(); +} +EXPORT_SYMBOL(local_bh_disable); + +void __local_bh_disable_ip(unsigned long ip, unsigned int cnt) +{ + __local_bh_disable(); + if (cnt & PREEMPT_CHECK_OFFSET) + preempt_disable(); +} + +static void __local_bh_enable(void) +{ + if (WARN_ON(current->softirq_nestcnt == 0)) + return; + + local_irq_disable(); + if (current->softirq_nestcnt == 1 && current->softirqs_raised) + do_current_softirqs(); + local_irq_enable(); + + if (--current->softirq_nestcnt == 0) + migrate_enable(); +} + +void local_bh_enable(void) +{ + __local_bh_enable(); +} +EXPORT_SYMBOL(local_bh_enable); + +extern void __local_bh_enable_ip(unsigned long ip, unsigned int cnt) +{ + __local_bh_enable(); + if (cnt & PREEMPT_CHECK_OFFSET) + preempt_enable(); +} + +void local_bh_enable_ip(unsigned long ip) +{ + local_bh_enable(); +} +EXPORT_SYMBOL(local_bh_enable_ip); + +void _local_bh_enable(void) +{ + if (WARN_ON(current->softirq_nestcnt == 0)) + return; + if (--current->softirq_nestcnt == 0) + migrate_enable(); +} +EXPORT_SYMBOL(_local_bh_enable); + +int in_serving_softirq(void) +{ + return current->flags & PF_IN_SOFTIRQ; +} +EXPORT_SYMBOL(in_serving_softirq); + +/* Called with preemption disabled */ +static void run_ksoftirqd(unsigned int cpu) +{ + local_irq_disable(); + current->softirq_nestcnt++; + + do_current_softirqs(); + current->softirq_nestcnt--; + rcu_note_context_switch(); + local_irq_enable(); +} + +/* + * Called from netif_rx_ni(). Preemption enabled, but migration + * disabled. So the cpu can't go away under us. + */ +void thread_do_softirq(void) +{ + if (!in_serving_softirq() && current->softirqs_raised) { + current->softirq_nestcnt++; + do_current_softirqs(); + current->softirq_nestcnt--; + } +} + +static void do_raise_softirq_irqoff(unsigned int nr) +{ + trace_softirq_raise(nr); + or_softirq_pending(1UL << nr); + + /* + * If we are not in a hard interrupt and inside a bh disabled + * region, we simply raise the flag on current. local_bh_enable() + * will make sure that the softirq is executed. Otherwise we + * delegate it to ksoftirqd. + */ + if (!in_irq() && current->softirq_nestcnt) + current->softirqs_raised |= (1U << nr); + else if (__this_cpu_read(ksoftirqd)) + __this_cpu_read(ksoftirqd)->softirqs_raised |= (1U << nr); +} + +void __raise_softirq_irqoff(unsigned int nr) +{ + do_raise_softirq_irqoff(nr); + if (!in_irq() && !current->softirq_nestcnt) + wakeup_softirqd(); +} + +/* + * This function must run with irqs disabled! + */ +void raise_softirq_irqoff(unsigned int nr) +{ + do_raise_softirq_irqoff(nr); + + /* + * If we're in an hard interrupt we let irq return code deal + * with the wakeup of ksoftirqd. + */ + if (in_irq()) + return; + /* + * If we are in thread context but outside of a bh disabled + * region, we need to wake ksoftirqd as well. + * + * CHECKME: Some of the places which do that could be wrapped + * into local_bh_disable/enable pairs. Though it's unclear + * whether this is worth the effort. To find those places just + * raise a WARN() if the condition is met. + */ + if (!current->softirq_nestcnt) + wakeup_softirqd(); +} + +static inline int ksoftirqd_softirq_pending(void) +{ + return current->softirqs_raised; +} + +static inline void local_bh_disable_nort(void) { } +static inline void _local_bh_enable_nort(void) { } + +static inline void ksoftirqd_set_sched_params(unsigned int cpu) +{ + struct sched_param param = { .sched_priority = 1 }; + + sched_setscheduler(current, SCHED_FIFO, ¶m); + /* Take over all pending softirqs when starting */ + local_irq_disable(); + current->softirqs_raised = local_softirq_pending(); + local_irq_enable(); +} + +static inline void ksoftirqd_clr_sched_params(unsigned int cpu, bool online) +{ + struct sched_param param = { .sched_priority = 0 }; + + sched_setscheduler(current, SCHED_NORMAL, ¶m); +} + +#endif /* PREEMPT_RT_FULL */ +/* + * Enter an interrupt context. + */ +void irq_enter(void) +{ + rcu_irq_enter(); + if (is_idle_task(current) && !in_interrupt()) { + /* + * Prevent raise_softirq from needlessly waking up ksoftirqd + * here, as softirq will be serviced on return from interrupt. + */ + local_bh_disable_nort(); + tick_irq_enter(); + _local_bh_enable_nort(); + } + + __irq_enter(); +} + +static inline void invoke_softirq(void) +{ +#ifndef CONFIG_PREEMPT_RT_FULL + if (!force_irqthreads) { +#ifdef CONFIG_HAVE_IRQ_EXIT_ON_IRQ_STACK + /* + * We can safely execute softirq on the current stack if + * it is the irq stack, because it should be near empty + * at this stage. + */ + __do_softirq(); +#else + /* + * Otherwise, irq_exit() is called on the task stack that can + * be potentially deep already. So call softirq in its own stack + * to prevent from any overrun. + */ + do_softirq_own_stack(); +#endif + } else { + wakeup_softirqd(); + } +#else /* PREEMPT_RT_FULL */ + unsigned long flags; + + local_irq_save(flags); + if (__this_cpu_read(ksoftirqd) && + __this_cpu_read(ksoftirqd)->softirqs_raised) + wakeup_softirqd(); + local_irq_restore(flags); +#endif +} + +static inline void tick_irq_exit(void) +{ +#ifdef CONFIG_NO_HZ_COMMON + int cpu = smp_processor_id(); + + /* Make sure that timer wheel updates are propagated */ + if ((idle_cpu(cpu) && !need_resched()) || tick_nohz_full_cpu(cpu)) { + if (!in_interrupt()) + tick_nohz_irq_exit(); + } +#endif +} + +/* + * Exit an interrupt context. Process softirqs if needed and possible: + */ +void irq_exit(void) +{ +#ifndef __ARCH_IRQ_EXIT_IRQS_DISABLED + local_irq_disable(); +#else + WARN_ON_ONCE(!irqs_disabled()); +#endif + + account_irq_exit_time(current); + preempt_count_sub(HARDIRQ_OFFSET); + if (!in_interrupt() && local_softirq_pending()) + invoke_softirq(); + + tick_irq_exit(); + rcu_irq_exit(); + trace_hardirq_exit(); /* must be last! */ +} + +void raise_softirq(unsigned int nr) +{ + unsigned long flags; + + local_irq_save(flags); + raise_softirq_irqoff(nr); + local_irq_restore(flags); +} + +void open_softirq(int nr, void (*action)(struct softirq_action *)) +{ + softirq_vec[nr].action = action; +} + +/* + * Tasklets + */ +struct tasklet_head { + struct tasklet_struct *head; + struct tasklet_struct **tail; +}; + +static DEFINE_PER_CPU(struct tasklet_head, tasklet_vec); +static DEFINE_PER_CPU(struct tasklet_head, tasklet_hi_vec); + +static void inline +__tasklet_common_schedule(struct tasklet_struct *t, struct tasklet_head *head, unsigned int nr) +{ + if (tasklet_trylock(t)) { +again: + /* We may have been preempted before tasklet_trylock + * and __tasklet_action may have already run. + * So double check the sched bit while the takslet + * is locked before adding it to the list. + */ + if (test_bit(TASKLET_STATE_SCHED, &t->state)) { + t->next = NULL; + *head->tail = t; + head->tail = &(t->next); + raise_softirq_irqoff(nr); + tasklet_unlock(t); + } else { + /* This is subtle. If we hit the corner case above + * It is possible that we get preempted right here, + * and another task has successfully called + * tasklet_schedule(), then this function, and + * failed on the trylock. Thus we must be sure + * before releasing the tasklet lock, that the + * SCHED_BIT is clear. Otherwise the tasklet + * may get its SCHED_BIT set, but not added to the + * list + */ + if (!tasklet_tryunlock(t)) + goto again; + } + } +} + +void __tasklet_schedule(struct tasklet_struct *t) +{ + unsigned long flags; + + local_irq_save(flags); + __tasklet_common_schedule(t, this_cpu_ptr(&tasklet_vec), TASKLET_SOFTIRQ); + local_irq_restore(flags); +} +EXPORT_SYMBOL(__tasklet_schedule); + +void __tasklet_hi_schedule(struct tasklet_struct *t) +{ + unsigned long flags; + + local_irq_save(flags); + __tasklet_common_schedule(t, this_cpu_ptr(&tasklet_hi_vec), HI_SOFTIRQ); + local_irq_restore(flags); +} +EXPORT_SYMBOL(__tasklet_hi_schedule); + +void __tasklet_hi_schedule_first(struct tasklet_struct *t) +{ + BUG_ON(!irqs_disabled()); + + __tasklet_hi_schedule(t); +} +EXPORT_SYMBOL(__tasklet_hi_schedule_first); + +void tasklet_enable(struct tasklet_struct *t) +{ + if (!atomic_dec_and_test(&t->count)) + return; + if (test_and_clear_bit(TASKLET_STATE_PENDING, &t->state)) + tasklet_schedule(t); +} +EXPORT_SYMBOL(tasklet_enable); + +static void __tasklet_action(struct softirq_action *a, + struct tasklet_struct *list) +{ + int loops = 1000000; + + while (list) { + struct tasklet_struct *t = list; + + list = list->next; + + /* + * Should always succeed - after a tasklist got on the + * list (after getting the SCHED bit set from 0 to 1), + * nothing but the tasklet softirq it got queued to can + * lock it: + */ + if (!tasklet_trylock(t)) { + WARN_ON(1); + continue; + } + + t->next = NULL; + + /* + * If we cannot handle the tasklet because it's disabled, + * mark it as pending. tasklet_enable() will later + * re-schedule the tasklet. + */ + if (unlikely(atomic_read(&t->count))) { +out_disabled: + /* implicit unlock: */ + wmb(); + t->state = TASKLET_STATEF_PENDING; + continue; + } + + /* + * After this point on the tasklet might be rescheduled + * on another CPU, but it can only be added to another + * CPU's tasklet list if we unlock the tasklet (which we + * dont do yet). + */ + if (!test_and_clear_bit(TASKLET_STATE_SCHED, &t->state)) + WARN_ON(1); + +again: + t->func(t->data); + + /* + * Try to unlock the tasklet. We must use cmpxchg, because + * another CPU might have scheduled or disabled the tasklet. + * We only allow the STATE_RUN -> 0 transition here. + */ + while (!tasklet_tryunlock(t)) { + /* + * If it got disabled meanwhile, bail out: + */ + if (atomic_read(&t->count)) + goto out_disabled; + /* + * If it got scheduled meanwhile, re-execute + * the tasklet function: + */ + if (test_and_clear_bit(TASKLET_STATE_SCHED, &t->state)) + goto again; + if (!--loops) { + printk("hm, tasklet state: %08lx\n", t->state); + WARN_ON(1); + tasklet_unlock(t); + break; + } + } + } +} + +static void tasklet_action(struct softirq_action *a) +{ + struct tasklet_struct *list; + + local_irq_disable(); + + list = __this_cpu_read(tasklet_vec.head); + __this_cpu_write(tasklet_vec.head, NULL); + __this_cpu_write(tasklet_vec.tail, this_cpu_ptr(&tasklet_vec.head)); + + local_irq_enable(); + + __tasklet_action(a, list); +} + +static void tasklet_hi_action(struct softirq_action *a) +{ + struct tasklet_struct *list; + + local_irq_disable(); + + list = __this_cpu_read(tasklet_hi_vec.head); + __this_cpu_write(tasklet_hi_vec.head, NULL); + __this_cpu_write(tasklet_hi_vec.tail, this_cpu_ptr(&tasklet_hi_vec.head)); + + local_irq_enable(); + + __tasklet_action(a, list); +} + +void tasklet_init(struct tasklet_struct *t, + void (*func)(unsigned long), unsigned long data) +{ + t->next = NULL; + t->state = 0; + atomic_set(&t->count, 0); + t->func = func; + t->data = data; +} +EXPORT_SYMBOL(tasklet_init); + +void tasklet_kill(struct tasklet_struct *t) +{ + if (in_interrupt()) + pr_notice("Attempt to kill tasklet from interrupt\n"); + + while (test_and_set_bit(TASKLET_STATE_SCHED, &t->state)) { + do { + msleep(1); + } while (test_bit(TASKLET_STATE_SCHED, &t->state)); + } + tasklet_unlock_wait(t); + clear_bit(TASKLET_STATE_SCHED, &t->state); +} +EXPORT_SYMBOL(tasklet_kill); + +/* + * tasklet_hrtimer + */ + +/* + * The trampoline is called when the hrtimer expires. It schedules a tasklet + * to run __tasklet_hrtimer_trampoline() which in turn will call the intended + * hrtimer callback, but from softirq context. + */ +static enum hrtimer_restart __hrtimer_tasklet_trampoline(struct hrtimer *timer) +{ + struct tasklet_hrtimer *ttimer = + container_of(timer, struct tasklet_hrtimer, timer); + + tasklet_hi_schedule(&ttimer->tasklet); + return HRTIMER_NORESTART; +} + +/* + * Helper function which calls the hrtimer callback from + * tasklet/softirq context + */ +static void __tasklet_hrtimer_trampoline(unsigned long data) +{ + struct tasklet_hrtimer *ttimer = (void *)data; + enum hrtimer_restart restart; + + restart = ttimer->function(&ttimer->timer); + if (restart != HRTIMER_NORESTART) + hrtimer_restart(&ttimer->timer); +} + +/** + * tasklet_hrtimer_init - Init a tasklet/hrtimer combo for softirq callbacks + * @ttimer: tasklet_hrtimer which is initialized + * @function: hrtimer callback function which gets called from softirq context + * @which_clock: clock id (CLOCK_MONOTONIC/CLOCK_REALTIME) + * @mode: hrtimer mode (HRTIMER_MODE_ABS/HRTIMER_MODE_REL) + */ +void tasklet_hrtimer_init(struct tasklet_hrtimer *ttimer, + enum hrtimer_restart (*function)(struct hrtimer *), + clockid_t which_clock, enum hrtimer_mode mode) +{ + hrtimer_init(&ttimer->timer, which_clock, mode); + ttimer->timer.function = __hrtimer_tasklet_trampoline; + tasklet_init(&ttimer->tasklet, __tasklet_hrtimer_trampoline, + (unsigned long)ttimer); + ttimer->function = function; +} +EXPORT_SYMBOL_GPL(tasklet_hrtimer_init); + +void __init softirq_init(void) +{ + int cpu; + + for_each_possible_cpu(cpu) { + per_cpu(tasklet_vec, cpu).tail = + &per_cpu(tasklet_vec, cpu).head; + per_cpu(tasklet_hi_vec, cpu).tail = + &per_cpu(tasklet_hi_vec, cpu).head; + } + + open_softirq(TASKLET_SOFTIRQ, tasklet_action); + open_softirq(HI_SOFTIRQ, tasklet_hi_action); +} + +#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT_FULL) +void tasklet_unlock_wait(struct tasklet_struct *t) +{ + while (test_bit(TASKLET_STATE_RUN, &(t)->state)) { + /* + * Hack for now to avoid this busy-loop: + */ +#ifdef CONFIG_PREEMPT_RT_FULL + msleep(1); +#else + barrier(); +#endif + } +} +EXPORT_SYMBOL(tasklet_unlock_wait); +#endif + +static int ksoftirqd_should_run(unsigned int cpu) +{ + return ksoftirqd_softirq_pending(); +} + +#ifdef CONFIG_HOTPLUG_CPU +/* + * tasklet_kill_immediate is called to remove a tasklet which can already be + * scheduled for execution on @cpu. + * + * Unlike tasklet_kill, this function removes the tasklet + * _immediately_, even if the tasklet is in TASKLET_STATE_SCHED state. + * + * When this function is called, @cpu must be in the CPU_DEAD state. + */ +void tasklet_kill_immediate(struct tasklet_struct *t, unsigned int cpu) +{ + struct tasklet_struct **i; + + BUG_ON(cpu_online(cpu)); + BUG_ON(test_bit(TASKLET_STATE_RUN, &t->state)); + + if (!test_bit(TASKLET_STATE_SCHED, &t->state)) + return; + + /* CPU is dead, so no lock needed. */ + for (i = &per_cpu(tasklet_vec, cpu).head; *i; i = &(*i)->next) { + if (*i == t) { + *i = t->next; + /* If this was the tail element, move the tail ptr */ + if (*i == NULL) + per_cpu(tasklet_vec, cpu).tail = i; + return; + } + } + BUG(); +} + +static void takeover_tasklets(unsigned int cpu) +{ + /* CPU is dead, so no lock needed. */ + local_irq_disable(); + + /* Find end, append list for that CPU. */ + if (&per_cpu(tasklet_vec, cpu).head != per_cpu(tasklet_vec, cpu).tail) { + *__this_cpu_read(tasklet_vec.tail) = per_cpu(tasklet_vec, cpu).head; + this_cpu_write(tasklet_vec.tail, per_cpu(tasklet_vec, cpu).tail); + per_cpu(tasklet_vec, cpu).head = NULL; + per_cpu(tasklet_vec, cpu).tail = &per_cpu(tasklet_vec, cpu).head; + } + raise_softirq_irqoff(TASKLET_SOFTIRQ); + + if (&per_cpu(tasklet_hi_vec, cpu).head != per_cpu(tasklet_hi_vec, cpu).tail) { + *__this_cpu_read(tasklet_hi_vec.tail) = per_cpu(tasklet_hi_vec, cpu).head; + __this_cpu_write(tasklet_hi_vec.tail, per_cpu(tasklet_hi_vec, cpu).tail); + per_cpu(tasklet_hi_vec, cpu).head = NULL; + per_cpu(tasklet_hi_vec, cpu).tail = &per_cpu(tasklet_hi_vec, cpu).head; + } + raise_softirq_irqoff(HI_SOFTIRQ); + + local_irq_enable(); +} +#endif /* CONFIG_HOTPLUG_CPU */ + +static int cpu_callback(struct notifier_block *nfb, unsigned long action, + void *hcpu) +{ + switch (action) { +#ifdef CONFIG_HOTPLUG_CPU + case CPU_DEAD: + case CPU_DEAD_FROZEN: + takeover_tasklets((unsigned long)hcpu); + break; +#endif /* CONFIG_HOTPLUG_CPU */ + } + return NOTIFY_OK; +} + +static struct notifier_block cpu_nfb = { + .notifier_call = cpu_callback +}; + +static struct smp_hotplug_thread softirq_threads = { + .store = &ksoftirqd, + .setup = ksoftirqd_set_sched_params, + .cleanup = ksoftirqd_clr_sched_params, + .thread_should_run = ksoftirqd_should_run, + .thread_fn = run_ksoftirqd, + .thread_comm = "ksoftirqd/%u", +}; + +static __init int spawn_ksoftirqd(void) +{ + register_cpu_notifier(&cpu_nfb); + + BUG_ON(smpboot_register_percpu_thread(&softirq_threads)); + + return 0; +} +early_initcall(spawn_ksoftirqd); + +/* + * [ These __weak aliases are kept in a separate compilation unit, so that + * GCC does not inline them incorrectly. ] + */ + +int __init __weak early_irq_init(void) +{ + return 0; +} + +int __init __weak arch_probe_nr_irqs(void) +{ + return NR_IRQS_LEGACY; +} + +int __init __weak arch_early_irq_init(void) +{ + return 0; +} + +unsigned int __weak arch_dynirq_lower_bound(unsigned int from) +{ + return from; +} diff --git a/kernel/kernel/stacktrace.c b/kernel/kernel/stacktrace.c new file mode 100644 index 000000000..b6e4c1637 --- /dev/null +++ b/kernel/kernel/stacktrace.c @@ -0,0 +1,75 @@ +/* + * kernel/stacktrace.c + * + * Stack trace management functions + * + * Copyright (C) 2006 Red Hat, Inc., Ingo Molnar + */ +#include +#include +#include +#include +#include + +void print_stack_trace(struct stack_trace *trace, int spaces) +{ + int i; + + if (WARN_ON(!trace->entries)) + return; + + for (i = 0; i < trace->nr_entries; i++) { + printk("%*c", 1 + spaces, ' '); + print_ip_sym(trace->entries[i]); + } +} +EXPORT_SYMBOL_GPL(print_stack_trace); + +int snprint_stack_trace(char *buf, size_t size, + struct stack_trace *trace, int spaces) +{ + int i; + unsigned long ip; + int generated; + int total = 0; + + if (WARN_ON(!trace->entries)) + return 0; + + for (i = 0; i < trace->nr_entries; i++) { + ip = trace->entries[i]; + generated = snprintf(buf, size, "%*c[<%p>] %pS\n", + 1 + spaces, ' ', (void *) ip, (void *) ip); + + total += generated; + + /* Assume that generated isn't a negative number */ + if (generated >= size) { + buf += size; + size = 0; + } else { + buf += generated; + size -= generated; + } + } + + return total; +} +EXPORT_SYMBOL_GPL(snprint_stack_trace); + +/* + * Architectures that do not implement save_stack_trace_tsk or + * save_stack_trace_regs get this weak alias and a once-per-bootup warning + * (whenever this facility is utilized - for example by procfs): + */ +__weak void +save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace) +{ + WARN_ONCE(1, KERN_INFO "save_stack_trace_tsk() not implemented yet.\n"); +} + +__weak void +save_stack_trace_regs(struct pt_regs *regs, struct stack_trace *trace) +{ + WARN_ONCE(1, KERN_INFO "save_stack_trace_regs() not implemented yet.\n"); +} diff --git a/kernel/kernel/stop_machine.c b/kernel/kernel/stop_machine.c new file mode 100644 index 000000000..1af29ad20 --- /dev/null +++ b/kernel/kernel/stop_machine.c @@ -0,0 +1,686 @@ +/* + * kernel/stop_machine.c + * + * Copyright (C) 2008, 2005 IBM Corporation. + * Copyright (C) 2008, 2005 Rusty Russell rusty@rustcorp.com.au + * Copyright (C) 2010 SUSE Linux Products GmbH + * Copyright (C) 2010 Tejun Heo + * + * This file is released under the GPLv2 and any later version. + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +/* + * Structure to determine completion condition and record errors. May + * be shared by works on different cpus. + */ +struct cpu_stop_done { + atomic_t nr_todo; /* nr left to execute */ + bool executed; /* actually executed? */ + int ret; /* collected return value */ + struct task_struct *waiter; /* woken when nr_todo reaches 0 */ +}; + +/* the actual stopper, one per every possible cpu, enabled on online cpus */ +struct cpu_stopper { + raw_spinlock_t lock; + bool enabled; /* is this stopper enabled? */ + struct list_head works; /* list of pending works */ +}; + +static DEFINE_PER_CPU(struct cpu_stopper, cpu_stopper); +static DEFINE_PER_CPU(struct task_struct *, cpu_stopper_task); +static bool stop_machine_initialized = false; + +/* + * Avoids a race between stop_two_cpus and global stop_cpus, where + * the stoppers could get queued up in reverse order, leading to + * system deadlock. Using an lglock means stop_two_cpus remains + * relatively cheap. + */ +DEFINE_STATIC_LGLOCK(stop_cpus_lock); + +static void cpu_stop_init_done(struct cpu_stop_done *done, unsigned int nr_todo) +{ + memset(done, 0, sizeof(*done)); + atomic_set(&done->nr_todo, nr_todo); + done->waiter = current; +} + +/* signal completion unless @done is NULL */ +static void cpu_stop_signal_done(struct cpu_stop_done *done, bool executed) +{ + if (done) { + if (executed) + done->executed = true; + if (atomic_dec_and_test(&done->nr_todo)) { + wake_up_process(done->waiter); + done->waiter = NULL; + } + } +} + +/* queue @work to @stopper. if offline, @work is completed immediately */ +static void cpu_stop_queue_work(unsigned int cpu, struct cpu_stop_work *work) +{ + struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu); + struct task_struct *p = per_cpu(cpu_stopper_task, cpu); + + unsigned long flags; + + raw_spin_lock_irqsave(&stopper->lock, flags); + + if (stopper->enabled) { + list_add_tail(&work->list, &stopper->works); + wake_up_process(p); + } else + cpu_stop_signal_done(work->done, false); + + raw_spin_unlock_irqrestore(&stopper->lock, flags); +} + +static void wait_for_stop_done(struct cpu_stop_done *done) +{ + set_current_state(TASK_UNINTERRUPTIBLE); + while (atomic_read(&done->nr_todo)) { + schedule(); + set_current_state(TASK_UNINTERRUPTIBLE); + } + /* + * We need to wait until cpu_stop_signal_done() has cleared + * done->waiter. + */ + while (done->waiter) + cpu_relax(); + set_current_state(TASK_RUNNING); +} + +/** + * stop_one_cpu - stop a cpu + * @cpu: cpu to stop + * @fn: function to execute + * @arg: argument to @fn + * + * Execute @fn(@arg) on @cpu. @fn is run in a process context with + * the highest priority preempting any task on the cpu and + * monopolizing it. This function returns after the execution is + * complete. + * + * This function doesn't guarantee @cpu stays online till @fn + * completes. If @cpu goes down in the middle, execution may happen + * partially or fully on different cpus. @fn should either be ready + * for that or the caller should ensure that @cpu stays online until + * this function completes. + * + * CONTEXT: + * Might sleep. + * + * RETURNS: + * -ENOENT if @fn(@arg) was not executed because @cpu was offline; + * otherwise, the return value of @fn. + */ +int stop_one_cpu(unsigned int cpu, cpu_stop_fn_t fn, void *arg) +{ + struct cpu_stop_done done; + struct cpu_stop_work work = { .fn = fn, .arg = arg, .done = &done }; + + cpu_stop_init_done(&done, 1); + cpu_stop_queue_work(cpu, &work); + wait_for_stop_done(&done); + return done.executed ? done.ret : -ENOENT; +} + +/* This controls the threads on each CPU. */ +enum multi_stop_state { + /* Dummy starting state for thread. */ + MULTI_STOP_NONE, + /* Awaiting everyone to be scheduled. */ + MULTI_STOP_PREPARE, + /* Disable interrupts. */ + MULTI_STOP_DISABLE_IRQ, + /* Run the function */ + MULTI_STOP_RUN, + /* Exit */ + MULTI_STOP_EXIT, +}; + +struct multi_stop_data { + int (*fn)(void *); + void *data; + /* Like num_online_cpus(), but hotplug cpu uses us, so we need this. */ + unsigned int num_threads; + const struct cpumask *active_cpus; + + enum multi_stop_state state; + atomic_t thread_ack; +}; + +static void set_state(struct multi_stop_data *msdata, + enum multi_stop_state newstate) +{ + /* Reset ack counter. */ + atomic_set(&msdata->thread_ack, msdata->num_threads); + smp_wmb(); + msdata->state = newstate; +} + +/* Last one to ack a state moves to the next state. */ +static void ack_state(struct multi_stop_data *msdata) +{ + if (atomic_dec_and_test(&msdata->thread_ack)) + set_state(msdata, msdata->state + 1); +} + +/* This is the cpu_stop function which stops the CPU. */ +static int multi_cpu_stop(void *data) +{ + struct multi_stop_data *msdata = data; + enum multi_stop_state curstate = MULTI_STOP_NONE; + int cpu = smp_processor_id(), err = 0; + unsigned long flags; + bool is_active; + + /* + * When called from stop_machine_from_inactive_cpu(), irq might + * already be disabled. Save the state and restore it on exit. + */ + local_save_flags(flags); + + if (!msdata->active_cpus) + is_active = cpu == cpumask_first(cpu_online_mask); + else + is_active = cpumask_test_cpu(cpu, msdata->active_cpus); + + /* Simple state machine */ + do { + /* Chill out and ensure we re-read multi_stop_state. */ + cpu_relax(); + if (msdata->state != curstate) { + curstate = msdata->state; + switch (curstate) { + case MULTI_STOP_DISABLE_IRQ: + local_irq_disable(); + hard_irq_disable(); + break; + case MULTI_STOP_RUN: + if (is_active) + err = msdata->fn(msdata->data); + break; + default: + break; + } + ack_state(msdata); + } + } while (curstate != MULTI_STOP_EXIT); + + local_irq_restore(flags); + return err; +} + +struct irq_cpu_stop_queue_work_info { + int cpu1; + int cpu2; + struct cpu_stop_work *work1; + struct cpu_stop_work *work2; +}; + +/* + * This function is always run with irqs and preemption disabled. + * This guarantees that both work1 and work2 get queued, before + * our local migrate thread gets the chance to preempt us. + */ +static void irq_cpu_stop_queue_work(void *arg) +{ + struct irq_cpu_stop_queue_work_info *info = arg; + cpu_stop_queue_work(info->cpu1, info->work1); + cpu_stop_queue_work(info->cpu2, info->work2); +} + +/** + * stop_two_cpus - stops two cpus + * @cpu1: the cpu to stop + * @cpu2: the other cpu to stop + * @fn: function to execute + * @arg: argument to @fn + * + * Stops both the current and specified CPU and runs @fn on one of them. + * + * returns when both are completed. + */ +int stop_two_cpus(unsigned int cpu1, unsigned int cpu2, cpu_stop_fn_t fn, void *arg) +{ + struct cpu_stop_done done; + struct cpu_stop_work work1, work2; + struct irq_cpu_stop_queue_work_info call_args; + struct multi_stop_data msdata; + + preempt_disable_nort(); + msdata = (struct multi_stop_data){ + .fn = fn, + .data = arg, + .num_threads = 2, + .active_cpus = cpumask_of(cpu1), + }; + + work1 = work2 = (struct cpu_stop_work){ + .fn = multi_cpu_stop, + .arg = &msdata, + .done = &done + }; + + call_args = (struct irq_cpu_stop_queue_work_info){ + .cpu1 = cpu1, + .cpu2 = cpu2, + .work1 = &work1, + .work2 = &work2, + }; + + cpu_stop_init_done(&done, 2); + set_state(&msdata, MULTI_STOP_PREPARE); + + /* + * If we observe both CPUs active we know _cpu_down() cannot yet have + * queued its stop_machine works and therefore ours will get executed + * first. Or its not either one of our CPUs that's getting unplugged, + * in which case we don't care. + * + * This relies on the stopper workqueues to be FIFO. + */ + if (!cpu_active(cpu1) || !cpu_active(cpu2)) { + preempt_enable_nort(); + return -ENOENT; + } + + lg_local_lock(&stop_cpus_lock); + /* + * Queuing needs to be done by the lowest numbered CPU, to ensure + * that works are always queued in the same order on every CPU. + * This prevents deadlocks. + */ + smp_call_function_single(min(cpu1, cpu2), + &irq_cpu_stop_queue_work, + &call_args, 1); + lg_local_unlock(&stop_cpus_lock); + preempt_enable_nort(); + + wait_for_stop_done(&done); + + return done.executed ? done.ret : -ENOENT; +} + +/** + * stop_one_cpu_nowait - stop a cpu but don't wait for completion + * @cpu: cpu to stop + * @fn: function to execute + * @arg: argument to @fn + * @work_buf: pointer to cpu_stop_work structure + * + * Similar to stop_one_cpu() but doesn't wait for completion. The + * caller is responsible for ensuring @work_buf is currently unused + * and will remain untouched until stopper starts executing @fn. + * + * CONTEXT: + * Don't care. + */ +void stop_one_cpu_nowait(unsigned int cpu, cpu_stop_fn_t fn, void *arg, + struct cpu_stop_work *work_buf) +{ + *work_buf = (struct cpu_stop_work){ .fn = fn, .arg = arg, }; + cpu_stop_queue_work(cpu, work_buf); +} + +/* static data for stop_cpus */ +static DEFINE_MUTEX(stop_cpus_mutex); +static DEFINE_PER_CPU(struct cpu_stop_work, stop_cpus_work); + +static void queue_stop_cpus_work(const struct cpumask *cpumask, + cpu_stop_fn_t fn, void *arg, + struct cpu_stop_done *done, bool inactive) +{ + struct cpu_stop_work *work; + unsigned int cpu; + + /* initialize works and done */ + for_each_cpu(cpu, cpumask) { + work = &per_cpu(stop_cpus_work, cpu); + work->fn = fn; + work->arg = arg; + work->done = done; + } + + /* + * Make sure that all work is queued on all cpus before + * any of the cpus can execute it. + */ + if (!inactive) + lg_global_lock(&stop_cpus_lock); + else + lg_global_trylock_relax(&stop_cpus_lock); + for_each_cpu(cpu, cpumask) + cpu_stop_queue_work(cpu, &per_cpu(stop_cpus_work, cpu)); + lg_global_unlock(&stop_cpus_lock); +} + +static int __stop_cpus(const struct cpumask *cpumask, + cpu_stop_fn_t fn, void *arg) +{ + struct cpu_stop_done done; + + cpu_stop_init_done(&done, cpumask_weight(cpumask)); + queue_stop_cpus_work(cpumask, fn, arg, &done, false); + wait_for_stop_done(&done); + return done.executed ? done.ret : -ENOENT; +} + +/** + * stop_cpus - stop multiple cpus + * @cpumask: cpus to stop + * @fn: function to execute + * @arg: argument to @fn + * + * Execute @fn(@arg) on online cpus in @cpumask. On each target cpu, + * @fn is run in a process context with the highest priority + * preempting any task on the cpu and monopolizing it. This function + * returns after all executions are complete. + * + * This function doesn't guarantee the cpus in @cpumask stay online + * till @fn completes. If some cpus go down in the middle, execution + * on the cpu may happen partially or fully on different cpus. @fn + * should either be ready for that or the caller should ensure that + * the cpus stay online until this function completes. + * + * All stop_cpus() calls are serialized making it safe for @fn to wait + * for all cpus to start executing it. + * + * CONTEXT: + * Might sleep. + * + * RETURNS: + * -ENOENT if @fn(@arg) was not executed at all because all cpus in + * @cpumask were offline; otherwise, 0 if all executions of @fn + * returned 0, any non zero return value if any returned non zero. + */ +int stop_cpus(const struct cpumask *cpumask, cpu_stop_fn_t fn, void *arg) +{ + int ret; + + /* static works are used, process one request at a time */ + mutex_lock(&stop_cpus_mutex); + ret = __stop_cpus(cpumask, fn, arg); + mutex_unlock(&stop_cpus_mutex); + return ret; +} + +/** + * try_stop_cpus - try to stop multiple cpus + * @cpumask: cpus to stop + * @fn: function to execute + * @arg: argument to @fn + * + * Identical to stop_cpus() except that it fails with -EAGAIN if + * someone else is already using the facility. + * + * CONTEXT: + * Might sleep. + * + * RETURNS: + * -EAGAIN if someone else is already stopping cpus, -ENOENT if + * @fn(@arg) was not executed at all because all cpus in @cpumask were + * offline; otherwise, 0 if all executions of @fn returned 0, any non + * zero return value if any returned non zero. + */ +int try_stop_cpus(const struct cpumask *cpumask, cpu_stop_fn_t fn, void *arg) +{ + int ret; + + /* static works are used, process one request at a time */ + if (!mutex_trylock(&stop_cpus_mutex)) + return -EAGAIN; + ret = __stop_cpus(cpumask, fn, arg); + mutex_unlock(&stop_cpus_mutex); + return ret; +} + +static int cpu_stop_should_run(unsigned int cpu) +{ + struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu); + unsigned long flags; + int run; + + raw_spin_lock_irqsave(&stopper->lock, flags); + run = !list_empty(&stopper->works); + raw_spin_unlock_irqrestore(&stopper->lock, flags); + return run; +} + +static void cpu_stopper_thread(unsigned int cpu) +{ + struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu); + struct cpu_stop_work *work; + int ret; + +repeat: + work = NULL; + raw_spin_lock_irq(&stopper->lock); + if (!list_empty(&stopper->works)) { + work = list_first_entry(&stopper->works, + struct cpu_stop_work, list); + list_del_init(&work->list); + } + raw_spin_unlock_irq(&stopper->lock); + + if (work) { + cpu_stop_fn_t fn = work->fn; + void *arg = work->arg; + struct cpu_stop_done *done = work->done; + char ksym_buf[KSYM_NAME_LEN] __maybe_unused; + + /* + * Wait until the stopper finished scheduling on all + * cpus + */ + lg_global_lock(&stop_cpus_lock); + /* + * Let other cpu threads continue as well + */ + lg_global_unlock(&stop_cpus_lock); + + /* cpu stop callbacks are not allowed to sleep */ + preempt_disable(); + + ret = fn(arg); + if (ret) + done->ret = ret; + + /* restore preemption and check it's still balanced */ + preempt_enable(); + WARN_ONCE(preempt_count(), + "cpu_stop: %s(%p) leaked preempt count\n", + kallsyms_lookup((unsigned long)fn, NULL, NULL, NULL, + ksym_buf), arg); + + /* + * Make sure that the wakeup and setting done->waiter + * to NULL is atomic. + */ + local_irq_disable(); + cpu_stop_signal_done(done, true); + local_irq_enable(); + goto repeat; + } +} + +extern void sched_set_stop_task(int cpu, struct task_struct *stop); + +static void cpu_stop_create(unsigned int cpu) +{ + sched_set_stop_task(cpu, per_cpu(cpu_stopper_task, cpu)); +} + +static void cpu_stop_park(unsigned int cpu) +{ + struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu); + struct cpu_stop_work *work; + unsigned long flags; + + /* drain remaining works */ + raw_spin_lock_irqsave(&stopper->lock, flags); + list_for_each_entry(work, &stopper->works, list) + cpu_stop_signal_done(work->done, false); + stopper->enabled = false; + raw_spin_unlock_irqrestore(&stopper->lock, flags); +} + +static void cpu_stop_unpark(unsigned int cpu) +{ + struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu); + + raw_spin_lock_irq(&stopper->lock); + stopper->enabled = true; + raw_spin_unlock_irq(&stopper->lock); +} + +static struct smp_hotplug_thread cpu_stop_threads = { + .store = &cpu_stopper_task, + .thread_should_run = cpu_stop_should_run, + .thread_fn = cpu_stopper_thread, + .thread_comm = "migration/%u", + .create = cpu_stop_create, + .setup = cpu_stop_unpark, + .park = cpu_stop_park, + .pre_unpark = cpu_stop_unpark, + .selfparking = true, +}; + +static int __init cpu_stop_init(void) +{ + unsigned int cpu; + + for_each_possible_cpu(cpu) { + struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu); + + raw_spin_lock_init(&stopper->lock); + INIT_LIST_HEAD(&stopper->works); + } + + lg_lock_init(&stop_cpus_lock, "stop_cpus_lock"); + + BUG_ON(smpboot_register_percpu_thread(&cpu_stop_threads)); + stop_machine_initialized = true; + return 0; +} +early_initcall(cpu_stop_init); + +#ifdef CONFIG_STOP_MACHINE + +int __stop_machine(int (*fn)(void *), void *data, const struct cpumask *cpus) +{ + struct multi_stop_data msdata = { + .fn = fn, + .data = data, + .num_threads = num_online_cpus(), + .active_cpus = cpus, + }; + + if (!stop_machine_initialized) { + /* + * Handle the case where stop_machine() is called + * early in boot before stop_machine() has been + * initialized. + */ + unsigned long flags; + int ret; + + WARN_ON_ONCE(msdata.num_threads != 1); + + local_irq_save(flags); + hard_irq_disable(); + ret = (*fn)(data); + local_irq_restore(flags); + + return ret; + } + + /* Set the initial state and stop all online cpus. */ + set_state(&msdata, MULTI_STOP_PREPARE); + return stop_cpus(cpu_online_mask, multi_cpu_stop, &msdata); +} + +int stop_machine(int (*fn)(void *), void *data, const struct cpumask *cpus) +{ + int ret; + + /* No CPUs can come up or down during this. */ + get_online_cpus(); + ret = __stop_machine(fn, data, cpus); + put_online_cpus(); + return ret; +} +EXPORT_SYMBOL_GPL(stop_machine); + +/** + * stop_machine_from_inactive_cpu - stop_machine() from inactive CPU + * @fn: the function to run + * @data: the data ptr for the @fn() + * @cpus: the cpus to run the @fn() on (NULL = any online cpu) + * + * This is identical to stop_machine() but can be called from a CPU which + * is not active. The local CPU is in the process of hotplug (so no other + * CPU hotplug can start) and not marked active and doesn't have enough + * context to sleep. + * + * This function provides stop_machine() functionality for such state by + * using busy-wait for synchronization and executing @fn directly for local + * CPU. + * + * CONTEXT: + * Local CPU is inactive. Temporarily stops all active CPUs. + * + * RETURNS: + * 0 if all executions of @fn returned 0, any non zero return value if any + * returned non zero. + */ +int stop_machine_from_inactive_cpu(int (*fn)(void *), void *data, + const struct cpumask *cpus) +{ + struct multi_stop_data msdata = { .fn = fn, .data = data, + .active_cpus = cpus }; + struct cpu_stop_done done; + int ret; + + /* Local CPU must be inactive and CPU hotplug in progress. */ + BUG_ON(cpu_active(raw_smp_processor_id())); + msdata.num_threads = num_active_cpus() + 1; /* +1 for local */ + + /* No proper task established and can't sleep - busy wait for lock. */ + while (!mutex_trylock(&stop_cpus_mutex)) + cpu_relax(); + + /* Schedule work on other CPUs and execute directly for local CPU */ + set_state(&msdata, MULTI_STOP_PREPARE); + cpu_stop_init_done(&done, num_active_cpus()); + queue_stop_cpus_work(cpu_active_mask, multi_cpu_stop, &msdata, + &done, true); + ret = multi_cpu_stop(&msdata); + + /* Busy wait for completion. */ + while (atomic_read(&done.nr_todo)) + cpu_relax(); + + mutex_unlock(&stop_cpus_mutex); + return ret ?: done.ret; +} + +#endif /* CONFIG_STOP_MACHINE */ diff --git a/kernel/kernel/sys.c b/kernel/kernel/sys.c new file mode 100644 index 000000000..a4e372b79 --- /dev/null +++ b/kernel/kernel/sys.c @@ -0,0 +1,2408 @@ +/* + * linux/kernel/sys.c + * + * Copyright (C) 1991, 1992 Linus Torvalds + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include + +#include +#include +#include +#include + +#include +/* Move somewhere else to avoid recompiling? */ +#include + +#include +#include +#include + +#ifndef SET_UNALIGN_CTL +# define SET_UNALIGN_CTL(a, b) (-EINVAL) +#endif +#ifndef GET_UNALIGN_CTL +# define GET_UNALIGN_CTL(a, b) (-EINVAL) +#endif +#ifndef SET_FPEMU_CTL +# define SET_FPEMU_CTL(a, b) (-EINVAL) +#endif +#ifndef GET_FPEMU_CTL +# define GET_FPEMU_CTL(a, b) (-EINVAL) +#endif +#ifndef SET_FPEXC_CTL +# define SET_FPEXC_CTL(a, b) (-EINVAL) +#endif +#ifndef GET_FPEXC_CTL +# define GET_FPEXC_CTL(a, b) (-EINVAL) +#endif +#ifndef GET_ENDIAN +# define GET_ENDIAN(a, b) (-EINVAL) +#endif +#ifndef SET_ENDIAN +# define SET_ENDIAN(a, b) (-EINVAL) +#endif +#ifndef GET_TSC_CTL +# define GET_TSC_CTL(a) (-EINVAL) +#endif +#ifndef SET_TSC_CTL +# define SET_TSC_CTL(a) (-EINVAL) +#endif +#ifndef MPX_ENABLE_MANAGEMENT +# define MPX_ENABLE_MANAGEMENT(a) (-EINVAL) +#endif +#ifndef MPX_DISABLE_MANAGEMENT +# define MPX_DISABLE_MANAGEMENT(a) (-EINVAL) +#endif +#ifndef GET_FP_MODE +# define GET_FP_MODE(a) (-EINVAL) +#endif +#ifndef SET_FP_MODE +# define SET_FP_MODE(a,b) (-EINVAL) +#endif + +/* + * this is where the system-wide overflow UID and GID are defined, for + * architectures that now have 32-bit UID/GID but didn't in the past + */ + +int overflowuid = DEFAULT_OVERFLOWUID; +int overflowgid = DEFAULT_OVERFLOWGID; + +EXPORT_SYMBOL(overflowuid); +EXPORT_SYMBOL(overflowgid); + +/* + * the same as above, but for filesystems which can only store a 16-bit + * UID and GID. as such, this is needed on all architectures + */ + +int fs_overflowuid = DEFAULT_FS_OVERFLOWUID; +int fs_overflowgid = DEFAULT_FS_OVERFLOWUID; + +EXPORT_SYMBOL(fs_overflowuid); +EXPORT_SYMBOL(fs_overflowgid); + +/* + * Returns true if current's euid is same as p's uid or euid, + * or has CAP_SYS_NICE to p's user_ns. + * + * Called with rcu_read_lock, creds are safe + */ +static bool set_one_prio_perm(struct task_struct *p) +{ + const struct cred *cred = current_cred(), *pcred = __task_cred(p); + + if (uid_eq(pcred->uid, cred->euid) || + uid_eq(pcred->euid, cred->euid)) + return true; + if (ns_capable(pcred->user_ns, CAP_SYS_NICE)) + return true; + return false; +} + +/* + * set the priority of a task + * - the caller must hold the RCU read lock + */ +static int set_one_prio(struct task_struct *p, int niceval, int error) +{ + int no_nice; + + if (!set_one_prio_perm(p)) { + error = -EPERM; + goto out; + } + if (niceval < task_nice(p) && !can_nice(p, niceval)) { + error = -EACCES; + goto out; + } + no_nice = security_task_setnice(p, niceval); + if (no_nice) { + error = no_nice; + goto out; + } + if (error == -ESRCH) + error = 0; + set_user_nice(p, niceval); +out: + return error; +} + +SYSCALL_DEFINE3(setpriority, int, which, int, who, int, niceval) +{ + struct task_struct *g, *p; + struct user_struct *user; + const struct cred *cred = current_cred(); + int error = -EINVAL; + struct pid *pgrp; + kuid_t uid; + + if (which > PRIO_USER || which < PRIO_PROCESS) + goto out; + + /* normalize: avoid signed division (rounding problems) */ + error = -ESRCH; + if (niceval < MIN_NICE) + niceval = MIN_NICE; + if (niceval > MAX_NICE) + niceval = MAX_NICE; + + rcu_read_lock(); + read_lock(&tasklist_lock); + switch (which) { + case PRIO_PROCESS: + if (who) + p = find_task_by_vpid(who); + else + p = current; + if (p) + error = set_one_prio(p, niceval, error); + break; + case PRIO_PGRP: + if (who) + pgrp = find_vpid(who); + else + pgrp = task_pgrp(current); + do_each_pid_thread(pgrp, PIDTYPE_PGID, p) { + error = set_one_prio(p, niceval, error); + } while_each_pid_thread(pgrp, PIDTYPE_PGID, p); + break; + case PRIO_USER: + uid = make_kuid(cred->user_ns, who); + user = cred->user; + if (!who) + uid = cred->uid; + else if (!uid_eq(uid, cred->uid)) { + user = find_user(uid); + if (!user) + goto out_unlock; /* No processes for this user */ + } + do_each_thread(g, p) { + if (uid_eq(task_uid(p), uid)) + error = set_one_prio(p, niceval, error); + } while_each_thread(g, p); + if (!uid_eq(uid, cred->uid)) + free_uid(user); /* For find_user() */ + break; + } +out_unlock: + read_unlock(&tasklist_lock); + rcu_read_unlock(); +out: + return error; +} + +/* + * Ugh. To avoid negative return values, "getpriority()" will + * not return the normal nice-value, but a negated value that + * has been offset by 20 (ie it returns 40..1 instead of -20..19) + * to stay compatible. + */ +SYSCALL_DEFINE2(getpriority, int, which, int, who) +{ + struct task_struct *g, *p; + struct user_struct *user; + const struct cred *cred = current_cred(); + long niceval, retval = -ESRCH; + struct pid *pgrp; + kuid_t uid; + + if (which > PRIO_USER || which < PRIO_PROCESS) + return -EINVAL; + + rcu_read_lock(); + read_lock(&tasklist_lock); + switch (which) { + case PRIO_PROCESS: + if (who) + p = find_task_by_vpid(who); + else + p = current; + if (p) { + niceval = nice_to_rlimit(task_nice(p)); + if (niceval > retval) + retval = niceval; + } + break; + case PRIO_PGRP: + if (who) + pgrp = find_vpid(who); + else + pgrp = task_pgrp(current); + do_each_pid_thread(pgrp, PIDTYPE_PGID, p) { + niceval = nice_to_rlimit(task_nice(p)); + if (niceval > retval) + retval = niceval; + } while_each_pid_thread(pgrp, PIDTYPE_PGID, p); + break; + case PRIO_USER: + uid = make_kuid(cred->user_ns, who); + user = cred->user; + if (!who) + uid = cred->uid; + else if (!uid_eq(uid, cred->uid)) { + user = find_user(uid); + if (!user) + goto out_unlock; /* No processes for this user */ + } + do_each_thread(g, p) { + if (uid_eq(task_uid(p), uid)) { + niceval = nice_to_rlimit(task_nice(p)); + if (niceval > retval) + retval = niceval; + } + } while_each_thread(g, p); + if (!uid_eq(uid, cred->uid)) + free_uid(user); /* for find_user() */ + break; + } +out_unlock: + read_unlock(&tasklist_lock); + rcu_read_unlock(); + + return retval; +} + +/* + * Unprivileged users may change the real gid to the effective gid + * or vice versa. (BSD-style) + * + * If you set the real gid at all, or set the effective gid to a value not + * equal to the real gid, then the saved gid is set to the new effective gid. + * + * This makes it possible for a setgid program to completely drop its + * privileges, which is often a useful assertion to make when you are doing + * a security audit over a program. + * + * The general idea is that a program which uses just setregid() will be + * 100% compatible with BSD. A program which uses just setgid() will be + * 100% compatible with POSIX with saved IDs. + * + * SMP: There are not races, the GIDs are checked only by filesystem + * operations (as far as semantic preservation is concerned). + */ +#ifdef CONFIG_MULTIUSER +SYSCALL_DEFINE2(setregid, gid_t, rgid, gid_t, egid) +{ + struct user_namespace *ns = current_user_ns(); + const struct cred *old; + struct cred *new; + int retval; + kgid_t krgid, kegid; + + krgid = make_kgid(ns, rgid); + kegid = make_kgid(ns, egid); + + if ((rgid != (gid_t) -1) && !gid_valid(krgid)) + return -EINVAL; + if ((egid != (gid_t) -1) && !gid_valid(kegid)) + return -EINVAL; + + new = prepare_creds(); + if (!new) + return -ENOMEM; + old = current_cred(); + + retval = -EPERM; + if (rgid != (gid_t) -1) { + if (gid_eq(old->gid, krgid) || + gid_eq(old->egid, krgid) || + ns_capable(old->user_ns, CAP_SETGID)) + new->gid = krgid; + else + goto error; + } + if (egid != (gid_t) -1) { + if (gid_eq(old->gid, kegid) || + gid_eq(old->egid, kegid) || + gid_eq(old->sgid, kegid) || + ns_capable(old->user_ns, CAP_SETGID)) + new->egid = kegid; + else + goto error; + } + + if (rgid != (gid_t) -1 || + (egid != (gid_t) -1 && !gid_eq(kegid, old->gid))) + new->sgid = new->egid; + new->fsgid = new->egid; + + return commit_creds(new); + +error: + abort_creds(new); + return retval; +} + +/* + * setgid() is implemented like SysV w/ SAVED_IDS + * + * SMP: Same implicit races as above. + */ +SYSCALL_DEFINE1(setgid, gid_t, gid) +{ + struct user_namespace *ns = current_user_ns(); + const struct cred *old; + struct cred *new; + int retval; + kgid_t kgid; + + kgid = make_kgid(ns, gid); + if (!gid_valid(kgid)) + return -EINVAL; + + new = prepare_creds(); + if (!new) + return -ENOMEM; + old = current_cred(); + + retval = -EPERM; + if (ns_capable(old->user_ns, CAP_SETGID)) + new->gid = new->egid = new->sgid = new->fsgid = kgid; + else if (gid_eq(kgid, old->gid) || gid_eq(kgid, old->sgid)) + new->egid = new->fsgid = kgid; + else + goto error; + + return commit_creds(new); + +error: + abort_creds(new); + return retval; +} + +/* + * change the user struct in a credentials set to match the new UID + */ +static int set_user(struct cred *new) +{ + struct user_struct *new_user; + + new_user = alloc_uid(new->uid); + if (!new_user) + return -EAGAIN; + + /* + * We don't fail in case of NPROC limit excess here because too many + * poorly written programs don't check set*uid() return code, assuming + * it never fails if called by root. We may still enforce NPROC limit + * for programs doing set*uid()+execve() by harmlessly deferring the + * failure to the execve() stage. + */ + if (atomic_read(&new_user->processes) >= rlimit(RLIMIT_NPROC) && + new_user != INIT_USER) + current->flags |= PF_NPROC_EXCEEDED; + else + current->flags &= ~PF_NPROC_EXCEEDED; + + free_uid(new->user); + new->user = new_user; + return 0; +} + +/* + * Unprivileged users may change the real uid to the effective uid + * or vice versa. (BSD-style) + * + * If you set the real uid at all, or set the effective uid to a value not + * equal to the real uid, then the saved uid is set to the new effective uid. + * + * This makes it possible for a setuid program to completely drop its + * privileges, which is often a useful assertion to make when you are doing + * a security audit over a program. + * + * The general idea is that a program which uses just setreuid() will be + * 100% compatible with BSD. A program which uses just setuid() will be + * 100% compatible with POSIX with saved IDs. + */ +SYSCALL_DEFINE2(setreuid, uid_t, ruid, uid_t, euid) +{ + struct user_namespace *ns = current_user_ns(); + const struct cred *old; + struct cred *new; + int retval; + kuid_t kruid, keuid; + + kruid = make_kuid(ns, ruid); + keuid = make_kuid(ns, euid); + + if ((ruid != (uid_t) -1) && !uid_valid(kruid)) + return -EINVAL; + if ((euid != (uid_t) -1) && !uid_valid(keuid)) + return -EINVAL; + + new = prepare_creds(); + if (!new) + return -ENOMEM; + old = current_cred(); + + retval = -EPERM; + if (ruid != (uid_t) -1) { + new->uid = kruid; + if (!uid_eq(old->uid, kruid) && + !uid_eq(old->euid, kruid) && + !ns_capable(old->user_ns, CAP_SETUID)) + goto error; + } + + if (euid != (uid_t) -1) { + new->euid = keuid; + if (!uid_eq(old->uid, keuid) && + !uid_eq(old->euid, keuid) && + !uid_eq(old->suid, keuid) && + !ns_capable(old->user_ns, CAP_SETUID)) + goto error; + } + + if (!uid_eq(new->uid, old->uid)) { + retval = set_user(new); + if (retval < 0) + goto error; + } + if (ruid != (uid_t) -1 || + (euid != (uid_t) -1 && !uid_eq(keuid, old->uid))) + new->suid = new->euid; + new->fsuid = new->euid; + + retval = security_task_fix_setuid(new, old, LSM_SETID_RE); + if (retval < 0) + goto error; + + return commit_creds(new); + +error: + abort_creds(new); + return retval; +} + +/* + * setuid() is implemented like SysV with SAVED_IDS + * + * Note that SAVED_ID's is deficient in that a setuid root program + * like sendmail, for example, cannot set its uid to be a normal + * user and then switch back, because if you're root, setuid() sets + * the saved uid too. If you don't like this, blame the bright people + * in the POSIX committee and/or USG. Note that the BSD-style setreuid() + * will allow a root program to temporarily drop privileges and be able to + * regain them by swapping the real and effective uid. + */ +SYSCALL_DEFINE1(setuid, uid_t, uid) +{ + struct user_namespace *ns = current_user_ns(); + const struct cred *old; + struct cred *new; + int retval; + kuid_t kuid; + + kuid = make_kuid(ns, uid); + if (!uid_valid(kuid)) + return -EINVAL; + + new = prepare_creds(); + if (!new) + return -ENOMEM; + old = current_cred(); + + retval = -EPERM; + if (ns_capable(old->user_ns, CAP_SETUID)) { + new->suid = new->uid = kuid; + if (!uid_eq(kuid, old->uid)) { + retval = set_user(new); + if (retval < 0) + goto error; + } + } else if (!uid_eq(kuid, old->uid) && !uid_eq(kuid, new->suid)) { + goto error; + } + + new->fsuid = new->euid = kuid; + + retval = security_task_fix_setuid(new, old, LSM_SETID_ID); + if (retval < 0) + goto error; + + return commit_creds(new); + +error: + abort_creds(new); + return retval; +} + + +/* + * This function implements a generic ability to update ruid, euid, + * and suid. This allows you to implement the 4.4 compatible seteuid(). + */ +SYSCALL_DEFINE3(setresuid, uid_t, ruid, uid_t, euid, uid_t, suid) +{ + struct user_namespace *ns = current_user_ns(); + const struct cred *old; + struct cred *new; + int retval; + kuid_t kruid, keuid, ksuid; + + kruid = make_kuid(ns, ruid); + keuid = make_kuid(ns, euid); + ksuid = make_kuid(ns, suid); + + if ((ruid != (uid_t) -1) && !uid_valid(kruid)) + return -EINVAL; + + if ((euid != (uid_t) -1) && !uid_valid(keuid)) + return -EINVAL; + + if ((suid != (uid_t) -1) && !uid_valid(ksuid)) + return -EINVAL; + + new = prepare_creds(); + if (!new) + return -ENOMEM; + + old = current_cred(); + + retval = -EPERM; + if (!ns_capable(old->user_ns, CAP_SETUID)) { + if (ruid != (uid_t) -1 && !uid_eq(kruid, old->uid) && + !uid_eq(kruid, old->euid) && !uid_eq(kruid, old->suid)) + goto error; + if (euid != (uid_t) -1 && !uid_eq(keuid, old->uid) && + !uid_eq(keuid, old->euid) && !uid_eq(keuid, old->suid)) + goto error; + if (suid != (uid_t) -1 && !uid_eq(ksuid, old->uid) && + !uid_eq(ksuid, old->euid) && !uid_eq(ksuid, old->suid)) + goto error; + } + + if (ruid != (uid_t) -1) { + new->uid = kruid; + if (!uid_eq(kruid, old->uid)) { + retval = set_user(new); + if (retval < 0) + goto error; + } + } + if (euid != (uid_t) -1) + new->euid = keuid; + if (suid != (uid_t) -1) + new->suid = ksuid; + new->fsuid = new->euid; + + retval = security_task_fix_setuid(new, old, LSM_SETID_RES); + if (retval < 0) + goto error; + + return commit_creds(new); + +error: + abort_creds(new); + return retval; +} + +SYSCALL_DEFINE3(getresuid, uid_t __user *, ruidp, uid_t __user *, euidp, uid_t __user *, suidp) +{ + const struct cred *cred = current_cred(); + int retval; + uid_t ruid, euid, suid; + + ruid = from_kuid_munged(cred->user_ns, cred->uid); + euid = from_kuid_munged(cred->user_ns, cred->euid); + suid = from_kuid_munged(cred->user_ns, cred->suid); + + retval = put_user(ruid, ruidp); + if (!retval) { + retval = put_user(euid, euidp); + if (!retval) + return put_user(suid, suidp); + } + return retval; +} + +/* + * Same as above, but for rgid, egid, sgid. + */ +SYSCALL_DEFINE3(setresgid, gid_t, rgid, gid_t, egid, gid_t, sgid) +{ + struct user_namespace *ns = current_user_ns(); + const struct cred *old; + struct cred *new; + int retval; + kgid_t krgid, kegid, ksgid; + + krgid = make_kgid(ns, rgid); + kegid = make_kgid(ns, egid); + ksgid = make_kgid(ns, sgid); + + if ((rgid != (gid_t) -1) && !gid_valid(krgid)) + return -EINVAL; + if ((egid != (gid_t) -1) && !gid_valid(kegid)) + return -EINVAL; + if ((sgid != (gid_t) -1) && !gid_valid(ksgid)) + return -EINVAL; + + new = prepare_creds(); + if (!new) + return -ENOMEM; + old = current_cred(); + + retval = -EPERM; + if (!ns_capable(old->user_ns, CAP_SETGID)) { + if (rgid != (gid_t) -1 && !gid_eq(krgid, old->gid) && + !gid_eq(krgid, old->egid) && !gid_eq(krgid, old->sgid)) + goto error; + if (egid != (gid_t) -1 && !gid_eq(kegid, old->gid) && + !gid_eq(kegid, old->egid) && !gid_eq(kegid, old->sgid)) + goto error; + if (sgid != (gid_t) -1 && !gid_eq(ksgid, old->gid) && + !gid_eq(ksgid, old->egid) && !gid_eq(ksgid, old->sgid)) + goto error; + } + + if (rgid != (gid_t) -1) + new->gid = krgid; + if (egid != (gid_t) -1) + new->egid = kegid; + if (sgid != (gid_t) -1) + new->sgid = ksgid; + new->fsgid = new->egid; + + return commit_creds(new); + +error: + abort_creds(new); + return retval; +} + +SYSCALL_DEFINE3(getresgid, gid_t __user *, rgidp, gid_t __user *, egidp, gid_t __user *, sgidp) +{ + const struct cred *cred = current_cred(); + int retval; + gid_t rgid, egid, sgid; + + rgid = from_kgid_munged(cred->user_ns, cred->gid); + egid = from_kgid_munged(cred->user_ns, cred->egid); + sgid = from_kgid_munged(cred->user_ns, cred->sgid); + + retval = put_user(rgid, rgidp); + if (!retval) { + retval = put_user(egid, egidp); + if (!retval) + retval = put_user(sgid, sgidp); + } + + return retval; +} + + +/* + * "setfsuid()" sets the fsuid - the uid used for filesystem checks. This + * is used for "access()" and for the NFS daemon (letting nfsd stay at + * whatever uid it wants to). It normally shadows "euid", except when + * explicitly set by setfsuid() or for access.. + */ +SYSCALL_DEFINE1(setfsuid, uid_t, uid) +{ + const struct cred *old; + struct cred *new; + uid_t old_fsuid; + kuid_t kuid; + + old = current_cred(); + old_fsuid = from_kuid_munged(old->user_ns, old->fsuid); + + kuid = make_kuid(old->user_ns, uid); + if (!uid_valid(kuid)) + return old_fsuid; + + new = prepare_creds(); + if (!new) + return old_fsuid; + + if (uid_eq(kuid, old->uid) || uid_eq(kuid, old->euid) || + uid_eq(kuid, old->suid) || uid_eq(kuid, old->fsuid) || + ns_capable(old->user_ns, CAP_SETUID)) { + if (!uid_eq(kuid, old->fsuid)) { + new->fsuid = kuid; + if (security_task_fix_setuid(new, old, LSM_SETID_FS) == 0) + goto change_okay; + } + } + + abort_creds(new); + return old_fsuid; + +change_okay: + commit_creds(new); + return old_fsuid; +} + +/* + * Samma pÃ¥ svenska.. + */ +SYSCALL_DEFINE1(setfsgid, gid_t, gid) +{ + const struct cred *old; + struct cred *new; + gid_t old_fsgid; + kgid_t kgid; + + old = current_cred(); + old_fsgid = from_kgid_munged(old->user_ns, old->fsgid); + + kgid = make_kgid(old->user_ns, gid); + if (!gid_valid(kgid)) + return old_fsgid; + + new = prepare_creds(); + if (!new) + return old_fsgid; + + if (gid_eq(kgid, old->gid) || gid_eq(kgid, old->egid) || + gid_eq(kgid, old->sgid) || gid_eq(kgid, old->fsgid) || + ns_capable(old->user_ns, CAP_SETGID)) { + if (!gid_eq(kgid, old->fsgid)) { + new->fsgid = kgid; + goto change_okay; + } + } + + abort_creds(new); + return old_fsgid; + +change_okay: + commit_creds(new); + return old_fsgid; +} +#endif /* CONFIG_MULTIUSER */ + +/** + * sys_getpid - return the thread group id of the current process + * + * Note, despite the name, this returns the tgid not the pid. The tgid and + * the pid are identical unless CLONE_THREAD was specified on clone() in + * which case the tgid is the same in all threads of the same group. + * + * This is SMP safe as current->tgid does not change. + */ +SYSCALL_DEFINE0(getpid) +{ + return task_tgid_vnr(current); +} + +/* Thread ID - the internal kernel "pid" */ +SYSCALL_DEFINE0(gettid) +{ + return task_pid_vnr(current); +} + +/* + * Accessing ->real_parent is not SMP-safe, it could + * change from under us. However, we can use a stale + * value of ->real_parent under rcu_read_lock(), see + * release_task()->call_rcu(delayed_put_task_struct). + */ +SYSCALL_DEFINE0(getppid) +{ + int pid; + + rcu_read_lock(); + pid = task_tgid_vnr(rcu_dereference(current->real_parent)); + rcu_read_unlock(); + + return pid; +} + +SYSCALL_DEFINE0(getuid) +{ + /* Only we change this so SMP safe */ + return from_kuid_munged(current_user_ns(), current_uid()); +} + +SYSCALL_DEFINE0(geteuid) +{ + /* Only we change this so SMP safe */ + return from_kuid_munged(current_user_ns(), current_euid()); +} + +SYSCALL_DEFINE0(getgid) +{ + /* Only we change this so SMP safe */ + return from_kgid_munged(current_user_ns(), current_gid()); +} + +SYSCALL_DEFINE0(getegid) +{ + /* Only we change this so SMP safe */ + return from_kgid_munged(current_user_ns(), current_egid()); +} + +void do_sys_times(struct tms *tms) +{ + cputime_t tgutime, tgstime, cutime, cstime; + + thread_group_cputime_adjusted(current, &tgutime, &tgstime); + cutime = current->signal->cutime; + cstime = current->signal->cstime; + tms->tms_utime = cputime_to_clock_t(tgutime); + tms->tms_stime = cputime_to_clock_t(tgstime); + tms->tms_cutime = cputime_to_clock_t(cutime); + tms->tms_cstime = cputime_to_clock_t(cstime); +} + +SYSCALL_DEFINE1(times, struct tms __user *, tbuf) +{ + if (tbuf) { + struct tms tmp; + + do_sys_times(&tmp); + if (copy_to_user(tbuf, &tmp, sizeof(struct tms))) + return -EFAULT; + } + force_successful_syscall_return(); + return (long) jiffies_64_to_clock_t(get_jiffies_64()); +} + +/* + * This needs some heavy checking ... + * I just haven't the stomach for it. I also don't fully + * understand sessions/pgrp etc. Let somebody who does explain it. + * + * OK, I think I have the protection semantics right.... this is really + * only important on a multi-user system anyway, to make sure one user + * can't send a signal to a process owned by another. -TYT, 12/12/91 + * + * !PF_FORKNOEXEC check to conform completely to POSIX. + */ +SYSCALL_DEFINE2(setpgid, pid_t, pid, pid_t, pgid) +{ + struct task_struct *p; + struct task_struct *group_leader = current->group_leader; + struct pid *pgrp; + int err; + + if (!pid) + pid = task_pid_vnr(group_leader); + if (!pgid) + pgid = pid; + if (pgid < 0) + return -EINVAL; + rcu_read_lock(); + + /* From this point forward we keep holding onto the tasklist lock + * so that our parent does not change from under us. -DaveM + */ + write_lock_irq(&tasklist_lock); + + err = -ESRCH; + p = find_task_by_vpid(pid); + if (!p) + goto out; + + err = -EINVAL; + if (!thread_group_leader(p)) + goto out; + + if (same_thread_group(p->real_parent, group_leader)) { + err = -EPERM; + if (task_session(p) != task_session(group_leader)) + goto out; + err = -EACCES; + if (!(p->flags & PF_FORKNOEXEC)) + goto out; + } else { + err = -ESRCH; + if (p != group_leader) + goto out; + } + + err = -EPERM; + if (p->signal->leader) + goto out; + + pgrp = task_pid(p); + if (pgid != pid) { + struct task_struct *g; + + pgrp = find_vpid(pgid); + g = pid_task(pgrp, PIDTYPE_PGID); + if (!g || task_session(g) != task_session(group_leader)) + goto out; + } + + err = security_task_setpgid(p, pgid); + if (err) + goto out; + + if (task_pgrp(p) != pgrp) + change_pid(p, PIDTYPE_PGID, pgrp); + + err = 0; +out: + /* All paths lead to here, thus we are safe. -DaveM */ + write_unlock_irq(&tasklist_lock); + rcu_read_unlock(); + return err; +} + +SYSCALL_DEFINE1(getpgid, pid_t, pid) +{ + struct task_struct *p; + struct pid *grp; + int retval; + + rcu_read_lock(); + if (!pid) + grp = task_pgrp(current); + else { + retval = -ESRCH; + p = find_task_by_vpid(pid); + if (!p) + goto out; + grp = task_pgrp(p); + if (!grp) + goto out; + + retval = security_task_getpgid(p); + if (retval) + goto out; + } + retval = pid_vnr(grp); +out: + rcu_read_unlock(); + return retval; +} + +#ifdef __ARCH_WANT_SYS_GETPGRP + +SYSCALL_DEFINE0(getpgrp) +{ + return sys_getpgid(0); +} + +#endif + +SYSCALL_DEFINE1(getsid, pid_t, pid) +{ + struct task_struct *p; + struct pid *sid; + int retval; + + rcu_read_lock(); + if (!pid) + sid = task_session(current); + else { + retval = -ESRCH; + p = find_task_by_vpid(pid); + if (!p) + goto out; + sid = task_session(p); + if (!sid) + goto out; + + retval = security_task_getsid(p); + if (retval) + goto out; + } + retval = pid_vnr(sid); +out: + rcu_read_unlock(); + return retval; +} + +static void set_special_pids(struct pid *pid) +{ + struct task_struct *curr = current->group_leader; + + if (task_session(curr) != pid) + change_pid(curr, PIDTYPE_SID, pid); + + if (task_pgrp(curr) != pid) + change_pid(curr, PIDTYPE_PGID, pid); +} + +SYSCALL_DEFINE0(setsid) +{ + struct task_struct *group_leader = current->group_leader; + struct pid *sid = task_pid(group_leader); + pid_t session = pid_vnr(sid); + int err = -EPERM; + + write_lock_irq(&tasklist_lock); + /* Fail if I am already a session leader */ + if (group_leader->signal->leader) + goto out; + + /* Fail if a process group id already exists that equals the + * proposed session id. + */ + if (pid_task(sid, PIDTYPE_PGID)) + goto out; + + group_leader->signal->leader = 1; + set_special_pids(sid); + + proc_clear_tty(group_leader); + + err = session; +out: + write_unlock_irq(&tasklist_lock); + if (err > 0) { + proc_sid_connector(group_leader); + sched_autogroup_create_attach(group_leader); + } + return err; +} + +DECLARE_RWSEM(uts_sem); + +#ifdef COMPAT_UTS_MACHINE +#define override_architecture(name) \ + (personality(current->personality) == PER_LINUX32 && \ + copy_to_user(name->machine, COMPAT_UTS_MACHINE, \ + sizeof(COMPAT_UTS_MACHINE))) +#else +#define override_architecture(name) 0 +#endif + +/* + * Work around broken programs that cannot handle "Linux 3.0". + * Instead we map 3.x to 2.6.40+x, so e.g. 3.0 would be 2.6.40 + * And we map 4.x to 2.6.60+x, so 4.0 would be 2.6.60. + */ +static int override_release(char __user *release, size_t len) +{ + int ret = 0; + + if (current->personality & UNAME26) { + const char *rest = UTS_RELEASE; + char buf[65] = { 0 }; + int ndots = 0; + unsigned v; + size_t copy; + + while (*rest) { + if (*rest == '.' && ++ndots >= 3) + break; + if (!isdigit(*rest) && *rest != '.') + break; + rest++; + } + v = ((LINUX_VERSION_CODE >> 8) & 0xff) + 60; + copy = clamp_t(size_t, len, 1, sizeof(buf)); + copy = scnprintf(buf, copy, "2.6.%u%s", v, rest); + ret = copy_to_user(release, buf, copy + 1); + } + return ret; +} + +SYSCALL_DEFINE1(newuname, struct new_utsname __user *, name) +{ + int errno = 0; + + down_read(&uts_sem); + if (copy_to_user(name, utsname(), sizeof *name)) + errno = -EFAULT; + up_read(&uts_sem); + + if (!errno && override_release(name->release, sizeof(name->release))) + errno = -EFAULT; + if (!errno && override_architecture(name)) + errno = -EFAULT; + return errno; +} + +#ifdef __ARCH_WANT_SYS_OLD_UNAME +/* + * Old cruft + */ +SYSCALL_DEFINE1(uname, struct old_utsname __user *, name) +{ + int error = 0; + + if (!name) + return -EFAULT; + + down_read(&uts_sem); + if (copy_to_user(name, utsname(), sizeof(*name))) + error = -EFAULT; + up_read(&uts_sem); + + if (!error && override_release(name->release, sizeof(name->release))) + error = -EFAULT; + if (!error && override_architecture(name)) + error = -EFAULT; + return error; +} + +SYSCALL_DEFINE1(olduname, struct oldold_utsname __user *, name) +{ + int error; + + if (!name) + return -EFAULT; + if (!access_ok(VERIFY_WRITE, name, sizeof(struct oldold_utsname))) + return -EFAULT; + + down_read(&uts_sem); + error = __copy_to_user(&name->sysname, &utsname()->sysname, + __OLD_UTS_LEN); + error |= __put_user(0, name->sysname + __OLD_UTS_LEN); + error |= __copy_to_user(&name->nodename, &utsname()->nodename, + __OLD_UTS_LEN); + error |= __put_user(0, name->nodename + __OLD_UTS_LEN); + error |= __copy_to_user(&name->release, &utsname()->release, + __OLD_UTS_LEN); + error |= __put_user(0, name->release + __OLD_UTS_LEN); + error |= __copy_to_user(&name->version, &utsname()->version, + __OLD_UTS_LEN); + error |= __put_user(0, name->version + __OLD_UTS_LEN); + error |= __copy_to_user(&name->machine, &utsname()->machine, + __OLD_UTS_LEN); + error |= __put_user(0, name->machine + __OLD_UTS_LEN); + up_read(&uts_sem); + + if (!error && override_architecture(name)) + error = -EFAULT; + if (!error && override_release(name->release, sizeof(name->release))) + error = -EFAULT; + return error ? -EFAULT : 0; +} +#endif + +SYSCALL_DEFINE2(sethostname, char __user *, name, int, len) +{ + int errno; + char tmp[__NEW_UTS_LEN]; + + if (!ns_capable(current->nsproxy->uts_ns->user_ns, CAP_SYS_ADMIN)) + return -EPERM; + + if (len < 0 || len > __NEW_UTS_LEN) + return -EINVAL; + down_write(&uts_sem); + errno = -EFAULT; + if (!copy_from_user(tmp, name, len)) { + struct new_utsname *u = utsname(); + + memcpy(u->nodename, tmp, len); + memset(u->nodename + len, 0, sizeof(u->nodename) - len); + errno = 0; + uts_proc_notify(UTS_PROC_HOSTNAME); + } + up_write(&uts_sem); + return errno; +} + +#ifdef __ARCH_WANT_SYS_GETHOSTNAME + +SYSCALL_DEFINE2(gethostname, char __user *, name, int, len) +{ + int i, errno; + struct new_utsname *u; + + if (len < 0) + return -EINVAL; + down_read(&uts_sem); + u = utsname(); + i = 1 + strlen(u->nodename); + if (i > len) + i = len; + errno = 0; + if (copy_to_user(name, u->nodename, i)) + errno = -EFAULT; + up_read(&uts_sem); + return errno; +} + +#endif + +/* + * Only setdomainname; getdomainname can be implemented by calling + * uname() + */ +SYSCALL_DEFINE2(setdomainname, char __user *, name, int, len) +{ + int errno; + char tmp[__NEW_UTS_LEN]; + + if (!ns_capable(current->nsproxy->uts_ns->user_ns, CAP_SYS_ADMIN)) + return -EPERM; + if (len < 0 || len > __NEW_UTS_LEN) + return -EINVAL; + + down_write(&uts_sem); + errno = -EFAULT; + if (!copy_from_user(tmp, name, len)) { + struct new_utsname *u = utsname(); + + memcpy(u->domainname, tmp, len); + memset(u->domainname + len, 0, sizeof(u->domainname) - len); + errno = 0; + uts_proc_notify(UTS_PROC_DOMAINNAME); + } + up_write(&uts_sem); + return errno; +} + +SYSCALL_DEFINE2(getrlimit, unsigned int, resource, struct rlimit __user *, rlim) +{ + struct rlimit value; + int ret; + + ret = do_prlimit(current, resource, NULL, &value); + if (!ret) + ret = copy_to_user(rlim, &value, sizeof(*rlim)) ? -EFAULT : 0; + + return ret; +} + +#ifdef __ARCH_WANT_SYS_OLD_GETRLIMIT + +/* + * Back compatibility for getrlimit. Needed for some apps. + */ +SYSCALL_DEFINE2(old_getrlimit, unsigned int, resource, + struct rlimit __user *, rlim) +{ + struct rlimit x; + if (resource >= RLIM_NLIMITS) + return -EINVAL; + + task_lock(current->group_leader); + x = current->signal->rlim[resource]; + task_unlock(current->group_leader); + if (x.rlim_cur > 0x7FFFFFFF) + x.rlim_cur = 0x7FFFFFFF; + if (x.rlim_max > 0x7FFFFFFF) + x.rlim_max = 0x7FFFFFFF; + return copy_to_user(rlim, &x, sizeof(x)) ? -EFAULT : 0; +} + +#endif + +static inline bool rlim64_is_infinity(__u64 rlim64) +{ +#if BITS_PER_LONG < 64 + return rlim64 >= ULONG_MAX; +#else + return rlim64 == RLIM64_INFINITY; +#endif +} + +static void rlim_to_rlim64(const struct rlimit *rlim, struct rlimit64 *rlim64) +{ + if (rlim->rlim_cur == RLIM_INFINITY) + rlim64->rlim_cur = RLIM64_INFINITY; + else + rlim64->rlim_cur = rlim->rlim_cur; + if (rlim->rlim_max == RLIM_INFINITY) + rlim64->rlim_max = RLIM64_INFINITY; + else + rlim64->rlim_max = rlim->rlim_max; +} + +static void rlim64_to_rlim(const struct rlimit64 *rlim64, struct rlimit *rlim) +{ + if (rlim64_is_infinity(rlim64->rlim_cur)) + rlim->rlim_cur = RLIM_INFINITY; + else + rlim->rlim_cur = (unsigned long)rlim64->rlim_cur; + if (rlim64_is_infinity(rlim64->rlim_max)) + rlim->rlim_max = RLIM_INFINITY; + else + rlim->rlim_max = (unsigned long)rlim64->rlim_max; +} + +/* make sure you are allowed to change @tsk limits before calling this */ +int do_prlimit(struct task_struct *tsk, unsigned int resource, + struct rlimit *new_rlim, struct rlimit *old_rlim) +{ + struct rlimit *rlim; + int retval = 0; + + if (resource >= RLIM_NLIMITS) + return -EINVAL; + if (new_rlim) { + if (new_rlim->rlim_cur > new_rlim->rlim_max) + return -EINVAL; + if (resource == RLIMIT_NOFILE && + new_rlim->rlim_max > sysctl_nr_open) + return -EPERM; + } + + /* protect tsk->signal and tsk->sighand from disappearing */ + read_lock(&tasklist_lock); + if (!tsk->sighand) { + retval = -ESRCH; + goto out; + } + + rlim = tsk->signal->rlim + resource; + task_lock(tsk->group_leader); + if (new_rlim) { + /* Keep the capable check against init_user_ns until + cgroups can contain all limits */ + if (new_rlim->rlim_max > rlim->rlim_max && + !capable(CAP_SYS_RESOURCE)) + retval = -EPERM; + if (!retval) + retval = security_task_setrlimit(tsk->group_leader, + resource, new_rlim); + if (resource == RLIMIT_CPU && new_rlim->rlim_cur == 0) { + /* + * The caller is asking for an immediate RLIMIT_CPU + * expiry. But we use the zero value to mean "it was + * never set". So let's cheat and make it one second + * instead + */ + new_rlim->rlim_cur = 1; + } + } + if (!retval) { + if (old_rlim) + *old_rlim = *rlim; + if (new_rlim) + *rlim = *new_rlim; + } + task_unlock(tsk->group_leader); + + /* + * RLIMIT_CPU handling. Note that the kernel fails to return an error + * code if it rejected the user's attempt to set RLIMIT_CPU. This is a + * very long-standing error, and fixing it now risks breakage of + * applications, so we live with it + */ + if (!retval && new_rlim && resource == RLIMIT_CPU && + new_rlim->rlim_cur != RLIM_INFINITY) + update_rlimit_cpu(tsk, new_rlim->rlim_cur); +out: + read_unlock(&tasklist_lock); + return retval; +} + +/* rcu lock must be held */ +static int check_prlimit_permission(struct task_struct *task) +{ + const struct cred *cred = current_cred(), *tcred; + + if (current == task) + return 0; + + tcred = __task_cred(task); + if (uid_eq(cred->uid, tcred->euid) && + uid_eq(cred->uid, tcred->suid) && + uid_eq(cred->uid, tcred->uid) && + gid_eq(cred->gid, tcred->egid) && + gid_eq(cred->gid, tcred->sgid) && + gid_eq(cred->gid, tcred->gid)) + return 0; + if (ns_capable(tcred->user_ns, CAP_SYS_RESOURCE)) + return 0; + + return -EPERM; +} + +SYSCALL_DEFINE4(prlimit64, pid_t, pid, unsigned int, resource, + const struct rlimit64 __user *, new_rlim, + struct rlimit64 __user *, old_rlim) +{ + struct rlimit64 old64, new64; + struct rlimit old, new; + struct task_struct *tsk; + int ret; + + if (new_rlim) { + if (copy_from_user(&new64, new_rlim, sizeof(new64))) + return -EFAULT; + rlim64_to_rlim(&new64, &new); + } + + rcu_read_lock(); + tsk = pid ? find_task_by_vpid(pid) : current; + if (!tsk) { + rcu_read_unlock(); + return -ESRCH; + } + ret = check_prlimit_permission(tsk); + if (ret) { + rcu_read_unlock(); + return ret; + } + get_task_struct(tsk); + rcu_read_unlock(); + + ret = do_prlimit(tsk, resource, new_rlim ? &new : NULL, + old_rlim ? &old : NULL); + + if (!ret && old_rlim) { + rlim_to_rlim64(&old, &old64); + if (copy_to_user(old_rlim, &old64, sizeof(old64))) + ret = -EFAULT; + } + + put_task_struct(tsk); + return ret; +} + +SYSCALL_DEFINE2(setrlimit, unsigned int, resource, struct rlimit __user *, rlim) +{ + struct rlimit new_rlim; + + if (copy_from_user(&new_rlim, rlim, sizeof(*rlim))) + return -EFAULT; + return do_prlimit(current, resource, &new_rlim, NULL); +} + +/* + * It would make sense to put struct rusage in the task_struct, + * except that would make the task_struct be *really big*. After + * task_struct gets moved into malloc'ed memory, it would + * make sense to do this. It will make moving the rest of the information + * a lot simpler! (Which we're not doing right now because we're not + * measuring them yet). + * + * When sampling multiple threads for RUSAGE_SELF, under SMP we might have + * races with threads incrementing their own counters. But since word + * reads are atomic, we either get new values or old values and we don't + * care which for the sums. We always take the siglock to protect reading + * the c* fields from p->signal from races with exit.c updating those + * fields when reaping, so a sample either gets all the additions of a + * given child after it's reaped, or none so this sample is before reaping. + * + * Locking: + * We need to take the siglock for CHILDEREN, SELF and BOTH + * for the cases current multithreaded, non-current single threaded + * non-current multithreaded. Thread traversal is now safe with + * the siglock held. + * Strictly speaking, we donot need to take the siglock if we are current and + * single threaded, as no one else can take our signal_struct away, no one + * else can reap the children to update signal->c* counters, and no one else + * can race with the signal-> fields. If we do not take any lock, the + * signal-> fields could be read out of order while another thread was just + * exiting. So we should place a read memory barrier when we avoid the lock. + * On the writer side, write memory barrier is implied in __exit_signal + * as __exit_signal releases the siglock spinlock after updating the signal-> + * fields. But we don't do this yet to keep things simple. + * + */ + +static void accumulate_thread_rusage(struct task_struct *t, struct rusage *r) +{ + r->ru_nvcsw += t->nvcsw; + r->ru_nivcsw += t->nivcsw; + r->ru_minflt += t->min_flt; + r->ru_majflt += t->maj_flt; + r->ru_inblock += task_io_get_inblock(t); + r->ru_oublock += task_io_get_oublock(t); +} + +static void k_getrusage(struct task_struct *p, int who, struct rusage *r) +{ + struct task_struct *t; + unsigned long flags; + cputime_t tgutime, tgstime, utime, stime; + unsigned long maxrss = 0; + + memset((char *)r, 0, sizeof (*r)); + utime = stime = 0; + + if (who == RUSAGE_THREAD) { + task_cputime_adjusted(current, &utime, &stime); + accumulate_thread_rusage(p, r); + maxrss = p->signal->maxrss; + goto out; + } + + if (!lock_task_sighand(p, &flags)) + return; + + switch (who) { + case RUSAGE_BOTH: + case RUSAGE_CHILDREN: + utime = p->signal->cutime; + stime = p->signal->cstime; + r->ru_nvcsw = p->signal->cnvcsw; + r->ru_nivcsw = p->signal->cnivcsw; + r->ru_minflt = p->signal->cmin_flt; + r->ru_majflt = p->signal->cmaj_flt; + r->ru_inblock = p->signal->cinblock; + r->ru_oublock = p->signal->coublock; + maxrss = p->signal->cmaxrss; + + if (who == RUSAGE_CHILDREN) + break; + + case RUSAGE_SELF: + thread_group_cputime_adjusted(p, &tgutime, &tgstime); + utime += tgutime; + stime += tgstime; + r->ru_nvcsw += p->signal->nvcsw; + r->ru_nivcsw += p->signal->nivcsw; + r->ru_minflt += p->signal->min_flt; + r->ru_majflt += p->signal->maj_flt; + r->ru_inblock += p->signal->inblock; + r->ru_oublock += p->signal->oublock; + if (maxrss < p->signal->maxrss) + maxrss = p->signal->maxrss; + t = p; + do { + accumulate_thread_rusage(t, r); + } while_each_thread(p, t); + break; + + default: + BUG(); + } + unlock_task_sighand(p, &flags); + +out: + cputime_to_timeval(utime, &r->ru_utime); + cputime_to_timeval(stime, &r->ru_stime); + + if (who != RUSAGE_CHILDREN) { + struct mm_struct *mm = get_task_mm(p); + + if (mm) { + setmax_mm_hiwater_rss(&maxrss, mm); + mmput(mm); + } + } + r->ru_maxrss = maxrss * (PAGE_SIZE / 1024); /* convert pages to KBs */ +} + +int getrusage(struct task_struct *p, int who, struct rusage __user *ru) +{ + struct rusage r; + + k_getrusage(p, who, &r); + return copy_to_user(ru, &r, sizeof(r)) ? -EFAULT : 0; +} + +SYSCALL_DEFINE2(getrusage, int, who, struct rusage __user *, ru) +{ + if (who != RUSAGE_SELF && who != RUSAGE_CHILDREN && + who != RUSAGE_THREAD) + return -EINVAL; + return getrusage(current, who, ru); +} + +#ifdef CONFIG_COMPAT +COMPAT_SYSCALL_DEFINE2(getrusage, int, who, struct compat_rusage __user *, ru) +{ + struct rusage r; + + if (who != RUSAGE_SELF && who != RUSAGE_CHILDREN && + who != RUSAGE_THREAD) + return -EINVAL; + + k_getrusage(current, who, &r); + return put_compat_rusage(&r, ru); +} +#endif + +SYSCALL_DEFINE1(umask, int, mask) +{ + mask = xchg(¤t->fs->umask, mask & S_IRWXUGO); + return mask; +} + +static int prctl_set_mm_exe_file(struct mm_struct *mm, unsigned int fd) +{ + struct fd exe; + struct file *old_exe, *exe_file; + struct inode *inode; + int err; + + exe = fdget(fd); + if (!exe.file) + return -EBADF; + + inode = file_inode(exe.file); + + /* + * Because the original mm->exe_file points to executable file, make + * sure that this one is executable as well, to avoid breaking an + * overall picture. + */ + err = -EACCES; + if (!S_ISREG(inode->i_mode) || + exe.file->f_path.mnt->mnt_flags & MNT_NOEXEC) + goto exit; + + err = inode_permission(inode, MAY_EXEC); + if (err) + goto exit; + + /* + * Forbid mm->exe_file change if old file still mapped. + */ + exe_file = get_mm_exe_file(mm); + err = -EBUSY; + if (exe_file) { + struct vm_area_struct *vma; + + down_read(&mm->mmap_sem); + for (vma = mm->mmap; vma; vma = vma->vm_next) { + if (!vma->vm_file) + continue; + if (path_equal(&vma->vm_file->f_path, + &exe_file->f_path)) + goto exit_err; + } + + up_read(&mm->mmap_sem); + fput(exe_file); + } + + /* + * The symlink can be changed only once, just to disallow arbitrary + * transitions malicious software might bring in. This means one + * could make a snapshot over all processes running and monitor + * /proc/pid/exe changes to notice unusual activity if needed. + */ + err = -EPERM; + if (test_and_set_bit(MMF_EXE_FILE_CHANGED, &mm->flags)) + goto exit; + + err = 0; + /* set the new file, lockless */ + get_file(exe.file); + old_exe = xchg(&mm->exe_file, exe.file); + if (old_exe) + fput(old_exe); +exit: + fdput(exe); + return err; +exit_err: + up_read(&mm->mmap_sem); + fput(exe_file); + goto exit; +} + +#ifdef CONFIG_CHECKPOINT_RESTORE +/* + * WARNING: we don't require any capability here so be very careful + * in what is allowed for modification from userspace. + */ +static int validate_prctl_map(struct prctl_mm_map *prctl_map) +{ + unsigned long mmap_max_addr = TASK_SIZE; + struct mm_struct *mm = current->mm; + int error = -EINVAL, i; + + static const unsigned char offsets[] = { + offsetof(struct prctl_mm_map, start_code), + offsetof(struct prctl_mm_map, end_code), + offsetof(struct prctl_mm_map, start_data), + offsetof(struct prctl_mm_map, end_data), + offsetof(struct prctl_mm_map, start_brk), + offsetof(struct prctl_mm_map, brk), + offsetof(struct prctl_mm_map, start_stack), + offsetof(struct prctl_mm_map, arg_start), + offsetof(struct prctl_mm_map, arg_end), + offsetof(struct prctl_mm_map, env_start), + offsetof(struct prctl_mm_map, env_end), + }; + + /* + * Make sure the members are not somewhere outside + * of allowed address space. + */ + for (i = 0; i < ARRAY_SIZE(offsets); i++) { + u64 val = *(u64 *)((char *)prctl_map + offsets[i]); + + if ((unsigned long)val >= mmap_max_addr || + (unsigned long)val < mmap_min_addr) + goto out; + } + + /* + * Make sure the pairs are ordered. + */ +#define __prctl_check_order(__m1, __op, __m2) \ + ((unsigned long)prctl_map->__m1 __op \ + (unsigned long)prctl_map->__m2) ? 0 : -EINVAL + error = __prctl_check_order(start_code, <, end_code); + error |= __prctl_check_order(start_data, <, end_data); + error |= __prctl_check_order(start_brk, <=, brk); + error |= __prctl_check_order(arg_start, <=, arg_end); + error |= __prctl_check_order(env_start, <=, env_end); + if (error) + goto out; +#undef __prctl_check_order + + error = -EINVAL; + + /* + * @brk should be after @end_data in traditional maps. + */ + if (prctl_map->start_brk <= prctl_map->end_data || + prctl_map->brk <= prctl_map->end_data) + goto out; + + /* + * Neither we should allow to override limits if they set. + */ + if (check_data_rlimit(rlimit(RLIMIT_DATA), prctl_map->brk, + prctl_map->start_brk, prctl_map->end_data, + prctl_map->start_data)) + goto out; + + /* + * Someone is trying to cheat the auxv vector. + */ + if (prctl_map->auxv_size) { + if (!prctl_map->auxv || prctl_map->auxv_size > sizeof(mm->saved_auxv)) + goto out; + } + + /* + * Finally, make sure the caller has the rights to + * change /proc/pid/exe link: only local root should + * be allowed to. + */ + if (prctl_map->exe_fd != (u32)-1) { + struct user_namespace *ns = current_user_ns(); + const struct cred *cred = current_cred(); + + if (!uid_eq(cred->uid, make_kuid(ns, 0)) || + !gid_eq(cred->gid, make_kgid(ns, 0))) + goto out; + } + + error = 0; +out: + return error; +} + +static int prctl_set_mm_map(int opt, const void __user *addr, unsigned long data_size) +{ + struct prctl_mm_map prctl_map = { .exe_fd = (u32)-1, }; + unsigned long user_auxv[AT_VECTOR_SIZE]; + struct mm_struct *mm = current->mm; + int error; + + BUILD_BUG_ON(sizeof(user_auxv) != sizeof(mm->saved_auxv)); + BUILD_BUG_ON(sizeof(struct prctl_mm_map) > 256); + + if (opt == PR_SET_MM_MAP_SIZE) + return put_user((unsigned int)sizeof(prctl_map), + (unsigned int __user *)addr); + + if (data_size != sizeof(prctl_map)) + return -EINVAL; + + if (copy_from_user(&prctl_map, addr, sizeof(prctl_map))) + return -EFAULT; + + error = validate_prctl_map(&prctl_map); + if (error) + return error; + + if (prctl_map.auxv_size) { + memset(user_auxv, 0, sizeof(user_auxv)); + if (copy_from_user(user_auxv, + (const void __user *)prctl_map.auxv, + prctl_map.auxv_size)) + return -EFAULT; + + /* Last entry must be AT_NULL as specification requires */ + user_auxv[AT_VECTOR_SIZE - 2] = AT_NULL; + user_auxv[AT_VECTOR_SIZE - 1] = AT_NULL; + } + + if (prctl_map.exe_fd != (u32)-1) + error = prctl_set_mm_exe_file(mm, prctl_map.exe_fd); + down_read(&mm->mmap_sem); + if (error) + goto out; + + /* + * We don't validate if these members are pointing to + * real present VMAs because application may have correspond + * VMAs already unmapped and kernel uses these members for statistics + * output in procfs mostly, except + * + * - @start_brk/@brk which are used in do_brk but kernel lookups + * for VMAs when updating these memvers so anything wrong written + * here cause kernel to swear at userspace program but won't lead + * to any problem in kernel itself + */ + + mm->start_code = prctl_map.start_code; + mm->end_code = prctl_map.end_code; + mm->start_data = prctl_map.start_data; + mm->end_data = prctl_map.end_data; + mm->start_brk = prctl_map.start_brk; + mm->brk = prctl_map.brk; + mm->start_stack = prctl_map.start_stack; + mm->arg_start = prctl_map.arg_start; + mm->arg_end = prctl_map.arg_end; + mm->env_start = prctl_map.env_start; + mm->env_end = prctl_map.env_end; + + /* + * Note this update of @saved_auxv is lockless thus + * if someone reads this member in procfs while we're + * updating -- it may get partly updated results. It's + * known and acceptable trade off: we leave it as is to + * not introduce additional locks here making the kernel + * more complex. + */ + if (prctl_map.auxv_size) + memcpy(mm->saved_auxv, user_auxv, sizeof(user_auxv)); + + error = 0; +out: + up_read(&mm->mmap_sem); + return error; +} +#endif /* CONFIG_CHECKPOINT_RESTORE */ + +static int prctl_set_mm(int opt, unsigned long addr, + unsigned long arg4, unsigned long arg5) +{ + struct mm_struct *mm = current->mm; + struct vm_area_struct *vma; + int error; + + if (arg5 || (arg4 && (opt != PR_SET_MM_AUXV && + opt != PR_SET_MM_MAP && + opt != PR_SET_MM_MAP_SIZE))) + return -EINVAL; + +#ifdef CONFIG_CHECKPOINT_RESTORE + if (opt == PR_SET_MM_MAP || opt == PR_SET_MM_MAP_SIZE) + return prctl_set_mm_map(opt, (const void __user *)addr, arg4); +#endif + + if (!capable(CAP_SYS_RESOURCE)) + return -EPERM; + + if (opt == PR_SET_MM_EXE_FILE) + return prctl_set_mm_exe_file(mm, (unsigned int)addr); + + if (addr >= TASK_SIZE || addr < mmap_min_addr) + return -EINVAL; + + error = -EINVAL; + + down_read(&mm->mmap_sem); + vma = find_vma(mm, addr); + + switch (opt) { + case PR_SET_MM_START_CODE: + mm->start_code = addr; + break; + case PR_SET_MM_END_CODE: + mm->end_code = addr; + break; + case PR_SET_MM_START_DATA: + mm->start_data = addr; + break; + case PR_SET_MM_END_DATA: + mm->end_data = addr; + break; + + case PR_SET_MM_START_BRK: + if (addr <= mm->end_data) + goto out; + + if (check_data_rlimit(rlimit(RLIMIT_DATA), mm->brk, addr, + mm->end_data, mm->start_data)) + goto out; + + mm->start_brk = addr; + break; + + case PR_SET_MM_BRK: + if (addr <= mm->end_data) + goto out; + + if (check_data_rlimit(rlimit(RLIMIT_DATA), addr, mm->start_brk, + mm->end_data, mm->start_data)) + goto out; + + mm->brk = addr; + break; + + /* + * If command line arguments and environment + * are placed somewhere else on stack, we can + * set them up here, ARG_START/END to setup + * command line argumets and ENV_START/END + * for environment. + */ + case PR_SET_MM_START_STACK: + case PR_SET_MM_ARG_START: + case PR_SET_MM_ARG_END: + case PR_SET_MM_ENV_START: + case PR_SET_MM_ENV_END: + if (!vma) { + error = -EFAULT; + goto out; + } + if (opt == PR_SET_MM_START_STACK) + mm->start_stack = addr; + else if (opt == PR_SET_MM_ARG_START) + mm->arg_start = addr; + else if (opt == PR_SET_MM_ARG_END) + mm->arg_end = addr; + else if (opt == PR_SET_MM_ENV_START) + mm->env_start = addr; + else if (opt == PR_SET_MM_ENV_END) + mm->env_end = addr; + break; + + /* + * This doesn't move auxiliary vector itself + * since it's pinned to mm_struct, but allow + * to fill vector with new values. It's up + * to a caller to provide sane values here + * otherwise user space tools which use this + * vector might be unhappy. + */ + case PR_SET_MM_AUXV: { + unsigned long user_auxv[AT_VECTOR_SIZE]; + + if (arg4 > sizeof(user_auxv)) + goto out; + up_read(&mm->mmap_sem); + + if (copy_from_user(user_auxv, (const void __user *)addr, arg4)) + return -EFAULT; + + /* Make sure the last entry is always AT_NULL */ + user_auxv[AT_VECTOR_SIZE - 2] = 0; + user_auxv[AT_VECTOR_SIZE - 1] = 0; + + BUILD_BUG_ON(sizeof(user_auxv) != sizeof(mm->saved_auxv)); + + task_lock(current); + memcpy(mm->saved_auxv, user_auxv, arg4); + task_unlock(current); + + return 0; + } + default: + goto out; + } + + error = 0; +out: + up_read(&mm->mmap_sem); + return error; +} + +#ifdef CONFIG_CHECKPOINT_RESTORE +static int prctl_get_tid_address(struct task_struct *me, int __user **tid_addr) +{ + return put_user(me->clear_child_tid, tid_addr); +} +#else +static int prctl_get_tid_address(struct task_struct *me, int __user **tid_addr) +{ + return -EINVAL; +} +#endif + +SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, + unsigned long, arg4, unsigned long, arg5) +{ + struct task_struct *me = current; + unsigned char comm[sizeof(me->comm)]; + long error; + + error = security_task_prctl(option, arg2, arg3, arg4, arg5); + if (error != -ENOSYS) + return error; + + error = 0; + switch (option) { + case PR_SET_PDEATHSIG: + if (!valid_signal(arg2)) { + error = -EINVAL; + break; + } + me->pdeath_signal = arg2; + break; + case PR_GET_PDEATHSIG: + error = put_user(me->pdeath_signal, (int __user *)arg2); + break; + case PR_GET_DUMPABLE: + error = get_dumpable(me->mm); + break; + case PR_SET_DUMPABLE: + if (arg2 != SUID_DUMP_DISABLE && arg2 != SUID_DUMP_USER) { + error = -EINVAL; + break; + } + set_dumpable(me->mm, arg2); + break; + + case PR_SET_UNALIGN: + error = SET_UNALIGN_CTL(me, arg2); + break; + case PR_GET_UNALIGN: + error = GET_UNALIGN_CTL(me, arg2); + break; + case PR_SET_FPEMU: + error = SET_FPEMU_CTL(me, arg2); + break; + case PR_GET_FPEMU: + error = GET_FPEMU_CTL(me, arg2); + break; + case PR_SET_FPEXC: + error = SET_FPEXC_CTL(me, arg2); + break; + case PR_GET_FPEXC: + error = GET_FPEXC_CTL(me, arg2); + break; + case PR_GET_TIMING: + error = PR_TIMING_STATISTICAL; + break; + case PR_SET_TIMING: + if (arg2 != PR_TIMING_STATISTICAL) + error = -EINVAL; + break; + case PR_SET_NAME: + comm[sizeof(me->comm) - 1] = 0; + if (strncpy_from_user(comm, (char __user *)arg2, + sizeof(me->comm) - 1) < 0) + return -EFAULT; + set_task_comm(me, comm); + proc_comm_connector(me); + break; + case PR_GET_NAME: + get_task_comm(comm, me); + if (copy_to_user((char __user *)arg2, comm, sizeof(comm))) + return -EFAULT; + break; + case PR_GET_ENDIAN: + error = GET_ENDIAN(me, arg2); + break; + case PR_SET_ENDIAN: + error = SET_ENDIAN(me, arg2); + break; + case PR_GET_SECCOMP: + error = prctl_get_seccomp(); + break; + case PR_SET_SECCOMP: + error = prctl_set_seccomp(arg2, (char __user *)arg3); + break; + case PR_GET_TSC: + error = GET_TSC_CTL(arg2); + break; + case PR_SET_TSC: + error = SET_TSC_CTL(arg2); + break; + case PR_TASK_PERF_EVENTS_DISABLE: + error = perf_event_task_disable(); + break; + case PR_TASK_PERF_EVENTS_ENABLE: + error = perf_event_task_enable(); + break; + case PR_GET_TIMERSLACK: + error = current->timer_slack_ns; + break; + case PR_SET_TIMERSLACK: + if (arg2 <= 0) + current->timer_slack_ns = + current->default_timer_slack_ns; + else + current->timer_slack_ns = arg2; + break; + case PR_MCE_KILL: + if (arg4 | arg5) + return -EINVAL; + switch (arg2) { + case PR_MCE_KILL_CLEAR: + if (arg3 != 0) + return -EINVAL; + current->flags &= ~PF_MCE_PROCESS; + break; + case PR_MCE_KILL_SET: + current->flags |= PF_MCE_PROCESS; + if (arg3 == PR_MCE_KILL_EARLY) + current->flags |= PF_MCE_EARLY; + else if (arg3 == PR_MCE_KILL_LATE) + current->flags &= ~PF_MCE_EARLY; + else if (arg3 == PR_MCE_KILL_DEFAULT) + current->flags &= + ~(PF_MCE_EARLY|PF_MCE_PROCESS); + else + return -EINVAL; + break; + default: + return -EINVAL; + } + break; + case PR_MCE_KILL_GET: + if (arg2 | arg3 | arg4 | arg5) + return -EINVAL; + if (current->flags & PF_MCE_PROCESS) + error = (current->flags & PF_MCE_EARLY) ? + PR_MCE_KILL_EARLY : PR_MCE_KILL_LATE; + else + error = PR_MCE_KILL_DEFAULT; + break; + case PR_SET_MM: + error = prctl_set_mm(arg2, arg3, arg4, arg5); + break; + case PR_GET_TID_ADDRESS: + error = prctl_get_tid_address(me, (int __user **)arg2); + break; + case PR_SET_CHILD_SUBREAPER: + me->signal->is_child_subreaper = !!arg2; + break; + case PR_GET_CHILD_SUBREAPER: + error = put_user(me->signal->is_child_subreaper, + (int __user *)arg2); + break; + case PR_SET_NO_NEW_PRIVS: + if (arg2 != 1 || arg3 || arg4 || arg5) + return -EINVAL; + + task_set_no_new_privs(current); + break; + case PR_GET_NO_NEW_PRIVS: + if (arg2 || arg3 || arg4 || arg5) + return -EINVAL; + return task_no_new_privs(current) ? 1 : 0; + case PR_GET_THP_DISABLE: + if (arg2 || arg3 || arg4 || arg5) + return -EINVAL; + error = !!(me->mm->def_flags & VM_NOHUGEPAGE); + break; + case PR_SET_THP_DISABLE: + if (arg3 || arg4 || arg5) + return -EINVAL; + down_write(&me->mm->mmap_sem); + if (arg2) + me->mm->def_flags |= VM_NOHUGEPAGE; + else + me->mm->def_flags &= ~VM_NOHUGEPAGE; + up_write(&me->mm->mmap_sem); + break; + case PR_MPX_ENABLE_MANAGEMENT: + if (arg2 || arg3 || arg4 || arg5) + return -EINVAL; + error = MPX_ENABLE_MANAGEMENT(me); + break; + case PR_MPX_DISABLE_MANAGEMENT: + if (arg2 || arg3 || arg4 || arg5) + return -EINVAL; + error = MPX_DISABLE_MANAGEMENT(me); + break; + case PR_SET_FP_MODE: + error = SET_FP_MODE(me, arg2); + break; + case PR_GET_FP_MODE: + error = GET_FP_MODE(me); + break; + default: + error = -EINVAL; + break; + } + return error; +} + +SYSCALL_DEFINE3(getcpu, unsigned __user *, cpup, unsigned __user *, nodep, + struct getcpu_cache __user *, unused) +{ + int err = 0; + int cpu = raw_smp_processor_id(); + + if (cpup) + err |= put_user(cpu, cpup); + if (nodep) + err |= put_user(cpu_to_node(cpu), nodep); + return err ? -EFAULT : 0; +} + +/** + * do_sysinfo - fill in sysinfo struct + * @info: pointer to buffer to fill + */ +static int do_sysinfo(struct sysinfo *info) +{ + unsigned long mem_total, sav_total; + unsigned int mem_unit, bitcount; + struct timespec tp; + + memset(info, 0, sizeof(struct sysinfo)); + + get_monotonic_boottime(&tp); + info->uptime = tp.tv_sec + (tp.tv_nsec ? 1 : 0); + + get_avenrun(info->loads, 0, SI_LOAD_SHIFT - FSHIFT); + + info->procs = nr_threads; + + si_meminfo(info); + si_swapinfo(info); + + /* + * If the sum of all the available memory (i.e. ram + swap) + * is less than can be stored in a 32 bit unsigned long then + * we can be binary compatible with 2.2.x kernels. If not, + * well, in that case 2.2.x was broken anyways... + * + * -Erik Andersen + */ + + mem_total = info->totalram + info->totalswap; + if (mem_total < info->totalram || mem_total < info->totalswap) + goto out; + bitcount = 0; + mem_unit = info->mem_unit; + while (mem_unit > 1) { + bitcount++; + mem_unit >>= 1; + sav_total = mem_total; + mem_total <<= 1; + if (mem_total < sav_total) + goto out; + } + + /* + * If mem_total did not overflow, multiply all memory values by + * info->mem_unit and set it to 1. This leaves things compatible + * with 2.2.x, and also retains compatibility with earlier 2.4.x + * kernels... + */ + + info->mem_unit = 1; + info->totalram <<= bitcount; + info->freeram <<= bitcount; + info->sharedram <<= bitcount; + info->bufferram <<= bitcount; + info->totalswap <<= bitcount; + info->freeswap <<= bitcount; + info->totalhigh <<= bitcount; + info->freehigh <<= bitcount; + +out: + return 0; +} + +SYSCALL_DEFINE1(sysinfo, struct sysinfo __user *, info) +{ + struct sysinfo val; + + do_sysinfo(&val); + + if (copy_to_user(info, &val, sizeof(struct sysinfo))) + return -EFAULT; + + return 0; +} + +#ifdef CONFIG_COMPAT +struct compat_sysinfo { + s32 uptime; + u32 loads[3]; + u32 totalram; + u32 freeram; + u32 sharedram; + u32 bufferram; + u32 totalswap; + u32 freeswap; + u16 procs; + u16 pad; + u32 totalhigh; + u32 freehigh; + u32 mem_unit; + char _f[20-2*sizeof(u32)-sizeof(int)]; +}; + +COMPAT_SYSCALL_DEFINE1(sysinfo, struct compat_sysinfo __user *, info) +{ + struct sysinfo s; + + do_sysinfo(&s); + + /* Check to see if any memory value is too large for 32-bit and scale + * down if needed + */ + if (upper_32_bits(s.totalram) || upper_32_bits(s.totalswap)) { + int bitcount = 0; + + while (s.mem_unit < PAGE_SIZE) { + s.mem_unit <<= 1; + bitcount++; + } + + s.totalram >>= bitcount; + s.freeram >>= bitcount; + s.sharedram >>= bitcount; + s.bufferram >>= bitcount; + s.totalswap >>= bitcount; + s.freeswap >>= bitcount; + s.totalhigh >>= bitcount; + s.freehigh >>= bitcount; + } + + if (!access_ok(VERIFY_WRITE, info, sizeof(struct compat_sysinfo)) || + __put_user(s.uptime, &info->uptime) || + __put_user(s.loads[0], &info->loads[0]) || + __put_user(s.loads[1], &info->loads[1]) || + __put_user(s.loads[2], &info->loads[2]) || + __put_user(s.totalram, &info->totalram) || + __put_user(s.freeram, &info->freeram) || + __put_user(s.sharedram, &info->sharedram) || + __put_user(s.bufferram, &info->bufferram) || + __put_user(s.totalswap, &info->totalswap) || + __put_user(s.freeswap, &info->freeswap) || + __put_user(s.procs, &info->procs) || + __put_user(s.totalhigh, &info->totalhigh) || + __put_user(s.freehigh, &info->freehigh) || + __put_user(s.mem_unit, &info->mem_unit)) + return -EFAULT; + + return 0; +} +#endif /* CONFIG_COMPAT */ diff --git a/kernel/kernel/sys_ni.c b/kernel/kernel/sys_ni.c new file mode 100644 index 000000000..7995ef586 --- /dev/null +++ b/kernel/kernel/sys_ni.c @@ -0,0 +1,245 @@ + +#include +#include + +#include + +/* we can't #include here, + but tell gcc to not warn with -Wmissing-prototypes */ +asmlinkage long sys_ni_syscall(void); + +/* + * Non-implemented system calls get redirected here. + */ +asmlinkage long sys_ni_syscall(void) +{ + return -ENOSYS; +} + +cond_syscall(sys_quotactl); +cond_syscall(sys32_quotactl); +cond_syscall(sys_acct); +cond_syscall(sys_lookup_dcookie); +cond_syscall(compat_sys_lookup_dcookie); +cond_syscall(sys_swapon); +cond_syscall(sys_swapoff); +cond_syscall(sys_kexec_load); +cond_syscall(compat_sys_kexec_load); +cond_syscall(sys_kexec_file_load); +cond_syscall(sys_init_module); +cond_syscall(sys_finit_module); +cond_syscall(sys_delete_module); +cond_syscall(sys_socketpair); +cond_syscall(sys_bind); +cond_syscall(sys_listen); +cond_syscall(sys_accept); +cond_syscall(sys_accept4); +cond_syscall(sys_connect); +cond_syscall(sys_getsockname); +cond_syscall(sys_getpeername); +cond_syscall(sys_sendto); +cond_syscall(sys_send); +cond_syscall(sys_recvfrom); +cond_syscall(sys_recv); +cond_syscall(sys_socket); +cond_syscall(sys_setsockopt); +cond_syscall(compat_sys_setsockopt); +cond_syscall(sys_getsockopt); +cond_syscall(compat_sys_getsockopt); +cond_syscall(sys_shutdown); +cond_syscall(sys_sendmsg); +cond_syscall(sys_sendmmsg); +cond_syscall(compat_sys_sendmsg); +cond_syscall(compat_sys_sendmmsg); +cond_syscall(sys_recvmsg); +cond_syscall(sys_recvmmsg); +cond_syscall(compat_sys_recvmsg); +cond_syscall(compat_sys_recv); +cond_syscall(compat_sys_recvfrom); +cond_syscall(compat_sys_recvmmsg); +cond_syscall(sys_socketcall); +cond_syscall(sys_futex); +cond_syscall(compat_sys_futex); +cond_syscall(sys_set_robust_list); +cond_syscall(compat_sys_set_robust_list); +cond_syscall(sys_get_robust_list); +cond_syscall(compat_sys_get_robust_list); +cond_syscall(sys_epoll_create); +cond_syscall(sys_epoll_create1); +cond_syscall(sys_epoll_ctl); +cond_syscall(sys_epoll_wait); +cond_syscall(sys_epoll_pwait); +cond_syscall(compat_sys_epoll_pwait); +cond_syscall(sys_semget); +cond_syscall(sys_semop); +cond_syscall(sys_semtimedop); +cond_syscall(compat_sys_semtimedop); +cond_syscall(sys_semctl); +cond_syscall(compat_sys_semctl); +cond_syscall(sys_msgget); +cond_syscall(sys_msgsnd); +cond_syscall(compat_sys_msgsnd); +cond_syscall(sys_msgrcv); +cond_syscall(compat_sys_msgrcv); +cond_syscall(sys_msgctl); +cond_syscall(compat_sys_msgctl); +cond_syscall(sys_shmget); +cond_syscall(sys_shmat); +cond_syscall(compat_sys_shmat); +cond_syscall(sys_shmdt); +cond_syscall(sys_shmctl); +cond_syscall(compat_sys_shmctl); +cond_syscall(sys_mq_open); +cond_syscall(sys_mq_unlink); +cond_syscall(sys_mq_timedsend); +cond_syscall(sys_mq_timedreceive); +cond_syscall(sys_mq_notify); +cond_syscall(sys_mq_getsetattr); +cond_syscall(compat_sys_mq_open); +cond_syscall(compat_sys_mq_timedsend); +cond_syscall(compat_sys_mq_timedreceive); +cond_syscall(compat_sys_mq_notify); +cond_syscall(compat_sys_mq_getsetattr); +cond_syscall(sys_mbind); +cond_syscall(sys_get_mempolicy); +cond_syscall(sys_set_mempolicy); +cond_syscall(compat_sys_mbind); +cond_syscall(compat_sys_get_mempolicy); +cond_syscall(compat_sys_set_mempolicy); +cond_syscall(sys_add_key); +cond_syscall(sys_request_key); +cond_syscall(sys_keyctl); +cond_syscall(compat_sys_keyctl); +cond_syscall(compat_sys_socketcall); +cond_syscall(sys_inotify_init); +cond_syscall(sys_inotify_init1); +cond_syscall(sys_inotify_add_watch); +cond_syscall(sys_inotify_rm_watch); +cond_syscall(sys_migrate_pages); +cond_syscall(sys_move_pages); +cond_syscall(sys_chown16); +cond_syscall(sys_fchown16); +cond_syscall(sys_getegid16); +cond_syscall(sys_geteuid16); +cond_syscall(sys_getgid16); +cond_syscall(sys_getgroups16); +cond_syscall(sys_getresgid16); +cond_syscall(sys_getresuid16); +cond_syscall(sys_getuid16); +cond_syscall(sys_lchown16); +cond_syscall(sys_setfsgid16); +cond_syscall(sys_setfsuid16); +cond_syscall(sys_setgid16); +cond_syscall(sys_setgroups16); +cond_syscall(sys_setregid16); +cond_syscall(sys_setresgid16); +cond_syscall(sys_setresuid16); +cond_syscall(sys_setreuid16); +cond_syscall(sys_setuid16); +cond_syscall(sys_sgetmask); +cond_syscall(sys_ssetmask); +cond_syscall(sys_vm86old); +cond_syscall(sys_vm86); +cond_syscall(sys_ipc); +cond_syscall(compat_sys_ipc); +cond_syscall(compat_sys_sysctl); +cond_syscall(sys_flock); +cond_syscall(sys_io_setup); +cond_syscall(sys_io_destroy); +cond_syscall(sys_io_submit); +cond_syscall(sys_io_cancel); +cond_syscall(sys_io_getevents); +cond_syscall(sys_sysfs); +cond_syscall(sys_syslog); +cond_syscall(sys_process_vm_readv); +cond_syscall(sys_process_vm_writev); +cond_syscall(compat_sys_process_vm_readv); +cond_syscall(compat_sys_process_vm_writev); +cond_syscall(sys_uselib); +cond_syscall(sys_fadvise64); +cond_syscall(sys_fadvise64_64); +cond_syscall(sys_madvise); +cond_syscall(sys_setuid); +cond_syscall(sys_setregid); +cond_syscall(sys_setgid); +cond_syscall(sys_setreuid); +cond_syscall(sys_setresuid); +cond_syscall(sys_getresuid); +cond_syscall(sys_setresgid); +cond_syscall(sys_getresgid); +cond_syscall(sys_setgroups); +cond_syscall(sys_getgroups); +cond_syscall(sys_setfsuid); +cond_syscall(sys_setfsgid); +cond_syscall(sys_capget); +cond_syscall(sys_capset); + +/* arch-specific weak syscall entries */ +cond_syscall(sys_pciconfig_read); +cond_syscall(sys_pciconfig_write); +cond_syscall(sys_pciconfig_iobase); +cond_syscall(compat_sys_s390_ipc); +cond_syscall(ppc_rtas); +cond_syscall(sys_spu_run); +cond_syscall(sys_spu_create); +cond_syscall(sys_subpage_prot); +cond_syscall(sys_s390_pci_mmio_read); +cond_syscall(sys_s390_pci_mmio_write); + +/* mmu depending weak syscall entries */ +cond_syscall(sys_mprotect); +cond_syscall(sys_msync); +cond_syscall(sys_mlock); +cond_syscall(sys_munlock); +cond_syscall(sys_mlockall); +cond_syscall(sys_munlockall); +cond_syscall(sys_mincore); +cond_syscall(sys_madvise); +cond_syscall(sys_mremap); +cond_syscall(sys_remap_file_pages); +cond_syscall(compat_sys_move_pages); +cond_syscall(compat_sys_migrate_pages); + +/* block-layer dependent */ +cond_syscall(sys_bdflush); +cond_syscall(sys_ioprio_set); +cond_syscall(sys_ioprio_get); + +/* New file descriptors */ +cond_syscall(sys_signalfd); +cond_syscall(sys_signalfd4); +cond_syscall(compat_sys_signalfd); +cond_syscall(compat_sys_signalfd4); +cond_syscall(sys_timerfd_create); +cond_syscall(sys_timerfd_settime); +cond_syscall(sys_timerfd_gettime); +cond_syscall(compat_sys_timerfd_settime); +cond_syscall(compat_sys_timerfd_gettime); +cond_syscall(sys_eventfd); +cond_syscall(sys_eventfd2); +cond_syscall(sys_memfd_create); + +/* performance counters: */ +cond_syscall(sys_perf_event_open); + +/* fanotify! */ +cond_syscall(sys_fanotify_init); +cond_syscall(sys_fanotify_mark); +cond_syscall(compat_sys_fanotify_mark); + +/* open by handle */ +cond_syscall(sys_name_to_handle_at); +cond_syscall(sys_open_by_handle_at); +cond_syscall(compat_sys_open_by_handle_at); + +/* compare kernel pointers */ +cond_syscall(sys_kcmp); + +/* operate on Secure Computing state */ +cond_syscall(sys_seccomp); + +/* access BPF programs and maps */ +cond_syscall(sys_bpf); + +/* execveat */ +cond_syscall(sys_execveat); diff --git a/kernel/kernel/sysctl.c b/kernel/kernel/sysctl.c new file mode 100644 index 000000000..c3eee4c6d --- /dev/null +++ b/kernel/kernel/sysctl.c @@ -0,0 +1,2792 @@ +/* + * sysctl.c: General linux system control interface + * + * Begun 24 March 1995, Stephen Tweedie + * Added /proc support, Dec 1995 + * Added bdflush entry and intvec min/max checking, 2/23/96, Tom Dyas. + * Added hooks for /proc/sys/net (minor, minor patch), 96/4/1, Mike Shaver. + * Added kernel/java-{interpreter,appletviewer}, 96/5/10, Mike Shaver. + * Dynamic registration fixes, Stephen Tweedie. + * Added kswapd-interval, ctrl-alt-del, printk stuff, 1/8/97, Chris Horn. + * Made sysctl support optional via CONFIG_SYSCTL, 1/10/97, Chris + * Horn. + * Added proc_doulongvec_ms_jiffies_minmax, 09/08/99, Carlos H. Bauer. + * Added proc_doulongvec_minmax, 09/08/99, Carlos H. Bauer. + * Changed linked lists to use list.h instead of lists.h, 02/24/00, Bill + * Wendling. + * The list_for_each() macro wasn't appropriate for the sysctl loop. + * Removed it and replaced it with older style, 03/23/00, Bill Wendling + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include + +#ifdef CONFIG_X86 +#include +#include +#include +#endif +#ifdef CONFIG_SPARC +#include +#endif +#ifdef CONFIG_BSD_PROCESS_ACCT +#include +#endif +#ifdef CONFIG_RT_MUTEXES +#include +#endif +#if defined(CONFIG_PROVE_LOCKING) || defined(CONFIG_LOCK_STAT) +#include +#endif +#ifdef CONFIG_CHR_DEV_SG +#include +#endif + +#ifdef CONFIG_LOCKUP_DETECTOR +#include +#endif + +#if defined(CONFIG_SYSCTL) + +/* External variables not in a header file. */ +extern int suid_dumpable; +#ifdef CONFIG_COREDUMP +extern int core_uses_pid; +extern char core_pattern[]; +extern unsigned int core_pipe_limit; +#endif +extern int pid_max; +extern int pid_max_min, pid_max_max; +extern int percpu_pagelist_fraction; +extern int compat_log; +extern int latencytop_enabled; +extern int sysctl_nr_open_min, sysctl_nr_open_max; +#ifndef CONFIG_MMU +extern int sysctl_nr_trim_pages; +#endif + +/* Constants used for minimum and maximum */ +#ifdef CONFIG_LOCKUP_DETECTOR +static int sixty = 60; +#endif + +static int __maybe_unused neg_one = -1; + +static int zero; +static int __maybe_unused one = 1; +static int __maybe_unused two = 2; +static int __maybe_unused four = 4; +static unsigned long one_ul = 1; +static int one_hundred = 100; +#ifdef CONFIG_PRINTK +static int ten_thousand = 10000; +#endif + +/* this is needed for the proc_doulongvec_minmax of vm_dirty_bytes */ +static unsigned long dirty_bytes_min = 2 * PAGE_SIZE; + +/* this is needed for the proc_dointvec_minmax for [fs_]overflow UID and GID */ +static int maxolduid = 65535; +static int minolduid; + +static int ngroups_max = NGROUPS_MAX; +static const int cap_last_cap = CAP_LAST_CAP; + +/*this is needed for proc_doulongvec_minmax of sysctl_hung_task_timeout_secs */ +#ifdef CONFIG_DETECT_HUNG_TASK +static unsigned long hung_task_timeout_max = (LONG_MAX/HZ); +#endif + +#ifdef CONFIG_INOTIFY_USER +#include +#endif +#ifdef CONFIG_SPARC +#endif + +#ifdef __hppa__ +extern int pwrsw_enabled; +#endif + +#ifdef CONFIG_SYSCTL_ARCH_UNALIGN_ALLOW +extern int unaligned_enabled; +#endif + +#ifdef CONFIG_IA64 +extern int unaligned_dump_stack; +#endif + +#ifdef CONFIG_SYSCTL_ARCH_UNALIGN_NO_WARN +extern int no_unaligned_warning; +#endif + +#ifdef CONFIG_PROC_SYSCTL + +#define SYSCTL_WRITES_LEGACY -1 +#define SYSCTL_WRITES_WARN 0 +#define SYSCTL_WRITES_STRICT 1 + +static int sysctl_writes_strict = SYSCTL_WRITES_WARN; + +static int proc_do_cad_pid(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos); +static int proc_taint(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos); +#endif + +#ifdef CONFIG_PRINTK +static int proc_dointvec_minmax_sysadmin(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos); +#endif + +static int proc_dointvec_minmax_coredump(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos); +#ifdef CONFIG_COREDUMP +static int proc_dostring_coredump(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos); +#endif + +#ifdef CONFIG_MAGIC_SYSRQ +/* Note: sysrq code uses it's own private copy */ +static int __sysrq_enabled = CONFIG_MAGIC_SYSRQ_DEFAULT_ENABLE; + +static int sysrq_sysctl_handler(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos) +{ + int error; + + error = proc_dointvec(table, write, buffer, lenp, ppos); + if (error) + return error; + + if (write) + sysrq_toggle_support(__sysrq_enabled); + + return 0; +} + +#endif + +static struct ctl_table kern_table[]; +static struct ctl_table vm_table[]; +static struct ctl_table fs_table[]; +static struct ctl_table debug_table[]; +static struct ctl_table dev_table[]; +extern struct ctl_table random_table[]; +#ifdef CONFIG_EPOLL +extern struct ctl_table epoll_table[]; +#endif + +#ifdef HAVE_ARCH_PICK_MMAP_LAYOUT +int sysctl_legacy_va_layout; +#endif + +/* The default sysctl tables: */ + +static struct ctl_table sysctl_base_table[] = { + { + .procname = "kernel", + .mode = 0555, + .child = kern_table, + }, + { + .procname = "vm", + .mode = 0555, + .child = vm_table, + }, + { + .procname = "fs", + .mode = 0555, + .child = fs_table, + }, + { + .procname = "debug", + .mode = 0555, + .child = debug_table, + }, + { + .procname = "dev", + .mode = 0555, + .child = dev_table, + }, + { } +}; + +#ifdef CONFIG_SCHED_DEBUG +static int min_sched_granularity_ns = 100000; /* 100 usecs */ +static int max_sched_granularity_ns = NSEC_PER_SEC; /* 1 second */ +static int min_wakeup_granularity_ns; /* 0 usecs */ +static int max_wakeup_granularity_ns = NSEC_PER_SEC; /* 1 second */ +#ifdef CONFIG_SMP +static int min_sched_tunable_scaling = SCHED_TUNABLESCALING_NONE; +static int max_sched_tunable_scaling = SCHED_TUNABLESCALING_END-1; +#endif /* CONFIG_SMP */ +#endif /* CONFIG_SCHED_DEBUG */ + +#ifdef CONFIG_COMPACTION +static int min_extfrag_threshold; +static int max_extfrag_threshold = 1000; +#endif + +static struct ctl_table kern_table[] = { + { + .procname = "sched_child_runs_first", + .data = &sysctl_sched_child_runs_first, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, +#ifdef CONFIG_SCHED_DEBUG + { + .procname = "sched_min_granularity_ns", + .data = &sysctl_sched_min_granularity, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = sched_proc_update_handler, + .extra1 = &min_sched_granularity_ns, + .extra2 = &max_sched_granularity_ns, + }, + { + .procname = "sched_latency_ns", + .data = &sysctl_sched_latency, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = sched_proc_update_handler, + .extra1 = &min_sched_granularity_ns, + .extra2 = &max_sched_granularity_ns, + }, + { + .procname = "sched_wakeup_granularity_ns", + .data = &sysctl_sched_wakeup_granularity, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = sched_proc_update_handler, + .extra1 = &min_wakeup_granularity_ns, + .extra2 = &max_wakeup_granularity_ns, + }, +#ifdef CONFIG_SMP + { + .procname = "sched_tunable_scaling", + .data = &sysctl_sched_tunable_scaling, + .maxlen = sizeof(enum sched_tunable_scaling), + .mode = 0644, + .proc_handler = sched_proc_update_handler, + .extra1 = &min_sched_tunable_scaling, + .extra2 = &max_sched_tunable_scaling, + }, + { + .procname = "sched_migration_cost_ns", + .data = &sysctl_sched_migration_cost, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .procname = "sched_nr_migrate", + .data = &sysctl_sched_nr_migrate, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .procname = "sched_time_avg_ms", + .data = &sysctl_sched_time_avg, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .procname = "sched_shares_window_ns", + .data = &sysctl_sched_shares_window, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .procname = "timer_migration", + .data = &sysctl_timer_migration, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &one, + }, +#endif /* CONFIG_SMP */ +#ifdef CONFIG_NUMA_BALANCING + { + .procname = "numa_balancing_scan_delay_ms", + .data = &sysctl_numa_balancing_scan_delay, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .procname = "numa_balancing_scan_period_min_ms", + .data = &sysctl_numa_balancing_scan_period_min, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .procname = "numa_balancing_scan_period_max_ms", + .data = &sysctl_numa_balancing_scan_period_max, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .procname = "numa_balancing_scan_size_mb", + .data = &sysctl_numa_balancing_scan_size, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &one, + }, + { + .procname = "numa_balancing", + .data = NULL, /* filled in by handler */ + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = sysctl_numa_balancing, + .extra1 = &zero, + .extra2 = &one, + }, +#endif /* CONFIG_NUMA_BALANCING */ +#endif /* CONFIG_SCHED_DEBUG */ + { + .procname = "sched_rt_period_us", + .data = &sysctl_sched_rt_period, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = sched_rt_handler, + }, + { + .procname = "sched_rt_runtime_us", + .data = &sysctl_sched_rt_runtime, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = sched_rt_handler, + }, + { + .procname = "sched_rr_timeslice_ms", + .data = &sched_rr_timeslice, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = sched_rr_handler, + }, +#ifdef CONFIG_SCHED_AUTOGROUP + { + .procname = "sched_autogroup_enabled", + .data = &sysctl_sched_autogroup_enabled, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &one, + }, +#endif +#ifdef CONFIG_CFS_BANDWIDTH + { + .procname = "sched_cfs_bandwidth_slice_us", + .data = &sysctl_sched_cfs_bandwidth_slice, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &one, + }, +#endif +#ifdef CONFIG_PROVE_LOCKING + { + .procname = "prove_locking", + .data = &prove_locking, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, +#endif +#ifdef CONFIG_LOCK_STAT + { + .procname = "lock_stat", + .data = &lock_stat, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, +#endif + { + .procname = "panic", + .data = &panic_timeout, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, +#ifdef CONFIG_COREDUMP + { + .procname = "core_uses_pid", + .data = &core_uses_pid, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .procname = "core_pattern", + .data = core_pattern, + .maxlen = CORENAME_MAX_SIZE, + .mode = 0644, + .proc_handler = proc_dostring_coredump, + }, + { + .procname = "core_pipe_limit", + .data = &core_pipe_limit, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, +#endif +#ifdef CONFIG_PROC_SYSCTL + { + .procname = "tainted", + .maxlen = sizeof(long), + .mode = 0644, + .proc_handler = proc_taint, + }, + { + .procname = "sysctl_writes_strict", + .data = &sysctl_writes_strict, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &neg_one, + .extra2 = &one, + }, +#endif +#ifdef CONFIG_LATENCYTOP + { + .procname = "latencytop", + .data = &latencytop_enabled, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, +#endif +#ifdef CONFIG_BLK_DEV_INITRD + { + .procname = "real-root-dev", + .data = &real_root_dev, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, +#endif + { + .procname = "print-fatal-signals", + .data = &print_fatal_signals, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, +#ifdef CONFIG_SPARC + { + .procname = "reboot-cmd", + .data = reboot_command, + .maxlen = 256, + .mode = 0644, + .proc_handler = proc_dostring, + }, + { + .procname = "stop-a", + .data = &stop_a_enabled, + .maxlen = sizeof (int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .procname = "scons-poweroff", + .data = &scons_pwroff, + .maxlen = sizeof (int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, +#endif +#ifdef CONFIG_SPARC64 + { + .procname = "tsb-ratio", + .data = &sysctl_tsb_ratio, + .maxlen = sizeof (int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, +#endif +#ifdef __hppa__ + { + .procname = "soft-power", + .data = &pwrsw_enabled, + .maxlen = sizeof (int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, +#endif +#ifdef CONFIG_SYSCTL_ARCH_UNALIGN_ALLOW + { + .procname = "unaligned-trap", + .data = &unaligned_enabled, + .maxlen = sizeof (int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, +#endif + { + .procname = "ctrl-alt-del", + .data = &C_A_D, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, +#ifdef CONFIG_FUNCTION_TRACER + { + .procname = "ftrace_enabled", + .data = &ftrace_enabled, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = ftrace_enable_sysctl, + }, +#endif +#ifdef CONFIG_STACK_TRACER + { + .procname = "stack_tracer_enabled", + .data = &stack_tracer_enabled, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = stack_trace_sysctl, + }, +#endif +#ifdef CONFIG_TRACING + { + .procname = "ftrace_dump_on_oops", + .data = &ftrace_dump_on_oops, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .procname = "traceoff_on_warning", + .data = &__disable_trace_on_warning, + .maxlen = sizeof(__disable_trace_on_warning), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .procname = "tracepoint_printk", + .data = &tracepoint_printk, + .maxlen = sizeof(tracepoint_printk), + .mode = 0644, + .proc_handler = proc_dointvec, + }, +#endif +#ifdef CONFIG_KEXEC + { + .procname = "kexec_load_disabled", + .data = &kexec_load_disabled, + .maxlen = sizeof(int), + .mode = 0644, + /* only handle a transition from default "0" to "1" */ + .proc_handler = proc_dointvec_minmax, + .extra1 = &one, + .extra2 = &one, + }, +#endif +#ifdef CONFIG_MODULES + { + .procname = "modprobe", + .data = &modprobe_path, + .maxlen = KMOD_PATH_LEN, + .mode = 0644, + .proc_handler = proc_dostring, + }, + { + .procname = "modules_disabled", + .data = &modules_disabled, + .maxlen = sizeof(int), + .mode = 0644, + /* only handle a transition from default "0" to "1" */ + .proc_handler = proc_dointvec_minmax, + .extra1 = &one, + .extra2 = &one, + }, +#endif +#ifdef CONFIG_UEVENT_HELPER + { + .procname = "hotplug", + .data = &uevent_helper, + .maxlen = UEVENT_HELPER_PATH_LEN, + .mode = 0644, + .proc_handler = proc_dostring, + }, +#endif +#ifdef CONFIG_CHR_DEV_SG + { + .procname = "sg-big-buff", + .data = &sg_big_buff, + .maxlen = sizeof (int), + .mode = 0444, + .proc_handler = proc_dointvec, + }, +#endif +#ifdef CONFIG_BSD_PROCESS_ACCT + { + .procname = "acct", + .data = &acct_parm, + .maxlen = 3*sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, +#endif +#ifdef CONFIG_MAGIC_SYSRQ + { + .procname = "sysrq", + .data = &__sysrq_enabled, + .maxlen = sizeof (int), + .mode = 0644, + .proc_handler = sysrq_sysctl_handler, + }, +#endif +#ifdef CONFIG_PROC_SYSCTL + { + .procname = "cad_pid", + .data = NULL, + .maxlen = sizeof (int), + .mode = 0600, + .proc_handler = proc_do_cad_pid, + }, +#endif + { + .procname = "threads-max", + .data = NULL, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = sysctl_max_threads, + }, + { + .procname = "random", + .mode = 0555, + .child = random_table, + }, + { + .procname = "usermodehelper", + .mode = 0555, + .child = usermodehelper_table, + }, + { + .procname = "overflowuid", + .data = &overflowuid, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &minolduid, + .extra2 = &maxolduid, + }, + { + .procname = "overflowgid", + .data = &overflowgid, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &minolduid, + .extra2 = &maxolduid, + }, +#ifdef CONFIG_S390 +#ifdef CONFIG_MATHEMU + { + .procname = "ieee_emulation_warnings", + .data = &sysctl_ieee_emulation_warnings, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, +#endif + { + .procname = "userprocess_debug", + .data = &show_unhandled_signals, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, +#endif + { + .procname = "pid_max", + .data = &pid_max, + .maxlen = sizeof (int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &pid_max_min, + .extra2 = &pid_max_max, + }, + { + .procname = "panic_on_oops", + .data = &panic_on_oops, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, +#if defined CONFIG_PRINTK + { + .procname = "printk", + .data = &console_loglevel, + .maxlen = 4*sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .procname = "printk_ratelimit", + .data = &printk_ratelimit_state.interval, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, + { + .procname = "printk_ratelimit_burst", + .data = &printk_ratelimit_state.burst, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .procname = "printk_delay", + .data = &printk_delay_msec, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &ten_thousand, + }, + { + .procname = "dmesg_restrict", + .data = &dmesg_restrict, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax_sysadmin, + .extra1 = &zero, + .extra2 = &one, + }, + { + .procname = "kptr_restrict", + .data = &kptr_restrict, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax_sysadmin, + .extra1 = &zero, + .extra2 = &two, + }, +#endif + { + .procname = "ngroups_max", + .data = &ngroups_max, + .maxlen = sizeof (int), + .mode = 0444, + .proc_handler = proc_dointvec, + }, + { + .procname = "cap_last_cap", + .data = (void *)&cap_last_cap, + .maxlen = sizeof(int), + .mode = 0444, + .proc_handler = proc_dointvec, + }, +#if defined(CONFIG_LOCKUP_DETECTOR) + { + .procname = "watchdog", + .data = &watchdog_user_enabled, + .maxlen = sizeof (int), + .mode = 0644, + .proc_handler = proc_watchdog, + .extra1 = &zero, + .extra2 = &one, + }, + { + .procname = "watchdog_thresh", + .data = &watchdog_thresh, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_watchdog_thresh, + .extra1 = &zero, + .extra2 = &sixty, + }, + { + .procname = "nmi_watchdog", + .data = &nmi_watchdog_enabled, + .maxlen = sizeof (int), + .mode = 0644, + .proc_handler = proc_nmi_watchdog, + .extra1 = &zero, +#if defined(CONFIG_HAVE_NMI_WATCHDOG) || defined(CONFIG_HARDLOCKUP_DETECTOR) + .extra2 = &one, +#else + .extra2 = &zero, +#endif + }, + { + .procname = "soft_watchdog", + .data = &soft_watchdog_enabled, + .maxlen = sizeof (int), + .mode = 0644, + .proc_handler = proc_soft_watchdog, + .extra1 = &zero, + .extra2 = &one, + }, + { + .procname = "softlockup_panic", + .data = &softlockup_panic, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &one, + }, +#ifdef CONFIG_SMP + { + .procname = "softlockup_all_cpu_backtrace", + .data = &sysctl_softlockup_all_cpu_backtrace, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &one, + }, +#endif /* CONFIG_SMP */ +#endif +#if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86) + { + .procname = "unknown_nmi_panic", + .data = &unknown_nmi_panic, + .maxlen = sizeof (int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, +#endif +#if defined(CONFIG_X86) + { + .procname = "panic_on_unrecovered_nmi", + .data = &panic_on_unrecovered_nmi, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .procname = "panic_on_io_nmi", + .data = &panic_on_io_nmi, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, +#ifdef CONFIG_DEBUG_STACKOVERFLOW + { + .procname = "panic_on_stackoverflow", + .data = &sysctl_panic_on_stackoverflow, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, +#endif + { + .procname = "bootloader_type", + .data = &bootloader_type, + .maxlen = sizeof (int), + .mode = 0444, + .proc_handler = proc_dointvec, + }, + { + .procname = "bootloader_version", + .data = &bootloader_version, + .maxlen = sizeof (int), + .mode = 0444, + .proc_handler = proc_dointvec, + }, + { + .procname = "kstack_depth_to_print", + .data = &kstack_depth_to_print, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .procname = "io_delay_type", + .data = &io_delay_type, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, +#endif +#if defined(CONFIG_MMU) + { + .procname = "randomize_va_space", + .data = &randomize_va_space, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, +#endif +#if defined(CONFIG_S390) && defined(CONFIG_SMP) + { + .procname = "spin_retry", + .data = &spin_retry, + .maxlen = sizeof (int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, +#endif +#if defined(CONFIG_ACPI_SLEEP) && defined(CONFIG_X86) + { + .procname = "acpi_video_flags", + .data = &acpi_realmode_flags, + .maxlen = sizeof (unsigned long), + .mode = 0644, + .proc_handler = proc_doulongvec_minmax, + }, +#endif +#ifdef CONFIG_SYSCTL_ARCH_UNALIGN_NO_WARN + { + .procname = "ignore-unaligned-usertrap", + .data = &no_unaligned_warning, + .maxlen = sizeof (int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, +#endif +#ifdef CONFIG_IA64 + { + .procname = "unaligned-dump-stack", + .data = &unaligned_dump_stack, + .maxlen = sizeof (int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, +#endif +#ifdef CONFIG_DETECT_HUNG_TASK + { + .procname = "hung_task_panic", + .data = &sysctl_hung_task_panic, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &one, + }, + { + .procname = "hung_task_check_count", + .data = &sysctl_hung_task_check_count, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + }, + { + .procname = "hung_task_timeout_secs", + .data = &sysctl_hung_task_timeout_secs, + .maxlen = sizeof(unsigned long), + .mode = 0644, + .proc_handler = proc_dohung_task_timeout_secs, + .extra2 = &hung_task_timeout_max, + }, + { + .procname = "hung_task_warnings", + .data = &sysctl_hung_task_warnings, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &neg_one, + }, +#endif +#ifdef CONFIG_COMPAT + { + .procname = "compat-log", + .data = &compat_log, + .maxlen = sizeof (int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, +#endif +#ifdef CONFIG_RT_MUTEXES + { + .procname = "max_lock_depth", + .data = &max_lock_depth, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, +#endif + { + .procname = "poweroff_cmd", + .data = &poweroff_cmd, + .maxlen = POWEROFF_CMD_PATH_LEN, + .mode = 0644, + .proc_handler = proc_dostring, + }, +#ifdef CONFIG_KEYS + { + .procname = "keys", + .mode = 0555, + .child = key_sysctls, + }, +#endif +#ifdef CONFIG_PERF_EVENTS + /* + * User-space scripts rely on the existence of this file + * as a feature check for perf_events being enabled. + * + * So it's an ABI, do not remove! + */ + { + .procname = "perf_event_paranoid", + .data = &sysctl_perf_event_paranoid, + .maxlen = sizeof(sysctl_perf_event_paranoid), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .procname = "perf_event_mlock_kb", + .data = &sysctl_perf_event_mlock, + .maxlen = sizeof(sysctl_perf_event_mlock), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .procname = "perf_event_max_sample_rate", + .data = &sysctl_perf_event_sample_rate, + .maxlen = sizeof(sysctl_perf_event_sample_rate), + .mode = 0644, + .proc_handler = perf_proc_update_handler, + .extra1 = &one, + }, + { + .procname = "perf_cpu_time_max_percent", + .data = &sysctl_perf_cpu_time_max_percent, + .maxlen = sizeof(sysctl_perf_cpu_time_max_percent), + .mode = 0644, + .proc_handler = perf_cpu_time_max_percent_handler, + .extra1 = &zero, + .extra2 = &one_hundred, + }, +#endif +#ifdef CONFIG_KMEMCHECK + { + .procname = "kmemcheck", + .data = &kmemcheck_enabled, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, +#endif + { + .procname = "panic_on_warn", + .data = &panic_on_warn, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &one, + }, + { } +}; + +static struct ctl_table vm_table[] = { + { + .procname = "overcommit_memory", + .data = &sysctl_overcommit_memory, + .maxlen = sizeof(sysctl_overcommit_memory), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &two, + }, + { + .procname = "panic_on_oom", + .data = &sysctl_panic_on_oom, + .maxlen = sizeof(sysctl_panic_on_oom), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &two, + }, + { + .procname = "oom_kill_allocating_task", + .data = &sysctl_oom_kill_allocating_task, + .maxlen = sizeof(sysctl_oom_kill_allocating_task), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .procname = "oom_dump_tasks", + .data = &sysctl_oom_dump_tasks, + .maxlen = sizeof(sysctl_oom_dump_tasks), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .procname = "overcommit_ratio", + .data = &sysctl_overcommit_ratio, + .maxlen = sizeof(sysctl_overcommit_ratio), + .mode = 0644, + .proc_handler = overcommit_ratio_handler, + }, + { + .procname = "overcommit_kbytes", + .data = &sysctl_overcommit_kbytes, + .maxlen = sizeof(sysctl_overcommit_kbytes), + .mode = 0644, + .proc_handler = overcommit_kbytes_handler, + }, + { + .procname = "page-cluster", + .data = &page_cluster, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + }, + { + .procname = "dirty_background_ratio", + .data = &dirty_background_ratio, + .maxlen = sizeof(dirty_background_ratio), + .mode = 0644, + .proc_handler = dirty_background_ratio_handler, + .extra1 = &zero, + .extra2 = &one_hundred, + }, + { + .procname = "dirty_background_bytes", + .data = &dirty_background_bytes, + .maxlen = sizeof(dirty_background_bytes), + .mode = 0644, + .proc_handler = dirty_background_bytes_handler, + .extra1 = &one_ul, + }, + { + .procname = "dirty_ratio", + .data = &vm_dirty_ratio, + .maxlen = sizeof(vm_dirty_ratio), + .mode = 0644, + .proc_handler = dirty_ratio_handler, + .extra1 = &zero, + .extra2 = &one_hundred, + }, + { + .procname = "dirty_bytes", + .data = &vm_dirty_bytes, + .maxlen = sizeof(vm_dirty_bytes), + .mode = 0644, + .proc_handler = dirty_bytes_handler, + .extra1 = &dirty_bytes_min, + }, + { + .procname = "dirty_writeback_centisecs", + .data = &dirty_writeback_interval, + .maxlen = sizeof(dirty_writeback_interval), + .mode = 0644, + .proc_handler = dirty_writeback_centisecs_handler, + }, + { + .procname = "dirty_expire_centisecs", + .data = &dirty_expire_interval, + .maxlen = sizeof(dirty_expire_interval), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + }, + { + .procname = "dirtytime_expire_seconds", + .data = &dirtytime_expire_interval, + .maxlen = sizeof(dirty_expire_interval), + .mode = 0644, + .proc_handler = dirtytime_interval_handler, + .extra1 = &zero, + }, + { + .procname = "nr_pdflush_threads", + .mode = 0444 /* read-only */, + .proc_handler = pdflush_proc_obsolete, + }, + { + .procname = "swappiness", + .data = &vm_swappiness, + .maxlen = sizeof(vm_swappiness), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &one_hundred, + }, +#ifdef CONFIG_HUGETLB_PAGE + { + .procname = "nr_hugepages", + .data = NULL, + .maxlen = sizeof(unsigned long), + .mode = 0644, + .proc_handler = hugetlb_sysctl_handler, + }, +#ifdef CONFIG_NUMA + { + .procname = "nr_hugepages_mempolicy", + .data = NULL, + .maxlen = sizeof(unsigned long), + .mode = 0644, + .proc_handler = &hugetlb_mempolicy_sysctl_handler, + }, +#endif + { + .procname = "hugetlb_shm_group", + .data = &sysctl_hugetlb_shm_group, + .maxlen = sizeof(gid_t), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .procname = "hugepages_treat_as_movable", + .data = &hugepages_treat_as_movable, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .procname = "nr_overcommit_hugepages", + .data = NULL, + .maxlen = sizeof(unsigned long), + .mode = 0644, + .proc_handler = hugetlb_overcommit_handler, + }, +#endif + { + .procname = "lowmem_reserve_ratio", + .data = &sysctl_lowmem_reserve_ratio, + .maxlen = sizeof(sysctl_lowmem_reserve_ratio), + .mode = 0644, + .proc_handler = lowmem_reserve_ratio_sysctl_handler, + }, + { + .procname = "drop_caches", + .data = &sysctl_drop_caches, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = drop_caches_sysctl_handler, + .extra1 = &one, + .extra2 = &four, + }, +#ifdef CONFIG_COMPACTION + { + .procname = "compact_memory", + .data = &sysctl_compact_memory, + .maxlen = sizeof(int), + .mode = 0200, + .proc_handler = sysctl_compaction_handler, + }, + { + .procname = "extfrag_threshold", + .data = &sysctl_extfrag_threshold, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = sysctl_extfrag_handler, + .extra1 = &min_extfrag_threshold, + .extra2 = &max_extfrag_threshold, + }, + { + .procname = "compact_unevictable_allowed", + .data = &sysctl_compact_unevictable_allowed, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + .extra1 = &zero, + .extra2 = &one, + }, + +#endif /* CONFIG_COMPACTION */ + { + .procname = "min_free_kbytes", + .data = &min_free_kbytes, + .maxlen = sizeof(min_free_kbytes), + .mode = 0644, + .proc_handler = min_free_kbytes_sysctl_handler, + .extra1 = &zero, + }, + { + .procname = "percpu_pagelist_fraction", + .data = &percpu_pagelist_fraction, + .maxlen = sizeof(percpu_pagelist_fraction), + .mode = 0644, + .proc_handler = percpu_pagelist_fraction_sysctl_handler, + .extra1 = &zero, + }, +#ifdef CONFIG_MMU + { + .procname = "max_map_count", + .data = &sysctl_max_map_count, + .maxlen = sizeof(sysctl_max_map_count), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + }, +#else + { + .procname = "nr_trim_pages", + .data = &sysctl_nr_trim_pages, + .maxlen = sizeof(sysctl_nr_trim_pages), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + }, +#endif + { + .procname = "laptop_mode", + .data = &laptop_mode, + .maxlen = sizeof(laptop_mode), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, + { + .procname = "block_dump", + .data = &block_dump, + .maxlen = sizeof(block_dump), + .mode = 0644, + .proc_handler = proc_dointvec, + .extra1 = &zero, + }, + { + .procname = "vfs_cache_pressure", + .data = &sysctl_vfs_cache_pressure, + .maxlen = sizeof(sysctl_vfs_cache_pressure), + .mode = 0644, + .proc_handler = proc_dointvec, + .extra1 = &zero, + }, +#ifdef HAVE_ARCH_PICK_MMAP_LAYOUT + { + .procname = "legacy_va_layout", + .data = &sysctl_legacy_va_layout, + .maxlen = sizeof(sysctl_legacy_va_layout), + .mode = 0644, + .proc_handler = proc_dointvec, + .extra1 = &zero, + }, +#endif +#ifdef CONFIG_NUMA + { + .procname = "zone_reclaim_mode", + .data = &zone_reclaim_mode, + .maxlen = sizeof(zone_reclaim_mode), + .mode = 0644, + .proc_handler = proc_dointvec, + .extra1 = &zero, + }, + { + .procname = "min_unmapped_ratio", + .data = &sysctl_min_unmapped_ratio, + .maxlen = sizeof(sysctl_min_unmapped_ratio), + .mode = 0644, + .proc_handler = sysctl_min_unmapped_ratio_sysctl_handler, + .extra1 = &zero, + .extra2 = &one_hundred, + }, + { + .procname = "min_slab_ratio", + .data = &sysctl_min_slab_ratio, + .maxlen = sizeof(sysctl_min_slab_ratio), + .mode = 0644, + .proc_handler = sysctl_min_slab_ratio_sysctl_handler, + .extra1 = &zero, + .extra2 = &one_hundred, + }, +#endif +#ifdef CONFIG_SMP + { + .procname = "stat_interval", + .data = &sysctl_stat_interval, + .maxlen = sizeof(sysctl_stat_interval), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, +#endif +#ifdef CONFIG_MMU + { + .procname = "mmap_min_addr", + .data = &dac_mmap_min_addr, + .maxlen = sizeof(unsigned long), + .mode = 0644, + .proc_handler = mmap_min_addr_handler, + }, +#endif +#ifdef CONFIG_NUMA + { + .procname = "numa_zonelist_order", + .data = &numa_zonelist_order, + .maxlen = NUMA_ZONELIST_ORDER_LEN, + .mode = 0644, + .proc_handler = numa_zonelist_order_handler, + }, +#endif +#if (defined(CONFIG_X86_32) && !defined(CONFIG_UML))|| \ + (defined(CONFIG_SUPERH) && defined(CONFIG_VSYSCALL)) + { + .procname = "vdso_enabled", +#ifdef CONFIG_X86_32 + .data = &vdso32_enabled, + .maxlen = sizeof(vdso32_enabled), +#else + .data = &vdso_enabled, + .maxlen = sizeof(vdso_enabled), +#endif + .mode = 0644, + .proc_handler = proc_dointvec, + .extra1 = &zero, + }, +#endif +#ifdef CONFIG_HIGHMEM + { + .procname = "highmem_is_dirtyable", + .data = &vm_highmem_is_dirtyable, + .maxlen = sizeof(vm_highmem_is_dirtyable), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &one, + }, +#endif +#ifdef CONFIG_MEMORY_FAILURE + { + .procname = "memory_failure_early_kill", + .data = &sysctl_memory_failure_early_kill, + .maxlen = sizeof(sysctl_memory_failure_early_kill), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &one, + }, + { + .procname = "memory_failure_recovery", + .data = &sysctl_memory_failure_recovery, + .maxlen = sizeof(sysctl_memory_failure_recovery), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &one, + }, +#endif + { + .procname = "user_reserve_kbytes", + .data = &sysctl_user_reserve_kbytes, + .maxlen = sizeof(sysctl_user_reserve_kbytes), + .mode = 0644, + .proc_handler = proc_doulongvec_minmax, + }, + { + .procname = "admin_reserve_kbytes", + .data = &sysctl_admin_reserve_kbytes, + .maxlen = sizeof(sysctl_admin_reserve_kbytes), + .mode = 0644, + .proc_handler = proc_doulongvec_minmax, + }, + { } +}; + +static struct ctl_table fs_table[] = { + { + .procname = "inode-nr", + .data = &inodes_stat, + .maxlen = 2*sizeof(long), + .mode = 0444, + .proc_handler = proc_nr_inodes, + }, + { + .procname = "inode-state", + .data = &inodes_stat, + .maxlen = 7*sizeof(long), + .mode = 0444, + .proc_handler = proc_nr_inodes, + }, + { + .procname = "file-nr", + .data = &files_stat, + .maxlen = sizeof(files_stat), + .mode = 0444, + .proc_handler = proc_nr_files, + }, + { + .procname = "file-max", + .data = &files_stat.max_files, + .maxlen = sizeof(files_stat.max_files), + .mode = 0644, + .proc_handler = proc_doulongvec_minmax, + }, + { + .procname = "nr_open", + .data = &sysctl_nr_open, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &sysctl_nr_open_min, + .extra2 = &sysctl_nr_open_max, + }, + { + .procname = "dentry-state", + .data = &dentry_stat, + .maxlen = 6*sizeof(long), + .mode = 0444, + .proc_handler = proc_nr_dentry, + }, + { + .procname = "overflowuid", + .data = &fs_overflowuid, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &minolduid, + .extra2 = &maxolduid, + }, + { + .procname = "overflowgid", + .data = &fs_overflowgid, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &minolduid, + .extra2 = &maxolduid, + }, +#ifdef CONFIG_FILE_LOCKING + { + .procname = "leases-enable", + .data = &leases_enable, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, +#endif +#ifdef CONFIG_DNOTIFY + { + .procname = "dir-notify-enable", + .data = &dir_notify_enable, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, +#endif +#ifdef CONFIG_MMU +#ifdef CONFIG_FILE_LOCKING + { + .procname = "lease-break-time", + .data = &lease_break_time, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, +#endif +#ifdef CONFIG_AIO + { + .procname = "aio-nr", + .data = &aio_nr, + .maxlen = sizeof(aio_nr), + .mode = 0444, + .proc_handler = proc_doulongvec_minmax, + }, + { + .procname = "aio-max-nr", + .data = &aio_max_nr, + .maxlen = sizeof(aio_max_nr), + .mode = 0644, + .proc_handler = proc_doulongvec_minmax, + }, +#endif /* CONFIG_AIO */ +#ifdef CONFIG_INOTIFY_USER + { + .procname = "inotify", + .mode = 0555, + .child = inotify_table, + }, +#endif +#ifdef CONFIG_EPOLL + { + .procname = "epoll", + .mode = 0555, + .child = epoll_table, + }, +#endif +#endif + { + .procname = "protected_symlinks", + .data = &sysctl_protected_symlinks, + .maxlen = sizeof(int), + .mode = 0600, + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &one, + }, + { + .procname = "protected_hardlinks", + .data = &sysctl_protected_hardlinks, + .maxlen = sizeof(int), + .mode = 0600, + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &one, + }, + { + .procname = "suid_dumpable", + .data = &suid_dumpable, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax_coredump, + .extra1 = &zero, + .extra2 = &two, + }, +#if defined(CONFIG_BINFMT_MISC) || defined(CONFIG_BINFMT_MISC_MODULE) + { + .procname = "binfmt_misc", + .mode = 0555, + .child = sysctl_mount_point, + }, +#endif + { + .procname = "pipe-max-size", + .data = &pipe_max_size, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = &pipe_proc_fn, + .extra1 = &pipe_min_size, + }, + { } +}; + +static struct ctl_table debug_table[] = { +#ifdef CONFIG_SYSCTL_EXCEPTION_TRACE + { + .procname = "exception-trace", + .data = &show_unhandled_signals, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, +#endif +#if defined(CONFIG_OPTPROBES) + { + .procname = "kprobes-optimization", + .data = &sysctl_kprobes_optimization, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_kprobes_optimization_handler, + .extra1 = &zero, + .extra2 = &one, + }, +#endif + { } +}; + +static struct ctl_table dev_table[] = { + { } +}; + +int __init sysctl_init(void) +{ + struct ctl_table_header *hdr; + + hdr = register_sysctl_table(sysctl_base_table); + kmemleak_not_leak(hdr); + return 0; +} + +#endif /* CONFIG_SYSCTL */ + +/* + * /proc/sys support + */ + +#ifdef CONFIG_PROC_SYSCTL + +static int _proc_do_string(char *data, int maxlen, int write, + char __user *buffer, + size_t *lenp, loff_t *ppos) +{ + size_t len; + char __user *p; + char c; + + if (!data || !maxlen || !*lenp) { + *lenp = 0; + return 0; + } + + if (write) { + if (sysctl_writes_strict == SYSCTL_WRITES_STRICT) { + /* Only continue writes not past the end of buffer. */ + len = strlen(data); + if (len > maxlen - 1) + len = maxlen - 1; + + if (*ppos > len) + return 0; + len = *ppos; + } else { + /* Start writing from beginning of buffer. */ + len = 0; + } + + *ppos += *lenp; + p = buffer; + while ((p - buffer) < *lenp && len < maxlen - 1) { + if (get_user(c, p++)) + return -EFAULT; + if (c == 0 || c == '\n') + break; + data[len++] = c; + } + data[len] = 0; + } else { + len = strlen(data); + if (len > maxlen) + len = maxlen; + + if (*ppos > len) { + *lenp = 0; + return 0; + } + + data += *ppos; + len -= *ppos; + + if (len > *lenp) + len = *lenp; + if (len) + if (copy_to_user(buffer, data, len)) + return -EFAULT; + if (len < *lenp) { + if (put_user('\n', buffer + len)) + return -EFAULT; + len++; + } + *lenp = len; + *ppos += len; + } + return 0; +} + +static void warn_sysctl_write(struct ctl_table *table) +{ + pr_warn_once("%s wrote to %s when file position was not 0!\n" + "This will not be supported in the future. To silence this\n" + "warning, set kernel.sysctl_writes_strict = -1\n", + current->comm, table->procname); +} + +/** + * proc_dostring - read a string sysctl + * @table: the sysctl table + * @write: %TRUE if this is a write to the sysctl file + * @buffer: the user buffer + * @lenp: the size of the user buffer + * @ppos: file position + * + * Reads/writes a string from/to the user buffer. If the kernel + * buffer provided is not large enough to hold the string, the + * string is truncated. The copied string is %NULL-terminated. + * If the string is being read by the user process, it is copied + * and a newline '\n' is added. It is truncated if the buffer is + * not large enough. + * + * Returns 0 on success. + */ +int proc_dostring(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + if (write && *ppos && sysctl_writes_strict == SYSCTL_WRITES_WARN) + warn_sysctl_write(table); + + return _proc_do_string((char *)(table->data), table->maxlen, write, + (char __user *)buffer, lenp, ppos); +} + +static size_t proc_skip_spaces(char **buf) +{ + size_t ret; + char *tmp = skip_spaces(*buf); + ret = tmp - *buf; + *buf = tmp; + return ret; +} + +static void proc_skip_char(char **buf, size_t *size, const char v) +{ + while (*size) { + if (**buf != v) + break; + (*size)--; + (*buf)++; + } +} + +#define TMPBUFLEN 22 +/** + * proc_get_long - reads an ASCII formatted integer from a user buffer + * + * @buf: a kernel buffer + * @size: size of the kernel buffer + * @val: this is where the number will be stored + * @neg: set to %TRUE if number is negative + * @perm_tr: a vector which contains the allowed trailers + * @perm_tr_len: size of the perm_tr vector + * @tr: pointer to store the trailer character + * + * In case of success %0 is returned and @buf and @size are updated with + * the amount of bytes read. If @tr is non-NULL and a trailing + * character exists (size is non-zero after returning from this + * function), @tr is updated with the trailing character. + */ +static int proc_get_long(char **buf, size_t *size, + unsigned long *val, bool *neg, + const char *perm_tr, unsigned perm_tr_len, char *tr) +{ + int len; + char *p, tmp[TMPBUFLEN]; + + if (!*size) + return -EINVAL; + + len = *size; + if (len > TMPBUFLEN - 1) + len = TMPBUFLEN - 1; + + memcpy(tmp, *buf, len); + + tmp[len] = 0; + p = tmp; + if (*p == '-' && *size > 1) { + *neg = true; + p++; + } else + *neg = false; + if (!isdigit(*p)) + return -EINVAL; + + *val = simple_strtoul(p, &p, 0); + + len = p - tmp; + + /* We don't know if the next char is whitespace thus we may accept + * invalid integers (e.g. 1234...a) or two integers instead of one + * (e.g. 123...1). So lets not allow such large numbers. */ + if (len == TMPBUFLEN - 1) + return -EINVAL; + + if (len < *size && perm_tr_len && !memchr(perm_tr, *p, perm_tr_len)) + return -EINVAL; + + if (tr && (len < *size)) + *tr = *p; + + *buf += len; + *size -= len; + + return 0; +} + +/** + * proc_put_long - converts an integer to a decimal ASCII formatted string + * + * @buf: the user buffer + * @size: the size of the user buffer + * @val: the integer to be converted + * @neg: sign of the number, %TRUE for negative + * + * In case of success %0 is returned and @buf and @size are updated with + * the amount of bytes written. + */ +static int proc_put_long(void __user **buf, size_t *size, unsigned long val, + bool neg) +{ + int len; + char tmp[TMPBUFLEN], *p = tmp; + + sprintf(p, "%s%lu", neg ? "-" : "", val); + len = strlen(tmp); + if (len > *size) + len = *size; + if (copy_to_user(*buf, tmp, len)) + return -EFAULT; + *size -= len; + *buf += len; + return 0; +} +#undef TMPBUFLEN + +static int proc_put_char(void __user **buf, size_t *size, char c) +{ + if (*size) { + char __user **buffer = (char __user **)buf; + if (put_user(c, *buffer)) + return -EFAULT; + (*size)--, (*buffer)++; + *buf = *buffer; + } + return 0; +} + +static int do_proc_dointvec_conv(bool *negp, unsigned long *lvalp, + int *valp, + int write, void *data) +{ + if (write) { + if (*negp) { + if (*lvalp > (unsigned long) INT_MAX + 1) + return -EINVAL; + *valp = -*lvalp; + } else { + if (*lvalp > (unsigned long) INT_MAX) + return -EINVAL; + *valp = *lvalp; + } + } else { + int val = *valp; + if (val < 0) { + *negp = true; + *lvalp = (unsigned long)-val; + } else { + *negp = false; + *lvalp = (unsigned long)val; + } + } + return 0; +} + +static const char proc_wspace_sep[] = { ' ', '\t', '\n' }; + +static int __do_proc_dointvec(void *tbl_data, struct ctl_table *table, + int write, void __user *buffer, + size_t *lenp, loff_t *ppos, + int (*conv)(bool *negp, unsigned long *lvalp, int *valp, + int write, void *data), + void *data) +{ + int *i, vleft, first = 1, err = 0; + unsigned long page = 0; + size_t left; + char *kbuf; + + if (!tbl_data || !table->maxlen || !*lenp || (*ppos && !write)) { + *lenp = 0; + return 0; + } + + i = (int *) tbl_data; + vleft = table->maxlen / sizeof(*i); + left = *lenp; + + if (!conv) + conv = do_proc_dointvec_conv; + + if (write) { + if (*ppos) { + switch (sysctl_writes_strict) { + case SYSCTL_WRITES_STRICT: + goto out; + case SYSCTL_WRITES_WARN: + warn_sysctl_write(table); + break; + default: + break; + } + } + + if (left > PAGE_SIZE - 1) + left = PAGE_SIZE - 1; + page = __get_free_page(GFP_TEMPORARY); + kbuf = (char *) page; + if (!kbuf) + return -ENOMEM; + if (copy_from_user(kbuf, buffer, left)) { + err = -EFAULT; + goto free; + } + kbuf[left] = 0; + } + + for (; left && vleft--; i++, first=0) { + unsigned long lval; + bool neg; + + if (write) { + left -= proc_skip_spaces(&kbuf); + + if (!left) + break; + err = proc_get_long(&kbuf, &left, &lval, &neg, + proc_wspace_sep, + sizeof(proc_wspace_sep), NULL); + if (err) + break; + if (conv(&neg, &lval, i, 1, data)) { + err = -EINVAL; + break; + } + } else { + if (conv(&neg, &lval, i, 0, data)) { + err = -EINVAL; + break; + } + if (!first) + err = proc_put_char(&buffer, &left, '\t'); + if (err) + break; + err = proc_put_long(&buffer, &left, lval, neg); + if (err) + break; + } + } + + if (!write && !first && left && !err) + err = proc_put_char(&buffer, &left, '\n'); + if (write && !err && left) + left -= proc_skip_spaces(&kbuf); +free: + if (write) { + free_page(page); + if (first) + return err ? : -EINVAL; + } + *lenp -= left; +out: + *ppos += *lenp; + return err; +} + +static int do_proc_dointvec(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos, + int (*conv)(bool *negp, unsigned long *lvalp, int *valp, + int write, void *data), + void *data) +{ + return __do_proc_dointvec(table->data, table, write, + buffer, lenp, ppos, conv, data); +} + +/** + * proc_dointvec - read a vector of integers + * @table: the sysctl table + * @write: %TRUE if this is a write to the sysctl file + * @buffer: the user buffer + * @lenp: the size of the user buffer + * @ppos: file position + * + * Reads/writes up to table->maxlen/sizeof(unsigned int) integer + * values from/to the user buffer, treated as an ASCII string. + * + * Returns 0 on success. + */ +int proc_dointvec(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + return do_proc_dointvec(table,write,buffer,lenp,ppos, + NULL,NULL); +} + +/* + * Taint values can only be increased + * This means we can safely use a temporary. + */ +static int proc_taint(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + struct ctl_table t; + unsigned long tmptaint = get_taint(); + int err; + + if (write && !capable(CAP_SYS_ADMIN)) + return -EPERM; + + t = *table; + t.data = &tmptaint; + err = proc_doulongvec_minmax(&t, write, buffer, lenp, ppos); + if (err < 0) + return err; + + if (write) { + /* + * Poor man's atomic or. Not worth adding a primitive + * to everyone's atomic.h for this + */ + int i; + for (i = 0; i < BITS_PER_LONG && tmptaint >> i; i++) { + if ((tmptaint >> i) & 1) + add_taint(i, LOCKDEP_STILL_OK); + } + } + + return err; +} + +#ifdef CONFIG_PRINTK +static int proc_dointvec_minmax_sysadmin(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + if (write && !capable(CAP_SYS_ADMIN)) + return -EPERM; + + return proc_dointvec_minmax(table, write, buffer, lenp, ppos); +} +#endif + +struct do_proc_dointvec_minmax_conv_param { + int *min; + int *max; +}; + +static int do_proc_dointvec_minmax_conv(bool *negp, unsigned long *lvalp, + int *valp, + int write, void *data) +{ + struct do_proc_dointvec_minmax_conv_param *param = data; + if (write) { + int val = *negp ? -*lvalp : *lvalp; + if ((param->min && *param->min > val) || + (param->max && *param->max < val)) + return -EINVAL; + *valp = val; + } else { + int val = *valp; + if (val < 0) { + *negp = true; + *lvalp = (unsigned long)-val; + } else { + *negp = false; + *lvalp = (unsigned long)val; + } + } + return 0; +} + +/** + * proc_dointvec_minmax - read a vector of integers with min/max values + * @table: the sysctl table + * @write: %TRUE if this is a write to the sysctl file + * @buffer: the user buffer + * @lenp: the size of the user buffer + * @ppos: file position + * + * Reads/writes up to table->maxlen/sizeof(unsigned int) integer + * values from/to the user buffer, treated as an ASCII string. + * + * This routine will ensure the values are within the range specified by + * table->extra1 (min) and table->extra2 (max). + * + * Returns 0 on success. + */ +int proc_dointvec_minmax(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + struct do_proc_dointvec_minmax_conv_param param = { + .min = (int *) table->extra1, + .max = (int *) table->extra2, + }; + return do_proc_dointvec(table, write, buffer, lenp, ppos, + do_proc_dointvec_minmax_conv, ¶m); +} + +static void validate_coredump_safety(void) +{ +#ifdef CONFIG_COREDUMP + if (suid_dumpable == SUID_DUMP_ROOT && + core_pattern[0] != '/' && core_pattern[0] != '|') { + printk(KERN_WARNING "Unsafe core_pattern used with "\ + "suid_dumpable=2. Pipe handler or fully qualified "\ + "core dump path required.\n"); + } +#endif +} + +static int proc_dointvec_minmax_coredump(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + int error = proc_dointvec_minmax(table, write, buffer, lenp, ppos); + if (!error) + validate_coredump_safety(); + return error; +} + +#ifdef CONFIG_COREDUMP +static int proc_dostring_coredump(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + int error = proc_dostring(table, write, buffer, lenp, ppos); + if (!error) + validate_coredump_safety(); + return error; +} +#endif + +static int __do_proc_doulongvec_minmax(void *data, struct ctl_table *table, int write, + void __user *buffer, + size_t *lenp, loff_t *ppos, + unsigned long convmul, + unsigned long convdiv) +{ + unsigned long *i, *min, *max; + int vleft, first = 1, err = 0; + unsigned long page = 0; + size_t left; + char *kbuf; + + if (!data || !table->maxlen || !*lenp || (*ppos && !write)) { + *lenp = 0; + return 0; + } + + i = (unsigned long *) data; + min = (unsigned long *) table->extra1; + max = (unsigned long *) table->extra2; + vleft = table->maxlen / sizeof(unsigned long); + left = *lenp; + + if (write) { + if (*ppos) { + switch (sysctl_writes_strict) { + case SYSCTL_WRITES_STRICT: + goto out; + case SYSCTL_WRITES_WARN: + warn_sysctl_write(table); + break; + default: + break; + } + } + + if (left > PAGE_SIZE - 1) + left = PAGE_SIZE - 1; + page = __get_free_page(GFP_TEMPORARY); + kbuf = (char *) page; + if (!kbuf) + return -ENOMEM; + if (copy_from_user(kbuf, buffer, left)) { + err = -EFAULT; + goto free; + } + kbuf[left] = 0; + } + + for (; left && vleft--; i++, first = 0) { + unsigned long val; + + if (write) { + bool neg; + + left -= proc_skip_spaces(&kbuf); + + err = proc_get_long(&kbuf, &left, &val, &neg, + proc_wspace_sep, + sizeof(proc_wspace_sep), NULL); + if (err) + break; + if (neg) + continue; + if ((min && val < *min) || (max && val > *max)) + continue; + *i = val; + } else { + val = convdiv * (*i) / convmul; + if (!first) { + err = proc_put_char(&buffer, &left, '\t'); + if (err) + break; + } + err = proc_put_long(&buffer, &left, val, false); + if (err) + break; + } + } + + if (!write && !first && left && !err) + err = proc_put_char(&buffer, &left, '\n'); + if (write && !err) + left -= proc_skip_spaces(&kbuf); +free: + if (write) { + free_page(page); + if (first) + return err ? : -EINVAL; + } + *lenp -= left; +out: + *ppos += *lenp; + return err; +} + +static int do_proc_doulongvec_minmax(struct ctl_table *table, int write, + void __user *buffer, + size_t *lenp, loff_t *ppos, + unsigned long convmul, + unsigned long convdiv) +{ + return __do_proc_doulongvec_minmax(table->data, table, write, + buffer, lenp, ppos, convmul, convdiv); +} + +/** + * proc_doulongvec_minmax - read a vector of long integers with min/max values + * @table: the sysctl table + * @write: %TRUE if this is a write to the sysctl file + * @buffer: the user buffer + * @lenp: the size of the user buffer + * @ppos: file position + * + * Reads/writes up to table->maxlen/sizeof(unsigned long) unsigned long + * values from/to the user buffer, treated as an ASCII string. + * + * This routine will ensure the values are within the range specified by + * table->extra1 (min) and table->extra2 (max). + * + * Returns 0 on success. + */ +int proc_doulongvec_minmax(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + return do_proc_doulongvec_minmax(table, write, buffer, lenp, ppos, 1l, 1l); +} + +/** + * proc_doulongvec_ms_jiffies_minmax - read a vector of millisecond values with min/max values + * @table: the sysctl table + * @write: %TRUE if this is a write to the sysctl file + * @buffer: the user buffer + * @lenp: the size of the user buffer + * @ppos: file position + * + * Reads/writes up to table->maxlen/sizeof(unsigned long) unsigned long + * values from/to the user buffer, treated as an ASCII string. The values + * are treated as milliseconds, and converted to jiffies when they are stored. + * + * This routine will ensure the values are within the range specified by + * table->extra1 (min) and table->extra2 (max). + * + * Returns 0 on success. + */ +int proc_doulongvec_ms_jiffies_minmax(struct ctl_table *table, int write, + void __user *buffer, + size_t *lenp, loff_t *ppos) +{ + return do_proc_doulongvec_minmax(table, write, buffer, + lenp, ppos, HZ, 1000l); +} + + +static int do_proc_dointvec_jiffies_conv(bool *negp, unsigned long *lvalp, + int *valp, + int write, void *data) +{ + if (write) { + if (*lvalp > LONG_MAX / HZ) + return 1; + *valp = *negp ? -(*lvalp*HZ) : (*lvalp*HZ); + } else { + int val = *valp; + unsigned long lval; + if (val < 0) { + *negp = true; + lval = (unsigned long)-val; + } else { + *negp = false; + lval = (unsigned long)val; + } + *lvalp = lval / HZ; + } + return 0; +} + +static int do_proc_dointvec_userhz_jiffies_conv(bool *negp, unsigned long *lvalp, + int *valp, + int write, void *data) +{ + if (write) { + if (USER_HZ < HZ && *lvalp > (LONG_MAX / HZ) * USER_HZ) + return 1; + *valp = clock_t_to_jiffies(*negp ? -*lvalp : *lvalp); + } else { + int val = *valp; + unsigned long lval; + if (val < 0) { + *negp = true; + lval = (unsigned long)-val; + } else { + *negp = false; + lval = (unsigned long)val; + } + *lvalp = jiffies_to_clock_t(lval); + } + return 0; +} + +static int do_proc_dointvec_ms_jiffies_conv(bool *negp, unsigned long *lvalp, + int *valp, + int write, void *data) +{ + if (write) { + unsigned long jif = msecs_to_jiffies(*negp ? -*lvalp : *lvalp); + + if (jif > INT_MAX) + return 1; + *valp = (int)jif; + } else { + int val = *valp; + unsigned long lval; + if (val < 0) { + *negp = true; + lval = (unsigned long)-val; + } else { + *negp = false; + lval = (unsigned long)val; + } + *lvalp = jiffies_to_msecs(lval); + } + return 0; +} + +/** + * proc_dointvec_jiffies - read a vector of integers as seconds + * @table: the sysctl table + * @write: %TRUE if this is a write to the sysctl file + * @buffer: the user buffer + * @lenp: the size of the user buffer + * @ppos: file position + * + * Reads/writes up to table->maxlen/sizeof(unsigned int) integer + * values from/to the user buffer, treated as an ASCII string. + * The values read are assumed to be in seconds, and are converted into + * jiffies. + * + * Returns 0 on success. + */ +int proc_dointvec_jiffies(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + return do_proc_dointvec(table,write,buffer,lenp,ppos, + do_proc_dointvec_jiffies_conv,NULL); +} + +/** + * proc_dointvec_userhz_jiffies - read a vector of integers as 1/USER_HZ seconds + * @table: the sysctl table + * @write: %TRUE if this is a write to the sysctl file + * @buffer: the user buffer + * @lenp: the size of the user buffer + * @ppos: pointer to the file position + * + * Reads/writes up to table->maxlen/sizeof(unsigned int) integer + * values from/to the user buffer, treated as an ASCII string. + * The values read are assumed to be in 1/USER_HZ seconds, and + * are converted into jiffies. + * + * Returns 0 on success. + */ +int proc_dointvec_userhz_jiffies(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + return do_proc_dointvec(table,write,buffer,lenp,ppos, + do_proc_dointvec_userhz_jiffies_conv,NULL); +} + +/** + * proc_dointvec_ms_jiffies - read a vector of integers as 1 milliseconds + * @table: the sysctl table + * @write: %TRUE if this is a write to the sysctl file + * @buffer: the user buffer + * @lenp: the size of the user buffer + * @ppos: file position + * @ppos: the current position in the file + * + * Reads/writes up to table->maxlen/sizeof(unsigned int) integer + * values from/to the user buffer, treated as an ASCII string. + * The values read are assumed to be in 1/1000 seconds, and + * are converted into jiffies. + * + * Returns 0 on success. + */ +int proc_dointvec_ms_jiffies(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + return do_proc_dointvec(table, write, buffer, lenp, ppos, + do_proc_dointvec_ms_jiffies_conv, NULL); +} + +static int proc_do_cad_pid(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + struct pid *new_pid; + pid_t tmp; + int r; + + tmp = pid_vnr(cad_pid); + + r = __do_proc_dointvec(&tmp, table, write, buffer, + lenp, ppos, NULL, NULL); + if (r || !write) + return r; + + new_pid = find_get_pid(tmp); + if (!new_pid) + return -ESRCH; + + put_pid(xchg(&cad_pid, new_pid)); + return 0; +} + +/** + * proc_do_large_bitmap - read/write from/to a large bitmap + * @table: the sysctl table + * @write: %TRUE if this is a write to the sysctl file + * @buffer: the user buffer + * @lenp: the size of the user buffer + * @ppos: file position + * + * The bitmap is stored at table->data and the bitmap length (in bits) + * in table->maxlen. + * + * We use a range comma separated format (e.g. 1,3-4,10-10) so that + * large bitmaps may be represented in a compact manner. Writing into + * the file will clear the bitmap then update it with the given input. + * + * Returns 0 on success. + */ +int proc_do_large_bitmap(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + int err = 0; + bool first = 1; + size_t left = *lenp; + unsigned long bitmap_len = table->maxlen; + unsigned long *bitmap = *(unsigned long **) table->data; + unsigned long *tmp_bitmap = NULL; + char tr_a[] = { '-', ',', '\n' }, tr_b[] = { ',', '\n', 0 }, c; + + if (!bitmap || !bitmap_len || !left || (*ppos && !write)) { + *lenp = 0; + return 0; + } + + if (write) { + unsigned long page = 0; + char *kbuf; + + if (left > PAGE_SIZE - 1) + left = PAGE_SIZE - 1; + + page = __get_free_page(GFP_TEMPORARY); + kbuf = (char *) page; + if (!kbuf) + return -ENOMEM; + if (copy_from_user(kbuf, buffer, left)) { + free_page(page); + return -EFAULT; + } + kbuf[left] = 0; + + tmp_bitmap = kzalloc(BITS_TO_LONGS(bitmap_len) * sizeof(unsigned long), + GFP_KERNEL); + if (!tmp_bitmap) { + free_page(page); + return -ENOMEM; + } + proc_skip_char(&kbuf, &left, '\n'); + while (!err && left) { + unsigned long val_a, val_b; + bool neg; + + err = proc_get_long(&kbuf, &left, &val_a, &neg, tr_a, + sizeof(tr_a), &c); + if (err) + break; + if (val_a >= bitmap_len || neg) { + err = -EINVAL; + break; + } + + val_b = val_a; + if (left) { + kbuf++; + left--; + } + + if (c == '-') { + err = proc_get_long(&kbuf, &left, &val_b, + &neg, tr_b, sizeof(tr_b), + &c); + if (err) + break; + if (val_b >= bitmap_len || neg || + val_a > val_b) { + err = -EINVAL; + break; + } + if (left) { + kbuf++; + left--; + } + } + + bitmap_set(tmp_bitmap, val_a, val_b - val_a + 1); + first = 0; + proc_skip_char(&kbuf, &left, '\n'); + } + free_page(page); + } else { + unsigned long bit_a, bit_b = 0; + + while (left) { + bit_a = find_next_bit(bitmap, bitmap_len, bit_b); + if (bit_a >= bitmap_len) + break; + bit_b = find_next_zero_bit(bitmap, bitmap_len, + bit_a + 1) - 1; + + if (!first) { + err = proc_put_char(&buffer, &left, ','); + if (err) + break; + } + err = proc_put_long(&buffer, &left, bit_a, false); + if (err) + break; + if (bit_a != bit_b) { + err = proc_put_char(&buffer, &left, '-'); + if (err) + break; + err = proc_put_long(&buffer, &left, bit_b, false); + if (err) + break; + } + + first = 0; bit_b++; + } + if (!err) + err = proc_put_char(&buffer, &left, '\n'); + } + + if (!err) { + if (write) { + if (*ppos) + bitmap_or(bitmap, bitmap, tmp_bitmap, bitmap_len); + else + bitmap_copy(bitmap, tmp_bitmap, bitmap_len); + } + kfree(tmp_bitmap); + *lenp -= left; + *ppos += *lenp; + return 0; + } else { + kfree(tmp_bitmap); + return err; + } +} + +#else /* CONFIG_PROC_SYSCTL */ + +int proc_dostring(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + return -ENOSYS; +} + +int proc_dointvec(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + return -ENOSYS; +} + +int proc_dointvec_minmax(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + return -ENOSYS; +} + +int proc_dointvec_jiffies(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + return -ENOSYS; +} + +int proc_dointvec_userhz_jiffies(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + return -ENOSYS; +} + +int proc_dointvec_ms_jiffies(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + return -ENOSYS; +} + +int proc_doulongvec_minmax(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + return -ENOSYS; +} + +int proc_doulongvec_ms_jiffies_minmax(struct ctl_table *table, int write, + void __user *buffer, + size_t *lenp, loff_t *ppos) +{ + return -ENOSYS; +} + + +#endif /* CONFIG_PROC_SYSCTL */ + +/* + * No sense putting this after each symbol definition, twice, + * exception granted :-) + */ +EXPORT_SYMBOL(proc_dointvec); +EXPORT_SYMBOL(proc_dointvec_jiffies); +EXPORT_SYMBOL(proc_dointvec_minmax); +EXPORT_SYMBOL(proc_dointvec_userhz_jiffies); +EXPORT_SYMBOL(proc_dointvec_ms_jiffies); +EXPORT_SYMBOL(proc_dostring); +EXPORT_SYMBOL(proc_doulongvec_minmax); +EXPORT_SYMBOL(proc_doulongvec_ms_jiffies_minmax); diff --git a/kernel/kernel/sysctl_binary.c b/kernel/kernel/sysctl_binary.c new file mode 100644 index 000000000..7e7746a42 --- /dev/null +++ b/kernel/kernel/sysctl_binary.c @@ -0,0 +1,1494 @@ +#include +#include +#include "../fs/xfs/xfs_sysctl.h" +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#ifdef CONFIG_SYSCTL_SYSCALL + +struct bin_table; +typedef ssize_t bin_convert_t(struct file *file, + void __user *oldval, size_t oldlen, void __user *newval, size_t newlen); + +static bin_convert_t bin_dir; +static bin_convert_t bin_string; +static bin_convert_t bin_intvec; +static bin_convert_t bin_ulongvec; +static bin_convert_t bin_uuid; +static bin_convert_t bin_dn_node_address; + +#define CTL_DIR bin_dir +#define CTL_STR bin_string +#define CTL_INT bin_intvec +#define CTL_ULONG bin_ulongvec +#define CTL_UUID bin_uuid +#define CTL_DNADR bin_dn_node_address + +#define BUFSZ 256 + +struct bin_table { + bin_convert_t *convert; + int ctl_name; + const char *procname; + const struct bin_table *child; +}; + +static const struct bin_table bin_random_table[] = { + { CTL_INT, RANDOM_POOLSIZE, "poolsize" }, + { CTL_INT, RANDOM_ENTROPY_COUNT, "entropy_avail" }, + { CTL_INT, RANDOM_READ_THRESH, "read_wakeup_threshold" }, + { CTL_INT, RANDOM_WRITE_THRESH, "write_wakeup_threshold" }, + { CTL_UUID, RANDOM_BOOT_ID, "boot_id" }, + { CTL_UUID, RANDOM_UUID, "uuid" }, + {} +}; + +static const struct bin_table bin_pty_table[] = { + { CTL_INT, PTY_MAX, "max" }, + { CTL_INT, PTY_NR, "nr" }, + {} +}; + +static const struct bin_table bin_kern_table[] = { + { CTL_STR, KERN_OSTYPE, "ostype" }, + { CTL_STR, KERN_OSRELEASE, "osrelease" }, + /* KERN_OSREV not used */ + { CTL_STR, KERN_VERSION, "version" }, + /* KERN_SECUREMASK not used */ + /* KERN_PROF not used */ + { CTL_STR, KERN_NODENAME, "hostname" }, + { CTL_STR, KERN_DOMAINNAME, "domainname" }, + + { CTL_INT, KERN_PANIC, "panic" }, + { CTL_INT, KERN_REALROOTDEV, "real-root-dev" }, + + { CTL_STR, KERN_SPARC_REBOOT, "reboot-cmd" }, + { CTL_INT, KERN_CTLALTDEL, "ctrl-alt-del" }, + { CTL_INT, KERN_PRINTK, "printk" }, + + /* KERN_NAMETRANS not used */ + /* KERN_PPC_HTABRECLAIM not used */ + /* KERN_PPC_ZEROPAGED not used */ + { CTL_INT, KERN_PPC_POWERSAVE_NAP, "powersave-nap" }, + + { CTL_STR, KERN_MODPROBE, "modprobe" }, + { CTL_INT, KERN_SG_BIG_BUFF, "sg-big-buff" }, + { CTL_INT, KERN_ACCT, "acct" }, + /* KERN_PPC_L2CR "l2cr" no longer used */ + + /* KERN_RTSIGNR not used */ + /* KERN_RTSIGMAX not used */ + + { CTL_ULONG, KERN_SHMMAX, "shmmax" }, + { CTL_INT, KERN_MSGMAX, "msgmax" }, + { CTL_INT, KERN_MSGMNB, "msgmnb" }, + /* KERN_MSGPOOL not used*/ + { CTL_INT, KERN_SYSRQ, "sysrq" }, + { CTL_INT, KERN_MAX_THREADS, "threads-max" }, + { CTL_DIR, KERN_RANDOM, "random", bin_random_table }, + { CTL_ULONG, KERN_SHMALL, "shmall" }, + { CTL_INT, KERN_MSGMNI, "msgmni" }, + { CTL_INT, KERN_SEM, "sem" }, + { CTL_INT, KERN_SPARC_STOP_A, "stop-a" }, + { CTL_INT, KERN_SHMMNI, "shmmni" }, + + { CTL_INT, KERN_OVERFLOWUID, "overflowuid" }, + { CTL_INT, KERN_OVERFLOWGID, "overflowgid" }, + + { CTL_STR, KERN_HOTPLUG, "hotplug", }, + { CTL_INT, KERN_IEEE_EMULATION_WARNINGS, "ieee_emulation_warnings" }, + + { CTL_INT, KERN_S390_USER_DEBUG_LOGGING, "userprocess_debug" }, + { CTL_INT, KERN_CORE_USES_PID, "core_uses_pid" }, + /* KERN_TAINTED "tainted" no longer used */ + { CTL_INT, KERN_CADPID, "cad_pid" }, + { CTL_INT, KERN_PIDMAX, "pid_max" }, + { CTL_STR, KERN_CORE_PATTERN, "core_pattern" }, + { CTL_INT, KERN_PANIC_ON_OOPS, "panic_on_oops" }, + { CTL_INT, KERN_HPPA_PWRSW, "soft-power" }, + { CTL_INT, KERN_HPPA_UNALIGNED, "unaligned-trap" }, + + { CTL_INT, KERN_PRINTK_RATELIMIT, "printk_ratelimit" }, + { CTL_INT, KERN_PRINTK_RATELIMIT_BURST, "printk_ratelimit_burst" }, + + { CTL_DIR, KERN_PTY, "pty", bin_pty_table }, + { CTL_INT, KERN_NGROUPS_MAX, "ngroups_max" }, + { CTL_INT, KERN_SPARC_SCONS_PWROFF, "scons-poweroff" }, + /* KERN_HZ_TIMER "hz_timer" no longer used */ + { CTL_INT, KERN_UNKNOWN_NMI_PANIC, "unknown_nmi_panic" }, + { CTL_INT, KERN_BOOTLOADER_TYPE, "bootloader_type" }, + { CTL_INT, KERN_RANDOMIZE, "randomize_va_space" }, + + { CTL_INT, KERN_SPIN_RETRY, "spin_retry" }, + /* KERN_ACPI_VIDEO_FLAGS "acpi_video_flags" no longer used */ + { CTL_INT, KERN_IA64_UNALIGNED, "ignore-unaligned-usertrap" }, + { CTL_INT, KERN_COMPAT_LOG, "compat-log" }, + { CTL_INT, KERN_MAX_LOCK_DEPTH, "max_lock_depth" }, + { CTL_INT, KERN_PANIC_ON_NMI, "panic_on_unrecovered_nmi" }, + { CTL_INT, KERN_PANIC_ON_WARN, "panic_on_warn" }, + {} +}; + +static const struct bin_table bin_vm_table[] = { + { CTL_INT, VM_OVERCOMMIT_MEMORY, "overcommit_memory" }, + { CTL_INT, VM_PAGE_CLUSTER, "page-cluster" }, + { CTL_INT, VM_DIRTY_BACKGROUND, "dirty_background_ratio" }, + { CTL_INT, VM_DIRTY_RATIO, "dirty_ratio" }, + /* VM_DIRTY_WB_CS "dirty_writeback_centisecs" no longer used */ + /* VM_DIRTY_EXPIRE_CS "dirty_expire_centisecs" no longer used */ + /* VM_NR_PDFLUSH_THREADS "nr_pdflush_threads" no longer used */ + { CTL_INT, VM_OVERCOMMIT_RATIO, "overcommit_ratio" }, + /* VM_PAGEBUF unused */ + /* VM_HUGETLB_PAGES "nr_hugepages" no longer used */ + { CTL_INT, VM_SWAPPINESS, "swappiness" }, + { CTL_INT, VM_LOWMEM_RESERVE_RATIO, "lowmem_reserve_ratio" }, + { CTL_INT, VM_MIN_FREE_KBYTES, "min_free_kbytes" }, + { CTL_INT, VM_MAX_MAP_COUNT, "max_map_count" }, + { CTL_INT, VM_LAPTOP_MODE, "laptop_mode" }, + { CTL_INT, VM_BLOCK_DUMP, "block_dump" }, + { CTL_INT, VM_HUGETLB_GROUP, "hugetlb_shm_group" }, + { CTL_INT, VM_VFS_CACHE_PRESSURE, "vfs_cache_pressure" }, + { CTL_INT, VM_LEGACY_VA_LAYOUT, "legacy_va_layout" }, + /* VM_SWAP_TOKEN_TIMEOUT unused */ + { CTL_INT, VM_DROP_PAGECACHE, "drop_caches" }, + { CTL_INT, VM_PERCPU_PAGELIST_FRACTION, "percpu_pagelist_fraction" }, + { CTL_INT, VM_ZONE_RECLAIM_MODE, "zone_reclaim_mode" }, + { CTL_INT, VM_MIN_UNMAPPED, "min_unmapped_ratio" }, + { CTL_INT, VM_PANIC_ON_OOM, "panic_on_oom" }, + { CTL_INT, VM_VDSO_ENABLED, "vdso_enabled" }, + { CTL_INT, VM_MIN_SLAB, "min_slab_ratio" }, + + {} +}; + +static const struct bin_table bin_net_core_table[] = { + { CTL_INT, NET_CORE_WMEM_MAX, "wmem_max" }, + { CTL_INT, NET_CORE_RMEM_MAX, "rmem_max" }, + { CTL_INT, NET_CORE_WMEM_DEFAULT, "wmem_default" }, + { CTL_INT, NET_CORE_RMEM_DEFAULT, "rmem_default" }, + /* NET_CORE_DESTROY_DELAY unused */ + { CTL_INT, NET_CORE_MAX_BACKLOG, "netdev_max_backlog" }, + /* NET_CORE_FASTROUTE unused */ + { CTL_INT, NET_CORE_MSG_COST, "message_cost" }, + { CTL_INT, NET_CORE_MSG_BURST, "message_burst" }, + { CTL_INT, NET_CORE_OPTMEM_MAX, "optmem_max" }, + /* NET_CORE_HOT_LIST_LENGTH unused */ + /* NET_CORE_DIVERT_VERSION unused */ + /* NET_CORE_NO_CONG_THRESH unused */ + /* NET_CORE_NO_CONG unused */ + /* NET_CORE_LO_CONG unused */ + /* NET_CORE_MOD_CONG unused */ + { CTL_INT, NET_CORE_DEV_WEIGHT, "dev_weight" }, + { CTL_INT, NET_CORE_SOMAXCONN, "somaxconn" }, + { CTL_INT, NET_CORE_BUDGET, "netdev_budget" }, + { CTL_INT, NET_CORE_AEVENT_ETIME, "xfrm_aevent_etime" }, + { CTL_INT, NET_CORE_AEVENT_RSEQTH, "xfrm_aevent_rseqth" }, + { CTL_INT, NET_CORE_WARNINGS, "warnings" }, + {}, +}; + +static const struct bin_table bin_net_unix_table[] = { + /* NET_UNIX_DESTROY_DELAY unused */ + /* NET_UNIX_DELETE_DELAY unused */ + { CTL_INT, NET_UNIX_MAX_DGRAM_QLEN, "max_dgram_qlen" }, + {} +}; + +static const struct bin_table bin_net_ipv4_route_table[] = { + { CTL_INT, NET_IPV4_ROUTE_FLUSH, "flush" }, + /* NET_IPV4_ROUTE_MIN_DELAY "min_delay" no longer used */ + /* NET_IPV4_ROUTE_MAX_DELAY "max_delay" no longer used */ + { CTL_INT, NET_IPV4_ROUTE_GC_THRESH, "gc_thresh" }, + { CTL_INT, NET_IPV4_ROUTE_MAX_SIZE, "max_size" }, + { CTL_INT, NET_IPV4_ROUTE_GC_MIN_INTERVAL, "gc_min_interval" }, + { CTL_INT, NET_IPV4_ROUTE_GC_MIN_INTERVAL_MS, "gc_min_interval_ms" }, + { CTL_INT, NET_IPV4_ROUTE_GC_TIMEOUT, "gc_timeout" }, + /* NET_IPV4_ROUTE_GC_INTERVAL "gc_interval" no longer used */ + { CTL_INT, NET_IPV4_ROUTE_REDIRECT_LOAD, "redirect_load" }, + { CTL_INT, NET_IPV4_ROUTE_REDIRECT_NUMBER, "redirect_number" }, + { CTL_INT, NET_IPV4_ROUTE_REDIRECT_SILENCE, "redirect_silence" }, + { CTL_INT, NET_IPV4_ROUTE_ERROR_COST, "error_cost" }, + { CTL_INT, NET_IPV4_ROUTE_ERROR_BURST, "error_burst" }, + { CTL_INT, NET_IPV4_ROUTE_GC_ELASTICITY, "gc_elasticity" }, + { CTL_INT, NET_IPV4_ROUTE_MTU_EXPIRES, "mtu_expires" }, + { CTL_INT, NET_IPV4_ROUTE_MIN_PMTU, "min_pmtu" }, + { CTL_INT, NET_IPV4_ROUTE_MIN_ADVMSS, "min_adv_mss" }, + {} +}; + +static const struct bin_table bin_net_ipv4_conf_vars_table[] = { + { CTL_INT, NET_IPV4_CONF_FORWARDING, "forwarding" }, + { CTL_INT, NET_IPV4_CONF_MC_FORWARDING, "mc_forwarding" }, + + { CTL_INT, NET_IPV4_CONF_ACCEPT_REDIRECTS, "accept_redirects" }, + { CTL_INT, NET_IPV4_CONF_SECURE_REDIRECTS, "secure_redirects" }, + { CTL_INT, NET_IPV4_CONF_SEND_REDIRECTS, "send_redirects" }, + { CTL_INT, NET_IPV4_CONF_SHARED_MEDIA, "shared_media" }, + { CTL_INT, NET_IPV4_CONF_RP_FILTER, "rp_filter" }, + { CTL_INT, NET_IPV4_CONF_ACCEPT_SOURCE_ROUTE, "accept_source_route" }, + { CTL_INT, NET_IPV4_CONF_PROXY_ARP, "proxy_arp" }, + { CTL_INT, NET_IPV4_CONF_MEDIUM_ID, "medium_id" }, + { CTL_INT, NET_IPV4_CONF_BOOTP_RELAY, "bootp_relay" }, + { CTL_INT, NET_IPV4_CONF_LOG_MARTIANS, "log_martians" }, + { CTL_INT, NET_IPV4_CONF_TAG, "tag" }, + { CTL_INT, NET_IPV4_CONF_ARPFILTER, "arp_filter" }, + { CTL_INT, NET_IPV4_CONF_ARP_ANNOUNCE, "arp_announce" }, + { CTL_INT, NET_IPV4_CONF_ARP_IGNORE, "arp_ignore" }, + { CTL_INT, NET_IPV4_CONF_ARP_ACCEPT, "arp_accept" }, + { CTL_INT, NET_IPV4_CONF_ARP_NOTIFY, "arp_notify" }, + + { CTL_INT, NET_IPV4_CONF_NOXFRM, "disable_xfrm" }, + { CTL_INT, NET_IPV4_CONF_NOPOLICY, "disable_policy" }, + { CTL_INT, NET_IPV4_CONF_FORCE_IGMP_VERSION, "force_igmp_version" }, + { CTL_INT, NET_IPV4_CONF_PROMOTE_SECONDARIES, "promote_secondaries" }, + {} +}; + +static const struct bin_table bin_net_ipv4_conf_table[] = { + { CTL_DIR, NET_PROTO_CONF_ALL, "all", bin_net_ipv4_conf_vars_table }, + { CTL_DIR, NET_PROTO_CONF_DEFAULT, "default", bin_net_ipv4_conf_vars_table }, + { CTL_DIR, 0, NULL, bin_net_ipv4_conf_vars_table }, + {} +}; + +static const struct bin_table bin_net_neigh_vars_table[] = { + { CTL_INT, NET_NEIGH_MCAST_SOLICIT, "mcast_solicit" }, + { CTL_INT, NET_NEIGH_UCAST_SOLICIT, "ucast_solicit" }, + { CTL_INT, NET_NEIGH_APP_SOLICIT, "app_solicit" }, + /* NET_NEIGH_RETRANS_TIME "retrans_time" no longer used */ + { CTL_INT, NET_NEIGH_REACHABLE_TIME, "base_reachable_time" }, + { CTL_INT, NET_NEIGH_DELAY_PROBE_TIME, "delay_first_probe_time" }, + { CTL_INT, NET_NEIGH_GC_STALE_TIME, "gc_stale_time" }, + { CTL_INT, NET_NEIGH_UNRES_QLEN, "unres_qlen" }, + { CTL_INT, NET_NEIGH_PROXY_QLEN, "proxy_qlen" }, + /* NET_NEIGH_ANYCAST_DELAY "anycast_delay" no longer used */ + /* NET_NEIGH_PROXY_DELAY "proxy_delay" no longer used */ + /* NET_NEIGH_LOCKTIME "locktime" no longer used */ + { CTL_INT, NET_NEIGH_GC_INTERVAL, "gc_interval" }, + { CTL_INT, NET_NEIGH_GC_THRESH1, "gc_thresh1" }, + { CTL_INT, NET_NEIGH_GC_THRESH2, "gc_thresh2" }, + { CTL_INT, NET_NEIGH_GC_THRESH3, "gc_thresh3" }, + { CTL_INT, NET_NEIGH_RETRANS_TIME_MS, "retrans_time_ms" }, + { CTL_INT, NET_NEIGH_REACHABLE_TIME_MS, "base_reachable_time_ms" }, + {} +}; + +static const struct bin_table bin_net_neigh_table[] = { + { CTL_DIR, NET_PROTO_CONF_DEFAULT, "default", bin_net_neigh_vars_table }, + { CTL_DIR, 0, NULL, bin_net_neigh_vars_table }, + {} +}; + +static const struct bin_table bin_net_ipv4_netfilter_table[] = { + { CTL_INT, NET_IPV4_NF_CONNTRACK_MAX, "ip_conntrack_max" }, + + /* NET_IPV4_NF_CONNTRACK_TCP_TIMEOUT_SYN_SENT "ip_conntrack_tcp_timeout_syn_sent" no longer used */ + /* NET_IPV4_NF_CONNTRACK_TCP_TIMEOUT_SYN_RECV "ip_conntrack_tcp_timeout_syn_recv" no longer used */ + /* NET_IPV4_NF_CONNTRACK_TCP_TIMEOUT_ESTABLISHED "ip_conntrack_tcp_timeout_established" no longer used */ + /* NET_IPV4_NF_CONNTRACK_TCP_TIMEOUT_FIN_WAIT "ip_conntrack_tcp_timeout_fin_wait" no longer used */ + /* NET_IPV4_NF_CONNTRACK_TCP_TIMEOUT_CLOSE_WAIT "ip_conntrack_tcp_timeout_close_wait" no longer used */ + /* NET_IPV4_NF_CONNTRACK_TCP_TIMEOUT_LAST_ACK "ip_conntrack_tcp_timeout_last_ack" no longer used */ + /* NET_IPV4_NF_CONNTRACK_TCP_TIMEOUT_TIME_WAIT "ip_conntrack_tcp_timeout_time_wait" no longer used */ + /* NET_IPV4_NF_CONNTRACK_TCP_TIMEOUT_CLOSE "ip_conntrack_tcp_timeout_close" no longer used */ + + /* NET_IPV4_NF_CONNTRACK_UDP_TIMEOUT "ip_conntrack_udp_timeout" no longer used */ + /* NET_IPV4_NF_CONNTRACK_UDP_TIMEOUT_STREAM "ip_conntrack_udp_timeout_stream" no longer used */ + /* NET_IPV4_NF_CONNTRACK_ICMP_TIMEOUT "ip_conntrack_icmp_timeout" no longer used */ + /* NET_IPV4_NF_CONNTRACK_GENERIC_TIMEOUT "ip_conntrack_generic_timeout" no longer used */ + + { CTL_INT, NET_IPV4_NF_CONNTRACK_BUCKETS, "ip_conntrack_buckets" }, + { CTL_INT, NET_IPV4_NF_CONNTRACK_LOG_INVALID, "ip_conntrack_log_invalid" }, + /* NET_IPV4_NF_CONNTRACK_TCP_TIMEOUT_MAX_RETRANS "ip_conntrack_tcp_timeout_max_retrans" no longer used */ + { CTL_INT, NET_IPV4_NF_CONNTRACK_TCP_LOOSE, "ip_conntrack_tcp_loose" }, + { CTL_INT, NET_IPV4_NF_CONNTRACK_TCP_BE_LIBERAL, "ip_conntrack_tcp_be_liberal" }, + { CTL_INT, NET_IPV4_NF_CONNTRACK_TCP_MAX_RETRANS, "ip_conntrack_tcp_max_retrans" }, + + /* NET_IPV4_NF_CONNTRACK_SCTP_TIMEOUT_CLOSED "ip_conntrack_sctp_timeout_closed" no longer used */ + /* NET_IPV4_NF_CONNTRACK_SCTP_TIMEOUT_COOKIE_WAIT "ip_conntrack_sctp_timeout_cookie_wait" no longer used */ + /* NET_IPV4_NF_CONNTRACK_SCTP_TIMEOUT_COOKIE_ECHOED "ip_conntrack_sctp_timeout_cookie_echoed" no longer used */ + /* NET_IPV4_NF_CONNTRACK_SCTP_TIMEOUT_ESTABLISHED "ip_conntrack_sctp_timeout_established" no longer used */ + /* NET_IPV4_NF_CONNTRACK_SCTP_TIMEOUT_SHUTDOWN_SENT "ip_conntrack_sctp_timeout_shutdown_sent" no longer used */ + /* NET_IPV4_NF_CONNTRACK_SCTP_TIMEOUT_SHUTDOWN_RECD "ip_conntrack_sctp_timeout_shutdown_recd" no longer used */ + /* NET_IPV4_NF_CONNTRACK_SCTP_TIMEOUT_SHUTDOWN_ACK_SENT "ip_conntrack_sctp_timeout_shutdown_ack_sent" no longer used */ + + { CTL_INT, NET_IPV4_NF_CONNTRACK_COUNT, "ip_conntrack_count" }, + { CTL_INT, NET_IPV4_NF_CONNTRACK_CHECKSUM, "ip_conntrack_checksum" }, + {} +}; + +static const struct bin_table bin_net_ipv4_table[] = { + {CTL_INT, NET_IPV4_FORWARD, "ip_forward" }, + + { CTL_DIR, NET_IPV4_CONF, "conf", bin_net_ipv4_conf_table }, + { CTL_DIR, NET_IPV4_NEIGH, "neigh", bin_net_neigh_table }, + { CTL_DIR, NET_IPV4_ROUTE, "route", bin_net_ipv4_route_table }, + /* NET_IPV4_FIB_HASH unused */ + { CTL_DIR, NET_IPV4_NETFILTER, "netfilter", bin_net_ipv4_netfilter_table }, + + { CTL_INT, NET_IPV4_TCP_TIMESTAMPS, "tcp_timestamps" }, + { CTL_INT, NET_IPV4_TCP_WINDOW_SCALING, "tcp_window_scaling" }, + { CTL_INT, NET_IPV4_TCP_SACK, "tcp_sack" }, + { CTL_INT, NET_IPV4_TCP_RETRANS_COLLAPSE, "tcp_retrans_collapse" }, + { CTL_INT, NET_IPV4_DEFAULT_TTL, "ip_default_ttl" }, + /* NET_IPV4_AUTOCONFIG unused */ + { CTL_INT, NET_IPV4_NO_PMTU_DISC, "ip_no_pmtu_disc" }, + { CTL_INT, NET_IPV4_NONLOCAL_BIND, "ip_nonlocal_bind" }, + { CTL_INT, NET_IPV4_TCP_SYN_RETRIES, "tcp_syn_retries" }, + { CTL_INT, NET_TCP_SYNACK_RETRIES, "tcp_synack_retries" }, + { CTL_INT, NET_TCP_MAX_ORPHANS, "tcp_max_orphans" }, + { CTL_INT, NET_TCP_MAX_TW_BUCKETS, "tcp_max_tw_buckets" }, + { CTL_INT, NET_IPV4_DYNADDR, "ip_dynaddr" }, + { CTL_INT, NET_IPV4_TCP_KEEPALIVE_TIME, "tcp_keepalive_time" }, + { CTL_INT, NET_IPV4_TCP_KEEPALIVE_PROBES, "tcp_keepalive_probes" }, + { CTL_INT, NET_IPV4_TCP_KEEPALIVE_INTVL, "tcp_keepalive_intvl" }, + { CTL_INT, NET_IPV4_TCP_RETRIES1, "tcp_retries1" }, + { CTL_INT, NET_IPV4_TCP_RETRIES2, "tcp_retries2" }, + { CTL_INT, NET_IPV4_TCP_FIN_TIMEOUT, "tcp_fin_timeout" }, + { CTL_INT, NET_TCP_SYNCOOKIES, "tcp_syncookies" }, + { CTL_INT, NET_TCP_TW_RECYCLE, "tcp_tw_recycle" }, + { CTL_INT, NET_TCP_ABORT_ON_OVERFLOW, "tcp_abort_on_overflow" }, + { CTL_INT, NET_TCP_STDURG, "tcp_stdurg" }, + { CTL_INT, NET_TCP_RFC1337, "tcp_rfc1337" }, + { CTL_INT, NET_TCP_MAX_SYN_BACKLOG, "tcp_max_syn_backlog" }, + { CTL_INT, NET_IPV4_LOCAL_PORT_RANGE, "ip_local_port_range" }, + { CTL_INT, NET_IPV4_IGMP_MAX_MEMBERSHIPS, "igmp_max_memberships" }, + { CTL_INT, NET_IPV4_IGMP_MAX_MSF, "igmp_max_msf" }, + { CTL_INT, NET_IPV4_INET_PEER_THRESHOLD, "inet_peer_threshold" }, + { CTL_INT, NET_IPV4_INET_PEER_MINTTL, "inet_peer_minttl" }, + { CTL_INT, NET_IPV4_INET_PEER_MAXTTL, "inet_peer_maxttl" }, + { CTL_INT, NET_IPV4_INET_PEER_GC_MINTIME, "inet_peer_gc_mintime" }, + { CTL_INT, NET_IPV4_INET_PEER_GC_MAXTIME, "inet_peer_gc_maxtime" }, + { CTL_INT, NET_TCP_ORPHAN_RETRIES, "tcp_orphan_retries" }, + { CTL_INT, NET_TCP_FACK, "tcp_fack" }, + { CTL_INT, NET_TCP_REORDERING, "tcp_reordering" }, + { CTL_INT, NET_TCP_ECN, "tcp_ecn" }, + { CTL_INT, NET_TCP_DSACK, "tcp_dsack" }, + { CTL_INT, NET_TCP_MEM, "tcp_mem" }, + { CTL_INT, NET_TCP_WMEM, "tcp_wmem" }, + { CTL_INT, NET_TCP_RMEM, "tcp_rmem" }, + { CTL_INT, NET_TCP_APP_WIN, "tcp_app_win" }, + { CTL_INT, NET_TCP_ADV_WIN_SCALE, "tcp_adv_win_scale" }, + { CTL_INT, NET_TCP_TW_REUSE, "tcp_tw_reuse" }, + { CTL_INT, NET_TCP_FRTO, "tcp_frto" }, + { CTL_INT, NET_TCP_FRTO_RESPONSE, "tcp_frto_response" }, + { CTL_INT, NET_TCP_LOW_LATENCY, "tcp_low_latency" }, + { CTL_INT, NET_TCP_NO_METRICS_SAVE, "tcp_no_metrics_save" }, + { CTL_INT, NET_TCP_MODERATE_RCVBUF, "tcp_moderate_rcvbuf" }, + { CTL_INT, NET_TCP_TSO_WIN_DIVISOR, "tcp_tso_win_divisor" }, + { CTL_STR, NET_TCP_CONG_CONTROL, "tcp_congestion_control" }, + { CTL_INT, NET_TCP_MTU_PROBING, "tcp_mtu_probing" }, + { CTL_INT, NET_TCP_BASE_MSS, "tcp_base_mss" }, + { CTL_INT, NET_IPV4_TCP_WORKAROUND_SIGNED_WINDOWS, "tcp_workaround_signed_windows" }, + { CTL_INT, NET_TCP_SLOW_START_AFTER_IDLE, "tcp_slow_start_after_idle" }, + { CTL_INT, NET_CIPSOV4_CACHE_ENABLE, "cipso_cache_enable" }, + { CTL_INT, NET_CIPSOV4_CACHE_BUCKET_SIZE, "cipso_cache_bucket_size" }, + { CTL_INT, NET_CIPSOV4_RBM_OPTFMT, "cipso_rbm_optfmt" }, + { CTL_INT, NET_CIPSOV4_RBM_STRICTVALID, "cipso_rbm_strictvalid" }, + /* NET_TCP_AVAIL_CONG_CONTROL "tcp_available_congestion_control" no longer used */ + { CTL_STR, NET_TCP_ALLOWED_CONG_CONTROL, "tcp_allowed_congestion_control" }, + { CTL_INT, NET_TCP_MAX_SSTHRESH, "tcp_max_ssthresh" }, + + { CTL_INT, NET_IPV4_ICMP_ECHO_IGNORE_ALL, "icmp_echo_ignore_all" }, + { CTL_INT, NET_IPV4_ICMP_ECHO_IGNORE_BROADCASTS, "icmp_echo_ignore_broadcasts" }, + { CTL_INT, NET_IPV4_ICMP_IGNORE_BOGUS_ERROR_RESPONSES, "icmp_ignore_bogus_error_responses" }, + { CTL_INT, NET_IPV4_ICMP_ERRORS_USE_INBOUND_IFADDR, "icmp_errors_use_inbound_ifaddr" }, + { CTL_INT, NET_IPV4_ICMP_RATELIMIT, "icmp_ratelimit" }, + { CTL_INT, NET_IPV4_ICMP_RATEMASK, "icmp_ratemask" }, + + { CTL_INT, NET_IPV4_IPFRAG_HIGH_THRESH, "ipfrag_high_thresh" }, + { CTL_INT, NET_IPV4_IPFRAG_LOW_THRESH, "ipfrag_low_thresh" }, + { CTL_INT, NET_IPV4_IPFRAG_TIME, "ipfrag_time" }, + + { CTL_INT, NET_IPV4_IPFRAG_SECRET_INTERVAL, "ipfrag_secret_interval" }, + /* NET_IPV4_IPFRAG_MAX_DIST "ipfrag_max_dist" no longer used */ + + { CTL_INT, 2088 /* NET_IPQ_QMAX */, "ip_queue_maxlen" }, + + /* NET_TCP_DEFAULT_WIN_SCALE unused */ + /* NET_TCP_BIC_BETA unused */ + /* NET_IPV4_TCP_MAX_KA_PROBES unused */ + /* NET_IPV4_IP_MASQ_DEBUG unused */ + /* NET_TCP_SYN_TAILDROP unused */ + /* NET_IPV4_ICMP_SOURCEQUENCH_RATE unused */ + /* NET_IPV4_ICMP_DESTUNREACH_RATE unused */ + /* NET_IPV4_ICMP_TIMEEXCEED_RATE unused */ + /* NET_IPV4_ICMP_PARAMPROB_RATE unused */ + /* NET_IPV4_ICMP_ECHOREPLY_RATE unused */ + /* NET_IPV4_ALWAYS_DEFRAG unused */ + {} +}; + +static const struct bin_table bin_net_ipx_table[] = { + { CTL_INT, NET_IPX_PPROP_BROADCASTING, "ipx_pprop_broadcasting" }, + /* NET_IPX_FORWARDING unused */ + {} +}; + +static const struct bin_table bin_net_atalk_table[] = { + { CTL_INT, NET_ATALK_AARP_EXPIRY_TIME, "aarp-expiry-time" }, + { CTL_INT, NET_ATALK_AARP_TICK_TIME, "aarp-tick-time" }, + { CTL_INT, NET_ATALK_AARP_RETRANSMIT_LIMIT, "aarp-retransmit-limit" }, + { CTL_INT, NET_ATALK_AARP_RESOLVE_TIME, "aarp-resolve-time" }, + {}, +}; + +static const struct bin_table bin_net_netrom_table[] = { + { CTL_INT, NET_NETROM_DEFAULT_PATH_QUALITY, "default_path_quality" }, + { CTL_INT, NET_NETROM_OBSOLESCENCE_COUNT_INITIALISER, "obsolescence_count_initialiser" }, + { CTL_INT, NET_NETROM_NETWORK_TTL_INITIALISER, "network_ttl_initialiser" }, + { CTL_INT, NET_NETROM_TRANSPORT_TIMEOUT, "transport_timeout" }, + { CTL_INT, NET_NETROM_TRANSPORT_MAXIMUM_TRIES, "transport_maximum_tries" }, + { CTL_INT, NET_NETROM_TRANSPORT_ACKNOWLEDGE_DELAY, "transport_acknowledge_delay" }, + { CTL_INT, NET_NETROM_TRANSPORT_BUSY_DELAY, "transport_busy_delay" }, + { CTL_INT, NET_NETROM_TRANSPORT_REQUESTED_WINDOW_SIZE, "transport_requested_window_size" }, + { CTL_INT, NET_NETROM_TRANSPORT_NO_ACTIVITY_TIMEOUT, "transport_no_activity_timeout" }, + { CTL_INT, NET_NETROM_ROUTING_CONTROL, "routing_control" }, + { CTL_INT, NET_NETROM_LINK_FAILS_COUNT, "link_fails_count" }, + { CTL_INT, NET_NETROM_RESET, "reset" }, + {} +}; + +static const struct bin_table bin_net_ax25_param_table[] = { + { CTL_INT, NET_AX25_IP_DEFAULT_MODE, "ip_default_mode" }, + { CTL_INT, NET_AX25_DEFAULT_MODE, "ax25_default_mode" }, + { CTL_INT, NET_AX25_BACKOFF_TYPE, "backoff_type" }, + { CTL_INT, NET_AX25_CONNECT_MODE, "connect_mode" }, + { CTL_INT, NET_AX25_STANDARD_WINDOW, "standard_window_size" }, + { CTL_INT, NET_AX25_EXTENDED_WINDOW, "extended_window_size" }, + { CTL_INT, NET_AX25_T1_TIMEOUT, "t1_timeout" }, + { CTL_INT, NET_AX25_T2_TIMEOUT, "t2_timeout" }, + { CTL_INT, NET_AX25_T3_TIMEOUT, "t3_timeout" }, + { CTL_INT, NET_AX25_IDLE_TIMEOUT, "idle_timeout" }, + { CTL_INT, NET_AX25_N2, "maximum_retry_count" }, + { CTL_INT, NET_AX25_PACLEN, "maximum_packet_length" }, + { CTL_INT, NET_AX25_PROTOCOL, "protocol" }, + { CTL_INT, NET_AX25_DAMA_SLAVE_TIMEOUT, "dama_slave_timeout" }, + {} +}; + +static const struct bin_table bin_net_ax25_table[] = { + { CTL_DIR, 0, NULL, bin_net_ax25_param_table }, + {} +}; + +static const struct bin_table bin_net_rose_table[] = { + { CTL_INT, NET_ROSE_RESTART_REQUEST_TIMEOUT, "restart_request_timeout" }, + { CTL_INT, NET_ROSE_CALL_REQUEST_TIMEOUT, "call_request_timeout" }, + { CTL_INT, NET_ROSE_RESET_REQUEST_TIMEOUT, "reset_request_timeout" }, + { CTL_INT, NET_ROSE_CLEAR_REQUEST_TIMEOUT, "clear_request_timeout" }, + { CTL_INT, NET_ROSE_ACK_HOLD_BACK_TIMEOUT, "acknowledge_hold_back_timeout" }, + { CTL_INT, NET_ROSE_ROUTING_CONTROL, "routing_control" }, + { CTL_INT, NET_ROSE_LINK_FAIL_TIMEOUT, "link_fail_timeout" }, + { CTL_INT, NET_ROSE_MAX_VCS, "maximum_virtual_circuits" }, + { CTL_INT, NET_ROSE_WINDOW_SIZE, "window_size" }, + { CTL_INT, NET_ROSE_NO_ACTIVITY_TIMEOUT, "no_activity_timeout" }, + {} +}; + +static const struct bin_table bin_net_ipv6_conf_var_table[] = { + { CTL_INT, NET_IPV6_FORWARDING, "forwarding" }, + { CTL_INT, NET_IPV6_HOP_LIMIT, "hop_limit" }, + { CTL_INT, NET_IPV6_MTU, "mtu" }, + { CTL_INT, NET_IPV6_ACCEPT_RA, "accept_ra" }, + { CTL_INT, NET_IPV6_ACCEPT_REDIRECTS, "accept_redirects" }, + { CTL_INT, NET_IPV6_AUTOCONF, "autoconf" }, + { CTL_INT, NET_IPV6_DAD_TRANSMITS, "dad_transmits" }, + { CTL_INT, NET_IPV6_RTR_SOLICITS, "router_solicitations" }, + { CTL_INT, NET_IPV6_RTR_SOLICIT_INTERVAL, "router_solicitation_interval" }, + { CTL_INT, NET_IPV6_RTR_SOLICIT_DELAY, "router_solicitation_delay" }, + { CTL_INT, NET_IPV6_USE_TEMPADDR, "use_tempaddr" }, + { CTL_INT, NET_IPV6_TEMP_VALID_LFT, "temp_valid_lft" }, + { CTL_INT, NET_IPV6_TEMP_PREFERED_LFT, "temp_prefered_lft" }, + { CTL_INT, NET_IPV6_REGEN_MAX_RETRY, "regen_max_retry" }, + { CTL_INT, NET_IPV6_MAX_DESYNC_FACTOR, "max_desync_factor" }, + { CTL_INT, NET_IPV6_MAX_ADDRESSES, "max_addresses" }, + { CTL_INT, NET_IPV6_FORCE_MLD_VERSION, "force_mld_version" }, + { CTL_INT, NET_IPV6_ACCEPT_RA_DEFRTR, "accept_ra_defrtr" }, + { CTL_INT, NET_IPV6_ACCEPT_RA_PINFO, "accept_ra_pinfo" }, + { CTL_INT, NET_IPV6_ACCEPT_RA_RTR_PREF, "accept_ra_rtr_pref" }, + { CTL_INT, NET_IPV6_RTR_PROBE_INTERVAL, "router_probe_interval" }, + { CTL_INT, NET_IPV6_ACCEPT_RA_RT_INFO_MAX_PLEN, "accept_ra_rt_info_max_plen" }, + { CTL_INT, NET_IPV6_PROXY_NDP, "proxy_ndp" }, + { CTL_INT, NET_IPV6_ACCEPT_SOURCE_ROUTE, "accept_source_route" }, + { CTL_INT, NET_IPV6_ACCEPT_RA_FROM_LOCAL, "accept_ra_from_local" }, + {} +}; + +static const struct bin_table bin_net_ipv6_conf_table[] = { + { CTL_DIR, NET_PROTO_CONF_ALL, "all", bin_net_ipv6_conf_var_table }, + { CTL_DIR, NET_PROTO_CONF_DEFAULT, "default", bin_net_ipv6_conf_var_table }, + { CTL_DIR, 0, NULL, bin_net_ipv6_conf_var_table }, + {} +}; + +static const struct bin_table bin_net_ipv6_route_table[] = { + /* NET_IPV6_ROUTE_FLUSH "flush" no longer used */ + { CTL_INT, NET_IPV6_ROUTE_GC_THRESH, "gc_thresh" }, + { CTL_INT, NET_IPV6_ROUTE_MAX_SIZE, "max_size" }, + { CTL_INT, NET_IPV6_ROUTE_GC_MIN_INTERVAL, "gc_min_interval" }, + { CTL_INT, NET_IPV6_ROUTE_GC_TIMEOUT, "gc_timeout" }, + { CTL_INT, NET_IPV6_ROUTE_GC_INTERVAL, "gc_interval" }, + { CTL_INT, NET_IPV6_ROUTE_GC_ELASTICITY, "gc_elasticity" }, + { CTL_INT, NET_IPV6_ROUTE_MTU_EXPIRES, "mtu_expires" }, + { CTL_INT, NET_IPV6_ROUTE_MIN_ADVMSS, "min_adv_mss" }, + { CTL_INT, NET_IPV6_ROUTE_GC_MIN_INTERVAL_MS, "gc_min_interval_ms" }, + {} +}; + +static const struct bin_table bin_net_ipv6_icmp_table[] = { + { CTL_INT, NET_IPV6_ICMP_RATELIMIT, "ratelimit" }, + {} +}; + +static const struct bin_table bin_net_ipv6_table[] = { + { CTL_DIR, NET_IPV6_CONF, "conf", bin_net_ipv6_conf_table }, + { CTL_DIR, NET_IPV6_NEIGH, "neigh", bin_net_neigh_table }, + { CTL_DIR, NET_IPV6_ROUTE, "route", bin_net_ipv6_route_table }, + { CTL_DIR, NET_IPV6_ICMP, "icmp", bin_net_ipv6_icmp_table }, + { CTL_INT, NET_IPV6_BINDV6ONLY, "bindv6only" }, + { CTL_INT, NET_IPV6_IP6FRAG_HIGH_THRESH, "ip6frag_high_thresh" }, + { CTL_INT, NET_IPV6_IP6FRAG_LOW_THRESH, "ip6frag_low_thresh" }, + { CTL_INT, NET_IPV6_IP6FRAG_TIME, "ip6frag_time" }, + { CTL_INT, NET_IPV6_IP6FRAG_SECRET_INTERVAL, "ip6frag_secret_interval" }, + { CTL_INT, NET_IPV6_MLD_MAX_MSF, "mld_max_msf" }, + { CTL_INT, 2088 /* IPQ_QMAX */, "ip6_queue_maxlen" }, + {} +}; + +static const struct bin_table bin_net_x25_table[] = { + { CTL_INT, NET_X25_RESTART_REQUEST_TIMEOUT, "restart_request_timeout" }, + { CTL_INT, NET_X25_CALL_REQUEST_TIMEOUT, "call_request_timeout" }, + { CTL_INT, NET_X25_RESET_REQUEST_TIMEOUT, "reset_request_timeout" }, + { CTL_INT, NET_X25_CLEAR_REQUEST_TIMEOUT, "clear_request_timeout" }, + { CTL_INT, NET_X25_ACK_HOLD_BACK_TIMEOUT, "acknowledgement_hold_back_timeout" }, + { CTL_INT, NET_X25_FORWARD, "x25_forward" }, + {} +}; + +static const struct bin_table bin_net_tr_table[] = { + { CTL_INT, NET_TR_RIF_TIMEOUT, "rif_timeout" }, + {} +}; + + +static const struct bin_table bin_net_decnet_conf_vars[] = { + { CTL_INT, NET_DECNET_CONF_DEV_FORWARDING, "forwarding" }, + { CTL_INT, NET_DECNET_CONF_DEV_PRIORITY, "priority" }, + { CTL_INT, NET_DECNET_CONF_DEV_T2, "t2" }, + { CTL_INT, NET_DECNET_CONF_DEV_T3, "t3" }, + {} +}; + +static const struct bin_table bin_net_decnet_conf[] = { + { CTL_DIR, NET_DECNET_CONF_ETHER, "ethernet", bin_net_decnet_conf_vars }, + { CTL_DIR, NET_DECNET_CONF_GRE, "ipgre", bin_net_decnet_conf_vars }, + { CTL_DIR, NET_DECNET_CONF_X25, "x25", bin_net_decnet_conf_vars }, + { CTL_DIR, NET_DECNET_CONF_PPP, "ppp", bin_net_decnet_conf_vars }, + { CTL_DIR, NET_DECNET_CONF_DDCMP, "ddcmp", bin_net_decnet_conf_vars }, + { CTL_DIR, NET_DECNET_CONF_LOOPBACK, "loopback", bin_net_decnet_conf_vars }, + { CTL_DIR, 0, NULL, bin_net_decnet_conf_vars }, + {} +}; + +static const struct bin_table bin_net_decnet_table[] = { + { CTL_DIR, NET_DECNET_CONF, "conf", bin_net_decnet_conf }, + { CTL_DNADR, NET_DECNET_NODE_ADDRESS, "node_address" }, + { CTL_STR, NET_DECNET_NODE_NAME, "node_name" }, + { CTL_STR, NET_DECNET_DEFAULT_DEVICE, "default_device" }, + { CTL_INT, NET_DECNET_TIME_WAIT, "time_wait" }, + { CTL_INT, NET_DECNET_DN_COUNT, "dn_count" }, + { CTL_INT, NET_DECNET_DI_COUNT, "di_count" }, + { CTL_INT, NET_DECNET_DR_COUNT, "dr_count" }, + { CTL_INT, NET_DECNET_DST_GC_INTERVAL, "dst_gc_interval" }, + { CTL_INT, NET_DECNET_NO_FC_MAX_CWND, "no_fc_max_cwnd" }, + { CTL_INT, NET_DECNET_MEM, "decnet_mem" }, + { CTL_INT, NET_DECNET_RMEM, "decnet_rmem" }, + { CTL_INT, NET_DECNET_WMEM, "decnet_wmem" }, + { CTL_INT, NET_DECNET_DEBUG_LEVEL, "debug" }, + {} +}; + +static const struct bin_table bin_net_sctp_table[] = { + { CTL_INT, NET_SCTP_RTO_INITIAL, "rto_initial" }, + { CTL_INT, NET_SCTP_RTO_MIN, "rto_min" }, + { CTL_INT, NET_SCTP_RTO_MAX, "rto_max" }, + { CTL_INT, NET_SCTP_RTO_ALPHA, "rto_alpha_exp_divisor" }, + { CTL_INT, NET_SCTP_RTO_BETA, "rto_beta_exp_divisor" }, + { CTL_INT, NET_SCTP_VALID_COOKIE_LIFE, "valid_cookie_life" }, + { CTL_INT, NET_SCTP_ASSOCIATION_MAX_RETRANS, "association_max_retrans" }, + { CTL_INT, NET_SCTP_PATH_MAX_RETRANS, "path_max_retrans" }, + { CTL_INT, NET_SCTP_MAX_INIT_RETRANSMITS, "max_init_retransmits" }, + { CTL_INT, NET_SCTP_HB_INTERVAL, "hb_interval" }, + { CTL_INT, NET_SCTP_PRESERVE_ENABLE, "cookie_preserve_enable" }, + { CTL_INT, NET_SCTP_MAX_BURST, "max_burst" }, + { CTL_INT, NET_SCTP_ADDIP_ENABLE, "addip_enable" }, + { CTL_INT, NET_SCTP_PRSCTP_ENABLE, "prsctp_enable" }, + { CTL_INT, NET_SCTP_SNDBUF_POLICY, "sndbuf_policy" }, + { CTL_INT, NET_SCTP_SACK_TIMEOUT, "sack_timeout" }, + { CTL_INT, NET_SCTP_RCVBUF_POLICY, "rcvbuf_policy" }, + {} +}; + +static const struct bin_table bin_net_llc_llc2_timeout_table[] = { + { CTL_INT, NET_LLC2_ACK_TIMEOUT, "ack" }, + { CTL_INT, NET_LLC2_P_TIMEOUT, "p" }, + { CTL_INT, NET_LLC2_REJ_TIMEOUT, "rej" }, + { CTL_INT, NET_LLC2_BUSY_TIMEOUT, "busy" }, + {} +}; + +static const struct bin_table bin_net_llc_station_table[] = { + { CTL_INT, NET_LLC_STATION_ACK_TIMEOUT, "ack_timeout" }, + {} +}; + +static const struct bin_table bin_net_llc_llc2_table[] = { + { CTL_DIR, NET_LLC2, "timeout", bin_net_llc_llc2_timeout_table }, + {} +}; + +static const struct bin_table bin_net_llc_table[] = { + { CTL_DIR, NET_LLC2, "llc2", bin_net_llc_llc2_table }, + { CTL_DIR, NET_LLC_STATION, "station", bin_net_llc_station_table }, + {} +}; + +static const struct bin_table bin_net_netfilter_table[] = { + { CTL_INT, NET_NF_CONNTRACK_MAX, "nf_conntrack_max" }, + /* NET_NF_CONNTRACK_TCP_TIMEOUT_SYN_SENT "nf_conntrack_tcp_timeout_syn_sent" no longer used */ + /* NET_NF_CONNTRACK_TCP_TIMEOUT_SYN_RECV "nf_conntrack_tcp_timeout_syn_recv" no longer used */ + /* NET_NF_CONNTRACK_TCP_TIMEOUT_ESTABLISHED "nf_conntrack_tcp_timeout_established" no longer used */ + /* NET_NF_CONNTRACK_TCP_TIMEOUT_FIN_WAIT "nf_conntrack_tcp_timeout_fin_wait" no longer used */ + /* NET_NF_CONNTRACK_TCP_TIMEOUT_CLOSE_WAIT "nf_conntrack_tcp_timeout_close_wait" no longer used */ + /* NET_NF_CONNTRACK_TCP_TIMEOUT_LAST_ACK "nf_conntrack_tcp_timeout_last_ack" no longer used */ + /* NET_NF_CONNTRACK_TCP_TIMEOUT_TIME_WAIT "nf_conntrack_tcp_timeout_time_wait" no longer used */ + /* NET_NF_CONNTRACK_TCP_TIMEOUT_CLOSE "nf_conntrack_tcp_timeout_close" no longer used */ + /* NET_NF_CONNTRACK_UDP_TIMEOUT "nf_conntrack_udp_timeout" no longer used */ + /* NET_NF_CONNTRACK_UDP_TIMEOUT_STREAM "nf_conntrack_udp_timeout_stream" no longer used */ + /* NET_NF_CONNTRACK_ICMP_TIMEOUT "nf_conntrack_icmp_timeout" no longer used */ + /* NET_NF_CONNTRACK_GENERIC_TIMEOUT "nf_conntrack_generic_timeout" no longer used */ + { CTL_INT, NET_NF_CONNTRACK_BUCKETS, "nf_conntrack_buckets" }, + { CTL_INT, NET_NF_CONNTRACK_LOG_INVALID, "nf_conntrack_log_invalid" }, + /* NET_NF_CONNTRACK_TCP_TIMEOUT_MAX_RETRANS "nf_conntrack_tcp_timeout_max_retrans" no longer used */ + { CTL_INT, NET_NF_CONNTRACK_TCP_LOOSE, "nf_conntrack_tcp_loose" }, + { CTL_INT, NET_NF_CONNTRACK_TCP_BE_LIBERAL, "nf_conntrack_tcp_be_liberal" }, + { CTL_INT, NET_NF_CONNTRACK_TCP_MAX_RETRANS, "nf_conntrack_tcp_max_retrans" }, + /* NET_NF_CONNTRACK_SCTP_TIMEOUT_CLOSED "nf_conntrack_sctp_timeout_closed" no longer used */ + /* NET_NF_CONNTRACK_SCTP_TIMEOUT_COOKIE_WAIT "nf_conntrack_sctp_timeout_cookie_wait" no longer used */ + /* NET_NF_CONNTRACK_SCTP_TIMEOUT_COOKIE_ECHOED "nf_conntrack_sctp_timeout_cookie_echoed" no longer used */ + /* NET_NF_CONNTRACK_SCTP_TIMEOUT_ESTABLISHED "nf_conntrack_sctp_timeout_established" no longer used */ + /* NET_NF_CONNTRACK_SCTP_TIMEOUT_SHUTDOWN_SENT "nf_conntrack_sctp_timeout_shutdown_sent" no longer used */ + /* NET_NF_CONNTRACK_SCTP_TIMEOUT_SHUTDOWN_RECD "nf_conntrack_sctp_timeout_shutdown_recd" no longer used */ + /* NET_NF_CONNTRACK_SCTP_TIMEOUT_SHUTDOWN_ACK_SENT "nf_conntrack_sctp_timeout_shutdown_ack_sent" no longer used */ + { CTL_INT, NET_NF_CONNTRACK_COUNT, "nf_conntrack_count" }, + /* NET_NF_CONNTRACK_ICMPV6_TIMEOUT "nf_conntrack_icmpv6_timeout" no longer used */ + /* NET_NF_CONNTRACK_FRAG6_TIMEOUT "nf_conntrack_frag6_timeout" no longer used */ + { CTL_INT, NET_NF_CONNTRACK_FRAG6_LOW_THRESH, "nf_conntrack_frag6_low_thresh" }, + { CTL_INT, NET_NF_CONNTRACK_FRAG6_HIGH_THRESH, "nf_conntrack_frag6_high_thresh" }, + { CTL_INT, NET_NF_CONNTRACK_CHECKSUM, "nf_conntrack_checksum" }, + + {} +}; + +static const struct bin_table bin_net_irda_table[] = { + { CTL_INT, NET_IRDA_DISCOVERY, "discovery" }, + { CTL_STR, NET_IRDA_DEVNAME, "devname" }, + { CTL_INT, NET_IRDA_DEBUG, "debug" }, + { CTL_INT, NET_IRDA_FAST_POLL, "fast_poll_increase" }, + { CTL_INT, NET_IRDA_DISCOVERY_SLOTS, "discovery_slots" }, + { CTL_INT, NET_IRDA_DISCOVERY_TIMEOUT, "discovery_timeout" }, + { CTL_INT, NET_IRDA_SLOT_TIMEOUT, "slot_timeout" }, + { CTL_INT, NET_IRDA_MAX_BAUD_RATE, "max_baud_rate" }, + { CTL_INT, NET_IRDA_MIN_TX_TURN_TIME, "min_tx_turn_time" }, + { CTL_INT, NET_IRDA_MAX_TX_DATA_SIZE, "max_tx_data_size" }, + { CTL_INT, NET_IRDA_MAX_TX_WINDOW, "max_tx_window" }, + { CTL_INT, NET_IRDA_MAX_NOREPLY_TIME, "max_noreply_time" }, + { CTL_INT, NET_IRDA_WARN_NOREPLY_TIME, "warn_noreply_time" }, + { CTL_INT, NET_IRDA_LAP_KEEPALIVE_TIME, "lap_keepalive_time" }, + {} +}; + +static const struct bin_table bin_net_table[] = { + { CTL_DIR, NET_CORE, "core", bin_net_core_table }, + /* NET_ETHER not used */ + /* NET_802 not used */ + { CTL_DIR, NET_UNIX, "unix", bin_net_unix_table }, + { CTL_DIR, NET_IPV4, "ipv4", bin_net_ipv4_table }, + { CTL_DIR, NET_IPX, "ipx", bin_net_ipx_table }, + { CTL_DIR, NET_ATALK, "appletalk", bin_net_atalk_table }, + { CTL_DIR, NET_NETROM, "netrom", bin_net_netrom_table }, + { CTL_DIR, NET_AX25, "ax25", bin_net_ax25_table }, + /* NET_BRIDGE "bridge" no longer used */ + { CTL_DIR, NET_ROSE, "rose", bin_net_rose_table }, + { CTL_DIR, NET_IPV6, "ipv6", bin_net_ipv6_table }, + { CTL_DIR, NET_X25, "x25", bin_net_x25_table }, + { CTL_DIR, NET_TR, "token-ring", bin_net_tr_table }, + { CTL_DIR, NET_DECNET, "decnet", bin_net_decnet_table }, + /* NET_ECONET not used */ + { CTL_DIR, NET_SCTP, "sctp", bin_net_sctp_table }, + { CTL_DIR, NET_LLC, "llc", bin_net_llc_table }, + { CTL_DIR, NET_NETFILTER, "netfilter", bin_net_netfilter_table }, + /* NET_DCCP "dccp" no longer used */ + { CTL_DIR, NET_IRDA, "irda", bin_net_irda_table }, + { CTL_INT, 2089, "nf_conntrack_max" }, + {} +}; + +static const struct bin_table bin_fs_quota_table[] = { + { CTL_INT, FS_DQ_LOOKUPS, "lookups" }, + { CTL_INT, FS_DQ_DROPS, "drops" }, + { CTL_INT, FS_DQ_READS, "reads" }, + { CTL_INT, FS_DQ_WRITES, "writes" }, + { CTL_INT, FS_DQ_CACHE_HITS, "cache_hits" }, + { CTL_INT, FS_DQ_ALLOCATED, "allocated_dquots" }, + { CTL_INT, FS_DQ_FREE, "free_dquots" }, + { CTL_INT, FS_DQ_SYNCS, "syncs" }, + { CTL_INT, FS_DQ_WARNINGS, "warnings" }, + {} +}; + +static const struct bin_table bin_fs_xfs_table[] = { + { CTL_INT, XFS_SGID_INHERIT, "irix_sgid_inherit" }, + { CTL_INT, XFS_SYMLINK_MODE, "irix_symlink_mode" }, + { CTL_INT, XFS_PANIC_MASK, "panic_mask" }, + + { CTL_INT, XFS_ERRLEVEL, "error_level" }, + { CTL_INT, XFS_SYNCD_TIMER, "xfssyncd_centisecs" }, + { CTL_INT, XFS_INHERIT_SYNC, "inherit_sync" }, + { CTL_INT, XFS_INHERIT_NODUMP, "inherit_nodump" }, + { CTL_INT, XFS_INHERIT_NOATIME, "inherit_noatime" }, + { CTL_INT, XFS_BUF_TIMER, "xfsbufd_centisecs" }, + { CTL_INT, XFS_BUF_AGE, "age_buffer_centisecs" }, + { CTL_INT, XFS_INHERIT_NOSYM, "inherit_nosymlinks" }, + { CTL_INT, XFS_ROTORSTEP, "rotorstep" }, + { CTL_INT, XFS_INHERIT_NODFRG, "inherit_nodefrag" }, + { CTL_INT, XFS_FILESTREAM_TIMER, "filestream_centisecs" }, + { CTL_INT, XFS_STATS_CLEAR, "stats_clear" }, + {} +}; + +static const struct bin_table bin_fs_ocfs2_nm_table[] = { + { CTL_STR, 1, "hb_ctl_path" }, + {} +}; + +static const struct bin_table bin_fs_ocfs2_table[] = { + { CTL_DIR, 1, "nm", bin_fs_ocfs2_nm_table }, + {} +}; + +static const struct bin_table bin_inotify_table[] = { + { CTL_INT, INOTIFY_MAX_USER_INSTANCES, "max_user_instances" }, + { CTL_INT, INOTIFY_MAX_USER_WATCHES, "max_user_watches" }, + { CTL_INT, INOTIFY_MAX_QUEUED_EVENTS, "max_queued_events" }, + {} +}; + +static const struct bin_table bin_fs_table[] = { + { CTL_INT, FS_NRINODE, "inode-nr" }, + { CTL_INT, FS_STATINODE, "inode-state" }, + /* FS_MAXINODE unused */ + /* FS_NRDQUOT unused */ + /* FS_MAXDQUOT unused */ + /* FS_NRFILE "file-nr" no longer used */ + { CTL_INT, FS_MAXFILE, "file-max" }, + { CTL_INT, FS_DENTRY, "dentry-state" }, + /* FS_NRSUPER unused */ + /* FS_MAXUPSER unused */ + { CTL_INT, FS_OVERFLOWUID, "overflowuid" }, + { CTL_INT, FS_OVERFLOWGID, "overflowgid" }, + { CTL_INT, FS_LEASES, "leases-enable" }, + { CTL_INT, FS_DIR_NOTIFY, "dir-notify-enable" }, + { CTL_INT, FS_LEASE_TIME, "lease-break-time" }, + { CTL_DIR, FS_DQSTATS, "quota", bin_fs_quota_table }, + { CTL_DIR, FS_XFS, "xfs", bin_fs_xfs_table }, + { CTL_ULONG, FS_AIO_NR, "aio-nr" }, + { CTL_ULONG, FS_AIO_MAX_NR, "aio-max-nr" }, + { CTL_DIR, FS_INOTIFY, "inotify", bin_inotify_table }, + { CTL_DIR, FS_OCFS2, "ocfs2", bin_fs_ocfs2_table }, + { CTL_INT, KERN_SETUID_DUMPABLE, "suid_dumpable" }, + {} +}; + +static const struct bin_table bin_ipmi_table[] = { + { CTL_INT, DEV_IPMI_POWEROFF_POWERCYCLE, "poweroff_powercycle" }, + {} +}; + +static const struct bin_table bin_mac_hid_files[] = { + /* DEV_MAC_HID_KEYBOARD_SENDS_LINUX_KEYCODES unused */ + /* DEV_MAC_HID_KEYBOARD_LOCK_KEYCODES unused */ + { CTL_INT, DEV_MAC_HID_MOUSE_BUTTON_EMULATION, "mouse_button_emulation" }, + { CTL_INT, DEV_MAC_HID_MOUSE_BUTTON2_KEYCODE, "mouse_button2_keycode" }, + { CTL_INT, DEV_MAC_HID_MOUSE_BUTTON3_KEYCODE, "mouse_button3_keycode" }, + /* DEV_MAC_HID_ADB_MOUSE_SENDS_KEYCODES unused */ + {} +}; + +static const struct bin_table bin_raid_table[] = { + { CTL_INT, DEV_RAID_SPEED_LIMIT_MIN, "speed_limit_min" }, + { CTL_INT, DEV_RAID_SPEED_LIMIT_MAX, "speed_limit_max" }, + {} +}; + +static const struct bin_table bin_scsi_table[] = { + { CTL_INT, DEV_SCSI_LOGGING_LEVEL, "logging_level" }, + {} +}; + +static const struct bin_table bin_dev_table[] = { + /* DEV_CDROM "cdrom" no longer used */ + /* DEV_HWMON unused */ + /* DEV_PARPORT "parport" no longer used */ + { CTL_DIR, DEV_RAID, "raid", bin_raid_table }, + { CTL_DIR, DEV_MAC_HID, "mac_hid", bin_mac_hid_files }, + { CTL_DIR, DEV_SCSI, "scsi", bin_scsi_table }, + { CTL_DIR, DEV_IPMI, "ipmi", bin_ipmi_table }, + {} +}; + +static const struct bin_table bin_bus_isa_table[] = { + { CTL_INT, BUS_ISA_MEM_BASE, "membase" }, + { CTL_INT, BUS_ISA_PORT_BASE, "portbase" }, + { CTL_INT, BUS_ISA_PORT_SHIFT, "portshift" }, + {} +}; + +static const struct bin_table bin_bus_table[] = { + { CTL_DIR, CTL_BUS_ISA, "isa", bin_bus_isa_table }, + {} +}; + + +static const struct bin_table bin_s390dbf_table[] = { + { CTL_INT, 5678 /* CTL_S390DBF_STOPPABLE */, "debug_stoppable" }, + { CTL_INT, 5679 /* CTL_S390DBF_ACTIVE */, "debug_active" }, + {} +}; + +static const struct bin_table bin_sunrpc_table[] = { + /* CTL_RPCDEBUG "rpc_debug" no longer used */ + /* CTL_NFSDEBUG "nfs_debug" no longer used */ + /* CTL_NFSDDEBUG "nfsd_debug" no longer used */ + /* CTL_NLMDEBUG "nlm_debug" no longer used */ + + { CTL_INT, CTL_SLOTTABLE_UDP, "udp_slot_table_entries" }, + { CTL_INT, CTL_SLOTTABLE_TCP, "tcp_slot_table_entries" }, + { CTL_INT, CTL_MIN_RESVPORT, "min_resvport" }, + { CTL_INT, CTL_MAX_RESVPORT, "max_resvport" }, + {} +}; + +static const struct bin_table bin_pm_table[] = { + /* frv specific */ + /* 1 == CTL_PM_SUSPEND "suspend" no longer used" */ + { CTL_INT, 2 /* CTL_PM_CMODE */, "cmode" }, + { CTL_INT, 3 /* CTL_PM_P0 */, "p0" }, + { CTL_INT, 4 /* CTL_PM_CM */, "cm" }, + {} +}; + +static const struct bin_table bin_root_table[] = { + { CTL_DIR, CTL_KERN, "kernel", bin_kern_table }, + { CTL_DIR, CTL_VM, "vm", bin_vm_table }, + { CTL_DIR, CTL_NET, "net", bin_net_table }, + /* CTL_PROC not used */ + { CTL_DIR, CTL_FS, "fs", bin_fs_table }, + /* CTL_DEBUG "debug" no longer used */ + { CTL_DIR, CTL_DEV, "dev", bin_dev_table }, + { CTL_DIR, CTL_BUS, "bus", bin_bus_table }, + { CTL_DIR, CTL_ABI, "abi" }, + /* CTL_CPU not used */ + /* CTL_ARLAN "arlan" no longer used */ + { CTL_DIR, CTL_S390DBF, "s390dbf", bin_s390dbf_table }, + { CTL_DIR, CTL_SUNRPC, "sunrpc", bin_sunrpc_table }, + { CTL_DIR, CTL_PM, "pm", bin_pm_table }, + {} +}; + +static ssize_t bin_dir(struct file *file, + void __user *oldval, size_t oldlen, void __user *newval, size_t newlen) +{ + return -ENOTDIR; +} + + +static ssize_t bin_string(struct file *file, + void __user *oldval, size_t oldlen, void __user *newval, size_t newlen) +{ + ssize_t result, copied = 0; + + if (oldval && oldlen) { + char __user *lastp; + loff_t pos = 0; + int ch; + + result = vfs_read(file, oldval, oldlen, &pos); + if (result < 0) + goto out; + + copied = result; + lastp = oldval + copied - 1; + + result = -EFAULT; + if (get_user(ch, lastp)) + goto out; + + /* Trim off the trailing newline */ + if (ch == '\n') { + result = -EFAULT; + if (put_user('\0', lastp)) + goto out; + copied -= 1; + } + } + + if (newval && newlen) { + loff_t pos = 0; + + result = vfs_write(file, newval, newlen, &pos); + if (result < 0) + goto out; + } + + result = copied; +out: + return result; +} + +static ssize_t bin_intvec(struct file *file, + void __user *oldval, size_t oldlen, void __user *newval, size_t newlen) +{ + ssize_t copied = 0; + char *buffer; + ssize_t result; + + result = -ENOMEM; + buffer = kmalloc(BUFSZ, GFP_KERNEL); + if (!buffer) + goto out; + + if (oldval && oldlen) { + unsigned __user *vec = oldval; + size_t length = oldlen / sizeof(*vec); + char *str, *end; + int i; + + result = kernel_read(file, 0, buffer, BUFSZ - 1); + if (result < 0) + goto out_kfree; + + str = buffer; + end = str + result; + *end++ = '\0'; + for (i = 0; i < length; i++) { + unsigned long value; + + value = simple_strtoul(str, &str, 10); + while (isspace(*str)) + str++; + + result = -EFAULT; + if (put_user(value, vec + i)) + goto out_kfree; + + copied += sizeof(*vec); + if (!isdigit(*str)) + break; + } + } + + if (newval && newlen) { + unsigned __user *vec = newval; + size_t length = newlen / sizeof(*vec); + char *str, *end; + int i; + + str = buffer; + end = str + BUFSZ; + for (i = 0; i < length; i++) { + unsigned long value; + + result = -EFAULT; + if (get_user(value, vec + i)) + goto out_kfree; + + str += scnprintf(str, end - str, "%lu\t", value); + } + + result = kernel_write(file, buffer, str - buffer, 0); + if (result < 0) + goto out_kfree; + } + result = copied; +out_kfree: + kfree(buffer); +out: + return result; +} + +static ssize_t bin_ulongvec(struct file *file, + void __user *oldval, size_t oldlen, void __user *newval, size_t newlen) +{ + ssize_t copied = 0; + char *buffer; + ssize_t result; + + result = -ENOMEM; + buffer = kmalloc(BUFSZ, GFP_KERNEL); + if (!buffer) + goto out; + + if (oldval && oldlen) { + unsigned long __user *vec = oldval; + size_t length = oldlen / sizeof(*vec); + char *str, *end; + int i; + + result = kernel_read(file, 0, buffer, BUFSZ - 1); + if (result < 0) + goto out_kfree; + + str = buffer; + end = str + result; + *end++ = '\0'; + for (i = 0; i < length; i++) { + unsigned long value; + + value = simple_strtoul(str, &str, 10); + while (isspace(*str)) + str++; + + result = -EFAULT; + if (put_user(value, vec + i)) + goto out_kfree; + + copied += sizeof(*vec); + if (!isdigit(*str)) + break; + } + } + + if (newval && newlen) { + unsigned long __user *vec = newval; + size_t length = newlen / sizeof(*vec); + char *str, *end; + int i; + + str = buffer; + end = str + BUFSZ; + for (i = 0; i < length; i++) { + unsigned long value; + + result = -EFAULT; + if (get_user(value, vec + i)) + goto out_kfree; + + str += scnprintf(str, end - str, "%lu\t", value); + } + + result = kernel_write(file, buffer, str - buffer, 0); + if (result < 0) + goto out_kfree; + } + result = copied; +out_kfree: + kfree(buffer); +out: + return result; +} + +static ssize_t bin_uuid(struct file *file, + void __user *oldval, size_t oldlen, void __user *newval, size_t newlen) +{ + ssize_t result, copied = 0; + + /* Only supports reads */ + if (oldval && oldlen) { + char buf[40], *str = buf; + unsigned char uuid[16]; + int i; + + result = kernel_read(file, 0, buf, sizeof(buf) - 1); + if (result < 0) + goto out; + + buf[result] = '\0'; + + /* Convert the uuid to from a string to binary */ + for (i = 0; i < 16; i++) { + result = -EIO; + if (!isxdigit(str[0]) || !isxdigit(str[1])) + goto out; + + uuid[i] = (hex_to_bin(str[0]) << 4) | + hex_to_bin(str[1]); + str += 2; + if (*str == '-') + str++; + } + + if (oldlen > 16) + oldlen = 16; + + result = -EFAULT; + if (copy_to_user(oldval, uuid, oldlen)) + goto out; + + copied = oldlen; + } + result = copied; +out: + return result; +} + +static ssize_t bin_dn_node_address(struct file *file, + void __user *oldval, size_t oldlen, void __user *newval, size_t newlen) +{ + ssize_t result, copied = 0; + + if (oldval && oldlen) { + char buf[15], *nodep; + unsigned long area, node; + __le16 dnaddr; + + result = kernel_read(file, 0, buf, sizeof(buf) - 1); + if (result < 0) + goto out; + + buf[result] = '\0'; + + /* Convert the decnet address to binary */ + result = -EIO; + nodep = strchr(buf, '.'); + if (!nodep) + goto out; + ++nodep; + + area = simple_strtoul(buf, NULL, 10); + node = simple_strtoul(nodep, NULL, 10); + + result = -EIO; + if ((area > 63)||(node > 1023)) + goto out; + + dnaddr = cpu_to_le16((area << 10) | node); + + result = -EFAULT; + if (put_user(dnaddr, (__le16 __user *)oldval)) + goto out; + + copied = sizeof(dnaddr); + } + + if (newval && newlen) { + __le16 dnaddr; + char buf[15]; + int len; + + result = -EINVAL; + if (newlen != sizeof(dnaddr)) + goto out; + + result = -EFAULT; + if (get_user(dnaddr, (__le16 __user *)newval)) + goto out; + + len = scnprintf(buf, sizeof(buf), "%hu.%hu", + le16_to_cpu(dnaddr) >> 10, + le16_to_cpu(dnaddr) & 0x3ff); + + result = kernel_write(file, buf, len, 0); + if (result < 0) + goto out; + } + + result = copied; +out: + return result; +} + +static const struct bin_table *get_sysctl(const int *name, int nlen, char *path) +{ + const struct bin_table *table = &bin_root_table[0]; + int ctl_name; + + /* The binary sysctl tables have a small maximum depth so + * there is no danger of overflowing our path as it PATH_MAX + * bytes long. + */ + memcpy(path, "sys/", 4); + path += 4; + +repeat: + if (!nlen) + return ERR_PTR(-ENOTDIR); + ctl_name = *name; + name++; + nlen--; + for ( ; table->convert; table++) { + int len = 0; + + /* + * For a wild card entry map from ifindex to network + * device name. + */ + if (!table->ctl_name) { +#ifdef CONFIG_NET + struct net *net = current->nsproxy->net_ns; + struct net_device *dev; + dev = dev_get_by_index(net, ctl_name); + if (dev) { + len = strlen(dev->name); + memcpy(path, dev->name, len); + dev_put(dev); + } +#endif + /* Use the well known sysctl number to proc name mapping */ + } else if (ctl_name == table->ctl_name) { + len = strlen(table->procname); + memcpy(path, table->procname, len); + } + if (len) { + path += len; + if (table->child) { + *path++ = '/'; + table = table->child; + goto repeat; + } + *path = '\0'; + return table; + } + } + return ERR_PTR(-ENOTDIR); +} + +static char *sysctl_getname(const int *name, int nlen, const struct bin_table **tablep) +{ + char *tmp, *result; + + result = ERR_PTR(-ENOMEM); + tmp = __getname(); + if (tmp) { + const struct bin_table *table = get_sysctl(name, nlen, tmp); + result = tmp; + *tablep = table; + if (IS_ERR(table)) { + __putname(tmp); + result = ERR_CAST(table); + } + } + return result; +} + +static ssize_t binary_sysctl(const int *name, int nlen, + void __user *oldval, size_t oldlen, void __user *newval, size_t newlen) +{ + const struct bin_table *table = NULL; + struct vfsmount *mnt; + struct file *file; + ssize_t result; + char *pathname; + int flags; + + pathname = sysctl_getname(name, nlen, &table); + result = PTR_ERR(pathname); + if (IS_ERR(pathname)) + goto out; + + /* How should the sysctl be accessed? */ + if (oldval && oldlen && newval && newlen) { + flags = O_RDWR; + } else if (newval && newlen) { + flags = O_WRONLY; + } else if (oldval && oldlen) { + flags = O_RDONLY; + } else { + result = 0; + goto out_putname; + } + + mnt = task_active_pid_ns(current)->proc_mnt; + file = file_open_root(mnt->mnt_root, mnt, pathname, flags); + result = PTR_ERR(file); + if (IS_ERR(file)) + goto out_putname; + + result = table->convert(file, oldval, oldlen, newval, newlen); + + fput(file); +out_putname: + __putname(pathname); +out: + return result; +} + + +#else /* CONFIG_SYSCTL_SYSCALL */ + +static ssize_t binary_sysctl(const int *name, int nlen, + void __user *oldval, size_t oldlen, void __user *newval, size_t newlen) +{ + return -ENOSYS; +} + +#endif /* CONFIG_SYSCTL_SYSCALL */ + + +static void deprecated_sysctl_warning(const int *name, int nlen) +{ + int i; + + /* + * CTL_KERN/KERN_VERSION is used by older glibc and cannot + * ever go away. + */ + if (name[0] == CTL_KERN && name[1] == KERN_VERSION) + return; + + if (printk_ratelimit()) { + printk(KERN_INFO + "warning: process `%s' used the deprecated sysctl " + "system call with ", current->comm); + for (i = 0; i < nlen; i++) + printk("%d.", name[i]); + printk("\n"); + } + return; +} + +#define WARN_ONCE_HASH_BITS 8 +#define WARN_ONCE_HASH_SIZE (1<nlen. */ + if (nlen < 0 || nlen > CTL_MAXNAME) + return -ENOTDIR; + /* Read in the sysctl name for simplicity */ + for (i = 0; i < nlen; i++) + if (get_user(name[i], args_name + i)) + return -EFAULT; + + warn_on_bintable(name, nlen); + + return binary_sysctl(name, nlen, oldval, oldlen, newval, newlen); +} + +SYSCALL_DEFINE1(sysctl, struct __sysctl_args __user *, args) +{ + struct __sysctl_args tmp; + size_t oldlen = 0; + ssize_t result; + + if (copy_from_user(&tmp, args, sizeof(tmp))) + return -EFAULT; + + if (tmp.oldval && !tmp.oldlenp) + return -EFAULT; + + if (tmp.oldlenp && get_user(oldlen, tmp.oldlenp)) + return -EFAULT; + + result = do_sysctl(tmp.name, tmp.nlen, tmp.oldval, oldlen, + tmp.newval, tmp.newlen); + + if (result >= 0) { + oldlen = result; + result = 0; + } + + if (tmp.oldlenp && put_user(oldlen, tmp.oldlenp)) + return -EFAULT; + + return result; +} + + +#ifdef CONFIG_COMPAT + +struct compat_sysctl_args { + compat_uptr_t name; + int nlen; + compat_uptr_t oldval; + compat_uptr_t oldlenp; + compat_uptr_t newval; + compat_size_t newlen; + compat_ulong_t __unused[4]; +}; + +COMPAT_SYSCALL_DEFINE1(sysctl, struct compat_sysctl_args __user *, args) +{ + struct compat_sysctl_args tmp; + compat_size_t __user *compat_oldlenp; + size_t oldlen = 0; + ssize_t result; + + if (copy_from_user(&tmp, args, sizeof(tmp))) + return -EFAULT; + + if (tmp.oldval && !tmp.oldlenp) + return -EFAULT; + + compat_oldlenp = compat_ptr(tmp.oldlenp); + if (compat_oldlenp && get_user(oldlen, compat_oldlenp)) + return -EFAULT; + + result = do_sysctl(compat_ptr(tmp.name), tmp.nlen, + compat_ptr(tmp.oldval), oldlen, + compat_ptr(tmp.newval), tmp.newlen); + + if (result >= 0) { + oldlen = result; + result = 0; + } + + if (compat_oldlenp && put_user(oldlen, compat_oldlenp)) + return -EFAULT; + + return result; +} + +#endif /* CONFIG_COMPAT */ diff --git a/kernel/kernel/system_certificates.S b/kernel/kernel/system_certificates.S new file mode 100644 index 000000000..3e9868d47 --- /dev/null +++ b/kernel/kernel/system_certificates.S @@ -0,0 +1,20 @@ +#include +#include + + __INITRODATA + + .align 8 + .globl VMLINUX_SYMBOL(system_certificate_list) +VMLINUX_SYMBOL(system_certificate_list): +__cert_list_start: + .incbin "kernel/x509_certificate_list" +__cert_list_end: + + .align 8 + .globl VMLINUX_SYMBOL(system_certificate_list_size) +VMLINUX_SYMBOL(system_certificate_list_size): +#ifdef CONFIG_64BIT + .quad __cert_list_end - __cert_list_start +#else + .long __cert_list_end - __cert_list_start +#endif diff --git a/kernel/kernel/system_keyring.c b/kernel/kernel/system_keyring.c new file mode 100644 index 000000000..875f64e89 --- /dev/null +++ b/kernel/kernel/system_keyring.c @@ -0,0 +1,106 @@ +/* System trusted keyring for trusted public keys + * + * Copyright (C) 2012 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public Licence + * as published by the Free Software Foundation; either version + * 2 of the Licence, or (at your option) any later version. + */ + +#include +#include +#include +#include +#include +#include +#include +#include "module-internal.h" + +struct key *system_trusted_keyring; +EXPORT_SYMBOL_GPL(system_trusted_keyring); + +extern __initconst const u8 system_certificate_list[]; +extern __initconst const unsigned long system_certificate_list_size; + +/* + * Load the compiled-in keys + */ +static __init int system_trusted_keyring_init(void) +{ + pr_notice("Initialise system trusted keyring\n"); + + system_trusted_keyring = + keyring_alloc(".system_keyring", + KUIDT_INIT(0), KGIDT_INIT(0), current_cred(), + ((KEY_POS_ALL & ~KEY_POS_SETATTR) | + KEY_USR_VIEW | KEY_USR_READ | KEY_USR_SEARCH), + KEY_ALLOC_NOT_IN_QUOTA, NULL); + if (IS_ERR(system_trusted_keyring)) + panic("Can't allocate system trusted keyring\n"); + + set_bit(KEY_FLAG_TRUSTED_ONLY, &system_trusted_keyring->flags); + return 0; +} + +/* + * Must be initialised before we try and load the keys into the keyring. + */ +device_initcall(system_trusted_keyring_init); + +/* + * Load the compiled-in list of X.509 certificates. + */ +static __init int load_system_certificate_list(void) +{ + key_ref_t key; + const u8 *p, *end; + size_t plen; + + pr_notice("Loading compiled-in X.509 certificates\n"); + + p = system_certificate_list; + end = p + system_certificate_list_size; + while (p < end) { + /* Each cert begins with an ASN.1 SEQUENCE tag and must be more + * than 256 bytes in size. + */ + if (end - p < 4) + goto dodgy_cert; + if (p[0] != 0x30 && + p[1] != 0x82) + goto dodgy_cert; + plen = (p[2] << 8) | p[3]; + plen += 4; + if (plen > end - p) + goto dodgy_cert; + + key = key_create_or_update(make_key_ref(system_trusted_keyring, 1), + "asymmetric", + NULL, + p, + plen, + ((KEY_POS_ALL & ~KEY_POS_SETATTR) | + KEY_USR_VIEW | KEY_USR_READ), + KEY_ALLOC_NOT_IN_QUOTA | + KEY_ALLOC_TRUSTED); + if (IS_ERR(key)) { + pr_err("Problem loading in-kernel X.509 certificate (%ld)\n", + PTR_ERR(key)); + } else { + set_bit(KEY_FLAG_BUILTIN, &key_ref_to_ptr(key)->flags); + pr_notice("Loaded X.509 cert '%s'\n", + key_ref_to_ptr(key)->description); + key_ref_put(key); + } + p += plen; + } + + return 0; + +dodgy_cert: + pr_err("Problem parsing in-kernel X.509 certificate list\n"); + return 0; +} +late_initcall(load_system_certificate_list); diff --git a/kernel/kernel/task_work.c b/kernel/kernel/task_work.c new file mode 100644 index 000000000..8727032e3 --- /dev/null +++ b/kernel/kernel/task_work.c @@ -0,0 +1,128 @@ +#include +#include +#include + +static struct callback_head work_exited; /* all we need is ->next == NULL */ + +/** + * task_work_add - ask the @task to execute @work->func() + * @task: the task which should run the callback + * @work: the callback to run + * @notify: send the notification if true + * + * Queue @work for task_work_run() below and notify the @task if @notify. + * Fails if the @task is exiting/exited and thus it can't process this @work. + * Otherwise @work->func() will be called when the @task returns from kernel + * mode or exits. + * + * This is like the signal handler which runs in kernel mode, but it doesn't + * try to wake up the @task. + * + * RETURNS: + * 0 if succeeds or -ESRCH. + */ +int +task_work_add(struct task_struct *task, struct callback_head *work, bool notify) +{ + struct callback_head *head; + + do { + head = ACCESS_ONCE(task->task_works); + if (unlikely(head == &work_exited)) + return -ESRCH; + work->next = head; + } while (cmpxchg(&task->task_works, head, work) != head); + + if (notify) + set_notify_resume(task); + return 0; +} + +/** + * task_work_cancel - cancel a pending work added by task_work_add() + * @task: the task which should execute the work + * @func: identifies the work to remove + * + * Find the last queued pending work with ->func == @func and remove + * it from queue. + * + * RETURNS: + * The found work or NULL if not found. + */ +struct callback_head * +task_work_cancel(struct task_struct *task, task_work_func_t func) +{ + struct callback_head **pprev = &task->task_works; + struct callback_head *work; + unsigned long flags; + /* + * If cmpxchg() fails we continue without updating pprev. + * Either we raced with task_work_add() which added the + * new entry before this work, we will find it again. Or + * we raced with task_work_run(), *pprev == NULL/exited. + */ + raw_spin_lock_irqsave(&task->pi_lock, flags); + while ((work = ACCESS_ONCE(*pprev))) { + smp_read_barrier_depends(); + if (work->func != func) + pprev = &work->next; + else if (cmpxchg(pprev, work, work->next) == work) + break; + } + raw_spin_unlock_irqrestore(&task->pi_lock, flags); + + return work; +} + +/** + * task_work_run - execute the works added by task_work_add() + * + * Flush the pending works. Should be used by the core kernel code. + * Called before the task returns to the user-mode or stops, or when + * it exits. In the latter case task_work_add() can no longer add the + * new work after task_work_run() returns. + */ +void task_work_run(void) +{ + struct task_struct *task = current; + struct callback_head *work, *head, *next; + + for (;;) { + /* + * work->func() can do task_work_add(), do not set + * work_exited unless the list is empty. + */ + do { + work = ACCESS_ONCE(task->task_works); + head = !work && (task->flags & PF_EXITING) ? + &work_exited : NULL; + } while (cmpxchg(&task->task_works, work, head) != work); + + if (!work) + break; + /* + * Synchronize with task_work_cancel(). It can't remove + * the first entry == work, cmpxchg(task_works) should + * fail, but it can play with *work and other entries. + */ + raw_spin_unlock_wait(&task->pi_lock); + smp_mb(); + + /* Reverse the list to run the works in fifo order */ + head = NULL; + do { + next = work->next; + work->next = head; + head = work; + work = next; + } while (work); + + work = head; + do { + next = work->next; + work->func(work); + work = next; + cond_resched(); + } while (work); + } +} diff --git a/kernel/kernel/taskstats.c b/kernel/kernel/taskstats.c new file mode 100644 index 000000000..21f82c29c --- /dev/null +++ b/kernel/kernel/taskstats.c @@ -0,0 +1,710 @@ +/* + * taskstats.c - Export per-task statistics to userland + * + * Copyright (C) Shailabh Nagar, IBM Corp. 2006 + * (C) Balbir Singh, IBM Corp. 2006 + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +/* + * Maximum length of a cpumask that can be specified in + * the TASKSTATS_CMD_ATTR_REGISTER/DEREGISTER_CPUMASK attribute + */ +#define TASKSTATS_CPUMASK_MAXLEN (100+6*NR_CPUS) + +static DEFINE_PER_CPU(__u32, taskstats_seqnum); +static int family_registered; +struct kmem_cache *taskstats_cache; + +static struct genl_family family = { + .id = GENL_ID_GENERATE, + .name = TASKSTATS_GENL_NAME, + .version = TASKSTATS_GENL_VERSION, + .maxattr = TASKSTATS_CMD_ATTR_MAX, +}; + +static const struct nla_policy taskstats_cmd_get_policy[TASKSTATS_CMD_ATTR_MAX+1] = { + [TASKSTATS_CMD_ATTR_PID] = { .type = NLA_U32 }, + [TASKSTATS_CMD_ATTR_TGID] = { .type = NLA_U32 }, + [TASKSTATS_CMD_ATTR_REGISTER_CPUMASK] = { .type = NLA_STRING }, + [TASKSTATS_CMD_ATTR_DEREGISTER_CPUMASK] = { .type = NLA_STRING },}; + +static const struct nla_policy cgroupstats_cmd_get_policy[CGROUPSTATS_CMD_ATTR_MAX+1] = { + [CGROUPSTATS_CMD_ATTR_FD] = { .type = NLA_U32 }, +}; + +struct listener { + struct list_head list; + pid_t pid; + char valid; +}; + +struct listener_list { + struct rw_semaphore sem; + struct list_head list; +}; +static DEFINE_PER_CPU(struct listener_list, listener_array); + +enum actions { + REGISTER, + DEREGISTER, + CPU_DONT_CARE +}; + +static int prepare_reply(struct genl_info *info, u8 cmd, struct sk_buff **skbp, + size_t size) +{ + struct sk_buff *skb; + void *reply; + + /* + * If new attributes are added, please revisit this allocation + */ + skb = genlmsg_new(size, GFP_KERNEL); + if (!skb) + return -ENOMEM; + + if (!info) { + int seq = this_cpu_inc_return(taskstats_seqnum) - 1; + + reply = genlmsg_put(skb, 0, seq, &family, 0, cmd); + } else + reply = genlmsg_put_reply(skb, info, &family, 0, cmd); + if (reply == NULL) { + nlmsg_free(skb); + return -EINVAL; + } + + *skbp = skb; + return 0; +} + +/* + * Send taskstats data in @skb to listener with nl_pid @pid + */ +static int send_reply(struct sk_buff *skb, struct genl_info *info) +{ + struct genlmsghdr *genlhdr = nlmsg_data(nlmsg_hdr(skb)); + void *reply = genlmsg_data(genlhdr); + + genlmsg_end(skb, reply); + + return genlmsg_reply(skb, info); +} + +/* + * Send taskstats data in @skb to listeners registered for @cpu's exit data + */ +static void send_cpu_listeners(struct sk_buff *skb, + struct listener_list *listeners) +{ + struct genlmsghdr *genlhdr = nlmsg_data(nlmsg_hdr(skb)); + struct listener *s, *tmp; + struct sk_buff *skb_next, *skb_cur = skb; + void *reply = genlmsg_data(genlhdr); + int rc, delcount = 0; + + genlmsg_end(skb, reply); + + rc = 0; + down_read(&listeners->sem); + list_for_each_entry(s, &listeners->list, list) { + skb_next = NULL; + if (!list_is_last(&s->list, &listeners->list)) { + skb_next = skb_clone(skb_cur, GFP_KERNEL); + if (!skb_next) + break; + } + rc = genlmsg_unicast(&init_net, skb_cur, s->pid); + if (rc == -ECONNREFUSED) { + s->valid = 0; + delcount++; + } + skb_cur = skb_next; + } + up_read(&listeners->sem); + + if (skb_cur) + nlmsg_free(skb_cur); + + if (!delcount) + return; + + /* Delete invalidated entries */ + down_write(&listeners->sem); + list_for_each_entry_safe(s, tmp, &listeners->list, list) { + if (!s->valid) { + list_del(&s->list); + kfree(s); + } + } + up_write(&listeners->sem); +} + +static void fill_stats(struct user_namespace *user_ns, + struct pid_namespace *pid_ns, + struct task_struct *tsk, struct taskstats *stats) +{ + memset(stats, 0, sizeof(*stats)); + /* + * Each accounting subsystem adds calls to its functions to + * fill in relevant parts of struct taskstsats as follows + * + * per-task-foo(stats, tsk); + */ + + delayacct_add_tsk(stats, tsk); + + /* fill in basic acct fields */ + stats->version = TASKSTATS_VERSION; + stats->nvcsw = tsk->nvcsw; + stats->nivcsw = tsk->nivcsw; + bacct_add_tsk(user_ns, pid_ns, stats, tsk); + + /* fill in extended acct fields */ + xacct_add_tsk(stats, tsk); +} + +static int fill_stats_for_pid(pid_t pid, struct taskstats *stats) +{ + struct task_struct *tsk; + + rcu_read_lock(); + tsk = find_task_by_vpid(pid); + if (tsk) + get_task_struct(tsk); + rcu_read_unlock(); + if (!tsk) + return -ESRCH; + fill_stats(current_user_ns(), task_active_pid_ns(current), tsk, stats); + put_task_struct(tsk); + return 0; +} + +static int fill_stats_for_tgid(pid_t tgid, struct taskstats *stats) +{ + struct task_struct *tsk, *first; + unsigned long flags; + int rc = -ESRCH; + + /* + * Add additional stats from live tasks except zombie thread group + * leaders who are already counted with the dead tasks + */ + rcu_read_lock(); + first = find_task_by_vpid(tgid); + + if (!first || !lock_task_sighand(first, &flags)) + goto out; + + if (first->signal->stats) + memcpy(stats, first->signal->stats, sizeof(*stats)); + else + memset(stats, 0, sizeof(*stats)); + + tsk = first; + do { + if (tsk->exit_state) + continue; + /* + * Accounting subsystem can call its functions here to + * fill in relevant parts of struct taskstsats as follows + * + * per-task-foo(stats, tsk); + */ + delayacct_add_tsk(stats, tsk); + + stats->nvcsw += tsk->nvcsw; + stats->nivcsw += tsk->nivcsw; + } while_each_thread(first, tsk); + + unlock_task_sighand(first, &flags); + rc = 0; +out: + rcu_read_unlock(); + + stats->version = TASKSTATS_VERSION; + /* + * Accounting subsystems can also add calls here to modify + * fields of taskstats. + */ + return rc; +} + +static void fill_tgid_exit(struct task_struct *tsk) +{ + unsigned long flags; + + spin_lock_irqsave(&tsk->sighand->siglock, flags); + if (!tsk->signal->stats) + goto ret; + + /* + * Each accounting subsystem calls its functions here to + * accumalate its per-task stats for tsk, into the per-tgid structure + * + * per-task-foo(tsk->signal->stats, tsk); + */ + delayacct_add_tsk(tsk->signal->stats, tsk); +ret: + spin_unlock_irqrestore(&tsk->sighand->siglock, flags); + return; +} + +static int add_del_listener(pid_t pid, const struct cpumask *mask, int isadd) +{ + struct listener_list *listeners; + struct listener *s, *tmp, *s2; + unsigned int cpu; + int ret = 0; + + if (!cpumask_subset(mask, cpu_possible_mask)) + return -EINVAL; + + if (current_user_ns() != &init_user_ns) + return -EINVAL; + + if (task_active_pid_ns(current) != &init_pid_ns) + return -EINVAL; + + if (isadd == REGISTER) { + for_each_cpu(cpu, mask) { + s = kmalloc_node(sizeof(struct listener), + GFP_KERNEL, cpu_to_node(cpu)); + if (!s) { + ret = -ENOMEM; + goto cleanup; + } + s->pid = pid; + s->valid = 1; + + listeners = &per_cpu(listener_array, cpu); + down_write(&listeners->sem); + list_for_each_entry(s2, &listeners->list, list) { + if (s2->pid == pid && s2->valid) + goto exists; + } + list_add(&s->list, &listeners->list); + s = NULL; +exists: + up_write(&listeners->sem); + kfree(s); /* nop if NULL */ + } + return 0; + } + + /* Deregister or cleanup */ +cleanup: + for_each_cpu(cpu, mask) { + listeners = &per_cpu(listener_array, cpu); + down_write(&listeners->sem); + list_for_each_entry_safe(s, tmp, &listeners->list, list) { + if (s->pid == pid) { + list_del(&s->list); + kfree(s); + break; + } + } + up_write(&listeners->sem); + } + return ret; +} + +static int parse(struct nlattr *na, struct cpumask *mask) +{ + char *data; + int len; + int ret; + + if (na == NULL) + return 1; + len = nla_len(na); + if (len > TASKSTATS_CPUMASK_MAXLEN) + return -E2BIG; + if (len < 1) + return -EINVAL; + data = kmalloc(len, GFP_KERNEL); + if (!data) + return -ENOMEM; + nla_strlcpy(data, na, len); + ret = cpulist_parse(data, mask); + kfree(data); + return ret; +} + +#if defined(CONFIG_64BIT) && !defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) +#define TASKSTATS_NEEDS_PADDING 1 +#endif + +static struct taskstats *mk_reply(struct sk_buff *skb, int type, u32 pid) +{ + struct nlattr *na, *ret; + int aggr; + + aggr = (type == TASKSTATS_TYPE_PID) + ? TASKSTATS_TYPE_AGGR_PID + : TASKSTATS_TYPE_AGGR_TGID; + + /* + * The taskstats structure is internally aligned on 8 byte + * boundaries but the layout of the aggregrate reply, with + * two NLA headers and the pid (each 4 bytes), actually + * force the entire structure to be unaligned. This causes + * the kernel to issue unaligned access warnings on some + * architectures like ia64. Unfortunately, some software out there + * doesn't properly unroll the NLA packet and assumes that the start + * of the taskstats structure will always be 20 bytes from the start + * of the netlink payload. Aligning the start of the taskstats + * structure breaks this software, which we don't want. So, for now + * the alignment only happens on architectures that require it + * and those users will have to update to fixed versions of those + * packages. Space is reserved in the packet only when needed. + * This ifdef should be removed in several years e.g. 2012 once + * we can be confident that fixed versions are installed on most + * systems. We add the padding before the aggregate since the + * aggregate is already a defined type. + */ +#ifdef TASKSTATS_NEEDS_PADDING + if (nla_put(skb, TASKSTATS_TYPE_NULL, 0, NULL) < 0) + goto err; +#endif + na = nla_nest_start(skb, aggr); + if (!na) + goto err; + + if (nla_put(skb, type, sizeof(pid), &pid) < 0) { + nla_nest_cancel(skb, na); + goto err; + } + ret = nla_reserve(skb, TASKSTATS_TYPE_STATS, sizeof(struct taskstats)); + if (!ret) { + nla_nest_cancel(skb, na); + goto err; + } + nla_nest_end(skb, na); + + return nla_data(ret); +err: + return NULL; +} + +static int cgroupstats_user_cmd(struct sk_buff *skb, struct genl_info *info) +{ + int rc = 0; + struct sk_buff *rep_skb; + struct cgroupstats *stats; + struct nlattr *na; + size_t size; + u32 fd; + struct fd f; + + na = info->attrs[CGROUPSTATS_CMD_ATTR_FD]; + if (!na) + return -EINVAL; + + fd = nla_get_u32(info->attrs[CGROUPSTATS_CMD_ATTR_FD]); + f = fdget(fd); + if (!f.file) + return 0; + + size = nla_total_size(sizeof(struct cgroupstats)); + + rc = prepare_reply(info, CGROUPSTATS_CMD_NEW, &rep_skb, + size); + if (rc < 0) + goto err; + + na = nla_reserve(rep_skb, CGROUPSTATS_TYPE_CGROUP_STATS, + sizeof(struct cgroupstats)); + if (na == NULL) { + nlmsg_free(rep_skb); + rc = -EMSGSIZE; + goto err; + } + + stats = nla_data(na); + memset(stats, 0, sizeof(*stats)); + + rc = cgroupstats_build(stats, f.file->f_path.dentry); + if (rc < 0) { + nlmsg_free(rep_skb); + goto err; + } + + rc = send_reply(rep_skb, info); + +err: + fdput(f); + return rc; +} + +static int cmd_attr_register_cpumask(struct genl_info *info) +{ + cpumask_var_t mask; + int rc; + + if (!alloc_cpumask_var(&mask, GFP_KERNEL)) + return -ENOMEM; + rc = parse(info->attrs[TASKSTATS_CMD_ATTR_REGISTER_CPUMASK], mask); + if (rc < 0) + goto out; + rc = add_del_listener(info->snd_portid, mask, REGISTER); +out: + free_cpumask_var(mask); + return rc; +} + +static int cmd_attr_deregister_cpumask(struct genl_info *info) +{ + cpumask_var_t mask; + int rc; + + if (!alloc_cpumask_var(&mask, GFP_KERNEL)) + return -ENOMEM; + rc = parse(info->attrs[TASKSTATS_CMD_ATTR_DEREGISTER_CPUMASK], mask); + if (rc < 0) + goto out; + rc = add_del_listener(info->snd_portid, mask, DEREGISTER); +out: + free_cpumask_var(mask); + return rc; +} + +static size_t taskstats_packet_size(void) +{ + size_t size; + + size = nla_total_size(sizeof(u32)) + + nla_total_size(sizeof(struct taskstats)) + nla_total_size(0); +#ifdef TASKSTATS_NEEDS_PADDING + size += nla_total_size(0); /* Padding for alignment */ +#endif + return size; +} + +static int cmd_attr_pid(struct genl_info *info) +{ + struct taskstats *stats; + struct sk_buff *rep_skb; + size_t size; + u32 pid; + int rc; + + size = taskstats_packet_size(); + + rc = prepare_reply(info, TASKSTATS_CMD_NEW, &rep_skb, size); + if (rc < 0) + return rc; + + rc = -EINVAL; + pid = nla_get_u32(info->attrs[TASKSTATS_CMD_ATTR_PID]); + stats = mk_reply(rep_skb, TASKSTATS_TYPE_PID, pid); + if (!stats) + goto err; + + rc = fill_stats_for_pid(pid, stats); + if (rc < 0) + goto err; + return send_reply(rep_skb, info); +err: + nlmsg_free(rep_skb); + return rc; +} + +static int cmd_attr_tgid(struct genl_info *info) +{ + struct taskstats *stats; + struct sk_buff *rep_skb; + size_t size; + u32 tgid; + int rc; + + size = taskstats_packet_size(); + + rc = prepare_reply(info, TASKSTATS_CMD_NEW, &rep_skb, size); + if (rc < 0) + return rc; + + rc = -EINVAL; + tgid = nla_get_u32(info->attrs[TASKSTATS_CMD_ATTR_TGID]); + stats = mk_reply(rep_skb, TASKSTATS_TYPE_TGID, tgid); + if (!stats) + goto err; + + rc = fill_stats_for_tgid(tgid, stats); + if (rc < 0) + goto err; + return send_reply(rep_skb, info); +err: + nlmsg_free(rep_skb); + return rc; +} + +static int taskstats_user_cmd(struct sk_buff *skb, struct genl_info *info) +{ + if (info->attrs[TASKSTATS_CMD_ATTR_REGISTER_CPUMASK]) + return cmd_attr_register_cpumask(info); + else if (info->attrs[TASKSTATS_CMD_ATTR_DEREGISTER_CPUMASK]) + return cmd_attr_deregister_cpumask(info); + else if (info->attrs[TASKSTATS_CMD_ATTR_PID]) + return cmd_attr_pid(info); + else if (info->attrs[TASKSTATS_CMD_ATTR_TGID]) + return cmd_attr_tgid(info); + else + return -EINVAL; +} + +static struct taskstats *taskstats_tgid_alloc(struct task_struct *tsk) +{ + struct signal_struct *sig = tsk->signal; + struct taskstats *stats; + + if (sig->stats || thread_group_empty(tsk)) + goto ret; + + /* No problem if kmem_cache_zalloc() fails */ + stats = kmem_cache_zalloc(taskstats_cache, GFP_KERNEL); + + spin_lock_irq(&tsk->sighand->siglock); + if (!sig->stats) { + sig->stats = stats; + stats = NULL; + } + spin_unlock_irq(&tsk->sighand->siglock); + + if (stats) + kmem_cache_free(taskstats_cache, stats); +ret: + return sig->stats; +} + +/* Send pid data out on exit */ +void taskstats_exit(struct task_struct *tsk, int group_dead) +{ + int rc; + struct listener_list *listeners; + struct taskstats *stats; + struct sk_buff *rep_skb; + size_t size; + int is_thread_group; + + if (!family_registered) + return; + + /* + * Size includes space for nested attributes + */ + size = taskstats_packet_size(); + + is_thread_group = !!taskstats_tgid_alloc(tsk); + if (is_thread_group) { + /* PID + STATS + TGID + STATS */ + size = 2 * size; + /* fill the tsk->signal->stats structure */ + fill_tgid_exit(tsk); + } + + listeners = raw_cpu_ptr(&listener_array); + if (list_empty(&listeners->list)) + return; + + rc = prepare_reply(NULL, TASKSTATS_CMD_NEW, &rep_skb, size); + if (rc < 0) + return; + + stats = mk_reply(rep_skb, TASKSTATS_TYPE_PID, + task_pid_nr_ns(tsk, &init_pid_ns)); + if (!stats) + goto err; + + fill_stats(&init_user_ns, &init_pid_ns, tsk, stats); + + /* + * Doesn't matter if tsk is the leader or the last group member leaving + */ + if (!is_thread_group || !group_dead) + goto send; + + stats = mk_reply(rep_skb, TASKSTATS_TYPE_TGID, + task_tgid_nr_ns(tsk, &init_pid_ns)); + if (!stats) + goto err; + + memcpy(stats, tsk->signal->stats, sizeof(*stats)); + +send: + send_cpu_listeners(rep_skb, listeners); + return; +err: + nlmsg_free(rep_skb); +} + +static const struct genl_ops taskstats_ops[] = { + { + .cmd = TASKSTATS_CMD_GET, + .doit = taskstats_user_cmd, + .policy = taskstats_cmd_get_policy, + .flags = GENL_ADMIN_PERM, + }, + { + .cmd = CGROUPSTATS_CMD_GET, + .doit = cgroupstats_user_cmd, + .policy = cgroupstats_cmd_get_policy, + }, +}; + +/* Needed early in initialization */ +void __init taskstats_init_early(void) +{ + unsigned int i; + + taskstats_cache = KMEM_CACHE(taskstats, SLAB_PANIC); + for_each_possible_cpu(i) { + INIT_LIST_HEAD(&(per_cpu(listener_array, i).list)); + init_rwsem(&(per_cpu(listener_array, i).sem)); + } +} + +static int __init taskstats_init(void) +{ + int rc; + + rc = genl_register_family_with_ops(&family, taskstats_ops); + if (rc) + return rc; + + family_registered = 1; + pr_info("registered taskstats version %d\n", TASKSTATS_GENL_VERSION); + return 0; +} + +/* + * late initcall ensures initialization of statistics collection + * mechanisms precedes initialization of the taskstats interface + */ +late_initcall(taskstats_init); diff --git a/kernel/kernel/test_kprobes.c b/kernel/kernel/test_kprobes.c new file mode 100644 index 000000000..0dbab6d1a --- /dev/null +++ b/kernel/kernel/test_kprobes.c @@ -0,0 +1,389 @@ +/* + * test_kprobes.c - simple sanity test for *probes + * + * Copyright IBM Corp. 2008 + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it would be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See + * the GNU General Public License for more details. + */ + +#define pr_fmt(fmt) "Kprobe smoke test: " fmt + +#include +#include +#include + +#define div_factor 3 + +static u32 rand1, preh_val, posth_val, jph_val; +static int errors, handler_errors, num_tests; +static u32 (*target)(u32 value); +static u32 (*target2)(u32 value); + +static noinline u32 kprobe_target(u32 value) +{ + return (value / div_factor); +} + +static int kp_pre_handler(struct kprobe *p, struct pt_regs *regs) +{ + preh_val = (rand1 / div_factor); + return 0; +} + +static void kp_post_handler(struct kprobe *p, struct pt_regs *regs, + unsigned long flags) +{ + if (preh_val != (rand1 / div_factor)) { + handler_errors++; + pr_err("incorrect value in post_handler\n"); + } + posth_val = preh_val + div_factor; +} + +static struct kprobe kp = { + .symbol_name = "kprobe_target", + .pre_handler = kp_pre_handler, + .post_handler = kp_post_handler +}; + +static int test_kprobe(void) +{ + int ret; + + ret = register_kprobe(&kp); + if (ret < 0) { + pr_err("register_kprobe returned %d\n", ret); + return ret; + } + + ret = target(rand1); + unregister_kprobe(&kp); + + if (preh_val == 0) { + pr_err("kprobe pre_handler not called\n"); + handler_errors++; + } + + if (posth_val == 0) { + pr_err("kprobe post_handler not called\n"); + handler_errors++; + } + + return 0; +} + +static noinline u32 kprobe_target2(u32 value) +{ + return (value / div_factor) + 1; +} + +static int kp_pre_handler2(struct kprobe *p, struct pt_regs *regs) +{ + preh_val = (rand1 / div_factor) + 1; + return 0; +} + +static void kp_post_handler2(struct kprobe *p, struct pt_regs *regs, + unsigned long flags) +{ + if (preh_val != (rand1 / div_factor) + 1) { + handler_errors++; + pr_err("incorrect value in post_handler2\n"); + } + posth_val = preh_val + div_factor; +} + +static struct kprobe kp2 = { + .symbol_name = "kprobe_target2", + .pre_handler = kp_pre_handler2, + .post_handler = kp_post_handler2 +}; + +static int test_kprobes(void) +{ + int ret; + struct kprobe *kps[2] = {&kp, &kp2}; + + /* addr and flags should be cleard for reusing kprobe. */ + kp.addr = NULL; + kp.flags = 0; + ret = register_kprobes(kps, 2); + if (ret < 0) { + pr_err("register_kprobes returned %d\n", ret); + return ret; + } + + preh_val = 0; + posth_val = 0; + ret = target(rand1); + + if (preh_val == 0) { + pr_err("kprobe pre_handler not called\n"); + handler_errors++; + } + + if (posth_val == 0) { + pr_err("kprobe post_handler not called\n"); + handler_errors++; + } + + preh_val = 0; + posth_val = 0; + ret = target2(rand1); + + if (preh_val == 0) { + pr_err("kprobe pre_handler2 not called\n"); + handler_errors++; + } + + if (posth_val == 0) { + pr_err("kprobe post_handler2 not called\n"); + handler_errors++; + } + + unregister_kprobes(kps, 2); + return 0; + +} + +static u32 j_kprobe_target(u32 value) +{ + if (value != rand1) { + handler_errors++; + pr_err("incorrect value in jprobe handler\n"); + } + + jph_val = rand1; + jprobe_return(); + return 0; +} + +static struct jprobe jp = { + .entry = j_kprobe_target, + .kp.symbol_name = "kprobe_target" +}; + +static int test_jprobe(void) +{ + int ret; + + ret = register_jprobe(&jp); + if (ret < 0) { + pr_err("register_jprobe returned %d\n", ret); + return ret; + } + + ret = target(rand1); + unregister_jprobe(&jp); + if (jph_val == 0) { + pr_err("jprobe handler not called\n"); + handler_errors++; + } + + return 0; +} + +static struct jprobe jp2 = { + .entry = j_kprobe_target, + .kp.symbol_name = "kprobe_target2" +}; + +static int test_jprobes(void) +{ + int ret; + struct jprobe *jps[2] = {&jp, &jp2}; + + /* addr and flags should be cleard for reusing kprobe. */ + jp.kp.addr = NULL; + jp.kp.flags = 0; + ret = register_jprobes(jps, 2); + if (ret < 0) { + pr_err("register_jprobes returned %d\n", ret); + return ret; + } + + jph_val = 0; + ret = target(rand1); + if (jph_val == 0) { + pr_err("jprobe handler not called\n"); + handler_errors++; + } + + jph_val = 0; + ret = target2(rand1); + if (jph_val == 0) { + pr_err("jprobe handler2 not called\n"); + handler_errors++; + } + unregister_jprobes(jps, 2); + + return 0; +} +#ifdef CONFIG_KRETPROBES +static u32 krph_val; + +static int entry_handler(struct kretprobe_instance *ri, struct pt_regs *regs) +{ + krph_val = (rand1 / div_factor); + return 0; +} + +static int return_handler(struct kretprobe_instance *ri, struct pt_regs *regs) +{ + unsigned long ret = regs_return_value(regs); + + if (ret != (rand1 / div_factor)) { + handler_errors++; + pr_err("incorrect value in kretprobe handler\n"); + } + if (krph_val == 0) { + handler_errors++; + pr_err("call to kretprobe entry handler failed\n"); + } + + krph_val = rand1; + return 0; +} + +static struct kretprobe rp = { + .handler = return_handler, + .entry_handler = entry_handler, + .kp.symbol_name = "kprobe_target" +}; + +static int test_kretprobe(void) +{ + int ret; + + ret = register_kretprobe(&rp); + if (ret < 0) { + pr_err("register_kretprobe returned %d\n", ret); + return ret; + } + + ret = target(rand1); + unregister_kretprobe(&rp); + if (krph_val != rand1) { + pr_err("kretprobe handler not called\n"); + handler_errors++; + } + + return 0; +} + +static int return_handler2(struct kretprobe_instance *ri, struct pt_regs *regs) +{ + unsigned long ret = regs_return_value(regs); + + if (ret != (rand1 / div_factor) + 1) { + handler_errors++; + pr_err("incorrect value in kretprobe handler2\n"); + } + if (krph_val == 0) { + handler_errors++; + pr_err("call to kretprobe entry handler failed\n"); + } + + krph_val = rand1; + return 0; +} + +static struct kretprobe rp2 = { + .handler = return_handler2, + .entry_handler = entry_handler, + .kp.symbol_name = "kprobe_target2" +}; + +static int test_kretprobes(void) +{ + int ret; + struct kretprobe *rps[2] = {&rp, &rp2}; + + /* addr and flags should be cleard for reusing kprobe. */ + rp.kp.addr = NULL; + rp.kp.flags = 0; + ret = register_kretprobes(rps, 2); + if (ret < 0) { + pr_err("register_kretprobe returned %d\n", ret); + return ret; + } + + krph_val = 0; + ret = target(rand1); + if (krph_val != rand1) { + pr_err("kretprobe handler not called\n"); + handler_errors++; + } + + krph_val = 0; + ret = target2(rand1); + if (krph_val != rand1) { + pr_err("kretprobe handler2 not called\n"); + handler_errors++; + } + unregister_kretprobes(rps, 2); + return 0; +} +#endif /* CONFIG_KRETPROBES */ + +int init_test_probes(void) +{ + int ret; + + target = kprobe_target; + target2 = kprobe_target2; + + do { + rand1 = prandom_u32(); + } while (rand1 <= div_factor); + + pr_info("started\n"); + num_tests++; + ret = test_kprobe(); + if (ret < 0) + errors++; + + num_tests++; + ret = test_kprobes(); + if (ret < 0) + errors++; + + num_tests++; + ret = test_jprobe(); + if (ret < 0) + errors++; + + num_tests++; + ret = test_jprobes(); + if (ret < 0) + errors++; + +#ifdef CONFIG_KRETPROBES + num_tests++; + ret = test_kretprobe(); + if (ret < 0) + errors++; + + num_tests++; + ret = test_kretprobes(); + if (ret < 0) + errors++; +#endif /* CONFIG_KRETPROBES */ + + if (errors) + pr_err("BUG: %d out of %d tests failed\n", errors, num_tests); + else if (handler_errors) + pr_err("BUG: %d error(s) running handlers\n", handler_errors); + else + pr_info("passed successfully\n"); + + return 0; +} diff --git a/kernel/kernel/time/Kconfig b/kernel/kernel/time/Kconfig new file mode 100644 index 000000000..579ce1b92 --- /dev/null +++ b/kernel/kernel/time/Kconfig @@ -0,0 +1,199 @@ +# +# Timer subsystem related configuration options +# + +# Options selectable by arch Kconfig + +# Watchdog function for clocksources to detect instabilities +config CLOCKSOURCE_WATCHDOG + bool + +# Architecture has extra clocksource data +config ARCH_CLOCKSOURCE_DATA + bool + +# Clocksources require validation of the clocksource against the last +# cycle update - x86/TSC misfeature +config CLOCKSOURCE_VALIDATE_LAST_CYCLE + bool + +# Timekeeping vsyscall support +config GENERIC_TIME_VSYSCALL + bool + +# Timekeeping vsyscall support +config GENERIC_TIME_VSYSCALL_OLD + bool + +# Old style timekeeping +config ARCH_USES_GETTIMEOFFSET + bool + +# The generic clock events infrastructure +config GENERIC_CLOCKEVENTS + bool + +# Architecture can handle broadcast in a driver-agnostic way +config ARCH_HAS_TICK_BROADCAST + bool + +# Clockevents broadcasting infrastructure +config GENERIC_CLOCKEVENTS_BROADCAST + bool + depends on GENERIC_CLOCKEVENTS + +# Automatically adjust the min. reprogramming time for +# clock event device +config GENERIC_CLOCKEVENTS_MIN_ADJUST + bool + +# Generic update of CMOS clock +config GENERIC_CMOS_UPDATE + bool + +if GENERIC_CLOCKEVENTS +menu "Timers subsystem" + +# Core internal switch. Selected by NO_HZ_COMMON / HIGH_RES_TIMERS. This is +# only related to the tick functionality. Oneshot clockevent devices +# are supported independ of this. +config TICK_ONESHOT + bool + +config NO_HZ_COMMON + bool + depends on !ARCH_USES_GETTIMEOFFSET && GENERIC_CLOCKEVENTS + select TICK_ONESHOT + +choice + prompt "Timer tick handling" + default NO_HZ_IDLE if NO_HZ + +config HZ_PERIODIC + bool "Periodic timer ticks (constant rate, no dynticks)" + help + This option keeps the tick running periodically at a constant + rate, even when the CPU doesn't need it. + +config NO_HZ_IDLE + bool "Idle dynticks system (tickless idle)" + depends on !ARCH_USES_GETTIMEOFFSET && GENERIC_CLOCKEVENTS + select NO_HZ_COMMON + help + This option enables a tickless idle system: timer interrupts + will only trigger on an as-needed basis when the system is idle. + This is usually interesting for energy saving. + + Most of the time you want to say Y here. + +config NO_HZ_FULL + bool "Full dynticks system (tickless)" + # NO_HZ_COMMON dependency + depends on !ARCH_USES_GETTIMEOFFSET && GENERIC_CLOCKEVENTS + # We need at least one periodic CPU for timekeeping + depends on SMP + # RCU_USER_QS dependency + depends on HAVE_CONTEXT_TRACKING + # VIRT_CPU_ACCOUNTING_GEN dependency + depends on HAVE_VIRT_CPU_ACCOUNTING_GEN + select NO_HZ_COMMON + select RCU_USER_QS + select RCU_NOCB_CPU + select VIRT_CPU_ACCOUNTING_GEN + select IRQ_WORK + help + Adaptively try to shutdown the tick whenever possible, even when + the CPU is running tasks. Typically this requires running a single + task on the CPU. Chances for running tickless are maximized when + the task mostly runs in userspace and has few kernel activity. + + You need to fill up the nohz_full boot parameter with the + desired range of dynticks CPUs. + + This is implemented at the expense of some overhead in user <-> kernel + transitions: syscalls, exceptions and interrupts. Even when it's + dynamically off. + + Say N. + +endchoice + +config NO_HZ_FULL_ALL + bool "Full dynticks system on all CPUs by default (except CPU 0)" + depends on NO_HZ_FULL + help + If the user doesn't pass the nohz_full boot option to + define the range of full dynticks CPUs, consider that all + CPUs in the system are full dynticks by default. + Note the boot CPU will still be kept outside the range to + handle the timekeeping duty. + +config NO_HZ_FULL_SYSIDLE + bool "Detect full-system idle state for full dynticks system" + depends on NO_HZ_FULL + default n + help + At least one CPU must keep the scheduling-clock tick running for + timekeeping purposes whenever there is a non-idle CPU, where + "non-idle" also includes dynticks CPUs as long as they are + running non-idle tasks. Because the underlying adaptive-tick + support cannot distinguish between all CPUs being idle and + all CPUs each running a single task in dynticks mode, the + underlying support simply ensures that there is always a CPU + handling the scheduling-clock tick, whether or not all CPUs + are idle. This Kconfig option enables scalable detection of + the all-CPUs-idle state, thus allowing the scheduling-clock + tick to be disabled when all CPUs are idle. Note that scalable + detection of the all-CPUs-idle state means that larger systems + will be slower to declare the all-CPUs-idle state. + + Say Y if you would like to help debug all-CPUs-idle detection. + + Say N if you are unsure. + +config NO_HZ_FULL_SYSIDLE_SMALL + int "Number of CPUs above which large-system approach is used" + depends on NO_HZ_FULL_SYSIDLE + range 1 NR_CPUS + default 8 + help + The full-system idle detection mechanism takes a lazy approach + on large systems, as is required to attain decent scalability. + However, on smaller systems, scalability is not anywhere near as + large a concern as is energy efficiency. The sysidle subsystem + therefore uses a fast but non-scalable algorithm for small + systems and a lazier but scalable algorithm for large systems. + This Kconfig parameter defines the number of CPUs in the largest + system that will be considered to be "small". + + The default value will be fine in most cases. Battery-powered + systems that (1) enable NO_HZ_FULL_SYSIDLE, (2) have larger + numbers of CPUs, and (3) are suffering from battery-lifetime + problems due to long sysidle latencies might wish to experiment + with larger values for this Kconfig parameter. On the other + hand, they might be even better served by disabling NO_HZ_FULL + entirely, given that NO_HZ_FULL is intended for HPC and + real-time workloads that at present do not tend to be run on + battery-powered systems. + + Take the default if you are unsure. + +config NO_HZ + bool "Old Idle dynticks config" + depends on !ARCH_USES_GETTIMEOFFSET && GENERIC_CLOCKEVENTS + help + This is the old config entry that enables dynticks idle. + We keep it around for a little while to enforce backward + compatibility with older config files. + +config HIGH_RES_TIMERS + bool "High Resolution Timer Support" + depends on !ARCH_USES_GETTIMEOFFSET && GENERIC_CLOCKEVENTS + select TICK_ONESHOT + help + This option enables high resolution timer support. If your + hardware is not capable then this option only increases + the size of the kernel image. + +endmenu +endif diff --git a/kernel/kernel/time/Makefile b/kernel/kernel/time/Makefile new file mode 100644 index 000000000..01f031241 --- /dev/null +++ b/kernel/kernel/time/Makefile @@ -0,0 +1,31 @@ +obj-y += time.o timer.o hrtimer.o itimer.o posix-timers.o posix-cpu-timers.o +obj-y += timekeeping.o ntp.o clocksource.o jiffies.o timer_list.o +obj-y += timeconv.o timecounter.o posix-clock.o alarmtimer.o + +obj-$(CONFIG_GENERIC_CLOCKEVENTS) += clockevents.o tick-common.o +ifeq ($(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST),y) + obj-y += tick-broadcast.o + obj-$(CONFIG_TICK_ONESHOT) += tick-broadcast-hrtimer.o +endif +obj-$(CONFIG_GENERIC_SCHED_CLOCK) += sched_clock.o +obj-$(CONFIG_TICK_ONESHOT) += tick-oneshot.o tick-sched.o +obj-$(CONFIG_TIMER_STATS) += timer_stats.o +obj-$(CONFIG_DEBUG_FS) += timekeeping_debug.o +obj-$(CONFIG_TEST_UDELAY) += test_udelay.o + +$(obj)/time.o: $(obj)/timeconst.h + +quiet_cmd_hzfile = HZFILE $@ + cmd_hzfile = echo "hz=$(CONFIG_HZ)" > $@ + +targets += hz.bc +$(obj)/hz.bc: $(objtree)/include/config/hz.h FORCE + $(call if_changed,hzfile) + +quiet_cmd_bc = BC $@ + cmd_bc = bc -q $(filter-out FORCE,$^) > $@ + +targets += timeconst.h +$(obj)/timeconst.h: $(obj)/hz.bc $(src)/timeconst.bc FORCE + $(call if_changed,bc) + diff --git a/kernel/kernel/time/alarmtimer.c b/kernel/kernel/time/alarmtimer.c new file mode 100644 index 000000000..1b001ed1e --- /dev/null +++ b/kernel/kernel/time/alarmtimer.c @@ -0,0 +1,873 @@ +/* + * Alarmtimer interface + * + * This interface provides a timer which is similarto hrtimers, + * but triggers a RTC alarm if the box is suspend. + * + * This interface is influenced by the Android RTC Alarm timer + * interface. + * + * Copyright (C) 2010 IBM Corperation + * + * Author: John Stultz + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +/** + * struct alarm_base - Alarm timer bases + * @lock: Lock for syncrhonized access to the base + * @timerqueue: Timerqueue head managing the list of events + * @timer: hrtimer used to schedule events while running + * @gettime: Function to read the time correlating to the base + * @base_clockid: clockid for the base + */ +static struct alarm_base { + spinlock_t lock; + struct timerqueue_head timerqueue; + ktime_t (*gettime)(void); + clockid_t base_clockid; +} alarm_bases[ALARM_NUMTYPE]; + +/* freezer delta & lock used to handle clock_nanosleep triggered wakeups */ +static ktime_t freezer_delta; +static DEFINE_SPINLOCK(freezer_delta_lock); + +static struct wakeup_source *ws; + +#ifdef CONFIG_RTC_CLASS +/* rtc timer and device for setting alarm wakeups at suspend */ +static struct rtc_timer rtctimer; +static struct rtc_device *rtcdev; +static DEFINE_SPINLOCK(rtcdev_lock); + +/** + * alarmtimer_get_rtcdev - Return selected rtcdevice + * + * This function returns the rtc device to use for wakealarms. + * If one has not already been chosen, it checks to see if a + * functional rtc device is available. + */ +struct rtc_device *alarmtimer_get_rtcdev(void) +{ + unsigned long flags; + struct rtc_device *ret; + + spin_lock_irqsave(&rtcdev_lock, flags); + ret = rtcdev; + spin_unlock_irqrestore(&rtcdev_lock, flags); + + return ret; +} +EXPORT_SYMBOL_GPL(alarmtimer_get_rtcdev); + +static int alarmtimer_rtc_add_device(struct device *dev, + struct class_interface *class_intf) +{ + unsigned long flags; + struct rtc_device *rtc = to_rtc_device(dev); + + if (rtcdev) + return -EBUSY; + + if (!rtc->ops->set_alarm) + return -1; + if (!device_may_wakeup(rtc->dev.parent)) + return -1; + + spin_lock_irqsave(&rtcdev_lock, flags); + if (!rtcdev) { + rtcdev = rtc; + /* hold a reference so it doesn't go away */ + get_device(dev); + } + spin_unlock_irqrestore(&rtcdev_lock, flags); + return 0; +} + +static inline void alarmtimer_rtc_timer_init(void) +{ + rtc_timer_init(&rtctimer, NULL, NULL); +} + +static struct class_interface alarmtimer_rtc_interface = { + .add_dev = &alarmtimer_rtc_add_device, +}; + +static int alarmtimer_rtc_interface_setup(void) +{ + alarmtimer_rtc_interface.class = rtc_class; + return class_interface_register(&alarmtimer_rtc_interface); +} +static void alarmtimer_rtc_interface_remove(void) +{ + class_interface_unregister(&alarmtimer_rtc_interface); +} +#else +struct rtc_device *alarmtimer_get_rtcdev(void) +{ + return NULL; +} +#define rtcdev (NULL) +static inline int alarmtimer_rtc_interface_setup(void) { return 0; } +static inline void alarmtimer_rtc_interface_remove(void) { } +static inline void alarmtimer_rtc_timer_init(void) { } +#endif + +/** + * alarmtimer_enqueue - Adds an alarm timer to an alarm_base timerqueue + * @base: pointer to the base where the timer is being run + * @alarm: pointer to alarm being enqueued. + * + * Adds alarm to a alarm_base timerqueue + * + * Must hold base->lock when calling. + */ +static void alarmtimer_enqueue(struct alarm_base *base, struct alarm *alarm) +{ + if (alarm->state & ALARMTIMER_STATE_ENQUEUED) + timerqueue_del(&base->timerqueue, &alarm->node); + + timerqueue_add(&base->timerqueue, &alarm->node); + alarm->state |= ALARMTIMER_STATE_ENQUEUED; +} + +/** + * alarmtimer_dequeue - Removes an alarm timer from an alarm_base timerqueue + * @base: pointer to the base where the timer is running + * @alarm: pointer to alarm being removed + * + * Removes alarm to a alarm_base timerqueue + * + * Must hold base->lock when calling. + */ +static void alarmtimer_dequeue(struct alarm_base *base, struct alarm *alarm) +{ + if (!(alarm->state & ALARMTIMER_STATE_ENQUEUED)) + return; + + timerqueue_del(&base->timerqueue, &alarm->node); + alarm->state &= ~ALARMTIMER_STATE_ENQUEUED; +} + + +/** + * alarmtimer_fired - Handles alarm hrtimer being fired. + * @timer: pointer to hrtimer being run + * + * When a alarm timer fires, this runs through the timerqueue to + * see which alarms expired, and runs those. If there are more alarm + * timers queued for the future, we set the hrtimer to fire when + * when the next future alarm timer expires. + */ +static enum hrtimer_restart alarmtimer_fired(struct hrtimer *timer) +{ + struct alarm *alarm = container_of(timer, struct alarm, timer); + struct alarm_base *base = &alarm_bases[alarm->type]; + unsigned long flags; + int ret = HRTIMER_NORESTART; + int restart = ALARMTIMER_NORESTART; + + spin_lock_irqsave(&base->lock, flags); + alarmtimer_dequeue(base, alarm); + spin_unlock_irqrestore(&base->lock, flags); + + if (alarm->function) + restart = alarm->function(alarm, base->gettime()); + + spin_lock_irqsave(&base->lock, flags); + if (restart != ALARMTIMER_NORESTART) { + hrtimer_set_expires(&alarm->timer, alarm->node.expires); + alarmtimer_enqueue(base, alarm); + ret = HRTIMER_RESTART; + } + spin_unlock_irqrestore(&base->lock, flags); + + return ret; + +} + +ktime_t alarm_expires_remaining(const struct alarm *alarm) +{ + struct alarm_base *base = &alarm_bases[alarm->type]; + return ktime_sub(alarm->node.expires, base->gettime()); +} +EXPORT_SYMBOL_GPL(alarm_expires_remaining); + +#ifdef CONFIG_RTC_CLASS +/** + * alarmtimer_suspend - Suspend time callback + * @dev: unused + * @state: unused + * + * When we are going into suspend, we look through the bases + * to see which is the soonest timer to expire. We then + * set an rtc timer to fire that far into the future, which + * will wake us from suspend. + */ +static int alarmtimer_suspend(struct device *dev) +{ + struct rtc_time tm; + ktime_t min, now; + unsigned long flags; + struct rtc_device *rtc; + int i; + int ret; + + spin_lock_irqsave(&freezer_delta_lock, flags); + min = freezer_delta; + freezer_delta = ktime_set(0, 0); + spin_unlock_irqrestore(&freezer_delta_lock, flags); + + rtc = alarmtimer_get_rtcdev(); + /* If we have no rtcdev, just return */ + if (!rtc) + return 0; + + /* Find the soonest timer to expire*/ + for (i = 0; i < ALARM_NUMTYPE; i++) { + struct alarm_base *base = &alarm_bases[i]; + struct timerqueue_node *next; + ktime_t delta; + + spin_lock_irqsave(&base->lock, flags); + next = timerqueue_getnext(&base->timerqueue); + spin_unlock_irqrestore(&base->lock, flags); + if (!next) + continue; + delta = ktime_sub(next->expires, base->gettime()); + if (!min.tv64 || (delta.tv64 < min.tv64)) + min = delta; + } + if (min.tv64 == 0) + return 0; + + if (ktime_to_ns(min) < 2 * NSEC_PER_SEC) { + __pm_wakeup_event(ws, 2 * MSEC_PER_SEC); + return -EBUSY; + } + + /* Setup an rtc timer to fire that far in the future */ + rtc_timer_cancel(rtc, &rtctimer); + rtc_read_time(rtc, &tm); + now = rtc_tm_to_ktime(tm); + now = ktime_add(now, min); + + /* Set alarm, if in the past reject suspend briefly to handle */ + ret = rtc_timer_start(rtc, &rtctimer, now, ktime_set(0, 0)); + if (ret < 0) + __pm_wakeup_event(ws, MSEC_PER_SEC); + return ret; +} +#else +static int alarmtimer_suspend(struct device *dev) +{ + return 0; +} +#endif + +static void alarmtimer_freezerset(ktime_t absexp, enum alarmtimer_type type) +{ + ktime_t delta; + unsigned long flags; + struct alarm_base *base = &alarm_bases[type]; + + delta = ktime_sub(absexp, base->gettime()); + + spin_lock_irqsave(&freezer_delta_lock, flags); + if (!freezer_delta.tv64 || (delta.tv64 < freezer_delta.tv64)) + freezer_delta = delta; + spin_unlock_irqrestore(&freezer_delta_lock, flags); +} + + +/** + * alarm_init - Initialize an alarm structure + * @alarm: ptr to alarm to be initialized + * @type: the type of the alarm + * @function: callback that is run when the alarm fires + */ +void alarm_init(struct alarm *alarm, enum alarmtimer_type type, + enum alarmtimer_restart (*function)(struct alarm *, ktime_t)) +{ + timerqueue_init(&alarm->node); + hrtimer_init(&alarm->timer, alarm_bases[type].base_clockid, + HRTIMER_MODE_ABS); + alarm->timer.function = alarmtimer_fired; + alarm->function = function; + alarm->type = type; + alarm->state = ALARMTIMER_STATE_INACTIVE; +} +EXPORT_SYMBOL_GPL(alarm_init); + +/** + * alarm_start - Sets an absolute alarm to fire + * @alarm: ptr to alarm to set + * @start: time to run the alarm + */ +int alarm_start(struct alarm *alarm, ktime_t start) +{ + struct alarm_base *base = &alarm_bases[alarm->type]; + unsigned long flags; + int ret; + + spin_lock_irqsave(&base->lock, flags); + alarm->node.expires = start; + alarmtimer_enqueue(base, alarm); + ret = hrtimer_start(&alarm->timer, alarm->node.expires, + HRTIMER_MODE_ABS); + spin_unlock_irqrestore(&base->lock, flags); + return ret; +} +EXPORT_SYMBOL_GPL(alarm_start); + +/** + * alarm_start_relative - Sets a relative alarm to fire + * @alarm: ptr to alarm to set + * @start: time relative to now to run the alarm + */ +int alarm_start_relative(struct alarm *alarm, ktime_t start) +{ + struct alarm_base *base = &alarm_bases[alarm->type]; + + start = ktime_add(start, base->gettime()); + return alarm_start(alarm, start); +} +EXPORT_SYMBOL_GPL(alarm_start_relative); + +void alarm_restart(struct alarm *alarm) +{ + struct alarm_base *base = &alarm_bases[alarm->type]; + unsigned long flags; + + spin_lock_irqsave(&base->lock, flags); + hrtimer_set_expires(&alarm->timer, alarm->node.expires); + hrtimer_restart(&alarm->timer); + alarmtimer_enqueue(base, alarm); + spin_unlock_irqrestore(&base->lock, flags); +} +EXPORT_SYMBOL_GPL(alarm_restart); + +/** + * alarm_try_to_cancel - Tries to cancel an alarm timer + * @alarm: ptr to alarm to be canceled + * + * Returns 1 if the timer was canceled, 0 if it was not running, + * and -1 if the callback was running + */ +int alarm_try_to_cancel(struct alarm *alarm) +{ + struct alarm_base *base = &alarm_bases[alarm->type]; + unsigned long flags; + int ret; + + spin_lock_irqsave(&base->lock, flags); + ret = hrtimer_try_to_cancel(&alarm->timer); + if (ret >= 0) + alarmtimer_dequeue(base, alarm); + spin_unlock_irqrestore(&base->lock, flags); + return ret; +} +EXPORT_SYMBOL_GPL(alarm_try_to_cancel); + + +/** + * alarm_cancel - Spins trying to cancel an alarm timer until it is done + * @alarm: ptr to alarm to be canceled + * + * Returns 1 if the timer was canceled, 0 if it was not active. + */ +int alarm_cancel(struct alarm *alarm) +{ + for (;;) { + int ret = alarm_try_to_cancel(alarm); + if (ret >= 0) + return ret; + cpu_relax(); + } +} +EXPORT_SYMBOL_GPL(alarm_cancel); + + +u64 alarm_forward(struct alarm *alarm, ktime_t now, ktime_t interval) +{ + u64 overrun = 1; + ktime_t delta; + + delta = ktime_sub(now, alarm->node.expires); + + if (delta.tv64 < 0) + return 0; + + if (unlikely(delta.tv64 >= interval.tv64)) { + s64 incr = ktime_to_ns(interval); + + overrun = ktime_divns(delta, incr); + + alarm->node.expires = ktime_add_ns(alarm->node.expires, + incr*overrun); + + if (alarm->node.expires.tv64 > now.tv64) + return overrun; + /* + * This (and the ktime_add() below) is the + * correction for exact: + */ + overrun++; + } + + alarm->node.expires = ktime_add(alarm->node.expires, interval); + return overrun; +} +EXPORT_SYMBOL_GPL(alarm_forward); + +u64 alarm_forward_now(struct alarm *alarm, ktime_t interval) +{ + struct alarm_base *base = &alarm_bases[alarm->type]; + + return alarm_forward(alarm, base->gettime(), interval); +} +EXPORT_SYMBOL_GPL(alarm_forward_now); + + +/** + * clock2alarm - helper that converts from clockid to alarmtypes + * @clockid: clockid. + */ +static enum alarmtimer_type clock2alarm(clockid_t clockid) +{ + if (clockid == CLOCK_REALTIME_ALARM) + return ALARM_REALTIME; + if (clockid == CLOCK_BOOTTIME_ALARM) + return ALARM_BOOTTIME; + return -1; +} + +/** + * alarm_handle_timer - Callback for posix timers + * @alarm: alarm that fired + * + * Posix timer callback for expired alarm timers. + */ +static enum alarmtimer_restart alarm_handle_timer(struct alarm *alarm, + ktime_t now) +{ + unsigned long flags; + struct k_itimer *ptr = container_of(alarm, struct k_itimer, + it.alarm.alarmtimer); + enum alarmtimer_restart result = ALARMTIMER_NORESTART; + + spin_lock_irqsave(&ptr->it_lock, flags); + if ((ptr->it_sigev_notify & ~SIGEV_THREAD_ID) != SIGEV_NONE) { + if (posix_timer_event(ptr, 0) != 0) + ptr->it_overrun++; + } + + /* Re-add periodic timers */ + if (ptr->it.alarm.interval.tv64) { + ptr->it_overrun += alarm_forward(alarm, now, + ptr->it.alarm.interval); + result = ALARMTIMER_RESTART; + } + spin_unlock_irqrestore(&ptr->it_lock, flags); + + return result; +} + +/** + * alarm_clock_getres - posix getres interface + * @which_clock: clockid + * @tp: timespec to fill + * + * Returns the granularity of underlying alarm base clock + */ +static int alarm_clock_getres(const clockid_t which_clock, struct timespec *tp) +{ + clockid_t baseid = alarm_bases[clock2alarm(which_clock)].base_clockid; + + if (!alarmtimer_get_rtcdev()) + return -EINVAL; + + return hrtimer_get_res(baseid, tp); +} + +/** + * alarm_clock_get - posix clock_get interface + * @which_clock: clockid + * @tp: timespec to fill. + * + * Provides the underlying alarm base time. + */ +static int alarm_clock_get(clockid_t which_clock, struct timespec *tp) +{ + struct alarm_base *base = &alarm_bases[clock2alarm(which_clock)]; + + if (!alarmtimer_get_rtcdev()) + return -EINVAL; + + *tp = ktime_to_timespec(base->gettime()); + return 0; +} + +/** + * alarm_timer_create - posix timer_create interface + * @new_timer: k_itimer pointer to manage + * + * Initializes the k_itimer structure. + */ +static int alarm_timer_create(struct k_itimer *new_timer) +{ + enum alarmtimer_type type; + struct alarm_base *base; + + if (!alarmtimer_get_rtcdev()) + return -ENOTSUPP; + + if (!capable(CAP_WAKE_ALARM)) + return -EPERM; + + type = clock2alarm(new_timer->it_clock); + base = &alarm_bases[type]; + alarm_init(&new_timer->it.alarm.alarmtimer, type, alarm_handle_timer); + return 0; +} + +/** + * alarm_timer_get - posix timer_get interface + * @new_timer: k_itimer pointer + * @cur_setting: itimerspec data to fill + * + * Copies out the current itimerspec data + */ +static void alarm_timer_get(struct k_itimer *timr, + struct itimerspec *cur_setting) +{ + ktime_t relative_expiry_time = + alarm_expires_remaining(&(timr->it.alarm.alarmtimer)); + + if (ktime_to_ns(relative_expiry_time) > 0) { + cur_setting->it_value = ktime_to_timespec(relative_expiry_time); + } else { + cur_setting->it_value.tv_sec = 0; + cur_setting->it_value.tv_nsec = 0; + } + + cur_setting->it_interval = ktime_to_timespec(timr->it.alarm.interval); +} + +/** + * alarm_timer_del - posix timer_del interface + * @timr: k_itimer pointer to be deleted + * + * Cancels any programmed alarms for the given timer. + */ +static int alarm_timer_del(struct k_itimer *timr) +{ + if (!rtcdev) + return -ENOTSUPP; + + if (alarm_try_to_cancel(&timr->it.alarm.alarmtimer) < 0) + return TIMER_RETRY; + + return 0; +} + +/** + * alarm_timer_set - posix timer_set interface + * @timr: k_itimer pointer to be deleted + * @flags: timer flags + * @new_setting: itimerspec to be used + * @old_setting: itimerspec being replaced + * + * Sets the timer to new_setting, and starts the timer. + */ +static int alarm_timer_set(struct k_itimer *timr, int flags, + struct itimerspec *new_setting, + struct itimerspec *old_setting) +{ + ktime_t exp; + + if (!rtcdev) + return -ENOTSUPP; + + if (flags & ~TIMER_ABSTIME) + return -EINVAL; + + if (old_setting) + alarm_timer_get(timr, old_setting); + + /* If the timer was already set, cancel it */ + if (alarm_try_to_cancel(&timr->it.alarm.alarmtimer) < 0) + return TIMER_RETRY; + + /* start the timer */ + timr->it.alarm.interval = timespec_to_ktime(new_setting->it_interval); + exp = timespec_to_ktime(new_setting->it_value); + /* Convert (if necessary) to absolute time */ + if (flags != TIMER_ABSTIME) { + ktime_t now; + + now = alarm_bases[timr->it.alarm.alarmtimer.type].gettime(); + exp = ktime_add(now, exp); + } + + alarm_start(&timr->it.alarm.alarmtimer, exp); + return 0; +} + +/** + * alarmtimer_nsleep_wakeup - Wakeup function for alarm_timer_nsleep + * @alarm: ptr to alarm that fired + * + * Wakes up the task that set the alarmtimer + */ +static enum alarmtimer_restart alarmtimer_nsleep_wakeup(struct alarm *alarm, + ktime_t now) +{ + struct task_struct *task = (struct task_struct *)alarm->data; + + alarm->data = NULL; + if (task) + wake_up_process(task); + return ALARMTIMER_NORESTART; +} + +/** + * alarmtimer_do_nsleep - Internal alarmtimer nsleep implementation + * @alarm: ptr to alarmtimer + * @absexp: absolute expiration time + * + * Sets the alarm timer and sleeps until it is fired or interrupted. + */ +static int alarmtimer_do_nsleep(struct alarm *alarm, ktime_t absexp) +{ + alarm->data = (void *)current; + do { + set_current_state(TASK_INTERRUPTIBLE); + alarm_start(alarm, absexp); + if (likely(alarm->data)) + schedule(); + + alarm_cancel(alarm); + } while (alarm->data && !signal_pending(current)); + + __set_current_state(TASK_RUNNING); + + return (alarm->data == NULL); +} + + +/** + * update_rmtp - Update remaining timespec value + * @exp: expiration time + * @type: timer type + * @rmtp: user pointer to remaining timepsec value + * + * Helper function that fills in rmtp value with time between + * now and the exp value + */ +static int update_rmtp(ktime_t exp, enum alarmtimer_type type, + struct timespec __user *rmtp) +{ + struct timespec rmt; + ktime_t rem; + + rem = ktime_sub(exp, alarm_bases[type].gettime()); + + if (rem.tv64 <= 0) + return 0; + rmt = ktime_to_timespec(rem); + + if (copy_to_user(rmtp, &rmt, sizeof(*rmtp))) + return -EFAULT; + + return 1; + +} + +/** + * alarm_timer_nsleep_restart - restartblock alarmtimer nsleep + * @restart: ptr to restart block + * + * Handles restarted clock_nanosleep calls + */ +static long __sched alarm_timer_nsleep_restart(struct restart_block *restart) +{ + enum alarmtimer_type type = restart->nanosleep.clockid; + ktime_t exp; + struct timespec __user *rmtp; + struct alarm alarm; + int ret = 0; + + exp.tv64 = restart->nanosleep.expires; + alarm_init(&alarm, type, alarmtimer_nsleep_wakeup); + + if (alarmtimer_do_nsleep(&alarm, exp)) + goto out; + + if (freezing(current)) + alarmtimer_freezerset(exp, type); + + rmtp = restart->nanosleep.rmtp; + if (rmtp) { + ret = update_rmtp(exp, type, rmtp); + if (ret <= 0) + goto out; + } + + + /* The other values in restart are already filled in */ + ret = -ERESTART_RESTARTBLOCK; +out: + return ret; +} + +/** + * alarm_timer_nsleep - alarmtimer nanosleep + * @which_clock: clockid + * @flags: determins abstime or relative + * @tsreq: requested sleep time (abs or rel) + * @rmtp: remaining sleep time saved + * + * Handles clock_nanosleep calls against _ALARM clockids + */ +static int alarm_timer_nsleep(const clockid_t which_clock, int flags, + struct timespec *tsreq, struct timespec __user *rmtp) +{ + enum alarmtimer_type type = clock2alarm(which_clock); + struct alarm alarm; + ktime_t exp; + int ret = 0; + struct restart_block *restart; + + if (!alarmtimer_get_rtcdev()) + return -ENOTSUPP; + + if (flags & ~TIMER_ABSTIME) + return -EINVAL; + + if (!capable(CAP_WAKE_ALARM)) + return -EPERM; + + alarm_init(&alarm, type, alarmtimer_nsleep_wakeup); + + exp = timespec_to_ktime(*tsreq); + /* Convert (if necessary) to absolute time */ + if (flags != TIMER_ABSTIME) { + ktime_t now = alarm_bases[type].gettime(); + exp = ktime_add(now, exp); + } + + if (alarmtimer_do_nsleep(&alarm, exp)) + goto out; + + if (freezing(current)) + alarmtimer_freezerset(exp, type); + + /* abs timers don't set remaining time or restart */ + if (flags == TIMER_ABSTIME) { + ret = -ERESTARTNOHAND; + goto out; + } + + if (rmtp) { + ret = update_rmtp(exp, type, rmtp); + if (ret <= 0) + goto out; + } + + restart = ¤t->restart_block; + restart->fn = alarm_timer_nsleep_restart; + restart->nanosleep.clockid = type; + restart->nanosleep.expires = exp.tv64; + restart->nanosleep.rmtp = rmtp; + ret = -ERESTART_RESTARTBLOCK; + +out: + return ret; +} + + +/* Suspend hook structures */ +static const struct dev_pm_ops alarmtimer_pm_ops = { + .suspend = alarmtimer_suspend, +}; + +static struct platform_driver alarmtimer_driver = { + .driver = { + .name = "alarmtimer", + .pm = &alarmtimer_pm_ops, + } +}; + +/** + * alarmtimer_init - Initialize alarm timer code + * + * This function initializes the alarm bases and registers + * the posix clock ids. + */ +static int __init alarmtimer_init(void) +{ + struct platform_device *pdev; + int error = 0; + int i; + struct k_clock alarm_clock = { + .clock_getres = alarm_clock_getres, + .clock_get = alarm_clock_get, + .timer_create = alarm_timer_create, + .timer_set = alarm_timer_set, + .timer_del = alarm_timer_del, + .timer_get = alarm_timer_get, + .nsleep = alarm_timer_nsleep, + }; + + alarmtimer_rtc_timer_init(); + + posix_timers_register_clock(CLOCK_REALTIME_ALARM, &alarm_clock); + posix_timers_register_clock(CLOCK_BOOTTIME_ALARM, &alarm_clock); + + /* Initialize alarm bases */ + alarm_bases[ALARM_REALTIME].base_clockid = CLOCK_REALTIME; + alarm_bases[ALARM_REALTIME].gettime = &ktime_get_real; + alarm_bases[ALARM_BOOTTIME].base_clockid = CLOCK_BOOTTIME; + alarm_bases[ALARM_BOOTTIME].gettime = &ktime_get_boottime; + for (i = 0; i < ALARM_NUMTYPE; i++) { + timerqueue_init_head(&alarm_bases[i].timerqueue); + spin_lock_init(&alarm_bases[i].lock); + } + + error = alarmtimer_rtc_interface_setup(); + if (error) + return error; + + error = platform_driver_register(&alarmtimer_driver); + if (error) + goto out_if; + + pdev = platform_device_register_simple("alarmtimer", -1, NULL, 0); + if (IS_ERR(pdev)) { + error = PTR_ERR(pdev); + goto out_drv; + } + ws = wakeup_source_register("alarmtimer"); + return 0; + +out_drv: + platform_driver_unregister(&alarmtimer_driver); +out_if: + alarmtimer_rtc_interface_remove(); + return error; +} +device_initcall(alarmtimer_init); diff --git a/kernel/kernel/time/clockevents.c b/kernel/kernel/time/clockevents.c new file mode 100644 index 000000000..637a09461 --- /dev/null +++ b/kernel/kernel/time/clockevents.c @@ -0,0 +1,792 @@ +/* + * linux/kernel/time/clockevents.c + * + * This file contains functions which manage clock event devices. + * + * Copyright(C) 2005-2006, Thomas Gleixner + * Copyright(C) 2005-2007, Red Hat, Inc., Ingo Molnar + * Copyright(C) 2006-2007, Timesys Corp., Thomas Gleixner + * + * This code is licenced under the GPL version 2. For details see + * kernel-base/COPYING. + */ + +#include +#include +#include +#include +#include +#include + +#include "tick-internal.h" + +/* The registered clock event devices */ +static LIST_HEAD(clockevent_devices); +static LIST_HEAD(clockevents_released); +/* Protection for the above */ +static DEFINE_RAW_SPINLOCK(clockevents_lock); +/* Protection for unbind operations */ +static DEFINE_MUTEX(clockevents_mutex); + +struct ce_unbind { + struct clock_event_device *ce; + int res; +}; + +static u64 cev_delta2ns(unsigned long latch, struct clock_event_device *evt, + bool ismax) +{ + u64 clc = (u64) latch << evt->shift; + u64 rnd; + + if (unlikely(!evt->mult)) { + evt->mult = 1; + WARN_ON(1); + } + rnd = (u64) evt->mult - 1; + + /* + * Upper bound sanity check. If the backwards conversion is + * not equal latch, we know that the above shift overflowed. + */ + if ((clc >> evt->shift) != (u64)latch) + clc = ~0ULL; + + /* + * Scaled math oddities: + * + * For mult <= (1 << shift) we can safely add mult - 1 to + * prevent integer rounding loss. So the backwards conversion + * from nsec to device ticks will be correct. + * + * For mult > (1 << shift), i.e. device frequency is > 1GHz we + * need to be careful. Adding mult - 1 will result in a value + * which when converted back to device ticks can be larger + * than latch by up to (mult - 1) >> shift. For the min_delta + * calculation we still want to apply this in order to stay + * above the minimum device ticks limit. For the upper limit + * we would end up with a latch value larger than the upper + * limit of the device, so we omit the add to stay below the + * device upper boundary. + * + * Also omit the add if it would overflow the u64 boundary. + */ + if ((~0ULL - clc > rnd) && + (!ismax || evt->mult <= (1ULL << evt->shift))) + clc += rnd; + + do_div(clc, evt->mult); + + /* Deltas less than 1usec are pointless noise */ + return clc > 1000 ? clc : 1000; +} + +/** + * clockevents_delta2ns - Convert a latch value (device ticks) to nanoseconds + * @latch: value to convert + * @evt: pointer to clock event device descriptor + * + * Math helper, returns latch value converted to nanoseconds (bound checked) + */ +u64 clockevent_delta2ns(unsigned long latch, struct clock_event_device *evt) +{ + return cev_delta2ns(latch, evt, false); +} +EXPORT_SYMBOL_GPL(clockevent_delta2ns); + +static int __clockevents_set_state(struct clock_event_device *dev, + enum clock_event_state state) +{ + /* Transition with legacy set_mode() callback */ + if (dev->set_mode) { + /* Legacy callback doesn't support new modes */ + if (state > CLOCK_EVT_STATE_ONESHOT) + return -ENOSYS; + /* + * 'clock_event_state' and 'clock_event_mode' have 1-to-1 + * mapping until *_ONESHOT, and so a simple cast will work. + */ + dev->set_mode((enum clock_event_mode)state, dev); + dev->mode = (enum clock_event_mode)state; + return 0; + } + + if (dev->features & CLOCK_EVT_FEAT_DUMMY) + return 0; + + /* Transition with new state-specific callbacks */ + switch (state) { + case CLOCK_EVT_STATE_DETACHED: + /* The clockevent device is getting replaced. Shut it down. */ + + case CLOCK_EVT_STATE_SHUTDOWN: + return dev->set_state_shutdown(dev); + + case CLOCK_EVT_STATE_PERIODIC: + /* Core internal bug */ + if (!(dev->features & CLOCK_EVT_FEAT_PERIODIC)) + return -ENOSYS; + return dev->set_state_periodic(dev); + + case CLOCK_EVT_STATE_ONESHOT: + /* Core internal bug */ + if (!(dev->features & CLOCK_EVT_FEAT_ONESHOT)) + return -ENOSYS; + return dev->set_state_oneshot(dev); + + default: + return -ENOSYS; + } +} + +/** + * clockevents_set_state - set the operating state of a clock event device + * @dev: device to modify + * @state: new state + * + * Must be called with interrupts disabled ! + */ +void clockevents_set_state(struct clock_event_device *dev, + enum clock_event_state state) +{ + if (dev->state != state) { + if (__clockevents_set_state(dev, state)) + return; + + dev->state = state; + + /* + * A nsec2cyc multiplicator of 0 is invalid and we'd crash + * on it, so fix it up and emit a warning: + */ + if (state == CLOCK_EVT_STATE_ONESHOT) { + if (unlikely(!dev->mult)) { + dev->mult = 1; + WARN_ON(1); + } + } + } +} + +/** + * clockevents_shutdown - shutdown the device and clear next_event + * @dev: device to shutdown + */ +void clockevents_shutdown(struct clock_event_device *dev) +{ + clockevents_set_state(dev, CLOCK_EVT_STATE_SHUTDOWN); + dev->next_event.tv64 = KTIME_MAX; +} + +/** + * clockevents_tick_resume - Resume the tick device before using it again + * @dev: device to resume + */ +int clockevents_tick_resume(struct clock_event_device *dev) +{ + int ret = 0; + + if (dev->set_mode) { + dev->set_mode(CLOCK_EVT_MODE_RESUME, dev); + dev->mode = CLOCK_EVT_MODE_RESUME; + } else if (dev->tick_resume) { + ret = dev->tick_resume(dev); + } + + return ret; +} + +#ifdef CONFIG_GENERIC_CLOCKEVENTS_MIN_ADJUST + +/* Limit min_delta to a jiffie */ +#define MIN_DELTA_LIMIT (NSEC_PER_SEC / HZ) + +/** + * clockevents_increase_min_delta - raise minimum delta of a clock event device + * @dev: device to increase the minimum delta + * + * Returns 0 on success, -ETIME when the minimum delta reached the limit. + */ +static int clockevents_increase_min_delta(struct clock_event_device *dev) +{ + /* Nothing to do if we already reached the limit */ + if (dev->min_delta_ns >= MIN_DELTA_LIMIT) { + printk_deferred(KERN_WARNING + "CE: Reprogramming failure. Giving up\n"); + dev->next_event.tv64 = KTIME_MAX; + return -ETIME; + } + + if (dev->min_delta_ns < 5000) + dev->min_delta_ns = 5000; + else + dev->min_delta_ns += dev->min_delta_ns >> 1; + + if (dev->min_delta_ns > MIN_DELTA_LIMIT) + dev->min_delta_ns = MIN_DELTA_LIMIT; + + printk_deferred(KERN_WARNING + "CE: %s increased min_delta_ns to %llu nsec\n", + dev->name ? dev->name : "?", + (unsigned long long) dev->min_delta_ns); + return 0; +} + +/** + * clockevents_program_min_delta - Set clock event device to the minimum delay. + * @dev: device to program + * + * Returns 0 on success, -ETIME when the retry loop failed. + */ +static int clockevents_program_min_delta(struct clock_event_device *dev) +{ + unsigned long long clc; + int64_t delta; + int i; + + for (i = 0;;) { + delta = dev->min_delta_ns; + dev->next_event = ktime_add_ns(ktime_get(), delta); + + if (dev->state == CLOCK_EVT_STATE_SHUTDOWN) + return 0; + + dev->retries++; + clc = ((unsigned long long) delta * dev->mult) >> dev->shift; + if (dev->set_next_event((unsigned long) clc, dev) == 0) + return 0; + + if (++i > 2) { + /* + * We tried 3 times to program the device with the + * given min_delta_ns. Try to increase the minimum + * delta, if that fails as well get out of here. + */ + if (clockevents_increase_min_delta(dev)) + return -ETIME; + i = 0; + } + } +} + +#else /* CONFIG_GENERIC_CLOCKEVENTS_MIN_ADJUST */ + +/** + * clockevents_program_min_delta - Set clock event device to the minimum delay. + * @dev: device to program + * + * Returns 0 on success, -ETIME when the retry loop failed. + */ +static int clockevents_program_min_delta(struct clock_event_device *dev) +{ + unsigned long long clc; + int64_t delta; + + delta = dev->min_delta_ns; + dev->next_event = ktime_add_ns(ktime_get(), delta); + + if (dev->state == CLOCK_EVT_STATE_SHUTDOWN) + return 0; + + dev->retries++; + clc = ((unsigned long long) delta * dev->mult) >> dev->shift; + return dev->set_next_event((unsigned long) clc, dev); +} + +#endif /* CONFIG_GENERIC_CLOCKEVENTS_MIN_ADJUST */ + +/** + * clockevents_program_event - Reprogram the clock event device. + * @dev: device to program + * @expires: absolute expiry time (monotonic clock) + * @force: program minimum delay if expires can not be set + * + * Returns 0 on success, -ETIME when the event is in the past. + */ +int clockevents_program_event(struct clock_event_device *dev, ktime_t expires, + bool force) +{ + unsigned long long clc; + int64_t delta; + int rc; + + if (unlikely(expires.tv64 < 0)) { + WARN_ON_ONCE(1); + return -ETIME; + } + + dev->next_event = expires; + + if (dev->state == CLOCK_EVT_STATE_SHUTDOWN) + return 0; + + /* Shortcut for clockevent devices that can deal with ktime. */ + if (dev->features & CLOCK_EVT_FEAT_KTIME) + return dev->set_next_ktime(expires, dev); + + delta = ktime_to_ns(ktime_sub(expires, ktime_get())); + if (delta <= 0) + return force ? clockevents_program_min_delta(dev) : -ETIME; + + delta = min(delta, (int64_t) dev->max_delta_ns); + delta = max(delta, (int64_t) dev->min_delta_ns); + + clc = ((unsigned long long) delta * dev->mult) >> dev->shift; + rc = dev->set_next_event((unsigned long) clc, dev); + + return (rc && force) ? clockevents_program_min_delta(dev) : rc; +} + +/* + * Called after a notify add to make devices available which were + * released from the notifier call. + */ +static void clockevents_notify_released(void) +{ + struct clock_event_device *dev; + + while (!list_empty(&clockevents_released)) { + dev = list_entry(clockevents_released.next, + struct clock_event_device, list); + list_del(&dev->list); + list_add(&dev->list, &clockevent_devices); + tick_check_new_device(dev); + } +} + +/* + * Try to install a replacement clock event device + */ +static int clockevents_replace(struct clock_event_device *ced) +{ + struct clock_event_device *dev, *newdev = NULL; + + list_for_each_entry(dev, &clockevent_devices, list) { + if (dev == ced || dev->state != CLOCK_EVT_STATE_DETACHED) + continue; + + if (!tick_check_replacement(newdev, dev)) + continue; + + if (!try_module_get(dev->owner)) + continue; + + if (newdev) + module_put(newdev->owner); + newdev = dev; + } + if (newdev) { + tick_install_replacement(newdev); + list_del_init(&ced->list); + } + return newdev ? 0 : -EBUSY; +} + +/* + * Called with clockevents_mutex and clockevents_lock held + */ +static int __clockevents_try_unbind(struct clock_event_device *ced, int cpu) +{ + /* Fast track. Device is unused */ + if (ced->state == CLOCK_EVT_STATE_DETACHED) { + list_del_init(&ced->list); + return 0; + } + + return ced == per_cpu(tick_cpu_device, cpu).evtdev ? -EAGAIN : -EBUSY; +} + +/* + * SMP function call to unbind a device + */ +static void __clockevents_unbind(void *arg) +{ + struct ce_unbind *cu = arg; + int res; + + raw_spin_lock(&clockevents_lock); + res = __clockevents_try_unbind(cu->ce, smp_processor_id()); + if (res == -EAGAIN) + res = clockevents_replace(cu->ce); + cu->res = res; + raw_spin_unlock(&clockevents_lock); +} + +/* + * Issues smp function call to unbind a per cpu device. Called with + * clockevents_mutex held. + */ +static int clockevents_unbind(struct clock_event_device *ced, int cpu) +{ + struct ce_unbind cu = { .ce = ced, .res = -ENODEV }; + + smp_call_function_single(cpu, __clockevents_unbind, &cu, 1); + return cu.res; +} + +/* + * Unbind a clockevents device. + */ +int clockevents_unbind_device(struct clock_event_device *ced, int cpu) +{ + int ret; + + mutex_lock(&clockevents_mutex); + ret = clockevents_unbind(ced, cpu); + mutex_unlock(&clockevents_mutex); + return ret; +} +EXPORT_SYMBOL_GPL(clockevents_unbind_device); + +/* Sanity check of state transition callbacks */ +static int clockevents_sanity_check(struct clock_event_device *dev) +{ + /* Legacy set_mode() callback */ + if (dev->set_mode) { + /* We shouldn't be supporting new modes now */ + WARN_ON(dev->set_state_periodic || dev->set_state_oneshot || + dev->set_state_shutdown || dev->tick_resume); + + BUG_ON(dev->mode != CLOCK_EVT_MODE_UNUSED); + return 0; + } + + if (dev->features & CLOCK_EVT_FEAT_DUMMY) + return 0; + + /* New state-specific callbacks */ + if (!dev->set_state_shutdown) + return -EINVAL; + + if ((dev->features & CLOCK_EVT_FEAT_PERIODIC) && + !dev->set_state_periodic) + return -EINVAL; + + if ((dev->features & CLOCK_EVT_FEAT_ONESHOT) && + !dev->set_state_oneshot) + return -EINVAL; + + return 0; +} + +/** + * clockevents_register_device - register a clock event device + * @dev: device to register + */ +void clockevents_register_device(struct clock_event_device *dev) +{ + unsigned long flags; + + BUG_ON(clockevents_sanity_check(dev)); + + /* Initialize state to DETACHED */ + dev->state = CLOCK_EVT_STATE_DETACHED; + + if (!dev->cpumask) { + WARN_ON(num_possible_cpus() > 1); + dev->cpumask = cpumask_of(smp_processor_id()); + } + + raw_spin_lock_irqsave(&clockevents_lock, flags); + + list_add(&dev->list, &clockevent_devices); + tick_check_new_device(dev); + clockevents_notify_released(); + + raw_spin_unlock_irqrestore(&clockevents_lock, flags); +} +EXPORT_SYMBOL_GPL(clockevents_register_device); + +void clockevents_config(struct clock_event_device *dev, u32 freq) +{ + u64 sec; + + if (!(dev->features & CLOCK_EVT_FEAT_ONESHOT)) + return; + + /* + * Calculate the maximum number of seconds we can sleep. Limit + * to 10 minutes for hardware which can program more than + * 32bit ticks so we still get reasonable conversion values. + */ + sec = dev->max_delta_ticks; + do_div(sec, freq); + if (!sec) + sec = 1; + else if (sec > 600 && dev->max_delta_ticks > UINT_MAX) + sec = 600; + + clockevents_calc_mult_shift(dev, freq, sec); + dev->min_delta_ns = cev_delta2ns(dev->min_delta_ticks, dev, false); + dev->max_delta_ns = cev_delta2ns(dev->max_delta_ticks, dev, true); +} + +/** + * clockevents_config_and_register - Configure and register a clock event device + * @dev: device to register + * @freq: The clock frequency + * @min_delta: The minimum clock ticks to program in oneshot mode + * @max_delta: The maximum clock ticks to program in oneshot mode + * + * min/max_delta can be 0 for devices which do not support oneshot mode. + */ +void clockevents_config_and_register(struct clock_event_device *dev, + u32 freq, unsigned long min_delta, + unsigned long max_delta) +{ + dev->min_delta_ticks = min_delta; + dev->max_delta_ticks = max_delta; + clockevents_config(dev, freq); + clockevents_register_device(dev); +} +EXPORT_SYMBOL_GPL(clockevents_config_and_register); + +int __clockevents_update_freq(struct clock_event_device *dev, u32 freq) +{ + clockevents_config(dev, freq); + + if (dev->state == CLOCK_EVT_STATE_ONESHOT) + return clockevents_program_event(dev, dev->next_event, false); + + if (dev->state == CLOCK_EVT_STATE_PERIODIC) + return __clockevents_set_state(dev, CLOCK_EVT_STATE_PERIODIC); + + return 0; +} + +/** + * clockevents_update_freq - Update frequency and reprogram a clock event device. + * @dev: device to modify + * @freq: new device frequency + * + * Reconfigure and reprogram a clock event device in oneshot + * mode. Must be called on the cpu for which the device delivers per + * cpu timer events. If called for the broadcast device the core takes + * care of serialization. + * + * Returns 0 on success, -ETIME when the event is in the past. + */ +int clockevents_update_freq(struct clock_event_device *dev, u32 freq) +{ + unsigned long flags; + int ret; + + local_irq_save(flags); + ret = tick_broadcast_update_freq(dev, freq); + if (ret == -ENODEV) + ret = __clockevents_update_freq(dev, freq); + local_irq_restore(flags); + return ret; +} + +/* + * Noop handler when we shut down an event device + */ +void clockevents_handle_noop(struct clock_event_device *dev) +{ +} + +/** + * clockevents_exchange_device - release and request clock devices + * @old: device to release (can be NULL) + * @new: device to request (can be NULL) + * + * Called from various tick functions with clockevents_lock held and + * interrupts disabled. + */ +void clockevents_exchange_device(struct clock_event_device *old, + struct clock_event_device *new) +{ + /* + * Caller releases a clock event device. We queue it into the + * released list and do a notify add later. + */ + if (old) { + module_put(old->owner); + clockevents_set_state(old, CLOCK_EVT_STATE_DETACHED); + list_del(&old->list); + list_add(&old->list, &clockevents_released); + } + + if (new) { + BUG_ON(new->state != CLOCK_EVT_STATE_DETACHED); + clockevents_shutdown(new); + } +} + +/** + * clockevents_suspend - suspend clock devices + */ +void clockevents_suspend(void) +{ + struct clock_event_device *dev; + + list_for_each_entry_reverse(dev, &clockevent_devices, list) + if (dev->suspend) + dev->suspend(dev); +} + +/** + * clockevents_resume - resume clock devices + */ +void clockevents_resume(void) +{ + struct clock_event_device *dev; + + list_for_each_entry(dev, &clockevent_devices, list) + if (dev->resume) + dev->resume(dev); +} + +#ifdef CONFIG_HOTPLUG_CPU +/** + * tick_cleanup_dead_cpu - Cleanup the tick and clockevents of a dead cpu + */ +void tick_cleanup_dead_cpu(int cpu) +{ + struct clock_event_device *dev, *tmp; + unsigned long flags; + + raw_spin_lock_irqsave(&clockevents_lock, flags); + + tick_shutdown_broadcast_oneshot(cpu); + tick_shutdown_broadcast(cpu); + tick_shutdown(cpu); + /* + * Unregister the clock event devices which were + * released from the users in the notify chain. + */ + list_for_each_entry_safe(dev, tmp, &clockevents_released, list) + list_del(&dev->list); + /* + * Now check whether the CPU has left unused per cpu devices + */ + list_for_each_entry_safe(dev, tmp, &clockevent_devices, list) { + if (cpumask_test_cpu(cpu, dev->cpumask) && + cpumask_weight(dev->cpumask) == 1 && + !tick_is_broadcast_device(dev)) { + BUG_ON(dev->state != CLOCK_EVT_STATE_DETACHED); + list_del(&dev->list); + } + } + raw_spin_unlock_irqrestore(&clockevents_lock, flags); +} +#endif + +#ifdef CONFIG_SYSFS +struct bus_type clockevents_subsys = { + .name = "clockevents", + .dev_name = "clockevent", +}; + +static DEFINE_PER_CPU(struct device, tick_percpu_dev); +static struct tick_device *tick_get_tick_dev(struct device *dev); + +static ssize_t sysfs_show_current_tick_dev(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct tick_device *td; + ssize_t count = 0; + + raw_spin_lock_irq(&clockevents_lock); + td = tick_get_tick_dev(dev); + if (td && td->evtdev) + count = snprintf(buf, PAGE_SIZE, "%s\n", td->evtdev->name); + raw_spin_unlock_irq(&clockevents_lock); + return count; +} +static DEVICE_ATTR(current_device, 0444, sysfs_show_current_tick_dev, NULL); + +/* We don't support the abomination of removable broadcast devices */ +static ssize_t sysfs_unbind_tick_dev(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + char name[CS_NAME_LEN]; + ssize_t ret = sysfs_get_uname(buf, name, count); + struct clock_event_device *ce; + + if (ret < 0) + return ret; + + ret = -ENODEV; + mutex_lock(&clockevents_mutex); + raw_spin_lock_irq(&clockevents_lock); + list_for_each_entry(ce, &clockevent_devices, list) { + if (!strcmp(ce->name, name)) { + ret = __clockevents_try_unbind(ce, dev->id); + break; + } + } + raw_spin_unlock_irq(&clockevents_lock); + /* + * We hold clockevents_mutex, so ce can't go away + */ + if (ret == -EAGAIN) + ret = clockevents_unbind(ce, dev->id); + mutex_unlock(&clockevents_mutex); + return ret ? ret : count; +} +static DEVICE_ATTR(unbind_device, 0200, NULL, sysfs_unbind_tick_dev); + +#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST +static struct device tick_bc_dev = { + .init_name = "broadcast", + .id = 0, + .bus = &clockevents_subsys, +}; + +static struct tick_device *tick_get_tick_dev(struct device *dev) +{ + return dev == &tick_bc_dev ? tick_get_broadcast_device() : + &per_cpu(tick_cpu_device, dev->id); +} + +static __init int tick_broadcast_init_sysfs(void) +{ + int err = device_register(&tick_bc_dev); + + if (!err) + err = device_create_file(&tick_bc_dev, &dev_attr_current_device); + return err; +} +#else +static struct tick_device *tick_get_tick_dev(struct device *dev) +{ + return &per_cpu(tick_cpu_device, dev->id); +} +static inline int tick_broadcast_init_sysfs(void) { return 0; } +#endif + +static int __init tick_init_sysfs(void) +{ + int cpu; + + for_each_possible_cpu(cpu) { + struct device *dev = &per_cpu(tick_percpu_dev, cpu); + int err; + + dev->id = cpu; + dev->bus = &clockevents_subsys; + err = device_register(dev); + if (!err) + err = device_create_file(dev, &dev_attr_current_device); + if (!err) + err = device_create_file(dev, &dev_attr_unbind_device); + if (err) + return err; + } + return tick_broadcast_init_sysfs(); +} + +static int __init clockevents_init_sysfs(void) +{ + int err = subsys_system_register(&clockevents_subsys, NULL); + + if (!err) + err = tick_init_sysfs(); + return err; +} +device_initcall(clockevents_init_sysfs); +#endif /* SYSFS */ diff --git a/kernel/kernel/time/clocksource.c b/kernel/kernel/time/clocksource.c new file mode 100644 index 000000000..15facb1b9 --- /dev/null +++ b/kernel/kernel/time/clocksource.c @@ -0,0 +1,1020 @@ +/* + * linux/kernel/time/clocksource.c + * + * This file contains the functions which manage clocksource drivers. + * + * Copyright (C) 2004, 2005 IBM, John Stultz (johnstul@us.ibm.com) + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. + * + * TODO WishList: + * o Allow clocksource drivers to be unregistered + */ + +#include +#include +#include +#include +#include /* for spin_unlock_irq() using preempt_count() m68k */ +#include +#include + +#include "tick-internal.h" +#include "timekeeping_internal.h" + +/** + * clocks_calc_mult_shift - calculate mult/shift factors for scaled math of clocks + * @mult: pointer to mult variable + * @shift: pointer to shift variable + * @from: frequency to convert from + * @to: frequency to convert to + * @maxsec: guaranteed runtime conversion range in seconds + * + * The function evaluates the shift/mult pair for the scaled math + * operations of clocksources and clockevents. + * + * @to and @from are frequency values in HZ. For clock sources @to is + * NSEC_PER_SEC == 1GHz and @from is the counter frequency. For clock + * event @to is the counter frequency and @from is NSEC_PER_SEC. + * + * The @maxsec conversion range argument controls the time frame in + * seconds which must be covered by the runtime conversion with the + * calculated mult and shift factors. This guarantees that no 64bit + * overflow happens when the input value of the conversion is + * multiplied with the calculated mult factor. Larger ranges may + * reduce the conversion accuracy by chosing smaller mult and shift + * factors. + */ +void +clocks_calc_mult_shift(u32 *mult, u32 *shift, u32 from, u32 to, u32 maxsec) +{ + u64 tmp; + u32 sft, sftacc= 32; + + /* + * Calculate the shift factor which is limiting the conversion + * range: + */ + tmp = ((u64)maxsec * from) >> 32; + while (tmp) { + tmp >>=1; + sftacc--; + } + + /* + * Find the conversion shift/mult pair which has the best + * accuracy and fits the maxsec conversion range: + */ + for (sft = 32; sft > 0; sft--) { + tmp = (u64) to << sft; + tmp += from / 2; + do_div(tmp, from); + if ((tmp >> sftacc) == 0) + break; + } + *mult = tmp; + *shift = sft; +} + +/*[Clocksource internal variables]--------- + * curr_clocksource: + * currently selected clocksource. + * clocksource_list: + * linked list with the registered clocksources + * clocksource_mutex: + * protects manipulations to curr_clocksource and the clocksource_list + * override_name: + * Name of the user-specified clocksource. + */ +static struct clocksource *curr_clocksource; +static LIST_HEAD(clocksource_list); +static DEFINE_MUTEX(clocksource_mutex); +static char override_name[CS_NAME_LEN]; +static int finished_booting; + +#ifdef CONFIG_CLOCKSOURCE_WATCHDOG +static void clocksource_watchdog_work(struct work_struct *work); +static void clocksource_select(void); + +static LIST_HEAD(watchdog_list); +static struct clocksource *watchdog; +static struct timer_list watchdog_timer; +static DECLARE_WORK(watchdog_work, clocksource_watchdog_work); +static DEFINE_SPINLOCK(watchdog_lock); +static int watchdog_running; +static atomic_t watchdog_reset_pending; + +static int clocksource_watchdog_kthread(void *data); +static void __clocksource_change_rating(struct clocksource *cs, int rating); + +/* + * Interval: 0.5sec Threshold: 0.0625s + */ +#define WATCHDOG_INTERVAL (HZ >> 1) +#define WATCHDOG_THRESHOLD (NSEC_PER_SEC >> 4) + +static void clocksource_watchdog_work(struct work_struct *work) +{ + /* + * If kthread_run fails the next watchdog scan over the + * watchdog_list will find the unstable clock again. + */ + kthread_run(clocksource_watchdog_kthread, NULL, "kwatchdog"); +} + +static void __clocksource_unstable(struct clocksource *cs) +{ + cs->flags &= ~(CLOCK_SOURCE_VALID_FOR_HRES | CLOCK_SOURCE_WATCHDOG); + cs->flags |= CLOCK_SOURCE_UNSTABLE; + if (finished_booting) + schedule_work(&watchdog_work); +} + +/** + * clocksource_mark_unstable - mark clocksource unstable via watchdog + * @cs: clocksource to be marked unstable + * + * This function is called instead of clocksource_change_rating from + * cpu hotplug code to avoid a deadlock between the clocksource mutex + * and the cpu hotplug mutex. It defers the update of the clocksource + * to the watchdog thread. + */ +void clocksource_mark_unstable(struct clocksource *cs) +{ + unsigned long flags; + + spin_lock_irqsave(&watchdog_lock, flags); + if (!(cs->flags & CLOCK_SOURCE_UNSTABLE)) { + if (list_empty(&cs->wd_list)) + list_add(&cs->wd_list, &watchdog_list); + __clocksource_unstable(cs); + } + spin_unlock_irqrestore(&watchdog_lock, flags); +} + +static void clocksource_watchdog(unsigned long data) +{ + struct clocksource *cs; + cycle_t csnow, wdnow, cslast, wdlast, delta; + int64_t wd_nsec, cs_nsec; + int next_cpu, reset_pending; + + spin_lock(&watchdog_lock); + if (!watchdog_running) + goto out; + + reset_pending = atomic_read(&watchdog_reset_pending); + + list_for_each_entry(cs, &watchdog_list, wd_list) { + + /* Clocksource already marked unstable? */ + if (cs->flags & CLOCK_SOURCE_UNSTABLE) { + if (finished_booting) + schedule_work(&watchdog_work); + continue; + } + + local_irq_disable(); + csnow = cs->read(cs); + wdnow = watchdog->read(watchdog); + local_irq_enable(); + + /* Clocksource initialized ? */ + if (!(cs->flags & CLOCK_SOURCE_WATCHDOG) || + atomic_read(&watchdog_reset_pending)) { + cs->flags |= CLOCK_SOURCE_WATCHDOG; + cs->wd_last = wdnow; + cs->cs_last = csnow; + continue; + } + + delta = clocksource_delta(wdnow, cs->wd_last, watchdog->mask); + wd_nsec = clocksource_cyc2ns(delta, watchdog->mult, + watchdog->shift); + + delta = clocksource_delta(csnow, cs->cs_last, cs->mask); + cs_nsec = clocksource_cyc2ns(delta, cs->mult, cs->shift); + wdlast = cs->wd_last; /* save these in case we print them */ + cslast = cs->cs_last; + cs->cs_last = csnow; + cs->wd_last = wdnow; + + if (atomic_read(&watchdog_reset_pending)) + continue; + + /* Check the deviation from the watchdog clocksource. */ + if ((abs(cs_nsec - wd_nsec) > WATCHDOG_THRESHOLD)) { + pr_warn("timekeeping watchdog: Marking clocksource '%s' as unstable, because the skew is too large:\n", cs->name); + pr_warn(" '%s' wd_now: %llx wd_last: %llx mask: %llx\n", + watchdog->name, wdnow, wdlast, watchdog->mask); + pr_warn(" '%s' cs_now: %llx cs_last: %llx mask: %llx\n", + cs->name, csnow, cslast, cs->mask); + __clocksource_unstable(cs); + continue; + } + + if (!(cs->flags & CLOCK_SOURCE_VALID_FOR_HRES) && + (cs->flags & CLOCK_SOURCE_IS_CONTINUOUS) && + (watchdog->flags & CLOCK_SOURCE_IS_CONTINUOUS)) { + /* Mark it valid for high-res. */ + cs->flags |= CLOCK_SOURCE_VALID_FOR_HRES; + + /* + * clocksource_done_booting() will sort it if + * finished_booting is not set yet. + */ + if (!finished_booting) + continue; + + /* + * If this is not the current clocksource let + * the watchdog thread reselect it. Due to the + * change to high res this clocksource might + * be preferred now. If it is the current + * clocksource let the tick code know about + * that change. + */ + if (cs != curr_clocksource) { + cs->flags |= CLOCK_SOURCE_RESELECT; + schedule_work(&watchdog_work); + } else { + tick_clock_notify(); + } + } + } + + /* + * We only clear the watchdog_reset_pending, when we did a + * full cycle through all clocksources. + */ + if (reset_pending) + atomic_dec(&watchdog_reset_pending); + + /* + * Cycle through CPUs to check if the CPUs stay synchronized + * to each other. + */ + next_cpu = cpumask_next(raw_smp_processor_id(), cpu_online_mask); + if (next_cpu >= nr_cpu_ids) + next_cpu = cpumask_first(cpu_online_mask); + watchdog_timer.expires += WATCHDOG_INTERVAL; + add_timer_on(&watchdog_timer, next_cpu); +out: + spin_unlock(&watchdog_lock); +} + +static inline void clocksource_start_watchdog(void) +{ + if (watchdog_running || !watchdog || list_empty(&watchdog_list)) + return; + init_timer(&watchdog_timer); + watchdog_timer.function = clocksource_watchdog; + watchdog_timer.expires = jiffies + WATCHDOG_INTERVAL; + add_timer_on(&watchdog_timer, cpumask_first(cpu_online_mask)); + watchdog_running = 1; +} + +static inline void clocksource_stop_watchdog(void) +{ + if (!watchdog_running || (watchdog && !list_empty(&watchdog_list))) + return; + del_timer(&watchdog_timer); + watchdog_running = 0; +} + +static inline void clocksource_reset_watchdog(void) +{ + struct clocksource *cs; + + list_for_each_entry(cs, &watchdog_list, wd_list) + cs->flags &= ~CLOCK_SOURCE_WATCHDOG; +} + +static void clocksource_resume_watchdog(void) +{ + atomic_inc(&watchdog_reset_pending); +} + +static void clocksource_enqueue_watchdog(struct clocksource *cs) +{ + unsigned long flags; + + spin_lock_irqsave(&watchdog_lock, flags); + if (cs->flags & CLOCK_SOURCE_MUST_VERIFY) { + /* cs is a clocksource to be watched. */ + list_add(&cs->wd_list, &watchdog_list); + cs->flags &= ~CLOCK_SOURCE_WATCHDOG; + } else { + /* cs is a watchdog. */ + if (cs->flags & CLOCK_SOURCE_IS_CONTINUOUS) + cs->flags |= CLOCK_SOURCE_VALID_FOR_HRES; + /* Pick the best watchdog. */ + if (!watchdog || cs->rating > watchdog->rating) { + watchdog = cs; + /* Reset watchdog cycles */ + clocksource_reset_watchdog(); + } + } + /* Check if the watchdog timer needs to be started. */ + clocksource_start_watchdog(); + spin_unlock_irqrestore(&watchdog_lock, flags); +} + +static void clocksource_dequeue_watchdog(struct clocksource *cs) +{ + unsigned long flags; + + spin_lock_irqsave(&watchdog_lock, flags); + if (cs != watchdog) { + if (cs->flags & CLOCK_SOURCE_MUST_VERIFY) { + /* cs is a watched clocksource. */ + list_del_init(&cs->wd_list); + /* Check if the watchdog timer needs to be stopped. */ + clocksource_stop_watchdog(); + } + } + spin_unlock_irqrestore(&watchdog_lock, flags); +} + +static int __clocksource_watchdog_kthread(void) +{ + struct clocksource *cs, *tmp; + unsigned long flags; + LIST_HEAD(unstable); + int select = 0; + + spin_lock_irqsave(&watchdog_lock, flags); + list_for_each_entry_safe(cs, tmp, &watchdog_list, wd_list) { + if (cs->flags & CLOCK_SOURCE_UNSTABLE) { + list_del_init(&cs->wd_list); + list_add(&cs->wd_list, &unstable); + select = 1; + } + if (cs->flags & CLOCK_SOURCE_RESELECT) { + cs->flags &= ~CLOCK_SOURCE_RESELECT; + select = 1; + } + } + /* Check if the watchdog timer needs to be stopped. */ + clocksource_stop_watchdog(); + spin_unlock_irqrestore(&watchdog_lock, flags); + + /* Needs to be done outside of watchdog lock */ + list_for_each_entry_safe(cs, tmp, &unstable, wd_list) { + list_del_init(&cs->wd_list); + __clocksource_change_rating(cs, 0); + } + return select; +} + +static int clocksource_watchdog_kthread(void *data) +{ + mutex_lock(&clocksource_mutex); + if (__clocksource_watchdog_kthread()) + clocksource_select(); + mutex_unlock(&clocksource_mutex); + return 0; +} + +static bool clocksource_is_watchdog(struct clocksource *cs) +{ + return cs == watchdog; +} + +#else /* CONFIG_CLOCKSOURCE_WATCHDOG */ + +static void clocksource_enqueue_watchdog(struct clocksource *cs) +{ + if (cs->flags & CLOCK_SOURCE_IS_CONTINUOUS) + cs->flags |= CLOCK_SOURCE_VALID_FOR_HRES; +} + +static inline void clocksource_dequeue_watchdog(struct clocksource *cs) { } +static inline void clocksource_resume_watchdog(void) { } +static inline int __clocksource_watchdog_kthread(void) { return 0; } +static bool clocksource_is_watchdog(struct clocksource *cs) { return false; } +void clocksource_mark_unstable(struct clocksource *cs) { } + +#endif /* CONFIG_CLOCKSOURCE_WATCHDOG */ + +/** + * clocksource_suspend - suspend the clocksource(s) + */ +void clocksource_suspend(void) +{ + struct clocksource *cs; + + list_for_each_entry_reverse(cs, &clocksource_list, list) + if (cs->suspend) + cs->suspend(cs); +} + +/** + * clocksource_resume - resume the clocksource(s) + */ +void clocksource_resume(void) +{ + struct clocksource *cs; + + list_for_each_entry(cs, &clocksource_list, list) + if (cs->resume) + cs->resume(cs); + + clocksource_resume_watchdog(); +} + +/** + * clocksource_touch_watchdog - Update watchdog + * + * Update the watchdog after exception contexts such as kgdb so as not + * to incorrectly trip the watchdog. This might fail when the kernel + * was stopped in code which holds watchdog_lock. + */ +void clocksource_touch_watchdog(void) +{ + clocksource_resume_watchdog(); +} + +/** + * clocksource_max_adjustment- Returns max adjustment amount + * @cs: Pointer to clocksource + * + */ +static u32 clocksource_max_adjustment(struct clocksource *cs) +{ + u64 ret; + /* + * We won't try to correct for more than 11% adjustments (110,000 ppm), + */ + ret = (u64)cs->mult * 11; + do_div(ret,100); + return (u32)ret; +} + +/** + * clocks_calc_max_nsecs - Returns maximum nanoseconds that can be converted + * @mult: cycle to nanosecond multiplier + * @shift: cycle to nanosecond divisor (power of two) + * @maxadj: maximum adjustment value to mult (~11%) + * @mask: bitmask for two's complement subtraction of non 64 bit counters + * @max_cyc: maximum cycle value before potential overflow (does not include + * any safety margin) + * + * NOTE: This function includes a safety margin of 50%, in other words, we + * return half the number of nanoseconds the hardware counter can technically + * cover. This is done so that we can potentially detect problems caused by + * delayed timers or bad hardware, which might result in time intervals that + * are larger then what the math used can handle without overflows. + */ +u64 clocks_calc_max_nsecs(u32 mult, u32 shift, u32 maxadj, u64 mask, u64 *max_cyc) +{ + u64 max_nsecs, max_cycles; + + /* + * Calculate the maximum number of cycles that we can pass to the + * cyc2ns() function without overflowing a 64-bit result. + */ + max_cycles = ULLONG_MAX; + do_div(max_cycles, mult+maxadj); + + /* + * The actual maximum number of cycles we can defer the clocksource is + * determined by the minimum of max_cycles and mask. + * Note: Here we subtract the maxadj to make sure we don't sleep for + * too long if there's a large negative adjustment. + */ + max_cycles = min(max_cycles, mask); + max_nsecs = clocksource_cyc2ns(max_cycles, mult - maxadj, shift); + + /* return the max_cycles value as well if requested */ + if (max_cyc) + *max_cyc = max_cycles; + + /* Return 50% of the actual maximum, so we can detect bad values */ + max_nsecs >>= 1; + + return max_nsecs; +} + +/** + * clocksource_update_max_deferment - Updates the clocksource max_idle_ns & max_cycles + * @cs: Pointer to clocksource to be updated + * + */ +static inline void clocksource_update_max_deferment(struct clocksource *cs) +{ + cs->max_idle_ns = clocks_calc_max_nsecs(cs->mult, cs->shift, + cs->maxadj, cs->mask, + &cs->max_cycles); +} + +#ifndef CONFIG_ARCH_USES_GETTIMEOFFSET + +static struct clocksource *clocksource_find_best(bool oneshot, bool skipcur) +{ + struct clocksource *cs; + + if (!finished_booting || list_empty(&clocksource_list)) + return NULL; + + /* + * We pick the clocksource with the highest rating. If oneshot + * mode is active, we pick the highres valid clocksource with + * the best rating. + */ + list_for_each_entry(cs, &clocksource_list, list) { + if (skipcur && cs == curr_clocksource) + continue; + if (oneshot && !(cs->flags & CLOCK_SOURCE_VALID_FOR_HRES)) + continue; + return cs; + } + return NULL; +} + +static void __clocksource_select(bool skipcur) +{ + bool oneshot = tick_oneshot_mode_active(); + struct clocksource *best, *cs; + + /* Find the best suitable clocksource */ + best = clocksource_find_best(oneshot, skipcur); + if (!best) + return; + + /* Check for the override clocksource. */ + list_for_each_entry(cs, &clocksource_list, list) { + if (skipcur && cs == curr_clocksource) + continue; + if (strcmp(cs->name, override_name) != 0) + continue; + /* + * Check to make sure we don't switch to a non-highres + * capable clocksource if the tick code is in oneshot + * mode (highres or nohz) + */ + if (!(cs->flags & CLOCK_SOURCE_VALID_FOR_HRES) && oneshot) { + /* Override clocksource cannot be used. */ + printk(KERN_WARNING "Override clocksource %s is not " + "HRT compatible. Cannot switch while in " + "HRT/NOHZ mode\n", cs->name); + override_name[0] = 0; + } else + /* Override clocksource can be used. */ + best = cs; + break; + } + + if (curr_clocksource != best && !timekeeping_notify(best)) { + pr_info("Switched to clocksource %s\n", best->name); + curr_clocksource = best; + } +} + +/** + * clocksource_select - Select the best clocksource available + * + * Private function. Must hold clocksource_mutex when called. + * + * Select the clocksource with the best rating, or the clocksource, + * which is selected by userspace override. + */ +static void clocksource_select(void) +{ + return __clocksource_select(false); +} + +static void clocksource_select_fallback(void) +{ + return __clocksource_select(true); +} + +#else /* !CONFIG_ARCH_USES_GETTIMEOFFSET */ + +static inline void clocksource_select(void) { } +static inline void clocksource_select_fallback(void) { } + +#endif + +/* + * clocksource_done_booting - Called near the end of core bootup + * + * Hack to avoid lots of clocksource churn at boot time. + * We use fs_initcall because we want this to start before + * device_initcall but after subsys_initcall. + */ +static int __init clocksource_done_booting(void) +{ + mutex_lock(&clocksource_mutex); + curr_clocksource = clocksource_default_clock(); + finished_booting = 1; + /* + * Run the watchdog first to eliminate unstable clock sources + */ + __clocksource_watchdog_kthread(); + clocksource_select(); + mutex_unlock(&clocksource_mutex); + return 0; +} +fs_initcall(clocksource_done_booting); + +/* + * Enqueue the clocksource sorted by rating + */ +static void clocksource_enqueue(struct clocksource *cs) +{ + struct list_head *entry = &clocksource_list; + struct clocksource *tmp; + + list_for_each_entry(tmp, &clocksource_list, list) + /* Keep track of the place, where to insert */ + if (tmp->rating >= cs->rating) + entry = &tmp->list; + list_add(&cs->list, entry); +} + +/** + * __clocksource_update_freq_scale - Used update clocksource with new freq + * @cs: clocksource to be registered + * @scale: Scale factor multiplied against freq to get clocksource hz + * @freq: clocksource frequency (cycles per second) divided by scale + * + * This should only be called from the clocksource->enable() method. + * + * This *SHOULD NOT* be called directly! Please use the + * __clocksource_update_freq_hz() or __clocksource_update_freq_khz() helper + * functions. + */ +void __clocksource_update_freq_scale(struct clocksource *cs, u32 scale, u32 freq) +{ + u64 sec; + + /* + * Default clocksources are *special* and self-define their mult/shift. + * But, you're not special, so you should specify a freq value. + */ + if (freq) { + /* + * Calc the maximum number of seconds which we can run before + * wrapping around. For clocksources which have a mask > 32-bit + * we need to limit the max sleep time to have a good + * conversion precision. 10 minutes is still a reasonable + * amount. That results in a shift value of 24 for a + * clocksource with mask >= 40-bit and f >= 4GHz. That maps to + * ~ 0.06ppm granularity for NTP. + */ + sec = cs->mask; + do_div(sec, freq); + do_div(sec, scale); + if (!sec) + sec = 1; + else if (sec > 600 && cs->mask > UINT_MAX) + sec = 600; + + clocks_calc_mult_shift(&cs->mult, &cs->shift, freq, + NSEC_PER_SEC / scale, sec * scale); + } + /* + * Ensure clocksources that have large 'mult' values don't overflow + * when adjusted. + */ + cs->maxadj = clocksource_max_adjustment(cs); + while (freq && ((cs->mult + cs->maxadj < cs->mult) + || (cs->mult - cs->maxadj > cs->mult))) { + cs->mult >>= 1; + cs->shift--; + cs->maxadj = clocksource_max_adjustment(cs); + } + + /* + * Only warn for *special* clocksources that self-define + * their mult/shift values and don't specify a freq. + */ + WARN_ONCE(cs->mult + cs->maxadj < cs->mult, + "timekeeping: Clocksource %s might overflow on 11%% adjustment\n", + cs->name); + + clocksource_update_max_deferment(cs); + + pr_info("clocksource %s: mask: 0x%llx max_cycles: 0x%llx, max_idle_ns: %lld ns\n", + cs->name, cs->mask, cs->max_cycles, cs->max_idle_ns); +} +EXPORT_SYMBOL_GPL(__clocksource_update_freq_scale); + +/** + * __clocksource_register_scale - Used to install new clocksources + * @cs: clocksource to be registered + * @scale: Scale factor multiplied against freq to get clocksource hz + * @freq: clocksource frequency (cycles per second) divided by scale + * + * Returns -EBUSY if registration fails, zero otherwise. + * + * This *SHOULD NOT* be called directly! Please use the + * clocksource_register_hz() or clocksource_register_khz helper functions. + */ +int __clocksource_register_scale(struct clocksource *cs, u32 scale, u32 freq) +{ + + /* Initialize mult/shift and max_idle_ns */ + __clocksource_update_freq_scale(cs, scale, freq); + + /* Add clocksource to the clocksource list */ + mutex_lock(&clocksource_mutex); + clocksource_enqueue(cs); + clocksource_enqueue_watchdog(cs); + clocksource_select(); + mutex_unlock(&clocksource_mutex); + return 0; +} +EXPORT_SYMBOL_GPL(__clocksource_register_scale); + +static void __clocksource_change_rating(struct clocksource *cs, int rating) +{ + list_del(&cs->list); + cs->rating = rating; + clocksource_enqueue(cs); +} + +/** + * clocksource_change_rating - Change the rating of a registered clocksource + * @cs: clocksource to be changed + * @rating: new rating + */ +void clocksource_change_rating(struct clocksource *cs, int rating) +{ + mutex_lock(&clocksource_mutex); + __clocksource_change_rating(cs, rating); + clocksource_select(); + mutex_unlock(&clocksource_mutex); +} +EXPORT_SYMBOL(clocksource_change_rating); + +/* + * Unbind clocksource @cs. Called with clocksource_mutex held + */ +static int clocksource_unbind(struct clocksource *cs) +{ + /* + * I really can't convince myself to support this on hardware + * designed by lobotomized monkeys. + */ + if (clocksource_is_watchdog(cs)) + return -EBUSY; + + if (cs == curr_clocksource) { + /* Select and try to install a replacement clock source */ + clocksource_select_fallback(); + if (curr_clocksource == cs) + return -EBUSY; + } + clocksource_dequeue_watchdog(cs); + list_del_init(&cs->list); + return 0; +} + +/** + * clocksource_unregister - remove a registered clocksource + * @cs: clocksource to be unregistered + */ +int clocksource_unregister(struct clocksource *cs) +{ + int ret = 0; + + mutex_lock(&clocksource_mutex); + if (!list_empty(&cs->list)) + ret = clocksource_unbind(cs); + mutex_unlock(&clocksource_mutex); + return ret; +} +EXPORT_SYMBOL(clocksource_unregister); + +#ifdef CONFIG_SYSFS +/** + * sysfs_show_current_clocksources - sysfs interface for current clocksource + * @dev: unused + * @attr: unused + * @buf: char buffer to be filled with clocksource list + * + * Provides sysfs interface for listing current clocksource. + */ +static ssize_t +sysfs_show_current_clocksources(struct device *dev, + struct device_attribute *attr, char *buf) +{ + ssize_t count = 0; + + mutex_lock(&clocksource_mutex); + count = snprintf(buf, PAGE_SIZE, "%s\n", curr_clocksource->name); + mutex_unlock(&clocksource_mutex); + + return count; +} + +ssize_t sysfs_get_uname(const char *buf, char *dst, size_t cnt) +{ + size_t ret = cnt; + + /* strings from sysfs write are not 0 terminated! */ + if (!cnt || cnt >= CS_NAME_LEN) + return -EINVAL; + + /* strip of \n: */ + if (buf[cnt-1] == '\n') + cnt--; + if (cnt > 0) + memcpy(dst, buf, cnt); + dst[cnt] = 0; + return ret; +} + +/** + * sysfs_override_clocksource - interface for manually overriding clocksource + * @dev: unused + * @attr: unused + * @buf: name of override clocksource + * @count: length of buffer + * + * Takes input from sysfs interface for manually overriding the default + * clocksource selection. + */ +static ssize_t sysfs_override_clocksource(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + ssize_t ret; + + mutex_lock(&clocksource_mutex); + + ret = sysfs_get_uname(buf, override_name, count); + if (ret >= 0) + clocksource_select(); + + mutex_unlock(&clocksource_mutex); + + return ret; +} + +/** + * sysfs_unbind_current_clocksource - interface for manually unbinding clocksource + * @dev: unused + * @attr: unused + * @buf: unused + * @count: length of buffer + * + * Takes input from sysfs interface for manually unbinding a clocksource. + */ +static ssize_t sysfs_unbind_clocksource(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct clocksource *cs; + char name[CS_NAME_LEN]; + ssize_t ret; + + ret = sysfs_get_uname(buf, name, count); + if (ret < 0) + return ret; + + ret = -ENODEV; + mutex_lock(&clocksource_mutex); + list_for_each_entry(cs, &clocksource_list, list) { + if (strcmp(cs->name, name)) + continue; + ret = clocksource_unbind(cs); + break; + } + mutex_unlock(&clocksource_mutex); + + return ret ? ret : count; +} + +/** + * sysfs_show_available_clocksources - sysfs interface for listing clocksource + * @dev: unused + * @attr: unused + * @buf: char buffer to be filled with clocksource list + * + * Provides sysfs interface for listing registered clocksources + */ +static ssize_t +sysfs_show_available_clocksources(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct clocksource *src; + ssize_t count = 0; + + mutex_lock(&clocksource_mutex); + list_for_each_entry(src, &clocksource_list, list) { + /* + * Don't show non-HRES clocksource if the tick code is + * in one shot mode (highres=on or nohz=on) + */ + if (!tick_oneshot_mode_active() || + (src->flags & CLOCK_SOURCE_VALID_FOR_HRES)) + count += snprintf(buf + count, + max((ssize_t)PAGE_SIZE - count, (ssize_t)0), + "%s ", src->name); + } + mutex_unlock(&clocksource_mutex); + + count += snprintf(buf + count, + max((ssize_t)PAGE_SIZE - count, (ssize_t)0), "\n"); + + return count; +} + +/* + * Sysfs setup bits: + */ +static DEVICE_ATTR(current_clocksource, 0644, sysfs_show_current_clocksources, + sysfs_override_clocksource); + +static DEVICE_ATTR(unbind_clocksource, 0200, NULL, sysfs_unbind_clocksource); + +static DEVICE_ATTR(available_clocksource, 0444, + sysfs_show_available_clocksources, NULL); + +static struct bus_type clocksource_subsys = { + .name = "clocksource", + .dev_name = "clocksource", +}; + +static struct device device_clocksource = { + .id = 0, + .bus = &clocksource_subsys, +}; + +static int __init init_clocksource_sysfs(void) +{ + int error = subsys_system_register(&clocksource_subsys, NULL); + + if (!error) + error = device_register(&device_clocksource); + if (!error) + error = device_create_file( + &device_clocksource, + &dev_attr_current_clocksource); + if (!error) + error = device_create_file(&device_clocksource, + &dev_attr_unbind_clocksource); + if (!error) + error = device_create_file( + &device_clocksource, + &dev_attr_available_clocksource); + return error; +} + +device_initcall(init_clocksource_sysfs); +#endif /* CONFIG_SYSFS */ + +/** + * boot_override_clocksource - boot clock override + * @str: override name + * + * Takes a clocksource= boot argument and uses it + * as the clocksource override name. + */ +static int __init boot_override_clocksource(char* str) +{ + mutex_lock(&clocksource_mutex); + if (str) + strlcpy(override_name, str, sizeof(override_name)); + mutex_unlock(&clocksource_mutex); + return 1; +} + +__setup("clocksource=", boot_override_clocksource); + +/** + * boot_override_clock - Compatibility layer for deprecated boot option + * @str: override name + * + * DEPRECATED! Takes a clock= boot argument and uses it + * as the clocksource override name + */ +static int __init boot_override_clock(char* str) +{ + if (!strcmp(str, "pmtmr")) { + printk("Warning: clock=pmtmr is deprecated. " + "Use clocksource=acpi_pm.\n"); + return boot_override_clocksource("acpi_pm"); + } + printk("Warning! clock= boot option is deprecated. " + "Use clocksource=xyz\n"); + return boot_override_clocksource(str); +} + +__setup("clock=", boot_override_clock); diff --git a/kernel/kernel/time/hrtimer.c b/kernel/kernel/time/hrtimer.c new file mode 100644 index 000000000..2c6be169b --- /dev/null +++ b/kernel/kernel/time/hrtimer.c @@ -0,0 +1,2140 @@ +/* + * linux/kernel/hrtimer.c + * + * Copyright(C) 2005-2006, Thomas Gleixner + * Copyright(C) 2005-2007, Red Hat, Inc., Ingo Molnar + * Copyright(C) 2006-2007 Timesys Corp., Thomas Gleixner + * + * High-resolution kernel timers + * + * In contrast to the low-resolution timeout API implemented in + * kernel/timer.c, hrtimers provide finer resolution and accuracy + * depending on system configuration and capabilities. + * + * These timers are currently used for: + * - itimers + * - POSIX timers + * - nanosleep + * - precise in-kernel timing + * + * Started by: Thomas Gleixner and Ingo Molnar + * + * Credits: + * based on kernel/timer.c + * + * Help, testing, suggestions, bugfixes, improvements were + * provided by: + * + * George Anzinger, Andrew Morton, Steven Rostedt, Roman Zippel + * et. al. + * + * For licencing details see kernel-base/COPYING + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +#include +#include + +#include "tick-internal.h" + +/* + * The timer bases: + * + * There are more clockids then hrtimer bases. Thus, we index + * into the timer bases by the hrtimer_base_type enum. When trying + * to reach a base using a clockid, hrtimer_clockid_to_base() + * is used to convert from clockid to the proper hrtimer_base_type. + */ +DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) = +{ + + .lock = __RAW_SPIN_LOCK_UNLOCKED(hrtimer_bases.lock), + .clock_base = + { + { + .index = HRTIMER_BASE_MONOTONIC, + .clockid = CLOCK_MONOTONIC, + .get_time = &ktime_get, + .resolution = KTIME_LOW_RES, + }, + { + .index = HRTIMER_BASE_REALTIME, + .clockid = CLOCK_REALTIME, + .get_time = &ktime_get_real, + .resolution = KTIME_LOW_RES, + }, + { + .index = HRTIMER_BASE_BOOTTIME, + .clockid = CLOCK_BOOTTIME, + .get_time = &ktime_get_boottime, + .resolution = KTIME_LOW_RES, + }, + { + .index = HRTIMER_BASE_TAI, + .clockid = CLOCK_TAI, + .get_time = &ktime_get_clocktai, + .resolution = KTIME_LOW_RES, + }, + } +}; + +static const int hrtimer_clock_to_base_table[MAX_CLOCKS] = { + [CLOCK_REALTIME] = HRTIMER_BASE_REALTIME, + [CLOCK_MONOTONIC] = HRTIMER_BASE_MONOTONIC, + [CLOCK_BOOTTIME] = HRTIMER_BASE_BOOTTIME, + [CLOCK_TAI] = HRTIMER_BASE_TAI, +}; + +static inline int hrtimer_clockid_to_base(clockid_t clock_id) +{ + return hrtimer_clock_to_base_table[clock_id]; +} + + +/* + * Get the coarse grained time at the softirq based on xtime and + * wall_to_monotonic. + */ +static void hrtimer_get_softirq_time(struct hrtimer_cpu_base *base) +{ + ktime_t xtim, mono, boot, tai; + ktime_t off_real, off_boot, off_tai; + + mono = ktime_get_update_offsets_tick(&off_real, &off_boot, &off_tai); + boot = ktime_add(mono, off_boot); + xtim = ktime_add(mono, off_real); + tai = ktime_add(mono, off_tai); + + base->clock_base[HRTIMER_BASE_REALTIME].softirq_time = xtim; + base->clock_base[HRTIMER_BASE_MONOTONIC].softirq_time = mono; + base->clock_base[HRTIMER_BASE_BOOTTIME].softirq_time = boot; + base->clock_base[HRTIMER_BASE_TAI].softirq_time = tai; +} + +/* + * Functions and macros which are different for UP/SMP systems are kept in a + * single place + */ +#ifdef CONFIG_SMP + +/* + * We are using hashed locking: holding per_cpu(hrtimer_bases)[n].lock + * means that all timers which are tied to this base via timer->base are + * locked, and the base itself is locked too. + * + * So __run_timers/migrate_timers can safely modify all timers which could + * be found on the lists/queues. + * + * When the timer's base is locked, and the timer removed from list, it is + * possible to set timer->base = NULL and drop the lock: the timer remains + * locked. + */ +static +struct hrtimer_clock_base *lock_hrtimer_base(const struct hrtimer *timer, + unsigned long *flags) +{ + struct hrtimer_clock_base *base; + + for (;;) { + base = timer->base; + if (likely(base != NULL)) { + raw_spin_lock_irqsave(&base->cpu_base->lock, *flags); + if (likely(base == timer->base)) + return base; + /* The timer has migrated to another CPU: */ + raw_spin_unlock_irqrestore(&base->cpu_base->lock, *flags); + } + cpu_relax(); + } +} + +/* + * With HIGHRES=y we do not migrate the timer when it is expiring + * before the next event on the target cpu because we cannot reprogram + * the target cpu hardware and we would cause it to fire late. + * + * Called with cpu_base->lock of target cpu held. + */ +static int +hrtimer_check_target(struct hrtimer *timer, struct hrtimer_clock_base *new_base) +{ +#ifdef CONFIG_HIGH_RES_TIMERS + ktime_t expires; + + if (!new_base->cpu_base->hres_active) + return 0; + + expires = ktime_sub(hrtimer_get_expires(timer), new_base->offset); + return expires.tv64 <= new_base->cpu_base->expires_next.tv64; +#else + return 0; +#endif +} + +/* + * Switch the timer base to the current CPU when possible. + */ +static inline struct hrtimer_clock_base * +switch_hrtimer_base(struct hrtimer *timer, struct hrtimer_clock_base *base, + int pinned) +{ + struct hrtimer_clock_base *new_base; + struct hrtimer_cpu_base *new_cpu_base; + int this_cpu = smp_processor_id(); + int cpu = get_nohz_timer_target(pinned); + int basenum = base->index; + +again: + new_cpu_base = &per_cpu(hrtimer_bases, cpu); + new_base = &new_cpu_base->clock_base[basenum]; + + if (base != new_base) { + /* + * We are trying to move timer to new_base. + * However we can't change timer's base while it is running, + * so we keep it on the same CPU. No hassle vs. reprogramming + * the event source in the high resolution case. The softirq + * code will take care of this when the timer function has + * completed. There is no conflict as we hold the lock until + * the timer is enqueued. + */ + if (unlikely(hrtimer_callback_running(timer))) + return base; + + /* See the comment in lock_timer_base() */ + timer->base = NULL; + raw_spin_unlock(&base->cpu_base->lock); + raw_spin_lock(&new_base->cpu_base->lock); + + if (cpu != this_cpu && hrtimer_check_target(timer, new_base)) { + cpu = this_cpu; + raw_spin_unlock(&new_base->cpu_base->lock); + raw_spin_lock(&base->cpu_base->lock); + timer->base = base; + goto again; + } + timer->base = new_base; + } else { + if (cpu != this_cpu && hrtimer_check_target(timer, new_base)) { + cpu = this_cpu; + goto again; + } + } + return new_base; +} + +#else /* CONFIG_SMP */ + +static inline struct hrtimer_clock_base * +lock_hrtimer_base(const struct hrtimer *timer, unsigned long *flags) +{ + struct hrtimer_clock_base *base = timer->base; + + raw_spin_lock_irqsave(&base->cpu_base->lock, *flags); + + return base; +} + +# define switch_hrtimer_base(t, b, p) (b) + +#endif /* !CONFIG_SMP */ + +/* + * Functions for the union type storage format of ktime_t which are + * too large for inlining: + */ +#if BITS_PER_LONG < 64 +/* + * Divide a ktime value by a nanosecond value + */ +s64 __ktime_divns(const ktime_t kt, s64 div) +{ + int sft = 0; + s64 dclc; + u64 tmp; + + dclc = ktime_to_ns(kt); + tmp = dclc < 0 ? -dclc : dclc; + + /* Make sure the divisor is less than 2^32: */ + while (div >> 32) { + sft++; + div >>= 1; + } + tmp >>= sft; + do_div(tmp, (unsigned long) div); + return dclc < 0 ? -tmp : tmp; +} +EXPORT_SYMBOL_GPL(__ktime_divns); +#endif /* BITS_PER_LONG >= 64 */ + +/* + * Add two ktime values and do a safety check for overflow: + */ +ktime_t ktime_add_safe(const ktime_t lhs, const ktime_t rhs) +{ + ktime_t res = ktime_add(lhs, rhs); + + /* + * We use KTIME_SEC_MAX here, the maximum timeout which we can + * return to user space in a timespec: + */ + if (res.tv64 < 0 || res.tv64 < lhs.tv64 || res.tv64 < rhs.tv64) + res = ktime_set(KTIME_SEC_MAX, 0); + + return res; +} + +EXPORT_SYMBOL_GPL(ktime_add_safe); + +#ifdef CONFIG_DEBUG_OBJECTS_TIMERS + +static struct debug_obj_descr hrtimer_debug_descr; + +static void *hrtimer_debug_hint(void *addr) +{ + return ((struct hrtimer *) addr)->function; +} + +/* + * fixup_init is called when: + * - an active object is initialized + */ +static int hrtimer_fixup_init(void *addr, enum debug_obj_state state) +{ + struct hrtimer *timer = addr; + + switch (state) { + case ODEBUG_STATE_ACTIVE: + hrtimer_cancel(timer); + debug_object_init(timer, &hrtimer_debug_descr); + return 1; + default: + return 0; + } +} + +/* + * fixup_activate is called when: + * - an active object is activated + * - an unknown object is activated (might be a statically initialized object) + */ +static int hrtimer_fixup_activate(void *addr, enum debug_obj_state state) +{ + switch (state) { + + case ODEBUG_STATE_NOTAVAILABLE: + WARN_ON_ONCE(1); + return 0; + + case ODEBUG_STATE_ACTIVE: + WARN_ON(1); + + default: + return 0; + } +} + +/* + * fixup_free is called when: + * - an active object is freed + */ +static int hrtimer_fixup_free(void *addr, enum debug_obj_state state) +{ + struct hrtimer *timer = addr; + + switch (state) { + case ODEBUG_STATE_ACTIVE: + hrtimer_cancel(timer); + debug_object_free(timer, &hrtimer_debug_descr); + return 1; + default: + return 0; + } +} + +static struct debug_obj_descr hrtimer_debug_descr = { + .name = "hrtimer", + .debug_hint = hrtimer_debug_hint, + .fixup_init = hrtimer_fixup_init, + .fixup_activate = hrtimer_fixup_activate, + .fixup_free = hrtimer_fixup_free, +}; + +static inline void debug_hrtimer_init(struct hrtimer *timer) +{ + debug_object_init(timer, &hrtimer_debug_descr); +} + +static inline void debug_hrtimer_activate(struct hrtimer *timer) +{ + debug_object_activate(timer, &hrtimer_debug_descr); +} + +static inline void debug_hrtimer_deactivate(struct hrtimer *timer) +{ + debug_object_deactivate(timer, &hrtimer_debug_descr); +} + +static inline void debug_hrtimer_free(struct hrtimer *timer) +{ + debug_object_free(timer, &hrtimer_debug_descr); +} + +static void __hrtimer_init(struct hrtimer *timer, clockid_t clock_id, + enum hrtimer_mode mode); + +void hrtimer_init_on_stack(struct hrtimer *timer, clockid_t clock_id, + enum hrtimer_mode mode) +{ + debug_object_init_on_stack(timer, &hrtimer_debug_descr); + __hrtimer_init(timer, clock_id, mode); +} +EXPORT_SYMBOL_GPL(hrtimer_init_on_stack); + +void destroy_hrtimer_on_stack(struct hrtimer *timer) +{ + debug_object_free(timer, &hrtimer_debug_descr); +} + +#else +static inline void debug_hrtimer_init(struct hrtimer *timer) { } +static inline void debug_hrtimer_activate(struct hrtimer *timer) { } +static inline void debug_hrtimer_deactivate(struct hrtimer *timer) { } +#endif + +static inline void +debug_init(struct hrtimer *timer, clockid_t clockid, + enum hrtimer_mode mode) +{ + debug_hrtimer_init(timer); + trace_hrtimer_init(timer, clockid, mode); +} + +static inline void debug_activate(struct hrtimer *timer) +{ + debug_hrtimer_activate(timer); + trace_hrtimer_start(timer); +} + +static inline void debug_deactivate(struct hrtimer *timer) +{ + debug_hrtimer_deactivate(timer); + trace_hrtimer_cancel(timer); +} + +#if defined(CONFIG_NO_HZ_COMMON) || defined(CONFIG_HIGH_RES_TIMERS) +static ktime_t __hrtimer_get_next_event(struct hrtimer_cpu_base *cpu_base) +{ + struct hrtimer_clock_base *base = cpu_base->clock_base; + ktime_t expires, expires_next = { .tv64 = KTIME_MAX }; + int i; + + for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++, base++) { + struct timerqueue_node *next; + struct hrtimer *timer; + + next = timerqueue_getnext(&base->active); + if (!next) + continue; + + timer = container_of(next, struct hrtimer, node); + expires = ktime_sub(hrtimer_get_expires(timer), base->offset); + if (expires.tv64 < expires_next.tv64) + expires_next = expires; + } + /* + * clock_was_set() might have changed base->offset of any of + * the clock bases so the result might be negative. Fix it up + * to prevent a false positive in clockevents_program_event(). + */ + if (expires_next.tv64 < 0) + expires_next.tv64 = 0; + return expires_next; +} +#endif + +/* High resolution timer related functions */ +#ifdef CONFIG_HIGH_RES_TIMERS + +/* + * High resolution timer enabled ? + */ +static int hrtimer_hres_enabled __read_mostly = 1; + +/* + * Enable / Disable high resolution mode + */ +static int __init setup_hrtimer_hres(char *str) +{ + if (!strcmp(str, "off")) + hrtimer_hres_enabled = 0; + else if (!strcmp(str, "on")) + hrtimer_hres_enabled = 1; + else + return 0; + return 1; +} + +__setup("highres=", setup_hrtimer_hres); + +/* + * hrtimer_high_res_enabled - query, if the highres mode is enabled + */ +static inline int hrtimer_is_hres_enabled(void) +{ + return hrtimer_hres_enabled; +} + +/* + * Is the high resolution mode active ? + */ +static inline int hrtimer_hres_active(void) +{ + return __this_cpu_read(hrtimer_bases.hres_active); +} + +/* + * Reprogram the event source with checking both queues for the + * next event + * Called with interrupts disabled and base->lock held + */ +static void +hrtimer_force_reprogram(struct hrtimer_cpu_base *cpu_base, int skip_equal) +{ + ktime_t expires_next = __hrtimer_get_next_event(cpu_base); + + if (skip_equal && expires_next.tv64 == cpu_base->expires_next.tv64) + return; + + cpu_base->expires_next.tv64 = expires_next.tv64; + + /* + * If a hang was detected in the last timer interrupt then we + * leave the hang delay active in the hardware. We want the + * system to make progress. That also prevents the following + * scenario: + * T1 expires 50ms from now + * T2 expires 5s from now + * + * T1 is removed, so this code is called and would reprogram + * the hardware to 5s from now. Any hrtimer_start after that + * will not reprogram the hardware due to hang_detected being + * set. So we'd effectivly block all timers until the T2 event + * fires. + */ + if (cpu_base->hang_detected) + return; + + if (cpu_base->expires_next.tv64 != KTIME_MAX) + tick_program_event(cpu_base->expires_next, 1); +} + +/* + * Shared reprogramming for clock_realtime and clock_monotonic + * + * When a timer is enqueued and expires earlier than the already enqueued + * timers, we have to check, whether it expires earlier than the timer for + * which the clock event device was armed. + * + * Note, that in case the state has HRTIMER_STATE_CALLBACK set, no reprogramming + * and no expiry check happens. The timer gets enqueued into the rbtree. The + * reprogramming and expiry check is done in the hrtimer_interrupt or in the + * softirq. + * + * Called with interrupts disabled and base->cpu_base.lock held + */ +static int hrtimer_reprogram(struct hrtimer *timer, + struct hrtimer_clock_base *base) +{ + struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases); + ktime_t expires = ktime_sub(hrtimer_get_expires(timer), base->offset); + int res; + + WARN_ON_ONCE(hrtimer_get_expires_tv64(timer) < 0); + + /* + * When the callback is running, we do not reprogram the clock event + * device. The timer callback is either running on a different CPU or + * the callback is executed in the hrtimer_interrupt context. The + * reprogramming is handled at the end of the hrtimer_interrupt. + */ + if (hrtimer_callback_running(timer)) + return 0; + + /* + * CLOCK_REALTIME timer might be requested with an absolute + * expiry time which is less than base->offset. Nothing wrong + * about that, just avoid to call into the tick code, which + * has now objections against negative expiry values. + */ + if (expires.tv64 < 0) + return -ETIME; + + if (expires.tv64 >= cpu_base->expires_next.tv64) + return 0; + + /* + * When the target cpu of the timer is currently executing + * hrtimer_interrupt(), then we do not touch the clock event + * device. hrtimer_interrupt() will reevaluate all clock bases + * before reprogramming the device. + */ + if (cpu_base->in_hrtirq) + return 0; + + /* + * If a hang was detected in the last timer interrupt then we + * do not schedule a timer which is earlier than the expiry + * which we enforced in the hang detection. We want the system + * to make progress. + */ + if (cpu_base->hang_detected) + return 0; + + /* + * Clockevents returns -ETIME, when the event was in the past. + */ + res = tick_program_event(expires, 0); + if (!IS_ERR_VALUE(res)) + cpu_base->expires_next = expires; + return res; +} + +static void __run_hrtimer(struct hrtimer *timer, ktime_t *now); +static int hrtimer_rt_defer(struct hrtimer *timer); + +/* + * Initialize the high resolution related parts of cpu_base + */ +static inline void hrtimer_init_hres(struct hrtimer_cpu_base *base) +{ + base->expires_next.tv64 = KTIME_MAX; + base->hres_active = 0; +} + +static inline int hrtimer_enqueue_reprogram(struct hrtimer *timer, + struct hrtimer_clock_base *base, + int wakeup) +{ + if (!hrtimer_reprogram(timer, base)) + return 0; + if (!wakeup) + return -ETIME; +#ifdef CONFIG_PREEMPT_RT_BASE + if (!hrtimer_rt_defer(timer)) + return -ETIME; +#endif + return 1; +} + +static inline ktime_t hrtimer_update_base(struct hrtimer_cpu_base *base) +{ + ktime_t *offs_real = &base->clock_base[HRTIMER_BASE_REALTIME].offset; + ktime_t *offs_boot = &base->clock_base[HRTIMER_BASE_BOOTTIME].offset; + ktime_t *offs_tai = &base->clock_base[HRTIMER_BASE_TAI].offset; + + return ktime_get_update_offsets_now(offs_real, offs_boot, offs_tai); +} + +/* + * Retrigger next event is called after clock was set + * + * Called with interrupts disabled via on_each_cpu() + */ +static void retrigger_next_event(void *arg) +{ + struct hrtimer_cpu_base *base = this_cpu_ptr(&hrtimer_bases); + + if (!hrtimer_hres_active()) + return; + + raw_spin_lock(&base->lock); + hrtimer_update_base(base); + hrtimer_force_reprogram(base, 0); + raw_spin_unlock(&base->lock); +} + +/* + * Switch to high resolution mode + */ +static int hrtimer_switch_to_hres(void) +{ + int i, cpu = smp_processor_id(); + struct hrtimer_cpu_base *base = &per_cpu(hrtimer_bases, cpu); + unsigned long flags; + + if (base->hres_active) + return 1; + + local_irq_save(flags); + + if (tick_init_highres()) { + local_irq_restore(flags); + printk(KERN_WARNING "Could not switch to high resolution " + "mode on CPU %d\n", cpu); + return 0; + } + base->hres_active = 1; + for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) + base->clock_base[i].resolution = KTIME_HIGH_RES; + + tick_setup_sched_timer(); + /* "Retrigger" the interrupt to get things going */ + retrigger_next_event(NULL); + local_irq_restore(flags); + return 1; +} + +static void clock_was_set_work(struct work_struct *work) +{ + clock_was_set(); +} + +static DECLARE_WORK(hrtimer_work, clock_was_set_work); + +#ifdef CONFIG_PREEMPT_RT_FULL +/* + * RT can not call schedule_work from real interrupt context. + * Need to make a thread to do the real work. + */ +static struct task_struct *clock_set_delay_thread; +static bool do_clock_set_delay; + +static int run_clock_set_delay(void *ignore) +{ + while (!kthread_should_stop()) { + set_current_state(TASK_INTERRUPTIBLE); + if (do_clock_set_delay) { + do_clock_set_delay = false; + schedule_work(&hrtimer_work); + } + schedule(); + } + __set_current_state(TASK_RUNNING); + return 0; +} + +void clock_was_set_delayed(void) +{ + do_clock_set_delay = true; + /* Make visible before waking up process */ + smp_wmb(); + wake_up_process(clock_set_delay_thread); +} + +static __init int create_clock_set_delay_thread(void) +{ + clock_set_delay_thread = kthread_run(run_clock_set_delay, NULL, "kclksetdelayd"); + BUG_ON(!clock_set_delay_thread); + return 0; +} +early_initcall(create_clock_set_delay_thread); +#else /* PREEMPT_RT_FULL */ +/* + * Called from timekeeping and resume code to reprogramm the hrtimer + * interrupt device on all cpus. + */ +void clock_was_set_delayed(void) +{ + schedule_work(&hrtimer_work); +} +#endif + +#else + +static inline int hrtimer_hres_active(void) { return 0; } +static inline int hrtimer_is_hres_enabled(void) { return 0; } +static inline int hrtimer_switch_to_hres(void) { return 0; } +static inline void +hrtimer_force_reprogram(struct hrtimer_cpu_base *base, int skip_equal) { } +static inline int hrtimer_enqueue_reprogram(struct hrtimer *timer, + struct hrtimer_clock_base *base, + int wakeup) +{ + return 0; +} + +static inline int hrtimer_reprogram(struct hrtimer *timer, + struct hrtimer_clock_base *base) +{ + return 0; +} +static inline void hrtimer_init_hres(struct hrtimer_cpu_base *base) { } +static inline void retrigger_next_event(void *arg) { } +#endif /* CONFIG_HIGH_RES_TIMERS */ + +/* + * Clock realtime was set + * + * Change the offset of the realtime clock vs. the monotonic + * clock. + * + * We might have to reprogram the high resolution timer interrupt. On + * SMP we call the architecture specific code to retrigger _all_ high + * resolution timer interrupts. On UP we just disable interrupts and + * call the high resolution interrupt code. + */ +void clock_was_set(void) +{ +#ifdef CONFIG_HIGH_RES_TIMERS + /* Retrigger the CPU local events everywhere */ + on_each_cpu(retrigger_next_event, NULL, 1); +#endif + timerfd_clock_was_set(); +} + +/* + * During resume we might have to reprogram the high resolution timer + * interrupt on all online CPUs. However, all other CPUs will be + * stopped with IRQs interrupts disabled so the clock_was_set() call + * must be deferred. + */ +void hrtimers_resume(void) +{ + WARN_ONCE(!irqs_disabled(), + KERN_INFO "hrtimers_resume() called with IRQs enabled!"); + + /* Retrigger on the local CPU */ + retrigger_next_event(NULL); + /* And schedule a retrigger for all others */ + clock_was_set_delayed(); +} + +static inline void timer_stats_hrtimer_set_start_info(struct hrtimer *timer) +{ +#ifdef CONFIG_TIMER_STATS + if (timer->start_site) + return; + timer->start_site = __builtin_return_address(0); + memcpy(timer->start_comm, current->comm, TASK_COMM_LEN); + timer->start_pid = current->pid; +#endif +} + +static inline void timer_stats_hrtimer_clear_start_info(struct hrtimer *timer) +{ +#ifdef CONFIG_TIMER_STATS + timer->start_site = NULL; +#endif +} + +static inline void timer_stats_account_hrtimer(struct hrtimer *timer) +{ +#ifdef CONFIG_TIMER_STATS + if (likely(!timer_stats_active)) + return; + timer_stats_update_stats(timer, timer->start_pid, timer->start_site, + timer->function, timer->start_comm, 0); +#endif +} + +/* + * Counterpart to lock_hrtimer_base above: + */ +static inline +void unlock_hrtimer_base(const struct hrtimer *timer, unsigned long *flags) +{ + raw_spin_unlock_irqrestore(&timer->base->cpu_base->lock, *flags); +} + +/** + * hrtimer_forward - forward the timer expiry + * @timer: hrtimer to forward + * @now: forward past this time + * @interval: the interval to forward + * + * Forward the timer expiry so it will expire in the future. + * Returns the number of overruns. + */ +u64 hrtimer_forward(struct hrtimer *timer, ktime_t now, ktime_t interval) +{ + u64 orun = 1; + ktime_t delta; + + delta = ktime_sub(now, hrtimer_get_expires(timer)); + + if (delta.tv64 < 0) + return 0; + + if (interval.tv64 < timer->base->resolution.tv64) + interval.tv64 = timer->base->resolution.tv64; + + if (unlikely(delta.tv64 >= interval.tv64)) { + s64 incr = ktime_to_ns(interval); + + orun = ktime_divns(delta, incr); + hrtimer_add_expires_ns(timer, incr * orun); + if (hrtimer_get_expires_tv64(timer) > now.tv64) + return orun; + /* + * This (and the ktime_add() below) is the + * correction for exact: + */ + orun++; + } + hrtimer_add_expires(timer, interval); + + return orun; +} +EXPORT_SYMBOL_GPL(hrtimer_forward); + +#ifdef CONFIG_PREEMPT_RT_BASE +# define wake_up_timer_waiters(b) wake_up(&(b)->wait) + +/** + * hrtimer_wait_for_timer - Wait for a running timer + * + * @timer: timer to wait for + * + * The function waits in case the timers callback function is + * currently executed on the waitqueue of the timer base. The + * waitqueue is woken up after the timer callback function has + * finished execution. + */ +void hrtimer_wait_for_timer(const struct hrtimer *timer) +{ + struct hrtimer_clock_base *base = timer->base; + + if (base && base->cpu_base && !timer->irqsafe) + wait_event(base->cpu_base->wait, + !(timer->state & HRTIMER_STATE_CALLBACK)); +} + +#else +# define wake_up_timer_waiters(b) do { } while (0) +#endif + +/* + * enqueue_hrtimer - internal function to (re)start a timer + * + * The timer is inserted in expiry order. Insertion into the + * red black tree is O(log(n)). Must hold the base lock. + * + * Returns 1 when the new timer is the leftmost timer in the tree. + */ +static int enqueue_hrtimer(struct hrtimer *timer, + struct hrtimer_clock_base *base) +{ + debug_activate(timer); + + timerqueue_add(&base->active, &timer->node); + base->cpu_base->active_bases |= 1 << base->index; + + /* + * HRTIMER_STATE_ENQUEUED is or'ed to the current state to preserve the + * state of a possibly running callback. + */ + timer->state |= HRTIMER_STATE_ENQUEUED; + + return (&timer->node == base->active.next); +} + +/* + * __remove_hrtimer - internal function to remove a timer + * + * Caller must hold the base lock. + * + * High resolution timer mode reprograms the clock event device when the + * timer is the one which expires next. The caller can disable this by setting + * reprogram to zero. This is useful, when the context does a reprogramming + * anyway (e.g. timer interrupt) + */ +static void __remove_hrtimer(struct hrtimer *timer, + struct hrtimer_clock_base *base, + unsigned long newstate, int reprogram) +{ + struct timerqueue_node *next_timer; + if (!(timer->state & HRTIMER_STATE_ENQUEUED)) + goto out; + + if (unlikely(!list_empty(&timer->cb_entry))) { + list_del_init(&timer->cb_entry); + goto out; + } + + next_timer = timerqueue_getnext(&base->active); + timerqueue_del(&base->active, &timer->node); + if (&timer->node == next_timer) { +#ifdef CONFIG_HIGH_RES_TIMERS + /* Reprogram the clock event device. if enabled */ + if (reprogram && hrtimer_hres_active()) { + ktime_t expires; + + expires = ktime_sub(hrtimer_get_expires(timer), + base->offset); + if (base->cpu_base->expires_next.tv64 == expires.tv64) + hrtimer_force_reprogram(base->cpu_base, 1); + } +#endif + } + if (!timerqueue_getnext(&base->active)) + base->cpu_base->active_bases &= ~(1 << base->index); +out: + timer->state = newstate; +} + +/* + * remove hrtimer, called with base lock held + */ +static inline int +remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base) +{ + if (hrtimer_is_queued(timer)) { + unsigned long state; + int reprogram; + + /* + * Remove the timer and force reprogramming when high + * resolution mode is active and the timer is on the current + * CPU. If we remove a timer on another CPU, reprogramming is + * skipped. The interrupt event on this CPU is fired and + * reprogramming happens in the interrupt handler. This is a + * rare case and less expensive than a smp call. + */ + debug_deactivate(timer); + timer_stats_hrtimer_clear_start_info(timer); + reprogram = base->cpu_base == this_cpu_ptr(&hrtimer_bases); + /* + * We must preserve the CALLBACK state flag here, + * otherwise we could move the timer base in + * switch_hrtimer_base. + */ + state = timer->state & HRTIMER_STATE_CALLBACK; + __remove_hrtimer(timer, base, state, reprogram); + return 1; + } + return 0; +} + +int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, + unsigned long delta_ns, const enum hrtimer_mode mode, + int wakeup) +{ + struct hrtimer_clock_base *base, *new_base; + unsigned long flags; + int ret, leftmost; + + base = lock_hrtimer_base(timer, &flags); + + /* Remove an active timer from the queue: */ + ret = remove_hrtimer(timer, base); + + if (mode & HRTIMER_MODE_REL) { + tim = ktime_add_safe(tim, base->get_time()); + /* + * CONFIG_TIME_LOW_RES is a temporary way for architectures + * to signal that they simply return xtime in + * do_gettimeoffset(). In this case we want to round up by + * resolution when starting a relative timer, to avoid short + * timeouts. This will go away with the GTOD framework. + */ +#ifdef CONFIG_TIME_LOW_RES + tim = ktime_add_safe(tim, base->resolution); +#endif + } + + hrtimer_set_expires_range_ns(timer, tim, delta_ns); + + /* Switch the timer base, if necessary: */ + new_base = switch_hrtimer_base(timer, base, mode & HRTIMER_MODE_PINNED); + + timer_stats_hrtimer_set_start_info(timer); +#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST + { + ktime_t now = new_base->get_time(); + + if (ktime_to_ns(tim) < ktime_to_ns(now)) + timer->praecox = now; + else + timer->praecox = ktime_set(0, 0); + } +#endif + leftmost = enqueue_hrtimer(timer, new_base); + + if (!leftmost) { + unlock_hrtimer_base(timer, &flags); + return ret; + } + + if (!hrtimer_is_hres_active(timer)) { + /* + * Kick to reschedule the next tick to handle the new timer + * on dynticks target. + */ + wake_up_nohz_cpu(new_base->cpu_base->cpu); + } else if (new_base->cpu_base == this_cpu_ptr(&hrtimer_bases)) { + + ret = hrtimer_enqueue_reprogram(timer, new_base, wakeup); + if (ret < 0) { + /* + * In case we failed to reprogram the timer (mostly + * because out current timer is already elapsed), + * remove it again and report a failure. This avoids + * stale base->first entries. + */ + debug_deactivate(timer); + __remove_hrtimer(timer, new_base, + timer->state & HRTIMER_STATE_CALLBACK, 0); + } else if (ret > 0) { + /* + * Only allow reprogramming if the new base is on this CPU. + * (it might still be on another CPU if the timer was pending) + * + * XXX send_remote_softirq() ? + */ + /* + * We need to drop cpu_base->lock to avoid a + * lock ordering issue vs. rq->lock. + */ + raw_spin_unlock(&new_base->cpu_base->lock); + raise_softirq_irqoff(HRTIMER_SOFTIRQ); + local_irq_restore(flags); + return 0; + } + } + + unlock_hrtimer_base(timer, &flags); + + return ret; +} +EXPORT_SYMBOL_GPL(__hrtimer_start_range_ns); + +/** + * hrtimer_start_range_ns - (re)start an hrtimer on the current CPU + * @timer: the timer to be added + * @tim: expiry time + * @delta_ns: "slack" range for the timer + * @mode: expiry mode: absolute (HRTIMER_MODE_ABS) or + * relative (HRTIMER_MODE_REL) + * + * Returns: + * 0 on success + * 1 when the timer was active + */ +int hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, + unsigned long delta_ns, const enum hrtimer_mode mode) +{ + return __hrtimer_start_range_ns(timer, tim, delta_ns, mode, 1); +} +EXPORT_SYMBOL_GPL(hrtimer_start_range_ns); + +/** + * hrtimer_start - (re)start an hrtimer on the current CPU + * @timer: the timer to be added + * @tim: expiry time + * @mode: expiry mode: absolute (HRTIMER_MODE_ABS) or + * relative (HRTIMER_MODE_REL) + * + * Returns: + * 0 on success + * 1 when the timer was active + */ +int +hrtimer_start(struct hrtimer *timer, ktime_t tim, const enum hrtimer_mode mode) +{ + return __hrtimer_start_range_ns(timer, tim, 0, mode, 1); +} +EXPORT_SYMBOL_GPL(hrtimer_start); + + +/** + * hrtimer_try_to_cancel - try to deactivate a timer + * @timer: hrtimer to stop + * + * Returns: + * 0 when the timer was not active + * 1 when the timer was active + * -1 when the timer is currently excuting the callback function and + * cannot be stopped + */ +int hrtimer_try_to_cancel(struct hrtimer *timer) +{ + struct hrtimer_clock_base *base; + unsigned long flags; + int ret = -1; + + base = lock_hrtimer_base(timer, &flags); + + if (!hrtimer_callback_running(timer)) + ret = remove_hrtimer(timer, base); + + unlock_hrtimer_base(timer, &flags); + + return ret; + +} +EXPORT_SYMBOL_GPL(hrtimer_try_to_cancel); + +/** + * hrtimer_cancel - cancel a timer and wait for the handler to finish. + * @timer: the timer to be cancelled + * + * Returns: + * 0 when the timer was not active + * 1 when the timer was active + */ +int hrtimer_cancel(struct hrtimer *timer) +{ + for (;;) { + int ret = hrtimer_try_to_cancel(timer); + + if (ret >= 0) + return ret; + hrtimer_wait_for_timer(timer); + } +} +EXPORT_SYMBOL_GPL(hrtimer_cancel); + +/** + * hrtimer_get_remaining - get remaining time for the timer + * @timer: the timer to read + */ +ktime_t hrtimer_get_remaining(const struct hrtimer *timer) +{ + unsigned long flags; + ktime_t rem; + + lock_hrtimer_base(timer, &flags); + rem = hrtimer_expires_remaining(timer); + unlock_hrtimer_base(timer, &flags); + + return rem; +} +EXPORT_SYMBOL_GPL(hrtimer_get_remaining); + +#ifdef CONFIG_NO_HZ_COMMON +/** + * hrtimer_get_next_event - get the time until next expiry event + * + * Returns the delta to the next expiry event or KTIME_MAX if no timer + * is pending. + */ +ktime_t hrtimer_get_next_event(void) +{ + struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases); + ktime_t mindelta = { .tv64 = KTIME_MAX }; + unsigned long flags; + + raw_spin_lock_irqsave(&cpu_base->lock, flags); + + if (!hrtimer_hres_active()) + mindelta = ktime_sub(__hrtimer_get_next_event(cpu_base), + ktime_get()); + + raw_spin_unlock_irqrestore(&cpu_base->lock, flags); + + if (mindelta.tv64 < 0) + mindelta.tv64 = 0; + return mindelta; +} +#endif + +static void __hrtimer_init(struct hrtimer *timer, clockid_t clock_id, + enum hrtimer_mode mode) +{ + struct hrtimer_cpu_base *cpu_base; + int base; + + memset(timer, 0, sizeof(struct hrtimer)); + + cpu_base = raw_cpu_ptr(&hrtimer_bases); + + if (clock_id == CLOCK_REALTIME && mode != HRTIMER_MODE_ABS) + clock_id = CLOCK_MONOTONIC; + + base = hrtimer_clockid_to_base(clock_id); + timer->base = &cpu_base->clock_base[base]; + INIT_LIST_HEAD(&timer->cb_entry); + timerqueue_init(&timer->node); + +#ifdef CONFIG_TIMER_STATS + timer->start_site = NULL; + timer->start_pid = -1; + memset(timer->start_comm, 0, TASK_COMM_LEN); +#endif +} + +/** + * hrtimer_init - initialize a timer to the given clock + * @timer: the timer to be initialized + * @clock_id: the clock to be used + * @mode: timer mode abs/rel + */ +void hrtimer_init(struct hrtimer *timer, clockid_t clock_id, + enum hrtimer_mode mode) +{ + debug_init(timer, clock_id, mode); + __hrtimer_init(timer, clock_id, mode); +} +EXPORT_SYMBOL_GPL(hrtimer_init); + +/** + * hrtimer_get_res - get the timer resolution for a clock + * @which_clock: which clock to query + * @tp: pointer to timespec variable to store the resolution + * + * Store the resolution of the clock selected by @which_clock in the + * variable pointed to by @tp. + */ +int hrtimer_get_res(const clockid_t which_clock, struct timespec *tp) +{ + struct hrtimer_cpu_base *cpu_base; + int base = hrtimer_clockid_to_base(which_clock); + + cpu_base = raw_cpu_ptr(&hrtimer_bases); + *tp = ktime_to_timespec(cpu_base->clock_base[base].resolution); + + return 0; +} +EXPORT_SYMBOL_GPL(hrtimer_get_res); + +static void __run_hrtimer(struct hrtimer *timer, ktime_t *now) +{ + struct hrtimer_clock_base *base = timer->base; + struct hrtimer_cpu_base *cpu_base = base->cpu_base; + enum hrtimer_restart (*fn)(struct hrtimer *); + int restart; + + WARN_ON(!irqs_disabled()); + + debug_deactivate(timer); + __remove_hrtimer(timer, base, HRTIMER_STATE_CALLBACK, 0); + timer_stats_account_hrtimer(timer); + fn = timer->function; + + /* + * Because we run timers from hardirq context, there is no chance + * they get migrated to another cpu, therefore its safe to unlock + * the timer base. + */ + raw_spin_unlock(&cpu_base->lock); + trace_hrtimer_expire_entry(timer, now); + restart = fn(timer); + trace_hrtimer_expire_exit(timer); + raw_spin_lock(&cpu_base->lock); + + /* + * Note: We clear the CALLBACK bit after enqueue_hrtimer and + * we do not reprogramm the event hardware. Happens either in + * hrtimer_start_range_ns() or in hrtimer_interrupt() + */ + if (restart != HRTIMER_NORESTART) { + BUG_ON(timer->state != HRTIMER_STATE_CALLBACK); + enqueue_hrtimer(timer, base); + } + + WARN_ON_ONCE(!(timer->state & HRTIMER_STATE_CALLBACK)); + + timer->state &= ~HRTIMER_STATE_CALLBACK; +} + +static enum hrtimer_restart hrtimer_wakeup(struct hrtimer *timer); + +#ifdef CONFIG_PREEMPT_RT_BASE +static void hrtimer_rt_reprogram(int restart, struct hrtimer *timer, + struct hrtimer_clock_base *base) +{ + /* + * Note, we clear the callback flag before we requeue the + * timer otherwise we trigger the callback_running() check + * in hrtimer_reprogram(). + */ + timer->state &= ~HRTIMER_STATE_CALLBACK; + + if (restart != HRTIMER_NORESTART) { + BUG_ON(hrtimer_active(timer)); + /* + * Enqueue the timer, if it's the leftmost timer then + * we need to reprogram it. + */ + if (!enqueue_hrtimer(timer, base)) + return; + +#ifndef CONFIG_HIGH_RES_TIMERS + } +#else + if (base->cpu_base->hres_active && + hrtimer_reprogram(timer, base)) + goto requeue; + + } else if (hrtimer_active(timer)) { + /* + * If the timer was rearmed on another CPU, reprogram + * the event device. + */ + if (&timer->node == base->active.next && + base->cpu_base->hres_active && + hrtimer_reprogram(timer, base)) + goto requeue; + } + return; + +requeue: + /* + * Timer is expired. Thus move it from tree to pending list + * again. + */ + __remove_hrtimer(timer, base, timer->state, 0); + list_add_tail(&timer->cb_entry, &base->expired); +#endif +} + +/* + * The changes in mainline which removed the callback modes from + * hrtimer are not yet working with -rt. The non wakeup_process() + * based callbacks which involve sleeping locks need to be treated + * seperately. + */ +static void hrtimer_rt_run_pending(void) +{ + enum hrtimer_restart (*fn)(struct hrtimer *); + struct hrtimer_cpu_base *cpu_base; + struct hrtimer_clock_base *base; + struct hrtimer *timer; + int index, restart; + + local_irq_disable(); + cpu_base = &per_cpu(hrtimer_bases, smp_processor_id()); + + raw_spin_lock(&cpu_base->lock); + + for (index = 0; index < HRTIMER_MAX_CLOCK_BASES; index++) { + base = &cpu_base->clock_base[index]; + + while (!list_empty(&base->expired)) { + timer = list_first_entry(&base->expired, + struct hrtimer, cb_entry); + + /* + * Same as the above __run_hrtimer function + * just we run with interrupts enabled. + */ + debug_hrtimer_deactivate(timer); + __remove_hrtimer(timer, base, HRTIMER_STATE_CALLBACK, 0); + timer_stats_account_hrtimer(timer); + fn = timer->function; + + raw_spin_unlock_irq(&cpu_base->lock); + restart = fn(timer); + raw_spin_lock_irq(&cpu_base->lock); + + hrtimer_rt_reprogram(restart, timer, base); + } + } + + raw_spin_unlock_irq(&cpu_base->lock); + + wake_up_timer_waiters(cpu_base); +} + +static int hrtimer_rt_defer(struct hrtimer *timer) +{ + if (timer->irqsafe) + return 0; + + __remove_hrtimer(timer, timer->base, timer->state, 0); + list_add_tail(&timer->cb_entry, &timer->base->expired); + return 1; +} + +#else + +static inline void hrtimer_rt_run_pending(void) +{ + hrtimer_peek_ahead_timers(); +} + +static inline int hrtimer_rt_defer(struct hrtimer *timer) { return 0; } + +#endif + +#ifdef CONFIG_HIGH_RES_TIMERS + +/* + * High resolution timer interrupt + * Called with interrupts disabled + */ +void hrtimer_interrupt(struct clock_event_device *dev) +{ + struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases); + ktime_t expires_next, now, entry_time, delta; + int i, retries = 0, raise = 0; + + BUG_ON(!cpu_base->hres_active); + cpu_base->nr_events++; + dev->next_event.tv64 = KTIME_MAX; + + raw_spin_lock(&cpu_base->lock); + entry_time = now = hrtimer_update_base(cpu_base); +retry: + cpu_base->in_hrtirq = 1; + /* + * We set expires_next to KTIME_MAX here with cpu_base->lock + * held to prevent that a timer is enqueued in our queue via + * the migration code. This does not affect enqueueing of + * timers which run their callback and need to be requeued on + * this CPU. + */ + cpu_base->expires_next.tv64 = KTIME_MAX; + + for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) { + struct hrtimer_clock_base *base; + struct timerqueue_node *node; + ktime_t basenow; + + if (!(cpu_base->active_bases & (1 << i))) + continue; + + base = cpu_base->clock_base + i; + basenow = ktime_add(now, base->offset); + + while ((node = timerqueue_getnext(&base->active))) { + struct hrtimer *timer; + + timer = container_of(node, struct hrtimer, node); + + trace_hrtimer_interrupt(raw_smp_processor_id(), + ktime_to_ns(ktime_sub(ktime_to_ns(timer->praecox) ? + timer->praecox : hrtimer_get_expires(timer), + basenow)), + current, + timer->function == hrtimer_wakeup ? + container_of(timer, struct hrtimer_sleeper, + timer)->task : NULL); + + /* + * The immediate goal for using the softexpires is + * minimizing wakeups, not running timers at the + * earliest interrupt after their soft expiration. + * This allows us to avoid using a Priority Search + * Tree, which can answer a stabbing querry for + * overlapping intervals and instead use the simple + * BST we already have. + * We don't add extra wakeups by delaying timers that + * are right-of a not yet expired timer, because that + * timer will have to trigger a wakeup anyway. + */ + if (basenow.tv64 < hrtimer_get_softexpires_tv64(timer)) + break; + + if (!hrtimer_rt_defer(timer)) + __run_hrtimer(timer, &basenow); + else + raise = 1; + } + } + /* Reevaluate the clock bases for the next expiry */ + expires_next = __hrtimer_get_next_event(cpu_base); + /* + * Store the new expiry value so the migration code can verify + * against it. + */ + cpu_base->expires_next = expires_next; + cpu_base->in_hrtirq = 0; + raw_spin_unlock(&cpu_base->lock); + + /* Reprogramming necessary ? */ + if (expires_next.tv64 == KTIME_MAX || + !tick_program_event(expires_next, 0)) { + cpu_base->hang_detected = 0; + goto out; + } + + /* + * The next timer was already expired due to: + * - tracing + * - long lasting callbacks + * - being scheduled away when running in a VM + * + * We need to prevent that we loop forever in the hrtimer + * interrupt routine. We give it 3 attempts to avoid + * overreacting on some spurious event. + * + * Acquire base lock for updating the offsets and retrieving + * the current time. + */ + raw_spin_lock(&cpu_base->lock); + now = hrtimer_update_base(cpu_base); + cpu_base->nr_retries++; + if (++retries < 3) + goto retry; + /* + * Give the system a chance to do something else than looping + * here. We stored the entry time, so we know exactly how long + * we spent here. We schedule the next event this amount of + * time away. + */ + cpu_base->nr_hangs++; + cpu_base->hang_detected = 1; + raw_spin_unlock(&cpu_base->lock); + delta = ktime_sub(now, entry_time); + if (delta.tv64 > cpu_base->max_hang_time.tv64) + cpu_base->max_hang_time = delta; + /* + * Limit it to a sensible value as we enforce a longer + * delay. Give the CPU at least 100ms to catch up. + */ + if (delta.tv64 > 100 * NSEC_PER_MSEC) + expires_next = ktime_add_ns(now, 100 * NSEC_PER_MSEC); + else + expires_next = ktime_add(now, delta); + tick_program_event(expires_next, 1); + printk_once(KERN_WARNING "hrtimer: interrupt took %llu ns\n", + ktime_to_ns(delta)); +out: + if (raise) + raise_softirq_irqoff(HRTIMER_SOFTIRQ); +} + +/* + * local version of hrtimer_peek_ahead_timers() called with interrupts + * disabled. + */ +static void __hrtimer_peek_ahead_timers(void) +{ + struct tick_device *td; + + if (!hrtimer_hres_active()) + return; + + td = this_cpu_ptr(&tick_cpu_device); + if (td && td->evtdev) + hrtimer_interrupt(td->evtdev); +} + +/** + * hrtimer_peek_ahead_timers -- run soft-expired timers now + * + * hrtimer_peek_ahead_timers will peek at the timer queue of + * the current cpu and check if there are any timers for which + * the soft expires time has passed. If any such timers exist, + * they are run immediately and then removed from the timer queue. + * + */ +void hrtimer_peek_ahead_timers(void) +{ + unsigned long flags; + + local_irq_save(flags); + __hrtimer_peek_ahead_timers(); + local_irq_restore(flags); +} +#else /* CONFIG_HIGH_RES_TIMERS */ + +static inline void __hrtimer_peek_ahead_timers(void) { } + +#endif /* !CONFIG_HIGH_RES_TIMERS */ + + +static void run_hrtimer_softirq(struct softirq_action *h) +{ + hrtimer_rt_run_pending(); +} + +/* + * Called from timer softirq every jiffy, expire hrtimers: + * + * For HRT its the fall back code to run the softirq in the timer + * softirq context in case the hrtimer initialization failed or has + * not been done yet. + */ +void hrtimer_run_pending(void) +{ + if (hrtimer_hres_active()) + return; + + /* + * This _is_ ugly: We have to check in the softirq context, + * whether we can switch to highres and / or nohz mode. The + * clocksource switch happens in the timer interrupt with + * xtime_lock held. Notification from there only sets the + * check bit in the tick_oneshot code, otherwise we might + * deadlock vs. xtime_lock. + */ + if (tick_check_oneshot_change(!hrtimer_is_hres_enabled())) + hrtimer_switch_to_hres(); +} + +/* + * Called from hardirq context every jiffy + */ +void hrtimer_run_queues(void) +{ + struct timerqueue_node *node; + struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases); + struct hrtimer_clock_base *base; + int index, gettime = 1, raise = 0; + + if (hrtimer_hres_active()) + return; + + for (index = 0; index < HRTIMER_MAX_CLOCK_BASES; index++) { + base = &cpu_base->clock_base[index]; + if (!timerqueue_getnext(&base->active)) + continue; + + if (gettime) { + hrtimer_get_softirq_time(cpu_base); + gettime = 0; + } + + raw_spin_lock(&cpu_base->lock); + + while ((node = timerqueue_getnext(&base->active))) { + struct hrtimer *timer; + + timer = container_of(node, struct hrtimer, node); + if (base->softirq_time.tv64 <= + hrtimer_get_expires_tv64(timer)) + break; + + if (!hrtimer_rt_defer(timer)) + __run_hrtimer(timer, &base->softirq_time); + else + raise = 1; + } + raw_spin_unlock(&cpu_base->lock); + } + + if (raise) + raise_softirq_irqoff(HRTIMER_SOFTIRQ); +} + +/* + * Sleep related functions: + */ +static enum hrtimer_restart hrtimer_wakeup(struct hrtimer *timer) +{ + struct hrtimer_sleeper *t = + container_of(timer, struct hrtimer_sleeper, timer); + struct task_struct *task = t->task; + + t->task = NULL; + if (task) + wake_up_process(task); + + return HRTIMER_NORESTART; +} + +void hrtimer_init_sleeper(struct hrtimer_sleeper *sl, struct task_struct *task) +{ + sl->timer.function = hrtimer_wakeup; + sl->timer.irqsafe = 1; + sl->task = task; +} +EXPORT_SYMBOL_GPL(hrtimer_init_sleeper); + +static int __sched do_nanosleep(struct hrtimer_sleeper *t, enum hrtimer_mode mode, + unsigned long state) +{ + hrtimer_init_sleeper(t, current); + + do { + set_current_state(state); + hrtimer_start_expires(&t->timer, mode); + if (!hrtimer_active(&t->timer)) + t->task = NULL; + + if (likely(t->task)) + freezable_schedule(); + + hrtimer_cancel(&t->timer); + mode = HRTIMER_MODE_ABS; + + } while (t->task && !signal_pending(current)); + + __set_current_state(TASK_RUNNING); + + return t->task == NULL; +} + +static int update_rmtp(struct hrtimer *timer, struct timespec __user *rmtp) +{ + struct timespec rmt; + ktime_t rem; + + rem = hrtimer_expires_remaining(timer); + if (rem.tv64 <= 0) + return 0; + rmt = ktime_to_timespec(rem); + + if (copy_to_user(rmtp, &rmt, sizeof(*rmtp))) + return -EFAULT; + + return 1; +} + +long __sched hrtimer_nanosleep_restart(struct restart_block *restart) +{ + struct hrtimer_sleeper t; + struct timespec __user *rmtp; + int ret = 0; + + hrtimer_init_on_stack(&t.timer, restart->nanosleep.clockid, + HRTIMER_MODE_ABS); + hrtimer_set_expires_tv64(&t.timer, restart->nanosleep.expires); + + /* cpu_chill() does not care about restart state. */ + if (do_nanosleep(&t, HRTIMER_MODE_ABS, TASK_INTERRUPTIBLE)) + goto out; + + rmtp = restart->nanosleep.rmtp; + if (rmtp) { + ret = update_rmtp(&t.timer, rmtp); + if (ret <= 0) + goto out; + } + + /* The other values in restart are already filled in */ + ret = -ERESTART_RESTARTBLOCK; +out: + destroy_hrtimer_on_stack(&t.timer); + return ret; +} + +static long +__hrtimer_nanosleep(struct timespec *rqtp, struct timespec __user *rmtp, + const enum hrtimer_mode mode, const clockid_t clockid, + unsigned long state) +{ + struct restart_block *restart; + struct hrtimer_sleeper t; + int ret = 0; + unsigned long slack; + + slack = current->timer_slack_ns; + if (dl_task(current) || rt_task(current)) + slack = 0; + + hrtimer_init_on_stack(&t.timer, clockid, mode); + hrtimer_set_expires_range_ns(&t.timer, timespec_to_ktime(*rqtp), slack); + if (do_nanosleep(&t, mode, state)) + goto out; + + /* Absolute timers do not update the rmtp value and restart: */ + if (mode == HRTIMER_MODE_ABS) { + ret = -ERESTARTNOHAND; + goto out; + } + + if (rmtp) { + ret = update_rmtp(&t.timer, rmtp); + if (ret <= 0) + goto out; + } + + restart = ¤t->restart_block; + restart->fn = hrtimer_nanosleep_restart; + restart->nanosleep.clockid = t.timer.base->clockid; + restart->nanosleep.rmtp = rmtp; + restart->nanosleep.expires = hrtimer_get_expires_tv64(&t.timer); + + ret = -ERESTART_RESTARTBLOCK; +out: + destroy_hrtimer_on_stack(&t.timer); + return ret; +} + +long hrtimer_nanosleep(struct timespec *rqtp, struct timespec __user *rmtp, + const enum hrtimer_mode mode, const clockid_t clockid) +{ + return __hrtimer_nanosleep(rqtp, rmtp, mode, clockid, TASK_INTERRUPTIBLE); +} + +SYSCALL_DEFINE2(nanosleep, struct timespec __user *, rqtp, + struct timespec __user *, rmtp) +{ + struct timespec tu; + + if (copy_from_user(&tu, rqtp, sizeof(tu))) + return -EFAULT; + + if (!timespec_valid(&tu)) + return -EINVAL; + + return hrtimer_nanosleep(&tu, rmtp, HRTIMER_MODE_REL, CLOCK_MONOTONIC); +} + +#ifdef CONFIG_PREEMPT_RT_FULL +/* + * Sleep for 1 ms in hope whoever holds what we want will let it go. + */ +void cpu_chill(void) +{ + struct timespec tu = { + .tv_nsec = NSEC_PER_MSEC, + }; + unsigned int freeze_flag = current->flags & PF_NOFREEZE; + + current->flags |= PF_NOFREEZE; + __hrtimer_nanosleep(&tu, NULL, HRTIMER_MODE_REL, CLOCK_MONOTONIC, + TASK_UNINTERRUPTIBLE); + if (!freeze_flag) + current->flags &= ~PF_NOFREEZE; +} +EXPORT_SYMBOL(cpu_chill); +#endif + +/* + * Functions related to boot-time initialization: + */ +static void init_hrtimers_cpu(int cpu) +{ + struct hrtimer_cpu_base *cpu_base = &per_cpu(hrtimer_bases, cpu); + int i; + + for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) { + cpu_base->clock_base[i].cpu_base = cpu_base; + timerqueue_init_head(&cpu_base->clock_base[i].active); + INIT_LIST_HEAD(&cpu_base->clock_base[i].expired); + } + + cpu_base->cpu = cpu; + hrtimer_init_hres(cpu_base); +#ifdef CONFIG_PREEMPT_RT_BASE + init_waitqueue_head(&cpu_base->wait); +#endif +} + +#ifdef CONFIG_HOTPLUG_CPU + +static void migrate_hrtimer_list(struct hrtimer_clock_base *old_base, + struct hrtimer_clock_base *new_base) +{ + struct hrtimer *timer; + struct timerqueue_node *node; + + while ((node = timerqueue_getnext(&old_base->active))) { + timer = container_of(node, struct hrtimer, node); + BUG_ON(hrtimer_callback_running(timer)); + debug_deactivate(timer); + + /* + * Mark it as STATE_MIGRATE not INACTIVE otherwise the + * timer could be seen as !active and just vanish away + * under us on another CPU + */ + __remove_hrtimer(timer, old_base, HRTIMER_STATE_MIGRATE, 0); + timer->base = new_base; + /* + * Enqueue the timers on the new cpu. This does not + * reprogram the event device in case the timer + * expires before the earliest on this CPU, but we run + * hrtimer_interrupt after we migrated everything to + * sort out already expired timers and reprogram the + * event device. + */ + enqueue_hrtimer(timer, new_base); + + /* Clear the migration state bit */ + timer->state &= ~HRTIMER_STATE_MIGRATE; + } +} + +static void migrate_hrtimers(int scpu) +{ + struct hrtimer_cpu_base *old_base, *new_base; + int i; + + BUG_ON(cpu_online(scpu)); + tick_cancel_sched_timer(scpu); + + local_irq_disable(); + old_base = &per_cpu(hrtimer_bases, scpu); + new_base = this_cpu_ptr(&hrtimer_bases); + /* + * The caller is globally serialized and nobody else + * takes two locks at once, deadlock is not possible. + */ + raw_spin_lock(&new_base->lock); + raw_spin_lock_nested(&old_base->lock, SINGLE_DEPTH_NESTING); + + for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) { + migrate_hrtimer_list(&old_base->clock_base[i], + &new_base->clock_base[i]); + } + + raw_spin_unlock(&old_base->lock); + raw_spin_unlock(&new_base->lock); + + /* Check, if we got expired work to do */ + __hrtimer_peek_ahead_timers(); + local_irq_enable(); +} + +#endif /* CONFIG_HOTPLUG_CPU */ + +static int hrtimer_cpu_notify(struct notifier_block *self, + unsigned long action, void *hcpu) +{ + int scpu = (long)hcpu; + + switch (action) { + + case CPU_UP_PREPARE: + case CPU_UP_PREPARE_FROZEN: + init_hrtimers_cpu(scpu); + break; + +#ifdef CONFIG_HOTPLUG_CPU + case CPU_DEAD: + case CPU_DEAD_FROZEN: + migrate_hrtimers(scpu); + break; +#endif + + default: + break; + } + + return NOTIFY_OK; +} + +static struct notifier_block hrtimers_nb = { + .notifier_call = hrtimer_cpu_notify, +}; + +void __init hrtimers_init(void) +{ + hrtimer_cpu_notify(&hrtimers_nb, (unsigned long)CPU_UP_PREPARE, + (void *)(long)smp_processor_id()); + register_cpu_notifier(&hrtimers_nb); + open_softirq(HRTIMER_SOFTIRQ, run_hrtimer_softirq); +} + +/** + * schedule_hrtimeout_range_clock - sleep until timeout + * @expires: timeout value (ktime_t) + * @delta: slack in expires timeout (ktime_t) + * @mode: timer mode, HRTIMER_MODE_ABS or HRTIMER_MODE_REL + * @clock: timer clock, CLOCK_MONOTONIC or CLOCK_REALTIME + */ +int __sched +schedule_hrtimeout_range_clock(ktime_t *expires, unsigned long delta, + const enum hrtimer_mode mode, int clock) +{ + struct hrtimer_sleeper t; + + /* + * Optimize when a zero timeout value is given. It does not + * matter whether this is an absolute or a relative time. + */ + if (expires && !expires->tv64) { + __set_current_state(TASK_RUNNING); + return 0; + } + + /* + * A NULL parameter means "infinite" + */ + if (!expires) { + schedule(); + return -EINTR; + } + + hrtimer_init_on_stack(&t.timer, clock, mode); + hrtimer_set_expires_range_ns(&t.timer, *expires, delta); + + hrtimer_init_sleeper(&t, current); + + hrtimer_start_expires(&t.timer, mode); + if (!hrtimer_active(&t.timer)) + t.task = NULL; + + if (likely(t.task)) + schedule(); + + hrtimer_cancel(&t.timer); + destroy_hrtimer_on_stack(&t.timer); + + __set_current_state(TASK_RUNNING); + + return !t.task ? 0 : -EINTR; +} + +/** + * schedule_hrtimeout_range - sleep until timeout + * @expires: timeout value (ktime_t) + * @delta: slack in expires timeout (ktime_t) + * @mode: timer mode, HRTIMER_MODE_ABS or HRTIMER_MODE_REL + * + * Make the current task sleep until the given expiry time has + * elapsed. The routine will return immediately unless + * the current task state has been set (see set_current_state()). + * + * The @delta argument gives the kernel the freedom to schedule the + * actual wakeup to a time that is both power and performance friendly. + * The kernel give the normal best effort behavior for "@expires+@delta", + * but may decide to fire the timer earlier, but no earlier than @expires. + * + * You can set the task state as follows - + * + * %TASK_UNINTERRUPTIBLE - at least @timeout time is guaranteed to + * pass before the routine returns. + * + * %TASK_INTERRUPTIBLE - the routine may return early if a signal is + * delivered to the current task. + * + * The current task state is guaranteed to be TASK_RUNNING when this + * routine returns. + * + * Returns 0 when the timer has expired otherwise -EINTR + */ +int __sched schedule_hrtimeout_range(ktime_t *expires, unsigned long delta, + const enum hrtimer_mode mode) +{ + return schedule_hrtimeout_range_clock(expires, delta, mode, + CLOCK_MONOTONIC); +} +EXPORT_SYMBOL_GPL(schedule_hrtimeout_range); + +/** + * schedule_hrtimeout - sleep until timeout + * @expires: timeout value (ktime_t) + * @mode: timer mode, HRTIMER_MODE_ABS or HRTIMER_MODE_REL + * + * Make the current task sleep until the given expiry time has + * elapsed. The routine will return immediately unless + * the current task state has been set (see set_current_state()). + * + * You can set the task state as follows - + * + * %TASK_UNINTERRUPTIBLE - at least @timeout time is guaranteed to + * pass before the routine returns. + * + * %TASK_INTERRUPTIBLE - the routine may return early if a signal is + * delivered to the current task. + * + * The current task state is guaranteed to be TASK_RUNNING when this + * routine returns. + * + * Returns 0 when the timer has expired otherwise -EINTR + */ +int __sched schedule_hrtimeout(ktime_t *expires, + const enum hrtimer_mode mode) +{ + return schedule_hrtimeout_range(expires, 0, mode); +} +EXPORT_SYMBOL_GPL(schedule_hrtimeout); diff --git a/kernel/kernel/time/itimer.c b/kernel/kernel/time/itimer.c new file mode 100644 index 000000000..d0513909d --- /dev/null +++ b/kernel/kernel/time/itimer.c @@ -0,0 +1,302 @@ +/* + * linux/kernel/itimer.c + * + * Copyright (C) 1992 Darren Senn + */ + +/* These are all the functions necessary to implement itimers */ + +#include +#include +#include +#include +#include +#include +#include + +#include + +/** + * itimer_get_remtime - get remaining time for the timer + * + * @timer: the timer to read + * + * Returns the delta between the expiry time and now, which can be + * less than zero or 1usec for an pending expired timer + */ +static struct timeval itimer_get_remtime(struct hrtimer *timer) +{ + ktime_t rem = hrtimer_get_remaining(timer); + + /* + * Racy but safe: if the itimer expires after the above + * hrtimer_get_remtime() call but before this condition + * then we return 0 - which is correct. + */ + if (hrtimer_active(timer)) { + if (rem.tv64 <= 0) + rem.tv64 = NSEC_PER_USEC; + } else + rem.tv64 = 0; + + return ktime_to_timeval(rem); +} + +static void get_cpu_itimer(struct task_struct *tsk, unsigned int clock_id, + struct itimerval *const value) +{ + cputime_t cval, cinterval; + struct cpu_itimer *it = &tsk->signal->it[clock_id]; + + spin_lock_irq(&tsk->sighand->siglock); + + cval = it->expires; + cinterval = it->incr; + if (cval) { + struct task_cputime cputime; + cputime_t t; + + thread_group_cputimer(tsk, &cputime); + if (clock_id == CPUCLOCK_PROF) + t = cputime.utime + cputime.stime; + else + /* CPUCLOCK_VIRT */ + t = cputime.utime; + + if (cval < t) + /* about to fire */ + cval = cputime_one_jiffy; + else + cval = cval - t; + } + + spin_unlock_irq(&tsk->sighand->siglock); + + cputime_to_timeval(cval, &value->it_value); + cputime_to_timeval(cinterval, &value->it_interval); +} + +int do_getitimer(int which, struct itimerval *value) +{ + struct task_struct *tsk = current; + + switch (which) { + case ITIMER_REAL: + spin_lock_irq(&tsk->sighand->siglock); + value->it_value = itimer_get_remtime(&tsk->signal->real_timer); + value->it_interval = + ktime_to_timeval(tsk->signal->it_real_incr); + spin_unlock_irq(&tsk->sighand->siglock); + break; + case ITIMER_VIRTUAL: + get_cpu_itimer(tsk, CPUCLOCK_VIRT, value); + break; + case ITIMER_PROF: + get_cpu_itimer(tsk, CPUCLOCK_PROF, value); + break; + default: + return(-EINVAL); + } + return 0; +} + +SYSCALL_DEFINE2(getitimer, int, which, struct itimerval __user *, value) +{ + int error = -EFAULT; + struct itimerval get_buffer; + + if (value) { + error = do_getitimer(which, &get_buffer); + if (!error && + copy_to_user(value, &get_buffer, sizeof(get_buffer))) + error = -EFAULT; + } + return error; +} + + +/* + * The timer is automagically restarted, when interval != 0 + */ +enum hrtimer_restart it_real_fn(struct hrtimer *timer) +{ + struct signal_struct *sig = + container_of(timer, struct signal_struct, real_timer); + + trace_itimer_expire(ITIMER_REAL, sig->leader_pid, 0); + kill_pid_info(SIGALRM, SEND_SIG_PRIV, sig->leader_pid); + + return HRTIMER_NORESTART; +} + +static inline u32 cputime_sub_ns(cputime_t ct, s64 real_ns) +{ + struct timespec ts; + s64 cpu_ns; + + cputime_to_timespec(ct, &ts); + cpu_ns = timespec_to_ns(&ts); + + return (cpu_ns <= real_ns) ? 0 : cpu_ns - real_ns; +} + +static void set_cpu_itimer(struct task_struct *tsk, unsigned int clock_id, + const struct itimerval *const value, + struct itimerval *const ovalue) +{ + cputime_t cval, nval, cinterval, ninterval; + s64 ns_ninterval, ns_nval; + u32 error, incr_error; + struct cpu_itimer *it = &tsk->signal->it[clock_id]; + + nval = timeval_to_cputime(&value->it_value); + ns_nval = timeval_to_ns(&value->it_value); + ninterval = timeval_to_cputime(&value->it_interval); + ns_ninterval = timeval_to_ns(&value->it_interval); + + error = cputime_sub_ns(nval, ns_nval); + incr_error = cputime_sub_ns(ninterval, ns_ninterval); + + spin_lock_irq(&tsk->sighand->siglock); + + cval = it->expires; + cinterval = it->incr; + if (cval || nval) { + if (nval > 0) + nval += cputime_one_jiffy; + set_process_cpu_timer(tsk, clock_id, &nval, &cval); + } + it->expires = nval; + it->incr = ninterval; + it->error = error; + it->incr_error = incr_error; + trace_itimer_state(clock_id == CPUCLOCK_VIRT ? + ITIMER_VIRTUAL : ITIMER_PROF, value, nval); + + spin_unlock_irq(&tsk->sighand->siglock); + + if (ovalue) { + cputime_to_timeval(cval, &ovalue->it_value); + cputime_to_timeval(cinterval, &ovalue->it_interval); + } +} + +/* + * Returns true if the timeval is in canonical form + */ +#define timeval_valid(t) \ + (((t)->tv_sec >= 0) && (((unsigned long) (t)->tv_usec) < USEC_PER_SEC)) + +int do_setitimer(int which, struct itimerval *value, struct itimerval *ovalue) +{ + struct task_struct *tsk = current; + struct hrtimer *timer; + ktime_t expires; + + /* + * Validate the timevals in value. + */ + if (!timeval_valid(&value->it_value) || + !timeval_valid(&value->it_interval)) + return -EINVAL; + + switch (which) { + case ITIMER_REAL: +again: + spin_lock_irq(&tsk->sighand->siglock); + timer = &tsk->signal->real_timer; + if (ovalue) { + ovalue->it_value = itimer_get_remtime(timer); + ovalue->it_interval + = ktime_to_timeval(tsk->signal->it_real_incr); + } + /* We are sharing ->siglock with it_real_fn() */ + if (hrtimer_try_to_cancel(timer) < 0) { + spin_unlock_irq(&tsk->sighand->siglock); + hrtimer_wait_for_timer(&tsk->signal->real_timer); + goto again; + } + expires = timeval_to_ktime(value->it_value); + if (expires.tv64 != 0) { + tsk->signal->it_real_incr = + timeval_to_ktime(value->it_interval); + hrtimer_start(timer, expires, HRTIMER_MODE_REL); + } else + tsk->signal->it_real_incr.tv64 = 0; + + trace_itimer_state(ITIMER_REAL, value, 0); + spin_unlock_irq(&tsk->sighand->siglock); + break; + case ITIMER_VIRTUAL: + set_cpu_itimer(tsk, CPUCLOCK_VIRT, value, ovalue); + break; + case ITIMER_PROF: + set_cpu_itimer(tsk, CPUCLOCK_PROF, value, ovalue); + break; + default: + return -EINVAL; + } + return 0; +} + +/** + * alarm_setitimer - set alarm in seconds + * + * @seconds: number of seconds until alarm + * 0 disables the alarm + * + * Returns the remaining time in seconds of a pending timer or 0 when + * the timer is not active. + * + * On 32 bit machines the seconds value is limited to (INT_MAX/2) to avoid + * negative timeval settings which would cause immediate expiry. + */ +unsigned int alarm_setitimer(unsigned int seconds) +{ + struct itimerval it_new, it_old; + +#if BITS_PER_LONG < 64 + if (seconds > INT_MAX) + seconds = INT_MAX; +#endif + it_new.it_value.tv_sec = seconds; + it_new.it_value.tv_usec = 0; + it_new.it_interval.tv_sec = it_new.it_interval.tv_usec = 0; + + do_setitimer(ITIMER_REAL, &it_new, &it_old); + + /* + * We can't return 0 if we have an alarm pending ... And we'd + * better return too much than too little anyway + */ + if ((!it_old.it_value.tv_sec && it_old.it_value.tv_usec) || + it_old.it_value.tv_usec >= 500000) + it_old.it_value.tv_sec++; + + return it_old.it_value.tv_sec; +} + +SYSCALL_DEFINE3(setitimer, int, which, struct itimerval __user *, value, + struct itimerval __user *, ovalue) +{ + struct itimerval set_buffer, get_buffer; + int error; + + if (value) { + if(copy_from_user(&set_buffer, value, sizeof(set_buffer))) + return -EFAULT; + } else { + memset(&set_buffer, 0, sizeof(set_buffer)); + printk_once(KERN_WARNING "%s calls setitimer() with new_value NULL pointer." + " Misfeature support will be removed\n", + current->comm); + } + + error = do_setitimer(which, &set_buffer, ovalue ? &get_buffer : NULL); + if (error || !ovalue) + return error; + + if (copy_to_user(ovalue, &get_buffer, sizeof(get_buffer))) + return -EFAULT; + return 0; +} diff --git a/kernel/kernel/time/jiffies.c b/kernel/kernel/time/jiffies.c new file mode 100644 index 000000000..2ede47408 --- /dev/null +++ b/kernel/kernel/time/jiffies.c @@ -0,0 +1,137 @@ +/*********************************************************************** +* linux/kernel/time/jiffies.c +* +* This file contains the jiffies based clocksource. +* +* Copyright (C) 2004, 2005 IBM, John Stultz (johnstul@us.ibm.com) +* +* This program is free software; you can redistribute it and/or modify +* it under the terms of the GNU General Public License as published by +* the Free Software Foundation; either version 2 of the License, or +* (at your option) any later version. +* +* This program is distributed in the hope that it will be useful, +* but WITHOUT ANY WARRANTY; without even the implied warranty of +* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +* GNU General Public License for more details. +* +* You should have received a copy of the GNU General Public License +* along with this program; if not, write to the Free Software +* Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. +* +************************************************************************/ +#include +#include +#include +#include + +#include "timekeeping.h" + +/* The Jiffies based clocksource is the lowest common + * denominator clock source which should function on + * all systems. It has the same coarse resolution as + * the timer interrupt frequency HZ and it suffers + * inaccuracies caused by missed or lost timer + * interrupts and the inability for the timer + * interrupt hardware to accuratly tick at the + * requested HZ value. It is also not recommended + * for "tick-less" systems. + */ +#define NSEC_PER_JIFFY ((NSEC_PER_SEC+HZ/2)/HZ) + +/* Since jiffies uses a simple NSEC_PER_JIFFY multiplier + * conversion, the .shift value could be zero. However + * this would make NTP adjustments impossible as they are + * in units of 1/2^.shift. Thus we use JIFFIES_SHIFT to + * shift both the nominator and denominator the same + * amount, and give ntp adjustments in units of 1/2^8 + * + * The value 8 is somewhat carefully chosen, as anything + * larger can result in overflows. NSEC_PER_JIFFY grows as + * HZ shrinks, so values greater than 8 overflow 32bits when + * HZ=100. + */ +#if HZ < 34 +#define JIFFIES_SHIFT 6 +#elif HZ < 67 +#define JIFFIES_SHIFT 7 +#else +#define JIFFIES_SHIFT 8 +#endif + +static cycle_t jiffies_read(struct clocksource *cs) +{ + return (cycle_t) jiffies; +} + +static struct clocksource clocksource_jiffies = { + .name = "jiffies", + .rating = 1, /* lowest valid rating*/ + .read = jiffies_read, + .mask = 0xffffffff, /*32bits*/ + .mult = NSEC_PER_JIFFY << JIFFIES_SHIFT, /* details above */ + .shift = JIFFIES_SHIFT, + .max_cycles = 10, +}; + +__cacheline_aligned_in_smp DEFINE_RAW_SPINLOCK(jiffies_lock); +__cacheline_aligned_in_smp seqcount_t jiffies_seq; + +#if (BITS_PER_LONG < 64) +u64 get_jiffies_64(void) +{ + unsigned long seq; + u64 ret; + + do { + seq = read_seqcount_begin(&jiffies_seq); + ret = jiffies_64; + } while (read_seqcount_retry(&jiffies_seq, seq)); + return ret; +} +EXPORT_SYMBOL(get_jiffies_64); +#endif + +EXPORT_SYMBOL(jiffies); + +static int __init init_jiffies_clocksource(void) +{ + return __clocksource_register(&clocksource_jiffies); +} + +core_initcall(init_jiffies_clocksource); + +struct clocksource * __init __weak clocksource_default_clock(void) +{ + return &clocksource_jiffies; +} + +struct clocksource refined_jiffies; + +int register_refined_jiffies(long cycles_per_second) +{ + u64 nsec_per_tick, shift_hz; + long cycles_per_tick; + + + + refined_jiffies = clocksource_jiffies; + refined_jiffies.name = "refined-jiffies"; + refined_jiffies.rating++; + + /* Calc cycles per tick */ + cycles_per_tick = (cycles_per_second + HZ/2)/HZ; + /* shift_hz stores hz<<8 for extra accuracy */ + shift_hz = (u64)cycles_per_second << 8; + shift_hz += cycles_per_tick/2; + do_div(shift_hz, cycles_per_tick); + /* Calculate nsec_per_tick using shift_hz */ + nsec_per_tick = (u64)NSEC_PER_SEC << 8; + nsec_per_tick += (u32)shift_hz/2; + do_div(nsec_per_tick, (u32)shift_hz); + + refined_jiffies.mult = ((u32)nsec_per_tick) << JIFFIES_SHIFT; + + __clocksource_register(&refined_jiffies); + return 0; +} diff --git a/kernel/kernel/time/ntp.c b/kernel/kernel/time/ntp.c new file mode 100644 index 000000000..bd9c53985 --- /dev/null +++ b/kernel/kernel/time/ntp.c @@ -0,0 +1,1008 @@ +/* + * NTP state machine interfaces and logic. + * + * This code was mainly moved from kernel/timer.c and kernel/time.c + * Please see those files for relevant copyright info and historical + * changelogs. + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "ntp_internal.h" + +/* + * NTP timekeeping variables: + * + * Note: All of the NTP state is protected by the timekeeping locks. + */ + + +/* USER_HZ period (usecs): */ +unsigned long tick_usec = TICK_USEC; + +/* SHIFTED_HZ period (nsecs): */ +unsigned long tick_nsec; + +static u64 tick_length; +static u64 tick_length_base; + +#define MAX_TICKADJ 500LL /* usecs */ +#define MAX_TICKADJ_SCALED \ + (((MAX_TICKADJ * NSEC_PER_USEC) << NTP_SCALE_SHIFT) / NTP_INTERVAL_FREQ) + +/* + * phase-lock loop variables + */ + +/* + * clock synchronization status + * + * (TIME_ERROR prevents overwriting the CMOS clock) + */ +static int time_state = TIME_OK; + +/* clock status bits: */ +static int time_status = STA_UNSYNC; + +/* time adjustment (nsecs): */ +static s64 time_offset; + +/* pll time constant: */ +static long time_constant = 2; + +/* maximum error (usecs): */ +static long time_maxerror = NTP_PHASE_LIMIT; + +/* estimated error (usecs): */ +static long time_esterror = NTP_PHASE_LIMIT; + +/* frequency offset (scaled nsecs/secs): */ +static s64 time_freq; + +/* time at last adjustment (secs): */ +static long time_reftime; + +static long time_adjust; + +/* constant (boot-param configurable) NTP tick adjustment (upscaled) */ +static s64 ntp_tick_adj; + +#ifdef CONFIG_NTP_PPS + +/* + * The following variables are used when a pulse-per-second (PPS) signal + * is available. They establish the engineering parameters of the clock + * discipline loop when controlled by the PPS signal. + */ +#define PPS_VALID 10 /* PPS signal watchdog max (s) */ +#define PPS_POPCORN 4 /* popcorn spike threshold (shift) */ +#define PPS_INTMIN 2 /* min freq interval (s) (shift) */ +#define PPS_INTMAX 8 /* max freq interval (s) (shift) */ +#define PPS_INTCOUNT 4 /* number of consecutive good intervals to + increase pps_shift or consecutive bad + intervals to decrease it */ +#define PPS_MAXWANDER 100000 /* max PPS freq wander (ns/s) */ + +static int pps_valid; /* signal watchdog counter */ +static long pps_tf[3]; /* phase median filter */ +static long pps_jitter; /* current jitter (ns) */ +static struct timespec pps_fbase; /* beginning of the last freq interval */ +static int pps_shift; /* current interval duration (s) (shift) */ +static int pps_intcnt; /* interval counter */ +static s64 pps_freq; /* frequency offset (scaled ns/s) */ +static long pps_stabil; /* current stability (scaled ns/s) */ + +/* + * PPS signal quality monitors + */ +static long pps_calcnt; /* calibration intervals */ +static long pps_jitcnt; /* jitter limit exceeded */ +static long pps_stbcnt; /* stability limit exceeded */ +static long pps_errcnt; /* calibration errors */ + + +/* PPS kernel consumer compensates the whole phase error immediately. + * Otherwise, reduce the offset by a fixed factor times the time constant. + */ +static inline s64 ntp_offset_chunk(s64 offset) +{ + if (time_status & STA_PPSTIME && time_status & STA_PPSSIGNAL) + return offset; + else + return shift_right(offset, SHIFT_PLL + time_constant); +} + +static inline void pps_reset_freq_interval(void) +{ + /* the PPS calibration interval may end + surprisingly early */ + pps_shift = PPS_INTMIN; + pps_intcnt = 0; +} + +/** + * pps_clear - Clears the PPS state variables + */ +static inline void pps_clear(void) +{ + pps_reset_freq_interval(); + pps_tf[0] = 0; + pps_tf[1] = 0; + pps_tf[2] = 0; + pps_fbase.tv_sec = pps_fbase.tv_nsec = 0; + pps_freq = 0; +} + +/* Decrease pps_valid to indicate that another second has passed since + * the last PPS signal. When it reaches 0, indicate that PPS signal is + * missing. + */ +static inline void pps_dec_valid(void) +{ + if (pps_valid > 0) + pps_valid--; + else { + time_status &= ~(STA_PPSSIGNAL | STA_PPSJITTER | + STA_PPSWANDER | STA_PPSERROR); + pps_clear(); + } +} + +static inline void pps_set_freq(s64 freq) +{ + pps_freq = freq; +} + +static inline int is_error_status(int status) +{ + return (status & (STA_UNSYNC|STA_CLOCKERR)) + /* PPS signal lost when either PPS time or + * PPS frequency synchronization requested + */ + || ((status & (STA_PPSFREQ|STA_PPSTIME)) + && !(status & STA_PPSSIGNAL)) + /* PPS jitter exceeded when + * PPS time synchronization requested */ + || ((status & (STA_PPSTIME|STA_PPSJITTER)) + == (STA_PPSTIME|STA_PPSJITTER)) + /* PPS wander exceeded or calibration error when + * PPS frequency synchronization requested + */ + || ((status & STA_PPSFREQ) + && (status & (STA_PPSWANDER|STA_PPSERROR))); +} + +static inline void pps_fill_timex(struct timex *txc) +{ + txc->ppsfreq = shift_right((pps_freq >> PPM_SCALE_INV_SHIFT) * + PPM_SCALE_INV, NTP_SCALE_SHIFT); + txc->jitter = pps_jitter; + if (!(time_status & STA_NANO)) + txc->jitter /= NSEC_PER_USEC; + txc->shift = pps_shift; + txc->stabil = pps_stabil; + txc->jitcnt = pps_jitcnt; + txc->calcnt = pps_calcnt; + txc->errcnt = pps_errcnt; + txc->stbcnt = pps_stbcnt; +} + +#else /* !CONFIG_NTP_PPS */ + +static inline s64 ntp_offset_chunk(s64 offset) +{ + return shift_right(offset, SHIFT_PLL + time_constant); +} + +static inline void pps_reset_freq_interval(void) {} +static inline void pps_clear(void) {} +static inline void pps_dec_valid(void) {} +static inline void pps_set_freq(s64 freq) {} + +static inline int is_error_status(int status) +{ + return status & (STA_UNSYNC|STA_CLOCKERR); +} + +static inline void pps_fill_timex(struct timex *txc) +{ + /* PPS is not implemented, so these are zero */ + txc->ppsfreq = 0; + txc->jitter = 0; + txc->shift = 0; + txc->stabil = 0; + txc->jitcnt = 0; + txc->calcnt = 0; + txc->errcnt = 0; + txc->stbcnt = 0; +} + +#endif /* CONFIG_NTP_PPS */ + + +/** + * ntp_synced - Returns 1 if the NTP status is not UNSYNC + * + */ +static inline int ntp_synced(void) +{ + return !(time_status & STA_UNSYNC); +} + + +/* + * NTP methods: + */ + +/* + * Update (tick_length, tick_length_base, tick_nsec), based + * on (tick_usec, ntp_tick_adj, time_freq): + */ +static void ntp_update_frequency(void) +{ + u64 second_length; + u64 new_base; + + second_length = (u64)(tick_usec * NSEC_PER_USEC * USER_HZ) + << NTP_SCALE_SHIFT; + + second_length += ntp_tick_adj; + second_length += time_freq; + + tick_nsec = div_u64(second_length, HZ) >> NTP_SCALE_SHIFT; + new_base = div_u64(second_length, NTP_INTERVAL_FREQ); + + /* + * Don't wait for the next second_overflow, apply + * the change to the tick length immediately: + */ + tick_length += new_base - tick_length_base; + tick_length_base = new_base; +} + +static inline s64 ntp_update_offset_fll(s64 offset64, long secs) +{ + time_status &= ~STA_MODE; + + if (secs < MINSEC) + return 0; + + if (!(time_status & STA_FLL) && (secs <= MAXSEC)) + return 0; + + time_status |= STA_MODE; + + return div64_long(offset64 << (NTP_SCALE_SHIFT - SHIFT_FLL), secs); +} + +static void ntp_update_offset(long offset) +{ + s64 freq_adj; + s64 offset64; + long secs; + + if (!(time_status & STA_PLL)) + return; + + if (!(time_status & STA_NANO)) + offset *= NSEC_PER_USEC; + + /* + * Scale the phase adjustment and + * clamp to the operating range. + */ + offset = min(offset, MAXPHASE); + offset = max(offset, -MAXPHASE); + + /* + * Select how the frequency is to be controlled + * and in which mode (PLL or FLL). + */ + secs = get_seconds() - time_reftime; + if (unlikely(time_status & STA_FREQHOLD)) + secs = 0; + + time_reftime = get_seconds(); + + offset64 = offset; + freq_adj = ntp_update_offset_fll(offset64, secs); + + /* + * Clamp update interval to reduce PLL gain with low + * sampling rate (e.g. intermittent network connection) + * to avoid instability. + */ + if (unlikely(secs > 1 << (SHIFT_PLL + 1 + time_constant))) + secs = 1 << (SHIFT_PLL + 1 + time_constant); + + freq_adj += (offset64 * secs) << + (NTP_SCALE_SHIFT - 2 * (SHIFT_PLL + 2 + time_constant)); + + freq_adj = min(freq_adj + time_freq, MAXFREQ_SCALED); + + time_freq = max(freq_adj, -MAXFREQ_SCALED); + + time_offset = div_s64(offset64 << NTP_SCALE_SHIFT, NTP_INTERVAL_FREQ); +} + +/** + * ntp_clear - Clears the NTP state variables + */ +void ntp_clear(void) +{ + time_adjust = 0; /* stop active adjtime() */ + time_status |= STA_UNSYNC; + time_maxerror = NTP_PHASE_LIMIT; + time_esterror = NTP_PHASE_LIMIT; + + ntp_update_frequency(); + + tick_length = tick_length_base; + time_offset = 0; + + /* Clear PPS state variables */ + pps_clear(); +} + + +u64 ntp_tick_length(void) +{ + return tick_length; +} + + +/* + * this routine handles the overflow of the microsecond field + * + * The tricky bits of code to handle the accurate clock support + * were provided by Dave Mills (Mills@UDEL.EDU) of NTP fame. + * They were originally developed for SUN and DEC kernels. + * All the kudos should go to Dave for this stuff. + * + * Also handles leap second processing, and returns leap offset + */ +int second_overflow(unsigned long secs) +{ + s64 delta; + int leap = 0; + + /* + * Leap second processing. If in leap-insert state at the end of the + * day, the system clock is set back one second; if in leap-delete + * state, the system clock is set ahead one second. + */ + switch (time_state) { + case TIME_OK: + if (time_status & STA_INS) + time_state = TIME_INS; + else if (time_status & STA_DEL) + time_state = TIME_DEL; + break; + case TIME_INS: + if (!(time_status & STA_INS)) + time_state = TIME_OK; + else if (secs % 86400 == 0) { + leap = -1; + time_state = TIME_OOP; + printk(KERN_NOTICE + "Clock: inserting leap second 23:59:60 UTC\n"); + } + break; + case TIME_DEL: + if (!(time_status & STA_DEL)) + time_state = TIME_OK; + else if ((secs + 1) % 86400 == 0) { + leap = 1; + time_state = TIME_WAIT; + printk(KERN_NOTICE + "Clock: deleting leap second 23:59:59 UTC\n"); + } + break; + case TIME_OOP: + time_state = TIME_WAIT; + break; + + case TIME_WAIT: + if (!(time_status & (STA_INS | STA_DEL))) + time_state = TIME_OK; + break; + } + + + /* Bump the maxerror field */ + time_maxerror += MAXFREQ / NSEC_PER_USEC; + if (time_maxerror > NTP_PHASE_LIMIT) { + time_maxerror = NTP_PHASE_LIMIT; + time_status |= STA_UNSYNC; + } + + /* Compute the phase adjustment for the next second */ + tick_length = tick_length_base; + + delta = ntp_offset_chunk(time_offset); + time_offset -= delta; + tick_length += delta; + + /* Check PPS signal */ + pps_dec_valid(); + + if (!time_adjust) + goto out; + + if (time_adjust > MAX_TICKADJ) { + time_adjust -= MAX_TICKADJ; + tick_length += MAX_TICKADJ_SCALED; + goto out; + } + + if (time_adjust < -MAX_TICKADJ) { + time_adjust += MAX_TICKADJ; + tick_length -= MAX_TICKADJ_SCALED; + goto out; + } + + tick_length += (s64)(time_adjust * NSEC_PER_USEC / NTP_INTERVAL_FREQ) + << NTP_SCALE_SHIFT; + time_adjust = 0; + +out: + return leap; +} + +#ifdef CONFIG_GENERIC_CMOS_UPDATE +int __weak update_persistent_clock64(struct timespec64 now64) +{ + struct timespec now; + + now = timespec64_to_timespec(now64); + return update_persistent_clock(now); +} +#endif + +#if defined(CONFIG_GENERIC_CMOS_UPDATE) || defined(CONFIG_RTC_SYSTOHC) +static void sync_cmos_clock(struct work_struct *work); + +static DECLARE_DELAYED_WORK(sync_cmos_work, sync_cmos_clock); + +static void sync_cmos_clock(struct work_struct *work) +{ + struct timespec64 now; + struct timespec next; + int fail = 1; + + /* + * If we have an externally synchronized Linux clock, then update + * CMOS clock accordingly every ~11 minutes. Set_rtc_mmss() has to be + * called as close as possible to 500 ms before the new second starts. + * This code is run on a timer. If the clock is set, that timer + * may not expire at the correct time. Thus, we adjust... + * We want the clock to be within a couple of ticks from the target. + */ + if (!ntp_synced()) { + /* + * Not synced, exit, do not restart a timer (if one is + * running, let it run out). + */ + return; + } + + getnstimeofday64(&now); + if (abs(now.tv_nsec - (NSEC_PER_SEC / 2)) <= tick_nsec * 5) { + struct timespec64 adjust = now; + + fail = -ENODEV; + if (persistent_clock_is_local) + adjust.tv_sec -= (sys_tz.tz_minuteswest * 60); +#ifdef CONFIG_GENERIC_CMOS_UPDATE + fail = update_persistent_clock64(adjust); +#endif + +#ifdef CONFIG_RTC_SYSTOHC + if (fail == -ENODEV) + fail = rtc_set_ntp_time(adjust); +#endif + } + + next.tv_nsec = (NSEC_PER_SEC / 2) - now.tv_nsec - (TICK_NSEC / 2); + if (next.tv_nsec <= 0) + next.tv_nsec += NSEC_PER_SEC; + + if (!fail || fail == -ENODEV) + next.tv_sec = 659; + else + next.tv_sec = 0; + + if (next.tv_nsec >= NSEC_PER_SEC) { + next.tv_sec++; + next.tv_nsec -= NSEC_PER_SEC; + } + queue_delayed_work(system_power_efficient_wq, + &sync_cmos_work, timespec_to_jiffies(&next)); +} + +#ifdef CONFIG_PREEMPT_RT_FULL +/* + * RT can not call schedule_delayed_work from real interrupt context. + * Need to make a thread to do the real work. + */ +static struct task_struct *cmos_delay_thread; +static bool do_cmos_delay; + +static int run_cmos_delay(void *ignore) +{ + while (!kthread_should_stop()) { + set_current_state(TASK_INTERRUPTIBLE); + if (do_cmos_delay) { + do_cmos_delay = false; + queue_delayed_work(system_power_efficient_wq, + &sync_cmos_work, 0); + } + schedule(); + } + __set_current_state(TASK_RUNNING); + return 0; +} + +void ntp_notify_cmos_timer(void) +{ + do_cmos_delay = true; + /* Make visible before waking up process */ + smp_wmb(); + wake_up_process(cmos_delay_thread); +} + +static __init int create_cmos_delay_thread(void) +{ + cmos_delay_thread = kthread_run(run_cmos_delay, NULL, "kcmosdelayd"); + BUG_ON(!cmos_delay_thread); + return 0; +} +early_initcall(create_cmos_delay_thread); + +#else + +void ntp_notify_cmos_timer(void) +{ + queue_delayed_work(system_power_efficient_wq, &sync_cmos_work, 0); +} +#endif /* CONFIG_PREEMPT_RT_FULL */ + +#else +void ntp_notify_cmos_timer(void) { } +#endif + + +/* + * Propagate a new txc->status value into the NTP state: + */ +static inline void process_adj_status(struct timex *txc, struct timespec64 *ts) +{ + if ((time_status & STA_PLL) && !(txc->status & STA_PLL)) { + time_state = TIME_OK; + time_status = STA_UNSYNC; + /* restart PPS frequency calibration */ + pps_reset_freq_interval(); + } + + /* + * If we turn on PLL adjustments then reset the + * reference time to current time. + */ + if (!(time_status & STA_PLL) && (txc->status & STA_PLL)) + time_reftime = get_seconds(); + + /* only set allowed bits */ + time_status &= STA_RONLY; + time_status |= txc->status & ~STA_RONLY; +} + + +static inline void process_adjtimex_modes(struct timex *txc, + struct timespec64 *ts, + s32 *time_tai) +{ + if (txc->modes & ADJ_STATUS) + process_adj_status(txc, ts); + + if (txc->modes & ADJ_NANO) + time_status |= STA_NANO; + + if (txc->modes & ADJ_MICRO) + time_status &= ~STA_NANO; + + if (txc->modes & ADJ_FREQUENCY) { + time_freq = txc->freq * PPM_SCALE; + time_freq = min(time_freq, MAXFREQ_SCALED); + time_freq = max(time_freq, -MAXFREQ_SCALED); + /* update pps_freq */ + pps_set_freq(time_freq); + } + + if (txc->modes & ADJ_MAXERROR) + time_maxerror = txc->maxerror; + + if (txc->modes & ADJ_ESTERROR) + time_esterror = txc->esterror; + + if (txc->modes & ADJ_TIMECONST) { + time_constant = txc->constant; + if (!(time_status & STA_NANO)) + time_constant += 4; + time_constant = min(time_constant, (long)MAXTC); + time_constant = max(time_constant, 0l); + } + + if (txc->modes & ADJ_TAI && txc->constant > 0) + *time_tai = txc->constant; + + if (txc->modes & ADJ_OFFSET) + ntp_update_offset(txc->offset); + + if (txc->modes & ADJ_TICK) + tick_usec = txc->tick; + + if (txc->modes & (ADJ_TICK|ADJ_FREQUENCY|ADJ_OFFSET)) + ntp_update_frequency(); +} + + + +/** + * ntp_validate_timex - Ensures the timex is ok for use in do_adjtimex + */ +int ntp_validate_timex(struct timex *txc) +{ + if (txc->modes & ADJ_ADJTIME) { + /* singleshot must not be used with any other mode bits */ + if (!(txc->modes & ADJ_OFFSET_SINGLESHOT)) + return -EINVAL; + if (!(txc->modes & ADJ_OFFSET_READONLY) && + !capable(CAP_SYS_TIME)) + return -EPERM; + } else { + /* In order to modify anything, you gotta be super-user! */ + if (txc->modes && !capable(CAP_SYS_TIME)) + return -EPERM; + /* + * if the quartz is off by more than 10% then + * something is VERY wrong! + */ + if (txc->modes & ADJ_TICK && + (txc->tick < 900000/USER_HZ || + txc->tick > 1100000/USER_HZ)) + return -EINVAL; + } + + if ((txc->modes & ADJ_SETOFFSET) && (!capable(CAP_SYS_TIME))) + return -EPERM; + + /* + * Check for potential multiplication overflows that can + * only happen on 64-bit systems: + */ + if ((txc->modes & ADJ_FREQUENCY) && (BITS_PER_LONG == 64)) { + if (LLONG_MIN / PPM_SCALE > txc->freq) + return -EINVAL; + if (LLONG_MAX / PPM_SCALE < txc->freq) + return -EINVAL; + } + + return 0; +} + + +/* + * adjtimex mainly allows reading (and writing, if superuser) of + * kernel time-keeping variables. used by xntpd. + */ +int __do_adjtimex(struct timex *txc, struct timespec64 *ts, s32 *time_tai) +{ + int result; + + if (txc->modes & ADJ_ADJTIME) { + long save_adjust = time_adjust; + + if (!(txc->modes & ADJ_OFFSET_READONLY)) { + /* adjtime() is independent from ntp_adjtime() */ + time_adjust = txc->offset; + ntp_update_frequency(); + } + txc->offset = save_adjust; + } else { + + /* If there are input parameters, then process them: */ + if (txc->modes) + process_adjtimex_modes(txc, ts, time_tai); + + txc->offset = shift_right(time_offset * NTP_INTERVAL_FREQ, + NTP_SCALE_SHIFT); + if (!(time_status & STA_NANO)) + txc->offset /= NSEC_PER_USEC; + } + + result = time_state; /* mostly `TIME_OK' */ + /* check for errors */ + if (is_error_status(time_status)) + result = TIME_ERROR; + + txc->freq = shift_right((time_freq >> PPM_SCALE_INV_SHIFT) * + PPM_SCALE_INV, NTP_SCALE_SHIFT); + txc->maxerror = time_maxerror; + txc->esterror = time_esterror; + txc->status = time_status; + txc->constant = time_constant; + txc->precision = 1; + txc->tolerance = MAXFREQ_SCALED / PPM_SCALE; + txc->tick = tick_usec; + txc->tai = *time_tai; + + /* fill PPS status fields */ + pps_fill_timex(txc); + + txc->time.tv_sec = (time_t)ts->tv_sec; + txc->time.tv_usec = ts->tv_nsec; + if (!(time_status & STA_NANO)) + txc->time.tv_usec /= NSEC_PER_USEC; + + return result; +} + +#ifdef CONFIG_NTP_PPS + +/* actually struct pps_normtime is good old struct timespec, but it is + * semantically different (and it is the reason why it was invented): + * pps_normtime.nsec has a range of ( -NSEC_PER_SEC / 2, NSEC_PER_SEC / 2 ] + * while timespec.tv_nsec has a range of [0, NSEC_PER_SEC) */ +struct pps_normtime { + __kernel_time_t sec; /* seconds */ + long nsec; /* nanoseconds */ +}; + +/* normalize the timestamp so that nsec is in the + ( -NSEC_PER_SEC / 2, NSEC_PER_SEC / 2 ] interval */ +static inline struct pps_normtime pps_normalize_ts(struct timespec ts) +{ + struct pps_normtime norm = { + .sec = ts.tv_sec, + .nsec = ts.tv_nsec + }; + + if (norm.nsec > (NSEC_PER_SEC >> 1)) { + norm.nsec -= NSEC_PER_SEC; + norm.sec++; + } + + return norm; +} + +/* get current phase correction and jitter */ +static inline long pps_phase_filter_get(long *jitter) +{ + *jitter = pps_tf[0] - pps_tf[1]; + if (*jitter < 0) + *jitter = -*jitter; + + /* TODO: test various filters */ + return pps_tf[0]; +} + +/* add the sample to the phase filter */ +static inline void pps_phase_filter_add(long err) +{ + pps_tf[2] = pps_tf[1]; + pps_tf[1] = pps_tf[0]; + pps_tf[0] = err; +} + +/* decrease frequency calibration interval length. + * It is halved after four consecutive unstable intervals. + */ +static inline void pps_dec_freq_interval(void) +{ + if (--pps_intcnt <= -PPS_INTCOUNT) { + pps_intcnt = -PPS_INTCOUNT; + if (pps_shift > PPS_INTMIN) { + pps_shift--; + pps_intcnt = 0; + } + } +} + +/* increase frequency calibration interval length. + * It is doubled after four consecutive stable intervals. + */ +static inline void pps_inc_freq_interval(void) +{ + if (++pps_intcnt >= PPS_INTCOUNT) { + pps_intcnt = PPS_INTCOUNT; + if (pps_shift < PPS_INTMAX) { + pps_shift++; + pps_intcnt = 0; + } + } +} + +/* update clock frequency based on MONOTONIC_RAW clock PPS signal + * timestamps + * + * At the end of the calibration interval the difference between the + * first and last MONOTONIC_RAW clock timestamps divided by the length + * of the interval becomes the frequency update. If the interval was + * too long, the data are discarded. + * Returns the difference between old and new frequency values. + */ +static long hardpps_update_freq(struct pps_normtime freq_norm) +{ + long delta, delta_mod; + s64 ftemp; + + /* check if the frequency interval was too long */ + if (freq_norm.sec > (2 << pps_shift)) { + time_status |= STA_PPSERROR; + pps_errcnt++; + pps_dec_freq_interval(); + printk_deferred(KERN_ERR + "hardpps: PPSERROR: interval too long - %ld s\n", + freq_norm.sec); + return 0; + } + + /* here the raw frequency offset and wander (stability) is + * calculated. If the wander is less than the wander threshold + * the interval is increased; otherwise it is decreased. + */ + ftemp = div_s64(((s64)(-freq_norm.nsec)) << NTP_SCALE_SHIFT, + freq_norm.sec); + delta = shift_right(ftemp - pps_freq, NTP_SCALE_SHIFT); + pps_freq = ftemp; + if (delta > PPS_MAXWANDER || delta < -PPS_MAXWANDER) { + printk_deferred(KERN_WARNING + "hardpps: PPSWANDER: change=%ld\n", delta); + time_status |= STA_PPSWANDER; + pps_stbcnt++; + pps_dec_freq_interval(); + } else { /* good sample */ + pps_inc_freq_interval(); + } + + /* the stability metric is calculated as the average of recent + * frequency changes, but is used only for performance + * monitoring + */ + delta_mod = delta; + if (delta_mod < 0) + delta_mod = -delta_mod; + pps_stabil += (div_s64(((s64)delta_mod) << + (NTP_SCALE_SHIFT - SHIFT_USEC), + NSEC_PER_USEC) - pps_stabil) >> PPS_INTMIN; + + /* if enabled, the system clock frequency is updated */ + if ((time_status & STA_PPSFREQ) != 0 && + (time_status & STA_FREQHOLD) == 0) { + time_freq = pps_freq; + ntp_update_frequency(); + } + + return delta; +} + +/* correct REALTIME clock phase error against PPS signal */ +static void hardpps_update_phase(long error) +{ + long correction = -error; + long jitter; + + /* add the sample to the median filter */ + pps_phase_filter_add(correction); + correction = pps_phase_filter_get(&jitter); + + /* Nominal jitter is due to PPS signal noise. If it exceeds the + * threshold, the sample is discarded; otherwise, if so enabled, + * the time offset is updated. + */ + if (jitter > (pps_jitter << PPS_POPCORN)) { + printk_deferred(KERN_WARNING + "hardpps: PPSJITTER: jitter=%ld, limit=%ld\n", + jitter, (pps_jitter << PPS_POPCORN)); + time_status |= STA_PPSJITTER; + pps_jitcnt++; + } else if (time_status & STA_PPSTIME) { + /* correct the time using the phase offset */ + time_offset = div_s64(((s64)correction) << NTP_SCALE_SHIFT, + NTP_INTERVAL_FREQ); + /* cancel running adjtime() */ + time_adjust = 0; + } + /* update jitter */ + pps_jitter += (jitter - pps_jitter) >> PPS_INTMIN; +} + +/* + * __hardpps() - discipline CPU clock oscillator to external PPS signal + * + * This routine is called at each PPS signal arrival in order to + * discipline the CPU clock oscillator to the PPS signal. It takes two + * parameters: REALTIME and MONOTONIC_RAW clock timestamps. The former + * is used to correct clock phase error and the latter is used to + * correct the frequency. + * + * This code is based on David Mills's reference nanokernel + * implementation. It was mostly rewritten but keeps the same idea. + */ +void __hardpps(const struct timespec *phase_ts, const struct timespec *raw_ts) +{ + struct pps_normtime pts_norm, freq_norm; + + pts_norm = pps_normalize_ts(*phase_ts); + + /* clear the error bits, they will be set again if needed */ + time_status &= ~(STA_PPSJITTER | STA_PPSWANDER | STA_PPSERROR); + + /* indicate signal presence */ + time_status |= STA_PPSSIGNAL; + pps_valid = PPS_VALID; + + /* when called for the first time, + * just start the frequency interval */ + if (unlikely(pps_fbase.tv_sec == 0)) { + pps_fbase = *raw_ts; + return; + } + + /* ok, now we have a base for frequency calculation */ + freq_norm = pps_normalize_ts(timespec_sub(*raw_ts, pps_fbase)); + + /* check that the signal is in the range + * [1s - MAXFREQ us, 1s + MAXFREQ us], otherwise reject it */ + if ((freq_norm.sec == 0) || + (freq_norm.nsec > MAXFREQ * freq_norm.sec) || + (freq_norm.nsec < -MAXFREQ * freq_norm.sec)) { + time_status |= STA_PPSJITTER; + /* restart the frequency calibration interval */ + pps_fbase = *raw_ts; + printk_deferred(KERN_ERR "hardpps: PPSJITTER: bad pulse\n"); + return; + } + + /* signal is ok */ + + /* check if the current frequency interval is finished */ + if (freq_norm.sec >= (1 << pps_shift)) { + pps_calcnt++; + /* restart the frequency calibration interval */ + pps_fbase = *raw_ts; + hardpps_update_freq(freq_norm); + } + + hardpps_update_phase(pts_norm.nsec); + +} +#endif /* CONFIG_NTP_PPS */ + +static int __init ntp_tick_adj_setup(char *str) +{ + int rc = kstrtol(str, 0, (long *)&ntp_tick_adj); + + if (rc) + return rc; + ntp_tick_adj <<= NTP_SCALE_SHIFT; + + return 1; +} + +__setup("ntp_tick_adj=", ntp_tick_adj_setup); + +void __init ntp_init(void) +{ + ntp_clear(); +} diff --git a/kernel/kernel/time/ntp_internal.h b/kernel/kernel/time/ntp_internal.h new file mode 100644 index 000000000..bbd102ad9 --- /dev/null +++ b/kernel/kernel/time/ntp_internal.h @@ -0,0 +1,12 @@ +#ifndef _LINUX_NTP_INTERNAL_H +#define _LINUX_NTP_INTERNAL_H + +extern void ntp_init(void); +extern void ntp_clear(void); +/* Returns how long ticks are at present, in ns / 2^NTP_SCALE_SHIFT. */ +extern u64 ntp_tick_length(void); +extern int second_overflow(unsigned long secs); +extern int ntp_validate_timex(struct timex *); +extern int __do_adjtimex(struct timex *, struct timespec64 *, s32 *); +extern void __hardpps(const struct timespec *, const struct timespec *); +#endif /* _LINUX_NTP_INTERNAL_H */ diff --git a/kernel/kernel/time/posix-clock.c b/kernel/kernel/time/posix-clock.c new file mode 100644 index 000000000..ce033c7aa --- /dev/null +++ b/kernel/kernel/time/posix-clock.c @@ -0,0 +1,446 @@ +/* + * posix-clock.c - support for dynamic clock devices + * + * Copyright (C) 2010 OMICRON electronics GmbH + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. + */ +#include +#include +#include +#include +#include +#include +#include + +static void delete_clock(struct kref *kref); + +/* + * Returns NULL if the posix_clock instance attached to 'fp' is old and stale. + */ +static struct posix_clock *get_posix_clock(struct file *fp) +{ + struct posix_clock *clk = fp->private_data; + + down_read(&clk->rwsem); + + if (!clk->zombie) + return clk; + + up_read(&clk->rwsem); + + return NULL; +} + +static void put_posix_clock(struct posix_clock *clk) +{ + up_read(&clk->rwsem); +} + +static ssize_t posix_clock_read(struct file *fp, char __user *buf, + size_t count, loff_t *ppos) +{ + struct posix_clock *clk = get_posix_clock(fp); + int err = -EINVAL; + + if (!clk) + return -ENODEV; + + if (clk->ops.read) + err = clk->ops.read(clk, fp->f_flags, buf, count); + + put_posix_clock(clk); + + return err; +} + +static unsigned int posix_clock_poll(struct file *fp, poll_table *wait) +{ + struct posix_clock *clk = get_posix_clock(fp); + int result = 0; + + if (!clk) + return -ENODEV; + + if (clk->ops.poll) + result = clk->ops.poll(clk, fp, wait); + + put_posix_clock(clk); + + return result; +} + +static int posix_clock_fasync(int fd, struct file *fp, int on) +{ + struct posix_clock *clk = get_posix_clock(fp); + int err = 0; + + if (!clk) + return -ENODEV; + + if (clk->ops.fasync) + err = clk->ops.fasync(clk, fd, fp, on); + + put_posix_clock(clk); + + return err; +} + +static int posix_clock_mmap(struct file *fp, struct vm_area_struct *vma) +{ + struct posix_clock *clk = get_posix_clock(fp); + int err = -ENODEV; + + if (!clk) + return -ENODEV; + + if (clk->ops.mmap) + err = clk->ops.mmap(clk, vma); + + put_posix_clock(clk); + + return err; +} + +static long posix_clock_ioctl(struct file *fp, + unsigned int cmd, unsigned long arg) +{ + struct posix_clock *clk = get_posix_clock(fp); + int err = -ENOTTY; + + if (!clk) + return -ENODEV; + + if (clk->ops.ioctl) + err = clk->ops.ioctl(clk, cmd, arg); + + put_posix_clock(clk); + + return err; +} + +#ifdef CONFIG_COMPAT +static long posix_clock_compat_ioctl(struct file *fp, + unsigned int cmd, unsigned long arg) +{ + struct posix_clock *clk = get_posix_clock(fp); + int err = -ENOTTY; + + if (!clk) + return -ENODEV; + + if (clk->ops.ioctl) + err = clk->ops.ioctl(clk, cmd, arg); + + put_posix_clock(clk); + + return err; +} +#endif + +static int posix_clock_open(struct inode *inode, struct file *fp) +{ + int err; + struct posix_clock *clk = + container_of(inode->i_cdev, struct posix_clock, cdev); + + down_read(&clk->rwsem); + + if (clk->zombie) { + err = -ENODEV; + goto out; + } + if (clk->ops.open) + err = clk->ops.open(clk, fp->f_mode); + else + err = 0; + + if (!err) { + kref_get(&clk->kref); + fp->private_data = clk; + } +out: + up_read(&clk->rwsem); + return err; +} + +static int posix_clock_release(struct inode *inode, struct file *fp) +{ + struct posix_clock *clk = fp->private_data; + int err = 0; + + if (clk->ops.release) + err = clk->ops.release(clk); + + kref_put(&clk->kref, delete_clock); + + fp->private_data = NULL; + + return err; +} + +static const struct file_operations posix_clock_file_operations = { + .owner = THIS_MODULE, + .llseek = no_llseek, + .read = posix_clock_read, + .poll = posix_clock_poll, + .unlocked_ioctl = posix_clock_ioctl, + .open = posix_clock_open, + .release = posix_clock_release, + .fasync = posix_clock_fasync, + .mmap = posix_clock_mmap, +#ifdef CONFIG_COMPAT + .compat_ioctl = posix_clock_compat_ioctl, +#endif +}; + +int posix_clock_register(struct posix_clock *clk, dev_t devid) +{ + int err; + + kref_init(&clk->kref); + init_rwsem(&clk->rwsem); + + cdev_init(&clk->cdev, &posix_clock_file_operations); + clk->cdev.owner = clk->ops.owner; + err = cdev_add(&clk->cdev, devid, 1); + + return err; +} +EXPORT_SYMBOL_GPL(posix_clock_register); + +static void delete_clock(struct kref *kref) +{ + struct posix_clock *clk = container_of(kref, struct posix_clock, kref); + + if (clk->release) + clk->release(clk); +} + +void posix_clock_unregister(struct posix_clock *clk) +{ + cdev_del(&clk->cdev); + + down_write(&clk->rwsem); + clk->zombie = true; + up_write(&clk->rwsem); + + kref_put(&clk->kref, delete_clock); +} +EXPORT_SYMBOL_GPL(posix_clock_unregister); + +struct posix_clock_desc { + struct file *fp; + struct posix_clock *clk; +}; + +static int get_clock_desc(const clockid_t id, struct posix_clock_desc *cd) +{ + struct file *fp = fget(CLOCKID_TO_FD(id)); + int err = -EINVAL; + + if (!fp) + return err; + + if (fp->f_op->open != posix_clock_open || !fp->private_data) + goto out; + + cd->fp = fp; + cd->clk = get_posix_clock(fp); + + err = cd->clk ? 0 : -ENODEV; +out: + if (err) + fput(fp); + return err; +} + +static void put_clock_desc(struct posix_clock_desc *cd) +{ + put_posix_clock(cd->clk); + fput(cd->fp); +} + +static int pc_clock_adjtime(clockid_t id, struct timex *tx) +{ + struct posix_clock_desc cd; + int err; + + err = get_clock_desc(id, &cd); + if (err) + return err; + + if ((cd.fp->f_mode & FMODE_WRITE) == 0) { + err = -EACCES; + goto out; + } + + if (cd.clk->ops.clock_adjtime) + err = cd.clk->ops.clock_adjtime(cd.clk, tx); + else + err = -EOPNOTSUPP; +out: + put_clock_desc(&cd); + + return err; +} + +static int pc_clock_gettime(clockid_t id, struct timespec *ts) +{ + struct posix_clock_desc cd; + int err; + + err = get_clock_desc(id, &cd); + if (err) + return err; + + if (cd.clk->ops.clock_gettime) + err = cd.clk->ops.clock_gettime(cd.clk, ts); + else + err = -EOPNOTSUPP; + + put_clock_desc(&cd); + + return err; +} + +static int pc_clock_getres(clockid_t id, struct timespec *ts) +{ + struct posix_clock_desc cd; + int err; + + err = get_clock_desc(id, &cd); + if (err) + return err; + + if (cd.clk->ops.clock_getres) + err = cd.clk->ops.clock_getres(cd.clk, ts); + else + err = -EOPNOTSUPP; + + put_clock_desc(&cd); + + return err; +} + +static int pc_clock_settime(clockid_t id, const struct timespec *ts) +{ + struct posix_clock_desc cd; + int err; + + err = get_clock_desc(id, &cd); + if (err) + return err; + + if ((cd.fp->f_mode & FMODE_WRITE) == 0) { + err = -EACCES; + goto out; + } + + if (cd.clk->ops.clock_settime) + err = cd.clk->ops.clock_settime(cd.clk, ts); + else + err = -EOPNOTSUPP; +out: + put_clock_desc(&cd); + + return err; +} + +static int pc_timer_create(struct k_itimer *kit) +{ + clockid_t id = kit->it_clock; + struct posix_clock_desc cd; + int err; + + err = get_clock_desc(id, &cd); + if (err) + return err; + + if (cd.clk->ops.timer_create) + err = cd.clk->ops.timer_create(cd.clk, kit); + else + err = -EOPNOTSUPP; + + put_clock_desc(&cd); + + return err; +} + +static int pc_timer_delete(struct k_itimer *kit) +{ + clockid_t id = kit->it_clock; + struct posix_clock_desc cd; + int err; + + err = get_clock_desc(id, &cd); + if (err) + return err; + + if (cd.clk->ops.timer_delete) + err = cd.clk->ops.timer_delete(cd.clk, kit); + else + err = -EOPNOTSUPP; + + put_clock_desc(&cd); + + return err; +} + +static void pc_timer_gettime(struct k_itimer *kit, struct itimerspec *ts) +{ + clockid_t id = kit->it_clock; + struct posix_clock_desc cd; + + if (get_clock_desc(id, &cd)) + return; + + if (cd.clk->ops.timer_gettime) + cd.clk->ops.timer_gettime(cd.clk, kit, ts); + + put_clock_desc(&cd); +} + +static int pc_timer_settime(struct k_itimer *kit, int flags, + struct itimerspec *ts, struct itimerspec *old) +{ + clockid_t id = kit->it_clock; + struct posix_clock_desc cd; + int err; + + err = get_clock_desc(id, &cd); + if (err) + return err; + + if (cd.clk->ops.timer_settime) + err = cd.clk->ops.timer_settime(cd.clk, kit, flags, ts, old); + else + err = -EOPNOTSUPP; + + put_clock_desc(&cd); + + return err; +} + +struct k_clock clock_posix_dynamic = { + .clock_getres = pc_clock_getres, + .clock_set = pc_clock_settime, + .clock_get = pc_clock_gettime, + .clock_adj = pc_clock_adjtime, + .timer_create = pc_timer_create, + .timer_set = pc_timer_settime, + .timer_del = pc_timer_delete, + .timer_get = pc_timer_gettime, +}; diff --git a/kernel/kernel/time/posix-cpu-timers.c b/kernel/kernel/time/posix-cpu-timers.c new file mode 100644 index 000000000..c8c7150f2 --- /dev/null +++ b/kernel/kernel/time/posix-cpu-timers.c @@ -0,0 +1,1661 @@ +/* + * Implement CPU time clocks for the POSIX clock interface. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +/* + * Called after updating RLIMIT_CPU to run cpu timer and update + * tsk->signal->cputime_expires expiration cache if necessary. Needs + * siglock protection since other code may update expiration cache as + * well. + */ +void update_rlimit_cpu(struct task_struct *task, unsigned long rlim_new) +{ + cputime_t cputime = secs_to_cputime(rlim_new); + + spin_lock_irq(&task->sighand->siglock); + set_process_cpu_timer(task, CPUCLOCK_PROF, &cputime, NULL); + spin_unlock_irq(&task->sighand->siglock); +} + +static int check_clock(const clockid_t which_clock) +{ + int error = 0; + struct task_struct *p; + const pid_t pid = CPUCLOCK_PID(which_clock); + + if (CPUCLOCK_WHICH(which_clock) >= CPUCLOCK_MAX) + return -EINVAL; + + if (pid == 0) + return 0; + + rcu_read_lock(); + p = find_task_by_vpid(pid); + if (!p || !(CPUCLOCK_PERTHREAD(which_clock) ? + same_thread_group(p, current) : has_group_leader_pid(p))) { + error = -EINVAL; + } + rcu_read_unlock(); + + return error; +} + +static inline unsigned long long +timespec_to_sample(const clockid_t which_clock, const struct timespec *tp) +{ + unsigned long long ret; + + ret = 0; /* high half always zero when .cpu used */ + if (CPUCLOCK_WHICH(which_clock) == CPUCLOCK_SCHED) { + ret = (unsigned long long)tp->tv_sec * NSEC_PER_SEC + tp->tv_nsec; + } else { + ret = cputime_to_expires(timespec_to_cputime(tp)); + } + return ret; +} + +static void sample_to_timespec(const clockid_t which_clock, + unsigned long long expires, + struct timespec *tp) +{ + if (CPUCLOCK_WHICH(which_clock) == CPUCLOCK_SCHED) + *tp = ns_to_timespec(expires); + else + cputime_to_timespec((__force cputime_t)expires, tp); +} + +/* + * Update expiry time from increment, and increase overrun count, + * given the current clock sample. + */ +static void bump_cpu_timer(struct k_itimer *timer, + unsigned long long now) +{ + int i; + unsigned long long delta, incr; + + if (timer->it.cpu.incr == 0) + return; + + if (now < timer->it.cpu.expires) + return; + + incr = timer->it.cpu.incr; + delta = now + incr - timer->it.cpu.expires; + + /* Don't use (incr*2 < delta), incr*2 might overflow. */ + for (i = 0; incr < delta - incr; i++) + incr = incr << 1; + + for (; i >= 0; incr >>= 1, i--) { + if (delta < incr) + continue; + + timer->it.cpu.expires += incr; + timer->it_overrun += 1 << i; + delta -= incr; + } +} + +/** + * task_cputime_zero - Check a task_cputime struct for all zero fields. + * + * @cputime: The struct to compare. + * + * Checks @cputime to see if all fields are zero. Returns true if all fields + * are zero, false if any field is nonzero. + */ +static inline int task_cputime_zero(const struct task_cputime *cputime) +{ + if (!cputime->utime && !cputime->stime && !cputime->sum_exec_runtime) + return 1; + return 0; +} + +static inline unsigned long long prof_ticks(struct task_struct *p) +{ + cputime_t utime, stime; + + task_cputime(p, &utime, &stime); + + return cputime_to_expires(utime + stime); +} +static inline unsigned long long virt_ticks(struct task_struct *p) +{ + cputime_t utime; + + task_cputime(p, &utime, NULL); + + return cputime_to_expires(utime); +} + +static int +posix_cpu_clock_getres(const clockid_t which_clock, struct timespec *tp) +{ + int error = check_clock(which_clock); + if (!error) { + tp->tv_sec = 0; + tp->tv_nsec = ((NSEC_PER_SEC + HZ - 1) / HZ); + if (CPUCLOCK_WHICH(which_clock) == CPUCLOCK_SCHED) { + /* + * If sched_clock is using a cycle counter, we + * don't have any idea of its true resolution + * exported, but it is much more than 1s/HZ. + */ + tp->tv_nsec = 1; + } + } + return error; +} + +static int +posix_cpu_clock_set(const clockid_t which_clock, const struct timespec *tp) +{ + /* + * You can never reset a CPU clock, but we check for other errors + * in the call before failing with EPERM. + */ + int error = check_clock(which_clock); + if (error == 0) { + error = -EPERM; + } + return error; +} + + +/* + * Sample a per-thread clock for the given task. + */ +static int cpu_clock_sample(const clockid_t which_clock, struct task_struct *p, + unsigned long long *sample) +{ + switch (CPUCLOCK_WHICH(which_clock)) { + default: + return -EINVAL; + case CPUCLOCK_PROF: + *sample = prof_ticks(p); + break; + case CPUCLOCK_VIRT: + *sample = virt_ticks(p); + break; + case CPUCLOCK_SCHED: + *sample = task_sched_runtime(p); + break; + } + return 0; +} + +static void update_gt_cputime(struct task_cputime *a, struct task_cputime *b) +{ + if (b->utime > a->utime) + a->utime = b->utime; + + if (b->stime > a->stime) + a->stime = b->stime; + + if (b->sum_exec_runtime > a->sum_exec_runtime) + a->sum_exec_runtime = b->sum_exec_runtime; +} + +void thread_group_cputimer(struct task_struct *tsk, struct task_cputime *times) +{ + struct thread_group_cputimer *cputimer = &tsk->signal->cputimer; + struct task_cputime sum; + unsigned long flags; + + if (!cputimer->running) { + /* + * The POSIX timer interface allows for absolute time expiry + * values through the TIMER_ABSTIME flag, therefore we have + * to synchronize the timer to the clock every time we start + * it. + */ + thread_group_cputime(tsk, &sum); + raw_spin_lock_irqsave(&cputimer->lock, flags); + cputimer->running = 1; + update_gt_cputime(&cputimer->cputime, &sum); + } else + raw_spin_lock_irqsave(&cputimer->lock, flags); + *times = cputimer->cputime; + raw_spin_unlock_irqrestore(&cputimer->lock, flags); +} + +/* + * Sample a process (thread group) clock for the given group_leader task. + * Must be called with task sighand lock held for safe while_each_thread() + * traversal. + */ +static int cpu_clock_sample_group(const clockid_t which_clock, + struct task_struct *p, + unsigned long long *sample) +{ + struct task_cputime cputime; + + switch (CPUCLOCK_WHICH(which_clock)) { + default: + return -EINVAL; + case CPUCLOCK_PROF: + thread_group_cputime(p, &cputime); + *sample = cputime_to_expires(cputime.utime + cputime.stime); + break; + case CPUCLOCK_VIRT: + thread_group_cputime(p, &cputime); + *sample = cputime_to_expires(cputime.utime); + break; + case CPUCLOCK_SCHED: + thread_group_cputime(p, &cputime); + *sample = cputime.sum_exec_runtime; + break; + } + return 0; +} + +static int posix_cpu_clock_get_task(struct task_struct *tsk, + const clockid_t which_clock, + struct timespec *tp) +{ + int err = -EINVAL; + unsigned long long rtn; + + if (CPUCLOCK_PERTHREAD(which_clock)) { + if (same_thread_group(tsk, current)) + err = cpu_clock_sample(which_clock, tsk, &rtn); + } else { + if (tsk == current || thread_group_leader(tsk)) + err = cpu_clock_sample_group(which_clock, tsk, &rtn); + } + + if (!err) + sample_to_timespec(which_clock, rtn, tp); + + return err; +} + + +static int posix_cpu_clock_get(const clockid_t which_clock, struct timespec *tp) +{ + const pid_t pid = CPUCLOCK_PID(which_clock); + int err = -EINVAL; + + if (pid == 0) { + /* + * Special case constant value for our own clocks. + * We don't have to do any lookup to find ourselves. + */ + err = posix_cpu_clock_get_task(current, which_clock, tp); + } else { + /* + * Find the given PID, and validate that the caller + * should be able to see it. + */ + struct task_struct *p; + rcu_read_lock(); + p = find_task_by_vpid(pid); + if (p) + err = posix_cpu_clock_get_task(p, which_clock, tp); + rcu_read_unlock(); + } + + return err; +} + + +/* + * Validate the clockid_t for a new CPU-clock timer, and initialize the timer. + * This is called from sys_timer_create() and do_cpu_nanosleep() with the + * new timer already all-zeros initialized. + */ +static int posix_cpu_timer_create(struct k_itimer *new_timer) +{ + int ret = 0; + const pid_t pid = CPUCLOCK_PID(new_timer->it_clock); + struct task_struct *p; + + if (CPUCLOCK_WHICH(new_timer->it_clock) >= CPUCLOCK_MAX) + return -EINVAL; + + INIT_LIST_HEAD(&new_timer->it.cpu.entry); + + rcu_read_lock(); + if (CPUCLOCK_PERTHREAD(new_timer->it_clock)) { + if (pid == 0) { + p = current; + } else { + p = find_task_by_vpid(pid); + if (p && !same_thread_group(p, current)) + p = NULL; + } + } else { + if (pid == 0) { + p = current->group_leader; + } else { + p = find_task_by_vpid(pid); + if (p && !has_group_leader_pid(p)) + p = NULL; + } + } + new_timer->it.cpu.task = p; + if (p) { + get_task_struct(p); + } else { + ret = -EINVAL; + } + rcu_read_unlock(); + + return ret; +} + +/* + * Clean up a CPU-clock timer that is about to be destroyed. + * This is called from timer deletion with the timer already locked. + * If we return TIMER_RETRY, it's necessary to release the timer's lock + * and try again. (This happens when the timer is in the middle of firing.) + */ +static int posix_cpu_timer_del(struct k_itimer *timer) +{ + int ret = 0; + unsigned long flags; + struct sighand_struct *sighand; + struct task_struct *p = timer->it.cpu.task; + + WARN_ON_ONCE(p == NULL); + + /* + * Protect against sighand release/switch in exit/exec and process/ + * thread timer list entry concurrent read/writes. + */ + sighand = lock_task_sighand(p, &flags); + if (unlikely(sighand == NULL)) { + /* + * We raced with the reaping of the task. + * The deletion should have cleared us off the list. + */ + WARN_ON_ONCE(!list_empty(&timer->it.cpu.entry)); + } else { + if (timer->it.cpu.firing) + ret = TIMER_RETRY; + else + list_del(&timer->it.cpu.entry); + + unlock_task_sighand(p, &flags); + } + + if (!ret) + put_task_struct(p); + + return ret; +} + +static void cleanup_timers_list(struct list_head *head) +{ + struct cpu_timer_list *timer, *next; + + list_for_each_entry_safe(timer, next, head, entry) + list_del_init(&timer->entry); +} + +/* + * Clean out CPU timers still ticking when a thread exited. The task + * pointer is cleared, and the expiry time is replaced with the residual + * time for later timer_gettime calls to return. + * This must be called with the siglock held. + */ +static void cleanup_timers(struct list_head *head) +{ + cleanup_timers_list(head); + cleanup_timers_list(++head); + cleanup_timers_list(++head); +} + +/* + * These are both called with the siglock held, when the current thread + * is being reaped. When the final (leader) thread in the group is reaped, + * posix_cpu_timers_exit_group will be called after posix_cpu_timers_exit. + */ +void posix_cpu_timers_exit(struct task_struct *tsk) +{ + add_device_randomness((const void*) &tsk->se.sum_exec_runtime, + sizeof(unsigned long long)); + cleanup_timers(tsk->cpu_timers); + +} +void posix_cpu_timers_exit_group(struct task_struct *tsk) +{ + cleanup_timers(tsk->signal->cpu_timers); +} + +static inline int expires_gt(cputime_t expires, cputime_t new_exp) +{ + return expires == 0 || expires > new_exp; +} + +/* + * Insert the timer on the appropriate list before any timers that + * expire later. This must be called with the sighand lock held. + */ +static void arm_timer(struct k_itimer *timer) +{ + struct task_struct *p = timer->it.cpu.task; + struct list_head *head, *listpos; + struct task_cputime *cputime_expires; + struct cpu_timer_list *const nt = &timer->it.cpu; + struct cpu_timer_list *next; + + if (CPUCLOCK_PERTHREAD(timer->it_clock)) { + head = p->cpu_timers; + cputime_expires = &p->cputime_expires; + } else { + head = p->signal->cpu_timers; + cputime_expires = &p->signal->cputime_expires; + } + head += CPUCLOCK_WHICH(timer->it_clock); + + listpos = head; + list_for_each_entry(next, head, entry) { + if (nt->expires < next->expires) + break; + listpos = &next->entry; + } + list_add(&nt->entry, listpos); + + if (listpos == head) { + unsigned long long exp = nt->expires; + + /* + * We are the new earliest-expiring POSIX 1.b timer, hence + * need to update expiration cache. Take into account that + * for process timers we share expiration cache with itimers + * and RLIMIT_CPU and for thread timers with RLIMIT_RTTIME. + */ + + switch (CPUCLOCK_WHICH(timer->it_clock)) { + case CPUCLOCK_PROF: + if (expires_gt(cputime_expires->prof_exp, expires_to_cputime(exp))) + cputime_expires->prof_exp = expires_to_cputime(exp); + break; + case CPUCLOCK_VIRT: + if (expires_gt(cputime_expires->virt_exp, expires_to_cputime(exp))) + cputime_expires->virt_exp = expires_to_cputime(exp); + break; + case CPUCLOCK_SCHED: + if (cputime_expires->sched_exp == 0 || + cputime_expires->sched_exp > exp) + cputime_expires->sched_exp = exp; + break; + } + } +} + +/* + * The timer is locked, fire it and arrange for its reload. + */ +static void cpu_timer_fire(struct k_itimer *timer) +{ + if ((timer->it_sigev_notify & ~SIGEV_THREAD_ID) == SIGEV_NONE) { + /* + * User don't want any signal. + */ + timer->it.cpu.expires = 0; + } else if (unlikely(timer->sigq == NULL)) { + /* + * This a special case for clock_nanosleep, + * not a normal timer from sys_timer_create. + */ + wake_up_process(timer->it_process); + timer->it.cpu.expires = 0; + } else if (timer->it.cpu.incr == 0) { + /* + * One-shot timer. Clear it as soon as it's fired. + */ + posix_timer_event(timer, 0); + timer->it.cpu.expires = 0; + } else if (posix_timer_event(timer, ++timer->it_requeue_pending)) { + /* + * The signal did not get queued because the signal + * was ignored, so we won't get any callback to + * reload the timer. But we need to keep it + * ticking in case the signal is deliverable next time. + */ + posix_cpu_timer_schedule(timer); + } +} + +/* + * Sample a process (thread group) timer for the given group_leader task. + * Must be called with task sighand lock held for safe while_each_thread() + * traversal. + */ +static int cpu_timer_sample_group(const clockid_t which_clock, + struct task_struct *p, + unsigned long long *sample) +{ + struct task_cputime cputime; + + thread_group_cputimer(p, &cputime); + switch (CPUCLOCK_WHICH(which_clock)) { + default: + return -EINVAL; + case CPUCLOCK_PROF: + *sample = cputime_to_expires(cputime.utime + cputime.stime); + break; + case CPUCLOCK_VIRT: + *sample = cputime_to_expires(cputime.utime); + break; + case CPUCLOCK_SCHED: + *sample = cputime.sum_exec_runtime; + break; + } + return 0; +} + +#ifdef CONFIG_NO_HZ_FULL +static void nohz_kick_work_fn(struct work_struct *work) +{ + tick_nohz_full_kick_all(); +} + +static DECLARE_WORK(nohz_kick_work, nohz_kick_work_fn); + +/* + * We need the IPIs to be sent from sane process context. + * The posix cpu timers are always set with irqs disabled. + */ +static void posix_cpu_timer_kick_nohz(void) +{ + if (context_tracking_is_enabled()) + schedule_work(&nohz_kick_work); +} + +bool posix_cpu_timers_can_stop_tick(struct task_struct *tsk) +{ + if (!task_cputime_zero(&tsk->cputime_expires)) + return false; + + if (tsk->signal->cputimer.running) + return false; + + return true; +} +#else +static inline void posix_cpu_timer_kick_nohz(void) { } +#endif + +/* + * Guts of sys_timer_settime for CPU timers. + * This is called with the timer locked and interrupts disabled. + * If we return TIMER_RETRY, it's necessary to release the timer's lock + * and try again. (This happens when the timer is in the middle of firing.) + */ +static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags, + struct itimerspec *new, struct itimerspec *old) +{ + unsigned long flags; + struct sighand_struct *sighand; + struct task_struct *p = timer->it.cpu.task; + unsigned long long old_expires, new_expires, old_incr, val; + int ret; + + WARN_ON_ONCE(p == NULL); + + new_expires = timespec_to_sample(timer->it_clock, &new->it_value); + + /* + * Protect against sighand release/switch in exit/exec and p->cpu_timers + * and p->signal->cpu_timers read/write in arm_timer() + */ + sighand = lock_task_sighand(p, &flags); + /* + * If p has just been reaped, we can no + * longer get any information about it at all. + */ + if (unlikely(sighand == NULL)) { + return -ESRCH; + } + + /* + * Disarm any old timer after extracting its expiry time. + */ + WARN_ON_ONCE_NONRT(!irqs_disabled()); + + ret = 0; + old_incr = timer->it.cpu.incr; + old_expires = timer->it.cpu.expires; + if (unlikely(timer->it.cpu.firing)) { + timer->it.cpu.firing = -1; + ret = TIMER_RETRY; + } else + list_del_init(&timer->it.cpu.entry); + + /* + * We need to sample the current value to convert the new + * value from to relative and absolute, and to convert the + * old value from absolute to relative. To set a process + * timer, we need a sample to balance the thread expiry + * times (in arm_timer). With an absolute time, we must + * check if it's already passed. In short, we need a sample. + */ + if (CPUCLOCK_PERTHREAD(timer->it_clock)) { + cpu_clock_sample(timer->it_clock, p, &val); + } else { + cpu_timer_sample_group(timer->it_clock, p, &val); + } + + if (old) { + if (old_expires == 0) { + old->it_value.tv_sec = 0; + old->it_value.tv_nsec = 0; + } else { + /* + * Update the timer in case it has + * overrun already. If it has, + * we'll report it as having overrun + * and with the next reloaded timer + * already ticking, though we are + * swallowing that pending + * notification here to install the + * new setting. + */ + bump_cpu_timer(timer, val); + if (val < timer->it.cpu.expires) { + old_expires = timer->it.cpu.expires - val; + sample_to_timespec(timer->it_clock, + old_expires, + &old->it_value); + } else { + old->it_value.tv_nsec = 1; + old->it_value.tv_sec = 0; + } + } + } + + if (unlikely(ret)) { + /* + * We are colliding with the timer actually firing. + * Punt after filling in the timer's old value, and + * disable this firing since we are already reporting + * it as an overrun (thanks to bump_cpu_timer above). + */ + unlock_task_sighand(p, &flags); + goto out; + } + + if (new_expires != 0 && !(timer_flags & TIMER_ABSTIME)) { + new_expires += val; + } + + /* + * Install the new expiry time (or zero). + * For a timer with no notification action, we don't actually + * arm the timer (we'll just fake it for timer_gettime). + */ + timer->it.cpu.expires = new_expires; + if (new_expires != 0 && val < new_expires) { + arm_timer(timer); + } + + unlock_task_sighand(p, &flags); + /* + * Install the new reload setting, and + * set up the signal and overrun bookkeeping. + */ + timer->it.cpu.incr = timespec_to_sample(timer->it_clock, + &new->it_interval); + + /* + * This acts as a modification timestamp for the timer, + * so any automatic reload attempt will punt on seeing + * that we have reset the timer manually. + */ + timer->it_requeue_pending = (timer->it_requeue_pending + 2) & + ~REQUEUE_PENDING; + timer->it_overrun_last = 0; + timer->it_overrun = -1; + + if (new_expires != 0 && !(val < new_expires)) { + /* + * The designated time already passed, so we notify + * immediately, even if the thread never runs to + * accumulate more time on this clock. + */ + cpu_timer_fire(timer); + } + + ret = 0; + out: + if (old) { + sample_to_timespec(timer->it_clock, + old_incr, &old->it_interval); + } + if (!ret) + posix_cpu_timer_kick_nohz(); + return ret; +} + +static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp) +{ + unsigned long long now; + struct task_struct *p = timer->it.cpu.task; + + WARN_ON_ONCE(p == NULL); + + /* + * Easy part: convert the reload time. + */ + sample_to_timespec(timer->it_clock, + timer->it.cpu.incr, &itp->it_interval); + + if (timer->it.cpu.expires == 0) { /* Timer not armed at all. */ + itp->it_value.tv_sec = itp->it_value.tv_nsec = 0; + return; + } + + /* + * Sample the clock to take the difference with the expiry time. + */ + if (CPUCLOCK_PERTHREAD(timer->it_clock)) { + cpu_clock_sample(timer->it_clock, p, &now); + } else { + struct sighand_struct *sighand; + unsigned long flags; + + /* + * Protect against sighand release/switch in exit/exec and + * also make timer sampling safe if it ends up calling + * thread_group_cputime(). + */ + sighand = lock_task_sighand(p, &flags); + if (unlikely(sighand == NULL)) { + /* + * The process has been reaped. + * We can't even collect a sample any more. + * Call the timer disarmed, nothing else to do. + */ + timer->it.cpu.expires = 0; + sample_to_timespec(timer->it_clock, timer->it.cpu.expires, + &itp->it_value); + } else { + cpu_timer_sample_group(timer->it_clock, p, &now); + unlock_task_sighand(p, &flags); + } + } + + if (now < timer->it.cpu.expires) { + sample_to_timespec(timer->it_clock, + timer->it.cpu.expires - now, + &itp->it_value); + } else { + /* + * The timer should have expired already, but the firing + * hasn't taken place yet. Say it's just about to expire. + */ + itp->it_value.tv_nsec = 1; + itp->it_value.tv_sec = 0; + } +} + +static unsigned long long +check_timers_list(struct list_head *timers, + struct list_head *firing, + unsigned long long curr) +{ + int maxfire = 20; + + while (!list_empty(timers)) { + struct cpu_timer_list *t; + + t = list_first_entry(timers, struct cpu_timer_list, entry); + + if (!--maxfire || curr < t->expires) + return t->expires; + + t->firing = 1; + list_move_tail(&t->entry, firing); + } + + return 0; +} + +/* + * Check for any per-thread CPU timers that have fired and move them off + * the tsk->cpu_timers[N] list onto the firing list. Here we update the + * tsk->it_*_expires values to reflect the remaining thread CPU timers. + */ +static void check_thread_timers(struct task_struct *tsk, + struct list_head *firing) +{ + struct list_head *timers = tsk->cpu_timers; + struct signal_struct *const sig = tsk->signal; + struct task_cputime *tsk_expires = &tsk->cputime_expires; + unsigned long long expires; + unsigned long soft; + + expires = check_timers_list(timers, firing, prof_ticks(tsk)); + tsk_expires->prof_exp = expires_to_cputime(expires); + + expires = check_timers_list(++timers, firing, virt_ticks(tsk)); + tsk_expires->virt_exp = expires_to_cputime(expires); + + tsk_expires->sched_exp = check_timers_list(++timers, firing, + tsk->se.sum_exec_runtime); + + /* + * Check for the special case thread timers. + */ + soft = ACCESS_ONCE(sig->rlim[RLIMIT_RTTIME].rlim_cur); + if (soft != RLIM_INFINITY) { + unsigned long hard = + ACCESS_ONCE(sig->rlim[RLIMIT_RTTIME].rlim_max); + + if (hard != RLIM_INFINITY && + tsk->rt.timeout > DIV_ROUND_UP(hard, USEC_PER_SEC/HZ)) { + /* + * At the hard limit, we just die. + * No need to calculate anything else now. + */ + __group_send_sig_info(SIGKILL, SEND_SIG_PRIV, tsk); + return; + } + if (tsk->rt.timeout > DIV_ROUND_UP(soft, USEC_PER_SEC/HZ)) { + /* + * At the soft limit, send a SIGXCPU every second. + */ + if (soft < hard) { + soft += USEC_PER_SEC; + sig->rlim[RLIMIT_RTTIME].rlim_cur = soft; + } + printk(KERN_INFO + "RT Watchdog Timeout: %s[%d]\n", + tsk->comm, task_pid_nr(tsk)); + __group_send_sig_info(SIGXCPU, SEND_SIG_PRIV, tsk); + } + } +} + +static void stop_process_timers(struct signal_struct *sig) +{ + struct thread_group_cputimer *cputimer = &sig->cputimer; + unsigned long flags; + + raw_spin_lock_irqsave(&cputimer->lock, flags); + cputimer->running = 0; + raw_spin_unlock_irqrestore(&cputimer->lock, flags); +} + +static u32 onecputick; + +static void check_cpu_itimer(struct task_struct *tsk, struct cpu_itimer *it, + unsigned long long *expires, + unsigned long long cur_time, int signo) +{ + if (!it->expires) + return; + + if (cur_time >= it->expires) { + if (it->incr) { + it->expires += it->incr; + it->error += it->incr_error; + if (it->error >= onecputick) { + it->expires -= cputime_one_jiffy; + it->error -= onecputick; + } + } else { + it->expires = 0; + } + + trace_itimer_expire(signo == SIGPROF ? + ITIMER_PROF : ITIMER_VIRTUAL, + tsk->signal->leader_pid, cur_time); + __group_send_sig_info(signo, SEND_SIG_PRIV, tsk); + } + + if (it->expires && (!*expires || it->expires < *expires)) { + *expires = it->expires; + } +} + +/* + * Check for any per-thread CPU timers that have fired and move them + * off the tsk->*_timers list onto the firing list. Per-thread timers + * have already been taken off. + */ +static void check_process_timers(struct task_struct *tsk, + struct list_head *firing) +{ + struct signal_struct *const sig = tsk->signal; + unsigned long long utime, ptime, virt_expires, prof_expires; + unsigned long long sum_sched_runtime, sched_expires; + struct list_head *timers = sig->cpu_timers; + struct task_cputime cputime; + unsigned long soft; + + /* + * Collect the current process totals. + */ + thread_group_cputimer(tsk, &cputime); + utime = cputime_to_expires(cputime.utime); + ptime = utime + cputime_to_expires(cputime.stime); + sum_sched_runtime = cputime.sum_exec_runtime; + + prof_expires = check_timers_list(timers, firing, ptime); + virt_expires = check_timers_list(++timers, firing, utime); + sched_expires = check_timers_list(++timers, firing, sum_sched_runtime); + + /* + * Check for the special case process timers. + */ + check_cpu_itimer(tsk, &sig->it[CPUCLOCK_PROF], &prof_expires, ptime, + SIGPROF); + check_cpu_itimer(tsk, &sig->it[CPUCLOCK_VIRT], &virt_expires, utime, + SIGVTALRM); + soft = ACCESS_ONCE(sig->rlim[RLIMIT_CPU].rlim_cur); + if (soft != RLIM_INFINITY) { + unsigned long psecs = cputime_to_secs(ptime); + unsigned long hard = + ACCESS_ONCE(sig->rlim[RLIMIT_CPU].rlim_max); + cputime_t x; + if (psecs >= hard) { + /* + * At the hard limit, we just die. + * No need to calculate anything else now. + */ + __group_send_sig_info(SIGKILL, SEND_SIG_PRIV, tsk); + return; + } + if (psecs >= soft) { + /* + * At the soft limit, send a SIGXCPU every second. + */ + __group_send_sig_info(SIGXCPU, SEND_SIG_PRIV, tsk); + if (soft < hard) { + soft++; + sig->rlim[RLIMIT_CPU].rlim_cur = soft; + } + } + x = secs_to_cputime(soft); + if (!prof_expires || x < prof_expires) { + prof_expires = x; + } + } + + sig->cputime_expires.prof_exp = expires_to_cputime(prof_expires); + sig->cputime_expires.virt_exp = expires_to_cputime(virt_expires); + sig->cputime_expires.sched_exp = sched_expires; + if (task_cputime_zero(&sig->cputime_expires)) + stop_process_timers(sig); +} + +/* + * This is called from the signal code (via do_schedule_next_timer) + * when the last timer signal was delivered and we have to reload the timer. + */ +void posix_cpu_timer_schedule(struct k_itimer *timer) +{ + struct sighand_struct *sighand; + unsigned long flags; + struct task_struct *p = timer->it.cpu.task; + unsigned long long now; + + WARN_ON_ONCE(p == NULL); + + /* + * Fetch the current sample and update the timer's expiry time. + */ + if (CPUCLOCK_PERTHREAD(timer->it_clock)) { + cpu_clock_sample(timer->it_clock, p, &now); + bump_cpu_timer(timer, now); + if (unlikely(p->exit_state)) + goto out; + + /* Protect timer list r/w in arm_timer() */ + sighand = lock_task_sighand(p, &flags); + if (!sighand) + goto out; + } else { + /* + * Protect arm_timer() and timer sampling in case of call to + * thread_group_cputime(). + */ + sighand = lock_task_sighand(p, &flags); + if (unlikely(sighand == NULL)) { + /* + * The process has been reaped. + * We can't even collect a sample any more. + */ + timer->it.cpu.expires = 0; + goto out; + } else if (unlikely(p->exit_state) && thread_group_empty(p)) { + unlock_task_sighand(p, &flags); + /* Optimizations: if the process is dying, no need to rearm */ + goto out; + } + cpu_timer_sample_group(timer->it_clock, p, &now); + bump_cpu_timer(timer, now); + /* Leave the sighand locked for the call below. */ + } + + /* + * Now re-arm for the new expiry time. + */ + WARN_ON_ONCE_NONRT(!irqs_disabled()); + arm_timer(timer); + unlock_task_sighand(p, &flags); + + /* Kick full dynticks CPUs in case they need to tick on the new timer */ + posix_cpu_timer_kick_nohz(); +out: + timer->it_overrun_last = timer->it_overrun; + timer->it_overrun = -1; + ++timer->it_requeue_pending; +} + +/** + * task_cputime_expired - Compare two task_cputime entities. + * + * @sample: The task_cputime structure to be checked for expiration. + * @expires: Expiration times, against which @sample will be checked. + * + * Checks @sample against @expires to see if any field of @sample has expired. + * Returns true if any field of the former is greater than the corresponding + * field of the latter if the latter field is set. Otherwise returns false. + */ +static inline int task_cputime_expired(const struct task_cputime *sample, + const struct task_cputime *expires) +{ + if (expires->utime && sample->utime >= expires->utime) + return 1; + if (expires->stime && sample->utime + sample->stime >= expires->stime) + return 1; + if (expires->sum_exec_runtime != 0 && + sample->sum_exec_runtime >= expires->sum_exec_runtime) + return 1; + return 0; +} + +/** + * fastpath_timer_check - POSIX CPU timers fast path. + * + * @tsk: The task (thread) being checked. + * + * Check the task and thread group timers. If both are zero (there are no + * timers set) return false. Otherwise snapshot the task and thread group + * timers and compare them with the corresponding expiration times. Return + * true if a timer has expired, else return false. + */ +static inline int fastpath_timer_check(struct task_struct *tsk) +{ + struct signal_struct *sig; + cputime_t utime, stime; + + task_cputime(tsk, &utime, &stime); + + if (!task_cputime_zero(&tsk->cputime_expires)) { + struct task_cputime task_sample = { + .utime = utime, + .stime = stime, + .sum_exec_runtime = tsk->se.sum_exec_runtime + }; + + if (task_cputime_expired(&task_sample, &tsk->cputime_expires)) + return 1; + } + + sig = tsk->signal; + if (sig->cputimer.running) { + struct task_cputime group_sample; + unsigned long flags; + + raw_spin_lock_irqsave(&sig->cputimer.lock, flags); + group_sample = sig->cputimer.cputime; + raw_spin_unlock_irqrestore(&sig->cputimer.lock, flags); + + if (task_cputime_expired(&group_sample, &sig->cputime_expires)) + return 1; + } + + return 0; +} + +/* + * This is called from the timer interrupt handler. The irq handler has + * already updated our counts. We need to check if any timers fire now. + * Interrupts are disabled. + */ +static void __run_posix_cpu_timers(struct task_struct *tsk) +{ + LIST_HEAD(firing); + struct k_itimer *timer, *next; + unsigned long flags; + + WARN_ON_ONCE_NONRT(!irqs_disabled()); + + /* + * The fast path checks that there are no expired thread or thread + * group timers. If that's so, just return. + */ + if (!fastpath_timer_check(tsk)) + return; + + if (!lock_task_sighand(tsk, &flags)) + return; + /* + * Here we take off tsk->signal->cpu_timers[N] and + * tsk->cpu_timers[N] all the timers that are firing, and + * put them on the firing list. + */ + check_thread_timers(tsk, &firing); + /* + * If there are any active process wide timers (POSIX 1.b, itimers, + * RLIMIT_CPU) cputimer must be running. + */ + if (tsk->signal->cputimer.running) + check_process_timers(tsk, &firing); + + /* + * We must release these locks before taking any timer's lock. + * There is a potential race with timer deletion here, as the + * siglock now protects our private firing list. We have set + * the firing flag in each timer, so that a deletion attempt + * that gets the timer lock before we do will give it up and + * spin until we've taken care of that timer below. + */ + unlock_task_sighand(tsk, &flags); + + /* + * Now that all the timers on our list have the firing flag, + * no one will touch their list entries but us. We'll take + * each timer's lock before clearing its firing flag, so no + * timer call will interfere. + */ + list_for_each_entry_safe(timer, next, &firing, it.cpu.entry) { + int cpu_firing; + + spin_lock(&timer->it_lock); + list_del_init(&timer->it.cpu.entry); + cpu_firing = timer->it.cpu.firing; + timer->it.cpu.firing = 0; + /* + * The firing flag is -1 if we collided with a reset + * of the timer, which already reported this + * almost-firing as an overrun. So don't generate an event. + */ + if (likely(cpu_firing >= 0)) + cpu_timer_fire(timer); + spin_unlock(&timer->it_lock); + } +} + +#ifdef CONFIG_PREEMPT_RT_BASE +#include +#include +DEFINE_PER_CPU(struct task_struct *, posix_timer_task); +DEFINE_PER_CPU(struct task_struct *, posix_timer_tasklist); + +static int posix_cpu_timers_thread(void *data) +{ + int cpu = (long)data; + + BUG_ON(per_cpu(posix_timer_task,cpu) != current); + + while (!kthread_should_stop()) { + struct task_struct *tsk = NULL; + struct task_struct *next = NULL; + + if (cpu_is_offline(cpu)) + goto wait_to_die; + + /* grab task list */ + raw_local_irq_disable(); + tsk = per_cpu(posix_timer_tasklist, cpu); + per_cpu(posix_timer_tasklist, cpu) = NULL; + raw_local_irq_enable(); + + /* its possible the list is empty, just return */ + if (!tsk) { + set_current_state(TASK_INTERRUPTIBLE); + schedule(); + __set_current_state(TASK_RUNNING); + continue; + } + + /* Process task list */ + while (1) { + /* save next */ + next = tsk->posix_timer_list; + + /* run the task timers, clear its ptr and + * unreference it + */ + __run_posix_cpu_timers(tsk); + tsk->posix_timer_list = NULL; + put_task_struct(tsk); + + /* check if this is the last on the list */ + if (next == tsk) + break; + tsk = next; + } + } + return 0; + +wait_to_die: + /* Wait for kthread_stop */ + set_current_state(TASK_INTERRUPTIBLE); + while (!kthread_should_stop()) { + schedule(); + set_current_state(TASK_INTERRUPTIBLE); + } + __set_current_state(TASK_RUNNING); + return 0; +} + +static inline int __fastpath_timer_check(struct task_struct *tsk) +{ + /* tsk == current, ensure it is safe to use ->signal/sighand */ + if (unlikely(tsk->exit_state)) + return 0; + + if (!task_cputime_zero(&tsk->cputime_expires)) + return 1; + + if (!task_cputime_zero(&tsk->signal->cputime_expires)) + return 1; + + return 0; +} + +void run_posix_cpu_timers(struct task_struct *tsk) +{ + unsigned long cpu = smp_processor_id(); + struct task_struct *tasklist; + + BUG_ON(!irqs_disabled()); + if(!per_cpu(posix_timer_task, cpu)) + return; + /* get per-cpu references */ + tasklist = per_cpu(posix_timer_tasklist, cpu); + + /* check to see if we're already queued */ + if (!tsk->posix_timer_list && __fastpath_timer_check(tsk)) { + get_task_struct(tsk); + if (tasklist) { + tsk->posix_timer_list = tasklist; + } else { + /* + * The list is terminated by a self-pointing + * task_struct + */ + tsk->posix_timer_list = tsk; + } + per_cpu(posix_timer_tasklist, cpu) = tsk; + + wake_up_process(per_cpu(posix_timer_task, cpu)); + } +} + +/* + * posix_cpu_thread_call - callback that gets triggered when a CPU is added. + * Here we can start up the necessary migration thread for the new CPU. + */ +static int posix_cpu_thread_call(struct notifier_block *nfb, + unsigned long action, void *hcpu) +{ + int cpu = (long)hcpu; + struct task_struct *p; + struct sched_param param; + + switch (action) { + case CPU_UP_PREPARE: + p = kthread_create(posix_cpu_timers_thread, hcpu, + "posixcputmr/%d",cpu); + if (IS_ERR(p)) + return NOTIFY_BAD; + p->flags |= PF_NOFREEZE; + kthread_bind(p, cpu); + /* Must be high prio to avoid getting starved */ + param.sched_priority = MAX_RT_PRIO-1; + sched_setscheduler(p, SCHED_FIFO, ¶m); + per_cpu(posix_timer_task,cpu) = p; + break; + case CPU_ONLINE: + /* Strictly unneccessary, as first user will wake it. */ + wake_up_process(per_cpu(posix_timer_task,cpu)); + break; +#ifdef CONFIG_HOTPLUG_CPU + case CPU_UP_CANCELED: + /* Unbind it from offline cpu so it can run. Fall thru. */ + kthread_bind(per_cpu(posix_timer_task, cpu), + cpumask_any(cpu_online_mask)); + kthread_stop(per_cpu(posix_timer_task,cpu)); + per_cpu(posix_timer_task,cpu) = NULL; + break; + case CPU_DEAD: + kthread_stop(per_cpu(posix_timer_task,cpu)); + per_cpu(posix_timer_task,cpu) = NULL; + break; +#endif + } + return NOTIFY_OK; +} + +/* Register at highest priority so that task migration (migrate_all_tasks) + * happens before everything else. + */ +static struct notifier_block posix_cpu_thread_notifier = { + .notifier_call = posix_cpu_thread_call, + .priority = 10 +}; + +static int __init posix_cpu_thread_init(void) +{ + void *hcpu = (void *)(long)smp_processor_id(); + /* Start one for boot CPU. */ + unsigned long cpu; + + /* init the per-cpu posix_timer_tasklets */ + for_each_possible_cpu(cpu) + per_cpu(posix_timer_tasklist, cpu) = NULL; + + posix_cpu_thread_call(&posix_cpu_thread_notifier, CPU_UP_PREPARE, hcpu); + posix_cpu_thread_call(&posix_cpu_thread_notifier, CPU_ONLINE, hcpu); + register_cpu_notifier(&posix_cpu_thread_notifier); + return 0; +} +early_initcall(posix_cpu_thread_init); +#else /* CONFIG_PREEMPT_RT_BASE */ +void run_posix_cpu_timers(struct task_struct *tsk) +{ + __run_posix_cpu_timers(tsk); +} +#endif /* CONFIG_PREEMPT_RT_BASE */ + +/* + * Set one of the process-wide special case CPU timers or RLIMIT_CPU. + * The tsk->sighand->siglock must be held by the caller. + */ +void set_process_cpu_timer(struct task_struct *tsk, unsigned int clock_idx, + cputime_t *newval, cputime_t *oldval) +{ + unsigned long long now; + + WARN_ON_ONCE(clock_idx == CPUCLOCK_SCHED); + cpu_timer_sample_group(clock_idx, tsk, &now); + + if (oldval) { + /* + * We are setting itimer. The *oldval is absolute and we update + * it to be relative, *newval argument is relative and we update + * it to be absolute. + */ + if (*oldval) { + if (*oldval <= now) { + /* Just about to fire. */ + *oldval = cputime_one_jiffy; + } else { + *oldval -= now; + } + } + + if (!*newval) + goto out; + *newval += now; + } + + /* + * Update expiration cache if we are the earliest timer, or eventually + * RLIMIT_CPU limit is earlier than prof_exp cpu timer expire. + */ + switch (clock_idx) { + case CPUCLOCK_PROF: + if (expires_gt(tsk->signal->cputime_expires.prof_exp, *newval)) + tsk->signal->cputime_expires.prof_exp = *newval; + break; + case CPUCLOCK_VIRT: + if (expires_gt(tsk->signal->cputime_expires.virt_exp, *newval)) + tsk->signal->cputime_expires.virt_exp = *newval; + break; + } +out: + posix_cpu_timer_kick_nohz(); +} + +static int do_cpu_nanosleep(const clockid_t which_clock, int flags, + struct timespec *rqtp, struct itimerspec *it) +{ + struct k_itimer timer; + int error; + + /* + * Set up a temporary timer and then wait for it to go off. + */ + memset(&timer, 0, sizeof timer); + spin_lock_init(&timer.it_lock); + timer.it_clock = which_clock; + timer.it_overrun = -1; + error = posix_cpu_timer_create(&timer); + timer.it_process = current; + if (!error) { + static struct itimerspec zero_it; + + memset(it, 0, sizeof *it); + it->it_value = *rqtp; + + spin_lock_irq(&timer.it_lock); + error = posix_cpu_timer_set(&timer, flags, it, NULL); + if (error) { + spin_unlock_irq(&timer.it_lock); + return error; + } + + while (!signal_pending(current)) { + if (timer.it.cpu.expires == 0) { + /* + * Our timer fired and was reset, below + * deletion can not fail. + */ + posix_cpu_timer_del(&timer); + spin_unlock_irq(&timer.it_lock); + return 0; + } + + /* + * Block until cpu_timer_fire (or a signal) wakes us. + */ + __set_current_state(TASK_INTERRUPTIBLE); + spin_unlock_irq(&timer.it_lock); + schedule(); + spin_lock_irq(&timer.it_lock); + } + + /* + * We were interrupted by a signal. + */ + sample_to_timespec(which_clock, timer.it.cpu.expires, rqtp); + error = posix_cpu_timer_set(&timer, 0, &zero_it, it); + if (!error) { + /* + * Timer is now unarmed, deletion can not fail. + */ + posix_cpu_timer_del(&timer); + } + spin_unlock_irq(&timer.it_lock); + + while (error == TIMER_RETRY) { + /* + * We need to handle case when timer was or is in the + * middle of firing. In other cases we already freed + * resources. + */ + spin_lock_irq(&timer.it_lock); + error = posix_cpu_timer_del(&timer); + spin_unlock_irq(&timer.it_lock); + } + + if ((it->it_value.tv_sec | it->it_value.tv_nsec) == 0) { + /* + * It actually did fire already. + */ + return 0; + } + + error = -ERESTART_RESTARTBLOCK; + } + + return error; +} + +static long posix_cpu_nsleep_restart(struct restart_block *restart_block); + +static int posix_cpu_nsleep(const clockid_t which_clock, int flags, + struct timespec *rqtp, struct timespec __user *rmtp) +{ + struct restart_block *restart_block = ¤t->restart_block; + struct itimerspec it; + int error; + + /* + * Diagnose required errors first. + */ + if (CPUCLOCK_PERTHREAD(which_clock) && + (CPUCLOCK_PID(which_clock) == 0 || + CPUCLOCK_PID(which_clock) == current->pid)) + return -EINVAL; + + error = do_cpu_nanosleep(which_clock, flags, rqtp, &it); + + if (error == -ERESTART_RESTARTBLOCK) { + + if (flags & TIMER_ABSTIME) + return -ERESTARTNOHAND; + /* + * Report back to the user the time still remaining. + */ + if (rmtp && copy_to_user(rmtp, &it.it_value, sizeof *rmtp)) + return -EFAULT; + + restart_block->fn = posix_cpu_nsleep_restart; + restart_block->nanosleep.clockid = which_clock; + restart_block->nanosleep.rmtp = rmtp; + restart_block->nanosleep.expires = timespec_to_ns(rqtp); + } + return error; +} + +static long posix_cpu_nsleep_restart(struct restart_block *restart_block) +{ + clockid_t which_clock = restart_block->nanosleep.clockid; + struct timespec t; + struct itimerspec it; + int error; + + t = ns_to_timespec(restart_block->nanosleep.expires); + + error = do_cpu_nanosleep(which_clock, TIMER_ABSTIME, &t, &it); + + if (error == -ERESTART_RESTARTBLOCK) { + struct timespec __user *rmtp = restart_block->nanosleep.rmtp; + /* + * Report back to the user the time still remaining. + */ + if (rmtp && copy_to_user(rmtp, &it.it_value, sizeof *rmtp)) + return -EFAULT; + + restart_block->nanosleep.expires = timespec_to_ns(&t); + } + return error; + +} + +#define PROCESS_CLOCK MAKE_PROCESS_CPUCLOCK(0, CPUCLOCK_SCHED) +#define THREAD_CLOCK MAKE_THREAD_CPUCLOCK(0, CPUCLOCK_SCHED) + +static int process_cpu_clock_getres(const clockid_t which_clock, + struct timespec *tp) +{ + return posix_cpu_clock_getres(PROCESS_CLOCK, tp); +} +static int process_cpu_clock_get(const clockid_t which_clock, + struct timespec *tp) +{ + return posix_cpu_clock_get(PROCESS_CLOCK, tp); +} +static int process_cpu_timer_create(struct k_itimer *timer) +{ + timer->it_clock = PROCESS_CLOCK; + return posix_cpu_timer_create(timer); +} +static int process_cpu_nsleep(const clockid_t which_clock, int flags, + struct timespec *rqtp, + struct timespec __user *rmtp) +{ + return posix_cpu_nsleep(PROCESS_CLOCK, flags, rqtp, rmtp); +} +static long process_cpu_nsleep_restart(struct restart_block *restart_block) +{ + return -EINVAL; +} +static int thread_cpu_clock_getres(const clockid_t which_clock, + struct timespec *tp) +{ + return posix_cpu_clock_getres(THREAD_CLOCK, tp); +} +static int thread_cpu_clock_get(const clockid_t which_clock, + struct timespec *tp) +{ + return posix_cpu_clock_get(THREAD_CLOCK, tp); +} +static int thread_cpu_timer_create(struct k_itimer *timer) +{ + timer->it_clock = THREAD_CLOCK; + return posix_cpu_timer_create(timer); +} + +struct k_clock clock_posix_cpu = { + .clock_getres = posix_cpu_clock_getres, + .clock_set = posix_cpu_clock_set, + .clock_get = posix_cpu_clock_get, + .timer_create = posix_cpu_timer_create, + .nsleep = posix_cpu_nsleep, + .nsleep_restart = posix_cpu_nsleep_restart, + .timer_set = posix_cpu_timer_set, + .timer_del = posix_cpu_timer_del, + .timer_get = posix_cpu_timer_get, +}; + +static __init int init_posix_cpu_timers(void) +{ + struct k_clock process = { + .clock_getres = process_cpu_clock_getres, + .clock_get = process_cpu_clock_get, + .timer_create = process_cpu_timer_create, + .nsleep = process_cpu_nsleep, + .nsleep_restart = process_cpu_nsleep_restart, + }; + struct k_clock thread = { + .clock_getres = thread_cpu_clock_getres, + .clock_get = thread_cpu_clock_get, + .timer_create = thread_cpu_timer_create, + }; + struct timespec ts; + + posix_timers_register_clock(CLOCK_PROCESS_CPUTIME_ID, &process); + posix_timers_register_clock(CLOCK_THREAD_CPUTIME_ID, &thread); + + cputime_to_timespec(cputime_one_jiffy, &ts); + onecputick = ts.tv_nsec; + WARN_ON(ts.tv_sec != 0); + + return 0; +} +__initcall(init_posix_cpu_timers); diff --git a/kernel/kernel/time/posix-timers.c b/kernel/kernel/time/posix-timers.c new file mode 100644 index 000000000..0f5d7eae6 --- /dev/null +++ b/kernel/kernel/time/posix-timers.c @@ -0,0 +1,1159 @@ +/* + * linux/kernel/posix-timers.c + * + * + * 2002-10-15 Posix Clocks & timers + * by George Anzinger george@mvista.com + * + * Copyright (C) 2002 2003 by MontaVista Software. + * + * 2004-06-01 Fix CLOCK_REALTIME clock/timer TIMER_ABSTIME bug. + * Copyright (C) 2004 Boris Hu + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or (at + * your option) any later version. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. + * + * MontaVista Software | 1237 East Arques Avenue | Sunnyvale | CA 94085 | USA + */ + +/* These are all the functions necessary to implement + * POSIX clocks & timers + */ +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "timekeeping.h" + +/* + * Management arrays for POSIX timers. Timers are now kept in static hash table + * with 512 entries. + * Timer ids are allocated by local routine, which selects proper hash head by + * key, constructed from current->signal address and per signal struct counter. + * This keeps timer ids unique per process, but now they can intersect between + * processes. + */ + +/* + * Lets keep our timers in a slab cache :-) + */ +static struct kmem_cache *posix_timers_cache; + +static DEFINE_HASHTABLE(posix_timers_hashtable, 9); +static DEFINE_SPINLOCK(hash_lock); + +/* + * we assume that the new SIGEV_THREAD_ID shares no bits with the other + * SIGEV values. Here we put out an error if this assumption fails. + */ +#if SIGEV_THREAD_ID != (SIGEV_THREAD_ID & \ + ~(SIGEV_SIGNAL | SIGEV_NONE | SIGEV_THREAD)) +#error "SIGEV_THREAD_ID must not share bit with other SIGEV values!" +#endif + +/* + * parisc wants ENOTSUP instead of EOPNOTSUPP + */ +#ifndef ENOTSUP +# define ENANOSLEEP_NOTSUP EOPNOTSUPP +#else +# define ENANOSLEEP_NOTSUP ENOTSUP +#endif + +/* + * The timer ID is turned into a timer address by idr_find(). + * Verifying a valid ID consists of: + * + * a) checking that idr_find() returns other than -1. + * b) checking that the timer id matches the one in the timer itself. + * c) that the timer owner is in the callers thread group. + */ + +/* + * CLOCKs: The POSIX standard calls for a couple of clocks and allows us + * to implement others. This structure defines the various + * clocks. + * + * RESOLUTION: Clock resolution is used to round up timer and interval + * times, NOT to report clock times, which are reported with as + * much resolution as the system can muster. In some cases this + * resolution may depend on the underlying clock hardware and + * may not be quantifiable until run time, and only then is the + * necessary code is written. The standard says we should say + * something about this issue in the documentation... + * + * FUNCTIONS: The CLOCKs structure defines possible functions to + * handle various clock functions. + * + * The standard POSIX timer management code assumes the + * following: 1.) The k_itimer struct (sched.h) is used for + * the timer. 2.) The list, it_lock, it_clock, it_id and + * it_pid fields are not modified by timer code. + * + * Permissions: It is assumed that the clock_settime() function defined + * for each clock will take care of permission checks. Some + * clocks may be set able by any user (i.e. local process + * clocks) others not. Currently the only set able clock we + * have is CLOCK_REALTIME and its high res counter part, both of + * which we beg off on and pass to do_sys_settimeofday(). + */ + +static struct k_clock posix_clocks[MAX_CLOCKS]; + +/* + * These ones are defined below. + */ +static int common_nsleep(const clockid_t, int flags, struct timespec *t, + struct timespec __user *rmtp); +static int common_timer_create(struct k_itimer *new_timer); +static void common_timer_get(struct k_itimer *, struct itimerspec *); +static int common_timer_set(struct k_itimer *, int, + struct itimerspec *, struct itimerspec *); +static int common_timer_del(struct k_itimer *timer); + +static enum hrtimer_restart posix_timer_fn(struct hrtimer *data); + +static struct k_itimer *__lock_timer(timer_t timer_id, unsigned long *flags); + +#define lock_timer(tid, flags) \ +({ struct k_itimer *__timr; \ + __cond_lock(&__timr->it_lock, __timr = __lock_timer(tid, flags)); \ + __timr; \ +}) + +static int hash(struct signal_struct *sig, unsigned int nr) +{ + return hash_32(hash32_ptr(sig) ^ nr, HASH_BITS(posix_timers_hashtable)); +} + +static struct k_itimer *__posix_timers_find(struct hlist_head *head, + struct signal_struct *sig, + timer_t id) +{ + struct k_itimer *timer; + + hlist_for_each_entry_rcu(timer, head, t_hash) { + if ((timer->it_signal == sig) && (timer->it_id == id)) + return timer; + } + return NULL; +} + +static struct k_itimer *posix_timer_by_id(timer_t id) +{ + struct signal_struct *sig = current->signal; + struct hlist_head *head = &posix_timers_hashtable[hash(sig, id)]; + + return __posix_timers_find(head, sig, id); +} + +static int posix_timer_add(struct k_itimer *timer) +{ + struct signal_struct *sig = current->signal; + int first_free_id = sig->posix_timer_id; + struct hlist_head *head; + int ret = -ENOENT; + + do { + spin_lock(&hash_lock); + head = &posix_timers_hashtable[hash(sig, sig->posix_timer_id)]; + if (!__posix_timers_find(head, sig, sig->posix_timer_id)) { + hlist_add_head_rcu(&timer->t_hash, head); + ret = sig->posix_timer_id; + } + if (++sig->posix_timer_id < 0) + sig->posix_timer_id = 0; + if ((sig->posix_timer_id == first_free_id) && (ret == -ENOENT)) + /* Loop over all possible ids completed */ + ret = -EAGAIN; + spin_unlock(&hash_lock); + } while (ret == -ENOENT); + return ret; +} + +static inline void unlock_timer(struct k_itimer *timr, unsigned long flags) +{ + spin_unlock_irqrestore(&timr->it_lock, flags); +} + +/* Get clock_realtime */ +static int posix_clock_realtime_get(clockid_t which_clock, struct timespec *tp) +{ + ktime_get_real_ts(tp); + return 0; +} + +/* Set clock_realtime */ +static int posix_clock_realtime_set(const clockid_t which_clock, + const struct timespec *tp) +{ + return do_sys_settimeofday(tp, NULL); +} + +static int posix_clock_realtime_adj(const clockid_t which_clock, + struct timex *t) +{ + return do_adjtimex(t); +} + +/* + * Get monotonic time for posix timers + */ +static int posix_ktime_get_ts(clockid_t which_clock, struct timespec *tp) +{ + ktime_get_ts(tp); + return 0; +} + +/* + * Get monotonic-raw time for posix timers + */ +static int posix_get_monotonic_raw(clockid_t which_clock, struct timespec *tp) +{ + getrawmonotonic(tp); + return 0; +} + + +static int posix_get_realtime_coarse(clockid_t which_clock, struct timespec *tp) +{ + *tp = current_kernel_time(); + return 0; +} + +static int posix_get_monotonic_coarse(clockid_t which_clock, + struct timespec *tp) +{ + *tp = get_monotonic_coarse(); + return 0; +} + +static int posix_get_coarse_res(const clockid_t which_clock, struct timespec *tp) +{ + *tp = ktime_to_timespec(KTIME_LOW_RES); + return 0; +} + +static int posix_get_boottime(const clockid_t which_clock, struct timespec *tp) +{ + get_monotonic_boottime(tp); + return 0; +} + +static int posix_get_tai(clockid_t which_clock, struct timespec *tp) +{ + timekeeping_clocktai(tp); + return 0; +} + +/* + * Initialize everything, well, just everything in Posix clocks/timers ;) + */ +static __init int init_posix_timers(void) +{ + struct k_clock clock_realtime = { + .clock_getres = hrtimer_get_res, + .clock_get = posix_clock_realtime_get, + .clock_set = posix_clock_realtime_set, + .clock_adj = posix_clock_realtime_adj, + .nsleep = common_nsleep, + .nsleep_restart = hrtimer_nanosleep_restart, + .timer_create = common_timer_create, + .timer_set = common_timer_set, + .timer_get = common_timer_get, + .timer_del = common_timer_del, + }; + struct k_clock clock_monotonic = { + .clock_getres = hrtimer_get_res, + .clock_get = posix_ktime_get_ts, + .nsleep = common_nsleep, + .nsleep_restart = hrtimer_nanosleep_restart, + .timer_create = common_timer_create, + .timer_set = common_timer_set, + .timer_get = common_timer_get, + .timer_del = common_timer_del, + }; + struct k_clock clock_monotonic_raw = { + .clock_getres = hrtimer_get_res, + .clock_get = posix_get_monotonic_raw, + }; + struct k_clock clock_realtime_coarse = { + .clock_getres = posix_get_coarse_res, + .clock_get = posix_get_realtime_coarse, + }; + struct k_clock clock_monotonic_coarse = { + .clock_getres = posix_get_coarse_res, + .clock_get = posix_get_monotonic_coarse, + }; + struct k_clock clock_tai = { + .clock_getres = hrtimer_get_res, + .clock_get = posix_get_tai, + .nsleep = common_nsleep, + .nsleep_restart = hrtimer_nanosleep_restart, + .timer_create = common_timer_create, + .timer_set = common_timer_set, + .timer_get = common_timer_get, + .timer_del = common_timer_del, + }; + struct k_clock clock_boottime = { + .clock_getres = hrtimer_get_res, + .clock_get = posix_get_boottime, + .nsleep = common_nsleep, + .nsleep_restart = hrtimer_nanosleep_restart, + .timer_create = common_timer_create, + .timer_set = common_timer_set, + .timer_get = common_timer_get, + .timer_del = common_timer_del, + }; + + posix_timers_register_clock(CLOCK_REALTIME, &clock_realtime); + posix_timers_register_clock(CLOCK_MONOTONIC, &clock_monotonic); + posix_timers_register_clock(CLOCK_MONOTONIC_RAW, &clock_monotonic_raw); + posix_timers_register_clock(CLOCK_REALTIME_COARSE, &clock_realtime_coarse); + posix_timers_register_clock(CLOCK_MONOTONIC_COARSE, &clock_monotonic_coarse); + posix_timers_register_clock(CLOCK_BOOTTIME, &clock_boottime); + posix_timers_register_clock(CLOCK_TAI, &clock_tai); + + posix_timers_cache = kmem_cache_create("posix_timers_cache", + sizeof (struct k_itimer), 0, SLAB_PANIC, + NULL); + return 0; +} + +__initcall(init_posix_timers); + +static void schedule_next_timer(struct k_itimer *timr) +{ + struct hrtimer *timer = &timr->it.real.timer; + + if (timr->it.real.interval.tv64 == 0) + return; + + timr->it_overrun += (unsigned int) hrtimer_forward(timer, + timer->base->get_time(), + timr->it.real.interval); + + timr->it_overrun_last = timr->it_overrun; + timr->it_overrun = -1; + ++timr->it_requeue_pending; + hrtimer_restart(timer); +} + +/* + * This function is exported for use by the signal deliver code. It is + * called just prior to the info block being released and passes that + * block to us. It's function is to update the overrun entry AND to + * restart the timer. It should only be called if the timer is to be + * restarted (i.e. we have flagged this in the sys_private entry of the + * info block). + * + * To protect against the timer going away while the interrupt is queued, + * we require that the it_requeue_pending flag be set. + */ +void do_schedule_next_timer(struct siginfo *info) +{ + struct k_itimer *timr; + unsigned long flags; + + timr = lock_timer(info->si_tid, &flags); + + if (timr && timr->it_requeue_pending == info->si_sys_private) { + if (timr->it_clock < 0) + posix_cpu_timer_schedule(timr); + else + schedule_next_timer(timr); + + info->si_overrun += timr->it_overrun_last; + } + + if (timr) + unlock_timer(timr, flags); +} + +int posix_timer_event(struct k_itimer *timr, int si_private) +{ + struct task_struct *task; + int shared, ret = -1; + /* + * FIXME: if ->sigq is queued we can race with + * dequeue_signal()->do_schedule_next_timer(). + * + * If dequeue_signal() sees the "right" value of + * si_sys_private it calls do_schedule_next_timer(). + * We re-queue ->sigq and drop ->it_lock(). + * do_schedule_next_timer() locks the timer + * and re-schedules it while ->sigq is pending. + * Not really bad, but not that we want. + */ + timr->sigq->info.si_sys_private = si_private; + + rcu_read_lock(); + task = pid_task(timr->it_pid, PIDTYPE_PID); + if (task) { + shared = !(timr->it_sigev_notify & SIGEV_THREAD_ID); + ret = send_sigqueue(timr->sigq, task, shared); + } + rcu_read_unlock(); + /* If we failed to send the signal the timer stops. */ + return ret > 0; +} +EXPORT_SYMBOL_GPL(posix_timer_event); + +/* + * This function gets called when a POSIX.1b interval timer expires. It + * is used as a callback from the kernel internal timer. The + * run_timer_list code ALWAYS calls with interrupts on. + + * This code is for CLOCK_REALTIME* and CLOCK_MONOTONIC* timers. + */ +static enum hrtimer_restart posix_timer_fn(struct hrtimer *timer) +{ + struct k_itimer *timr; + unsigned long flags; + int si_private = 0; + enum hrtimer_restart ret = HRTIMER_NORESTART; + + timr = container_of(timer, struct k_itimer, it.real.timer); + spin_lock_irqsave(&timr->it_lock, flags); + + if (timr->it.real.interval.tv64 != 0) + si_private = ++timr->it_requeue_pending; + + if (posix_timer_event(timr, si_private)) { + /* + * signal was not sent because of sig_ignor + * we will not get a call back to restart it AND + * it should be restarted. + */ + if (timr->it.real.interval.tv64 != 0) { + ktime_t now = hrtimer_cb_get_time(timer); + + /* + * FIXME: What we really want, is to stop this + * timer completely and restart it in case the + * SIG_IGN is removed. This is a non trivial + * change which involves sighand locking + * (sigh !), which we don't want to do late in + * the release cycle. + * + * For now we just let timers with an interval + * less than a jiffie expire every jiffie to + * avoid softirq starvation in case of SIG_IGN + * and a very small interval, which would put + * the timer right back on the softirq pending + * list. By moving now ahead of time we trick + * hrtimer_forward() to expire the timer + * later, while we still maintain the overrun + * accuracy, but have some inconsistency in + * the timer_gettime() case. This is at least + * better than a starved softirq. A more + * complex fix which solves also another related + * inconsistency is already in the pipeline. + */ +#ifdef CONFIG_HIGH_RES_TIMERS + { + ktime_t kj = ktime_set(0, NSEC_PER_SEC / HZ); + + if (timr->it.real.interval.tv64 < kj.tv64) + now = ktime_add(now, kj); + } +#endif + timr->it_overrun += (unsigned int) + hrtimer_forward(timer, now, + timr->it.real.interval); + ret = HRTIMER_RESTART; + ++timr->it_requeue_pending; + } + } + + unlock_timer(timr, flags); + return ret; +} + +static struct pid *good_sigevent(sigevent_t * event) +{ + struct task_struct *rtn = current->group_leader; + int sig = event->sigev_signo; + + if ((event->sigev_notify & SIGEV_THREAD_ID ) && + (!(rtn = find_task_by_vpid(event->sigev_notify_thread_id)) || + !same_thread_group(rtn, current) || + (event->sigev_notify & ~SIGEV_THREAD_ID) != SIGEV_SIGNAL)) + return NULL; + + if (((event->sigev_notify & ~SIGEV_THREAD_ID) != SIGEV_NONE) && + (sig <= 0 || sig > SIGRTMAX || sig_kernel_only(sig) || + sig_kernel_coredump(sig))) + return NULL; + + return task_pid(rtn); +} + +void posix_timers_register_clock(const clockid_t clock_id, + struct k_clock *new_clock) +{ + if ((unsigned) clock_id >= MAX_CLOCKS) { + printk(KERN_WARNING "POSIX clock register failed for clock_id %d\n", + clock_id); + return; + } + + if (!new_clock->clock_get) { + printk(KERN_WARNING "POSIX clock id %d lacks clock_get()\n", + clock_id); + return; + } + if (!new_clock->clock_getres) { + printk(KERN_WARNING "POSIX clock id %d lacks clock_getres()\n", + clock_id); + return; + } + + posix_clocks[clock_id] = *new_clock; +} +EXPORT_SYMBOL_GPL(posix_timers_register_clock); + +static struct k_itimer * alloc_posix_timer(void) +{ + struct k_itimer *tmr; + tmr = kmem_cache_zalloc(posix_timers_cache, GFP_KERNEL); + if (!tmr) + return tmr; + if (unlikely(!(tmr->sigq = sigqueue_alloc()))) { + kmem_cache_free(posix_timers_cache, tmr); + return NULL; + } + memset(&tmr->sigq->info, 0, sizeof(siginfo_t)); + return tmr; +} + +static void k_itimer_rcu_free(struct rcu_head *head) +{ + struct k_itimer *tmr = container_of(head, struct k_itimer, it.rcu); + + kmem_cache_free(posix_timers_cache, tmr); +} + +#define IT_ID_SET 1 +#define IT_ID_NOT_SET 0 +static void release_posix_timer(struct k_itimer *tmr, int it_id_set) +{ + if (it_id_set) { + unsigned long flags; + spin_lock_irqsave(&hash_lock, flags); + hlist_del_rcu(&tmr->t_hash); + spin_unlock_irqrestore(&hash_lock, flags); + } + put_pid(tmr->it_pid); + sigqueue_free(tmr->sigq); + call_rcu(&tmr->it.rcu, k_itimer_rcu_free); +} + +static struct k_clock *clockid_to_kclock(const clockid_t id) +{ + if (id < 0) + return (id & CLOCKFD_MASK) == CLOCKFD ? + &clock_posix_dynamic : &clock_posix_cpu; + + if (id >= MAX_CLOCKS || !posix_clocks[id].clock_getres) + return NULL; + return &posix_clocks[id]; +} + +static int common_timer_create(struct k_itimer *new_timer) +{ + hrtimer_init(&new_timer->it.real.timer, new_timer->it_clock, 0); + return 0; +} + +/* Create a POSIX.1b interval timer. */ + +SYSCALL_DEFINE3(timer_create, const clockid_t, which_clock, + struct sigevent __user *, timer_event_spec, + timer_t __user *, created_timer_id) +{ + struct k_clock *kc = clockid_to_kclock(which_clock); + struct k_itimer *new_timer; + int error, new_timer_id; + sigevent_t event; + int it_id_set = IT_ID_NOT_SET; + + if (!kc) + return -EINVAL; + if (!kc->timer_create) + return -EOPNOTSUPP; + + new_timer = alloc_posix_timer(); + if (unlikely(!new_timer)) + return -EAGAIN; + + spin_lock_init(&new_timer->it_lock); + new_timer_id = posix_timer_add(new_timer); + if (new_timer_id < 0) { + error = new_timer_id; + goto out; + } + + it_id_set = IT_ID_SET; + new_timer->it_id = (timer_t) new_timer_id; + new_timer->it_clock = which_clock; + new_timer->it_overrun = -1; + + if (timer_event_spec) { + if (copy_from_user(&event, timer_event_spec, sizeof (event))) { + error = -EFAULT; + goto out; + } + rcu_read_lock(); + new_timer->it_pid = get_pid(good_sigevent(&event)); + rcu_read_unlock(); + if (!new_timer->it_pid) { + error = -EINVAL; + goto out; + } + } else { + memset(&event.sigev_value, 0, sizeof(event.sigev_value)); + event.sigev_notify = SIGEV_SIGNAL; + event.sigev_signo = SIGALRM; + event.sigev_value.sival_int = new_timer->it_id; + new_timer->it_pid = get_pid(task_tgid(current)); + } + + new_timer->it_sigev_notify = event.sigev_notify; + new_timer->sigq->info.si_signo = event.sigev_signo; + new_timer->sigq->info.si_value = event.sigev_value; + new_timer->sigq->info.si_tid = new_timer->it_id; + new_timer->sigq->info.si_code = SI_TIMER; + + if (copy_to_user(created_timer_id, + &new_timer_id, sizeof (new_timer_id))) { + error = -EFAULT; + goto out; + } + + error = kc->timer_create(new_timer); + if (error) + goto out; + + spin_lock_irq(¤t->sighand->siglock); + new_timer->it_signal = current->signal; + list_add(&new_timer->list, ¤t->signal->posix_timers); + spin_unlock_irq(¤t->sighand->siglock); + + return 0; + /* + * In the case of the timer belonging to another task, after + * the task is unlocked, the timer is owned by the other task + * and may cease to exist at any time. Don't use or modify + * new_timer after the unlock call. + */ +out: + release_posix_timer(new_timer, it_id_set); + return error; +} + +/* + * Locking issues: We need to protect the result of the id look up until + * we get the timer locked down so it is not deleted under us. The + * removal is done under the idr spinlock so we use that here to bridge + * the find to the timer lock. To avoid a dead lock, the timer id MUST + * be release with out holding the timer lock. + */ +static struct k_itimer *__lock_timer(timer_t timer_id, unsigned long *flags) +{ + struct k_itimer *timr; + + /* + * timer_t could be any type >= int and we want to make sure any + * @timer_id outside positive int range fails lookup. + */ + if ((unsigned long long)timer_id > INT_MAX) + return NULL; + + rcu_read_lock(); + timr = posix_timer_by_id(timer_id); + if (timr) { + spin_lock_irqsave(&timr->it_lock, *flags); + if (timr->it_signal == current->signal) { + rcu_read_unlock(); + return timr; + } + spin_unlock_irqrestore(&timr->it_lock, *flags); + } + rcu_read_unlock(); + + return NULL; +} + +/* + * Get the time remaining on a POSIX.1b interval timer. This function + * is ALWAYS called with spin_lock_irq on the timer, thus it must not + * mess with irq. + * + * We have a couple of messes to clean up here. First there is the case + * of a timer that has a requeue pending. These timers should appear to + * be in the timer list with an expiry as if we were to requeue them + * now. + * + * The second issue is the SIGEV_NONE timer which may be active but is + * not really ever put in the timer list (to save system resources). + * This timer may be expired, and if so, we will do it here. Otherwise + * it is the same as a requeue pending timer WRT to what we should + * report. + */ +static void +common_timer_get(struct k_itimer *timr, struct itimerspec *cur_setting) +{ + ktime_t now, remaining, iv; + struct hrtimer *timer = &timr->it.real.timer; + + memset(cur_setting, 0, sizeof(struct itimerspec)); + + iv = timr->it.real.interval; + + /* interval timer ? */ + if (iv.tv64) + cur_setting->it_interval = ktime_to_timespec(iv); + else if (!hrtimer_active(timer) && + (timr->it_sigev_notify & ~SIGEV_THREAD_ID) != SIGEV_NONE) + return; + + now = timer->base->get_time(); + + /* + * When a requeue is pending or this is a SIGEV_NONE + * timer move the expiry time forward by intervals, so + * expiry is > now. + */ + if (iv.tv64 && (timr->it_requeue_pending & REQUEUE_PENDING || + (timr->it_sigev_notify & ~SIGEV_THREAD_ID) == SIGEV_NONE)) + timr->it_overrun += (unsigned int) hrtimer_forward(timer, now, iv); + + remaining = ktime_sub(hrtimer_get_expires(timer), now); + /* Return 0 only, when the timer is expired and not pending */ + if (remaining.tv64 <= 0) { + /* + * A single shot SIGEV_NONE timer must return 0, when + * it is expired ! + */ + if ((timr->it_sigev_notify & ~SIGEV_THREAD_ID) != SIGEV_NONE) + cur_setting->it_value.tv_nsec = 1; + } else + cur_setting->it_value = ktime_to_timespec(remaining); +} + +/* Get the time remaining on a POSIX.1b interval timer. */ +SYSCALL_DEFINE2(timer_gettime, timer_t, timer_id, + struct itimerspec __user *, setting) +{ + struct itimerspec cur_setting; + struct k_itimer *timr; + struct k_clock *kc; + unsigned long flags; + int ret = 0; + + timr = lock_timer(timer_id, &flags); + if (!timr) + return -EINVAL; + + kc = clockid_to_kclock(timr->it_clock); + if (WARN_ON_ONCE(!kc || !kc->timer_get)) + ret = -EINVAL; + else + kc->timer_get(timr, &cur_setting); + + unlock_timer(timr, flags); + + if (!ret && copy_to_user(setting, &cur_setting, sizeof (cur_setting))) + return -EFAULT; + + return ret; +} + +/* + * Get the number of overruns of a POSIX.1b interval timer. This is to + * be the overrun of the timer last delivered. At the same time we are + * accumulating overruns on the next timer. The overrun is frozen when + * the signal is delivered, either at the notify time (if the info block + * is not queued) or at the actual delivery time (as we are informed by + * the call back to do_schedule_next_timer(). So all we need to do is + * to pick up the frozen overrun. + */ +SYSCALL_DEFINE1(timer_getoverrun, timer_t, timer_id) +{ + struct k_itimer *timr; + int overrun; + unsigned long flags; + + timr = lock_timer(timer_id, &flags); + if (!timr) + return -EINVAL; + + overrun = timr->it_overrun_last; + unlock_timer(timr, flags); + + return overrun; +} + +/* + * Protected by RCU! + */ +static void timer_wait_for_callback(struct k_clock *kc, struct k_itimer *timr) +{ +#ifdef CONFIG_PREEMPT_RT_FULL + if (kc->timer_set == common_timer_set) + hrtimer_wait_for_timer(&timr->it.real.timer); + else + /* FIXME: Whacky hack for posix-cpu-timers */ + schedule_timeout(1); +#endif +} + +/* Set a POSIX.1b interval timer. */ +/* timr->it_lock is taken. */ +static int +common_timer_set(struct k_itimer *timr, int flags, + struct itimerspec *new_setting, struct itimerspec *old_setting) +{ + struct hrtimer *timer = &timr->it.real.timer; + enum hrtimer_mode mode; + + if (old_setting) + common_timer_get(timr, old_setting); + + /* disable the timer */ + timr->it.real.interval.tv64 = 0; + /* + * careful here. If smp we could be in the "fire" routine which will + * be spinning as we hold the lock. But this is ONLY an SMP issue. + */ + if (hrtimer_try_to_cancel(timer) < 0) + return TIMER_RETRY; + + timr->it_requeue_pending = (timr->it_requeue_pending + 2) & + ~REQUEUE_PENDING; + timr->it_overrun_last = 0; + + /* switch off the timer when it_value is zero */ + if (!new_setting->it_value.tv_sec && !new_setting->it_value.tv_nsec) + return 0; + + mode = flags & TIMER_ABSTIME ? HRTIMER_MODE_ABS : HRTIMER_MODE_REL; + hrtimer_init(&timr->it.real.timer, timr->it_clock, mode); + timr->it.real.timer.function = posix_timer_fn; + + hrtimer_set_expires(timer, timespec_to_ktime(new_setting->it_value)); + + /* Convert interval */ + timr->it.real.interval = timespec_to_ktime(new_setting->it_interval); + + /* SIGEV_NONE timers are not queued ! See common_timer_get */ + if (((timr->it_sigev_notify & ~SIGEV_THREAD_ID) == SIGEV_NONE)) { + /* Setup correct expiry time for relative timers */ + if (mode == HRTIMER_MODE_REL) { + hrtimer_add_expires(timer, timer->base->get_time()); + } + return 0; + } + + hrtimer_start_expires(timer, mode); + return 0; +} + +/* Set a POSIX.1b interval timer */ +SYSCALL_DEFINE4(timer_settime, timer_t, timer_id, int, flags, + const struct itimerspec __user *, new_setting, + struct itimerspec __user *, old_setting) +{ + struct k_itimer *timr; + struct itimerspec new_spec, old_spec; + int error = 0; + unsigned long flag; + struct itimerspec *rtn = old_setting ? &old_spec : NULL; + struct k_clock *kc; + + if (!new_setting) + return -EINVAL; + + if (copy_from_user(&new_spec, new_setting, sizeof (new_spec))) + return -EFAULT; + + if (!timespec_valid(&new_spec.it_interval) || + !timespec_valid(&new_spec.it_value)) + return -EINVAL; +retry: + timr = lock_timer(timer_id, &flag); + if (!timr) + return -EINVAL; + + rcu_read_lock(); + kc = clockid_to_kclock(timr->it_clock); + if (WARN_ON_ONCE(!kc || !kc->timer_set)) + error = -EINVAL; + else + error = kc->timer_set(timr, flags, &new_spec, rtn); + + unlock_timer(timr, flag); + if (error == TIMER_RETRY) { + timer_wait_for_callback(kc, timr); + rtn = NULL; // We already got the old time... + rcu_read_unlock(); + goto retry; + } + rcu_read_unlock(); + + if (old_setting && !error && + copy_to_user(old_setting, &old_spec, sizeof (old_spec))) + error = -EFAULT; + + return error; +} + +static int common_timer_del(struct k_itimer *timer) +{ + timer->it.real.interval.tv64 = 0; + + if (hrtimer_try_to_cancel(&timer->it.real.timer) < 0) + return TIMER_RETRY; + return 0; +} + +static inline int timer_delete_hook(struct k_itimer *timer) +{ + struct k_clock *kc = clockid_to_kclock(timer->it_clock); + + if (WARN_ON_ONCE(!kc || !kc->timer_del)) + return -EINVAL; + return kc->timer_del(timer); +} + +/* Delete a POSIX.1b interval timer. */ +SYSCALL_DEFINE1(timer_delete, timer_t, timer_id) +{ + struct k_itimer *timer; + unsigned long flags; + +retry_delete: + timer = lock_timer(timer_id, &flags); + if (!timer) + return -EINVAL; + + rcu_read_lock(); + if (timer_delete_hook(timer) == TIMER_RETRY) { + unlock_timer(timer, flags); + timer_wait_for_callback(clockid_to_kclock(timer->it_clock), + timer); + rcu_read_unlock(); + goto retry_delete; + } + rcu_read_unlock(); + + spin_lock(¤t->sighand->siglock); + list_del(&timer->list); + spin_unlock(¤t->sighand->siglock); + /* + * This keeps any tasks waiting on the spin lock from thinking + * they got something (see the lock code above). + */ + timer->it_signal = NULL; + + unlock_timer(timer, flags); + release_posix_timer(timer, IT_ID_SET); + return 0; +} + +/* + * return timer owned by the process, used by exit_itimers + */ +static void itimer_delete(struct k_itimer *timer) +{ + unsigned long flags; + +retry_delete: + spin_lock_irqsave(&timer->it_lock, flags); + + /* On RT we can race with a deletion */ + if (!timer->it_signal) { + unlock_timer(timer, flags); + return; + } + + if (timer_delete_hook(timer) == TIMER_RETRY) { + rcu_read_lock(); + unlock_timer(timer, flags); + timer_wait_for_callback(clockid_to_kclock(timer->it_clock), + timer); + rcu_read_unlock(); + goto retry_delete; + } + list_del(&timer->list); + /* + * This keeps any tasks waiting on the spin lock from thinking + * they got something (see the lock code above). + */ + timer->it_signal = NULL; + + unlock_timer(timer, flags); + release_posix_timer(timer, IT_ID_SET); +} + +/* + * This is called by do_exit or de_thread, only when there are no more + * references to the shared signal_struct. + */ +void exit_itimers(struct signal_struct *sig) +{ + struct k_itimer *tmr; + + while (!list_empty(&sig->posix_timers)) { + tmr = list_entry(sig->posix_timers.next, struct k_itimer, list); + itimer_delete(tmr); + } +} + +SYSCALL_DEFINE2(clock_settime, const clockid_t, which_clock, + const struct timespec __user *, tp) +{ + struct k_clock *kc = clockid_to_kclock(which_clock); + struct timespec new_tp; + + if (!kc || !kc->clock_set) + return -EINVAL; + + if (copy_from_user(&new_tp, tp, sizeof (*tp))) + return -EFAULT; + + return kc->clock_set(which_clock, &new_tp); +} + +SYSCALL_DEFINE2(clock_gettime, const clockid_t, which_clock, + struct timespec __user *,tp) +{ + struct k_clock *kc = clockid_to_kclock(which_clock); + struct timespec kernel_tp; + int error; + + if (!kc) + return -EINVAL; + + error = kc->clock_get(which_clock, &kernel_tp); + + if (!error && copy_to_user(tp, &kernel_tp, sizeof (kernel_tp))) + error = -EFAULT; + + return error; +} + +SYSCALL_DEFINE2(clock_adjtime, const clockid_t, which_clock, + struct timex __user *, utx) +{ + struct k_clock *kc = clockid_to_kclock(which_clock); + struct timex ktx; + int err; + + if (!kc) + return -EINVAL; + if (!kc->clock_adj) + return -EOPNOTSUPP; + + if (copy_from_user(&ktx, utx, sizeof(ktx))) + return -EFAULT; + + err = kc->clock_adj(which_clock, &ktx); + + if (err >= 0 && copy_to_user(utx, &ktx, sizeof(ktx))) + return -EFAULT; + + return err; +} + +SYSCALL_DEFINE2(clock_getres, const clockid_t, which_clock, + struct timespec __user *, tp) +{ + struct k_clock *kc = clockid_to_kclock(which_clock); + struct timespec rtn_tp; + int error; + + if (!kc) + return -EINVAL; + + error = kc->clock_getres(which_clock, &rtn_tp); + + if (!error && tp && copy_to_user(tp, &rtn_tp, sizeof (rtn_tp))) + error = -EFAULT; + + return error; +} + +/* + * nanosleep for monotonic and realtime clocks + */ +static int common_nsleep(const clockid_t which_clock, int flags, + struct timespec *tsave, struct timespec __user *rmtp) +{ + return hrtimer_nanosleep(tsave, rmtp, flags & TIMER_ABSTIME ? + HRTIMER_MODE_ABS : HRTIMER_MODE_REL, + which_clock); +} + +SYSCALL_DEFINE4(clock_nanosleep, const clockid_t, which_clock, int, flags, + const struct timespec __user *, rqtp, + struct timespec __user *, rmtp) +{ + struct k_clock *kc = clockid_to_kclock(which_clock); + struct timespec t; + + if (!kc) + return -EINVAL; + if (!kc->nsleep) + return -ENANOSLEEP_NOTSUP; + + if (copy_from_user(&t, rqtp, sizeof (struct timespec))) + return -EFAULT; + + if (!timespec_valid(&t)) + return -EINVAL; + + return kc->nsleep(which_clock, flags, &t, rmtp); +} + +/* + * This will restart clock_nanosleep. This is required only by + * compat_clock_nanosleep_restart for now. + */ +long clock_nanosleep_restart(struct restart_block *restart_block) +{ + clockid_t which_clock = restart_block->nanosleep.clockid; + struct k_clock *kc = clockid_to_kclock(which_clock); + + if (WARN_ON_ONCE(!kc || !kc->nsleep_restart)) + return -EINVAL; + + return kc->nsleep_restart(restart_block); +} diff --git a/kernel/kernel/time/sched_clock.c b/kernel/kernel/time/sched_clock.c new file mode 100644 index 000000000..a26036d37 --- /dev/null +++ b/kernel/kernel/time/sched_clock.c @@ -0,0 +1,303 @@ +/* + * sched_clock.c: Generic sched_clock() support, to extend low level + * hardware time counters to full 64-bit ns values. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +/** + * struct clock_read_data - data required to read from sched_clock() + * + * @epoch_ns: sched_clock() value at last update + * @epoch_cyc: Clock cycle value at last update. + * @sched_clock_mask: Bitmask for two's complement subtraction of non 64bit + * clocks. + * @read_sched_clock: Current clock source (or dummy source when suspended). + * @mult: Multipler for scaled math conversion. + * @shift: Shift value for scaled math conversion. + * + * Care must be taken when updating this structure; it is read by + * some very hot code paths. It occupies <=40 bytes and, when combined + * with the seqcount used to synchronize access, comfortably fits into + * a 64 byte cache line. + */ +struct clock_read_data { + u64 epoch_ns; + u64 epoch_cyc; + u64 sched_clock_mask; + u64 (*read_sched_clock)(void); + u32 mult; + u32 shift; +}; + +/** + * struct clock_data - all data needed for sched_clock() (including + * registration of a new clock source) + * + * @seq: Sequence counter for protecting updates. The lowest + * bit is the index for @read_data. + * @read_data: Data required to read from sched_clock. + * @wrap_kt: Duration for which clock can run before wrapping. + * @rate: Tick rate of the registered clock. + * @actual_read_sched_clock: Registered hardware level clock read function. + * + * The ordering of this structure has been chosen to optimize cache + * performance. In particular 'seq' and 'read_data[0]' (combined) should fit + * into a single 64-byte cache line. + */ +struct clock_data { + seqcount_t seq; + struct clock_read_data read_data[2]; + ktime_t wrap_kt; + unsigned long rate; + + u64 (*actual_read_sched_clock)(void); +}; + +static struct hrtimer sched_clock_timer; +static int irqtime = -1; + +core_param(irqtime, irqtime, int, 0400); + +static u64 notrace jiffy_sched_clock_read(void) +{ + /* + * We don't need to use get_jiffies_64 on 32-bit arches here + * because we register with BITS_PER_LONG + */ + return (u64)(jiffies - INITIAL_JIFFIES); +} + +static struct clock_data cd ____cacheline_aligned = { + .read_data[0] = { .mult = NSEC_PER_SEC / HZ, + .read_sched_clock = jiffy_sched_clock_read, }, + .actual_read_sched_clock = jiffy_sched_clock_read, +}; + +static inline u64 notrace cyc_to_ns(u64 cyc, u32 mult, u32 shift) +{ + return (cyc * mult) >> shift; +} + +unsigned long long notrace sched_clock(void) +{ + u64 cyc, res; + unsigned long seq; + struct clock_read_data *rd; + + do { + seq = raw_read_seqcount(&cd.seq); + rd = cd.read_data + (seq & 1); + + cyc = (rd->read_sched_clock() - rd->epoch_cyc) & + rd->sched_clock_mask; + res = rd->epoch_ns + cyc_to_ns(cyc, rd->mult, rd->shift); + } while (read_seqcount_retry(&cd.seq, seq)); + + return res; +} + +/* + * Updating the data required to read the clock. + * + * sched_clock() will never observe mis-matched data even if called from + * an NMI. We do this by maintaining an odd/even copy of the data and + * steering sched_clock() to one or the other using a sequence counter. + * In order to preserve the data cache profile of sched_clock() as much + * as possible the system reverts back to the even copy when the update + * completes; the odd copy is used *only* during an update. + */ +static void update_clock_read_data(struct clock_read_data *rd) +{ + /* update the backup (odd) copy with the new data */ + cd.read_data[1] = *rd; + + /* steer readers towards the odd copy */ + raw_write_seqcount_latch(&cd.seq); + + /* now its safe for us to update the normal (even) copy */ + cd.read_data[0] = *rd; + + /* switch readers back to the even copy */ + raw_write_seqcount_latch(&cd.seq); +} + +/* + * Atomically update the sched_clock() epoch. + */ +static void update_sched_clock(void) +{ + u64 cyc; + u64 ns; + struct clock_read_data rd; + + rd = cd.read_data[0]; + + cyc = cd.actual_read_sched_clock(); + ns = rd.epoch_ns + cyc_to_ns((cyc - rd.epoch_cyc) & rd.sched_clock_mask, rd.mult, rd.shift); + + rd.epoch_ns = ns; + rd.epoch_cyc = cyc; + + update_clock_read_data(&rd); +} + +static enum hrtimer_restart sched_clock_poll(struct hrtimer *hrt) +{ + update_sched_clock(); + hrtimer_forward_now(hrt, cd.wrap_kt); + + return HRTIMER_RESTART; +} + +void __init +sched_clock_register(u64 (*read)(void), int bits, unsigned long rate) +{ + u64 res, wrap, new_mask, new_epoch, cyc, ns; + u32 new_mult, new_shift; + unsigned long r; + char r_unit; + struct clock_read_data rd; + + if (cd.rate > rate) + return; + + WARN_ON(!irqs_disabled()); + + /* Calculate the mult/shift to convert counter ticks to ns. */ + clocks_calc_mult_shift(&new_mult, &new_shift, rate, NSEC_PER_SEC, 3600); + + new_mask = CLOCKSOURCE_MASK(bits); + cd.rate = rate; + + /* Calculate how many nanosecs until we risk wrapping */ + wrap = clocks_calc_max_nsecs(new_mult, new_shift, 0, new_mask, NULL); + cd.wrap_kt = ns_to_ktime(wrap); + + rd = cd.read_data[0]; + + /* Update epoch for new counter and update 'epoch_ns' from old counter*/ + new_epoch = read(); + cyc = cd.actual_read_sched_clock(); + ns = rd.epoch_ns + cyc_to_ns((cyc - rd.epoch_cyc) & rd.sched_clock_mask, rd.mult, rd.shift); + cd.actual_read_sched_clock = read; + + rd.read_sched_clock = read; + rd.sched_clock_mask = new_mask; + rd.mult = new_mult; + rd.shift = new_shift; + rd.epoch_cyc = new_epoch; + rd.epoch_ns = ns; + + update_clock_read_data(&rd); + + r = rate; + if (r >= 4000000) { + r /= 1000000; + r_unit = 'M'; + } else { + if (r >= 1000) { + r /= 1000; + r_unit = 'k'; + } else { + r_unit = ' '; + } + } + + /* Calculate the ns resolution of this counter */ + res = cyc_to_ns(1ULL, new_mult, new_shift); + + pr_info("sched_clock: %u bits at %lu%cHz, resolution %lluns, wraps every %lluns\n", + bits, r, r_unit, res, wrap); + + /* Enable IRQ time accounting if we have a fast enough sched_clock() */ + if (irqtime > 0 || (irqtime == -1 && rate >= 1000000)) + enable_sched_clock_irqtime(); + + pr_debug("Registered %pF as sched_clock source\n", read); +} + +void __init sched_clock_postinit(void) +{ + /* + * If no sched_clock() function has been provided at that point, + * make it the final one one. + */ + if (cd.actual_read_sched_clock == jiffy_sched_clock_read) + sched_clock_register(jiffy_sched_clock_read, BITS_PER_LONG, HZ); + + update_sched_clock(); + + /* + * Start the timer to keep sched_clock() properly updated and + * sets the initial epoch. + */ + hrtimer_init(&sched_clock_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + sched_clock_timer.function = sched_clock_poll; + hrtimer_start(&sched_clock_timer, cd.wrap_kt, HRTIMER_MODE_REL); +} + +/* + * Clock read function for use when the clock is suspended. + * + * This function makes it appear to sched_clock() as if the clock + * stopped counting at its last update. + * + * This function must only be called from the critical + * section in sched_clock(). It relies on the read_seqcount_retry() + * at the end of the critical section to be sure we observe the + * correct copy of 'epoch_cyc'. + */ +static u64 notrace suspended_sched_clock_read(void) +{ + unsigned long seq = raw_read_seqcount(&cd.seq); + + return cd.read_data[seq & 1].epoch_cyc; +} + +static int sched_clock_suspend(void) +{ + struct clock_read_data *rd = &cd.read_data[0]; + + update_sched_clock(); + hrtimer_cancel(&sched_clock_timer); + rd->read_sched_clock = suspended_sched_clock_read; + + return 0; +} + +static void sched_clock_resume(void) +{ + struct clock_read_data *rd = &cd.read_data[0]; + + rd->epoch_cyc = cd.actual_read_sched_clock(); + hrtimer_start(&sched_clock_timer, cd.wrap_kt, HRTIMER_MODE_REL); + rd->read_sched_clock = cd.actual_read_sched_clock; +} + +static struct syscore_ops sched_clock_ops = { + .suspend = sched_clock_suspend, + .resume = sched_clock_resume, +}; + +static int __init sched_clock_syscore_init(void) +{ + register_syscore_ops(&sched_clock_ops); + + return 0; +} +device_initcall(sched_clock_syscore_init); diff --git a/kernel/kernel/time/test_udelay.c b/kernel/kernel/time/test_udelay.c new file mode 100644 index 000000000..e622ba365 --- /dev/null +++ b/kernel/kernel/time/test_udelay.c @@ -0,0 +1,168 @@ +/* + * udelay() test kernel module + * + * Test is executed by writing and reading to /sys/kernel/debug/udelay_test + * Tests are configured by writing: USECS ITERATIONS + * Tests are executed by reading from the same file. + * Specifying usecs of 0 or negative values will run multiples tests. + * + * Copyright (C) 2014 Google, Inc. + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#include +#include +#include +#include +#include + +#define DEFAULT_ITERATIONS 100 + +#define DEBUGFS_FILENAME "udelay_test" + +static DEFINE_MUTEX(udelay_test_lock); +static struct dentry *udelay_test_debugfs_file; +static int udelay_test_usecs; +static int udelay_test_iterations = DEFAULT_ITERATIONS; + +static int udelay_test_single(struct seq_file *s, int usecs, uint32_t iters) +{ + int min = 0, max = 0, fail_count = 0; + uint64_t sum = 0; + uint64_t avg; + int i; + /* Allow udelay to be up to 0.5% fast */ + int allowed_error_ns = usecs * 5; + + for (i = 0; i < iters; ++i) { + struct timespec ts1, ts2; + int time_passed; + + ktime_get_ts(&ts1); + udelay(usecs); + ktime_get_ts(&ts2); + time_passed = timespec_to_ns(&ts2) - timespec_to_ns(&ts1); + + if (i == 0 || time_passed < min) + min = time_passed; + if (i == 0 || time_passed > max) + max = time_passed; + if ((time_passed + allowed_error_ns) / 1000 < usecs) + ++fail_count; + WARN_ON(time_passed < 0); + sum += time_passed; + } + + avg = sum; + do_div(avg, iters); + seq_printf(s, "%d usecs x %d: exp=%d allowed=%d min=%d avg=%lld max=%d", + usecs, iters, usecs * 1000, + (usecs * 1000) - allowed_error_ns, min, avg, max); + if (fail_count) + seq_printf(s, " FAIL=%d", fail_count); + seq_puts(s, "\n"); + + return 0; +} + +static int udelay_test_show(struct seq_file *s, void *v) +{ + int usecs; + int iters; + int ret = 0; + + mutex_lock(&udelay_test_lock); + usecs = udelay_test_usecs; + iters = udelay_test_iterations; + mutex_unlock(&udelay_test_lock); + + if (usecs > 0 && iters > 0) { + return udelay_test_single(s, usecs, iters); + } else if (usecs == 0) { + struct timespec ts; + + ktime_get_ts(&ts); + seq_printf(s, "udelay() test (lpj=%ld kt=%ld.%09ld)\n", + loops_per_jiffy, ts.tv_sec, ts.tv_nsec); + seq_puts(s, "usage:\n"); + seq_puts(s, "echo USECS [ITERS] > " DEBUGFS_FILENAME "\n"); + seq_puts(s, "cat " DEBUGFS_FILENAME "\n"); + } + + return ret; +} + +static int udelay_test_open(struct inode *inode, struct file *file) +{ + return single_open(file, udelay_test_show, inode->i_private); +} + +static ssize_t udelay_test_write(struct file *file, const char __user *buf, + size_t count, loff_t *pos) +{ + char lbuf[32]; + int ret; + int usecs; + int iters; + + if (count >= sizeof(lbuf)) + return -EINVAL; + + if (copy_from_user(lbuf, buf, count)) + return -EFAULT; + lbuf[count] = '\0'; + + ret = sscanf(lbuf, "%d %d", &usecs, &iters); + if (ret < 1) + return -EINVAL; + else if (ret < 2) + iters = DEFAULT_ITERATIONS; + + mutex_lock(&udelay_test_lock); + udelay_test_usecs = usecs; + udelay_test_iterations = iters; + mutex_unlock(&udelay_test_lock); + + return count; +} + +static const struct file_operations udelay_test_debugfs_ops = { + .owner = THIS_MODULE, + .open = udelay_test_open, + .read = seq_read, + .write = udelay_test_write, + .llseek = seq_lseek, + .release = single_release, +}; + +static int __init udelay_test_init(void) +{ + mutex_lock(&udelay_test_lock); + udelay_test_debugfs_file = debugfs_create_file(DEBUGFS_FILENAME, + S_IRUSR, NULL, NULL, &udelay_test_debugfs_ops); + mutex_unlock(&udelay_test_lock); + + return 0; +} + +module_init(udelay_test_init); + +static void __exit udelay_test_exit(void) +{ + mutex_lock(&udelay_test_lock); + debugfs_remove(udelay_test_debugfs_file); + mutex_unlock(&udelay_test_lock); +} + +module_exit(udelay_test_exit); + +MODULE_AUTHOR("David Riley "); +MODULE_LICENSE("GPL"); diff --git a/kernel/kernel/time/tick-broadcast-hrtimer.c b/kernel/kernel/time/tick-broadcast-hrtimer.c new file mode 100644 index 000000000..6aac4beed --- /dev/null +++ b/kernel/kernel/time/tick-broadcast-hrtimer.c @@ -0,0 +1,113 @@ +/* + * linux/kernel/time/tick-broadcast-hrtimer.c + * This file emulates a local clock event device + * via a pseudo clock device. + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "tick-internal.h" + +static struct hrtimer bctimer; + +static void bc_set_mode(enum clock_event_mode mode, + struct clock_event_device *bc) +{ + switch (mode) { + case CLOCK_EVT_MODE_SHUTDOWN: + /* + * Note, we cannot cancel the timer here as we might + * run into the following live lock scenario: + * + * cpu 0 cpu1 + * lock(broadcast_lock); + * hrtimer_interrupt() + * bc_handler() + * tick_handle_oneshot_broadcast(); + * lock(broadcast_lock); + * hrtimer_cancel() + * wait_for_callback() + */ + hrtimer_try_to_cancel(&bctimer); + break; + default: + break; + } +} + +/* + * This is called from the guts of the broadcast code when the cpu + * which is about to enter idle has the earliest broadcast timer event. + */ +static int bc_set_next(ktime_t expires, struct clock_event_device *bc) +{ + int bc_moved; + /* + * We try to cancel the timer first. If the callback is on + * flight on some other cpu then we let it handle it. If we + * were able to cancel the timer nothing can rearm it as we + * own broadcast_lock. + * + * However we can also be called from the event handler of + * ce_broadcast_hrtimer itself when it expires. We cannot + * restart the timer because we are in the callback, but we + * can set the expiry time and let the callback return + * HRTIMER_RESTART. + * + * Since we are in the idle loop at this point and because + * hrtimer_{start/cancel} functions call into tracing, + * calls to these functions must be bound within RCU_NONIDLE. + */ + RCU_NONIDLE(bc_moved = (hrtimer_try_to_cancel(&bctimer) >= 0) ? + !hrtimer_start(&bctimer, expires, HRTIMER_MODE_ABS_PINNED) : + 0); + if (bc_moved) { + /* Bind the "device" to the cpu */ + bc->bound_on = smp_processor_id(); + } else if (bc->bound_on == smp_processor_id()) { + hrtimer_set_expires(&bctimer, expires); + } + return 0; +} + +static struct clock_event_device ce_broadcast_hrtimer = { + .set_mode = bc_set_mode, + .set_next_ktime = bc_set_next, + .features = CLOCK_EVT_FEAT_ONESHOT | + CLOCK_EVT_FEAT_KTIME | + CLOCK_EVT_FEAT_HRTIMER, + .rating = 0, + .bound_on = -1, + .min_delta_ns = 1, + .max_delta_ns = KTIME_MAX, + .min_delta_ticks = 1, + .max_delta_ticks = ULONG_MAX, + .mult = 1, + .shift = 0, + .cpumask = cpu_all_mask, +}; + +static enum hrtimer_restart bc_handler(struct hrtimer *t) +{ + ce_broadcast_hrtimer.event_handler(&ce_broadcast_hrtimer); + + if (ce_broadcast_hrtimer.next_event.tv64 == KTIME_MAX) + return HRTIMER_NORESTART; + + return HRTIMER_RESTART; +} + +void tick_setup_hrtimer_broadcast(void) +{ + hrtimer_init(&bctimer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS); + bctimer.function = bc_handler; + clockevents_register_device(&ce_broadcast_hrtimer); +} diff --git a/kernel/kernel/time/tick-broadcast.c b/kernel/kernel/time/tick-broadcast.c new file mode 100644 index 000000000..7e8ca4f44 --- /dev/null +++ b/kernel/kernel/time/tick-broadcast.c @@ -0,0 +1,964 @@ +/* + * linux/kernel/time/tick-broadcast.c + * + * This file contains functions which emulate a local clock-event + * device via a broadcast event source. + * + * Copyright(C) 2005-2006, Thomas Gleixner + * Copyright(C) 2005-2007, Red Hat, Inc., Ingo Molnar + * Copyright(C) 2006-2007, Timesys Corp., Thomas Gleixner + * + * This code is licenced under the GPL version 2. For details see + * kernel-base/COPYING. + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "tick-internal.h" + +/* + * Broadcast support for broken x86 hardware, where the local apic + * timer stops in C3 state. + */ + +static struct tick_device tick_broadcast_device; +static cpumask_var_t tick_broadcast_mask; +static cpumask_var_t tick_broadcast_on; +static cpumask_var_t tmpmask; +static DEFINE_RAW_SPINLOCK(tick_broadcast_lock); +static int tick_broadcast_forced; + +#ifdef CONFIG_TICK_ONESHOT +static void tick_broadcast_clear_oneshot(int cpu); +static void tick_resume_broadcast_oneshot(struct clock_event_device *bc); +#else +static inline void tick_broadcast_clear_oneshot(int cpu) { } +static inline void tick_resume_broadcast_oneshot(struct clock_event_device *bc) { } +#endif + +/* + * Debugging: see timer_list.c + */ +struct tick_device *tick_get_broadcast_device(void) +{ + return &tick_broadcast_device; +} + +struct cpumask *tick_get_broadcast_mask(void) +{ + return tick_broadcast_mask; +} + +/* + * Start the device in periodic mode + */ +static void tick_broadcast_start_periodic(struct clock_event_device *bc) +{ + if (bc) + tick_setup_periodic(bc, 1); +} + +/* + * Check, if the device can be utilized as broadcast device: + */ +static bool tick_check_broadcast_device(struct clock_event_device *curdev, + struct clock_event_device *newdev) +{ + if ((newdev->features & CLOCK_EVT_FEAT_DUMMY) || + (newdev->features & CLOCK_EVT_FEAT_PERCPU) || + (newdev->features & CLOCK_EVT_FEAT_C3STOP)) + return false; + + if (tick_broadcast_device.mode == TICKDEV_MODE_ONESHOT && + !(newdev->features & CLOCK_EVT_FEAT_ONESHOT)) + return false; + + return !curdev || newdev->rating > curdev->rating; +} + +/* + * Conditionally install/replace broadcast device + */ +void tick_install_broadcast_device(struct clock_event_device *dev) +{ + struct clock_event_device *cur = tick_broadcast_device.evtdev; + + if (!tick_check_broadcast_device(cur, dev)) + return; + + if (!try_module_get(dev->owner)) + return; + + clockevents_exchange_device(cur, dev); + if (cur) + cur->event_handler = clockevents_handle_noop; + tick_broadcast_device.evtdev = dev; + if (!cpumask_empty(tick_broadcast_mask)) + tick_broadcast_start_periodic(dev); + /* + * Inform all cpus about this. We might be in a situation + * where we did not switch to oneshot mode because the per cpu + * devices are affected by CLOCK_EVT_FEAT_C3STOP and the lack + * of a oneshot capable broadcast device. Without that + * notification the systems stays stuck in periodic mode + * forever. + */ + if (dev->features & CLOCK_EVT_FEAT_ONESHOT) + tick_clock_notify(); +} + +/* + * Check, if the device is the broadcast device + */ +int tick_is_broadcast_device(struct clock_event_device *dev) +{ + return (dev && tick_broadcast_device.evtdev == dev); +} + +int tick_broadcast_update_freq(struct clock_event_device *dev, u32 freq) +{ + int ret = -ENODEV; + + if (tick_is_broadcast_device(dev)) { + raw_spin_lock(&tick_broadcast_lock); + ret = __clockevents_update_freq(dev, freq); + raw_spin_unlock(&tick_broadcast_lock); + } + return ret; +} + + +static void err_broadcast(const struct cpumask *mask) +{ + pr_crit_once("Failed to broadcast timer tick. Some CPUs may be unresponsive.\n"); +} + +static void tick_device_setup_broadcast_func(struct clock_event_device *dev) +{ + if (!dev->broadcast) + dev->broadcast = tick_broadcast; + if (!dev->broadcast) { + pr_warn_once("%s depends on broadcast, but no broadcast function available\n", + dev->name); + dev->broadcast = err_broadcast; + } +} + +/* + * Check, if the device is disfunctional and a place holder, which + * needs to be handled by the broadcast device. + */ +int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu) +{ + struct clock_event_device *bc = tick_broadcast_device.evtdev; + unsigned long flags; + int ret; + + raw_spin_lock_irqsave(&tick_broadcast_lock, flags); + + /* + * Devices might be registered with both periodic and oneshot + * mode disabled. This signals, that the device needs to be + * operated from the broadcast device and is a placeholder for + * the cpu local device. + */ + if (!tick_device_is_functional(dev)) { + dev->event_handler = tick_handle_periodic; + tick_device_setup_broadcast_func(dev); + cpumask_set_cpu(cpu, tick_broadcast_mask); + if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC) + tick_broadcast_start_periodic(bc); + else + tick_broadcast_setup_oneshot(bc); + ret = 1; + } else { + /* + * Clear the broadcast bit for this cpu if the + * device is not power state affected. + */ + if (!(dev->features & CLOCK_EVT_FEAT_C3STOP)) + cpumask_clear_cpu(cpu, tick_broadcast_mask); + else + tick_device_setup_broadcast_func(dev); + + /* + * Clear the broadcast bit if the CPU is not in + * periodic broadcast on state. + */ + if (!cpumask_test_cpu(cpu, tick_broadcast_on)) + cpumask_clear_cpu(cpu, tick_broadcast_mask); + + switch (tick_broadcast_device.mode) { + case TICKDEV_MODE_ONESHOT: + /* + * If the system is in oneshot mode we can + * unconditionally clear the oneshot mask bit, + * because the CPU is running and therefore + * not in an idle state which causes the power + * state affected device to stop. Let the + * caller initialize the device. + */ + tick_broadcast_clear_oneshot(cpu); + ret = 0; + break; + + case TICKDEV_MODE_PERIODIC: + /* + * If the system is in periodic mode, check + * whether the broadcast device can be + * switched off now. + */ + if (cpumask_empty(tick_broadcast_mask) && bc) + clockevents_shutdown(bc); + /* + * If we kept the cpu in the broadcast mask, + * tell the caller to leave the per cpu device + * in shutdown state. The periodic interrupt + * is delivered by the broadcast device. + */ + ret = cpumask_test_cpu(cpu, tick_broadcast_mask); + break; + default: + /* Nothing to do */ + ret = 0; + break; + } + } + raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags); + return ret; +} + +#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST +int tick_receive_broadcast(void) +{ + struct tick_device *td = this_cpu_ptr(&tick_cpu_device); + struct clock_event_device *evt = td->evtdev; + + if (!evt) + return -ENODEV; + + if (!evt->event_handler) + return -EINVAL; + + evt->event_handler(evt); + return 0; +} +#endif + +/* + * Broadcast the event to the cpus, which are set in the mask (mangled). + */ +static void tick_do_broadcast(struct cpumask *mask) +{ + int cpu = smp_processor_id(); + struct tick_device *td; + + /* + * Check, if the current cpu is in the mask + */ + if (cpumask_test_cpu(cpu, mask)) { + cpumask_clear_cpu(cpu, mask); + td = &per_cpu(tick_cpu_device, cpu); + td->evtdev->event_handler(td->evtdev); + } + + if (!cpumask_empty(mask)) { + /* + * It might be necessary to actually check whether the devices + * have different broadcast functions. For now, just use the + * one of the first device. This works as long as we have this + * misfeature only on x86 (lapic) + */ + td = &per_cpu(tick_cpu_device, cpumask_first(mask)); + td->evtdev->broadcast(mask); + } +} + +/* + * Periodic broadcast: + * - invoke the broadcast handlers + */ +static void tick_do_periodic_broadcast(void) +{ + cpumask_and(tmpmask, cpu_online_mask, tick_broadcast_mask); + tick_do_broadcast(tmpmask); +} + +/* + * Event handler for periodic broadcast ticks + */ +static void tick_handle_periodic_broadcast(struct clock_event_device *dev) +{ + ktime_t next; + + raw_spin_lock(&tick_broadcast_lock); + + tick_do_periodic_broadcast(); + + /* + * The device is in periodic mode. No reprogramming necessary: + */ + if (dev->state == CLOCK_EVT_STATE_PERIODIC) + goto unlock; + + /* + * Setup the next period for devices, which do not have + * periodic mode. We read dev->next_event first and add to it + * when the event already expired. clockevents_program_event() + * sets dev->next_event only when the event is really + * programmed to the device. + */ + for (next = dev->next_event; ;) { + next = ktime_add(next, tick_period); + + if (!clockevents_program_event(dev, next, false)) + goto unlock; + tick_do_periodic_broadcast(); + } +unlock: + raw_spin_unlock(&tick_broadcast_lock); +} + +/** + * tick_broadcast_control - Enable/disable or force broadcast mode + * @mode: The selected broadcast mode + * + * Called when the system enters a state where affected tick devices + * might stop. Note: TICK_BROADCAST_FORCE cannot be undone. + * + * Called with interrupts disabled, so clockevents_lock is not + * required here because the local clock event device cannot go away + * under us. + */ +void tick_broadcast_control(enum tick_broadcast_mode mode) +{ + struct clock_event_device *bc, *dev; + struct tick_device *td; + int cpu, bc_stopped; + + td = this_cpu_ptr(&tick_cpu_device); + dev = td->evtdev; + + /* + * Is the device not affected by the powerstate ? + */ + if (!dev || !(dev->features & CLOCK_EVT_FEAT_C3STOP)) + return; + + if (!tick_device_is_functional(dev)) + return; + + raw_spin_lock(&tick_broadcast_lock); + cpu = smp_processor_id(); + bc = tick_broadcast_device.evtdev; + bc_stopped = cpumask_empty(tick_broadcast_mask); + + switch (mode) { + case TICK_BROADCAST_FORCE: + tick_broadcast_forced = 1; + case TICK_BROADCAST_ON: + cpumask_set_cpu(cpu, tick_broadcast_on); + if (!cpumask_test_and_set_cpu(cpu, tick_broadcast_mask)) { + if (tick_broadcast_device.mode == + TICKDEV_MODE_PERIODIC) + clockevents_shutdown(dev); + } + break; + + case TICK_BROADCAST_OFF: + if (tick_broadcast_forced) + break; + cpumask_clear_cpu(cpu, tick_broadcast_on); + if (!tick_device_is_functional(dev)) + break; + if (cpumask_test_and_clear_cpu(cpu, tick_broadcast_mask)) { + if (tick_broadcast_device.mode == + TICKDEV_MODE_PERIODIC) + tick_setup_periodic(dev, 0); + } + break; + } + + if (cpumask_empty(tick_broadcast_mask)) { + if (!bc_stopped) + clockevents_shutdown(bc); + } else if (bc_stopped) { + if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC) + tick_broadcast_start_periodic(bc); + else + tick_broadcast_setup_oneshot(bc); + } + raw_spin_unlock(&tick_broadcast_lock); +} +EXPORT_SYMBOL_GPL(tick_broadcast_control); + +/* + * Set the periodic handler depending on broadcast on/off + */ +void tick_set_periodic_handler(struct clock_event_device *dev, int broadcast) +{ + if (!broadcast) + dev->event_handler = tick_handle_periodic; + else + dev->event_handler = tick_handle_periodic_broadcast; +} + +#ifdef CONFIG_HOTPLUG_CPU +/* + * Remove a CPU from broadcasting + */ +void tick_shutdown_broadcast(unsigned int cpu) +{ + struct clock_event_device *bc; + unsigned long flags; + + raw_spin_lock_irqsave(&tick_broadcast_lock, flags); + + bc = tick_broadcast_device.evtdev; + cpumask_clear_cpu(cpu, tick_broadcast_mask); + cpumask_clear_cpu(cpu, tick_broadcast_on); + + if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC) { + if (bc && cpumask_empty(tick_broadcast_mask)) + clockevents_shutdown(bc); + } + + raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags); +} +#endif + +void tick_suspend_broadcast(void) +{ + struct clock_event_device *bc; + unsigned long flags; + + raw_spin_lock_irqsave(&tick_broadcast_lock, flags); + + bc = tick_broadcast_device.evtdev; + if (bc) + clockevents_shutdown(bc); + + raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags); +} + +/* + * This is called from tick_resume_local() on a resuming CPU. That's + * called from the core resume function, tick_unfreeze() and the magic XEN + * resume hackery. + * + * In none of these cases the broadcast device mode can change and the + * bit of the resuming CPU in the broadcast mask is safe as well. + */ +bool tick_resume_check_broadcast(void) +{ + if (tick_broadcast_device.mode == TICKDEV_MODE_ONESHOT) + return false; + else + return cpumask_test_cpu(smp_processor_id(), tick_broadcast_mask); +} + +void tick_resume_broadcast(void) +{ + struct clock_event_device *bc; + unsigned long flags; + + raw_spin_lock_irqsave(&tick_broadcast_lock, flags); + + bc = tick_broadcast_device.evtdev; + + if (bc) { + clockevents_tick_resume(bc); + + switch (tick_broadcast_device.mode) { + case TICKDEV_MODE_PERIODIC: + if (!cpumask_empty(tick_broadcast_mask)) + tick_broadcast_start_periodic(bc); + break; + case TICKDEV_MODE_ONESHOT: + if (!cpumask_empty(tick_broadcast_mask)) + tick_resume_broadcast_oneshot(bc); + break; + } + } + raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags); +} + +#ifdef CONFIG_TICK_ONESHOT + +static cpumask_var_t tick_broadcast_oneshot_mask; +static cpumask_var_t tick_broadcast_pending_mask; +static cpumask_var_t tick_broadcast_force_mask; + +/* + * Exposed for debugging: see timer_list.c + */ +struct cpumask *tick_get_broadcast_oneshot_mask(void) +{ + return tick_broadcast_oneshot_mask; +} + +/* + * Called before going idle with interrupts disabled. Checks whether a + * broadcast event from the other core is about to happen. We detected + * that in tick_broadcast_oneshot_control(). The callsite can use this + * to avoid a deep idle transition as we are about to get the + * broadcast IPI right away. + */ +int tick_check_broadcast_expired(void) +{ + return cpumask_test_cpu(smp_processor_id(), tick_broadcast_force_mask); +} + +/* + * Set broadcast interrupt affinity + */ +static void tick_broadcast_set_affinity(struct clock_event_device *bc, + const struct cpumask *cpumask) +{ + if (!(bc->features & CLOCK_EVT_FEAT_DYNIRQ)) + return; + + if (cpumask_equal(bc->cpumask, cpumask)) + return; + + bc->cpumask = cpumask; + irq_set_affinity(bc->irq, bc->cpumask); +} + +static int tick_broadcast_set_event(struct clock_event_device *bc, int cpu, + ktime_t expires, int force) +{ + int ret; + + if (bc->state != CLOCK_EVT_STATE_ONESHOT) + clockevents_set_state(bc, CLOCK_EVT_STATE_ONESHOT); + + ret = clockevents_program_event(bc, expires, force); + if (!ret) + tick_broadcast_set_affinity(bc, cpumask_of(cpu)); + return ret; +} + +static void tick_resume_broadcast_oneshot(struct clock_event_device *bc) +{ + clockevents_set_state(bc, CLOCK_EVT_STATE_ONESHOT); +} + +/* + * Called from irq_enter() when idle was interrupted to reenable the + * per cpu device. + */ +void tick_check_oneshot_broadcast_this_cpu(void) +{ + if (cpumask_test_cpu(smp_processor_id(), tick_broadcast_oneshot_mask)) { + struct tick_device *td = this_cpu_ptr(&tick_cpu_device); + + /* + * We might be in the middle of switching over from + * periodic to oneshot. If the CPU has not yet + * switched over, leave the device alone. + */ + if (td->mode == TICKDEV_MODE_ONESHOT) { + clockevents_set_state(td->evtdev, + CLOCK_EVT_STATE_ONESHOT); + } + } +} + +/* + * Handle oneshot mode broadcasting + */ +static void tick_handle_oneshot_broadcast(struct clock_event_device *dev) +{ + struct tick_device *td; + ktime_t now, next_event; + int cpu, next_cpu = 0; + + raw_spin_lock(&tick_broadcast_lock); +again: + dev->next_event.tv64 = KTIME_MAX; + next_event.tv64 = KTIME_MAX; + cpumask_clear(tmpmask); + now = ktime_get(); + /* Find all expired events */ + for_each_cpu(cpu, tick_broadcast_oneshot_mask) { + td = &per_cpu(tick_cpu_device, cpu); + if (td->evtdev->next_event.tv64 <= now.tv64) { + cpumask_set_cpu(cpu, tmpmask); + /* + * Mark the remote cpu in the pending mask, so + * it can avoid reprogramming the cpu local + * timer in tick_broadcast_oneshot_control(). + */ + cpumask_set_cpu(cpu, tick_broadcast_pending_mask); + } else if (td->evtdev->next_event.tv64 < next_event.tv64) { + next_event.tv64 = td->evtdev->next_event.tv64; + next_cpu = cpu; + } + } + + /* + * Remove the current cpu from the pending mask. The event is + * delivered immediately in tick_do_broadcast() ! + */ + cpumask_clear_cpu(smp_processor_id(), tick_broadcast_pending_mask); + + /* Take care of enforced broadcast requests */ + cpumask_or(tmpmask, tmpmask, tick_broadcast_force_mask); + cpumask_clear(tick_broadcast_force_mask); + + /* + * Sanity check. Catch the case where we try to broadcast to + * offline cpus. + */ + if (WARN_ON_ONCE(!cpumask_subset(tmpmask, cpu_online_mask))) + cpumask_and(tmpmask, tmpmask, cpu_online_mask); + + /* + * Wakeup the cpus which have an expired event. + */ + tick_do_broadcast(tmpmask); + + /* + * Two reasons for reprogram: + * + * - The global event did not expire any CPU local + * events. This happens in dyntick mode, as the maximum PIT + * delta is quite small. + * + * - There are pending events on sleeping CPUs which were not + * in the event mask + */ + if (next_event.tv64 != KTIME_MAX) { + /* + * Rearm the broadcast device. If event expired, + * repeat the above + */ + if (tick_broadcast_set_event(dev, next_cpu, next_event, 0)) + goto again; + } + raw_spin_unlock(&tick_broadcast_lock); +} + +static int broadcast_needs_cpu(struct clock_event_device *bc, int cpu) +{ + if (!(bc->features & CLOCK_EVT_FEAT_HRTIMER)) + return 0; + if (bc->next_event.tv64 == KTIME_MAX) + return 0; + return bc->bound_on == cpu ? -EBUSY : 0; +} + +static void broadcast_shutdown_local(struct clock_event_device *bc, + struct clock_event_device *dev) +{ + /* + * For hrtimer based broadcasting we cannot shutdown the cpu + * local device if our own event is the first one to expire or + * if we own the broadcast timer. + */ + if (bc->features & CLOCK_EVT_FEAT_HRTIMER) { + if (broadcast_needs_cpu(bc, smp_processor_id())) + return; + if (dev->next_event.tv64 < bc->next_event.tv64) + return; + } + clockevents_set_state(dev, CLOCK_EVT_STATE_SHUTDOWN); +} + +/** + * tick_broadcast_oneshot_control - Enter/exit broadcast oneshot mode + * @state: The target state (enter/exit) + * + * The system enters/leaves a state, where affected devices might stop + * Returns 0 on success, -EBUSY if the cpu is used to broadcast wakeups. + * + * Called with interrupts disabled, so clockevents_lock is not + * required here because the local clock event device cannot go away + * under us. + */ +int tick_broadcast_oneshot_control(enum tick_broadcast_state state) +{ + struct clock_event_device *bc, *dev; + struct tick_device *td; + int cpu, ret = 0; + ktime_t now; + + /* + * Periodic mode does not care about the enter/exit of power + * states + */ + if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC) + return 0; + + /* + * We are called with preemtion disabled from the depth of the + * idle code, so we can't be moved away. + */ + td = this_cpu_ptr(&tick_cpu_device); + dev = td->evtdev; + + if (!(dev->features & CLOCK_EVT_FEAT_C3STOP)) + return 0; + + raw_spin_lock(&tick_broadcast_lock); + bc = tick_broadcast_device.evtdev; + cpu = smp_processor_id(); + + if (state == TICK_BROADCAST_ENTER) { + if (!cpumask_test_and_set_cpu(cpu, tick_broadcast_oneshot_mask)) { + WARN_ON_ONCE(cpumask_test_cpu(cpu, tick_broadcast_pending_mask)); + broadcast_shutdown_local(bc, dev); + /* + * We only reprogram the broadcast timer if we + * did not mark ourself in the force mask and + * if the cpu local event is earlier than the + * broadcast event. If the current CPU is in + * the force mask, then we are going to be + * woken by the IPI right away. + */ + if (!cpumask_test_cpu(cpu, tick_broadcast_force_mask) && + dev->next_event.tv64 < bc->next_event.tv64) + tick_broadcast_set_event(bc, cpu, dev->next_event, 1); + } + /* + * If the current CPU owns the hrtimer broadcast + * mechanism, it cannot go deep idle and we remove the + * CPU from the broadcast mask. We don't have to go + * through the EXIT path as the local timer is not + * shutdown. + */ + ret = broadcast_needs_cpu(bc, cpu); + if (ret) + cpumask_clear_cpu(cpu, tick_broadcast_oneshot_mask); + } else { + if (cpumask_test_and_clear_cpu(cpu, tick_broadcast_oneshot_mask)) { + clockevents_set_state(dev, CLOCK_EVT_STATE_ONESHOT); + /* + * The cpu which was handling the broadcast + * timer marked this cpu in the broadcast + * pending mask and fired the broadcast + * IPI. So we are going to handle the expired + * event anyway via the broadcast IPI + * handler. No need to reprogram the timer + * with an already expired event. + */ + if (cpumask_test_and_clear_cpu(cpu, + tick_broadcast_pending_mask)) + goto out; + + /* + * Bail out if there is no next event. + */ + if (dev->next_event.tv64 == KTIME_MAX) + goto out; + /* + * If the pending bit is not set, then we are + * either the CPU handling the broadcast + * interrupt or we got woken by something else. + * + * We are not longer in the broadcast mask, so + * if the cpu local expiry time is already + * reached, we would reprogram the cpu local + * timer with an already expired event. + * + * This can lead to a ping-pong when we return + * to idle and therefor rearm the broadcast + * timer before the cpu local timer was able + * to fire. This happens because the forced + * reprogramming makes sure that the event + * will happen in the future and depending on + * the min_delta setting this might be far + * enough out that the ping-pong starts. + * + * If the cpu local next_event has expired + * then we know that the broadcast timer + * next_event has expired as well and + * broadcast is about to be handled. So we + * avoid reprogramming and enforce that the + * broadcast handler, which did not run yet, + * will invoke the cpu local handler. + * + * We cannot call the handler directly from + * here, because we might be in a NOHZ phase + * and we did not go through the irq_enter() + * nohz fixups. + */ + now = ktime_get(); + if (dev->next_event.tv64 <= now.tv64) { + cpumask_set_cpu(cpu, tick_broadcast_force_mask); + goto out; + } + /* + * We got woken by something else. Reprogram + * the cpu local timer device. + */ + tick_program_event(dev->next_event, 1); + } + } +out: + raw_spin_unlock(&tick_broadcast_lock); + return ret; +} +EXPORT_SYMBOL_GPL(tick_broadcast_oneshot_control); + +/* + * Reset the one shot broadcast for a cpu + * + * Called with tick_broadcast_lock held + */ +static void tick_broadcast_clear_oneshot(int cpu) +{ + cpumask_clear_cpu(cpu, tick_broadcast_oneshot_mask); + cpumask_clear_cpu(cpu, tick_broadcast_pending_mask); +} + +static void tick_broadcast_init_next_event(struct cpumask *mask, + ktime_t expires) +{ + struct tick_device *td; + int cpu; + + for_each_cpu(cpu, mask) { + td = &per_cpu(tick_cpu_device, cpu); + if (td->evtdev) + td->evtdev->next_event = expires; + } +} + +/** + * tick_broadcast_setup_oneshot - setup the broadcast device + */ +void tick_broadcast_setup_oneshot(struct clock_event_device *bc) +{ + int cpu = smp_processor_id(); + + /* Set it up only once ! */ + if (bc->event_handler != tick_handle_oneshot_broadcast) { + int was_periodic = bc->state == CLOCK_EVT_STATE_PERIODIC; + + bc->event_handler = tick_handle_oneshot_broadcast; + + /* + * We must be careful here. There might be other CPUs + * waiting for periodic broadcast. We need to set the + * oneshot_mask bits for those and program the + * broadcast device to fire. + */ + cpumask_copy(tmpmask, tick_broadcast_mask); + cpumask_clear_cpu(cpu, tmpmask); + cpumask_or(tick_broadcast_oneshot_mask, + tick_broadcast_oneshot_mask, tmpmask); + + if (was_periodic && !cpumask_empty(tmpmask)) { + clockevents_set_state(bc, CLOCK_EVT_STATE_ONESHOT); + tick_broadcast_init_next_event(tmpmask, + tick_next_period); + tick_broadcast_set_event(bc, cpu, tick_next_period, 1); + } else + bc->next_event.tv64 = KTIME_MAX; + } else { + /* + * The first cpu which switches to oneshot mode sets + * the bit for all other cpus which are in the general + * (periodic) broadcast mask. So the bit is set and + * would prevent the first broadcast enter after this + * to program the bc device. + */ + tick_broadcast_clear_oneshot(cpu); + } +} + +/* + * Select oneshot operating mode for the broadcast device + */ +void tick_broadcast_switch_to_oneshot(void) +{ + struct clock_event_device *bc; + unsigned long flags; + + raw_spin_lock_irqsave(&tick_broadcast_lock, flags); + + tick_broadcast_device.mode = TICKDEV_MODE_ONESHOT; + bc = tick_broadcast_device.evtdev; + if (bc) + tick_broadcast_setup_oneshot(bc); + + raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags); +} + +#ifdef CONFIG_HOTPLUG_CPU +void hotplug_cpu__broadcast_tick_pull(int deadcpu) +{ + struct clock_event_device *bc; + unsigned long flags; + + raw_spin_lock_irqsave(&tick_broadcast_lock, flags); + bc = tick_broadcast_device.evtdev; + + if (bc && broadcast_needs_cpu(bc, deadcpu)) { + /* This moves the broadcast assignment to this CPU: */ + clockevents_program_event(bc, bc->next_event, 1); + } + raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags); +} + +/* + * Remove a dead CPU from broadcasting + */ +void tick_shutdown_broadcast_oneshot(unsigned int cpu) +{ + unsigned long flags; + + raw_spin_lock_irqsave(&tick_broadcast_lock, flags); + + /* + * Clear the broadcast masks for the dead cpu, but do not stop + * the broadcast device! + */ + cpumask_clear_cpu(cpu, tick_broadcast_oneshot_mask); + cpumask_clear_cpu(cpu, tick_broadcast_pending_mask); + cpumask_clear_cpu(cpu, tick_broadcast_force_mask); + + raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags); +} +#endif + +/* + * Check, whether the broadcast device is in one shot mode + */ +int tick_broadcast_oneshot_active(void) +{ + return tick_broadcast_device.mode == TICKDEV_MODE_ONESHOT; +} + +/* + * Check whether the broadcast device supports oneshot. + */ +bool tick_broadcast_oneshot_available(void) +{ + struct clock_event_device *bc = tick_broadcast_device.evtdev; + + return bc ? bc->features & CLOCK_EVT_FEAT_ONESHOT : false; +} + +#endif + +void __init tick_broadcast_init(void) +{ + zalloc_cpumask_var(&tick_broadcast_mask, GFP_NOWAIT); + zalloc_cpumask_var(&tick_broadcast_on, GFP_NOWAIT); + zalloc_cpumask_var(&tmpmask, GFP_NOWAIT); +#ifdef CONFIG_TICK_ONESHOT + zalloc_cpumask_var(&tick_broadcast_oneshot_mask, GFP_NOWAIT); + zalloc_cpumask_var(&tick_broadcast_pending_mask, GFP_NOWAIT); + zalloc_cpumask_var(&tick_broadcast_force_mask, GFP_NOWAIT); +#endif +} diff --git a/kernel/kernel/time/tick-common.c b/kernel/kernel/time/tick-common.c new file mode 100644 index 000000000..14a10917c --- /dev/null +++ b/kernel/kernel/time/tick-common.c @@ -0,0 +1,500 @@ +/* + * linux/kernel/time/tick-common.c + * + * This file contains the base functions to manage periodic tick + * related events. + * + * Copyright(C) 2005-2006, Thomas Gleixner + * Copyright(C) 2005-2007, Red Hat, Inc., Ingo Molnar + * Copyright(C) 2006-2007, Timesys Corp., Thomas Gleixner + * + * This code is licenced under the GPL version 2. For details see + * kernel-base/COPYING. + */ +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +#include "tick-internal.h" + +/* + * Tick devices + */ +DEFINE_PER_CPU(struct tick_device, tick_cpu_device); +/* + * Tick next event: keeps track of the tick time + */ +ktime_t tick_next_period; +ktime_t tick_period; + +/* + * tick_do_timer_cpu is a timer core internal variable which holds the CPU NR + * which is responsible for calling do_timer(), i.e. the timekeeping stuff. This + * variable has two functions: + * + * 1) Prevent a thundering herd issue of a gazillion of CPUs trying to grab the + * timekeeping lock all at once. Only the CPU which is assigned to do the + * update is handling it. + * + * 2) Hand off the duty in the NOHZ idle case by setting the value to + * TICK_DO_TIMER_NONE, i.e. a non existing CPU. So the next cpu which looks + * at it will take over and keep the time keeping alive. The handover + * procedure also covers cpu hotplug. + */ +int tick_do_timer_cpu __read_mostly = TICK_DO_TIMER_BOOT; + +/* + * Debugging: see timer_list.c + */ +struct tick_device *tick_get_device(int cpu) +{ + return &per_cpu(tick_cpu_device, cpu); +} + +/** + * tick_is_oneshot_available - check for a oneshot capable event device + */ +int tick_is_oneshot_available(void) +{ + struct clock_event_device *dev = __this_cpu_read(tick_cpu_device.evtdev); + + if (!dev || !(dev->features & CLOCK_EVT_FEAT_ONESHOT)) + return 0; + if (!(dev->features & CLOCK_EVT_FEAT_C3STOP)) + return 1; + return tick_broadcast_oneshot_available(); +} + +/* + * Periodic tick + */ +static void tick_periodic(int cpu) +{ + if (tick_do_timer_cpu == cpu) { + raw_spin_lock(&jiffies_lock); + write_seqcount_begin(&jiffies_seq); + + /* Keep track of the next tick event */ + tick_next_period = ktime_add(tick_next_period, tick_period); + + do_timer(1); + write_seqcount_end(&jiffies_seq); + raw_spin_unlock(&jiffies_lock); + update_wall_time(); + } + + update_process_times(user_mode(get_irq_regs())); + profile_tick(CPU_PROFILING); +} + +/* + * Event handler for periodic ticks + */ +void tick_handle_periodic(struct clock_event_device *dev) +{ + int cpu = smp_processor_id(); + ktime_t next = dev->next_event; + + tick_periodic(cpu); + + if (dev->state != CLOCK_EVT_STATE_ONESHOT) + return; + for (;;) { + /* + * Setup the next period for devices, which do not have + * periodic mode: + */ + next = ktime_add(next, tick_period); + + if (!clockevents_program_event(dev, next, false)) + return; + /* + * Have to be careful here. If we're in oneshot mode, + * before we call tick_periodic() in a loop, we need + * to be sure we're using a real hardware clocksource. + * Otherwise we could get trapped in an infinite + * loop, as the tick_periodic() increments jiffies, + * which then will increment time, possibly causing + * the loop to trigger again and again. + */ + if (timekeeping_valid_for_hres()) + tick_periodic(cpu); + } +} + +/* + * Setup the device for a periodic tick + */ +void tick_setup_periodic(struct clock_event_device *dev, int broadcast) +{ + tick_set_periodic_handler(dev, broadcast); + + /* Broadcast setup ? */ + if (!tick_device_is_functional(dev)) + return; + + if ((dev->features & CLOCK_EVT_FEAT_PERIODIC) && + !tick_broadcast_oneshot_active()) { + clockevents_set_state(dev, CLOCK_EVT_STATE_PERIODIC); + } else { + unsigned long seq; + ktime_t next; + + do { + seq = read_seqcount_begin(&jiffies_seq); + next = tick_next_period; + } while (read_seqcount_retry(&jiffies_seq, seq)); + + clockevents_set_state(dev, CLOCK_EVT_STATE_ONESHOT); + + for (;;) { + if (!clockevents_program_event(dev, next, false)) + return; + next = ktime_add(next, tick_period); + } + } +} + +/* + * Setup the tick device + */ +static void tick_setup_device(struct tick_device *td, + struct clock_event_device *newdev, int cpu, + const struct cpumask *cpumask) +{ + ktime_t next_event; + void (*handler)(struct clock_event_device *) = NULL; + + /* + * First device setup ? + */ + if (!td->evtdev) { + /* + * If no cpu took the do_timer update, assign it to + * this cpu: + */ + if (tick_do_timer_cpu == TICK_DO_TIMER_BOOT) { + if (!tick_nohz_full_cpu(cpu)) + tick_do_timer_cpu = cpu; + else + tick_do_timer_cpu = TICK_DO_TIMER_NONE; + tick_next_period = ktime_get(); + tick_period = ktime_set(0, NSEC_PER_SEC / HZ); + } + + /* + * Startup in periodic mode first. + */ + td->mode = TICKDEV_MODE_PERIODIC; + } else { + handler = td->evtdev->event_handler; + next_event = td->evtdev->next_event; + td->evtdev->event_handler = clockevents_handle_noop; + } + + td->evtdev = newdev; + + /* + * When the device is not per cpu, pin the interrupt to the + * current cpu: + */ + if (!cpumask_equal(newdev->cpumask, cpumask)) + irq_set_affinity(newdev->irq, cpumask); + + /* + * When global broadcasting is active, check if the current + * device is registered as a placeholder for broadcast mode. + * This allows us to handle this x86 misfeature in a generic + * way. This function also returns !=0 when we keep the + * current active broadcast state for this CPU. + */ + if (tick_device_uses_broadcast(newdev, cpu)) + return; + + if (td->mode == TICKDEV_MODE_PERIODIC) + tick_setup_periodic(newdev, 0); + else + tick_setup_oneshot(newdev, handler, next_event); +} + +void tick_install_replacement(struct clock_event_device *newdev) +{ + struct tick_device *td = this_cpu_ptr(&tick_cpu_device); + int cpu = smp_processor_id(); + + clockevents_exchange_device(td->evtdev, newdev); + tick_setup_device(td, newdev, cpu, cpumask_of(cpu)); + if (newdev->features & CLOCK_EVT_FEAT_ONESHOT) + tick_oneshot_notify(); +} + +static bool tick_check_percpu(struct clock_event_device *curdev, + struct clock_event_device *newdev, int cpu) +{ + if (!cpumask_test_cpu(cpu, newdev->cpumask)) + return false; + if (cpumask_equal(newdev->cpumask, cpumask_of(cpu))) + return true; + /* Check if irq affinity can be set */ + if (newdev->irq >= 0 && !irq_can_set_affinity(newdev->irq)) + return false; + /* Prefer an existing cpu local device */ + if (curdev && cpumask_equal(curdev->cpumask, cpumask_of(cpu))) + return false; + return true; +} + +static bool tick_check_preferred(struct clock_event_device *curdev, + struct clock_event_device *newdev) +{ + /* Prefer oneshot capable device */ + if (!(newdev->features & CLOCK_EVT_FEAT_ONESHOT)) { + if (curdev && (curdev->features & CLOCK_EVT_FEAT_ONESHOT)) + return false; + if (tick_oneshot_mode_active()) + return false; + } + + /* + * Use the higher rated one, but prefer a CPU local device with a lower + * rating than a non-CPU local device + */ + return !curdev || + newdev->rating > curdev->rating || + !cpumask_equal(curdev->cpumask, newdev->cpumask); +} + +/* + * Check whether the new device is a better fit than curdev. curdev + * can be NULL ! + */ +bool tick_check_replacement(struct clock_event_device *curdev, + struct clock_event_device *newdev) +{ + if (!tick_check_percpu(curdev, newdev, smp_processor_id())) + return false; + + return tick_check_preferred(curdev, newdev); +} + +/* + * Check, if the new registered device should be used. Called with + * clockevents_lock held and interrupts disabled. + */ +void tick_check_new_device(struct clock_event_device *newdev) +{ + struct clock_event_device *curdev; + struct tick_device *td; + int cpu; + + cpu = smp_processor_id(); + if (!cpumask_test_cpu(cpu, newdev->cpumask)) + goto out_bc; + + td = &per_cpu(tick_cpu_device, cpu); + curdev = td->evtdev; + + /* cpu local device ? */ + if (!tick_check_percpu(curdev, newdev, cpu)) + goto out_bc; + + /* Preference decision */ + if (!tick_check_preferred(curdev, newdev)) + goto out_bc; + + if (!try_module_get(newdev->owner)) + return; + + /* + * Replace the eventually existing device by the new + * device. If the current device is the broadcast device, do + * not give it back to the clockevents layer ! + */ + if (tick_is_broadcast_device(curdev)) { + clockevents_shutdown(curdev); + curdev = NULL; + } + clockevents_exchange_device(curdev, newdev); + tick_setup_device(td, newdev, cpu, cpumask_of(cpu)); + if (newdev->features & CLOCK_EVT_FEAT_ONESHOT) + tick_oneshot_notify(); + return; + +out_bc: + /* + * Can the new device be used as a broadcast device ? + */ + tick_install_broadcast_device(newdev); +} + +#ifdef CONFIG_HOTPLUG_CPU +/* + * Transfer the do_timer job away from a dying cpu. + * + * Called with interrupts disabled. Not locking required. If + * tick_do_timer_cpu is owned by this cpu, nothing can change it. + */ +void tick_handover_do_timer(void) +{ + if (tick_do_timer_cpu == smp_processor_id()) { + int cpu = cpumask_first(cpu_online_mask); + + tick_do_timer_cpu = (cpu < nr_cpu_ids) ? cpu : + TICK_DO_TIMER_NONE; + } +} + +/* + * Shutdown an event device on a given cpu: + * + * This is called on a life CPU, when a CPU is dead. So we cannot + * access the hardware device itself. + * We just set the mode and remove it from the lists. + */ +void tick_shutdown(unsigned int cpu) +{ + struct tick_device *td = &per_cpu(tick_cpu_device, cpu); + struct clock_event_device *dev = td->evtdev; + + td->mode = TICKDEV_MODE_PERIODIC; + if (dev) { + /* + * Prevent that the clock events layer tries to call + * the set mode function! + */ + dev->state = CLOCK_EVT_STATE_DETACHED; + dev->mode = CLOCK_EVT_MODE_UNUSED; + clockevents_exchange_device(dev, NULL); + dev->event_handler = clockevents_handle_noop; + td->evtdev = NULL; + } +} +#endif + +/** + * tick_suspend_local - Suspend the local tick device + * + * Called from the local cpu for freeze with interrupts disabled. + * + * No locks required. Nothing can change the per cpu device. + */ +void tick_suspend_local(void) +{ + struct tick_device *td = this_cpu_ptr(&tick_cpu_device); + + clockevents_shutdown(td->evtdev); +} + +/** + * tick_resume_local - Resume the local tick device + * + * Called from the local CPU for unfreeze or XEN resume magic. + * + * No locks required. Nothing can change the per cpu device. + */ +void tick_resume_local(void) +{ + struct tick_device *td = this_cpu_ptr(&tick_cpu_device); + bool broadcast = tick_resume_check_broadcast(); + + clockevents_tick_resume(td->evtdev); + if (!broadcast) { + if (td->mode == TICKDEV_MODE_PERIODIC) + tick_setup_periodic(td->evtdev, 0); + else + tick_resume_oneshot(); + } +} + +/** + * tick_suspend - Suspend the tick and the broadcast device + * + * Called from syscore_suspend() via timekeeping_suspend with only one + * CPU online and interrupts disabled or from tick_unfreeze() under + * tick_freeze_lock. + * + * No locks required. Nothing can change the per cpu device. + */ +void tick_suspend(void) +{ + tick_suspend_local(); + tick_suspend_broadcast(); +} + +/** + * tick_resume - Resume the tick and the broadcast device + * + * Called from syscore_resume() via timekeeping_resume with only one + * CPU online and interrupts disabled. + * + * No locks required. Nothing can change the per cpu device. + */ +void tick_resume(void) +{ + tick_resume_broadcast(); + tick_resume_local(); +} + +static DEFINE_RAW_SPINLOCK(tick_freeze_lock); +static unsigned int tick_freeze_depth; + +/** + * tick_freeze - Suspend the local tick and (possibly) timekeeping. + * + * Check if this is the last online CPU executing the function and if so, + * suspend timekeeping. Otherwise suspend the local tick. + * + * Call with interrupts disabled. Must be balanced with %tick_unfreeze(). + * Interrupts must not be enabled before the subsequent %tick_unfreeze(). + */ +void tick_freeze(void) +{ + raw_spin_lock(&tick_freeze_lock); + + tick_freeze_depth++; + if (tick_freeze_depth == num_online_cpus()) + timekeeping_suspend(); + else + tick_suspend_local(); + + raw_spin_unlock(&tick_freeze_lock); +} + +/** + * tick_unfreeze - Resume the local tick and (possibly) timekeeping. + * + * Check if this is the first CPU executing the function and if so, resume + * timekeeping. Otherwise resume the local tick. + * + * Call with interrupts disabled. Must be balanced with %tick_freeze(). + * Interrupts must not be enabled after the preceding %tick_freeze(). + */ +void tick_unfreeze(void) +{ + raw_spin_lock(&tick_freeze_lock); + + if (tick_freeze_depth == num_online_cpus()) + timekeeping_resume(); + else + tick_resume_local(); + + tick_freeze_depth--; + + raw_spin_unlock(&tick_freeze_lock); +} + +/** + * tick_init - initialize the tick control + */ +void __init tick_init(void) +{ + tick_broadcast_init(); + tick_nohz_init(); +} diff --git a/kernel/kernel/time/tick-internal.h b/kernel/kernel/time/tick-internal.h new file mode 100644 index 000000000..b64fdd805 --- /dev/null +++ b/kernel/kernel/time/tick-internal.h @@ -0,0 +1,139 @@ +/* + * tick internal variable and functions used by low/high res code + */ +#include +#include + +#include "timekeeping.h" +#include "tick-sched.h" + +#ifdef CONFIG_GENERIC_CLOCKEVENTS + +# define TICK_DO_TIMER_NONE -1 +# define TICK_DO_TIMER_BOOT -2 + +DECLARE_PER_CPU(struct tick_device, tick_cpu_device); +extern ktime_t tick_next_period; +extern ktime_t tick_period; +extern int tick_do_timer_cpu __read_mostly; + +extern void tick_setup_periodic(struct clock_event_device *dev, int broadcast); +extern void tick_handle_periodic(struct clock_event_device *dev); +extern void tick_check_new_device(struct clock_event_device *dev); +extern void tick_shutdown(unsigned int cpu); +extern void tick_suspend(void); +extern void tick_resume(void); +extern bool tick_check_replacement(struct clock_event_device *curdev, + struct clock_event_device *newdev); +extern void tick_install_replacement(struct clock_event_device *dev); +extern int tick_is_oneshot_available(void); +extern struct tick_device *tick_get_device(int cpu); + +extern int clockevents_tick_resume(struct clock_event_device *dev); +/* Check, if the device is functional or a dummy for broadcast */ +static inline int tick_device_is_functional(struct clock_event_device *dev) +{ + return !(dev->features & CLOCK_EVT_FEAT_DUMMY); +} + +extern void clockevents_shutdown(struct clock_event_device *dev); +extern void clockevents_exchange_device(struct clock_event_device *old, + struct clock_event_device *new); +extern void clockevents_set_state(struct clock_event_device *dev, + enum clock_event_state state); +extern int clockevents_program_event(struct clock_event_device *dev, + ktime_t expires, bool force); +extern void clockevents_handle_noop(struct clock_event_device *dev); +extern int __clockevents_update_freq(struct clock_event_device *dev, u32 freq); +extern ssize_t sysfs_get_uname(const char *buf, char *dst, size_t cnt); + +/* Broadcasting support */ +# ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST +extern int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu); +extern void tick_install_broadcast_device(struct clock_event_device *dev); +extern int tick_is_broadcast_device(struct clock_event_device *dev); +extern void tick_shutdown_broadcast(unsigned int cpu); +extern void tick_suspend_broadcast(void); +extern void tick_resume_broadcast(void); +extern bool tick_resume_check_broadcast(void); +extern void tick_broadcast_init(void); +extern void tick_set_periodic_handler(struct clock_event_device *dev, int broadcast); +extern int tick_broadcast_update_freq(struct clock_event_device *dev, u32 freq); +extern struct tick_device *tick_get_broadcast_device(void); +extern struct cpumask *tick_get_broadcast_mask(void); +# else /* !CONFIG_GENERIC_CLOCKEVENTS_BROADCAST: */ +static inline void tick_install_broadcast_device(struct clock_event_device *dev) { } +static inline int tick_is_broadcast_device(struct clock_event_device *dev) { return 0; } +static inline int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu) { return 0; } +static inline void tick_do_periodic_broadcast(struct clock_event_device *d) { } +static inline void tick_shutdown_broadcast(unsigned int cpu) { } +static inline void tick_suspend_broadcast(void) { } +static inline void tick_resume_broadcast(void) { } +static inline bool tick_resume_check_broadcast(void) { return false; } +static inline void tick_broadcast_init(void) { } +static inline int tick_broadcast_update_freq(struct clock_event_device *dev, u32 freq) { return -ENODEV; } + +/* Set the periodic handler in non broadcast mode */ +static inline void tick_set_periodic_handler(struct clock_event_device *dev, int broadcast) +{ + dev->event_handler = tick_handle_periodic; +} +# endif /* !CONFIG_GENERIC_CLOCKEVENTS_BROADCAST */ + +#else /* !GENERIC_CLOCKEVENTS: */ +static inline void tick_suspend(void) { } +static inline void tick_resume(void) { } +#endif /* !GENERIC_CLOCKEVENTS */ + +/* Oneshot related functions */ +#ifdef CONFIG_TICK_ONESHOT +extern void tick_setup_oneshot(struct clock_event_device *newdev, + void (*handler)(struct clock_event_device *), + ktime_t nextevt); +extern int tick_program_event(ktime_t expires, int force); +extern void tick_oneshot_notify(void); +extern int tick_switch_to_oneshot(void (*handler)(struct clock_event_device *)); +extern void tick_resume_oneshot(void); +static inline bool tick_oneshot_possible(void) { return true; } +extern int tick_oneshot_mode_active(void); +extern void tick_clock_notify(void); +extern int tick_check_oneshot_change(int allow_nohz); +extern int tick_init_highres(void); +#else /* !CONFIG_TICK_ONESHOT: */ +static inline +void tick_setup_oneshot(struct clock_event_device *newdev, + void (*handler)(struct clock_event_device *), + ktime_t nextevt) { BUG(); } +static inline void tick_resume_oneshot(void) { BUG(); } +static inline int tick_program_event(ktime_t expires, int force) { return 0; } +static inline void tick_oneshot_notify(void) { } +static inline bool tick_oneshot_possible(void) { return false; } +static inline int tick_oneshot_mode_active(void) { return 0; } +static inline void tick_clock_notify(void) { } +static inline int tick_check_oneshot_change(int allow_nohz) { return 0; } +#endif /* !CONFIG_TICK_ONESHOT */ + +/* Functions related to oneshot broadcasting */ +#if defined(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST) && defined(CONFIG_TICK_ONESHOT) +extern void tick_broadcast_setup_oneshot(struct clock_event_device *bc); +extern void tick_broadcast_switch_to_oneshot(void); +extern void tick_shutdown_broadcast_oneshot(unsigned int cpu); +extern int tick_broadcast_oneshot_active(void); +extern void tick_check_oneshot_broadcast_this_cpu(void); +bool tick_broadcast_oneshot_available(void); +extern struct cpumask *tick_get_broadcast_oneshot_mask(void); +#else /* !(BROADCAST && ONESHOT): */ +static inline void tick_broadcast_setup_oneshot(struct clock_event_device *bc) { BUG(); } +static inline void tick_broadcast_switch_to_oneshot(void) { } +static inline void tick_shutdown_broadcast_oneshot(unsigned int cpu) { } +static inline int tick_broadcast_oneshot_active(void) { return 0; } +static inline void tick_check_oneshot_broadcast_this_cpu(void) { } +static inline bool tick_broadcast_oneshot_available(void) { return tick_oneshot_possible(); } +#endif /* !(BROADCAST && ONESHOT) */ + +/* NO_HZ_FULL internal */ +#ifdef CONFIG_NO_HZ_FULL +extern void tick_nohz_init(void); +# else +static inline void tick_nohz_init(void) { } +#endif diff --git a/kernel/kernel/time/tick-oneshot.c b/kernel/kernel/time/tick-oneshot.c new file mode 100644 index 000000000..67a64b167 --- /dev/null +++ b/kernel/kernel/time/tick-oneshot.c @@ -0,0 +1,116 @@ +/* + * linux/kernel/time/tick-oneshot.c + * + * This file contains functions which manage high resolution tick + * related events. + * + * Copyright(C) 2005-2006, Thomas Gleixner + * Copyright(C) 2005-2007, Red Hat, Inc., Ingo Molnar + * Copyright(C) 2006-2007, Timesys Corp., Thomas Gleixner + * + * This code is licenced under the GPL version 2. For details see + * kernel-base/COPYING. + */ +#include +#include +#include +#include +#include +#include +#include + +#include "tick-internal.h" + +/** + * tick_program_event + */ +int tick_program_event(ktime_t expires, int force) +{ + struct clock_event_device *dev = __this_cpu_read(tick_cpu_device.evtdev); + + return clockevents_program_event(dev, expires, force); +} + +/** + * tick_resume_onshot - resume oneshot mode + */ +void tick_resume_oneshot(void) +{ + struct clock_event_device *dev = __this_cpu_read(tick_cpu_device.evtdev); + + clockevents_set_state(dev, CLOCK_EVT_STATE_ONESHOT); + clockevents_program_event(dev, ktime_get(), true); +} + +/** + * tick_setup_oneshot - setup the event device for oneshot mode (hres or nohz) + */ +void tick_setup_oneshot(struct clock_event_device *newdev, + void (*handler)(struct clock_event_device *), + ktime_t next_event) +{ + newdev->event_handler = handler; + clockevents_set_state(newdev, CLOCK_EVT_STATE_ONESHOT); + clockevents_program_event(newdev, next_event, true); +} + +/** + * tick_switch_to_oneshot - switch to oneshot mode + */ +int tick_switch_to_oneshot(void (*handler)(struct clock_event_device *)) +{ + struct tick_device *td = this_cpu_ptr(&tick_cpu_device); + struct clock_event_device *dev = td->evtdev; + + if (!dev || !(dev->features & CLOCK_EVT_FEAT_ONESHOT) || + !tick_device_is_functional(dev)) { + + printk(KERN_INFO "Clockevents: " + "could not switch to one-shot mode:"); + if (!dev) { + printk(" no tick device\n"); + } else { + if (!tick_device_is_functional(dev)) + printk(" %s is not functional.\n", dev->name); + else + printk(" %s does not support one-shot mode.\n", + dev->name); + } + return -EINVAL; + } + + td->mode = TICKDEV_MODE_ONESHOT; + dev->event_handler = handler; + clockevents_set_state(dev, CLOCK_EVT_STATE_ONESHOT); + tick_broadcast_switch_to_oneshot(); + return 0; +} + +/** + * tick_check_oneshot_mode - check whether the system is in oneshot mode + * + * returns 1 when either nohz or highres are enabled. otherwise 0. + */ +int tick_oneshot_mode_active(void) +{ + unsigned long flags; + int ret; + + local_irq_save(flags); + ret = __this_cpu_read(tick_cpu_device.mode) == TICKDEV_MODE_ONESHOT; + local_irq_restore(flags); + + return ret; +} + +#ifdef CONFIG_HIGH_RES_TIMERS +/** + * tick_init_highres - switch to high resolution mode + * + * Called with interrupts disabled. + */ +int tick_init_highres(void) +{ + return tick_switch_to_oneshot(hrtimer_interrupt); +} +#endif diff --git a/kernel/kernel/time/tick-sched.c b/kernel/kernel/time/tick-sched.c new file mode 100644 index 000000000..b3841ba00 --- /dev/null +++ b/kernel/kernel/time/tick-sched.c @@ -0,0 +1,1255 @@ +/* + * linux/kernel/time/tick-sched.c + * + * Copyright(C) 2005-2006, Thomas Gleixner + * Copyright(C) 2005-2007, Red Hat, Inc., Ingo Molnar + * Copyright(C) 2006-2007 Timesys Corp., Thomas Gleixner + * + * No idle tick implementation for low and high resolution timers + * + * Started by: Thomas Gleixner and Ingo Molnar + * + * Distribute under GPLv2. + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +#include "tick-internal.h" + +#include + +/* + * Per cpu nohz control structure + */ +static DEFINE_PER_CPU(struct tick_sched, tick_cpu_sched); + +/* + * The time, when the last jiffy update happened. Protected by jiffies_lock. + */ +static ktime_t last_jiffies_update; + +struct tick_sched *tick_get_tick_sched(int cpu) +{ + return &per_cpu(tick_cpu_sched, cpu); +} + +/* + * Must be called with interrupts disabled ! + */ +static void tick_do_update_jiffies64(ktime_t now) +{ + unsigned long ticks = 0; + ktime_t delta; + + /* + * Do a quick check without holding jiffies_lock: + */ + delta = ktime_sub(now, last_jiffies_update); + if (delta.tv64 < tick_period.tv64) + return; + + /* Reevalute with jiffies_lock held */ + raw_spin_lock(&jiffies_lock); + write_seqcount_begin(&jiffies_seq); + + delta = ktime_sub(now, last_jiffies_update); + if (delta.tv64 >= tick_period.tv64) { + + delta = ktime_sub(delta, tick_period); + last_jiffies_update = ktime_add(last_jiffies_update, + tick_period); + + /* Slow path for long timeouts */ + if (unlikely(delta.tv64 >= tick_period.tv64)) { + s64 incr = ktime_to_ns(tick_period); + + ticks = ktime_divns(delta, incr); + + last_jiffies_update = ktime_add_ns(last_jiffies_update, + incr * ticks); + } + do_timer(++ticks); + + /* Keep the tick_next_period variable up to date */ + tick_next_period = ktime_add(last_jiffies_update, tick_period); + } else { + write_seqcount_end(&jiffies_seq); + raw_spin_unlock(&jiffies_lock); + return; + } + write_seqcount_end(&jiffies_seq); + raw_spin_unlock(&jiffies_lock); + update_wall_time(); +} + +/* + * Initialize and return retrieve the jiffies update. + */ +static ktime_t tick_init_jiffy_update(void) +{ + ktime_t period; + + raw_spin_lock(&jiffies_lock); + write_seqcount_begin(&jiffies_seq); + /* Did we start the jiffies update yet ? */ + if (last_jiffies_update.tv64 == 0) + last_jiffies_update = tick_next_period; + period = last_jiffies_update; + write_seqcount_end(&jiffies_seq); + raw_spin_unlock(&jiffies_lock); + return period; +} + + +static void tick_sched_do_timer(ktime_t now) +{ + int cpu = smp_processor_id(); + +#ifdef CONFIG_NO_HZ_COMMON + /* + * Check if the do_timer duty was dropped. We don't care about + * concurrency: This happens only when the cpu in charge went + * into a long sleep. If two cpus happen to assign themself to + * this duty, then the jiffies update is still serialized by + * jiffies_lock. + */ + if (unlikely(tick_do_timer_cpu == TICK_DO_TIMER_NONE) + && !tick_nohz_full_cpu(cpu)) + tick_do_timer_cpu = cpu; +#endif + + /* Check, if the jiffies need an update */ + if (tick_do_timer_cpu == cpu) + tick_do_update_jiffies64(now); +} + +static void tick_sched_handle(struct tick_sched *ts, struct pt_regs *regs) +{ +#ifdef CONFIG_NO_HZ_COMMON + /* + * When we are idle and the tick is stopped, we have to touch + * the watchdog as we might not schedule for a really long + * time. This happens on complete idle SMP systems while + * waiting on the login prompt. We also increment the "start of + * idle" jiffy stamp so the idle accounting adjustment we do + * when we go busy again does not account too much ticks. + */ + if (ts->tick_stopped) { + touch_softlockup_watchdog(); + if (is_idle_task(current)) + ts->idle_jiffies++; + } +#endif + update_process_times(user_mode(regs)); + profile_tick(CPU_PROFILING); +} + +#ifdef CONFIG_NO_HZ_FULL +cpumask_var_t tick_nohz_full_mask; +cpumask_var_t housekeeping_mask; +bool tick_nohz_full_running; + +static bool can_stop_full_tick(void) +{ + WARN_ON_ONCE(!irqs_disabled()); + + if (!sched_can_stop_tick()) { + trace_tick_stop(0, "more than 1 task in runqueue\n"); + return false; + } + + if (!posix_cpu_timers_can_stop_tick(current)) { + trace_tick_stop(0, "posix timers running\n"); + return false; + } + + if (!perf_event_can_stop_tick()) { + trace_tick_stop(0, "perf events running\n"); + return false; + } + + if (!arch_irq_work_has_interrupt()) { + trace_tick_stop(0, "missing irq work interrupt\n"); + return false; + } + + /* sched_clock_tick() needs us? */ +#ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK + /* + * TODO: kick full dynticks CPUs when + * sched_clock_stable is set. + */ + if (!sched_clock_stable()) { + trace_tick_stop(0, "unstable sched clock\n"); + /* + * Don't allow the user to think they can get + * full NO_HZ with this machine. + */ + WARN_ONCE(tick_nohz_full_running, + "NO_HZ FULL will not work with unstable sched clock"); + return false; + } +#endif + + return true; +} + +static void tick_nohz_restart_sched_tick(struct tick_sched *ts, ktime_t now); + +/* + * Re-evaluate the need for the tick on the current CPU + * and restart it if necessary. + */ +void __tick_nohz_full_check(void) +{ + struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); + + if (tick_nohz_full_cpu(smp_processor_id())) { + if (ts->tick_stopped && !is_idle_task(current)) { + if (!can_stop_full_tick()) + tick_nohz_restart_sched_tick(ts, ktime_get()); + } + } +} + +static void nohz_full_kick_work_func(struct irq_work *work) +{ + __tick_nohz_full_check(); +} + +static DEFINE_PER_CPU(struct irq_work, nohz_full_kick_work) = { + .func = nohz_full_kick_work_func, + .flags = IRQ_WORK_HARD_IRQ, +}; + +/* + * Kick this CPU if it's full dynticks in order to force it to + * re-evaluate its dependency on the tick and restart it if necessary. + * This kick, unlike tick_nohz_full_kick_cpu() and tick_nohz_full_kick_all(), + * is NMI safe. + */ +void tick_nohz_full_kick(void) +{ + if (!tick_nohz_full_cpu(smp_processor_id())) + return; + + irq_work_queue(this_cpu_ptr(&nohz_full_kick_work)); +} + +/* + * Kick the CPU if it's full dynticks in order to force it to + * re-evaluate its dependency on the tick and restart it if necessary. + */ +void tick_nohz_full_kick_cpu(int cpu) +{ + if (!tick_nohz_full_cpu(cpu)) + return; + + irq_work_queue_on(&per_cpu(nohz_full_kick_work, cpu), cpu); +} + +static void nohz_full_kick_ipi(void *info) +{ + __tick_nohz_full_check(); +} + +/* + * Kick all full dynticks CPUs in order to force these to re-evaluate + * their dependency on the tick and restart it if necessary. + */ +void tick_nohz_full_kick_all(void) +{ + if (!tick_nohz_full_running) + return; + + preempt_disable(); + smp_call_function_many(tick_nohz_full_mask, + nohz_full_kick_ipi, NULL, false); + tick_nohz_full_kick(); + preempt_enable(); +} + +/* + * Re-evaluate the need for the tick as we switch the current task. + * It might need the tick due to per task/process properties: + * perf events, posix cpu timers, ... + */ +void __tick_nohz_task_switch(struct task_struct *tsk) +{ + unsigned long flags; + + local_irq_save(flags); + + if (!tick_nohz_full_cpu(smp_processor_id())) + goto out; + + if (tick_nohz_tick_stopped() && !can_stop_full_tick()) + tick_nohz_full_kick(); + +out: + local_irq_restore(flags); +} + +/* Parse the boot-time nohz CPU list from the kernel parameters. */ +static int __init tick_nohz_full_setup(char *str) +{ + alloc_bootmem_cpumask_var(&tick_nohz_full_mask); + if (cpulist_parse(str, tick_nohz_full_mask) < 0) { + pr_warning("NOHZ: Incorrect nohz_full cpumask\n"); + free_bootmem_cpumask_var(tick_nohz_full_mask); + return 1; + } + tick_nohz_full_running = true; + + return 1; +} +__setup("nohz_full=", tick_nohz_full_setup); + +static int tick_nohz_cpu_down_callback(struct notifier_block *nfb, + unsigned long action, + void *hcpu) +{ + unsigned int cpu = (unsigned long)hcpu; + + switch (action & ~CPU_TASKS_FROZEN) { + case CPU_DOWN_PREPARE: + /* + * If we handle the timekeeping duty for full dynticks CPUs, + * we can't safely shutdown that CPU. + */ + if (tick_nohz_full_running && tick_do_timer_cpu == cpu) + return NOTIFY_BAD; + break; + } + return NOTIFY_OK; +} + +static int tick_nohz_init_all(void) +{ + int err = -1; + +#ifdef CONFIG_NO_HZ_FULL_ALL + if (!alloc_cpumask_var(&tick_nohz_full_mask, GFP_KERNEL)) { + WARN(1, "NO_HZ: Can't allocate full dynticks cpumask\n"); + return err; + } + err = 0; + cpumask_setall(tick_nohz_full_mask); + tick_nohz_full_running = true; +#endif + return err; +} + +void __init tick_nohz_init(void) +{ + int cpu; + + if (!tick_nohz_full_running) { + if (tick_nohz_init_all() < 0) + return; + } + + if (!alloc_cpumask_var(&housekeeping_mask, GFP_KERNEL)) { + WARN(1, "NO_HZ: Can't allocate not-full dynticks cpumask\n"); + cpumask_clear(tick_nohz_full_mask); + tick_nohz_full_running = false; + return; + } + + /* + * Full dynticks uses irq work to drive the tick rescheduling on safe + * locking contexts. But then we need irq work to raise its own + * interrupts to avoid circular dependency on the tick + */ + if (!arch_irq_work_has_interrupt()) { + pr_warning("NO_HZ: Can't run full dynticks because arch doesn't " + "support irq work self-IPIs\n"); + cpumask_clear(tick_nohz_full_mask); + cpumask_copy(housekeeping_mask, cpu_possible_mask); + tick_nohz_full_running = false; + return; + } + + cpu = smp_processor_id(); + + if (cpumask_test_cpu(cpu, tick_nohz_full_mask)) { + pr_warning("NO_HZ: Clearing %d from nohz_full range for timekeeping\n", cpu); + cpumask_clear_cpu(cpu, tick_nohz_full_mask); + } + + cpumask_andnot(housekeeping_mask, + cpu_possible_mask, tick_nohz_full_mask); + + for_each_cpu(cpu, tick_nohz_full_mask) + context_tracking_cpu_set(cpu); + + cpu_notifier(tick_nohz_cpu_down_callback, 0); + pr_info("NO_HZ: Full dynticks CPUs: %*pbl.\n", + cpumask_pr_args(tick_nohz_full_mask)); +} +#endif + +/* + * NOHZ - aka dynamic tick functionality + */ +#ifdef CONFIG_NO_HZ_COMMON +/* + * NO HZ enabled ? + */ +static int tick_nohz_enabled __read_mostly = 1; +int tick_nohz_active __read_mostly; +/* + * Enable / Disable tickless mode + */ +static int __init setup_tick_nohz(char *str) +{ + if (!strcmp(str, "off")) + tick_nohz_enabled = 0; + else if (!strcmp(str, "on")) + tick_nohz_enabled = 1; + else + return 0; + return 1; +} + +__setup("nohz=", setup_tick_nohz); + +int tick_nohz_tick_stopped(void) +{ + return __this_cpu_read(tick_cpu_sched.tick_stopped); +} + +/** + * tick_nohz_update_jiffies - update jiffies when idle was interrupted + * + * Called from interrupt entry when the CPU was idle + * + * In case the sched_tick was stopped on this CPU, we have to check if jiffies + * must be updated. Otherwise an interrupt handler could use a stale jiffy + * value. We do this unconditionally on any cpu, as we don't know whether the + * cpu, which has the update task assigned is in a long sleep. + */ +static void tick_nohz_update_jiffies(ktime_t now) +{ + unsigned long flags; + + __this_cpu_write(tick_cpu_sched.idle_waketime, now); + + local_irq_save(flags); + tick_do_update_jiffies64(now); + local_irq_restore(flags); + + touch_softlockup_watchdog(); +} + +/* + * Updates the per cpu time idle statistics counters + */ +static void +update_ts_time_stats(int cpu, struct tick_sched *ts, ktime_t now, u64 *last_update_time) +{ + ktime_t delta; + + if (ts->idle_active) { + delta = ktime_sub(now, ts->idle_entrytime); + if (nr_iowait_cpu(cpu) > 0) + ts->iowait_sleeptime = ktime_add(ts->iowait_sleeptime, delta); + else + ts->idle_sleeptime = ktime_add(ts->idle_sleeptime, delta); + ts->idle_entrytime = now; + } + + if (last_update_time) + *last_update_time = ktime_to_us(now); + +} + +static void tick_nohz_stop_idle(struct tick_sched *ts, ktime_t now) +{ + update_ts_time_stats(smp_processor_id(), ts, now, NULL); + ts->idle_active = 0; + + sched_clock_idle_wakeup_event(0); +} + +static ktime_t tick_nohz_start_idle(struct tick_sched *ts) +{ + ktime_t now = ktime_get(); + + ts->idle_entrytime = now; + ts->idle_active = 1; + sched_clock_idle_sleep_event(); + return now; +} + +/** + * get_cpu_idle_time_us - get the total idle time of a cpu + * @cpu: CPU number to query + * @last_update_time: variable to store update time in. Do not update + * counters if NULL. + * + * Return the cummulative idle time (since boot) for a given + * CPU, in microseconds. + * + * This time is measured via accounting rather than sampling, + * and is as accurate as ktime_get() is. + * + * This function returns -1 if NOHZ is not enabled. + */ +u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time) +{ + struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu); + ktime_t now, idle; + + if (!tick_nohz_active) + return -1; + + now = ktime_get(); + if (last_update_time) { + update_ts_time_stats(cpu, ts, now, last_update_time); + idle = ts->idle_sleeptime; + } else { + if (ts->idle_active && !nr_iowait_cpu(cpu)) { + ktime_t delta = ktime_sub(now, ts->idle_entrytime); + + idle = ktime_add(ts->idle_sleeptime, delta); + } else { + idle = ts->idle_sleeptime; + } + } + + return ktime_to_us(idle); + +} +EXPORT_SYMBOL_GPL(get_cpu_idle_time_us); + +/** + * get_cpu_iowait_time_us - get the total iowait time of a cpu + * @cpu: CPU number to query + * @last_update_time: variable to store update time in. Do not update + * counters if NULL. + * + * Return the cummulative iowait time (since boot) for a given + * CPU, in microseconds. + * + * This time is measured via accounting rather than sampling, + * and is as accurate as ktime_get() is. + * + * This function returns -1 if NOHZ is not enabled. + */ +u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time) +{ + struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu); + ktime_t now, iowait; + + if (!tick_nohz_active) + return -1; + + now = ktime_get(); + if (last_update_time) { + update_ts_time_stats(cpu, ts, now, last_update_time); + iowait = ts->iowait_sleeptime; + } else { + if (ts->idle_active && nr_iowait_cpu(cpu) > 0) { + ktime_t delta = ktime_sub(now, ts->idle_entrytime); + + iowait = ktime_add(ts->iowait_sleeptime, delta); + } else { + iowait = ts->iowait_sleeptime; + } + } + + return ktime_to_us(iowait); +} +EXPORT_SYMBOL_GPL(get_cpu_iowait_time_us); + +static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts, + ktime_t now, int cpu) +{ + unsigned long seq, last_jiffies, next_jiffies, delta_jiffies; + ktime_t last_update, expires, ret = { .tv64 = 0 }; + unsigned long rcu_delta_jiffies; + struct clock_event_device *dev = __this_cpu_read(tick_cpu_device.evtdev); + u64 time_delta; + + time_delta = timekeeping_max_deferment(); + + /* Read jiffies and the time when jiffies were updated last */ + do { + seq = read_seqcount_begin(&jiffies_seq); + last_update = last_jiffies_update; + last_jiffies = jiffies; + } while (read_seqcount_retry(&jiffies_seq, seq)); + + if (rcu_needs_cpu(&rcu_delta_jiffies) || + arch_needs_cpu() || irq_work_needs_cpu()) { + next_jiffies = last_jiffies + 1; + delta_jiffies = 1; + } else { + /* Get the next timer wheel timer */ + next_jiffies = get_next_timer_interrupt(last_jiffies); + delta_jiffies = next_jiffies - last_jiffies; + if (rcu_delta_jiffies < delta_jiffies) { + next_jiffies = last_jiffies + rcu_delta_jiffies; + delta_jiffies = rcu_delta_jiffies; + } + } + + /* + * Do not stop the tick, if we are only one off (or less) + * or if the cpu is required for RCU: + */ + if (!ts->tick_stopped && delta_jiffies <= 1) + goto out; + + /* Schedule the tick, if we are at least one jiffie off */ + if ((long)delta_jiffies >= 1) { + + /* + * If this cpu is the one which updates jiffies, then + * give up the assignment and let it be taken by the + * cpu which runs the tick timer next, which might be + * this cpu as well. If we don't drop this here the + * jiffies might be stale and do_timer() never + * invoked. Keep track of the fact that it was the one + * which had the do_timer() duty last. If this cpu is + * the one which had the do_timer() duty last, we + * limit the sleep time to the timekeeping + * max_deferement value which we retrieved + * above. Otherwise we can sleep as long as we want. + */ + if (cpu == tick_do_timer_cpu) { + tick_do_timer_cpu = TICK_DO_TIMER_NONE; + ts->do_timer_last = 1; + } else if (tick_do_timer_cpu != TICK_DO_TIMER_NONE) { + time_delta = KTIME_MAX; + ts->do_timer_last = 0; + } else if (!ts->do_timer_last) { + time_delta = KTIME_MAX; + } + +#ifdef CONFIG_NO_HZ_FULL + if (!ts->inidle) { + time_delta = min(time_delta, + scheduler_tick_max_deferment()); + } +#endif + + /* + * calculate the expiry time for the next timer wheel + * timer. delta_jiffies >= NEXT_TIMER_MAX_DELTA signals + * that there is no timer pending or at least extremely + * far into the future (12 days for HZ=1000). In this + * case we set the expiry to the end of time. + */ + if (likely(delta_jiffies < NEXT_TIMER_MAX_DELTA)) { + /* + * Calculate the time delta for the next timer event. + * If the time delta exceeds the maximum time delta + * permitted by the current clocksource then adjust + * the time delta accordingly to ensure the + * clocksource does not wrap. + */ + time_delta = min_t(u64, time_delta, + tick_period.tv64 * delta_jiffies); + } + + if (time_delta < KTIME_MAX) + expires = ktime_add_ns(last_update, time_delta); + else + expires.tv64 = KTIME_MAX; + + /* Skip reprogram of event if its not changed */ + if (ts->tick_stopped && ktime_equal(expires, dev->next_event)) + goto out; + + ret = expires; + + /* + * nohz_stop_sched_tick can be called several times before + * the nohz_restart_sched_tick is called. This happens when + * interrupts arrive which do not cause a reschedule. In the + * first call we save the current tick time, so we can restart + * the scheduler tick in nohz_restart_sched_tick. + */ + if (!ts->tick_stopped) { + nohz_balance_enter_idle(cpu); + calc_load_enter_idle(); + + ts->last_tick = hrtimer_get_expires(&ts->sched_timer); + ts->tick_stopped = 1; + trace_tick_stop(1, " "); + } + + /* + * If the expiration time == KTIME_MAX, then + * in this case we simply stop the tick timer. + */ + if (unlikely(expires.tv64 == KTIME_MAX)) { + if (ts->nohz_mode == NOHZ_MODE_HIGHRES) + hrtimer_cancel(&ts->sched_timer); + goto out; + } + + if (ts->nohz_mode == NOHZ_MODE_HIGHRES) { + hrtimer_start(&ts->sched_timer, expires, + HRTIMER_MODE_ABS_PINNED); + /* Check, if the timer was already in the past */ + if (hrtimer_active(&ts->sched_timer)) + goto out; + } else if (!tick_program_event(expires, 0)) + goto out; + /* + * We are past the event already. So we crossed a + * jiffie boundary. Update jiffies and raise the + * softirq. + */ + tick_do_update_jiffies64(ktime_get()); + } + raise_softirq_irqoff(TIMER_SOFTIRQ); +out: + ts->next_jiffies = next_jiffies; + ts->last_jiffies = last_jiffies; + ts->sleep_length = ktime_sub(dev->next_event, now); + + return ret; +} + +static void tick_nohz_full_stop_tick(struct tick_sched *ts) +{ +#ifdef CONFIG_NO_HZ_FULL + int cpu = smp_processor_id(); + + if (!tick_nohz_full_cpu(cpu) || is_idle_task(current)) + return; + + if (!ts->tick_stopped && ts->nohz_mode == NOHZ_MODE_INACTIVE) + return; + + if (!can_stop_full_tick()) + return; + + tick_nohz_stop_sched_tick(ts, ktime_get(), cpu); +#endif +} + +static bool can_stop_idle_tick(int cpu, struct tick_sched *ts) +{ + /* + * If this cpu is offline and it is the one which updates + * jiffies, then give up the assignment and let it be taken by + * the cpu which runs the tick timer next. If we don't drop + * this here the jiffies might be stale and do_timer() never + * invoked. + */ + if (unlikely(!cpu_online(cpu))) { + if (cpu == tick_do_timer_cpu) + tick_do_timer_cpu = TICK_DO_TIMER_NONE; + return false; + } + + if (unlikely(ts->nohz_mode == NOHZ_MODE_INACTIVE)) { + ts->sleep_length = (ktime_t) { .tv64 = NSEC_PER_SEC/HZ }; + return false; + } + + if (need_resched()) + return false; + + if (unlikely(local_softirq_pending() && cpu_online(cpu))) { + softirq_check_pending_idle(); + return false; + } + + if (tick_nohz_full_enabled()) { + /* + * Keep the tick alive to guarantee timekeeping progression + * if there are full dynticks CPUs around + */ + if (tick_do_timer_cpu == cpu) + return false; + /* + * Boot safety: make sure the timekeeping duty has been + * assigned before entering dyntick-idle mode, + */ + if (tick_do_timer_cpu == TICK_DO_TIMER_NONE) + return false; + } + + return true; +} + +static void __tick_nohz_idle_enter(struct tick_sched *ts) +{ + ktime_t now, expires; + int cpu = smp_processor_id(); + + now = tick_nohz_start_idle(ts); + + if (can_stop_idle_tick(cpu, ts)) { + int was_stopped = ts->tick_stopped; + + ts->idle_calls++; + + expires = tick_nohz_stop_sched_tick(ts, now, cpu); + if (expires.tv64 > 0LL) { + ts->idle_sleeps++; + ts->idle_expires = expires; + } + + if (!was_stopped && ts->tick_stopped) + ts->idle_jiffies = ts->last_jiffies; + } +} + +/** + * tick_nohz_idle_enter - stop the idle tick from the idle task + * + * When the next event is more than a tick into the future, stop the idle tick + * Called when we start the idle loop. + * + * The arch is responsible of calling: + * + * - rcu_idle_enter() after its last use of RCU before the CPU is put + * to sleep. + * - rcu_idle_exit() before the first use of RCU after the CPU is woken up. + */ +void tick_nohz_idle_enter(void) +{ + struct tick_sched *ts; + + WARN_ON_ONCE(irqs_disabled()); + + /* + * Update the idle state in the scheduler domain hierarchy + * when tick_nohz_stop_sched_tick() is called from the idle loop. + * State will be updated to busy during the first busy tick after + * exiting idle. + */ + set_cpu_sd_state_idle(); + + local_irq_disable(); + + ts = this_cpu_ptr(&tick_cpu_sched); + ts->inidle = 1; + __tick_nohz_idle_enter(ts); + + local_irq_enable(); +} + +/** + * tick_nohz_irq_exit - update next tick event from interrupt exit + * + * When an interrupt fires while we are idle and it doesn't cause + * a reschedule, it may still add, modify or delete a timer, enqueue + * an RCU callback, etc... + * So we need to re-calculate and reprogram the next tick event. + */ +void tick_nohz_irq_exit(void) +{ + struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); + + if (ts->inidle) + __tick_nohz_idle_enter(ts); + else + tick_nohz_full_stop_tick(ts); +} + +/** + * tick_nohz_get_sleep_length - return the length of the current sleep + * + * Called from power state control code with interrupts disabled + */ +ktime_t tick_nohz_get_sleep_length(void) +{ + struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); + + return ts->sleep_length; +} + +static void tick_nohz_restart(struct tick_sched *ts, ktime_t now) +{ + hrtimer_cancel(&ts->sched_timer); + hrtimer_set_expires(&ts->sched_timer, ts->last_tick); + + while (1) { + /* Forward the time to expire in the future */ + hrtimer_forward(&ts->sched_timer, now, tick_period); + + if (ts->nohz_mode == NOHZ_MODE_HIGHRES) { + hrtimer_start_expires(&ts->sched_timer, + HRTIMER_MODE_ABS_PINNED); + /* Check, if the timer was already in the past */ + if (hrtimer_active(&ts->sched_timer)) + break; + } else { + if (!tick_program_event( + hrtimer_get_expires(&ts->sched_timer), 0)) + break; + } + /* Reread time and update jiffies */ + now = ktime_get(); + tick_do_update_jiffies64(now); + } +} + +static void tick_nohz_restart_sched_tick(struct tick_sched *ts, ktime_t now) +{ + /* Update jiffies first */ + tick_do_update_jiffies64(now); + update_cpu_load_nohz(); + + calc_load_exit_idle(); + touch_softlockup_watchdog(); + /* + * Cancel the scheduled timer and restore the tick + */ + ts->tick_stopped = 0; + ts->idle_exittime = now; + + tick_nohz_restart(ts, now); +} + +static void tick_nohz_account_idle_ticks(struct tick_sched *ts) +{ +#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE + unsigned long ticks; + + if (vtime_accounting_enabled()) + return; + /* + * We stopped the tick in idle. Update process times would miss the + * time we slept as update_process_times does only a 1 tick + * accounting. Enforce that this is accounted to idle ! + */ + ticks = jiffies - ts->idle_jiffies; + /* + * We might be one off. Do not randomly account a huge number of ticks! + */ + if (ticks && ticks < LONG_MAX) + account_idle_ticks(ticks); +#endif +} + +/** + * tick_nohz_idle_exit - restart the idle tick from the idle task + * + * Restart the idle tick when the CPU is woken up from idle + * This also exit the RCU extended quiescent state. The CPU + * can use RCU again after this function is called. + */ +void tick_nohz_idle_exit(void) +{ + struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); + ktime_t now; + + local_irq_disable(); + + WARN_ON_ONCE(!ts->inidle); + + ts->inidle = 0; + + if (ts->idle_active || ts->tick_stopped) + now = ktime_get(); + + if (ts->idle_active) + tick_nohz_stop_idle(ts, now); + + if (ts->tick_stopped) { + tick_nohz_restart_sched_tick(ts, now); + tick_nohz_account_idle_ticks(ts); + } + + local_irq_enable(); +} + +static int tick_nohz_reprogram(struct tick_sched *ts, ktime_t now) +{ + hrtimer_forward(&ts->sched_timer, now, tick_period); + return tick_program_event(hrtimer_get_expires(&ts->sched_timer), 0); +} + +/* + * The nohz low res interrupt handler + */ +static void tick_nohz_handler(struct clock_event_device *dev) +{ + struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); + struct pt_regs *regs = get_irq_regs(); + ktime_t now = ktime_get(); + + dev->next_event.tv64 = KTIME_MAX; + + tick_sched_do_timer(now); + tick_sched_handle(ts, regs); + + /* No need to reprogram if we are running tickless */ + if (unlikely(ts->tick_stopped)) + return; + + while (tick_nohz_reprogram(ts, now)) { + now = ktime_get(); + tick_do_update_jiffies64(now); + } +} + +/** + * tick_nohz_switch_to_nohz - switch to nohz mode + */ +static void tick_nohz_switch_to_nohz(void) +{ + struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); + ktime_t next; + + if (!tick_nohz_enabled) + return; + + local_irq_disable(); + if (tick_switch_to_oneshot(tick_nohz_handler)) { + local_irq_enable(); + return; + } + tick_nohz_active = 1; + ts->nohz_mode = NOHZ_MODE_LOWRES; + + /* + * Recycle the hrtimer in ts, so we can share the + * hrtimer_forward with the highres code. + */ + hrtimer_init(&ts->sched_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS); + /* Get the next period */ + next = tick_init_jiffy_update(); + + for (;;) { + hrtimer_set_expires(&ts->sched_timer, next); + if (!tick_program_event(next, 0)) + break; + next = ktime_add(next, tick_period); + } + local_irq_enable(); +} + +/* + * When NOHZ is enabled and the tick is stopped, we need to kick the + * tick timer from irq_enter() so that the jiffies update is kept + * alive during long running softirqs. That's ugly as hell, but + * correctness is key even if we need to fix the offending softirq in + * the first place. + * + * Note, this is different to tick_nohz_restart. We just kick the + * timer and do not touch the other magic bits which need to be done + * when idle is left. + */ +static void tick_nohz_kick_tick(struct tick_sched *ts, ktime_t now) +{ +#if 0 + /* Switch back to 2.6.27 behaviour */ + ktime_t delta; + + /* + * Do not touch the tick device, when the next expiry is either + * already reached or less/equal than the tick period. + */ + delta = ktime_sub(hrtimer_get_expires(&ts->sched_timer), now); + if (delta.tv64 <= tick_period.tv64) + return; + + tick_nohz_restart(ts, now); +#endif +} + +static inline void tick_nohz_irq_enter(void) +{ + struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); + ktime_t now; + + if (!ts->idle_active && !ts->tick_stopped) + return; + now = ktime_get(); + if (ts->idle_active) + tick_nohz_stop_idle(ts, now); + if (ts->tick_stopped) { + tick_nohz_update_jiffies(now); + tick_nohz_kick_tick(ts, now); + } +} + +#else + +static inline void tick_nohz_switch_to_nohz(void) { } +static inline void tick_nohz_irq_enter(void) { } + +#endif /* CONFIG_NO_HZ_COMMON */ + +/* + * Called from irq_enter to notify about the possible interruption of idle() + */ +void tick_irq_enter(void) +{ + tick_check_oneshot_broadcast_this_cpu(); + tick_nohz_irq_enter(); +} + +/* + * High resolution timer specific code + */ +#ifdef CONFIG_HIGH_RES_TIMERS +/* + * We rearm the timer until we get disabled by the idle code. + * Called with interrupts disabled. + */ +static enum hrtimer_restart tick_sched_timer(struct hrtimer *timer) +{ + struct tick_sched *ts = + container_of(timer, struct tick_sched, sched_timer); + struct pt_regs *regs = get_irq_regs(); + ktime_t now = ktime_get(); + + tick_sched_do_timer(now); + + /* + * Do not call, when we are not in irq context and have + * no valid regs pointer + */ + if (regs) + tick_sched_handle(ts, regs); + + /* No need to reprogram if we are in idle or full dynticks mode */ + if (unlikely(ts->tick_stopped)) + return HRTIMER_NORESTART; + + hrtimer_forward(timer, now, tick_period); + + return HRTIMER_RESTART; +} + +static int sched_skew_tick; + +static int __init skew_tick(char *str) +{ + get_option(&str, &sched_skew_tick); + + return 0; +} +early_param("skew_tick", skew_tick); + +/** + * tick_setup_sched_timer - setup the tick emulation timer + */ +void tick_setup_sched_timer(void) +{ + struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); + ktime_t now = ktime_get(); + + /* + * Emulate tick processing via per-CPU hrtimers: + */ + hrtimer_init(&ts->sched_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS); + ts->sched_timer.irqsafe = 1; + ts->sched_timer.function = tick_sched_timer; + + /* Get the next period (per cpu) */ + hrtimer_set_expires(&ts->sched_timer, tick_init_jiffy_update()); + + /* Offset the tick to avert jiffies_lock contention. */ + if (sched_skew_tick) { + u64 offset = ktime_to_ns(tick_period) >> 1; + do_div(offset, num_possible_cpus()); + offset *= smp_processor_id(); + hrtimer_add_expires_ns(&ts->sched_timer, offset); + } + + for (;;) { + hrtimer_forward(&ts->sched_timer, now, tick_period); + hrtimer_start_expires(&ts->sched_timer, + HRTIMER_MODE_ABS_PINNED); + /* Check, if the timer was already in the past */ + if (hrtimer_active(&ts->sched_timer)) + break; + now = ktime_get(); + } + +#ifdef CONFIG_NO_HZ_COMMON + if (tick_nohz_enabled) { + ts->nohz_mode = NOHZ_MODE_HIGHRES; + tick_nohz_active = 1; + } +#endif +} +#endif /* HIGH_RES_TIMERS */ + +#if defined CONFIG_NO_HZ_COMMON || defined CONFIG_HIGH_RES_TIMERS +void tick_cancel_sched_timer(int cpu) +{ + struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu); + +# ifdef CONFIG_HIGH_RES_TIMERS + if (ts->sched_timer.base) + hrtimer_cancel(&ts->sched_timer); +# endif + + memset(ts, 0, sizeof(*ts)); +} +#endif + +/** + * Async notification about clocksource changes + */ +void tick_clock_notify(void) +{ + int cpu; + + for_each_possible_cpu(cpu) + set_bit(0, &per_cpu(tick_cpu_sched, cpu).check_clocks); +} + +/* + * Async notification about clock event changes + */ +void tick_oneshot_notify(void) +{ + struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); + + set_bit(0, &ts->check_clocks); +} + +/** + * Check, if a change happened, which makes oneshot possible. + * + * Called cyclic from the hrtimer softirq (driven by the timer + * softirq) allow_nohz signals, that we can switch into low-res nohz + * mode, because high resolution timers are disabled (either compile + * or runtime). + */ +int tick_check_oneshot_change(int allow_nohz) +{ + struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); + + if (!test_and_clear_bit(0, &ts->check_clocks)) + return 0; + + if (ts->nohz_mode != NOHZ_MODE_INACTIVE) + return 0; + + if (!timekeeping_valid_for_hres() || !tick_is_oneshot_available()) + return 0; + + if (!allow_nohz) + return 1; + + tick_nohz_switch_to_nohz(); + return 0; +} diff --git a/kernel/kernel/time/tick-sched.h b/kernel/kernel/time/tick-sched.h new file mode 100644 index 000000000..28b5da3e1 --- /dev/null +++ b/kernel/kernel/time/tick-sched.h @@ -0,0 +1,74 @@ +#ifndef _TICK_SCHED_H +#define _TICK_SCHED_H + +#include + +enum tick_device_mode { + TICKDEV_MODE_PERIODIC, + TICKDEV_MODE_ONESHOT, +}; + +struct tick_device { + struct clock_event_device *evtdev; + enum tick_device_mode mode; +}; + +enum tick_nohz_mode { + NOHZ_MODE_INACTIVE, + NOHZ_MODE_LOWRES, + NOHZ_MODE_HIGHRES, +}; + +/** + * struct tick_sched - sched tick emulation and no idle tick control/stats + * @sched_timer: hrtimer to schedule the periodic tick in high + * resolution mode + * @last_tick: Store the last tick expiry time when the tick + * timer is modified for nohz sleeps. This is necessary + * to resume the tick timer operation in the timeline + * when the CPU returns from nohz sleep. + * @tick_stopped: Indicator that the idle tick has been stopped + * @idle_jiffies: jiffies at the entry to idle for idle time accounting + * @idle_calls: Total number of idle calls + * @idle_sleeps: Number of idle calls, where the sched tick was stopped + * @idle_entrytime: Time when the idle call was entered + * @idle_waketime: Time when the idle was interrupted + * @idle_exittime: Time when the idle state was left + * @idle_sleeptime: Sum of the time slept in idle with sched tick stopped + * @iowait_sleeptime: Sum of the time slept in idle with sched tick stopped, with IO outstanding + * @sleep_length: Duration of the current idle sleep + * @do_timer_lst: CPU was the last one doing do_timer before going idle + */ +struct tick_sched { + struct hrtimer sched_timer; + unsigned long check_clocks; + enum tick_nohz_mode nohz_mode; + ktime_t last_tick; + int inidle; + int tick_stopped; + unsigned long idle_jiffies; + unsigned long idle_calls; + unsigned long idle_sleeps; + int idle_active; + ktime_t idle_entrytime; + ktime_t idle_waketime; + ktime_t idle_exittime; + ktime_t idle_sleeptime; + ktime_t iowait_sleeptime; + ktime_t sleep_length; + unsigned long last_jiffies; + unsigned long next_jiffies; + ktime_t idle_expires; + int do_timer_last; +}; + +extern struct tick_sched *tick_get_tick_sched(int cpu); + +extern void tick_setup_sched_timer(void); +#if defined CONFIG_NO_HZ_COMMON || defined CONFIG_HIGH_RES_TIMERS +extern void tick_cancel_sched_timer(int cpu); +#else +static inline void tick_cancel_sched_timer(int cpu) { } +#endif + +#endif diff --git a/kernel/kernel/time/time.c b/kernel/kernel/time/time.c new file mode 100644 index 000000000..2c85b7724 --- /dev/null +++ b/kernel/kernel/time/time.c @@ -0,0 +1,785 @@ +/* + * linux/kernel/time.c + * + * Copyright (C) 1991, 1992 Linus Torvalds + * + * This file contains the interface functions for the various + * time related system calls: time, stime, gettimeofday, settimeofday, + * adjtime + */ +/* + * Modification history kernel/time.c + * + * 1993-09-02 Philip Gladstone + * Created file with time related functions from sched/core.c and adjtimex() + * 1993-10-08 Torsten Duwe + * adjtime interface update and CMOS clock write code + * 1995-08-13 Torsten Duwe + * kernel PLL updated to 1994-12-13 specs (rfc-1589) + * 1999-01-16 Ulrich Windl + * Introduced error checking for many cases in adjtimex(). + * Updated NTP code according to technical memorandum Jan '96 + * "A Kernel Model for Precision Timekeeping" by Dave Mills + * Allow time_constant larger than MAXTC(6) for NTP v4 (MAXTC == 10) + * (Even though the technical memorandum forbids it) + * 2004-07-14 Christoph Lameter + * Added getnstimeofday to allow the posix timer functions to return + * with nanosecond accuracy + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include + +#include "timeconst.h" +#include "timekeeping.h" + +/* + * The timezone where the local system is located. Used as a default by some + * programs who obtain this value by using gettimeofday. + */ +struct timezone sys_tz; + +EXPORT_SYMBOL(sys_tz); + +#ifdef __ARCH_WANT_SYS_TIME + +/* + * sys_time() can be implemented in user-level using + * sys_gettimeofday(). Is this for backwards compatibility? If so, + * why not move it into the appropriate arch directory (for those + * architectures that need it). + */ +SYSCALL_DEFINE1(time, time_t __user *, tloc) +{ + time_t i = get_seconds(); + + if (tloc) { + if (put_user(i,tloc)) + return -EFAULT; + } + force_successful_syscall_return(); + return i; +} + +/* + * sys_stime() can be implemented in user-level using + * sys_settimeofday(). Is this for backwards compatibility? If so, + * why not move it into the appropriate arch directory (for those + * architectures that need it). + */ + +SYSCALL_DEFINE1(stime, time_t __user *, tptr) +{ + struct timespec tv; + int err; + + if (get_user(tv.tv_sec, tptr)) + return -EFAULT; + + tv.tv_nsec = 0; + + err = security_settime(&tv, NULL); + if (err) + return err; + + do_settimeofday(&tv); + return 0; +} + +#endif /* __ARCH_WANT_SYS_TIME */ + +SYSCALL_DEFINE2(gettimeofday, struct timeval __user *, tv, + struct timezone __user *, tz) +{ + if (likely(tv != NULL)) { + struct timeval ktv; + do_gettimeofday(&ktv); + if (copy_to_user(tv, &ktv, sizeof(ktv))) + return -EFAULT; + } + if (unlikely(tz != NULL)) { + if (copy_to_user(tz, &sys_tz, sizeof(sys_tz))) + return -EFAULT; + } + return 0; +} + +/* + * Indicates if there is an offset between the system clock and the hardware + * clock/persistent clock/rtc. + */ +int persistent_clock_is_local; + +/* + * Adjust the time obtained from the CMOS to be UTC time instead of + * local time. + * + * This is ugly, but preferable to the alternatives. Otherwise we + * would either need to write a program to do it in /etc/rc (and risk + * confusion if the program gets run more than once; it would also be + * hard to make the program warp the clock precisely n hours) or + * compile in the timezone information into the kernel. Bad, bad.... + * + * - TYT, 1992-01-01 + * + * The best thing to do is to keep the CMOS clock in universal time (UTC) + * as real UNIX machines always do it. This avoids all headaches about + * daylight saving times and warping kernel clocks. + */ +static inline void warp_clock(void) +{ + if (sys_tz.tz_minuteswest != 0) { + struct timespec adjust; + + persistent_clock_is_local = 1; + adjust.tv_sec = sys_tz.tz_minuteswest * 60; + adjust.tv_nsec = 0; + timekeeping_inject_offset(&adjust); + } +} + +/* + * In case for some reason the CMOS clock has not already been running + * in UTC, but in some local time: The first time we set the timezone, + * we will warp the clock so that it is ticking UTC time instead of + * local time. Presumably, if someone is setting the timezone then we + * are running in an environment where the programs understand about + * timezones. This should be done at boot time in the /etc/rc script, + * as soon as possible, so that the clock can be set right. Otherwise, + * various programs will get confused when the clock gets warped. + */ + +int do_sys_settimeofday(const struct timespec *tv, const struct timezone *tz) +{ + static int firsttime = 1; + int error = 0; + + if (tv && !timespec_valid(tv)) + return -EINVAL; + + error = security_settime(tv, tz); + if (error) + return error; + + if (tz) { + sys_tz = *tz; + update_vsyscall_tz(); + if (firsttime) { + firsttime = 0; + if (!tv) + warp_clock(); + } + } + if (tv) + return do_settimeofday(tv); + return 0; +} + +SYSCALL_DEFINE2(settimeofday, struct timeval __user *, tv, + struct timezone __user *, tz) +{ + struct timeval user_tv; + struct timespec new_ts; + struct timezone new_tz; + + if (tv) { + if (copy_from_user(&user_tv, tv, sizeof(*tv))) + return -EFAULT; + + if (!timeval_valid(&user_tv)) + return -EINVAL; + + new_ts.tv_sec = user_tv.tv_sec; + new_ts.tv_nsec = user_tv.tv_usec * NSEC_PER_USEC; + } + if (tz) { + if (copy_from_user(&new_tz, tz, sizeof(*tz))) + return -EFAULT; + } + + return do_sys_settimeofday(tv ? &new_ts : NULL, tz ? &new_tz : NULL); +} + +SYSCALL_DEFINE1(adjtimex, struct timex __user *, txc_p) +{ + struct timex txc; /* Local copy of parameter */ + int ret; + + /* Copy the user data space into the kernel copy + * structure. But bear in mind that the structures + * may change + */ + if(copy_from_user(&txc, txc_p, sizeof(struct timex))) + return -EFAULT; + ret = do_adjtimex(&txc); + return copy_to_user(txc_p, &txc, sizeof(struct timex)) ? -EFAULT : ret; +} + +/** + * current_fs_time - Return FS time + * @sb: Superblock. + * + * Return the current time truncated to the time granularity supported by + * the fs. + */ +struct timespec current_fs_time(struct super_block *sb) +{ + struct timespec now = current_kernel_time(); + return timespec_trunc(now, sb->s_time_gran); +} +EXPORT_SYMBOL(current_fs_time); + +/* + * Convert jiffies to milliseconds and back. + * + * Avoid unnecessary multiplications/divisions in the + * two most common HZ cases: + */ +unsigned int jiffies_to_msecs(const unsigned long j) +{ +#if HZ <= MSEC_PER_SEC && !(MSEC_PER_SEC % HZ) + return (MSEC_PER_SEC / HZ) * j; +#elif HZ > MSEC_PER_SEC && !(HZ % MSEC_PER_SEC) + return (j + (HZ / MSEC_PER_SEC) - 1)/(HZ / MSEC_PER_SEC); +#else +# if BITS_PER_LONG == 32 + return (HZ_TO_MSEC_MUL32 * j) >> HZ_TO_MSEC_SHR32; +# else + return (j * HZ_TO_MSEC_NUM) / HZ_TO_MSEC_DEN; +# endif +#endif +} +EXPORT_SYMBOL(jiffies_to_msecs); + +unsigned int jiffies_to_usecs(const unsigned long j) +{ +#if HZ <= USEC_PER_SEC && !(USEC_PER_SEC % HZ) + return (USEC_PER_SEC / HZ) * j; +#elif HZ > USEC_PER_SEC && !(HZ % USEC_PER_SEC) + return (j + (HZ / USEC_PER_SEC) - 1)/(HZ / USEC_PER_SEC); +#else +# if BITS_PER_LONG == 32 + return (HZ_TO_USEC_MUL32 * j) >> HZ_TO_USEC_SHR32; +# else + return (j * HZ_TO_USEC_NUM) / HZ_TO_USEC_DEN; +# endif +#endif +} +EXPORT_SYMBOL(jiffies_to_usecs); + +/** + * timespec_trunc - Truncate timespec to a granularity + * @t: Timespec + * @gran: Granularity in ns. + * + * Truncate a timespec to a granularity. gran must be smaller than a second. + * Always rounds down. + * + * This function should be only used for timestamps returned by + * current_kernel_time() or CURRENT_TIME, not with do_gettimeofday() because + * it doesn't handle the better resolution of the latter. + */ +struct timespec timespec_trunc(struct timespec t, unsigned gran) +{ + /* + * Division is pretty slow so avoid it for common cases. + * Currently current_kernel_time() never returns better than + * jiffies resolution. Exploit that. + */ + if (gran <= jiffies_to_usecs(1) * 1000) { + /* nothing */ + } else if (gran == 1000000000) { + t.tv_nsec = 0; + } else { + t.tv_nsec -= t.tv_nsec % gran; + } + return t; +} +EXPORT_SYMBOL(timespec_trunc); + +/* + * mktime64 - Converts date to seconds. + * Converts Gregorian date to seconds since 1970-01-01 00:00:00. + * Assumes input in normal date format, i.e. 1980-12-31 23:59:59 + * => year=1980, mon=12, day=31, hour=23, min=59, sec=59. + * + * [For the Julian calendar (which was used in Russia before 1917, + * Britain & colonies before 1752, anywhere else before 1582, + * and is still in use by some communities) leave out the + * -year/100+year/400 terms, and add 10.] + * + * This algorithm was first published by Gauss (I think). + */ +time64_t mktime64(const unsigned int year0, const unsigned int mon0, + const unsigned int day, const unsigned int hour, + const unsigned int min, const unsigned int sec) +{ + unsigned int mon = mon0, year = year0; + + /* 1..12 -> 11,12,1..10 */ + if (0 >= (int) (mon -= 2)) { + mon += 12; /* Puts Feb last since it has leap day */ + year -= 1; + } + + return ((((time64_t) + (year/4 - year/100 + year/400 + 367*mon/12 + day) + + year*365 - 719499 + )*24 + hour /* now have hours */ + )*60 + min /* now have minutes */ + )*60 + sec; /* finally seconds */ +} +EXPORT_SYMBOL(mktime64); + +/** + * set_normalized_timespec - set timespec sec and nsec parts and normalize + * + * @ts: pointer to timespec variable to be set + * @sec: seconds to set + * @nsec: nanoseconds to set + * + * Set seconds and nanoseconds field of a timespec variable and + * normalize to the timespec storage format + * + * Note: The tv_nsec part is always in the range of + * 0 <= tv_nsec < NSEC_PER_SEC + * For negative values only the tv_sec field is negative ! + */ +void set_normalized_timespec(struct timespec *ts, time_t sec, s64 nsec) +{ + while (nsec >= NSEC_PER_SEC) { + /* + * The following asm() prevents the compiler from + * optimising this loop into a modulo operation. See + * also __iter_div_u64_rem() in include/linux/time.h + */ + asm("" : "+rm"(nsec)); + nsec -= NSEC_PER_SEC; + ++sec; + } + while (nsec < 0) { + asm("" : "+rm"(nsec)); + nsec += NSEC_PER_SEC; + --sec; + } + ts->tv_sec = sec; + ts->tv_nsec = nsec; +} +EXPORT_SYMBOL(set_normalized_timespec); + +/** + * ns_to_timespec - Convert nanoseconds to timespec + * @nsec: the nanoseconds value to be converted + * + * Returns the timespec representation of the nsec parameter. + */ +struct timespec ns_to_timespec(const s64 nsec) +{ + struct timespec ts; + s32 rem; + + if (!nsec) + return (struct timespec) {0, 0}; + + ts.tv_sec = div_s64_rem(nsec, NSEC_PER_SEC, &rem); + if (unlikely(rem < 0)) { + ts.tv_sec--; + rem += NSEC_PER_SEC; + } + ts.tv_nsec = rem; + + return ts; +} +EXPORT_SYMBOL(ns_to_timespec); + +/** + * ns_to_timeval - Convert nanoseconds to timeval + * @nsec: the nanoseconds value to be converted + * + * Returns the timeval representation of the nsec parameter. + */ +struct timeval ns_to_timeval(const s64 nsec) +{ + struct timespec ts = ns_to_timespec(nsec); + struct timeval tv; + + tv.tv_sec = ts.tv_sec; + tv.tv_usec = (suseconds_t) ts.tv_nsec / 1000; + + return tv; +} +EXPORT_SYMBOL(ns_to_timeval); + +#if BITS_PER_LONG == 32 +/** + * set_normalized_timespec - set timespec sec and nsec parts and normalize + * + * @ts: pointer to timespec variable to be set + * @sec: seconds to set + * @nsec: nanoseconds to set + * + * Set seconds and nanoseconds field of a timespec variable and + * normalize to the timespec storage format + * + * Note: The tv_nsec part is always in the range of + * 0 <= tv_nsec < NSEC_PER_SEC + * For negative values only the tv_sec field is negative ! + */ +void set_normalized_timespec64(struct timespec64 *ts, time64_t sec, s64 nsec) +{ + while (nsec >= NSEC_PER_SEC) { + /* + * The following asm() prevents the compiler from + * optimising this loop into a modulo operation. See + * also __iter_div_u64_rem() in include/linux/time.h + */ + asm("" : "+rm"(nsec)); + nsec -= NSEC_PER_SEC; + ++sec; + } + while (nsec < 0) { + asm("" : "+rm"(nsec)); + nsec += NSEC_PER_SEC; + --sec; + } + ts->tv_sec = sec; + ts->tv_nsec = nsec; +} +EXPORT_SYMBOL(set_normalized_timespec64); + +/** + * ns_to_timespec64 - Convert nanoseconds to timespec64 + * @nsec: the nanoseconds value to be converted + * + * Returns the timespec64 representation of the nsec parameter. + */ +struct timespec64 ns_to_timespec64(const s64 nsec) +{ + struct timespec64 ts; + s32 rem; + + if (!nsec) + return (struct timespec64) {0, 0}; + + ts.tv_sec = div_s64_rem(nsec, NSEC_PER_SEC, &rem); + if (unlikely(rem < 0)) { + ts.tv_sec--; + rem += NSEC_PER_SEC; + } + ts.tv_nsec = rem; + + return ts; +} +EXPORT_SYMBOL(ns_to_timespec64); +#endif +/* + * When we convert to jiffies then we interpret incoming values + * the following way: + * + * - negative values mean 'infinite timeout' (MAX_JIFFY_OFFSET) + * + * - 'too large' values [that would result in larger than + * MAX_JIFFY_OFFSET values] mean 'infinite timeout' too. + * + * - all other values are converted to jiffies by either multiplying + * the input value by a factor or dividing it with a factor + * + * We must also be careful about 32-bit overflows. + */ +unsigned long msecs_to_jiffies(const unsigned int m) +{ + /* + * Negative value, means infinite timeout: + */ + if ((int)m < 0) + return MAX_JIFFY_OFFSET; + +#if HZ <= MSEC_PER_SEC && !(MSEC_PER_SEC % HZ) + /* + * HZ is equal to or smaller than 1000, and 1000 is a nice + * round multiple of HZ, divide with the factor between them, + * but round upwards: + */ + return (m + (MSEC_PER_SEC / HZ) - 1) / (MSEC_PER_SEC / HZ); +#elif HZ > MSEC_PER_SEC && !(HZ % MSEC_PER_SEC) + /* + * HZ is larger than 1000, and HZ is a nice round multiple of + * 1000 - simply multiply with the factor between them. + * + * But first make sure the multiplication result cannot + * overflow: + */ + if (m > jiffies_to_msecs(MAX_JIFFY_OFFSET)) + return MAX_JIFFY_OFFSET; + + return m * (HZ / MSEC_PER_SEC); +#else + /* + * Generic case - multiply, round and divide. But first + * check that if we are doing a net multiplication, that + * we wouldn't overflow: + */ + if (HZ > MSEC_PER_SEC && m > jiffies_to_msecs(MAX_JIFFY_OFFSET)) + return MAX_JIFFY_OFFSET; + + return (MSEC_TO_HZ_MUL32 * m + MSEC_TO_HZ_ADJ32) + >> MSEC_TO_HZ_SHR32; +#endif +} +EXPORT_SYMBOL(msecs_to_jiffies); + +unsigned long usecs_to_jiffies(const unsigned int u) +{ + if (u > jiffies_to_usecs(MAX_JIFFY_OFFSET)) + return MAX_JIFFY_OFFSET; +#if HZ <= USEC_PER_SEC && !(USEC_PER_SEC % HZ) + return (u + (USEC_PER_SEC / HZ) - 1) / (USEC_PER_SEC / HZ); +#elif HZ > USEC_PER_SEC && !(HZ % USEC_PER_SEC) + return u * (HZ / USEC_PER_SEC); +#else + return (USEC_TO_HZ_MUL32 * u + USEC_TO_HZ_ADJ32) + >> USEC_TO_HZ_SHR32; +#endif +} +EXPORT_SYMBOL(usecs_to_jiffies); + +/* + * The TICK_NSEC - 1 rounds up the value to the next resolution. Note + * that a remainder subtract here would not do the right thing as the + * resolution values don't fall on second boundries. I.e. the line: + * nsec -= nsec % TICK_NSEC; is NOT a correct resolution rounding. + * Note that due to the small error in the multiplier here, this + * rounding is incorrect for sufficiently large values of tv_nsec, but + * well formed timespecs should have tv_nsec < NSEC_PER_SEC, so we're + * OK. + * + * Rather, we just shift the bits off the right. + * + * The >> (NSEC_JIFFIE_SC - SEC_JIFFIE_SC) converts the scaled nsec + * value to a scaled second value. + */ +static unsigned long +__timespec_to_jiffies(unsigned long sec, long nsec) +{ + nsec = nsec + TICK_NSEC - 1; + + if (sec >= MAX_SEC_IN_JIFFIES){ + sec = MAX_SEC_IN_JIFFIES; + nsec = 0; + } + return (((u64)sec * SEC_CONVERSION) + + (((u64)nsec * NSEC_CONVERSION) >> + (NSEC_JIFFIE_SC - SEC_JIFFIE_SC))) >> SEC_JIFFIE_SC; + +} + +unsigned long +timespec_to_jiffies(const struct timespec *value) +{ + return __timespec_to_jiffies(value->tv_sec, value->tv_nsec); +} + +EXPORT_SYMBOL(timespec_to_jiffies); + +void +jiffies_to_timespec(const unsigned long jiffies, struct timespec *value) +{ + /* + * Convert jiffies to nanoseconds and separate with + * one divide. + */ + u32 rem; + value->tv_sec = div_u64_rem((u64)jiffies * TICK_NSEC, + NSEC_PER_SEC, &rem); + value->tv_nsec = rem; +} +EXPORT_SYMBOL(jiffies_to_timespec); + +/* + * We could use a similar algorithm to timespec_to_jiffies (with a + * different multiplier for usec instead of nsec). But this has a + * problem with rounding: we can't exactly add TICK_NSEC - 1 to the + * usec value, since it's not necessarily integral. + * + * We could instead round in the intermediate scaled representation + * (i.e. in units of 1/2^(large scale) jiffies) but that's also + * perilous: the scaling introduces a small positive error, which + * combined with a division-rounding-upward (i.e. adding 2^(scale) - 1 + * units to the intermediate before shifting) leads to accidental + * overflow and overestimates. + * + * At the cost of one additional multiplication by a constant, just + * use the timespec implementation. + */ +unsigned long +timeval_to_jiffies(const struct timeval *value) +{ + return __timespec_to_jiffies(value->tv_sec, + value->tv_usec * NSEC_PER_USEC); +} +EXPORT_SYMBOL(timeval_to_jiffies); + +void jiffies_to_timeval(const unsigned long jiffies, struct timeval *value) +{ + /* + * Convert jiffies to nanoseconds and separate with + * one divide. + */ + u32 rem; + + value->tv_sec = div_u64_rem((u64)jiffies * TICK_NSEC, + NSEC_PER_SEC, &rem); + value->tv_usec = rem / NSEC_PER_USEC; +} +EXPORT_SYMBOL(jiffies_to_timeval); + +/* + * Convert jiffies/jiffies_64 to clock_t and back. + */ +clock_t jiffies_to_clock_t(unsigned long x) +{ +#if (TICK_NSEC % (NSEC_PER_SEC / USER_HZ)) == 0 +# if HZ < USER_HZ + return x * (USER_HZ / HZ); +# else + return x / (HZ / USER_HZ); +# endif +#else + return div_u64((u64)x * TICK_NSEC, NSEC_PER_SEC / USER_HZ); +#endif +} +EXPORT_SYMBOL(jiffies_to_clock_t); + +unsigned long clock_t_to_jiffies(unsigned long x) +{ +#if (HZ % USER_HZ)==0 + if (x >= ~0UL / (HZ / USER_HZ)) + return ~0UL; + return x * (HZ / USER_HZ); +#else + /* Don't worry about loss of precision here .. */ + if (x >= ~0UL / HZ * USER_HZ) + return ~0UL; + + /* .. but do try to contain it here */ + return div_u64((u64)x * HZ, USER_HZ); +#endif +} +EXPORT_SYMBOL(clock_t_to_jiffies); + +u64 jiffies_64_to_clock_t(u64 x) +{ +#if (TICK_NSEC % (NSEC_PER_SEC / USER_HZ)) == 0 +# if HZ < USER_HZ + x = div_u64(x * USER_HZ, HZ); +# elif HZ > USER_HZ + x = div_u64(x, HZ / USER_HZ); +# else + /* Nothing to do */ +# endif +#else + /* + * There are better ways that don't overflow early, + * but even this doesn't overflow in hundreds of years + * in 64 bits, so.. + */ + x = div_u64(x * TICK_NSEC, (NSEC_PER_SEC / USER_HZ)); +#endif + return x; +} +EXPORT_SYMBOL(jiffies_64_to_clock_t); + +u64 nsec_to_clock_t(u64 x) +{ +#if (NSEC_PER_SEC % USER_HZ) == 0 + return div_u64(x, NSEC_PER_SEC / USER_HZ); +#elif (USER_HZ % 512) == 0 + return div_u64(x * USER_HZ / 512, NSEC_PER_SEC / 512); +#else + /* + * max relative error 5.7e-8 (1.8s per year) for USER_HZ <= 1024, + * overflow after 64.99 years. + * exact for HZ=60, 72, 90, 120, 144, 180, 300, 600, 900, ... + */ + return div_u64(x * 9, (9ull * NSEC_PER_SEC + (USER_HZ / 2)) / USER_HZ); +#endif +} + +/** + * nsecs_to_jiffies64 - Convert nsecs in u64 to jiffies64 + * + * @n: nsecs in u64 + * + * Unlike {m,u}secs_to_jiffies, type of input is not unsigned int but u64. + * And this doesn't return MAX_JIFFY_OFFSET since this function is designed + * for scheduler, not for use in device drivers to calculate timeout value. + * + * note: + * NSEC_PER_SEC = 10^9 = (5^9 * 2^9) = (1953125 * 512) + * ULLONG_MAX ns = 18446744073.709551615 secs = about 584 years + */ +u64 nsecs_to_jiffies64(u64 n) +{ +#if (NSEC_PER_SEC % HZ) == 0 + /* Common case, HZ = 100, 128, 200, 250, 256, 500, 512, 1000 etc. */ + return div_u64(n, NSEC_PER_SEC / HZ); +#elif (HZ % 512) == 0 + /* overflow after 292 years if HZ = 1024 */ + return div_u64(n * HZ / 512, NSEC_PER_SEC / 512); +#else + /* + * Generic case - optimized for cases where HZ is a multiple of 3. + * overflow after 64.99 years, exact for HZ = 60, 72, 90, 120 etc. + */ + return div_u64(n * 9, (9ull * NSEC_PER_SEC + HZ / 2) / HZ); +#endif +} +EXPORT_SYMBOL(nsecs_to_jiffies64); + +/** + * nsecs_to_jiffies - Convert nsecs in u64 to jiffies + * + * @n: nsecs in u64 + * + * Unlike {m,u}secs_to_jiffies, type of input is not unsigned int but u64. + * And this doesn't return MAX_JIFFY_OFFSET since this function is designed + * for scheduler, not for use in device drivers to calculate timeout value. + * + * note: + * NSEC_PER_SEC = 10^9 = (5^9 * 2^9) = (1953125 * 512) + * ULLONG_MAX ns = 18446744073.709551615 secs = about 584 years + */ +unsigned long nsecs_to_jiffies(u64 n) +{ + return (unsigned long)nsecs_to_jiffies64(n); +} +EXPORT_SYMBOL_GPL(nsecs_to_jiffies); + +/* + * Add two timespec values and do a safety check for overflow. + * It's assumed that both values are valid (>= 0) + */ +struct timespec timespec_add_safe(const struct timespec lhs, + const struct timespec rhs) +{ + struct timespec res; + + set_normalized_timespec(&res, lhs.tv_sec + rhs.tv_sec, + lhs.tv_nsec + rhs.tv_nsec); + + if (res.tv_sec < lhs.tv_sec || res.tv_sec < rhs.tv_sec) + res.tv_sec = TIME_T_MAX; + + return res; +} diff --git a/kernel/kernel/time/timeconst.bc b/kernel/kernel/time/timeconst.bc new file mode 100644 index 000000000..511bdf2ca --- /dev/null +++ b/kernel/kernel/time/timeconst.bc @@ -0,0 +1,108 @@ +scale=0 + +define gcd(a,b) { + auto t; + while (b) { + t = b; + b = a % b; + a = t; + } + return a; +} + +/* Division by reciprocal multiplication. */ +define fmul(b,n,d) { + return (2^b*n+d-1)/d; +} + +/* Adjustment factor when a ceiling value is used. Use as: + (imul * n) + (fmulxx * n + fadjxx) >> xx) */ +define fadj(b,n,d) { + auto v; + d = d/gcd(n,d); + v = 2^b*(d-1)/d; + return v; +} + +/* Compute the appropriate mul/adj values as well as a shift count, + which brings the mul value into the range 2^b-1 <= x < 2^b. Such + a shift value will be correct in the signed integer range and off + by at most one in the upper half of the unsigned range. */ +define fmuls(b,n,d) { + auto s, m; + for (s = 0; 1; s++) { + m = fmul(s,n,d); + if (m >= 2^(b-1)) + return s; + } + return 0; +} + +define timeconst(hz) { + print "/* Automatically generated by kernel/timeconst.bc */\n" + print "/* Time conversion constants for HZ == ", hz, " */\n" + print "\n" + + print "#ifndef KERNEL_TIMECONST_H\n" + print "#define KERNEL_TIMECONST_H\n\n" + + print "#include \n" + print "#include \n\n" + + print "#if HZ != ", hz, "\n" + print "#error \qkernel/timeconst.h has the wrong HZ value!\q\n" + print "#endif\n\n" + + if (hz < 2) { + print "#error Totally bogus HZ value!\n" + } else { + s=fmuls(32,1000,hz) + obase=16 + print "#define HZ_TO_MSEC_MUL32\tU64_C(0x", fmul(s,1000,hz), ")\n" + print "#define HZ_TO_MSEC_ADJ32\tU64_C(0x", fadj(s,1000,hz), ")\n" + obase=10 + print "#define HZ_TO_MSEC_SHR32\t", s, "\n" + + s=fmuls(32,hz,1000) + obase=16 + print "#define MSEC_TO_HZ_MUL32\tU64_C(0x", fmul(s,hz,1000), ")\n" + print "#define MSEC_TO_HZ_ADJ32\tU64_C(0x", fadj(s,hz,1000), ")\n" + obase=10 + print "#define MSEC_TO_HZ_SHR32\t", s, "\n" + + obase=10 + cd=gcd(hz,1000) + print "#define HZ_TO_MSEC_NUM\t\t", 1000/cd, "\n" + print "#define HZ_TO_MSEC_DEN\t\t", hz/cd, "\n" + print "#define MSEC_TO_HZ_NUM\t\t", hz/cd, "\n" + print "#define MSEC_TO_HZ_DEN\t\t", 1000/cd, "\n" + print "\n" + + s=fmuls(32,1000000,hz) + obase=16 + print "#define HZ_TO_USEC_MUL32\tU64_C(0x", fmul(s,1000000,hz), ")\n" + print "#define HZ_TO_USEC_ADJ32\tU64_C(0x", fadj(s,1000000,hz), ")\n" + obase=10 + print "#define HZ_TO_USEC_SHR32\t", s, "\n" + + s=fmuls(32,hz,1000000) + obase=16 + print "#define USEC_TO_HZ_MUL32\tU64_C(0x", fmul(s,hz,1000000), ")\n" + print "#define USEC_TO_HZ_ADJ32\tU64_C(0x", fadj(s,hz,1000000), ")\n" + obase=10 + print "#define USEC_TO_HZ_SHR32\t", s, "\n" + + obase=10 + cd=gcd(hz,1000000) + print "#define HZ_TO_USEC_NUM\t\t", 1000000/cd, "\n" + print "#define HZ_TO_USEC_DEN\t\t", hz/cd, "\n" + print "#define USEC_TO_HZ_NUM\t\t", hz/cd, "\n" + print "#define USEC_TO_HZ_DEN\t\t", 1000000/cd, "\n" + print "\n" + + print "#endif /* KERNEL_TIMECONST_H */\n" + } + halt +} + +timeconst(hz) diff --git a/kernel/kernel/time/timeconv.c b/kernel/kernel/time/timeconv.c new file mode 100644 index 000000000..86628e755 --- /dev/null +++ b/kernel/kernel/time/timeconv.c @@ -0,0 +1,127 @@ +/* + * Copyright (C) 1993, 1994, 1995, 1996, 1997 Free Software Foundation, Inc. + * This file is part of the GNU C Library. + * Contributed by Paul Eggert (eggert@twinsun.com). + * + * The GNU C Library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Library General Public License as + * published by the Free Software Foundation; either version 2 of the + * License, or (at your option) any later version. + * + * The GNU C Library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Library General Public License for more details. + * + * You should have received a copy of the GNU Library General Public + * License along with the GNU C Library; see the file COPYING.LIB. If not, + * write to the Free Software Foundation, Inc., 59 Temple Place - Suite 330, + * Boston, MA 02111-1307, USA. + */ + +/* + * Converts the calendar time to broken-down time representation + * Based on code from glibc-2.6 + * + * 2009-7-14: + * Moved from glibc-2.6 to kernel by Zhaolei + */ + +#include +#include + +/* + * Nonzero if YEAR is a leap year (every 4 years, + * except every 100th isn't, and every 400th is). + */ +static int __isleap(long year) +{ + return (year) % 4 == 0 && ((year) % 100 != 0 || (year) % 400 == 0); +} + +/* do a mathdiv for long type */ +static long math_div(long a, long b) +{ + return a / b - (a % b < 0); +} + +/* How many leap years between y1 and y2, y1 must less or equal to y2 */ +static long leaps_between(long y1, long y2) +{ + long leaps1 = math_div(y1 - 1, 4) - math_div(y1 - 1, 100) + + math_div(y1 - 1, 400); + long leaps2 = math_div(y2 - 1, 4) - math_div(y2 - 1, 100) + + math_div(y2 - 1, 400); + return leaps2 - leaps1; +} + +/* How many days come before each month (0-12). */ +static const unsigned short __mon_yday[2][13] = { + /* Normal years. */ + {0, 31, 59, 90, 120, 151, 181, 212, 243, 273, 304, 334, 365}, + /* Leap years. */ + {0, 31, 60, 91, 121, 152, 182, 213, 244, 274, 305, 335, 366} +}; + +#define SECS_PER_HOUR (60 * 60) +#define SECS_PER_DAY (SECS_PER_HOUR * 24) + +/** + * time_to_tm - converts the calendar time to local broken-down time + * + * @totalsecs the number of seconds elapsed since 00:00:00 on January 1, 1970, + * Coordinated Universal Time (UTC). + * @offset offset seconds adding to totalsecs. + * @result pointer to struct tm variable to receive broken-down time + */ +void time_to_tm(time_t totalsecs, int offset, struct tm *result) +{ + long days, rem, y; + const unsigned short *ip; + + days = totalsecs / SECS_PER_DAY; + rem = totalsecs % SECS_PER_DAY; + rem += offset; + while (rem < 0) { + rem += SECS_PER_DAY; + --days; + } + while (rem >= SECS_PER_DAY) { + rem -= SECS_PER_DAY; + ++days; + } + + result->tm_hour = rem / SECS_PER_HOUR; + rem %= SECS_PER_HOUR; + result->tm_min = rem / 60; + result->tm_sec = rem % 60; + + /* January 1, 1970 was a Thursday. */ + result->tm_wday = (4 + days) % 7; + if (result->tm_wday < 0) + result->tm_wday += 7; + + y = 1970; + + while (days < 0 || days >= (__isleap(y) ? 366 : 365)) { + /* Guess a corrected year, assuming 365 days per year. */ + long yg = y + math_div(days, 365); + + /* Adjust DAYS and Y to match the guessed year. */ + days -= (yg - y) * 365 + leaps_between(y, yg); + y = yg; + } + + result->tm_year = y - 1900; + + result->tm_yday = days; + + ip = __mon_yday[__isleap(y)]; + for (y = 11; days < ip[y]; y--) + continue; + days -= ip[y]; + + result->tm_mon = y; + result->tm_mday = days + 1; +} +EXPORT_SYMBOL(time_to_tm); diff --git a/kernel/kernel/time/timecounter.c b/kernel/kernel/time/timecounter.c new file mode 100644 index 000000000..4687b3104 --- /dev/null +++ b/kernel/kernel/time/timecounter.c @@ -0,0 +1,112 @@ +/* + * linux/kernel/time/timecounter.c + * + * based on code that migrated away from + * linux/kernel/time/clocksource.c + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#include +#include + +void timecounter_init(struct timecounter *tc, + const struct cyclecounter *cc, + u64 start_tstamp) +{ + tc->cc = cc; + tc->cycle_last = cc->read(cc); + tc->nsec = start_tstamp; + tc->mask = (1ULL << cc->shift) - 1; + tc->frac = 0; +} +EXPORT_SYMBOL_GPL(timecounter_init); + +/** + * timecounter_read_delta - get nanoseconds since last call of this function + * @tc: Pointer to time counter + * + * When the underlying cycle counter runs over, this will be handled + * correctly as long as it does not run over more than once between + * calls. + * + * The first call to this function for a new time counter initializes + * the time tracking and returns an undefined result. + */ +static u64 timecounter_read_delta(struct timecounter *tc) +{ + cycle_t cycle_now, cycle_delta; + u64 ns_offset; + + /* read cycle counter: */ + cycle_now = tc->cc->read(tc->cc); + + /* calculate the delta since the last timecounter_read_delta(): */ + cycle_delta = (cycle_now - tc->cycle_last) & tc->cc->mask; + + /* convert to nanoseconds: */ + ns_offset = cyclecounter_cyc2ns(tc->cc, cycle_delta, + tc->mask, &tc->frac); + + /* update time stamp of timecounter_read_delta() call: */ + tc->cycle_last = cycle_now; + + return ns_offset; +} + +u64 timecounter_read(struct timecounter *tc) +{ + u64 nsec; + + /* increment time by nanoseconds since last call */ + nsec = timecounter_read_delta(tc); + nsec += tc->nsec; + tc->nsec = nsec; + + return nsec; +} +EXPORT_SYMBOL_GPL(timecounter_read); + +/* + * This is like cyclecounter_cyc2ns(), but it is used for computing a + * time previous to the time stored in the cycle counter. + */ +static u64 cc_cyc2ns_backwards(const struct cyclecounter *cc, + cycle_t cycles, u64 mask, u64 frac) +{ + u64 ns = (u64) cycles; + + ns = ((ns * cc->mult) - frac) >> cc->shift; + + return ns; +} + +u64 timecounter_cyc2time(struct timecounter *tc, + cycle_t cycle_tstamp) +{ + u64 delta = (cycle_tstamp - tc->cycle_last) & tc->cc->mask; + u64 nsec = tc->nsec, frac = tc->frac; + + /* + * Instead of always treating cycle_tstamp as more recent + * than tc->cycle_last, detect when it is too far in the + * future and treat it as old time stamp instead. + */ + if (delta > tc->cc->mask / 2) { + delta = (tc->cycle_last - cycle_tstamp) & tc->cc->mask; + nsec -= cc_cyc2ns_backwards(tc->cc, delta, tc->mask, frac); + } else { + nsec += cyclecounter_cyc2ns(tc->cc, delta, tc->mask, &frac); + } + + return nsec; +} +EXPORT_SYMBOL_GPL(timecounter_cyc2time); diff --git a/kernel/kernel/time/timekeeping.c b/kernel/kernel/time/timekeeping.c new file mode 100644 index 000000000..17d4a8933 --- /dev/null +++ b/kernel/kernel/time/timekeeping.c @@ -0,0 +1,2074 @@ +/* + * linux/kernel/time/timekeeping.c + * + * Kernel timekeeping code and accessor functions + * + * This code was moved from linux/kernel/timer.c. + * Please see that file for copyright and history logs. + * + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "tick-internal.h" +#include "ntp_internal.h" +#include "timekeeping_internal.h" + +#define TK_CLEAR_NTP (1 << 0) +#define TK_MIRROR (1 << 1) +#define TK_CLOCK_WAS_SET (1 << 2) + +/* + * The most important data for readout fits into a single 64 byte + * cache line. + */ +static struct { + seqcount_t seq; + struct timekeeper timekeeper; +} tk_core ____cacheline_aligned; + +static DEFINE_RAW_SPINLOCK(timekeeper_lock); +static struct timekeeper shadow_timekeeper; + +/** + * struct tk_fast - NMI safe timekeeper + * @seq: Sequence counter for protecting updates. The lowest bit + * is the index for the tk_read_base array + * @base: tk_read_base array. Access is indexed by the lowest bit of + * @seq. + * + * See @update_fast_timekeeper() below. + */ +struct tk_fast { + seqcount_t seq; + struct tk_read_base base[2]; +}; + +static struct tk_fast tk_fast_mono ____cacheline_aligned; +static struct tk_fast tk_fast_raw ____cacheline_aligned; + +/* flag for if timekeeping is suspended */ +int __read_mostly timekeeping_suspended; + +static inline void tk_normalize_xtime(struct timekeeper *tk) +{ + while (tk->tkr_mono.xtime_nsec >= ((u64)NSEC_PER_SEC << tk->tkr_mono.shift)) { + tk->tkr_mono.xtime_nsec -= (u64)NSEC_PER_SEC << tk->tkr_mono.shift; + tk->xtime_sec++; + } +} + +static inline struct timespec64 tk_xtime(struct timekeeper *tk) +{ + struct timespec64 ts; + + ts.tv_sec = tk->xtime_sec; + ts.tv_nsec = (long)(tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift); + return ts; +} + +static void tk_set_xtime(struct timekeeper *tk, const struct timespec64 *ts) +{ + tk->xtime_sec = ts->tv_sec; + tk->tkr_mono.xtime_nsec = (u64)ts->tv_nsec << tk->tkr_mono.shift; +} + +static void tk_xtime_add(struct timekeeper *tk, const struct timespec64 *ts) +{ + tk->xtime_sec += ts->tv_sec; + tk->tkr_mono.xtime_nsec += (u64)ts->tv_nsec << tk->tkr_mono.shift; + tk_normalize_xtime(tk); +} + +static void tk_set_wall_to_mono(struct timekeeper *tk, struct timespec64 wtm) +{ + struct timespec64 tmp; + + /* + * Verify consistency of: offset_real = -wall_to_monotonic + * before modifying anything + */ + set_normalized_timespec64(&tmp, -tk->wall_to_monotonic.tv_sec, + -tk->wall_to_monotonic.tv_nsec); + WARN_ON_ONCE(tk->offs_real.tv64 != timespec64_to_ktime(tmp).tv64); + tk->wall_to_monotonic = wtm; + set_normalized_timespec64(&tmp, -wtm.tv_sec, -wtm.tv_nsec); + tk->offs_real = timespec64_to_ktime(tmp); + tk->offs_tai = ktime_add(tk->offs_real, ktime_set(tk->tai_offset, 0)); +} + +static inline void tk_update_sleep_time(struct timekeeper *tk, ktime_t delta) +{ + tk->offs_boot = ktime_add(tk->offs_boot, delta); +} + +#ifdef CONFIG_DEBUG_TIMEKEEPING +#define WARNING_FREQ (HZ*300) /* 5 minute rate-limiting */ +/* + * These simple flag variables are managed + * without locks, which is racy, but ok since + * we don't really care about being super + * precise about how many events were seen, + * just that a problem was observed. + */ +static int timekeeping_underflow_seen; +static int timekeeping_overflow_seen; + +/* last_warning is only modified under the timekeeping lock */ +static long timekeeping_last_warning; + +static void timekeeping_check_update(struct timekeeper *tk, cycle_t offset) +{ + + cycle_t max_cycles = tk->tkr_mono.clock->max_cycles; + const char *name = tk->tkr_mono.clock->name; + + if (offset > max_cycles) { + printk_deferred("WARNING: timekeeping: Cycle offset (%lld) is larger than allowed by the '%s' clock's max_cycles value (%lld): time overflow danger\n", + offset, name, max_cycles); + printk_deferred(" timekeeping: Your kernel is sick, but tries to cope by capping time updates\n"); + } else { + if (offset > (max_cycles >> 1)) { + printk_deferred("INFO: timekeeping: Cycle offset (%lld) is larger than the the '%s' clock's 50%% safety margin (%lld)\n", + offset, name, max_cycles >> 1); + printk_deferred(" timekeeping: Your kernel is still fine, but is feeling a bit nervous\n"); + } + } + + if (timekeeping_underflow_seen) { + if (jiffies - timekeeping_last_warning > WARNING_FREQ) { + printk_deferred("WARNING: Underflow in clocksource '%s' observed, time update ignored.\n", name); + printk_deferred(" Please report this, consider using a different clocksource, if possible.\n"); + printk_deferred(" Your kernel is probably still fine.\n"); + timekeeping_last_warning = jiffies; + } + timekeeping_underflow_seen = 0; + } + + if (timekeeping_overflow_seen) { + if (jiffies - timekeeping_last_warning > WARNING_FREQ) { + printk_deferred("WARNING: Overflow in clocksource '%s' observed, time update capped.\n", name); + printk_deferred(" Please report this, consider using a different clocksource, if possible.\n"); + printk_deferred(" Your kernel is probably still fine.\n"); + timekeeping_last_warning = jiffies; + } + timekeeping_overflow_seen = 0; + } +} + +static inline cycle_t timekeeping_get_delta(struct tk_read_base *tkr) +{ + cycle_t now, last, mask, max, delta; + unsigned int seq; + + /* + * Since we're called holding a seqlock, the data may shift + * under us while we're doing the calculation. This can cause + * false positives, since we'd note a problem but throw the + * results away. So nest another seqlock here to atomically + * grab the points we are checking with. + */ + do { + seq = read_seqcount_begin(&tk_core.seq); + now = tkr->read(tkr->clock); + last = tkr->cycle_last; + mask = tkr->mask; + max = tkr->clock->max_cycles; + } while (read_seqcount_retry(&tk_core.seq, seq)); + + delta = clocksource_delta(now, last, mask); + + /* + * Try to catch underflows by checking if we are seeing small + * mask-relative negative values. + */ + if (unlikely((~delta & mask) < (mask >> 3))) { + timekeeping_underflow_seen = 1; + delta = 0; + } + + /* Cap delta value to the max_cycles values to avoid mult overflows */ + if (unlikely(delta > max)) { + timekeeping_overflow_seen = 1; + delta = tkr->clock->max_cycles; + } + + return delta; +} +#else +static inline void timekeeping_check_update(struct timekeeper *tk, cycle_t offset) +{ +} +static inline cycle_t timekeeping_get_delta(struct tk_read_base *tkr) +{ + cycle_t cycle_now, delta; + + /* read clocksource */ + cycle_now = tkr->read(tkr->clock); + + /* calculate the delta since the last update_wall_time */ + delta = clocksource_delta(cycle_now, tkr->cycle_last, tkr->mask); + + return delta; +} +#endif + +/** + * tk_setup_internals - Set up internals to use clocksource clock. + * + * @tk: The target timekeeper to setup. + * @clock: Pointer to clocksource. + * + * Calculates a fixed cycle/nsec interval for a given clocksource/adjustment + * pair and interval request. + * + * Unless you're the timekeeping code, you should not be using this! + */ +static void tk_setup_internals(struct timekeeper *tk, struct clocksource *clock) +{ + cycle_t interval; + u64 tmp, ntpinterval; + struct clocksource *old_clock; + + old_clock = tk->tkr_mono.clock; + tk->tkr_mono.clock = clock; + tk->tkr_mono.read = clock->read; + tk->tkr_mono.mask = clock->mask; + tk->tkr_mono.cycle_last = tk->tkr_mono.read(clock); + + tk->tkr_raw.clock = clock; + tk->tkr_raw.read = clock->read; + tk->tkr_raw.mask = clock->mask; + tk->tkr_raw.cycle_last = tk->tkr_mono.cycle_last; + + /* Do the ns -> cycle conversion first, using original mult */ + tmp = NTP_INTERVAL_LENGTH; + tmp <<= clock->shift; + ntpinterval = tmp; + tmp += clock->mult/2; + do_div(tmp, clock->mult); + if (tmp == 0) + tmp = 1; + + interval = (cycle_t) tmp; + tk->cycle_interval = interval; + + /* Go back from cycles -> shifted ns */ + tk->xtime_interval = (u64) interval * clock->mult; + tk->xtime_remainder = ntpinterval - tk->xtime_interval; + tk->raw_interval = + ((u64) interval * clock->mult) >> clock->shift; + + /* if changing clocks, convert xtime_nsec shift units */ + if (old_clock) { + int shift_change = clock->shift - old_clock->shift; + if (shift_change < 0) + tk->tkr_mono.xtime_nsec >>= -shift_change; + else + tk->tkr_mono.xtime_nsec <<= shift_change; + } + tk->tkr_raw.xtime_nsec = 0; + + tk->tkr_mono.shift = clock->shift; + tk->tkr_raw.shift = clock->shift; + + tk->ntp_error = 0; + tk->ntp_error_shift = NTP_SCALE_SHIFT - clock->shift; + tk->ntp_tick = ntpinterval << tk->ntp_error_shift; + + /* + * The timekeeper keeps its own mult values for the currently + * active clocksource. These value will be adjusted via NTP + * to counteract clock drifting. + */ + tk->tkr_mono.mult = clock->mult; + tk->tkr_raw.mult = clock->mult; + tk->ntp_err_mult = 0; +} + +/* Timekeeper helper functions. */ + +#ifdef CONFIG_ARCH_USES_GETTIMEOFFSET +static u32 default_arch_gettimeoffset(void) { return 0; } +u32 (*arch_gettimeoffset)(void) = default_arch_gettimeoffset; +#else +static inline u32 arch_gettimeoffset(void) { return 0; } +#endif + +static inline s64 timekeeping_get_ns(struct tk_read_base *tkr) +{ + cycle_t delta; + s64 nsec; + + delta = timekeeping_get_delta(tkr); + + nsec = delta * tkr->mult + tkr->xtime_nsec; + nsec >>= tkr->shift; + + /* If arch requires, add in get_arch_timeoffset() */ + return nsec + arch_gettimeoffset(); +} + +/** + * update_fast_timekeeper - Update the fast and NMI safe monotonic timekeeper. + * @tkr: Timekeeping readout base from which we take the update + * + * We want to use this from any context including NMI and tracing / + * instrumenting the timekeeping code itself. + * + * So we handle this differently than the other timekeeping accessor + * functions which retry when the sequence count has changed. The + * update side does: + * + * smp_wmb(); <- Ensure that the last base[1] update is visible + * tkf->seq++; + * smp_wmb(); <- Ensure that the seqcount update is visible + * update(tkf->base[0], tkr); + * smp_wmb(); <- Ensure that the base[0] update is visible + * tkf->seq++; + * smp_wmb(); <- Ensure that the seqcount update is visible + * update(tkf->base[1], tkr); + * + * The reader side does: + * + * do { + * seq = tkf->seq; + * smp_rmb(); + * idx = seq & 0x01; + * now = now(tkf->base[idx]); + * smp_rmb(); + * } while (seq != tkf->seq) + * + * As long as we update base[0] readers are forced off to + * base[1]. Once base[0] is updated readers are redirected to base[0] + * and the base[1] update takes place. + * + * So if a NMI hits the update of base[0] then it will use base[1] + * which is still consistent. In the worst case this can result is a + * slightly wrong timestamp (a few nanoseconds). See + * @ktime_get_mono_fast_ns. + */ +static void update_fast_timekeeper(struct tk_read_base *tkr, struct tk_fast *tkf) +{ + struct tk_read_base *base = tkf->base; + + /* Force readers off to base[1] */ + raw_write_seqcount_latch(&tkf->seq); + + /* Update base[0] */ + memcpy(base, tkr, sizeof(*base)); + + /* Force readers back to base[0] */ + raw_write_seqcount_latch(&tkf->seq); + + /* Update base[1] */ + memcpy(base + 1, base, sizeof(*base)); +} + +/** + * ktime_get_mono_fast_ns - Fast NMI safe access to clock monotonic + * + * This timestamp is not guaranteed to be monotonic across an update. + * The timestamp is calculated by: + * + * now = base_mono + clock_delta * slope + * + * So if the update lowers the slope, readers who are forced to the + * not yet updated second array are still using the old steeper slope. + * + * tmono + * ^ + * | o n + * | o n + * | u + * | o + * |o + * |12345678---> reader order + * + * o = old slope + * u = update + * n = new slope + * + * So reader 6 will observe time going backwards versus reader 5. + * + * While other CPUs are likely to be able observe that, the only way + * for a CPU local observation is when an NMI hits in the middle of + * the update. Timestamps taken from that NMI context might be ahead + * of the following timestamps. Callers need to be aware of that and + * deal with it. + */ +static __always_inline u64 __ktime_get_fast_ns(struct tk_fast *tkf) +{ + struct tk_read_base *tkr; + unsigned int seq; + u64 now; + + do { + seq = raw_read_seqcount(&tkf->seq); + tkr = tkf->base + (seq & 0x01); + now = ktime_to_ns(tkr->base) + timekeeping_get_ns(tkr); + } while (read_seqcount_retry(&tkf->seq, seq)); + + return now; +} + +u64 ktime_get_mono_fast_ns(void) +{ + return __ktime_get_fast_ns(&tk_fast_mono); +} +EXPORT_SYMBOL_GPL(ktime_get_mono_fast_ns); + +u64 ktime_get_raw_fast_ns(void) +{ + return __ktime_get_fast_ns(&tk_fast_raw); +} +EXPORT_SYMBOL_GPL(ktime_get_raw_fast_ns); + +/* Suspend-time cycles value for halted fast timekeeper. */ +static cycle_t cycles_at_suspend; + +static cycle_t dummy_clock_read(struct clocksource *cs) +{ + return cycles_at_suspend; +} + +/** + * halt_fast_timekeeper - Prevent fast timekeeper from accessing clocksource. + * @tk: Timekeeper to snapshot. + * + * It generally is unsafe to access the clocksource after timekeeping has been + * suspended, so take a snapshot of the readout base of @tk and use it as the + * fast timekeeper's readout base while suspended. It will return the same + * number of cycles every time until timekeeping is resumed at which time the + * proper readout base for the fast timekeeper will be restored automatically. + */ +static void halt_fast_timekeeper(struct timekeeper *tk) +{ + static struct tk_read_base tkr_dummy; + struct tk_read_base *tkr = &tk->tkr_mono; + + memcpy(&tkr_dummy, tkr, sizeof(tkr_dummy)); + cycles_at_suspend = tkr->read(tkr->clock); + tkr_dummy.read = dummy_clock_read; + update_fast_timekeeper(&tkr_dummy, &tk_fast_mono); + + tkr = &tk->tkr_raw; + memcpy(&tkr_dummy, tkr, sizeof(tkr_dummy)); + tkr_dummy.read = dummy_clock_read; + update_fast_timekeeper(&tkr_dummy, &tk_fast_raw); +} + +#ifdef CONFIG_GENERIC_TIME_VSYSCALL_OLD + +static inline void update_vsyscall(struct timekeeper *tk) +{ + struct timespec xt, wm; + + xt = timespec64_to_timespec(tk_xtime(tk)); + wm = timespec64_to_timespec(tk->wall_to_monotonic); + update_vsyscall_old(&xt, &wm, tk->tkr_mono.clock, tk->tkr_mono.mult, + tk->tkr_mono.cycle_last); +} + +static inline void old_vsyscall_fixup(struct timekeeper *tk) +{ + s64 remainder; + + /* + * Store only full nanoseconds into xtime_nsec after rounding + * it up and add the remainder to the error difference. + * XXX - This is necessary to avoid small 1ns inconsistnecies caused + * by truncating the remainder in vsyscalls. However, it causes + * additional work to be done in timekeeping_adjust(). Once + * the vsyscall implementations are converted to use xtime_nsec + * (shifted nanoseconds), and CONFIG_GENERIC_TIME_VSYSCALL_OLD + * users are removed, this can be killed. + */ + remainder = tk->tkr_mono.xtime_nsec & ((1ULL << tk->tkr_mono.shift) - 1); + tk->tkr_mono.xtime_nsec -= remainder; + tk->tkr_mono.xtime_nsec += 1ULL << tk->tkr_mono.shift; + tk->ntp_error += remainder << tk->ntp_error_shift; + tk->ntp_error -= (1ULL << tk->tkr_mono.shift) << tk->ntp_error_shift; +} +#else +#define old_vsyscall_fixup(tk) +#endif + +static RAW_NOTIFIER_HEAD(pvclock_gtod_chain); + +static void update_pvclock_gtod(struct timekeeper *tk, bool was_set) +{ + raw_notifier_call_chain(&pvclock_gtod_chain, was_set, tk); +} + +/** + * pvclock_gtod_register_notifier - register a pvclock timedata update listener + */ +int pvclock_gtod_register_notifier(struct notifier_block *nb) +{ + struct timekeeper *tk = &tk_core.timekeeper; + unsigned long flags; + int ret; + + raw_spin_lock_irqsave(&timekeeper_lock, flags); + ret = raw_notifier_chain_register(&pvclock_gtod_chain, nb); + update_pvclock_gtod(tk, true); + raw_spin_unlock_irqrestore(&timekeeper_lock, flags); + + return ret; +} +EXPORT_SYMBOL_GPL(pvclock_gtod_register_notifier); + +/** + * pvclock_gtod_unregister_notifier - unregister a pvclock + * timedata update listener + */ +int pvclock_gtod_unregister_notifier(struct notifier_block *nb) +{ + unsigned long flags; + int ret; + + raw_spin_lock_irqsave(&timekeeper_lock, flags); + ret = raw_notifier_chain_unregister(&pvclock_gtod_chain, nb); + raw_spin_unlock_irqrestore(&timekeeper_lock, flags); + + return ret; +} +EXPORT_SYMBOL_GPL(pvclock_gtod_unregister_notifier); + +/* + * Update the ktime_t based scalar nsec members of the timekeeper + */ +static inline void tk_update_ktime_data(struct timekeeper *tk) +{ + u64 seconds; + u32 nsec; + + /* + * The xtime based monotonic readout is: + * nsec = (xtime_sec + wtm_sec) * 1e9 + wtm_nsec + now(); + * The ktime based monotonic readout is: + * nsec = base_mono + now(); + * ==> base_mono = (xtime_sec + wtm_sec) * 1e9 + wtm_nsec + */ + seconds = (u64)(tk->xtime_sec + tk->wall_to_monotonic.tv_sec); + nsec = (u32) tk->wall_to_monotonic.tv_nsec; + tk->tkr_mono.base = ns_to_ktime(seconds * NSEC_PER_SEC + nsec); + + /* Update the monotonic raw base */ + tk->tkr_raw.base = timespec64_to_ktime(tk->raw_time); + + /* + * The sum of the nanoseconds portions of xtime and + * wall_to_monotonic can be greater/equal one second. Take + * this into account before updating tk->ktime_sec. + */ + nsec += (u32)(tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift); + if (nsec >= NSEC_PER_SEC) + seconds++; + tk->ktime_sec = seconds; +} + +/* must hold timekeeper_lock */ +static void timekeeping_update(struct timekeeper *tk, unsigned int action) +{ + if (action & TK_CLEAR_NTP) { + tk->ntp_error = 0; + ntp_clear(); + } + + tk_update_ktime_data(tk); + + update_vsyscall(tk); + update_pvclock_gtod(tk, action & TK_CLOCK_WAS_SET); + + if (action & TK_MIRROR) + memcpy(&shadow_timekeeper, &tk_core.timekeeper, + sizeof(tk_core.timekeeper)); + + update_fast_timekeeper(&tk->tkr_mono, &tk_fast_mono); + update_fast_timekeeper(&tk->tkr_raw, &tk_fast_raw); +} + +/** + * timekeeping_forward_now - update clock to the current time + * + * Forward the current clock to update its state since the last call to + * update_wall_time(). This is useful before significant clock changes, + * as it avoids having to deal with this time offset explicitly. + */ +static void timekeeping_forward_now(struct timekeeper *tk) +{ + struct clocksource *clock = tk->tkr_mono.clock; + cycle_t cycle_now, delta; + s64 nsec; + + cycle_now = tk->tkr_mono.read(clock); + delta = clocksource_delta(cycle_now, tk->tkr_mono.cycle_last, tk->tkr_mono.mask); + tk->tkr_mono.cycle_last = cycle_now; + tk->tkr_raw.cycle_last = cycle_now; + + tk->tkr_mono.xtime_nsec += delta * tk->tkr_mono.mult; + + /* If arch requires, add in get_arch_timeoffset() */ + tk->tkr_mono.xtime_nsec += (u64)arch_gettimeoffset() << tk->tkr_mono.shift; + + tk_normalize_xtime(tk); + + nsec = clocksource_cyc2ns(delta, tk->tkr_raw.mult, tk->tkr_raw.shift); + timespec64_add_ns(&tk->raw_time, nsec); +} + +/** + * __getnstimeofday64 - Returns the time of day in a timespec64. + * @ts: pointer to the timespec to be set + * + * Updates the time of day in the timespec. + * Returns 0 on success, or -ve when suspended (timespec will be undefined). + */ +int __getnstimeofday64(struct timespec64 *ts) +{ + struct timekeeper *tk = &tk_core.timekeeper; + unsigned long seq; + s64 nsecs = 0; + + do { + seq = read_seqcount_begin(&tk_core.seq); + + ts->tv_sec = tk->xtime_sec; + nsecs = timekeeping_get_ns(&tk->tkr_mono); + + } while (read_seqcount_retry(&tk_core.seq, seq)); + + ts->tv_nsec = 0; + timespec64_add_ns(ts, nsecs); + + /* + * Do not bail out early, in case there were callers still using + * the value, even in the face of the WARN_ON. + */ + if (unlikely(timekeeping_suspended)) + return -EAGAIN; + return 0; +} +EXPORT_SYMBOL(__getnstimeofday64); + +/** + * getnstimeofday64 - Returns the time of day in a timespec64. + * @ts: pointer to the timespec64 to be set + * + * Returns the time of day in a timespec64 (WARN if suspended). + */ +void getnstimeofday64(struct timespec64 *ts) +{ + WARN_ON(__getnstimeofday64(ts)); +} +EXPORT_SYMBOL(getnstimeofday64); + +ktime_t ktime_get(void) +{ + struct timekeeper *tk = &tk_core.timekeeper; + unsigned int seq; + ktime_t base; + s64 nsecs; + + WARN_ON(timekeeping_suspended); + + do { + seq = read_seqcount_begin(&tk_core.seq); + base = tk->tkr_mono.base; + nsecs = timekeeping_get_ns(&tk->tkr_mono); + + } while (read_seqcount_retry(&tk_core.seq, seq)); + + return ktime_add_ns(base, nsecs); +} +EXPORT_SYMBOL_GPL(ktime_get); + +static ktime_t *offsets[TK_OFFS_MAX] = { + [TK_OFFS_REAL] = &tk_core.timekeeper.offs_real, + [TK_OFFS_BOOT] = &tk_core.timekeeper.offs_boot, + [TK_OFFS_TAI] = &tk_core.timekeeper.offs_tai, +}; + +ktime_t ktime_get_with_offset(enum tk_offsets offs) +{ + struct timekeeper *tk = &tk_core.timekeeper; + unsigned int seq; + ktime_t base, *offset = offsets[offs]; + s64 nsecs; + + WARN_ON(timekeeping_suspended); + + do { + seq = read_seqcount_begin(&tk_core.seq); + base = ktime_add(tk->tkr_mono.base, *offset); + nsecs = timekeeping_get_ns(&tk->tkr_mono); + + } while (read_seqcount_retry(&tk_core.seq, seq)); + + return ktime_add_ns(base, nsecs); + +} +EXPORT_SYMBOL_GPL(ktime_get_with_offset); + +/** + * ktime_mono_to_any() - convert mononotic time to any other time + * @tmono: time to convert. + * @offs: which offset to use + */ +ktime_t ktime_mono_to_any(ktime_t tmono, enum tk_offsets offs) +{ + ktime_t *offset = offsets[offs]; + unsigned long seq; + ktime_t tconv; + + do { + seq = read_seqcount_begin(&tk_core.seq); + tconv = ktime_add(tmono, *offset); + } while (read_seqcount_retry(&tk_core.seq, seq)); + + return tconv; +} +EXPORT_SYMBOL_GPL(ktime_mono_to_any); + +/** + * ktime_get_raw - Returns the raw monotonic time in ktime_t format + */ +ktime_t ktime_get_raw(void) +{ + struct timekeeper *tk = &tk_core.timekeeper; + unsigned int seq; + ktime_t base; + s64 nsecs; + + do { + seq = read_seqcount_begin(&tk_core.seq); + base = tk->tkr_raw.base; + nsecs = timekeeping_get_ns(&tk->tkr_raw); + + } while (read_seqcount_retry(&tk_core.seq, seq)); + + return ktime_add_ns(base, nsecs); +} +EXPORT_SYMBOL_GPL(ktime_get_raw); + +/** + * ktime_get_ts64 - get the monotonic clock in timespec64 format + * @ts: pointer to timespec variable + * + * The function calculates the monotonic clock from the realtime + * clock and the wall_to_monotonic offset and stores the result + * in normalized timespec64 format in the variable pointed to by @ts. + */ +void ktime_get_ts64(struct timespec64 *ts) +{ + struct timekeeper *tk = &tk_core.timekeeper; + struct timespec64 tomono; + s64 nsec; + unsigned int seq; + + WARN_ON(timekeeping_suspended); + + do { + seq = read_seqcount_begin(&tk_core.seq); + ts->tv_sec = tk->xtime_sec; + nsec = timekeeping_get_ns(&tk->tkr_mono); + tomono = tk->wall_to_monotonic; + + } while (read_seqcount_retry(&tk_core.seq, seq)); + + ts->tv_sec += tomono.tv_sec; + ts->tv_nsec = 0; + timespec64_add_ns(ts, nsec + tomono.tv_nsec); +} +EXPORT_SYMBOL_GPL(ktime_get_ts64); + +/** + * ktime_get_seconds - Get the seconds portion of CLOCK_MONOTONIC + * + * Returns the seconds portion of CLOCK_MONOTONIC with a single non + * serialized read. tk->ktime_sec is of type 'unsigned long' so this + * works on both 32 and 64 bit systems. On 32 bit systems the readout + * covers ~136 years of uptime which should be enough to prevent + * premature wrap arounds. + */ +time64_t ktime_get_seconds(void) +{ + struct timekeeper *tk = &tk_core.timekeeper; + + WARN_ON(timekeeping_suspended); + return tk->ktime_sec; +} +EXPORT_SYMBOL_GPL(ktime_get_seconds); + +/** + * ktime_get_real_seconds - Get the seconds portion of CLOCK_REALTIME + * + * Returns the wall clock seconds since 1970. This replaces the + * get_seconds() interface which is not y2038 safe on 32bit systems. + * + * For 64bit systems the fast access to tk->xtime_sec is preserved. On + * 32bit systems the access must be protected with the sequence + * counter to provide "atomic" access to the 64bit tk->xtime_sec + * value. + */ +time64_t ktime_get_real_seconds(void) +{ + struct timekeeper *tk = &tk_core.timekeeper; + time64_t seconds; + unsigned int seq; + + if (IS_ENABLED(CONFIG_64BIT)) + return tk->xtime_sec; + + do { + seq = read_seqcount_begin(&tk_core.seq); + seconds = tk->xtime_sec; + + } while (read_seqcount_retry(&tk_core.seq, seq)); + + return seconds; +} +EXPORT_SYMBOL_GPL(ktime_get_real_seconds); + +#ifdef CONFIG_NTP_PPS + +/** + * getnstime_raw_and_real - get day and raw monotonic time in timespec format + * @ts_raw: pointer to the timespec to be set to raw monotonic time + * @ts_real: pointer to the timespec to be set to the time of day + * + * This function reads both the time of day and raw monotonic time at the + * same time atomically and stores the resulting timestamps in timespec + * format. + */ +void getnstime_raw_and_real(struct timespec *ts_raw, struct timespec *ts_real) +{ + struct timekeeper *tk = &tk_core.timekeeper; + unsigned long seq; + s64 nsecs_raw, nsecs_real; + + WARN_ON_ONCE(timekeeping_suspended); + + do { + seq = read_seqcount_begin(&tk_core.seq); + + *ts_raw = timespec64_to_timespec(tk->raw_time); + ts_real->tv_sec = tk->xtime_sec; + ts_real->tv_nsec = 0; + + nsecs_raw = timekeeping_get_ns(&tk->tkr_raw); + nsecs_real = timekeeping_get_ns(&tk->tkr_mono); + + } while (read_seqcount_retry(&tk_core.seq, seq)); + + timespec_add_ns(ts_raw, nsecs_raw); + timespec_add_ns(ts_real, nsecs_real); +} +EXPORT_SYMBOL(getnstime_raw_and_real); + +#endif /* CONFIG_NTP_PPS */ + +/** + * do_gettimeofday - Returns the time of day in a timeval + * @tv: pointer to the timeval to be set + * + * NOTE: Users should be converted to using getnstimeofday() + */ +void do_gettimeofday(struct timeval *tv) +{ + struct timespec64 now; + + getnstimeofday64(&now); + tv->tv_sec = now.tv_sec; + tv->tv_usec = now.tv_nsec/1000; +} +EXPORT_SYMBOL(do_gettimeofday); + +/** + * do_settimeofday64 - Sets the time of day. + * @ts: pointer to the timespec64 variable containing the new time + * + * Sets the time of day to the new time and update NTP and notify hrtimers + */ +int do_settimeofday64(const struct timespec64 *ts) +{ + struct timekeeper *tk = &tk_core.timekeeper; + struct timespec64 ts_delta, xt; + unsigned long flags; + + if (!timespec64_valid_strict(ts)) + return -EINVAL; + + raw_spin_lock_irqsave(&timekeeper_lock, flags); + write_seqcount_begin(&tk_core.seq); + + timekeeping_forward_now(tk); + + xt = tk_xtime(tk); + ts_delta.tv_sec = ts->tv_sec - xt.tv_sec; + ts_delta.tv_nsec = ts->tv_nsec - xt.tv_nsec; + + tk_set_wall_to_mono(tk, timespec64_sub(tk->wall_to_monotonic, ts_delta)); + + tk_set_xtime(tk, ts); + + timekeeping_update(tk, TK_CLEAR_NTP | TK_MIRROR | TK_CLOCK_WAS_SET); + + write_seqcount_end(&tk_core.seq); + raw_spin_unlock_irqrestore(&timekeeper_lock, flags); + + /* signal hrtimers about time change */ + clock_was_set(); + + return 0; +} +EXPORT_SYMBOL(do_settimeofday64); + +/** + * timekeeping_inject_offset - Adds or subtracts from the current time. + * @tv: pointer to the timespec variable containing the offset + * + * Adds or subtracts an offset value from the current time. + */ +int timekeeping_inject_offset(struct timespec *ts) +{ + struct timekeeper *tk = &tk_core.timekeeper; + unsigned long flags; + struct timespec64 ts64, tmp; + int ret = 0; + + if ((unsigned long)ts->tv_nsec >= NSEC_PER_SEC) + return -EINVAL; + + ts64 = timespec_to_timespec64(*ts); + + raw_spin_lock_irqsave(&timekeeper_lock, flags); + write_seqcount_begin(&tk_core.seq); + + timekeeping_forward_now(tk); + + /* Make sure the proposed value is valid */ + tmp = timespec64_add(tk_xtime(tk), ts64); + if (!timespec64_valid_strict(&tmp)) { + ret = -EINVAL; + goto error; + } + + tk_xtime_add(tk, &ts64); + tk_set_wall_to_mono(tk, timespec64_sub(tk->wall_to_monotonic, ts64)); + +error: /* even if we error out, we forwarded the time, so call update */ + timekeeping_update(tk, TK_CLEAR_NTP | TK_MIRROR | TK_CLOCK_WAS_SET); + + write_seqcount_end(&tk_core.seq); + raw_spin_unlock_irqrestore(&timekeeper_lock, flags); + + /* signal hrtimers about time change */ + clock_was_set(); + + return ret; +} +EXPORT_SYMBOL(timekeeping_inject_offset); + + +/** + * timekeeping_get_tai_offset - Returns current TAI offset from UTC + * + */ +s32 timekeeping_get_tai_offset(void) +{ + struct timekeeper *tk = &tk_core.timekeeper; + unsigned int seq; + s32 ret; + + do { + seq = read_seqcount_begin(&tk_core.seq); + ret = tk->tai_offset; + } while (read_seqcount_retry(&tk_core.seq, seq)); + + return ret; +} + +/** + * __timekeeping_set_tai_offset - Lock free worker function + * + */ +static void __timekeeping_set_tai_offset(struct timekeeper *tk, s32 tai_offset) +{ + tk->tai_offset = tai_offset; + tk->offs_tai = ktime_add(tk->offs_real, ktime_set(tai_offset, 0)); +} + +/** + * timekeeping_set_tai_offset - Sets the current TAI offset from UTC + * + */ +void timekeeping_set_tai_offset(s32 tai_offset) +{ + struct timekeeper *tk = &tk_core.timekeeper; + unsigned long flags; + + raw_spin_lock_irqsave(&timekeeper_lock, flags); + write_seqcount_begin(&tk_core.seq); + __timekeeping_set_tai_offset(tk, tai_offset); + timekeeping_update(tk, TK_MIRROR | TK_CLOCK_WAS_SET); + write_seqcount_end(&tk_core.seq); + raw_spin_unlock_irqrestore(&timekeeper_lock, flags); + clock_was_set(); +} + +/** + * change_clocksource - Swaps clocksources if a new one is available + * + * Accumulates current time interval and initializes new clocksource + */ +static int change_clocksource(void *data) +{ + struct timekeeper *tk = &tk_core.timekeeper; + struct clocksource *new, *old; + unsigned long flags; + + new = (struct clocksource *) data; + + raw_spin_lock_irqsave(&timekeeper_lock, flags); + write_seqcount_begin(&tk_core.seq); + + timekeeping_forward_now(tk); + /* + * If the cs is in module, get a module reference. Succeeds + * for built-in code (owner == NULL) as well. + */ + if (try_module_get(new->owner)) { + if (!new->enable || new->enable(new) == 0) { + old = tk->tkr_mono.clock; + tk_setup_internals(tk, new); + if (old->disable) + old->disable(old); + module_put(old->owner); + } else { + module_put(new->owner); + } + } + timekeeping_update(tk, TK_CLEAR_NTP | TK_MIRROR | TK_CLOCK_WAS_SET); + + write_seqcount_end(&tk_core.seq); + raw_spin_unlock_irqrestore(&timekeeper_lock, flags); + + return 0; +} + +/** + * timekeeping_notify - Install a new clock source + * @clock: pointer to the clock source + * + * This function is called from clocksource.c after a new, better clock + * source has been registered. The caller holds the clocksource_mutex. + */ +int timekeeping_notify(struct clocksource *clock) +{ + struct timekeeper *tk = &tk_core.timekeeper; + + if (tk->tkr_mono.clock == clock) + return 0; + stop_machine(change_clocksource, clock, NULL); + tick_clock_notify(); + return tk->tkr_mono.clock == clock ? 0 : -1; +} + +/** + * getrawmonotonic64 - Returns the raw monotonic time in a timespec + * @ts: pointer to the timespec64 to be set + * + * Returns the raw monotonic time (completely un-modified by ntp) + */ +void getrawmonotonic64(struct timespec64 *ts) +{ + struct timekeeper *tk = &tk_core.timekeeper; + struct timespec64 ts64; + unsigned long seq; + s64 nsecs; + + do { + seq = read_seqcount_begin(&tk_core.seq); + nsecs = timekeeping_get_ns(&tk->tkr_raw); + ts64 = tk->raw_time; + + } while (read_seqcount_retry(&tk_core.seq, seq)); + + timespec64_add_ns(&ts64, nsecs); + *ts = ts64; +} +EXPORT_SYMBOL(getrawmonotonic64); + + +/** + * timekeeping_valid_for_hres - Check if timekeeping is suitable for hres + */ +int timekeeping_valid_for_hres(void) +{ + struct timekeeper *tk = &tk_core.timekeeper; + unsigned long seq; + int ret; + + do { + seq = read_seqcount_begin(&tk_core.seq); + + ret = tk->tkr_mono.clock->flags & CLOCK_SOURCE_VALID_FOR_HRES; + + } while (read_seqcount_retry(&tk_core.seq, seq)); + + return ret; +} + +/** + * timekeeping_max_deferment - Returns max time the clocksource can be deferred + */ +u64 timekeeping_max_deferment(void) +{ + struct timekeeper *tk = &tk_core.timekeeper; + unsigned long seq; + u64 ret; + + do { + seq = read_seqcount_begin(&tk_core.seq); + + ret = tk->tkr_mono.clock->max_idle_ns; + + } while (read_seqcount_retry(&tk_core.seq, seq)); + + return ret; +} + +/** + * read_persistent_clock - Return time from the persistent clock. + * + * Weak dummy function for arches that do not yet support it. + * Reads the time from the battery backed persistent clock. + * Returns a timespec with tv_sec=0 and tv_nsec=0 if unsupported. + * + * XXX - Do be sure to remove it once all arches implement it. + */ +void __weak read_persistent_clock(struct timespec *ts) +{ + ts->tv_sec = 0; + ts->tv_nsec = 0; +} + +void __weak read_persistent_clock64(struct timespec64 *ts64) +{ + struct timespec ts; + + read_persistent_clock(&ts); + *ts64 = timespec_to_timespec64(ts); +} + +/** + * read_boot_clock - Return time of the system start. + * + * Weak dummy function for arches that do not yet support it. + * Function to read the exact time the system has been started. + * Returns a timespec with tv_sec=0 and tv_nsec=0 if unsupported. + * + * XXX - Do be sure to remove it once all arches implement it. + */ +void __weak read_boot_clock(struct timespec *ts) +{ + ts->tv_sec = 0; + ts->tv_nsec = 0; +} + +void __weak read_boot_clock64(struct timespec64 *ts64) +{ + struct timespec ts; + + read_boot_clock(&ts); + *ts64 = timespec_to_timespec64(ts); +} + +/* Flag for if timekeeping_resume() has injected sleeptime */ +static bool sleeptime_injected; + +/* Flag for if there is a persistent clock on this platform */ +static bool persistent_clock_exists; + +/* + * timekeeping_init - Initializes the clocksource and common timekeeping values + */ +void __init timekeeping_init(void) +{ + struct timekeeper *tk = &tk_core.timekeeper; + struct clocksource *clock; + unsigned long flags; + struct timespec64 now, boot, tmp; + + read_persistent_clock64(&now); + if (!timespec64_valid_strict(&now)) { + pr_warn("WARNING: Persistent clock returned invalid value!\n" + " Check your CMOS/BIOS settings.\n"); + now.tv_sec = 0; + now.tv_nsec = 0; + } else if (now.tv_sec || now.tv_nsec) + persistent_clock_exists = true; + + read_boot_clock64(&boot); + if (!timespec64_valid_strict(&boot)) { + pr_warn("WARNING: Boot clock returned invalid value!\n" + " Check your CMOS/BIOS settings.\n"); + boot.tv_sec = 0; + boot.tv_nsec = 0; + } + + raw_spin_lock_irqsave(&timekeeper_lock, flags); + write_seqcount_begin(&tk_core.seq); + ntp_init(); + + clock = clocksource_default_clock(); + if (clock->enable) + clock->enable(clock); + tk_setup_internals(tk, clock); + + tk_set_xtime(tk, &now); + tk->raw_time.tv_sec = 0; + tk->raw_time.tv_nsec = 0; + if (boot.tv_sec == 0 && boot.tv_nsec == 0) + boot = tk_xtime(tk); + + set_normalized_timespec64(&tmp, -boot.tv_sec, -boot.tv_nsec); + tk_set_wall_to_mono(tk, tmp); + + timekeeping_update(tk, TK_MIRROR); + + write_seqcount_end(&tk_core.seq); + raw_spin_unlock_irqrestore(&timekeeper_lock, flags); +} + +/* time in seconds when suspend began for persistent clock */ +static struct timespec64 timekeeping_suspend_time; + +/** + * __timekeeping_inject_sleeptime - Internal function to add sleep interval + * @delta: pointer to a timespec delta value + * + * Takes a timespec offset measuring a suspend interval and properly + * adds the sleep offset to the timekeeping variables. + */ +static void __timekeeping_inject_sleeptime(struct timekeeper *tk, + struct timespec64 *delta) +{ + if (!timespec64_valid_strict(delta)) { + printk_deferred(KERN_WARNING + "__timekeeping_inject_sleeptime: Invalid " + "sleep delta value!\n"); + return; + } + tk_xtime_add(tk, delta); + tk_set_wall_to_mono(tk, timespec64_sub(tk->wall_to_monotonic, *delta)); + tk_update_sleep_time(tk, timespec64_to_ktime(*delta)); + tk_debug_account_sleep_time(delta); +} + +#if defined(CONFIG_PM_SLEEP) && defined(CONFIG_RTC_HCTOSYS_DEVICE) +/** + * We have three kinds of time sources to use for sleep time + * injection, the preference order is: + * 1) non-stop clocksource + * 2) persistent clock (ie: RTC accessible when irqs are off) + * 3) RTC + * + * 1) and 2) are used by timekeeping, 3) by RTC subsystem. + * If system has neither 1) nor 2), 3) will be used finally. + * + * + * If timekeeping has injected sleeptime via either 1) or 2), + * 3) becomes needless, so in this case we don't need to call + * rtc_resume(), and this is what timekeeping_rtc_skipresume() + * means. + */ +bool timekeeping_rtc_skipresume(void) +{ + return sleeptime_injected; +} + +/** + * 1) can be determined whether to use or not only when doing + * timekeeping_resume() which is invoked after rtc_suspend(), + * so we can't skip rtc_suspend() surely if system has 1). + * + * But if system has 2), 2) will definitely be used, so in this + * case we don't need to call rtc_suspend(), and this is what + * timekeeping_rtc_skipsuspend() means. + */ +bool timekeeping_rtc_skipsuspend(void) +{ + return persistent_clock_exists; +} + +/** + * timekeeping_inject_sleeptime64 - Adds suspend interval to timeekeeping values + * @delta: pointer to a timespec64 delta value + * + * This hook is for architectures that cannot support read_persistent_clock64 + * because their RTC/persistent clock is only accessible when irqs are enabled. + * and also don't have an effective nonstop clocksource. + * + * This function should only be called by rtc_resume(), and allows + * a suspend offset to be injected into the timekeeping values. + */ +void timekeeping_inject_sleeptime64(struct timespec64 *delta) +{ + struct timekeeper *tk = &tk_core.timekeeper; + unsigned long flags; + + raw_spin_lock_irqsave(&timekeeper_lock, flags); + write_seqcount_begin(&tk_core.seq); + + timekeeping_forward_now(tk); + + __timekeeping_inject_sleeptime(tk, delta); + + timekeeping_update(tk, TK_CLEAR_NTP | TK_MIRROR | TK_CLOCK_WAS_SET); + + write_seqcount_end(&tk_core.seq); + raw_spin_unlock_irqrestore(&timekeeper_lock, flags); + + /* signal hrtimers about time change */ + clock_was_set(); +} +#endif + +/** + * timekeeping_resume - Resumes the generic timekeeping subsystem. + */ +void timekeeping_resume(void) +{ + struct timekeeper *tk = &tk_core.timekeeper; + struct clocksource *clock = tk->tkr_mono.clock; + unsigned long flags; + struct timespec64 ts_new, ts_delta; + cycle_t cycle_now, cycle_delta; + + sleeptime_injected = false; + read_persistent_clock64(&ts_new); + + clockevents_resume(); + clocksource_resume(); + + raw_spin_lock_irqsave(&timekeeper_lock, flags); + write_seqcount_begin(&tk_core.seq); + + /* + * After system resumes, we need to calculate the suspended time and + * compensate it for the OS time. There are 3 sources that could be + * used: Nonstop clocksource during suspend, persistent clock and rtc + * device. + * + * One specific platform may have 1 or 2 or all of them, and the + * preference will be: + * suspend-nonstop clocksource -> persistent clock -> rtc + * The less preferred source will only be tried if there is no better + * usable source. The rtc part is handled separately in rtc core code. + */ + cycle_now = tk->tkr_mono.read(clock); + if ((clock->flags & CLOCK_SOURCE_SUSPEND_NONSTOP) && + cycle_now > tk->tkr_mono.cycle_last) { + u64 num, max = ULLONG_MAX; + u32 mult = clock->mult; + u32 shift = clock->shift; + s64 nsec = 0; + + cycle_delta = clocksource_delta(cycle_now, tk->tkr_mono.cycle_last, + tk->tkr_mono.mask); + + /* + * "cycle_delta * mutl" may cause 64 bits overflow, if the + * suspended time is too long. In that case we need do the + * 64 bits math carefully + */ + do_div(max, mult); + if (cycle_delta > max) { + num = div64_u64(cycle_delta, max); + nsec = (((u64) max * mult) >> shift) * num; + cycle_delta -= num * max; + } + nsec += ((u64) cycle_delta * mult) >> shift; + + ts_delta = ns_to_timespec64(nsec); + sleeptime_injected = true; + } else if (timespec64_compare(&ts_new, &timekeeping_suspend_time) > 0) { + ts_delta = timespec64_sub(ts_new, timekeeping_suspend_time); + sleeptime_injected = true; + } + + if (sleeptime_injected) + __timekeeping_inject_sleeptime(tk, &ts_delta); + + /* Re-base the last cycle value */ + tk->tkr_mono.cycle_last = cycle_now; + tk->tkr_raw.cycle_last = cycle_now; + + tk->ntp_error = 0; + timekeeping_suspended = 0; + timekeeping_update(tk, TK_MIRROR | TK_CLOCK_WAS_SET); + write_seqcount_end(&tk_core.seq); + raw_spin_unlock_irqrestore(&timekeeper_lock, flags); + + touch_softlockup_watchdog(); + + tick_resume(); + hrtimers_resume(); +} + +int timekeeping_suspend(void) +{ + struct timekeeper *tk = &tk_core.timekeeper; + unsigned long flags; + struct timespec64 delta, delta_delta; + static struct timespec64 old_delta; + + read_persistent_clock64(&timekeeping_suspend_time); + + /* + * On some systems the persistent_clock can not be detected at + * timekeeping_init by its return value, so if we see a valid + * value returned, update the persistent_clock_exists flag. + */ + if (timekeeping_suspend_time.tv_sec || timekeeping_suspend_time.tv_nsec) + persistent_clock_exists = true; + + raw_spin_lock_irqsave(&timekeeper_lock, flags); + write_seqcount_begin(&tk_core.seq); + timekeeping_forward_now(tk); + timekeeping_suspended = 1; + + if (persistent_clock_exists) { + /* + * To avoid drift caused by repeated suspend/resumes, + * which each can add ~1 second drift error, + * try to compensate so the difference in system time + * and persistent_clock time stays close to constant. + */ + delta = timespec64_sub(tk_xtime(tk), timekeeping_suspend_time); + delta_delta = timespec64_sub(delta, old_delta); + if (abs(delta_delta.tv_sec) >= 2) { + /* + * if delta_delta is too large, assume time correction + * has occurred and set old_delta to the current delta. + */ + old_delta = delta; + } else { + /* Otherwise try to adjust old_system to compensate */ + timekeeping_suspend_time = + timespec64_add(timekeeping_suspend_time, delta_delta); + } + } + + timekeeping_update(tk, TK_MIRROR); + halt_fast_timekeeper(tk); + write_seqcount_end(&tk_core.seq); + raw_spin_unlock_irqrestore(&timekeeper_lock, flags); + + tick_suspend(); + clocksource_suspend(); + clockevents_suspend(); + + return 0; +} + +/* sysfs resume/suspend bits for timekeeping */ +static struct syscore_ops timekeeping_syscore_ops = { + .resume = timekeeping_resume, + .suspend = timekeeping_suspend, +}; + +static int __init timekeeping_init_ops(void) +{ + register_syscore_ops(&timekeeping_syscore_ops); + return 0; +} +device_initcall(timekeeping_init_ops); + +/* + * Apply a multiplier adjustment to the timekeeper + */ +static __always_inline void timekeeping_apply_adjustment(struct timekeeper *tk, + s64 offset, + bool negative, + int adj_scale) +{ + s64 interval = tk->cycle_interval; + s32 mult_adj = 1; + + if (negative) { + mult_adj = -mult_adj; + interval = -interval; + offset = -offset; + } + mult_adj <<= adj_scale; + interval <<= adj_scale; + offset <<= adj_scale; + + /* + * So the following can be confusing. + * + * To keep things simple, lets assume mult_adj == 1 for now. + * + * When mult_adj != 1, remember that the interval and offset values + * have been appropriately scaled so the math is the same. + * + * The basic idea here is that we're increasing the multiplier + * by one, this causes the xtime_interval to be incremented by + * one cycle_interval. This is because: + * xtime_interval = cycle_interval * mult + * So if mult is being incremented by one: + * xtime_interval = cycle_interval * (mult + 1) + * Its the same as: + * xtime_interval = (cycle_interval * mult) + cycle_interval + * Which can be shortened to: + * xtime_interval += cycle_interval + * + * So offset stores the non-accumulated cycles. Thus the current + * time (in shifted nanoseconds) is: + * now = (offset * adj) + xtime_nsec + * Now, even though we're adjusting the clock frequency, we have + * to keep time consistent. In other words, we can't jump back + * in time, and we also want to avoid jumping forward in time. + * + * So given the same offset value, we need the time to be the same + * both before and after the freq adjustment. + * now = (offset * adj_1) + xtime_nsec_1 + * now = (offset * adj_2) + xtime_nsec_2 + * So: + * (offset * adj_1) + xtime_nsec_1 = + * (offset * adj_2) + xtime_nsec_2 + * And we know: + * adj_2 = adj_1 + 1 + * So: + * (offset * adj_1) + xtime_nsec_1 = + * (offset * (adj_1+1)) + xtime_nsec_2 + * (offset * adj_1) + xtime_nsec_1 = + * (offset * adj_1) + offset + xtime_nsec_2 + * Canceling the sides: + * xtime_nsec_1 = offset + xtime_nsec_2 + * Which gives us: + * xtime_nsec_2 = xtime_nsec_1 - offset + * Which simplfies to: + * xtime_nsec -= offset + * + * XXX - TODO: Doc ntp_error calculation. + */ + if ((mult_adj > 0) && (tk->tkr_mono.mult + mult_adj < mult_adj)) { + /* NTP adjustment caused clocksource mult overflow */ + WARN_ON_ONCE(1); + return; + } + + tk->tkr_mono.mult += mult_adj; + tk->xtime_interval += interval; + tk->tkr_mono.xtime_nsec -= offset; + tk->ntp_error -= (interval - offset) << tk->ntp_error_shift; +} + +/* + * Calculate the multiplier adjustment needed to match the frequency + * specified by NTP + */ +static __always_inline void timekeeping_freqadjust(struct timekeeper *tk, + s64 offset) +{ + s64 interval = tk->cycle_interval; + s64 xinterval = tk->xtime_interval; + s64 tick_error; + bool negative; + u32 adj; + + /* Remove any current error adj from freq calculation */ + if (tk->ntp_err_mult) + xinterval -= tk->cycle_interval; + + tk->ntp_tick = ntp_tick_length(); + + /* Calculate current error per tick */ + tick_error = ntp_tick_length() >> tk->ntp_error_shift; + tick_error -= (xinterval + tk->xtime_remainder); + + /* Don't worry about correcting it if its small */ + if (likely((tick_error >= 0) && (tick_error <= interval))) + return; + + /* preserve the direction of correction */ + negative = (tick_error < 0); + + /* Sort out the magnitude of the correction */ + tick_error = abs(tick_error); + for (adj = 0; tick_error > interval; adj++) + tick_error >>= 1; + + /* scale the corrections */ + timekeeping_apply_adjustment(tk, offset, negative, adj); +} + +/* + * Adjust the timekeeper's multiplier to the correct frequency + * and also to reduce the accumulated error value. + */ +static void timekeeping_adjust(struct timekeeper *tk, s64 offset) +{ + /* Correct for the current frequency error */ + timekeeping_freqadjust(tk, offset); + + /* Next make a small adjustment to fix any cumulative error */ + if (!tk->ntp_err_mult && (tk->ntp_error > 0)) { + tk->ntp_err_mult = 1; + timekeeping_apply_adjustment(tk, offset, 0, 0); + } else if (tk->ntp_err_mult && (tk->ntp_error <= 0)) { + /* Undo any existing error adjustment */ + timekeeping_apply_adjustment(tk, offset, 1, 0); + tk->ntp_err_mult = 0; + } + + if (unlikely(tk->tkr_mono.clock->maxadj && + (abs(tk->tkr_mono.mult - tk->tkr_mono.clock->mult) + > tk->tkr_mono.clock->maxadj))) { + printk_once(KERN_WARNING + "Adjusting %s more than 11%% (%ld vs %ld)\n", + tk->tkr_mono.clock->name, (long)tk->tkr_mono.mult, + (long)tk->tkr_mono.clock->mult + tk->tkr_mono.clock->maxadj); + } + + /* + * It may be possible that when we entered this function, xtime_nsec + * was very small. Further, if we're slightly speeding the clocksource + * in the code above, its possible the required corrective factor to + * xtime_nsec could cause it to underflow. + * + * Now, since we already accumulated the second, cannot simply roll + * the accumulated second back, since the NTP subsystem has been + * notified via second_overflow. So instead we push xtime_nsec forward + * by the amount we underflowed, and add that amount into the error. + * + * We'll correct this error next time through this function, when + * xtime_nsec is not as small. + */ + if (unlikely((s64)tk->tkr_mono.xtime_nsec < 0)) { + s64 neg = -(s64)tk->tkr_mono.xtime_nsec; + tk->tkr_mono.xtime_nsec = 0; + tk->ntp_error += neg << tk->ntp_error_shift; + } +} + +/** + * accumulate_nsecs_to_secs - Accumulates nsecs into secs + * + * Helper function that accumulates a the nsecs greater then a second + * from the xtime_nsec field to the xtime_secs field. + * It also calls into the NTP code to handle leapsecond processing. + * + */ +static inline unsigned int accumulate_nsecs_to_secs(struct timekeeper *tk) +{ + u64 nsecps = (u64)NSEC_PER_SEC << tk->tkr_mono.shift; + unsigned int clock_set = 0; + + while (tk->tkr_mono.xtime_nsec >= nsecps) { + int leap; + + tk->tkr_mono.xtime_nsec -= nsecps; + tk->xtime_sec++; + + /* Figure out if its a leap sec and apply if needed */ + leap = second_overflow(tk->xtime_sec); + if (unlikely(leap)) { + struct timespec64 ts; + + tk->xtime_sec += leap; + + ts.tv_sec = leap; + ts.tv_nsec = 0; + tk_set_wall_to_mono(tk, + timespec64_sub(tk->wall_to_monotonic, ts)); + + __timekeeping_set_tai_offset(tk, tk->tai_offset - leap); + + clock_set = TK_CLOCK_WAS_SET; + } + } + return clock_set; +} + +/** + * logarithmic_accumulation - shifted accumulation of cycles + * + * This functions accumulates a shifted interval of cycles into + * into a shifted interval nanoseconds. Allows for O(log) accumulation + * loop. + * + * Returns the unconsumed cycles. + */ +static cycle_t logarithmic_accumulation(struct timekeeper *tk, cycle_t offset, + u32 shift, + unsigned int *clock_set) +{ + cycle_t interval = tk->cycle_interval << shift; + u64 raw_nsecs; + + /* If the offset is smaller then a shifted interval, do nothing */ + if (offset < interval) + return offset; + + /* Accumulate one shifted interval */ + offset -= interval; + tk->tkr_mono.cycle_last += interval; + tk->tkr_raw.cycle_last += interval; + + tk->tkr_mono.xtime_nsec += tk->xtime_interval << shift; + *clock_set |= accumulate_nsecs_to_secs(tk); + + /* Accumulate raw time */ + raw_nsecs = (u64)tk->raw_interval << shift; + raw_nsecs += tk->raw_time.tv_nsec; + if (raw_nsecs >= NSEC_PER_SEC) { + u64 raw_secs = raw_nsecs; + raw_nsecs = do_div(raw_secs, NSEC_PER_SEC); + tk->raw_time.tv_sec += raw_secs; + } + tk->raw_time.tv_nsec = raw_nsecs; + + /* Accumulate error between NTP and clock interval */ + tk->ntp_error += tk->ntp_tick << shift; + tk->ntp_error -= (tk->xtime_interval + tk->xtime_remainder) << + (tk->ntp_error_shift + shift); + + return offset; +} + +/** + * update_wall_time - Uses the current clocksource to increment the wall time + * + */ +void update_wall_time(void) +{ + struct timekeeper *real_tk = &tk_core.timekeeper; + struct timekeeper *tk = &shadow_timekeeper; + cycle_t offset; + int shift = 0, maxshift; + unsigned int clock_set = 0; + unsigned long flags; + + raw_spin_lock_irqsave(&timekeeper_lock, flags); + + /* Make sure we're fully resumed: */ + if (unlikely(timekeeping_suspended)) + goto out; + +#ifdef CONFIG_ARCH_USES_GETTIMEOFFSET + offset = real_tk->cycle_interval; +#else + offset = clocksource_delta(tk->tkr_mono.read(tk->tkr_mono.clock), + tk->tkr_mono.cycle_last, tk->tkr_mono.mask); +#endif + + /* Check if there's really nothing to do */ + if (offset < real_tk->cycle_interval) + goto out; + + /* Do some additional sanity checking */ + timekeeping_check_update(real_tk, offset); + + /* + * With NO_HZ we may have to accumulate many cycle_intervals + * (think "ticks") worth of time at once. To do this efficiently, + * we calculate the largest doubling multiple of cycle_intervals + * that is smaller than the offset. We then accumulate that + * chunk in one go, and then try to consume the next smaller + * doubled multiple. + */ + shift = ilog2(offset) - ilog2(tk->cycle_interval); + shift = max(0, shift); + /* Bound shift to one less than what overflows tick_length */ + maxshift = (64 - (ilog2(ntp_tick_length())+1)) - 1; + shift = min(shift, maxshift); + while (offset >= tk->cycle_interval) { + offset = logarithmic_accumulation(tk, offset, shift, + &clock_set); + if (offset < tk->cycle_interval<offs_real, tk->offs_boot); + + *ts = ktime_to_timespec64(t); +} +EXPORT_SYMBOL_GPL(getboottime64); + +unsigned long get_seconds(void) +{ + struct timekeeper *tk = &tk_core.timekeeper; + + return tk->xtime_sec; +} +EXPORT_SYMBOL(get_seconds); + +struct timespec __current_kernel_time(void) +{ + struct timekeeper *tk = &tk_core.timekeeper; + + return timespec64_to_timespec(tk_xtime(tk)); +} + +struct timespec current_kernel_time(void) +{ + struct timekeeper *tk = &tk_core.timekeeper; + struct timespec64 now; + unsigned long seq; + + do { + seq = read_seqcount_begin(&tk_core.seq); + + now = tk_xtime(tk); + } while (read_seqcount_retry(&tk_core.seq, seq)); + + return timespec64_to_timespec(now); +} +EXPORT_SYMBOL(current_kernel_time); + +struct timespec64 get_monotonic_coarse64(void) +{ + struct timekeeper *tk = &tk_core.timekeeper; + struct timespec64 now, mono; + unsigned long seq; + + do { + seq = read_seqcount_begin(&tk_core.seq); + + now = tk_xtime(tk); + mono = tk->wall_to_monotonic; + } while (read_seqcount_retry(&tk_core.seq, seq)); + + set_normalized_timespec64(&now, now.tv_sec + mono.tv_sec, + now.tv_nsec + mono.tv_nsec); + + return now; +} + +/* + * Must hold jiffies_lock + */ +void do_timer(unsigned long ticks) +{ + jiffies_64 += ticks; + calc_global_load(ticks); +} + +/** + * ktime_get_update_offsets_tick - hrtimer helper + * @offs_real: pointer to storage for monotonic -> realtime offset + * @offs_boot: pointer to storage for monotonic -> boottime offset + * @offs_tai: pointer to storage for monotonic -> clock tai offset + * + * Returns monotonic time at last tick and various offsets + */ +ktime_t ktime_get_update_offsets_tick(ktime_t *offs_real, ktime_t *offs_boot, + ktime_t *offs_tai) +{ + struct timekeeper *tk = &tk_core.timekeeper; + unsigned int seq; + ktime_t base; + u64 nsecs; + + do { + seq = read_seqcount_begin(&tk_core.seq); + + base = tk->tkr_mono.base; + nsecs = tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift; + + *offs_real = tk->offs_real; + *offs_boot = tk->offs_boot; + *offs_tai = tk->offs_tai; + } while (read_seqcount_retry(&tk_core.seq, seq)); + + return ktime_add_ns(base, nsecs); +} + +#ifdef CONFIG_HIGH_RES_TIMERS +/** + * ktime_get_update_offsets_now - hrtimer helper + * @offs_real: pointer to storage for monotonic -> realtime offset + * @offs_boot: pointer to storage for monotonic -> boottime offset + * @offs_tai: pointer to storage for monotonic -> clock tai offset + * + * Returns current monotonic time and updates the offsets + * Called from hrtimer_interrupt() or retrigger_next_event() + */ +ktime_t ktime_get_update_offsets_now(ktime_t *offs_real, ktime_t *offs_boot, + ktime_t *offs_tai) +{ + struct timekeeper *tk = &tk_core.timekeeper; + unsigned int seq; + ktime_t base; + u64 nsecs; + + do { + seq = read_seqcount_begin(&tk_core.seq); + + base = tk->tkr_mono.base; + nsecs = timekeeping_get_ns(&tk->tkr_mono); + + *offs_real = tk->offs_real; + *offs_boot = tk->offs_boot; + *offs_tai = tk->offs_tai; + } while (read_seqcount_retry(&tk_core.seq, seq)); + + return ktime_add_ns(base, nsecs); +} +#endif + +/** + * do_adjtimex() - Accessor function to NTP __do_adjtimex function + */ +int do_adjtimex(struct timex *txc) +{ + struct timekeeper *tk = &tk_core.timekeeper; + unsigned long flags; + struct timespec64 ts; + s32 orig_tai, tai; + int ret; + + /* Validate the data before disabling interrupts */ + ret = ntp_validate_timex(txc); + if (ret) + return ret; + + if (txc->modes & ADJ_SETOFFSET) { + struct timespec delta; + delta.tv_sec = txc->time.tv_sec; + delta.tv_nsec = txc->time.tv_usec; + if (!(txc->modes & ADJ_NANO)) + delta.tv_nsec *= 1000; + ret = timekeeping_inject_offset(&delta); + if (ret) + return ret; + } + + getnstimeofday64(&ts); + + raw_spin_lock_irqsave(&timekeeper_lock, flags); + write_seqcount_begin(&tk_core.seq); + + orig_tai = tai = tk->tai_offset; + ret = __do_adjtimex(txc, &ts, &tai); + + if (tai != orig_tai) { + __timekeeping_set_tai_offset(tk, tai); + timekeeping_update(tk, TK_MIRROR | TK_CLOCK_WAS_SET); + } + write_seqcount_end(&tk_core.seq); + raw_spin_unlock_irqrestore(&timekeeper_lock, flags); + + if (tai != orig_tai) + clock_was_set(); + + ntp_notify_cmos_timer(); + + return ret; +} + +#ifdef CONFIG_NTP_PPS +/** + * hardpps() - Accessor function to NTP __hardpps function + */ +void hardpps(const struct timespec *phase_ts, const struct timespec *raw_ts) +{ + unsigned long flags; + + raw_spin_lock_irqsave(&timekeeper_lock, flags); + write_seqcount_begin(&tk_core.seq); + + __hardpps(phase_ts, raw_ts); + + write_seqcount_end(&tk_core.seq); + raw_spin_unlock_irqrestore(&timekeeper_lock, flags); +} +EXPORT_SYMBOL(hardpps); +#endif + +/** + * xtime_update() - advances the timekeeping infrastructure + * @ticks: number of ticks, that have elapsed since the last call. + * + * Must be called with interrupts disabled. + */ +void xtime_update(unsigned long ticks) +{ + raw_spin_lock(&jiffies_lock); + write_seqcount_begin(&jiffies_seq); + do_timer(ticks); + write_seqcount_end(&jiffies_seq); + raw_spin_unlock(&jiffies_lock); + update_wall_time(); +} diff --git a/kernel/kernel/time/timekeeping.h b/kernel/kernel/time/timekeeping.h new file mode 100644 index 000000000..d7a9120a9 --- /dev/null +++ b/kernel/kernel/time/timekeeping.h @@ -0,0 +1,30 @@ +#ifndef _KERNEL_TIME_TIMEKEEPING_H +#define _KERNEL_TIME_TIMEKEEPING_H +/* + * Internal interfaces for kernel/time/ + */ +extern ktime_t ktime_get_update_offsets_tick(ktime_t *offs_real, + ktime_t *offs_boot, + ktime_t *offs_tai); +extern ktime_t ktime_get_update_offsets_now(ktime_t *offs_real, + ktime_t *offs_boot, + ktime_t *offs_tai); + +extern int timekeeping_valid_for_hres(void); +extern u64 timekeeping_max_deferment(void); +extern int timekeeping_inject_offset(struct timespec *ts); +extern s32 timekeeping_get_tai_offset(void); +extern void timekeeping_set_tai_offset(s32 tai_offset); +extern void timekeeping_clocktai(struct timespec *ts); +extern int timekeeping_suspend(void); +extern void timekeeping_resume(void); + +extern void do_timer(unsigned long ticks); +extern void update_wall_time(void); + +extern raw_spinlock_t jiffies_lock; +extern seqcount_t jiffies_seq; + +#define CS_NAME_LEN 32 + +#endif diff --git a/kernel/kernel/time/timekeeping_debug.c b/kernel/kernel/time/timekeeping_debug.c new file mode 100644 index 000000000..f6bd65236 --- /dev/null +++ b/kernel/kernel/time/timekeeping_debug.c @@ -0,0 +1,74 @@ +/* + * debugfs file to track time spent in suspend + * + * Copyright (c) 2011, Google, Inc. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + */ + +#include +#include +#include +#include +#include +#include + +#include "timekeeping_internal.h" + +static unsigned int sleep_time_bin[32] = {0}; + +static int tk_debug_show_sleep_time(struct seq_file *s, void *data) +{ + unsigned int bin; + seq_puts(s, " time (secs) count\n"); + seq_puts(s, "------------------------------\n"); + for (bin = 0; bin < 32; bin++) { + if (sleep_time_bin[bin] == 0) + continue; + seq_printf(s, "%10u - %-10u %4u\n", + bin ? 1 << (bin - 1) : 0, 1 << bin, + sleep_time_bin[bin]); + } + return 0; +} + +static int tk_debug_sleep_time_open(struct inode *inode, struct file *file) +{ + return single_open(file, tk_debug_show_sleep_time, NULL); +} + +static const struct file_operations tk_debug_sleep_time_fops = { + .open = tk_debug_sleep_time_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static int __init tk_debug_sleep_time_init(void) +{ + struct dentry *d; + + d = debugfs_create_file("sleep_time", 0444, NULL, NULL, + &tk_debug_sleep_time_fops); + if (!d) { + pr_err("Failed to create sleep_time debug file\n"); + return -ENOMEM; + } + + return 0; +} +late_initcall(tk_debug_sleep_time_init); + +void tk_debug_account_sleep_time(struct timespec64 *t) +{ + sleep_time_bin[fls(t->tv_sec)]++; +} + diff --git a/kernel/kernel/time/timekeeping_internal.h b/kernel/kernel/time/timekeeping_internal.h new file mode 100644 index 000000000..4ea005a7f --- /dev/null +++ b/kernel/kernel/time/timekeeping_internal.h @@ -0,0 +1,29 @@ +#ifndef _TIMEKEEPING_INTERNAL_H +#define _TIMEKEEPING_INTERNAL_H +/* + * timekeeping debug functions + */ +#include +#include + +#ifdef CONFIG_DEBUG_FS +extern void tk_debug_account_sleep_time(struct timespec64 *t); +#else +#define tk_debug_account_sleep_time(x) +#endif + +#ifdef CONFIG_CLOCKSOURCE_VALIDATE_LAST_CYCLE +static inline cycle_t clocksource_delta(cycle_t now, cycle_t last, cycle_t mask) +{ + cycle_t ret = (now - last) & mask; + + return (s64) ret > 0 ? ret : 0; +} +#else +static inline cycle_t clocksource_delta(cycle_t now, cycle_t last, cycle_t mask) +{ + return (now - last) & mask; +} +#endif + +#endif /* _TIMEKEEPING_INTERNAL_H */ diff --git a/kernel/kernel/time/timer.c b/kernel/kernel/time/timer.c new file mode 100644 index 000000000..adb1d82d6 --- /dev/null +++ b/kernel/kernel/time/timer.c @@ -0,0 +1,1787 @@ +/* + * linux/kernel/timer.c + * + * Kernel internal timers + * + * Copyright (C) 1991, 1992 Linus Torvalds + * + * 1997-01-28 Modified by Finn Arne Gangstad to make timers scale better. + * + * 1997-09-10 Updated NTP code according to technical memorandum Jan '96 + * "A Kernel Model for Precision Timekeeping" by Dave Mills + * 1998-12-24 Fixed a xtime SMP race (we need the xtime_lock rw spinlock to + * serialize accesses to xtime/lost_ticks). + * Copyright (C) 1998 Andrea Arcangeli + * 1999-03-10 Improved NTP compatibility by Ulrich Windl + * 2002-05-31 Move sys_sysinfo here and make its locking sane, Robert Love + * 2000-10-05 Implemented scalable SMP per-CPU timer handling. + * Copyright (C) 2000, 2001, 2002 Ingo Molnar + * Designed by David S. Miller, Alexey Kuznetsov and Ingo Molnar + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include + +#define CREATE_TRACE_POINTS +#include + +__visible u64 jiffies_64 __cacheline_aligned_in_smp = INITIAL_JIFFIES; + +EXPORT_SYMBOL(jiffies_64); + +/* + * per-CPU timer vector definitions: + */ +#define TVN_BITS (CONFIG_BASE_SMALL ? 4 : 6) +#define TVR_BITS (CONFIG_BASE_SMALL ? 6 : 8) +#define TVN_SIZE (1 << TVN_BITS) +#define TVR_SIZE (1 << TVR_BITS) +#define TVN_MASK (TVN_SIZE - 1) +#define TVR_MASK (TVR_SIZE - 1) +#define MAX_TVAL ((unsigned long)((1ULL << (TVR_BITS + 4*TVN_BITS)) - 1)) + +struct tvec { + struct list_head vec[TVN_SIZE]; +}; + +struct tvec_root { + struct list_head vec[TVR_SIZE]; +}; + +struct tvec_base { + spinlock_t lock; + struct timer_list *running_timer; +#ifdef CONFIG_PREEMPT_RT_FULL + wait_queue_head_t wait_for_running_timer; +#endif + unsigned long timer_jiffies; + unsigned long next_timer; + unsigned long active_timers; + unsigned long all_timers; + int cpu; + struct tvec_root tv1; + struct tvec tv2; + struct tvec tv3; + struct tvec tv4; + struct tvec tv5; +} ____cacheline_aligned; + +/* + * __TIMER_INITIALIZER() needs to set ->base to a valid pointer (because we've + * made NULL special, hint: lock_timer_base()) and we cannot get a compile time + * pointer to per-cpu entries because we don't know where we'll map the section, + * even for the boot cpu. + * + * And so we use boot_tvec_bases for boot CPU and per-cpu __tvec_bases for the + * rest of them. + */ +struct tvec_base boot_tvec_bases; +EXPORT_SYMBOL(boot_tvec_bases); + +static DEFINE_PER_CPU(struct tvec_base *, tvec_bases) = &boot_tvec_bases; + +/* Functions below help us manage 'deferrable' flag */ +static inline unsigned int tbase_get_deferrable(struct tvec_base *base) +{ + return ((unsigned int)(unsigned long)base & TIMER_DEFERRABLE); +} + +static inline unsigned int tbase_get_irqsafe(struct tvec_base *base) +{ + return ((unsigned int)(unsigned long)base & TIMER_IRQSAFE); +} + +static inline struct tvec_base *tbase_get_base(struct tvec_base *base) +{ + return ((struct tvec_base *)((unsigned long)base & ~TIMER_FLAG_MASK)); +} + +static inline void +timer_set_base(struct timer_list *timer, struct tvec_base *new_base) +{ + unsigned long flags = (unsigned long)timer->base & TIMER_FLAG_MASK; + + timer->base = (struct tvec_base *)((unsigned long)(new_base) | flags); +} + +static unsigned long round_jiffies_common(unsigned long j, int cpu, + bool force_up) +{ + int rem; + unsigned long original = j; + + /* + * We don't want all cpus firing their timers at once hitting the + * same lock or cachelines, so we skew each extra cpu with an extra + * 3 jiffies. This 3 jiffies came originally from the mm/ code which + * already did this. + * The skew is done by adding 3*cpunr, then round, then subtract this + * extra offset again. + */ + j += cpu * 3; + + rem = j % HZ; + + /* + * If the target jiffie is just after a whole second (which can happen + * due to delays of the timer irq, long irq off times etc etc) then + * we should round down to the whole second, not up. Use 1/4th second + * as cutoff for this rounding as an extreme upper bound for this. + * But never round down if @force_up is set. + */ + if (rem < HZ/4 && !force_up) /* round down */ + j = j - rem; + else /* round up */ + j = j - rem + HZ; + + /* now that we have rounded, subtract the extra skew again */ + j -= cpu * 3; + + /* + * Make sure j is still in the future. Otherwise return the + * unmodified value. + */ + return time_is_after_jiffies(j) ? j : original; +} + +/** + * __round_jiffies - function to round jiffies to a full second + * @j: the time in (absolute) jiffies that should be rounded + * @cpu: the processor number on which the timeout will happen + * + * __round_jiffies() rounds an absolute time in the future (in jiffies) + * up or down to (approximately) full seconds. This is useful for timers + * for which the exact time they fire does not matter too much, as long as + * they fire approximately every X seconds. + * + * By rounding these timers to whole seconds, all such timers will fire + * at the same time, rather than at various times spread out. The goal + * of this is to have the CPU wake up less, which saves power. + * + * The exact rounding is skewed for each processor to avoid all + * processors firing at the exact same time, which could lead + * to lock contention or spurious cache line bouncing. + * + * The return value is the rounded version of the @j parameter. + */ +unsigned long __round_jiffies(unsigned long j, int cpu) +{ + return round_jiffies_common(j, cpu, false); +} +EXPORT_SYMBOL_GPL(__round_jiffies); + +/** + * __round_jiffies_relative - function to round jiffies to a full second + * @j: the time in (relative) jiffies that should be rounded + * @cpu: the processor number on which the timeout will happen + * + * __round_jiffies_relative() rounds a time delta in the future (in jiffies) + * up or down to (approximately) full seconds. This is useful for timers + * for which the exact time they fire does not matter too much, as long as + * they fire approximately every X seconds. + * + * By rounding these timers to whole seconds, all such timers will fire + * at the same time, rather than at various times spread out. The goal + * of this is to have the CPU wake up less, which saves power. + * + * The exact rounding is skewed for each processor to avoid all + * processors firing at the exact same time, which could lead + * to lock contention or spurious cache line bouncing. + * + * The return value is the rounded version of the @j parameter. + */ +unsigned long __round_jiffies_relative(unsigned long j, int cpu) +{ + unsigned long j0 = jiffies; + + /* Use j0 because jiffies might change while we run */ + return round_jiffies_common(j + j0, cpu, false) - j0; +} +EXPORT_SYMBOL_GPL(__round_jiffies_relative); + +/** + * round_jiffies - function to round jiffies to a full second + * @j: the time in (absolute) jiffies that should be rounded + * + * round_jiffies() rounds an absolute time in the future (in jiffies) + * up or down to (approximately) full seconds. This is useful for timers + * for which the exact time they fire does not matter too much, as long as + * they fire approximately every X seconds. + * + * By rounding these timers to whole seconds, all such timers will fire + * at the same time, rather than at various times spread out. The goal + * of this is to have the CPU wake up less, which saves power. + * + * The return value is the rounded version of the @j parameter. + */ +unsigned long round_jiffies(unsigned long j) +{ + return round_jiffies_common(j, raw_smp_processor_id(), false); +} +EXPORT_SYMBOL_GPL(round_jiffies); + +/** + * round_jiffies_relative - function to round jiffies to a full second + * @j: the time in (relative) jiffies that should be rounded + * + * round_jiffies_relative() rounds a time delta in the future (in jiffies) + * up or down to (approximately) full seconds. This is useful for timers + * for which the exact time they fire does not matter too much, as long as + * they fire approximately every X seconds. + * + * By rounding these timers to whole seconds, all such timers will fire + * at the same time, rather than at various times spread out. The goal + * of this is to have the CPU wake up less, which saves power. + * + * The return value is the rounded version of the @j parameter. + */ +unsigned long round_jiffies_relative(unsigned long j) +{ + return __round_jiffies_relative(j, raw_smp_processor_id()); +} +EXPORT_SYMBOL_GPL(round_jiffies_relative); + +/** + * __round_jiffies_up - function to round jiffies up to a full second + * @j: the time in (absolute) jiffies that should be rounded + * @cpu: the processor number on which the timeout will happen + * + * This is the same as __round_jiffies() except that it will never + * round down. This is useful for timeouts for which the exact time + * of firing does not matter too much, as long as they don't fire too + * early. + */ +unsigned long __round_jiffies_up(unsigned long j, int cpu) +{ + return round_jiffies_common(j, cpu, true); +} +EXPORT_SYMBOL_GPL(__round_jiffies_up); + +/** + * __round_jiffies_up_relative - function to round jiffies up to a full second + * @j: the time in (relative) jiffies that should be rounded + * @cpu: the processor number on which the timeout will happen + * + * This is the same as __round_jiffies_relative() except that it will never + * round down. This is useful for timeouts for which the exact time + * of firing does not matter too much, as long as they don't fire too + * early. + */ +unsigned long __round_jiffies_up_relative(unsigned long j, int cpu) +{ + unsigned long j0 = jiffies; + + /* Use j0 because jiffies might change while we run */ + return round_jiffies_common(j + j0, cpu, true) - j0; +} +EXPORT_SYMBOL_GPL(__round_jiffies_up_relative); + +/** + * round_jiffies_up - function to round jiffies up to a full second + * @j: the time in (absolute) jiffies that should be rounded + * + * This is the same as round_jiffies() except that it will never + * round down. This is useful for timeouts for which the exact time + * of firing does not matter too much, as long as they don't fire too + * early. + */ +unsigned long round_jiffies_up(unsigned long j) +{ + return round_jiffies_common(j, raw_smp_processor_id(), true); +} +EXPORT_SYMBOL_GPL(round_jiffies_up); + +/** + * round_jiffies_up_relative - function to round jiffies up to a full second + * @j: the time in (relative) jiffies that should be rounded + * + * This is the same as round_jiffies_relative() except that it will never + * round down. This is useful for timeouts for which the exact time + * of firing does not matter too much, as long as they don't fire too + * early. + */ +unsigned long round_jiffies_up_relative(unsigned long j) +{ + return __round_jiffies_up_relative(j, raw_smp_processor_id()); +} +EXPORT_SYMBOL_GPL(round_jiffies_up_relative); + +/** + * set_timer_slack - set the allowed slack for a timer + * @timer: the timer to be modified + * @slack_hz: the amount of time (in jiffies) allowed for rounding + * + * Set the amount of time, in jiffies, that a certain timer has + * in terms of slack. By setting this value, the timer subsystem + * will schedule the actual timer somewhere between + * the time mod_timer() asks for, and that time plus the slack. + * + * By setting the slack to -1, a percentage of the delay is used + * instead. + */ +void set_timer_slack(struct timer_list *timer, int slack_hz) +{ + timer->slack = slack_hz; +} +EXPORT_SYMBOL_GPL(set_timer_slack); + +/* + * If the list is empty, catch up ->timer_jiffies to the current time. + * The caller must hold the tvec_base lock. Returns true if the list + * was empty and therefore ->timer_jiffies was updated. + */ +static bool catchup_timer_jiffies(struct tvec_base *base) +{ + if (!base->all_timers) { + base->timer_jiffies = jiffies; + return true; + } + return false; +} + +static void +__internal_add_timer(struct tvec_base *base, struct timer_list *timer) +{ + unsigned long expires = timer->expires; + unsigned long idx = expires - base->timer_jiffies; + struct list_head *vec; + + if (idx < TVR_SIZE) { + int i = expires & TVR_MASK; + vec = base->tv1.vec + i; + } else if (idx < 1 << (TVR_BITS + TVN_BITS)) { + int i = (expires >> TVR_BITS) & TVN_MASK; + vec = base->tv2.vec + i; + } else if (idx < 1 << (TVR_BITS + 2 * TVN_BITS)) { + int i = (expires >> (TVR_BITS + TVN_BITS)) & TVN_MASK; + vec = base->tv3.vec + i; + } else if (idx < 1 << (TVR_BITS + 3 * TVN_BITS)) { + int i = (expires >> (TVR_BITS + 2 * TVN_BITS)) & TVN_MASK; + vec = base->tv4.vec + i; + } else if ((signed long) idx < 0) { + /* + * Can happen if you add a timer with expires == jiffies, + * or you set a timer to go off in the past + */ + vec = base->tv1.vec + (base->timer_jiffies & TVR_MASK); + } else { + int i; + /* If the timeout is larger than MAX_TVAL (on 64-bit + * architectures or with CONFIG_BASE_SMALL=1) then we + * use the maximum timeout. + */ + if (idx > MAX_TVAL) { + idx = MAX_TVAL; + expires = idx + base->timer_jiffies; + } + i = (expires >> (TVR_BITS + 3 * TVN_BITS)) & TVN_MASK; + vec = base->tv5.vec + i; + } + /* + * Timers are FIFO: + */ + list_add_tail(&timer->entry, vec); +} + +static void internal_add_timer(struct tvec_base *base, struct timer_list *timer) +{ + (void)catchup_timer_jiffies(base); + __internal_add_timer(base, timer); + /* + * Update base->active_timers and base->next_timer + */ + if (!tbase_get_deferrable(timer->base)) { + if (!base->active_timers++ || + time_before(timer->expires, base->next_timer)) + base->next_timer = timer->expires; + } + base->all_timers++; + + /* + * Check whether the other CPU is in dynticks mode and needs + * to be triggered to reevaluate the timer wheel. + * We are protected against the other CPU fiddling + * with the timer by holding the timer base lock. This also + * makes sure that a CPU on the way to stop its tick can not + * evaluate the timer wheel. + * + * Spare the IPI for deferrable timers on idle targets though. + * The next busy ticks will take care of it. Except full dynticks + * require special care against races with idle_cpu(), lets deal + * with that later. + */ + if (!tbase_get_deferrable(base) || tick_nohz_full_cpu(base->cpu)) + wake_up_nohz_cpu(base->cpu); +} + +#ifdef CONFIG_TIMER_STATS +void __timer_stats_timer_set_start_info(struct timer_list *timer, void *addr) +{ + if (timer->start_site) + return; + + timer->start_site = addr; + memcpy(timer->start_comm, current->comm, TASK_COMM_LEN); + timer->start_pid = current->pid; +} + +static void timer_stats_account_timer(struct timer_list *timer) +{ + unsigned int flag = 0; + + if (likely(!timer->start_site)) + return; + if (unlikely(tbase_get_deferrable(timer->base))) + flag |= TIMER_STATS_FLAG_DEFERRABLE; + + timer_stats_update_stats(timer, timer->start_pid, timer->start_site, + timer->function, timer->start_comm, flag); +} + +#else +static void timer_stats_account_timer(struct timer_list *timer) {} +#endif + +#ifdef CONFIG_DEBUG_OBJECTS_TIMERS + +static struct debug_obj_descr timer_debug_descr; + +static void *timer_debug_hint(void *addr) +{ + return ((struct timer_list *) addr)->function; +} + +/* + * fixup_init is called when: + * - an active object is initialized + */ +static int timer_fixup_init(void *addr, enum debug_obj_state state) +{ + struct timer_list *timer = addr; + + switch (state) { + case ODEBUG_STATE_ACTIVE: + del_timer_sync(timer); + debug_object_init(timer, &timer_debug_descr); + return 1; + default: + return 0; + } +} + +/* Stub timer callback for improperly used timers. */ +static void stub_timer(unsigned long data) +{ + WARN_ON(1); +} + +/* + * fixup_activate is called when: + * - an active object is activated + * - an unknown object is activated (might be a statically initialized object) + */ +static int timer_fixup_activate(void *addr, enum debug_obj_state state) +{ + struct timer_list *timer = addr; + + switch (state) { + + case ODEBUG_STATE_NOTAVAILABLE: + /* + * This is not really a fixup. The timer was + * statically initialized. We just make sure that it + * is tracked in the object tracker. + */ + if (timer->entry.next == NULL && + timer->entry.prev == TIMER_ENTRY_STATIC) { + debug_object_init(timer, &timer_debug_descr); + debug_object_activate(timer, &timer_debug_descr); + return 0; + } else { + setup_timer(timer, stub_timer, 0); + return 1; + } + return 0; + + case ODEBUG_STATE_ACTIVE: + WARN_ON(1); + + default: + return 0; + } +} + +/* + * fixup_free is called when: + * - an active object is freed + */ +static int timer_fixup_free(void *addr, enum debug_obj_state state) +{ + struct timer_list *timer = addr; + + switch (state) { + case ODEBUG_STATE_ACTIVE: + del_timer_sync(timer); + debug_object_free(timer, &timer_debug_descr); + return 1; + default: + return 0; + } +} + +/* + * fixup_assert_init is called when: + * - an untracked/uninit-ed object is found + */ +static int timer_fixup_assert_init(void *addr, enum debug_obj_state state) +{ + struct timer_list *timer = addr; + + switch (state) { + case ODEBUG_STATE_NOTAVAILABLE: + if (timer->entry.prev == TIMER_ENTRY_STATIC) { + /* + * This is not really a fixup. The timer was + * statically initialized. We just make sure that it + * is tracked in the object tracker. + */ + debug_object_init(timer, &timer_debug_descr); + return 0; + } else { + setup_timer(timer, stub_timer, 0); + return 1; + } + default: + return 0; + } +} + +static struct debug_obj_descr timer_debug_descr = { + .name = "timer_list", + .debug_hint = timer_debug_hint, + .fixup_init = timer_fixup_init, + .fixup_activate = timer_fixup_activate, + .fixup_free = timer_fixup_free, + .fixup_assert_init = timer_fixup_assert_init, +}; + +static inline void debug_timer_init(struct timer_list *timer) +{ + debug_object_init(timer, &timer_debug_descr); +} + +static inline void debug_timer_activate(struct timer_list *timer) +{ + debug_object_activate(timer, &timer_debug_descr); +} + +static inline void debug_timer_deactivate(struct timer_list *timer) +{ + debug_object_deactivate(timer, &timer_debug_descr); +} + +static inline void debug_timer_free(struct timer_list *timer) +{ + debug_object_free(timer, &timer_debug_descr); +} + +static inline void debug_timer_assert_init(struct timer_list *timer) +{ + debug_object_assert_init(timer, &timer_debug_descr); +} + +static void do_init_timer(struct timer_list *timer, unsigned int flags, + const char *name, struct lock_class_key *key); + +void init_timer_on_stack_key(struct timer_list *timer, unsigned int flags, + const char *name, struct lock_class_key *key) +{ + debug_object_init_on_stack(timer, &timer_debug_descr); + do_init_timer(timer, flags, name, key); +} +EXPORT_SYMBOL_GPL(init_timer_on_stack_key); + +void destroy_timer_on_stack(struct timer_list *timer) +{ + debug_object_free(timer, &timer_debug_descr); +} +EXPORT_SYMBOL_GPL(destroy_timer_on_stack); + +#else +static inline void debug_timer_init(struct timer_list *timer) { } +static inline void debug_timer_activate(struct timer_list *timer) { } +static inline void debug_timer_deactivate(struct timer_list *timer) { } +static inline void debug_timer_assert_init(struct timer_list *timer) { } +#endif + +static inline void debug_init(struct timer_list *timer) +{ + debug_timer_init(timer); + trace_timer_init(timer); +} + +static inline void +debug_activate(struct timer_list *timer, unsigned long expires) +{ + debug_timer_activate(timer); + trace_timer_start(timer, expires); +} + +static inline void debug_deactivate(struct timer_list *timer) +{ + debug_timer_deactivate(timer); + trace_timer_cancel(timer); +} + +static inline void debug_assert_init(struct timer_list *timer) +{ + debug_timer_assert_init(timer); +} + +static void do_init_timer(struct timer_list *timer, unsigned int flags, + const char *name, struct lock_class_key *key) +{ + struct tvec_base *base = raw_cpu_read(tvec_bases); + + timer->entry.next = NULL; + timer->base = (void *)((unsigned long)base | flags); + timer->slack = -1; +#ifdef CONFIG_TIMER_STATS + timer->start_site = NULL; + timer->start_pid = -1; + memset(timer->start_comm, 0, TASK_COMM_LEN); +#endif + lockdep_init_map(&timer->lockdep_map, name, key, 0); +} + +/** + * init_timer_key - initialize a timer + * @timer: the timer to be initialized + * @flags: timer flags + * @name: name of the timer + * @key: lockdep class key of the fake lock used for tracking timer + * sync lock dependencies + * + * init_timer_key() must be done to a timer prior calling *any* of the + * other timer functions. + */ +void init_timer_key(struct timer_list *timer, unsigned int flags, + const char *name, struct lock_class_key *key) +{ + debug_init(timer); + do_init_timer(timer, flags, name, key); +} +EXPORT_SYMBOL(init_timer_key); + +static inline void detach_timer(struct timer_list *timer, bool clear_pending) +{ + struct list_head *entry = &timer->entry; + + debug_deactivate(timer); + + __list_del(entry->prev, entry->next); + if (clear_pending) + entry->next = NULL; + entry->prev = LIST_POISON2; +} + +static inline void +detach_expired_timer(struct timer_list *timer, struct tvec_base *base) +{ + detach_timer(timer, true); + if (!tbase_get_deferrable(timer->base)) + base->active_timers--; + base->all_timers--; + (void)catchup_timer_jiffies(base); +} + +static int detach_if_pending(struct timer_list *timer, struct tvec_base *base, + bool clear_pending) +{ + if (!timer_pending(timer)) + return 0; + + detach_timer(timer, clear_pending); + if (!tbase_get_deferrable(timer->base)) { + base->active_timers--; + if (timer->expires == base->next_timer) + base->next_timer = base->timer_jiffies; + } + base->all_timers--; + (void)catchup_timer_jiffies(base); + return 1; +} + +/* + * We are using hashed locking: holding per_cpu(tvec_bases).lock + * means that all timers which are tied to this base via timer->base are + * locked, and the base itself is locked too. + * + * So __run_timers/migrate_timers can safely modify all timers which could + * be found on ->tvX lists. + * + * When the timer's base is locked, and the timer removed from list, it is + * possible to set timer->base = NULL and drop the lock: the timer remains + * locked. + */ +static struct tvec_base *lock_timer_base(struct timer_list *timer, + unsigned long *flags) + __acquires(timer->base->lock) +{ + struct tvec_base *base; + + for (;;) { + struct tvec_base *prelock_base = timer->base; + base = tbase_get_base(prelock_base); + if (likely(base != NULL)) { + spin_lock_irqsave(&base->lock, *flags); + if (likely(prelock_base == timer->base)) + return base; + /* The timer has migrated to another CPU */ + spin_unlock_irqrestore(&base->lock, *flags); + } + cpu_relax(); + } +} + +#ifndef CONFIG_PREEMPT_RT_FULL +static inline struct tvec_base *switch_timer_base(struct timer_list *timer, + struct tvec_base *old, + struct tvec_base *new) +{ + /* See the comment in lock_timer_base() */ + timer_set_base(timer, NULL); + spin_unlock(&old->lock); + spin_lock(&new->lock); + timer_set_base(timer, new); + return new; +} +#else +static inline struct tvec_base *switch_timer_base(struct timer_list *timer, + struct tvec_base *old, + struct tvec_base *new) +{ + /* + * We cannot do the above because we might be preempted and + * then the preempter would see NULL and loop forever. + */ + if (spin_trylock(&new->lock)) { + timer_set_base(timer, new); + spin_unlock(&old->lock); + return new; + } + return old; +} +#endif + +static inline int +__mod_timer(struct timer_list *timer, unsigned long expires, + bool pending_only, int pinned) +{ + struct tvec_base *base, *new_base; + unsigned long flags; + int ret = 0 , cpu; + + timer_stats_timer_set_start_info(timer); + BUG_ON(!timer->function); + + base = lock_timer_base(timer, &flags); + + ret = detach_if_pending(timer, base, false); + if (!ret && pending_only) + goto out_unlock; + + debug_activate(timer, expires); + + cpu = get_nohz_timer_target(pinned); + new_base = per_cpu(tvec_bases, cpu); + + if (base != new_base) { + /* + * We are trying to schedule the timer on the local CPU. + * However we can't change timer's base while it is running, + * otherwise del_timer_sync() can't detect that the timer's + * handler yet has not finished. This also guarantees that + * the timer is serialized wrt itself. + */ + if (likely(base->running_timer != timer)) + base = switch_timer_base(timer, base, new_base); + } + + timer->expires = expires; + internal_add_timer(base, timer); + +out_unlock: + spin_unlock_irqrestore(&base->lock, flags); + + return ret; +} + +/** + * mod_timer_pending - modify a pending timer's timeout + * @timer: the pending timer to be modified + * @expires: new timeout in jiffies + * + * mod_timer_pending() is the same for pending timers as mod_timer(), + * but will not re-activate and modify already deleted timers. + * + * It is useful for unserialized use of timers. + */ +int mod_timer_pending(struct timer_list *timer, unsigned long expires) +{ + return __mod_timer(timer, expires, true, TIMER_NOT_PINNED); +} +EXPORT_SYMBOL(mod_timer_pending); + +/* + * Decide where to put the timer while taking the slack into account + * + * Algorithm: + * 1) calculate the maximum (absolute) time + * 2) calculate the highest bit where the expires and new max are different + * 3) use this bit to make a mask + * 4) use the bitmask to round down the maximum time, so that all last + * bits are zeros + */ +static inline +unsigned long apply_slack(struct timer_list *timer, unsigned long expires) +{ + unsigned long expires_limit, mask; + int bit; + + if (timer->slack >= 0) { + expires_limit = expires + timer->slack; + } else { + long delta = expires - jiffies; + + if (delta < 256) + return expires; + + expires_limit = expires + delta / 256; + } + mask = expires ^ expires_limit; + if (mask == 0) + return expires; + + bit = find_last_bit(&mask, BITS_PER_LONG); + + mask = (1UL << bit) - 1; + + expires_limit = expires_limit & ~(mask); + + return expires_limit; +} + +/** + * mod_timer - modify a timer's timeout + * @timer: the timer to be modified + * @expires: new timeout in jiffies + * + * mod_timer() is a more efficient way to update the expire field of an + * active timer (if the timer is inactive it will be activated) + * + * mod_timer(timer, expires) is equivalent to: + * + * del_timer(timer); timer->expires = expires; add_timer(timer); + * + * Note that if there are multiple unserialized concurrent users of the + * same timer, then mod_timer() is the only safe way to modify the timeout, + * since add_timer() cannot modify an already running timer. + * + * The function returns whether it has modified a pending timer or not. + * (ie. mod_timer() of an inactive timer returns 0, mod_timer() of an + * active timer returns 1.) + */ +int mod_timer(struct timer_list *timer, unsigned long expires) +{ + expires = apply_slack(timer, expires); + + /* + * This is a common optimization triggered by the + * networking code - if the timer is re-modified + * to be the same thing then just return: + */ + if (timer_pending(timer) && timer->expires == expires) + return 1; + + return __mod_timer(timer, expires, false, TIMER_NOT_PINNED); +} +EXPORT_SYMBOL(mod_timer); + +/** + * mod_timer_pinned - modify a timer's timeout + * @timer: the timer to be modified + * @expires: new timeout in jiffies + * + * mod_timer_pinned() is a way to update the expire field of an + * active timer (if the timer is inactive it will be activated) + * and to ensure that the timer is scheduled on the current CPU. + * + * Note that this does not prevent the timer from being migrated + * when the current CPU goes offline. If this is a problem for + * you, use CPU-hotplug notifiers to handle it correctly, for + * example, cancelling the timer when the corresponding CPU goes + * offline. + * + * mod_timer_pinned(timer, expires) is equivalent to: + * + * del_timer(timer); timer->expires = expires; add_timer(timer); + */ +int mod_timer_pinned(struct timer_list *timer, unsigned long expires) +{ + if (timer->expires == expires && timer_pending(timer)) + return 1; + + return __mod_timer(timer, expires, false, TIMER_PINNED); +} +EXPORT_SYMBOL(mod_timer_pinned); + +/** + * add_timer - start a timer + * @timer: the timer to be added + * + * The kernel will do a ->function(->data) callback from the + * timer interrupt at the ->expires point in the future. The + * current time is 'jiffies'. + * + * The timer's ->expires, ->function (and if the handler uses it, ->data) + * fields must be set prior calling this function. + * + * Timers with an ->expires field in the past will be executed in the next + * timer tick. + */ +void add_timer(struct timer_list *timer) +{ + BUG_ON(timer_pending(timer)); + mod_timer(timer, timer->expires); +} +EXPORT_SYMBOL(add_timer); + +/** + * add_timer_on - start a timer on a particular CPU + * @timer: the timer to be added + * @cpu: the CPU to start it on + * + * This is not very scalable on SMP. Double adds are not possible. + */ +void add_timer_on(struct timer_list *timer, int cpu) +{ + struct tvec_base *base = per_cpu(tvec_bases, cpu); + unsigned long flags; + + timer_stats_timer_set_start_info(timer); + BUG_ON(timer_pending(timer) || !timer->function); + spin_lock_irqsave(&base->lock, flags); + timer_set_base(timer, base); + debug_activate(timer, timer->expires); + internal_add_timer(base, timer); + spin_unlock_irqrestore(&base->lock, flags); +} +EXPORT_SYMBOL_GPL(add_timer_on); + +#ifdef CONFIG_PREEMPT_RT_FULL +/* + * Wait for a running timer + */ +static void wait_for_running_timer(struct timer_list *timer) +{ + struct tvec_base *base = timer->base; + + if (base->running_timer == timer) + wait_event(base->wait_for_running_timer, + base->running_timer != timer); +} + +# define wakeup_timer_waiters(b) wake_up(&(b)->wait_for_running_timer) +#else +static inline void wait_for_running_timer(struct timer_list *timer) +{ + cpu_relax(); +} + +# define wakeup_timer_waiters(b) do { } while (0) +#endif + +/** + * del_timer - deactive a timer. + * @timer: the timer to be deactivated + * + * del_timer() deactivates a timer - this works on both active and inactive + * timers. + * + * The function returns whether it has deactivated a pending timer or not. + * (ie. del_timer() of an inactive timer returns 0, del_timer() of an + * active timer returns 1.) + */ +int del_timer(struct timer_list *timer) +{ + struct tvec_base *base; + unsigned long flags; + int ret = 0; + + debug_assert_init(timer); + + timer_stats_timer_clear_start_info(timer); + if (timer_pending(timer)) { + base = lock_timer_base(timer, &flags); + ret = detach_if_pending(timer, base, true); + spin_unlock_irqrestore(&base->lock, flags); + } + + return ret; +} +EXPORT_SYMBOL(del_timer); + +/** + * try_to_del_timer_sync - Try to deactivate a timer + * @timer: timer do del + * + * This function tries to deactivate a timer. Upon successful (ret >= 0) + * exit the timer is not queued and the handler is not running on any CPU. + */ +int try_to_del_timer_sync(struct timer_list *timer) +{ + struct tvec_base *base; + unsigned long flags; + int ret = -1; + + debug_assert_init(timer); + + base = lock_timer_base(timer, &flags); + + if (base->running_timer != timer) { + timer_stats_timer_clear_start_info(timer); + ret = detach_if_pending(timer, base, true); + } + spin_unlock_irqrestore(&base->lock, flags); + + return ret; +} +EXPORT_SYMBOL(try_to_del_timer_sync); + +#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT_FULL) +static DEFINE_PER_CPU(struct tvec_base, __tvec_bases); + +/** + * del_timer_sync - deactivate a timer and wait for the handler to finish. + * @timer: the timer to be deactivated + * + * This function only differs from del_timer() on SMP: besides deactivating + * the timer it also makes sure the handler has finished executing on other + * CPUs. + * + * Synchronization rules: Callers must prevent restarting of the timer, + * otherwise this function is meaningless. It must not be called from + * interrupt contexts unless the timer is an irqsafe one. The caller must + * not hold locks which would prevent completion of the timer's + * handler. The timer's handler must not call add_timer_on(). Upon exit the + * timer is not queued and the handler is not running on any CPU. + * + * Note: For !irqsafe timers, you must not hold locks that are held in + * interrupt context while calling this function. Even if the lock has + * nothing to do with the timer in question. Here's why: + * + * CPU0 CPU1 + * ---- ---- + * + * call_timer_fn(); + * base->running_timer = mytimer; + * spin_lock_irq(somelock); + * + * spin_lock(somelock); + * del_timer_sync(mytimer); + * while (base->running_timer == mytimer); + * + * Now del_timer_sync() will never return and never release somelock. + * The interrupt on the other CPU is waiting to grab somelock but + * it has interrupted the softirq that CPU0 is waiting to finish. + * + * The function returns whether it has deactivated a pending timer or not. + */ +int del_timer_sync(struct timer_list *timer) +{ +#ifdef CONFIG_LOCKDEP + unsigned long flags; + + /* + * If lockdep gives a backtrace here, please reference + * the synchronization rules above. + */ + local_irq_save(flags); + lock_map_acquire(&timer->lockdep_map); + lock_map_release(&timer->lockdep_map); + local_irq_restore(flags); +#endif + /* + * don't use it in hardirq context, because it + * could lead to deadlock. + */ + WARN_ON(in_irq() && !tbase_get_irqsafe(timer->base)); + for (;;) { + int ret = try_to_del_timer_sync(timer); + if (ret >= 0) + return ret; + wait_for_running_timer(timer); + } +} +EXPORT_SYMBOL(del_timer_sync); +#endif + +static int cascade(struct tvec_base *base, struct tvec *tv, int index) +{ + /* cascade all the timers from tv up one level */ + struct timer_list *timer, *tmp; + struct list_head tv_list; + + list_replace_init(tv->vec + index, &tv_list); + + /* + * We are removing _all_ timers from the list, so we + * don't have to detach them individually. + */ + list_for_each_entry_safe(timer, tmp, &tv_list, entry) { + BUG_ON(tbase_get_base(timer->base) != base); + /* No accounting, while moving them */ + __internal_add_timer(base, timer); + } + + return index; +} + +static void call_timer_fn(struct timer_list *timer, void (*fn)(unsigned long), + unsigned long data) +{ + int count = preempt_count(); + +#ifdef CONFIG_LOCKDEP + /* + * It is permissible to free the timer from inside the + * function that is called from it, this we need to take into + * account for lockdep too. To avoid bogus "held lock freed" + * warnings as well as problems when looking into + * timer->lockdep_map, make a copy and use that here. + */ + struct lockdep_map lockdep_map; + + lockdep_copy_map(&lockdep_map, &timer->lockdep_map); +#endif + /* + * Couple the lock chain with the lock chain at + * del_timer_sync() by acquiring the lock_map around the fn() + * call here and in del_timer_sync(). + */ + lock_map_acquire(&lockdep_map); + + trace_timer_expire_entry(timer); + fn(data); + trace_timer_expire_exit(timer); + + lock_map_release(&lockdep_map); + + if (count != preempt_count()) { + WARN_ONCE(1, "timer: %pF preempt leak: %08x -> %08x\n", + fn, count, preempt_count()); + /* + * Restore the preempt count. That gives us a decent + * chance to survive and extract information. If the + * callback kept a lock held, bad luck, but not worse + * than the BUG() we had. + */ + preempt_count_set(count); + } +} + +#define INDEX(N) ((base->timer_jiffies >> (TVR_BITS + (N) * TVN_BITS)) & TVN_MASK) + +/** + * __run_timers - run all expired timers (if any) on this CPU. + * @base: the timer vector to be processed. + * + * This function cascades all vectors and executes all expired timer + * vectors. + */ +static inline void __run_timers(struct tvec_base *base) +{ + struct timer_list *timer; + + spin_lock_irq(&base->lock); + if (catchup_timer_jiffies(base)) { + spin_unlock_irq(&base->lock); + return; + } + while (time_after_eq(jiffies, base->timer_jiffies)) { + struct list_head work_list; + struct list_head *head = &work_list; + int index = base->timer_jiffies & TVR_MASK; + + /* + * Cascade timers: + */ + if (!index && + (!cascade(base, &base->tv2, INDEX(0))) && + (!cascade(base, &base->tv3, INDEX(1))) && + !cascade(base, &base->tv4, INDEX(2))) + cascade(base, &base->tv5, INDEX(3)); + ++base->timer_jiffies; + list_replace_init(base->tv1.vec + index, head); + while (!list_empty(head)) { + void (*fn)(unsigned long); + unsigned long data; + bool irqsafe; + + timer = list_first_entry(head, struct timer_list,entry); + fn = timer->function; + data = timer->data; + irqsafe = tbase_get_irqsafe(timer->base); + + timer_stats_account_timer(timer); + + base->running_timer = timer; + detach_expired_timer(timer, base); + + if (irqsafe) { + spin_unlock(&base->lock); + call_timer_fn(timer, fn, data); + base->running_timer = NULL; + spin_lock(&base->lock); + } else { + spin_unlock_irq(&base->lock); + call_timer_fn(timer, fn, data); + base->running_timer = NULL; + spin_lock_irq(&base->lock); + } + } + } + wakeup_timer_waiters(base); + spin_unlock_irq(&base->lock); +} + +#ifdef CONFIG_NO_HZ_COMMON +/* + * Find out when the next timer event is due to happen. This + * is used on S/390 to stop all activity when a CPU is idle. + * This function needs to be called with interrupts disabled. + */ +static unsigned long __next_timer_interrupt(struct tvec_base *base) +{ + unsigned long timer_jiffies = base->timer_jiffies; + unsigned long expires = timer_jiffies + NEXT_TIMER_MAX_DELTA; + int index, slot, array, found = 0; + struct timer_list *nte; + struct tvec *varray[4]; + + /* Look for timer events in tv1. */ + index = slot = timer_jiffies & TVR_MASK; + do { + list_for_each_entry(nte, base->tv1.vec + slot, entry) { + if (tbase_get_deferrable(nte->base)) + continue; + + found = 1; + expires = nte->expires; + /* Look at the cascade bucket(s)? */ + if (!index || slot < index) + goto cascade; + return expires; + } + slot = (slot + 1) & TVR_MASK; + } while (slot != index); + +cascade: + /* Calculate the next cascade event */ + if (index) + timer_jiffies += TVR_SIZE - index; + timer_jiffies >>= TVR_BITS; + + /* Check tv2-tv5. */ + varray[0] = &base->tv2; + varray[1] = &base->tv3; + varray[2] = &base->tv4; + varray[3] = &base->tv5; + + for (array = 0; array < 4; array++) { + struct tvec *varp = varray[array]; + + index = slot = timer_jiffies & TVN_MASK; + do { + list_for_each_entry(nte, varp->vec + slot, entry) { + if (tbase_get_deferrable(nte->base)) + continue; + + found = 1; + if (time_before(nte->expires, expires)) + expires = nte->expires; + } + /* + * Do we still search for the first timer or are + * we looking up the cascade buckets ? + */ + if (found) { + /* Look at the cascade bucket(s)? */ + if (!index || slot < index) + break; + return expires; + } + slot = (slot + 1) & TVN_MASK; + } while (slot != index); + + if (index) + timer_jiffies += TVN_SIZE - index; + timer_jiffies >>= TVN_BITS; + } + return expires; +} + +/* + * Check, if the next hrtimer event is before the next timer wheel + * event: + */ +static unsigned long cmp_next_hrtimer_event(unsigned long now, + unsigned long expires) +{ + ktime_t hr_delta = hrtimer_get_next_event(); + struct timespec tsdelta; + unsigned long delta; + + if (hr_delta.tv64 == KTIME_MAX) + return expires; + + /* + * Expired timer available, let it expire in the next tick + */ + if (hr_delta.tv64 <= 0) + return now + 1; + + tsdelta = ktime_to_timespec(hr_delta); + delta = timespec_to_jiffies(&tsdelta); + + /* + * Limit the delta to the max value, which is checked in + * tick_nohz_stop_sched_tick(): + */ + if (delta > NEXT_TIMER_MAX_DELTA) + delta = NEXT_TIMER_MAX_DELTA; + + /* + * Take rounding errors in to account and make sure, that it + * expires in the next tick. Otherwise we go into an endless + * ping pong due to tick_nohz_stop_sched_tick() retriggering + * the timer softirq + */ + if (delta < 1) + delta = 1; + now += delta; + if (time_before(now, expires)) + return now; + return expires; +} + +/** + * get_next_timer_interrupt - return the jiffy of the next pending timer + * @now: current time (in jiffies) + */ +unsigned long get_next_timer_interrupt(unsigned long now) +{ + struct tvec_base *base = __this_cpu_read(tvec_bases); + unsigned long expires = now + NEXT_TIMER_MAX_DELTA; + + /* + * Pretend that there is no timer pending if the cpu is offline. + * Possible pending timers will be migrated later to an active cpu. + */ + if (cpu_is_offline(smp_processor_id())) + return expires; + +#ifdef CONFIG_PREEMPT_RT_FULL + /* + * On PREEMPT_RT we cannot sleep here. As a result we can't take + * the base lock to check when the next timer is pending and so + * we assume the next jiffy. + */ + return now + 1; +#endif + spin_lock(&base->lock); + if (base->active_timers) { + if (time_before_eq(base->next_timer, base->timer_jiffies)) + base->next_timer = __next_timer_interrupt(base); + expires = base->next_timer; + } + spin_unlock(&base->lock); + + if (time_before_eq(expires, now)) + return now; + + return cmp_next_hrtimer_event(now, expires); +} +#endif + +/* + * Called from the timer interrupt handler to charge one tick to the current + * process. user_tick is 1 if the tick is user time, 0 for system. + */ +void update_process_times(int user_tick) +{ + struct task_struct *p = current; + + /* Note: this timer irq context must be accounted for as well. */ + account_process_tick(p, user_tick); + scheduler_tick(); + run_local_timers(); + rcu_check_callbacks(user_tick); +#if defined(CONFIG_IRQ_WORK) && !defined(CONFIG_PREEMPT_RT_FULL) + if (in_irq()) + irq_work_tick(); +#endif + run_posix_cpu_timers(p); +} + +/* + * This function runs timers and the timer-tq in bottom half context. + */ +static void run_timer_softirq(struct softirq_action *h) +{ + struct tvec_base *base = __this_cpu_read(tvec_bases); + + hrtimer_run_pending(); + +#if defined(CONFIG_IRQ_WORK) && defined(CONFIG_PREEMPT_RT_FULL) + irq_work_tick(); +#endif + + if (time_after_eq(jiffies, base->timer_jiffies)) + __run_timers(base); +} + +/* + * Called by the local, per-CPU timer interrupt on SMP. + */ +void run_local_timers(void) +{ + hrtimer_run_queues(); + raise_softirq(TIMER_SOFTIRQ); +} + +#ifdef __ARCH_WANT_SYS_ALARM + +/* + * For backwards compatibility? This can be done in libc so Alpha + * and all newer ports shouldn't need it. + */ +SYSCALL_DEFINE1(alarm, unsigned int, seconds) +{ + return alarm_setitimer(seconds); +} + +#endif + +static void process_timeout(unsigned long __data) +{ + wake_up_process((struct task_struct *)__data); +} + +/** + * schedule_timeout - sleep until timeout + * @timeout: timeout value in jiffies + * + * Make the current task sleep until @timeout jiffies have + * elapsed. The routine will return immediately unless + * the current task state has been set (see set_current_state()). + * + * You can set the task state as follows - + * + * %TASK_UNINTERRUPTIBLE - at least @timeout jiffies are guaranteed to + * pass before the routine returns. The routine will return 0 + * + * %TASK_INTERRUPTIBLE - the routine may return early if a signal is + * delivered to the current task. In this case the remaining time + * in jiffies will be returned, or 0 if the timer expired in time + * + * The current task state is guaranteed to be TASK_RUNNING when this + * routine returns. + * + * Specifying a @timeout value of %MAX_SCHEDULE_TIMEOUT will schedule + * the CPU away without a bound on the timeout. In this case the return + * value will be %MAX_SCHEDULE_TIMEOUT. + * + * In all cases the return value is guaranteed to be non-negative. + */ +signed long __sched schedule_timeout(signed long timeout) +{ + struct timer_list timer; + unsigned long expire; + + switch (timeout) + { + case MAX_SCHEDULE_TIMEOUT: + /* + * These two special cases are useful to be comfortable + * in the caller. Nothing more. We could take + * MAX_SCHEDULE_TIMEOUT from one of the negative value + * but I' d like to return a valid offset (>=0) to allow + * the caller to do everything it want with the retval. + */ + schedule(); + goto out; + default: + /* + * Another bit of PARANOID. Note that the retval will be + * 0 since no piece of kernel is supposed to do a check + * for a negative retval of schedule_timeout() (since it + * should never happens anyway). You just have the printk() + * that will tell you if something is gone wrong and where. + */ + if (timeout < 0) { + printk(KERN_ERR "schedule_timeout: wrong timeout " + "value %lx\n", timeout); + dump_stack(); + current->state = TASK_RUNNING; + goto out; + } + } + + expire = timeout + jiffies; + + setup_timer_on_stack(&timer, process_timeout, (unsigned long)current); + __mod_timer(&timer, expire, false, TIMER_NOT_PINNED); + schedule(); + del_singleshot_timer_sync(&timer); + + /* Remove the timer from the object tracker */ + destroy_timer_on_stack(&timer); + + timeout = expire - jiffies; + + out: + return timeout < 0 ? 0 : timeout; +} +EXPORT_SYMBOL(schedule_timeout); + +/* + * We can use __set_current_state() here because schedule_timeout() calls + * schedule() unconditionally. + */ +signed long __sched schedule_timeout_interruptible(signed long timeout) +{ + __set_current_state(TASK_INTERRUPTIBLE); + return schedule_timeout(timeout); +} +EXPORT_SYMBOL(schedule_timeout_interruptible); + +signed long __sched schedule_timeout_killable(signed long timeout) +{ + __set_current_state(TASK_KILLABLE); + return schedule_timeout(timeout); +} +EXPORT_SYMBOL(schedule_timeout_killable); + +signed long __sched schedule_timeout_uninterruptible(signed long timeout) +{ + __set_current_state(TASK_UNINTERRUPTIBLE); + return schedule_timeout(timeout); +} +EXPORT_SYMBOL(schedule_timeout_uninterruptible); + +#ifdef CONFIG_HOTPLUG_CPU +static void migrate_timer_list(struct tvec_base *new_base, struct list_head *head) +{ + struct timer_list *timer; + + while (!list_empty(head)) { + timer = list_first_entry(head, struct timer_list, entry); + /* We ignore the accounting on the dying cpu */ + detach_timer(timer, false); + timer_set_base(timer, new_base); + internal_add_timer(new_base, timer); + } +} + +static void migrate_timers(int cpu) +{ + struct tvec_base *old_base; + struct tvec_base *new_base; + int i; + + BUG_ON(cpu_online(cpu)); + old_base = per_cpu(tvec_bases, cpu); + new_base = get_local_var(tvec_bases); + /* + * The caller is globally serialized and nobody else + * takes two locks at once, deadlock is not possible. + */ + spin_lock_irq(&new_base->lock); + spin_lock_nested(&old_base->lock, SINGLE_DEPTH_NESTING); + + BUG_ON(old_base->running_timer); + + for (i = 0; i < TVR_SIZE; i++) + migrate_timer_list(new_base, old_base->tv1.vec + i); + for (i = 0; i < TVN_SIZE; i++) { + migrate_timer_list(new_base, old_base->tv2.vec + i); + migrate_timer_list(new_base, old_base->tv3.vec + i); + migrate_timer_list(new_base, old_base->tv4.vec + i); + migrate_timer_list(new_base, old_base->tv5.vec + i); + } + + old_base->active_timers = 0; + old_base->all_timers = 0; + + spin_unlock(&old_base->lock); + spin_unlock_irq(&new_base->lock); + put_local_var(tvec_bases); +} + +static int timer_cpu_notify(struct notifier_block *self, + unsigned long action, void *hcpu) +{ + switch (action) { + case CPU_DEAD: + case CPU_DEAD_FROZEN: + migrate_timers((long)hcpu); + break; + default: + break; + } + + return NOTIFY_OK; +} + +static inline void timer_register_cpu_notifier(void) +{ + cpu_notifier(timer_cpu_notify, 0); +} +#else +static inline void timer_register_cpu_notifier(void) { } +#endif /* CONFIG_HOTPLUG_CPU */ + +static void __init init_timer_cpu(struct tvec_base *base, int cpu) +{ + int j; + + BUG_ON(base != tbase_get_base(base)); + + base->cpu = cpu; + per_cpu(tvec_bases, cpu) = base; + spin_lock_init(&base->lock); +#ifdef CONFIG_PREEMPT_RT_FULL + init_waitqueue_head(&base->wait_for_running_timer); +#endif + + for (j = 0; j < TVN_SIZE; j++) { + INIT_LIST_HEAD(base->tv5.vec + j); + INIT_LIST_HEAD(base->tv4.vec + j); + INIT_LIST_HEAD(base->tv3.vec + j); + INIT_LIST_HEAD(base->tv2.vec + j); + } + for (j = 0; j < TVR_SIZE; j++) + INIT_LIST_HEAD(base->tv1.vec + j); + + base->timer_jiffies = jiffies; + base->next_timer = base->timer_jiffies; +} + +static void __init init_timer_cpus(void) +{ + struct tvec_base *base; + int local_cpu = smp_processor_id(); + int cpu; + + for_each_possible_cpu(cpu) { + if (cpu == local_cpu) + base = &boot_tvec_bases; +#ifdef CONFIG_SMP + else + base = per_cpu_ptr(&__tvec_bases, cpu); +#endif + + init_timer_cpu(base, cpu); + } +} + +void __init init_timers(void) +{ + /* ensure there are enough low bits for flags in timer->base pointer */ + BUILD_BUG_ON(__alignof__(struct tvec_base) & TIMER_FLAG_MASK); + + init_timer_cpus(); + init_timer_stats(); + timer_register_cpu_notifier(); + open_softirq(TIMER_SOFTIRQ, run_timer_softirq); +} + +/** + * msleep - sleep safely even with waitqueue interruptions + * @msecs: Time in milliseconds to sleep for + */ +void msleep(unsigned int msecs) +{ + unsigned long timeout = msecs_to_jiffies(msecs) + 1; + + while (timeout) + timeout = schedule_timeout_uninterruptible(timeout); +} + +EXPORT_SYMBOL(msleep); + +/** + * msleep_interruptible - sleep waiting for signals + * @msecs: Time in milliseconds to sleep for + */ +unsigned long msleep_interruptible(unsigned int msecs) +{ + unsigned long timeout = msecs_to_jiffies(msecs) + 1; + + while (timeout && !signal_pending(current)) + timeout = schedule_timeout_interruptible(timeout); + return jiffies_to_msecs(timeout); +} + +EXPORT_SYMBOL(msleep_interruptible); + +static int __sched do_usleep_range(unsigned long min, unsigned long max) +{ + ktime_t kmin; + unsigned long delta; + + kmin = ktime_set(0, min * NSEC_PER_USEC); + delta = (max - min) * NSEC_PER_USEC; + return schedule_hrtimeout_range(&kmin, delta, HRTIMER_MODE_REL); +} + +/** + * usleep_range - Drop in replacement for udelay where wakeup is flexible + * @min: Minimum time in usecs to sleep + * @max: Maximum time in usecs to sleep + */ +void usleep_range(unsigned long min, unsigned long max) +{ + __set_current_state(TASK_UNINTERRUPTIBLE); + do_usleep_range(min, max); +} +EXPORT_SYMBOL(usleep_range); diff --git a/kernel/kernel/time/timer_list.c b/kernel/kernel/time/timer_list.c new file mode 100644 index 000000000..e878c2e0b --- /dev/null +++ b/kernel/kernel/time/timer_list.c @@ -0,0 +1,396 @@ +/* + * kernel/time/timer_list.c + * + * List pending timers + * + * Copyright(C) 2006, Red Hat, Inc., Ingo Molnar + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include +#include +#include +#include +#include +#include + +#include + +#include "tick-internal.h" + +struct timer_list_iter { + int cpu; + bool second_pass; + u64 now; +}; + +typedef void (*print_fn_t)(struct seq_file *m, unsigned int *classes); + +DECLARE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases); + +/* + * This allows printing both to /proc/timer_list and + * to the console (on SysRq-Q): + */ +#define SEQ_printf(m, x...) \ + do { \ + if (m) \ + seq_printf(m, x); \ + else \ + printk(x); \ + } while (0) + +static void print_name_offset(struct seq_file *m, void *sym) +{ + char symname[KSYM_NAME_LEN]; + + if (lookup_symbol_name((unsigned long)sym, symname) < 0) + SEQ_printf(m, "<%pK>", sym); + else + SEQ_printf(m, "%s", symname); +} + +static void +print_timer(struct seq_file *m, struct hrtimer *taddr, struct hrtimer *timer, + int idx, u64 now) +{ +#ifdef CONFIG_TIMER_STATS + char tmp[TASK_COMM_LEN + 1]; +#endif + SEQ_printf(m, " #%d: ", idx); + print_name_offset(m, taddr); + SEQ_printf(m, ", "); + print_name_offset(m, timer->function); + SEQ_printf(m, ", S:%02lx", timer->state); +#ifdef CONFIG_TIMER_STATS + SEQ_printf(m, ", "); + print_name_offset(m, timer->start_site); + memcpy(tmp, timer->start_comm, TASK_COMM_LEN); + tmp[TASK_COMM_LEN] = 0; + SEQ_printf(m, ", %s/%d", tmp, timer->start_pid); +#endif + SEQ_printf(m, "\n"); + SEQ_printf(m, " # expires at %Lu-%Lu nsecs [in %Ld to %Ld nsecs]\n", + (unsigned long long)ktime_to_ns(hrtimer_get_softexpires(timer)), + (unsigned long long)ktime_to_ns(hrtimer_get_expires(timer)), + (long long)(ktime_to_ns(hrtimer_get_softexpires(timer)) - now), + (long long)(ktime_to_ns(hrtimer_get_expires(timer)) - now)); +} + +static void +print_active_timers(struct seq_file *m, struct hrtimer_clock_base *base, + u64 now) +{ + struct hrtimer *timer, tmp; + unsigned long next = 0, i; + struct timerqueue_node *curr; + unsigned long flags; + +next_one: + i = 0; + raw_spin_lock_irqsave(&base->cpu_base->lock, flags); + + curr = timerqueue_getnext(&base->active); + /* + * Crude but we have to do this O(N*N) thing, because + * we have to unlock the base when printing: + */ + while (curr && i < next) { + curr = timerqueue_iterate_next(curr); + i++; + } + + if (curr) { + + timer = container_of(curr, struct hrtimer, node); + tmp = *timer; + raw_spin_unlock_irqrestore(&base->cpu_base->lock, flags); + + print_timer(m, timer, &tmp, i, now); + next++; + goto next_one; + } + raw_spin_unlock_irqrestore(&base->cpu_base->lock, flags); +} + +static void +print_base(struct seq_file *m, struct hrtimer_clock_base *base, u64 now) +{ + SEQ_printf(m, " .base: %pK\n", base); + SEQ_printf(m, " .index: %d\n", + base->index); + SEQ_printf(m, " .resolution: %Lu nsecs\n", + (unsigned long long)ktime_to_ns(base->resolution)); + SEQ_printf(m, " .get_time: "); + print_name_offset(m, base->get_time); + SEQ_printf(m, "\n"); +#ifdef CONFIG_HIGH_RES_TIMERS + SEQ_printf(m, " .offset: %Lu nsecs\n", + (unsigned long long) ktime_to_ns(base->offset)); +#endif + SEQ_printf(m, "active timers:\n"); + print_active_timers(m, base, now); +} + +static void print_cpu(struct seq_file *m, int cpu, u64 now) +{ + struct hrtimer_cpu_base *cpu_base = &per_cpu(hrtimer_bases, cpu); + int i; + + SEQ_printf(m, "cpu: %d\n", cpu); + for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) { + SEQ_printf(m, " clock %d:\n", i); + print_base(m, cpu_base->clock_base + i, now); + } +#define P(x) \ + SEQ_printf(m, " .%-15s: %Lu\n", #x, \ + (unsigned long long)(cpu_base->x)) +#define P_ns(x) \ + SEQ_printf(m, " .%-15s: %Lu nsecs\n", #x, \ + (unsigned long long)(ktime_to_ns(cpu_base->x))) + +#ifdef CONFIG_HIGH_RES_TIMERS + P_ns(expires_next); + P(hres_active); + P(nr_events); + P(nr_retries); + P(nr_hangs); + P_ns(max_hang_time); +#endif +#undef P +#undef P_ns + +#ifdef CONFIG_TICK_ONESHOT +# define P(x) \ + SEQ_printf(m, " .%-15s: %Lu\n", #x, \ + (unsigned long long)(ts->x)) +# define P_ns(x) \ + SEQ_printf(m, " .%-15s: %Lu nsecs\n", #x, \ + (unsigned long long)(ktime_to_ns(ts->x))) + { + struct tick_sched *ts = tick_get_tick_sched(cpu); + P(nohz_mode); + P_ns(last_tick); + P(tick_stopped); + P(idle_jiffies); + P(idle_calls); + P(idle_sleeps); + P_ns(idle_entrytime); + P_ns(idle_waketime); + P_ns(idle_exittime); + P_ns(idle_sleeptime); + P_ns(iowait_sleeptime); + P(last_jiffies); + P(next_jiffies); + P_ns(idle_expires); + SEQ_printf(m, "jiffies: %Lu\n", + (unsigned long long)jiffies); + } +#endif + +#undef P +#undef P_ns + SEQ_printf(m, "\n"); +} + +#ifdef CONFIG_GENERIC_CLOCKEVENTS +static void +print_tickdevice(struct seq_file *m, struct tick_device *td, int cpu) +{ + struct clock_event_device *dev = td->evtdev; + + SEQ_printf(m, "Tick Device: mode: %d\n", td->mode); + if (cpu < 0) + SEQ_printf(m, "Broadcast device\n"); + else + SEQ_printf(m, "Per CPU device: %d\n", cpu); + + SEQ_printf(m, "Clock Event Device: "); + if (!dev) { + SEQ_printf(m, "\n"); + return; + } + SEQ_printf(m, "%s\n", dev->name); + SEQ_printf(m, " max_delta_ns: %llu\n", + (unsigned long long) dev->max_delta_ns); + SEQ_printf(m, " min_delta_ns: %llu\n", + (unsigned long long) dev->min_delta_ns); + SEQ_printf(m, " mult: %u\n", dev->mult); + SEQ_printf(m, " shift: %u\n", dev->shift); + SEQ_printf(m, " mode: %d\n", dev->mode); + SEQ_printf(m, " next_event: %Ld nsecs\n", + (unsigned long long) ktime_to_ns(dev->next_event)); + + SEQ_printf(m, " set_next_event: "); + print_name_offset(m, dev->set_next_event); + SEQ_printf(m, "\n"); + + if (dev->set_mode) { + SEQ_printf(m, " set_mode: "); + print_name_offset(m, dev->set_mode); + SEQ_printf(m, "\n"); + } else { + if (dev->set_state_shutdown) { + SEQ_printf(m, " shutdown: "); + print_name_offset(m, dev->set_state_shutdown); + SEQ_printf(m, "\n"); + } + + if (dev->set_state_periodic) { + SEQ_printf(m, " periodic: "); + print_name_offset(m, dev->set_state_periodic); + SEQ_printf(m, "\n"); + } + + if (dev->set_state_oneshot) { + SEQ_printf(m, " oneshot: "); + print_name_offset(m, dev->set_state_oneshot); + SEQ_printf(m, "\n"); + } + + if (dev->tick_resume) { + SEQ_printf(m, " resume: "); + print_name_offset(m, dev->tick_resume); + SEQ_printf(m, "\n"); + } + } + + SEQ_printf(m, " event_handler: "); + print_name_offset(m, dev->event_handler); + SEQ_printf(m, "\n"); + SEQ_printf(m, " retries: %lu\n", dev->retries); + SEQ_printf(m, "\n"); +} + +static void timer_list_show_tickdevices_header(struct seq_file *m) +{ +#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST + print_tickdevice(m, tick_get_broadcast_device(), -1); + SEQ_printf(m, "tick_broadcast_mask: %08lx\n", + cpumask_bits(tick_get_broadcast_mask())[0]); +#ifdef CONFIG_TICK_ONESHOT + SEQ_printf(m, "tick_broadcast_oneshot_mask: %08lx\n", + cpumask_bits(tick_get_broadcast_oneshot_mask())[0]); +#endif + SEQ_printf(m, "\n"); +#endif +} +#endif + +static inline void timer_list_header(struct seq_file *m, u64 now) +{ + SEQ_printf(m, "Timer List Version: v0.7\n"); + SEQ_printf(m, "HRTIMER_MAX_CLOCK_BASES: %d\n", HRTIMER_MAX_CLOCK_BASES); + SEQ_printf(m, "now at %Ld nsecs\n", (unsigned long long)now); + SEQ_printf(m, "\n"); +} + +static int timer_list_show(struct seq_file *m, void *v) +{ + struct timer_list_iter *iter = v; + + if (iter->cpu == -1 && !iter->second_pass) + timer_list_header(m, iter->now); + else if (!iter->second_pass) + print_cpu(m, iter->cpu, iter->now); +#ifdef CONFIG_GENERIC_CLOCKEVENTS + else if (iter->cpu == -1 && iter->second_pass) + timer_list_show_tickdevices_header(m); + else + print_tickdevice(m, tick_get_device(iter->cpu), iter->cpu); +#endif + return 0; +} + +void sysrq_timer_list_show(void) +{ + u64 now = ktime_to_ns(ktime_get()); + int cpu; + + timer_list_header(NULL, now); + + for_each_online_cpu(cpu) + print_cpu(NULL, cpu, now); + +#ifdef CONFIG_GENERIC_CLOCKEVENTS + timer_list_show_tickdevices_header(NULL); + for_each_online_cpu(cpu) + print_tickdevice(NULL, tick_get_device(cpu), cpu); +#endif + return; +} + +static void *move_iter(struct timer_list_iter *iter, loff_t offset) +{ + for (; offset; offset--) { + iter->cpu = cpumask_next(iter->cpu, cpu_online_mask); + if (iter->cpu >= nr_cpu_ids) { +#ifdef CONFIG_GENERIC_CLOCKEVENTS + if (!iter->second_pass) { + iter->cpu = -1; + iter->second_pass = true; + } else + return NULL; +#else + return NULL; +#endif + } + } + return iter; +} + +static void *timer_list_start(struct seq_file *file, loff_t *offset) +{ + struct timer_list_iter *iter = file->private; + + if (!*offset) + iter->now = ktime_to_ns(ktime_get()); + iter->cpu = -1; + iter->second_pass = false; + return move_iter(iter, *offset); +} + +static void *timer_list_next(struct seq_file *file, void *v, loff_t *offset) +{ + struct timer_list_iter *iter = file->private; + ++*offset; + return move_iter(iter, 1); +} + +static void timer_list_stop(struct seq_file *seq, void *v) +{ +} + +static const struct seq_operations timer_list_sops = { + .start = timer_list_start, + .next = timer_list_next, + .stop = timer_list_stop, + .show = timer_list_show, +}; + +static int timer_list_open(struct inode *inode, struct file *filp) +{ + return seq_open_private(filp, &timer_list_sops, + sizeof(struct timer_list_iter)); +} + +static const struct file_operations timer_list_fops = { + .open = timer_list_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release_private, +}; + +static int __init init_timer_list_procfs(void) +{ + struct proc_dir_entry *pe; + + pe = proc_create("timer_list", 0444, NULL, &timer_list_fops); + if (!pe) + return -ENOMEM; + return 0; +} +__initcall(init_timer_list_procfs); diff --git a/kernel/kernel/time/timer_stats.c b/kernel/kernel/time/timer_stats.c new file mode 100644 index 000000000..1fb08f213 --- /dev/null +++ b/kernel/kernel/time/timer_stats.c @@ -0,0 +1,425 @@ +/* + * kernel/time/timer_stats.c + * + * Collect timer usage statistics. + * + * Copyright(C) 2006, Red Hat, Inc., Ingo Molnar + * Copyright(C) 2006 Timesys Corp., Thomas Gleixner + * + * timer_stats is based on timer_top, a similar functionality which was part of + * Con Kolivas dyntick patch set. It was developed by Daniel Petrini at the + * Instituto Nokia de Tecnologia - INdT - Manaus. timer_top's design was based + * on dynamic allocation of the statistics entries and linear search based + * lookup combined with a global lock, rather than the static array, hash + * and per-CPU locking which is used by timer_stats. It was written for the + * pre hrtimer kernel code and therefore did not take hrtimers into account. + * Nevertheless it provided the base for the timer_stats implementation and + * was a helpful source of inspiration. Kudos to Daniel and the Nokia folks + * for this effort. + * + * timer_top.c is + * Copyright (C) 2005 Instituto Nokia de Tecnologia - INdT - Manaus + * Written by Daniel Petrini + * timer_top.c was released under the GNU General Public License version 2 + * + * We export the addresses and counting of timer functions being called, + * the pid and cmdline from the owner process if applicable. + * + * Start/stop data collection: + * # echo [1|0] >/proc/timer_stats + * + * Display the information collected so far: + * # cat /proc/timer_stats + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include +#include +#include +#include +#include +#include + +#include + +/* + * This is our basic unit of interest: a timer expiry event identified + * by the timer, its start/expire functions and the PID of the task that + * started the timer. We count the number of times an event happens: + */ +struct entry { + /* + * Hash list: + */ + struct entry *next; + + /* + * Hash keys: + */ + void *timer; + void *start_func; + void *expire_func; + pid_t pid; + + /* + * Number of timeout events: + */ + unsigned long count; + unsigned int timer_flag; + + /* + * We save the command-line string to preserve + * this information past task exit: + */ + char comm[TASK_COMM_LEN + 1]; + +} ____cacheline_aligned_in_smp; + +/* + * Spinlock protecting the tables - not taken during lookup: + */ +static DEFINE_RAW_SPINLOCK(table_lock); + +/* + * Per-CPU lookup locks for fast hash lookup: + */ +static DEFINE_PER_CPU(raw_spinlock_t, tstats_lookup_lock); + +/* + * Mutex to serialize state changes with show-stats activities: + */ +static DEFINE_MUTEX(show_mutex); + +/* + * Collection status, active/inactive: + */ +int __read_mostly timer_stats_active; + +/* + * Beginning/end timestamps of measurement: + */ +static ktime_t time_start, time_stop; + +/* + * tstat entry structs only get allocated while collection is + * active and never freed during that time - this simplifies + * things quite a bit. + * + * They get freed when a new collection period is started. + */ +#define MAX_ENTRIES_BITS 10 +#define MAX_ENTRIES (1UL << MAX_ENTRIES_BITS) + +static unsigned long nr_entries; +static struct entry entries[MAX_ENTRIES]; + +static atomic_t overflow_count; + +/* + * The entries are in a hash-table, for fast lookup: + */ +#define TSTAT_HASH_BITS (MAX_ENTRIES_BITS - 1) +#define TSTAT_HASH_SIZE (1UL << TSTAT_HASH_BITS) +#define TSTAT_HASH_MASK (TSTAT_HASH_SIZE - 1) + +#define __tstat_hashfn(entry) \ + (((unsigned long)(entry)->timer ^ \ + (unsigned long)(entry)->start_func ^ \ + (unsigned long)(entry)->expire_func ^ \ + (unsigned long)(entry)->pid ) & TSTAT_HASH_MASK) + +#define tstat_hashentry(entry) (tstat_hash_table + __tstat_hashfn(entry)) + +static struct entry *tstat_hash_table[TSTAT_HASH_SIZE] __read_mostly; + +static void reset_entries(void) +{ + nr_entries = 0; + memset(entries, 0, sizeof(entries)); + memset(tstat_hash_table, 0, sizeof(tstat_hash_table)); + atomic_set(&overflow_count, 0); +} + +static struct entry *alloc_entry(void) +{ + if (nr_entries >= MAX_ENTRIES) + return NULL; + + return entries + nr_entries++; +} + +static int match_entries(struct entry *entry1, struct entry *entry2) +{ + return entry1->timer == entry2->timer && + entry1->start_func == entry2->start_func && + entry1->expire_func == entry2->expire_func && + entry1->pid == entry2->pid; +} + +/* + * Look up whether an entry matching this item is present + * in the hash already. Must be called with irqs off and the + * lookup lock held: + */ +static struct entry *tstat_lookup(struct entry *entry, char *comm) +{ + struct entry **head, *curr, *prev; + + head = tstat_hashentry(entry); + curr = *head; + + /* + * The fastpath is when the entry is already hashed, + * we do this with the lookup lock held, but with the + * table lock not held: + */ + while (curr) { + if (match_entries(curr, entry)) + return curr; + + curr = curr->next; + } + /* + * Slowpath: allocate, set up and link a new hash entry: + */ + prev = NULL; + curr = *head; + + raw_spin_lock(&table_lock); + /* + * Make sure we have not raced with another CPU: + */ + while (curr) { + if (match_entries(curr, entry)) + goto out_unlock; + + prev = curr; + curr = curr->next; + } + + curr = alloc_entry(); + if (curr) { + *curr = *entry; + curr->count = 0; + curr->next = NULL; + memcpy(curr->comm, comm, TASK_COMM_LEN); + + smp_mb(); /* Ensure that curr is initialized before insert */ + + if (prev) + prev->next = curr; + else + *head = curr; + } + out_unlock: + raw_spin_unlock(&table_lock); + + return curr; +} + +/** + * timer_stats_update_stats - Update the statistics for a timer. + * @timer: pointer to either a timer_list or a hrtimer + * @pid: the pid of the task which set up the timer + * @startf: pointer to the function which did the timer setup + * @timerf: pointer to the timer callback function of the timer + * @comm: name of the process which set up the timer + * + * When the timer is already registered, then the event counter is + * incremented. Otherwise the timer is registered in a free slot. + */ +void timer_stats_update_stats(void *timer, pid_t pid, void *startf, + void *timerf, char *comm, + unsigned int timer_flag) +{ + /* + * It doesn't matter which lock we take: + */ + raw_spinlock_t *lock; + struct entry *entry, input; + unsigned long flags; + + if (likely(!timer_stats_active)) + return; + + lock = &per_cpu(tstats_lookup_lock, raw_smp_processor_id()); + + input.timer = timer; + input.start_func = startf; + input.expire_func = timerf; + input.pid = pid; + input.timer_flag = timer_flag; + + raw_spin_lock_irqsave(lock, flags); + if (!timer_stats_active) + goto out_unlock; + + entry = tstat_lookup(&input, comm); + if (likely(entry)) + entry->count++; + else + atomic_inc(&overflow_count); + + out_unlock: + raw_spin_unlock_irqrestore(lock, flags); +} + +static void print_name_offset(struct seq_file *m, unsigned long addr) +{ + char symname[KSYM_NAME_LEN]; + + if (lookup_symbol_name(addr, symname) < 0) + seq_printf(m, "<%p>", (void *)addr); + else + seq_printf(m, "%s", symname); +} + +static int tstats_show(struct seq_file *m, void *v) +{ + struct timespec period; + struct entry *entry; + unsigned long ms; + long events = 0; + ktime_t time; + int i; + + mutex_lock(&show_mutex); + /* + * If still active then calculate up to now: + */ + if (timer_stats_active) + time_stop = ktime_get(); + + time = ktime_sub(time_stop, time_start); + + period = ktime_to_timespec(time); + ms = period.tv_nsec / 1000000; + + seq_puts(m, "Timer Stats Version: v0.3\n"); + seq_printf(m, "Sample period: %ld.%03ld s\n", period.tv_sec, ms); + if (atomic_read(&overflow_count)) + seq_printf(m, "Overflow: %d entries\n", atomic_read(&overflow_count)); + seq_printf(m, "Collection: %s\n", timer_stats_active ? "active" : "inactive"); + + for (i = 0; i < nr_entries; i++) { + entry = entries + i; + if (entry->timer_flag & TIMER_STATS_FLAG_DEFERRABLE) { + seq_printf(m, "%4luD, %5d %-16s ", + entry->count, entry->pid, entry->comm); + } else { + seq_printf(m, " %4lu, %5d %-16s ", + entry->count, entry->pid, entry->comm); + } + + print_name_offset(m, (unsigned long)entry->start_func); + seq_puts(m, " ("); + print_name_offset(m, (unsigned long)entry->expire_func); + seq_puts(m, ")\n"); + + events += entry->count; + } + + ms += period.tv_sec * 1000; + if (!ms) + ms = 1; + + if (events && period.tv_sec) + seq_printf(m, "%ld total events, %ld.%03ld events/sec\n", + events, events * 1000 / ms, + (events * 1000000 / ms) % 1000); + else + seq_printf(m, "%ld total events\n", events); + + mutex_unlock(&show_mutex); + + return 0; +} + +/* + * After a state change, make sure all concurrent lookup/update + * activities have stopped: + */ +static void sync_access(void) +{ + unsigned long flags; + int cpu; + + for_each_online_cpu(cpu) { + raw_spinlock_t *lock = &per_cpu(tstats_lookup_lock, cpu); + + raw_spin_lock_irqsave(lock, flags); + /* nothing */ + raw_spin_unlock_irqrestore(lock, flags); + } +} + +static ssize_t tstats_write(struct file *file, const char __user *buf, + size_t count, loff_t *offs) +{ + char ctl[2]; + + if (count != 2 || *offs) + return -EINVAL; + + if (copy_from_user(ctl, buf, count)) + return -EFAULT; + + mutex_lock(&show_mutex); + switch (ctl[0]) { + case '0': + if (timer_stats_active) { + timer_stats_active = 0; + time_stop = ktime_get(); + sync_access(); + } + break; + case '1': + if (!timer_stats_active) { + reset_entries(); + time_start = ktime_get(); + smp_mb(); + timer_stats_active = 1; + } + break; + default: + count = -EINVAL; + } + mutex_unlock(&show_mutex); + + return count; +} + +static int tstats_open(struct inode *inode, struct file *filp) +{ + return single_open(filp, tstats_show, NULL); +} + +static const struct file_operations tstats_fops = { + .open = tstats_open, + .read = seq_read, + .write = tstats_write, + .llseek = seq_lseek, + .release = single_release, +}; + +void __init init_timer_stats(void) +{ + int cpu; + + for_each_possible_cpu(cpu) + raw_spin_lock_init(&per_cpu(tstats_lookup_lock, cpu)); +} + +static int __init init_tstats_procfs(void) +{ + struct proc_dir_entry *pe; + + pe = proc_create("timer_stats", 0644, NULL, &tstats_fops); + if (!pe) + return -ENOMEM; + return 0; +} +__initcall(init_tstats_procfs); diff --git a/kernel/kernel/torture.c b/kernel/kernel/torture.c new file mode 100644 index 000000000..dd70993c2 --- /dev/null +++ b/kernel/kernel/torture.c @@ -0,0 +1,741 @@ +/* + * Common functions for in-kernel torture tests. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, you can access it online at + * http://www.gnu.org/licenses/gpl-2.0.html. + * + * Copyright (C) IBM Corporation, 2014 + * + * Author: Paul E. McKenney + * Based on kernel/rcu/torture.c. + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Paul E. McKenney "); + +static char *torture_type; +static bool verbose; + +/* Mediate rmmod and system shutdown. Concurrent rmmod & shutdown illegal! */ +#define FULLSTOP_DONTSTOP 0 /* Normal operation. */ +#define FULLSTOP_SHUTDOWN 1 /* System shutdown with torture running. */ +#define FULLSTOP_RMMOD 2 /* Normal rmmod of torture. */ +static int fullstop = FULLSTOP_RMMOD; +static DEFINE_MUTEX(fullstop_mutex); +static int *torture_runnable; + +#ifdef CONFIG_HOTPLUG_CPU + +/* + * Variables for online-offline handling. Only present if CPU hotplug + * is enabled, otherwise does nothing. + */ + +static struct task_struct *onoff_task; +static long onoff_holdoff; +static long onoff_interval; +static long n_offline_attempts; +static long n_offline_successes; +static unsigned long sum_offline; +static int min_offline = -1; +static int max_offline; +static long n_online_attempts; +static long n_online_successes; +static unsigned long sum_online; +static int min_online = -1; +static int max_online; + +/* + * Execute random CPU-hotplug operations at the interval specified + * by the onoff_interval. + */ +static int +torture_onoff(void *arg) +{ + int cpu; + unsigned long delta; + int maxcpu = -1; + DEFINE_TORTURE_RANDOM(rand); + int ret; + unsigned long starttime; + + VERBOSE_TOROUT_STRING("torture_onoff task started"); + for_each_online_cpu(cpu) + maxcpu = cpu; + WARN_ON(maxcpu < 0); + if (onoff_holdoff > 0) { + VERBOSE_TOROUT_STRING("torture_onoff begin holdoff"); + schedule_timeout_interruptible(onoff_holdoff); + VERBOSE_TOROUT_STRING("torture_onoff end holdoff"); + } + while (!torture_must_stop()) { + cpu = (torture_random(&rand) >> 4) % (maxcpu + 1); + if (cpu_online(cpu) && cpu_is_hotpluggable(cpu)) { + if (verbose) + pr_alert("%s" TORTURE_FLAG + "torture_onoff task: offlining %d\n", + torture_type, cpu); + starttime = jiffies; + n_offline_attempts++; + ret = cpu_down(cpu); + if (ret) { + if (verbose) + pr_alert("%s" TORTURE_FLAG + "torture_onoff task: offline %d failed: errno %d\n", + torture_type, cpu, ret); + } else { + if (verbose) + pr_alert("%s" TORTURE_FLAG + "torture_onoff task: offlined %d\n", + torture_type, cpu); + n_offline_successes++; + delta = jiffies - starttime; + sum_offline += delta; + if (min_offline < 0) { + min_offline = delta; + max_offline = delta; + } + if (min_offline > delta) + min_offline = delta; + if (max_offline < delta) + max_offline = delta; + } + } else if (cpu_is_hotpluggable(cpu)) { + if (verbose) + pr_alert("%s" TORTURE_FLAG + "torture_onoff task: onlining %d\n", + torture_type, cpu); + starttime = jiffies; + n_online_attempts++; + ret = cpu_up(cpu); + if (ret) { + if (verbose) + pr_alert("%s" TORTURE_FLAG + "torture_onoff task: online %d failed: errno %d\n", + torture_type, cpu, ret); + } else { + if (verbose) + pr_alert("%s" TORTURE_FLAG + "torture_onoff task: onlined %d\n", + torture_type, cpu); + n_online_successes++; + delta = jiffies - starttime; + sum_online += delta; + if (min_online < 0) { + min_online = delta; + max_online = delta; + } + if (min_online > delta) + min_online = delta; + if (max_online < delta) + max_online = delta; + } + } + schedule_timeout_interruptible(onoff_interval); + } + torture_kthread_stopping("torture_onoff"); + return 0; +} + +#endif /* #ifdef CONFIG_HOTPLUG_CPU */ + +/* + * Initiate online-offline handling. + */ +int torture_onoff_init(long ooholdoff, long oointerval) +{ + int ret = 0; + +#ifdef CONFIG_HOTPLUG_CPU + onoff_holdoff = ooholdoff; + onoff_interval = oointerval; + if (onoff_interval <= 0) + return 0; + ret = torture_create_kthread(torture_onoff, NULL, onoff_task); +#endif /* #ifdef CONFIG_HOTPLUG_CPU */ + return ret; +} +EXPORT_SYMBOL_GPL(torture_onoff_init); + +/* + * Clean up after online/offline testing. + */ +static void torture_onoff_cleanup(void) +{ +#ifdef CONFIG_HOTPLUG_CPU + if (onoff_task == NULL) + return; + VERBOSE_TOROUT_STRING("Stopping torture_onoff task"); + kthread_stop(onoff_task); + onoff_task = NULL; +#endif /* #ifdef CONFIG_HOTPLUG_CPU */ +} +EXPORT_SYMBOL_GPL(torture_onoff_cleanup); + +/* + * Print online/offline testing statistics. + */ +void torture_onoff_stats(void) +{ +#ifdef CONFIG_HOTPLUG_CPU + pr_cont("onoff: %ld/%ld:%ld/%ld %d,%d:%d,%d %lu:%lu (HZ=%d) ", + n_online_successes, n_online_attempts, + n_offline_successes, n_offline_attempts, + min_online, max_online, + min_offline, max_offline, + sum_online, sum_offline, HZ); +#endif /* #ifdef CONFIG_HOTPLUG_CPU */ +} +EXPORT_SYMBOL_GPL(torture_onoff_stats); + +/* + * Were all the online/offline operations successful? + */ +bool torture_onoff_failures(void) +{ +#ifdef CONFIG_HOTPLUG_CPU + return n_online_successes != n_online_attempts || + n_offline_successes != n_offline_attempts; +#else /* #ifdef CONFIG_HOTPLUG_CPU */ + return false; +#endif /* #else #ifdef CONFIG_HOTPLUG_CPU */ +} +EXPORT_SYMBOL_GPL(torture_onoff_failures); + +#define TORTURE_RANDOM_MULT 39916801 /* prime */ +#define TORTURE_RANDOM_ADD 479001701 /* prime */ +#define TORTURE_RANDOM_REFRESH 10000 + +/* + * Crude but fast random-number generator. Uses a linear congruential + * generator, with occasional help from cpu_clock(). + */ +unsigned long +torture_random(struct torture_random_state *trsp) +{ + if (--trsp->trs_count < 0) { + trsp->trs_state += (unsigned long)local_clock(); + trsp->trs_count = TORTURE_RANDOM_REFRESH; + } + trsp->trs_state = trsp->trs_state * TORTURE_RANDOM_MULT + + TORTURE_RANDOM_ADD; + return swahw32(trsp->trs_state); +} +EXPORT_SYMBOL_GPL(torture_random); + +/* + * Variables for shuffling. The idea is to ensure that each CPU stays + * idle for an extended period to test interactions with dyntick idle, + * as well as interactions with any per-CPU varibles. + */ +struct shuffle_task { + struct list_head st_l; + struct task_struct *st_t; +}; + +static long shuffle_interval; /* In jiffies. */ +static struct task_struct *shuffler_task; +static cpumask_var_t shuffle_tmp_mask; +static int shuffle_idle_cpu; /* Force all torture tasks off this CPU */ +static struct list_head shuffle_task_list = LIST_HEAD_INIT(shuffle_task_list); +static DEFINE_MUTEX(shuffle_task_mutex); + +/* + * Register a task to be shuffled. If there is no memory, just splat + * and don't bother registering. + */ +void torture_shuffle_task_register(struct task_struct *tp) +{ + struct shuffle_task *stp; + + if (WARN_ON_ONCE(tp == NULL)) + return; + stp = kmalloc(sizeof(*stp), GFP_KERNEL); + if (WARN_ON_ONCE(stp == NULL)) + return; + stp->st_t = tp; + mutex_lock(&shuffle_task_mutex); + list_add(&stp->st_l, &shuffle_task_list); + mutex_unlock(&shuffle_task_mutex); +} +EXPORT_SYMBOL_GPL(torture_shuffle_task_register); + +/* + * Unregister all tasks, for example, at the end of the torture run. + */ +static void torture_shuffle_task_unregister_all(void) +{ + struct shuffle_task *stp; + struct shuffle_task *p; + + mutex_lock(&shuffle_task_mutex); + list_for_each_entry_safe(stp, p, &shuffle_task_list, st_l) { + list_del(&stp->st_l); + kfree(stp); + } + mutex_unlock(&shuffle_task_mutex); +} + +/* Shuffle tasks such that we allow shuffle_idle_cpu to become idle. + * A special case is when shuffle_idle_cpu = -1, in which case we allow + * the tasks to run on all CPUs. + */ +static void torture_shuffle_tasks(void) +{ + struct shuffle_task *stp; + + cpumask_setall(shuffle_tmp_mask); + get_online_cpus(); + + /* No point in shuffling if there is only one online CPU (ex: UP) */ + if (num_online_cpus() == 1) { + put_online_cpus(); + return; + } + + /* Advance to the next CPU. Upon overflow, don't idle any CPUs. */ + shuffle_idle_cpu = cpumask_next(shuffle_idle_cpu, shuffle_tmp_mask); + if (shuffle_idle_cpu >= nr_cpu_ids) + shuffle_idle_cpu = -1; + else + cpumask_clear_cpu(shuffle_idle_cpu, shuffle_tmp_mask); + + mutex_lock(&shuffle_task_mutex); + list_for_each_entry(stp, &shuffle_task_list, st_l) + set_cpus_allowed_ptr(stp->st_t, shuffle_tmp_mask); + mutex_unlock(&shuffle_task_mutex); + + put_online_cpus(); +} + +/* Shuffle tasks across CPUs, with the intent of allowing each CPU in the + * system to become idle at a time and cut off its timer ticks. This is meant + * to test the support for such tickless idle CPU in RCU. + */ +static int torture_shuffle(void *arg) +{ + VERBOSE_TOROUT_STRING("torture_shuffle task started"); + do { + schedule_timeout_interruptible(shuffle_interval); + torture_shuffle_tasks(); + torture_shutdown_absorb("torture_shuffle"); + } while (!torture_must_stop()); + torture_kthread_stopping("torture_shuffle"); + return 0; +} + +/* + * Start the shuffler, with shuffint in jiffies. + */ +int torture_shuffle_init(long shuffint) +{ + shuffle_interval = shuffint; + + shuffle_idle_cpu = -1; + + if (!alloc_cpumask_var(&shuffle_tmp_mask, GFP_KERNEL)) { + VERBOSE_TOROUT_ERRSTRING("Failed to alloc mask"); + return -ENOMEM; + } + + /* Create the shuffler thread */ + return torture_create_kthread(torture_shuffle, NULL, shuffler_task); +} +EXPORT_SYMBOL_GPL(torture_shuffle_init); + +/* + * Stop the shuffling. + */ +static void torture_shuffle_cleanup(void) +{ + torture_shuffle_task_unregister_all(); + if (shuffler_task) { + VERBOSE_TOROUT_STRING("Stopping torture_shuffle task"); + kthread_stop(shuffler_task); + free_cpumask_var(shuffle_tmp_mask); + } + shuffler_task = NULL; +} +EXPORT_SYMBOL_GPL(torture_shuffle_cleanup); + +/* + * Variables for auto-shutdown. This allows "lights out" torture runs + * to be fully scripted. + */ +static int shutdown_secs; /* desired test duration in seconds. */ +static struct task_struct *shutdown_task; +static unsigned long shutdown_time; /* jiffies to system shutdown. */ +static void (*torture_shutdown_hook)(void); + +/* + * Absorb kthreads into a kernel function that won't return, so that + * they won't ever access module text or data again. + */ +void torture_shutdown_absorb(const char *title) +{ + while (ACCESS_ONCE(fullstop) == FULLSTOP_SHUTDOWN) { + pr_notice("torture thread %s parking due to system shutdown\n", + title); + schedule_timeout_uninterruptible(MAX_SCHEDULE_TIMEOUT); + } +} +EXPORT_SYMBOL_GPL(torture_shutdown_absorb); + +/* + * Cause the torture test to shutdown the system after the test has + * run for the time specified by the shutdown_secs parameter. + */ +static int torture_shutdown(void *arg) +{ + long delta; + unsigned long jiffies_snap; + + VERBOSE_TOROUT_STRING("torture_shutdown task started"); + jiffies_snap = jiffies; + while (ULONG_CMP_LT(jiffies_snap, shutdown_time) && + !torture_must_stop()) { + delta = shutdown_time - jiffies_snap; + if (verbose) + pr_alert("%s" TORTURE_FLAG + "torture_shutdown task: %lu jiffies remaining\n", + torture_type, delta); + schedule_timeout_interruptible(delta); + jiffies_snap = jiffies; + } + if (torture_must_stop()) { + torture_kthread_stopping("torture_shutdown"); + return 0; + } + + /* OK, shut down the system. */ + + VERBOSE_TOROUT_STRING("torture_shutdown task shutting down system"); + shutdown_task = NULL; /* Avoid self-kill deadlock. */ + if (torture_shutdown_hook) + torture_shutdown_hook(); + else + VERBOSE_TOROUT_STRING("No torture_shutdown_hook(), skipping."); + kernel_power_off(); /* Shut down the system. */ + return 0; +} + +/* + * Start up the shutdown task. + */ +int torture_shutdown_init(int ssecs, void (*cleanup)(void)) +{ + int ret = 0; + + shutdown_secs = ssecs; + torture_shutdown_hook = cleanup; + if (shutdown_secs > 0) { + shutdown_time = jiffies + shutdown_secs * HZ; + ret = torture_create_kthread(torture_shutdown, NULL, + shutdown_task); + } + return ret; +} +EXPORT_SYMBOL_GPL(torture_shutdown_init); + +/* + * Detect and respond to a system shutdown. + */ +static int torture_shutdown_notify(struct notifier_block *unused1, + unsigned long unused2, void *unused3) +{ + mutex_lock(&fullstop_mutex); + if (ACCESS_ONCE(fullstop) == FULLSTOP_DONTSTOP) { + VERBOSE_TOROUT_STRING("Unscheduled system shutdown detected"); + ACCESS_ONCE(fullstop) = FULLSTOP_SHUTDOWN; + } else { + pr_warn("Concurrent rmmod and shutdown illegal!\n"); + } + mutex_unlock(&fullstop_mutex); + return NOTIFY_DONE; +} + +static struct notifier_block torture_shutdown_nb = { + .notifier_call = torture_shutdown_notify, +}; + +/* + * Shut down the shutdown task. Say what??? Heh! This can happen if + * the torture module gets an rmmod before the shutdown time arrives. ;-) + */ +static void torture_shutdown_cleanup(void) +{ + unregister_reboot_notifier(&torture_shutdown_nb); + if (shutdown_task != NULL) { + VERBOSE_TOROUT_STRING("Stopping torture_shutdown task"); + kthread_stop(shutdown_task); + } + shutdown_task = NULL; +} + +/* + * Variables for stuttering, which means to periodically pause and + * restart testing in order to catch bugs that appear when load is + * suddenly applied to or removed from the system. + */ +static struct task_struct *stutter_task; +static int stutter_pause_test; +static int stutter; + +/* + * Block until the stutter interval ends. This must be called periodically + * by all running kthreads that need to be subject to stuttering. + */ +void stutter_wait(const char *title) +{ + while (ACCESS_ONCE(stutter_pause_test) || + (torture_runnable && !ACCESS_ONCE(*torture_runnable))) { + if (stutter_pause_test) + if (ACCESS_ONCE(stutter_pause_test) == 1) + schedule_timeout_interruptible(1); + else + while (ACCESS_ONCE(stutter_pause_test)) + cond_resched(); + else + schedule_timeout_interruptible(round_jiffies_relative(HZ)); + torture_shutdown_absorb(title); + } +} +EXPORT_SYMBOL_GPL(stutter_wait); + +/* + * Cause the torture test to "stutter", starting and stopping all + * threads periodically. + */ +static int torture_stutter(void *arg) +{ + VERBOSE_TOROUT_STRING("torture_stutter task started"); + do { + if (!torture_must_stop()) { + if (stutter > 1) { + schedule_timeout_interruptible(stutter - 1); + ACCESS_ONCE(stutter_pause_test) = 2; + } + schedule_timeout_interruptible(1); + ACCESS_ONCE(stutter_pause_test) = 1; + } + if (!torture_must_stop()) + schedule_timeout_interruptible(stutter); + ACCESS_ONCE(stutter_pause_test) = 0; + torture_shutdown_absorb("torture_stutter"); + } while (!torture_must_stop()); + torture_kthread_stopping("torture_stutter"); + return 0; +} + +/* + * Initialize and kick off the torture_stutter kthread. + */ +int torture_stutter_init(int s) +{ + int ret; + + stutter = s; + ret = torture_create_kthread(torture_stutter, NULL, stutter_task); + return ret; +} +EXPORT_SYMBOL_GPL(torture_stutter_init); + +/* + * Cleanup after the torture_stutter kthread. + */ +static void torture_stutter_cleanup(void) +{ + if (!stutter_task) + return; + VERBOSE_TOROUT_STRING("Stopping torture_stutter task"); + kthread_stop(stutter_task); + stutter_task = NULL; +} + +/* + * Initialize torture module. Please note that this is -not- invoked via + * the usual module_init() mechanism, but rather by an explicit call from + * the client torture module. This call must be paired with a later + * torture_init_end(). + * + * The runnable parameter points to a flag that controls whether or not + * the test is currently runnable. If there is no such flag, pass in NULL. + */ +bool torture_init_begin(char *ttype, bool v, int *runnable) +{ + mutex_lock(&fullstop_mutex); + if (torture_type != NULL) { + pr_alert("torture_init_begin: refusing %s init: %s running", + ttype, torture_type); + mutex_unlock(&fullstop_mutex); + return false; + } + torture_type = ttype; + verbose = v; + torture_runnable = runnable; + fullstop = FULLSTOP_DONTSTOP; + return true; +} +EXPORT_SYMBOL_GPL(torture_init_begin); + +/* + * Tell the torture module that initialization is complete. + */ +void torture_init_end(void) +{ + mutex_unlock(&fullstop_mutex); + register_reboot_notifier(&torture_shutdown_nb); +} +EXPORT_SYMBOL_GPL(torture_init_end); + +/* + * Clean up torture module. Please note that this is -not- invoked via + * the usual module_exit() mechanism, but rather by an explicit call from + * the client torture module. Returns true if a race with system shutdown + * is detected, otherwise, all kthreads started by functions in this file + * will be shut down. + * + * This must be called before the caller starts shutting down its own + * kthreads. + * + * Both torture_cleanup_begin() and torture_cleanup_end() must be paired, + * in order to correctly perform the cleanup. They are separated because + * threads can still need to reference the torture_type type, thus nullify + * only after completing all other relevant calls. + */ +bool torture_cleanup_begin(void) +{ + mutex_lock(&fullstop_mutex); + if (ACCESS_ONCE(fullstop) == FULLSTOP_SHUTDOWN) { + pr_warn("Concurrent rmmod and shutdown illegal!\n"); + mutex_unlock(&fullstop_mutex); + schedule_timeout_uninterruptible(10); + return true; + } + ACCESS_ONCE(fullstop) = FULLSTOP_RMMOD; + mutex_unlock(&fullstop_mutex); + torture_shutdown_cleanup(); + torture_shuffle_cleanup(); + torture_stutter_cleanup(); + torture_onoff_cleanup(); + return false; +} +EXPORT_SYMBOL_GPL(torture_cleanup_begin); + +void torture_cleanup_end(void) +{ + mutex_lock(&fullstop_mutex); + torture_type = NULL; + mutex_unlock(&fullstop_mutex); +} +EXPORT_SYMBOL_GPL(torture_cleanup_end); + +/* + * Is it time for the current torture test to stop? + */ +bool torture_must_stop(void) +{ + return torture_must_stop_irq() || kthread_should_stop(); +} +EXPORT_SYMBOL_GPL(torture_must_stop); + +/* + * Is it time for the current torture test to stop? This is the irq-safe + * version, hence no check for kthread_should_stop(). + */ +bool torture_must_stop_irq(void) +{ + return ACCESS_ONCE(fullstop) != FULLSTOP_DONTSTOP; +} +EXPORT_SYMBOL_GPL(torture_must_stop_irq); + +/* + * Each kthread must wait for kthread_should_stop() before returning from + * its top-level function, otherwise segfaults ensue. This function + * prints a "stopping" message and waits for kthread_should_stop(), and + * should be called from all torture kthreads immediately prior to + * returning. + */ +void torture_kthread_stopping(char *title) +{ + char buf[128]; + + snprintf(buf, sizeof(buf), "Stopping %s", title); + VERBOSE_TOROUT_STRING(buf); + while (!kthread_should_stop()) { + torture_shutdown_absorb(title); + schedule_timeout_uninterruptible(1); + } +} +EXPORT_SYMBOL_GPL(torture_kthread_stopping); + +/* + * Create a generic torture kthread that is immediately runnable. If you + * need the kthread to be stopped so that you can do something to it before + * it starts, you will need to open-code your own. + */ +int _torture_create_kthread(int (*fn)(void *arg), void *arg, char *s, char *m, + char *f, struct task_struct **tp) +{ + int ret = 0; + + VERBOSE_TOROUT_STRING(m); + *tp = kthread_run(fn, arg, "%s", s); + if (IS_ERR(*tp)) { + ret = PTR_ERR(*tp); + VERBOSE_TOROUT_ERRSTRING(f); + *tp = NULL; + } + torture_shuffle_task_register(*tp); + return ret; +} +EXPORT_SYMBOL_GPL(_torture_create_kthread); + +/* + * Stop a generic kthread, emitting a message. + */ +void _torture_stop_kthread(char *m, struct task_struct **tp) +{ + if (*tp == NULL) + return; + VERBOSE_TOROUT_STRING(m); + kthread_stop(*tp); + *tp = NULL; +} +EXPORT_SYMBOL_GPL(_torture_stop_kthread); diff --git a/kernel/kernel/trace/Kconfig b/kernel/kernel/trace/Kconfig new file mode 100644 index 000000000..ab3a277a3 --- /dev/null +++ b/kernel/kernel/trace/Kconfig @@ -0,0 +1,745 @@ +# +# Architectures that offer an FUNCTION_TRACER implementation should +# select HAVE_FUNCTION_TRACER: +# + +config USER_STACKTRACE_SUPPORT + bool + +config NOP_TRACER + bool + +config HAVE_FTRACE_NMI_ENTER + bool + help + See Documentation/trace/ftrace-design.txt + +config HAVE_FUNCTION_TRACER + bool + help + See Documentation/trace/ftrace-design.txt + +config HAVE_FUNCTION_GRAPH_TRACER + bool + help + See Documentation/trace/ftrace-design.txt + +config HAVE_FUNCTION_GRAPH_FP_TEST + bool + help + See Documentation/trace/ftrace-design.txt + +config HAVE_DYNAMIC_FTRACE + bool + help + See Documentation/trace/ftrace-design.txt + +config HAVE_DYNAMIC_FTRACE_WITH_REGS + bool + +config HAVE_FTRACE_MCOUNT_RECORD + bool + help + See Documentation/trace/ftrace-design.txt + +config HAVE_SYSCALL_TRACEPOINTS + bool + help + See Documentation/trace/ftrace-design.txt + +config HAVE_FENTRY + bool + help + Arch supports the gcc options -pg with -mfentry + +config HAVE_C_RECORDMCOUNT + bool + help + C version of recordmcount available? + +config TRACER_MAX_TRACE + bool + +config TRACE_CLOCK + bool + +config RING_BUFFER + bool + select TRACE_CLOCK + select IRQ_WORK + +config FTRACE_NMI_ENTER + bool + depends on HAVE_FTRACE_NMI_ENTER + default y + +config EVENT_TRACING + select CONTEXT_SWITCH_TRACER + bool + +config CONTEXT_SWITCH_TRACER + bool + +config RING_BUFFER_ALLOW_SWAP + bool + help + Allow the use of ring_buffer_swap_cpu. + Adds a very slight overhead to tracing when enabled. + +# All tracer options should select GENERIC_TRACER. For those options that are +# enabled by all tracers (context switch and event tracer) they select TRACING. +# This allows those options to appear when no other tracer is selected. But the +# options do not appear when something else selects it. We need the two options +# GENERIC_TRACER and TRACING to avoid circular dependencies to accomplish the +# hiding of the automatic options. + +config TRACING + bool + select DEBUG_FS + select RING_BUFFER + select STACKTRACE if STACKTRACE_SUPPORT + select TRACEPOINTS + select NOP_TRACER + select BINARY_PRINTF + select EVENT_TRACING + select TRACE_CLOCK + +config GENERIC_TRACER + bool + select TRACING + +# +# Minimum requirements an architecture has to meet for us to +# be able to offer generic tracing facilities: +# +config TRACING_SUPPORT + bool + # PPC32 has no irqflags tracing support, but it can use most of the + # tracers anyway, they were tested to build and work. Note that new + # exceptions to this list aren't welcomed, better implement the + # irqflags tracing for your architecture. + depends on TRACE_IRQFLAGS_SUPPORT || PPC32 + depends on STACKTRACE_SUPPORT + default y + +if TRACING_SUPPORT + +menuconfig FTRACE + bool "Tracers" + default y if DEBUG_KERNEL + help + Enable the kernel tracing infrastructure. + +if FTRACE + +config FUNCTION_TRACER + bool "Kernel Function Tracer" + depends on HAVE_FUNCTION_TRACER + select KALLSYMS + select GENERIC_TRACER + select CONTEXT_SWITCH_TRACER + help + Enable the kernel to trace every kernel function. This is done + by using a compiler feature to insert a small, 5-byte No-Operation + instruction at the beginning of every kernel function, which NOP + sequence is then dynamically patched into a tracer call when + tracing is enabled by the administrator. If it's runtime disabled + (the bootup default), then the overhead of the instructions is very + small and not measurable even in micro-benchmarks. + +config FUNCTION_GRAPH_TRACER + bool "Kernel Function Graph Tracer" + depends on HAVE_FUNCTION_GRAPH_TRACER + depends on FUNCTION_TRACER + depends on !X86_32 || !CC_OPTIMIZE_FOR_SIZE + default y + help + Enable the kernel to trace a function at both its return + and its entry. + Its first purpose is to trace the duration of functions and + draw a call graph for each thread with some information like + the return value. This is done by setting the current return + address on the current task structure into a stack of calls. + + +config IRQSOFF_TRACER + bool "Interrupts-off Latency Tracer" + default n + depends on TRACE_IRQFLAGS_SUPPORT + depends on !ARCH_USES_GETTIMEOFFSET + select TRACE_IRQFLAGS + select GENERIC_TRACER + select TRACER_MAX_TRACE + select RING_BUFFER_ALLOW_SWAP + select TRACER_SNAPSHOT + select TRACER_SNAPSHOT_PER_CPU_SWAP + help + This option measures the time spent in irqs-off critical + sections, with microsecond accuracy. + + The default measurement method is a maximum search, which is + disabled by default and can be runtime (re-)started + via: + + echo 0 > /sys/kernel/debug/tracing/tracing_max_latency + + (Note that kernel size and overhead increase with this option + enabled. This option and the preempt-off timing option can be + used together or separately.) + +config INTERRUPT_OFF_HIST + bool "Interrupts-off Latency Histogram" + depends on IRQSOFF_TRACER + help + This option generates continuously updated histograms (one per cpu) + of the duration of time periods with interrupts disabled. The + histograms are disabled by default. To enable them, write a non-zero + number to + + /sys/kernel/debug/tracing/latency_hist/enable/preemptirqsoff + + If PREEMPT_OFF_HIST is also selected, additional histograms (one + per cpu) are generated that accumulate the duration of time periods + when both interrupts and preemption are disabled. The histogram data + will be located in the debug file system at + + /sys/kernel/debug/tracing/latency_hist/irqsoff + +config PREEMPT_TRACER + bool "Preemption-off Latency Tracer" + default n + depends on !ARCH_USES_GETTIMEOFFSET + depends on PREEMPT + select GENERIC_TRACER + select TRACER_MAX_TRACE + select RING_BUFFER_ALLOW_SWAP + select TRACER_SNAPSHOT + select TRACER_SNAPSHOT_PER_CPU_SWAP + help + This option measures the time spent in preemption-off critical + sections, with microsecond accuracy. + + The default measurement method is a maximum search, which is + disabled by default and can be runtime (re-)started + via: + + echo 0 > /sys/kernel/debug/tracing/tracing_max_latency + + (Note that kernel size and overhead increase with this option + enabled. This option and the irqs-off timing option can be + used together or separately.) + +config PREEMPT_OFF_HIST + bool "Preemption-off Latency Histogram" + depends on PREEMPT_TRACER + help + This option generates continuously updated histograms (one per cpu) + of the duration of time periods with preemption disabled. The + histograms are disabled by default. To enable them, write a non-zero + number to + + /sys/kernel/debug/tracing/latency_hist/enable/preemptirqsoff + + If INTERRUPT_OFF_HIST is also selected, additional histograms (one + per cpu) are generated that accumulate the duration of time periods + when both interrupts and preemption are disabled. The histogram data + will be located in the debug file system at + + /sys/kernel/debug/tracing/latency_hist/preemptoff + +config SCHED_TRACER + bool "Scheduling Latency Tracer" + select GENERIC_TRACER + select CONTEXT_SWITCH_TRACER + select TRACER_MAX_TRACE + select TRACER_SNAPSHOT + help + This tracer tracks the latency of the highest priority task + to be scheduled in, starting from the point it has woken up. + +config WAKEUP_LATENCY_HIST + bool "Scheduling Latency Histogram" + depends on SCHED_TRACER + help + This option generates continuously updated histograms (one per cpu) + of the scheduling latency of the highest priority task. + The histograms are disabled by default. To enable them, write a + non-zero number to + + /sys/kernel/debug/tracing/latency_hist/enable/wakeup + + Two different algorithms are used, one to determine the latency of + processes that exclusively use the highest priority of the system and + another one to determine the latency of processes that share the + highest system priority with other processes. The former is used to + improve hardware and system software, the latter to optimize the + priority design of a given system. The histogram data will be + located in the debug file system at + + /sys/kernel/debug/tracing/latency_hist/wakeup + + and + + /sys/kernel/debug/tracing/latency_hist/wakeup/sharedprio + + If both Scheduling Latency Histogram and Missed Timer Offsets + Histogram are selected, additional histogram data will be collected + that contain, in addition to the wakeup latency, the timer latency, in + case the wakeup was triggered by an expired timer. These histograms + are available in the + + /sys/kernel/debug/tracing/latency_hist/timerandwakeup + + directory. They reflect the apparent interrupt and scheduling latency + and are best suitable to determine the worst-case latency of a given + system. To enable these histograms, write a non-zero number to + + /sys/kernel/debug/tracing/latency_hist/enable/timerandwakeup + +config MISSED_TIMER_OFFSETS_HIST + depends on HIGH_RES_TIMERS + select GENERIC_TRACER + bool "Missed Timer Offsets Histogram" + help + Generate a histogram of missed timer offsets in microseconds. The + histograms are disabled by default. To enable them, write a non-zero + number to + + /sys/kernel/debug/tracing/latency_hist/enable/missed_timer_offsets + + The histogram data will be located in the debug file system at + + /sys/kernel/debug/tracing/latency_hist/missed_timer_offsets + + If both Scheduling Latency Histogram and Missed Timer Offsets + Histogram are selected, additional histogram data will be collected + that contain, in addition to the wakeup latency, the timer latency, in + case the wakeup was triggered by an expired timer. These histograms + are available in the + + /sys/kernel/debug/tracing/latency_hist/timerandwakeup + + directory. They reflect the apparent interrupt and scheduling latency + and are best suitable to determine the worst-case latency of a given + system. To enable these histograms, write a non-zero number to + + /sys/kernel/debug/tracing/latency_hist/enable/timerandwakeup + +config ENABLE_DEFAULT_TRACERS + bool "Trace process context switches and events" + depends on !GENERIC_TRACER + select TRACING + help + This tracer hooks to various trace points in the kernel, + allowing the user to pick and choose which trace point they + want to trace. It also includes the sched_switch tracer plugin. + +config FTRACE_SYSCALLS + bool "Trace syscalls" + depends on HAVE_SYSCALL_TRACEPOINTS + select GENERIC_TRACER + select KALLSYMS + help + Basic tracer to catch the syscall entry and exit events. + +config TRACER_SNAPSHOT + bool "Create a snapshot trace buffer" + select TRACER_MAX_TRACE + help + Allow tracing users to take snapshot of the current buffer using the + ftrace interface, e.g.: + + echo 1 > /sys/kernel/debug/tracing/snapshot + cat snapshot + +config TRACER_SNAPSHOT_PER_CPU_SWAP + bool "Allow snapshot to swap per CPU" + depends on TRACER_SNAPSHOT + select RING_BUFFER_ALLOW_SWAP + help + Allow doing a snapshot of a single CPU buffer instead of a + full swap (all buffers). If this is set, then the following is + allowed: + + echo 1 > /sys/kernel/debug/tracing/per_cpu/cpu2/snapshot + + After which, only the tracing buffer for CPU 2 was swapped with + the main tracing buffer, and the other CPU buffers remain the same. + + When this is enabled, this adds a little more overhead to the + trace recording, as it needs to add some checks to synchronize + recording with swaps. But this does not affect the performance + of the overall system. This is enabled by default when the preempt + or irq latency tracers are enabled, as those need to swap as well + and already adds the overhead (plus a lot more). + +config TRACE_BRANCH_PROFILING + bool + select GENERIC_TRACER + +choice + prompt "Branch Profiling" + default BRANCH_PROFILE_NONE + help + The branch profiling is a software profiler. It will add hooks + into the C conditionals to test which path a branch takes. + + The likely/unlikely profiler only looks at the conditions that + are annotated with a likely or unlikely macro. + + The "all branch" profiler will profile every if-statement in the + kernel. This profiler will also enable the likely/unlikely + profiler. + + Either of the above profilers adds a bit of overhead to the system. + If unsure, choose "No branch profiling". + +config BRANCH_PROFILE_NONE + bool "No branch profiling" + help + No branch profiling. Branch profiling adds a bit of overhead. + Only enable it if you want to analyse the branching behavior. + Otherwise keep it disabled. + +config PROFILE_ANNOTATED_BRANCHES + bool "Trace likely/unlikely profiler" + select TRACE_BRANCH_PROFILING + help + This tracer profiles all likely and unlikely macros + in the kernel. It will display the results in: + + /sys/kernel/debug/tracing/trace_stat/branch_annotated + + Note: this will add a significant overhead; only turn this + on if you need to profile the system's use of these macros. + +config PROFILE_ALL_BRANCHES + bool "Profile all if conditionals" + select TRACE_BRANCH_PROFILING + help + This tracer profiles all branch conditions. Every if () + taken in the kernel is recorded whether it hit or miss. + The results will be displayed in: + + /sys/kernel/debug/tracing/trace_stat/branch_all + + This option also enables the likely/unlikely profiler. + + This configuration, when enabled, will impose a great overhead + on the system. This should only be enabled when the system + is to be analyzed in much detail. +endchoice + +config TRACING_BRANCHES + bool + help + Selected by tracers that will trace the likely and unlikely + conditions. This prevents the tracers themselves from being + profiled. Profiling the tracing infrastructure can only happen + when the likelys and unlikelys are not being traced. + +config BRANCH_TRACER + bool "Trace likely/unlikely instances" + depends on TRACE_BRANCH_PROFILING + select TRACING_BRANCHES + help + This traces the events of likely and unlikely condition + calls in the kernel. The difference between this and the + "Trace likely/unlikely profiler" is that this is not a + histogram of the callers, but actually places the calling + events into a running trace buffer to see when and where the + events happened, as well as their results. + + Say N if unsure. + +config STACK_TRACER + bool "Trace max stack" + depends on HAVE_FUNCTION_TRACER + select FUNCTION_TRACER + select STACKTRACE + select KALLSYMS + help + This special tracer records the maximum stack footprint of the + kernel and displays it in /sys/kernel/debug/tracing/stack_trace. + + This tracer works by hooking into every function call that the + kernel executes, and keeping a maximum stack depth value and + stack-trace saved. If this is configured with DYNAMIC_FTRACE + then it will not have any overhead while the stack tracer + is disabled. + + To enable the stack tracer on bootup, pass in 'stacktrace' + on the kernel command line. + + The stack tracer can also be enabled or disabled via the + sysctl kernel.stack_tracer_enabled + + Say N if unsure. + +config BLK_DEV_IO_TRACE + bool "Support for tracing block IO actions" + depends on SYSFS + depends on BLOCK + select RELAY + select DEBUG_FS + select TRACEPOINTS + select GENERIC_TRACER + select STACKTRACE + help + Say Y here if you want to be able to trace the block layer actions + on a given queue. Tracing allows you to see any traffic happening + on a block device queue. For more information (and the userspace + support tools needed), fetch the blktrace tools from: + + git://git.kernel.dk/blktrace.git + + Tracing also is possible using the ftrace interface, e.g.: + + echo 1 > /sys/block/sda/sda1/trace/enable + echo blk > /sys/kernel/debug/tracing/current_tracer + cat /sys/kernel/debug/tracing/trace_pipe + + If unsure, say N. + +config KPROBE_EVENT + depends on KPROBES + depends on HAVE_REGS_AND_STACK_ACCESS_API + bool "Enable kprobes-based dynamic events" + select TRACING + select PROBE_EVENTS + default y + help + This allows the user to add tracing events (similar to tracepoints) + on the fly via the ftrace interface. See + Documentation/trace/kprobetrace.txt for more details. + + Those events can be inserted wherever kprobes can probe, and record + various register and memory values. + + This option is also required by perf-probe subcommand of perf tools. + If you want to use perf tools, this option is strongly recommended. + +config UPROBE_EVENT + bool "Enable uprobes-based dynamic events" + depends on ARCH_SUPPORTS_UPROBES + depends on MMU + depends on PERF_EVENTS + select UPROBES + select PROBE_EVENTS + select TRACING + default n + help + This allows the user to add tracing events on top of userspace + dynamic events (similar to tracepoints) on the fly via the trace + events interface. Those events can be inserted wherever uprobes + can probe, and record various registers. + This option is required if you plan to use perf-probe subcommand + of perf tools on user space applications. + +config BPF_EVENTS + depends on BPF_SYSCALL + depends on KPROBE_EVENT + bool + default y + help + This allows the user to attach BPF programs to kprobe events. + +config PROBE_EVENTS + def_bool n + +config DYNAMIC_FTRACE + bool "enable/disable function tracing dynamically" + depends on FUNCTION_TRACER + depends on HAVE_DYNAMIC_FTRACE + default y + help + This option will modify all the calls to function tracing + dynamically (will patch them out of the binary image and + replace them with a No-Op instruction) on boot up. During + compile time, a table is made of all the locations that ftrace + can function trace, and this table is linked into the kernel + image. When this is enabled, functions can be individually + enabled, and the functions not enabled will not affect + performance of the system. + + See the files in /sys/kernel/debug/tracing: + available_filter_functions + set_ftrace_filter + set_ftrace_notrace + + This way a CONFIG_FUNCTION_TRACER kernel is slightly larger, but + otherwise has native performance as long as no tracing is active. + +config DYNAMIC_FTRACE_WITH_REGS + def_bool y + depends on DYNAMIC_FTRACE + depends on HAVE_DYNAMIC_FTRACE_WITH_REGS + +config FUNCTION_PROFILER + bool "Kernel function profiler" + depends on FUNCTION_TRACER + default n + help + This option enables the kernel function profiler. A file is created + in debugfs called function_profile_enabled which defaults to zero. + When a 1 is echoed into this file profiling begins, and when a + zero is entered, profiling stops. A "functions" file is created in + the trace_stats directory; this file shows the list of functions that + have been hit and their counters. + + If in doubt, say N. + +config FTRACE_MCOUNT_RECORD + def_bool y + depends on DYNAMIC_FTRACE + depends on HAVE_FTRACE_MCOUNT_RECORD + +config FTRACE_SELFTEST + bool + +config FTRACE_STARTUP_TEST + bool "Perform a startup test on ftrace" + depends on GENERIC_TRACER + select FTRACE_SELFTEST + help + This option performs a series of startup tests on ftrace. On bootup + a series of tests are made to verify that the tracer is + functioning properly. It will do tests on all the configured + tracers of ftrace. + +config EVENT_TRACE_TEST_SYSCALLS + bool "Run selftest on syscall events" + depends on FTRACE_STARTUP_TEST + help + This option will also enable testing every syscall event. + It only enables the event and disables it and runs various loads + with the event enabled. This adds a bit more time for kernel boot + up since it runs this on every system call defined. + + TBD - enable a way to actually call the syscalls as we test their + events + +config MMIOTRACE + bool "Memory mapped IO tracing" + depends on HAVE_MMIOTRACE_SUPPORT && PCI + select GENERIC_TRACER + help + Mmiotrace traces Memory Mapped I/O access and is meant for + debugging and reverse engineering. It is called from the ioremap + implementation and works via page faults. Tracing is disabled by + default and can be enabled at run-time. + + See Documentation/trace/mmiotrace.txt. + If you are not helping to develop drivers, say N. + +config MMIOTRACE_TEST + tristate "Test module for mmiotrace" + depends on MMIOTRACE && m + help + This is a dumb module for testing mmiotrace. It is very dangerous + as it will write garbage to IO memory starting at a given address. + However, it should be safe to use on e.g. unused portion of VRAM. + + Say N, unless you absolutely know what you are doing. + +config TRACEPOINT_BENCHMARK + bool "Add tracepoint that benchmarks tracepoints" + help + This option creates the tracepoint "benchmark:benchmark_event". + When the tracepoint is enabled, it kicks off a kernel thread that + goes into an infinite loop (calling cond_sched() to let other tasks + run), and calls the tracepoint. Each iteration will record the time + it took to write to the tracepoint and the next iteration that + data will be passed to the tracepoint itself. That is, the tracepoint + will report the time it took to do the previous tracepoint. + The string written to the tracepoint is a static string of 128 bytes + to keep the time the same. The initial string is simply a write of + "START". The second string records the cold cache time of the first + write which is not added to the rest of the calculations. + + As it is a tight loop, it benchmarks as hot cache. That's fine because + we care most about hot paths that are probably in cache already. + + An example of the output: + + START + first=3672 [COLD CACHED] + last=632 first=3672 max=632 min=632 avg=316 std=446 std^2=199712 + last=278 first=3672 max=632 min=278 avg=303 std=316 std^2=100337 + last=277 first=3672 max=632 min=277 avg=296 std=258 std^2=67064 + last=273 first=3672 max=632 min=273 avg=292 std=224 std^2=50411 + last=273 first=3672 max=632 min=273 avg=288 std=200 std^2=40389 + last=281 first=3672 max=632 min=273 avg=287 std=183 std^2=33666 + + +config RING_BUFFER_BENCHMARK + tristate "Ring buffer benchmark stress tester" + depends on RING_BUFFER + help + This option creates a test to stress the ring buffer and benchmark it. + It creates its own ring buffer such that it will not interfere with + any other users of the ring buffer (such as ftrace). It then creates + a producer and consumer that will run for 10 seconds and sleep for + 10 seconds. Each interval it will print out the number of events + it recorded and give a rough estimate of how long each iteration took. + + It does not disable interrupts or raise its priority, so it may be + affected by processes that are running. + + If unsure, say N. + +config RING_BUFFER_STARTUP_TEST + bool "Ring buffer startup self test" + depends on RING_BUFFER + help + Run a simple self test on the ring buffer on boot up. Late in the + kernel boot sequence, the test will start that kicks off + a thread per cpu. Each thread will write various size events + into the ring buffer. Another thread is created to send IPIs + to each of the threads, where the IPI handler will also write + to the ring buffer, to test/stress the nesting ability. + If any anomalies are discovered, a warning will be displayed + and all ring buffers will be disabled. + + The test runs for 10 seconds. This will slow your boot time + by at least 10 more seconds. + + At the end of the test, statics and more checks are done. + It will output the stats of each per cpu buffer. What + was written, the sizes, what was read, what was lost, and + other similar details. + + If unsure, say N + +config TRACE_ENUM_MAP_FILE + bool "Show enum mappings for trace events" + depends on TRACING + help + The "print fmt" of the trace events will show the enum names instead + of their values. This can cause problems for user space tools that + use this string to parse the raw data as user space does not know + how to convert the string to its value. + + To fix this, there's a special macro in the kernel that can be used + to convert the enum into its value. If this macro is used, then the + print fmt strings will have the enums converted to their values. + + If something does not get converted properly, this option can be + used to show what enums the kernel tried to convert. + + This option is for debugging the enum conversions. A file is created + in the tracing directory called "enum_map" that will show the enum + names matched with their values and what trace event system they + belong too. + + Normally, the mapping of the strings to values will be freed after + boot up or module load. With this option, they will not be freed, as + they are needed for the "enum_map" file. Enabling this option will + increase the memory footprint of the running kernel. + + If unsure, say N + +endif # FTRACE + +endif # TRACING_SUPPORT + diff --git a/kernel/kernel/trace/Makefile b/kernel/kernel/trace/Makefile new file mode 100644 index 000000000..3bbaea068 --- /dev/null +++ b/kernel/kernel/trace/Makefile @@ -0,0 +1,74 @@ + +# Do not instrument the tracer itself: + +ifdef CONFIG_FUNCTION_TRACER +ORIG_CFLAGS := $(KBUILD_CFLAGS) +KBUILD_CFLAGS = $(subst $(CC_FLAGS_FTRACE),,$(ORIG_CFLAGS)) + +ifdef CONFIG_FTRACE_SELFTEST +# selftest needs instrumentation +CFLAGS_trace_selftest_dynamic.o = $(CC_FLAGS_FTRACE) +obj-y += trace_selftest_dynamic.o +endif +endif + +# If unlikely tracing is enabled, do not trace these files +ifdef CONFIG_TRACING_BRANCHES +KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING +endif + +CFLAGS_trace_benchmark.o := -I$(src) +CFLAGS_trace_events_filter.o := -I$(src) + +obj-$(CONFIG_TRACE_CLOCK) += trace_clock.o + +obj-$(CONFIG_FUNCTION_TRACER) += libftrace.o +obj-$(CONFIG_RING_BUFFER) += ring_buffer.o +obj-$(CONFIG_RING_BUFFER_BENCHMARK) += ring_buffer_benchmark.o + +obj-$(CONFIG_TRACING) += trace.o +obj-$(CONFIG_TRACING) += trace_output.o +obj-$(CONFIG_TRACING) += trace_seq.o +obj-$(CONFIG_TRACING) += trace_stat.o +obj-$(CONFIG_TRACING) += trace_printk.o +obj-$(CONFIG_CONTEXT_SWITCH_TRACER) += trace_sched_switch.o +obj-$(CONFIG_FUNCTION_TRACER) += trace_functions.o +obj-$(CONFIG_IRQSOFF_TRACER) += trace_irqsoff.o +obj-$(CONFIG_PREEMPT_TRACER) += trace_irqsoff.o +obj-$(CONFIG_SCHED_TRACER) += trace_sched_wakeup.o +obj-$(CONFIG_INTERRUPT_OFF_HIST) += latency_hist.o +obj-$(CONFIG_PREEMPT_OFF_HIST) += latency_hist.o +obj-$(CONFIG_WAKEUP_LATENCY_HIST) += latency_hist.o +obj-$(CONFIG_MISSED_TIMER_OFFSETS_HIST) += latency_hist.o +obj-$(CONFIG_NOP_TRACER) += trace_nop.o +obj-$(CONFIG_STACK_TRACER) += trace_stack.o +obj-$(CONFIG_MMIOTRACE) += trace_mmiotrace.o +obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += trace_functions_graph.o +obj-$(CONFIG_TRACE_BRANCH_PROFILING) += trace_branch.o +obj-$(CONFIG_BLK_DEV_IO_TRACE) += blktrace.o +ifeq ($(CONFIG_BLOCK),y) +obj-$(CONFIG_EVENT_TRACING) += blktrace.o +endif +obj-$(CONFIG_EVENT_TRACING) += trace_events.o +obj-$(CONFIG_EVENT_TRACING) += trace_export.o +obj-$(CONFIG_FTRACE_SYSCALLS) += trace_syscalls.o +ifeq ($(CONFIG_PERF_EVENTS),y) +obj-$(CONFIG_EVENT_TRACING) += trace_event_perf.o +endif +obj-$(CONFIG_EVENT_TRACING) += trace_events_filter.o +obj-$(CONFIG_EVENT_TRACING) += trace_events_trigger.o +obj-$(CONFIG_BPF_EVENTS) += bpf_trace.o +obj-$(CONFIG_KPROBE_EVENT) += trace_kprobe.o +obj-$(CONFIG_TRACEPOINTS) += power-traces.o +ifeq ($(CONFIG_PM),y) +obj-$(CONFIG_TRACEPOINTS) += rpm-traces.o +endif +ifeq ($(CONFIG_TRACING),y) +obj-$(CONFIG_KGDB_KDB) += trace_kdb.o +endif +obj-$(CONFIG_PROBE_EVENTS) += trace_probe.o +obj-$(CONFIG_UPROBE_EVENT) += trace_uprobe.o + +obj-$(CONFIG_TRACEPOINT_BENCHMARK) += trace_benchmark.o + +libftrace-y := ftrace.o diff --git a/kernel/kernel/trace/blktrace.c b/kernel/kernel/trace/blktrace.c new file mode 100644 index 000000000..483cecfa5 --- /dev/null +++ b/kernel/kernel/trace/blktrace.c @@ -0,0 +1,1819 @@ +/* + * Copyright (C) 2006 Jens Axboe + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + * + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +#include "trace_output.h" + +#ifdef CONFIG_BLK_DEV_IO_TRACE + +static unsigned int blktrace_seq __read_mostly = 1; + +static struct trace_array *blk_tr; +static bool blk_tracer_enabled __read_mostly; + +static LIST_HEAD(running_trace_list); +static __cacheline_aligned_in_smp DEFINE_SPINLOCK(running_trace_lock); + +/* Select an alternative, minimalistic output than the original one */ +#define TRACE_BLK_OPT_CLASSIC 0x1 + +static struct tracer_opt blk_tracer_opts[] = { + /* Default disable the minimalistic output */ + { TRACER_OPT(blk_classic, TRACE_BLK_OPT_CLASSIC) }, + { } +}; + +static struct tracer_flags blk_tracer_flags = { + .val = 0, + .opts = blk_tracer_opts, +}; + +/* Global reference count of probes */ +static atomic_t blk_probes_ref = ATOMIC_INIT(0); + +static void blk_register_tracepoints(void); +static void blk_unregister_tracepoints(void); + +/* + * Send out a notify message. + */ +static void trace_note(struct blk_trace *bt, pid_t pid, int action, + const void *data, size_t len) +{ + struct blk_io_trace *t; + struct ring_buffer_event *event = NULL; + struct ring_buffer *buffer = NULL; + int pc = 0; + int cpu = smp_processor_id(); + bool blk_tracer = blk_tracer_enabled; + + if (blk_tracer) { + buffer = blk_tr->trace_buffer.buffer; + pc = preempt_count(); + event = trace_buffer_lock_reserve(buffer, TRACE_BLK, + sizeof(*t) + len, + 0, pc); + if (!event) + return; + t = ring_buffer_event_data(event); + goto record_it; + } + + if (!bt->rchan) + return; + + t = relay_reserve(bt->rchan, sizeof(*t) + len); + if (t) { + t->magic = BLK_IO_TRACE_MAGIC | BLK_IO_TRACE_VERSION; + t->time = ktime_to_ns(ktime_get()); +record_it: + t->device = bt->dev; + t->action = action; + t->pid = pid; + t->cpu = cpu; + t->pdu_len = len; + memcpy((void *) t + sizeof(*t), data, len); + + if (blk_tracer) + trace_buffer_unlock_commit(buffer, event, 0, pc); + } +} + +/* + * Send out a notify for this process, if we haven't done so since a trace + * started + */ +static void trace_note_tsk(struct task_struct *tsk) +{ + unsigned long flags; + struct blk_trace *bt; + + tsk->btrace_seq = blktrace_seq; + spin_lock_irqsave(&running_trace_lock, flags); + list_for_each_entry(bt, &running_trace_list, running_list) { + trace_note(bt, tsk->pid, BLK_TN_PROCESS, tsk->comm, + sizeof(tsk->comm)); + } + spin_unlock_irqrestore(&running_trace_lock, flags); +} + +static void trace_note_time(struct blk_trace *bt) +{ + struct timespec now; + unsigned long flags; + u32 words[2]; + + getnstimeofday(&now); + words[0] = now.tv_sec; + words[1] = now.tv_nsec; + + local_irq_save(flags); + trace_note(bt, 0, BLK_TN_TIMESTAMP, words, sizeof(words)); + local_irq_restore(flags); +} + +void __trace_note_message(struct blk_trace *bt, const char *fmt, ...) +{ + int n; + va_list args; + unsigned long flags; + char *buf; + + if (unlikely(bt->trace_state != Blktrace_running && + !blk_tracer_enabled)) + return; + + /* + * If the BLK_TC_NOTIFY action mask isn't set, don't send any note + * message to the trace. + */ + if (!(bt->act_mask & BLK_TC_NOTIFY)) + return; + + local_irq_save(flags); + buf = this_cpu_ptr(bt->msg_data); + va_start(args, fmt); + n = vscnprintf(buf, BLK_TN_MAX_MSG, fmt, args); + va_end(args); + + trace_note(bt, 0, BLK_TN_MESSAGE, buf, n); + local_irq_restore(flags); +} +EXPORT_SYMBOL_GPL(__trace_note_message); + +static int act_log_check(struct blk_trace *bt, u32 what, sector_t sector, + pid_t pid) +{ + if (((bt->act_mask << BLK_TC_SHIFT) & what) == 0) + return 1; + if (sector && (sector < bt->start_lba || sector > bt->end_lba)) + return 1; + if (bt->pid && pid != bt->pid) + return 1; + + return 0; +} + +/* + * Data direction bit lookup + */ +static const u32 ddir_act[2] = { BLK_TC_ACT(BLK_TC_READ), + BLK_TC_ACT(BLK_TC_WRITE) }; + +#define BLK_TC_RAHEAD BLK_TC_AHEAD + +/* The ilog2() calls fall out because they're constant */ +#define MASK_TC_BIT(rw, __name) ((rw & REQ_ ## __name) << \ + (ilog2(BLK_TC_ ## __name) + BLK_TC_SHIFT - __REQ_ ## __name)) + +/* + * The worker for the various blk_add_trace*() types. Fills out a + * blk_io_trace structure and places it in a per-cpu subbuffer. + */ +static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes, + int rw, u32 what, int error, int pdu_len, void *pdu_data) +{ + struct task_struct *tsk = current; + struct ring_buffer_event *event = NULL; + struct ring_buffer *buffer = NULL; + struct blk_io_trace *t; + unsigned long flags = 0; + unsigned long *sequence; + pid_t pid; + int cpu, pc = 0; + bool blk_tracer = blk_tracer_enabled; + + if (unlikely(bt->trace_state != Blktrace_running && !blk_tracer)) + return; + + what |= ddir_act[rw & WRITE]; + what |= MASK_TC_BIT(rw, SYNC); + what |= MASK_TC_BIT(rw, RAHEAD); + what |= MASK_TC_BIT(rw, META); + what |= MASK_TC_BIT(rw, DISCARD); + what |= MASK_TC_BIT(rw, FLUSH); + what |= MASK_TC_BIT(rw, FUA); + + pid = tsk->pid; + if (act_log_check(bt, what, sector, pid)) + return; + cpu = raw_smp_processor_id(); + + if (blk_tracer) { + tracing_record_cmdline(current); + + buffer = blk_tr->trace_buffer.buffer; + pc = preempt_count(); + event = trace_buffer_lock_reserve(buffer, TRACE_BLK, + sizeof(*t) + pdu_len, + 0, pc); + if (!event) + return; + t = ring_buffer_event_data(event); + goto record_it; + } + + if (unlikely(tsk->btrace_seq != blktrace_seq)) + trace_note_tsk(tsk); + + /* + * A word about the locking here - we disable interrupts to reserve + * some space in the relay per-cpu buffer, to prevent an irq + * from coming in and stepping on our toes. + */ + local_irq_save(flags); + t = relay_reserve(bt->rchan, sizeof(*t) + pdu_len); + if (t) { + sequence = per_cpu_ptr(bt->sequence, cpu); + + t->magic = BLK_IO_TRACE_MAGIC | BLK_IO_TRACE_VERSION; + t->sequence = ++(*sequence); + t->time = ktime_to_ns(ktime_get()); +record_it: + /* + * These two are not needed in ftrace as they are in the + * generic trace_entry, filled by tracing_generic_entry_update, + * but for the trace_event->bin() synthesizer benefit we do it + * here too. + */ + t->cpu = cpu; + t->pid = pid; + + t->sector = sector; + t->bytes = bytes; + t->action = what; + t->device = bt->dev; + t->error = error; + t->pdu_len = pdu_len; + + if (pdu_len) + memcpy((void *) t + sizeof(*t), pdu_data, pdu_len); + + if (blk_tracer) { + trace_buffer_unlock_commit(buffer, event, 0, pc); + return; + } + } + + local_irq_restore(flags); +} + +static struct dentry *blk_tree_root; +static DEFINE_MUTEX(blk_tree_mutex); + +static void blk_trace_free(struct blk_trace *bt) +{ + debugfs_remove(bt->msg_file); + debugfs_remove(bt->dropped_file); + relay_close(bt->rchan); + debugfs_remove(bt->dir); + free_percpu(bt->sequence); + free_percpu(bt->msg_data); + kfree(bt); +} + +static void blk_trace_cleanup(struct blk_trace *bt) +{ + blk_trace_free(bt); + if (atomic_dec_and_test(&blk_probes_ref)) + blk_unregister_tracepoints(); +} + +int blk_trace_remove(struct request_queue *q) +{ + struct blk_trace *bt; + + bt = xchg(&q->blk_trace, NULL); + if (!bt) + return -EINVAL; + + if (bt->trace_state != Blktrace_running) + blk_trace_cleanup(bt); + + return 0; +} +EXPORT_SYMBOL_GPL(blk_trace_remove); + +static ssize_t blk_dropped_read(struct file *filp, char __user *buffer, + size_t count, loff_t *ppos) +{ + struct blk_trace *bt = filp->private_data; + char buf[16]; + + snprintf(buf, sizeof(buf), "%u\n", atomic_read(&bt->dropped)); + + return simple_read_from_buffer(buffer, count, ppos, buf, strlen(buf)); +} + +static const struct file_operations blk_dropped_fops = { + .owner = THIS_MODULE, + .open = simple_open, + .read = blk_dropped_read, + .llseek = default_llseek, +}; + +static ssize_t blk_msg_write(struct file *filp, const char __user *buffer, + size_t count, loff_t *ppos) +{ + char *msg; + struct blk_trace *bt; + + if (count >= BLK_TN_MAX_MSG) + return -EINVAL; + + msg = kmalloc(count + 1, GFP_KERNEL); + if (msg == NULL) + return -ENOMEM; + + if (copy_from_user(msg, buffer, count)) { + kfree(msg); + return -EFAULT; + } + + msg[count] = '\0'; + bt = filp->private_data; + __trace_note_message(bt, "%s", msg); + kfree(msg); + + return count; +} + +static const struct file_operations blk_msg_fops = { + .owner = THIS_MODULE, + .open = simple_open, + .write = blk_msg_write, + .llseek = noop_llseek, +}; + +/* + * Keep track of how many times we encountered a full subbuffer, to aid + * the user space app in telling how many lost events there were. + */ +static int blk_subbuf_start_callback(struct rchan_buf *buf, void *subbuf, + void *prev_subbuf, size_t prev_padding) +{ + struct blk_trace *bt; + + if (!relay_buf_full(buf)) + return 1; + + bt = buf->chan->private_data; + atomic_inc(&bt->dropped); + return 0; +} + +static int blk_remove_buf_file_callback(struct dentry *dentry) +{ + debugfs_remove(dentry); + + return 0; +} + +static struct dentry *blk_create_buf_file_callback(const char *filename, + struct dentry *parent, + umode_t mode, + struct rchan_buf *buf, + int *is_global) +{ + return debugfs_create_file(filename, mode, parent, buf, + &relay_file_operations); +} + +static struct rchan_callbacks blk_relay_callbacks = { + .subbuf_start = blk_subbuf_start_callback, + .create_buf_file = blk_create_buf_file_callback, + .remove_buf_file = blk_remove_buf_file_callback, +}; + +static void blk_trace_setup_lba(struct blk_trace *bt, + struct block_device *bdev) +{ + struct hd_struct *part = NULL; + + if (bdev) + part = bdev->bd_part; + + if (part) { + bt->start_lba = part->start_sect; + bt->end_lba = part->start_sect + part->nr_sects; + } else { + bt->start_lba = 0; + bt->end_lba = -1ULL; + } +} + +/* + * Setup everything required to start tracing + */ +int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev, + struct block_device *bdev, + struct blk_user_trace_setup *buts) +{ + struct blk_trace *old_bt, *bt = NULL; + struct dentry *dir = NULL; + int ret, i; + + if (!buts->buf_size || !buts->buf_nr) + return -EINVAL; + + strncpy(buts->name, name, BLKTRACE_BDEV_SIZE); + buts->name[BLKTRACE_BDEV_SIZE - 1] = '\0'; + + /* + * some device names have larger paths - convert the slashes + * to underscores for this to work as expected + */ + for (i = 0; i < strlen(buts->name); i++) + if (buts->name[i] == '/') + buts->name[i] = '_'; + + bt = kzalloc(sizeof(*bt), GFP_KERNEL); + if (!bt) + return -ENOMEM; + + ret = -ENOMEM; + bt->sequence = alloc_percpu(unsigned long); + if (!bt->sequence) + goto err; + + bt->msg_data = __alloc_percpu(BLK_TN_MAX_MSG, __alignof__(char)); + if (!bt->msg_data) + goto err; + + ret = -ENOENT; + + mutex_lock(&blk_tree_mutex); + if (!blk_tree_root) { + blk_tree_root = debugfs_create_dir("block", NULL); + if (!blk_tree_root) { + mutex_unlock(&blk_tree_mutex); + goto err; + } + } + mutex_unlock(&blk_tree_mutex); + + dir = debugfs_create_dir(buts->name, blk_tree_root); + + if (!dir) + goto err; + + bt->dir = dir; + bt->dev = dev; + atomic_set(&bt->dropped, 0); + INIT_LIST_HEAD(&bt->running_list); + + ret = -EIO; + bt->dropped_file = debugfs_create_file("dropped", 0444, dir, bt, + &blk_dropped_fops); + if (!bt->dropped_file) + goto err; + + bt->msg_file = debugfs_create_file("msg", 0222, dir, bt, &blk_msg_fops); + if (!bt->msg_file) + goto err; + + bt->rchan = relay_open("trace", dir, buts->buf_size, + buts->buf_nr, &blk_relay_callbacks, bt); + if (!bt->rchan) + goto err; + + bt->act_mask = buts->act_mask; + if (!bt->act_mask) + bt->act_mask = (u16) -1; + + blk_trace_setup_lba(bt, bdev); + + /* overwrite with user settings */ + if (buts->start_lba) + bt->start_lba = buts->start_lba; + if (buts->end_lba) + bt->end_lba = buts->end_lba; + + bt->pid = buts->pid; + bt->trace_state = Blktrace_setup; + + ret = -EBUSY; + old_bt = xchg(&q->blk_trace, bt); + if (old_bt) { + (void) xchg(&q->blk_trace, old_bt); + goto err; + } + + if (atomic_inc_return(&blk_probes_ref) == 1) + blk_register_tracepoints(); + + return 0; +err: + blk_trace_free(bt); + return ret; +} + +int blk_trace_setup(struct request_queue *q, char *name, dev_t dev, + struct block_device *bdev, + char __user *arg) +{ + struct blk_user_trace_setup buts; + int ret; + + ret = copy_from_user(&buts, arg, sizeof(buts)); + if (ret) + return -EFAULT; + + ret = do_blk_trace_setup(q, name, dev, bdev, &buts); + if (ret) + return ret; + + if (copy_to_user(arg, &buts, sizeof(buts))) { + blk_trace_remove(q); + return -EFAULT; + } + return 0; +} +EXPORT_SYMBOL_GPL(blk_trace_setup); + +#if defined(CONFIG_COMPAT) && defined(CONFIG_X86_64) +static int compat_blk_trace_setup(struct request_queue *q, char *name, + dev_t dev, struct block_device *bdev, + char __user *arg) +{ + struct blk_user_trace_setup buts; + struct compat_blk_user_trace_setup cbuts; + int ret; + + if (copy_from_user(&cbuts, arg, sizeof(cbuts))) + return -EFAULT; + + buts = (struct blk_user_trace_setup) { + .act_mask = cbuts.act_mask, + .buf_size = cbuts.buf_size, + .buf_nr = cbuts.buf_nr, + .start_lba = cbuts.start_lba, + .end_lba = cbuts.end_lba, + .pid = cbuts.pid, + }; + + ret = do_blk_trace_setup(q, name, dev, bdev, &buts); + if (ret) + return ret; + + if (copy_to_user(arg, &buts.name, ARRAY_SIZE(buts.name))) { + blk_trace_remove(q); + return -EFAULT; + } + + return 0; +} +#endif + +int blk_trace_startstop(struct request_queue *q, int start) +{ + int ret; + struct blk_trace *bt = q->blk_trace; + + if (bt == NULL) + return -EINVAL; + + /* + * For starting a trace, we can transition from a setup or stopped + * trace. For stopping a trace, the state must be running + */ + ret = -EINVAL; + if (start) { + if (bt->trace_state == Blktrace_setup || + bt->trace_state == Blktrace_stopped) { + blktrace_seq++; + smp_mb(); + bt->trace_state = Blktrace_running; + spin_lock_irq(&running_trace_lock); + list_add(&bt->running_list, &running_trace_list); + spin_unlock_irq(&running_trace_lock); + + trace_note_time(bt); + ret = 0; + } + } else { + if (bt->trace_state == Blktrace_running) { + bt->trace_state = Blktrace_stopped; + spin_lock_irq(&running_trace_lock); + list_del_init(&bt->running_list); + spin_unlock_irq(&running_trace_lock); + relay_flush(bt->rchan); + ret = 0; + } + } + + return ret; +} +EXPORT_SYMBOL_GPL(blk_trace_startstop); + +/** + * blk_trace_ioctl: - handle the ioctls associated with tracing + * @bdev: the block device + * @cmd: the ioctl cmd + * @arg: the argument data, if any + * + **/ +int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg) +{ + struct request_queue *q; + int ret, start = 0; + char b[BDEVNAME_SIZE]; + + q = bdev_get_queue(bdev); + if (!q) + return -ENXIO; + + mutex_lock(&bdev->bd_mutex); + + switch (cmd) { + case BLKTRACESETUP: + bdevname(bdev, b); + ret = blk_trace_setup(q, b, bdev->bd_dev, bdev, arg); + break; +#if defined(CONFIG_COMPAT) && defined(CONFIG_X86_64) + case BLKTRACESETUP32: + bdevname(bdev, b); + ret = compat_blk_trace_setup(q, b, bdev->bd_dev, bdev, arg); + break; +#endif + case BLKTRACESTART: + start = 1; + case BLKTRACESTOP: + ret = blk_trace_startstop(q, start); + break; + case BLKTRACETEARDOWN: + ret = blk_trace_remove(q); + break; + default: + ret = -ENOTTY; + break; + } + + mutex_unlock(&bdev->bd_mutex); + return ret; +} + +/** + * blk_trace_shutdown: - stop and cleanup trace structures + * @q: the request queue associated with the device + * + **/ +void blk_trace_shutdown(struct request_queue *q) +{ + if (q->blk_trace) { + blk_trace_startstop(q, 0); + blk_trace_remove(q); + } +} + +/* + * blktrace probes + */ + +/** + * blk_add_trace_rq - Add a trace for a request oriented action + * @q: queue the io is for + * @rq: the source request + * @nr_bytes: number of completed bytes + * @what: the action + * + * Description: + * Records an action against a request. Will log the bio offset + size. + * + **/ +static void blk_add_trace_rq(struct request_queue *q, struct request *rq, + unsigned int nr_bytes, u32 what) +{ + struct blk_trace *bt = q->blk_trace; + + if (likely(!bt)) + return; + + if (rq->cmd_type == REQ_TYPE_BLOCK_PC) { + what |= BLK_TC_ACT(BLK_TC_PC); + __blk_add_trace(bt, 0, nr_bytes, rq->cmd_flags, + what, rq->errors, rq->cmd_len, rq->cmd); + } else { + what |= BLK_TC_ACT(BLK_TC_FS); + __blk_add_trace(bt, blk_rq_pos(rq), nr_bytes, + rq->cmd_flags, what, rq->errors, 0, NULL); + } +} + +static void blk_add_trace_rq_abort(void *ignore, + struct request_queue *q, struct request *rq) +{ + blk_add_trace_rq(q, rq, blk_rq_bytes(rq), BLK_TA_ABORT); +} + +static void blk_add_trace_rq_insert(void *ignore, + struct request_queue *q, struct request *rq) +{ + blk_add_trace_rq(q, rq, blk_rq_bytes(rq), BLK_TA_INSERT); +} + +static void blk_add_trace_rq_issue(void *ignore, + struct request_queue *q, struct request *rq) +{ + blk_add_trace_rq(q, rq, blk_rq_bytes(rq), BLK_TA_ISSUE); +} + +static void blk_add_trace_rq_requeue(void *ignore, + struct request_queue *q, + struct request *rq) +{ + blk_add_trace_rq(q, rq, blk_rq_bytes(rq), BLK_TA_REQUEUE); +} + +static void blk_add_trace_rq_complete(void *ignore, + struct request_queue *q, + struct request *rq, + unsigned int nr_bytes) +{ + blk_add_trace_rq(q, rq, nr_bytes, BLK_TA_COMPLETE); +} + +/** + * blk_add_trace_bio - Add a trace for a bio oriented action + * @q: queue the io is for + * @bio: the source bio + * @what: the action + * @error: error, if any + * + * Description: + * Records an action against a bio. Will log the bio offset + size. + * + **/ +static void blk_add_trace_bio(struct request_queue *q, struct bio *bio, + u32 what, int error) +{ + struct blk_trace *bt = q->blk_trace; + + if (likely(!bt)) + return; + + if (!error && !bio_flagged(bio, BIO_UPTODATE)) + error = EIO; + + __blk_add_trace(bt, bio->bi_iter.bi_sector, bio->bi_iter.bi_size, + bio->bi_rw, what, error, 0, NULL); +} + +static void blk_add_trace_bio_bounce(void *ignore, + struct request_queue *q, struct bio *bio) +{ + blk_add_trace_bio(q, bio, BLK_TA_BOUNCE, 0); +} + +static void blk_add_trace_bio_complete(void *ignore, + struct request_queue *q, struct bio *bio, + int error) +{ + blk_add_trace_bio(q, bio, BLK_TA_COMPLETE, error); +} + +static void blk_add_trace_bio_backmerge(void *ignore, + struct request_queue *q, + struct request *rq, + struct bio *bio) +{ + blk_add_trace_bio(q, bio, BLK_TA_BACKMERGE, 0); +} + +static void blk_add_trace_bio_frontmerge(void *ignore, + struct request_queue *q, + struct request *rq, + struct bio *bio) +{ + blk_add_trace_bio(q, bio, BLK_TA_FRONTMERGE, 0); +} + +static void blk_add_trace_bio_queue(void *ignore, + struct request_queue *q, struct bio *bio) +{ + blk_add_trace_bio(q, bio, BLK_TA_QUEUE, 0); +} + +static void blk_add_trace_getrq(void *ignore, + struct request_queue *q, + struct bio *bio, int rw) +{ + if (bio) + blk_add_trace_bio(q, bio, BLK_TA_GETRQ, 0); + else { + struct blk_trace *bt = q->blk_trace; + + if (bt) + __blk_add_trace(bt, 0, 0, rw, BLK_TA_GETRQ, 0, 0, NULL); + } +} + + +static void blk_add_trace_sleeprq(void *ignore, + struct request_queue *q, + struct bio *bio, int rw) +{ + if (bio) + blk_add_trace_bio(q, bio, BLK_TA_SLEEPRQ, 0); + else { + struct blk_trace *bt = q->blk_trace; + + if (bt) + __blk_add_trace(bt, 0, 0, rw, BLK_TA_SLEEPRQ, + 0, 0, NULL); + } +} + +static void blk_add_trace_plug(void *ignore, struct request_queue *q) +{ + struct blk_trace *bt = q->blk_trace; + + if (bt) + __blk_add_trace(bt, 0, 0, 0, BLK_TA_PLUG, 0, 0, NULL); +} + +static void blk_add_trace_unplug(void *ignore, struct request_queue *q, + unsigned int depth, bool explicit) +{ + struct blk_trace *bt = q->blk_trace; + + if (bt) { + __be64 rpdu = cpu_to_be64(depth); + u32 what; + + if (explicit) + what = BLK_TA_UNPLUG_IO; + else + what = BLK_TA_UNPLUG_TIMER; + + __blk_add_trace(bt, 0, 0, 0, what, 0, sizeof(rpdu), &rpdu); + } +} + +static void blk_add_trace_split(void *ignore, + struct request_queue *q, struct bio *bio, + unsigned int pdu) +{ + struct blk_trace *bt = q->blk_trace; + + if (bt) { + __be64 rpdu = cpu_to_be64(pdu); + + __blk_add_trace(bt, bio->bi_iter.bi_sector, + bio->bi_iter.bi_size, bio->bi_rw, BLK_TA_SPLIT, + !bio_flagged(bio, BIO_UPTODATE), + sizeof(rpdu), &rpdu); + } +} + +/** + * blk_add_trace_bio_remap - Add a trace for a bio-remap operation + * @ignore: trace callback data parameter (not used) + * @q: queue the io is for + * @bio: the source bio + * @dev: target device + * @from: source sector + * + * Description: + * Device mapper or raid target sometimes need to split a bio because + * it spans a stripe (or similar). Add a trace for that action. + * + **/ +static void blk_add_trace_bio_remap(void *ignore, + struct request_queue *q, struct bio *bio, + dev_t dev, sector_t from) +{ + struct blk_trace *bt = q->blk_trace; + struct blk_io_trace_remap r; + + if (likely(!bt)) + return; + + r.device_from = cpu_to_be32(dev); + r.device_to = cpu_to_be32(bio->bi_bdev->bd_dev); + r.sector_from = cpu_to_be64(from); + + __blk_add_trace(bt, bio->bi_iter.bi_sector, bio->bi_iter.bi_size, + bio->bi_rw, BLK_TA_REMAP, + !bio_flagged(bio, BIO_UPTODATE), sizeof(r), &r); +} + +/** + * blk_add_trace_rq_remap - Add a trace for a request-remap operation + * @ignore: trace callback data parameter (not used) + * @q: queue the io is for + * @rq: the source request + * @dev: target device + * @from: source sector + * + * Description: + * Device mapper remaps request to other devices. + * Add a trace for that action. + * + **/ +static void blk_add_trace_rq_remap(void *ignore, + struct request_queue *q, + struct request *rq, dev_t dev, + sector_t from) +{ + struct blk_trace *bt = q->blk_trace; + struct blk_io_trace_remap r; + + if (likely(!bt)) + return; + + r.device_from = cpu_to_be32(dev); + r.device_to = cpu_to_be32(disk_devt(rq->rq_disk)); + r.sector_from = cpu_to_be64(from); + + __blk_add_trace(bt, blk_rq_pos(rq), blk_rq_bytes(rq), + rq_data_dir(rq), BLK_TA_REMAP, !!rq->errors, + sizeof(r), &r); +} + +/** + * blk_add_driver_data - Add binary message with driver-specific data + * @q: queue the io is for + * @rq: io request + * @data: driver-specific data + * @len: length of driver-specific data + * + * Description: + * Some drivers might want to write driver-specific data per request. + * + **/ +void blk_add_driver_data(struct request_queue *q, + struct request *rq, + void *data, size_t len) +{ + struct blk_trace *bt = q->blk_trace; + + if (likely(!bt)) + return; + + if (rq->cmd_type == REQ_TYPE_BLOCK_PC) + __blk_add_trace(bt, 0, blk_rq_bytes(rq), 0, + BLK_TA_DRV_DATA, rq->errors, len, data); + else + __blk_add_trace(bt, blk_rq_pos(rq), blk_rq_bytes(rq), 0, + BLK_TA_DRV_DATA, rq->errors, len, data); +} +EXPORT_SYMBOL_GPL(blk_add_driver_data); + +static void blk_register_tracepoints(void) +{ + int ret; + + ret = register_trace_block_rq_abort(blk_add_trace_rq_abort, NULL); + WARN_ON(ret); + ret = register_trace_block_rq_insert(blk_add_trace_rq_insert, NULL); + WARN_ON(ret); + ret = register_trace_block_rq_issue(blk_add_trace_rq_issue, NULL); + WARN_ON(ret); + ret = register_trace_block_rq_requeue(blk_add_trace_rq_requeue, NULL); + WARN_ON(ret); + ret = register_trace_block_rq_complete(blk_add_trace_rq_complete, NULL); + WARN_ON(ret); + ret = register_trace_block_bio_bounce(blk_add_trace_bio_bounce, NULL); + WARN_ON(ret); + ret = register_trace_block_bio_complete(blk_add_trace_bio_complete, NULL); + WARN_ON(ret); + ret = register_trace_block_bio_backmerge(blk_add_trace_bio_backmerge, NULL); + WARN_ON(ret); + ret = register_trace_block_bio_frontmerge(blk_add_trace_bio_frontmerge, NULL); + WARN_ON(ret); + ret = register_trace_block_bio_queue(blk_add_trace_bio_queue, NULL); + WARN_ON(ret); + ret = register_trace_block_getrq(blk_add_trace_getrq, NULL); + WARN_ON(ret); + ret = register_trace_block_sleeprq(blk_add_trace_sleeprq, NULL); + WARN_ON(ret); + ret = register_trace_block_plug(blk_add_trace_plug, NULL); + WARN_ON(ret); + ret = register_trace_block_unplug(blk_add_trace_unplug, NULL); + WARN_ON(ret); + ret = register_trace_block_split(blk_add_trace_split, NULL); + WARN_ON(ret); + ret = register_trace_block_bio_remap(blk_add_trace_bio_remap, NULL); + WARN_ON(ret); + ret = register_trace_block_rq_remap(blk_add_trace_rq_remap, NULL); + WARN_ON(ret); +} + +static void blk_unregister_tracepoints(void) +{ + unregister_trace_block_rq_remap(blk_add_trace_rq_remap, NULL); + unregister_trace_block_bio_remap(blk_add_trace_bio_remap, NULL); + unregister_trace_block_split(blk_add_trace_split, NULL); + unregister_trace_block_unplug(blk_add_trace_unplug, NULL); + unregister_trace_block_plug(blk_add_trace_plug, NULL); + unregister_trace_block_sleeprq(blk_add_trace_sleeprq, NULL); + unregister_trace_block_getrq(blk_add_trace_getrq, NULL); + unregister_trace_block_bio_queue(blk_add_trace_bio_queue, NULL); + unregister_trace_block_bio_frontmerge(blk_add_trace_bio_frontmerge, NULL); + unregister_trace_block_bio_backmerge(blk_add_trace_bio_backmerge, NULL); + unregister_trace_block_bio_complete(blk_add_trace_bio_complete, NULL); + unregister_trace_block_bio_bounce(blk_add_trace_bio_bounce, NULL); + unregister_trace_block_rq_complete(blk_add_trace_rq_complete, NULL); + unregister_trace_block_rq_requeue(blk_add_trace_rq_requeue, NULL); + unregister_trace_block_rq_issue(blk_add_trace_rq_issue, NULL); + unregister_trace_block_rq_insert(blk_add_trace_rq_insert, NULL); + unregister_trace_block_rq_abort(blk_add_trace_rq_abort, NULL); + + tracepoint_synchronize_unregister(); +} + +/* + * struct blk_io_tracer formatting routines + */ + +static void fill_rwbs(char *rwbs, const struct blk_io_trace *t) +{ + int i = 0; + int tc = t->action >> BLK_TC_SHIFT; + + if (t->action == BLK_TN_MESSAGE) { + rwbs[i++] = 'N'; + goto out; + } + + if (tc & BLK_TC_FLUSH) + rwbs[i++] = 'F'; + + if (tc & BLK_TC_DISCARD) + rwbs[i++] = 'D'; + else if (tc & BLK_TC_WRITE) + rwbs[i++] = 'W'; + else if (t->bytes) + rwbs[i++] = 'R'; + else + rwbs[i++] = 'N'; + + if (tc & BLK_TC_FUA) + rwbs[i++] = 'F'; + if (tc & BLK_TC_AHEAD) + rwbs[i++] = 'A'; + if (tc & BLK_TC_SYNC) + rwbs[i++] = 'S'; + if (tc & BLK_TC_META) + rwbs[i++] = 'M'; +out: + rwbs[i] = '\0'; +} + +static inline +const struct blk_io_trace *te_blk_io_trace(const struct trace_entry *ent) +{ + return (const struct blk_io_trace *)ent; +} + +static inline const void *pdu_start(const struct trace_entry *ent) +{ + return te_blk_io_trace(ent) + 1; +} + +static inline u32 t_action(const struct trace_entry *ent) +{ + return te_blk_io_trace(ent)->action; +} + +static inline u32 t_bytes(const struct trace_entry *ent) +{ + return te_blk_io_trace(ent)->bytes; +} + +static inline u32 t_sec(const struct trace_entry *ent) +{ + return te_blk_io_trace(ent)->bytes >> 9; +} + +static inline unsigned long long t_sector(const struct trace_entry *ent) +{ + return te_blk_io_trace(ent)->sector; +} + +static inline __u16 t_error(const struct trace_entry *ent) +{ + return te_blk_io_trace(ent)->error; +} + +static __u64 get_pdu_int(const struct trace_entry *ent) +{ + const __u64 *val = pdu_start(ent); + return be64_to_cpu(*val); +} + +static void get_pdu_remap(const struct trace_entry *ent, + struct blk_io_trace_remap *r) +{ + const struct blk_io_trace_remap *__r = pdu_start(ent); + __u64 sector_from = __r->sector_from; + + r->device_from = be32_to_cpu(__r->device_from); + r->device_to = be32_to_cpu(__r->device_to); + r->sector_from = be64_to_cpu(sector_from); +} + +typedef void (blk_log_action_t) (struct trace_iterator *iter, const char *act); + +static void blk_log_action_classic(struct trace_iterator *iter, const char *act) +{ + char rwbs[RWBS_LEN]; + unsigned long long ts = iter->ts; + unsigned long nsec_rem = do_div(ts, NSEC_PER_SEC); + unsigned secs = (unsigned long)ts; + const struct blk_io_trace *t = te_blk_io_trace(iter->ent); + + fill_rwbs(rwbs, t); + + trace_seq_printf(&iter->seq, + "%3d,%-3d %2d %5d.%09lu %5u %2s %3s ", + MAJOR(t->device), MINOR(t->device), iter->cpu, + secs, nsec_rem, iter->ent->pid, act, rwbs); +} + +static void blk_log_action(struct trace_iterator *iter, const char *act) +{ + char rwbs[RWBS_LEN]; + const struct blk_io_trace *t = te_blk_io_trace(iter->ent); + + fill_rwbs(rwbs, t); + trace_seq_printf(&iter->seq, "%3d,%-3d %2s %3s ", + MAJOR(t->device), MINOR(t->device), act, rwbs); +} + +static void blk_log_dump_pdu(struct trace_seq *s, const struct trace_entry *ent) +{ + const unsigned char *pdu_buf; + int pdu_len; + int i, end; + + pdu_buf = pdu_start(ent); + pdu_len = te_blk_io_trace(ent)->pdu_len; + + if (!pdu_len) + return; + + /* find the last zero that needs to be printed */ + for (end = pdu_len - 1; end >= 0; end--) + if (pdu_buf[end]) + break; + end++; + + trace_seq_putc(s, '('); + + for (i = 0; i < pdu_len; i++) { + + trace_seq_printf(s, "%s%02x", + i == 0 ? "" : " ", pdu_buf[i]); + + /* + * stop when the rest is just zeroes and indicate so + * with a ".." appended + */ + if (i == end && end != pdu_len - 1) { + trace_seq_puts(s, " ..) "); + return; + } + } + + trace_seq_puts(s, ") "); +} + +static void blk_log_generic(struct trace_seq *s, const struct trace_entry *ent) +{ + char cmd[TASK_COMM_LEN]; + + trace_find_cmdline(ent->pid, cmd); + + if (t_action(ent) & BLK_TC_ACT(BLK_TC_PC)) { + trace_seq_printf(s, "%u ", t_bytes(ent)); + blk_log_dump_pdu(s, ent); + trace_seq_printf(s, "[%s]\n", cmd); + } else { + if (t_sec(ent)) + trace_seq_printf(s, "%llu + %u [%s]\n", + t_sector(ent), t_sec(ent), cmd); + else + trace_seq_printf(s, "[%s]\n", cmd); + } +} + +static void blk_log_with_error(struct trace_seq *s, + const struct trace_entry *ent) +{ + if (t_action(ent) & BLK_TC_ACT(BLK_TC_PC)) { + blk_log_dump_pdu(s, ent); + trace_seq_printf(s, "[%d]\n", t_error(ent)); + } else { + if (t_sec(ent)) + trace_seq_printf(s, "%llu + %u [%d]\n", + t_sector(ent), + t_sec(ent), t_error(ent)); + else + trace_seq_printf(s, "%llu [%d]\n", + t_sector(ent), t_error(ent)); + } +} + +static void blk_log_remap(struct trace_seq *s, const struct trace_entry *ent) +{ + struct blk_io_trace_remap r = { .device_from = 0, }; + + get_pdu_remap(ent, &r); + trace_seq_printf(s, "%llu + %u <- (%d,%d) %llu\n", + t_sector(ent), t_sec(ent), + MAJOR(r.device_from), MINOR(r.device_from), + (unsigned long long)r.sector_from); +} + +static void blk_log_plug(struct trace_seq *s, const struct trace_entry *ent) +{ + char cmd[TASK_COMM_LEN]; + + trace_find_cmdline(ent->pid, cmd); + + trace_seq_printf(s, "[%s]\n", cmd); +} + +static void blk_log_unplug(struct trace_seq *s, const struct trace_entry *ent) +{ + char cmd[TASK_COMM_LEN]; + + trace_find_cmdline(ent->pid, cmd); + + trace_seq_printf(s, "[%s] %llu\n", cmd, get_pdu_int(ent)); +} + +static void blk_log_split(struct trace_seq *s, const struct trace_entry *ent) +{ + char cmd[TASK_COMM_LEN]; + + trace_find_cmdline(ent->pid, cmd); + + trace_seq_printf(s, "%llu / %llu [%s]\n", t_sector(ent), + get_pdu_int(ent), cmd); +} + +static void blk_log_msg(struct trace_seq *s, const struct trace_entry *ent) +{ + const struct blk_io_trace *t = te_blk_io_trace(ent); + + trace_seq_putmem(s, t + 1, t->pdu_len); + trace_seq_putc(s, '\n'); +} + +/* + * struct tracer operations + */ + +static void blk_tracer_print_header(struct seq_file *m) +{ + if (!(blk_tracer_flags.val & TRACE_BLK_OPT_CLASSIC)) + return; + seq_puts(m, "# DEV CPU TIMESTAMP PID ACT FLG\n" + "# | | | | | |\n"); +} + +static void blk_tracer_start(struct trace_array *tr) +{ + blk_tracer_enabled = true; +} + +static int blk_tracer_init(struct trace_array *tr) +{ + blk_tr = tr; + blk_tracer_start(tr); + return 0; +} + +static void blk_tracer_stop(struct trace_array *tr) +{ + blk_tracer_enabled = false; +} + +static void blk_tracer_reset(struct trace_array *tr) +{ + blk_tracer_stop(tr); +} + +static const struct { + const char *act[2]; + void (*print)(struct trace_seq *s, const struct trace_entry *ent); +} what2act[] = { + [__BLK_TA_QUEUE] = {{ "Q", "queue" }, blk_log_generic }, + [__BLK_TA_BACKMERGE] = {{ "M", "backmerge" }, blk_log_generic }, + [__BLK_TA_FRONTMERGE] = {{ "F", "frontmerge" }, blk_log_generic }, + [__BLK_TA_GETRQ] = {{ "G", "getrq" }, blk_log_generic }, + [__BLK_TA_SLEEPRQ] = {{ "S", "sleeprq" }, blk_log_generic }, + [__BLK_TA_REQUEUE] = {{ "R", "requeue" }, blk_log_with_error }, + [__BLK_TA_ISSUE] = {{ "D", "issue" }, blk_log_generic }, + [__BLK_TA_COMPLETE] = {{ "C", "complete" }, blk_log_with_error }, + [__BLK_TA_PLUG] = {{ "P", "plug" }, blk_log_plug }, + [__BLK_TA_UNPLUG_IO] = {{ "U", "unplug_io" }, blk_log_unplug }, + [__BLK_TA_UNPLUG_TIMER] = {{ "UT", "unplug_timer" }, blk_log_unplug }, + [__BLK_TA_INSERT] = {{ "I", "insert" }, blk_log_generic }, + [__BLK_TA_SPLIT] = {{ "X", "split" }, blk_log_split }, + [__BLK_TA_BOUNCE] = {{ "B", "bounce" }, blk_log_generic }, + [__BLK_TA_REMAP] = {{ "A", "remap" }, blk_log_remap }, +}; + +static enum print_line_t print_one_line(struct trace_iterator *iter, + bool classic) +{ + struct trace_seq *s = &iter->seq; + const struct blk_io_trace *t; + u16 what; + bool long_act; + blk_log_action_t *log_action; + + t = te_blk_io_trace(iter->ent); + what = t->action & ((1 << BLK_TC_SHIFT) - 1); + long_act = !!(trace_flags & TRACE_ITER_VERBOSE); + log_action = classic ? &blk_log_action_classic : &blk_log_action; + + if (t->action == BLK_TN_MESSAGE) { + log_action(iter, long_act ? "message" : "m"); + blk_log_msg(s, iter->ent); + } + + if (unlikely(what == 0 || what >= ARRAY_SIZE(what2act))) + trace_seq_printf(s, "Unknown action %x\n", what); + else { + log_action(iter, what2act[what].act[long_act]); + what2act[what].print(s, iter->ent); + } + + return trace_handle_return(s); +} + +static enum print_line_t blk_trace_event_print(struct trace_iterator *iter, + int flags, struct trace_event *event) +{ + return print_one_line(iter, false); +} + +static void blk_trace_synthesize_old_trace(struct trace_iterator *iter) +{ + struct trace_seq *s = &iter->seq; + struct blk_io_trace *t = (struct blk_io_trace *)iter->ent; + const int offset = offsetof(struct blk_io_trace, sector); + struct blk_io_trace old = { + .magic = BLK_IO_TRACE_MAGIC | BLK_IO_TRACE_VERSION, + .time = iter->ts, + }; + + trace_seq_putmem(s, &old, offset); + trace_seq_putmem(s, &t->sector, + sizeof(old) - offset + t->pdu_len); +} + +static enum print_line_t +blk_trace_event_print_binary(struct trace_iterator *iter, int flags, + struct trace_event *event) +{ + blk_trace_synthesize_old_trace(iter); + + return trace_handle_return(&iter->seq); +} + +static enum print_line_t blk_tracer_print_line(struct trace_iterator *iter) +{ + if (!(blk_tracer_flags.val & TRACE_BLK_OPT_CLASSIC)) + return TRACE_TYPE_UNHANDLED; + + return print_one_line(iter, true); +} + +static int +blk_tracer_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set) +{ + /* don't output context-info for blk_classic output */ + if (bit == TRACE_BLK_OPT_CLASSIC) { + if (set) + trace_flags &= ~TRACE_ITER_CONTEXT_INFO; + else + trace_flags |= TRACE_ITER_CONTEXT_INFO; + } + return 0; +} + +static struct tracer blk_tracer __read_mostly = { + .name = "blk", + .init = blk_tracer_init, + .reset = blk_tracer_reset, + .start = blk_tracer_start, + .stop = blk_tracer_stop, + .print_header = blk_tracer_print_header, + .print_line = blk_tracer_print_line, + .flags = &blk_tracer_flags, + .set_flag = blk_tracer_set_flag, +}; + +static struct trace_event_functions trace_blk_event_funcs = { + .trace = blk_trace_event_print, + .binary = blk_trace_event_print_binary, +}; + +static struct trace_event trace_blk_event = { + .type = TRACE_BLK, + .funcs = &trace_blk_event_funcs, +}; + +static int __init init_blk_tracer(void) +{ + if (!register_ftrace_event(&trace_blk_event)) { + pr_warning("Warning: could not register block events\n"); + return 1; + } + + if (register_tracer(&blk_tracer) != 0) { + pr_warning("Warning: could not register the block tracer\n"); + unregister_ftrace_event(&trace_blk_event); + return 1; + } + + return 0; +} + +device_initcall(init_blk_tracer); + +static int blk_trace_remove_queue(struct request_queue *q) +{ + struct blk_trace *bt; + + bt = xchg(&q->blk_trace, NULL); + if (bt == NULL) + return -EINVAL; + + if (atomic_dec_and_test(&blk_probes_ref)) + blk_unregister_tracepoints(); + + blk_trace_free(bt); + return 0; +} + +/* + * Setup everything required to start tracing + */ +static int blk_trace_setup_queue(struct request_queue *q, + struct block_device *bdev) +{ + struct blk_trace *old_bt, *bt = NULL; + int ret = -ENOMEM; + + bt = kzalloc(sizeof(*bt), GFP_KERNEL); + if (!bt) + return -ENOMEM; + + bt->msg_data = __alloc_percpu(BLK_TN_MAX_MSG, __alignof__(char)); + if (!bt->msg_data) + goto free_bt; + + bt->dev = bdev->bd_dev; + bt->act_mask = (u16)-1; + + blk_trace_setup_lba(bt, bdev); + + old_bt = xchg(&q->blk_trace, bt); + if (old_bt != NULL) { + (void)xchg(&q->blk_trace, old_bt); + ret = -EBUSY; + goto free_bt; + } + + if (atomic_inc_return(&blk_probes_ref) == 1) + blk_register_tracepoints(); + return 0; + +free_bt: + blk_trace_free(bt); + return ret; +} + +/* + * sysfs interface to enable and configure tracing + */ + +static ssize_t sysfs_blk_trace_attr_show(struct device *dev, + struct device_attribute *attr, + char *buf); +static ssize_t sysfs_blk_trace_attr_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count); +#define BLK_TRACE_DEVICE_ATTR(_name) \ + DEVICE_ATTR(_name, S_IRUGO | S_IWUSR, \ + sysfs_blk_trace_attr_show, \ + sysfs_blk_trace_attr_store) + +static BLK_TRACE_DEVICE_ATTR(enable); +static BLK_TRACE_DEVICE_ATTR(act_mask); +static BLK_TRACE_DEVICE_ATTR(pid); +static BLK_TRACE_DEVICE_ATTR(start_lba); +static BLK_TRACE_DEVICE_ATTR(end_lba); + +static struct attribute *blk_trace_attrs[] = { + &dev_attr_enable.attr, + &dev_attr_act_mask.attr, + &dev_attr_pid.attr, + &dev_attr_start_lba.attr, + &dev_attr_end_lba.attr, + NULL +}; + +struct attribute_group blk_trace_attr_group = { + .name = "trace", + .attrs = blk_trace_attrs, +}; + +static const struct { + int mask; + const char *str; +} mask_maps[] = { + { BLK_TC_READ, "read" }, + { BLK_TC_WRITE, "write" }, + { BLK_TC_FLUSH, "flush" }, + { BLK_TC_SYNC, "sync" }, + { BLK_TC_QUEUE, "queue" }, + { BLK_TC_REQUEUE, "requeue" }, + { BLK_TC_ISSUE, "issue" }, + { BLK_TC_COMPLETE, "complete" }, + { BLK_TC_FS, "fs" }, + { BLK_TC_PC, "pc" }, + { BLK_TC_AHEAD, "ahead" }, + { BLK_TC_META, "meta" }, + { BLK_TC_DISCARD, "discard" }, + { BLK_TC_DRV_DATA, "drv_data" }, + { BLK_TC_FUA, "fua" }, +}; + +static int blk_trace_str2mask(const char *str) +{ + int i; + int mask = 0; + char *buf, *s, *token; + + buf = kstrdup(str, GFP_KERNEL); + if (buf == NULL) + return -ENOMEM; + s = strstrip(buf); + + while (1) { + token = strsep(&s, ","); + if (token == NULL) + break; + + if (*token == '\0') + continue; + + for (i = 0; i < ARRAY_SIZE(mask_maps); i++) { + if (strcasecmp(token, mask_maps[i].str) == 0) { + mask |= mask_maps[i].mask; + break; + } + } + if (i == ARRAY_SIZE(mask_maps)) { + mask = -EINVAL; + break; + } + } + kfree(buf); + + return mask; +} + +static ssize_t blk_trace_mask2str(char *buf, int mask) +{ + int i; + char *p = buf; + + for (i = 0; i < ARRAY_SIZE(mask_maps); i++) { + if (mask & mask_maps[i].mask) { + p += sprintf(p, "%s%s", + (p == buf) ? "" : ",", mask_maps[i].str); + } + } + *p++ = '\n'; + + return p - buf; +} + +static struct request_queue *blk_trace_get_queue(struct block_device *bdev) +{ + if (bdev->bd_disk == NULL) + return NULL; + + return bdev_get_queue(bdev); +} + +static ssize_t sysfs_blk_trace_attr_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct hd_struct *p = dev_to_part(dev); + struct request_queue *q; + struct block_device *bdev; + ssize_t ret = -ENXIO; + + bdev = bdget(part_devt(p)); + if (bdev == NULL) + goto out; + + q = blk_trace_get_queue(bdev); + if (q == NULL) + goto out_bdput; + + mutex_lock(&bdev->bd_mutex); + + if (attr == &dev_attr_enable) { + ret = sprintf(buf, "%u\n", !!q->blk_trace); + goto out_unlock_bdev; + } + + if (q->blk_trace == NULL) + ret = sprintf(buf, "disabled\n"); + else if (attr == &dev_attr_act_mask) + ret = blk_trace_mask2str(buf, q->blk_trace->act_mask); + else if (attr == &dev_attr_pid) + ret = sprintf(buf, "%u\n", q->blk_trace->pid); + else if (attr == &dev_attr_start_lba) + ret = sprintf(buf, "%llu\n", q->blk_trace->start_lba); + else if (attr == &dev_attr_end_lba) + ret = sprintf(buf, "%llu\n", q->blk_trace->end_lba); + +out_unlock_bdev: + mutex_unlock(&bdev->bd_mutex); +out_bdput: + bdput(bdev); +out: + return ret; +} + +static ssize_t sysfs_blk_trace_attr_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct block_device *bdev; + struct request_queue *q; + struct hd_struct *p; + u64 value; + ssize_t ret = -EINVAL; + + if (count == 0) + goto out; + + if (attr == &dev_attr_act_mask) { + if (sscanf(buf, "%llx", &value) != 1) { + /* Assume it is a list of trace category names */ + ret = blk_trace_str2mask(buf); + if (ret < 0) + goto out; + value = ret; + } + } else if (sscanf(buf, "%llu", &value) != 1) + goto out; + + ret = -ENXIO; + + p = dev_to_part(dev); + bdev = bdget(part_devt(p)); + if (bdev == NULL) + goto out; + + q = blk_trace_get_queue(bdev); + if (q == NULL) + goto out_bdput; + + mutex_lock(&bdev->bd_mutex); + + if (attr == &dev_attr_enable) { + if (value) + ret = blk_trace_setup_queue(q, bdev); + else + ret = blk_trace_remove_queue(q); + goto out_unlock_bdev; + } + + ret = 0; + if (q->blk_trace == NULL) + ret = blk_trace_setup_queue(q, bdev); + + if (ret == 0) { + if (attr == &dev_attr_act_mask) + q->blk_trace->act_mask = value; + else if (attr == &dev_attr_pid) + q->blk_trace->pid = value; + else if (attr == &dev_attr_start_lba) + q->blk_trace->start_lba = value; + else if (attr == &dev_attr_end_lba) + q->blk_trace->end_lba = value; + } + +out_unlock_bdev: + mutex_unlock(&bdev->bd_mutex); +out_bdput: + bdput(bdev); +out: + return ret ? ret : count; +} + +int blk_trace_init_sysfs(struct device *dev) +{ + return sysfs_create_group(&dev->kobj, &blk_trace_attr_group); +} + +void blk_trace_remove_sysfs(struct device *dev) +{ + sysfs_remove_group(&dev->kobj, &blk_trace_attr_group); +} + +#endif /* CONFIG_BLK_DEV_IO_TRACE */ + +#ifdef CONFIG_EVENT_TRACING + +void blk_dump_cmd(char *buf, struct request *rq) +{ + int i, end; + int len = rq->cmd_len; + unsigned char *cmd = rq->cmd; + + if (rq->cmd_type != REQ_TYPE_BLOCK_PC) { + buf[0] = '\0'; + return; + } + + for (end = len - 1; end >= 0; end--) + if (cmd[end]) + break; + end++; + + for (i = 0; i < len; i++) { + buf += sprintf(buf, "%s%02x", i == 0 ? "" : " ", cmd[i]); + if (i == end && end != len - 1) { + sprintf(buf, " .."); + break; + } + } +} + +void blk_fill_rwbs(char *rwbs, u32 rw, int bytes) +{ + int i = 0; + + if (rw & REQ_FLUSH) + rwbs[i++] = 'F'; + + if (rw & WRITE) + rwbs[i++] = 'W'; + else if (rw & REQ_DISCARD) + rwbs[i++] = 'D'; + else if (bytes) + rwbs[i++] = 'R'; + else + rwbs[i++] = 'N'; + + if (rw & REQ_FUA) + rwbs[i++] = 'F'; + if (rw & REQ_RAHEAD) + rwbs[i++] = 'A'; + if (rw & REQ_SYNC) + rwbs[i++] = 'S'; + if (rw & REQ_META) + rwbs[i++] = 'M'; + if (rw & REQ_SECURE) + rwbs[i++] = 'E'; + + rwbs[i] = '\0'; +} +EXPORT_SYMBOL_GPL(blk_fill_rwbs); + +#endif /* CONFIG_EVENT_TRACING */ + diff --git a/kernel/kernel/trace/bpf_trace.c b/kernel/kernel/trace/bpf_trace.c new file mode 100644 index 000000000..2d56ce501 --- /dev/null +++ b/kernel/kernel/trace/bpf_trace.c @@ -0,0 +1,222 @@ +/* Copyright (c) 2011-2015 PLUMgrid, http://plumgrid.com + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ +#include +#include +#include +#include +#include +#include +#include +#include "trace.h" + +static DEFINE_PER_CPU(int, bpf_prog_active); + +/** + * trace_call_bpf - invoke BPF program + * @prog: BPF program + * @ctx: opaque context pointer + * + * kprobe handlers execute BPF programs via this helper. + * Can be used from static tracepoints in the future. + * + * Return: BPF programs always return an integer which is interpreted by + * kprobe handler as: + * 0 - return from kprobe (event is filtered out) + * 1 - store kprobe event into ring buffer + * Other values are reserved and currently alias to 1 + */ +unsigned int trace_call_bpf(struct bpf_prog *prog, void *ctx) +{ + unsigned int ret; + + if (in_nmi()) /* not supported yet */ + return 1; + + preempt_disable(); + + if (unlikely(__this_cpu_inc_return(bpf_prog_active) != 1)) { + /* + * since some bpf program is already running on this cpu, + * don't call into another bpf program (same or different) + * and don't send kprobe event into ring-buffer, + * so return zero here + */ + ret = 0; + goto out; + } + + rcu_read_lock(); + ret = BPF_PROG_RUN(prog, ctx); + rcu_read_unlock(); + + out: + __this_cpu_dec(bpf_prog_active); + preempt_enable(); + + return ret; +} +EXPORT_SYMBOL_GPL(trace_call_bpf); + +static u64 bpf_probe_read(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) +{ + void *dst = (void *) (long) r1; + int size = (int) r2; + void *unsafe_ptr = (void *) (long) r3; + + return probe_kernel_read(dst, unsafe_ptr, size); +} + +static const struct bpf_func_proto bpf_probe_read_proto = { + .func = bpf_probe_read, + .gpl_only = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_STACK, + .arg2_type = ARG_CONST_STACK_SIZE, + .arg3_type = ARG_ANYTHING, +}; + +static u64 bpf_ktime_get_ns(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) +{ + /* NMI safe access to clock monotonic */ + return ktime_get_mono_fast_ns(); +} + +static const struct bpf_func_proto bpf_ktime_get_ns_proto = { + .func = bpf_ktime_get_ns, + .gpl_only = true, + .ret_type = RET_INTEGER, +}; + +/* + * limited trace_printk() + * only %d %u %x %ld %lu %lx %lld %llu %llx %p conversion specifiers allowed + */ +static u64 bpf_trace_printk(u64 r1, u64 fmt_size, u64 r3, u64 r4, u64 r5) +{ + char *fmt = (char *) (long) r1; + int mod[3] = {}; + int fmt_cnt = 0; + int i; + + /* + * bpf_check()->check_func_arg()->check_stack_boundary() + * guarantees that fmt points to bpf program stack, + * fmt_size bytes of it were initialized and fmt_size > 0 + */ + if (fmt[--fmt_size] != 0) + return -EINVAL; + + /* check format string for allowed specifiers */ + for (i = 0; i < fmt_size; i++) { + if ((!isprint(fmt[i]) && !isspace(fmt[i])) || !isascii(fmt[i])) + return -EINVAL; + + if (fmt[i] != '%') + continue; + + if (fmt_cnt >= 3) + return -EINVAL; + + /* fmt[i] != 0 && fmt[last] == 0, so we can access fmt[i + 1] */ + i++; + if (fmt[i] == 'l') { + mod[fmt_cnt]++; + i++; + } else if (fmt[i] == 'p') { + mod[fmt_cnt]++; + i++; + if (!isspace(fmt[i]) && !ispunct(fmt[i]) && fmt[i] != 0) + return -EINVAL; + fmt_cnt++; + continue; + } + + if (fmt[i] == 'l') { + mod[fmt_cnt]++; + i++; + } + + if (fmt[i] != 'd' && fmt[i] != 'u' && fmt[i] != 'x') + return -EINVAL; + fmt_cnt++; + } + + return __trace_printk(1/* fake ip will not be printed */, fmt, + mod[0] == 2 ? r3 : mod[0] == 1 ? (long) r3 : (u32) r3, + mod[1] == 2 ? r4 : mod[1] == 1 ? (long) r4 : (u32) r4, + mod[2] == 2 ? r5 : mod[2] == 1 ? (long) r5 : (u32) r5); +} + +static const struct bpf_func_proto bpf_trace_printk_proto = { + .func = bpf_trace_printk, + .gpl_only = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_STACK, + .arg2_type = ARG_CONST_STACK_SIZE, +}; + +static const struct bpf_func_proto *kprobe_prog_func_proto(enum bpf_func_id func_id) +{ + switch (func_id) { + case BPF_FUNC_map_lookup_elem: + return &bpf_map_lookup_elem_proto; + case BPF_FUNC_map_update_elem: + return &bpf_map_update_elem_proto; + case BPF_FUNC_map_delete_elem: + return &bpf_map_delete_elem_proto; + case BPF_FUNC_probe_read: + return &bpf_probe_read_proto; + case BPF_FUNC_ktime_get_ns: + return &bpf_ktime_get_ns_proto; + + case BPF_FUNC_trace_printk: + /* + * this program might be calling bpf_trace_printk, + * so allocate per-cpu printk buffers + */ + trace_printk_init_buffers(); + + return &bpf_trace_printk_proto; + default: + return NULL; + } +} + +/* bpf+kprobe programs can access fields of 'struct pt_regs' */ +static bool kprobe_prog_is_valid_access(int off, int size, enum bpf_access_type type) +{ + /* check bounds */ + if (off < 0 || off >= sizeof(struct pt_regs)) + return false; + + /* only read is allowed */ + if (type != BPF_READ) + return false; + + /* disallow misaligned access */ + if (off % size != 0) + return false; + + return true; +} + +static struct bpf_verifier_ops kprobe_prog_ops = { + .get_func_proto = kprobe_prog_func_proto, + .is_valid_access = kprobe_prog_is_valid_access, +}; + +static struct bpf_prog_type_list kprobe_tl = { + .ops = &kprobe_prog_ops, + .type = BPF_PROG_TYPE_KPROBE, +}; + +static int __init register_kprobe_prog_ops(void) +{ + bpf_register_prog_type(&kprobe_tl); + return 0; +} +late_initcall(register_kprobe_prog_ops); diff --git a/kernel/kernel/trace/ftrace.c b/kernel/kernel/trace/ftrace.c new file mode 100644 index 000000000..02bece4a9 --- /dev/null +++ b/kernel/kernel/trace/ftrace.c @@ -0,0 +1,5951 @@ +/* + * Infrastructure for profiling code inserted by 'gcc -pg'. + * + * Copyright (C) 2007-2008 Steven Rostedt + * Copyright (C) 2004-2008 Ingo Molnar + * + * Originally ported from the -rt patch by: + * Copyright (C) 2007 Arnaldo Carvalho de Melo + * + * Based on code in the latency_tracer, that is: + * + * Copyright (C) 2004-2006 Ingo Molnar + * Copyright (C) 2004 Nadia Yvette Chambers + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +#include + +#include "trace_output.h" +#include "trace_stat.h" + +#define FTRACE_WARN_ON(cond) \ + ({ \ + int ___r = cond; \ + if (WARN_ON(___r)) \ + ftrace_kill(); \ + ___r; \ + }) + +#define FTRACE_WARN_ON_ONCE(cond) \ + ({ \ + int ___r = cond; \ + if (WARN_ON_ONCE(___r)) \ + ftrace_kill(); \ + ___r; \ + }) + +/* hash bits for specific function selection */ +#define FTRACE_HASH_BITS 7 +#define FTRACE_FUNC_HASHSIZE (1 << FTRACE_HASH_BITS) +#define FTRACE_HASH_DEFAULT_BITS 10 +#define FTRACE_HASH_MAX_BITS 12 + +#define FL_GLOBAL_CONTROL_MASK (FTRACE_OPS_FL_CONTROL) + +#ifdef CONFIG_DYNAMIC_FTRACE +#define INIT_OPS_HASH(opsname) \ + .func_hash = &opsname.local_hash, \ + .local_hash.regex_lock = __MUTEX_INITIALIZER(opsname.local_hash.regex_lock), +#define ASSIGN_OPS_HASH(opsname, val) \ + .func_hash = val, \ + .local_hash.regex_lock = __MUTEX_INITIALIZER(opsname.local_hash.regex_lock), +#else +#define INIT_OPS_HASH(opsname) +#define ASSIGN_OPS_HASH(opsname, val) +#endif + +static struct ftrace_ops ftrace_list_end __read_mostly = { + .func = ftrace_stub, + .flags = FTRACE_OPS_FL_RECURSION_SAFE | FTRACE_OPS_FL_STUB, + INIT_OPS_HASH(ftrace_list_end) +}; + +/* ftrace_enabled is a method to turn ftrace on or off */ +int ftrace_enabled __read_mostly; +static int last_ftrace_enabled; + +/* Current function tracing op */ +struct ftrace_ops *function_trace_op __read_mostly = &ftrace_list_end; +/* What to set function_trace_op to */ +static struct ftrace_ops *set_function_trace_op; + +/* List for set_ftrace_pid's pids. */ +LIST_HEAD(ftrace_pids); +struct ftrace_pid { + struct list_head list; + struct pid *pid; +}; + +/* + * ftrace_disabled is set when an anomaly is discovered. + * ftrace_disabled is much stronger than ftrace_enabled. + */ +static int ftrace_disabled __read_mostly; + +static DEFINE_MUTEX(ftrace_lock); + +static struct ftrace_ops *ftrace_control_list __read_mostly = &ftrace_list_end; +static struct ftrace_ops *ftrace_ops_list __read_mostly = &ftrace_list_end; +ftrace_func_t ftrace_trace_function __read_mostly = ftrace_stub; +ftrace_func_t ftrace_pid_function __read_mostly = ftrace_stub; +static struct ftrace_ops global_ops; +static struct ftrace_ops control_ops; + +static void ftrace_ops_recurs_func(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct pt_regs *regs); + +#if ARCH_SUPPORTS_FTRACE_OPS +static void ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct pt_regs *regs); +#else +/* See comment below, where ftrace_ops_list_func is defined */ +static void ftrace_ops_no_ops(unsigned long ip, unsigned long parent_ip); +#define ftrace_ops_list_func ((ftrace_func_t)ftrace_ops_no_ops) +#endif + +/* + * Traverse the ftrace_global_list, invoking all entries. The reason that we + * can use rcu_dereference_raw_notrace() is that elements removed from this list + * are simply leaked, so there is no need to interact with a grace-period + * mechanism. The rcu_dereference_raw_notrace() calls are needed to handle + * concurrent insertions into the ftrace_global_list. + * + * Silly Alpha and silly pointer-speculation compiler optimizations! + */ +#define do_for_each_ftrace_op(op, list) \ + op = rcu_dereference_raw_notrace(list); \ + do + +/* + * Optimized for just a single item in the list (as that is the normal case). + */ +#define while_for_each_ftrace_op(op) \ + while (likely(op = rcu_dereference_raw_notrace((op)->next)) && \ + unlikely((op) != &ftrace_list_end)) + +static inline void ftrace_ops_init(struct ftrace_ops *ops) +{ +#ifdef CONFIG_DYNAMIC_FTRACE + if (!(ops->flags & FTRACE_OPS_FL_INITIALIZED)) { + mutex_init(&ops->local_hash.regex_lock); + ops->func_hash = &ops->local_hash; + ops->flags |= FTRACE_OPS_FL_INITIALIZED; + } +#endif +} + +/** + * ftrace_nr_registered_ops - return number of ops registered + * + * Returns the number of ftrace_ops registered and tracing functions + */ +int ftrace_nr_registered_ops(void) +{ + struct ftrace_ops *ops; + int cnt = 0; + + mutex_lock(&ftrace_lock); + + for (ops = ftrace_ops_list; + ops != &ftrace_list_end; ops = ops->next) + cnt++; + + mutex_unlock(&ftrace_lock); + + return cnt; +} + +static void ftrace_pid_func(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct pt_regs *regs) +{ + if (!test_tsk_trace_trace(current)) + return; + + ftrace_pid_function(ip, parent_ip, op, regs); +} + +static void set_ftrace_pid_function(ftrace_func_t func) +{ + /* do not set ftrace_pid_function to itself! */ + if (func != ftrace_pid_func) + ftrace_pid_function = func; +} + +/** + * clear_ftrace_function - reset the ftrace function + * + * This NULLs the ftrace function and in essence stops + * tracing. There may be lag + */ +void clear_ftrace_function(void) +{ + ftrace_trace_function = ftrace_stub; + ftrace_pid_function = ftrace_stub; +} + +static void control_ops_disable_all(struct ftrace_ops *ops) +{ + int cpu; + + for_each_possible_cpu(cpu) + *per_cpu_ptr(ops->disabled, cpu) = 1; +} + +static int control_ops_alloc(struct ftrace_ops *ops) +{ + int __percpu *disabled; + + disabled = alloc_percpu(int); + if (!disabled) + return -ENOMEM; + + ops->disabled = disabled; + control_ops_disable_all(ops); + return 0; +} + +static void ftrace_sync(struct work_struct *work) +{ + /* + * This function is just a stub to implement a hard force + * of synchronize_sched(). This requires synchronizing + * tasks even in userspace and idle. + * + * Yes, function tracing is rude. + */ +} + +static void ftrace_sync_ipi(void *data) +{ + /* Probably not needed, but do it anyway */ + smp_rmb(); +} + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER +static void update_function_graph_func(void); +#else +static inline void update_function_graph_func(void) { } +#endif + + +static ftrace_func_t ftrace_ops_get_list_func(struct ftrace_ops *ops) +{ + /* + * If this is a dynamic ops or we force list func, + * then it needs to call the list anyway. + */ + if (ops->flags & FTRACE_OPS_FL_DYNAMIC || FTRACE_FORCE_LIST_FUNC) + return ftrace_ops_list_func; + + return ftrace_ops_get_func(ops); +} + +static void update_ftrace_function(void) +{ + ftrace_func_t func; + + /* + * Prepare the ftrace_ops that the arch callback will use. + * If there's only one ftrace_ops registered, the ftrace_ops_list + * will point to the ops we want. + */ + set_function_trace_op = ftrace_ops_list; + + /* If there's no ftrace_ops registered, just call the stub function */ + if (ftrace_ops_list == &ftrace_list_end) { + func = ftrace_stub; + + /* + * If we are at the end of the list and this ops is + * recursion safe and not dynamic and the arch supports passing ops, + * then have the mcount trampoline call the function directly. + */ + } else if (ftrace_ops_list->next == &ftrace_list_end) { + func = ftrace_ops_get_list_func(ftrace_ops_list); + + } else { + /* Just use the default ftrace_ops */ + set_function_trace_op = &ftrace_list_end; + func = ftrace_ops_list_func; + } + + update_function_graph_func(); + + /* If there's no change, then do nothing more here */ + if (ftrace_trace_function == func) + return; + + /* + * If we are using the list function, it doesn't care + * about the function_trace_ops. + */ + if (func == ftrace_ops_list_func) { + ftrace_trace_function = func; + /* + * Don't even bother setting function_trace_ops, + * it would be racy to do so anyway. + */ + return; + } + +#ifndef CONFIG_DYNAMIC_FTRACE + /* + * For static tracing, we need to be a bit more careful. + * The function change takes affect immediately. Thus, + * we need to coorditate the setting of the function_trace_ops + * with the setting of the ftrace_trace_function. + * + * Set the function to the list ops, which will call the + * function we want, albeit indirectly, but it handles the + * ftrace_ops and doesn't depend on function_trace_op. + */ + ftrace_trace_function = ftrace_ops_list_func; + /* + * Make sure all CPUs see this. Yes this is slow, but static + * tracing is slow and nasty to have enabled. + */ + schedule_on_each_cpu(ftrace_sync); + /* Now all cpus are using the list ops. */ + function_trace_op = set_function_trace_op; + /* Make sure the function_trace_op is visible on all CPUs */ + smp_wmb(); + /* Nasty way to force a rmb on all cpus */ + smp_call_function(ftrace_sync_ipi, NULL, 1); + /* OK, we are all set to update the ftrace_trace_function now! */ +#endif /* !CONFIG_DYNAMIC_FTRACE */ + + ftrace_trace_function = func; +} + +int using_ftrace_ops_list_func(void) +{ + return ftrace_trace_function == ftrace_ops_list_func; +} + +static void add_ftrace_ops(struct ftrace_ops **list, struct ftrace_ops *ops) +{ + ops->next = *list; + /* + * We are entering ops into the list but another + * CPU might be walking that list. We need to make sure + * the ops->next pointer is valid before another CPU sees + * the ops pointer included into the list. + */ + rcu_assign_pointer(*list, ops); +} + +static int remove_ftrace_ops(struct ftrace_ops **list, struct ftrace_ops *ops) +{ + struct ftrace_ops **p; + + /* + * If we are removing the last function, then simply point + * to the ftrace_stub. + */ + if (*list == ops && ops->next == &ftrace_list_end) { + *list = &ftrace_list_end; + return 0; + } + + for (p = list; *p != &ftrace_list_end; p = &(*p)->next) + if (*p == ops) + break; + + if (*p != ops) + return -1; + + *p = (*p)->next; + return 0; +} + +static void add_ftrace_list_ops(struct ftrace_ops **list, + struct ftrace_ops *main_ops, + struct ftrace_ops *ops) +{ + int first = *list == &ftrace_list_end; + add_ftrace_ops(list, ops); + if (first) + add_ftrace_ops(&ftrace_ops_list, main_ops); +} + +static int remove_ftrace_list_ops(struct ftrace_ops **list, + struct ftrace_ops *main_ops, + struct ftrace_ops *ops) +{ + int ret = remove_ftrace_ops(list, ops); + if (!ret && *list == &ftrace_list_end) + ret = remove_ftrace_ops(&ftrace_ops_list, main_ops); + return ret; +} + +static void ftrace_update_trampoline(struct ftrace_ops *ops); + +static int __register_ftrace_function(struct ftrace_ops *ops) +{ + if (ops->flags & FTRACE_OPS_FL_DELETED) + return -EINVAL; + + if (WARN_ON(ops->flags & FTRACE_OPS_FL_ENABLED)) + return -EBUSY; + +#ifndef CONFIG_DYNAMIC_FTRACE_WITH_REGS + /* + * If the ftrace_ops specifies SAVE_REGS, then it only can be used + * if the arch supports it, or SAVE_REGS_IF_SUPPORTED is also set. + * Setting SAVE_REGS_IF_SUPPORTED makes SAVE_REGS irrelevant. + */ + if (ops->flags & FTRACE_OPS_FL_SAVE_REGS && + !(ops->flags & FTRACE_OPS_FL_SAVE_REGS_IF_SUPPORTED)) + return -EINVAL; + + if (ops->flags & FTRACE_OPS_FL_SAVE_REGS_IF_SUPPORTED) + ops->flags |= FTRACE_OPS_FL_SAVE_REGS; +#endif + + if (!core_kernel_data((unsigned long)ops)) + ops->flags |= FTRACE_OPS_FL_DYNAMIC; + + if (ops->flags & FTRACE_OPS_FL_CONTROL) { + if (control_ops_alloc(ops)) + return -ENOMEM; + add_ftrace_list_ops(&ftrace_control_list, &control_ops, ops); + /* The control_ops needs the trampoline update */ + ops = &control_ops; + } else + add_ftrace_ops(&ftrace_ops_list, ops); + + ftrace_update_trampoline(ops); + + if (ftrace_enabled) + update_ftrace_function(); + + return 0; +} + +static int __unregister_ftrace_function(struct ftrace_ops *ops) +{ + int ret; + + if (WARN_ON(!(ops->flags & FTRACE_OPS_FL_ENABLED))) + return -EBUSY; + + if (ops->flags & FTRACE_OPS_FL_CONTROL) { + ret = remove_ftrace_list_ops(&ftrace_control_list, + &control_ops, ops); + } else + ret = remove_ftrace_ops(&ftrace_ops_list, ops); + + if (ret < 0) + return ret; + + if (ftrace_enabled) + update_ftrace_function(); + + return 0; +} + +static void ftrace_update_pid_func(void) +{ + /* Only do something if we are tracing something */ + if (ftrace_trace_function == ftrace_stub) + return; + + update_ftrace_function(); +} + +#ifdef CONFIG_FUNCTION_PROFILER +struct ftrace_profile { + struct hlist_node node; + unsigned long ip; + unsigned long counter; +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + unsigned long long time; + unsigned long long time_squared; +#endif +}; + +struct ftrace_profile_page { + struct ftrace_profile_page *next; + unsigned long index; + struct ftrace_profile records[]; +}; + +struct ftrace_profile_stat { + atomic_t disabled; + struct hlist_head *hash; + struct ftrace_profile_page *pages; + struct ftrace_profile_page *start; + struct tracer_stat stat; +}; + +#define PROFILE_RECORDS_SIZE \ + (PAGE_SIZE - offsetof(struct ftrace_profile_page, records)) + +#define PROFILES_PER_PAGE \ + (PROFILE_RECORDS_SIZE / sizeof(struct ftrace_profile)) + +static int ftrace_profile_enabled __read_mostly; + +/* ftrace_profile_lock - synchronize the enable and disable of the profiler */ +static DEFINE_MUTEX(ftrace_profile_lock); + +static DEFINE_PER_CPU(struct ftrace_profile_stat, ftrace_profile_stats); + +#define FTRACE_PROFILE_HASH_BITS 10 +#define FTRACE_PROFILE_HASH_SIZE (1 << FTRACE_PROFILE_HASH_BITS) + +static void * +function_stat_next(void *v, int idx) +{ + struct ftrace_profile *rec = v; + struct ftrace_profile_page *pg; + + pg = (struct ftrace_profile_page *)((unsigned long)rec & PAGE_MASK); + + again: + if (idx != 0) + rec++; + + if ((void *)rec >= (void *)&pg->records[pg->index]) { + pg = pg->next; + if (!pg) + return NULL; + rec = &pg->records[0]; + if (!rec->counter) + goto again; + } + + return rec; +} + +static void *function_stat_start(struct tracer_stat *trace) +{ + struct ftrace_profile_stat *stat = + container_of(trace, struct ftrace_profile_stat, stat); + + if (!stat || !stat->start) + return NULL; + + return function_stat_next(&stat->start->records[0], 0); +} + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER +/* function graph compares on total time */ +static int function_stat_cmp(void *p1, void *p2) +{ + struct ftrace_profile *a = p1; + struct ftrace_profile *b = p2; + + if (a->time < b->time) + return -1; + if (a->time > b->time) + return 1; + else + return 0; +} +#else +/* not function graph compares against hits */ +static int function_stat_cmp(void *p1, void *p2) +{ + struct ftrace_profile *a = p1; + struct ftrace_profile *b = p2; + + if (a->counter < b->counter) + return -1; + if (a->counter > b->counter) + return 1; + else + return 0; +} +#endif + +static int function_stat_headers(struct seq_file *m) +{ +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + seq_puts(m, " Function " + "Hit Time Avg s^2\n" + " -------- " + "--- ---- --- ---\n"); +#else + seq_puts(m, " Function Hit\n" + " -------- ---\n"); +#endif + return 0; +} + +static int function_stat_show(struct seq_file *m, void *v) +{ + struct ftrace_profile *rec = v; + char str[KSYM_SYMBOL_LEN]; + int ret = 0; +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + static struct trace_seq s; + unsigned long long avg; + unsigned long long stddev; +#endif + mutex_lock(&ftrace_profile_lock); + + /* we raced with function_profile_reset() */ + if (unlikely(rec->counter == 0)) { + ret = -EBUSY; + goto out; + } + + kallsyms_lookup(rec->ip, NULL, NULL, NULL, str); + seq_printf(m, " %-30.30s %10lu", str, rec->counter); + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + seq_puts(m, " "); + avg = rec->time; + do_div(avg, rec->counter); + + /* Sample standard deviation (s^2) */ + if (rec->counter <= 1) + stddev = 0; + else { + /* + * Apply Welford's method: + * s^2 = 1 / (n * (n-1)) * (n * \Sum (x_i)^2 - (\Sum x_i)^2) + */ + stddev = rec->counter * rec->time_squared - + rec->time * rec->time; + + /* + * Divide only 1000 for ns^2 -> us^2 conversion. + * trace_print_graph_duration will divide 1000 again. + */ + do_div(stddev, rec->counter * (rec->counter - 1) * 1000); + } + + trace_seq_init(&s); + trace_print_graph_duration(rec->time, &s); + trace_seq_puts(&s, " "); + trace_print_graph_duration(avg, &s); + trace_seq_puts(&s, " "); + trace_print_graph_duration(stddev, &s); + trace_print_seq(m, &s); +#endif + seq_putc(m, '\n'); +out: + mutex_unlock(&ftrace_profile_lock); + + return ret; +} + +static void ftrace_profile_reset(struct ftrace_profile_stat *stat) +{ + struct ftrace_profile_page *pg; + + pg = stat->pages = stat->start; + + while (pg) { + memset(pg->records, 0, PROFILE_RECORDS_SIZE); + pg->index = 0; + pg = pg->next; + } + + memset(stat->hash, 0, + FTRACE_PROFILE_HASH_SIZE * sizeof(struct hlist_head)); +} + +int ftrace_profile_pages_init(struct ftrace_profile_stat *stat) +{ + struct ftrace_profile_page *pg; + int functions; + int pages; + int i; + + /* If we already allocated, do nothing */ + if (stat->pages) + return 0; + + stat->pages = (void *)get_zeroed_page(GFP_KERNEL); + if (!stat->pages) + return -ENOMEM; + +#ifdef CONFIG_DYNAMIC_FTRACE + functions = ftrace_update_tot_cnt; +#else + /* + * We do not know the number of functions that exist because + * dynamic tracing is what counts them. With past experience + * we have around 20K functions. That should be more than enough. + * It is highly unlikely we will execute every function in + * the kernel. + */ + functions = 20000; +#endif + + pg = stat->start = stat->pages; + + pages = DIV_ROUND_UP(functions, PROFILES_PER_PAGE); + + for (i = 1; i < pages; i++) { + pg->next = (void *)get_zeroed_page(GFP_KERNEL); + if (!pg->next) + goto out_free; + pg = pg->next; + } + + return 0; + + out_free: + pg = stat->start; + while (pg) { + unsigned long tmp = (unsigned long)pg; + + pg = pg->next; + free_page(tmp); + } + + stat->pages = NULL; + stat->start = NULL; + + return -ENOMEM; +} + +static int ftrace_profile_init_cpu(int cpu) +{ + struct ftrace_profile_stat *stat; + int size; + + stat = &per_cpu(ftrace_profile_stats, cpu); + + if (stat->hash) { + /* If the profile is already created, simply reset it */ + ftrace_profile_reset(stat); + return 0; + } + + /* + * We are profiling all functions, but usually only a few thousand + * functions are hit. We'll make a hash of 1024 items. + */ + size = FTRACE_PROFILE_HASH_SIZE; + + stat->hash = kzalloc(sizeof(struct hlist_head) * size, GFP_KERNEL); + + if (!stat->hash) + return -ENOMEM; + + /* Preallocate the function profiling pages */ + if (ftrace_profile_pages_init(stat) < 0) { + kfree(stat->hash); + stat->hash = NULL; + return -ENOMEM; + } + + return 0; +} + +static int ftrace_profile_init(void) +{ + int cpu; + int ret = 0; + + for_each_possible_cpu(cpu) { + ret = ftrace_profile_init_cpu(cpu); + if (ret) + break; + } + + return ret; +} + +/* interrupts must be disabled */ +static struct ftrace_profile * +ftrace_find_profiled_func(struct ftrace_profile_stat *stat, unsigned long ip) +{ + struct ftrace_profile *rec; + struct hlist_head *hhd; + unsigned long key; + + key = hash_long(ip, FTRACE_PROFILE_HASH_BITS); + hhd = &stat->hash[key]; + + if (hlist_empty(hhd)) + return NULL; + + hlist_for_each_entry_rcu_notrace(rec, hhd, node) { + if (rec->ip == ip) + return rec; + } + + return NULL; +} + +static void ftrace_add_profile(struct ftrace_profile_stat *stat, + struct ftrace_profile *rec) +{ + unsigned long key; + + key = hash_long(rec->ip, FTRACE_PROFILE_HASH_BITS); + hlist_add_head_rcu(&rec->node, &stat->hash[key]); +} + +/* + * The memory is already allocated, this simply finds a new record to use. + */ +static struct ftrace_profile * +ftrace_profile_alloc(struct ftrace_profile_stat *stat, unsigned long ip) +{ + struct ftrace_profile *rec = NULL; + + /* prevent recursion (from NMIs) */ + if (atomic_inc_return(&stat->disabled) != 1) + goto out; + + /* + * Try to find the function again since an NMI + * could have added it + */ + rec = ftrace_find_profiled_func(stat, ip); + if (rec) + goto out; + + if (stat->pages->index == PROFILES_PER_PAGE) { + if (!stat->pages->next) + goto out; + stat->pages = stat->pages->next; + } + + rec = &stat->pages->records[stat->pages->index++]; + rec->ip = ip; + ftrace_add_profile(stat, rec); + + out: + atomic_dec(&stat->disabled); + + return rec; +} + +static void +function_profile_call(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *ops, struct pt_regs *regs) +{ + struct ftrace_profile_stat *stat; + struct ftrace_profile *rec; + unsigned long flags; + + if (!ftrace_profile_enabled) + return; + + local_irq_save(flags); + + stat = this_cpu_ptr(&ftrace_profile_stats); + if (!stat->hash || !ftrace_profile_enabled) + goto out; + + rec = ftrace_find_profiled_func(stat, ip); + if (!rec) { + rec = ftrace_profile_alloc(stat, ip); + if (!rec) + goto out; + } + + rec->counter++; + out: + local_irq_restore(flags); +} + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER +static int profile_graph_entry(struct ftrace_graph_ent *trace) +{ + function_profile_call(trace->func, 0, NULL, NULL); + return 1; +} + +static void profile_graph_return(struct ftrace_graph_ret *trace) +{ + struct ftrace_profile_stat *stat; + unsigned long long calltime; + struct ftrace_profile *rec; + unsigned long flags; + + local_irq_save(flags); + stat = this_cpu_ptr(&ftrace_profile_stats); + if (!stat->hash || !ftrace_profile_enabled) + goto out; + + /* If the calltime was zero'd ignore it */ + if (!trace->calltime) + goto out; + + calltime = trace->rettime - trace->calltime; + + if (!(trace_flags & TRACE_ITER_GRAPH_TIME)) { + int index; + + index = trace->depth; + + /* Append this call time to the parent time to subtract */ + if (index) + current->ret_stack[index - 1].subtime += calltime; + + if (current->ret_stack[index].subtime < calltime) + calltime -= current->ret_stack[index].subtime; + else + calltime = 0; + } + + rec = ftrace_find_profiled_func(stat, trace->func); + if (rec) { + rec->time += calltime; + rec->time_squared += calltime * calltime; + } + + out: + local_irq_restore(flags); +} + +static int register_ftrace_profiler(void) +{ + return register_ftrace_graph(&profile_graph_return, + &profile_graph_entry); +} + +static void unregister_ftrace_profiler(void) +{ + unregister_ftrace_graph(); +} +#else +static struct ftrace_ops ftrace_profile_ops __read_mostly = { + .func = function_profile_call, + .flags = FTRACE_OPS_FL_RECURSION_SAFE | FTRACE_OPS_FL_INITIALIZED, + INIT_OPS_HASH(ftrace_profile_ops) +}; + +static int register_ftrace_profiler(void) +{ + return register_ftrace_function(&ftrace_profile_ops); +} + +static void unregister_ftrace_profiler(void) +{ + unregister_ftrace_function(&ftrace_profile_ops); +} +#endif /* CONFIG_FUNCTION_GRAPH_TRACER */ + +static ssize_t +ftrace_profile_write(struct file *filp, const char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + unsigned long val; + int ret; + + ret = kstrtoul_from_user(ubuf, cnt, 10, &val); + if (ret) + return ret; + + val = !!val; + + mutex_lock(&ftrace_profile_lock); + if (ftrace_profile_enabled ^ val) { + if (val) { + ret = ftrace_profile_init(); + if (ret < 0) { + cnt = ret; + goto out; + } + + ret = register_ftrace_profiler(); + if (ret < 0) { + cnt = ret; + goto out; + } + ftrace_profile_enabled = 1; + } else { + ftrace_profile_enabled = 0; + /* + * unregister_ftrace_profiler calls stop_machine + * so this acts like an synchronize_sched. + */ + unregister_ftrace_profiler(); + } + } + out: + mutex_unlock(&ftrace_profile_lock); + + *ppos += cnt; + + return cnt; +} + +static ssize_t +ftrace_profile_read(struct file *filp, char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + char buf[64]; /* big enough to hold a number */ + int r; + + r = sprintf(buf, "%u\n", ftrace_profile_enabled); + return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); +} + +static const struct file_operations ftrace_profile_fops = { + .open = tracing_open_generic, + .read = ftrace_profile_read, + .write = ftrace_profile_write, + .llseek = default_llseek, +}; + +/* used to initialize the real stat files */ +static struct tracer_stat function_stats __initdata = { + .name = "functions", + .stat_start = function_stat_start, + .stat_next = function_stat_next, + .stat_cmp = function_stat_cmp, + .stat_headers = function_stat_headers, + .stat_show = function_stat_show +}; + +static __init void ftrace_profile_tracefs(struct dentry *d_tracer) +{ + struct ftrace_profile_stat *stat; + struct dentry *entry; + char *name; + int ret; + int cpu; + + for_each_possible_cpu(cpu) { + stat = &per_cpu(ftrace_profile_stats, cpu); + + /* allocate enough for function name + cpu number */ + name = kmalloc(32, GFP_KERNEL); + if (!name) { + /* + * The files created are permanent, if something happens + * we still do not free memory. + */ + WARN(1, + "Could not allocate stat file for cpu %d\n", + cpu); + return; + } + stat->stat = function_stats; + snprintf(name, 32, "function%d", cpu); + stat->stat.name = name; + ret = register_stat_tracer(&stat->stat); + if (ret) { + WARN(1, + "Could not register function stat for cpu %d\n", + cpu); + kfree(name); + return; + } + } + + entry = tracefs_create_file("function_profile_enabled", 0644, + d_tracer, NULL, &ftrace_profile_fops); + if (!entry) + pr_warning("Could not create tracefs " + "'function_profile_enabled' entry\n"); +} + +#else /* CONFIG_FUNCTION_PROFILER */ +static __init void ftrace_profile_tracefs(struct dentry *d_tracer) +{ +} +#endif /* CONFIG_FUNCTION_PROFILER */ + +static struct pid * const ftrace_swapper_pid = &init_struct_pid; + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER +static int ftrace_graph_active; +#else +# define ftrace_graph_active 0 +#endif + +#ifdef CONFIG_DYNAMIC_FTRACE + +static struct ftrace_ops *removed_ops; + +/* + * Set when doing a global update, like enabling all recs or disabling them. + * It is not set when just updating a single ftrace_ops. + */ +static bool update_all_ops; + +#ifndef CONFIG_FTRACE_MCOUNT_RECORD +# error Dynamic ftrace depends on MCOUNT_RECORD +#endif + +static struct hlist_head ftrace_func_hash[FTRACE_FUNC_HASHSIZE] __read_mostly; + +struct ftrace_func_probe { + struct hlist_node node; + struct ftrace_probe_ops *ops; + unsigned long flags; + unsigned long ip; + void *data; + struct list_head free_list; +}; + +struct ftrace_func_entry { + struct hlist_node hlist; + unsigned long ip; +}; + +struct ftrace_hash { + unsigned long size_bits; + struct hlist_head *buckets; + unsigned long count; + struct rcu_head rcu; +}; + +/* + * We make these constant because no one should touch them, + * but they are used as the default "empty hash", to avoid allocating + * it all the time. These are in a read only section such that if + * anyone does try to modify it, it will cause an exception. + */ +static const struct hlist_head empty_buckets[1]; +static const struct ftrace_hash empty_hash = { + .buckets = (struct hlist_head *)empty_buckets, +}; +#define EMPTY_HASH ((struct ftrace_hash *)&empty_hash) + +static struct ftrace_ops global_ops = { + .func = ftrace_stub, + .local_hash.notrace_hash = EMPTY_HASH, + .local_hash.filter_hash = EMPTY_HASH, + INIT_OPS_HASH(global_ops) + .flags = FTRACE_OPS_FL_RECURSION_SAFE | + FTRACE_OPS_FL_INITIALIZED, +}; + +/* + * This is used by __kernel_text_address() to return true if the + * address is on a dynamically allocated trampoline that would + * not return true for either core_kernel_text() or + * is_module_text_address(). + */ +bool is_ftrace_trampoline(unsigned long addr) +{ + struct ftrace_ops *op; + bool ret = false; + + /* + * Some of the ops may be dynamically allocated, + * they are freed after a synchronize_sched(). + */ + preempt_disable_notrace(); + + do_for_each_ftrace_op(op, ftrace_ops_list) { + /* + * This is to check for dynamically allocated trampolines. + * Trampolines that are in kernel text will have + * core_kernel_text() return true. + */ + if (op->trampoline && op->trampoline_size) + if (addr >= op->trampoline && + addr < op->trampoline + op->trampoline_size) { + ret = true; + goto out; + } + } while_for_each_ftrace_op(op); + + out: + preempt_enable_notrace(); + + return ret; +} + +struct ftrace_page { + struct ftrace_page *next; + struct dyn_ftrace *records; + int index; + int size; +}; + +#define ENTRY_SIZE sizeof(struct dyn_ftrace) +#define ENTRIES_PER_PAGE (PAGE_SIZE / ENTRY_SIZE) + +/* estimate from running different kernels */ +#define NR_TO_INIT 10000 + +static struct ftrace_page *ftrace_pages_start; +static struct ftrace_page *ftrace_pages; + +static bool __always_inline ftrace_hash_empty(struct ftrace_hash *hash) +{ + return !hash || !hash->count; +} + +static struct ftrace_func_entry * +ftrace_lookup_ip(struct ftrace_hash *hash, unsigned long ip) +{ + unsigned long key; + struct ftrace_func_entry *entry; + struct hlist_head *hhd; + + if (ftrace_hash_empty(hash)) + return NULL; + + if (hash->size_bits > 0) + key = hash_long(ip, hash->size_bits); + else + key = 0; + + hhd = &hash->buckets[key]; + + hlist_for_each_entry_rcu_notrace(entry, hhd, hlist) { + if (entry->ip == ip) + return entry; + } + return NULL; +} + +static void __add_hash_entry(struct ftrace_hash *hash, + struct ftrace_func_entry *entry) +{ + struct hlist_head *hhd; + unsigned long key; + + if (hash->size_bits) + key = hash_long(entry->ip, hash->size_bits); + else + key = 0; + + hhd = &hash->buckets[key]; + hlist_add_head(&entry->hlist, hhd); + hash->count++; +} + +static int add_hash_entry(struct ftrace_hash *hash, unsigned long ip) +{ + struct ftrace_func_entry *entry; + + entry = kmalloc(sizeof(*entry), GFP_KERNEL); + if (!entry) + return -ENOMEM; + + entry->ip = ip; + __add_hash_entry(hash, entry); + + return 0; +} + +static void +free_hash_entry(struct ftrace_hash *hash, + struct ftrace_func_entry *entry) +{ + hlist_del(&entry->hlist); + kfree(entry); + hash->count--; +} + +static void +remove_hash_entry(struct ftrace_hash *hash, + struct ftrace_func_entry *entry) +{ + hlist_del(&entry->hlist); + hash->count--; +} + +static void ftrace_hash_clear(struct ftrace_hash *hash) +{ + struct hlist_head *hhd; + struct hlist_node *tn; + struct ftrace_func_entry *entry; + int size = 1 << hash->size_bits; + int i; + + if (!hash->count) + return; + + for (i = 0; i < size; i++) { + hhd = &hash->buckets[i]; + hlist_for_each_entry_safe(entry, tn, hhd, hlist) + free_hash_entry(hash, entry); + } + FTRACE_WARN_ON(hash->count); +} + +static void free_ftrace_hash(struct ftrace_hash *hash) +{ + if (!hash || hash == EMPTY_HASH) + return; + ftrace_hash_clear(hash); + kfree(hash->buckets); + kfree(hash); +} + +static void __free_ftrace_hash_rcu(struct rcu_head *rcu) +{ + struct ftrace_hash *hash; + + hash = container_of(rcu, struct ftrace_hash, rcu); + free_ftrace_hash(hash); +} + +static void free_ftrace_hash_rcu(struct ftrace_hash *hash) +{ + if (!hash || hash == EMPTY_HASH) + return; + call_rcu_sched(&hash->rcu, __free_ftrace_hash_rcu); +} + +void ftrace_free_filter(struct ftrace_ops *ops) +{ + ftrace_ops_init(ops); + free_ftrace_hash(ops->func_hash->filter_hash); + free_ftrace_hash(ops->func_hash->notrace_hash); +} + +static struct ftrace_hash *alloc_ftrace_hash(int size_bits) +{ + struct ftrace_hash *hash; + int size; + + hash = kzalloc(sizeof(*hash), GFP_KERNEL); + if (!hash) + return NULL; + + size = 1 << size_bits; + hash->buckets = kcalloc(size, sizeof(*hash->buckets), GFP_KERNEL); + + if (!hash->buckets) { + kfree(hash); + return NULL; + } + + hash->size_bits = size_bits; + + return hash; +} + +static struct ftrace_hash * +alloc_and_copy_ftrace_hash(int size_bits, struct ftrace_hash *hash) +{ + struct ftrace_func_entry *entry; + struct ftrace_hash *new_hash; + int size; + int ret; + int i; + + new_hash = alloc_ftrace_hash(size_bits); + if (!new_hash) + return NULL; + + /* Empty hash? */ + if (ftrace_hash_empty(hash)) + return new_hash; + + size = 1 << hash->size_bits; + for (i = 0; i < size; i++) { + hlist_for_each_entry(entry, &hash->buckets[i], hlist) { + ret = add_hash_entry(new_hash, entry->ip); + if (ret < 0) + goto free_hash; + } + } + + FTRACE_WARN_ON(new_hash->count != hash->count); + + return new_hash; + + free_hash: + free_ftrace_hash(new_hash); + return NULL; +} + +static void +ftrace_hash_rec_disable_modify(struct ftrace_ops *ops, int filter_hash); +static void +ftrace_hash_rec_enable_modify(struct ftrace_ops *ops, int filter_hash); + +static int ftrace_hash_ipmodify_update(struct ftrace_ops *ops, + struct ftrace_hash *new_hash); + +static int +ftrace_hash_move(struct ftrace_ops *ops, int enable, + struct ftrace_hash **dst, struct ftrace_hash *src) +{ + struct ftrace_func_entry *entry; + struct hlist_node *tn; + struct hlist_head *hhd; + struct ftrace_hash *new_hash; + int size = src->count; + int bits = 0; + int ret; + int i; + + /* Reject setting notrace hash on IPMODIFY ftrace_ops */ + if (ops->flags & FTRACE_OPS_FL_IPMODIFY && !enable) + return -EINVAL; + + /* + * If the new source is empty, just free dst and assign it + * the empty_hash. + */ + if (!src->count) { + new_hash = EMPTY_HASH; + goto update; + } + + /* + * Make the hash size about 1/2 the # found + */ + for (size /= 2; size; size >>= 1) + bits++; + + /* Don't allocate too much */ + if (bits > FTRACE_HASH_MAX_BITS) + bits = FTRACE_HASH_MAX_BITS; + + new_hash = alloc_ftrace_hash(bits); + if (!new_hash) + return -ENOMEM; + + size = 1 << src->size_bits; + for (i = 0; i < size; i++) { + hhd = &src->buckets[i]; + hlist_for_each_entry_safe(entry, tn, hhd, hlist) { + remove_hash_entry(src, entry); + __add_hash_entry(new_hash, entry); + } + } + +update: + /* Make sure this can be applied if it is IPMODIFY ftrace_ops */ + if (enable) { + /* IPMODIFY should be updated only when filter_hash updating */ + ret = ftrace_hash_ipmodify_update(ops, new_hash); + if (ret < 0) { + free_ftrace_hash(new_hash); + return ret; + } + } + + /* + * Remove the current set, update the hash and add + * them back. + */ + ftrace_hash_rec_disable_modify(ops, enable); + + rcu_assign_pointer(*dst, new_hash); + + ftrace_hash_rec_enable_modify(ops, enable); + + return 0; +} + +static bool hash_contains_ip(unsigned long ip, + struct ftrace_ops_hash *hash) +{ + /* + * The function record is a match if it exists in the filter + * hash and not in the notrace hash. Note, an emty hash is + * considered a match for the filter hash, but an empty + * notrace hash is considered not in the notrace hash. + */ + return (ftrace_hash_empty(hash->filter_hash) || + ftrace_lookup_ip(hash->filter_hash, ip)) && + (ftrace_hash_empty(hash->notrace_hash) || + !ftrace_lookup_ip(hash->notrace_hash, ip)); +} + +/* + * Test the hashes for this ops to see if we want to call + * the ops->func or not. + * + * It's a match if the ip is in the ops->filter_hash or + * the filter_hash does not exist or is empty, + * AND + * the ip is not in the ops->notrace_hash. + * + * This needs to be called with preemption disabled as + * the hashes are freed with call_rcu_sched(). + */ +static int +ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip, void *regs) +{ + struct ftrace_ops_hash hash; + int ret; + +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS + /* + * There's a small race when adding ops that the ftrace handler + * that wants regs, may be called without them. We can not + * allow that handler to be called if regs is NULL. + */ + if (regs == NULL && (ops->flags & FTRACE_OPS_FL_SAVE_REGS)) + return 0; +#endif + + hash.filter_hash = rcu_dereference_raw_notrace(ops->func_hash->filter_hash); + hash.notrace_hash = rcu_dereference_raw_notrace(ops->func_hash->notrace_hash); + + if (hash_contains_ip(ip, &hash)) + ret = 1; + else + ret = 0; + + return ret; +} + +/* + * This is a double for. Do not use 'break' to break out of the loop, + * you must use a goto. + */ +#define do_for_each_ftrace_rec(pg, rec) \ + for (pg = ftrace_pages_start; pg; pg = pg->next) { \ + int _____i; \ + for (_____i = 0; _____i < pg->index; _____i++) { \ + rec = &pg->records[_____i]; + +#define while_for_each_ftrace_rec() \ + } \ + } + + +static int ftrace_cmp_recs(const void *a, const void *b) +{ + const struct dyn_ftrace *key = a; + const struct dyn_ftrace *rec = b; + + if (key->flags < rec->ip) + return -1; + if (key->ip >= rec->ip + MCOUNT_INSN_SIZE) + return 1; + return 0; +} + +static unsigned long ftrace_location_range(unsigned long start, unsigned long end) +{ + struct ftrace_page *pg; + struct dyn_ftrace *rec; + struct dyn_ftrace key; + + key.ip = start; + key.flags = end; /* overload flags, as it is unsigned long */ + + for (pg = ftrace_pages_start; pg; pg = pg->next) { + if (end < pg->records[0].ip || + start >= (pg->records[pg->index - 1].ip + MCOUNT_INSN_SIZE)) + continue; + rec = bsearch(&key, pg->records, pg->index, + sizeof(struct dyn_ftrace), + ftrace_cmp_recs); + if (rec) + return rec->ip; + } + + return 0; +} + +/** + * ftrace_location - return true if the ip giving is a traced location + * @ip: the instruction pointer to check + * + * Returns rec->ip if @ip given is a pointer to a ftrace location. + * That is, the instruction that is either a NOP or call to + * the function tracer. It checks the ftrace internal tables to + * determine if the address belongs or not. + */ +unsigned long ftrace_location(unsigned long ip) +{ + return ftrace_location_range(ip, ip); +} + +/** + * ftrace_text_reserved - return true if range contains an ftrace location + * @start: start of range to search + * @end: end of range to search (inclusive). @end points to the last byte to check. + * + * Returns 1 if @start and @end contains a ftrace location. + * That is, the instruction that is either a NOP or call to + * the function tracer. It checks the ftrace internal tables to + * determine if the address belongs or not. + */ +int ftrace_text_reserved(const void *start, const void *end) +{ + unsigned long ret; + + ret = ftrace_location_range((unsigned long)start, + (unsigned long)end); + + return (int)!!ret; +} + +/* Test if ops registered to this rec needs regs */ +static bool test_rec_ops_needs_regs(struct dyn_ftrace *rec) +{ + struct ftrace_ops *ops; + bool keep_regs = false; + + for (ops = ftrace_ops_list; + ops != &ftrace_list_end; ops = ops->next) { + /* pass rec in as regs to have non-NULL val */ + if (ftrace_ops_test(ops, rec->ip, rec)) { + if (ops->flags & FTRACE_OPS_FL_SAVE_REGS) { + keep_regs = true; + break; + } + } + } + + return keep_regs; +} + +static void __ftrace_hash_rec_update(struct ftrace_ops *ops, + int filter_hash, + bool inc) +{ + struct ftrace_hash *hash; + struct ftrace_hash *other_hash; + struct ftrace_page *pg; + struct dyn_ftrace *rec; + int count = 0; + int all = 0; + + /* Only update if the ops has been registered */ + if (!(ops->flags & FTRACE_OPS_FL_ENABLED)) + return; + + /* + * In the filter_hash case: + * If the count is zero, we update all records. + * Otherwise we just update the items in the hash. + * + * In the notrace_hash case: + * We enable the update in the hash. + * As disabling notrace means enabling the tracing, + * and enabling notrace means disabling, the inc variable + * gets inversed. + */ + if (filter_hash) { + hash = ops->func_hash->filter_hash; + other_hash = ops->func_hash->notrace_hash; + if (ftrace_hash_empty(hash)) + all = 1; + } else { + inc = !inc; + hash = ops->func_hash->notrace_hash; + other_hash = ops->func_hash->filter_hash; + /* + * If the notrace hash has no items, + * then there's nothing to do. + */ + if (ftrace_hash_empty(hash)) + return; + } + + do_for_each_ftrace_rec(pg, rec) { + int in_other_hash = 0; + int in_hash = 0; + int match = 0; + + if (all) { + /* + * Only the filter_hash affects all records. + * Update if the record is not in the notrace hash. + */ + if (!other_hash || !ftrace_lookup_ip(other_hash, rec->ip)) + match = 1; + } else { + in_hash = !!ftrace_lookup_ip(hash, rec->ip); + in_other_hash = !!ftrace_lookup_ip(other_hash, rec->ip); + + /* + * If filter_hash is set, we want to match all functions + * that are in the hash but not in the other hash. + * + * If filter_hash is not set, then we are decrementing. + * That means we match anything that is in the hash + * and also in the other_hash. That is, we need to turn + * off functions in the other hash because they are disabled + * by this hash. + */ + if (filter_hash && in_hash && !in_other_hash) + match = 1; + else if (!filter_hash && in_hash && + (in_other_hash || ftrace_hash_empty(other_hash))) + match = 1; + } + if (!match) + continue; + + if (inc) { + rec->flags++; + if (FTRACE_WARN_ON(ftrace_rec_count(rec) == FTRACE_REF_MAX)) + return; + + /* + * If there's only a single callback registered to a + * function, and the ops has a trampoline registered + * for it, then we can call it directly. + */ + if (ftrace_rec_count(rec) == 1 && ops->trampoline) + rec->flags |= FTRACE_FL_TRAMP; + else + /* + * If we are adding another function callback + * to this function, and the previous had a + * custom trampoline in use, then we need to go + * back to the default trampoline. + */ + rec->flags &= ~FTRACE_FL_TRAMP; + + /* + * If any ops wants regs saved for this function + * then all ops will get saved regs. + */ + if (ops->flags & FTRACE_OPS_FL_SAVE_REGS) + rec->flags |= FTRACE_FL_REGS; + } else { + if (FTRACE_WARN_ON(ftrace_rec_count(rec) == 0)) + return; + rec->flags--; + + /* + * If the rec had REGS enabled and the ops that is + * being removed had REGS set, then see if there is + * still any ops for this record that wants regs. + * If not, we can stop recording them. + */ + if (ftrace_rec_count(rec) > 0 && + rec->flags & FTRACE_FL_REGS && + ops->flags & FTRACE_OPS_FL_SAVE_REGS) { + if (!test_rec_ops_needs_regs(rec)) + rec->flags &= ~FTRACE_FL_REGS; + } + + /* + * If the rec had TRAMP enabled, then it needs to + * be cleared. As TRAMP can only be enabled iff + * there is only a single ops attached to it. + * In otherwords, always disable it on decrementing. + * In the future, we may set it if rec count is + * decremented to one, and the ops that is left + * has a trampoline. + */ + rec->flags &= ~FTRACE_FL_TRAMP; + + /* + * flags will be cleared in ftrace_check_record() + * if rec count is zero. + */ + } + count++; + /* Shortcut, if we handled all records, we are done. */ + if (!all && count == hash->count) + return; + } while_for_each_ftrace_rec(); +} + +static void ftrace_hash_rec_disable(struct ftrace_ops *ops, + int filter_hash) +{ + __ftrace_hash_rec_update(ops, filter_hash, 0); +} + +static void ftrace_hash_rec_enable(struct ftrace_ops *ops, + int filter_hash) +{ + __ftrace_hash_rec_update(ops, filter_hash, 1); +} + +static void ftrace_hash_rec_update_modify(struct ftrace_ops *ops, + int filter_hash, int inc) +{ + struct ftrace_ops *op; + + __ftrace_hash_rec_update(ops, filter_hash, inc); + + if (ops->func_hash != &global_ops.local_hash) + return; + + /* + * If the ops shares the global_ops hash, then we need to update + * all ops that are enabled and use this hash. + */ + do_for_each_ftrace_op(op, ftrace_ops_list) { + /* Already done */ + if (op == ops) + continue; + if (op->func_hash == &global_ops.local_hash) + __ftrace_hash_rec_update(op, filter_hash, inc); + } while_for_each_ftrace_op(op); +} + +static void ftrace_hash_rec_disable_modify(struct ftrace_ops *ops, + int filter_hash) +{ + ftrace_hash_rec_update_modify(ops, filter_hash, 0); +} + +static void ftrace_hash_rec_enable_modify(struct ftrace_ops *ops, + int filter_hash) +{ + ftrace_hash_rec_update_modify(ops, filter_hash, 1); +} + +/* + * Try to update IPMODIFY flag on each ftrace_rec. Return 0 if it is OK + * or no-needed to update, -EBUSY if it detects a conflict of the flag + * on a ftrace_rec, and -EINVAL if the new_hash tries to trace all recs. + * Note that old_hash and new_hash has below meanings + * - If the hash is NULL, it hits all recs (if IPMODIFY is set, this is rejected) + * - If the hash is EMPTY_HASH, it hits nothing + * - Anything else hits the recs which match the hash entries. + */ +static int __ftrace_hash_update_ipmodify(struct ftrace_ops *ops, + struct ftrace_hash *old_hash, + struct ftrace_hash *new_hash) +{ + struct ftrace_page *pg; + struct dyn_ftrace *rec, *end = NULL; + int in_old, in_new; + + /* Only update if the ops has been registered */ + if (!(ops->flags & FTRACE_OPS_FL_ENABLED)) + return 0; + + if (!(ops->flags & FTRACE_OPS_FL_IPMODIFY)) + return 0; + + /* + * Since the IPMODIFY is a very address sensitive action, we do not + * allow ftrace_ops to set all functions to new hash. + */ + if (!new_hash || !old_hash) + return -EINVAL; + + /* Update rec->flags */ + do_for_each_ftrace_rec(pg, rec) { + /* We need to update only differences of filter_hash */ + in_old = !!ftrace_lookup_ip(old_hash, rec->ip); + in_new = !!ftrace_lookup_ip(new_hash, rec->ip); + if (in_old == in_new) + continue; + + if (in_new) { + /* New entries must ensure no others are using it */ + if (rec->flags & FTRACE_FL_IPMODIFY) + goto rollback; + rec->flags |= FTRACE_FL_IPMODIFY; + } else /* Removed entry */ + rec->flags &= ~FTRACE_FL_IPMODIFY; + } while_for_each_ftrace_rec(); + + return 0; + +rollback: + end = rec; + + /* Roll back what we did above */ + do_for_each_ftrace_rec(pg, rec) { + if (rec == end) + goto err_out; + + in_old = !!ftrace_lookup_ip(old_hash, rec->ip); + in_new = !!ftrace_lookup_ip(new_hash, rec->ip); + if (in_old == in_new) + continue; + + if (in_new) + rec->flags &= ~FTRACE_FL_IPMODIFY; + else + rec->flags |= FTRACE_FL_IPMODIFY; + } while_for_each_ftrace_rec(); + +err_out: + return -EBUSY; +} + +static int ftrace_hash_ipmodify_enable(struct ftrace_ops *ops) +{ + struct ftrace_hash *hash = ops->func_hash->filter_hash; + + if (ftrace_hash_empty(hash)) + hash = NULL; + + return __ftrace_hash_update_ipmodify(ops, EMPTY_HASH, hash); +} + +/* Disabling always succeeds */ +static void ftrace_hash_ipmodify_disable(struct ftrace_ops *ops) +{ + struct ftrace_hash *hash = ops->func_hash->filter_hash; + + if (ftrace_hash_empty(hash)) + hash = NULL; + + __ftrace_hash_update_ipmodify(ops, hash, EMPTY_HASH); +} + +static int ftrace_hash_ipmodify_update(struct ftrace_ops *ops, + struct ftrace_hash *new_hash) +{ + struct ftrace_hash *old_hash = ops->func_hash->filter_hash; + + if (ftrace_hash_empty(old_hash)) + old_hash = NULL; + + if (ftrace_hash_empty(new_hash)) + new_hash = NULL; + + return __ftrace_hash_update_ipmodify(ops, old_hash, new_hash); +} + +static void print_ip_ins(const char *fmt, unsigned char *p) +{ + int i; + + printk(KERN_CONT "%s", fmt); + + for (i = 0; i < MCOUNT_INSN_SIZE; i++) + printk(KERN_CONT "%s%02x", i ? ":" : "", p[i]); +} + +static struct ftrace_ops * +ftrace_find_tramp_ops_any(struct dyn_ftrace *rec); + +/** + * ftrace_bug - report and shutdown function tracer + * @failed: The failed type (EFAULT, EINVAL, EPERM) + * @rec: The record that failed + * + * The arch code that enables or disables the function tracing + * can call ftrace_bug() when it has detected a problem in + * modifying the code. @failed should be one of either: + * EFAULT - if the problem happens on reading the @ip address + * EINVAL - if what is read at @ip is not what was expected + * EPERM - if the problem happens on writting to the @ip address + */ +void ftrace_bug(int failed, struct dyn_ftrace *rec) +{ + unsigned long ip = rec ? rec->ip : 0; + + switch (failed) { + case -EFAULT: + FTRACE_WARN_ON_ONCE(1); + pr_info("ftrace faulted on modifying "); + print_ip_sym(ip); + break; + case -EINVAL: + FTRACE_WARN_ON_ONCE(1); + pr_info("ftrace failed to modify "); + print_ip_sym(ip); + print_ip_ins(" actual: ", (unsigned char *)ip); + pr_cont("\n"); + break; + case -EPERM: + FTRACE_WARN_ON_ONCE(1); + pr_info("ftrace faulted on writing "); + print_ip_sym(ip); + break; + default: + FTRACE_WARN_ON_ONCE(1); + pr_info("ftrace faulted on unknown error "); + print_ip_sym(ip); + } + if (rec) { + struct ftrace_ops *ops = NULL; + + pr_info("ftrace record flags: %lx\n", rec->flags); + pr_cont(" (%ld)%s", ftrace_rec_count(rec), + rec->flags & FTRACE_FL_REGS ? " R" : " "); + if (rec->flags & FTRACE_FL_TRAMP_EN) { + ops = ftrace_find_tramp_ops_any(rec); + if (ops) + pr_cont("\ttramp: %pS", + (void *)ops->trampoline); + else + pr_cont("\ttramp: ERROR!"); + + } + ip = ftrace_get_addr_curr(rec); + pr_cont(" expected tramp: %lx\n", ip); + } +} + +static int ftrace_check_record(struct dyn_ftrace *rec, int enable, int update) +{ + unsigned long flag = 0UL; + + /* + * If we are updating calls: + * + * If the record has a ref count, then we need to enable it + * because someone is using it. + * + * Otherwise we make sure its disabled. + * + * If we are disabling calls, then disable all records that + * are enabled. + */ + if (enable && ftrace_rec_count(rec)) + flag = FTRACE_FL_ENABLED; + + /* + * If enabling and the REGS flag does not match the REGS_EN, or + * the TRAMP flag doesn't match the TRAMP_EN, then do not ignore + * this record. Set flags to fail the compare against ENABLED. + */ + if (flag) { + if (!(rec->flags & FTRACE_FL_REGS) != + !(rec->flags & FTRACE_FL_REGS_EN)) + flag |= FTRACE_FL_REGS; + + if (!(rec->flags & FTRACE_FL_TRAMP) != + !(rec->flags & FTRACE_FL_TRAMP_EN)) + flag |= FTRACE_FL_TRAMP; + } + + /* If the state of this record hasn't changed, then do nothing */ + if ((rec->flags & FTRACE_FL_ENABLED) == flag) + return FTRACE_UPDATE_IGNORE; + + if (flag) { + /* Save off if rec is being enabled (for return value) */ + flag ^= rec->flags & FTRACE_FL_ENABLED; + + if (update) { + rec->flags |= FTRACE_FL_ENABLED; + if (flag & FTRACE_FL_REGS) { + if (rec->flags & FTRACE_FL_REGS) + rec->flags |= FTRACE_FL_REGS_EN; + else + rec->flags &= ~FTRACE_FL_REGS_EN; + } + if (flag & FTRACE_FL_TRAMP) { + if (rec->flags & FTRACE_FL_TRAMP) + rec->flags |= FTRACE_FL_TRAMP_EN; + else + rec->flags &= ~FTRACE_FL_TRAMP_EN; + } + } + + /* + * If this record is being updated from a nop, then + * return UPDATE_MAKE_CALL. + * Otherwise, + * return UPDATE_MODIFY_CALL to tell the caller to convert + * from the save regs, to a non-save regs function or + * vice versa, or from a trampoline call. + */ + if (flag & FTRACE_FL_ENABLED) + return FTRACE_UPDATE_MAKE_CALL; + + return FTRACE_UPDATE_MODIFY_CALL; + } + + if (update) { + /* If there's no more users, clear all flags */ + if (!ftrace_rec_count(rec)) + rec->flags = 0; + else + /* + * Just disable the record, but keep the ops TRAMP + * and REGS states. The _EN flags must be disabled though. + */ + rec->flags &= ~(FTRACE_FL_ENABLED | FTRACE_FL_TRAMP_EN | + FTRACE_FL_REGS_EN); + } + + return FTRACE_UPDATE_MAKE_NOP; +} + +/** + * ftrace_update_record, set a record that now is tracing or not + * @rec: the record to update + * @enable: set to 1 if the record is tracing, zero to force disable + * + * The records that represent all functions that can be traced need + * to be updated when tracing has been enabled. + */ +int ftrace_update_record(struct dyn_ftrace *rec, int enable) +{ + return ftrace_check_record(rec, enable, 1); +} + +/** + * ftrace_test_record, check if the record has been enabled or not + * @rec: the record to test + * @enable: set to 1 to check if enabled, 0 if it is disabled + * + * The arch code may need to test if a record is already set to + * tracing to determine how to modify the function code that it + * represents. + */ +int ftrace_test_record(struct dyn_ftrace *rec, int enable) +{ + return ftrace_check_record(rec, enable, 0); +} + +static struct ftrace_ops * +ftrace_find_tramp_ops_any(struct dyn_ftrace *rec) +{ + struct ftrace_ops *op; + unsigned long ip = rec->ip; + + do_for_each_ftrace_op(op, ftrace_ops_list) { + + if (!op->trampoline) + continue; + + if (hash_contains_ip(ip, op->func_hash)) + return op; + } while_for_each_ftrace_op(op); + + return NULL; +} + +static struct ftrace_ops * +ftrace_find_tramp_ops_curr(struct dyn_ftrace *rec) +{ + struct ftrace_ops *op; + unsigned long ip = rec->ip; + + /* + * Need to check removed ops first. + * If they are being removed, and this rec has a tramp, + * and this rec is in the ops list, then it would be the + * one with the tramp. + */ + if (removed_ops) { + if (hash_contains_ip(ip, &removed_ops->old_hash)) + return removed_ops; + } + + /* + * Need to find the current trampoline for a rec. + * Now, a trampoline is only attached to a rec if there + * was a single 'ops' attached to it. But this can be called + * when we are adding another op to the rec or removing the + * current one. Thus, if the op is being added, we can + * ignore it because it hasn't attached itself to the rec + * yet. + * + * If an ops is being modified (hooking to different functions) + * then we don't care about the new functions that are being + * added, just the old ones (that are probably being removed). + * + * If we are adding an ops to a function that already is using + * a trampoline, it needs to be removed (trampolines are only + * for single ops connected), then an ops that is not being + * modified also needs to be checked. + */ + do_for_each_ftrace_op(op, ftrace_ops_list) { + + if (!op->trampoline) + continue; + + /* + * If the ops is being added, it hasn't gotten to + * the point to be removed from this tree yet. + */ + if (op->flags & FTRACE_OPS_FL_ADDING) + continue; + + + /* + * If the ops is being modified and is in the old + * hash, then it is probably being removed from this + * function. + */ + if ((op->flags & FTRACE_OPS_FL_MODIFYING) && + hash_contains_ip(ip, &op->old_hash)) + return op; + /* + * If the ops is not being added or modified, and it's + * in its normal filter hash, then this must be the one + * we want! + */ + if (!(op->flags & FTRACE_OPS_FL_MODIFYING) && + hash_contains_ip(ip, op->func_hash)) + return op; + + } while_for_each_ftrace_op(op); + + return NULL; +} + +static struct ftrace_ops * +ftrace_find_tramp_ops_new(struct dyn_ftrace *rec) +{ + struct ftrace_ops *op; + unsigned long ip = rec->ip; + + do_for_each_ftrace_op(op, ftrace_ops_list) { + /* pass rec in as regs to have non-NULL val */ + if (hash_contains_ip(ip, op->func_hash)) + return op; + } while_for_each_ftrace_op(op); + + return NULL; +} + +/** + * ftrace_get_addr_new - Get the call address to set to + * @rec: The ftrace record descriptor + * + * If the record has the FTRACE_FL_REGS set, that means that it + * wants to convert to a callback that saves all regs. If FTRACE_FL_REGS + * is not not set, then it wants to convert to the normal callback. + * + * Returns the address of the trampoline to set to + */ +unsigned long ftrace_get_addr_new(struct dyn_ftrace *rec) +{ + struct ftrace_ops *ops; + + /* Trampolines take precedence over regs */ + if (rec->flags & FTRACE_FL_TRAMP) { + ops = ftrace_find_tramp_ops_new(rec); + if (FTRACE_WARN_ON(!ops || !ops->trampoline)) { + pr_warn("Bad trampoline accounting at: %p (%pS) (%lx)\n", + (void *)rec->ip, (void *)rec->ip, rec->flags); + /* Ftrace is shutting down, return anything */ + return (unsigned long)FTRACE_ADDR; + } + return ops->trampoline; + } + + if (rec->flags & FTRACE_FL_REGS) + return (unsigned long)FTRACE_REGS_ADDR; + else + return (unsigned long)FTRACE_ADDR; +} + +/** + * ftrace_get_addr_curr - Get the call address that is already there + * @rec: The ftrace record descriptor + * + * The FTRACE_FL_REGS_EN is set when the record already points to + * a function that saves all the regs. Basically the '_EN' version + * represents the current state of the function. + * + * Returns the address of the trampoline that is currently being called + */ +unsigned long ftrace_get_addr_curr(struct dyn_ftrace *rec) +{ + struct ftrace_ops *ops; + + /* Trampolines take precedence over regs */ + if (rec->flags & FTRACE_FL_TRAMP_EN) { + ops = ftrace_find_tramp_ops_curr(rec); + if (FTRACE_WARN_ON(!ops)) { + pr_warning("Bad trampoline accounting at: %p (%pS)\n", + (void *)rec->ip, (void *)rec->ip); + /* Ftrace is shutting down, return anything */ + return (unsigned long)FTRACE_ADDR; + } + return ops->trampoline; + } + + if (rec->flags & FTRACE_FL_REGS_EN) + return (unsigned long)FTRACE_REGS_ADDR; + else + return (unsigned long)FTRACE_ADDR; +} + +static int +__ftrace_replace_code(struct dyn_ftrace *rec, int enable) +{ + unsigned long ftrace_old_addr; + unsigned long ftrace_addr; + int ret; + + ftrace_addr = ftrace_get_addr_new(rec); + + /* This needs to be done before we call ftrace_update_record */ + ftrace_old_addr = ftrace_get_addr_curr(rec); + + ret = ftrace_update_record(rec, enable); + + switch (ret) { + case FTRACE_UPDATE_IGNORE: + return 0; + + case FTRACE_UPDATE_MAKE_CALL: + return ftrace_make_call(rec, ftrace_addr); + + case FTRACE_UPDATE_MAKE_NOP: + return ftrace_make_nop(NULL, rec, ftrace_old_addr); + + case FTRACE_UPDATE_MODIFY_CALL: + return ftrace_modify_call(rec, ftrace_old_addr, ftrace_addr); + } + + return -1; /* unknow ftrace bug */ +} + +void __weak ftrace_replace_code(int enable) +{ + struct dyn_ftrace *rec; + struct ftrace_page *pg; + int failed; + + if (unlikely(ftrace_disabled)) + return; + + do_for_each_ftrace_rec(pg, rec) { + failed = __ftrace_replace_code(rec, enable); + if (failed) { + ftrace_bug(failed, rec); + /* Stop processing */ + return; + } + } while_for_each_ftrace_rec(); +} + +struct ftrace_rec_iter { + struct ftrace_page *pg; + int index; +}; + +/** + * ftrace_rec_iter_start, start up iterating over traced functions + * + * Returns an iterator handle that is used to iterate over all + * the records that represent address locations where functions + * are traced. + * + * May return NULL if no records are available. + */ +struct ftrace_rec_iter *ftrace_rec_iter_start(void) +{ + /* + * We only use a single iterator. + * Protected by the ftrace_lock mutex. + */ + static struct ftrace_rec_iter ftrace_rec_iter; + struct ftrace_rec_iter *iter = &ftrace_rec_iter; + + iter->pg = ftrace_pages_start; + iter->index = 0; + + /* Could have empty pages */ + while (iter->pg && !iter->pg->index) + iter->pg = iter->pg->next; + + if (!iter->pg) + return NULL; + + return iter; +} + +/** + * ftrace_rec_iter_next, get the next record to process. + * @iter: The handle to the iterator. + * + * Returns the next iterator after the given iterator @iter. + */ +struct ftrace_rec_iter *ftrace_rec_iter_next(struct ftrace_rec_iter *iter) +{ + iter->index++; + + if (iter->index >= iter->pg->index) { + iter->pg = iter->pg->next; + iter->index = 0; + + /* Could have empty pages */ + while (iter->pg && !iter->pg->index) + iter->pg = iter->pg->next; + } + + if (!iter->pg) + return NULL; + + return iter; +} + +/** + * ftrace_rec_iter_record, get the record at the iterator location + * @iter: The current iterator location + * + * Returns the record that the current @iter is at. + */ +struct dyn_ftrace *ftrace_rec_iter_record(struct ftrace_rec_iter *iter) +{ + return &iter->pg->records[iter->index]; +} + +static int +ftrace_code_disable(struct module *mod, struct dyn_ftrace *rec) +{ + int ret; + + if (unlikely(ftrace_disabled)) + return 0; + + ret = ftrace_make_nop(mod, rec, MCOUNT_ADDR); + if (ret) { + ftrace_bug(ret, rec); + return 0; + } + return 1; +} + +/* + * archs can override this function if they must do something + * before the modifying code is performed. + */ +int __weak ftrace_arch_code_modify_prepare(void) +{ + return 0; +} + +/* + * archs can override this function if they must do something + * after the modifying code is performed. + */ +int __weak ftrace_arch_code_modify_post_process(void) +{ + return 0; +} + +void ftrace_modify_all_code(int command) +{ + int update = command & FTRACE_UPDATE_TRACE_FUNC; + int err = 0; + + /* + * If the ftrace_caller calls a ftrace_ops func directly, + * we need to make sure that it only traces functions it + * expects to trace. When doing the switch of functions, + * we need to update to the ftrace_ops_list_func first + * before the transition between old and new calls are set, + * as the ftrace_ops_list_func will check the ops hashes + * to make sure the ops are having the right functions + * traced. + */ + if (update) { + err = ftrace_update_ftrace_func(ftrace_ops_list_func); + if (FTRACE_WARN_ON(err)) + return; + } + + if (command & FTRACE_UPDATE_CALLS) + ftrace_replace_code(1); + else if (command & FTRACE_DISABLE_CALLS) + ftrace_replace_code(0); + + if (update && ftrace_trace_function != ftrace_ops_list_func) { + function_trace_op = set_function_trace_op; + smp_wmb(); + /* If irqs are disabled, we are in stop machine */ + if (!irqs_disabled()) + smp_call_function(ftrace_sync_ipi, NULL, 1); + err = ftrace_update_ftrace_func(ftrace_trace_function); + if (FTRACE_WARN_ON(err)) + return; + } + + if (command & FTRACE_START_FUNC_RET) + err = ftrace_enable_ftrace_graph_caller(); + else if (command & FTRACE_STOP_FUNC_RET) + err = ftrace_disable_ftrace_graph_caller(); + FTRACE_WARN_ON(err); +} + +static int __ftrace_modify_code(void *data) +{ + int *command = data; + + ftrace_modify_all_code(*command); + + return 0; +} + +/** + * ftrace_run_stop_machine, go back to the stop machine method + * @command: The command to tell ftrace what to do + * + * If an arch needs to fall back to the stop machine method, the + * it can call this function. + */ +void ftrace_run_stop_machine(int command) +{ + stop_machine(__ftrace_modify_code, &command, NULL); +} + +/** + * arch_ftrace_update_code, modify the code to trace or not trace + * @command: The command that needs to be done + * + * Archs can override this function if it does not need to + * run stop_machine() to modify code. + */ +void __weak arch_ftrace_update_code(int command) +{ + ftrace_run_stop_machine(command); +} + +static void ftrace_run_update_code(int command) +{ + int ret; + + ret = ftrace_arch_code_modify_prepare(); + FTRACE_WARN_ON(ret); + if (ret) + return; + + /* + * By default we use stop_machine() to modify the code. + * But archs can do what ever they want as long as it + * is safe. The stop_machine() is the safest, but also + * produces the most overhead. + */ + arch_ftrace_update_code(command); + + ret = ftrace_arch_code_modify_post_process(); + FTRACE_WARN_ON(ret); +} + +static void ftrace_run_modify_code(struct ftrace_ops *ops, int command, + struct ftrace_ops_hash *old_hash) +{ + ops->flags |= FTRACE_OPS_FL_MODIFYING; + ops->old_hash.filter_hash = old_hash->filter_hash; + ops->old_hash.notrace_hash = old_hash->notrace_hash; + ftrace_run_update_code(command); + ops->old_hash.filter_hash = NULL; + ops->old_hash.notrace_hash = NULL; + ops->flags &= ~FTRACE_OPS_FL_MODIFYING; +} + +static ftrace_func_t saved_ftrace_func; +static int ftrace_start_up; + +void __weak arch_ftrace_trampoline_free(struct ftrace_ops *ops) +{ +} + +static void control_ops_free(struct ftrace_ops *ops) +{ + free_percpu(ops->disabled); +} + +static void ftrace_startup_enable(int command) +{ + if (saved_ftrace_func != ftrace_trace_function) { + saved_ftrace_func = ftrace_trace_function; + command |= FTRACE_UPDATE_TRACE_FUNC; + } + + if (!command || !ftrace_enabled) + return; + + ftrace_run_update_code(command); +} + +static void ftrace_startup_all(int command) +{ + update_all_ops = true; + ftrace_startup_enable(command); + update_all_ops = false; +} + +static int ftrace_startup(struct ftrace_ops *ops, int command) +{ + int ret; + + if (unlikely(ftrace_disabled)) + return -ENODEV; + + ret = __register_ftrace_function(ops); + if (ret) + return ret; + + ftrace_start_up++; + command |= FTRACE_UPDATE_CALLS; + + /* + * Note that ftrace probes uses this to start up + * and modify functions it will probe. But we still + * set the ADDING flag for modification, as probes + * do not have trampolines. If they add them in the + * future, then the probes will need to distinguish + * between adding and updating probes. + */ + ops->flags |= FTRACE_OPS_FL_ENABLED | FTRACE_OPS_FL_ADDING; + + ret = ftrace_hash_ipmodify_enable(ops); + if (ret < 0) { + /* Rollback registration process */ + __unregister_ftrace_function(ops); + ftrace_start_up--; + ops->flags &= ~FTRACE_OPS_FL_ENABLED; + return ret; + } + + ftrace_hash_rec_enable(ops, 1); + + ftrace_startup_enable(command); + + ops->flags &= ~FTRACE_OPS_FL_ADDING; + + return 0; +} + +static int ftrace_shutdown(struct ftrace_ops *ops, int command) +{ + int ret; + + if (unlikely(ftrace_disabled)) + return -ENODEV; + + ret = __unregister_ftrace_function(ops); + if (ret) + return ret; + + ftrace_start_up--; + /* + * Just warn in case of unbalance, no need to kill ftrace, it's not + * critical but the ftrace_call callers may be never nopped again after + * further ftrace uses. + */ + WARN_ON_ONCE(ftrace_start_up < 0); + + /* Disabling ipmodify never fails */ + ftrace_hash_ipmodify_disable(ops); + ftrace_hash_rec_disable(ops, 1); + + ops->flags &= ~FTRACE_OPS_FL_ENABLED; + + command |= FTRACE_UPDATE_CALLS; + + if (saved_ftrace_func != ftrace_trace_function) { + saved_ftrace_func = ftrace_trace_function; + command |= FTRACE_UPDATE_TRACE_FUNC; + } + + if (!command || !ftrace_enabled) { + /* + * If these are control ops, they still need their + * per_cpu field freed. Since, function tracing is + * not currently active, we can just free them + * without synchronizing all CPUs. + */ + if (ops->flags & FTRACE_OPS_FL_CONTROL) + control_ops_free(ops); + return 0; + } + + /* + * If the ops uses a trampoline, then it needs to be + * tested first on update. + */ + ops->flags |= FTRACE_OPS_FL_REMOVING; + removed_ops = ops; + + /* The trampoline logic checks the old hashes */ + ops->old_hash.filter_hash = ops->func_hash->filter_hash; + ops->old_hash.notrace_hash = ops->func_hash->notrace_hash; + + ftrace_run_update_code(command); + + /* + * If there's no more ops registered with ftrace, run a + * sanity check to make sure all rec flags are cleared. + */ + if (ftrace_ops_list == &ftrace_list_end) { + struct ftrace_page *pg; + struct dyn_ftrace *rec; + + do_for_each_ftrace_rec(pg, rec) { + if (FTRACE_WARN_ON_ONCE(rec->flags)) + pr_warn(" %pS flags:%lx\n", + (void *)rec->ip, rec->flags); + } while_for_each_ftrace_rec(); + } + + ops->old_hash.filter_hash = NULL; + ops->old_hash.notrace_hash = NULL; + + removed_ops = NULL; + ops->flags &= ~FTRACE_OPS_FL_REMOVING; + + /* + * Dynamic ops may be freed, we must make sure that all + * callers are done before leaving this function. + * The same goes for freeing the per_cpu data of the control + * ops. + * + * Again, normal synchronize_sched() is not good enough. + * We need to do a hard force of sched synchronization. + * This is because we use preempt_disable() to do RCU, but + * the function tracers can be called where RCU is not watching + * (like before user_exit()). We can not rely on the RCU + * infrastructure to do the synchronization, thus we must do it + * ourselves. + */ + if (ops->flags & (FTRACE_OPS_FL_DYNAMIC | FTRACE_OPS_FL_CONTROL)) { + schedule_on_each_cpu(ftrace_sync); + + arch_ftrace_trampoline_free(ops); + + if (ops->flags & FTRACE_OPS_FL_CONTROL) + control_ops_free(ops); + } + + return 0; +} + +static void ftrace_startup_sysctl(void) +{ + int command; + + if (unlikely(ftrace_disabled)) + return; + + /* Force update next time */ + saved_ftrace_func = NULL; + /* ftrace_start_up is true if we want ftrace running */ + if (ftrace_start_up) { + command = FTRACE_UPDATE_CALLS; + if (ftrace_graph_active) + command |= FTRACE_START_FUNC_RET; + ftrace_startup_enable(command); + } +} + +static void ftrace_shutdown_sysctl(void) +{ + int command; + + if (unlikely(ftrace_disabled)) + return; + + /* ftrace_start_up is true if ftrace is running */ + if (ftrace_start_up) { + command = FTRACE_DISABLE_CALLS; + if (ftrace_graph_active) + command |= FTRACE_STOP_FUNC_RET; + ftrace_run_update_code(command); + } +} + +static cycle_t ftrace_update_time; +unsigned long ftrace_update_tot_cnt; + +static inline int ops_traces_mod(struct ftrace_ops *ops) +{ + /* + * Filter_hash being empty will default to trace module. + * But notrace hash requires a test of individual module functions. + */ + return ftrace_hash_empty(ops->func_hash->filter_hash) && + ftrace_hash_empty(ops->func_hash->notrace_hash); +} + +/* + * Check if the current ops references the record. + * + * If the ops traces all functions, then it was already accounted for. + * If the ops does not trace the current record function, skip it. + * If the ops ignores the function via notrace filter, skip it. + */ +static inline bool +ops_references_rec(struct ftrace_ops *ops, struct dyn_ftrace *rec) +{ + /* If ops isn't enabled, ignore it */ + if (!(ops->flags & FTRACE_OPS_FL_ENABLED)) + return 0; + + /* If ops traces all mods, we already accounted for it */ + if (ops_traces_mod(ops)) + return 0; + + /* The function must be in the filter */ + if (!ftrace_hash_empty(ops->func_hash->filter_hash) && + !ftrace_lookup_ip(ops->func_hash->filter_hash, rec->ip)) + return 0; + + /* If in notrace hash, we ignore it too */ + if (ftrace_lookup_ip(ops->func_hash->notrace_hash, rec->ip)) + return 0; + + return 1; +} + +static int referenced_filters(struct dyn_ftrace *rec) +{ + struct ftrace_ops *ops; + int cnt = 0; + + for (ops = ftrace_ops_list; ops != &ftrace_list_end; ops = ops->next) { + if (ops_references_rec(ops, rec)) + cnt++; + } + + return cnt; +} + +static int ftrace_update_code(struct module *mod, struct ftrace_page *new_pgs) +{ + struct ftrace_page *pg; + struct dyn_ftrace *p; + cycle_t start, stop; + unsigned long update_cnt = 0; + unsigned long ref = 0; + bool test = false; + int i; + + /* + * When adding a module, we need to check if tracers are + * currently enabled and if they are set to trace all functions. + * If they are, we need to enable the module functions as well + * as update the reference counts for those function records. + */ + if (mod) { + struct ftrace_ops *ops; + + for (ops = ftrace_ops_list; + ops != &ftrace_list_end; ops = ops->next) { + if (ops->flags & FTRACE_OPS_FL_ENABLED) { + if (ops_traces_mod(ops)) + ref++; + else + test = true; + } + } + } + + start = ftrace_now(raw_smp_processor_id()); + + for (pg = new_pgs; pg; pg = pg->next) { + + for (i = 0; i < pg->index; i++) { + int cnt = ref; + + /* If something went wrong, bail without enabling anything */ + if (unlikely(ftrace_disabled)) + return -1; + + p = &pg->records[i]; + if (test) + cnt += referenced_filters(p); + p->flags = cnt; + + /* + * Do the initial record conversion from mcount jump + * to the NOP instructions. + */ + if (!ftrace_code_disable(mod, p)) + break; + + update_cnt++; + + /* + * If the tracing is enabled, go ahead and enable the record. + * + * The reason not to enable the record immediatelly is the + * inherent check of ftrace_make_nop/ftrace_make_call for + * correct previous instructions. Making first the NOP + * conversion puts the module to the correct state, thus + * passing the ftrace_make_call check. + */ + if (ftrace_start_up && cnt) { + int failed = __ftrace_replace_code(p, 1); + if (failed) + ftrace_bug(failed, p); + } + } + } + + stop = ftrace_now(raw_smp_processor_id()); + ftrace_update_time = stop - start; + ftrace_update_tot_cnt += update_cnt; + + return 0; +} + +static int ftrace_allocate_records(struct ftrace_page *pg, int count) +{ + int order; + int cnt; + + if (WARN_ON(!count)) + return -EINVAL; + + order = get_count_order(DIV_ROUND_UP(count, ENTRIES_PER_PAGE)); + + /* + * We want to fill as much as possible. No more than a page + * may be empty. + */ + while ((PAGE_SIZE << order) / ENTRY_SIZE >= count + ENTRIES_PER_PAGE) + order--; + + again: + pg->records = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, order); + + if (!pg->records) { + /* if we can't allocate this size, try something smaller */ + if (!order) + return -ENOMEM; + order >>= 1; + goto again; + } + + cnt = (PAGE_SIZE << order) / ENTRY_SIZE; + pg->size = cnt; + + if (cnt > count) + cnt = count; + + return cnt; +} + +static struct ftrace_page * +ftrace_allocate_pages(unsigned long num_to_init) +{ + struct ftrace_page *start_pg; + struct ftrace_page *pg; + int order; + int cnt; + + if (!num_to_init) + return 0; + + start_pg = pg = kzalloc(sizeof(*pg), GFP_KERNEL); + if (!pg) + return NULL; + + /* + * Try to allocate as much as possible in one continues + * location that fills in all of the space. We want to + * waste as little space as possible. + */ + for (;;) { + cnt = ftrace_allocate_records(pg, num_to_init); + if (cnt < 0) + goto free_pages; + + num_to_init -= cnt; + if (!num_to_init) + break; + + pg->next = kzalloc(sizeof(*pg), GFP_KERNEL); + if (!pg->next) + goto free_pages; + + pg = pg->next; + } + + return start_pg; + + free_pages: + pg = start_pg; + while (pg) { + order = get_count_order(pg->size / ENTRIES_PER_PAGE); + free_pages((unsigned long)pg->records, order); + start_pg = pg->next; + kfree(pg); + pg = start_pg; + } + pr_info("ftrace: FAILED to allocate memory for functions\n"); + return NULL; +} + +#define FTRACE_BUFF_MAX (KSYM_SYMBOL_LEN+4) /* room for wildcards */ + +struct ftrace_iterator { + loff_t pos; + loff_t func_pos; + struct ftrace_page *pg; + struct dyn_ftrace *func; + struct ftrace_func_probe *probe; + struct trace_parser parser; + struct ftrace_hash *hash; + struct ftrace_ops *ops; + int hidx; + int idx; + unsigned flags; +}; + +static void * +t_hash_next(struct seq_file *m, loff_t *pos) +{ + struct ftrace_iterator *iter = m->private; + struct hlist_node *hnd = NULL; + struct hlist_head *hhd; + + (*pos)++; + iter->pos = *pos; + + if (iter->probe) + hnd = &iter->probe->node; + retry: + if (iter->hidx >= FTRACE_FUNC_HASHSIZE) + return NULL; + + hhd = &ftrace_func_hash[iter->hidx]; + + if (hlist_empty(hhd)) { + iter->hidx++; + hnd = NULL; + goto retry; + } + + if (!hnd) + hnd = hhd->first; + else { + hnd = hnd->next; + if (!hnd) { + iter->hidx++; + goto retry; + } + } + + if (WARN_ON_ONCE(!hnd)) + return NULL; + + iter->probe = hlist_entry(hnd, struct ftrace_func_probe, node); + + return iter; +} + +static void *t_hash_start(struct seq_file *m, loff_t *pos) +{ + struct ftrace_iterator *iter = m->private; + void *p = NULL; + loff_t l; + + if (!(iter->flags & FTRACE_ITER_DO_HASH)) + return NULL; + + if (iter->func_pos > *pos) + return NULL; + + iter->hidx = 0; + for (l = 0; l <= (*pos - iter->func_pos); ) { + p = t_hash_next(m, &l); + if (!p) + break; + } + if (!p) + return NULL; + + /* Only set this if we have an item */ + iter->flags |= FTRACE_ITER_HASH; + + return iter; +} + +static int +t_hash_show(struct seq_file *m, struct ftrace_iterator *iter) +{ + struct ftrace_func_probe *rec; + + rec = iter->probe; + if (WARN_ON_ONCE(!rec)) + return -EIO; + + if (rec->ops->print) + return rec->ops->print(m, rec->ip, rec->ops, rec->data); + + seq_printf(m, "%ps:%ps", (void *)rec->ip, (void *)rec->ops->func); + + if (rec->data) + seq_printf(m, ":%p", rec->data); + seq_putc(m, '\n'); + + return 0; +} + +static void * +t_next(struct seq_file *m, void *v, loff_t *pos) +{ + struct ftrace_iterator *iter = m->private; + struct ftrace_ops *ops = iter->ops; + struct dyn_ftrace *rec = NULL; + + if (unlikely(ftrace_disabled)) + return NULL; + + if (iter->flags & FTRACE_ITER_HASH) + return t_hash_next(m, pos); + + (*pos)++; + iter->pos = iter->func_pos = *pos; + + if (iter->flags & FTRACE_ITER_PRINTALL) + return t_hash_start(m, pos); + + retry: + if (iter->idx >= iter->pg->index) { + if (iter->pg->next) { + iter->pg = iter->pg->next; + iter->idx = 0; + goto retry; + } + } else { + rec = &iter->pg->records[iter->idx++]; + if (((iter->flags & FTRACE_ITER_FILTER) && + !(ftrace_lookup_ip(ops->func_hash->filter_hash, rec->ip))) || + + ((iter->flags & FTRACE_ITER_NOTRACE) && + !ftrace_lookup_ip(ops->func_hash->notrace_hash, rec->ip)) || + + ((iter->flags & FTRACE_ITER_ENABLED) && + !(rec->flags & FTRACE_FL_ENABLED))) { + + rec = NULL; + goto retry; + } + } + + if (!rec) + return t_hash_start(m, pos); + + iter->func = rec; + + return iter; +} + +static void reset_iter_read(struct ftrace_iterator *iter) +{ + iter->pos = 0; + iter->func_pos = 0; + iter->flags &= ~(FTRACE_ITER_PRINTALL | FTRACE_ITER_HASH); +} + +static void *t_start(struct seq_file *m, loff_t *pos) +{ + struct ftrace_iterator *iter = m->private; + struct ftrace_ops *ops = iter->ops; + void *p = NULL; + loff_t l; + + mutex_lock(&ftrace_lock); + + if (unlikely(ftrace_disabled)) + return NULL; + + /* + * If an lseek was done, then reset and start from beginning. + */ + if (*pos < iter->pos) + reset_iter_read(iter); + + /* + * For set_ftrace_filter reading, if we have the filter + * off, we can short cut and just print out that all + * functions are enabled. + */ + if ((iter->flags & FTRACE_ITER_FILTER && + ftrace_hash_empty(ops->func_hash->filter_hash)) || + (iter->flags & FTRACE_ITER_NOTRACE && + ftrace_hash_empty(ops->func_hash->notrace_hash))) { + if (*pos > 0) + return t_hash_start(m, pos); + iter->flags |= FTRACE_ITER_PRINTALL; + /* reset in case of seek/pread */ + iter->flags &= ~FTRACE_ITER_HASH; + return iter; + } + + if (iter->flags & FTRACE_ITER_HASH) + return t_hash_start(m, pos); + + /* + * Unfortunately, we need to restart at ftrace_pages_start + * every time we let go of the ftrace_mutex. This is because + * those pointers can change without the lock. + */ + iter->pg = ftrace_pages_start; + iter->idx = 0; + for (l = 0; l <= *pos; ) { + p = t_next(m, p, &l); + if (!p) + break; + } + + if (!p) + return t_hash_start(m, pos); + + return iter; +} + +static void t_stop(struct seq_file *m, void *p) +{ + mutex_unlock(&ftrace_lock); +} + +void * __weak +arch_ftrace_trampoline_func(struct ftrace_ops *ops, struct dyn_ftrace *rec) +{ + return NULL; +} + +static void add_trampoline_func(struct seq_file *m, struct ftrace_ops *ops, + struct dyn_ftrace *rec) +{ + void *ptr; + + ptr = arch_ftrace_trampoline_func(ops, rec); + if (ptr) + seq_printf(m, " ->%pS", ptr); +} + +static int t_show(struct seq_file *m, void *v) +{ + struct ftrace_iterator *iter = m->private; + struct dyn_ftrace *rec; + + if (iter->flags & FTRACE_ITER_HASH) + return t_hash_show(m, iter); + + if (iter->flags & FTRACE_ITER_PRINTALL) { + if (iter->flags & FTRACE_ITER_NOTRACE) + seq_puts(m, "#### no functions disabled ####\n"); + else + seq_puts(m, "#### all functions enabled ####\n"); + return 0; + } + + rec = iter->func; + + if (!rec) + return 0; + + seq_printf(m, "%ps", (void *)rec->ip); + if (iter->flags & FTRACE_ITER_ENABLED) { + struct ftrace_ops *ops = NULL; + + seq_printf(m, " (%ld)%s%s", + ftrace_rec_count(rec), + rec->flags & FTRACE_FL_REGS ? " R" : " ", + rec->flags & FTRACE_FL_IPMODIFY ? " I" : " "); + if (rec->flags & FTRACE_FL_TRAMP_EN) { + ops = ftrace_find_tramp_ops_any(rec); + if (ops) + seq_printf(m, "\ttramp: %pS", + (void *)ops->trampoline); + else + seq_puts(m, "\ttramp: ERROR!"); + + } + add_trampoline_func(m, ops, rec); + } + + seq_putc(m, '\n'); + + return 0; +} + +static const struct seq_operations show_ftrace_seq_ops = { + .start = t_start, + .next = t_next, + .stop = t_stop, + .show = t_show, +}; + +static int +ftrace_avail_open(struct inode *inode, struct file *file) +{ + struct ftrace_iterator *iter; + + if (unlikely(ftrace_disabled)) + return -ENODEV; + + iter = __seq_open_private(file, &show_ftrace_seq_ops, sizeof(*iter)); + if (iter) { + iter->pg = ftrace_pages_start; + iter->ops = &global_ops; + } + + return iter ? 0 : -ENOMEM; +} + +static int +ftrace_enabled_open(struct inode *inode, struct file *file) +{ + struct ftrace_iterator *iter; + + iter = __seq_open_private(file, &show_ftrace_seq_ops, sizeof(*iter)); + if (iter) { + iter->pg = ftrace_pages_start; + iter->flags = FTRACE_ITER_ENABLED; + iter->ops = &global_ops; + } + + return iter ? 0 : -ENOMEM; +} + +/** + * ftrace_regex_open - initialize function tracer filter files + * @ops: The ftrace_ops that hold the hash filters + * @flag: The type of filter to process + * @inode: The inode, usually passed in to your open routine + * @file: The file, usually passed in to your open routine + * + * ftrace_regex_open() initializes the filter files for the + * @ops. Depending on @flag it may process the filter hash or + * the notrace hash of @ops. With this called from the open + * routine, you can use ftrace_filter_write() for the write + * routine if @flag has FTRACE_ITER_FILTER set, or + * ftrace_notrace_write() if @flag has FTRACE_ITER_NOTRACE set. + * tracing_lseek() should be used as the lseek routine, and + * release must call ftrace_regex_release(). + */ +int +ftrace_regex_open(struct ftrace_ops *ops, int flag, + struct inode *inode, struct file *file) +{ + struct ftrace_iterator *iter; + struct ftrace_hash *hash; + int ret = 0; + + ftrace_ops_init(ops); + + if (unlikely(ftrace_disabled)) + return -ENODEV; + + iter = kzalloc(sizeof(*iter), GFP_KERNEL); + if (!iter) + return -ENOMEM; + + if (trace_parser_get_init(&iter->parser, FTRACE_BUFF_MAX)) { + kfree(iter); + return -ENOMEM; + } + + iter->ops = ops; + iter->flags = flag; + + mutex_lock(&ops->func_hash->regex_lock); + + if (flag & FTRACE_ITER_NOTRACE) + hash = ops->func_hash->notrace_hash; + else + hash = ops->func_hash->filter_hash; + + if (file->f_mode & FMODE_WRITE) { + const int size_bits = FTRACE_HASH_DEFAULT_BITS; + + if (file->f_flags & O_TRUNC) + iter->hash = alloc_ftrace_hash(size_bits); + else + iter->hash = alloc_and_copy_ftrace_hash(size_bits, hash); + + if (!iter->hash) { + trace_parser_put(&iter->parser); + kfree(iter); + ret = -ENOMEM; + goto out_unlock; + } + } + + if (file->f_mode & FMODE_READ) { + iter->pg = ftrace_pages_start; + + ret = seq_open(file, &show_ftrace_seq_ops); + if (!ret) { + struct seq_file *m = file->private_data; + m->private = iter; + } else { + /* Failed */ + free_ftrace_hash(iter->hash); + trace_parser_put(&iter->parser); + kfree(iter); + } + } else + file->private_data = iter; + + out_unlock: + mutex_unlock(&ops->func_hash->regex_lock); + + return ret; +} + +static int +ftrace_filter_open(struct inode *inode, struct file *file) +{ + struct ftrace_ops *ops = inode->i_private; + + return ftrace_regex_open(ops, + FTRACE_ITER_FILTER | FTRACE_ITER_DO_HASH, + inode, file); +} + +static int +ftrace_notrace_open(struct inode *inode, struct file *file) +{ + struct ftrace_ops *ops = inode->i_private; + + return ftrace_regex_open(ops, FTRACE_ITER_NOTRACE, + inode, file); +} + +static int ftrace_match(char *str, char *regex, int len, int type) +{ + int matched = 0; + int slen; + + switch (type) { + case MATCH_FULL: + if (strcmp(str, regex) == 0) + matched = 1; + break; + case MATCH_FRONT_ONLY: + if (strncmp(str, regex, len) == 0) + matched = 1; + break; + case MATCH_MIDDLE_ONLY: + if (strstr(str, regex)) + matched = 1; + break; + case MATCH_END_ONLY: + slen = strlen(str); + if (slen >= len && memcmp(str + slen - len, regex, len) == 0) + matched = 1; + break; + } + + return matched; +} + +static int +enter_record(struct ftrace_hash *hash, struct dyn_ftrace *rec, int not) +{ + struct ftrace_func_entry *entry; + int ret = 0; + + entry = ftrace_lookup_ip(hash, rec->ip); + if (not) { + /* Do nothing if it doesn't exist */ + if (!entry) + return 0; + + free_hash_entry(hash, entry); + } else { + /* Do nothing if it exists */ + if (entry) + return 0; + + ret = add_hash_entry(hash, rec->ip); + } + return ret; +} + +static int +ftrace_match_record(struct dyn_ftrace *rec, char *mod, + char *regex, int len, int type) +{ + char str[KSYM_SYMBOL_LEN]; + char *modname; + + kallsyms_lookup(rec->ip, NULL, NULL, &modname, str); + + if (mod) { + /* module lookup requires matching the module */ + if (!modname || strcmp(modname, mod)) + return 0; + + /* blank search means to match all funcs in the mod */ + if (!len) + return 1; + } + + return ftrace_match(str, regex, len, type); +} + +static int +match_records(struct ftrace_hash *hash, char *buff, + int len, char *mod, int not) +{ + unsigned search_len = 0; + struct ftrace_page *pg; + struct dyn_ftrace *rec; + int type = MATCH_FULL; + char *search = buff; + int found = 0; + int ret; + + if (len) { + type = filter_parse_regex(buff, len, &search, ¬); + search_len = strlen(search); + } + + mutex_lock(&ftrace_lock); + + if (unlikely(ftrace_disabled)) + goto out_unlock; + + do_for_each_ftrace_rec(pg, rec) { + if (ftrace_match_record(rec, mod, search, search_len, type)) { + ret = enter_record(hash, rec, not); + if (ret < 0) { + found = ret; + goto out_unlock; + } + found = 1; + } + } while_for_each_ftrace_rec(); + out_unlock: + mutex_unlock(&ftrace_lock); + + return found; +} + +static int +ftrace_match_records(struct ftrace_hash *hash, char *buff, int len) +{ + return match_records(hash, buff, len, NULL, 0); +} + +static int +ftrace_match_module_records(struct ftrace_hash *hash, char *buff, char *mod) +{ + int not = 0; + + /* blank or '*' mean the same */ + if (strcmp(buff, "*") == 0) + buff[0] = 0; + + /* handle the case of 'dont filter this module' */ + if (strcmp(buff, "!") == 0 || strcmp(buff, "!*") == 0) { + buff[0] = 0; + not = 1; + } + + return match_records(hash, buff, strlen(buff), mod, not); +} + +/* + * We register the module command as a template to show others how + * to register the a command as well. + */ + +static int +ftrace_mod_callback(struct ftrace_hash *hash, + char *func, char *cmd, char *param, int enable) +{ + char *mod; + int ret = -EINVAL; + + /* + * cmd == 'mod' because we only registered this func + * for the 'mod' ftrace_func_command. + * But if you register one func with multiple commands, + * you can tell which command was used by the cmd + * parameter. + */ + + /* we must have a module name */ + if (!param) + return ret; + + mod = strsep(¶m, ":"); + if (!strlen(mod)) + return ret; + + ret = ftrace_match_module_records(hash, func, mod); + if (!ret) + ret = -EINVAL; + if (ret < 0) + return ret; + + return 0; +} + +static struct ftrace_func_command ftrace_mod_cmd = { + .name = "mod", + .func = ftrace_mod_callback, +}; + +static int __init ftrace_mod_cmd_init(void) +{ + return register_ftrace_command(&ftrace_mod_cmd); +} +core_initcall(ftrace_mod_cmd_init); + +static void function_trace_probe_call(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct pt_regs *pt_regs) +{ + struct ftrace_func_probe *entry; + struct hlist_head *hhd; + unsigned long key; + + key = hash_long(ip, FTRACE_HASH_BITS); + + hhd = &ftrace_func_hash[key]; + + if (hlist_empty(hhd)) + return; + + /* + * Disable preemption for these calls to prevent a RCU grace + * period. This syncs the hash iteration and freeing of items + * on the hash. rcu_read_lock is too dangerous here. + */ + preempt_disable_notrace(); + hlist_for_each_entry_rcu_notrace(entry, hhd, node) { + if (entry->ip == ip) + entry->ops->func(ip, parent_ip, &entry->data); + } + preempt_enable_notrace(); +} + +static struct ftrace_ops trace_probe_ops __read_mostly = +{ + .func = function_trace_probe_call, + .flags = FTRACE_OPS_FL_INITIALIZED, + INIT_OPS_HASH(trace_probe_ops) +}; + +static int ftrace_probe_registered; + +static void __enable_ftrace_function_probe(struct ftrace_ops_hash *old_hash) +{ + int ret; + int i; + + if (ftrace_probe_registered) { + /* still need to update the function call sites */ + if (ftrace_enabled) + ftrace_run_modify_code(&trace_probe_ops, FTRACE_UPDATE_CALLS, + old_hash); + return; + } + + for (i = 0; i < FTRACE_FUNC_HASHSIZE; i++) { + struct hlist_head *hhd = &ftrace_func_hash[i]; + if (hhd->first) + break; + } + /* Nothing registered? */ + if (i == FTRACE_FUNC_HASHSIZE) + return; + + ret = ftrace_startup(&trace_probe_ops, 0); + + ftrace_probe_registered = 1; +} + +static void __disable_ftrace_function_probe(void) +{ + int i; + + if (!ftrace_probe_registered) + return; + + for (i = 0; i < FTRACE_FUNC_HASHSIZE; i++) { + struct hlist_head *hhd = &ftrace_func_hash[i]; + if (hhd->first) + return; + } + + /* no more funcs left */ + ftrace_shutdown(&trace_probe_ops, 0); + + ftrace_probe_registered = 0; +} + + +static void ftrace_free_entry(struct ftrace_func_probe *entry) +{ + if (entry->ops->free) + entry->ops->free(entry->ops, entry->ip, &entry->data); + kfree(entry); +} + +int +register_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops, + void *data) +{ + struct ftrace_ops_hash old_hash_ops; + struct ftrace_func_probe *entry; + struct ftrace_hash **orig_hash = &trace_probe_ops.func_hash->filter_hash; + struct ftrace_hash *old_hash = *orig_hash; + struct ftrace_hash *hash; + struct ftrace_page *pg; + struct dyn_ftrace *rec; + int type, len, not; + unsigned long key; + int count = 0; + char *search; + int ret; + + type = filter_parse_regex(glob, strlen(glob), &search, ¬); + len = strlen(search); + + /* we do not support '!' for function probes */ + if (WARN_ON(not)) + return -EINVAL; + + mutex_lock(&trace_probe_ops.func_hash->regex_lock); + + old_hash_ops.filter_hash = old_hash; + /* Probes only have filters */ + old_hash_ops.notrace_hash = NULL; + + hash = alloc_and_copy_ftrace_hash(FTRACE_HASH_DEFAULT_BITS, old_hash); + if (!hash) { + count = -ENOMEM; + goto out; + } + + if (unlikely(ftrace_disabled)) { + count = -ENODEV; + goto out; + } + + mutex_lock(&ftrace_lock); + + do_for_each_ftrace_rec(pg, rec) { + + if (!ftrace_match_record(rec, NULL, search, len, type)) + continue; + + entry = kmalloc(sizeof(*entry), GFP_KERNEL); + if (!entry) { + /* If we did not process any, then return error */ + if (!count) + count = -ENOMEM; + goto out_unlock; + } + + count++; + + entry->data = data; + + /* + * The caller might want to do something special + * for each function we find. We call the callback + * to give the caller an opportunity to do so. + */ + if (ops->init) { + if (ops->init(ops, rec->ip, &entry->data) < 0) { + /* caller does not like this func */ + kfree(entry); + continue; + } + } + + ret = enter_record(hash, rec, 0); + if (ret < 0) { + kfree(entry); + count = ret; + goto out_unlock; + } + + entry->ops = ops; + entry->ip = rec->ip; + + key = hash_long(entry->ip, FTRACE_HASH_BITS); + hlist_add_head_rcu(&entry->node, &ftrace_func_hash[key]); + + } while_for_each_ftrace_rec(); + + ret = ftrace_hash_move(&trace_probe_ops, 1, orig_hash, hash); + + __enable_ftrace_function_probe(&old_hash_ops); + + if (!ret) + free_ftrace_hash_rcu(old_hash); + else + count = ret; + + out_unlock: + mutex_unlock(&ftrace_lock); + out: + mutex_unlock(&trace_probe_ops.func_hash->regex_lock); + free_ftrace_hash(hash); + + return count; +} + +enum { + PROBE_TEST_FUNC = 1, + PROBE_TEST_DATA = 2 +}; + +static void +__unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops, + void *data, int flags) +{ + struct ftrace_func_entry *rec_entry; + struct ftrace_func_probe *entry; + struct ftrace_func_probe *p; + struct ftrace_hash **orig_hash = &trace_probe_ops.func_hash->filter_hash; + struct ftrace_hash *old_hash = *orig_hash; + struct list_head free_list; + struct ftrace_hash *hash; + struct hlist_node *tmp; + char str[KSYM_SYMBOL_LEN]; + int type = MATCH_FULL; + int i, len = 0; + char *search; + int ret; + + if (glob && (strcmp(glob, "*") == 0 || !strlen(glob))) + glob = NULL; + else if (glob) { + int not; + + type = filter_parse_regex(glob, strlen(glob), &search, ¬); + len = strlen(search); + + /* we do not support '!' for function probes */ + if (WARN_ON(not)) + return; + } + + mutex_lock(&trace_probe_ops.func_hash->regex_lock); + + hash = alloc_and_copy_ftrace_hash(FTRACE_HASH_DEFAULT_BITS, *orig_hash); + if (!hash) + /* Hmm, should report this somehow */ + goto out_unlock; + + INIT_LIST_HEAD(&free_list); + + for (i = 0; i < FTRACE_FUNC_HASHSIZE; i++) { + struct hlist_head *hhd = &ftrace_func_hash[i]; + + hlist_for_each_entry_safe(entry, tmp, hhd, node) { + + /* break up if statements for readability */ + if ((flags & PROBE_TEST_FUNC) && entry->ops != ops) + continue; + + if ((flags & PROBE_TEST_DATA) && entry->data != data) + continue; + + /* do this last, since it is the most expensive */ + if (glob) { + kallsyms_lookup(entry->ip, NULL, NULL, + NULL, str); + if (!ftrace_match(str, glob, len, type)) + continue; + } + + rec_entry = ftrace_lookup_ip(hash, entry->ip); + /* It is possible more than one entry had this ip */ + if (rec_entry) + free_hash_entry(hash, rec_entry); + + hlist_del_rcu(&entry->node); + list_add(&entry->free_list, &free_list); + } + } + mutex_lock(&ftrace_lock); + __disable_ftrace_function_probe(); + /* + * Remove after the disable is called. Otherwise, if the last + * probe is removed, a null hash means *all enabled*. + */ + ret = ftrace_hash_move(&trace_probe_ops, 1, orig_hash, hash); + synchronize_sched(); + if (!ret) + free_ftrace_hash_rcu(old_hash); + + list_for_each_entry_safe(entry, p, &free_list, free_list) { + list_del(&entry->free_list); + ftrace_free_entry(entry); + } + mutex_unlock(&ftrace_lock); + + out_unlock: + mutex_unlock(&trace_probe_ops.func_hash->regex_lock); + free_ftrace_hash(hash); +} + +void +unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops, + void *data) +{ + __unregister_ftrace_function_probe(glob, ops, data, + PROBE_TEST_FUNC | PROBE_TEST_DATA); +} + +void +unregister_ftrace_function_probe_func(char *glob, struct ftrace_probe_ops *ops) +{ + __unregister_ftrace_function_probe(glob, ops, NULL, PROBE_TEST_FUNC); +} + +void unregister_ftrace_function_probe_all(char *glob) +{ + __unregister_ftrace_function_probe(glob, NULL, NULL, 0); +} + +static LIST_HEAD(ftrace_commands); +static DEFINE_MUTEX(ftrace_cmd_mutex); + +/* + * Currently we only register ftrace commands from __init, so mark this + * __init too. + */ +__init int register_ftrace_command(struct ftrace_func_command *cmd) +{ + struct ftrace_func_command *p; + int ret = 0; + + mutex_lock(&ftrace_cmd_mutex); + list_for_each_entry(p, &ftrace_commands, list) { + if (strcmp(cmd->name, p->name) == 0) { + ret = -EBUSY; + goto out_unlock; + } + } + list_add(&cmd->list, &ftrace_commands); + out_unlock: + mutex_unlock(&ftrace_cmd_mutex); + + return ret; +} + +/* + * Currently we only unregister ftrace commands from __init, so mark + * this __init too. + */ +__init int unregister_ftrace_command(struct ftrace_func_command *cmd) +{ + struct ftrace_func_command *p, *n; + int ret = -ENODEV; + + mutex_lock(&ftrace_cmd_mutex); + list_for_each_entry_safe(p, n, &ftrace_commands, list) { + if (strcmp(cmd->name, p->name) == 0) { + ret = 0; + list_del_init(&p->list); + goto out_unlock; + } + } + out_unlock: + mutex_unlock(&ftrace_cmd_mutex); + + return ret; +} + +static int ftrace_process_regex(struct ftrace_hash *hash, + char *buff, int len, int enable) +{ + char *func, *command, *next = buff; + struct ftrace_func_command *p; + int ret = -EINVAL; + + func = strsep(&next, ":"); + + if (!next) { + ret = ftrace_match_records(hash, func, len); + if (!ret) + ret = -EINVAL; + if (ret < 0) + return ret; + return 0; + } + + /* command found */ + + command = strsep(&next, ":"); + + mutex_lock(&ftrace_cmd_mutex); + list_for_each_entry(p, &ftrace_commands, list) { + if (strcmp(p->name, command) == 0) { + ret = p->func(hash, func, command, next, enable); + goto out_unlock; + } + } + out_unlock: + mutex_unlock(&ftrace_cmd_mutex); + + return ret; +} + +static ssize_t +ftrace_regex_write(struct file *file, const char __user *ubuf, + size_t cnt, loff_t *ppos, int enable) +{ + struct ftrace_iterator *iter; + struct trace_parser *parser; + ssize_t ret, read; + + if (!cnt) + return 0; + + if (file->f_mode & FMODE_READ) { + struct seq_file *m = file->private_data; + iter = m->private; + } else + iter = file->private_data; + + if (unlikely(ftrace_disabled)) + return -ENODEV; + + /* iter->hash is a local copy, so we don't need regex_lock */ + + parser = &iter->parser; + read = trace_get_user(parser, ubuf, cnt, ppos); + + if (read >= 0 && trace_parser_loaded(parser) && + !trace_parser_cont(parser)) { + ret = ftrace_process_regex(iter->hash, parser->buffer, + parser->idx, enable); + trace_parser_clear(parser); + if (ret < 0) + goto out; + } + + ret = read; + out: + return ret; +} + +ssize_t +ftrace_filter_write(struct file *file, const char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + return ftrace_regex_write(file, ubuf, cnt, ppos, 1); +} + +ssize_t +ftrace_notrace_write(struct file *file, const char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + return ftrace_regex_write(file, ubuf, cnt, ppos, 0); +} + +static int +ftrace_match_addr(struct ftrace_hash *hash, unsigned long ip, int remove) +{ + struct ftrace_func_entry *entry; + + if (!ftrace_location(ip)) + return -EINVAL; + + if (remove) { + entry = ftrace_lookup_ip(hash, ip); + if (!entry) + return -ENOENT; + free_hash_entry(hash, entry); + return 0; + } + + return add_hash_entry(hash, ip); +} + +static void ftrace_ops_update_code(struct ftrace_ops *ops, + struct ftrace_ops_hash *old_hash) +{ + struct ftrace_ops *op; + + if (!ftrace_enabled) + return; + + if (ops->flags & FTRACE_OPS_FL_ENABLED) { + ftrace_run_modify_code(ops, FTRACE_UPDATE_CALLS, old_hash); + return; + } + + /* + * If this is the shared global_ops filter, then we need to + * check if there is another ops that shares it, is enabled. + * If so, we still need to run the modify code. + */ + if (ops->func_hash != &global_ops.local_hash) + return; + + do_for_each_ftrace_op(op, ftrace_ops_list) { + if (op->func_hash == &global_ops.local_hash && + op->flags & FTRACE_OPS_FL_ENABLED) { + ftrace_run_modify_code(op, FTRACE_UPDATE_CALLS, old_hash); + /* Only need to do this once */ + return; + } + } while_for_each_ftrace_op(op); +} + +static int +ftrace_set_hash(struct ftrace_ops *ops, unsigned char *buf, int len, + unsigned long ip, int remove, int reset, int enable) +{ + struct ftrace_hash **orig_hash; + struct ftrace_ops_hash old_hash_ops; + struct ftrace_hash *old_hash; + struct ftrace_hash *hash; + int ret; + + if (unlikely(ftrace_disabled)) + return -ENODEV; + + mutex_lock(&ops->func_hash->regex_lock); + + if (enable) + orig_hash = &ops->func_hash->filter_hash; + else + orig_hash = &ops->func_hash->notrace_hash; + + if (reset) + hash = alloc_ftrace_hash(FTRACE_HASH_DEFAULT_BITS); + else + hash = alloc_and_copy_ftrace_hash(FTRACE_HASH_DEFAULT_BITS, *orig_hash); + + if (!hash) { + ret = -ENOMEM; + goto out_regex_unlock; + } + + if (buf && !ftrace_match_records(hash, buf, len)) { + ret = -EINVAL; + goto out_regex_unlock; + } + if (ip) { + ret = ftrace_match_addr(hash, ip, remove); + if (ret < 0) + goto out_regex_unlock; + } + + mutex_lock(&ftrace_lock); + old_hash = *orig_hash; + old_hash_ops.filter_hash = ops->func_hash->filter_hash; + old_hash_ops.notrace_hash = ops->func_hash->notrace_hash; + ret = ftrace_hash_move(ops, enable, orig_hash, hash); + if (!ret) { + ftrace_ops_update_code(ops, &old_hash_ops); + free_ftrace_hash_rcu(old_hash); + } + mutex_unlock(&ftrace_lock); + + out_regex_unlock: + mutex_unlock(&ops->func_hash->regex_lock); + + free_ftrace_hash(hash); + return ret; +} + +static int +ftrace_set_addr(struct ftrace_ops *ops, unsigned long ip, int remove, + int reset, int enable) +{ + return ftrace_set_hash(ops, 0, 0, ip, remove, reset, enable); +} + +/** + * ftrace_set_filter_ip - set a function to filter on in ftrace by address + * @ops - the ops to set the filter with + * @ip - the address to add to or remove from the filter. + * @remove - non zero to remove the ip from the filter + * @reset - non zero to reset all filters before applying this filter. + * + * Filters denote which functions should be enabled when tracing is enabled + * If @ip is NULL, it failes to update filter. + */ +int ftrace_set_filter_ip(struct ftrace_ops *ops, unsigned long ip, + int remove, int reset) +{ + ftrace_ops_init(ops); + return ftrace_set_addr(ops, ip, remove, reset, 1); +} +EXPORT_SYMBOL_GPL(ftrace_set_filter_ip); + +static int +ftrace_set_regex(struct ftrace_ops *ops, unsigned char *buf, int len, + int reset, int enable) +{ + return ftrace_set_hash(ops, buf, len, 0, 0, reset, enable); +} + +/** + * ftrace_set_filter - set a function to filter on in ftrace + * @ops - the ops to set the filter with + * @buf - the string that holds the function filter text. + * @len - the length of the string. + * @reset - non zero to reset all filters before applying this filter. + * + * Filters denote which functions should be enabled when tracing is enabled. + * If @buf is NULL and reset is set, all functions will be enabled for tracing. + */ +int ftrace_set_filter(struct ftrace_ops *ops, unsigned char *buf, + int len, int reset) +{ + ftrace_ops_init(ops); + return ftrace_set_regex(ops, buf, len, reset, 1); +} +EXPORT_SYMBOL_GPL(ftrace_set_filter); + +/** + * ftrace_set_notrace - set a function to not trace in ftrace + * @ops - the ops to set the notrace filter with + * @buf - the string that holds the function notrace text. + * @len - the length of the string. + * @reset - non zero to reset all filters before applying this filter. + * + * Notrace Filters denote which functions should not be enabled when tracing + * is enabled. If @buf is NULL and reset is set, all functions will be enabled + * for tracing. + */ +int ftrace_set_notrace(struct ftrace_ops *ops, unsigned char *buf, + int len, int reset) +{ + ftrace_ops_init(ops); + return ftrace_set_regex(ops, buf, len, reset, 0); +} +EXPORT_SYMBOL_GPL(ftrace_set_notrace); +/** + * ftrace_set_global_filter - set a function to filter on with global tracers + * @buf - the string that holds the function filter text. + * @len - the length of the string. + * @reset - non zero to reset all filters before applying this filter. + * + * Filters denote which functions should be enabled when tracing is enabled. + * If @buf is NULL and reset is set, all functions will be enabled for tracing. + */ +void ftrace_set_global_filter(unsigned char *buf, int len, int reset) +{ + ftrace_set_regex(&global_ops, buf, len, reset, 1); +} +EXPORT_SYMBOL_GPL(ftrace_set_global_filter); + +/** + * ftrace_set_global_notrace - set a function to not trace with global tracers + * @buf - the string that holds the function notrace text. + * @len - the length of the string. + * @reset - non zero to reset all filters before applying this filter. + * + * Notrace Filters denote which functions should not be enabled when tracing + * is enabled. If @buf is NULL and reset is set, all functions will be enabled + * for tracing. + */ +void ftrace_set_global_notrace(unsigned char *buf, int len, int reset) +{ + ftrace_set_regex(&global_ops, buf, len, reset, 0); +} +EXPORT_SYMBOL_GPL(ftrace_set_global_notrace); + +/* + * command line interface to allow users to set filters on boot up. + */ +#define FTRACE_FILTER_SIZE COMMAND_LINE_SIZE +static char ftrace_notrace_buf[FTRACE_FILTER_SIZE] __initdata; +static char ftrace_filter_buf[FTRACE_FILTER_SIZE] __initdata; + +/* Used by function selftest to not test if filter is set */ +bool ftrace_filter_param __initdata; + +static int __init set_ftrace_notrace(char *str) +{ + ftrace_filter_param = true; + strlcpy(ftrace_notrace_buf, str, FTRACE_FILTER_SIZE); + return 1; +} +__setup("ftrace_notrace=", set_ftrace_notrace); + +static int __init set_ftrace_filter(char *str) +{ + ftrace_filter_param = true; + strlcpy(ftrace_filter_buf, str, FTRACE_FILTER_SIZE); + return 1; +} +__setup("ftrace_filter=", set_ftrace_filter); + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER +static char ftrace_graph_buf[FTRACE_FILTER_SIZE] __initdata; +static char ftrace_graph_notrace_buf[FTRACE_FILTER_SIZE] __initdata; +static int ftrace_set_func(unsigned long *array, int *idx, int size, char *buffer); + +static unsigned long save_global_trampoline; +static unsigned long save_global_flags; + +static int __init set_graph_function(char *str) +{ + strlcpy(ftrace_graph_buf, str, FTRACE_FILTER_SIZE); + return 1; +} +__setup("ftrace_graph_filter=", set_graph_function); + +static int __init set_graph_notrace_function(char *str) +{ + strlcpy(ftrace_graph_notrace_buf, str, FTRACE_FILTER_SIZE); + return 1; +} +__setup("ftrace_graph_notrace=", set_graph_notrace_function); + +static void __init set_ftrace_early_graph(char *buf, int enable) +{ + int ret; + char *func; + unsigned long *table = ftrace_graph_funcs; + int *count = &ftrace_graph_count; + + if (!enable) { + table = ftrace_graph_notrace_funcs; + count = &ftrace_graph_notrace_count; + } + + while (buf) { + func = strsep(&buf, ","); + /* we allow only one expression at a time */ + ret = ftrace_set_func(table, count, FTRACE_GRAPH_MAX_FUNCS, func); + if (ret) + printk(KERN_DEBUG "ftrace: function %s not " + "traceable\n", func); + } +} +#endif /* CONFIG_FUNCTION_GRAPH_TRACER */ + +void __init +ftrace_set_early_filter(struct ftrace_ops *ops, char *buf, int enable) +{ + char *func; + + ftrace_ops_init(ops); + + while (buf) { + func = strsep(&buf, ","); + ftrace_set_regex(ops, func, strlen(func), 0, enable); + } +} + +static void __init set_ftrace_early_filters(void) +{ + if (ftrace_filter_buf[0]) + ftrace_set_early_filter(&global_ops, ftrace_filter_buf, 1); + if (ftrace_notrace_buf[0]) + ftrace_set_early_filter(&global_ops, ftrace_notrace_buf, 0); +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + if (ftrace_graph_buf[0]) + set_ftrace_early_graph(ftrace_graph_buf, 1); + if (ftrace_graph_notrace_buf[0]) + set_ftrace_early_graph(ftrace_graph_notrace_buf, 0); +#endif /* CONFIG_FUNCTION_GRAPH_TRACER */ +} + +int ftrace_regex_release(struct inode *inode, struct file *file) +{ + struct seq_file *m = (struct seq_file *)file->private_data; + struct ftrace_ops_hash old_hash_ops; + struct ftrace_iterator *iter; + struct ftrace_hash **orig_hash; + struct ftrace_hash *old_hash; + struct trace_parser *parser; + int filter_hash; + int ret; + + if (file->f_mode & FMODE_READ) { + iter = m->private; + seq_release(inode, file); + } else + iter = file->private_data; + + parser = &iter->parser; + if (trace_parser_loaded(parser)) { + parser->buffer[parser->idx] = 0; + ftrace_match_records(iter->hash, parser->buffer, parser->idx); + } + + trace_parser_put(parser); + + mutex_lock(&iter->ops->func_hash->regex_lock); + + if (file->f_mode & FMODE_WRITE) { + filter_hash = !!(iter->flags & FTRACE_ITER_FILTER); + + if (filter_hash) + orig_hash = &iter->ops->func_hash->filter_hash; + else + orig_hash = &iter->ops->func_hash->notrace_hash; + + mutex_lock(&ftrace_lock); + old_hash = *orig_hash; + old_hash_ops.filter_hash = iter->ops->func_hash->filter_hash; + old_hash_ops.notrace_hash = iter->ops->func_hash->notrace_hash; + ret = ftrace_hash_move(iter->ops, filter_hash, + orig_hash, iter->hash); + if (!ret) { + ftrace_ops_update_code(iter->ops, &old_hash_ops); + free_ftrace_hash_rcu(old_hash); + } + mutex_unlock(&ftrace_lock); + } + + mutex_unlock(&iter->ops->func_hash->regex_lock); + free_ftrace_hash(iter->hash); + kfree(iter); + + return 0; +} + +static const struct file_operations ftrace_avail_fops = { + .open = ftrace_avail_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release_private, +}; + +static const struct file_operations ftrace_enabled_fops = { + .open = ftrace_enabled_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release_private, +}; + +static const struct file_operations ftrace_filter_fops = { + .open = ftrace_filter_open, + .read = seq_read, + .write = ftrace_filter_write, + .llseek = tracing_lseek, + .release = ftrace_regex_release, +}; + +static const struct file_operations ftrace_notrace_fops = { + .open = ftrace_notrace_open, + .read = seq_read, + .write = ftrace_notrace_write, + .llseek = tracing_lseek, + .release = ftrace_regex_release, +}; + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + +static DEFINE_MUTEX(graph_lock); + +int ftrace_graph_count; +int ftrace_graph_notrace_count; +unsigned long ftrace_graph_funcs[FTRACE_GRAPH_MAX_FUNCS] __read_mostly; +unsigned long ftrace_graph_notrace_funcs[FTRACE_GRAPH_MAX_FUNCS] __read_mostly; + +struct ftrace_graph_data { + unsigned long *table; + size_t size; + int *count; + const struct seq_operations *seq_ops; +}; + +static void * +__g_next(struct seq_file *m, loff_t *pos) +{ + struct ftrace_graph_data *fgd = m->private; + + if (*pos >= *fgd->count) + return NULL; + return &fgd->table[*pos]; +} + +static void * +g_next(struct seq_file *m, void *v, loff_t *pos) +{ + (*pos)++; + return __g_next(m, pos); +} + +static void *g_start(struct seq_file *m, loff_t *pos) +{ + struct ftrace_graph_data *fgd = m->private; + + mutex_lock(&graph_lock); + + /* Nothing, tell g_show to print all functions are enabled */ + if (!*fgd->count && !*pos) + return (void *)1; + + return __g_next(m, pos); +} + +static void g_stop(struct seq_file *m, void *p) +{ + mutex_unlock(&graph_lock); +} + +static int g_show(struct seq_file *m, void *v) +{ + unsigned long *ptr = v; + + if (!ptr) + return 0; + + if (ptr == (unsigned long *)1) { + struct ftrace_graph_data *fgd = m->private; + + if (fgd->table == ftrace_graph_funcs) + seq_puts(m, "#### all functions enabled ####\n"); + else + seq_puts(m, "#### no functions disabled ####\n"); + return 0; + } + + seq_printf(m, "%ps\n", (void *)*ptr); + + return 0; +} + +static const struct seq_operations ftrace_graph_seq_ops = { + .start = g_start, + .next = g_next, + .stop = g_stop, + .show = g_show, +}; + +static int +__ftrace_graph_open(struct inode *inode, struct file *file, + struct ftrace_graph_data *fgd) +{ + int ret = 0; + + mutex_lock(&graph_lock); + if ((file->f_mode & FMODE_WRITE) && + (file->f_flags & O_TRUNC)) { + *fgd->count = 0; + memset(fgd->table, 0, fgd->size * sizeof(*fgd->table)); + } + mutex_unlock(&graph_lock); + + if (file->f_mode & FMODE_READ) { + ret = seq_open(file, fgd->seq_ops); + if (!ret) { + struct seq_file *m = file->private_data; + m->private = fgd; + } + } else + file->private_data = fgd; + + return ret; +} + +static int +ftrace_graph_open(struct inode *inode, struct file *file) +{ + struct ftrace_graph_data *fgd; + + if (unlikely(ftrace_disabled)) + return -ENODEV; + + fgd = kmalloc(sizeof(*fgd), GFP_KERNEL); + if (fgd == NULL) + return -ENOMEM; + + fgd->table = ftrace_graph_funcs; + fgd->size = FTRACE_GRAPH_MAX_FUNCS; + fgd->count = &ftrace_graph_count; + fgd->seq_ops = &ftrace_graph_seq_ops; + + return __ftrace_graph_open(inode, file, fgd); +} + +static int +ftrace_graph_notrace_open(struct inode *inode, struct file *file) +{ + struct ftrace_graph_data *fgd; + + if (unlikely(ftrace_disabled)) + return -ENODEV; + + fgd = kmalloc(sizeof(*fgd), GFP_KERNEL); + if (fgd == NULL) + return -ENOMEM; + + fgd->table = ftrace_graph_notrace_funcs; + fgd->size = FTRACE_GRAPH_MAX_FUNCS; + fgd->count = &ftrace_graph_notrace_count; + fgd->seq_ops = &ftrace_graph_seq_ops; + + return __ftrace_graph_open(inode, file, fgd); +} + +static int +ftrace_graph_release(struct inode *inode, struct file *file) +{ + if (file->f_mode & FMODE_READ) { + struct seq_file *m = file->private_data; + + kfree(m->private); + seq_release(inode, file); + } else { + kfree(file->private_data); + } + + return 0; +} + +static int +ftrace_set_func(unsigned long *array, int *idx, int size, char *buffer) +{ + struct dyn_ftrace *rec; + struct ftrace_page *pg; + int search_len; + int fail = 1; + int type, not; + char *search; + bool exists; + int i; + + /* decode regex */ + type = filter_parse_regex(buffer, strlen(buffer), &search, ¬); + if (!not && *idx >= size) + return -EBUSY; + + search_len = strlen(search); + + mutex_lock(&ftrace_lock); + + if (unlikely(ftrace_disabled)) { + mutex_unlock(&ftrace_lock); + return -ENODEV; + } + + do_for_each_ftrace_rec(pg, rec) { + + if (ftrace_match_record(rec, NULL, search, search_len, type)) { + /* if it is in the array */ + exists = false; + for (i = 0; i < *idx; i++) { + if (array[i] == rec->ip) { + exists = true; + break; + } + } + + if (!not) { + fail = 0; + if (!exists) { + array[(*idx)++] = rec->ip; + if (*idx >= size) + goto out; + } + } else { + if (exists) { + array[i] = array[--(*idx)]; + array[*idx] = 0; + fail = 0; + } + } + } + } while_for_each_ftrace_rec(); +out: + mutex_unlock(&ftrace_lock); + + if (fail) + return -EINVAL; + + return 0; +} + +static ssize_t +ftrace_graph_write(struct file *file, const char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + struct trace_parser parser; + ssize_t read, ret = 0; + struct ftrace_graph_data *fgd = file->private_data; + + if (!cnt) + return 0; + + if (trace_parser_get_init(&parser, FTRACE_BUFF_MAX)) + return -ENOMEM; + + read = trace_get_user(&parser, ubuf, cnt, ppos); + + if (read >= 0 && trace_parser_loaded((&parser))) { + parser.buffer[parser.idx] = 0; + + mutex_lock(&graph_lock); + + /* we allow only one expression at a time */ + ret = ftrace_set_func(fgd->table, fgd->count, fgd->size, + parser.buffer); + + mutex_unlock(&graph_lock); + } + + if (!ret) + ret = read; + + trace_parser_put(&parser); + + return ret; +} + +static const struct file_operations ftrace_graph_fops = { + .open = ftrace_graph_open, + .read = seq_read, + .write = ftrace_graph_write, + .llseek = tracing_lseek, + .release = ftrace_graph_release, +}; + +static const struct file_operations ftrace_graph_notrace_fops = { + .open = ftrace_graph_notrace_open, + .read = seq_read, + .write = ftrace_graph_write, + .llseek = tracing_lseek, + .release = ftrace_graph_release, +}; +#endif /* CONFIG_FUNCTION_GRAPH_TRACER */ + +void ftrace_create_filter_files(struct ftrace_ops *ops, + struct dentry *parent) +{ + + trace_create_file("set_ftrace_filter", 0644, parent, + ops, &ftrace_filter_fops); + + trace_create_file("set_ftrace_notrace", 0644, parent, + ops, &ftrace_notrace_fops); +} + +/* + * The name "destroy_filter_files" is really a misnomer. Although + * in the future, it may actualy delete the files, but this is + * really intended to make sure the ops passed in are disabled + * and that when this function returns, the caller is free to + * free the ops. + * + * The "destroy" name is only to match the "create" name that this + * should be paired with. + */ +void ftrace_destroy_filter_files(struct ftrace_ops *ops) +{ + mutex_lock(&ftrace_lock); + if (ops->flags & FTRACE_OPS_FL_ENABLED) + ftrace_shutdown(ops, 0); + ops->flags |= FTRACE_OPS_FL_DELETED; + mutex_unlock(&ftrace_lock); +} + +static __init int ftrace_init_dyn_tracefs(struct dentry *d_tracer) +{ + + trace_create_file("available_filter_functions", 0444, + d_tracer, NULL, &ftrace_avail_fops); + + trace_create_file("enabled_functions", 0444, + d_tracer, NULL, &ftrace_enabled_fops); + + ftrace_create_filter_files(&global_ops, d_tracer); + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + trace_create_file("set_graph_function", 0444, d_tracer, + NULL, + &ftrace_graph_fops); + trace_create_file("set_graph_notrace", 0444, d_tracer, + NULL, + &ftrace_graph_notrace_fops); +#endif /* CONFIG_FUNCTION_GRAPH_TRACER */ + + return 0; +} + +static int ftrace_cmp_ips(const void *a, const void *b) +{ + const unsigned long *ipa = a; + const unsigned long *ipb = b; + + if (*ipa > *ipb) + return 1; + if (*ipa < *ipb) + return -1; + return 0; +} + +static void ftrace_swap_ips(void *a, void *b, int size) +{ + unsigned long *ipa = a; + unsigned long *ipb = b; + unsigned long t; + + t = *ipa; + *ipa = *ipb; + *ipb = t; +} + +static int ftrace_process_locs(struct module *mod, + unsigned long *start, + unsigned long *end) +{ + struct ftrace_page *start_pg; + struct ftrace_page *pg; + struct dyn_ftrace *rec; + unsigned long count; + unsigned long *p; + unsigned long addr; + unsigned long flags = 0; /* Shut up gcc */ + int ret = -ENOMEM; + + count = end - start; + + if (!count) + return 0; + + sort(start, count, sizeof(*start), + ftrace_cmp_ips, ftrace_swap_ips); + + start_pg = ftrace_allocate_pages(count); + if (!start_pg) + return -ENOMEM; + + mutex_lock(&ftrace_lock); + + /* + * Core and each module needs their own pages, as + * modules will free them when they are removed. + * Force a new page to be allocated for modules. + */ + if (!mod) { + WARN_ON(ftrace_pages || ftrace_pages_start); + /* First initialization */ + ftrace_pages = ftrace_pages_start = start_pg; + } else { + if (!ftrace_pages) + goto out; + + if (WARN_ON(ftrace_pages->next)) { + /* Hmm, we have free pages? */ + while (ftrace_pages->next) + ftrace_pages = ftrace_pages->next; + } + + ftrace_pages->next = start_pg; + } + + p = start; + pg = start_pg; + while (p < end) { + addr = ftrace_call_adjust(*p++); + /* + * Some architecture linkers will pad between + * the different mcount_loc sections of different + * object files to satisfy alignments. + * Skip any NULL pointers. + */ + if (!addr) + continue; + + if (pg->index == pg->size) { + /* We should have allocated enough */ + if (WARN_ON(!pg->next)) + break; + pg = pg->next; + } + + rec = &pg->records[pg->index++]; + rec->ip = addr; + } + + /* We should have used all pages */ + WARN_ON(pg->next); + + /* Assign the last page to ftrace_pages */ + ftrace_pages = pg; + + /* + * We only need to disable interrupts on start up + * because we are modifying code that an interrupt + * may execute, and the modification is not atomic. + * But for modules, nothing runs the code we modify + * until we are finished with it, and there's no + * reason to cause large interrupt latencies while we do it. + */ + if (!mod) + local_irq_save(flags); + ftrace_update_code(mod, start_pg); + if (!mod) + local_irq_restore(flags); + ret = 0; + out: + mutex_unlock(&ftrace_lock); + + return ret; +} + +#ifdef CONFIG_MODULES + +#define next_to_ftrace_page(p) container_of(p, struct ftrace_page, next) + +void ftrace_release_mod(struct module *mod) +{ + struct dyn_ftrace *rec; + struct ftrace_page **last_pg; + struct ftrace_page *pg; + int order; + + mutex_lock(&ftrace_lock); + + if (ftrace_disabled) + goto out_unlock; + + /* + * Each module has its own ftrace_pages, remove + * them from the list. + */ + last_pg = &ftrace_pages_start; + for (pg = ftrace_pages_start; pg; pg = *last_pg) { + rec = &pg->records[0]; + if (within_module_core(rec->ip, mod)) { + /* + * As core pages are first, the first + * page should never be a module page. + */ + if (WARN_ON(pg == ftrace_pages_start)) + goto out_unlock; + + /* Check if we are deleting the last page */ + if (pg == ftrace_pages) + ftrace_pages = next_to_ftrace_page(last_pg); + + *last_pg = pg->next; + order = get_count_order(pg->size / ENTRIES_PER_PAGE); + free_pages((unsigned long)pg->records, order); + kfree(pg); + } else + last_pg = &pg->next; + } + out_unlock: + mutex_unlock(&ftrace_lock); +} + +static void ftrace_init_module(struct module *mod, + unsigned long *start, unsigned long *end) +{ + if (ftrace_disabled || start == end) + return; + ftrace_process_locs(mod, start, end); +} + +void ftrace_module_init(struct module *mod) +{ + ftrace_init_module(mod, mod->ftrace_callsites, + mod->ftrace_callsites + + mod->num_ftrace_callsites); +} + +static int ftrace_module_notify_exit(struct notifier_block *self, + unsigned long val, void *data) +{ + struct module *mod = data; + + if (val == MODULE_STATE_GOING) + ftrace_release_mod(mod); + + return 0; +} +#else +static int ftrace_module_notify_exit(struct notifier_block *self, + unsigned long val, void *data) +{ + return 0; +} +#endif /* CONFIG_MODULES */ + +struct notifier_block ftrace_module_exit_nb = { + .notifier_call = ftrace_module_notify_exit, + .priority = INT_MIN, /* Run after anything that can remove kprobes */ +}; + +void __init ftrace_init(void) +{ + extern unsigned long __start_mcount_loc[]; + extern unsigned long __stop_mcount_loc[]; + unsigned long count, flags; + int ret; + + local_irq_save(flags); + ret = ftrace_dyn_arch_init(); + local_irq_restore(flags); + if (ret) + goto failed; + + count = __stop_mcount_loc - __start_mcount_loc; + if (!count) { + pr_info("ftrace: No functions to be traced?\n"); + goto failed; + } + + pr_info("ftrace: allocating %ld entries in %ld pages\n", + count, count / ENTRIES_PER_PAGE + 1); + + last_ftrace_enabled = ftrace_enabled = 1; + + ret = ftrace_process_locs(NULL, + __start_mcount_loc, + __stop_mcount_loc); + + ret = register_module_notifier(&ftrace_module_exit_nb); + if (ret) + pr_warning("Failed to register trace ftrace module exit notifier\n"); + + set_ftrace_early_filters(); + + return; + failed: + ftrace_disabled = 1; +} + +/* Do nothing if arch does not support this */ +void __weak arch_ftrace_update_trampoline(struct ftrace_ops *ops) +{ +} + +static void ftrace_update_trampoline(struct ftrace_ops *ops) +{ + +/* + * Currently there's no safe way to free a trampoline when the kernel + * is configured with PREEMPT. That is because a task could be preempted + * when it jumped to the trampoline, it may be preempted for a long time + * depending on the system load, and currently there's no way to know + * when it will be off the trampoline. If the trampoline is freed + * too early, when the task runs again, it will be executing on freed + * memory and crash. + */ +#ifdef CONFIG_PREEMPT + /* Currently, only non dynamic ops can have a trampoline */ + if (ops->flags & FTRACE_OPS_FL_DYNAMIC) + return; +#endif + + arch_ftrace_update_trampoline(ops); +} + +#else + +static struct ftrace_ops global_ops = { + .func = ftrace_stub, + .flags = FTRACE_OPS_FL_RECURSION_SAFE | FTRACE_OPS_FL_INITIALIZED, +}; + +static int __init ftrace_nodyn_init(void) +{ + ftrace_enabled = 1; + return 0; +} +core_initcall(ftrace_nodyn_init); + +static inline int ftrace_init_dyn_tracefs(struct dentry *d_tracer) { return 0; } +static inline void ftrace_startup_enable(int command) { } +static inline void ftrace_startup_all(int command) { } +/* Keep as macros so we do not need to define the commands */ +# define ftrace_startup(ops, command) \ + ({ \ + int ___ret = __register_ftrace_function(ops); \ + if (!___ret) \ + (ops)->flags |= FTRACE_OPS_FL_ENABLED; \ + ___ret; \ + }) +# define ftrace_shutdown(ops, command) \ + ({ \ + int ___ret = __unregister_ftrace_function(ops); \ + if (!___ret) \ + (ops)->flags &= ~FTRACE_OPS_FL_ENABLED; \ + ___ret; \ + }) + +# define ftrace_startup_sysctl() do { } while (0) +# define ftrace_shutdown_sysctl() do { } while (0) + +static inline int +ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip, void *regs) +{ + return 1; +} + +static void ftrace_update_trampoline(struct ftrace_ops *ops) +{ +} + +#endif /* CONFIG_DYNAMIC_FTRACE */ + +__init void ftrace_init_global_array_ops(struct trace_array *tr) +{ + tr->ops = &global_ops; + tr->ops->private = tr; +} + +void ftrace_init_array_ops(struct trace_array *tr, ftrace_func_t func) +{ + /* If we filter on pids, update to use the pid function */ + if (tr->flags & TRACE_ARRAY_FL_GLOBAL) { + if (WARN_ON(tr->ops->func != ftrace_stub)) + printk("ftrace ops had %pS for function\n", + tr->ops->func); + /* Only the top level instance does pid tracing */ + if (!list_empty(&ftrace_pids)) { + set_ftrace_pid_function(func); + func = ftrace_pid_func; + } + } + tr->ops->func = func; + tr->ops->private = tr; +} + +void ftrace_reset_array_ops(struct trace_array *tr) +{ + tr->ops->func = ftrace_stub; +} + +static void +ftrace_ops_control_func(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct pt_regs *regs) +{ + if (unlikely(trace_recursion_test(TRACE_CONTROL_BIT))) + return; + + /* + * Some of the ops may be dynamically allocated, + * they must be freed after a synchronize_sched(). + */ + preempt_disable_notrace(); + trace_recursion_set(TRACE_CONTROL_BIT); + + /* + * Control funcs (perf) uses RCU. Only trace if + * RCU is currently active. + */ + if (!rcu_is_watching()) + goto out; + + do_for_each_ftrace_op(op, ftrace_control_list) { + if (!(op->flags & FTRACE_OPS_FL_STUB) && + !ftrace_function_local_disabled(op) && + ftrace_ops_test(op, ip, regs)) + op->func(ip, parent_ip, op, regs); + } while_for_each_ftrace_op(op); + out: + trace_recursion_clear(TRACE_CONTROL_BIT); + preempt_enable_notrace(); +} + +static struct ftrace_ops control_ops = { + .func = ftrace_ops_control_func, + .flags = FTRACE_OPS_FL_RECURSION_SAFE | FTRACE_OPS_FL_INITIALIZED, + INIT_OPS_HASH(control_ops) +}; + +static inline void +__ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *ignored, struct pt_regs *regs) +{ + struct ftrace_ops *op; + int bit; + + bit = trace_test_and_set_recursion(TRACE_LIST_START, TRACE_LIST_MAX); + if (bit < 0) + return; + + /* + * Some of the ops may be dynamically allocated, + * they must be freed after a synchronize_sched(). + */ + preempt_disable_notrace(); + do_for_each_ftrace_op(op, ftrace_ops_list) { + if (ftrace_ops_test(op, ip, regs)) { + if (FTRACE_WARN_ON(!op->func)) { + pr_warn("op=%p %pS\n", op, op); + goto out; + } + op->func(ip, parent_ip, op, regs); + } + } while_for_each_ftrace_op(op); +out: + preempt_enable_notrace(); + trace_clear_recursion(bit); +} + +/* + * Some archs only support passing ip and parent_ip. Even though + * the list function ignores the op parameter, we do not want any + * C side effects, where a function is called without the caller + * sending a third parameter. + * Archs are to support both the regs and ftrace_ops at the same time. + * If they support ftrace_ops, it is assumed they support regs. + * If call backs want to use regs, they must either check for regs + * being NULL, or CONFIG_DYNAMIC_FTRACE_WITH_REGS. + * Note, CONFIG_DYNAMIC_FTRACE_WITH_REGS expects a full regs to be saved. + * An architecture can pass partial regs with ftrace_ops and still + * set the ARCH_SUPPORT_FTARCE_OPS. + */ +#if ARCH_SUPPORTS_FTRACE_OPS +static void ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct pt_regs *regs) +{ + __ftrace_ops_list_func(ip, parent_ip, NULL, regs); +} +#else +static void ftrace_ops_no_ops(unsigned long ip, unsigned long parent_ip) +{ + __ftrace_ops_list_func(ip, parent_ip, NULL, NULL); +} +#endif + +/* + * If there's only one function registered but it does not support + * recursion, this function will be called by the mcount trampoline. + * This function will handle recursion protection. + */ +static void ftrace_ops_recurs_func(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct pt_regs *regs) +{ + int bit; + + bit = trace_test_and_set_recursion(TRACE_LIST_START, TRACE_LIST_MAX); + if (bit < 0) + return; + + op->func(ip, parent_ip, op, regs); + + trace_clear_recursion(bit); +} + +/** + * ftrace_ops_get_func - get the function a trampoline should call + * @ops: the ops to get the function for + * + * Normally the mcount trampoline will call the ops->func, but there + * are times that it should not. For example, if the ops does not + * have its own recursion protection, then it should call the + * ftrace_ops_recurs_func() instead. + * + * Returns the function that the trampoline should call for @ops. + */ +ftrace_func_t ftrace_ops_get_func(struct ftrace_ops *ops) +{ + /* + * If the func handles its own recursion, call it directly. + * Otherwise call the recursion protected function that + * will call the ftrace ops function. + */ + if (!(ops->flags & FTRACE_OPS_FL_RECURSION_SAFE)) + return ftrace_ops_recurs_func; + + return ops->func; +} + +static void clear_ftrace_swapper(void) +{ + struct task_struct *p; + int cpu; + + get_online_cpus(); + for_each_online_cpu(cpu) { + p = idle_task(cpu); + clear_tsk_trace_trace(p); + } + put_online_cpus(); +} + +static void set_ftrace_swapper(void) +{ + struct task_struct *p; + int cpu; + + get_online_cpus(); + for_each_online_cpu(cpu) { + p = idle_task(cpu); + set_tsk_trace_trace(p); + } + put_online_cpus(); +} + +static void clear_ftrace_pid(struct pid *pid) +{ + struct task_struct *p; + + rcu_read_lock(); + do_each_pid_task(pid, PIDTYPE_PID, p) { + clear_tsk_trace_trace(p); + } while_each_pid_task(pid, PIDTYPE_PID, p); + rcu_read_unlock(); + + put_pid(pid); +} + +static void set_ftrace_pid(struct pid *pid) +{ + struct task_struct *p; + + rcu_read_lock(); + do_each_pid_task(pid, PIDTYPE_PID, p) { + set_tsk_trace_trace(p); + } while_each_pid_task(pid, PIDTYPE_PID, p); + rcu_read_unlock(); +} + +static void clear_ftrace_pid_task(struct pid *pid) +{ + if (pid == ftrace_swapper_pid) + clear_ftrace_swapper(); + else + clear_ftrace_pid(pid); +} + +static void set_ftrace_pid_task(struct pid *pid) +{ + if (pid == ftrace_swapper_pid) + set_ftrace_swapper(); + else + set_ftrace_pid(pid); +} + +static int ftrace_pid_add(int p) +{ + struct pid *pid; + struct ftrace_pid *fpid; + int ret = -EINVAL; + + mutex_lock(&ftrace_lock); + + if (!p) + pid = ftrace_swapper_pid; + else + pid = find_get_pid(p); + + if (!pid) + goto out; + + ret = 0; + + list_for_each_entry(fpid, &ftrace_pids, list) + if (fpid->pid == pid) + goto out_put; + + ret = -ENOMEM; + + fpid = kmalloc(sizeof(*fpid), GFP_KERNEL); + if (!fpid) + goto out_put; + + list_add(&fpid->list, &ftrace_pids); + fpid->pid = pid; + + set_ftrace_pid_task(pid); + + ftrace_update_pid_func(); + + ftrace_startup_all(0); + + mutex_unlock(&ftrace_lock); + return 0; + +out_put: + if (pid != ftrace_swapper_pid) + put_pid(pid); + +out: + mutex_unlock(&ftrace_lock); + return ret; +} + +static void ftrace_pid_reset(void) +{ + struct ftrace_pid *fpid, *safe; + + mutex_lock(&ftrace_lock); + list_for_each_entry_safe(fpid, safe, &ftrace_pids, list) { + struct pid *pid = fpid->pid; + + clear_ftrace_pid_task(pid); + + list_del(&fpid->list); + kfree(fpid); + } + + ftrace_update_pid_func(); + ftrace_startup_all(0); + + mutex_unlock(&ftrace_lock); +} + +static void *fpid_start(struct seq_file *m, loff_t *pos) +{ + mutex_lock(&ftrace_lock); + + if (list_empty(&ftrace_pids) && (!*pos)) + return (void *) 1; + + return seq_list_start(&ftrace_pids, *pos); +} + +static void *fpid_next(struct seq_file *m, void *v, loff_t *pos) +{ + if (v == (void *)1) + return NULL; + + return seq_list_next(v, &ftrace_pids, pos); +} + +static void fpid_stop(struct seq_file *m, void *p) +{ + mutex_unlock(&ftrace_lock); +} + +static int fpid_show(struct seq_file *m, void *v) +{ + const struct ftrace_pid *fpid = list_entry(v, struct ftrace_pid, list); + + if (v == (void *)1) { + seq_puts(m, "no pid\n"); + return 0; + } + + if (fpid->pid == ftrace_swapper_pid) + seq_puts(m, "swapper tasks\n"); + else + seq_printf(m, "%u\n", pid_vnr(fpid->pid)); + + return 0; +} + +static const struct seq_operations ftrace_pid_sops = { + .start = fpid_start, + .next = fpid_next, + .stop = fpid_stop, + .show = fpid_show, +}; + +static int +ftrace_pid_open(struct inode *inode, struct file *file) +{ + int ret = 0; + + if ((file->f_mode & FMODE_WRITE) && + (file->f_flags & O_TRUNC)) + ftrace_pid_reset(); + + if (file->f_mode & FMODE_READ) + ret = seq_open(file, &ftrace_pid_sops); + + return ret; +} + +static ssize_t +ftrace_pid_write(struct file *filp, const char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + char buf[64], *tmp; + long val; + int ret; + + if (cnt >= sizeof(buf)) + return -EINVAL; + + if (copy_from_user(&buf, ubuf, cnt)) + return -EFAULT; + + buf[cnt] = 0; + + /* + * Allow "echo > set_ftrace_pid" or "echo -n '' > set_ftrace_pid" + * to clean the filter quietly. + */ + tmp = strstrip(buf); + if (strlen(tmp) == 0) + return 1; + + ret = kstrtol(tmp, 10, &val); + if (ret < 0) + return ret; + + ret = ftrace_pid_add(val); + + return ret ? ret : cnt; +} + +static int +ftrace_pid_release(struct inode *inode, struct file *file) +{ + if (file->f_mode & FMODE_READ) + seq_release(inode, file); + + return 0; +} + +static const struct file_operations ftrace_pid_fops = { + .open = ftrace_pid_open, + .write = ftrace_pid_write, + .read = seq_read, + .llseek = tracing_lseek, + .release = ftrace_pid_release, +}; + +static __init int ftrace_init_tracefs(void) +{ + struct dentry *d_tracer; + + d_tracer = tracing_init_dentry(); + if (IS_ERR(d_tracer)) + return 0; + + ftrace_init_dyn_tracefs(d_tracer); + + trace_create_file("set_ftrace_pid", 0644, d_tracer, + NULL, &ftrace_pid_fops); + + ftrace_profile_tracefs(d_tracer); + + return 0; +} +fs_initcall(ftrace_init_tracefs); + +/** + * ftrace_kill - kill ftrace + * + * This function should be used by panic code. It stops ftrace + * but in a not so nice way. If you need to simply kill ftrace + * from a non-atomic section, use ftrace_kill. + */ +void ftrace_kill(void) +{ + ftrace_disabled = 1; + ftrace_enabled = 0; + clear_ftrace_function(); +} + +/** + * Test if ftrace is dead or not. + */ +int ftrace_is_dead(void) +{ + return ftrace_disabled; +} + +/** + * register_ftrace_function - register a function for profiling + * @ops - ops structure that holds the function for profiling. + * + * Register a function to be called by all functions in the + * kernel. + * + * Note: @ops->func and all the functions it calls must be labeled + * with "notrace", otherwise it will go into a + * recursive loop. + */ +int register_ftrace_function(struct ftrace_ops *ops) +{ + int ret = -1; + + ftrace_ops_init(ops); + + mutex_lock(&ftrace_lock); + + ret = ftrace_startup(ops, 0); + + mutex_unlock(&ftrace_lock); + + return ret; +} +EXPORT_SYMBOL_GPL(register_ftrace_function); + +/** + * unregister_ftrace_function - unregister a function for profiling. + * @ops - ops structure that holds the function to unregister + * + * Unregister a function that was added to be called by ftrace profiling. + */ +int unregister_ftrace_function(struct ftrace_ops *ops) +{ + int ret; + + mutex_lock(&ftrace_lock); + ret = ftrace_shutdown(ops, 0); + mutex_unlock(&ftrace_lock); + + return ret; +} +EXPORT_SYMBOL_GPL(unregister_ftrace_function); + +int +ftrace_enable_sysctl(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos) +{ + int ret = -ENODEV; + + mutex_lock(&ftrace_lock); + + if (unlikely(ftrace_disabled)) + goto out; + + ret = proc_dointvec(table, write, buffer, lenp, ppos); + + if (ret || !write || (last_ftrace_enabled == !!ftrace_enabled)) + goto out; + + last_ftrace_enabled = !!ftrace_enabled; + + if (ftrace_enabled) { + + /* we are starting ftrace again */ + if (ftrace_ops_list != &ftrace_list_end) + update_ftrace_function(); + + ftrace_startup_sysctl(); + + } else { + /* stopping ftrace calls (just send to ftrace_stub) */ + ftrace_trace_function = ftrace_stub; + + ftrace_shutdown_sysctl(); + } + + out: + mutex_unlock(&ftrace_lock); + return ret; +} + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + +static struct ftrace_ops graph_ops = { + .func = ftrace_stub, + .flags = FTRACE_OPS_FL_RECURSION_SAFE | + FTRACE_OPS_FL_INITIALIZED | + FTRACE_OPS_FL_STUB, +#ifdef FTRACE_GRAPH_TRAMP_ADDR + .trampoline = FTRACE_GRAPH_TRAMP_ADDR, + /* trampoline_size is only needed for dynamically allocated tramps */ +#endif + ASSIGN_OPS_HASH(graph_ops, &global_ops.local_hash) +}; + +int ftrace_graph_entry_stub(struct ftrace_graph_ent *trace) +{ + return 0; +} + +/* The callbacks that hook a function */ +trace_func_graph_ret_t ftrace_graph_return = + (trace_func_graph_ret_t)ftrace_stub; +trace_func_graph_ent_t ftrace_graph_entry = ftrace_graph_entry_stub; +static trace_func_graph_ent_t __ftrace_graph_entry = ftrace_graph_entry_stub; + +/* Try to assign a return stack array on FTRACE_RETSTACK_ALLOC_SIZE tasks. */ +static int alloc_retstack_tasklist(struct ftrace_ret_stack **ret_stack_list) +{ + int i; + int ret = 0; + unsigned long flags; + int start = 0, end = FTRACE_RETSTACK_ALLOC_SIZE; + struct task_struct *g, *t; + + for (i = 0; i < FTRACE_RETSTACK_ALLOC_SIZE; i++) { + ret_stack_list[i] = kmalloc(FTRACE_RETFUNC_DEPTH + * sizeof(struct ftrace_ret_stack), + GFP_KERNEL); + if (!ret_stack_list[i]) { + start = 0; + end = i; + ret = -ENOMEM; + goto free; + } + } + + read_lock_irqsave(&tasklist_lock, flags); + do_each_thread(g, t) { + if (start == end) { + ret = -EAGAIN; + goto unlock; + } + + if (t->ret_stack == NULL) { + atomic_set(&t->tracing_graph_pause, 0); + atomic_set(&t->trace_overrun, 0); + t->curr_ret_stack = -1; + /* Make sure the tasks see the -1 first: */ + smp_wmb(); + t->ret_stack = ret_stack_list[start++]; + } + } while_each_thread(g, t); + +unlock: + read_unlock_irqrestore(&tasklist_lock, flags); +free: + for (i = start; i < end; i++) + kfree(ret_stack_list[i]); + return ret; +} + +static void +ftrace_graph_probe_sched_switch(void *ignore, + struct task_struct *prev, struct task_struct *next) +{ + unsigned long long timestamp; + int index; + + /* + * Does the user want to count the time a function was asleep. + * If so, do not update the time stamps. + */ + if (trace_flags & TRACE_ITER_SLEEP_TIME) + return; + + timestamp = trace_clock_local(); + + prev->ftrace_timestamp = timestamp; + + /* only process tasks that we timestamped */ + if (!next->ftrace_timestamp) + return; + + /* + * Update all the counters in next to make up for the + * time next was sleeping. + */ + timestamp -= next->ftrace_timestamp; + + for (index = next->curr_ret_stack; index >= 0; index--) + next->ret_stack[index].calltime += timestamp; +} + +/* Allocate a return stack for each task */ +static int start_graph_tracing(void) +{ + struct ftrace_ret_stack **ret_stack_list; + int ret, cpu; + + ret_stack_list = kmalloc(FTRACE_RETSTACK_ALLOC_SIZE * + sizeof(struct ftrace_ret_stack *), + GFP_KERNEL); + + if (!ret_stack_list) + return -ENOMEM; + + /* The cpu_boot init_task->ret_stack will never be freed */ + for_each_online_cpu(cpu) { + if (!idle_task(cpu)->ret_stack) + ftrace_graph_init_idle_task(idle_task(cpu), cpu); + } + + do { + ret = alloc_retstack_tasklist(ret_stack_list); + } while (ret == -EAGAIN); + + if (!ret) { + ret = register_trace_sched_switch(ftrace_graph_probe_sched_switch, NULL); + if (ret) + pr_info("ftrace_graph: Couldn't activate tracepoint" + " probe to kernel_sched_switch\n"); + } + + kfree(ret_stack_list); + return ret; +} + +/* + * Hibernation protection. + * The state of the current task is too much unstable during + * suspend/restore to disk. We want to protect against that. + */ +static int +ftrace_suspend_notifier_call(struct notifier_block *bl, unsigned long state, + void *unused) +{ + switch (state) { + case PM_HIBERNATION_PREPARE: + pause_graph_tracing(); + break; + + case PM_POST_HIBERNATION: + unpause_graph_tracing(); + break; + } + return NOTIFY_DONE; +} + +static int ftrace_graph_entry_test(struct ftrace_graph_ent *trace) +{ + if (!ftrace_ops_test(&global_ops, trace->func, NULL)) + return 0; + return __ftrace_graph_entry(trace); +} + +/* + * The function graph tracer should only trace the functions defined + * by set_ftrace_filter and set_ftrace_notrace. If another function + * tracer ops is registered, the graph tracer requires testing the + * function against the global ops, and not just trace any function + * that any ftrace_ops registered. + */ +static void update_function_graph_func(void) +{ + struct ftrace_ops *op; + bool do_test = false; + + /* + * The graph and global ops share the same set of functions + * to test. If any other ops is on the list, then + * the graph tracing needs to test if its the function + * it should call. + */ + do_for_each_ftrace_op(op, ftrace_ops_list) { + if (op != &global_ops && op != &graph_ops && + op != &ftrace_list_end) { + do_test = true; + /* in double loop, break out with goto */ + goto out; + } + } while_for_each_ftrace_op(op); + out: + if (do_test) + ftrace_graph_entry = ftrace_graph_entry_test; + else + ftrace_graph_entry = __ftrace_graph_entry; +} + +static struct notifier_block ftrace_suspend_notifier = { + .notifier_call = ftrace_suspend_notifier_call, +}; + +int register_ftrace_graph(trace_func_graph_ret_t retfunc, + trace_func_graph_ent_t entryfunc) +{ + int ret = 0; + + mutex_lock(&ftrace_lock); + + /* we currently allow only one tracer registered at a time */ + if (ftrace_graph_active) { + ret = -EBUSY; + goto out; + } + + register_pm_notifier(&ftrace_suspend_notifier); + + ftrace_graph_active++; + ret = start_graph_tracing(); + if (ret) { + ftrace_graph_active--; + goto out; + } + + ftrace_graph_return = retfunc; + + /* + * Update the indirect function to the entryfunc, and the + * function that gets called to the entry_test first. Then + * call the update fgraph entry function to determine if + * the entryfunc should be called directly or not. + */ + __ftrace_graph_entry = entryfunc; + ftrace_graph_entry = ftrace_graph_entry_test; + update_function_graph_func(); + + ret = ftrace_startup(&graph_ops, FTRACE_START_FUNC_RET); +out: + mutex_unlock(&ftrace_lock); + return ret; +} + +void unregister_ftrace_graph(void) +{ + mutex_lock(&ftrace_lock); + + if (unlikely(!ftrace_graph_active)) + goto out; + + ftrace_graph_active--; + ftrace_graph_return = (trace_func_graph_ret_t)ftrace_stub; + ftrace_graph_entry = ftrace_graph_entry_stub; + __ftrace_graph_entry = ftrace_graph_entry_stub; + ftrace_shutdown(&graph_ops, FTRACE_STOP_FUNC_RET); + unregister_pm_notifier(&ftrace_suspend_notifier); + unregister_trace_sched_switch(ftrace_graph_probe_sched_switch, NULL); + +#ifdef CONFIG_DYNAMIC_FTRACE + /* + * Function graph does not allocate the trampoline, but + * other global_ops do. We need to reset the ALLOC_TRAMP flag + * if one was used. + */ + global_ops.trampoline = save_global_trampoline; + if (save_global_flags & FTRACE_OPS_FL_ALLOC_TRAMP) + global_ops.flags |= FTRACE_OPS_FL_ALLOC_TRAMP; +#endif + + out: + mutex_unlock(&ftrace_lock); +} + +static DEFINE_PER_CPU(struct ftrace_ret_stack *, idle_ret_stack); + +static void +graph_init_task(struct task_struct *t, struct ftrace_ret_stack *ret_stack) +{ + atomic_set(&t->tracing_graph_pause, 0); + atomic_set(&t->trace_overrun, 0); + t->ftrace_timestamp = 0; + /* make curr_ret_stack visible before we add the ret_stack */ + smp_wmb(); + t->ret_stack = ret_stack; +} + +/* + * Allocate a return stack for the idle task. May be the first + * time through, or it may be done by CPU hotplug online. + */ +void ftrace_graph_init_idle_task(struct task_struct *t, int cpu) +{ + t->curr_ret_stack = -1; + /* + * The idle task has no parent, it either has its own + * stack or no stack at all. + */ + if (t->ret_stack) + WARN_ON(t->ret_stack != per_cpu(idle_ret_stack, cpu)); + + if (ftrace_graph_active) { + struct ftrace_ret_stack *ret_stack; + + ret_stack = per_cpu(idle_ret_stack, cpu); + if (!ret_stack) { + ret_stack = kmalloc(FTRACE_RETFUNC_DEPTH + * sizeof(struct ftrace_ret_stack), + GFP_KERNEL); + if (!ret_stack) + return; + per_cpu(idle_ret_stack, cpu) = ret_stack; + } + graph_init_task(t, ret_stack); + } +} + +/* Allocate a return stack for newly created task */ +void ftrace_graph_init_task(struct task_struct *t) +{ + /* Make sure we do not use the parent ret_stack */ + t->ret_stack = NULL; + t->curr_ret_stack = -1; + + if (ftrace_graph_active) { + struct ftrace_ret_stack *ret_stack; + + ret_stack = kmalloc(FTRACE_RETFUNC_DEPTH + * sizeof(struct ftrace_ret_stack), + GFP_KERNEL); + if (!ret_stack) + return; + graph_init_task(t, ret_stack); + } +} + +void ftrace_graph_exit_task(struct task_struct *t) +{ + struct ftrace_ret_stack *ret_stack = t->ret_stack; + + t->ret_stack = NULL; + /* NULL must become visible to IRQs before we free it: */ + barrier(); + + kfree(ret_stack); +} +#endif diff --git a/kernel/kernel/trace/latency_hist.c b/kernel/kernel/trace/latency_hist.c new file mode 100644 index 000000000..66a69eb53 --- /dev/null +++ b/kernel/kernel/trace/latency_hist.c @@ -0,0 +1,1178 @@ +/* + * kernel/trace/latency_hist.c + * + * Add support for histograms of preemption-off latency and + * interrupt-off latency and wakeup latency, it depends on + * Real-Time Preemption Support. + * + * Copyright (C) 2005 MontaVista Software, Inc. + * Yi Yang + * + * Converted to work with the new latency tracer. + * Copyright (C) 2008 Red Hat, Inc. + * Steven Rostedt + * + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "trace.h" +#include + +#define NSECS_PER_USECS 1000L + +#define CREATE_TRACE_POINTS +#include + +enum { + IRQSOFF_LATENCY = 0, + PREEMPTOFF_LATENCY, + PREEMPTIRQSOFF_LATENCY, + WAKEUP_LATENCY, + WAKEUP_LATENCY_SHAREDPRIO, + MISSED_TIMER_OFFSETS, + TIMERANDWAKEUP_LATENCY, + MAX_LATENCY_TYPE, +}; + +#define MAX_ENTRY_NUM 10240 + +struct hist_data { + atomic_t hist_mode; /* 0 log, 1 don't log */ + long offset; /* set it to MAX_ENTRY_NUM/2 for a bipolar scale */ + long min_lat; + long max_lat; + unsigned long long below_hist_bound_samples; + unsigned long long above_hist_bound_samples; + long long accumulate_lat; + unsigned long long total_samples; + unsigned long long hist_array[MAX_ENTRY_NUM]; +}; + +struct enable_data { + int latency_type; + int enabled; +}; + +static char *latency_hist_dir_root = "latency_hist"; + +#ifdef CONFIG_INTERRUPT_OFF_HIST +static DEFINE_PER_CPU(struct hist_data, irqsoff_hist); +static char *irqsoff_hist_dir = "irqsoff"; +static DEFINE_PER_CPU(cycles_t, hist_irqsoff_start); +static DEFINE_PER_CPU(int, hist_irqsoff_counting); +#endif + +#ifdef CONFIG_PREEMPT_OFF_HIST +static DEFINE_PER_CPU(struct hist_data, preemptoff_hist); +static char *preemptoff_hist_dir = "preemptoff"; +static DEFINE_PER_CPU(cycles_t, hist_preemptoff_start); +static DEFINE_PER_CPU(int, hist_preemptoff_counting); +#endif + +#if defined(CONFIG_PREEMPT_OFF_HIST) && defined(CONFIG_INTERRUPT_OFF_HIST) +static DEFINE_PER_CPU(struct hist_data, preemptirqsoff_hist); +static char *preemptirqsoff_hist_dir = "preemptirqsoff"; +static DEFINE_PER_CPU(cycles_t, hist_preemptirqsoff_start); +static DEFINE_PER_CPU(int, hist_preemptirqsoff_counting); +#endif + +#if defined(CONFIG_PREEMPT_OFF_HIST) || defined(CONFIG_INTERRUPT_OFF_HIST) +static notrace void probe_preemptirqsoff_hist(void *v, int reason, int start); +static struct enable_data preemptirqsoff_enabled_data = { + .latency_type = PREEMPTIRQSOFF_LATENCY, + .enabled = 0, +}; +#endif + +#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \ + defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) +struct maxlatproc_data { + char comm[FIELD_SIZEOF(struct task_struct, comm)]; + char current_comm[FIELD_SIZEOF(struct task_struct, comm)]; + int pid; + int current_pid; + int prio; + int current_prio; + long latency; + long timeroffset; + cycle_t timestamp; +}; +#endif + +#ifdef CONFIG_WAKEUP_LATENCY_HIST +static DEFINE_PER_CPU(struct hist_data, wakeup_latency_hist); +static DEFINE_PER_CPU(struct hist_data, wakeup_latency_hist_sharedprio); +static char *wakeup_latency_hist_dir = "wakeup"; +static char *wakeup_latency_hist_dir_sharedprio = "sharedprio"; +static notrace void probe_wakeup_latency_hist_start(void *v, + struct task_struct *p, int success); +static notrace void probe_wakeup_latency_hist_stop(void *v, + struct task_struct *prev, struct task_struct *next); +static notrace void probe_sched_migrate_task(void *, + struct task_struct *task, int cpu); +static struct enable_data wakeup_latency_enabled_data = { + .latency_type = WAKEUP_LATENCY, + .enabled = 0, +}; +static DEFINE_PER_CPU(struct maxlatproc_data, wakeup_maxlatproc); +static DEFINE_PER_CPU(struct maxlatproc_data, wakeup_maxlatproc_sharedprio); +static DEFINE_PER_CPU(struct task_struct *, wakeup_task); +static DEFINE_PER_CPU(int, wakeup_sharedprio); +static unsigned long wakeup_pid; +#endif + +#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST +static DEFINE_PER_CPU(struct hist_data, missed_timer_offsets); +static char *missed_timer_offsets_dir = "missed_timer_offsets"; +static notrace void probe_hrtimer_interrupt(void *v, int cpu, + long long offset, struct task_struct *curr, struct task_struct *task); +static struct enable_data missed_timer_offsets_enabled_data = { + .latency_type = MISSED_TIMER_OFFSETS, + .enabled = 0, +}; +static DEFINE_PER_CPU(struct maxlatproc_data, missed_timer_offsets_maxlatproc); +static unsigned long missed_timer_offsets_pid; +#endif + +#if defined(CONFIG_WAKEUP_LATENCY_HIST) && \ + defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) +static DEFINE_PER_CPU(struct hist_data, timerandwakeup_latency_hist); +static char *timerandwakeup_latency_hist_dir = "timerandwakeup"; +static struct enable_data timerandwakeup_enabled_data = { + .latency_type = TIMERANDWAKEUP_LATENCY, + .enabled = 0, +}; +static DEFINE_PER_CPU(struct maxlatproc_data, timerandwakeup_maxlatproc); +#endif + +void notrace latency_hist(int latency_type, int cpu, long latency, + long timeroffset, cycle_t stop, + struct task_struct *p) +{ + struct hist_data *my_hist; +#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \ + defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) + struct maxlatproc_data *mp = NULL; +#endif + + if (!cpu_possible(cpu) || latency_type < 0 || + latency_type >= MAX_LATENCY_TYPE) + return; + + switch (latency_type) { +#ifdef CONFIG_INTERRUPT_OFF_HIST + case IRQSOFF_LATENCY: + my_hist = &per_cpu(irqsoff_hist, cpu); + break; +#endif +#ifdef CONFIG_PREEMPT_OFF_HIST + case PREEMPTOFF_LATENCY: + my_hist = &per_cpu(preemptoff_hist, cpu); + break; +#endif +#if defined(CONFIG_PREEMPT_OFF_HIST) && defined(CONFIG_INTERRUPT_OFF_HIST) + case PREEMPTIRQSOFF_LATENCY: + my_hist = &per_cpu(preemptirqsoff_hist, cpu); + break; +#endif +#ifdef CONFIG_WAKEUP_LATENCY_HIST + case WAKEUP_LATENCY: + my_hist = &per_cpu(wakeup_latency_hist, cpu); + mp = &per_cpu(wakeup_maxlatproc, cpu); + break; + case WAKEUP_LATENCY_SHAREDPRIO: + my_hist = &per_cpu(wakeup_latency_hist_sharedprio, cpu); + mp = &per_cpu(wakeup_maxlatproc_sharedprio, cpu); + break; +#endif +#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST + case MISSED_TIMER_OFFSETS: + my_hist = &per_cpu(missed_timer_offsets, cpu); + mp = &per_cpu(missed_timer_offsets_maxlatproc, cpu); + break; +#endif +#if defined(CONFIG_WAKEUP_LATENCY_HIST) && \ + defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) + case TIMERANDWAKEUP_LATENCY: + my_hist = &per_cpu(timerandwakeup_latency_hist, cpu); + mp = &per_cpu(timerandwakeup_maxlatproc, cpu); + break; +#endif + + default: + return; + } + + latency += my_hist->offset; + + if (atomic_read(&my_hist->hist_mode) == 0) + return; + + if (latency < 0 || latency >= MAX_ENTRY_NUM) { + if (latency < 0) + my_hist->below_hist_bound_samples++; + else + my_hist->above_hist_bound_samples++; + } else + my_hist->hist_array[latency]++; + + if (unlikely(latency > my_hist->max_lat || + my_hist->min_lat == LONG_MAX)) { +#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \ + defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) + if (latency_type == WAKEUP_LATENCY || + latency_type == WAKEUP_LATENCY_SHAREDPRIO || + latency_type == MISSED_TIMER_OFFSETS || + latency_type == TIMERANDWAKEUP_LATENCY) { + strncpy(mp->comm, p->comm, sizeof(mp->comm)); + strncpy(mp->current_comm, current->comm, + sizeof(mp->current_comm)); + mp->pid = task_pid_nr(p); + mp->current_pid = task_pid_nr(current); + mp->prio = p->prio; + mp->current_prio = current->prio; + mp->latency = latency; + mp->timeroffset = timeroffset; + mp->timestamp = stop; + } +#endif + my_hist->max_lat = latency; + } + if (unlikely(latency < my_hist->min_lat)) + my_hist->min_lat = latency; + my_hist->total_samples++; + my_hist->accumulate_lat += latency; +} + +static void *l_start(struct seq_file *m, loff_t *pos) +{ + loff_t *index_ptr = NULL; + loff_t index = *pos; + struct hist_data *my_hist = m->private; + + if (index == 0) { + char minstr[32], avgstr[32], maxstr[32]; + + atomic_dec(&my_hist->hist_mode); + + if (likely(my_hist->total_samples)) { + long avg = (long) div64_s64(my_hist->accumulate_lat, + my_hist->total_samples); + snprintf(minstr, sizeof(minstr), "%ld", + my_hist->min_lat - my_hist->offset); + snprintf(avgstr, sizeof(avgstr), "%ld", + avg - my_hist->offset); + snprintf(maxstr, sizeof(maxstr), "%ld", + my_hist->max_lat - my_hist->offset); + } else { + strcpy(minstr, ""); + strcpy(avgstr, minstr); + strcpy(maxstr, minstr); + } + + seq_printf(m, "#Minimum latency: %s microseconds\n" + "#Average latency: %s microseconds\n" + "#Maximum latency: %s microseconds\n" + "#Total samples: %llu\n" + "#There are %llu samples lower than %ld" + " microseconds.\n" + "#There are %llu samples greater or equal" + " than %ld microseconds.\n" + "#usecs\t%16s\n", + minstr, avgstr, maxstr, + my_hist->total_samples, + my_hist->below_hist_bound_samples, + -my_hist->offset, + my_hist->above_hist_bound_samples, + MAX_ENTRY_NUM - my_hist->offset, + "samples"); + } + if (index < MAX_ENTRY_NUM) { + index_ptr = kmalloc(sizeof(loff_t), GFP_KERNEL); + if (index_ptr) + *index_ptr = index; + } + + return index_ptr; +} + +static void *l_next(struct seq_file *m, void *p, loff_t *pos) +{ + loff_t *index_ptr = p; + struct hist_data *my_hist = m->private; + + if (++*pos >= MAX_ENTRY_NUM) { + atomic_inc(&my_hist->hist_mode); + return NULL; + } + *index_ptr = *pos; + return index_ptr; +} + +static void l_stop(struct seq_file *m, void *p) +{ + kfree(p); +} + +static int l_show(struct seq_file *m, void *p) +{ + int index = *(loff_t *) p; + struct hist_data *my_hist = m->private; + + seq_printf(m, "%6ld\t%16llu\n", index - my_hist->offset, + my_hist->hist_array[index]); + return 0; +} + +static const struct seq_operations latency_hist_seq_op = { + .start = l_start, + .next = l_next, + .stop = l_stop, + .show = l_show +}; + +static int latency_hist_open(struct inode *inode, struct file *file) +{ + int ret; + + ret = seq_open(file, &latency_hist_seq_op); + if (!ret) { + struct seq_file *seq = file->private_data; + seq->private = inode->i_private; + } + return ret; +} + +static const struct file_operations latency_hist_fops = { + .open = latency_hist_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, +}; + +#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \ + defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) +static void clear_maxlatprocdata(struct maxlatproc_data *mp) +{ + mp->comm[0] = mp->current_comm[0] = '\0'; + mp->prio = mp->current_prio = mp->pid = mp->current_pid = + mp->latency = mp->timeroffset = -1; + mp->timestamp = 0; +} +#endif + +static void hist_reset(struct hist_data *hist) +{ + atomic_dec(&hist->hist_mode); + + memset(hist->hist_array, 0, sizeof(hist->hist_array)); + hist->below_hist_bound_samples = 0ULL; + hist->above_hist_bound_samples = 0ULL; + hist->min_lat = LONG_MAX; + hist->max_lat = LONG_MIN; + hist->total_samples = 0ULL; + hist->accumulate_lat = 0LL; + + atomic_inc(&hist->hist_mode); +} + +static ssize_t +latency_hist_reset(struct file *file, const char __user *a, + size_t size, loff_t *off) +{ + int cpu; + struct hist_data *hist = NULL; +#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \ + defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) + struct maxlatproc_data *mp = NULL; +#endif + off_t latency_type = (off_t) file->private_data; + + for_each_online_cpu(cpu) { + + switch (latency_type) { +#ifdef CONFIG_PREEMPT_OFF_HIST + case PREEMPTOFF_LATENCY: + hist = &per_cpu(preemptoff_hist, cpu); + break; +#endif +#ifdef CONFIG_INTERRUPT_OFF_HIST + case IRQSOFF_LATENCY: + hist = &per_cpu(irqsoff_hist, cpu); + break; +#endif +#if defined(CONFIG_INTERRUPT_OFF_HIST) && defined(CONFIG_PREEMPT_OFF_HIST) + case PREEMPTIRQSOFF_LATENCY: + hist = &per_cpu(preemptirqsoff_hist, cpu); + break; +#endif +#ifdef CONFIG_WAKEUP_LATENCY_HIST + case WAKEUP_LATENCY: + hist = &per_cpu(wakeup_latency_hist, cpu); + mp = &per_cpu(wakeup_maxlatproc, cpu); + break; + case WAKEUP_LATENCY_SHAREDPRIO: + hist = &per_cpu(wakeup_latency_hist_sharedprio, cpu); + mp = &per_cpu(wakeup_maxlatproc_sharedprio, cpu); + break; +#endif +#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST + case MISSED_TIMER_OFFSETS: + hist = &per_cpu(missed_timer_offsets, cpu); + mp = &per_cpu(missed_timer_offsets_maxlatproc, cpu); + break; +#endif +#if defined(CONFIG_WAKEUP_LATENCY_HIST) && \ + defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) + case TIMERANDWAKEUP_LATENCY: + hist = &per_cpu(timerandwakeup_latency_hist, cpu); + mp = &per_cpu(timerandwakeup_maxlatproc, cpu); + break; +#endif + } + + hist_reset(hist); +#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \ + defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) + if (latency_type == WAKEUP_LATENCY || + latency_type == WAKEUP_LATENCY_SHAREDPRIO || + latency_type == MISSED_TIMER_OFFSETS || + latency_type == TIMERANDWAKEUP_LATENCY) + clear_maxlatprocdata(mp); +#endif + } + + return size; +} + +#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \ + defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) +static ssize_t +show_pid(struct file *file, char __user *ubuf, size_t cnt, loff_t *ppos) +{ + char buf[64]; + int r; + unsigned long *this_pid = file->private_data; + + r = snprintf(buf, sizeof(buf), "%lu\n", *this_pid); + return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); +} + +static ssize_t do_pid(struct file *file, const char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + char buf[64]; + unsigned long pid; + unsigned long *this_pid = file->private_data; + + if (cnt >= sizeof(buf)) + return -EINVAL; + + if (copy_from_user(&buf, ubuf, cnt)) + return -EFAULT; + + buf[cnt] = '\0'; + + if (kstrtoul(buf, 10, &pid)) + return -EINVAL; + + *this_pid = pid; + + return cnt; +} +#endif + +#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \ + defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) +static ssize_t +show_maxlatproc(struct file *file, char __user *ubuf, size_t cnt, loff_t *ppos) +{ + int r; + struct maxlatproc_data *mp = file->private_data; + int strmaxlen = (TASK_COMM_LEN * 2) + (8 * 8); + unsigned long long t; + unsigned long usecs, secs; + char *buf; + + if (mp->pid == -1 || mp->current_pid == -1) { + buf = "(none)\n"; + return simple_read_from_buffer(ubuf, cnt, ppos, buf, + strlen(buf)); + } + + buf = kmalloc(strmaxlen, GFP_KERNEL); + if (buf == NULL) + return -ENOMEM; + + t = ns2usecs(mp->timestamp); + usecs = do_div(t, USEC_PER_SEC); + secs = (unsigned long) t; + r = snprintf(buf, strmaxlen, + "%d %d %ld (%ld) %s <- %d %d %s %lu.%06lu\n", mp->pid, + MAX_RT_PRIO-1 - mp->prio, mp->latency, mp->timeroffset, mp->comm, + mp->current_pid, MAX_RT_PRIO-1 - mp->current_prio, mp->current_comm, + secs, usecs); + r = simple_read_from_buffer(ubuf, cnt, ppos, buf, r); + kfree(buf); + return r; +} +#endif + +static ssize_t +show_enable(struct file *file, char __user *ubuf, size_t cnt, loff_t *ppos) +{ + char buf[64]; + struct enable_data *ed = file->private_data; + int r; + + r = snprintf(buf, sizeof(buf), "%d\n", ed->enabled); + return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); +} + +static ssize_t +do_enable(struct file *file, const char __user *ubuf, size_t cnt, loff_t *ppos) +{ + char buf[64]; + long enable; + struct enable_data *ed = file->private_data; + + if (cnt >= sizeof(buf)) + return -EINVAL; + + if (copy_from_user(&buf, ubuf, cnt)) + return -EFAULT; + + buf[cnt] = 0; + + if (kstrtoul(buf, 10, &enable)) + return -EINVAL; + + if ((enable && ed->enabled) || (!enable && !ed->enabled)) + return cnt; + + if (enable) { + int ret; + + switch (ed->latency_type) { +#if defined(CONFIG_INTERRUPT_OFF_HIST) || defined(CONFIG_PREEMPT_OFF_HIST) + case PREEMPTIRQSOFF_LATENCY: + ret = register_trace_preemptirqsoff_hist( + probe_preemptirqsoff_hist, NULL); + if (ret) { + pr_info("wakeup trace: Couldn't assign " + "probe_preemptirqsoff_hist " + "to trace_preemptirqsoff_hist\n"); + return ret; + } + break; +#endif +#ifdef CONFIG_WAKEUP_LATENCY_HIST + case WAKEUP_LATENCY: + ret = register_trace_sched_wakeup( + probe_wakeup_latency_hist_start, NULL); + if (ret) { + pr_info("wakeup trace: Couldn't assign " + "probe_wakeup_latency_hist_start " + "to trace_sched_wakeup\n"); + return ret; + } + ret = register_trace_sched_wakeup_new( + probe_wakeup_latency_hist_start, NULL); + if (ret) { + pr_info("wakeup trace: Couldn't assign " + "probe_wakeup_latency_hist_start " + "to trace_sched_wakeup_new\n"); + unregister_trace_sched_wakeup( + probe_wakeup_latency_hist_start, NULL); + return ret; + } + ret = register_trace_sched_switch( + probe_wakeup_latency_hist_stop, NULL); + if (ret) { + pr_info("wakeup trace: Couldn't assign " + "probe_wakeup_latency_hist_stop " + "to trace_sched_switch\n"); + unregister_trace_sched_wakeup( + probe_wakeup_latency_hist_start, NULL); + unregister_trace_sched_wakeup_new( + probe_wakeup_latency_hist_start, NULL); + return ret; + } + ret = register_trace_sched_migrate_task( + probe_sched_migrate_task, NULL); + if (ret) { + pr_info("wakeup trace: Couldn't assign " + "probe_sched_migrate_task " + "to trace_sched_migrate_task\n"); + unregister_trace_sched_wakeup( + probe_wakeup_latency_hist_start, NULL); + unregister_trace_sched_wakeup_new( + probe_wakeup_latency_hist_start, NULL); + unregister_trace_sched_switch( + probe_wakeup_latency_hist_stop, NULL); + return ret; + } + break; +#endif +#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST + case MISSED_TIMER_OFFSETS: + ret = register_trace_hrtimer_interrupt( + probe_hrtimer_interrupt, NULL); + if (ret) { + pr_info("wakeup trace: Couldn't assign " + "probe_hrtimer_interrupt " + "to trace_hrtimer_interrupt\n"); + return ret; + } + break; +#endif +#if defined(CONFIG_WAKEUP_LATENCY_HIST) && \ + defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) + case TIMERANDWAKEUP_LATENCY: + if (!wakeup_latency_enabled_data.enabled || + !missed_timer_offsets_enabled_data.enabled) + return -EINVAL; + break; +#endif + default: + break; + } + } else { + switch (ed->latency_type) { +#if defined(CONFIG_INTERRUPT_OFF_HIST) || defined(CONFIG_PREEMPT_OFF_HIST) + case PREEMPTIRQSOFF_LATENCY: + { + int cpu; + + unregister_trace_preemptirqsoff_hist( + probe_preemptirqsoff_hist, NULL); + for_each_online_cpu(cpu) { +#ifdef CONFIG_INTERRUPT_OFF_HIST + per_cpu(hist_irqsoff_counting, + cpu) = 0; +#endif +#ifdef CONFIG_PREEMPT_OFF_HIST + per_cpu(hist_preemptoff_counting, + cpu) = 0; +#endif +#if defined(CONFIG_INTERRUPT_OFF_HIST) && defined(CONFIG_PREEMPT_OFF_HIST) + per_cpu(hist_preemptirqsoff_counting, + cpu) = 0; +#endif + } + } + break; +#endif +#ifdef CONFIG_WAKEUP_LATENCY_HIST + case WAKEUP_LATENCY: + { + int cpu; + + unregister_trace_sched_wakeup( + probe_wakeup_latency_hist_start, NULL); + unregister_trace_sched_wakeup_new( + probe_wakeup_latency_hist_start, NULL); + unregister_trace_sched_switch( + probe_wakeup_latency_hist_stop, NULL); + unregister_trace_sched_migrate_task( + probe_sched_migrate_task, NULL); + + for_each_online_cpu(cpu) { + per_cpu(wakeup_task, cpu) = NULL; + per_cpu(wakeup_sharedprio, cpu) = 0; + } + } +#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST + timerandwakeup_enabled_data.enabled = 0; +#endif + break; +#endif +#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST + case MISSED_TIMER_OFFSETS: + unregister_trace_hrtimer_interrupt( + probe_hrtimer_interrupt, NULL); +#ifdef CONFIG_WAKEUP_LATENCY_HIST + timerandwakeup_enabled_data.enabled = 0; +#endif + break; +#endif + default: + break; + } + } + ed->enabled = enable; + return cnt; +} + +static const struct file_operations latency_hist_reset_fops = { + .open = tracing_open_generic, + .write = latency_hist_reset, +}; + +static const struct file_operations enable_fops = { + .open = tracing_open_generic, + .read = show_enable, + .write = do_enable, +}; + +#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \ + defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) +static const struct file_operations pid_fops = { + .open = tracing_open_generic, + .read = show_pid, + .write = do_pid, +}; + +static const struct file_operations maxlatproc_fops = { + .open = tracing_open_generic, + .read = show_maxlatproc, +}; +#endif + +#if defined(CONFIG_INTERRUPT_OFF_HIST) || defined(CONFIG_PREEMPT_OFF_HIST) +static notrace void probe_preemptirqsoff_hist(void *v, int reason, + int starthist) +{ + int cpu = raw_smp_processor_id(); + int time_set = 0; + + if (starthist) { + cycle_t uninitialized_var(start); + + if (!preempt_count() && !irqs_disabled()) + return; + +#ifdef CONFIG_INTERRUPT_OFF_HIST + if ((reason == IRQS_OFF || reason == TRACE_START) && + !per_cpu(hist_irqsoff_counting, cpu)) { + per_cpu(hist_irqsoff_counting, cpu) = 1; + start = ftrace_now(cpu); + time_set++; + per_cpu(hist_irqsoff_start, cpu) = start; + } +#endif + +#ifdef CONFIG_PREEMPT_OFF_HIST + if ((reason == PREEMPT_OFF || reason == TRACE_START) && + !per_cpu(hist_preemptoff_counting, cpu)) { + per_cpu(hist_preemptoff_counting, cpu) = 1; + if (!(time_set++)) + start = ftrace_now(cpu); + per_cpu(hist_preemptoff_start, cpu) = start; + } +#endif + +#if defined(CONFIG_INTERRUPT_OFF_HIST) && defined(CONFIG_PREEMPT_OFF_HIST) + if (per_cpu(hist_irqsoff_counting, cpu) && + per_cpu(hist_preemptoff_counting, cpu) && + !per_cpu(hist_preemptirqsoff_counting, cpu)) { + per_cpu(hist_preemptirqsoff_counting, cpu) = 1; + if (!time_set) + start = ftrace_now(cpu); + per_cpu(hist_preemptirqsoff_start, cpu) = start; + } +#endif + } else { + cycle_t uninitialized_var(stop); + +#ifdef CONFIG_INTERRUPT_OFF_HIST + if ((reason == IRQS_ON || reason == TRACE_STOP) && + per_cpu(hist_irqsoff_counting, cpu)) { + cycle_t start = per_cpu(hist_irqsoff_start, cpu); + + stop = ftrace_now(cpu); + time_set++; + if (start) { + long latency = ((long) (stop - start)) / + NSECS_PER_USECS; + + latency_hist(IRQSOFF_LATENCY, cpu, latency, 0, + stop, NULL); + } + per_cpu(hist_irqsoff_counting, cpu) = 0; + } +#endif + +#ifdef CONFIG_PREEMPT_OFF_HIST + if ((reason == PREEMPT_ON || reason == TRACE_STOP) && + per_cpu(hist_preemptoff_counting, cpu)) { + cycle_t start = per_cpu(hist_preemptoff_start, cpu); + + if (!(time_set++)) + stop = ftrace_now(cpu); + if (start) { + long latency = ((long) (stop - start)) / + NSECS_PER_USECS; + + latency_hist(PREEMPTOFF_LATENCY, cpu, latency, + 0, stop, NULL); + } + per_cpu(hist_preemptoff_counting, cpu) = 0; + } +#endif + +#if defined(CONFIG_INTERRUPT_OFF_HIST) && defined(CONFIG_PREEMPT_OFF_HIST) + if ((!per_cpu(hist_irqsoff_counting, cpu) || + !per_cpu(hist_preemptoff_counting, cpu)) && + per_cpu(hist_preemptirqsoff_counting, cpu)) { + cycle_t start = per_cpu(hist_preemptirqsoff_start, cpu); + + if (!time_set) + stop = ftrace_now(cpu); + if (start) { + long latency = ((long) (stop - start)) / + NSECS_PER_USECS; + + latency_hist(PREEMPTIRQSOFF_LATENCY, cpu, + latency, 0, stop, NULL); + } + per_cpu(hist_preemptirqsoff_counting, cpu) = 0; + } +#endif + } +} +#endif + +#ifdef CONFIG_WAKEUP_LATENCY_HIST +static DEFINE_RAW_SPINLOCK(wakeup_lock); +static notrace void probe_sched_migrate_task(void *v, struct task_struct *task, + int cpu) +{ + int old_cpu = task_cpu(task); + + if (cpu != old_cpu) { + unsigned long flags; + struct task_struct *cpu_wakeup_task; + + raw_spin_lock_irqsave(&wakeup_lock, flags); + + cpu_wakeup_task = per_cpu(wakeup_task, old_cpu); + if (task == cpu_wakeup_task) { + put_task_struct(cpu_wakeup_task); + per_cpu(wakeup_task, old_cpu) = NULL; + cpu_wakeup_task = per_cpu(wakeup_task, cpu) = task; + get_task_struct(cpu_wakeup_task); + } + + raw_spin_unlock_irqrestore(&wakeup_lock, flags); + } +} + +static notrace void probe_wakeup_latency_hist_start(void *v, + struct task_struct *p, int success) +{ + unsigned long flags; + struct task_struct *curr = current; + int cpu = task_cpu(p); + struct task_struct *cpu_wakeup_task; + + raw_spin_lock_irqsave(&wakeup_lock, flags); + + cpu_wakeup_task = per_cpu(wakeup_task, cpu); + + if (wakeup_pid) { + if ((cpu_wakeup_task && p->prio == cpu_wakeup_task->prio) || + p->prio == curr->prio) + per_cpu(wakeup_sharedprio, cpu) = 1; + if (likely(wakeup_pid != task_pid_nr(p))) + goto out; + } else { + if (likely(!rt_task(p)) || + (cpu_wakeup_task && p->prio > cpu_wakeup_task->prio) || + p->prio > curr->prio) + goto out; + if ((cpu_wakeup_task && p->prio == cpu_wakeup_task->prio) || + p->prio == curr->prio) + per_cpu(wakeup_sharedprio, cpu) = 1; + } + + if (cpu_wakeup_task) + put_task_struct(cpu_wakeup_task); + cpu_wakeup_task = per_cpu(wakeup_task, cpu) = p; + get_task_struct(cpu_wakeup_task); + cpu_wakeup_task->preempt_timestamp_hist = + ftrace_now(raw_smp_processor_id()); +out: + raw_spin_unlock_irqrestore(&wakeup_lock, flags); +} + +static notrace void probe_wakeup_latency_hist_stop(void *v, + struct task_struct *prev, struct task_struct *next) +{ + unsigned long flags; + int cpu = task_cpu(next); + long latency; + cycle_t stop; + struct task_struct *cpu_wakeup_task; + + raw_spin_lock_irqsave(&wakeup_lock, flags); + + cpu_wakeup_task = per_cpu(wakeup_task, cpu); + + if (cpu_wakeup_task == NULL) + goto out; + + /* Already running? */ + if (unlikely(current == cpu_wakeup_task)) + goto out_reset; + + if (next != cpu_wakeup_task) { + if (next->prio < cpu_wakeup_task->prio) + goto out_reset; + + if (next->prio == cpu_wakeup_task->prio) + per_cpu(wakeup_sharedprio, cpu) = 1; + + goto out; + } + + if (current->prio == cpu_wakeup_task->prio) + per_cpu(wakeup_sharedprio, cpu) = 1; + + /* + * The task we are waiting for is about to be switched to. + * Calculate latency and store it in histogram. + */ + stop = ftrace_now(raw_smp_processor_id()); + + latency = ((long) (stop - next->preempt_timestamp_hist)) / + NSECS_PER_USECS; + + if (per_cpu(wakeup_sharedprio, cpu)) { + latency_hist(WAKEUP_LATENCY_SHAREDPRIO, cpu, latency, 0, stop, + next); + per_cpu(wakeup_sharedprio, cpu) = 0; + } else { + latency_hist(WAKEUP_LATENCY, cpu, latency, 0, stop, next); +#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST + if (timerandwakeup_enabled_data.enabled) { + latency_hist(TIMERANDWAKEUP_LATENCY, cpu, + next->timer_offset + latency, next->timer_offset, + stop, next); + } +#endif + } + +out_reset: +#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST + next->timer_offset = 0; +#endif + put_task_struct(cpu_wakeup_task); + per_cpu(wakeup_task, cpu) = NULL; +out: + raw_spin_unlock_irqrestore(&wakeup_lock, flags); +} +#endif + +#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST +static notrace void probe_hrtimer_interrupt(void *v, int cpu, + long long latency_ns, struct task_struct *curr, + struct task_struct *task) +{ + if (latency_ns <= 0 && task != NULL && rt_task(task) && + (task->prio < curr->prio || + (task->prio == curr->prio && + !cpumask_test_cpu(cpu, &task->cpus_allowed)))) { + long latency; + cycle_t now; + + if (missed_timer_offsets_pid) { + if (likely(missed_timer_offsets_pid != + task_pid_nr(task))) + return; + } + + now = ftrace_now(cpu); + latency = (long) div_s64(-latency_ns, NSECS_PER_USECS); + latency_hist(MISSED_TIMER_OFFSETS, cpu, latency, latency, now, + task); +#ifdef CONFIG_WAKEUP_LATENCY_HIST + task->timer_offset = latency; +#endif + } +} +#endif + +static __init int latency_hist_init(void) +{ + struct dentry *latency_hist_root = NULL; + struct dentry *dentry; +#ifdef CONFIG_WAKEUP_LATENCY_HIST + struct dentry *dentry_sharedprio; +#endif + struct dentry *entry; + struct dentry *enable_root; + int i = 0; + struct hist_data *my_hist; + char name[64]; + char *cpufmt = "CPU%d"; +#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \ + defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) + char *cpufmt_maxlatproc = "max_latency-CPU%d"; + struct maxlatproc_data *mp = NULL; +#endif + + dentry = tracing_init_dentry(); + latency_hist_root = debugfs_create_dir(latency_hist_dir_root, dentry); + enable_root = debugfs_create_dir("enable", latency_hist_root); + +#ifdef CONFIG_INTERRUPT_OFF_HIST + dentry = debugfs_create_dir(irqsoff_hist_dir, latency_hist_root); + for_each_possible_cpu(i) { + sprintf(name, cpufmt, i); + entry = debugfs_create_file(name, 0444, dentry, + &per_cpu(irqsoff_hist, i), &latency_hist_fops); + my_hist = &per_cpu(irqsoff_hist, i); + atomic_set(&my_hist->hist_mode, 1); + my_hist->min_lat = LONG_MAX; + } + entry = debugfs_create_file("reset", 0644, dentry, + (void *)IRQSOFF_LATENCY, &latency_hist_reset_fops); +#endif + +#ifdef CONFIG_PREEMPT_OFF_HIST + dentry = debugfs_create_dir(preemptoff_hist_dir, + latency_hist_root); + for_each_possible_cpu(i) { + sprintf(name, cpufmt, i); + entry = debugfs_create_file(name, 0444, dentry, + &per_cpu(preemptoff_hist, i), &latency_hist_fops); + my_hist = &per_cpu(preemptoff_hist, i); + atomic_set(&my_hist->hist_mode, 1); + my_hist->min_lat = LONG_MAX; + } + entry = debugfs_create_file("reset", 0644, dentry, + (void *)PREEMPTOFF_LATENCY, &latency_hist_reset_fops); +#endif + +#if defined(CONFIG_INTERRUPT_OFF_HIST) && defined(CONFIG_PREEMPT_OFF_HIST) + dentry = debugfs_create_dir(preemptirqsoff_hist_dir, + latency_hist_root); + for_each_possible_cpu(i) { + sprintf(name, cpufmt, i); + entry = debugfs_create_file(name, 0444, dentry, + &per_cpu(preemptirqsoff_hist, i), &latency_hist_fops); + my_hist = &per_cpu(preemptirqsoff_hist, i); + atomic_set(&my_hist->hist_mode, 1); + my_hist->min_lat = LONG_MAX; + } + entry = debugfs_create_file("reset", 0644, dentry, + (void *)PREEMPTIRQSOFF_LATENCY, &latency_hist_reset_fops); +#endif + +#if defined(CONFIG_INTERRUPT_OFF_HIST) || defined(CONFIG_PREEMPT_OFF_HIST) + entry = debugfs_create_file("preemptirqsoff", 0644, + enable_root, (void *)&preemptirqsoff_enabled_data, + &enable_fops); +#endif + +#ifdef CONFIG_WAKEUP_LATENCY_HIST + dentry = debugfs_create_dir(wakeup_latency_hist_dir, + latency_hist_root); + dentry_sharedprio = debugfs_create_dir( + wakeup_latency_hist_dir_sharedprio, dentry); + for_each_possible_cpu(i) { + sprintf(name, cpufmt, i); + + entry = debugfs_create_file(name, 0444, dentry, + &per_cpu(wakeup_latency_hist, i), + &latency_hist_fops); + my_hist = &per_cpu(wakeup_latency_hist, i); + atomic_set(&my_hist->hist_mode, 1); + my_hist->min_lat = LONG_MAX; + + entry = debugfs_create_file(name, 0444, dentry_sharedprio, + &per_cpu(wakeup_latency_hist_sharedprio, i), + &latency_hist_fops); + my_hist = &per_cpu(wakeup_latency_hist_sharedprio, i); + atomic_set(&my_hist->hist_mode, 1); + my_hist->min_lat = LONG_MAX; + + sprintf(name, cpufmt_maxlatproc, i); + + mp = &per_cpu(wakeup_maxlatproc, i); + entry = debugfs_create_file(name, 0444, dentry, mp, + &maxlatproc_fops); + clear_maxlatprocdata(mp); + + mp = &per_cpu(wakeup_maxlatproc_sharedprio, i); + entry = debugfs_create_file(name, 0444, dentry_sharedprio, mp, + &maxlatproc_fops); + clear_maxlatprocdata(mp); + } + entry = debugfs_create_file("pid", 0644, dentry, + (void *)&wakeup_pid, &pid_fops); + entry = debugfs_create_file("reset", 0644, dentry, + (void *)WAKEUP_LATENCY, &latency_hist_reset_fops); + entry = debugfs_create_file("reset", 0644, dentry_sharedprio, + (void *)WAKEUP_LATENCY_SHAREDPRIO, &latency_hist_reset_fops); + entry = debugfs_create_file("wakeup", 0644, + enable_root, (void *)&wakeup_latency_enabled_data, + &enable_fops); +#endif + +#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST + dentry = debugfs_create_dir(missed_timer_offsets_dir, + latency_hist_root); + for_each_possible_cpu(i) { + sprintf(name, cpufmt, i); + entry = debugfs_create_file(name, 0444, dentry, + &per_cpu(missed_timer_offsets, i), &latency_hist_fops); + my_hist = &per_cpu(missed_timer_offsets, i); + atomic_set(&my_hist->hist_mode, 1); + my_hist->min_lat = LONG_MAX; + + sprintf(name, cpufmt_maxlatproc, i); + mp = &per_cpu(missed_timer_offsets_maxlatproc, i); + entry = debugfs_create_file(name, 0444, dentry, mp, + &maxlatproc_fops); + clear_maxlatprocdata(mp); + } + entry = debugfs_create_file("pid", 0644, dentry, + (void *)&missed_timer_offsets_pid, &pid_fops); + entry = debugfs_create_file("reset", 0644, dentry, + (void *)MISSED_TIMER_OFFSETS, &latency_hist_reset_fops); + entry = debugfs_create_file("missed_timer_offsets", 0644, + enable_root, (void *)&missed_timer_offsets_enabled_data, + &enable_fops); +#endif + +#if defined(CONFIG_WAKEUP_LATENCY_HIST) && \ + defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) + dentry = debugfs_create_dir(timerandwakeup_latency_hist_dir, + latency_hist_root); + for_each_possible_cpu(i) { + sprintf(name, cpufmt, i); + entry = debugfs_create_file(name, 0444, dentry, + &per_cpu(timerandwakeup_latency_hist, i), + &latency_hist_fops); + my_hist = &per_cpu(timerandwakeup_latency_hist, i); + atomic_set(&my_hist->hist_mode, 1); + my_hist->min_lat = LONG_MAX; + + sprintf(name, cpufmt_maxlatproc, i); + mp = &per_cpu(timerandwakeup_maxlatproc, i); + entry = debugfs_create_file(name, 0444, dentry, mp, + &maxlatproc_fops); + clear_maxlatprocdata(mp); + } + entry = debugfs_create_file("reset", 0644, dentry, + (void *)TIMERANDWAKEUP_LATENCY, &latency_hist_reset_fops); + entry = debugfs_create_file("timerandwakeup", 0644, + enable_root, (void *)&timerandwakeup_enabled_data, + &enable_fops); +#endif + return 0; +} + +device_initcall(latency_hist_init); diff --git a/kernel/kernel/trace/power-traces.c b/kernel/kernel/trace/power-traces.c new file mode 100644 index 000000000..eb4220a13 --- /dev/null +++ b/kernel/kernel/trace/power-traces.c @@ -0,0 +1,18 @@ +/* + * Power trace points + * + * Copyright (C) 2009 Arjan van de Ven + */ + +#include +#include +#include +#include +#include + +#define CREATE_TRACE_POINTS +#include + +EXPORT_TRACEPOINT_SYMBOL_GPL(suspend_resume); +EXPORT_TRACEPOINT_SYMBOL_GPL(cpu_idle); + diff --git a/kernel/kernel/trace/ring_buffer.c b/kernel/kernel/trace/ring_buffer.c new file mode 100644 index 000000000..0315d4317 --- /dev/null +++ b/kernel/kernel/trace/ring_buffer.c @@ -0,0 +1,5014 @@ +/* + * Generic ring buffer + * + * Copyright (C) 2008 Steven Rostedt + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include /* for self test */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +static void update_pages_handler(struct work_struct *work); + +/* + * The ring buffer header is special. We must manually up keep it. + */ +int ring_buffer_print_entry_header(struct trace_seq *s) +{ + trace_seq_puts(s, "# compressed entry header\n"); + trace_seq_puts(s, "\ttype_len : 5 bits\n"); + trace_seq_puts(s, "\ttime_delta : 27 bits\n"); + trace_seq_puts(s, "\tarray : 32 bits\n"); + trace_seq_putc(s, '\n'); + trace_seq_printf(s, "\tpadding : type == %d\n", + RINGBUF_TYPE_PADDING); + trace_seq_printf(s, "\ttime_extend : type == %d\n", + RINGBUF_TYPE_TIME_EXTEND); + trace_seq_printf(s, "\tdata max type_len == %d\n", + RINGBUF_TYPE_DATA_TYPE_LEN_MAX); + + return !trace_seq_has_overflowed(s); +} + +/* + * The ring buffer is made up of a list of pages. A separate list of pages is + * allocated for each CPU. A writer may only write to a buffer that is + * associated with the CPU it is currently executing on. A reader may read + * from any per cpu buffer. + * + * The reader is special. For each per cpu buffer, the reader has its own + * reader page. When a reader has read the entire reader page, this reader + * page is swapped with another page in the ring buffer. + * + * Now, as long as the writer is off the reader page, the reader can do what + * ever it wants with that page. The writer will never write to that page + * again (as long as it is out of the ring buffer). + * + * Here's some silly ASCII art. + * + * +------+ + * |reader| RING BUFFER + * |page | + * +------+ +---+ +---+ +---+ + * | |-->| |-->| | + * +---+ +---+ +---+ + * ^ | + * | | + * +---------------+ + * + * + * +------+ + * |reader| RING BUFFER + * |page |------------------v + * +------+ +---+ +---+ +---+ + * | |-->| |-->| | + * +---+ +---+ +---+ + * ^ | + * | | + * +---------------+ + * + * + * +------+ + * |reader| RING BUFFER + * |page |------------------v + * +------+ +---+ +---+ +---+ + * ^ | |-->| |-->| | + * | +---+ +---+ +---+ + * | | + * | | + * +------------------------------+ + * + * + * +------+ + * |buffer| RING BUFFER + * |page |------------------v + * +------+ +---+ +---+ +---+ + * ^ | | | |-->| | + * | New +---+ +---+ +---+ + * | Reader------^ | + * | page | + * +------------------------------+ + * + * + * After we make this swap, the reader can hand this page off to the splice + * code and be done with it. It can even allocate a new page if it needs to + * and swap that into the ring buffer. + * + * We will be using cmpxchg soon to make all this lockless. + * + */ + +/* + * A fast way to enable or disable all ring buffers is to + * call tracing_on or tracing_off. Turning off the ring buffers + * prevents all ring buffers from being recorded to. + * Turning this switch on, makes it OK to write to the + * ring buffer, if the ring buffer is enabled itself. + * + * There's three layers that must be on in order to write + * to the ring buffer. + * + * 1) This global flag must be set. + * 2) The ring buffer must be enabled for recording. + * 3) The per cpu buffer must be enabled for recording. + * + * In case of an anomaly, this global flag has a bit set that + * will permantly disable all ring buffers. + */ + +/* + * Global flag to disable all recording to ring buffers + * This has two bits: ON, DISABLED + * + * ON DISABLED + * ---- ---------- + * 0 0 : ring buffers are off + * 1 0 : ring buffers are on + * X 1 : ring buffers are permanently disabled + */ + +enum { + RB_BUFFERS_ON_BIT = 0, + RB_BUFFERS_DISABLED_BIT = 1, +}; + +enum { + RB_BUFFERS_ON = 1 << RB_BUFFERS_ON_BIT, + RB_BUFFERS_DISABLED = 1 << RB_BUFFERS_DISABLED_BIT, +}; + +static unsigned long ring_buffer_flags __read_mostly = RB_BUFFERS_ON; + +/* Used for individual buffers (after the counter) */ +#define RB_BUFFER_OFF (1 << 20) + +#define BUF_PAGE_HDR_SIZE offsetof(struct buffer_data_page, data) + +/** + * tracing_off_permanent - permanently disable ring buffers + * + * This function, once called, will disable all ring buffers + * permanently. + */ +void tracing_off_permanent(void) +{ + set_bit(RB_BUFFERS_DISABLED_BIT, &ring_buffer_flags); +} + +#define RB_EVNT_HDR_SIZE (offsetof(struct ring_buffer_event, array)) +#define RB_ALIGNMENT 4U +#define RB_MAX_SMALL_DATA (RB_ALIGNMENT * RINGBUF_TYPE_DATA_TYPE_LEN_MAX) +#define RB_EVNT_MIN_SIZE 8U /* two 32bit words */ + +#ifndef CONFIG_HAVE_64BIT_ALIGNED_ACCESS +# define RB_FORCE_8BYTE_ALIGNMENT 0 +# define RB_ARCH_ALIGNMENT RB_ALIGNMENT +#else +# define RB_FORCE_8BYTE_ALIGNMENT 1 +# define RB_ARCH_ALIGNMENT 8U +#endif + +#define RB_ALIGN_DATA __aligned(RB_ARCH_ALIGNMENT) + +/* define RINGBUF_TYPE_DATA for 'case RINGBUF_TYPE_DATA:' */ +#define RINGBUF_TYPE_DATA 0 ... RINGBUF_TYPE_DATA_TYPE_LEN_MAX + +enum { + RB_LEN_TIME_EXTEND = 8, + RB_LEN_TIME_STAMP = 16, +}; + +#define skip_time_extend(event) \ + ((struct ring_buffer_event *)((char *)event + RB_LEN_TIME_EXTEND)) + +static inline int rb_null_event(struct ring_buffer_event *event) +{ + return event->type_len == RINGBUF_TYPE_PADDING && !event->time_delta; +} + +static void rb_event_set_padding(struct ring_buffer_event *event) +{ + /* padding has a NULL time_delta */ + event->type_len = RINGBUF_TYPE_PADDING; + event->time_delta = 0; +} + +static unsigned +rb_event_data_length(struct ring_buffer_event *event) +{ + unsigned length; + + if (event->type_len) + length = event->type_len * RB_ALIGNMENT; + else + length = event->array[0]; + return length + RB_EVNT_HDR_SIZE; +} + +/* + * Return the length of the given event. Will return + * the length of the time extend if the event is a + * time extend. + */ +static inline unsigned +rb_event_length(struct ring_buffer_event *event) +{ + switch (event->type_len) { + case RINGBUF_TYPE_PADDING: + if (rb_null_event(event)) + /* undefined */ + return -1; + return event->array[0] + RB_EVNT_HDR_SIZE; + + case RINGBUF_TYPE_TIME_EXTEND: + return RB_LEN_TIME_EXTEND; + + case RINGBUF_TYPE_TIME_STAMP: + return RB_LEN_TIME_STAMP; + + case RINGBUF_TYPE_DATA: + return rb_event_data_length(event); + default: + BUG(); + } + /* not hit */ + return 0; +} + +/* + * Return total length of time extend and data, + * or just the event length for all other events. + */ +static inline unsigned +rb_event_ts_length(struct ring_buffer_event *event) +{ + unsigned len = 0; + + if (event->type_len == RINGBUF_TYPE_TIME_EXTEND) { + /* time extends include the data event after it */ + len = RB_LEN_TIME_EXTEND; + event = skip_time_extend(event); + } + return len + rb_event_length(event); +} + +/** + * ring_buffer_event_length - return the length of the event + * @event: the event to get the length of + * + * Returns the size of the data load of a data event. + * If the event is something other than a data event, it + * returns the size of the event itself. With the exception + * of a TIME EXTEND, where it still returns the size of the + * data load of the data event after it. + */ +unsigned ring_buffer_event_length(struct ring_buffer_event *event) +{ + unsigned length; + + if (event->type_len == RINGBUF_TYPE_TIME_EXTEND) + event = skip_time_extend(event); + + length = rb_event_length(event); + if (event->type_len > RINGBUF_TYPE_DATA_TYPE_LEN_MAX) + return length; + length -= RB_EVNT_HDR_SIZE; + if (length > RB_MAX_SMALL_DATA + sizeof(event->array[0])) + length -= sizeof(event->array[0]); + return length; +} +EXPORT_SYMBOL_GPL(ring_buffer_event_length); + +/* inline for ring buffer fast paths */ +static void * +rb_event_data(struct ring_buffer_event *event) +{ + if (event->type_len == RINGBUF_TYPE_TIME_EXTEND) + event = skip_time_extend(event); + BUG_ON(event->type_len > RINGBUF_TYPE_DATA_TYPE_LEN_MAX); + /* If length is in len field, then array[0] has the data */ + if (event->type_len) + return (void *)&event->array[0]; + /* Otherwise length is in array[0] and array[1] has the data */ + return (void *)&event->array[1]; +} + +/** + * ring_buffer_event_data - return the data of the event + * @event: the event to get the data from + */ +void *ring_buffer_event_data(struct ring_buffer_event *event) +{ + return rb_event_data(event); +} +EXPORT_SYMBOL_GPL(ring_buffer_event_data); + +#define for_each_buffer_cpu(buffer, cpu) \ + for_each_cpu(cpu, buffer->cpumask) + +#define TS_SHIFT 27 +#define TS_MASK ((1ULL << TS_SHIFT) - 1) +#define TS_DELTA_TEST (~TS_MASK) + +/* Flag when events were overwritten */ +#define RB_MISSED_EVENTS (1 << 31) +/* Missed count stored at end */ +#define RB_MISSED_STORED (1 << 30) + +struct buffer_data_page { + u64 time_stamp; /* page time stamp */ + local_t commit; /* write committed index */ + unsigned char data[] RB_ALIGN_DATA; /* data of buffer page */ +}; + +/* + * Note, the buffer_page list must be first. The buffer pages + * are allocated in cache lines, which means that each buffer + * page will be at the beginning of a cache line, and thus + * the least significant bits will be zero. We use this to + * add flags in the list struct pointers, to make the ring buffer + * lockless. + */ +struct buffer_page { + struct list_head list; /* list of buffer pages */ + local_t write; /* index for next write */ + unsigned read; /* index for next read */ + local_t entries; /* entries on this page */ + unsigned long real_end; /* real end of data */ + struct buffer_data_page *page; /* Actual data page */ +}; + +/* + * The buffer page counters, write and entries, must be reset + * atomically when crossing page boundaries. To synchronize this + * update, two counters are inserted into the number. One is + * the actual counter for the write position or count on the page. + * + * The other is a counter of updaters. Before an update happens + * the update partition of the counter is incremented. This will + * allow the updater to update the counter atomically. + * + * The counter is 20 bits, and the state data is 12. + */ +#define RB_WRITE_MASK 0xfffff +#define RB_WRITE_INTCNT (1 << 20) + +static void rb_init_page(struct buffer_data_page *bpage) +{ + local_set(&bpage->commit, 0); +} + +/** + * ring_buffer_page_len - the size of data on the page. + * @page: The page to read + * + * Returns the amount of data on the page, including buffer page header. + */ +size_t ring_buffer_page_len(void *page) +{ + return local_read(&((struct buffer_data_page *)page)->commit) + + BUF_PAGE_HDR_SIZE; +} + +/* + * Also stolen from mm/slob.c. Thanks to Mathieu Desnoyers for pointing + * this issue out. + */ +static void free_buffer_page(struct buffer_page *bpage) +{ + free_page((unsigned long)bpage->page); + kfree(bpage); +} + +/* + * We need to fit the time_stamp delta into 27 bits. + */ +static inline int test_time_stamp(u64 delta) +{ + if (delta & TS_DELTA_TEST) + return 1; + return 0; +} + +#define BUF_PAGE_SIZE (PAGE_SIZE - BUF_PAGE_HDR_SIZE) + +/* Max payload is BUF_PAGE_SIZE - header (8bytes) */ +#define BUF_MAX_DATA_SIZE (BUF_PAGE_SIZE - (sizeof(u32) * 2)) + +int ring_buffer_print_page_header(struct trace_seq *s) +{ + struct buffer_data_page field; + + trace_seq_printf(s, "\tfield: u64 timestamp;\t" + "offset:0;\tsize:%u;\tsigned:%u;\n", + (unsigned int)sizeof(field.time_stamp), + (unsigned int)is_signed_type(u64)); + + trace_seq_printf(s, "\tfield: local_t commit;\t" + "offset:%u;\tsize:%u;\tsigned:%u;\n", + (unsigned int)offsetof(typeof(field), commit), + (unsigned int)sizeof(field.commit), + (unsigned int)is_signed_type(long)); + + trace_seq_printf(s, "\tfield: int overwrite;\t" + "offset:%u;\tsize:%u;\tsigned:%u;\n", + (unsigned int)offsetof(typeof(field), commit), + 1, + (unsigned int)is_signed_type(long)); + + trace_seq_printf(s, "\tfield: char data;\t" + "offset:%u;\tsize:%u;\tsigned:%u;\n", + (unsigned int)offsetof(typeof(field), data), + (unsigned int)BUF_PAGE_SIZE, + (unsigned int)is_signed_type(char)); + + return !trace_seq_has_overflowed(s); +} + +struct rb_irq_work { + struct irq_work work; + wait_queue_head_t waiters; + wait_queue_head_t full_waiters; + bool waiters_pending; + bool full_waiters_pending; + bool wakeup_full; +}; + +/* + * head_page == tail_page && head == tail then buffer is empty. + */ +struct ring_buffer_per_cpu { + int cpu; + atomic_t record_disabled; + struct ring_buffer *buffer; + raw_spinlock_t reader_lock; /* serialize readers */ + arch_spinlock_t lock; + struct lock_class_key lock_key; + unsigned int nr_pages; + struct list_head *pages; + struct buffer_page *head_page; /* read from head */ + struct buffer_page *tail_page; /* write to tail */ + struct buffer_page *commit_page; /* committed pages */ + struct buffer_page *reader_page; + unsigned long lost_events; + unsigned long last_overrun; + local_t entries_bytes; + local_t entries; + local_t overrun; + local_t commit_overrun; + local_t dropped_events; + local_t committing; + local_t commits; + unsigned long read; + unsigned long read_bytes; + u64 write_stamp; + u64 read_stamp; + /* ring buffer pages to update, > 0 to add, < 0 to remove */ + int nr_pages_to_update; + struct list_head new_pages; /* new pages to add */ + struct work_struct update_pages_work; + struct completion update_done; + + struct rb_irq_work irq_work; +}; + +struct ring_buffer { + unsigned flags; + int cpus; + atomic_t record_disabled; + atomic_t resize_disabled; + cpumask_var_t cpumask; + + struct lock_class_key *reader_lock_key; + + struct mutex mutex; + + struct ring_buffer_per_cpu **buffers; + +#ifdef CONFIG_HOTPLUG_CPU + struct notifier_block cpu_notify; +#endif + u64 (*clock)(void); + + struct rb_irq_work irq_work; +}; + +struct ring_buffer_iter { + struct ring_buffer_per_cpu *cpu_buffer; + unsigned long head; + struct buffer_page *head_page; + struct buffer_page *cache_reader_page; + unsigned long cache_read; + u64 read_stamp; +}; + +/* + * rb_wake_up_waiters - wake up tasks waiting for ring buffer input + * + * Schedules a delayed work to wake up any task that is blocked on the + * ring buffer waiters queue. + */ +static void rb_wake_up_waiters(struct irq_work *work) +{ + struct rb_irq_work *rbwork = container_of(work, struct rb_irq_work, work); + + wake_up_all(&rbwork->waiters); + if (rbwork->wakeup_full) { + rbwork->wakeup_full = false; + wake_up_all(&rbwork->full_waiters); + } +} + +/** + * ring_buffer_wait - wait for input to the ring buffer + * @buffer: buffer to wait on + * @cpu: the cpu buffer to wait on + * @full: wait until a full page is available, if @cpu != RING_BUFFER_ALL_CPUS + * + * If @cpu == RING_BUFFER_ALL_CPUS then the task will wake up as soon + * as data is added to any of the @buffer's cpu buffers. Otherwise + * it will wait for data to be added to a specific cpu buffer. + */ +int ring_buffer_wait(struct ring_buffer *buffer, int cpu, bool full) +{ + struct ring_buffer_per_cpu *uninitialized_var(cpu_buffer); + DEFINE_WAIT(wait); + struct rb_irq_work *work; + int ret = 0; + + /* + * Depending on what the caller is waiting for, either any + * data in any cpu buffer, or a specific buffer, put the + * caller on the appropriate wait queue. + */ + if (cpu == RING_BUFFER_ALL_CPUS) { + work = &buffer->irq_work; + /* Full only makes sense on per cpu reads */ + full = false; + } else { + if (!cpumask_test_cpu(cpu, buffer->cpumask)) + return -ENODEV; + cpu_buffer = buffer->buffers[cpu]; + work = &cpu_buffer->irq_work; + } + + + while (true) { + if (full) + prepare_to_wait(&work->full_waiters, &wait, TASK_INTERRUPTIBLE); + else + prepare_to_wait(&work->waiters, &wait, TASK_INTERRUPTIBLE); + + /* + * The events can happen in critical sections where + * checking a work queue can cause deadlocks. + * After adding a task to the queue, this flag is set + * only to notify events to try to wake up the queue + * using irq_work. + * + * We don't clear it even if the buffer is no longer + * empty. The flag only causes the next event to run + * irq_work to do the work queue wake up. The worse + * that can happen if we race with !trace_empty() is that + * an event will cause an irq_work to try to wake up + * an empty queue. + * + * There's no reason to protect this flag either, as + * the work queue and irq_work logic will do the necessary + * synchronization for the wake ups. The only thing + * that is necessary is that the wake up happens after + * a task has been queued. It's OK for spurious wake ups. + */ + if (full) + work->full_waiters_pending = true; + else + work->waiters_pending = true; + + if (signal_pending(current)) { + ret = -EINTR; + break; + } + + if (cpu == RING_BUFFER_ALL_CPUS && !ring_buffer_empty(buffer)) + break; + + if (cpu != RING_BUFFER_ALL_CPUS && + !ring_buffer_empty_cpu(buffer, cpu)) { + unsigned long flags; + bool pagebusy; + + if (!full) + break; + + raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); + pagebusy = cpu_buffer->reader_page == cpu_buffer->commit_page; + raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); + + if (!pagebusy) + break; + } + + schedule(); + } + + if (full) + finish_wait(&work->full_waiters, &wait); + else + finish_wait(&work->waiters, &wait); + + return ret; +} + +/** + * ring_buffer_poll_wait - poll on buffer input + * @buffer: buffer to wait on + * @cpu: the cpu buffer to wait on + * @filp: the file descriptor + * @poll_table: The poll descriptor + * + * If @cpu == RING_BUFFER_ALL_CPUS then the task will wake up as soon + * as data is added to any of the @buffer's cpu buffers. Otherwise + * it will wait for data to be added to a specific cpu buffer. + * + * Returns POLLIN | POLLRDNORM if data exists in the buffers, + * zero otherwise. + */ +int ring_buffer_poll_wait(struct ring_buffer *buffer, int cpu, + struct file *filp, poll_table *poll_table) +{ + struct ring_buffer_per_cpu *cpu_buffer; + struct rb_irq_work *work; + + if (cpu == RING_BUFFER_ALL_CPUS) + work = &buffer->irq_work; + else { + if (!cpumask_test_cpu(cpu, buffer->cpumask)) + return -EINVAL; + + cpu_buffer = buffer->buffers[cpu]; + work = &cpu_buffer->irq_work; + } + + poll_wait(filp, &work->waiters, poll_table); + work->waiters_pending = true; + /* + * There's a tight race between setting the waiters_pending and + * checking if the ring buffer is empty. Once the waiters_pending bit + * is set, the next event will wake the task up, but we can get stuck + * if there's only a single event in. + * + * FIXME: Ideally, we need a memory barrier on the writer side as well, + * but adding a memory barrier to all events will cause too much of a + * performance hit in the fast path. We only need a memory barrier when + * the buffer goes from empty to having content. But as this race is + * extremely small, and it's not a problem if another event comes in, we + * will fix it later. + */ + smp_mb(); + + if ((cpu == RING_BUFFER_ALL_CPUS && !ring_buffer_empty(buffer)) || + (cpu != RING_BUFFER_ALL_CPUS && !ring_buffer_empty_cpu(buffer, cpu))) + return POLLIN | POLLRDNORM; + return 0; +} + +/* buffer may be either ring_buffer or ring_buffer_per_cpu */ +#define RB_WARN_ON(b, cond) \ + ({ \ + int _____ret = unlikely(cond); \ + if (_____ret) { \ + if (__same_type(*(b), struct ring_buffer_per_cpu)) { \ + struct ring_buffer_per_cpu *__b = \ + (void *)b; \ + atomic_inc(&__b->buffer->record_disabled); \ + } else \ + atomic_inc(&b->record_disabled); \ + WARN_ON(1); \ + } \ + _____ret; \ + }) + +/* Up this if you want to test the TIME_EXTENTS and normalization */ +#define DEBUG_SHIFT 0 + +static inline u64 rb_time_stamp(struct ring_buffer *buffer) +{ + /* shift to debug/test normalization and TIME_EXTENTS */ + return buffer->clock() << DEBUG_SHIFT; +} + +u64 ring_buffer_time_stamp(struct ring_buffer *buffer, int cpu) +{ + u64 time; + + preempt_disable_notrace(); + time = rb_time_stamp(buffer); + preempt_enable_no_resched_notrace(); + + return time; +} +EXPORT_SYMBOL_GPL(ring_buffer_time_stamp); + +void ring_buffer_normalize_time_stamp(struct ring_buffer *buffer, + int cpu, u64 *ts) +{ + /* Just stupid testing the normalize function and deltas */ + *ts >>= DEBUG_SHIFT; +} +EXPORT_SYMBOL_GPL(ring_buffer_normalize_time_stamp); + +/* + * Making the ring buffer lockless makes things tricky. + * Although writes only happen on the CPU that they are on, + * and they only need to worry about interrupts. Reads can + * happen on any CPU. + * + * The reader page is always off the ring buffer, but when the + * reader finishes with a page, it needs to swap its page with + * a new one from the buffer. The reader needs to take from + * the head (writes go to the tail). But if a writer is in overwrite + * mode and wraps, it must push the head page forward. + * + * Here lies the problem. + * + * The reader must be careful to replace only the head page, and + * not another one. As described at the top of the file in the + * ASCII art, the reader sets its old page to point to the next + * page after head. It then sets the page after head to point to + * the old reader page. But if the writer moves the head page + * during this operation, the reader could end up with the tail. + * + * We use cmpxchg to help prevent this race. We also do something + * special with the page before head. We set the LSB to 1. + * + * When the writer must push the page forward, it will clear the + * bit that points to the head page, move the head, and then set + * the bit that points to the new head page. + * + * We also don't want an interrupt coming in and moving the head + * page on another writer. Thus we use the second LSB to catch + * that too. Thus: + * + * head->list->prev->next bit 1 bit 0 + * ------- ------- + * Normal page 0 0 + * Points to head page 0 1 + * New head page 1 0 + * + * Note we can not trust the prev pointer of the head page, because: + * + * +----+ +-----+ +-----+ + * | |------>| T |---X--->| N | + * | |<------| | | | + * +----+ +-----+ +-----+ + * ^ ^ | + * | +-----+ | | + * +----------| R |----------+ | + * | |<-----------+ + * +-----+ + * + * Key: ---X--> HEAD flag set in pointer + * T Tail page + * R Reader page + * N Next page + * + * (see __rb_reserve_next() to see where this happens) + * + * What the above shows is that the reader just swapped out + * the reader page with a page in the buffer, but before it + * could make the new header point back to the new page added + * it was preempted by a writer. The writer moved forward onto + * the new page added by the reader and is about to move forward + * again. + * + * You can see, it is legitimate for the previous pointer of + * the head (or any page) not to point back to itself. But only + * temporarially. + */ + +#define RB_PAGE_NORMAL 0UL +#define RB_PAGE_HEAD 1UL +#define RB_PAGE_UPDATE 2UL + + +#define RB_FLAG_MASK 3UL + +/* PAGE_MOVED is not part of the mask */ +#define RB_PAGE_MOVED 4UL + +/* + * rb_list_head - remove any bit + */ +static struct list_head *rb_list_head(struct list_head *list) +{ + unsigned long val = (unsigned long)list; + + return (struct list_head *)(val & ~RB_FLAG_MASK); +} + +/* + * rb_is_head_page - test if the given page is the head page + * + * Because the reader may move the head_page pointer, we can + * not trust what the head page is (it may be pointing to + * the reader page). But if the next page is a header page, + * its flags will be non zero. + */ +static inline int +rb_is_head_page(struct ring_buffer_per_cpu *cpu_buffer, + struct buffer_page *page, struct list_head *list) +{ + unsigned long val; + + val = (unsigned long)list->next; + + if ((val & ~RB_FLAG_MASK) != (unsigned long)&page->list) + return RB_PAGE_MOVED; + + return val & RB_FLAG_MASK; +} + +/* + * rb_is_reader_page + * + * The unique thing about the reader page, is that, if the + * writer is ever on it, the previous pointer never points + * back to the reader page. + */ +static int rb_is_reader_page(struct buffer_page *page) +{ + struct list_head *list = page->list.prev; + + return rb_list_head(list->next) != &page->list; +} + +/* + * rb_set_list_to_head - set a list_head to be pointing to head. + */ +static void rb_set_list_to_head(struct ring_buffer_per_cpu *cpu_buffer, + struct list_head *list) +{ + unsigned long *ptr; + + ptr = (unsigned long *)&list->next; + *ptr |= RB_PAGE_HEAD; + *ptr &= ~RB_PAGE_UPDATE; +} + +/* + * rb_head_page_activate - sets up head page + */ +static void rb_head_page_activate(struct ring_buffer_per_cpu *cpu_buffer) +{ + struct buffer_page *head; + + head = cpu_buffer->head_page; + if (!head) + return; + + /* + * Set the previous list pointer to have the HEAD flag. + */ + rb_set_list_to_head(cpu_buffer, head->list.prev); +} + +static void rb_list_head_clear(struct list_head *list) +{ + unsigned long *ptr = (unsigned long *)&list->next; + + *ptr &= ~RB_FLAG_MASK; +} + +/* + * rb_head_page_dactivate - clears head page ptr (for free list) + */ +static void +rb_head_page_deactivate(struct ring_buffer_per_cpu *cpu_buffer) +{ + struct list_head *hd; + + /* Go through the whole list and clear any pointers found. */ + rb_list_head_clear(cpu_buffer->pages); + + list_for_each(hd, cpu_buffer->pages) + rb_list_head_clear(hd); +} + +static int rb_head_page_set(struct ring_buffer_per_cpu *cpu_buffer, + struct buffer_page *head, + struct buffer_page *prev, + int old_flag, int new_flag) +{ + struct list_head *list; + unsigned long val = (unsigned long)&head->list; + unsigned long ret; + + list = &prev->list; + + val &= ~RB_FLAG_MASK; + + ret = cmpxchg((unsigned long *)&list->next, + val | old_flag, val | new_flag); + + /* check if the reader took the page */ + if ((ret & ~RB_FLAG_MASK) != val) + return RB_PAGE_MOVED; + + return ret & RB_FLAG_MASK; +} + +static int rb_head_page_set_update(struct ring_buffer_per_cpu *cpu_buffer, + struct buffer_page *head, + struct buffer_page *prev, + int old_flag) +{ + return rb_head_page_set(cpu_buffer, head, prev, + old_flag, RB_PAGE_UPDATE); +} + +static int rb_head_page_set_head(struct ring_buffer_per_cpu *cpu_buffer, + struct buffer_page *head, + struct buffer_page *prev, + int old_flag) +{ + return rb_head_page_set(cpu_buffer, head, prev, + old_flag, RB_PAGE_HEAD); +} + +static int rb_head_page_set_normal(struct ring_buffer_per_cpu *cpu_buffer, + struct buffer_page *head, + struct buffer_page *prev, + int old_flag) +{ + return rb_head_page_set(cpu_buffer, head, prev, + old_flag, RB_PAGE_NORMAL); +} + +static inline void rb_inc_page(struct ring_buffer_per_cpu *cpu_buffer, + struct buffer_page **bpage) +{ + struct list_head *p = rb_list_head((*bpage)->list.next); + + *bpage = list_entry(p, struct buffer_page, list); +} + +static struct buffer_page * +rb_set_head_page(struct ring_buffer_per_cpu *cpu_buffer) +{ + struct buffer_page *head; + struct buffer_page *page; + struct list_head *list; + int i; + + if (RB_WARN_ON(cpu_buffer, !cpu_buffer->head_page)) + return NULL; + + /* sanity check */ + list = cpu_buffer->pages; + if (RB_WARN_ON(cpu_buffer, rb_list_head(list->prev->next) != list)) + return NULL; + + page = head = cpu_buffer->head_page; + /* + * It is possible that the writer moves the header behind + * where we started, and we miss in one loop. + * A second loop should grab the header, but we'll do + * three loops just because I'm paranoid. + */ + for (i = 0; i < 3; i++) { + do { + if (rb_is_head_page(cpu_buffer, page, page->list.prev)) { + cpu_buffer->head_page = page; + return page; + } + rb_inc_page(cpu_buffer, &page); + } while (page != head); + } + + RB_WARN_ON(cpu_buffer, 1); + + return NULL; +} + +static int rb_head_page_replace(struct buffer_page *old, + struct buffer_page *new) +{ + unsigned long *ptr = (unsigned long *)&old->list.prev->next; + unsigned long val; + unsigned long ret; + + val = *ptr & ~RB_FLAG_MASK; + val |= RB_PAGE_HEAD; + + ret = cmpxchg(ptr, val, (unsigned long)&new->list); + + return ret == val; +} + +/* + * rb_tail_page_update - move the tail page forward + * + * Returns 1 if moved tail page, 0 if someone else did. + */ +static int rb_tail_page_update(struct ring_buffer_per_cpu *cpu_buffer, + struct buffer_page *tail_page, + struct buffer_page *next_page) +{ + struct buffer_page *old_tail; + unsigned long old_entries; + unsigned long old_write; + int ret = 0; + + /* + * The tail page now needs to be moved forward. + * + * We need to reset the tail page, but without messing + * with possible erasing of data brought in by interrupts + * that have moved the tail page and are currently on it. + * + * We add a counter to the write field to denote this. + */ + old_write = local_add_return(RB_WRITE_INTCNT, &next_page->write); + old_entries = local_add_return(RB_WRITE_INTCNT, &next_page->entries); + + /* + * Just make sure we have seen our old_write and synchronize + * with any interrupts that come in. + */ + barrier(); + + /* + * If the tail page is still the same as what we think + * it is, then it is up to us to update the tail + * pointer. + */ + if (tail_page == cpu_buffer->tail_page) { + /* Zero the write counter */ + unsigned long val = old_write & ~RB_WRITE_MASK; + unsigned long eval = old_entries & ~RB_WRITE_MASK; + + /* + * This will only succeed if an interrupt did + * not come in and change it. In which case, we + * do not want to modify it. + * + * We add (void) to let the compiler know that we do not care + * about the return value of these functions. We use the + * cmpxchg to only update if an interrupt did not already + * do it for us. If the cmpxchg fails, we don't care. + */ + (void)local_cmpxchg(&next_page->write, old_write, val); + (void)local_cmpxchg(&next_page->entries, old_entries, eval); + + /* + * No need to worry about races with clearing out the commit. + * it only can increment when a commit takes place. But that + * only happens in the outer most nested commit. + */ + local_set(&next_page->page->commit, 0); + + old_tail = cmpxchg(&cpu_buffer->tail_page, + tail_page, next_page); + + if (old_tail == tail_page) + ret = 1; + } + + return ret; +} + +static int rb_check_bpage(struct ring_buffer_per_cpu *cpu_buffer, + struct buffer_page *bpage) +{ + unsigned long val = (unsigned long)bpage; + + if (RB_WARN_ON(cpu_buffer, val & RB_FLAG_MASK)) + return 1; + + return 0; +} + +/** + * rb_check_list - make sure a pointer to a list has the last bits zero + */ +static int rb_check_list(struct ring_buffer_per_cpu *cpu_buffer, + struct list_head *list) +{ + if (RB_WARN_ON(cpu_buffer, rb_list_head(list->prev) != list->prev)) + return 1; + if (RB_WARN_ON(cpu_buffer, rb_list_head(list->next) != list->next)) + return 1; + return 0; +} + +/** + * rb_check_pages - integrity check of buffer pages + * @cpu_buffer: CPU buffer with pages to test + * + * As a safety measure we check to make sure the data pages have not + * been corrupted. + */ +static int rb_check_pages(struct ring_buffer_per_cpu *cpu_buffer) +{ + struct list_head *head = cpu_buffer->pages; + struct buffer_page *bpage, *tmp; + + /* Reset the head page if it exists */ + if (cpu_buffer->head_page) + rb_set_head_page(cpu_buffer); + + rb_head_page_deactivate(cpu_buffer); + + if (RB_WARN_ON(cpu_buffer, head->next->prev != head)) + return -1; + if (RB_WARN_ON(cpu_buffer, head->prev->next != head)) + return -1; + + if (rb_check_list(cpu_buffer, head)) + return -1; + + list_for_each_entry_safe(bpage, tmp, head, list) { + if (RB_WARN_ON(cpu_buffer, + bpage->list.next->prev != &bpage->list)) + return -1; + if (RB_WARN_ON(cpu_buffer, + bpage->list.prev->next != &bpage->list)) + return -1; + if (rb_check_list(cpu_buffer, &bpage->list)) + return -1; + } + + rb_head_page_activate(cpu_buffer); + + return 0; +} + +static int __rb_allocate_pages(int nr_pages, struct list_head *pages, int cpu) +{ + int i; + struct buffer_page *bpage, *tmp; + + for (i = 0; i < nr_pages; i++) { + struct page *page; + /* + * __GFP_NORETRY flag makes sure that the allocation fails + * gracefully without invoking oom-killer and the system is + * not destabilized. + */ + bpage = kzalloc_node(ALIGN(sizeof(*bpage), cache_line_size()), + GFP_KERNEL | __GFP_NORETRY, + cpu_to_node(cpu)); + if (!bpage) + goto free_pages; + + list_add(&bpage->list, pages); + + page = alloc_pages_node(cpu_to_node(cpu), + GFP_KERNEL | __GFP_NORETRY, 0); + if (!page) + goto free_pages; + bpage->page = page_address(page); + rb_init_page(bpage->page); + } + + return 0; + +free_pages: + list_for_each_entry_safe(bpage, tmp, pages, list) { + list_del_init(&bpage->list); + free_buffer_page(bpage); + } + + return -ENOMEM; +} + +static int rb_allocate_pages(struct ring_buffer_per_cpu *cpu_buffer, + unsigned nr_pages) +{ + LIST_HEAD(pages); + + WARN_ON(!nr_pages); + + if (__rb_allocate_pages(nr_pages, &pages, cpu_buffer->cpu)) + return -ENOMEM; + + /* + * The ring buffer page list is a circular list that does not + * start and end with a list head. All page list items point to + * other pages. + */ + cpu_buffer->pages = pages.next; + list_del(&pages); + + cpu_buffer->nr_pages = nr_pages; + + rb_check_pages(cpu_buffer); + + return 0; +} + +static struct ring_buffer_per_cpu * +rb_allocate_cpu_buffer(struct ring_buffer *buffer, int nr_pages, int cpu) +{ + struct ring_buffer_per_cpu *cpu_buffer; + struct buffer_page *bpage; + struct page *page; + int ret; + + cpu_buffer = kzalloc_node(ALIGN(sizeof(*cpu_buffer), cache_line_size()), + GFP_KERNEL, cpu_to_node(cpu)); + if (!cpu_buffer) + return NULL; + + cpu_buffer->cpu = cpu; + cpu_buffer->buffer = buffer; + raw_spin_lock_init(&cpu_buffer->reader_lock); + lockdep_set_class(&cpu_buffer->reader_lock, buffer->reader_lock_key); + cpu_buffer->lock = (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED; + INIT_WORK(&cpu_buffer->update_pages_work, update_pages_handler); + init_completion(&cpu_buffer->update_done); + init_irq_work(&cpu_buffer->irq_work.work, rb_wake_up_waiters); + init_waitqueue_head(&cpu_buffer->irq_work.waiters); + init_waitqueue_head(&cpu_buffer->irq_work.full_waiters); + + bpage = kzalloc_node(ALIGN(sizeof(*bpage), cache_line_size()), + GFP_KERNEL, cpu_to_node(cpu)); + if (!bpage) + goto fail_free_buffer; + + rb_check_bpage(cpu_buffer, bpage); + + cpu_buffer->reader_page = bpage; + page = alloc_pages_node(cpu_to_node(cpu), GFP_KERNEL, 0); + if (!page) + goto fail_free_reader; + bpage->page = page_address(page); + rb_init_page(bpage->page); + + INIT_LIST_HEAD(&cpu_buffer->reader_page->list); + INIT_LIST_HEAD(&cpu_buffer->new_pages); + + ret = rb_allocate_pages(cpu_buffer, nr_pages); + if (ret < 0) + goto fail_free_reader; + + cpu_buffer->head_page + = list_entry(cpu_buffer->pages, struct buffer_page, list); + cpu_buffer->tail_page = cpu_buffer->commit_page = cpu_buffer->head_page; + + rb_head_page_activate(cpu_buffer); + + return cpu_buffer; + + fail_free_reader: + free_buffer_page(cpu_buffer->reader_page); + + fail_free_buffer: + kfree(cpu_buffer); + return NULL; +} + +static void rb_free_cpu_buffer(struct ring_buffer_per_cpu *cpu_buffer) +{ + struct list_head *head = cpu_buffer->pages; + struct buffer_page *bpage, *tmp; + + free_buffer_page(cpu_buffer->reader_page); + + rb_head_page_deactivate(cpu_buffer); + + if (head) { + list_for_each_entry_safe(bpage, tmp, head, list) { + list_del_init(&bpage->list); + free_buffer_page(bpage); + } + bpage = list_entry(head, struct buffer_page, list); + free_buffer_page(bpage); + } + + kfree(cpu_buffer); +} + +#ifdef CONFIG_HOTPLUG_CPU +static int rb_cpu_notify(struct notifier_block *self, + unsigned long action, void *hcpu); +#endif + +/** + * __ring_buffer_alloc - allocate a new ring_buffer + * @size: the size in bytes per cpu that is needed. + * @flags: attributes to set for the ring buffer. + * + * Currently the only flag that is available is the RB_FL_OVERWRITE + * flag. This flag means that the buffer will overwrite old data + * when the buffer wraps. If this flag is not set, the buffer will + * drop data when the tail hits the head. + */ +struct ring_buffer *__ring_buffer_alloc(unsigned long size, unsigned flags, + struct lock_class_key *key) +{ + struct ring_buffer *buffer; + int bsize; + int cpu, nr_pages; + + /* keep it in its own cache line */ + buffer = kzalloc(ALIGN(sizeof(*buffer), cache_line_size()), + GFP_KERNEL); + if (!buffer) + return NULL; + + if (!alloc_cpumask_var(&buffer->cpumask, GFP_KERNEL)) + goto fail_free_buffer; + + nr_pages = DIV_ROUND_UP(size, BUF_PAGE_SIZE); + buffer->flags = flags; + buffer->clock = trace_clock_local; + buffer->reader_lock_key = key; + + init_irq_work(&buffer->irq_work.work, rb_wake_up_waiters); + init_waitqueue_head(&buffer->irq_work.waiters); + + /* need at least two pages */ + if (nr_pages < 2) + nr_pages = 2; + + /* + * In case of non-hotplug cpu, if the ring-buffer is allocated + * in early initcall, it will not be notified of secondary cpus. + * In that off case, we need to allocate for all possible cpus. + */ +#ifdef CONFIG_HOTPLUG_CPU + cpu_notifier_register_begin(); + cpumask_copy(buffer->cpumask, cpu_online_mask); +#else + cpumask_copy(buffer->cpumask, cpu_possible_mask); +#endif + buffer->cpus = nr_cpu_ids; + + bsize = sizeof(void *) * nr_cpu_ids; + buffer->buffers = kzalloc(ALIGN(bsize, cache_line_size()), + GFP_KERNEL); + if (!buffer->buffers) + goto fail_free_cpumask; + + for_each_buffer_cpu(buffer, cpu) { + buffer->buffers[cpu] = + rb_allocate_cpu_buffer(buffer, nr_pages, cpu); + if (!buffer->buffers[cpu]) + goto fail_free_buffers; + } + +#ifdef CONFIG_HOTPLUG_CPU + buffer->cpu_notify.notifier_call = rb_cpu_notify; + buffer->cpu_notify.priority = 0; + __register_cpu_notifier(&buffer->cpu_notify); + cpu_notifier_register_done(); +#endif + + mutex_init(&buffer->mutex); + + return buffer; + + fail_free_buffers: + for_each_buffer_cpu(buffer, cpu) { + if (buffer->buffers[cpu]) + rb_free_cpu_buffer(buffer->buffers[cpu]); + } + kfree(buffer->buffers); + + fail_free_cpumask: + free_cpumask_var(buffer->cpumask); +#ifdef CONFIG_HOTPLUG_CPU + cpu_notifier_register_done(); +#endif + + fail_free_buffer: + kfree(buffer); + return NULL; +} +EXPORT_SYMBOL_GPL(__ring_buffer_alloc); + +/** + * ring_buffer_free - free a ring buffer. + * @buffer: the buffer to free. + */ +void +ring_buffer_free(struct ring_buffer *buffer) +{ + int cpu; + +#ifdef CONFIG_HOTPLUG_CPU + cpu_notifier_register_begin(); + __unregister_cpu_notifier(&buffer->cpu_notify); +#endif + + for_each_buffer_cpu(buffer, cpu) + rb_free_cpu_buffer(buffer->buffers[cpu]); + +#ifdef CONFIG_HOTPLUG_CPU + cpu_notifier_register_done(); +#endif + + kfree(buffer->buffers); + free_cpumask_var(buffer->cpumask); + + kfree(buffer); +} +EXPORT_SYMBOL_GPL(ring_buffer_free); + +void ring_buffer_set_clock(struct ring_buffer *buffer, + u64 (*clock)(void)) +{ + buffer->clock = clock; +} + +static void rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer); + +static inline unsigned long rb_page_entries(struct buffer_page *bpage) +{ + return local_read(&bpage->entries) & RB_WRITE_MASK; +} + +static inline unsigned long rb_page_write(struct buffer_page *bpage) +{ + return local_read(&bpage->write) & RB_WRITE_MASK; +} + +static int +rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned int nr_pages) +{ + struct list_head *tail_page, *to_remove, *next_page; + struct buffer_page *to_remove_page, *tmp_iter_page; + struct buffer_page *last_page, *first_page; + unsigned int nr_removed; + unsigned long head_bit; + int page_entries; + + head_bit = 0; + + raw_spin_lock_irq(&cpu_buffer->reader_lock); + atomic_inc(&cpu_buffer->record_disabled); + /* + * We don't race with the readers since we have acquired the reader + * lock. We also don't race with writers after disabling recording. + * This makes it easy to figure out the first and the last page to be + * removed from the list. We unlink all the pages in between including + * the first and last pages. This is done in a busy loop so that we + * lose the least number of traces. + * The pages are freed after we restart recording and unlock readers. + */ + tail_page = &cpu_buffer->tail_page->list; + + /* + * tail page might be on reader page, we remove the next page + * from the ring buffer + */ + if (cpu_buffer->tail_page == cpu_buffer->reader_page) + tail_page = rb_list_head(tail_page->next); + to_remove = tail_page; + + /* start of pages to remove */ + first_page = list_entry(rb_list_head(to_remove->next), + struct buffer_page, list); + + for (nr_removed = 0; nr_removed < nr_pages; nr_removed++) { + to_remove = rb_list_head(to_remove)->next; + head_bit |= (unsigned long)to_remove & RB_PAGE_HEAD; + } + + next_page = rb_list_head(to_remove)->next; + + /* + * Now we remove all pages between tail_page and next_page. + * Make sure that we have head_bit value preserved for the + * next page + */ + tail_page->next = (struct list_head *)((unsigned long)next_page | + head_bit); + next_page = rb_list_head(next_page); + next_page->prev = tail_page; + + /* make sure pages points to a valid page in the ring buffer */ + cpu_buffer->pages = next_page; + + /* update head page */ + if (head_bit) + cpu_buffer->head_page = list_entry(next_page, + struct buffer_page, list); + + /* + * change read pointer to make sure any read iterators reset + * themselves + */ + cpu_buffer->read = 0; + + /* pages are removed, resume tracing and then free the pages */ + atomic_dec(&cpu_buffer->record_disabled); + raw_spin_unlock_irq(&cpu_buffer->reader_lock); + + RB_WARN_ON(cpu_buffer, list_empty(cpu_buffer->pages)); + + /* last buffer page to remove */ + last_page = list_entry(rb_list_head(to_remove), struct buffer_page, + list); + tmp_iter_page = first_page; + + do { + to_remove_page = tmp_iter_page; + rb_inc_page(cpu_buffer, &tmp_iter_page); + + /* update the counters */ + page_entries = rb_page_entries(to_remove_page); + if (page_entries) { + /* + * If something was added to this page, it was full + * since it is not the tail page. So we deduct the + * bytes consumed in ring buffer from here. + * Increment overrun to account for the lost events. + */ + local_add(page_entries, &cpu_buffer->overrun); + local_sub(BUF_PAGE_SIZE, &cpu_buffer->entries_bytes); + } + + /* + * We have already removed references to this list item, just + * free up the buffer_page and its page + */ + free_buffer_page(to_remove_page); + nr_removed--; + + } while (to_remove_page != last_page); + + RB_WARN_ON(cpu_buffer, nr_removed); + + return nr_removed == 0; +} + +static int +rb_insert_pages(struct ring_buffer_per_cpu *cpu_buffer) +{ + struct list_head *pages = &cpu_buffer->new_pages; + int retries, success; + + raw_spin_lock_irq(&cpu_buffer->reader_lock); + /* + * We are holding the reader lock, so the reader page won't be swapped + * in the ring buffer. Now we are racing with the writer trying to + * move head page and the tail page. + * We are going to adapt the reader page update process where: + * 1. We first splice the start and end of list of new pages between + * the head page and its previous page. + * 2. We cmpxchg the prev_page->next to point from head page to the + * start of new pages list. + * 3. Finally, we update the head->prev to the end of new list. + * + * We will try this process 10 times, to make sure that we don't keep + * spinning. + */ + retries = 10; + success = 0; + while (retries--) { + struct list_head *head_page, *prev_page, *r; + struct list_head *last_page, *first_page; + struct list_head *head_page_with_bit; + + head_page = &rb_set_head_page(cpu_buffer)->list; + if (!head_page) + break; + prev_page = head_page->prev; + + first_page = pages->next; + last_page = pages->prev; + + head_page_with_bit = (struct list_head *) + ((unsigned long)head_page | RB_PAGE_HEAD); + + last_page->next = head_page_with_bit; + first_page->prev = prev_page; + + r = cmpxchg(&prev_page->next, head_page_with_bit, first_page); + + if (r == head_page_with_bit) { + /* + * yay, we replaced the page pointer to our new list, + * now, we just have to update to head page's prev + * pointer to point to end of list + */ + head_page->prev = last_page; + success = 1; + break; + } + } + + if (success) + INIT_LIST_HEAD(pages); + /* + * If we weren't successful in adding in new pages, warn and stop + * tracing + */ + RB_WARN_ON(cpu_buffer, !success); + raw_spin_unlock_irq(&cpu_buffer->reader_lock); + + /* free pages if they weren't inserted */ + if (!success) { + struct buffer_page *bpage, *tmp; + list_for_each_entry_safe(bpage, tmp, &cpu_buffer->new_pages, + list) { + list_del_init(&bpage->list); + free_buffer_page(bpage); + } + } + return success; +} + +static void rb_update_pages(struct ring_buffer_per_cpu *cpu_buffer) +{ + int success; + + if (cpu_buffer->nr_pages_to_update > 0) + success = rb_insert_pages(cpu_buffer); + else + success = rb_remove_pages(cpu_buffer, + -cpu_buffer->nr_pages_to_update); + + if (success) + cpu_buffer->nr_pages += cpu_buffer->nr_pages_to_update; +} + +static void update_pages_handler(struct work_struct *work) +{ + struct ring_buffer_per_cpu *cpu_buffer = container_of(work, + struct ring_buffer_per_cpu, update_pages_work); + rb_update_pages(cpu_buffer); + complete(&cpu_buffer->update_done); +} + +/** + * ring_buffer_resize - resize the ring buffer + * @buffer: the buffer to resize. + * @size: the new size. + * @cpu_id: the cpu buffer to resize + * + * Minimum size is 2 * BUF_PAGE_SIZE. + * + * Returns 0 on success and < 0 on failure. + */ +int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size, + int cpu_id) +{ + struct ring_buffer_per_cpu *cpu_buffer; + unsigned nr_pages; + int cpu, err = 0; + + /* + * Always succeed at resizing a non-existent buffer: + */ + if (!buffer) + return size; + + /* Make sure the requested buffer exists */ + if (cpu_id != RING_BUFFER_ALL_CPUS && + !cpumask_test_cpu(cpu_id, buffer->cpumask)) + return size; + + size = DIV_ROUND_UP(size, BUF_PAGE_SIZE); + size *= BUF_PAGE_SIZE; + + /* we need a minimum of two pages */ + if (size < BUF_PAGE_SIZE * 2) + size = BUF_PAGE_SIZE * 2; + + nr_pages = DIV_ROUND_UP(size, BUF_PAGE_SIZE); + + /* + * Don't succeed if resizing is disabled, as a reader might be + * manipulating the ring buffer and is expecting a sane state while + * this is true. + */ + if (atomic_read(&buffer->resize_disabled)) + return -EBUSY; + + /* prevent another thread from changing buffer sizes */ + mutex_lock(&buffer->mutex); + + if (cpu_id == RING_BUFFER_ALL_CPUS) { + /* calculate the pages to update */ + for_each_buffer_cpu(buffer, cpu) { + cpu_buffer = buffer->buffers[cpu]; + + cpu_buffer->nr_pages_to_update = nr_pages - + cpu_buffer->nr_pages; + /* + * nothing more to do for removing pages or no update + */ + if (cpu_buffer->nr_pages_to_update <= 0) + continue; + /* + * to add pages, make sure all new pages can be + * allocated without receiving ENOMEM + */ + INIT_LIST_HEAD(&cpu_buffer->new_pages); + if (__rb_allocate_pages(cpu_buffer->nr_pages_to_update, + &cpu_buffer->new_pages, cpu)) { + /* not enough memory for new pages */ + err = -ENOMEM; + goto out_err; + } + } + + get_online_cpus(); + /* + * Fire off all the required work handlers + * We can't schedule on offline CPUs, but it's not necessary + * since we can change their buffer sizes without any race. + */ + for_each_buffer_cpu(buffer, cpu) { + cpu_buffer = buffer->buffers[cpu]; + if (!cpu_buffer->nr_pages_to_update) + continue; + + /* Can't run something on an offline CPU. */ + if (!cpu_online(cpu)) { + rb_update_pages(cpu_buffer); + cpu_buffer->nr_pages_to_update = 0; + } else { + schedule_work_on(cpu, + &cpu_buffer->update_pages_work); + } + } + + /* wait for all the updates to complete */ + for_each_buffer_cpu(buffer, cpu) { + cpu_buffer = buffer->buffers[cpu]; + if (!cpu_buffer->nr_pages_to_update) + continue; + + if (cpu_online(cpu)) + wait_for_completion(&cpu_buffer->update_done); + cpu_buffer->nr_pages_to_update = 0; + } + + put_online_cpus(); + } else { + /* Make sure this CPU has been intitialized */ + if (!cpumask_test_cpu(cpu_id, buffer->cpumask)) + goto out; + + cpu_buffer = buffer->buffers[cpu_id]; + + if (nr_pages == cpu_buffer->nr_pages) + goto out; + + cpu_buffer->nr_pages_to_update = nr_pages - + cpu_buffer->nr_pages; + + INIT_LIST_HEAD(&cpu_buffer->new_pages); + if (cpu_buffer->nr_pages_to_update > 0 && + __rb_allocate_pages(cpu_buffer->nr_pages_to_update, + &cpu_buffer->new_pages, cpu_id)) { + err = -ENOMEM; + goto out_err; + } + + get_online_cpus(); + + /* Can't run something on an offline CPU. */ + if (!cpu_online(cpu_id)) + rb_update_pages(cpu_buffer); + else { + schedule_work_on(cpu_id, + &cpu_buffer->update_pages_work); + wait_for_completion(&cpu_buffer->update_done); + } + + cpu_buffer->nr_pages_to_update = 0; + put_online_cpus(); + } + + out: + /* + * The ring buffer resize can happen with the ring buffer + * enabled, so that the update disturbs the tracing as little + * as possible. But if the buffer is disabled, we do not need + * to worry about that, and we can take the time to verify + * that the buffer is not corrupt. + */ + if (atomic_read(&buffer->record_disabled)) { + atomic_inc(&buffer->record_disabled); + /* + * Even though the buffer was disabled, we must make sure + * that it is truly disabled before calling rb_check_pages. + * There could have been a race between checking + * record_disable and incrementing it. + */ + synchronize_sched(); + for_each_buffer_cpu(buffer, cpu) { + cpu_buffer = buffer->buffers[cpu]; + rb_check_pages(cpu_buffer); + } + atomic_dec(&buffer->record_disabled); + } + + mutex_unlock(&buffer->mutex); + return size; + + out_err: + for_each_buffer_cpu(buffer, cpu) { + struct buffer_page *bpage, *tmp; + + cpu_buffer = buffer->buffers[cpu]; + cpu_buffer->nr_pages_to_update = 0; + + if (list_empty(&cpu_buffer->new_pages)) + continue; + + list_for_each_entry_safe(bpage, tmp, &cpu_buffer->new_pages, + list) { + list_del_init(&bpage->list); + free_buffer_page(bpage); + } + } + mutex_unlock(&buffer->mutex); + return err; +} +EXPORT_SYMBOL_GPL(ring_buffer_resize); + +void ring_buffer_change_overwrite(struct ring_buffer *buffer, int val) +{ + mutex_lock(&buffer->mutex); + if (val) + buffer->flags |= RB_FL_OVERWRITE; + else + buffer->flags &= ~RB_FL_OVERWRITE; + mutex_unlock(&buffer->mutex); +} +EXPORT_SYMBOL_GPL(ring_buffer_change_overwrite); + +static inline void * +__rb_data_page_index(struct buffer_data_page *bpage, unsigned index) +{ + return bpage->data + index; +} + +static inline void *__rb_page_index(struct buffer_page *bpage, unsigned index) +{ + return bpage->page->data + index; +} + +static inline struct ring_buffer_event * +rb_reader_event(struct ring_buffer_per_cpu *cpu_buffer) +{ + return __rb_page_index(cpu_buffer->reader_page, + cpu_buffer->reader_page->read); +} + +static inline struct ring_buffer_event * +rb_iter_head_event(struct ring_buffer_iter *iter) +{ + return __rb_page_index(iter->head_page, iter->head); +} + +static inline unsigned rb_page_commit(struct buffer_page *bpage) +{ + return local_read(&bpage->page->commit); +} + +/* Size is determined by what has been committed */ +static inline unsigned rb_page_size(struct buffer_page *bpage) +{ + return rb_page_commit(bpage); +} + +static inline unsigned +rb_commit_index(struct ring_buffer_per_cpu *cpu_buffer) +{ + return rb_page_commit(cpu_buffer->commit_page); +} + +static inline unsigned +rb_event_index(struct ring_buffer_event *event) +{ + unsigned long addr = (unsigned long)event; + + return (addr & ~PAGE_MASK) - BUF_PAGE_HDR_SIZE; +} + +static inline int +rb_event_is_commit(struct ring_buffer_per_cpu *cpu_buffer, + struct ring_buffer_event *event) +{ + unsigned long addr = (unsigned long)event; + unsigned long index; + + index = rb_event_index(event); + addr &= PAGE_MASK; + + return cpu_buffer->commit_page->page == (void *)addr && + rb_commit_index(cpu_buffer) == index; +} + +static void +rb_set_commit_to_write(struct ring_buffer_per_cpu *cpu_buffer) +{ + unsigned long max_count; + + /* + * We only race with interrupts and NMIs on this CPU. + * If we own the commit event, then we can commit + * all others that interrupted us, since the interruptions + * are in stack format (they finish before they come + * back to us). This allows us to do a simple loop to + * assign the commit to the tail. + */ + again: + max_count = cpu_buffer->nr_pages * 100; + + while (cpu_buffer->commit_page != cpu_buffer->tail_page) { + if (RB_WARN_ON(cpu_buffer, !(--max_count))) + return; + if (RB_WARN_ON(cpu_buffer, + rb_is_reader_page(cpu_buffer->tail_page))) + return; + local_set(&cpu_buffer->commit_page->page->commit, + rb_page_write(cpu_buffer->commit_page)); + rb_inc_page(cpu_buffer, &cpu_buffer->commit_page); + cpu_buffer->write_stamp = + cpu_buffer->commit_page->page->time_stamp; + /* add barrier to keep gcc from optimizing too much */ + barrier(); + } + while (rb_commit_index(cpu_buffer) != + rb_page_write(cpu_buffer->commit_page)) { + + local_set(&cpu_buffer->commit_page->page->commit, + rb_page_write(cpu_buffer->commit_page)); + RB_WARN_ON(cpu_buffer, + local_read(&cpu_buffer->commit_page->page->commit) & + ~RB_WRITE_MASK); + barrier(); + } + + /* again, keep gcc from optimizing */ + barrier(); + + /* + * If an interrupt came in just after the first while loop + * and pushed the tail page forward, we will be left with + * a dangling commit that will never go forward. + */ + if (unlikely(cpu_buffer->commit_page != cpu_buffer->tail_page)) + goto again; +} + +static void rb_reset_reader_page(struct ring_buffer_per_cpu *cpu_buffer) +{ + cpu_buffer->read_stamp = cpu_buffer->reader_page->page->time_stamp; + cpu_buffer->reader_page->read = 0; +} + +static void rb_inc_iter(struct ring_buffer_iter *iter) +{ + struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer; + + /* + * The iterator could be on the reader page (it starts there). + * But the head could have moved, since the reader was + * found. Check for this case and assign the iterator + * to the head page instead of next. + */ + if (iter->head_page == cpu_buffer->reader_page) + iter->head_page = rb_set_head_page(cpu_buffer); + else + rb_inc_page(cpu_buffer, &iter->head_page); + + iter->read_stamp = iter->head_page->page->time_stamp; + iter->head = 0; +} + +/* Slow path, do not inline */ +static noinline struct ring_buffer_event * +rb_add_time_stamp(struct ring_buffer_event *event, u64 delta) +{ + event->type_len = RINGBUF_TYPE_TIME_EXTEND; + + /* Not the first event on the page? */ + if (rb_event_index(event)) { + event->time_delta = delta & TS_MASK; + event->array[0] = delta >> TS_SHIFT; + } else { + /* nope, just zero it */ + event->time_delta = 0; + event->array[0] = 0; + } + + return skip_time_extend(event); +} + +/** + * rb_update_event - update event type and data + * @event: the event to update + * @type: the type of event + * @length: the size of the event field in the ring buffer + * + * Update the type and data fields of the event. The length + * is the actual size that is written to the ring buffer, + * and with this, we can determine what to place into the + * data field. + */ +static void +rb_update_event(struct ring_buffer_per_cpu *cpu_buffer, + struct ring_buffer_event *event, unsigned length, + int add_timestamp, u64 delta) +{ + /* Only a commit updates the timestamp */ + if (unlikely(!rb_event_is_commit(cpu_buffer, event))) + delta = 0; + + /* + * If we need to add a timestamp, then we + * add it to the start of the resevered space. + */ + if (unlikely(add_timestamp)) { + event = rb_add_time_stamp(event, delta); + length -= RB_LEN_TIME_EXTEND; + delta = 0; + } + + event->time_delta = delta; + length -= RB_EVNT_HDR_SIZE; + if (length > RB_MAX_SMALL_DATA || RB_FORCE_8BYTE_ALIGNMENT) { + event->type_len = 0; + event->array[0] = length; + } else + event->type_len = DIV_ROUND_UP(length, RB_ALIGNMENT); +} + +/* + * rb_handle_head_page - writer hit the head page + * + * Returns: +1 to retry page + * 0 to continue + * -1 on error + */ +static int +rb_handle_head_page(struct ring_buffer_per_cpu *cpu_buffer, + struct buffer_page *tail_page, + struct buffer_page *next_page) +{ + struct buffer_page *new_head; + int entries; + int type; + int ret; + + entries = rb_page_entries(next_page); + + /* + * The hard part is here. We need to move the head + * forward, and protect against both readers on + * other CPUs and writers coming in via interrupts. + */ + type = rb_head_page_set_update(cpu_buffer, next_page, tail_page, + RB_PAGE_HEAD); + + /* + * type can be one of four: + * NORMAL - an interrupt already moved it for us + * HEAD - we are the first to get here. + * UPDATE - we are the interrupt interrupting + * a current move. + * MOVED - a reader on another CPU moved the next + * pointer to its reader page. Give up + * and try again. + */ + + switch (type) { + case RB_PAGE_HEAD: + /* + * We changed the head to UPDATE, thus + * it is our responsibility to update + * the counters. + */ + local_add(entries, &cpu_buffer->overrun); + local_sub(BUF_PAGE_SIZE, &cpu_buffer->entries_bytes); + + /* + * The entries will be zeroed out when we move the + * tail page. + */ + + /* still more to do */ + break; + + case RB_PAGE_UPDATE: + /* + * This is an interrupt that interrupt the + * previous update. Still more to do. + */ + break; + case RB_PAGE_NORMAL: + /* + * An interrupt came in before the update + * and processed this for us. + * Nothing left to do. + */ + return 1; + case RB_PAGE_MOVED: + /* + * The reader is on another CPU and just did + * a swap with our next_page. + * Try again. + */ + return 1; + default: + RB_WARN_ON(cpu_buffer, 1); /* WTF??? */ + return -1; + } + + /* + * Now that we are here, the old head pointer is + * set to UPDATE. This will keep the reader from + * swapping the head page with the reader page. + * The reader (on another CPU) will spin till + * we are finished. + * + * We just need to protect against interrupts + * doing the job. We will set the next pointer + * to HEAD. After that, we set the old pointer + * to NORMAL, but only if it was HEAD before. + * otherwise we are an interrupt, and only + * want the outer most commit to reset it. + */ + new_head = next_page; + rb_inc_page(cpu_buffer, &new_head); + + ret = rb_head_page_set_head(cpu_buffer, new_head, next_page, + RB_PAGE_NORMAL); + + /* + * Valid returns are: + * HEAD - an interrupt came in and already set it. + * NORMAL - One of two things: + * 1) We really set it. + * 2) A bunch of interrupts came in and moved + * the page forward again. + */ + switch (ret) { + case RB_PAGE_HEAD: + case RB_PAGE_NORMAL: + /* OK */ + break; + default: + RB_WARN_ON(cpu_buffer, 1); + return -1; + } + + /* + * It is possible that an interrupt came in, + * set the head up, then more interrupts came in + * and moved it again. When we get back here, + * the page would have been set to NORMAL but we + * just set it back to HEAD. + * + * How do you detect this? Well, if that happened + * the tail page would have moved. + */ + if (ret == RB_PAGE_NORMAL) { + /* + * If the tail had moved passed next, then we need + * to reset the pointer. + */ + if (cpu_buffer->tail_page != tail_page && + cpu_buffer->tail_page != next_page) + rb_head_page_set_normal(cpu_buffer, new_head, + next_page, + RB_PAGE_HEAD); + } + + /* + * If this was the outer most commit (the one that + * changed the original pointer from HEAD to UPDATE), + * then it is up to us to reset it to NORMAL. + */ + if (type == RB_PAGE_HEAD) { + ret = rb_head_page_set_normal(cpu_buffer, next_page, + tail_page, + RB_PAGE_UPDATE); + if (RB_WARN_ON(cpu_buffer, + ret != RB_PAGE_UPDATE)) + return -1; + } + + return 0; +} + +static unsigned rb_calculate_event_length(unsigned length) +{ + struct ring_buffer_event event; /* Used only for sizeof array */ + + /* zero length can cause confusions */ + if (!length) + length = 1; + + if (length > RB_MAX_SMALL_DATA || RB_FORCE_8BYTE_ALIGNMENT) + length += sizeof(event.array[0]); + + length += RB_EVNT_HDR_SIZE; + length = ALIGN(length, RB_ARCH_ALIGNMENT); + + return length; +} + +static inline void +rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer, + struct buffer_page *tail_page, + unsigned long tail, unsigned long length) +{ + struct ring_buffer_event *event; + + /* + * Only the event that crossed the page boundary + * must fill the old tail_page with padding. + */ + if (tail >= BUF_PAGE_SIZE) { + /* + * If the page was filled, then we still need + * to update the real_end. Reset it to zero + * and the reader will ignore it. + */ + if (tail == BUF_PAGE_SIZE) + tail_page->real_end = 0; + + local_sub(length, &tail_page->write); + return; + } + + event = __rb_page_index(tail_page, tail); + kmemcheck_annotate_bitfield(event, bitfield); + + /* account for padding bytes */ + local_add(BUF_PAGE_SIZE - tail, &cpu_buffer->entries_bytes); + + /* + * Save the original length to the meta data. + * This will be used by the reader to add lost event + * counter. + */ + tail_page->real_end = tail; + + /* + * If this event is bigger than the minimum size, then + * we need to be careful that we don't subtract the + * write counter enough to allow another writer to slip + * in on this page. + * We put in a discarded commit instead, to make sure + * that this space is not used again. + * + * If we are less than the minimum size, we don't need to + * worry about it. + */ + if (tail > (BUF_PAGE_SIZE - RB_EVNT_MIN_SIZE)) { + /* No room for any events */ + + /* Mark the rest of the page with padding */ + rb_event_set_padding(event); + + /* Set the write back to the previous setting */ + local_sub(length, &tail_page->write); + return; + } + + /* Put in a discarded event */ + event->array[0] = (BUF_PAGE_SIZE - tail) - RB_EVNT_HDR_SIZE; + event->type_len = RINGBUF_TYPE_PADDING; + /* time delta must be non zero */ + event->time_delta = 1; + + /* Set write to end of buffer */ + length = (tail + length) - BUF_PAGE_SIZE; + local_sub(length, &tail_page->write); +} + +/* + * This is the slow path, force gcc not to inline it. + */ +static noinline struct ring_buffer_event * +rb_move_tail(struct ring_buffer_per_cpu *cpu_buffer, + unsigned long length, unsigned long tail, + struct buffer_page *tail_page, u64 ts) +{ + struct buffer_page *commit_page = cpu_buffer->commit_page; + struct ring_buffer *buffer = cpu_buffer->buffer; + struct buffer_page *next_page; + int ret; + + next_page = tail_page; + + rb_inc_page(cpu_buffer, &next_page); + + /* + * If for some reason, we had an interrupt storm that made + * it all the way around the buffer, bail, and warn + * about it. + */ + if (unlikely(next_page == commit_page)) { + local_inc(&cpu_buffer->commit_overrun); + goto out_reset; + } + + /* + * This is where the fun begins! + * + * We are fighting against races between a reader that + * could be on another CPU trying to swap its reader + * page with the buffer head. + * + * We are also fighting against interrupts coming in and + * moving the head or tail on us as well. + * + * If the next page is the head page then we have filled + * the buffer, unless the commit page is still on the + * reader page. + */ + if (rb_is_head_page(cpu_buffer, next_page, &tail_page->list)) { + + /* + * If the commit is not on the reader page, then + * move the header page. + */ + if (!rb_is_reader_page(cpu_buffer->commit_page)) { + /* + * If we are not in overwrite mode, + * this is easy, just stop here. + */ + if (!(buffer->flags & RB_FL_OVERWRITE)) { + local_inc(&cpu_buffer->dropped_events); + goto out_reset; + } + + ret = rb_handle_head_page(cpu_buffer, + tail_page, + next_page); + if (ret < 0) + goto out_reset; + if (ret) + goto out_again; + } else { + /* + * We need to be careful here too. The + * commit page could still be on the reader + * page. We could have a small buffer, and + * have filled up the buffer with events + * from interrupts and such, and wrapped. + * + * Note, if the tail page is also the on the + * reader_page, we let it move out. + */ + if (unlikely((cpu_buffer->commit_page != + cpu_buffer->tail_page) && + (cpu_buffer->commit_page == + cpu_buffer->reader_page))) { + local_inc(&cpu_buffer->commit_overrun); + goto out_reset; + } + } + } + + ret = rb_tail_page_update(cpu_buffer, tail_page, next_page); + if (ret) { + /* + * Nested commits always have zero deltas, so + * just reread the time stamp + */ + ts = rb_time_stamp(buffer); + next_page->page->time_stamp = ts; + } + + out_again: + + rb_reset_tail(cpu_buffer, tail_page, tail, length); + + /* fail and let the caller try again */ + return ERR_PTR(-EAGAIN); + + out_reset: + /* reset write */ + rb_reset_tail(cpu_buffer, tail_page, tail, length); + + return NULL; +} + +static struct ring_buffer_event * +__rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer, + unsigned long length, u64 ts, + u64 delta, int add_timestamp) +{ + struct buffer_page *tail_page; + struct ring_buffer_event *event; + unsigned long tail, write; + + /* + * If the time delta since the last event is too big to + * hold in the time field of the event, then we append a + * TIME EXTEND event ahead of the data event. + */ + if (unlikely(add_timestamp)) + length += RB_LEN_TIME_EXTEND; + + tail_page = cpu_buffer->tail_page; + write = local_add_return(length, &tail_page->write); + + /* set write to only the index of the write */ + write &= RB_WRITE_MASK; + tail = write - length; + + /* + * If this is the first commit on the page, then it has the same + * timestamp as the page itself. + */ + if (!tail) + delta = 0; + + /* See if we shot pass the end of this buffer page */ + if (unlikely(write > BUF_PAGE_SIZE)) + return rb_move_tail(cpu_buffer, length, tail, + tail_page, ts); + + /* We reserved something on the buffer */ + + event = __rb_page_index(tail_page, tail); + kmemcheck_annotate_bitfield(event, bitfield); + rb_update_event(cpu_buffer, event, length, add_timestamp, delta); + + local_inc(&tail_page->entries); + + /* + * If this is the first commit on the page, then update + * its timestamp. + */ + if (!tail) + tail_page->page->time_stamp = ts; + + /* account for these added bytes */ + local_add(length, &cpu_buffer->entries_bytes); + + return event; +} + +static inline int +rb_try_to_discard(struct ring_buffer_per_cpu *cpu_buffer, + struct ring_buffer_event *event) +{ + unsigned long new_index, old_index; + struct buffer_page *bpage; + unsigned long index; + unsigned long addr; + + new_index = rb_event_index(event); + old_index = new_index + rb_event_ts_length(event); + addr = (unsigned long)event; + addr &= PAGE_MASK; + + bpage = cpu_buffer->tail_page; + + if (bpage->page == (void *)addr && rb_page_write(bpage) == old_index) { + unsigned long write_mask = + local_read(&bpage->write) & ~RB_WRITE_MASK; + unsigned long event_length = rb_event_length(event); + /* + * This is on the tail page. It is possible that + * a write could come in and move the tail page + * and write to the next page. That is fine + * because we just shorten what is on this page. + */ + old_index += write_mask; + new_index += write_mask; + index = local_cmpxchg(&bpage->write, old_index, new_index); + if (index == old_index) { + /* update counters */ + local_sub(event_length, &cpu_buffer->entries_bytes); + return 1; + } + } + + /* could not discard */ + return 0; +} + +static void rb_start_commit(struct ring_buffer_per_cpu *cpu_buffer) +{ + local_inc(&cpu_buffer->committing); + local_inc(&cpu_buffer->commits); +} + +static inline void rb_end_commit(struct ring_buffer_per_cpu *cpu_buffer) +{ + unsigned long commits; + + if (RB_WARN_ON(cpu_buffer, + !local_read(&cpu_buffer->committing))) + return; + + again: + commits = local_read(&cpu_buffer->commits); + /* synchronize with interrupts */ + barrier(); + if (local_read(&cpu_buffer->committing) == 1) + rb_set_commit_to_write(cpu_buffer); + + local_dec(&cpu_buffer->committing); + + /* synchronize with interrupts */ + barrier(); + + /* + * Need to account for interrupts coming in between the + * updating of the commit page and the clearing of the + * committing counter. + */ + if (unlikely(local_read(&cpu_buffer->commits) != commits) && + !local_read(&cpu_buffer->committing)) { + local_inc(&cpu_buffer->committing); + goto again; + } +} + +static struct ring_buffer_event * +rb_reserve_next_event(struct ring_buffer *buffer, + struct ring_buffer_per_cpu *cpu_buffer, + unsigned long length) +{ + struct ring_buffer_event *event; + u64 ts, delta; + int nr_loops = 0; + int add_timestamp; + u64 diff; + + rb_start_commit(cpu_buffer); + +#ifdef CONFIG_RING_BUFFER_ALLOW_SWAP + /* + * Due to the ability to swap a cpu buffer from a buffer + * it is possible it was swapped before we committed. + * (committing stops a swap). We check for it here and + * if it happened, we have to fail the write. + */ + barrier(); + if (unlikely(ACCESS_ONCE(cpu_buffer->buffer) != buffer)) { + local_dec(&cpu_buffer->committing); + local_dec(&cpu_buffer->commits); + return NULL; + } +#endif + + length = rb_calculate_event_length(length); + again: + add_timestamp = 0; + delta = 0; + + /* + * We allow for interrupts to reenter here and do a trace. + * If one does, it will cause this original code to loop + * back here. Even with heavy interrupts happening, this + * should only happen a few times in a row. If this happens + * 1000 times in a row, there must be either an interrupt + * storm or we have something buggy. + * Bail! + */ + if (RB_WARN_ON(cpu_buffer, ++nr_loops > 1000)) + goto out_fail; + + ts = rb_time_stamp(cpu_buffer->buffer); + diff = ts - cpu_buffer->write_stamp; + + /* make sure this diff is calculated here */ + barrier(); + + /* Did the write stamp get updated already? */ + if (likely(ts >= cpu_buffer->write_stamp)) { + delta = diff; + if (unlikely(test_time_stamp(delta))) { + int local_clock_stable = 1; +#ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK + local_clock_stable = sched_clock_stable(); +#endif + WARN_ONCE(delta > (1ULL << 59), + KERN_WARNING "Delta way too big! %llu ts=%llu write stamp = %llu\n%s", + (unsigned long long)delta, + (unsigned long long)ts, + (unsigned long long)cpu_buffer->write_stamp, + local_clock_stable ? "" : + "If you just came from a suspend/resume,\n" + "please switch to the trace global clock:\n" + " echo global > /sys/kernel/debug/tracing/trace_clock\n"); + add_timestamp = 1; + } + } + + event = __rb_reserve_next(cpu_buffer, length, ts, + delta, add_timestamp); + if (unlikely(PTR_ERR(event) == -EAGAIN)) + goto again; + + if (!event) + goto out_fail; + + return event; + + out_fail: + rb_end_commit(cpu_buffer); + return NULL; +} + +#ifdef CONFIG_TRACING + +/* + * The lock and unlock are done within a preempt disable section. + * The current_context per_cpu variable can only be modified + * by the current task between lock and unlock. But it can + * be modified more than once via an interrupt. To pass this + * information from the lock to the unlock without having to + * access the 'in_interrupt()' functions again (which do show + * a bit of overhead in something as critical as function tracing, + * we use a bitmask trick. + * + * bit 0 = NMI context + * bit 1 = IRQ context + * bit 2 = SoftIRQ context + * bit 3 = normal context. + * + * This works because this is the order of contexts that can + * preempt other contexts. A SoftIRQ never preempts an IRQ + * context. + * + * When the context is determined, the corresponding bit is + * checked and set (if it was set, then a recursion of that context + * happened). + * + * On unlock, we need to clear this bit. To do so, just subtract + * 1 from the current_context and AND it to itself. + * + * (binary) + * 101 - 1 = 100 + * 101 & 100 = 100 (clearing bit zero) + * + * 1010 - 1 = 1001 + * 1010 & 1001 = 1000 (clearing bit 1) + * + * The least significant bit can be cleared this way, and it + * just so happens that it is the same bit corresponding to + * the current context. + */ +static DEFINE_PER_CPU(unsigned int, current_context); + +static __always_inline int trace_recursive_lock(void) +{ + unsigned int val = __this_cpu_read(current_context); + int bit; + + if (in_interrupt()) { + if (in_nmi()) + bit = 0; + else if (in_irq()) + bit = 1; + else + bit = 2; + } else + bit = 3; + + if (unlikely(val & (1 << bit))) + return 1; + + val |= (1 << bit); + __this_cpu_write(current_context, val); + + return 0; +} + +static __always_inline void trace_recursive_unlock(void) +{ + __this_cpu_and(current_context, __this_cpu_read(current_context) - 1); +} + +#else + +#define trace_recursive_lock() (0) +#define trace_recursive_unlock() do { } while (0) + +#endif + +/** + * ring_buffer_lock_reserve - reserve a part of the buffer + * @buffer: the ring buffer to reserve from + * @length: the length of the data to reserve (excluding event header) + * + * Returns a reseverd event on the ring buffer to copy directly to. + * The user of this interface will need to get the body to write into + * and can use the ring_buffer_event_data() interface. + * + * The length is the length of the data needed, not the event length + * which also includes the event header. + * + * Must be paired with ring_buffer_unlock_commit, unless NULL is returned. + * If NULL is returned, then nothing has been allocated or locked. + */ +struct ring_buffer_event * +ring_buffer_lock_reserve(struct ring_buffer *buffer, unsigned long length) +{ + struct ring_buffer_per_cpu *cpu_buffer; + struct ring_buffer_event *event; + int cpu; + + if (ring_buffer_flags != RB_BUFFERS_ON) + return NULL; + + /* If we are tracing schedule, we don't want to recurse */ + preempt_disable_notrace(); + + if (atomic_read(&buffer->record_disabled)) + goto out_nocheck; + + if (trace_recursive_lock()) + goto out_nocheck; + + cpu = raw_smp_processor_id(); + + if (!cpumask_test_cpu(cpu, buffer->cpumask)) + goto out; + + cpu_buffer = buffer->buffers[cpu]; + + if (atomic_read(&cpu_buffer->record_disabled)) + goto out; + + if (length > BUF_MAX_DATA_SIZE) + goto out; + + event = rb_reserve_next_event(buffer, cpu_buffer, length); + if (!event) + goto out; + + return event; + + out: + trace_recursive_unlock(); + + out_nocheck: + preempt_enable_notrace(); + return NULL; +} +EXPORT_SYMBOL_GPL(ring_buffer_lock_reserve); + +static void +rb_update_write_stamp(struct ring_buffer_per_cpu *cpu_buffer, + struct ring_buffer_event *event) +{ + u64 delta; + + /* + * The event first in the commit queue updates the + * time stamp. + */ + if (rb_event_is_commit(cpu_buffer, event)) { + /* + * A commit event that is first on a page + * updates the write timestamp with the page stamp + */ + if (!rb_event_index(event)) + cpu_buffer->write_stamp = + cpu_buffer->commit_page->page->time_stamp; + else if (event->type_len == RINGBUF_TYPE_TIME_EXTEND) { + delta = event->array[0]; + delta <<= TS_SHIFT; + delta += event->time_delta; + cpu_buffer->write_stamp += delta; + } else + cpu_buffer->write_stamp += event->time_delta; + } +} + +static void rb_commit(struct ring_buffer_per_cpu *cpu_buffer, + struct ring_buffer_event *event) +{ + local_inc(&cpu_buffer->entries); + rb_update_write_stamp(cpu_buffer, event); + rb_end_commit(cpu_buffer); +} + +static __always_inline void +rb_wakeups(struct ring_buffer *buffer, struct ring_buffer_per_cpu *cpu_buffer) +{ + bool pagebusy; + + if (buffer->irq_work.waiters_pending) { + buffer->irq_work.waiters_pending = false; + /* irq_work_queue() supplies it's own memory barriers */ + irq_work_queue(&buffer->irq_work.work); + } + + if (cpu_buffer->irq_work.waiters_pending) { + cpu_buffer->irq_work.waiters_pending = false; + /* irq_work_queue() supplies it's own memory barriers */ + irq_work_queue(&cpu_buffer->irq_work.work); + } + + pagebusy = cpu_buffer->reader_page == cpu_buffer->commit_page; + + if (!pagebusy && cpu_buffer->irq_work.full_waiters_pending) { + cpu_buffer->irq_work.wakeup_full = true; + cpu_buffer->irq_work.full_waiters_pending = false; + /* irq_work_queue() supplies it's own memory barriers */ + irq_work_queue(&cpu_buffer->irq_work.work); + } +} + +/** + * ring_buffer_unlock_commit - commit a reserved + * @buffer: The buffer to commit to + * @event: The event pointer to commit. + * + * This commits the data to the ring buffer, and releases any locks held. + * + * Must be paired with ring_buffer_lock_reserve. + */ +int ring_buffer_unlock_commit(struct ring_buffer *buffer, + struct ring_buffer_event *event) +{ + struct ring_buffer_per_cpu *cpu_buffer; + int cpu = raw_smp_processor_id(); + + cpu_buffer = buffer->buffers[cpu]; + + rb_commit(cpu_buffer, event); + + rb_wakeups(buffer, cpu_buffer); + + trace_recursive_unlock(); + + preempt_enable_notrace(); + + return 0; +} +EXPORT_SYMBOL_GPL(ring_buffer_unlock_commit); + +static inline void rb_event_discard(struct ring_buffer_event *event) +{ + if (event->type_len == RINGBUF_TYPE_TIME_EXTEND) + event = skip_time_extend(event); + + /* array[0] holds the actual length for the discarded event */ + event->array[0] = rb_event_data_length(event) - RB_EVNT_HDR_SIZE; + event->type_len = RINGBUF_TYPE_PADDING; + /* time delta must be non zero */ + if (!event->time_delta) + event->time_delta = 1; +} + +/* + * Decrement the entries to the page that an event is on. + * The event does not even need to exist, only the pointer + * to the page it is on. This may only be called before the commit + * takes place. + */ +static inline void +rb_decrement_entry(struct ring_buffer_per_cpu *cpu_buffer, + struct ring_buffer_event *event) +{ + unsigned long addr = (unsigned long)event; + struct buffer_page *bpage = cpu_buffer->commit_page; + struct buffer_page *start; + + addr &= PAGE_MASK; + + /* Do the likely case first */ + if (likely(bpage->page == (void *)addr)) { + local_dec(&bpage->entries); + return; + } + + /* + * Because the commit page may be on the reader page we + * start with the next page and check the end loop there. + */ + rb_inc_page(cpu_buffer, &bpage); + start = bpage; + do { + if (bpage->page == (void *)addr) { + local_dec(&bpage->entries); + return; + } + rb_inc_page(cpu_buffer, &bpage); + } while (bpage != start); + + /* commit not part of this buffer?? */ + RB_WARN_ON(cpu_buffer, 1); +} + +/** + * ring_buffer_commit_discard - discard an event that has not been committed + * @buffer: the ring buffer + * @event: non committed event to discard + * + * Sometimes an event that is in the ring buffer needs to be ignored. + * This function lets the user discard an event in the ring buffer + * and then that event will not be read later. + * + * This function only works if it is called before the the item has been + * committed. It will try to free the event from the ring buffer + * if another event has not been added behind it. + * + * If another event has been added behind it, it will set the event + * up as discarded, and perform the commit. + * + * If this function is called, do not call ring_buffer_unlock_commit on + * the event. + */ +void ring_buffer_discard_commit(struct ring_buffer *buffer, + struct ring_buffer_event *event) +{ + struct ring_buffer_per_cpu *cpu_buffer; + int cpu; + + /* The event is discarded regardless */ + rb_event_discard(event); + + cpu = smp_processor_id(); + cpu_buffer = buffer->buffers[cpu]; + + /* + * This must only be called if the event has not been + * committed yet. Thus we can assume that preemption + * is still disabled. + */ + RB_WARN_ON(buffer, !local_read(&cpu_buffer->committing)); + + rb_decrement_entry(cpu_buffer, event); + if (rb_try_to_discard(cpu_buffer, event)) + goto out; + + /* + * The commit is still visible by the reader, so we + * must still update the timestamp. + */ + rb_update_write_stamp(cpu_buffer, event); + out: + rb_end_commit(cpu_buffer); + + trace_recursive_unlock(); + + preempt_enable_notrace(); + +} +EXPORT_SYMBOL_GPL(ring_buffer_discard_commit); + +/** + * ring_buffer_write - write data to the buffer without reserving + * @buffer: The ring buffer to write to. + * @length: The length of the data being written (excluding the event header) + * @data: The data to write to the buffer. + * + * This is like ring_buffer_lock_reserve and ring_buffer_unlock_commit as + * one function. If you already have the data to write to the buffer, it + * may be easier to simply call this function. + * + * Note, like ring_buffer_lock_reserve, the length is the length of the data + * and not the length of the event which would hold the header. + */ +int ring_buffer_write(struct ring_buffer *buffer, + unsigned long length, + void *data) +{ + struct ring_buffer_per_cpu *cpu_buffer; + struct ring_buffer_event *event; + void *body; + int ret = -EBUSY; + int cpu; + + if (ring_buffer_flags != RB_BUFFERS_ON) + return -EBUSY; + + preempt_disable_notrace(); + + if (atomic_read(&buffer->record_disabled)) + goto out; + + cpu = raw_smp_processor_id(); + + if (!cpumask_test_cpu(cpu, buffer->cpumask)) + goto out; + + cpu_buffer = buffer->buffers[cpu]; + + if (atomic_read(&cpu_buffer->record_disabled)) + goto out; + + if (length > BUF_MAX_DATA_SIZE) + goto out; + + event = rb_reserve_next_event(buffer, cpu_buffer, length); + if (!event) + goto out; + + body = rb_event_data(event); + + memcpy(body, data, length); + + rb_commit(cpu_buffer, event); + + rb_wakeups(buffer, cpu_buffer); + + ret = 0; + out: + preempt_enable_notrace(); + + return ret; +} +EXPORT_SYMBOL_GPL(ring_buffer_write); + +static int rb_per_cpu_empty(struct ring_buffer_per_cpu *cpu_buffer) +{ + struct buffer_page *reader = cpu_buffer->reader_page; + struct buffer_page *head = rb_set_head_page(cpu_buffer); + struct buffer_page *commit = cpu_buffer->commit_page; + + /* In case of error, head will be NULL */ + if (unlikely(!head)) + return 1; + + return reader->read == rb_page_commit(reader) && + (commit == reader || + (commit == head && + head->read == rb_page_commit(commit))); +} + +/** + * ring_buffer_record_disable - stop all writes into the buffer + * @buffer: The ring buffer to stop writes to. + * + * This prevents all writes to the buffer. Any attempt to write + * to the buffer after this will fail and return NULL. + * + * The caller should call synchronize_sched() after this. + */ +void ring_buffer_record_disable(struct ring_buffer *buffer) +{ + atomic_inc(&buffer->record_disabled); +} +EXPORT_SYMBOL_GPL(ring_buffer_record_disable); + +/** + * ring_buffer_record_enable - enable writes to the buffer + * @buffer: The ring buffer to enable writes + * + * Note, multiple disables will need the same number of enables + * to truly enable the writing (much like preempt_disable). + */ +void ring_buffer_record_enable(struct ring_buffer *buffer) +{ + atomic_dec(&buffer->record_disabled); +} +EXPORT_SYMBOL_GPL(ring_buffer_record_enable); + +/** + * ring_buffer_record_off - stop all writes into the buffer + * @buffer: The ring buffer to stop writes to. + * + * This prevents all writes to the buffer. Any attempt to write + * to the buffer after this will fail and return NULL. + * + * This is different than ring_buffer_record_disable() as + * it works like an on/off switch, where as the disable() version + * must be paired with a enable(). + */ +void ring_buffer_record_off(struct ring_buffer *buffer) +{ + unsigned int rd; + unsigned int new_rd; + + do { + rd = atomic_read(&buffer->record_disabled); + new_rd = rd | RB_BUFFER_OFF; + } while (atomic_cmpxchg(&buffer->record_disabled, rd, new_rd) != rd); +} +EXPORT_SYMBOL_GPL(ring_buffer_record_off); + +/** + * ring_buffer_record_on - restart writes into the buffer + * @buffer: The ring buffer to start writes to. + * + * This enables all writes to the buffer that was disabled by + * ring_buffer_record_off(). + * + * This is different than ring_buffer_record_enable() as + * it works like an on/off switch, where as the enable() version + * must be paired with a disable(). + */ +void ring_buffer_record_on(struct ring_buffer *buffer) +{ + unsigned int rd; + unsigned int new_rd; + + do { + rd = atomic_read(&buffer->record_disabled); + new_rd = rd & ~RB_BUFFER_OFF; + } while (atomic_cmpxchg(&buffer->record_disabled, rd, new_rd) != rd); +} +EXPORT_SYMBOL_GPL(ring_buffer_record_on); + +/** + * ring_buffer_record_is_on - return true if the ring buffer can write + * @buffer: The ring buffer to see if write is enabled + * + * Returns true if the ring buffer is in a state that it accepts writes. + */ +int ring_buffer_record_is_on(struct ring_buffer *buffer) +{ + return !atomic_read(&buffer->record_disabled); +} + +/** + * ring_buffer_record_disable_cpu - stop all writes into the cpu_buffer + * @buffer: The ring buffer to stop writes to. + * @cpu: The CPU buffer to stop + * + * This prevents all writes to the buffer. Any attempt to write + * to the buffer after this will fail and return NULL. + * + * The caller should call synchronize_sched() after this. + */ +void ring_buffer_record_disable_cpu(struct ring_buffer *buffer, int cpu) +{ + struct ring_buffer_per_cpu *cpu_buffer; + + if (!cpumask_test_cpu(cpu, buffer->cpumask)) + return; + + cpu_buffer = buffer->buffers[cpu]; + atomic_inc(&cpu_buffer->record_disabled); +} +EXPORT_SYMBOL_GPL(ring_buffer_record_disable_cpu); + +/** + * ring_buffer_record_enable_cpu - enable writes to the buffer + * @buffer: The ring buffer to enable writes + * @cpu: The CPU to enable. + * + * Note, multiple disables will need the same number of enables + * to truly enable the writing (much like preempt_disable). + */ +void ring_buffer_record_enable_cpu(struct ring_buffer *buffer, int cpu) +{ + struct ring_buffer_per_cpu *cpu_buffer; + + if (!cpumask_test_cpu(cpu, buffer->cpumask)) + return; + + cpu_buffer = buffer->buffers[cpu]; + atomic_dec(&cpu_buffer->record_disabled); +} +EXPORT_SYMBOL_GPL(ring_buffer_record_enable_cpu); + +/* + * The total entries in the ring buffer is the running counter + * of entries entered into the ring buffer, minus the sum of + * the entries read from the ring buffer and the number of + * entries that were overwritten. + */ +static inline unsigned long +rb_num_of_entries(struct ring_buffer_per_cpu *cpu_buffer) +{ + return local_read(&cpu_buffer->entries) - + (local_read(&cpu_buffer->overrun) + cpu_buffer->read); +} + +/** + * ring_buffer_oldest_event_ts - get the oldest event timestamp from the buffer + * @buffer: The ring buffer + * @cpu: The per CPU buffer to read from. + */ +u64 ring_buffer_oldest_event_ts(struct ring_buffer *buffer, int cpu) +{ + unsigned long flags; + struct ring_buffer_per_cpu *cpu_buffer; + struct buffer_page *bpage; + u64 ret = 0; + + if (!cpumask_test_cpu(cpu, buffer->cpumask)) + return 0; + + cpu_buffer = buffer->buffers[cpu]; + raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); + /* + * if the tail is on reader_page, oldest time stamp is on the reader + * page + */ + if (cpu_buffer->tail_page == cpu_buffer->reader_page) + bpage = cpu_buffer->reader_page; + else + bpage = rb_set_head_page(cpu_buffer); + if (bpage) + ret = bpage->page->time_stamp; + raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); + + return ret; +} +EXPORT_SYMBOL_GPL(ring_buffer_oldest_event_ts); + +/** + * ring_buffer_bytes_cpu - get the number of bytes consumed in a cpu buffer + * @buffer: The ring buffer + * @cpu: The per CPU buffer to read from. + */ +unsigned long ring_buffer_bytes_cpu(struct ring_buffer *buffer, int cpu) +{ + struct ring_buffer_per_cpu *cpu_buffer; + unsigned long ret; + + if (!cpumask_test_cpu(cpu, buffer->cpumask)) + return 0; + + cpu_buffer = buffer->buffers[cpu]; + ret = local_read(&cpu_buffer->entries_bytes) - cpu_buffer->read_bytes; + + return ret; +} +EXPORT_SYMBOL_GPL(ring_buffer_bytes_cpu); + +/** + * ring_buffer_entries_cpu - get the number of entries in a cpu buffer + * @buffer: The ring buffer + * @cpu: The per CPU buffer to get the entries from. + */ +unsigned long ring_buffer_entries_cpu(struct ring_buffer *buffer, int cpu) +{ + struct ring_buffer_per_cpu *cpu_buffer; + + if (!cpumask_test_cpu(cpu, buffer->cpumask)) + return 0; + + cpu_buffer = buffer->buffers[cpu]; + + return rb_num_of_entries(cpu_buffer); +} +EXPORT_SYMBOL_GPL(ring_buffer_entries_cpu); + +/** + * ring_buffer_overrun_cpu - get the number of overruns caused by the ring + * buffer wrapping around (only if RB_FL_OVERWRITE is on). + * @buffer: The ring buffer + * @cpu: The per CPU buffer to get the number of overruns from + */ +unsigned long ring_buffer_overrun_cpu(struct ring_buffer *buffer, int cpu) +{ + struct ring_buffer_per_cpu *cpu_buffer; + unsigned long ret; + + if (!cpumask_test_cpu(cpu, buffer->cpumask)) + return 0; + + cpu_buffer = buffer->buffers[cpu]; + ret = local_read(&cpu_buffer->overrun); + + return ret; +} +EXPORT_SYMBOL_GPL(ring_buffer_overrun_cpu); + +/** + * ring_buffer_commit_overrun_cpu - get the number of overruns caused by + * commits failing due to the buffer wrapping around while there are uncommitted + * events, such as during an interrupt storm. + * @buffer: The ring buffer + * @cpu: The per CPU buffer to get the number of overruns from + */ +unsigned long +ring_buffer_commit_overrun_cpu(struct ring_buffer *buffer, int cpu) +{ + struct ring_buffer_per_cpu *cpu_buffer; + unsigned long ret; + + if (!cpumask_test_cpu(cpu, buffer->cpumask)) + return 0; + + cpu_buffer = buffer->buffers[cpu]; + ret = local_read(&cpu_buffer->commit_overrun); + + return ret; +} +EXPORT_SYMBOL_GPL(ring_buffer_commit_overrun_cpu); + +/** + * ring_buffer_dropped_events_cpu - get the number of dropped events caused by + * the ring buffer filling up (only if RB_FL_OVERWRITE is off). + * @buffer: The ring buffer + * @cpu: The per CPU buffer to get the number of overruns from + */ +unsigned long +ring_buffer_dropped_events_cpu(struct ring_buffer *buffer, int cpu) +{ + struct ring_buffer_per_cpu *cpu_buffer; + unsigned long ret; + + if (!cpumask_test_cpu(cpu, buffer->cpumask)) + return 0; + + cpu_buffer = buffer->buffers[cpu]; + ret = local_read(&cpu_buffer->dropped_events); + + return ret; +} +EXPORT_SYMBOL_GPL(ring_buffer_dropped_events_cpu); + +/** + * ring_buffer_read_events_cpu - get the number of events successfully read + * @buffer: The ring buffer + * @cpu: The per CPU buffer to get the number of events read + */ +unsigned long +ring_buffer_read_events_cpu(struct ring_buffer *buffer, int cpu) +{ + struct ring_buffer_per_cpu *cpu_buffer; + + if (!cpumask_test_cpu(cpu, buffer->cpumask)) + return 0; + + cpu_buffer = buffer->buffers[cpu]; + return cpu_buffer->read; +} +EXPORT_SYMBOL_GPL(ring_buffer_read_events_cpu); + +/** + * ring_buffer_entries - get the number of entries in a buffer + * @buffer: The ring buffer + * + * Returns the total number of entries in the ring buffer + * (all CPU entries) + */ +unsigned long ring_buffer_entries(struct ring_buffer *buffer) +{ + struct ring_buffer_per_cpu *cpu_buffer; + unsigned long entries = 0; + int cpu; + + /* if you care about this being correct, lock the buffer */ + for_each_buffer_cpu(buffer, cpu) { + cpu_buffer = buffer->buffers[cpu]; + entries += rb_num_of_entries(cpu_buffer); + } + + return entries; +} +EXPORT_SYMBOL_GPL(ring_buffer_entries); + +/** + * ring_buffer_overruns - get the number of overruns in buffer + * @buffer: The ring buffer + * + * Returns the total number of overruns in the ring buffer + * (all CPU entries) + */ +unsigned long ring_buffer_overruns(struct ring_buffer *buffer) +{ + struct ring_buffer_per_cpu *cpu_buffer; + unsigned long overruns = 0; + int cpu; + + /* if you care about this being correct, lock the buffer */ + for_each_buffer_cpu(buffer, cpu) { + cpu_buffer = buffer->buffers[cpu]; + overruns += local_read(&cpu_buffer->overrun); + } + + return overruns; +} +EXPORT_SYMBOL_GPL(ring_buffer_overruns); + +static void rb_iter_reset(struct ring_buffer_iter *iter) +{ + struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer; + + /* Iterator usage is expected to have record disabled */ + iter->head_page = cpu_buffer->reader_page; + iter->head = cpu_buffer->reader_page->read; + + iter->cache_reader_page = iter->head_page; + iter->cache_read = cpu_buffer->read; + + if (iter->head) + iter->read_stamp = cpu_buffer->read_stamp; + else + iter->read_stamp = iter->head_page->page->time_stamp; +} + +/** + * ring_buffer_iter_reset - reset an iterator + * @iter: The iterator to reset + * + * Resets the iterator, so that it will start from the beginning + * again. + */ +void ring_buffer_iter_reset(struct ring_buffer_iter *iter) +{ + struct ring_buffer_per_cpu *cpu_buffer; + unsigned long flags; + + if (!iter) + return; + + cpu_buffer = iter->cpu_buffer; + + raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); + rb_iter_reset(iter); + raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); +} +EXPORT_SYMBOL_GPL(ring_buffer_iter_reset); + +/** + * ring_buffer_iter_empty - check if an iterator has no more to read + * @iter: The iterator to check + */ +int ring_buffer_iter_empty(struct ring_buffer_iter *iter) +{ + struct ring_buffer_per_cpu *cpu_buffer; + + cpu_buffer = iter->cpu_buffer; + + return iter->head_page == cpu_buffer->commit_page && + iter->head == rb_commit_index(cpu_buffer); +} +EXPORT_SYMBOL_GPL(ring_buffer_iter_empty); + +static void +rb_update_read_stamp(struct ring_buffer_per_cpu *cpu_buffer, + struct ring_buffer_event *event) +{ + u64 delta; + + switch (event->type_len) { + case RINGBUF_TYPE_PADDING: + return; + + case RINGBUF_TYPE_TIME_EXTEND: + delta = event->array[0]; + delta <<= TS_SHIFT; + delta += event->time_delta; + cpu_buffer->read_stamp += delta; + return; + + case RINGBUF_TYPE_TIME_STAMP: + /* FIXME: not implemented */ + return; + + case RINGBUF_TYPE_DATA: + cpu_buffer->read_stamp += event->time_delta; + return; + + default: + BUG(); + } + return; +} + +static void +rb_update_iter_read_stamp(struct ring_buffer_iter *iter, + struct ring_buffer_event *event) +{ + u64 delta; + + switch (event->type_len) { + case RINGBUF_TYPE_PADDING: + return; + + case RINGBUF_TYPE_TIME_EXTEND: + delta = event->array[0]; + delta <<= TS_SHIFT; + delta += event->time_delta; + iter->read_stamp += delta; + return; + + case RINGBUF_TYPE_TIME_STAMP: + /* FIXME: not implemented */ + return; + + case RINGBUF_TYPE_DATA: + iter->read_stamp += event->time_delta; + return; + + default: + BUG(); + } + return; +} + +static struct buffer_page * +rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer) +{ + struct buffer_page *reader = NULL; + unsigned long overwrite; + unsigned long flags; + int nr_loops = 0; + int ret; + + local_irq_save(flags); + arch_spin_lock(&cpu_buffer->lock); + + again: + /* + * This should normally only loop twice. But because the + * start of the reader inserts an empty page, it causes + * a case where we will loop three times. There should be no + * reason to loop four times (that I know of). + */ + if (RB_WARN_ON(cpu_buffer, ++nr_loops > 3)) { + reader = NULL; + goto out; + } + + reader = cpu_buffer->reader_page; + + /* If there's more to read, return this page */ + if (cpu_buffer->reader_page->read < rb_page_size(reader)) + goto out; + + /* Never should we have an index greater than the size */ + if (RB_WARN_ON(cpu_buffer, + cpu_buffer->reader_page->read > rb_page_size(reader))) + goto out; + + /* check if we caught up to the tail */ + reader = NULL; + if (cpu_buffer->commit_page == cpu_buffer->reader_page) + goto out; + + /* Don't bother swapping if the ring buffer is empty */ + if (rb_num_of_entries(cpu_buffer) == 0) + goto out; + + /* + * Reset the reader page to size zero. + */ + local_set(&cpu_buffer->reader_page->write, 0); + local_set(&cpu_buffer->reader_page->entries, 0); + local_set(&cpu_buffer->reader_page->page->commit, 0); + cpu_buffer->reader_page->real_end = 0; + + spin: + /* + * Splice the empty reader page into the list around the head. + */ + reader = rb_set_head_page(cpu_buffer); + if (!reader) + goto out; + cpu_buffer->reader_page->list.next = rb_list_head(reader->list.next); + cpu_buffer->reader_page->list.prev = reader->list.prev; + + /* + * cpu_buffer->pages just needs to point to the buffer, it + * has no specific buffer page to point to. Lets move it out + * of our way so we don't accidentally swap it. + */ + cpu_buffer->pages = reader->list.prev; + + /* The reader page will be pointing to the new head */ + rb_set_list_to_head(cpu_buffer, &cpu_buffer->reader_page->list); + + /* + * We want to make sure we read the overruns after we set up our + * pointers to the next object. The writer side does a + * cmpxchg to cross pages which acts as the mb on the writer + * side. Note, the reader will constantly fail the swap + * while the writer is updating the pointers, so this + * guarantees that the overwrite recorded here is the one we + * want to compare with the last_overrun. + */ + smp_mb(); + overwrite = local_read(&(cpu_buffer->overrun)); + + /* + * Here's the tricky part. + * + * We need to move the pointer past the header page. + * But we can only do that if a writer is not currently + * moving it. The page before the header page has the + * flag bit '1' set if it is pointing to the page we want. + * but if the writer is in the process of moving it + * than it will be '2' or already moved '0'. + */ + + ret = rb_head_page_replace(reader, cpu_buffer->reader_page); + + /* + * If we did not convert it, then we must try again. + */ + if (!ret) + goto spin; + + /* + * Yeah! We succeeded in replacing the page. + * + * Now make the new head point back to the reader page. + */ + rb_list_head(reader->list.next)->prev = &cpu_buffer->reader_page->list; + rb_inc_page(cpu_buffer, &cpu_buffer->head_page); + + /* Finally update the reader page to the new head */ + cpu_buffer->reader_page = reader; + rb_reset_reader_page(cpu_buffer); + + if (overwrite != cpu_buffer->last_overrun) { + cpu_buffer->lost_events = overwrite - cpu_buffer->last_overrun; + cpu_buffer->last_overrun = overwrite; + } + + goto again; + + out: + arch_spin_unlock(&cpu_buffer->lock); + local_irq_restore(flags); + + return reader; +} + +static void rb_advance_reader(struct ring_buffer_per_cpu *cpu_buffer) +{ + struct ring_buffer_event *event; + struct buffer_page *reader; + unsigned length; + + reader = rb_get_reader_page(cpu_buffer); + + /* This function should not be called when buffer is empty */ + if (RB_WARN_ON(cpu_buffer, !reader)) + return; + + event = rb_reader_event(cpu_buffer); + + if (event->type_len <= RINGBUF_TYPE_DATA_TYPE_LEN_MAX) + cpu_buffer->read++; + + rb_update_read_stamp(cpu_buffer, event); + + length = rb_event_length(event); + cpu_buffer->reader_page->read += length; +} + +static void rb_advance_iter(struct ring_buffer_iter *iter) +{ + struct ring_buffer_per_cpu *cpu_buffer; + struct ring_buffer_event *event; + unsigned length; + + cpu_buffer = iter->cpu_buffer; + + /* + * Check if we are at the end of the buffer. + */ + if (iter->head >= rb_page_size(iter->head_page)) { + /* discarded commits can make the page empty */ + if (iter->head_page == cpu_buffer->commit_page) + return; + rb_inc_iter(iter); + return; + } + + event = rb_iter_head_event(iter); + + length = rb_event_length(event); + + /* + * This should not be called to advance the header if we are + * at the tail of the buffer. + */ + if (RB_WARN_ON(cpu_buffer, + (iter->head_page == cpu_buffer->commit_page) && + (iter->head + length > rb_commit_index(cpu_buffer)))) + return; + + rb_update_iter_read_stamp(iter, event); + + iter->head += length; + + /* check for end of page padding */ + if ((iter->head >= rb_page_size(iter->head_page)) && + (iter->head_page != cpu_buffer->commit_page)) + rb_inc_iter(iter); +} + +static int rb_lost_events(struct ring_buffer_per_cpu *cpu_buffer) +{ + return cpu_buffer->lost_events; +} + +static struct ring_buffer_event * +rb_buffer_peek(struct ring_buffer_per_cpu *cpu_buffer, u64 *ts, + unsigned long *lost_events) +{ + struct ring_buffer_event *event; + struct buffer_page *reader; + int nr_loops = 0; + + again: + /* + * We repeat when a time extend is encountered. + * Since the time extend is always attached to a data event, + * we should never loop more than once. + * (We never hit the following condition more than twice). + */ + if (RB_WARN_ON(cpu_buffer, ++nr_loops > 2)) + return NULL; + + reader = rb_get_reader_page(cpu_buffer); + if (!reader) + return NULL; + + event = rb_reader_event(cpu_buffer); + + switch (event->type_len) { + case RINGBUF_TYPE_PADDING: + if (rb_null_event(event)) + RB_WARN_ON(cpu_buffer, 1); + /* + * Because the writer could be discarding every + * event it creates (which would probably be bad) + * if we were to go back to "again" then we may never + * catch up, and will trigger the warn on, or lock + * the box. Return the padding, and we will release + * the current locks, and try again. + */ + return event; + + case RINGBUF_TYPE_TIME_EXTEND: + /* Internal data, OK to advance */ + rb_advance_reader(cpu_buffer); + goto again; + + case RINGBUF_TYPE_TIME_STAMP: + /* FIXME: not implemented */ + rb_advance_reader(cpu_buffer); + goto again; + + case RINGBUF_TYPE_DATA: + if (ts) { + *ts = cpu_buffer->read_stamp + event->time_delta; + ring_buffer_normalize_time_stamp(cpu_buffer->buffer, + cpu_buffer->cpu, ts); + } + if (lost_events) + *lost_events = rb_lost_events(cpu_buffer); + return event; + + default: + BUG(); + } + + return NULL; +} +EXPORT_SYMBOL_GPL(ring_buffer_peek); + +static struct ring_buffer_event * +rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts) +{ + struct ring_buffer *buffer; + struct ring_buffer_per_cpu *cpu_buffer; + struct ring_buffer_event *event; + int nr_loops = 0; + + cpu_buffer = iter->cpu_buffer; + buffer = cpu_buffer->buffer; + + /* + * Check if someone performed a consuming read to + * the buffer. A consuming read invalidates the iterator + * and we need to reset the iterator in this case. + */ + if (unlikely(iter->cache_read != cpu_buffer->read || + iter->cache_reader_page != cpu_buffer->reader_page)) + rb_iter_reset(iter); + + again: + if (ring_buffer_iter_empty(iter)) + return NULL; + + /* + * We repeat when a time extend is encountered or we hit + * the end of the page. Since the time extend is always attached + * to a data event, we should never loop more than three times. + * Once for going to next page, once on time extend, and + * finally once to get the event. + * (We never hit the following condition more than thrice). + */ + if (RB_WARN_ON(cpu_buffer, ++nr_loops > 3)) + return NULL; + + if (rb_per_cpu_empty(cpu_buffer)) + return NULL; + + if (iter->head >= rb_page_size(iter->head_page)) { + rb_inc_iter(iter); + goto again; + } + + event = rb_iter_head_event(iter); + + switch (event->type_len) { + case RINGBUF_TYPE_PADDING: + if (rb_null_event(event)) { + rb_inc_iter(iter); + goto again; + } + rb_advance_iter(iter); + return event; + + case RINGBUF_TYPE_TIME_EXTEND: + /* Internal data, OK to advance */ + rb_advance_iter(iter); + goto again; + + case RINGBUF_TYPE_TIME_STAMP: + /* FIXME: not implemented */ + rb_advance_iter(iter); + goto again; + + case RINGBUF_TYPE_DATA: + if (ts) { + *ts = iter->read_stamp + event->time_delta; + ring_buffer_normalize_time_stamp(buffer, + cpu_buffer->cpu, ts); + } + return event; + + default: + BUG(); + } + + return NULL; +} +EXPORT_SYMBOL_GPL(ring_buffer_iter_peek); + +static inline int rb_ok_to_lock(void) +{ + /* + * If an NMI die dumps out the content of the ring buffer + * do not grab locks. We also permanently disable the ring + * buffer too. A one time deal is all you get from reading + * the ring buffer from an NMI. + */ + if (likely(!in_nmi())) + return 1; + + tracing_off_permanent(); + return 0; +} + +/** + * ring_buffer_peek - peek at the next event to be read + * @buffer: The ring buffer to read + * @cpu: The cpu to peak at + * @ts: The timestamp counter of this event. + * @lost_events: a variable to store if events were lost (may be NULL) + * + * This will return the event that will be read next, but does + * not consume the data. + */ +struct ring_buffer_event * +ring_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts, + unsigned long *lost_events) +{ + struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu]; + struct ring_buffer_event *event; + unsigned long flags; + int dolock; + + if (!cpumask_test_cpu(cpu, buffer->cpumask)) + return NULL; + + dolock = rb_ok_to_lock(); + again: + local_irq_save(flags); + if (dolock) + raw_spin_lock(&cpu_buffer->reader_lock); + event = rb_buffer_peek(cpu_buffer, ts, lost_events); + if (event && event->type_len == RINGBUF_TYPE_PADDING) + rb_advance_reader(cpu_buffer); + if (dolock) + raw_spin_unlock(&cpu_buffer->reader_lock); + local_irq_restore(flags); + + if (event && event->type_len == RINGBUF_TYPE_PADDING) + goto again; + + return event; +} + +/** + * ring_buffer_iter_peek - peek at the next event to be read + * @iter: The ring buffer iterator + * @ts: The timestamp counter of this event. + * + * This will return the event that will be read next, but does + * not increment the iterator. + */ +struct ring_buffer_event * +ring_buffer_iter_peek(struct ring_buffer_iter *iter, u64 *ts) +{ + struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer; + struct ring_buffer_event *event; + unsigned long flags; + + again: + raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); + event = rb_iter_peek(iter, ts); + raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); + + if (event && event->type_len == RINGBUF_TYPE_PADDING) + goto again; + + return event; +} + +/** + * ring_buffer_consume - return an event and consume it + * @buffer: The ring buffer to get the next event from + * @cpu: the cpu to read the buffer from + * @ts: a variable to store the timestamp (may be NULL) + * @lost_events: a variable to store if events were lost (may be NULL) + * + * Returns the next event in the ring buffer, and that event is consumed. + * Meaning, that sequential reads will keep returning a different event, + * and eventually empty the ring buffer if the producer is slower. + */ +struct ring_buffer_event * +ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts, + unsigned long *lost_events) +{ + struct ring_buffer_per_cpu *cpu_buffer; + struct ring_buffer_event *event = NULL; + unsigned long flags; + int dolock; + + dolock = rb_ok_to_lock(); + + again: + /* might be called in atomic */ + preempt_disable(); + + if (!cpumask_test_cpu(cpu, buffer->cpumask)) + goto out; + + cpu_buffer = buffer->buffers[cpu]; + local_irq_save(flags); + if (dolock) + raw_spin_lock(&cpu_buffer->reader_lock); + + event = rb_buffer_peek(cpu_buffer, ts, lost_events); + if (event) { + cpu_buffer->lost_events = 0; + rb_advance_reader(cpu_buffer); + } + + if (dolock) + raw_spin_unlock(&cpu_buffer->reader_lock); + local_irq_restore(flags); + + out: + preempt_enable(); + + if (event && event->type_len == RINGBUF_TYPE_PADDING) + goto again; + + return event; +} +EXPORT_SYMBOL_GPL(ring_buffer_consume); + +/** + * ring_buffer_read_prepare - Prepare for a non consuming read of the buffer + * @buffer: The ring buffer to read from + * @cpu: The cpu buffer to iterate over + * + * This performs the initial preparations necessary to iterate + * through the buffer. Memory is allocated, buffer recording + * is disabled, and the iterator pointer is returned to the caller. + * + * Disabling buffer recordng prevents the reading from being + * corrupted. This is not a consuming read, so a producer is not + * expected. + * + * After a sequence of ring_buffer_read_prepare calls, the user is + * expected to make at least one call to ring_buffer_read_prepare_sync. + * Afterwards, ring_buffer_read_start is invoked to get things going + * for real. + * + * This overall must be paired with ring_buffer_read_finish. + */ +struct ring_buffer_iter * +ring_buffer_read_prepare(struct ring_buffer *buffer, int cpu) +{ + struct ring_buffer_per_cpu *cpu_buffer; + struct ring_buffer_iter *iter; + + if (!cpumask_test_cpu(cpu, buffer->cpumask)) + return NULL; + + iter = kmalloc(sizeof(*iter), GFP_KERNEL); + if (!iter) + return NULL; + + cpu_buffer = buffer->buffers[cpu]; + + iter->cpu_buffer = cpu_buffer; + + atomic_inc(&buffer->resize_disabled); + atomic_inc(&cpu_buffer->record_disabled); + + return iter; +} +EXPORT_SYMBOL_GPL(ring_buffer_read_prepare); + +/** + * ring_buffer_read_prepare_sync - Synchronize a set of prepare calls + * + * All previously invoked ring_buffer_read_prepare calls to prepare + * iterators will be synchronized. Afterwards, read_buffer_read_start + * calls on those iterators are allowed. + */ +void +ring_buffer_read_prepare_sync(void) +{ + synchronize_sched(); +} +EXPORT_SYMBOL_GPL(ring_buffer_read_prepare_sync); + +/** + * ring_buffer_read_start - start a non consuming read of the buffer + * @iter: The iterator returned by ring_buffer_read_prepare + * + * This finalizes the startup of an iteration through the buffer. + * The iterator comes from a call to ring_buffer_read_prepare and + * an intervening ring_buffer_read_prepare_sync must have been + * performed. + * + * Must be paired with ring_buffer_read_finish. + */ +void +ring_buffer_read_start(struct ring_buffer_iter *iter) +{ + struct ring_buffer_per_cpu *cpu_buffer; + unsigned long flags; + + if (!iter) + return; + + cpu_buffer = iter->cpu_buffer; + + raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); + arch_spin_lock(&cpu_buffer->lock); + rb_iter_reset(iter); + arch_spin_unlock(&cpu_buffer->lock); + raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); +} +EXPORT_SYMBOL_GPL(ring_buffer_read_start); + +/** + * ring_buffer_read_finish - finish reading the iterator of the buffer + * @iter: The iterator retrieved by ring_buffer_start + * + * This re-enables the recording to the buffer, and frees the + * iterator. + */ +void +ring_buffer_read_finish(struct ring_buffer_iter *iter) +{ + struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer; + unsigned long flags; + + /* + * Ring buffer is disabled from recording, here's a good place + * to check the integrity of the ring buffer. + * Must prevent readers from trying to read, as the check + * clears the HEAD page and readers require it. + */ + raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); + rb_check_pages(cpu_buffer); + raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); + + atomic_dec(&cpu_buffer->record_disabled); + atomic_dec(&cpu_buffer->buffer->resize_disabled); + kfree(iter); +} +EXPORT_SYMBOL_GPL(ring_buffer_read_finish); + +/** + * ring_buffer_read - read the next item in the ring buffer by the iterator + * @iter: The ring buffer iterator + * @ts: The time stamp of the event read. + * + * This reads the next event in the ring buffer and increments the iterator. + */ +struct ring_buffer_event * +ring_buffer_read(struct ring_buffer_iter *iter, u64 *ts) +{ + struct ring_buffer_event *event; + struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer; + unsigned long flags; + + raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); + again: + event = rb_iter_peek(iter, ts); + if (!event) + goto out; + + if (event->type_len == RINGBUF_TYPE_PADDING) + goto again; + + rb_advance_iter(iter); + out: + raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); + + return event; +} +EXPORT_SYMBOL_GPL(ring_buffer_read); + +/** + * ring_buffer_size - return the size of the ring buffer (in bytes) + * @buffer: The ring buffer. + */ +unsigned long ring_buffer_size(struct ring_buffer *buffer, int cpu) +{ + /* + * Earlier, this method returned + * BUF_PAGE_SIZE * buffer->nr_pages + * Since the nr_pages field is now removed, we have converted this to + * return the per cpu buffer value. + */ + if (!cpumask_test_cpu(cpu, buffer->cpumask)) + return 0; + + return BUF_PAGE_SIZE * buffer->buffers[cpu]->nr_pages; +} +EXPORT_SYMBOL_GPL(ring_buffer_size); + +static void +rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer) +{ + rb_head_page_deactivate(cpu_buffer); + + cpu_buffer->head_page + = list_entry(cpu_buffer->pages, struct buffer_page, list); + local_set(&cpu_buffer->head_page->write, 0); + local_set(&cpu_buffer->head_page->entries, 0); + local_set(&cpu_buffer->head_page->page->commit, 0); + + cpu_buffer->head_page->read = 0; + + cpu_buffer->tail_page = cpu_buffer->head_page; + cpu_buffer->commit_page = cpu_buffer->head_page; + + INIT_LIST_HEAD(&cpu_buffer->reader_page->list); + INIT_LIST_HEAD(&cpu_buffer->new_pages); + local_set(&cpu_buffer->reader_page->write, 0); + local_set(&cpu_buffer->reader_page->entries, 0); + local_set(&cpu_buffer->reader_page->page->commit, 0); + cpu_buffer->reader_page->read = 0; + + local_set(&cpu_buffer->entries_bytes, 0); + local_set(&cpu_buffer->overrun, 0); + local_set(&cpu_buffer->commit_overrun, 0); + local_set(&cpu_buffer->dropped_events, 0); + local_set(&cpu_buffer->entries, 0); + local_set(&cpu_buffer->committing, 0); + local_set(&cpu_buffer->commits, 0); + cpu_buffer->read = 0; + cpu_buffer->read_bytes = 0; + + cpu_buffer->write_stamp = 0; + cpu_buffer->read_stamp = 0; + + cpu_buffer->lost_events = 0; + cpu_buffer->last_overrun = 0; + + rb_head_page_activate(cpu_buffer); +} + +/** + * ring_buffer_reset_cpu - reset a ring buffer per CPU buffer + * @buffer: The ring buffer to reset a per cpu buffer of + * @cpu: The CPU buffer to be reset + */ +void ring_buffer_reset_cpu(struct ring_buffer *buffer, int cpu) +{ + struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu]; + unsigned long flags; + + if (!cpumask_test_cpu(cpu, buffer->cpumask)) + return; + + atomic_inc(&buffer->resize_disabled); + atomic_inc(&cpu_buffer->record_disabled); + + /* Make sure all commits have finished */ + synchronize_sched(); + + raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); + + if (RB_WARN_ON(cpu_buffer, local_read(&cpu_buffer->committing))) + goto out; + + arch_spin_lock(&cpu_buffer->lock); + + rb_reset_cpu(cpu_buffer); + + arch_spin_unlock(&cpu_buffer->lock); + + out: + raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); + + atomic_dec(&cpu_buffer->record_disabled); + atomic_dec(&buffer->resize_disabled); +} +EXPORT_SYMBOL_GPL(ring_buffer_reset_cpu); + +/** + * ring_buffer_reset - reset a ring buffer + * @buffer: The ring buffer to reset all cpu buffers + */ +void ring_buffer_reset(struct ring_buffer *buffer) +{ + int cpu; + + for_each_buffer_cpu(buffer, cpu) + ring_buffer_reset_cpu(buffer, cpu); +} +EXPORT_SYMBOL_GPL(ring_buffer_reset); + +/** + * rind_buffer_empty - is the ring buffer empty? + * @buffer: The ring buffer to test + */ +int ring_buffer_empty(struct ring_buffer *buffer) +{ + struct ring_buffer_per_cpu *cpu_buffer; + unsigned long flags; + int dolock; + int cpu; + int ret; + + dolock = rb_ok_to_lock(); + + /* yes this is racy, but if you don't like the race, lock the buffer */ + for_each_buffer_cpu(buffer, cpu) { + cpu_buffer = buffer->buffers[cpu]; + local_irq_save(flags); + if (dolock) + raw_spin_lock(&cpu_buffer->reader_lock); + ret = rb_per_cpu_empty(cpu_buffer); + if (dolock) + raw_spin_unlock(&cpu_buffer->reader_lock); + local_irq_restore(flags); + + if (!ret) + return 0; + } + + return 1; +} +EXPORT_SYMBOL_GPL(ring_buffer_empty); + +/** + * ring_buffer_empty_cpu - is a cpu buffer of a ring buffer empty? + * @buffer: The ring buffer + * @cpu: The CPU buffer to test + */ +int ring_buffer_empty_cpu(struct ring_buffer *buffer, int cpu) +{ + struct ring_buffer_per_cpu *cpu_buffer; + unsigned long flags; + int dolock; + int ret; + + if (!cpumask_test_cpu(cpu, buffer->cpumask)) + return 1; + + dolock = rb_ok_to_lock(); + + cpu_buffer = buffer->buffers[cpu]; + local_irq_save(flags); + if (dolock) + raw_spin_lock(&cpu_buffer->reader_lock); + ret = rb_per_cpu_empty(cpu_buffer); + if (dolock) + raw_spin_unlock(&cpu_buffer->reader_lock); + local_irq_restore(flags); + + return ret; +} +EXPORT_SYMBOL_GPL(ring_buffer_empty_cpu); + +#ifdef CONFIG_RING_BUFFER_ALLOW_SWAP +/** + * ring_buffer_swap_cpu - swap a CPU buffer between two ring buffers + * @buffer_a: One buffer to swap with + * @buffer_b: The other buffer to swap with + * + * This function is useful for tracers that want to take a "snapshot" + * of a CPU buffer and has another back up buffer lying around. + * it is expected that the tracer handles the cpu buffer not being + * used at the moment. + */ +int ring_buffer_swap_cpu(struct ring_buffer *buffer_a, + struct ring_buffer *buffer_b, int cpu) +{ + struct ring_buffer_per_cpu *cpu_buffer_a; + struct ring_buffer_per_cpu *cpu_buffer_b; + int ret = -EINVAL; + + if (!cpumask_test_cpu(cpu, buffer_a->cpumask) || + !cpumask_test_cpu(cpu, buffer_b->cpumask)) + goto out; + + cpu_buffer_a = buffer_a->buffers[cpu]; + cpu_buffer_b = buffer_b->buffers[cpu]; + + /* At least make sure the two buffers are somewhat the same */ + if (cpu_buffer_a->nr_pages != cpu_buffer_b->nr_pages) + goto out; + + ret = -EAGAIN; + + if (ring_buffer_flags != RB_BUFFERS_ON) + goto out; + + if (atomic_read(&buffer_a->record_disabled)) + goto out; + + if (atomic_read(&buffer_b->record_disabled)) + goto out; + + if (atomic_read(&cpu_buffer_a->record_disabled)) + goto out; + + if (atomic_read(&cpu_buffer_b->record_disabled)) + goto out; + + /* + * We can't do a synchronize_sched here because this + * function can be called in atomic context. + * Normally this will be called from the same CPU as cpu. + * If not it's up to the caller to protect this. + */ + atomic_inc(&cpu_buffer_a->record_disabled); + atomic_inc(&cpu_buffer_b->record_disabled); + + ret = -EBUSY; + if (local_read(&cpu_buffer_a->committing)) + goto out_dec; + if (local_read(&cpu_buffer_b->committing)) + goto out_dec; + + buffer_a->buffers[cpu] = cpu_buffer_b; + buffer_b->buffers[cpu] = cpu_buffer_a; + + cpu_buffer_b->buffer = buffer_a; + cpu_buffer_a->buffer = buffer_b; + + ret = 0; + +out_dec: + atomic_dec(&cpu_buffer_a->record_disabled); + atomic_dec(&cpu_buffer_b->record_disabled); +out: + return ret; +} +EXPORT_SYMBOL_GPL(ring_buffer_swap_cpu); +#endif /* CONFIG_RING_BUFFER_ALLOW_SWAP */ + +/** + * ring_buffer_alloc_read_page - allocate a page to read from buffer + * @buffer: the buffer to allocate for. + * @cpu: the cpu buffer to allocate. + * + * This function is used in conjunction with ring_buffer_read_page. + * When reading a full page from the ring buffer, these functions + * can be used to speed up the process. The calling function should + * allocate a few pages first with this function. Then when it + * needs to get pages from the ring buffer, it passes the result + * of this function into ring_buffer_read_page, which will swap + * the page that was allocated, with the read page of the buffer. + * + * Returns: + * The page allocated, or NULL on error. + */ +void *ring_buffer_alloc_read_page(struct ring_buffer *buffer, int cpu) +{ + struct buffer_data_page *bpage; + struct page *page; + + page = alloc_pages_node(cpu_to_node(cpu), + GFP_KERNEL | __GFP_NORETRY, 0); + if (!page) + return NULL; + + bpage = page_address(page); + + rb_init_page(bpage); + + return bpage; +} +EXPORT_SYMBOL_GPL(ring_buffer_alloc_read_page); + +/** + * ring_buffer_free_read_page - free an allocated read page + * @buffer: the buffer the page was allocate for + * @data: the page to free + * + * Free a page allocated from ring_buffer_alloc_read_page. + */ +void ring_buffer_free_read_page(struct ring_buffer *buffer, void *data) +{ + free_page((unsigned long)data); +} +EXPORT_SYMBOL_GPL(ring_buffer_free_read_page); + +/** + * ring_buffer_read_page - extract a page from the ring buffer + * @buffer: buffer to extract from + * @data_page: the page to use allocated from ring_buffer_alloc_read_page + * @len: amount to extract + * @cpu: the cpu of the buffer to extract + * @full: should the extraction only happen when the page is full. + * + * This function will pull out a page from the ring buffer and consume it. + * @data_page must be the address of the variable that was returned + * from ring_buffer_alloc_read_page. This is because the page might be used + * to swap with a page in the ring buffer. + * + * for example: + * rpage = ring_buffer_alloc_read_page(buffer, cpu); + * if (!rpage) + * return error; + * ret = ring_buffer_read_page(buffer, &rpage, len, cpu, 0); + * if (ret >= 0) + * process_page(rpage, ret); + * + * When @full is set, the function will not return true unless + * the writer is off the reader page. + * + * Note: it is up to the calling functions to handle sleeps and wakeups. + * The ring buffer can be used anywhere in the kernel and can not + * blindly call wake_up. The layer that uses the ring buffer must be + * responsible for that. + * + * Returns: + * >=0 if data has been transferred, returns the offset of consumed data. + * <0 if no data has been transferred. + */ +int ring_buffer_read_page(struct ring_buffer *buffer, + void **data_page, size_t len, int cpu, int full) +{ + struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu]; + struct ring_buffer_event *event; + struct buffer_data_page *bpage; + struct buffer_page *reader; + unsigned long missed_events; + unsigned long flags; + unsigned int commit; + unsigned int read; + u64 save_timestamp; + int ret = -1; + + if (!cpumask_test_cpu(cpu, buffer->cpumask)) + goto out; + + /* + * If len is not big enough to hold the page header, then + * we can not copy anything. + */ + if (len <= BUF_PAGE_HDR_SIZE) + goto out; + + len -= BUF_PAGE_HDR_SIZE; + + if (!data_page) + goto out; + + bpage = *data_page; + if (!bpage) + goto out; + + raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); + + reader = rb_get_reader_page(cpu_buffer); + if (!reader) + goto out_unlock; + + event = rb_reader_event(cpu_buffer); + + read = reader->read; + commit = rb_page_commit(reader); + + /* Check if any events were dropped */ + missed_events = cpu_buffer->lost_events; + + /* + * If this page has been partially read or + * if len is not big enough to read the rest of the page or + * a writer is still on the page, then + * we must copy the data from the page to the buffer. + * Otherwise, we can simply swap the page with the one passed in. + */ + if (read || (len < (commit - read)) || + cpu_buffer->reader_page == cpu_buffer->commit_page) { + struct buffer_data_page *rpage = cpu_buffer->reader_page->page; + unsigned int rpos = read; + unsigned int pos = 0; + unsigned int size; + + if (full) + goto out_unlock; + + if (len > (commit - read)) + len = (commit - read); + + /* Always keep the time extend and data together */ + size = rb_event_ts_length(event); + + if (len < size) + goto out_unlock; + + /* save the current timestamp, since the user will need it */ + save_timestamp = cpu_buffer->read_stamp; + + /* Need to copy one event at a time */ + do { + /* We need the size of one event, because + * rb_advance_reader only advances by one event, + * whereas rb_event_ts_length may include the size of + * one or two events. + * We have already ensured there's enough space if this + * is a time extend. */ + size = rb_event_length(event); + memcpy(bpage->data + pos, rpage->data + rpos, size); + + len -= size; + + rb_advance_reader(cpu_buffer); + rpos = reader->read; + pos += size; + + if (rpos >= commit) + break; + + event = rb_reader_event(cpu_buffer); + /* Always keep the time extend and data together */ + size = rb_event_ts_length(event); + } while (len >= size); + + /* update bpage */ + local_set(&bpage->commit, pos); + bpage->time_stamp = save_timestamp; + + /* we copied everything to the beginning */ + read = 0; + } else { + /* update the entry counter */ + cpu_buffer->read += rb_page_entries(reader); + cpu_buffer->read_bytes += BUF_PAGE_SIZE; + + /* swap the pages */ + rb_init_page(bpage); + bpage = reader->page; + reader->page = *data_page; + local_set(&reader->write, 0); + local_set(&reader->entries, 0); + reader->read = 0; + *data_page = bpage; + + /* + * Use the real_end for the data size, + * This gives us a chance to store the lost events + * on the page. + */ + if (reader->real_end) + local_set(&bpage->commit, reader->real_end); + } + ret = read; + + cpu_buffer->lost_events = 0; + + commit = local_read(&bpage->commit); + /* + * Set a flag in the commit field if we lost events + */ + if (missed_events) { + /* If there is room at the end of the page to save the + * missed events, then record it there. + */ + if (BUF_PAGE_SIZE - commit >= sizeof(missed_events)) { + memcpy(&bpage->data[commit], &missed_events, + sizeof(missed_events)); + local_add(RB_MISSED_STORED, &bpage->commit); + commit += sizeof(missed_events); + } + local_add(RB_MISSED_EVENTS, &bpage->commit); + } + + /* + * This page may be off to user land. Zero it out here. + */ + if (commit < BUF_PAGE_SIZE) + memset(&bpage->data[commit], 0, BUF_PAGE_SIZE - commit); + + out_unlock: + raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); + + out: + return ret; +} +EXPORT_SYMBOL_GPL(ring_buffer_read_page); + +#ifdef CONFIG_HOTPLUG_CPU +static int rb_cpu_notify(struct notifier_block *self, + unsigned long action, void *hcpu) +{ + struct ring_buffer *buffer = + container_of(self, struct ring_buffer, cpu_notify); + long cpu = (long)hcpu; + int cpu_i, nr_pages_same; + unsigned int nr_pages; + + switch (action) { + case CPU_UP_PREPARE: + case CPU_UP_PREPARE_FROZEN: + if (cpumask_test_cpu(cpu, buffer->cpumask)) + return NOTIFY_OK; + + nr_pages = 0; + nr_pages_same = 1; + /* check if all cpu sizes are same */ + for_each_buffer_cpu(buffer, cpu_i) { + /* fill in the size from first enabled cpu */ + if (nr_pages == 0) + nr_pages = buffer->buffers[cpu_i]->nr_pages; + if (nr_pages != buffer->buffers[cpu_i]->nr_pages) { + nr_pages_same = 0; + break; + } + } + /* allocate minimum pages, user can later expand it */ + if (!nr_pages_same) + nr_pages = 2; + buffer->buffers[cpu] = + rb_allocate_cpu_buffer(buffer, nr_pages, cpu); + if (!buffer->buffers[cpu]) { + WARN(1, "failed to allocate ring buffer on CPU %ld\n", + cpu); + return NOTIFY_OK; + } + smp_wmb(); + cpumask_set_cpu(cpu, buffer->cpumask); + break; + case CPU_DOWN_PREPARE: + case CPU_DOWN_PREPARE_FROZEN: + /* + * Do nothing. + * If we were to free the buffer, then the user would + * lose any trace that was in the buffer. + */ + break; + default: + break; + } + return NOTIFY_OK; +} +#endif + +#ifdef CONFIG_RING_BUFFER_STARTUP_TEST +/* + * This is a basic integrity check of the ring buffer. + * Late in the boot cycle this test will run when configured in. + * It will kick off a thread per CPU that will go into a loop + * writing to the per cpu ring buffer various sizes of data. + * Some of the data will be large items, some small. + * + * Another thread is created that goes into a spin, sending out + * IPIs to the other CPUs to also write into the ring buffer. + * this is to test the nesting ability of the buffer. + * + * Basic stats are recorded and reported. If something in the + * ring buffer should happen that's not expected, a big warning + * is displayed and all ring buffers are disabled. + */ +static struct task_struct *rb_threads[NR_CPUS] __initdata; + +struct rb_test_data { + struct ring_buffer *buffer; + unsigned long events; + unsigned long bytes_written; + unsigned long bytes_alloc; + unsigned long bytes_dropped; + unsigned long events_nested; + unsigned long bytes_written_nested; + unsigned long bytes_alloc_nested; + unsigned long bytes_dropped_nested; + int min_size_nested; + int max_size_nested; + int max_size; + int min_size; + int cpu; + int cnt; +}; + +static struct rb_test_data rb_data[NR_CPUS] __initdata; + +/* 1 meg per cpu */ +#define RB_TEST_BUFFER_SIZE 1048576 + +static char rb_string[] __initdata = + "abcdefghijklmnopqrstuvwxyz1234567890!@#$%^&*()?+\\" + "?+|:';\",.<>/?abcdefghijklmnopqrstuvwxyz1234567890" + "!@#$%^&*()?+\\?+|:';\",.<>/?abcdefghijklmnopqrstuv"; + +static bool rb_test_started __initdata; + +struct rb_item { + int size; + char str[]; +}; + +static __init int rb_write_something(struct rb_test_data *data, bool nested) +{ + struct ring_buffer_event *event; + struct rb_item *item; + bool started; + int event_len; + int size; + int len; + int cnt; + + /* Have nested writes different that what is written */ + cnt = data->cnt + (nested ? 27 : 0); + + /* Multiply cnt by ~e, to make some unique increment */ + size = (data->cnt * 68 / 25) % (sizeof(rb_string) - 1); + + len = size + sizeof(struct rb_item); + + started = rb_test_started; + /* read rb_test_started before checking buffer enabled */ + smp_rmb(); + + event = ring_buffer_lock_reserve(data->buffer, len); + if (!event) { + /* Ignore dropped events before test starts. */ + if (started) { + if (nested) + data->bytes_dropped += len; + else + data->bytes_dropped_nested += len; + } + return len; + } + + event_len = ring_buffer_event_length(event); + + if (RB_WARN_ON(data->buffer, event_len < len)) + goto out; + + item = ring_buffer_event_data(event); + item->size = size; + memcpy(item->str, rb_string, size); + + if (nested) { + data->bytes_alloc_nested += event_len; + data->bytes_written_nested += len; + data->events_nested++; + if (!data->min_size_nested || len < data->min_size_nested) + data->min_size_nested = len; + if (len > data->max_size_nested) + data->max_size_nested = len; + } else { + data->bytes_alloc += event_len; + data->bytes_written += len; + data->events++; + if (!data->min_size || len < data->min_size) + data->max_size = len; + if (len > data->max_size) + data->max_size = len; + } + + out: + ring_buffer_unlock_commit(data->buffer, event); + + return 0; +} + +static __init int rb_test(void *arg) +{ + struct rb_test_data *data = arg; + + while (!kthread_should_stop()) { + rb_write_something(data, false); + data->cnt++; + + set_current_state(TASK_INTERRUPTIBLE); + /* Now sleep between a min of 100-300us and a max of 1ms */ + usleep_range(((data->cnt % 3) + 1) * 100, 1000); + } + + return 0; +} + +static __init void rb_ipi(void *ignore) +{ + struct rb_test_data *data; + int cpu = smp_processor_id(); + + data = &rb_data[cpu]; + rb_write_something(data, true); +} + +static __init int rb_hammer_test(void *arg) +{ + while (!kthread_should_stop()) { + + /* Send an IPI to all cpus to write data! */ + smp_call_function(rb_ipi, NULL, 1); + /* No sleep, but for non preempt, let others run */ + schedule(); + } + + return 0; +} + +static __init int test_ringbuffer(void) +{ + struct task_struct *rb_hammer; + struct ring_buffer *buffer; + int cpu; + int ret = 0; + + pr_info("Running ring buffer tests...\n"); + + buffer = ring_buffer_alloc(RB_TEST_BUFFER_SIZE, RB_FL_OVERWRITE); + if (WARN_ON(!buffer)) + return 0; + + /* Disable buffer so that threads can't write to it yet */ + ring_buffer_record_off(buffer); + + for_each_online_cpu(cpu) { + rb_data[cpu].buffer = buffer; + rb_data[cpu].cpu = cpu; + rb_data[cpu].cnt = cpu; + rb_threads[cpu] = kthread_create(rb_test, &rb_data[cpu], + "rbtester/%d", cpu); + if (WARN_ON(!rb_threads[cpu])) { + pr_cont("FAILED\n"); + ret = -1; + goto out_free; + } + + kthread_bind(rb_threads[cpu], cpu); + wake_up_process(rb_threads[cpu]); + } + + /* Now create the rb hammer! */ + rb_hammer = kthread_run(rb_hammer_test, NULL, "rbhammer"); + if (WARN_ON(!rb_hammer)) { + pr_cont("FAILED\n"); + ret = -1; + goto out_free; + } + + ring_buffer_record_on(buffer); + /* + * Show buffer is enabled before setting rb_test_started. + * Yes there's a small race window where events could be + * dropped and the thread wont catch it. But when a ring + * buffer gets enabled, there will always be some kind of + * delay before other CPUs see it. Thus, we don't care about + * those dropped events. We care about events dropped after + * the threads see that the buffer is active. + */ + smp_wmb(); + rb_test_started = true; + + set_current_state(TASK_INTERRUPTIBLE); + /* Just run for 10 seconds */; + schedule_timeout(10 * HZ); + + kthread_stop(rb_hammer); + + out_free: + for_each_online_cpu(cpu) { + if (!rb_threads[cpu]) + break; + kthread_stop(rb_threads[cpu]); + } + if (ret) { + ring_buffer_free(buffer); + return ret; + } + + /* Report! */ + pr_info("finished\n"); + for_each_online_cpu(cpu) { + struct ring_buffer_event *event; + struct rb_test_data *data = &rb_data[cpu]; + struct rb_item *item; + unsigned long total_events; + unsigned long total_dropped; + unsigned long total_written; + unsigned long total_alloc; + unsigned long total_read = 0; + unsigned long total_size = 0; + unsigned long total_len = 0; + unsigned long total_lost = 0; + unsigned long lost; + int big_event_size; + int small_event_size; + + ret = -1; + + total_events = data->events + data->events_nested; + total_written = data->bytes_written + data->bytes_written_nested; + total_alloc = data->bytes_alloc + data->bytes_alloc_nested; + total_dropped = data->bytes_dropped + data->bytes_dropped_nested; + + big_event_size = data->max_size + data->max_size_nested; + small_event_size = data->min_size + data->min_size_nested; + + pr_info("CPU %d:\n", cpu); + pr_info(" events: %ld\n", total_events); + pr_info(" dropped bytes: %ld\n", total_dropped); + pr_info(" alloced bytes: %ld\n", total_alloc); + pr_info(" written bytes: %ld\n", total_written); + pr_info(" biggest event: %d\n", big_event_size); + pr_info(" smallest event: %d\n", small_event_size); + + if (RB_WARN_ON(buffer, total_dropped)) + break; + + ret = 0; + + while ((event = ring_buffer_consume(buffer, cpu, NULL, &lost))) { + total_lost += lost; + item = ring_buffer_event_data(event); + total_len += ring_buffer_event_length(event); + total_size += item->size + sizeof(struct rb_item); + if (memcmp(&item->str[0], rb_string, item->size) != 0) { + pr_info("FAILED!\n"); + pr_info("buffer had: %.*s\n", item->size, item->str); + pr_info("expected: %.*s\n", item->size, rb_string); + RB_WARN_ON(buffer, 1); + ret = -1; + break; + } + total_read++; + } + if (ret) + break; + + ret = -1; + + pr_info(" read events: %ld\n", total_read); + pr_info(" lost events: %ld\n", total_lost); + pr_info(" total events: %ld\n", total_lost + total_read); + pr_info(" recorded len bytes: %ld\n", total_len); + pr_info(" recorded size bytes: %ld\n", total_size); + if (total_lost) + pr_info(" With dropped events, record len and size may not match\n" + " alloced and written from above\n"); + if (!total_lost) { + if (RB_WARN_ON(buffer, total_len != total_alloc || + total_size != total_written)) + break; + } + if (RB_WARN_ON(buffer, total_lost + total_read != total_events)) + break; + + ret = 0; + } + if (!ret) + pr_info("Ring buffer PASSED!\n"); + + ring_buffer_free(buffer); + return 0; +} + +late_initcall(test_ringbuffer); +#endif /* CONFIG_RING_BUFFER_STARTUP_TEST */ diff --git a/kernel/kernel/trace/ring_buffer_benchmark.c b/kernel/kernel/trace/ring_buffer_benchmark.c new file mode 100644 index 000000000..1b28df2d9 --- /dev/null +++ b/kernel/kernel/trace/ring_buffer_benchmark.c @@ -0,0 +1,483 @@ +/* + * ring buffer tester and benchmark + * + * Copyright (C) 2009 Steven Rostedt + */ +#include +#include +#include +#include +#include +#include + +struct rb_page { + u64 ts; + local_t commit; + char data[4080]; +}; + +/* run time and sleep time in seconds */ +#define RUN_TIME 10ULL +#define SLEEP_TIME 10 + +/* number of events for writer to wake up the reader */ +static int wakeup_interval = 100; + +static int reader_finish; +static struct completion read_start; +static struct completion read_done; + +static struct ring_buffer *buffer; +static struct task_struct *producer; +static struct task_struct *consumer; +static unsigned long read; + +static int disable_reader; +module_param(disable_reader, uint, 0644); +MODULE_PARM_DESC(disable_reader, "only run producer"); + +static int write_iteration = 50; +module_param(write_iteration, uint, 0644); +MODULE_PARM_DESC(write_iteration, "# of writes between timestamp readings"); + +static int producer_nice = MAX_NICE; +static int consumer_nice = MAX_NICE; + +static int producer_fifo = -1; +static int consumer_fifo = -1; + +module_param(producer_nice, uint, 0644); +MODULE_PARM_DESC(producer_nice, "nice prio for producer"); + +module_param(consumer_nice, uint, 0644); +MODULE_PARM_DESC(consumer_nice, "nice prio for consumer"); + +module_param(producer_fifo, uint, 0644); +MODULE_PARM_DESC(producer_fifo, "fifo prio for producer"); + +module_param(consumer_fifo, uint, 0644); +MODULE_PARM_DESC(consumer_fifo, "fifo prio for consumer"); + +static int read_events; + +static int kill_test; + +#define KILL_TEST() \ + do { \ + if (!kill_test) { \ + kill_test = 1; \ + WARN_ON(1); \ + } \ + } while (0) + +enum event_status { + EVENT_FOUND, + EVENT_DROPPED, +}; + +static enum event_status read_event(int cpu) +{ + struct ring_buffer_event *event; + int *entry; + u64 ts; + + event = ring_buffer_consume(buffer, cpu, &ts, NULL); + if (!event) + return EVENT_DROPPED; + + entry = ring_buffer_event_data(event); + if (*entry != cpu) { + KILL_TEST(); + return EVENT_DROPPED; + } + + read++; + return EVENT_FOUND; +} + +static enum event_status read_page(int cpu) +{ + struct ring_buffer_event *event; + struct rb_page *rpage; + unsigned long commit; + void *bpage; + int *entry; + int ret; + int inc; + int i; + + bpage = ring_buffer_alloc_read_page(buffer, cpu); + if (!bpage) + return EVENT_DROPPED; + + ret = ring_buffer_read_page(buffer, &bpage, PAGE_SIZE, cpu, 1); + if (ret >= 0) { + rpage = bpage; + /* The commit may have missed event flags set, clear them */ + commit = local_read(&rpage->commit) & 0xfffff; + for (i = 0; i < commit && !kill_test; i += inc) { + + if (i >= (PAGE_SIZE - offsetof(struct rb_page, data))) { + KILL_TEST(); + break; + } + + inc = -1; + event = (void *)&rpage->data[i]; + switch (event->type_len) { + case RINGBUF_TYPE_PADDING: + /* failed writes may be discarded events */ + if (!event->time_delta) + KILL_TEST(); + inc = event->array[0] + 4; + break; + case RINGBUF_TYPE_TIME_EXTEND: + inc = 8; + break; + case 0: + entry = ring_buffer_event_data(event); + if (*entry != cpu) { + KILL_TEST(); + break; + } + read++; + if (!event->array[0]) { + KILL_TEST(); + break; + } + inc = event->array[0] + 4; + break; + default: + entry = ring_buffer_event_data(event); + if (*entry != cpu) { + KILL_TEST(); + break; + } + read++; + inc = ((event->type_len + 1) * 4); + } + if (kill_test) + break; + + if (inc <= 0) { + KILL_TEST(); + break; + } + } + } + ring_buffer_free_read_page(buffer, bpage); + + if (ret < 0) + return EVENT_DROPPED; + return EVENT_FOUND; +} + +static void ring_buffer_consumer(void) +{ + /* toggle between reading pages and events */ + read_events ^= 1; + + read = 0; + while (!reader_finish && !kill_test) { + int found; + + do { + int cpu; + + found = 0; + for_each_online_cpu(cpu) { + enum event_status stat; + + if (read_events) + stat = read_event(cpu); + else + stat = read_page(cpu); + + if (kill_test) + break; + if (stat == EVENT_FOUND) + found = 1; + } + } while (found && !kill_test); + + set_current_state(TASK_INTERRUPTIBLE); + if (reader_finish) + break; + + schedule(); + } + reader_finish = 0; + complete(&read_done); +} + +static void ring_buffer_producer(void) +{ + ktime_t start_time, end_time, timeout; + unsigned long long time; + unsigned long long entries; + unsigned long long overruns; + unsigned long missed = 0; + unsigned long hit = 0; + unsigned long avg; + int cnt = 0; + + /* + * Hammer the buffer for 10 secs (this may + * make the system stall) + */ + trace_printk("Starting ring buffer hammer\n"); + start_time = ktime_get(); + timeout = ktime_add_ns(start_time, RUN_TIME * NSEC_PER_SEC); + do { + struct ring_buffer_event *event; + int *entry; + int i; + + for (i = 0; i < write_iteration; i++) { + event = ring_buffer_lock_reserve(buffer, 10); + if (!event) { + missed++; + } else { + hit++; + entry = ring_buffer_event_data(event); + *entry = smp_processor_id(); + ring_buffer_unlock_commit(buffer, event); + } + } + end_time = ktime_get(); + + cnt++; + if (consumer && !(cnt % wakeup_interval)) + wake_up_process(consumer); + +#ifndef CONFIG_PREEMPT + /* + * If we are a non preempt kernel, the 10 second run will + * stop everything while it runs. Instead, we will call + * cond_resched and also add any time that was lost by a + * rescedule. + * + * Do a cond resched at the same frequency we would wake up + * the reader. + */ + if (cnt % wakeup_interval) + cond_resched(); +#endif + + } while (ktime_before(end_time, timeout) && !kill_test); + trace_printk("End ring buffer hammer\n"); + + if (consumer) { + /* Init both completions here to avoid races */ + init_completion(&read_start); + init_completion(&read_done); + /* the completions must be visible before the finish var */ + smp_wmb(); + reader_finish = 1; + /* finish var visible before waking up the consumer */ + smp_wmb(); + wake_up_process(consumer); + wait_for_completion(&read_done); + } + + time = ktime_us_delta(end_time, start_time); + + entries = ring_buffer_entries(buffer); + overruns = ring_buffer_overruns(buffer); + + if (kill_test) + trace_printk("ERROR!\n"); + + if (!disable_reader) { + if (consumer_fifo < 0) + trace_printk("Running Consumer at nice: %d\n", + consumer_nice); + else + trace_printk("Running Consumer at SCHED_FIFO %d\n", + consumer_fifo); + } + if (producer_fifo < 0) + trace_printk("Running Producer at nice: %d\n", + producer_nice); + else + trace_printk("Running Producer at SCHED_FIFO %d\n", + producer_fifo); + + /* Let the user know that the test is running at low priority */ + if (producer_fifo < 0 && consumer_fifo < 0 && + producer_nice == MAX_NICE && consumer_nice == MAX_NICE) + trace_printk("WARNING!!! This test is running at lowest priority.\n"); + + trace_printk("Time: %lld (usecs)\n", time); + trace_printk("Overruns: %lld\n", overruns); + if (disable_reader) + trace_printk("Read: (reader disabled)\n"); + else + trace_printk("Read: %ld (by %s)\n", read, + read_events ? "events" : "pages"); + trace_printk("Entries: %lld\n", entries); + trace_printk("Total: %lld\n", entries + overruns + read); + trace_printk("Missed: %ld\n", missed); + trace_printk("Hit: %ld\n", hit); + + /* Convert time from usecs to millisecs */ + do_div(time, USEC_PER_MSEC); + if (time) + hit /= (long)time; + else + trace_printk("TIME IS ZERO??\n"); + + trace_printk("Entries per millisec: %ld\n", hit); + + if (hit) { + /* Calculate the average time in nanosecs */ + avg = NSEC_PER_MSEC / hit; + trace_printk("%ld ns per entry\n", avg); + } + + if (missed) { + if (time) + missed /= (long)time; + + trace_printk("Total iterations per millisec: %ld\n", + hit + missed); + + /* it is possible that hit + missed will overflow and be zero */ + if (!(hit + missed)) { + trace_printk("hit + missed overflowed and totalled zero!\n"); + hit--; /* make it non zero */ + } + + /* Caculate the average time in nanosecs */ + avg = NSEC_PER_MSEC / (hit + missed); + trace_printk("%ld ns per entry\n", avg); + } +} + +static void wait_to_die(void) +{ + set_current_state(TASK_INTERRUPTIBLE); + while (!kthread_should_stop()) { + schedule(); + set_current_state(TASK_INTERRUPTIBLE); + } + __set_current_state(TASK_RUNNING); +} + +static int ring_buffer_consumer_thread(void *arg) +{ + while (!kthread_should_stop() && !kill_test) { + complete(&read_start); + + ring_buffer_consumer(); + + set_current_state(TASK_INTERRUPTIBLE); + if (kthread_should_stop() || kill_test) + break; + + schedule(); + } + __set_current_state(TASK_RUNNING); + + if (kill_test) + wait_to_die(); + + return 0; +} + +static int ring_buffer_producer_thread(void *arg) +{ + init_completion(&read_start); + + while (!kthread_should_stop() && !kill_test) { + ring_buffer_reset(buffer); + + if (consumer) { + smp_wmb(); + wake_up_process(consumer); + wait_for_completion(&read_start); + } + + ring_buffer_producer(); + + trace_printk("Sleeping for 10 secs\n"); + set_current_state(TASK_INTERRUPTIBLE); + schedule_timeout(HZ * SLEEP_TIME); + } + + if (kill_test) + wait_to_die(); + + return 0; +} + +static int __init ring_buffer_benchmark_init(void) +{ + int ret; + + /* make a one meg buffer in overwite mode */ + buffer = ring_buffer_alloc(1000000, RB_FL_OVERWRITE); + if (!buffer) + return -ENOMEM; + + if (!disable_reader) { + consumer = kthread_create(ring_buffer_consumer_thread, + NULL, "rb_consumer"); + ret = PTR_ERR(consumer); + if (IS_ERR(consumer)) + goto out_fail; + } + + producer = kthread_run(ring_buffer_producer_thread, + NULL, "rb_producer"); + ret = PTR_ERR(producer); + + if (IS_ERR(producer)) + goto out_kill; + + /* + * Run them as low-prio background tasks by default: + */ + if (!disable_reader) { + if (consumer_fifo >= 0) { + struct sched_param param = { + .sched_priority = consumer_fifo + }; + sched_setscheduler(consumer, SCHED_FIFO, ¶m); + } else + set_user_nice(consumer, consumer_nice); + } + + if (producer_fifo >= 0) { + struct sched_param param = { + .sched_priority = producer_fifo + }; + sched_setscheduler(producer, SCHED_FIFO, ¶m); + } else + set_user_nice(producer, producer_nice); + + return 0; + + out_kill: + if (consumer) + kthread_stop(consumer); + + out_fail: + ring_buffer_free(buffer); + return ret; +} + +static void __exit ring_buffer_benchmark_exit(void) +{ + kthread_stop(producer); + if (consumer) + kthread_stop(consumer); + ring_buffer_free(buffer); +} + +module_init(ring_buffer_benchmark_init); +module_exit(ring_buffer_benchmark_exit); + +MODULE_AUTHOR("Steven Rostedt"); +MODULE_DESCRIPTION("ring_buffer_benchmark"); +MODULE_LICENSE("GPL"); diff --git a/kernel/kernel/trace/rpm-traces.c b/kernel/kernel/trace/rpm-traces.c new file mode 100644 index 000000000..4b3b5eaf9 --- /dev/null +++ b/kernel/kernel/trace/rpm-traces.c @@ -0,0 +1,20 @@ +/* + * Power trace points + * + * Copyright (C) 2009 Ming Lei + */ + +#include +#include +#include +#include +#include +#include + +#define CREATE_TRACE_POINTS +#include + +EXPORT_TRACEPOINT_SYMBOL_GPL(rpm_return_int); +EXPORT_TRACEPOINT_SYMBOL_GPL(rpm_idle); +EXPORT_TRACEPOINT_SYMBOL_GPL(rpm_suspend); +EXPORT_TRACEPOINT_SYMBOL_GPL(rpm_resume); diff --git a/kernel/kernel/trace/trace.c b/kernel/kernel/trace/trace.c new file mode 100644 index 000000000..5088d1ce2 --- /dev/null +++ b/kernel/kernel/trace/trace.c @@ -0,0 +1,7215 @@ +/* + * ring buffer based function tracer + * + * Copyright (C) 2007-2012 Steven Rostedt + * Copyright (C) 2008 Ingo Molnar + * + * Originally taken from the RT patch by: + * Arnaldo Carvalho de Melo + * + * Based on code from the latency_tracer, that is: + * Copyright (C) 2004-2006 Ingo Molnar + * Copyright (C) 2004 Nadia Yvette Chambers + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "trace.h" +#include "trace_output.h" + +/* + * On boot up, the ring buffer is set to the minimum size, so that + * we do not waste memory on systems that are not using tracing. + */ +bool ring_buffer_expanded; + +/* + * We need to change this state when a selftest is running. + * A selftest will lurk into the ring-buffer to count the + * entries inserted during the selftest although some concurrent + * insertions into the ring-buffer such as trace_printk could occurred + * at the same time, giving false positive or negative results. + */ +static bool __read_mostly tracing_selftest_running; + +/* + * If a tracer is running, we do not want to run SELFTEST. + */ +bool __read_mostly tracing_selftest_disabled; + +/* Pipe tracepoints to printk */ +struct trace_iterator *tracepoint_print_iter; +int tracepoint_printk; + +/* For tracers that don't implement custom flags */ +static struct tracer_opt dummy_tracer_opt[] = { + { } +}; + +static struct tracer_flags dummy_tracer_flags = { + .val = 0, + .opts = dummy_tracer_opt +}; + +static int +dummy_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set) +{ + return 0; +} + +/* + * To prevent the comm cache from being overwritten when no + * tracing is active, only save the comm when a trace event + * occurred. + */ +static DEFINE_PER_CPU(bool, trace_cmdline_save); + +/* + * Kill all tracing for good (never come back). + * It is initialized to 1 but will turn to zero if the initialization + * of the tracer is successful. But that is the only place that sets + * this back to zero. + */ +static int tracing_disabled = 1; + +DEFINE_PER_CPU(int, ftrace_cpu_disabled); + +cpumask_var_t __read_mostly tracing_buffer_mask; + +/* + * ftrace_dump_on_oops - variable to dump ftrace buffer on oops + * + * If there is an oops (or kernel panic) and the ftrace_dump_on_oops + * is set, then ftrace_dump is called. This will output the contents + * of the ftrace buffers to the console. This is very useful for + * capturing traces that lead to crashes and outputing it to a + * serial console. + * + * It is default off, but you can enable it with either specifying + * "ftrace_dump_on_oops" in the kernel command line, or setting + * /proc/sys/kernel/ftrace_dump_on_oops + * Set 1 if you want to dump buffers of all CPUs + * Set 2 if you want to dump the buffer of the CPU that triggered oops + */ + +enum ftrace_dump_mode ftrace_dump_on_oops; + +/* When set, tracing will stop when a WARN*() is hit */ +int __disable_trace_on_warning; + +#ifdef CONFIG_TRACE_ENUM_MAP_FILE +/* Map of enums to their values, for "enum_map" file */ +struct trace_enum_map_head { + struct module *mod; + unsigned long length; +}; + +union trace_enum_map_item; + +struct trace_enum_map_tail { + /* + * "end" is first and points to NULL as it must be different + * than "mod" or "enum_string" + */ + union trace_enum_map_item *next; + const char *end; /* points to NULL */ +}; + +static DEFINE_MUTEX(trace_enum_mutex); + +/* + * The trace_enum_maps are saved in an array with two extra elements, + * one at the beginning, and one at the end. The beginning item contains + * the count of the saved maps (head.length), and the module they + * belong to if not built in (head.mod). The ending item contains a + * pointer to the next array of saved enum_map items. + */ +union trace_enum_map_item { + struct trace_enum_map map; + struct trace_enum_map_head head; + struct trace_enum_map_tail tail; +}; + +static union trace_enum_map_item *trace_enum_maps; +#endif /* CONFIG_TRACE_ENUM_MAP_FILE */ + +static int tracing_set_tracer(struct trace_array *tr, const char *buf); + +#define MAX_TRACER_SIZE 100 +static char bootup_tracer_buf[MAX_TRACER_SIZE] __initdata; +static char *default_bootup_tracer; + +static bool allocate_snapshot; + +static int __init set_cmdline_ftrace(char *str) +{ + strlcpy(bootup_tracer_buf, str, MAX_TRACER_SIZE); + default_bootup_tracer = bootup_tracer_buf; + /* We are using ftrace early, expand it */ + ring_buffer_expanded = true; + return 1; +} +__setup("ftrace=", set_cmdline_ftrace); + +static int __init set_ftrace_dump_on_oops(char *str) +{ + if (*str++ != '=' || !*str) { + ftrace_dump_on_oops = DUMP_ALL; + return 1; + } + + if (!strcmp("orig_cpu", str)) { + ftrace_dump_on_oops = DUMP_ORIG; + return 1; + } + + return 0; +} +__setup("ftrace_dump_on_oops", set_ftrace_dump_on_oops); + +static int __init stop_trace_on_warning(char *str) +{ + if ((strcmp(str, "=0") != 0 && strcmp(str, "=off") != 0)) + __disable_trace_on_warning = 1; + return 1; +} +__setup("traceoff_on_warning", stop_trace_on_warning); + +static int __init boot_alloc_snapshot(char *str) +{ + allocate_snapshot = true; + /* We also need the main ring buffer expanded */ + ring_buffer_expanded = true; + return 1; +} +__setup("alloc_snapshot", boot_alloc_snapshot); + + +static char trace_boot_options_buf[MAX_TRACER_SIZE] __initdata; +static char *trace_boot_options __initdata; + +static int __init set_trace_boot_options(char *str) +{ + strlcpy(trace_boot_options_buf, str, MAX_TRACER_SIZE); + trace_boot_options = trace_boot_options_buf; + return 0; +} +__setup("trace_options=", set_trace_boot_options); + +static char trace_boot_clock_buf[MAX_TRACER_SIZE] __initdata; +static char *trace_boot_clock __initdata; + +static int __init set_trace_boot_clock(char *str) +{ + strlcpy(trace_boot_clock_buf, str, MAX_TRACER_SIZE); + trace_boot_clock = trace_boot_clock_buf; + return 0; +} +__setup("trace_clock=", set_trace_boot_clock); + +static int __init set_tracepoint_printk(char *str) +{ + if ((strcmp(str, "=0") != 0 && strcmp(str, "=off") != 0)) + tracepoint_printk = 1; + return 1; +} +__setup("tp_printk", set_tracepoint_printk); + +unsigned long long ns2usecs(cycle_t nsec) +{ + nsec += 500; + do_div(nsec, 1000); + return nsec; +} + +/* + * The global_trace is the descriptor that holds the tracing + * buffers for the live tracing. For each CPU, it contains + * a link list of pages that will store trace entries. The + * page descriptor of the pages in the memory is used to hold + * the link list by linking the lru item in the page descriptor + * to each of the pages in the buffer per CPU. + * + * For each active CPU there is a data field that holds the + * pages for the buffer for that CPU. Each CPU has the same number + * of pages allocated for its buffer. + */ +static struct trace_array global_trace; + +LIST_HEAD(ftrace_trace_arrays); + +int trace_array_get(struct trace_array *this_tr) +{ + struct trace_array *tr; + int ret = -ENODEV; + + mutex_lock(&trace_types_lock); + list_for_each_entry(tr, &ftrace_trace_arrays, list) { + if (tr == this_tr) { + tr->ref++; + ret = 0; + break; + } + } + mutex_unlock(&trace_types_lock); + + return ret; +} + +static void __trace_array_put(struct trace_array *this_tr) +{ + WARN_ON(!this_tr->ref); + this_tr->ref--; +} + +void trace_array_put(struct trace_array *this_tr) +{ + mutex_lock(&trace_types_lock); + __trace_array_put(this_tr); + mutex_unlock(&trace_types_lock); +} + +int filter_check_discard(struct ftrace_event_file *file, void *rec, + struct ring_buffer *buffer, + struct ring_buffer_event *event) +{ + if (unlikely(file->flags & FTRACE_EVENT_FL_FILTERED) && + !filter_match_preds(file->filter, rec)) { + ring_buffer_discard_commit(buffer, event); + return 1; + } + + return 0; +} +EXPORT_SYMBOL_GPL(filter_check_discard); + +int call_filter_check_discard(struct ftrace_event_call *call, void *rec, + struct ring_buffer *buffer, + struct ring_buffer_event *event) +{ + if (unlikely(call->flags & TRACE_EVENT_FL_FILTERED) && + !filter_match_preds(call->filter, rec)) { + ring_buffer_discard_commit(buffer, event); + return 1; + } + + return 0; +} +EXPORT_SYMBOL_GPL(call_filter_check_discard); + +static cycle_t buffer_ftrace_now(struct trace_buffer *buf, int cpu) +{ + u64 ts; + + /* Early boot up does not have a buffer yet */ + if (!buf->buffer) + return trace_clock_local(); + + ts = ring_buffer_time_stamp(buf->buffer, cpu); + ring_buffer_normalize_time_stamp(buf->buffer, cpu, &ts); + + return ts; +} + +cycle_t ftrace_now(int cpu) +{ + return buffer_ftrace_now(&global_trace.trace_buffer, cpu); +} + +/** + * tracing_is_enabled - Show if global_trace has been disabled + * + * Shows if the global trace has been enabled or not. It uses the + * mirror flag "buffer_disabled" to be used in fast paths such as for + * the irqsoff tracer. But it may be inaccurate due to races. If you + * need to know the accurate state, use tracing_is_on() which is a little + * slower, but accurate. + */ +int tracing_is_enabled(void) +{ + /* + * For quick access (irqsoff uses this in fast path), just + * return the mirror variable of the state of the ring buffer. + * It's a little racy, but we don't really care. + */ + smp_rmb(); + return !global_trace.buffer_disabled; +} + +/* + * trace_buf_size is the size in bytes that is allocated + * for a buffer. Note, the number of bytes is always rounded + * to page size. + * + * This number is purposely set to a low number of 16384. + * If the dump on oops happens, it will be much appreciated + * to not have to wait for all that output. Anyway this can be + * boot time and run time configurable. + */ +#define TRACE_BUF_SIZE_DEFAULT 1441792UL /* 16384 * 88 (sizeof(entry)) */ + +static unsigned long trace_buf_size = TRACE_BUF_SIZE_DEFAULT; + +/* trace_types holds a link list of available tracers. */ +static struct tracer *trace_types __read_mostly; + +/* + * trace_types_lock is used to protect the trace_types list. + */ +DEFINE_MUTEX(trace_types_lock); + +/* + * serialize the access of the ring buffer + * + * ring buffer serializes readers, but it is low level protection. + * The validity of the events (which returns by ring_buffer_peek() ..etc) + * are not protected by ring buffer. + * + * The content of events may become garbage if we allow other process consumes + * these events concurrently: + * A) the page of the consumed events may become a normal page + * (not reader page) in ring buffer, and this page will be rewrited + * by events producer. + * B) The page of the consumed events may become a page for splice_read, + * and this page will be returned to system. + * + * These primitives allow multi process access to different cpu ring buffer + * concurrently. + * + * These primitives don't distinguish read-only and read-consume access. + * Multi read-only access are also serialized. + */ + +#ifdef CONFIG_SMP +static DECLARE_RWSEM(all_cpu_access_lock); +static DEFINE_PER_CPU(struct mutex, cpu_access_lock); + +static inline void trace_access_lock(int cpu) +{ + if (cpu == RING_BUFFER_ALL_CPUS) { + /* gain it for accessing the whole ring buffer. */ + down_write(&all_cpu_access_lock); + } else { + /* gain it for accessing a cpu ring buffer. */ + + /* Firstly block other trace_access_lock(RING_BUFFER_ALL_CPUS). */ + down_read(&all_cpu_access_lock); + + /* Secondly block other access to this @cpu ring buffer. */ + mutex_lock(&per_cpu(cpu_access_lock, cpu)); + } +} + +static inline void trace_access_unlock(int cpu) +{ + if (cpu == RING_BUFFER_ALL_CPUS) { + up_write(&all_cpu_access_lock); + } else { + mutex_unlock(&per_cpu(cpu_access_lock, cpu)); + up_read(&all_cpu_access_lock); + } +} + +static inline void trace_access_lock_init(void) +{ + int cpu; + + for_each_possible_cpu(cpu) + mutex_init(&per_cpu(cpu_access_lock, cpu)); +} + +#else + +static DEFINE_MUTEX(access_lock); + +static inline void trace_access_lock(int cpu) +{ + (void)cpu; + mutex_lock(&access_lock); +} + +static inline void trace_access_unlock(int cpu) +{ + (void)cpu; + mutex_unlock(&access_lock); +} + +static inline void trace_access_lock_init(void) +{ +} + +#endif + +/* trace_flags holds trace_options default values */ +unsigned long trace_flags = TRACE_ITER_PRINT_PARENT | TRACE_ITER_PRINTK | + TRACE_ITER_ANNOTATE | TRACE_ITER_CONTEXT_INFO | TRACE_ITER_SLEEP_TIME | + TRACE_ITER_GRAPH_TIME | TRACE_ITER_RECORD_CMD | TRACE_ITER_OVERWRITE | + TRACE_ITER_IRQ_INFO | TRACE_ITER_MARKERS | TRACE_ITER_FUNCTION; + +static void tracer_tracing_on(struct trace_array *tr) +{ + if (tr->trace_buffer.buffer) + ring_buffer_record_on(tr->trace_buffer.buffer); + /* + * This flag is looked at when buffers haven't been allocated + * yet, or by some tracers (like irqsoff), that just want to + * know if the ring buffer has been disabled, but it can handle + * races of where it gets disabled but we still do a record. + * As the check is in the fast path of the tracers, it is more + * important to be fast than accurate. + */ + tr->buffer_disabled = 0; + /* Make the flag seen by readers */ + smp_wmb(); +} + +/** + * tracing_on - enable tracing buffers + * + * This function enables tracing buffers that may have been + * disabled with tracing_off. + */ +void tracing_on(void) +{ + tracer_tracing_on(&global_trace); +} +EXPORT_SYMBOL_GPL(tracing_on); + +/** + * __trace_puts - write a constant string into the trace buffer. + * @ip: The address of the caller + * @str: The constant string to write + * @size: The size of the string. + */ +int __trace_puts(unsigned long ip, const char *str, int size) +{ + struct ring_buffer_event *event; + struct ring_buffer *buffer; + struct print_entry *entry; + unsigned long irq_flags; + int alloc; + int pc; + + if (!(trace_flags & TRACE_ITER_PRINTK)) + return 0; + + pc = preempt_count(); + + if (unlikely(tracing_selftest_running || tracing_disabled)) + return 0; + + alloc = sizeof(*entry) + size + 2; /* possible \n added */ + + local_save_flags(irq_flags); + buffer = global_trace.trace_buffer.buffer; + event = trace_buffer_lock_reserve(buffer, TRACE_PRINT, alloc, + irq_flags, pc); + if (!event) + return 0; + + entry = ring_buffer_event_data(event); + entry->ip = ip; + + memcpy(&entry->buf, str, size); + + /* Add a newline if necessary */ + if (entry->buf[size - 1] != '\n') { + entry->buf[size] = '\n'; + entry->buf[size + 1] = '\0'; + } else + entry->buf[size] = '\0'; + + __buffer_unlock_commit(buffer, event); + ftrace_trace_stack(buffer, irq_flags, 4, pc); + + return size; +} +EXPORT_SYMBOL_GPL(__trace_puts); + +/** + * __trace_bputs - write the pointer to a constant string into trace buffer + * @ip: The address of the caller + * @str: The constant string to write to the buffer to + */ +int __trace_bputs(unsigned long ip, const char *str) +{ + struct ring_buffer_event *event; + struct ring_buffer *buffer; + struct bputs_entry *entry; + unsigned long irq_flags; + int size = sizeof(struct bputs_entry); + int pc; + + if (!(trace_flags & TRACE_ITER_PRINTK)) + return 0; + + pc = preempt_count(); + + if (unlikely(tracing_selftest_running || tracing_disabled)) + return 0; + + local_save_flags(irq_flags); + buffer = global_trace.trace_buffer.buffer; + event = trace_buffer_lock_reserve(buffer, TRACE_BPUTS, size, + irq_flags, pc); + if (!event) + return 0; + + entry = ring_buffer_event_data(event); + entry->ip = ip; + entry->str = str; + + __buffer_unlock_commit(buffer, event); + ftrace_trace_stack(buffer, irq_flags, 4, pc); + + return 1; +} +EXPORT_SYMBOL_GPL(__trace_bputs); + +#ifdef CONFIG_TRACER_SNAPSHOT +/** + * trace_snapshot - take a snapshot of the current buffer. + * + * This causes a swap between the snapshot buffer and the current live + * tracing buffer. You can use this to take snapshots of the live + * trace when some condition is triggered, but continue to trace. + * + * Note, make sure to allocate the snapshot with either + * a tracing_snapshot_alloc(), or by doing it manually + * with: echo 1 > /sys/kernel/debug/tracing/snapshot + * + * If the snapshot buffer is not allocated, it will stop tracing. + * Basically making a permanent snapshot. + */ +void tracing_snapshot(void) +{ + struct trace_array *tr = &global_trace; + struct tracer *tracer = tr->current_trace; + unsigned long flags; + + if (in_nmi()) { + internal_trace_puts("*** SNAPSHOT CALLED FROM NMI CONTEXT ***\n"); + internal_trace_puts("*** snapshot is being ignored ***\n"); + return; + } + + if (!tr->allocated_snapshot) { + internal_trace_puts("*** SNAPSHOT NOT ALLOCATED ***\n"); + internal_trace_puts("*** stopping trace here! ***\n"); + tracing_off(); + return; + } + + /* Note, snapshot can not be used when the tracer uses it */ + if (tracer->use_max_tr) { + internal_trace_puts("*** LATENCY TRACER ACTIVE ***\n"); + internal_trace_puts("*** Can not use snapshot (sorry) ***\n"); + return; + } + + local_irq_save(flags); + update_max_tr(tr, current, smp_processor_id()); + local_irq_restore(flags); +} +EXPORT_SYMBOL_GPL(tracing_snapshot); + +static int resize_buffer_duplicate_size(struct trace_buffer *trace_buf, + struct trace_buffer *size_buf, int cpu_id); +static void set_buffer_entries(struct trace_buffer *buf, unsigned long val); + +static int alloc_snapshot(struct trace_array *tr) +{ + int ret; + + if (!tr->allocated_snapshot) { + + /* allocate spare buffer */ + ret = resize_buffer_duplicate_size(&tr->max_buffer, + &tr->trace_buffer, RING_BUFFER_ALL_CPUS); + if (ret < 0) + return ret; + + tr->allocated_snapshot = true; + } + + return 0; +} + +static void free_snapshot(struct trace_array *tr) +{ + /* + * We don't free the ring buffer. instead, resize it because + * The max_tr ring buffer has some state (e.g. ring->clock) and + * we want preserve it. + */ + ring_buffer_resize(tr->max_buffer.buffer, 1, RING_BUFFER_ALL_CPUS); + set_buffer_entries(&tr->max_buffer, 1); + tracing_reset_online_cpus(&tr->max_buffer); + tr->allocated_snapshot = false; +} + +/** + * tracing_alloc_snapshot - allocate snapshot buffer. + * + * This only allocates the snapshot buffer if it isn't already + * allocated - it doesn't also take a snapshot. + * + * This is meant to be used in cases where the snapshot buffer needs + * to be set up for events that can't sleep but need to be able to + * trigger a snapshot. + */ +int tracing_alloc_snapshot(void) +{ + struct trace_array *tr = &global_trace; + int ret; + + ret = alloc_snapshot(tr); + WARN_ON(ret < 0); + + return ret; +} +EXPORT_SYMBOL_GPL(tracing_alloc_snapshot); + +/** + * trace_snapshot_alloc - allocate and take a snapshot of the current buffer. + * + * This is similar to trace_snapshot(), but it will allocate the + * snapshot buffer if it isn't already allocated. Use this only + * where it is safe to sleep, as the allocation may sleep. + * + * This causes a swap between the snapshot buffer and the current live + * tracing buffer. You can use this to take snapshots of the live + * trace when some condition is triggered, but continue to trace. + */ +void tracing_snapshot_alloc(void) +{ + int ret; + + ret = tracing_alloc_snapshot(); + if (ret < 0) + return; + + tracing_snapshot(); +} +EXPORT_SYMBOL_GPL(tracing_snapshot_alloc); +#else +void tracing_snapshot(void) +{ + WARN_ONCE(1, "Snapshot feature not enabled, but internal snapshot used"); +} +EXPORT_SYMBOL_GPL(tracing_snapshot); +int tracing_alloc_snapshot(void) +{ + WARN_ONCE(1, "Snapshot feature not enabled, but snapshot allocation used"); + return -ENODEV; +} +EXPORT_SYMBOL_GPL(tracing_alloc_snapshot); +void tracing_snapshot_alloc(void) +{ + /* Give warning */ + tracing_snapshot(); +} +EXPORT_SYMBOL_GPL(tracing_snapshot_alloc); +#endif /* CONFIG_TRACER_SNAPSHOT */ + +static void tracer_tracing_off(struct trace_array *tr) +{ + if (tr->trace_buffer.buffer) + ring_buffer_record_off(tr->trace_buffer.buffer); + /* + * This flag is looked at when buffers haven't been allocated + * yet, or by some tracers (like irqsoff), that just want to + * know if the ring buffer has been disabled, but it can handle + * races of where it gets disabled but we still do a record. + * As the check is in the fast path of the tracers, it is more + * important to be fast than accurate. + */ + tr->buffer_disabled = 1; + /* Make the flag seen by readers */ + smp_wmb(); +} + +/** + * tracing_off - turn off tracing buffers + * + * This function stops the tracing buffers from recording data. + * It does not disable any overhead the tracers themselves may + * be causing. This function simply causes all recording to + * the ring buffers to fail. + */ +void tracing_off(void) +{ + tracer_tracing_off(&global_trace); +} +EXPORT_SYMBOL_GPL(tracing_off); + +void disable_trace_on_warning(void) +{ + if (__disable_trace_on_warning) + tracing_off(); +} + +/** + * tracer_tracing_is_on - show real state of ring buffer enabled + * @tr : the trace array to know if ring buffer is enabled + * + * Shows real state of the ring buffer if it is enabled or not. + */ +static int tracer_tracing_is_on(struct trace_array *tr) +{ + if (tr->trace_buffer.buffer) + return ring_buffer_record_is_on(tr->trace_buffer.buffer); + return !tr->buffer_disabled; +} + +/** + * tracing_is_on - show state of ring buffers enabled + */ +int tracing_is_on(void) +{ + return tracer_tracing_is_on(&global_trace); +} +EXPORT_SYMBOL_GPL(tracing_is_on); + +static int __init set_buf_size(char *str) +{ + unsigned long buf_size; + + if (!str) + return 0; + buf_size = memparse(str, &str); + /* nr_entries can not be zero */ + if (buf_size == 0) + return 0; + trace_buf_size = buf_size; + return 1; +} +__setup("trace_buf_size=", set_buf_size); + +static int __init set_tracing_thresh(char *str) +{ + unsigned long threshold; + int ret; + + if (!str) + return 0; + ret = kstrtoul(str, 0, &threshold); + if (ret < 0) + return 0; + tracing_thresh = threshold * 1000; + return 1; +} +__setup("tracing_thresh=", set_tracing_thresh); + +unsigned long nsecs_to_usecs(unsigned long nsecs) +{ + return nsecs / 1000; +} + +/* These must match the bit postions in trace_iterator_flags */ +static const char *trace_options[] = { + "print-parent", + "sym-offset", + "sym-addr", + "verbose", + "raw", + "hex", + "bin", + "block", + "stacktrace", + "trace_printk", + "ftrace_preempt", + "branch", + "annotate", + "userstacktrace", + "sym-userobj", + "printk-msg-only", + "context-info", + "latency-format", + "sleep-time", + "graph-time", + "record-cmd", + "overwrite", + "disable_on_free", + "irq-info", + "markers", + "function-trace", + NULL +}; + +static struct { + u64 (*func)(void); + const char *name; + int in_ns; /* is this clock in nanoseconds? */ +} trace_clocks[] = { + { trace_clock_local, "local", 1 }, + { trace_clock_global, "global", 1 }, + { trace_clock_counter, "counter", 0 }, + { trace_clock_jiffies, "uptime", 0 }, + { trace_clock, "perf", 1 }, + { ktime_get_mono_fast_ns, "mono", 1 }, + ARCH_TRACE_CLOCKS +}; + +/* + * trace_parser_get_init - gets the buffer for trace parser + */ +int trace_parser_get_init(struct trace_parser *parser, int size) +{ + memset(parser, 0, sizeof(*parser)); + + parser->buffer = kmalloc(size, GFP_KERNEL); + if (!parser->buffer) + return 1; + + parser->size = size; + return 0; +} + +/* + * trace_parser_put - frees the buffer for trace parser + */ +void trace_parser_put(struct trace_parser *parser) +{ + kfree(parser->buffer); +} + +/* + * trace_get_user - reads the user input string separated by space + * (matched by isspace(ch)) + * + * For each string found the 'struct trace_parser' is updated, + * and the function returns. + * + * Returns number of bytes read. + * + * See kernel/trace/trace.h for 'struct trace_parser' details. + */ +int trace_get_user(struct trace_parser *parser, const char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + char ch; + size_t read = 0; + ssize_t ret; + + if (!*ppos) + trace_parser_clear(parser); + + ret = get_user(ch, ubuf++); + if (ret) + goto out; + + read++; + cnt--; + + /* + * The parser is not finished with the last write, + * continue reading the user input without skipping spaces. + */ + if (!parser->cont) { + /* skip white space */ + while (cnt && isspace(ch)) { + ret = get_user(ch, ubuf++); + if (ret) + goto out; + read++; + cnt--; + } + + /* only spaces were written */ + if (isspace(ch)) { + *ppos += read; + ret = read; + goto out; + } + + parser->idx = 0; + } + + /* read the non-space input */ + while (cnt && !isspace(ch)) { + if (parser->idx < parser->size - 1) + parser->buffer[parser->idx++] = ch; + else { + ret = -EINVAL; + goto out; + } + ret = get_user(ch, ubuf++); + if (ret) + goto out; + read++; + cnt--; + } + + /* We either got finished input or we have to wait for another call. */ + if (isspace(ch)) { + parser->buffer[parser->idx] = 0; + parser->cont = false; + } else if (parser->idx < parser->size - 1) { + parser->cont = true; + parser->buffer[parser->idx++] = ch; + } else { + ret = -EINVAL; + goto out; + } + + *ppos += read; + ret = read; + +out: + return ret; +} + +/* TODO add a seq_buf_to_buffer() */ +static ssize_t trace_seq_to_buffer(struct trace_seq *s, void *buf, size_t cnt) +{ + int len; + + if (trace_seq_used(s) <= s->seq.readpos) + return -EBUSY; + + len = trace_seq_used(s) - s->seq.readpos; + if (cnt > len) + cnt = len; + memcpy(buf, s->buffer + s->seq.readpos, cnt); + + s->seq.readpos += cnt; + return cnt; +} + +unsigned long __read_mostly tracing_thresh; + +#ifdef CONFIG_TRACER_MAX_TRACE +/* + * Copy the new maximum trace into the separate maximum-trace + * structure. (this way the maximum trace is permanently saved, + * for later retrieval via /sys/kernel/debug/tracing/latency_trace) + */ +static void +__update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu) +{ + struct trace_buffer *trace_buf = &tr->trace_buffer; + struct trace_buffer *max_buf = &tr->max_buffer; + struct trace_array_cpu *data = per_cpu_ptr(trace_buf->data, cpu); + struct trace_array_cpu *max_data = per_cpu_ptr(max_buf->data, cpu); + + max_buf->cpu = cpu; + max_buf->time_start = data->preempt_timestamp; + + max_data->saved_latency = tr->max_latency; + max_data->critical_start = data->critical_start; + max_data->critical_end = data->critical_end; + + memcpy(max_data->comm, tsk->comm, TASK_COMM_LEN); + max_data->pid = tsk->pid; + /* + * If tsk == current, then use current_uid(), as that does not use + * RCU. The irq tracer can be called out of RCU scope. + */ + if (tsk == current) + max_data->uid = current_uid(); + else + max_data->uid = task_uid(tsk); + + max_data->nice = tsk->static_prio - 20 - MAX_RT_PRIO; + max_data->policy = tsk->policy; + max_data->rt_priority = tsk->rt_priority; + + /* record this tasks comm */ + tracing_record_cmdline(tsk); +} + +/** + * update_max_tr - snapshot all trace buffers from global_trace to max_tr + * @tr: tracer + * @tsk: the task with the latency + * @cpu: The cpu that initiated the trace. + * + * Flip the buffers between the @tr and the max_tr and record information + * about which task was the cause of this latency. + */ +void +update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu) +{ + struct ring_buffer *buf; + + if (tr->stop_count) + return; + + WARN_ON_ONCE(!irqs_disabled()); + + if (!tr->allocated_snapshot) { + /* Only the nop tracer should hit this when disabling */ + WARN_ON_ONCE(tr->current_trace != &nop_trace); + return; + } + + arch_spin_lock(&tr->max_lock); + + buf = tr->trace_buffer.buffer; + tr->trace_buffer.buffer = tr->max_buffer.buffer; + tr->max_buffer.buffer = buf; + + __update_max_tr(tr, tsk, cpu); + arch_spin_unlock(&tr->max_lock); +} + +/** + * update_max_tr_single - only copy one trace over, and reset the rest + * @tr - tracer + * @tsk - task with the latency + * @cpu - the cpu of the buffer to copy. + * + * Flip the trace of a single CPU buffer between the @tr and the max_tr. + */ +void +update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu) +{ + int ret; + + if (tr->stop_count) + return; + + WARN_ON_ONCE(!irqs_disabled()); + if (!tr->allocated_snapshot) { + /* Only the nop tracer should hit this when disabling */ + WARN_ON_ONCE(tr->current_trace != &nop_trace); + return; + } + + arch_spin_lock(&tr->max_lock); + + ret = ring_buffer_swap_cpu(tr->max_buffer.buffer, tr->trace_buffer.buffer, cpu); + + if (ret == -EBUSY) { + /* + * We failed to swap the buffer due to a commit taking + * place on this CPU. We fail to record, but we reset + * the max trace buffer (no one writes directly to it) + * and flag that it failed. + */ + trace_array_printk_buf(tr->max_buffer.buffer, _THIS_IP_, + "Failed to swap buffers due to commit in progress\n"); + } + + WARN_ON_ONCE(ret && ret != -EAGAIN && ret != -EBUSY); + + __update_max_tr(tr, tsk, cpu); + arch_spin_unlock(&tr->max_lock); +} +#endif /* CONFIG_TRACER_MAX_TRACE */ + +static int wait_on_pipe(struct trace_iterator *iter, bool full) +{ + /* Iterators are static, they should be filled or empty */ + if (trace_buffer_iter(iter, iter->cpu_file)) + return 0; + + return ring_buffer_wait(iter->trace_buffer->buffer, iter->cpu_file, + full); +} + +#ifdef CONFIG_FTRACE_STARTUP_TEST +static int run_tracer_selftest(struct tracer *type) +{ + struct trace_array *tr = &global_trace; + struct tracer *saved_tracer = tr->current_trace; + int ret; + + if (!type->selftest || tracing_selftest_disabled) + return 0; + + /* + * Run a selftest on this tracer. + * Here we reset the trace buffer, and set the current + * tracer to be this tracer. The tracer can then run some + * internal tracing to verify that everything is in order. + * If we fail, we do not register this tracer. + */ + tracing_reset_online_cpus(&tr->trace_buffer); + + tr->current_trace = type; + +#ifdef CONFIG_TRACER_MAX_TRACE + if (type->use_max_tr) { + /* If we expanded the buffers, make sure the max is expanded too */ + if (ring_buffer_expanded) + ring_buffer_resize(tr->max_buffer.buffer, trace_buf_size, + RING_BUFFER_ALL_CPUS); + tr->allocated_snapshot = true; + } +#endif + + /* the test is responsible for initializing and enabling */ + pr_info("Testing tracer %s: ", type->name); + ret = type->selftest(type, tr); + /* the test is responsible for resetting too */ + tr->current_trace = saved_tracer; + if (ret) { + printk(KERN_CONT "FAILED!\n"); + /* Add the warning after printing 'FAILED' */ + WARN_ON(1); + return -1; + } + /* Only reset on passing, to avoid touching corrupted buffers */ + tracing_reset_online_cpus(&tr->trace_buffer); + +#ifdef CONFIG_TRACER_MAX_TRACE + if (type->use_max_tr) { + tr->allocated_snapshot = false; + + /* Shrink the max buffer again */ + if (ring_buffer_expanded) + ring_buffer_resize(tr->max_buffer.buffer, 1, + RING_BUFFER_ALL_CPUS); + } +#endif + + printk(KERN_CONT "PASSED\n"); + return 0; +} +#else +static inline int run_tracer_selftest(struct tracer *type) +{ + return 0; +} +#endif /* CONFIG_FTRACE_STARTUP_TEST */ + +/** + * register_tracer - register a tracer with the ftrace system. + * @type - the plugin for the tracer + * + * Register a new plugin tracer. + */ +int register_tracer(struct tracer *type) +{ + struct tracer *t; + int ret = 0; + + if (!type->name) { + pr_info("Tracer must have a name\n"); + return -1; + } + + if (strlen(type->name) >= MAX_TRACER_SIZE) { + pr_info("Tracer has a name longer than %d\n", MAX_TRACER_SIZE); + return -1; + } + + mutex_lock(&trace_types_lock); + + tracing_selftest_running = true; + + for (t = trace_types; t; t = t->next) { + if (strcmp(type->name, t->name) == 0) { + /* already found */ + pr_info("Tracer %s already registered\n", + type->name); + ret = -1; + goto out; + } + } + + if (!type->set_flag) + type->set_flag = &dummy_set_flag; + if (!type->flags) + type->flags = &dummy_tracer_flags; + else + if (!type->flags->opts) + type->flags->opts = dummy_tracer_opt; + + ret = run_tracer_selftest(type); + if (ret < 0) + goto out; + + type->next = trace_types; + trace_types = type; + + out: + tracing_selftest_running = false; + mutex_unlock(&trace_types_lock); + + if (ret || !default_bootup_tracer) + goto out_unlock; + + if (strncmp(default_bootup_tracer, type->name, MAX_TRACER_SIZE)) + goto out_unlock; + + printk(KERN_INFO "Starting tracer '%s'\n", type->name); + /* Do we want this tracer to start on bootup? */ + tracing_set_tracer(&global_trace, type->name); + default_bootup_tracer = NULL; + /* disable other selftests, since this will break it. */ + tracing_selftest_disabled = true; +#ifdef CONFIG_FTRACE_STARTUP_TEST + printk(KERN_INFO "Disabling FTRACE selftests due to running tracer '%s'\n", + type->name); +#endif + + out_unlock: + return ret; +} + +void tracing_reset(struct trace_buffer *buf, int cpu) +{ + struct ring_buffer *buffer = buf->buffer; + + if (!buffer) + return; + + ring_buffer_record_disable(buffer); + + /* Make sure all commits have finished */ + synchronize_sched(); + ring_buffer_reset_cpu(buffer, cpu); + + ring_buffer_record_enable(buffer); +} + +void tracing_reset_online_cpus(struct trace_buffer *buf) +{ + struct ring_buffer *buffer = buf->buffer; + int cpu; + + if (!buffer) + return; + + ring_buffer_record_disable(buffer); + + /* Make sure all commits have finished */ + synchronize_sched(); + + buf->time_start = buffer_ftrace_now(buf, buf->cpu); + + for_each_online_cpu(cpu) + ring_buffer_reset_cpu(buffer, cpu); + + ring_buffer_record_enable(buffer); +} + +/* Must have trace_types_lock held */ +void tracing_reset_all_online_cpus(void) +{ + struct trace_array *tr; + + list_for_each_entry(tr, &ftrace_trace_arrays, list) { + tracing_reset_online_cpus(&tr->trace_buffer); +#ifdef CONFIG_TRACER_MAX_TRACE + tracing_reset_online_cpus(&tr->max_buffer); +#endif + } +} + +#define SAVED_CMDLINES_DEFAULT 128 +#define NO_CMDLINE_MAP UINT_MAX +static arch_spinlock_t trace_cmdline_lock = __ARCH_SPIN_LOCK_UNLOCKED; +struct saved_cmdlines_buffer { + unsigned map_pid_to_cmdline[PID_MAX_DEFAULT+1]; + unsigned *map_cmdline_to_pid; + unsigned cmdline_num; + int cmdline_idx; + char *saved_cmdlines; +}; +static struct saved_cmdlines_buffer *savedcmd; + +/* temporary disable recording */ +static atomic_t trace_record_cmdline_disabled __read_mostly; + +static inline char *get_saved_cmdlines(int idx) +{ + return &savedcmd->saved_cmdlines[idx * TASK_COMM_LEN]; +} + +static inline void set_cmdline(int idx, const char *cmdline) +{ + memcpy(get_saved_cmdlines(idx), cmdline, TASK_COMM_LEN); +} + +static int allocate_cmdlines_buffer(unsigned int val, + struct saved_cmdlines_buffer *s) +{ + s->map_cmdline_to_pid = kmalloc(val * sizeof(*s->map_cmdline_to_pid), + GFP_KERNEL); + if (!s->map_cmdline_to_pid) + return -ENOMEM; + + s->saved_cmdlines = kmalloc(val * TASK_COMM_LEN, GFP_KERNEL); + if (!s->saved_cmdlines) { + kfree(s->map_cmdline_to_pid); + return -ENOMEM; + } + + s->cmdline_idx = 0; + s->cmdline_num = val; + memset(&s->map_pid_to_cmdline, NO_CMDLINE_MAP, + sizeof(s->map_pid_to_cmdline)); + memset(s->map_cmdline_to_pid, NO_CMDLINE_MAP, + val * sizeof(*s->map_cmdline_to_pid)); + + return 0; +} + +static int trace_create_savedcmd(void) +{ + int ret; + + savedcmd = kmalloc(sizeof(*savedcmd), GFP_KERNEL); + if (!savedcmd) + return -ENOMEM; + + ret = allocate_cmdlines_buffer(SAVED_CMDLINES_DEFAULT, savedcmd); + if (ret < 0) { + kfree(savedcmd); + savedcmd = NULL; + return -ENOMEM; + } + + return 0; +} + +int is_tracing_stopped(void) +{ + return global_trace.stop_count; +} + +/** + * tracing_start - quick start of the tracer + * + * If tracing is enabled but was stopped by tracing_stop, + * this will start the tracer back up. + */ +void tracing_start(void) +{ + struct ring_buffer *buffer; + unsigned long flags; + + if (tracing_disabled) + return; + + raw_spin_lock_irqsave(&global_trace.start_lock, flags); + if (--global_trace.stop_count) { + if (global_trace.stop_count < 0) { + /* Someone screwed up their debugging */ + WARN_ON_ONCE(1); + global_trace.stop_count = 0; + } + goto out; + } + + /* Prevent the buffers from switching */ + arch_spin_lock(&global_trace.max_lock); + + buffer = global_trace.trace_buffer.buffer; + if (buffer) + ring_buffer_record_enable(buffer); + +#ifdef CONFIG_TRACER_MAX_TRACE + buffer = global_trace.max_buffer.buffer; + if (buffer) + ring_buffer_record_enable(buffer); +#endif + + arch_spin_unlock(&global_trace.max_lock); + + out: + raw_spin_unlock_irqrestore(&global_trace.start_lock, flags); +} + +static void tracing_start_tr(struct trace_array *tr) +{ + struct ring_buffer *buffer; + unsigned long flags; + + if (tracing_disabled) + return; + + /* If global, we need to also start the max tracer */ + if (tr->flags & TRACE_ARRAY_FL_GLOBAL) + return tracing_start(); + + raw_spin_lock_irqsave(&tr->start_lock, flags); + + if (--tr->stop_count) { + if (tr->stop_count < 0) { + /* Someone screwed up their debugging */ + WARN_ON_ONCE(1); + tr->stop_count = 0; + } + goto out; + } + + buffer = tr->trace_buffer.buffer; + if (buffer) + ring_buffer_record_enable(buffer); + + out: + raw_spin_unlock_irqrestore(&tr->start_lock, flags); +} + +/** + * tracing_stop - quick stop of the tracer + * + * Light weight way to stop tracing. Use in conjunction with + * tracing_start. + */ +void tracing_stop(void) +{ + struct ring_buffer *buffer; + unsigned long flags; + + raw_spin_lock_irqsave(&global_trace.start_lock, flags); + if (global_trace.stop_count++) + goto out; + + /* Prevent the buffers from switching */ + arch_spin_lock(&global_trace.max_lock); + + buffer = global_trace.trace_buffer.buffer; + if (buffer) + ring_buffer_record_disable(buffer); + +#ifdef CONFIG_TRACER_MAX_TRACE + buffer = global_trace.max_buffer.buffer; + if (buffer) + ring_buffer_record_disable(buffer); +#endif + + arch_spin_unlock(&global_trace.max_lock); + + out: + raw_spin_unlock_irqrestore(&global_trace.start_lock, flags); +} + +static void tracing_stop_tr(struct trace_array *tr) +{ + struct ring_buffer *buffer; + unsigned long flags; + + /* If global, we need to also stop the max tracer */ + if (tr->flags & TRACE_ARRAY_FL_GLOBAL) + return tracing_stop(); + + raw_spin_lock_irqsave(&tr->start_lock, flags); + if (tr->stop_count++) + goto out; + + buffer = tr->trace_buffer.buffer; + if (buffer) + ring_buffer_record_disable(buffer); + + out: + raw_spin_unlock_irqrestore(&tr->start_lock, flags); +} + +void trace_stop_cmdline_recording(void); + +static int trace_save_cmdline(struct task_struct *tsk) +{ + unsigned pid, idx; + + if (!tsk->pid || unlikely(tsk->pid > PID_MAX_DEFAULT)) + return 0; + + /* + * It's not the end of the world if we don't get + * the lock, but we also don't want to spin + * nor do we want to disable interrupts, + * so if we miss here, then better luck next time. + */ + if (!arch_spin_trylock(&trace_cmdline_lock)) + return 0; + + idx = savedcmd->map_pid_to_cmdline[tsk->pid]; + if (idx == NO_CMDLINE_MAP) { + idx = (savedcmd->cmdline_idx + 1) % savedcmd->cmdline_num; + + /* + * Check whether the cmdline buffer at idx has a pid + * mapped. We are going to overwrite that entry so we + * need to clear the map_pid_to_cmdline. Otherwise we + * would read the new comm for the old pid. + */ + pid = savedcmd->map_cmdline_to_pid[idx]; + if (pid != NO_CMDLINE_MAP) + savedcmd->map_pid_to_cmdline[pid] = NO_CMDLINE_MAP; + + savedcmd->map_cmdline_to_pid[idx] = tsk->pid; + savedcmd->map_pid_to_cmdline[tsk->pid] = idx; + + savedcmd->cmdline_idx = idx; + } + + set_cmdline(idx, tsk->comm); + + arch_spin_unlock(&trace_cmdline_lock); + + return 1; +} + +static void __trace_find_cmdline(int pid, char comm[]) +{ + unsigned map; + + if (!pid) { + strcpy(comm, ""); + return; + } + + if (WARN_ON_ONCE(pid < 0)) { + strcpy(comm, ""); + return; + } + + if (pid > PID_MAX_DEFAULT) { + strcpy(comm, "<...>"); + return; + } + + map = savedcmd->map_pid_to_cmdline[pid]; + if (map != NO_CMDLINE_MAP) + strcpy(comm, get_saved_cmdlines(map)); + else + strcpy(comm, "<...>"); +} + +void trace_find_cmdline(int pid, char comm[]) +{ + preempt_disable(); + arch_spin_lock(&trace_cmdline_lock); + + __trace_find_cmdline(pid, comm); + + arch_spin_unlock(&trace_cmdline_lock); + preempt_enable(); +} + +void tracing_record_cmdline(struct task_struct *tsk) +{ + if (atomic_read(&trace_record_cmdline_disabled) || !tracing_is_on()) + return; + + if (!__this_cpu_read(trace_cmdline_save)) + return; + + if (trace_save_cmdline(tsk)) + __this_cpu_write(trace_cmdline_save, false); +} + +void +tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags, + int pc) +{ + struct task_struct *tsk = current; + + entry->preempt_count = pc & 0xff; + entry->preempt_lazy_count = preempt_lazy_count(); + entry->pid = (tsk) ? tsk->pid : 0; + entry->flags = +#ifdef CONFIG_TRACE_IRQFLAGS_SUPPORT + (irqs_disabled_flags(flags) ? TRACE_FLAG_IRQS_OFF : 0) | +#else + TRACE_FLAG_IRQS_NOSUPPORT | +#endif + ((pc & HARDIRQ_MASK) ? TRACE_FLAG_HARDIRQ : 0) | + ((pc & SOFTIRQ_MASK) ? TRACE_FLAG_SOFTIRQ : 0) | + (tif_need_resched_now() ? TRACE_FLAG_NEED_RESCHED : 0) | + (need_resched_lazy() ? TRACE_FLAG_NEED_RESCHED_LAZY : 0) | + (test_preempt_need_resched() ? TRACE_FLAG_PREEMPT_RESCHED : 0); + + entry->migrate_disable = (tsk) ? __migrate_disabled(tsk) & 0xFF : 0; +} +EXPORT_SYMBOL_GPL(tracing_generic_entry_update); + +struct ring_buffer_event * +trace_buffer_lock_reserve(struct ring_buffer *buffer, + int type, + unsigned long len, + unsigned long flags, int pc) +{ + struct ring_buffer_event *event; + + event = ring_buffer_lock_reserve(buffer, len); + if (event != NULL) { + struct trace_entry *ent = ring_buffer_event_data(event); + + tracing_generic_entry_update(ent, flags, pc); + ent->type = type; + } + + return event; +} + +void +__buffer_unlock_commit(struct ring_buffer *buffer, struct ring_buffer_event *event) +{ + __this_cpu_write(trace_cmdline_save, true); + ring_buffer_unlock_commit(buffer, event); +} + +static inline void +__trace_buffer_unlock_commit(struct ring_buffer *buffer, + struct ring_buffer_event *event, + unsigned long flags, int pc) +{ + __buffer_unlock_commit(buffer, event); + + ftrace_trace_stack(buffer, flags, 6, pc); + ftrace_trace_userstack(buffer, flags, pc); +} + +void trace_buffer_unlock_commit(struct ring_buffer *buffer, + struct ring_buffer_event *event, + unsigned long flags, int pc) +{ + __trace_buffer_unlock_commit(buffer, event, flags, pc); +} +EXPORT_SYMBOL_GPL(trace_buffer_unlock_commit); + +static struct ring_buffer *temp_buffer; + +struct ring_buffer_event * +trace_event_buffer_lock_reserve(struct ring_buffer **current_rb, + struct ftrace_event_file *ftrace_file, + int type, unsigned long len, + unsigned long flags, int pc) +{ + struct ring_buffer_event *entry; + + *current_rb = ftrace_file->tr->trace_buffer.buffer; + entry = trace_buffer_lock_reserve(*current_rb, + type, len, flags, pc); + /* + * If tracing is off, but we have triggers enabled + * we still need to look at the event data. Use the temp_buffer + * to store the trace event for the tigger to use. It's recusive + * safe and will not be recorded anywhere. + */ + if (!entry && ftrace_file->flags & FTRACE_EVENT_FL_TRIGGER_COND) { + *current_rb = temp_buffer; + entry = trace_buffer_lock_reserve(*current_rb, + type, len, flags, pc); + } + return entry; +} +EXPORT_SYMBOL_GPL(trace_event_buffer_lock_reserve); + +struct ring_buffer_event * +trace_current_buffer_lock_reserve(struct ring_buffer **current_rb, + int type, unsigned long len, + unsigned long flags, int pc) +{ + *current_rb = global_trace.trace_buffer.buffer; + return trace_buffer_lock_reserve(*current_rb, + type, len, flags, pc); +} +EXPORT_SYMBOL_GPL(trace_current_buffer_lock_reserve); + +void trace_current_buffer_unlock_commit(struct ring_buffer *buffer, + struct ring_buffer_event *event, + unsigned long flags, int pc) +{ + __trace_buffer_unlock_commit(buffer, event, flags, pc); +} +EXPORT_SYMBOL_GPL(trace_current_buffer_unlock_commit); + +void trace_buffer_unlock_commit_regs(struct ring_buffer *buffer, + struct ring_buffer_event *event, + unsigned long flags, int pc, + struct pt_regs *regs) +{ + __buffer_unlock_commit(buffer, event); + + ftrace_trace_stack_regs(buffer, flags, 0, pc, regs); + ftrace_trace_userstack(buffer, flags, pc); +} +EXPORT_SYMBOL_GPL(trace_buffer_unlock_commit_regs); + +void trace_current_buffer_discard_commit(struct ring_buffer *buffer, + struct ring_buffer_event *event) +{ + ring_buffer_discard_commit(buffer, event); +} +EXPORT_SYMBOL_GPL(trace_current_buffer_discard_commit); + +void +trace_function(struct trace_array *tr, + unsigned long ip, unsigned long parent_ip, unsigned long flags, + int pc) +{ + struct ftrace_event_call *call = &event_function; + struct ring_buffer *buffer = tr->trace_buffer.buffer; + struct ring_buffer_event *event; + struct ftrace_entry *entry; + + /* If we are reading the ring buffer, don't trace */ + if (unlikely(__this_cpu_read(ftrace_cpu_disabled))) + return; + + event = trace_buffer_lock_reserve(buffer, TRACE_FN, sizeof(*entry), + flags, pc); + if (!event) + return; + entry = ring_buffer_event_data(event); + entry->ip = ip; + entry->parent_ip = parent_ip; + + if (!call_filter_check_discard(call, entry, buffer, event)) + __buffer_unlock_commit(buffer, event); +} + +#ifdef CONFIG_STACKTRACE + +#define FTRACE_STACK_MAX_ENTRIES (PAGE_SIZE / sizeof(unsigned long)) +struct ftrace_stack { + unsigned long calls[FTRACE_STACK_MAX_ENTRIES]; +}; + +static DEFINE_PER_CPU(struct ftrace_stack, ftrace_stack); +static DEFINE_PER_CPU(int, ftrace_stack_reserve); + +static void __ftrace_trace_stack(struct ring_buffer *buffer, + unsigned long flags, + int skip, int pc, struct pt_regs *regs) +{ + struct ftrace_event_call *call = &event_kernel_stack; + struct ring_buffer_event *event; + struct stack_entry *entry; + struct stack_trace trace; + int use_stack; + int size = FTRACE_STACK_ENTRIES; + + trace.nr_entries = 0; + trace.skip = skip; + + /* + * Since events can happen in NMIs there's no safe way to + * use the per cpu ftrace_stacks. We reserve it and if an interrupt + * or NMI comes in, it will just have to use the default + * FTRACE_STACK_SIZE. + */ + preempt_disable_notrace(); + + use_stack = __this_cpu_inc_return(ftrace_stack_reserve); + /* + * We don't need any atomic variables, just a barrier. + * If an interrupt comes in, we don't care, because it would + * have exited and put the counter back to what we want. + * We just need a barrier to keep gcc from moving things + * around. + */ + barrier(); + if (use_stack == 1) { + trace.entries = this_cpu_ptr(ftrace_stack.calls); + trace.max_entries = FTRACE_STACK_MAX_ENTRIES; + + if (regs) + save_stack_trace_regs(regs, &trace); + else + save_stack_trace(&trace); + + if (trace.nr_entries > size) + size = trace.nr_entries; + } else + /* From now on, use_stack is a boolean */ + use_stack = 0; + + size *= sizeof(unsigned long); + + event = trace_buffer_lock_reserve(buffer, TRACE_STACK, + sizeof(*entry) + size, flags, pc); + if (!event) + goto out; + entry = ring_buffer_event_data(event); + + memset(&entry->caller, 0, size); + + if (use_stack) + memcpy(&entry->caller, trace.entries, + trace.nr_entries * sizeof(unsigned long)); + else { + trace.max_entries = FTRACE_STACK_ENTRIES; + trace.entries = entry->caller; + if (regs) + save_stack_trace_regs(regs, &trace); + else + save_stack_trace(&trace); + } + + entry->size = trace.nr_entries; + + if (!call_filter_check_discard(call, entry, buffer, event)) + __buffer_unlock_commit(buffer, event); + + out: + /* Again, don't let gcc optimize things here */ + barrier(); + __this_cpu_dec(ftrace_stack_reserve); + preempt_enable_notrace(); + +} + +void ftrace_trace_stack_regs(struct ring_buffer *buffer, unsigned long flags, + int skip, int pc, struct pt_regs *regs) +{ + if (!(trace_flags & TRACE_ITER_STACKTRACE)) + return; + + __ftrace_trace_stack(buffer, flags, skip, pc, regs); +} + +void ftrace_trace_stack(struct ring_buffer *buffer, unsigned long flags, + int skip, int pc) +{ + if (!(trace_flags & TRACE_ITER_STACKTRACE)) + return; + + __ftrace_trace_stack(buffer, flags, skip, pc, NULL); +} + +void __trace_stack(struct trace_array *tr, unsigned long flags, int skip, + int pc) +{ + __ftrace_trace_stack(tr->trace_buffer.buffer, flags, skip, pc, NULL); +} + +/** + * trace_dump_stack - record a stack back trace in the trace buffer + * @skip: Number of functions to skip (helper handlers) + */ +void trace_dump_stack(int skip) +{ + unsigned long flags; + + if (tracing_disabled || tracing_selftest_running) + return; + + local_save_flags(flags); + + /* + * Skip 3 more, seems to get us at the caller of + * this function. + */ + skip += 3; + __ftrace_trace_stack(global_trace.trace_buffer.buffer, + flags, skip, preempt_count(), NULL); +} + +static DEFINE_PER_CPU(int, user_stack_count); + +void +ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags, int pc) +{ + struct ftrace_event_call *call = &event_user_stack; + struct ring_buffer_event *event; + struct userstack_entry *entry; + struct stack_trace trace; + + if (!(trace_flags & TRACE_ITER_USERSTACKTRACE)) + return; + + /* + * NMIs can not handle page faults, even with fix ups. + * The save user stack can (and often does) fault. + */ + if (unlikely(in_nmi())) + return; + + /* + * prevent recursion, since the user stack tracing may + * trigger other kernel events. + */ + preempt_disable(); + if (__this_cpu_read(user_stack_count)) + goto out; + + __this_cpu_inc(user_stack_count); + + event = trace_buffer_lock_reserve(buffer, TRACE_USER_STACK, + sizeof(*entry), flags, pc); + if (!event) + goto out_drop_count; + entry = ring_buffer_event_data(event); + + entry->tgid = current->tgid; + memset(&entry->caller, 0, sizeof(entry->caller)); + + trace.nr_entries = 0; + trace.max_entries = FTRACE_STACK_ENTRIES; + trace.skip = 0; + trace.entries = entry->caller; + + save_stack_trace_user(&trace); + if (!call_filter_check_discard(call, entry, buffer, event)) + __buffer_unlock_commit(buffer, event); + + out_drop_count: + __this_cpu_dec(user_stack_count); + out: + preempt_enable(); +} + +#ifdef UNUSED +static void __trace_userstack(struct trace_array *tr, unsigned long flags) +{ + ftrace_trace_userstack(tr, flags, preempt_count()); +} +#endif /* UNUSED */ + +#endif /* CONFIG_STACKTRACE */ + +/* created for use with alloc_percpu */ +struct trace_buffer_struct { + char buffer[TRACE_BUF_SIZE]; +}; + +static struct trace_buffer_struct *trace_percpu_buffer; +static struct trace_buffer_struct *trace_percpu_sirq_buffer; +static struct trace_buffer_struct *trace_percpu_irq_buffer; +static struct trace_buffer_struct *trace_percpu_nmi_buffer; + +/* + * The buffer used is dependent on the context. There is a per cpu + * buffer for normal context, softirq contex, hard irq context and + * for NMI context. Thise allows for lockless recording. + * + * Note, if the buffers failed to be allocated, then this returns NULL + */ +static char *get_trace_buf(void) +{ + struct trace_buffer_struct *percpu_buffer; + + /* + * If we have allocated per cpu buffers, then we do not + * need to do any locking. + */ + if (in_nmi()) + percpu_buffer = trace_percpu_nmi_buffer; + else if (in_irq()) + percpu_buffer = trace_percpu_irq_buffer; + else if (in_softirq()) + percpu_buffer = trace_percpu_sirq_buffer; + else + percpu_buffer = trace_percpu_buffer; + + if (!percpu_buffer) + return NULL; + + return this_cpu_ptr(&percpu_buffer->buffer[0]); +} + +static int alloc_percpu_trace_buffer(void) +{ + struct trace_buffer_struct *buffers; + struct trace_buffer_struct *sirq_buffers; + struct trace_buffer_struct *irq_buffers; + struct trace_buffer_struct *nmi_buffers; + + buffers = alloc_percpu(struct trace_buffer_struct); + if (!buffers) + goto err_warn; + + sirq_buffers = alloc_percpu(struct trace_buffer_struct); + if (!sirq_buffers) + goto err_sirq; + + irq_buffers = alloc_percpu(struct trace_buffer_struct); + if (!irq_buffers) + goto err_irq; + + nmi_buffers = alloc_percpu(struct trace_buffer_struct); + if (!nmi_buffers) + goto err_nmi; + + trace_percpu_buffer = buffers; + trace_percpu_sirq_buffer = sirq_buffers; + trace_percpu_irq_buffer = irq_buffers; + trace_percpu_nmi_buffer = nmi_buffers; + + return 0; + + err_nmi: + free_percpu(irq_buffers); + err_irq: + free_percpu(sirq_buffers); + err_sirq: + free_percpu(buffers); + err_warn: + WARN(1, "Could not allocate percpu trace_printk buffer"); + return -ENOMEM; +} + +static int buffers_allocated; + +void trace_printk_init_buffers(void) +{ + if (buffers_allocated) + return; + + if (alloc_percpu_trace_buffer()) + return; + + /* trace_printk() is for debug use only. Don't use it in production. */ + + pr_warning("\n"); + pr_warning("**********************************************************\n"); + pr_warning("** NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE **\n"); + pr_warning("** **\n"); + pr_warning("** trace_printk() being used. Allocating extra memory. **\n"); + pr_warning("** **\n"); + pr_warning("** This means that this is a DEBUG kernel and it is **\n"); + pr_warning("** unsafe for production use. **\n"); + pr_warning("** **\n"); + pr_warning("** If you see this message and you are not debugging **\n"); + pr_warning("** the kernel, report this immediately to your vendor! **\n"); + pr_warning("** **\n"); + pr_warning("** NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE **\n"); + pr_warning("**********************************************************\n"); + + /* Expand the buffers to set size */ + tracing_update_buffers(); + + buffers_allocated = 1; + + /* + * trace_printk_init_buffers() can be called by modules. + * If that happens, then we need to start cmdline recording + * directly here. If the global_trace.buffer is already + * allocated here, then this was called by module code. + */ + if (global_trace.trace_buffer.buffer) + tracing_start_cmdline_record(); +} + +void trace_printk_start_comm(void) +{ + /* Start tracing comms if trace printk is set */ + if (!buffers_allocated) + return; + tracing_start_cmdline_record(); +} + +static void trace_printk_start_stop_comm(int enabled) +{ + if (!buffers_allocated) + return; + + if (enabled) + tracing_start_cmdline_record(); + else + tracing_stop_cmdline_record(); +} + +/** + * trace_vbprintk - write binary msg to tracing buffer + * + */ +int trace_vbprintk(unsigned long ip, const char *fmt, va_list args) +{ + struct ftrace_event_call *call = &event_bprint; + struct ring_buffer_event *event; + struct ring_buffer *buffer; + struct trace_array *tr = &global_trace; + struct bprint_entry *entry; + unsigned long flags; + char *tbuffer; + int len = 0, size, pc; + + if (unlikely(tracing_selftest_running || tracing_disabled)) + return 0; + + /* Don't pollute graph traces with trace_vprintk internals */ + pause_graph_tracing(); + + pc = preempt_count(); + preempt_disable_notrace(); + + tbuffer = get_trace_buf(); + if (!tbuffer) { + len = 0; + goto out; + } + + len = vbin_printf((u32 *)tbuffer, TRACE_BUF_SIZE/sizeof(int), fmt, args); + + if (len > TRACE_BUF_SIZE/sizeof(int) || len < 0) + goto out; + + local_save_flags(flags); + size = sizeof(*entry) + sizeof(u32) * len; + buffer = tr->trace_buffer.buffer; + event = trace_buffer_lock_reserve(buffer, TRACE_BPRINT, size, + flags, pc); + if (!event) + goto out; + entry = ring_buffer_event_data(event); + entry->ip = ip; + entry->fmt = fmt; + + memcpy(entry->buf, tbuffer, sizeof(u32) * len); + if (!call_filter_check_discard(call, entry, buffer, event)) { + __buffer_unlock_commit(buffer, event); + ftrace_trace_stack(buffer, flags, 6, pc); + } + +out: + preempt_enable_notrace(); + unpause_graph_tracing(); + + return len; +} +EXPORT_SYMBOL_GPL(trace_vbprintk); + +static int +__trace_array_vprintk(struct ring_buffer *buffer, + unsigned long ip, const char *fmt, va_list args) +{ + struct ftrace_event_call *call = &event_print; + struct ring_buffer_event *event; + int len = 0, size, pc; + struct print_entry *entry; + unsigned long flags; + char *tbuffer; + + if (tracing_disabled || tracing_selftest_running) + return 0; + + /* Don't pollute graph traces with trace_vprintk internals */ + pause_graph_tracing(); + + pc = preempt_count(); + preempt_disable_notrace(); + + + tbuffer = get_trace_buf(); + if (!tbuffer) { + len = 0; + goto out; + } + + len = vscnprintf(tbuffer, TRACE_BUF_SIZE, fmt, args); + + local_save_flags(flags); + size = sizeof(*entry) + len + 1; + event = trace_buffer_lock_reserve(buffer, TRACE_PRINT, size, + flags, pc); + if (!event) + goto out; + entry = ring_buffer_event_data(event); + entry->ip = ip; + + memcpy(&entry->buf, tbuffer, len + 1); + if (!call_filter_check_discard(call, entry, buffer, event)) { + __buffer_unlock_commit(buffer, event); + ftrace_trace_stack(buffer, flags, 6, pc); + } + out: + preempt_enable_notrace(); + unpause_graph_tracing(); + + return len; +} + +int trace_array_vprintk(struct trace_array *tr, + unsigned long ip, const char *fmt, va_list args) +{ + return __trace_array_vprintk(tr->trace_buffer.buffer, ip, fmt, args); +} + +int trace_array_printk(struct trace_array *tr, + unsigned long ip, const char *fmt, ...) +{ + int ret; + va_list ap; + + if (!(trace_flags & TRACE_ITER_PRINTK)) + return 0; + + va_start(ap, fmt); + ret = trace_array_vprintk(tr, ip, fmt, ap); + va_end(ap); + return ret; +} + +int trace_array_printk_buf(struct ring_buffer *buffer, + unsigned long ip, const char *fmt, ...) +{ + int ret; + va_list ap; + + if (!(trace_flags & TRACE_ITER_PRINTK)) + return 0; + + va_start(ap, fmt); + ret = __trace_array_vprintk(buffer, ip, fmt, ap); + va_end(ap); + return ret; +} + +int trace_vprintk(unsigned long ip, const char *fmt, va_list args) +{ + return trace_array_vprintk(&global_trace, ip, fmt, args); +} +EXPORT_SYMBOL_GPL(trace_vprintk); + +static void trace_iterator_increment(struct trace_iterator *iter) +{ + struct ring_buffer_iter *buf_iter = trace_buffer_iter(iter, iter->cpu); + + iter->idx++; + if (buf_iter) + ring_buffer_read(buf_iter, NULL); +} + +static struct trace_entry * +peek_next_entry(struct trace_iterator *iter, int cpu, u64 *ts, + unsigned long *lost_events) +{ + struct ring_buffer_event *event; + struct ring_buffer_iter *buf_iter = trace_buffer_iter(iter, cpu); + + if (buf_iter) + event = ring_buffer_iter_peek(buf_iter, ts); + else + event = ring_buffer_peek(iter->trace_buffer->buffer, cpu, ts, + lost_events); + + if (event) { + iter->ent_size = ring_buffer_event_length(event); + return ring_buffer_event_data(event); + } + iter->ent_size = 0; + return NULL; +} + +static struct trace_entry * +__find_next_entry(struct trace_iterator *iter, int *ent_cpu, + unsigned long *missing_events, u64 *ent_ts) +{ + struct ring_buffer *buffer = iter->trace_buffer->buffer; + struct trace_entry *ent, *next = NULL; + unsigned long lost_events = 0, next_lost = 0; + int cpu_file = iter->cpu_file; + u64 next_ts = 0, ts; + int next_cpu = -1; + int next_size = 0; + int cpu; + + /* + * If we are in a per_cpu trace file, don't bother by iterating over + * all cpu and peek directly. + */ + if (cpu_file > RING_BUFFER_ALL_CPUS) { + if (ring_buffer_empty_cpu(buffer, cpu_file)) + return NULL; + ent = peek_next_entry(iter, cpu_file, ent_ts, missing_events); + if (ent_cpu) + *ent_cpu = cpu_file; + + return ent; + } + + for_each_tracing_cpu(cpu) { + + if (ring_buffer_empty_cpu(buffer, cpu)) + continue; + + ent = peek_next_entry(iter, cpu, &ts, &lost_events); + + /* + * Pick the entry with the smallest timestamp: + */ + if (ent && (!next || ts < next_ts)) { + next = ent; + next_cpu = cpu; + next_ts = ts; + next_lost = lost_events; + next_size = iter->ent_size; + } + } + + iter->ent_size = next_size; + + if (ent_cpu) + *ent_cpu = next_cpu; + + if (ent_ts) + *ent_ts = next_ts; + + if (missing_events) + *missing_events = next_lost; + + return next; +} + +/* Find the next real entry, without updating the iterator itself */ +struct trace_entry *trace_find_next_entry(struct trace_iterator *iter, + int *ent_cpu, u64 *ent_ts) +{ + return __find_next_entry(iter, ent_cpu, NULL, ent_ts); +} + +/* Find the next real entry, and increment the iterator to the next entry */ +void *trace_find_next_entry_inc(struct trace_iterator *iter) +{ + iter->ent = __find_next_entry(iter, &iter->cpu, + &iter->lost_events, &iter->ts); + + if (iter->ent) + trace_iterator_increment(iter); + + return iter->ent ? iter : NULL; +} + +static void trace_consume(struct trace_iterator *iter) +{ + ring_buffer_consume(iter->trace_buffer->buffer, iter->cpu, &iter->ts, + &iter->lost_events); +} + +static void *s_next(struct seq_file *m, void *v, loff_t *pos) +{ + struct trace_iterator *iter = m->private; + int i = (int)*pos; + void *ent; + + WARN_ON_ONCE(iter->leftover); + + (*pos)++; + + /* can't go backwards */ + if (iter->idx > i) + return NULL; + + if (iter->idx < 0) + ent = trace_find_next_entry_inc(iter); + else + ent = iter; + + while (ent && iter->idx < i) + ent = trace_find_next_entry_inc(iter); + + iter->pos = *pos; + + return ent; +} + +void tracing_iter_reset(struct trace_iterator *iter, int cpu) +{ + struct ring_buffer_event *event; + struct ring_buffer_iter *buf_iter; + unsigned long entries = 0; + u64 ts; + + per_cpu_ptr(iter->trace_buffer->data, cpu)->skipped_entries = 0; + + buf_iter = trace_buffer_iter(iter, cpu); + if (!buf_iter) + return; + + ring_buffer_iter_reset(buf_iter); + + /* + * We could have the case with the max latency tracers + * that a reset never took place on a cpu. This is evident + * by the timestamp being before the start of the buffer. + */ + while ((event = ring_buffer_iter_peek(buf_iter, &ts))) { + if (ts >= iter->trace_buffer->time_start) + break; + entries++; + ring_buffer_read(buf_iter, NULL); + } + + per_cpu_ptr(iter->trace_buffer->data, cpu)->skipped_entries = entries; +} + +/* + * The current tracer is copied to avoid a global locking + * all around. + */ +static void *s_start(struct seq_file *m, loff_t *pos) +{ + struct trace_iterator *iter = m->private; + struct trace_array *tr = iter->tr; + int cpu_file = iter->cpu_file; + void *p = NULL; + loff_t l = 0; + int cpu; + + /* + * copy the tracer to avoid using a global lock all around. + * iter->trace is a copy of current_trace, the pointer to the + * name may be used instead of a strcmp(), as iter->trace->name + * will point to the same string as current_trace->name. + */ + mutex_lock(&trace_types_lock); + if (unlikely(tr->current_trace && iter->trace->name != tr->current_trace->name)) + *iter->trace = *tr->current_trace; + mutex_unlock(&trace_types_lock); + +#ifdef CONFIG_TRACER_MAX_TRACE + if (iter->snapshot && iter->trace->use_max_tr) + return ERR_PTR(-EBUSY); +#endif + + if (!iter->snapshot) + atomic_inc(&trace_record_cmdline_disabled); + + if (*pos != iter->pos) { + iter->ent = NULL; + iter->cpu = 0; + iter->idx = -1; + + if (cpu_file == RING_BUFFER_ALL_CPUS) { + for_each_tracing_cpu(cpu) + tracing_iter_reset(iter, cpu); + } else + tracing_iter_reset(iter, cpu_file); + + iter->leftover = 0; + for (p = iter; p && l < *pos; p = s_next(m, p, &l)) + ; + + } else { + /* + * If we overflowed the seq_file before, then we want + * to just reuse the trace_seq buffer again. + */ + if (iter->leftover) + p = iter; + else { + l = *pos - 1; + p = s_next(m, p, &l); + } + } + + trace_event_read_lock(); + trace_access_lock(cpu_file); + return p; +} + +static void s_stop(struct seq_file *m, void *p) +{ + struct trace_iterator *iter = m->private; + +#ifdef CONFIG_TRACER_MAX_TRACE + if (iter->snapshot && iter->trace->use_max_tr) + return; +#endif + + if (!iter->snapshot) + atomic_dec(&trace_record_cmdline_disabled); + + trace_access_unlock(iter->cpu_file); + trace_event_read_unlock(); +} + +static void +get_total_entries(struct trace_buffer *buf, + unsigned long *total, unsigned long *entries) +{ + unsigned long count; + int cpu; + + *total = 0; + *entries = 0; + + for_each_tracing_cpu(cpu) { + count = ring_buffer_entries_cpu(buf->buffer, cpu); + /* + * If this buffer has skipped entries, then we hold all + * entries for the trace and we need to ignore the + * ones before the time stamp. + */ + if (per_cpu_ptr(buf->data, cpu)->skipped_entries) { + count -= per_cpu_ptr(buf->data, cpu)->skipped_entries; + /* total is the same as the entries */ + *total += count; + } else + *total += count + + ring_buffer_overrun_cpu(buf->buffer, cpu); + *entries += count; + } +} + +static void print_lat_help_header(struct seq_file *m) +{ + seq_puts(m, "# _--------=> CPU# \n" + "# / _-------=> irqs-off \n" + "# | / _------=> need-resched \n" + "# || / _-----=> need-resched_lazy \n" + "# ||| / _----=> hardirq/softirq \n" + "# |||| / _---=> preempt-depth \n" + "# ||||| / _--=> preempt-lazy-depth\n" + "# |||||| / _-=> migrate-disable \n" + "# ||||||| / delay \n" + "# cmd pid |||||||| time | caller \n" + "# \\ / |||||||| \\ | / \n"); +} + +static void print_event_info(struct trace_buffer *buf, struct seq_file *m) +{ + unsigned long total; + unsigned long entries; + + get_total_entries(buf, &total, &entries); + seq_printf(m, "# entries-in-buffer/entries-written: %lu/%lu #P:%d\n", + entries, total, num_online_cpus()); + seq_puts(m, "#\n"); +} + +static void print_func_help_header(struct trace_buffer *buf, struct seq_file *m) +{ + print_event_info(buf, m); + seq_puts(m, "# TASK-PID CPU# TIMESTAMP FUNCTION\n" + "# | | | | |\n"); +} + +static void print_func_help_header_irq(struct trace_buffer *buf, struct seq_file *m) +{ + print_event_info(buf, m); + seq_puts(m, "# _-----=> irqs-off\n" + "# / _----=> need-resched\n" + "# |/ _-----=> need-resched_lazy\n" + "# || / _---=> hardirq/softirq\n" + "# ||| / _--=> preempt-depth\n" + "# |||| /_--=> preempt-lazy-depth\n" + "# ||||| _-=> migrate-disable \n" + "# ||||| / delay\n" + "# TASK-PID CPU# |||||| TIMESTAMP FUNCTION\n" + "# | | | |||||| | |\n"); +} + +void +print_trace_header(struct seq_file *m, struct trace_iterator *iter) +{ + unsigned long sym_flags = (trace_flags & TRACE_ITER_SYM_MASK); + struct trace_buffer *buf = iter->trace_buffer; + struct trace_array_cpu *data = per_cpu_ptr(buf->data, buf->cpu); + struct tracer *type = iter->trace; + unsigned long entries; + unsigned long total; + const char *name = "preemption"; + + name = type->name; + + get_total_entries(buf, &total, &entries); + + seq_printf(m, "# %s latency trace v1.1.5 on %s\n", + name, UTS_RELEASE); + seq_puts(m, "# -----------------------------------" + "---------------------------------\n"); + seq_printf(m, "# latency: %lu us, #%lu/%lu, CPU#%d |" + " (M:%s VP:%d, KP:%d, SP:%d HP:%d", + nsecs_to_usecs(data->saved_latency), + entries, + total, + buf->cpu, +#if defined(CONFIG_PREEMPT_NONE) + "server", +#elif defined(CONFIG_PREEMPT_VOLUNTARY) + "desktop", +#elif defined(CONFIG_PREEMPT) + "preempt", +#else + "unknown", +#endif + /* These are reserved for later use */ + 0, 0, 0, 0); +#ifdef CONFIG_SMP + seq_printf(m, " #P:%d)\n", num_online_cpus()); +#else + seq_puts(m, ")\n"); +#endif + seq_puts(m, "# -----------------\n"); + seq_printf(m, "# | task: %.16s-%d " + "(uid:%d nice:%ld policy:%ld rt_prio:%ld)\n", + data->comm, data->pid, + from_kuid_munged(seq_user_ns(m), data->uid), data->nice, + data->policy, data->rt_priority); + seq_puts(m, "# -----------------\n"); + + if (data->critical_start) { + seq_puts(m, "# => started at: "); + seq_print_ip_sym(&iter->seq, data->critical_start, sym_flags); + trace_print_seq(m, &iter->seq); + seq_puts(m, "\n# => ended at: "); + seq_print_ip_sym(&iter->seq, data->critical_end, sym_flags); + trace_print_seq(m, &iter->seq); + seq_puts(m, "\n#\n"); + } + + seq_puts(m, "#\n"); +} + +static void test_cpu_buff_start(struct trace_iterator *iter) +{ + struct trace_seq *s = &iter->seq; + + if (!(trace_flags & TRACE_ITER_ANNOTATE)) + return; + + if (!(iter->iter_flags & TRACE_FILE_ANNOTATE)) + return; + + if (cpumask_test_cpu(iter->cpu, iter->started)) + return; + + if (per_cpu_ptr(iter->trace_buffer->data, iter->cpu)->skipped_entries) + return; + + cpumask_set_cpu(iter->cpu, iter->started); + + /* Don't print started cpu buffer for the first entry of the trace */ + if (iter->idx > 1) + trace_seq_printf(s, "##### CPU %u buffer started ####\n", + iter->cpu); +} + +static enum print_line_t print_trace_fmt(struct trace_iterator *iter) +{ + struct trace_seq *s = &iter->seq; + unsigned long sym_flags = (trace_flags & TRACE_ITER_SYM_MASK); + struct trace_entry *entry; + struct trace_event *event; + + entry = iter->ent; + + test_cpu_buff_start(iter); + + event = ftrace_find_event(entry->type); + + if (trace_flags & TRACE_ITER_CONTEXT_INFO) { + if (iter->iter_flags & TRACE_FILE_LAT_FMT) + trace_print_lat_context(iter); + else + trace_print_context(iter); + } + + if (trace_seq_has_overflowed(s)) + return TRACE_TYPE_PARTIAL_LINE; + + if (event) + return event->funcs->trace(iter, sym_flags, event); + + trace_seq_printf(s, "Unknown type %d\n", entry->type); + + return trace_handle_return(s); +} + +static enum print_line_t print_raw_fmt(struct trace_iterator *iter) +{ + struct trace_seq *s = &iter->seq; + struct trace_entry *entry; + struct trace_event *event; + + entry = iter->ent; + + if (trace_flags & TRACE_ITER_CONTEXT_INFO) + trace_seq_printf(s, "%d %d %llu ", + entry->pid, iter->cpu, iter->ts); + + if (trace_seq_has_overflowed(s)) + return TRACE_TYPE_PARTIAL_LINE; + + event = ftrace_find_event(entry->type); + if (event) + return event->funcs->raw(iter, 0, event); + + trace_seq_printf(s, "%d ?\n", entry->type); + + return trace_handle_return(s); +} + +static enum print_line_t print_hex_fmt(struct trace_iterator *iter) +{ + struct trace_seq *s = &iter->seq; + unsigned char newline = '\n'; + struct trace_entry *entry; + struct trace_event *event; + + entry = iter->ent; + + if (trace_flags & TRACE_ITER_CONTEXT_INFO) { + SEQ_PUT_HEX_FIELD(s, entry->pid); + SEQ_PUT_HEX_FIELD(s, iter->cpu); + SEQ_PUT_HEX_FIELD(s, iter->ts); + if (trace_seq_has_overflowed(s)) + return TRACE_TYPE_PARTIAL_LINE; + } + + event = ftrace_find_event(entry->type); + if (event) { + enum print_line_t ret = event->funcs->hex(iter, 0, event); + if (ret != TRACE_TYPE_HANDLED) + return ret; + } + + SEQ_PUT_FIELD(s, newline); + + return trace_handle_return(s); +} + +static enum print_line_t print_bin_fmt(struct trace_iterator *iter) +{ + struct trace_seq *s = &iter->seq; + struct trace_entry *entry; + struct trace_event *event; + + entry = iter->ent; + + if (trace_flags & TRACE_ITER_CONTEXT_INFO) { + SEQ_PUT_FIELD(s, entry->pid); + SEQ_PUT_FIELD(s, iter->cpu); + SEQ_PUT_FIELD(s, iter->ts); + if (trace_seq_has_overflowed(s)) + return TRACE_TYPE_PARTIAL_LINE; + } + + event = ftrace_find_event(entry->type); + return event ? event->funcs->binary(iter, 0, event) : + TRACE_TYPE_HANDLED; +} + +int trace_empty(struct trace_iterator *iter) +{ + struct ring_buffer_iter *buf_iter; + int cpu; + + /* If we are looking at one CPU buffer, only check that one */ + if (iter->cpu_file != RING_BUFFER_ALL_CPUS) { + cpu = iter->cpu_file; + buf_iter = trace_buffer_iter(iter, cpu); + if (buf_iter) { + if (!ring_buffer_iter_empty(buf_iter)) + return 0; + } else { + if (!ring_buffer_empty_cpu(iter->trace_buffer->buffer, cpu)) + return 0; + } + return 1; + } + + for_each_tracing_cpu(cpu) { + buf_iter = trace_buffer_iter(iter, cpu); + if (buf_iter) { + if (!ring_buffer_iter_empty(buf_iter)) + return 0; + } else { + if (!ring_buffer_empty_cpu(iter->trace_buffer->buffer, cpu)) + return 0; + } + } + + return 1; +} + +/* Called with trace_event_read_lock() held. */ +enum print_line_t print_trace_line(struct trace_iterator *iter) +{ + enum print_line_t ret; + + if (iter->lost_events) { + trace_seq_printf(&iter->seq, "CPU:%d [LOST %lu EVENTS]\n", + iter->cpu, iter->lost_events); + if (trace_seq_has_overflowed(&iter->seq)) + return TRACE_TYPE_PARTIAL_LINE; + } + + if (iter->trace && iter->trace->print_line) { + ret = iter->trace->print_line(iter); + if (ret != TRACE_TYPE_UNHANDLED) + return ret; + } + + if (iter->ent->type == TRACE_BPUTS && + trace_flags & TRACE_ITER_PRINTK && + trace_flags & TRACE_ITER_PRINTK_MSGONLY) + return trace_print_bputs_msg_only(iter); + + if (iter->ent->type == TRACE_BPRINT && + trace_flags & TRACE_ITER_PRINTK && + trace_flags & TRACE_ITER_PRINTK_MSGONLY) + return trace_print_bprintk_msg_only(iter); + + if (iter->ent->type == TRACE_PRINT && + trace_flags & TRACE_ITER_PRINTK && + trace_flags & TRACE_ITER_PRINTK_MSGONLY) + return trace_print_printk_msg_only(iter); + + if (trace_flags & TRACE_ITER_BIN) + return print_bin_fmt(iter); + + if (trace_flags & TRACE_ITER_HEX) + return print_hex_fmt(iter); + + if (trace_flags & TRACE_ITER_RAW) + return print_raw_fmt(iter); + + return print_trace_fmt(iter); +} + +void trace_latency_header(struct seq_file *m) +{ + struct trace_iterator *iter = m->private; + + /* print nothing if the buffers are empty */ + if (trace_empty(iter)) + return; + + if (iter->iter_flags & TRACE_FILE_LAT_FMT) + print_trace_header(m, iter); + + if (!(trace_flags & TRACE_ITER_VERBOSE)) + print_lat_help_header(m); +} + +void trace_default_header(struct seq_file *m) +{ + struct trace_iterator *iter = m->private; + + if (!(trace_flags & TRACE_ITER_CONTEXT_INFO)) + return; + + if (iter->iter_flags & TRACE_FILE_LAT_FMT) { + /* print nothing if the buffers are empty */ + if (trace_empty(iter)) + return; + print_trace_header(m, iter); + if (!(trace_flags & TRACE_ITER_VERBOSE)) + print_lat_help_header(m); + } else { + if (!(trace_flags & TRACE_ITER_VERBOSE)) { + if (trace_flags & TRACE_ITER_IRQ_INFO) + print_func_help_header_irq(iter->trace_buffer, m); + else + print_func_help_header(iter->trace_buffer, m); + } + } +} + +static void test_ftrace_alive(struct seq_file *m) +{ + if (!ftrace_is_dead()) + return; + seq_puts(m, "# WARNING: FUNCTION TRACING IS CORRUPTED\n" + "# MAY BE MISSING FUNCTION EVENTS\n"); +} + +#ifdef CONFIG_TRACER_MAX_TRACE +static void show_snapshot_main_help(struct seq_file *m) +{ + seq_puts(m, "# echo 0 > snapshot : Clears and frees snapshot buffer\n" + "# echo 1 > snapshot : Allocates snapshot buffer, if not already allocated.\n" + "# Takes a snapshot of the main buffer.\n" + "# echo 2 > snapshot : Clears snapshot buffer (but does not allocate or free)\n" + "# (Doesn't have to be '2' works with any number that\n" + "# is not a '0' or '1')\n"); +} + +static void show_snapshot_percpu_help(struct seq_file *m) +{ + seq_puts(m, "# echo 0 > snapshot : Invalid for per_cpu snapshot file.\n"); +#ifdef CONFIG_RING_BUFFER_ALLOW_SWAP + seq_puts(m, "# echo 1 > snapshot : Allocates snapshot buffer, if not already allocated.\n" + "# Takes a snapshot of the main buffer for this cpu.\n"); +#else + seq_puts(m, "# echo 1 > snapshot : Not supported with this kernel.\n" + "# Must use main snapshot file to allocate.\n"); +#endif + seq_puts(m, "# echo 2 > snapshot : Clears this cpu's snapshot buffer (but does not allocate)\n" + "# (Doesn't have to be '2' works with any number that\n" + "# is not a '0' or '1')\n"); +} + +static void print_snapshot_help(struct seq_file *m, struct trace_iterator *iter) +{ + if (iter->tr->allocated_snapshot) + seq_puts(m, "#\n# * Snapshot is allocated *\n#\n"); + else + seq_puts(m, "#\n# * Snapshot is freed *\n#\n"); + + seq_puts(m, "# Snapshot commands:\n"); + if (iter->cpu_file == RING_BUFFER_ALL_CPUS) + show_snapshot_main_help(m); + else + show_snapshot_percpu_help(m); +} +#else +/* Should never be called */ +static inline void print_snapshot_help(struct seq_file *m, struct trace_iterator *iter) { } +#endif + +static int s_show(struct seq_file *m, void *v) +{ + struct trace_iterator *iter = v; + int ret; + + if (iter->ent == NULL) { + if (iter->tr) { + seq_printf(m, "# tracer: %s\n", iter->trace->name); + seq_puts(m, "#\n"); + test_ftrace_alive(m); + } + if (iter->snapshot && trace_empty(iter)) + print_snapshot_help(m, iter); + else if (iter->trace && iter->trace->print_header) + iter->trace->print_header(m); + else + trace_default_header(m); + + } else if (iter->leftover) { + /* + * If we filled the seq_file buffer earlier, we + * want to just show it now. + */ + ret = trace_print_seq(m, &iter->seq); + + /* ret should this time be zero, but you never know */ + iter->leftover = ret; + + } else { + print_trace_line(iter); + ret = trace_print_seq(m, &iter->seq); + /* + * If we overflow the seq_file buffer, then it will + * ask us for this data again at start up. + * Use that instead. + * ret is 0 if seq_file write succeeded. + * -1 otherwise. + */ + iter->leftover = ret; + } + + return 0; +} + +/* + * Should be used after trace_array_get(), trace_types_lock + * ensures that i_cdev was already initialized. + */ +static inline int tracing_get_cpu(struct inode *inode) +{ + if (inode->i_cdev) /* See trace_create_cpu_file() */ + return (long)inode->i_cdev - 1; + return RING_BUFFER_ALL_CPUS; +} + +static const struct seq_operations tracer_seq_ops = { + .start = s_start, + .next = s_next, + .stop = s_stop, + .show = s_show, +}; + +static struct trace_iterator * +__tracing_open(struct inode *inode, struct file *file, bool snapshot) +{ + struct trace_array *tr = inode->i_private; + struct trace_iterator *iter; + int cpu; + + if (tracing_disabled) + return ERR_PTR(-ENODEV); + + iter = __seq_open_private(file, &tracer_seq_ops, sizeof(*iter)); + if (!iter) + return ERR_PTR(-ENOMEM); + + iter->buffer_iter = kzalloc(sizeof(*iter->buffer_iter) * num_possible_cpus(), + GFP_KERNEL); + if (!iter->buffer_iter) + goto release; + + /* + * We make a copy of the current tracer to avoid concurrent + * changes on it while we are reading. + */ + mutex_lock(&trace_types_lock); + iter->trace = kzalloc(sizeof(*iter->trace), GFP_KERNEL); + if (!iter->trace) + goto fail; + + *iter->trace = *tr->current_trace; + + if (!zalloc_cpumask_var(&iter->started, GFP_KERNEL)) + goto fail; + + iter->tr = tr; + +#ifdef CONFIG_TRACER_MAX_TRACE + /* Currently only the top directory has a snapshot */ + if (tr->current_trace->print_max || snapshot) + iter->trace_buffer = &tr->max_buffer; + else +#endif + iter->trace_buffer = &tr->trace_buffer; + iter->snapshot = snapshot; + iter->pos = -1; + iter->cpu_file = tracing_get_cpu(inode); + mutex_init(&iter->mutex); + + /* Notify the tracer early; before we stop tracing. */ + if (iter->trace && iter->trace->open) + iter->trace->open(iter); + + /* Annotate start of buffers if we had overruns */ + if (ring_buffer_overruns(iter->trace_buffer->buffer)) + iter->iter_flags |= TRACE_FILE_ANNOTATE; + + /* Output in nanoseconds only if we are using a clock in nanoseconds. */ + if (trace_clocks[tr->clock_id].in_ns) + iter->iter_flags |= TRACE_FILE_TIME_IN_NS; + + /* stop the trace while dumping if we are not opening "snapshot" */ + if (!iter->snapshot) + tracing_stop_tr(tr); + + if (iter->cpu_file == RING_BUFFER_ALL_CPUS) { + for_each_tracing_cpu(cpu) { + iter->buffer_iter[cpu] = + ring_buffer_read_prepare(iter->trace_buffer->buffer, cpu); + } + ring_buffer_read_prepare_sync(); + for_each_tracing_cpu(cpu) { + ring_buffer_read_start(iter->buffer_iter[cpu]); + tracing_iter_reset(iter, cpu); + } + } else { + cpu = iter->cpu_file; + iter->buffer_iter[cpu] = + ring_buffer_read_prepare(iter->trace_buffer->buffer, cpu); + ring_buffer_read_prepare_sync(); + ring_buffer_read_start(iter->buffer_iter[cpu]); + tracing_iter_reset(iter, cpu); + } + + mutex_unlock(&trace_types_lock); + + return iter; + + fail: + mutex_unlock(&trace_types_lock); + kfree(iter->trace); + kfree(iter->buffer_iter); +release: + seq_release_private(inode, file); + return ERR_PTR(-ENOMEM); +} + +int tracing_open_generic(struct inode *inode, struct file *filp) +{ + if (tracing_disabled) + return -ENODEV; + + filp->private_data = inode->i_private; + return 0; +} + +bool tracing_is_disabled(void) +{ + return (tracing_disabled) ? true: false; +} + +/* + * Open and update trace_array ref count. + * Must have the current trace_array passed to it. + */ +static int tracing_open_generic_tr(struct inode *inode, struct file *filp) +{ + struct trace_array *tr = inode->i_private; + + if (tracing_disabled) + return -ENODEV; + + if (trace_array_get(tr) < 0) + return -ENODEV; + + filp->private_data = inode->i_private; + + return 0; +} + +static int tracing_release(struct inode *inode, struct file *file) +{ + struct trace_array *tr = inode->i_private; + struct seq_file *m = file->private_data; + struct trace_iterator *iter; + int cpu; + + if (!(file->f_mode & FMODE_READ)) { + trace_array_put(tr); + return 0; + } + + /* Writes do not use seq_file */ + iter = m->private; + mutex_lock(&trace_types_lock); + + for_each_tracing_cpu(cpu) { + if (iter->buffer_iter[cpu]) + ring_buffer_read_finish(iter->buffer_iter[cpu]); + } + + if (iter->trace && iter->trace->close) + iter->trace->close(iter); + + if (!iter->snapshot) + /* reenable tracing if it was previously enabled */ + tracing_start_tr(tr); + + __trace_array_put(tr); + + mutex_unlock(&trace_types_lock); + + mutex_destroy(&iter->mutex); + free_cpumask_var(iter->started); + kfree(iter->trace); + kfree(iter->buffer_iter); + seq_release_private(inode, file); + + return 0; +} + +static int tracing_release_generic_tr(struct inode *inode, struct file *file) +{ + struct trace_array *tr = inode->i_private; + + trace_array_put(tr); + return 0; +} + +static int tracing_single_release_tr(struct inode *inode, struct file *file) +{ + struct trace_array *tr = inode->i_private; + + trace_array_put(tr); + + return single_release(inode, file); +} + +static int tracing_open(struct inode *inode, struct file *file) +{ + struct trace_array *tr = inode->i_private; + struct trace_iterator *iter; + int ret = 0; + + if (trace_array_get(tr) < 0) + return -ENODEV; + + /* If this file was open for write, then erase contents */ + if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) { + int cpu = tracing_get_cpu(inode); + + if (cpu == RING_BUFFER_ALL_CPUS) + tracing_reset_online_cpus(&tr->trace_buffer); + else + tracing_reset(&tr->trace_buffer, cpu); + } + + if (file->f_mode & FMODE_READ) { + iter = __tracing_open(inode, file, false); + if (IS_ERR(iter)) + ret = PTR_ERR(iter); + else if (trace_flags & TRACE_ITER_LATENCY_FMT) + iter->iter_flags |= TRACE_FILE_LAT_FMT; + } + + if (ret < 0) + trace_array_put(tr); + + return ret; +} + +/* + * Some tracers are not suitable for instance buffers. + * A tracer is always available for the global array (toplevel) + * or if it explicitly states that it is. + */ +static bool +trace_ok_for_array(struct tracer *t, struct trace_array *tr) +{ + return (tr->flags & TRACE_ARRAY_FL_GLOBAL) || t->allow_instances; +} + +/* Find the next tracer that this trace array may use */ +static struct tracer * +get_tracer_for_array(struct trace_array *tr, struct tracer *t) +{ + while (t && !trace_ok_for_array(t, tr)) + t = t->next; + + return t; +} + +static void * +t_next(struct seq_file *m, void *v, loff_t *pos) +{ + struct trace_array *tr = m->private; + struct tracer *t = v; + + (*pos)++; + + if (t) + t = get_tracer_for_array(tr, t->next); + + return t; +} + +static void *t_start(struct seq_file *m, loff_t *pos) +{ + struct trace_array *tr = m->private; + struct tracer *t; + loff_t l = 0; + + mutex_lock(&trace_types_lock); + + t = get_tracer_for_array(tr, trace_types); + for (; t && l < *pos; t = t_next(m, t, &l)) + ; + + return t; +} + +static void t_stop(struct seq_file *m, void *p) +{ + mutex_unlock(&trace_types_lock); +} + +static int t_show(struct seq_file *m, void *v) +{ + struct tracer *t = v; + + if (!t) + return 0; + + seq_puts(m, t->name); + if (t->next) + seq_putc(m, ' '); + else + seq_putc(m, '\n'); + + return 0; +} + +static const struct seq_operations show_traces_seq_ops = { + .start = t_start, + .next = t_next, + .stop = t_stop, + .show = t_show, +}; + +static int show_traces_open(struct inode *inode, struct file *file) +{ + struct trace_array *tr = inode->i_private; + struct seq_file *m; + int ret; + + if (tracing_disabled) + return -ENODEV; + + ret = seq_open(file, &show_traces_seq_ops); + if (ret) + return ret; + + m = file->private_data; + m->private = tr; + + return 0; +} + +static ssize_t +tracing_write_stub(struct file *filp, const char __user *ubuf, + size_t count, loff_t *ppos) +{ + return count; +} + +loff_t tracing_lseek(struct file *file, loff_t offset, int whence) +{ + int ret; + + if (file->f_mode & FMODE_READ) + ret = seq_lseek(file, offset, whence); + else + file->f_pos = ret = 0; + + return ret; +} + +static const struct file_operations tracing_fops = { + .open = tracing_open, + .read = seq_read, + .write = tracing_write_stub, + .llseek = tracing_lseek, + .release = tracing_release, +}; + +static const struct file_operations show_traces_fops = { + .open = show_traces_open, + .read = seq_read, + .release = seq_release, + .llseek = seq_lseek, +}; + +/* + * The tracer itself will not take this lock, but still we want + * to provide a consistent cpumask to user-space: + */ +static DEFINE_MUTEX(tracing_cpumask_update_lock); + +/* + * Temporary storage for the character representation of the + * CPU bitmask (and one more byte for the newline): + */ +static char mask_str[NR_CPUS + 1]; + +static ssize_t +tracing_cpumask_read(struct file *filp, char __user *ubuf, + size_t count, loff_t *ppos) +{ + struct trace_array *tr = file_inode(filp)->i_private; + int len; + + mutex_lock(&tracing_cpumask_update_lock); + + len = snprintf(mask_str, count, "%*pb\n", + cpumask_pr_args(tr->tracing_cpumask)); + if (len >= count) { + count = -EINVAL; + goto out_err; + } + count = simple_read_from_buffer(ubuf, count, ppos, mask_str, NR_CPUS+1); + +out_err: + mutex_unlock(&tracing_cpumask_update_lock); + + return count; +} + +static ssize_t +tracing_cpumask_write(struct file *filp, const char __user *ubuf, + size_t count, loff_t *ppos) +{ + struct trace_array *tr = file_inode(filp)->i_private; + cpumask_var_t tracing_cpumask_new; + int err, cpu; + + if (!alloc_cpumask_var(&tracing_cpumask_new, GFP_KERNEL)) + return -ENOMEM; + + err = cpumask_parse_user(ubuf, count, tracing_cpumask_new); + if (err) + goto err_unlock; + + mutex_lock(&tracing_cpumask_update_lock); + + local_irq_disable(); + arch_spin_lock(&tr->max_lock); + for_each_tracing_cpu(cpu) { + /* + * Increase/decrease the disabled counter if we are + * about to flip a bit in the cpumask: + */ + if (cpumask_test_cpu(cpu, tr->tracing_cpumask) && + !cpumask_test_cpu(cpu, tracing_cpumask_new)) { + atomic_inc(&per_cpu_ptr(tr->trace_buffer.data, cpu)->disabled); + ring_buffer_record_disable_cpu(tr->trace_buffer.buffer, cpu); + } + if (!cpumask_test_cpu(cpu, tr->tracing_cpumask) && + cpumask_test_cpu(cpu, tracing_cpumask_new)) { + atomic_dec(&per_cpu_ptr(tr->trace_buffer.data, cpu)->disabled); + ring_buffer_record_enable_cpu(tr->trace_buffer.buffer, cpu); + } + } + arch_spin_unlock(&tr->max_lock); + local_irq_enable(); + + cpumask_copy(tr->tracing_cpumask, tracing_cpumask_new); + + mutex_unlock(&tracing_cpumask_update_lock); + free_cpumask_var(tracing_cpumask_new); + + return count; + +err_unlock: + free_cpumask_var(tracing_cpumask_new); + + return err; +} + +static const struct file_operations tracing_cpumask_fops = { + .open = tracing_open_generic_tr, + .read = tracing_cpumask_read, + .write = tracing_cpumask_write, + .release = tracing_release_generic_tr, + .llseek = generic_file_llseek, +}; + +static int tracing_trace_options_show(struct seq_file *m, void *v) +{ + struct tracer_opt *trace_opts; + struct trace_array *tr = m->private; + u32 tracer_flags; + int i; + + mutex_lock(&trace_types_lock); + tracer_flags = tr->current_trace->flags->val; + trace_opts = tr->current_trace->flags->opts; + + for (i = 0; trace_options[i]; i++) { + if (trace_flags & (1 << i)) + seq_printf(m, "%s\n", trace_options[i]); + else + seq_printf(m, "no%s\n", trace_options[i]); + } + + for (i = 0; trace_opts[i].name; i++) { + if (tracer_flags & trace_opts[i].bit) + seq_printf(m, "%s\n", trace_opts[i].name); + else + seq_printf(m, "no%s\n", trace_opts[i].name); + } + mutex_unlock(&trace_types_lock); + + return 0; +} + +static int __set_tracer_option(struct trace_array *tr, + struct tracer_flags *tracer_flags, + struct tracer_opt *opts, int neg) +{ + struct tracer *trace = tr->current_trace; + int ret; + + ret = trace->set_flag(tr, tracer_flags->val, opts->bit, !neg); + if (ret) + return ret; + + if (neg) + tracer_flags->val &= ~opts->bit; + else + tracer_flags->val |= opts->bit; + return 0; +} + +/* Try to assign a tracer specific option */ +static int set_tracer_option(struct trace_array *tr, char *cmp, int neg) +{ + struct tracer *trace = tr->current_trace; + struct tracer_flags *tracer_flags = trace->flags; + struct tracer_opt *opts = NULL; + int i; + + for (i = 0; tracer_flags->opts[i].name; i++) { + opts = &tracer_flags->opts[i]; + + if (strcmp(cmp, opts->name) == 0) + return __set_tracer_option(tr, trace->flags, opts, neg); + } + + return -EINVAL; +} + +/* Some tracers require overwrite to stay enabled */ +int trace_keep_overwrite(struct tracer *tracer, u32 mask, int set) +{ + if (tracer->enabled && (mask & TRACE_ITER_OVERWRITE) && !set) + return -1; + + return 0; +} + +int set_tracer_flag(struct trace_array *tr, unsigned int mask, int enabled) +{ + /* do nothing if flag is already set */ + if (!!(trace_flags & mask) == !!enabled) + return 0; + + /* Give the tracer a chance to approve the change */ + if (tr->current_trace->flag_changed) + if (tr->current_trace->flag_changed(tr, mask, !!enabled)) + return -EINVAL; + + if (enabled) + trace_flags |= mask; + else + trace_flags &= ~mask; + + if (mask == TRACE_ITER_RECORD_CMD) + trace_event_enable_cmd_record(enabled); + + if (mask == TRACE_ITER_OVERWRITE) { + ring_buffer_change_overwrite(tr->trace_buffer.buffer, enabled); +#ifdef CONFIG_TRACER_MAX_TRACE + ring_buffer_change_overwrite(tr->max_buffer.buffer, enabled); +#endif + } + + if (mask == TRACE_ITER_PRINTK) + trace_printk_start_stop_comm(enabled); + + return 0; +} + +static int trace_set_options(struct trace_array *tr, char *option) +{ + char *cmp; + int neg = 0; + int ret = -ENODEV; + int i; + + cmp = strstrip(option); + + if (strncmp(cmp, "no", 2) == 0) { + neg = 1; + cmp += 2; + } + + mutex_lock(&trace_types_lock); + + for (i = 0; trace_options[i]; i++) { + if (strcmp(cmp, trace_options[i]) == 0) { + ret = set_tracer_flag(tr, 1 << i, !neg); + break; + } + } + + /* If no option could be set, test the specific tracer options */ + if (!trace_options[i]) + ret = set_tracer_option(tr, cmp, neg); + + mutex_unlock(&trace_types_lock); + + return ret; +} + +static ssize_t +tracing_trace_options_write(struct file *filp, const char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + struct seq_file *m = filp->private_data; + struct trace_array *tr = m->private; + char buf[64]; + int ret; + + if (cnt >= sizeof(buf)) + return -EINVAL; + + if (copy_from_user(&buf, ubuf, cnt)) + return -EFAULT; + + buf[cnt] = 0; + + ret = trace_set_options(tr, buf); + if (ret < 0) + return ret; + + *ppos += cnt; + + return cnt; +} + +static int tracing_trace_options_open(struct inode *inode, struct file *file) +{ + struct trace_array *tr = inode->i_private; + int ret; + + if (tracing_disabled) + return -ENODEV; + + if (trace_array_get(tr) < 0) + return -ENODEV; + + ret = single_open(file, tracing_trace_options_show, inode->i_private); + if (ret < 0) + trace_array_put(tr); + + return ret; +} + +static const struct file_operations tracing_iter_fops = { + .open = tracing_trace_options_open, + .read = seq_read, + .llseek = seq_lseek, + .release = tracing_single_release_tr, + .write = tracing_trace_options_write, +}; + +static const char readme_msg[] = + "tracing mini-HOWTO:\n\n" + "# echo 0 > tracing_on : quick way to disable tracing\n" + "# echo 1 > tracing_on : quick way to re-enable tracing\n\n" + " Important files:\n" + " trace\t\t\t- The static contents of the buffer\n" + "\t\t\t To clear the buffer write into this file: echo > trace\n" + " trace_pipe\t\t- A consuming read to see the contents of the buffer\n" + " current_tracer\t- function and latency tracers\n" + " available_tracers\t- list of configured tracers for current_tracer\n" + " buffer_size_kb\t- view and modify size of per cpu buffer\n" + " buffer_total_size_kb - view total size of all cpu buffers\n\n" + " trace_clock\t\t-change the clock used to order events\n" + " local: Per cpu clock but may not be synced across CPUs\n" + " global: Synced across CPUs but slows tracing down.\n" + " counter: Not a clock, but just an increment\n" + " uptime: Jiffy counter from time of boot\n" + " perf: Same clock that perf events use\n" +#ifdef CONFIG_X86_64 + " x86-tsc: TSC cycle counter\n" +#endif + "\n trace_marker\t\t- Writes into this file writes into the kernel buffer\n" + " tracing_cpumask\t- Limit which CPUs to trace\n" + " instances\t\t- Make sub-buffers with: mkdir instances/foo\n" + "\t\t\t Remove sub-buffer with rmdir\n" + " trace_options\t\t- Set format or modify how tracing happens\n" + "\t\t\t Disable an option by adding a suffix 'no' to the\n" + "\t\t\t option name\n" + " saved_cmdlines_size\t- echo command number in here to store comm-pid list\n" +#ifdef CONFIG_DYNAMIC_FTRACE + "\n available_filter_functions - list of functions that can be filtered on\n" + " set_ftrace_filter\t- echo function name in here to only trace these\n" + "\t\t\t functions\n" + "\t accepts: func_full_name, *func_end, func_begin*, *func_middle*\n" + "\t modules: Can select a group via module\n" + "\t Format: :mod:\n" + "\t example: echo :mod:ext3 > set_ftrace_filter\n" + "\t triggers: a command to perform when function is hit\n" + "\t Format: :[:count]\n" + "\t trigger: traceon, traceoff\n" + "\t\t enable_event::\n" + "\t\t disable_event::\n" +#ifdef CONFIG_STACKTRACE + "\t\t stacktrace\n" +#endif +#ifdef CONFIG_TRACER_SNAPSHOT + "\t\t snapshot\n" +#endif + "\t\t dump\n" + "\t\t cpudump\n" + "\t example: echo do_fault:traceoff > set_ftrace_filter\n" + "\t echo do_trap:traceoff:3 > set_ftrace_filter\n" + "\t The first one will disable tracing every time do_fault is hit\n" + "\t The second will disable tracing at most 3 times when do_trap is hit\n" + "\t The first time do trap is hit and it disables tracing, the\n" + "\t counter will decrement to 2. If tracing is already disabled,\n" + "\t the counter will not decrement. It only decrements when the\n" + "\t trigger did work\n" + "\t To remove trigger without count:\n" + "\t echo '!: > set_ftrace_filter\n" + "\t To remove trigger with a count:\n" + "\t echo '!::0 > set_ftrace_filter\n" + " set_ftrace_notrace\t- echo function name in here to never trace.\n" + "\t accepts: func_full_name, *func_end, func_begin*, *func_middle*\n" + "\t modules: Can select a group via module command :mod:\n" + "\t Does not accept triggers\n" +#endif /* CONFIG_DYNAMIC_FTRACE */ +#ifdef CONFIG_FUNCTION_TRACER + " set_ftrace_pid\t- Write pid(s) to only function trace those pids\n" + "\t\t (function)\n" +#endif +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + " set_graph_function\t- Trace the nested calls of a function (function_graph)\n" + " set_graph_notrace\t- Do not trace the nested calls of a function (function_graph)\n" + " max_graph_depth\t- Trace a limited depth of nested calls (0 is unlimited)\n" +#endif +#ifdef CONFIG_TRACER_SNAPSHOT + "\n snapshot\t\t- Like 'trace' but shows the content of the static\n" + "\t\t\t snapshot buffer. Read the contents for more\n" + "\t\t\t information\n" +#endif +#ifdef CONFIG_STACK_TRACER + " stack_trace\t\t- Shows the max stack trace when active\n" + " stack_max_size\t- Shows current max stack size that was traced\n" + "\t\t\t Write into this file to reset the max size (trigger a\n" + "\t\t\t new trace)\n" +#ifdef CONFIG_DYNAMIC_FTRACE + " stack_trace_filter\t- Like set_ftrace_filter but limits what stack_trace\n" + "\t\t\t traces\n" +#endif +#endif /* CONFIG_STACK_TRACER */ + " events/\t\t- Directory containing all trace event subsystems:\n" + " enable\t\t- Write 0/1 to enable/disable tracing of all events\n" + " events//\t- Directory containing all trace events for :\n" + " enable\t\t- Write 0/1 to enable/disable tracing of all \n" + "\t\t\t events\n" + " filter\t\t- If set, only events passing filter are traced\n" + " events///\t- Directory containing control files for\n" + "\t\t\t :\n" + " enable\t\t- Write 0/1 to enable/disable tracing of \n" + " filter\t\t- If set, only events passing filter are traced\n" + " trigger\t\t- If set, a command to perform when event is hit\n" + "\t Format: [:count][if ]\n" + "\t trigger: traceon, traceoff\n" + "\t enable_event::\n" + "\t disable_event::\n" +#ifdef CONFIG_STACKTRACE + "\t\t stacktrace\n" +#endif +#ifdef CONFIG_TRACER_SNAPSHOT + "\t\t snapshot\n" +#endif + "\t example: echo traceoff > events/block/block_unplug/trigger\n" + "\t echo traceoff:3 > events/block/block_unplug/trigger\n" + "\t echo 'enable_event:kmem:kmalloc:3 if nr_rq > 1' > \\\n" + "\t events/block/block_unplug/trigger\n" + "\t The first disables tracing every time block_unplug is hit.\n" + "\t The second disables tracing the first 3 times block_unplug is hit.\n" + "\t The third enables the kmalloc event the first 3 times block_unplug\n" + "\t is hit and has value of greater than 1 for the 'nr_rq' event field.\n" + "\t Like function triggers, the counter is only decremented if it\n" + "\t enabled or disabled tracing.\n" + "\t To remove a trigger without a count:\n" + "\t echo '! > //trigger\n" + "\t To remove a trigger with a count:\n" + "\t echo '!:0 > //trigger\n" + "\t Filters can be ignored when removing a trigger.\n" +; + +static ssize_t +tracing_readme_read(struct file *filp, char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + return simple_read_from_buffer(ubuf, cnt, ppos, + readme_msg, strlen(readme_msg)); +} + +static const struct file_operations tracing_readme_fops = { + .open = tracing_open_generic, + .read = tracing_readme_read, + .llseek = generic_file_llseek, +}; + +static void *saved_cmdlines_next(struct seq_file *m, void *v, loff_t *pos) +{ + unsigned int *ptr = v; + + if (*pos || m->count) + ptr++; + + (*pos)++; + + for (; ptr < &savedcmd->map_cmdline_to_pid[savedcmd->cmdline_num]; + ptr++) { + if (*ptr == -1 || *ptr == NO_CMDLINE_MAP) + continue; + + return ptr; + } + + return NULL; +} + +static void *saved_cmdlines_start(struct seq_file *m, loff_t *pos) +{ + void *v; + loff_t l = 0; + + preempt_disable(); + arch_spin_lock(&trace_cmdline_lock); + + v = &savedcmd->map_cmdline_to_pid[0]; + while (l <= *pos) { + v = saved_cmdlines_next(m, v, &l); + if (!v) + return NULL; + } + + return v; +} + +static void saved_cmdlines_stop(struct seq_file *m, void *v) +{ + arch_spin_unlock(&trace_cmdline_lock); + preempt_enable(); +} + +static int saved_cmdlines_show(struct seq_file *m, void *v) +{ + char buf[TASK_COMM_LEN]; + unsigned int *pid = v; + + __trace_find_cmdline(*pid, buf); + seq_printf(m, "%d %s\n", *pid, buf); + return 0; +} + +static const struct seq_operations tracing_saved_cmdlines_seq_ops = { + .start = saved_cmdlines_start, + .next = saved_cmdlines_next, + .stop = saved_cmdlines_stop, + .show = saved_cmdlines_show, +}; + +static int tracing_saved_cmdlines_open(struct inode *inode, struct file *filp) +{ + if (tracing_disabled) + return -ENODEV; + + return seq_open(filp, &tracing_saved_cmdlines_seq_ops); +} + +static const struct file_operations tracing_saved_cmdlines_fops = { + .open = tracing_saved_cmdlines_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, +}; + +static ssize_t +tracing_saved_cmdlines_size_read(struct file *filp, char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + char buf[64]; + int r; + + arch_spin_lock(&trace_cmdline_lock); + r = scnprintf(buf, sizeof(buf), "%u\n", savedcmd->cmdline_num); + arch_spin_unlock(&trace_cmdline_lock); + + return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); +} + +static void free_saved_cmdlines_buffer(struct saved_cmdlines_buffer *s) +{ + kfree(s->saved_cmdlines); + kfree(s->map_cmdline_to_pid); + kfree(s); +} + +static int tracing_resize_saved_cmdlines(unsigned int val) +{ + struct saved_cmdlines_buffer *s, *savedcmd_temp; + + s = kmalloc(sizeof(*s), GFP_KERNEL); + if (!s) + return -ENOMEM; + + if (allocate_cmdlines_buffer(val, s) < 0) { + kfree(s); + return -ENOMEM; + } + + arch_spin_lock(&trace_cmdline_lock); + savedcmd_temp = savedcmd; + savedcmd = s; + arch_spin_unlock(&trace_cmdline_lock); + free_saved_cmdlines_buffer(savedcmd_temp); + + return 0; +} + +static ssize_t +tracing_saved_cmdlines_size_write(struct file *filp, const char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + unsigned long val; + int ret; + + ret = kstrtoul_from_user(ubuf, cnt, 10, &val); + if (ret) + return ret; + + /* must have at least 1 entry or less than PID_MAX_DEFAULT */ + if (!val || val > PID_MAX_DEFAULT) + return -EINVAL; + + ret = tracing_resize_saved_cmdlines((unsigned int)val); + if (ret < 0) + return ret; + + *ppos += cnt; + + return cnt; +} + +static const struct file_operations tracing_saved_cmdlines_size_fops = { + .open = tracing_open_generic, + .read = tracing_saved_cmdlines_size_read, + .write = tracing_saved_cmdlines_size_write, +}; + +#ifdef CONFIG_TRACE_ENUM_MAP_FILE +static union trace_enum_map_item * +update_enum_map(union trace_enum_map_item *ptr) +{ + if (!ptr->map.enum_string) { + if (ptr->tail.next) { + ptr = ptr->tail.next; + /* Set ptr to the next real item (skip head) */ + ptr++; + } else + return NULL; + } + return ptr; +} + +static void *enum_map_next(struct seq_file *m, void *v, loff_t *pos) +{ + union trace_enum_map_item *ptr = v; + + /* + * Paranoid! If ptr points to end, we don't want to increment past it. + * This really should never happen. + */ + ptr = update_enum_map(ptr); + if (WARN_ON_ONCE(!ptr)) + return NULL; + + ptr++; + + (*pos)++; + + ptr = update_enum_map(ptr); + + return ptr; +} + +static void *enum_map_start(struct seq_file *m, loff_t *pos) +{ + union trace_enum_map_item *v; + loff_t l = 0; + + mutex_lock(&trace_enum_mutex); + + v = trace_enum_maps; + if (v) + v++; + + while (v && l < *pos) { + v = enum_map_next(m, v, &l); + } + + return v; +} + +static void enum_map_stop(struct seq_file *m, void *v) +{ + mutex_unlock(&trace_enum_mutex); +} + +static int enum_map_show(struct seq_file *m, void *v) +{ + union trace_enum_map_item *ptr = v; + + seq_printf(m, "%s %ld (%s)\n", + ptr->map.enum_string, ptr->map.enum_value, + ptr->map.system); + + return 0; +} + +static const struct seq_operations tracing_enum_map_seq_ops = { + .start = enum_map_start, + .next = enum_map_next, + .stop = enum_map_stop, + .show = enum_map_show, +}; + +static int tracing_enum_map_open(struct inode *inode, struct file *filp) +{ + if (tracing_disabled) + return -ENODEV; + + return seq_open(filp, &tracing_enum_map_seq_ops); +} + +static const struct file_operations tracing_enum_map_fops = { + .open = tracing_enum_map_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, +}; + +static inline union trace_enum_map_item * +trace_enum_jmp_to_tail(union trace_enum_map_item *ptr) +{ + /* Return tail of array given the head */ + return ptr + ptr->head.length + 1; +} + +static void +trace_insert_enum_map_file(struct module *mod, struct trace_enum_map **start, + int len) +{ + struct trace_enum_map **stop; + struct trace_enum_map **map; + union trace_enum_map_item *map_array; + union trace_enum_map_item *ptr; + + stop = start + len; + + /* + * The trace_enum_maps contains the map plus a head and tail item, + * where the head holds the module and length of array, and the + * tail holds a pointer to the next list. + */ + map_array = kmalloc(sizeof(*map_array) * (len + 2), GFP_KERNEL); + if (!map_array) { + pr_warning("Unable to allocate trace enum mapping\n"); + return; + } + + mutex_lock(&trace_enum_mutex); + + if (!trace_enum_maps) + trace_enum_maps = map_array; + else { + ptr = trace_enum_maps; + for (;;) { + ptr = trace_enum_jmp_to_tail(ptr); + if (!ptr->tail.next) + break; + ptr = ptr->tail.next; + + } + ptr->tail.next = map_array; + } + map_array->head.mod = mod; + map_array->head.length = len; + map_array++; + + for (map = start; (unsigned long)map < (unsigned long)stop; map++) { + map_array->map = **map; + map_array++; + } + memset(map_array, 0, sizeof(*map_array)); + + mutex_unlock(&trace_enum_mutex); +} + +static void trace_create_enum_file(struct dentry *d_tracer) +{ + trace_create_file("enum_map", 0444, d_tracer, + NULL, &tracing_enum_map_fops); +} + +#else /* CONFIG_TRACE_ENUM_MAP_FILE */ +static inline void trace_create_enum_file(struct dentry *d_tracer) { } +static inline void trace_insert_enum_map_file(struct module *mod, + struct trace_enum_map **start, int len) { } +#endif /* !CONFIG_TRACE_ENUM_MAP_FILE */ + +static void trace_insert_enum_map(struct module *mod, + struct trace_enum_map **start, int len) +{ + struct trace_enum_map **map; + + if (len <= 0) + return; + + map = start; + + trace_event_enum_update(map, len); + + trace_insert_enum_map_file(mod, start, len); +} + +static ssize_t +tracing_set_trace_read(struct file *filp, char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + struct trace_array *tr = filp->private_data; + char buf[MAX_TRACER_SIZE+2]; + int r; + + mutex_lock(&trace_types_lock); + r = sprintf(buf, "%s\n", tr->current_trace->name); + mutex_unlock(&trace_types_lock); + + return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); +} + +int tracer_init(struct tracer *t, struct trace_array *tr) +{ + tracing_reset_online_cpus(&tr->trace_buffer); + return t->init(tr); +} + +static void set_buffer_entries(struct trace_buffer *buf, unsigned long val) +{ + int cpu; + + for_each_tracing_cpu(cpu) + per_cpu_ptr(buf->data, cpu)->entries = val; +} + +#ifdef CONFIG_TRACER_MAX_TRACE +/* resize @tr's buffer to the size of @size_tr's entries */ +static int resize_buffer_duplicate_size(struct trace_buffer *trace_buf, + struct trace_buffer *size_buf, int cpu_id) +{ + int cpu, ret = 0; + + if (cpu_id == RING_BUFFER_ALL_CPUS) { + for_each_tracing_cpu(cpu) { + ret = ring_buffer_resize(trace_buf->buffer, + per_cpu_ptr(size_buf->data, cpu)->entries, cpu); + if (ret < 0) + break; + per_cpu_ptr(trace_buf->data, cpu)->entries = + per_cpu_ptr(size_buf->data, cpu)->entries; + } + } else { + ret = ring_buffer_resize(trace_buf->buffer, + per_cpu_ptr(size_buf->data, cpu_id)->entries, cpu_id); + if (ret == 0) + per_cpu_ptr(trace_buf->data, cpu_id)->entries = + per_cpu_ptr(size_buf->data, cpu_id)->entries; + } + + return ret; +} +#endif /* CONFIG_TRACER_MAX_TRACE */ + +static int __tracing_resize_ring_buffer(struct trace_array *tr, + unsigned long size, int cpu) +{ + int ret; + + /* + * If kernel or user changes the size of the ring buffer + * we use the size that was given, and we can forget about + * expanding it later. + */ + ring_buffer_expanded = true; + + /* May be called before buffers are initialized */ + if (!tr->trace_buffer.buffer) + return 0; + + ret = ring_buffer_resize(tr->trace_buffer.buffer, size, cpu); + if (ret < 0) + return ret; + +#ifdef CONFIG_TRACER_MAX_TRACE + if (!(tr->flags & TRACE_ARRAY_FL_GLOBAL) || + !tr->current_trace->use_max_tr) + goto out; + + ret = ring_buffer_resize(tr->max_buffer.buffer, size, cpu); + if (ret < 0) { + int r = resize_buffer_duplicate_size(&tr->trace_buffer, + &tr->trace_buffer, cpu); + if (r < 0) { + /* + * AARGH! We are left with different + * size max buffer!!!! + * The max buffer is our "snapshot" buffer. + * When a tracer needs a snapshot (one of the + * latency tracers), it swaps the max buffer + * with the saved snap shot. We succeeded to + * update the size of the main buffer, but failed to + * update the size of the max buffer. But when we tried + * to reset the main buffer to the original size, we + * failed there too. This is very unlikely to + * happen, but if it does, warn and kill all + * tracing. + */ + WARN_ON(1); + tracing_disabled = 1; + } + return ret; + } + + if (cpu == RING_BUFFER_ALL_CPUS) + set_buffer_entries(&tr->max_buffer, size); + else + per_cpu_ptr(tr->max_buffer.data, cpu)->entries = size; + + out: +#endif /* CONFIG_TRACER_MAX_TRACE */ + + if (cpu == RING_BUFFER_ALL_CPUS) + set_buffer_entries(&tr->trace_buffer, size); + else + per_cpu_ptr(tr->trace_buffer.data, cpu)->entries = size; + + return ret; +} + +static ssize_t tracing_resize_ring_buffer(struct trace_array *tr, + unsigned long size, int cpu_id) +{ + int ret = size; + + mutex_lock(&trace_types_lock); + + if (cpu_id != RING_BUFFER_ALL_CPUS) { + /* make sure, this cpu is enabled in the mask */ + if (!cpumask_test_cpu(cpu_id, tracing_buffer_mask)) { + ret = -EINVAL; + goto out; + } + } + + ret = __tracing_resize_ring_buffer(tr, size, cpu_id); + if (ret < 0) + ret = -ENOMEM; + +out: + mutex_unlock(&trace_types_lock); + + return ret; +} + + +/** + * tracing_update_buffers - used by tracing facility to expand ring buffers + * + * To save on memory when the tracing is never used on a system with it + * configured in. The ring buffers are set to a minimum size. But once + * a user starts to use the tracing facility, then they need to grow + * to their default size. + * + * This function is to be called when a tracer is about to be used. + */ +int tracing_update_buffers(void) +{ + int ret = 0; + + mutex_lock(&trace_types_lock); + if (!ring_buffer_expanded) + ret = __tracing_resize_ring_buffer(&global_trace, trace_buf_size, + RING_BUFFER_ALL_CPUS); + mutex_unlock(&trace_types_lock); + + return ret; +} + +struct trace_option_dentry; + +static struct trace_option_dentry * +create_trace_option_files(struct trace_array *tr, struct tracer *tracer); + +static void +destroy_trace_option_files(struct trace_option_dentry *topts); + +/* + * Used to clear out the tracer before deletion of an instance. + * Must have trace_types_lock held. + */ +static void tracing_set_nop(struct trace_array *tr) +{ + if (tr->current_trace == &nop_trace) + return; + + tr->current_trace->enabled--; + + if (tr->current_trace->reset) + tr->current_trace->reset(tr); + + tr->current_trace = &nop_trace; +} + +static void update_tracer_options(struct trace_array *tr, struct tracer *t) +{ + static struct trace_option_dentry *topts; + + /* Only enable if the directory has been created already. */ + if (!tr->dir) + return; + + /* Currently, only the top instance has options */ + if (!(tr->flags & TRACE_ARRAY_FL_GLOBAL)) + return; + + destroy_trace_option_files(topts); + topts = create_trace_option_files(tr, t); +} + +static int tracing_set_tracer(struct trace_array *tr, const char *buf) +{ + struct tracer *t; +#ifdef CONFIG_TRACER_MAX_TRACE + bool had_max_tr; +#endif + int ret = 0; + + mutex_lock(&trace_types_lock); + + if (!ring_buffer_expanded) { + ret = __tracing_resize_ring_buffer(tr, trace_buf_size, + RING_BUFFER_ALL_CPUS); + if (ret < 0) + goto out; + ret = 0; + } + + for (t = trace_types; t; t = t->next) { + if (strcmp(t->name, buf) == 0) + break; + } + if (!t) { + ret = -EINVAL; + goto out; + } + if (t == tr->current_trace) + goto out; + + /* Some tracers are only allowed for the top level buffer */ + if (!trace_ok_for_array(t, tr)) { + ret = -EINVAL; + goto out; + } + + /* If trace pipe files are being read, we can't change the tracer */ + if (tr->current_trace->ref) { + ret = -EBUSY; + goto out; + } + + trace_branch_disable(); + + tr->current_trace->enabled--; + + if (tr->current_trace->reset) + tr->current_trace->reset(tr); + + /* Current trace needs to be nop_trace before synchronize_sched */ + tr->current_trace = &nop_trace; + +#ifdef CONFIG_TRACER_MAX_TRACE + had_max_tr = tr->allocated_snapshot; + + if (had_max_tr && !t->use_max_tr) { + /* + * We need to make sure that the update_max_tr sees that + * current_trace changed to nop_trace to keep it from + * swapping the buffers after we resize it. + * The update_max_tr is called from interrupts disabled + * so a synchronized_sched() is sufficient. + */ + synchronize_sched(); + free_snapshot(tr); + } +#endif + update_tracer_options(tr, t); + +#ifdef CONFIG_TRACER_MAX_TRACE + if (t->use_max_tr && !had_max_tr) { + ret = alloc_snapshot(tr); + if (ret < 0) + goto out; + } +#endif + + if (t->init) { + ret = tracer_init(t, tr); + if (ret) + goto out; + } + + tr->current_trace = t; + tr->current_trace->enabled++; + trace_branch_enable(tr); + out: + mutex_unlock(&trace_types_lock); + + return ret; +} + +static ssize_t +tracing_set_trace_write(struct file *filp, const char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + struct trace_array *tr = filp->private_data; + char buf[MAX_TRACER_SIZE+1]; + int i; + size_t ret; + int err; + + ret = cnt; + + if (cnt > MAX_TRACER_SIZE) + cnt = MAX_TRACER_SIZE; + + if (copy_from_user(&buf, ubuf, cnt)) + return -EFAULT; + + buf[cnt] = 0; + + /* strip ending whitespace. */ + for (i = cnt - 1; i > 0 && isspace(buf[i]); i--) + buf[i] = 0; + + err = tracing_set_tracer(tr, buf); + if (err) + return err; + + *ppos += ret; + + return ret; +} + +static ssize_t +tracing_nsecs_read(unsigned long *ptr, char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + char buf[64]; + int r; + + r = snprintf(buf, sizeof(buf), "%ld\n", + *ptr == (unsigned long)-1 ? -1 : nsecs_to_usecs(*ptr)); + if (r > sizeof(buf)) + r = sizeof(buf); + return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); +} + +static ssize_t +tracing_nsecs_write(unsigned long *ptr, const char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + unsigned long val; + int ret; + + ret = kstrtoul_from_user(ubuf, cnt, 10, &val); + if (ret) + return ret; + + *ptr = val * 1000; + + return cnt; +} + +static ssize_t +tracing_thresh_read(struct file *filp, char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + return tracing_nsecs_read(&tracing_thresh, ubuf, cnt, ppos); +} + +static ssize_t +tracing_thresh_write(struct file *filp, const char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + struct trace_array *tr = filp->private_data; + int ret; + + mutex_lock(&trace_types_lock); + ret = tracing_nsecs_write(&tracing_thresh, ubuf, cnt, ppos); + if (ret < 0) + goto out; + + if (tr->current_trace->update_thresh) { + ret = tr->current_trace->update_thresh(tr); + if (ret < 0) + goto out; + } + + ret = cnt; +out: + mutex_unlock(&trace_types_lock); + + return ret; +} + +static ssize_t +tracing_max_lat_read(struct file *filp, char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + return tracing_nsecs_read(filp->private_data, ubuf, cnt, ppos); +} + +static ssize_t +tracing_max_lat_write(struct file *filp, const char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + return tracing_nsecs_write(filp->private_data, ubuf, cnt, ppos); +} + +static int tracing_open_pipe(struct inode *inode, struct file *filp) +{ + struct trace_array *tr = inode->i_private; + struct trace_iterator *iter; + int ret = 0; + + if (tracing_disabled) + return -ENODEV; + + if (trace_array_get(tr) < 0) + return -ENODEV; + + mutex_lock(&trace_types_lock); + + /* create a buffer to store the information to pass to userspace */ + iter = kzalloc(sizeof(*iter), GFP_KERNEL); + if (!iter) { + ret = -ENOMEM; + __trace_array_put(tr); + goto out; + } + + trace_seq_init(&iter->seq); + iter->trace = tr->current_trace; + + if (!alloc_cpumask_var(&iter->started, GFP_KERNEL)) { + ret = -ENOMEM; + goto fail; + } + + /* trace pipe does not show start of buffer */ + cpumask_setall(iter->started); + + if (trace_flags & TRACE_ITER_LATENCY_FMT) + iter->iter_flags |= TRACE_FILE_LAT_FMT; + + /* Output in nanoseconds only if we are using a clock in nanoseconds. */ + if (trace_clocks[tr->clock_id].in_ns) + iter->iter_flags |= TRACE_FILE_TIME_IN_NS; + + iter->tr = tr; + iter->trace_buffer = &tr->trace_buffer; + iter->cpu_file = tracing_get_cpu(inode); + mutex_init(&iter->mutex); + filp->private_data = iter; + + if (iter->trace->pipe_open) + iter->trace->pipe_open(iter); + + nonseekable_open(inode, filp); + + tr->current_trace->ref++; +out: + mutex_unlock(&trace_types_lock); + return ret; + +fail: + kfree(iter->trace); + kfree(iter); + __trace_array_put(tr); + mutex_unlock(&trace_types_lock); + return ret; +} + +static int tracing_release_pipe(struct inode *inode, struct file *file) +{ + struct trace_iterator *iter = file->private_data; + struct trace_array *tr = inode->i_private; + + mutex_lock(&trace_types_lock); + + tr->current_trace->ref--; + + if (iter->trace->pipe_close) + iter->trace->pipe_close(iter); + + mutex_unlock(&trace_types_lock); + + free_cpumask_var(iter->started); + mutex_destroy(&iter->mutex); + kfree(iter); + + trace_array_put(tr); + + return 0; +} + +static unsigned int +trace_poll(struct trace_iterator *iter, struct file *filp, poll_table *poll_table) +{ + /* Iterators are static, they should be filled or empty */ + if (trace_buffer_iter(iter, iter->cpu_file)) + return POLLIN | POLLRDNORM; + + if (trace_flags & TRACE_ITER_BLOCK) + /* + * Always select as readable when in blocking mode + */ + return POLLIN | POLLRDNORM; + else + return ring_buffer_poll_wait(iter->trace_buffer->buffer, iter->cpu_file, + filp, poll_table); +} + +static unsigned int +tracing_poll_pipe(struct file *filp, poll_table *poll_table) +{ + struct trace_iterator *iter = filp->private_data; + + return trace_poll(iter, filp, poll_table); +} + +/* Must be called with iter->mutex held. */ +static int tracing_wait_pipe(struct file *filp) +{ + struct trace_iterator *iter = filp->private_data; + int ret; + + while (trace_empty(iter)) { + + if ((filp->f_flags & O_NONBLOCK)) { + return -EAGAIN; + } + + /* + * We block until we read something and tracing is disabled. + * We still block if tracing is disabled, but we have never + * read anything. This allows a user to cat this file, and + * then enable tracing. But after we have read something, + * we give an EOF when tracing is again disabled. + * + * iter->pos will be 0 if we haven't read anything. + */ + if (!tracing_is_on() && iter->pos) + break; + + mutex_unlock(&iter->mutex); + + ret = wait_on_pipe(iter, false); + + mutex_lock(&iter->mutex); + + if (ret) + return ret; + } + + return 1; +} + +/* + * Consumer reader. + */ +static ssize_t +tracing_read_pipe(struct file *filp, char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + struct trace_iterator *iter = filp->private_data; + ssize_t sret; + + /* return any leftover data */ + sret = trace_seq_to_user(&iter->seq, ubuf, cnt); + if (sret != -EBUSY) + return sret; + + trace_seq_init(&iter->seq); + + /* + * Avoid more than one consumer on a single file descriptor + * This is just a matter of traces coherency, the ring buffer itself + * is protected. + */ + mutex_lock(&iter->mutex); + if (iter->trace->read) { + sret = iter->trace->read(iter, filp, ubuf, cnt, ppos); + if (sret) + goto out; + } + +waitagain: + sret = tracing_wait_pipe(filp); + if (sret <= 0) + goto out; + + /* stop when tracing is finished */ + if (trace_empty(iter)) { + sret = 0; + goto out; + } + + if (cnt >= PAGE_SIZE) + cnt = PAGE_SIZE - 1; + + /* reset all but tr, trace, and overruns */ + memset(&iter->seq, 0, + sizeof(struct trace_iterator) - + offsetof(struct trace_iterator, seq)); + cpumask_clear(iter->started); + iter->pos = -1; + + trace_event_read_lock(); + trace_access_lock(iter->cpu_file); + while (trace_find_next_entry_inc(iter) != NULL) { + enum print_line_t ret; + int save_len = iter->seq.seq.len; + + ret = print_trace_line(iter); + if (ret == TRACE_TYPE_PARTIAL_LINE) { + /* don't print partial lines */ + iter->seq.seq.len = save_len; + break; + } + if (ret != TRACE_TYPE_NO_CONSUME) + trace_consume(iter); + + if (trace_seq_used(&iter->seq) >= cnt) + break; + + /* + * Setting the full flag means we reached the trace_seq buffer + * size and we should leave by partial output condition above. + * One of the trace_seq_* functions is not used properly. + */ + WARN_ONCE(iter->seq.full, "full flag set for trace type %d", + iter->ent->type); + } + trace_access_unlock(iter->cpu_file); + trace_event_read_unlock(); + + /* Now copy what we have to the user */ + sret = trace_seq_to_user(&iter->seq, ubuf, cnt); + if (iter->seq.seq.readpos >= trace_seq_used(&iter->seq)) + trace_seq_init(&iter->seq); + + /* + * If there was nothing to send to user, in spite of consuming trace + * entries, go back to wait for more entries. + */ + if (sret == -EBUSY) + goto waitagain; + +out: + mutex_unlock(&iter->mutex); + + return sret; +} + +static void tracing_spd_release_pipe(struct splice_pipe_desc *spd, + unsigned int idx) +{ + __free_page(spd->pages[idx]); +} + +static const struct pipe_buf_operations tracing_pipe_buf_ops = { + .can_merge = 0, + .confirm = generic_pipe_buf_confirm, + .release = generic_pipe_buf_release, + .steal = generic_pipe_buf_steal, + .get = generic_pipe_buf_get, +}; + +static size_t +tracing_fill_pipe_page(size_t rem, struct trace_iterator *iter) +{ + size_t count; + int save_len; + int ret; + + /* Seq buffer is page-sized, exactly what we need. */ + for (;;) { + save_len = iter->seq.seq.len; + ret = print_trace_line(iter); + + if (trace_seq_has_overflowed(&iter->seq)) { + iter->seq.seq.len = save_len; + break; + } + + /* + * This should not be hit, because it should only + * be set if the iter->seq overflowed. But check it + * anyway to be safe. + */ + if (ret == TRACE_TYPE_PARTIAL_LINE) { + iter->seq.seq.len = save_len; + break; + } + + count = trace_seq_used(&iter->seq) - save_len; + if (rem < count) { + rem = 0; + iter->seq.seq.len = save_len; + break; + } + + if (ret != TRACE_TYPE_NO_CONSUME) + trace_consume(iter); + rem -= count; + if (!trace_find_next_entry_inc(iter)) { + rem = 0; + iter->ent = NULL; + break; + } + } + + return rem; +} + +static ssize_t tracing_splice_read_pipe(struct file *filp, + loff_t *ppos, + struct pipe_inode_info *pipe, + size_t len, + unsigned int flags) +{ + struct page *pages_def[PIPE_DEF_BUFFERS]; + struct partial_page partial_def[PIPE_DEF_BUFFERS]; + struct trace_iterator *iter = filp->private_data; + struct splice_pipe_desc spd = { + .pages = pages_def, + .partial = partial_def, + .nr_pages = 0, /* This gets updated below. */ + .nr_pages_max = PIPE_DEF_BUFFERS, + .flags = flags, + .ops = &tracing_pipe_buf_ops, + .spd_release = tracing_spd_release_pipe, + }; + ssize_t ret; + size_t rem; + unsigned int i; + + if (splice_grow_spd(pipe, &spd)) + return -ENOMEM; + + mutex_lock(&iter->mutex); + + if (iter->trace->splice_read) { + ret = iter->trace->splice_read(iter, filp, + ppos, pipe, len, flags); + if (ret) + goto out_err; + } + + ret = tracing_wait_pipe(filp); + if (ret <= 0) + goto out_err; + + if (!iter->ent && !trace_find_next_entry_inc(iter)) { + ret = -EFAULT; + goto out_err; + } + + trace_event_read_lock(); + trace_access_lock(iter->cpu_file); + + /* Fill as many pages as possible. */ + for (i = 0, rem = len; i < spd.nr_pages_max && rem; i++) { + spd.pages[i] = alloc_page(GFP_KERNEL); + if (!spd.pages[i]) + break; + + rem = tracing_fill_pipe_page(rem, iter); + + /* Copy the data into the page, so we can start over. */ + ret = trace_seq_to_buffer(&iter->seq, + page_address(spd.pages[i]), + trace_seq_used(&iter->seq)); + if (ret < 0) { + __free_page(spd.pages[i]); + break; + } + spd.partial[i].offset = 0; + spd.partial[i].len = trace_seq_used(&iter->seq); + + trace_seq_init(&iter->seq); + } + + trace_access_unlock(iter->cpu_file); + trace_event_read_unlock(); + mutex_unlock(&iter->mutex); + + spd.nr_pages = i; + + ret = splice_to_pipe(pipe, &spd); +out: + splice_shrink_spd(&spd); + return ret; + +out_err: + mutex_unlock(&iter->mutex); + goto out; +} + +static ssize_t +tracing_entries_read(struct file *filp, char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + struct inode *inode = file_inode(filp); + struct trace_array *tr = inode->i_private; + int cpu = tracing_get_cpu(inode); + char buf[64]; + int r = 0; + ssize_t ret; + + mutex_lock(&trace_types_lock); + + if (cpu == RING_BUFFER_ALL_CPUS) { + int cpu, buf_size_same; + unsigned long size; + + size = 0; + buf_size_same = 1; + /* check if all cpu sizes are same */ + for_each_tracing_cpu(cpu) { + /* fill in the size from first enabled cpu */ + if (size == 0) + size = per_cpu_ptr(tr->trace_buffer.data, cpu)->entries; + if (size != per_cpu_ptr(tr->trace_buffer.data, cpu)->entries) { + buf_size_same = 0; + break; + } + } + + if (buf_size_same) { + if (!ring_buffer_expanded) + r = sprintf(buf, "%lu (expanded: %lu)\n", + size >> 10, + trace_buf_size >> 10); + else + r = sprintf(buf, "%lu\n", size >> 10); + } else + r = sprintf(buf, "X\n"); + } else + r = sprintf(buf, "%lu\n", per_cpu_ptr(tr->trace_buffer.data, cpu)->entries >> 10); + + mutex_unlock(&trace_types_lock); + + ret = simple_read_from_buffer(ubuf, cnt, ppos, buf, r); + return ret; +} + +static ssize_t +tracing_entries_write(struct file *filp, const char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + struct inode *inode = file_inode(filp); + struct trace_array *tr = inode->i_private; + unsigned long val; + int ret; + + ret = kstrtoul_from_user(ubuf, cnt, 10, &val); + if (ret) + return ret; + + /* must have at least 1 entry */ + if (!val) + return -EINVAL; + + /* value is in KB */ + val <<= 10; + ret = tracing_resize_ring_buffer(tr, val, tracing_get_cpu(inode)); + if (ret < 0) + return ret; + + *ppos += cnt; + + return cnt; +} + +static ssize_t +tracing_total_entries_read(struct file *filp, char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + struct trace_array *tr = filp->private_data; + char buf[64]; + int r, cpu; + unsigned long size = 0, expanded_size = 0; + + mutex_lock(&trace_types_lock); + for_each_tracing_cpu(cpu) { + size += per_cpu_ptr(tr->trace_buffer.data, cpu)->entries >> 10; + if (!ring_buffer_expanded) + expanded_size += trace_buf_size >> 10; + } + if (ring_buffer_expanded) + r = sprintf(buf, "%lu\n", size); + else + r = sprintf(buf, "%lu (expanded: %lu)\n", size, expanded_size); + mutex_unlock(&trace_types_lock); + + return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); +} + +static ssize_t +tracing_free_buffer_write(struct file *filp, const char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + /* + * There is no need to read what the user has written, this function + * is just to make sure that there is no error when "echo" is used + */ + + *ppos += cnt; + + return cnt; +} + +static int +tracing_free_buffer_release(struct inode *inode, struct file *filp) +{ + struct trace_array *tr = inode->i_private; + + /* disable tracing ? */ + if (trace_flags & TRACE_ITER_STOP_ON_FREE) + tracer_tracing_off(tr); + /* resize the ring buffer to 0 */ + tracing_resize_ring_buffer(tr, 0, RING_BUFFER_ALL_CPUS); + + trace_array_put(tr); + + return 0; +} + +static ssize_t +tracing_mark_write(struct file *filp, const char __user *ubuf, + size_t cnt, loff_t *fpos) +{ + unsigned long addr = (unsigned long)ubuf; + struct trace_array *tr = filp->private_data; + struct ring_buffer_event *event; + struct ring_buffer *buffer; + struct print_entry *entry; + unsigned long irq_flags; + struct page *pages[2]; + void *map_page[2]; + int nr_pages = 1; + ssize_t written; + int offset; + int size; + int len; + int ret; + int i; + + if (tracing_disabled) + return -EINVAL; + + if (!(trace_flags & TRACE_ITER_MARKERS)) + return -EINVAL; + + if (cnt > TRACE_BUF_SIZE) + cnt = TRACE_BUF_SIZE; + + /* + * Userspace is injecting traces into the kernel trace buffer. + * We want to be as non intrusive as possible. + * To do so, we do not want to allocate any special buffers + * or take any locks, but instead write the userspace data + * straight into the ring buffer. + * + * First we need to pin the userspace buffer into memory, + * which, most likely it is, because it just referenced it. + * But there's no guarantee that it is. By using get_user_pages_fast() + * and kmap_atomic/kunmap_atomic() we can get access to the + * pages directly. We then write the data directly into the + * ring buffer. + */ + BUILD_BUG_ON(TRACE_BUF_SIZE >= PAGE_SIZE); + + /* check if we cross pages */ + if ((addr & PAGE_MASK) != ((addr + cnt) & PAGE_MASK)) + nr_pages = 2; + + offset = addr & (PAGE_SIZE - 1); + addr &= PAGE_MASK; + + ret = get_user_pages_fast(addr, nr_pages, 0, pages); + if (ret < nr_pages) { + while (--ret >= 0) + put_page(pages[ret]); + written = -EFAULT; + goto out; + } + + for (i = 0; i < nr_pages; i++) + map_page[i] = kmap_atomic(pages[i]); + + local_save_flags(irq_flags); + size = sizeof(*entry) + cnt + 2; /* possible \n added */ + buffer = tr->trace_buffer.buffer; + event = trace_buffer_lock_reserve(buffer, TRACE_PRINT, size, + irq_flags, preempt_count()); + if (!event) { + /* Ring buffer disabled, return as if not open for write */ + written = -EBADF; + goto out_unlock; + } + + entry = ring_buffer_event_data(event); + entry->ip = _THIS_IP_; + + if (nr_pages == 2) { + len = PAGE_SIZE - offset; + memcpy(&entry->buf, map_page[0] + offset, len); + memcpy(&entry->buf[len], map_page[1], cnt - len); + } else + memcpy(&entry->buf, map_page[0] + offset, cnt); + + if (entry->buf[cnt - 1] != '\n') { + entry->buf[cnt] = '\n'; + entry->buf[cnt + 1] = '\0'; + } else + entry->buf[cnt] = '\0'; + + __buffer_unlock_commit(buffer, event); + + written = cnt; + + *fpos += written; + + out_unlock: + for (i = nr_pages - 1; i >= 0; i--) { + kunmap_atomic(map_page[i]); + put_page(pages[i]); + } + out: + return written; +} + +static int tracing_clock_show(struct seq_file *m, void *v) +{ + struct trace_array *tr = m->private; + int i; + + for (i = 0; i < ARRAY_SIZE(trace_clocks); i++) + seq_printf(m, + "%s%s%s%s", i ? " " : "", + i == tr->clock_id ? "[" : "", trace_clocks[i].name, + i == tr->clock_id ? "]" : ""); + seq_putc(m, '\n'); + + return 0; +} + +static int tracing_set_clock(struct trace_array *tr, const char *clockstr) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(trace_clocks); i++) { + if (strcmp(trace_clocks[i].name, clockstr) == 0) + break; + } + if (i == ARRAY_SIZE(trace_clocks)) + return -EINVAL; + + mutex_lock(&trace_types_lock); + + tr->clock_id = i; + + ring_buffer_set_clock(tr->trace_buffer.buffer, trace_clocks[i].func); + + /* + * New clock may not be consistent with the previous clock. + * Reset the buffer so that it doesn't have incomparable timestamps. + */ + tracing_reset_online_cpus(&tr->trace_buffer); + +#ifdef CONFIG_TRACER_MAX_TRACE + if (tr->flags & TRACE_ARRAY_FL_GLOBAL && tr->max_buffer.buffer) + ring_buffer_set_clock(tr->max_buffer.buffer, trace_clocks[i].func); + tracing_reset_online_cpus(&tr->max_buffer); +#endif + + mutex_unlock(&trace_types_lock); + + return 0; +} + +static ssize_t tracing_clock_write(struct file *filp, const char __user *ubuf, + size_t cnt, loff_t *fpos) +{ + struct seq_file *m = filp->private_data; + struct trace_array *tr = m->private; + char buf[64]; + const char *clockstr; + int ret; + + if (cnt >= sizeof(buf)) + return -EINVAL; + + if (copy_from_user(&buf, ubuf, cnt)) + return -EFAULT; + + buf[cnt] = 0; + + clockstr = strstrip(buf); + + ret = tracing_set_clock(tr, clockstr); + if (ret) + return ret; + + *fpos += cnt; + + return cnt; +} + +static int tracing_clock_open(struct inode *inode, struct file *file) +{ + struct trace_array *tr = inode->i_private; + int ret; + + if (tracing_disabled) + return -ENODEV; + + if (trace_array_get(tr)) + return -ENODEV; + + ret = single_open(file, tracing_clock_show, inode->i_private); + if (ret < 0) + trace_array_put(tr); + + return ret; +} + +struct ftrace_buffer_info { + struct trace_iterator iter; + void *spare; + unsigned int read; +}; + +#ifdef CONFIG_TRACER_SNAPSHOT +static int tracing_snapshot_open(struct inode *inode, struct file *file) +{ + struct trace_array *tr = inode->i_private; + struct trace_iterator *iter; + struct seq_file *m; + int ret = 0; + + if (trace_array_get(tr) < 0) + return -ENODEV; + + if (file->f_mode & FMODE_READ) { + iter = __tracing_open(inode, file, true); + if (IS_ERR(iter)) + ret = PTR_ERR(iter); + } else { + /* Writes still need the seq_file to hold the private data */ + ret = -ENOMEM; + m = kzalloc(sizeof(*m), GFP_KERNEL); + if (!m) + goto out; + iter = kzalloc(sizeof(*iter), GFP_KERNEL); + if (!iter) { + kfree(m); + goto out; + } + ret = 0; + + iter->tr = tr; + iter->trace_buffer = &tr->max_buffer; + iter->cpu_file = tracing_get_cpu(inode); + m->private = iter; + file->private_data = m; + } +out: + if (ret < 0) + trace_array_put(tr); + + return ret; +} + +static ssize_t +tracing_snapshot_write(struct file *filp, const char __user *ubuf, size_t cnt, + loff_t *ppos) +{ + struct seq_file *m = filp->private_data; + struct trace_iterator *iter = m->private; + struct trace_array *tr = iter->tr; + unsigned long val; + int ret; + + ret = tracing_update_buffers(); + if (ret < 0) + return ret; + + ret = kstrtoul_from_user(ubuf, cnt, 10, &val); + if (ret) + return ret; + + mutex_lock(&trace_types_lock); + + if (tr->current_trace->use_max_tr) { + ret = -EBUSY; + goto out; + } + + switch (val) { + case 0: + if (iter->cpu_file != RING_BUFFER_ALL_CPUS) { + ret = -EINVAL; + break; + } + if (tr->allocated_snapshot) + free_snapshot(tr); + break; + case 1: +/* Only allow per-cpu swap if the ring buffer supports it */ +#ifndef CONFIG_RING_BUFFER_ALLOW_SWAP + if (iter->cpu_file != RING_BUFFER_ALL_CPUS) { + ret = -EINVAL; + break; + } +#endif + if (!tr->allocated_snapshot) { + ret = alloc_snapshot(tr); + if (ret < 0) + break; + } + local_irq_disable(); + /* Now, we're going to swap */ + if (iter->cpu_file == RING_BUFFER_ALL_CPUS) + update_max_tr(tr, current, smp_processor_id()); + else + update_max_tr_single(tr, current, iter->cpu_file); + local_irq_enable(); + break; + default: + if (tr->allocated_snapshot) { + if (iter->cpu_file == RING_BUFFER_ALL_CPUS) + tracing_reset_online_cpus(&tr->max_buffer); + else + tracing_reset(&tr->max_buffer, iter->cpu_file); + } + break; + } + + if (ret >= 0) { + *ppos += cnt; + ret = cnt; + } +out: + mutex_unlock(&trace_types_lock); + return ret; +} + +static int tracing_snapshot_release(struct inode *inode, struct file *file) +{ + struct seq_file *m = file->private_data; + int ret; + + ret = tracing_release(inode, file); + + if (file->f_mode & FMODE_READ) + return ret; + + /* If write only, the seq_file is just a stub */ + if (m) + kfree(m->private); + kfree(m); + + return 0; +} + +static int tracing_buffers_open(struct inode *inode, struct file *filp); +static ssize_t tracing_buffers_read(struct file *filp, char __user *ubuf, + size_t count, loff_t *ppos); +static int tracing_buffers_release(struct inode *inode, struct file *file); +static ssize_t tracing_buffers_splice_read(struct file *file, loff_t *ppos, + struct pipe_inode_info *pipe, size_t len, unsigned int flags); + +static int snapshot_raw_open(struct inode *inode, struct file *filp) +{ + struct ftrace_buffer_info *info; + int ret; + + ret = tracing_buffers_open(inode, filp); + if (ret < 0) + return ret; + + info = filp->private_data; + + if (info->iter.trace->use_max_tr) { + tracing_buffers_release(inode, filp); + return -EBUSY; + } + + info->iter.snapshot = true; + info->iter.trace_buffer = &info->iter.tr->max_buffer; + + return ret; +} + +#endif /* CONFIG_TRACER_SNAPSHOT */ + + +static const struct file_operations tracing_thresh_fops = { + .open = tracing_open_generic, + .read = tracing_thresh_read, + .write = tracing_thresh_write, + .llseek = generic_file_llseek, +}; + +static const struct file_operations tracing_max_lat_fops = { + .open = tracing_open_generic, + .read = tracing_max_lat_read, + .write = tracing_max_lat_write, + .llseek = generic_file_llseek, +}; + +static const struct file_operations set_tracer_fops = { + .open = tracing_open_generic, + .read = tracing_set_trace_read, + .write = tracing_set_trace_write, + .llseek = generic_file_llseek, +}; + +static const struct file_operations tracing_pipe_fops = { + .open = tracing_open_pipe, + .poll = tracing_poll_pipe, + .read = tracing_read_pipe, + .splice_read = tracing_splice_read_pipe, + .release = tracing_release_pipe, + .llseek = no_llseek, +}; + +static const struct file_operations tracing_entries_fops = { + .open = tracing_open_generic_tr, + .read = tracing_entries_read, + .write = tracing_entries_write, + .llseek = generic_file_llseek, + .release = tracing_release_generic_tr, +}; + +static const struct file_operations tracing_total_entries_fops = { + .open = tracing_open_generic_tr, + .read = tracing_total_entries_read, + .llseek = generic_file_llseek, + .release = tracing_release_generic_tr, +}; + +static const struct file_operations tracing_free_buffer_fops = { + .open = tracing_open_generic_tr, + .write = tracing_free_buffer_write, + .release = tracing_free_buffer_release, +}; + +static const struct file_operations tracing_mark_fops = { + .open = tracing_open_generic_tr, + .write = tracing_mark_write, + .llseek = generic_file_llseek, + .release = tracing_release_generic_tr, +}; + +static const struct file_operations trace_clock_fops = { + .open = tracing_clock_open, + .read = seq_read, + .llseek = seq_lseek, + .release = tracing_single_release_tr, + .write = tracing_clock_write, +}; + +#ifdef CONFIG_TRACER_SNAPSHOT +static const struct file_operations snapshot_fops = { + .open = tracing_snapshot_open, + .read = seq_read, + .write = tracing_snapshot_write, + .llseek = tracing_lseek, + .release = tracing_snapshot_release, +}; + +static const struct file_operations snapshot_raw_fops = { + .open = snapshot_raw_open, + .read = tracing_buffers_read, + .release = tracing_buffers_release, + .splice_read = tracing_buffers_splice_read, + .llseek = no_llseek, +}; + +#endif /* CONFIG_TRACER_SNAPSHOT */ + +static int tracing_buffers_open(struct inode *inode, struct file *filp) +{ + struct trace_array *tr = inode->i_private; + struct ftrace_buffer_info *info; + int ret; + + if (tracing_disabled) + return -ENODEV; + + if (trace_array_get(tr) < 0) + return -ENODEV; + + info = kzalloc(sizeof(*info), GFP_KERNEL); + if (!info) { + trace_array_put(tr); + return -ENOMEM; + } + + mutex_lock(&trace_types_lock); + + info->iter.tr = tr; + info->iter.cpu_file = tracing_get_cpu(inode); + info->iter.trace = tr->current_trace; + info->iter.trace_buffer = &tr->trace_buffer; + info->spare = NULL; + /* Force reading ring buffer for first read */ + info->read = (unsigned int)-1; + + filp->private_data = info; + + tr->current_trace->ref++; + + mutex_unlock(&trace_types_lock); + + ret = nonseekable_open(inode, filp); + if (ret < 0) + trace_array_put(tr); + + return ret; +} + +static unsigned int +tracing_buffers_poll(struct file *filp, poll_table *poll_table) +{ + struct ftrace_buffer_info *info = filp->private_data; + struct trace_iterator *iter = &info->iter; + + return trace_poll(iter, filp, poll_table); +} + +static ssize_t +tracing_buffers_read(struct file *filp, char __user *ubuf, + size_t count, loff_t *ppos) +{ + struct ftrace_buffer_info *info = filp->private_data; + struct trace_iterator *iter = &info->iter; + ssize_t ret; + ssize_t size; + + if (!count) + return 0; + +#ifdef CONFIG_TRACER_MAX_TRACE + if (iter->snapshot && iter->tr->current_trace->use_max_tr) + return -EBUSY; +#endif + + if (!info->spare) + info->spare = ring_buffer_alloc_read_page(iter->trace_buffer->buffer, + iter->cpu_file); + if (!info->spare) + return -ENOMEM; + + /* Do we have previous read data to read? */ + if (info->read < PAGE_SIZE) + goto read; + + again: + trace_access_lock(iter->cpu_file); + ret = ring_buffer_read_page(iter->trace_buffer->buffer, + &info->spare, + count, + iter->cpu_file, 0); + trace_access_unlock(iter->cpu_file); + + if (ret < 0) { + if (trace_empty(iter)) { + if ((filp->f_flags & O_NONBLOCK)) + return -EAGAIN; + + ret = wait_on_pipe(iter, false); + if (ret) + return ret; + + goto again; + } + return 0; + } + + info->read = 0; + read: + size = PAGE_SIZE - info->read; + if (size > count) + size = count; + + ret = copy_to_user(ubuf, info->spare + info->read, size); + if (ret == size) + return -EFAULT; + + size -= ret; + + *ppos += size; + info->read += size; + + return size; +} + +static int tracing_buffers_release(struct inode *inode, struct file *file) +{ + struct ftrace_buffer_info *info = file->private_data; + struct trace_iterator *iter = &info->iter; + + mutex_lock(&trace_types_lock); + + iter->tr->current_trace->ref--; + + __trace_array_put(iter->tr); + + if (info->spare) + ring_buffer_free_read_page(iter->trace_buffer->buffer, info->spare); + kfree(info); + + mutex_unlock(&trace_types_lock); + + return 0; +} + +struct buffer_ref { + struct ring_buffer *buffer; + void *page; + int ref; +}; + +static void buffer_pipe_buf_release(struct pipe_inode_info *pipe, + struct pipe_buffer *buf) +{ + struct buffer_ref *ref = (struct buffer_ref *)buf->private; + + if (--ref->ref) + return; + + ring_buffer_free_read_page(ref->buffer, ref->page); + kfree(ref); + buf->private = 0; +} + +static void buffer_pipe_buf_get(struct pipe_inode_info *pipe, + struct pipe_buffer *buf) +{ + struct buffer_ref *ref = (struct buffer_ref *)buf->private; + + ref->ref++; +} + +/* Pipe buffer operations for a buffer. */ +static const struct pipe_buf_operations buffer_pipe_buf_ops = { + .can_merge = 0, + .confirm = generic_pipe_buf_confirm, + .release = buffer_pipe_buf_release, + .steal = generic_pipe_buf_steal, + .get = buffer_pipe_buf_get, +}; + +/* + * Callback from splice_to_pipe(), if we need to release some pages + * at the end of the spd in case we error'ed out in filling the pipe. + */ +static void buffer_spd_release(struct splice_pipe_desc *spd, unsigned int i) +{ + struct buffer_ref *ref = + (struct buffer_ref *)spd->partial[i].private; + + if (--ref->ref) + return; + + ring_buffer_free_read_page(ref->buffer, ref->page); + kfree(ref); + spd->partial[i].private = 0; +} + +static ssize_t +tracing_buffers_splice_read(struct file *file, loff_t *ppos, + struct pipe_inode_info *pipe, size_t len, + unsigned int flags) +{ + struct ftrace_buffer_info *info = file->private_data; + struct trace_iterator *iter = &info->iter; + struct partial_page partial_def[PIPE_DEF_BUFFERS]; + struct page *pages_def[PIPE_DEF_BUFFERS]; + struct splice_pipe_desc spd = { + .pages = pages_def, + .partial = partial_def, + .nr_pages_max = PIPE_DEF_BUFFERS, + .flags = flags, + .ops = &buffer_pipe_buf_ops, + .spd_release = buffer_spd_release, + }; + struct buffer_ref *ref; + int entries, size, i; + ssize_t ret = 0; + +#ifdef CONFIG_TRACER_MAX_TRACE + if (iter->snapshot && iter->tr->current_trace->use_max_tr) + return -EBUSY; +#endif + + if (splice_grow_spd(pipe, &spd)) + return -ENOMEM; + + if (*ppos & (PAGE_SIZE - 1)) + return -EINVAL; + + if (len & (PAGE_SIZE - 1)) { + if (len < PAGE_SIZE) + return -EINVAL; + len &= PAGE_MASK; + } + + again: + trace_access_lock(iter->cpu_file); + entries = ring_buffer_entries_cpu(iter->trace_buffer->buffer, iter->cpu_file); + + for (i = 0; i < spd.nr_pages_max && len && entries; i++, len -= PAGE_SIZE) { + struct page *page; + int r; + + ref = kzalloc(sizeof(*ref), GFP_KERNEL); + if (!ref) { + ret = -ENOMEM; + break; + } + + ref->ref = 1; + ref->buffer = iter->trace_buffer->buffer; + ref->page = ring_buffer_alloc_read_page(ref->buffer, iter->cpu_file); + if (!ref->page) { + ret = -ENOMEM; + kfree(ref); + break; + } + + r = ring_buffer_read_page(ref->buffer, &ref->page, + len, iter->cpu_file, 1); + if (r < 0) { + ring_buffer_free_read_page(ref->buffer, ref->page); + kfree(ref); + break; + } + + /* + * zero out any left over data, this is going to + * user land. + */ + size = ring_buffer_page_len(ref->page); + if (size < PAGE_SIZE) + memset(ref->page + size, 0, PAGE_SIZE - size); + + page = virt_to_page(ref->page); + + spd.pages[i] = page; + spd.partial[i].len = PAGE_SIZE; + spd.partial[i].offset = 0; + spd.partial[i].private = (unsigned long)ref; + spd.nr_pages++; + *ppos += PAGE_SIZE; + + entries = ring_buffer_entries_cpu(iter->trace_buffer->buffer, iter->cpu_file); + } + + trace_access_unlock(iter->cpu_file); + spd.nr_pages = i; + + /* did we read anything? */ + if (!spd.nr_pages) { + if (ret) + return ret; + + if ((file->f_flags & O_NONBLOCK) || (flags & SPLICE_F_NONBLOCK)) + return -EAGAIN; + + ret = wait_on_pipe(iter, true); + if (ret) + return ret; + + goto again; + } + + ret = splice_to_pipe(pipe, &spd); + splice_shrink_spd(&spd); + + return ret; +} + +static const struct file_operations tracing_buffers_fops = { + .open = tracing_buffers_open, + .read = tracing_buffers_read, + .poll = tracing_buffers_poll, + .release = tracing_buffers_release, + .splice_read = tracing_buffers_splice_read, + .llseek = no_llseek, +}; + +static ssize_t +tracing_stats_read(struct file *filp, char __user *ubuf, + size_t count, loff_t *ppos) +{ + struct inode *inode = file_inode(filp); + struct trace_array *tr = inode->i_private; + struct trace_buffer *trace_buf = &tr->trace_buffer; + int cpu = tracing_get_cpu(inode); + struct trace_seq *s; + unsigned long cnt; + unsigned long long t; + unsigned long usec_rem; + + s = kmalloc(sizeof(*s), GFP_KERNEL); + if (!s) + return -ENOMEM; + + trace_seq_init(s); + + cnt = ring_buffer_entries_cpu(trace_buf->buffer, cpu); + trace_seq_printf(s, "entries: %ld\n", cnt); + + cnt = ring_buffer_overrun_cpu(trace_buf->buffer, cpu); + trace_seq_printf(s, "overrun: %ld\n", cnt); + + cnt = ring_buffer_commit_overrun_cpu(trace_buf->buffer, cpu); + trace_seq_printf(s, "commit overrun: %ld\n", cnt); + + cnt = ring_buffer_bytes_cpu(trace_buf->buffer, cpu); + trace_seq_printf(s, "bytes: %ld\n", cnt); + + if (trace_clocks[tr->clock_id].in_ns) { + /* local or global for trace_clock */ + t = ns2usecs(ring_buffer_oldest_event_ts(trace_buf->buffer, cpu)); + usec_rem = do_div(t, USEC_PER_SEC); + trace_seq_printf(s, "oldest event ts: %5llu.%06lu\n", + t, usec_rem); + + t = ns2usecs(ring_buffer_time_stamp(trace_buf->buffer, cpu)); + usec_rem = do_div(t, USEC_PER_SEC); + trace_seq_printf(s, "now ts: %5llu.%06lu\n", t, usec_rem); + } else { + /* counter or tsc mode for trace_clock */ + trace_seq_printf(s, "oldest event ts: %llu\n", + ring_buffer_oldest_event_ts(trace_buf->buffer, cpu)); + + trace_seq_printf(s, "now ts: %llu\n", + ring_buffer_time_stamp(trace_buf->buffer, cpu)); + } + + cnt = ring_buffer_dropped_events_cpu(trace_buf->buffer, cpu); + trace_seq_printf(s, "dropped events: %ld\n", cnt); + + cnt = ring_buffer_read_events_cpu(trace_buf->buffer, cpu); + trace_seq_printf(s, "read events: %ld\n", cnt); + + count = simple_read_from_buffer(ubuf, count, ppos, + s->buffer, trace_seq_used(s)); + + kfree(s); + + return count; +} + +static const struct file_operations tracing_stats_fops = { + .open = tracing_open_generic_tr, + .read = tracing_stats_read, + .llseek = generic_file_llseek, + .release = tracing_release_generic_tr, +}; + +#ifdef CONFIG_DYNAMIC_FTRACE + +int __weak ftrace_arch_read_dyn_info(char *buf, int size) +{ + return 0; +} + +static ssize_t +tracing_read_dyn_info(struct file *filp, char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + static char ftrace_dyn_info_buffer[1024]; + static DEFINE_MUTEX(dyn_info_mutex); + unsigned long *p = filp->private_data; + char *buf = ftrace_dyn_info_buffer; + int size = ARRAY_SIZE(ftrace_dyn_info_buffer); + int r; + + mutex_lock(&dyn_info_mutex); + r = sprintf(buf, "%ld ", *p); + + r += ftrace_arch_read_dyn_info(buf+r, (size-1)-r); + buf[r++] = '\n'; + + r = simple_read_from_buffer(ubuf, cnt, ppos, buf, r); + + mutex_unlock(&dyn_info_mutex); + + return r; +} + +static const struct file_operations tracing_dyn_info_fops = { + .open = tracing_open_generic, + .read = tracing_read_dyn_info, + .llseek = generic_file_llseek, +}; +#endif /* CONFIG_DYNAMIC_FTRACE */ + +#if defined(CONFIG_TRACER_SNAPSHOT) && defined(CONFIG_DYNAMIC_FTRACE) +static void +ftrace_snapshot(unsigned long ip, unsigned long parent_ip, void **data) +{ + tracing_snapshot(); +} + +static void +ftrace_count_snapshot(unsigned long ip, unsigned long parent_ip, void **data) +{ + unsigned long *count = (long *)data; + + if (!*count) + return; + + if (*count != -1) + (*count)--; + + tracing_snapshot(); +} + +static int +ftrace_snapshot_print(struct seq_file *m, unsigned long ip, + struct ftrace_probe_ops *ops, void *data) +{ + long count = (long)data; + + seq_printf(m, "%ps:", (void *)ip); + + seq_puts(m, "snapshot"); + + if (count == -1) + seq_puts(m, ":unlimited\n"); + else + seq_printf(m, ":count=%ld\n", count); + + return 0; +} + +static struct ftrace_probe_ops snapshot_probe_ops = { + .func = ftrace_snapshot, + .print = ftrace_snapshot_print, +}; + +static struct ftrace_probe_ops snapshot_count_probe_ops = { + .func = ftrace_count_snapshot, + .print = ftrace_snapshot_print, +}; + +static int +ftrace_trace_snapshot_callback(struct ftrace_hash *hash, + char *glob, char *cmd, char *param, int enable) +{ + struct ftrace_probe_ops *ops; + void *count = (void *)-1; + char *number; + int ret; + + /* hash funcs only work with set_ftrace_filter */ + if (!enable) + return -EINVAL; + + ops = param ? &snapshot_count_probe_ops : &snapshot_probe_ops; + + if (glob[0] == '!') { + unregister_ftrace_function_probe_func(glob+1, ops); + return 0; + } + + if (!param) + goto out_reg; + + number = strsep(¶m, ":"); + + if (!strlen(number)) + goto out_reg; + + /* + * We use the callback data field (which is a pointer) + * as our counter. + */ + ret = kstrtoul(number, 0, (unsigned long *)&count); + if (ret) + return ret; + + out_reg: + ret = register_ftrace_function_probe(glob, ops, count); + + if (ret >= 0) + alloc_snapshot(&global_trace); + + return ret < 0 ? ret : 0; +} + +static struct ftrace_func_command ftrace_snapshot_cmd = { + .name = "snapshot", + .func = ftrace_trace_snapshot_callback, +}; + +static __init int register_snapshot_cmd(void) +{ + return register_ftrace_command(&ftrace_snapshot_cmd); +} +#else +static inline __init int register_snapshot_cmd(void) { return 0; } +#endif /* defined(CONFIG_TRACER_SNAPSHOT) && defined(CONFIG_DYNAMIC_FTRACE) */ + +static struct dentry *tracing_get_dentry(struct trace_array *tr) +{ + if (WARN_ON(!tr->dir)) + return ERR_PTR(-ENODEV); + + /* Top directory uses NULL as the parent */ + if (tr->flags & TRACE_ARRAY_FL_GLOBAL) + return NULL; + + /* All sub buffers have a descriptor */ + return tr->dir; +} + +static struct dentry *tracing_dentry_percpu(struct trace_array *tr, int cpu) +{ + struct dentry *d_tracer; + + if (tr->percpu_dir) + return tr->percpu_dir; + + d_tracer = tracing_get_dentry(tr); + if (IS_ERR(d_tracer)) + return NULL; + + tr->percpu_dir = tracefs_create_dir("per_cpu", d_tracer); + + WARN_ONCE(!tr->percpu_dir, + "Could not create tracefs directory 'per_cpu/%d'\n", cpu); + + return tr->percpu_dir; +} + +static struct dentry * +trace_create_cpu_file(const char *name, umode_t mode, struct dentry *parent, + void *data, long cpu, const struct file_operations *fops) +{ + struct dentry *ret = trace_create_file(name, mode, parent, data, fops); + + if (ret) /* See tracing_get_cpu() */ + d_inode(ret)->i_cdev = (void *)(cpu + 1); + return ret; +} + +static void +tracing_init_tracefs_percpu(struct trace_array *tr, long cpu) +{ + struct dentry *d_percpu = tracing_dentry_percpu(tr, cpu); + struct dentry *d_cpu; + char cpu_dir[30]; /* 30 characters should be more than enough */ + + if (!d_percpu) + return; + + snprintf(cpu_dir, 30, "cpu%ld", cpu); + d_cpu = tracefs_create_dir(cpu_dir, d_percpu); + if (!d_cpu) { + pr_warning("Could not create tracefs '%s' entry\n", cpu_dir); + return; + } + + /* per cpu trace_pipe */ + trace_create_cpu_file("trace_pipe", 0444, d_cpu, + tr, cpu, &tracing_pipe_fops); + + /* per cpu trace */ + trace_create_cpu_file("trace", 0644, d_cpu, + tr, cpu, &tracing_fops); + + trace_create_cpu_file("trace_pipe_raw", 0444, d_cpu, + tr, cpu, &tracing_buffers_fops); + + trace_create_cpu_file("stats", 0444, d_cpu, + tr, cpu, &tracing_stats_fops); + + trace_create_cpu_file("buffer_size_kb", 0444, d_cpu, + tr, cpu, &tracing_entries_fops); + +#ifdef CONFIG_TRACER_SNAPSHOT + trace_create_cpu_file("snapshot", 0644, d_cpu, + tr, cpu, &snapshot_fops); + + trace_create_cpu_file("snapshot_raw", 0444, d_cpu, + tr, cpu, &snapshot_raw_fops); +#endif +} + +#ifdef CONFIG_FTRACE_SELFTEST +/* Let selftest have access to static functions in this file */ +#include "trace_selftest.c" +#endif + +struct trace_option_dentry { + struct tracer_opt *opt; + struct tracer_flags *flags; + struct trace_array *tr; + struct dentry *entry; +}; + +static ssize_t +trace_options_read(struct file *filp, char __user *ubuf, size_t cnt, + loff_t *ppos) +{ + struct trace_option_dentry *topt = filp->private_data; + char *buf; + + if (topt->flags->val & topt->opt->bit) + buf = "1\n"; + else + buf = "0\n"; + + return simple_read_from_buffer(ubuf, cnt, ppos, buf, 2); +} + +static ssize_t +trace_options_write(struct file *filp, const char __user *ubuf, size_t cnt, + loff_t *ppos) +{ + struct trace_option_dentry *topt = filp->private_data; + unsigned long val; + int ret; + + ret = kstrtoul_from_user(ubuf, cnt, 10, &val); + if (ret) + return ret; + + if (val != 0 && val != 1) + return -EINVAL; + + if (!!(topt->flags->val & topt->opt->bit) != val) { + mutex_lock(&trace_types_lock); + ret = __set_tracer_option(topt->tr, topt->flags, + topt->opt, !val); + mutex_unlock(&trace_types_lock); + if (ret) + return ret; + } + + *ppos += cnt; + + return cnt; +} + + +static const struct file_operations trace_options_fops = { + .open = tracing_open_generic, + .read = trace_options_read, + .write = trace_options_write, + .llseek = generic_file_llseek, +}; + +static ssize_t +trace_options_core_read(struct file *filp, char __user *ubuf, size_t cnt, + loff_t *ppos) +{ + long index = (long)filp->private_data; + char *buf; + + if (trace_flags & (1 << index)) + buf = "1\n"; + else + buf = "0\n"; + + return simple_read_from_buffer(ubuf, cnt, ppos, buf, 2); +} + +static ssize_t +trace_options_core_write(struct file *filp, const char __user *ubuf, size_t cnt, + loff_t *ppos) +{ + struct trace_array *tr = &global_trace; + long index = (long)filp->private_data; + unsigned long val; + int ret; + + ret = kstrtoul_from_user(ubuf, cnt, 10, &val); + if (ret) + return ret; + + if (val != 0 && val != 1) + return -EINVAL; + + mutex_lock(&trace_types_lock); + ret = set_tracer_flag(tr, 1 << index, val); + mutex_unlock(&trace_types_lock); + + if (ret < 0) + return ret; + + *ppos += cnt; + + return cnt; +} + +static const struct file_operations trace_options_core_fops = { + .open = tracing_open_generic, + .read = trace_options_core_read, + .write = trace_options_core_write, + .llseek = generic_file_llseek, +}; + +struct dentry *trace_create_file(const char *name, + umode_t mode, + struct dentry *parent, + void *data, + const struct file_operations *fops) +{ + struct dentry *ret; + + ret = tracefs_create_file(name, mode, parent, data, fops); + if (!ret) + pr_warning("Could not create tracefs '%s' entry\n", name); + + return ret; +} + + +static struct dentry *trace_options_init_dentry(struct trace_array *tr) +{ + struct dentry *d_tracer; + + if (tr->options) + return tr->options; + + d_tracer = tracing_get_dentry(tr); + if (IS_ERR(d_tracer)) + return NULL; + + tr->options = tracefs_create_dir("options", d_tracer); + if (!tr->options) { + pr_warning("Could not create tracefs directory 'options'\n"); + return NULL; + } + + return tr->options; +} + +static void +create_trace_option_file(struct trace_array *tr, + struct trace_option_dentry *topt, + struct tracer_flags *flags, + struct tracer_opt *opt) +{ + struct dentry *t_options; + + t_options = trace_options_init_dentry(tr); + if (!t_options) + return; + + topt->flags = flags; + topt->opt = opt; + topt->tr = tr; + + topt->entry = trace_create_file(opt->name, 0644, t_options, topt, + &trace_options_fops); + +} + +static struct trace_option_dentry * +create_trace_option_files(struct trace_array *tr, struct tracer *tracer) +{ + struct trace_option_dentry *topts; + struct tracer_flags *flags; + struct tracer_opt *opts; + int cnt; + + if (!tracer) + return NULL; + + flags = tracer->flags; + + if (!flags || !flags->opts) + return NULL; + + opts = flags->opts; + + for (cnt = 0; opts[cnt].name; cnt++) + ; + + topts = kcalloc(cnt + 1, sizeof(*topts), GFP_KERNEL); + if (!topts) + return NULL; + + for (cnt = 0; opts[cnt].name; cnt++) + create_trace_option_file(tr, &topts[cnt], flags, + &opts[cnt]); + + return topts; +} + +static void +destroy_trace_option_files(struct trace_option_dentry *topts) +{ + int cnt; + + if (!topts) + return; + + for (cnt = 0; topts[cnt].opt; cnt++) + tracefs_remove(topts[cnt].entry); + + kfree(topts); +} + +static struct dentry * +create_trace_option_core_file(struct trace_array *tr, + const char *option, long index) +{ + struct dentry *t_options; + + t_options = trace_options_init_dentry(tr); + if (!t_options) + return NULL; + + return trace_create_file(option, 0644, t_options, (void *)index, + &trace_options_core_fops); +} + +static __init void create_trace_options_dir(struct trace_array *tr) +{ + struct dentry *t_options; + int i; + + t_options = trace_options_init_dentry(tr); + if (!t_options) + return; + + for (i = 0; trace_options[i]; i++) + create_trace_option_core_file(tr, trace_options[i], i); +} + +static ssize_t +rb_simple_read(struct file *filp, char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + struct trace_array *tr = filp->private_data; + char buf[64]; + int r; + + r = tracer_tracing_is_on(tr); + r = sprintf(buf, "%d\n", r); + + return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); +} + +static ssize_t +rb_simple_write(struct file *filp, const char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + struct trace_array *tr = filp->private_data; + struct ring_buffer *buffer = tr->trace_buffer.buffer; + unsigned long val; + int ret; + + ret = kstrtoul_from_user(ubuf, cnt, 10, &val); + if (ret) + return ret; + + if (buffer) { + mutex_lock(&trace_types_lock); + if (val) { + tracer_tracing_on(tr); + if (tr->current_trace->start) + tr->current_trace->start(tr); + } else { + tracer_tracing_off(tr); + if (tr->current_trace->stop) + tr->current_trace->stop(tr); + } + mutex_unlock(&trace_types_lock); + } + + (*ppos)++; + + return cnt; +} + +static const struct file_operations rb_simple_fops = { + .open = tracing_open_generic_tr, + .read = rb_simple_read, + .write = rb_simple_write, + .release = tracing_release_generic_tr, + .llseek = default_llseek, +}; + +struct dentry *trace_instance_dir; + +static void +init_tracer_tracefs(struct trace_array *tr, struct dentry *d_tracer); + +static int +allocate_trace_buffer(struct trace_array *tr, struct trace_buffer *buf, int size) +{ + enum ring_buffer_flags rb_flags; + + rb_flags = trace_flags & TRACE_ITER_OVERWRITE ? RB_FL_OVERWRITE : 0; + + buf->tr = tr; + + buf->buffer = ring_buffer_alloc(size, rb_flags); + if (!buf->buffer) + return -ENOMEM; + + buf->data = alloc_percpu(struct trace_array_cpu); + if (!buf->data) { + ring_buffer_free(buf->buffer); + return -ENOMEM; + } + + /* Allocate the first page for all buffers */ + set_buffer_entries(&tr->trace_buffer, + ring_buffer_size(tr->trace_buffer.buffer, 0)); + + return 0; +} + +static int allocate_trace_buffers(struct trace_array *tr, int size) +{ + int ret; + + ret = allocate_trace_buffer(tr, &tr->trace_buffer, size); + if (ret) + return ret; + +#ifdef CONFIG_TRACER_MAX_TRACE + ret = allocate_trace_buffer(tr, &tr->max_buffer, + allocate_snapshot ? size : 1); + if (WARN_ON(ret)) { + ring_buffer_free(tr->trace_buffer.buffer); + free_percpu(tr->trace_buffer.data); + return -ENOMEM; + } + tr->allocated_snapshot = allocate_snapshot; + + /* + * Only the top level trace array gets its snapshot allocated + * from the kernel command line. + */ + allocate_snapshot = false; +#endif + return 0; +} + +static void free_trace_buffer(struct trace_buffer *buf) +{ + if (buf->buffer) { + ring_buffer_free(buf->buffer); + buf->buffer = NULL; + free_percpu(buf->data); + buf->data = NULL; + } +} + +static void free_trace_buffers(struct trace_array *tr) +{ + if (!tr) + return; + + free_trace_buffer(&tr->trace_buffer); + +#ifdef CONFIG_TRACER_MAX_TRACE + free_trace_buffer(&tr->max_buffer); +#endif +} + +static int instance_mkdir(const char *name) +{ + struct trace_array *tr; + int ret; + + mutex_lock(&trace_types_lock); + + ret = -EEXIST; + list_for_each_entry(tr, &ftrace_trace_arrays, list) { + if (tr->name && strcmp(tr->name, name) == 0) + goto out_unlock; + } + + ret = -ENOMEM; + tr = kzalloc(sizeof(*tr), GFP_KERNEL); + if (!tr) + goto out_unlock; + + tr->name = kstrdup(name, GFP_KERNEL); + if (!tr->name) + goto out_free_tr; + + if (!alloc_cpumask_var(&tr->tracing_cpumask, GFP_KERNEL)) + goto out_free_tr; + + cpumask_copy(tr->tracing_cpumask, cpu_all_mask); + + raw_spin_lock_init(&tr->start_lock); + + tr->max_lock = (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED; + + tr->current_trace = &nop_trace; + + INIT_LIST_HEAD(&tr->systems); + INIT_LIST_HEAD(&tr->events); + + if (allocate_trace_buffers(tr, trace_buf_size) < 0) + goto out_free_tr; + + tr->dir = tracefs_create_dir(name, trace_instance_dir); + if (!tr->dir) + goto out_free_tr; + + ret = event_trace_add_tracer(tr->dir, tr); + if (ret) { + tracefs_remove_recursive(tr->dir); + goto out_free_tr; + } + + init_tracer_tracefs(tr, tr->dir); + + list_add(&tr->list, &ftrace_trace_arrays); + + mutex_unlock(&trace_types_lock); + + return 0; + + out_free_tr: + free_trace_buffers(tr); + free_cpumask_var(tr->tracing_cpumask); + kfree(tr->name); + kfree(tr); + + out_unlock: + mutex_unlock(&trace_types_lock); + + return ret; + +} + +static int instance_rmdir(const char *name) +{ + struct trace_array *tr; + int found = 0; + int ret; + + mutex_lock(&trace_types_lock); + + ret = -ENODEV; + list_for_each_entry(tr, &ftrace_trace_arrays, list) { + if (tr->name && strcmp(tr->name, name) == 0) { + found = 1; + break; + } + } + if (!found) + goto out_unlock; + + ret = -EBUSY; + if (tr->ref || (tr->current_trace && tr->current_trace->ref)) + goto out_unlock; + + list_del(&tr->list); + + tracing_set_nop(tr); + event_trace_del_tracer(tr); + ftrace_destroy_function_files(tr); + debugfs_remove_recursive(tr->dir); + free_trace_buffers(tr); + + kfree(tr->name); + kfree(tr); + + ret = 0; + + out_unlock: + mutex_unlock(&trace_types_lock); + + return ret; +} + +static __init void create_trace_instances(struct dentry *d_tracer) +{ + trace_instance_dir = tracefs_create_instance_dir("instances", d_tracer, + instance_mkdir, + instance_rmdir); + if (WARN_ON(!trace_instance_dir)) + return; +} + +static void +init_tracer_tracefs(struct trace_array *tr, struct dentry *d_tracer) +{ + int cpu; + + trace_create_file("available_tracers", 0444, d_tracer, + tr, &show_traces_fops); + + trace_create_file("current_tracer", 0644, d_tracer, + tr, &set_tracer_fops); + + trace_create_file("tracing_cpumask", 0644, d_tracer, + tr, &tracing_cpumask_fops); + + trace_create_file("trace_options", 0644, d_tracer, + tr, &tracing_iter_fops); + + trace_create_file("trace", 0644, d_tracer, + tr, &tracing_fops); + + trace_create_file("trace_pipe", 0444, d_tracer, + tr, &tracing_pipe_fops); + + trace_create_file("buffer_size_kb", 0644, d_tracer, + tr, &tracing_entries_fops); + + trace_create_file("buffer_total_size_kb", 0444, d_tracer, + tr, &tracing_total_entries_fops); + + trace_create_file("free_buffer", 0200, d_tracer, + tr, &tracing_free_buffer_fops); + + trace_create_file("trace_marker", 0220, d_tracer, + tr, &tracing_mark_fops); + + trace_create_file("trace_clock", 0644, d_tracer, tr, + &trace_clock_fops); + + trace_create_file("tracing_on", 0644, d_tracer, + tr, &rb_simple_fops); + +#ifdef CONFIG_TRACER_MAX_TRACE + trace_create_file("tracing_max_latency", 0644, d_tracer, + &tr->max_latency, &tracing_max_lat_fops); +#endif + + if (ftrace_create_function_files(tr, d_tracer)) + WARN(1, "Could not allocate function filter files"); + +#ifdef CONFIG_TRACER_SNAPSHOT + trace_create_file("snapshot", 0644, d_tracer, + tr, &snapshot_fops); +#endif + + for_each_tracing_cpu(cpu) + tracing_init_tracefs_percpu(tr, cpu); + +} + +static struct vfsmount *trace_automount(void *ingore) +{ + struct vfsmount *mnt; + struct file_system_type *type; + + /* + * To maintain backward compatibility for tools that mount + * debugfs to get to the tracing facility, tracefs is automatically + * mounted to the debugfs/tracing directory. + */ + type = get_fs_type("tracefs"); + if (!type) + return NULL; + mnt = vfs_kern_mount(type, 0, "tracefs", NULL); + put_filesystem(type); + if (IS_ERR(mnt)) + return NULL; + mntget(mnt); + + return mnt; +} + +/** + * tracing_init_dentry - initialize top level trace array + * + * This is called when creating files or directories in the tracing + * directory. It is called via fs_initcall() by any of the boot up code + * and expects to return the dentry of the top level tracing directory. + */ +struct dentry *tracing_init_dentry(void) +{ + struct trace_array *tr = &global_trace; + + /* The top level trace array uses NULL as parent */ + if (tr->dir) + return NULL; + + if (WARN_ON(!debugfs_initialized())) + return ERR_PTR(-ENODEV); + + /* + * As there may still be users that expect the tracing + * files to exist in debugfs/tracing, we must automount + * the tracefs file system there, so older tools still + * work with the newer kerenl. + */ + tr->dir = debugfs_create_automount("tracing", NULL, + trace_automount, NULL); + if (!tr->dir) { + pr_warn_once("Could not create debugfs directory 'tracing'\n"); + return ERR_PTR(-ENOMEM); + } + + return NULL; +} + +extern struct trace_enum_map *__start_ftrace_enum_maps[]; +extern struct trace_enum_map *__stop_ftrace_enum_maps[]; + +static void __init trace_enum_init(void) +{ + int len; + + len = __stop_ftrace_enum_maps - __start_ftrace_enum_maps; + trace_insert_enum_map(NULL, __start_ftrace_enum_maps, len); +} + +#ifdef CONFIG_MODULES +static void trace_module_add_enums(struct module *mod) +{ + if (!mod->num_trace_enums) + return; + + /* + * Modules with bad taint do not have events created, do + * not bother with enums either. + */ + if (trace_module_has_bad_taint(mod)) + return; + + trace_insert_enum_map(mod, mod->trace_enums, mod->num_trace_enums); +} + +#ifdef CONFIG_TRACE_ENUM_MAP_FILE +static void trace_module_remove_enums(struct module *mod) +{ + union trace_enum_map_item *map; + union trace_enum_map_item **last = &trace_enum_maps; + + if (!mod->num_trace_enums) + return; + + mutex_lock(&trace_enum_mutex); + + map = trace_enum_maps; + + while (map) { + if (map->head.mod == mod) + break; + map = trace_enum_jmp_to_tail(map); + last = &map->tail.next; + map = map->tail.next; + } + if (!map) + goto out; + + *last = trace_enum_jmp_to_tail(map)->tail.next; + kfree(map); + out: + mutex_unlock(&trace_enum_mutex); +} +#else +static inline void trace_module_remove_enums(struct module *mod) { } +#endif /* CONFIG_TRACE_ENUM_MAP_FILE */ + +static int trace_module_notify(struct notifier_block *self, + unsigned long val, void *data) +{ + struct module *mod = data; + + switch (val) { + case MODULE_STATE_COMING: + trace_module_add_enums(mod); + break; + case MODULE_STATE_GOING: + trace_module_remove_enums(mod); + break; + } + + return 0; +} + +static struct notifier_block trace_module_nb = { + .notifier_call = trace_module_notify, + .priority = 0, +}; +#endif /* CONFIG_MODULES */ + +static __init int tracer_init_tracefs(void) +{ + struct dentry *d_tracer; + + trace_access_lock_init(); + + d_tracer = tracing_init_dentry(); + if (IS_ERR(d_tracer)) + return 0; + + init_tracer_tracefs(&global_trace, d_tracer); + + trace_create_file("tracing_thresh", 0644, d_tracer, + &global_trace, &tracing_thresh_fops); + + trace_create_file("README", 0444, d_tracer, + NULL, &tracing_readme_fops); + + trace_create_file("saved_cmdlines", 0444, d_tracer, + NULL, &tracing_saved_cmdlines_fops); + + trace_create_file("saved_cmdlines_size", 0644, d_tracer, + NULL, &tracing_saved_cmdlines_size_fops); + + trace_enum_init(); + + trace_create_enum_file(d_tracer); + +#ifdef CONFIG_MODULES + register_module_notifier(&trace_module_nb); +#endif + +#ifdef CONFIG_DYNAMIC_FTRACE + trace_create_file("dyn_ftrace_total_info", 0444, d_tracer, + &ftrace_update_tot_cnt, &tracing_dyn_info_fops); +#endif + + create_trace_instances(d_tracer); + + create_trace_options_dir(&global_trace); + + /* If the tracer was started via cmdline, create options for it here */ + if (global_trace.current_trace != &nop_trace) + update_tracer_options(&global_trace, global_trace.current_trace); + + return 0; +} + +static int trace_panic_handler(struct notifier_block *this, + unsigned long event, void *unused) +{ + if (ftrace_dump_on_oops) + ftrace_dump(ftrace_dump_on_oops); + return NOTIFY_OK; +} + +static struct notifier_block trace_panic_notifier = { + .notifier_call = trace_panic_handler, + .next = NULL, + .priority = 150 /* priority: INT_MAX >= x >= 0 */ +}; + +static int trace_die_handler(struct notifier_block *self, + unsigned long val, + void *data) +{ + switch (val) { + case DIE_OOPS: + if (ftrace_dump_on_oops) + ftrace_dump(ftrace_dump_on_oops); + break; + default: + break; + } + return NOTIFY_OK; +} + +static struct notifier_block trace_die_notifier = { + .notifier_call = trace_die_handler, + .priority = 200 +}; + +/* + * printk is set to max of 1024, we really don't need it that big. + * Nothing should be printing 1000 characters anyway. + */ +#define TRACE_MAX_PRINT 1000 + +/* + * Define here KERN_TRACE so that we have one place to modify + * it if we decide to change what log level the ftrace dump + * should be at. + */ +#define KERN_TRACE KERN_EMERG + +void +trace_printk_seq(struct trace_seq *s) +{ + /* Probably should print a warning here. */ + if (s->seq.len >= TRACE_MAX_PRINT) + s->seq.len = TRACE_MAX_PRINT; + + /* + * More paranoid code. Although the buffer size is set to + * PAGE_SIZE, and TRACE_MAX_PRINT is 1000, this is just + * an extra layer of protection. + */ + if (WARN_ON_ONCE(s->seq.len >= s->seq.size)) + s->seq.len = s->seq.size - 1; + + /* should be zero ended, but we are paranoid. */ + s->buffer[s->seq.len] = 0; + + printk(KERN_TRACE "%s", s->buffer); + + trace_seq_init(s); +} + +void trace_init_global_iter(struct trace_iterator *iter) +{ + iter->tr = &global_trace; + iter->trace = iter->tr->current_trace; + iter->cpu_file = RING_BUFFER_ALL_CPUS; + iter->trace_buffer = &global_trace.trace_buffer; + + if (iter->trace && iter->trace->open) + iter->trace->open(iter); + + /* Annotate start of buffers if we had overruns */ + if (ring_buffer_overruns(iter->trace_buffer->buffer)) + iter->iter_flags |= TRACE_FILE_ANNOTATE; + + /* Output in nanoseconds only if we are using a clock in nanoseconds. */ + if (trace_clocks[iter->tr->clock_id].in_ns) + iter->iter_flags |= TRACE_FILE_TIME_IN_NS; +} + +void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) +{ + /* use static because iter can be a bit big for the stack */ + static struct trace_iterator iter; + static atomic_t dump_running; + unsigned int old_userobj; + unsigned long flags; + int cnt = 0, cpu; + + /* Only allow one dump user at a time. */ + if (atomic_inc_return(&dump_running) != 1) { + atomic_dec(&dump_running); + return; + } + + /* + * Always turn off tracing when we dump. + * We don't need to show trace output of what happens + * between multiple crashes. + * + * If the user does a sysrq-z, then they can re-enable + * tracing with echo 1 > tracing_on. + */ + tracing_off(); + + local_irq_save(flags); + + /* Simulate the iterator */ + trace_init_global_iter(&iter); + + for_each_tracing_cpu(cpu) { + atomic_inc(&per_cpu_ptr(iter.tr->trace_buffer.data, cpu)->disabled); + } + + old_userobj = trace_flags & TRACE_ITER_SYM_USEROBJ; + + /* don't look at user memory in panic mode */ + trace_flags &= ~TRACE_ITER_SYM_USEROBJ; + + switch (oops_dump_mode) { + case DUMP_ALL: + iter.cpu_file = RING_BUFFER_ALL_CPUS; + break; + case DUMP_ORIG: + iter.cpu_file = raw_smp_processor_id(); + break; + case DUMP_NONE: + goto out_enable; + default: + printk(KERN_TRACE "Bad dumping mode, switching to all CPUs dump\n"); + iter.cpu_file = RING_BUFFER_ALL_CPUS; + } + + printk(KERN_TRACE "Dumping ftrace buffer:\n"); + + /* Did function tracer already get disabled? */ + if (ftrace_is_dead()) { + printk("# WARNING: FUNCTION TRACING IS CORRUPTED\n"); + printk("# MAY BE MISSING FUNCTION EVENTS\n"); + } + + /* + * We need to stop all tracing on all CPUS to read the + * the next buffer. This is a bit expensive, but is + * not done often. We fill all what we can read, + * and then release the locks again. + */ + + while (!trace_empty(&iter)) { + + if (!cnt) + printk(KERN_TRACE "---------------------------------\n"); + + cnt++; + + /* reset all but tr, trace, and overruns */ + memset(&iter.seq, 0, + sizeof(struct trace_iterator) - + offsetof(struct trace_iterator, seq)); + iter.iter_flags |= TRACE_FILE_LAT_FMT; + iter.pos = -1; + + if (trace_find_next_entry_inc(&iter) != NULL) { + int ret; + + ret = print_trace_line(&iter); + if (ret != TRACE_TYPE_NO_CONSUME) + trace_consume(&iter); + } + touch_nmi_watchdog(); + + trace_printk_seq(&iter.seq); + } + + if (!cnt) + printk(KERN_TRACE " (ftrace buffer empty)\n"); + else + printk(KERN_TRACE "---------------------------------\n"); + + out_enable: + trace_flags |= old_userobj; + + for_each_tracing_cpu(cpu) { + atomic_dec(&per_cpu_ptr(iter.trace_buffer->data, cpu)->disabled); + } + atomic_dec(&dump_running); + local_irq_restore(flags); +} +EXPORT_SYMBOL_GPL(ftrace_dump); + +__init static int tracer_alloc_buffers(void) +{ + int ring_buf_size; + int ret = -ENOMEM; + + if (!alloc_cpumask_var(&tracing_buffer_mask, GFP_KERNEL)) + goto out; + + if (!alloc_cpumask_var(&global_trace.tracing_cpumask, GFP_KERNEL)) + goto out_free_buffer_mask; + + /* Only allocate trace_printk buffers if a trace_printk exists */ + if (__stop___trace_bprintk_fmt != __start___trace_bprintk_fmt) + /* Must be called before global_trace.buffer is allocated */ + trace_printk_init_buffers(); + + /* To save memory, keep the ring buffer size to its minimum */ + if (ring_buffer_expanded) + ring_buf_size = trace_buf_size; + else + ring_buf_size = 1; + + cpumask_copy(tracing_buffer_mask, cpu_possible_mask); + cpumask_copy(global_trace.tracing_cpumask, cpu_all_mask); + + raw_spin_lock_init(&global_trace.start_lock); + + /* Used for event triggers */ + temp_buffer = ring_buffer_alloc(PAGE_SIZE, RB_FL_OVERWRITE); + if (!temp_buffer) + goto out_free_cpumask; + + if (trace_create_savedcmd() < 0) + goto out_free_temp_buffer; + + /* TODO: make the number of buffers hot pluggable with CPUS */ + if (allocate_trace_buffers(&global_trace, ring_buf_size) < 0) { + printk(KERN_ERR "tracer: failed to allocate ring buffer!\n"); + WARN_ON(1); + goto out_free_savedcmd; + } + + if (global_trace.buffer_disabled) + tracing_off(); + + if (trace_boot_clock) { + ret = tracing_set_clock(&global_trace, trace_boot_clock); + if (ret < 0) + pr_warning("Trace clock %s not defined, going back to default\n", + trace_boot_clock); + } + + /* + * register_tracer() might reference current_trace, so it + * needs to be set before we register anything. This is + * just a bootstrap of current_trace anyway. + */ + global_trace.current_trace = &nop_trace; + + global_trace.max_lock = (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED; + + ftrace_init_global_array_ops(&global_trace); + + register_tracer(&nop_trace); + + /* All seems OK, enable tracing */ + tracing_disabled = 0; + + atomic_notifier_chain_register(&panic_notifier_list, + &trace_panic_notifier); + + register_die_notifier(&trace_die_notifier); + + global_trace.flags = TRACE_ARRAY_FL_GLOBAL; + + INIT_LIST_HEAD(&global_trace.systems); + INIT_LIST_HEAD(&global_trace.events); + list_add(&global_trace.list, &ftrace_trace_arrays); + + while (trace_boot_options) { + char *option; + + option = strsep(&trace_boot_options, ","); + trace_set_options(&global_trace, option); + } + + register_snapshot_cmd(); + + return 0; + +out_free_savedcmd: + free_saved_cmdlines_buffer(savedcmd); +out_free_temp_buffer: + ring_buffer_free(temp_buffer); +out_free_cpumask: + free_cpumask_var(global_trace.tracing_cpumask); +out_free_buffer_mask: + free_cpumask_var(tracing_buffer_mask); +out: + return ret; +} + +void __init trace_init(void) +{ + if (tracepoint_printk) { + tracepoint_print_iter = + kmalloc(sizeof(*tracepoint_print_iter), GFP_KERNEL); + if (WARN_ON(!tracepoint_print_iter)) + tracepoint_printk = 0; + } + tracer_alloc_buffers(); + trace_event_init(); +} + +__init static int clear_boot_tracer(void) +{ + /* + * The default tracer at boot buffer is an init section. + * This function is called in lateinit. If we did not + * find the boot tracer, then clear it out, to prevent + * later registration from accessing the buffer that is + * about to be freed. + */ + if (!default_bootup_tracer) + return 0; + + printk(KERN_INFO "ftrace bootup tracer '%s' not registered.\n", + default_bootup_tracer); + default_bootup_tracer = NULL; + + return 0; +} + +fs_initcall(tracer_init_tracefs); +late_initcall(clear_boot_tracer); diff --git a/kernel/kernel/trace/trace.h b/kernel/kernel/trace/trace.h new file mode 100644 index 000000000..a6784ca9c --- /dev/null +++ b/kernel/kernel/trace/trace.h @@ -0,0 +1,1322 @@ + +#ifndef _LINUX_KERNEL_TRACE_H +#define _LINUX_KERNEL_TRACE_H + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#ifdef CONFIG_FTRACE_SYSCALLS +#include /* For NR_SYSCALLS */ +#include /* some archs define it here */ +#endif + +enum trace_type { + __TRACE_FIRST_TYPE = 0, + + TRACE_FN, + TRACE_CTX, + TRACE_WAKE, + TRACE_STACK, + TRACE_PRINT, + TRACE_BPRINT, + TRACE_MMIO_RW, + TRACE_MMIO_MAP, + TRACE_BRANCH, + TRACE_GRAPH_RET, + TRACE_GRAPH_ENT, + TRACE_USER_STACK, + TRACE_BLK, + TRACE_BPUTS, + + __TRACE_LAST_TYPE, +}; + + +#undef __field +#define __field(type, item) type item; + +#undef __field_struct +#define __field_struct(type, item) __field(type, item) + +#undef __field_desc +#define __field_desc(type, container, item) + +#undef __array +#define __array(type, item, size) type item[size]; + +#undef __array_desc +#define __array_desc(type, container, item, size) + +#undef __dynamic_array +#define __dynamic_array(type, item) type item[]; + +#undef F_STRUCT +#define F_STRUCT(args...) args + +#undef FTRACE_ENTRY +#define FTRACE_ENTRY(name, struct_name, id, tstruct, print, filter) \ + struct struct_name { \ + struct trace_entry ent; \ + tstruct \ + } + +#undef TP_ARGS +#define TP_ARGS(args...) args + +#undef FTRACE_ENTRY_DUP +#define FTRACE_ENTRY_DUP(name, name_struct, id, tstruct, printk, filter) + +#undef FTRACE_ENTRY_REG +#define FTRACE_ENTRY_REG(name, struct_name, id, tstruct, print, \ + filter, regfn) \ + FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print), \ + filter) + +#include "trace_entries.h" + +/* + * syscalls are special, and need special handling, this is why + * they are not included in trace_entries.h + */ +struct syscall_trace_enter { + struct trace_entry ent; + int nr; + unsigned long args[]; +}; + +struct syscall_trace_exit { + struct trace_entry ent; + int nr; + long ret; +}; + +struct kprobe_trace_entry_head { + struct trace_entry ent; + unsigned long ip; +}; + +struct kretprobe_trace_entry_head { + struct trace_entry ent; + unsigned long func; + unsigned long ret_ip; +}; + +/* + * trace_flag_type is an enumeration that holds different + * states when a trace occurs. These are: + * IRQS_OFF - interrupts were disabled + * IRQS_NOSUPPORT - arch does not support irqs_disabled_flags + * NEED_RESCHED - reschedule is requested + * HARDIRQ - inside an interrupt handler + * SOFTIRQ - inside a softirq handler + * NEED_RESCHED_LAZY - lazy reschedule is requested + */ +enum trace_flag_type { + TRACE_FLAG_IRQS_OFF = 0x01, + TRACE_FLAG_IRQS_NOSUPPORT = 0x02, + TRACE_FLAG_NEED_RESCHED = 0x04, + TRACE_FLAG_HARDIRQ = 0x08, + TRACE_FLAG_SOFTIRQ = 0x10, + TRACE_FLAG_PREEMPT_RESCHED = 0x20, + TRACE_FLAG_NEED_RESCHED_LAZY = 0x40, +}; + +#define TRACE_BUF_SIZE 1024 + +struct trace_array; + +/* + * The CPU trace array - it consists of thousands of trace entries + * plus some other descriptor data: (for example which task started + * the trace, etc.) + */ +struct trace_array_cpu { + atomic_t disabled; + void *buffer_page; /* ring buffer spare */ + + unsigned long entries; + unsigned long saved_latency; + unsigned long critical_start; + unsigned long critical_end; + unsigned long critical_sequence; + unsigned long nice; + unsigned long policy; + unsigned long rt_priority; + unsigned long skipped_entries; + cycle_t preempt_timestamp; + pid_t pid; + kuid_t uid; + char comm[TASK_COMM_LEN]; +}; + +struct tracer; + +struct trace_buffer { + struct trace_array *tr; + struct ring_buffer *buffer; + struct trace_array_cpu __percpu *data; + cycle_t time_start; + int cpu; +}; + +/* + * The trace array - an array of per-CPU trace arrays. This is the + * highest level data structure that individual tracers deal with. + * They have on/off state as well: + */ +struct trace_array { + struct list_head list; + char *name; + struct trace_buffer trace_buffer; +#ifdef CONFIG_TRACER_MAX_TRACE + /* + * The max_buffer is used to snapshot the trace when a maximum + * latency is reached, or when the user initiates a snapshot. + * Some tracers will use this to store a maximum trace while + * it continues examining live traces. + * + * The buffers for the max_buffer are set up the same as the trace_buffer + * When a snapshot is taken, the buffer of the max_buffer is swapped + * with the buffer of the trace_buffer and the buffers are reset for + * the trace_buffer so the tracing can continue. + */ + struct trace_buffer max_buffer; + bool allocated_snapshot; + unsigned long max_latency; +#endif + /* + * max_lock is used to protect the swapping of buffers + * when taking a max snapshot. The buffers themselves are + * protected by per_cpu spinlocks. But the action of the swap + * needs its own lock. + * + * This is defined as a arch_spinlock_t in order to help + * with performance when lockdep debugging is enabled. + * + * It is also used in other places outside the update_max_tr + * so it needs to be defined outside of the + * CONFIG_TRACER_MAX_TRACE. + */ + arch_spinlock_t max_lock; + int buffer_disabled; +#ifdef CONFIG_FTRACE_SYSCALLS + int sys_refcount_enter; + int sys_refcount_exit; + struct ftrace_event_file __rcu *enter_syscall_files[NR_syscalls]; + struct ftrace_event_file __rcu *exit_syscall_files[NR_syscalls]; +#endif + int stop_count; + int clock_id; + struct tracer *current_trace; + unsigned int flags; + raw_spinlock_t start_lock; + struct dentry *dir; + struct dentry *options; + struct dentry *percpu_dir; + struct dentry *event_dir; + struct list_head systems; + struct list_head events; + cpumask_var_t tracing_cpumask; /* only trace on set CPUs */ + int ref; +#ifdef CONFIG_FUNCTION_TRACER + struct ftrace_ops *ops; + /* function tracing enabled */ + int function_enabled; +#endif +}; + +enum { + TRACE_ARRAY_FL_GLOBAL = (1 << 0) +}; + +extern struct list_head ftrace_trace_arrays; + +extern struct mutex trace_types_lock; + +extern int trace_array_get(struct trace_array *tr); +extern void trace_array_put(struct trace_array *tr); + +/* + * The global tracer (top) should be the first trace array added, + * but we check the flag anyway. + */ +static inline struct trace_array *top_trace_array(void) +{ + struct trace_array *tr; + + if (list_empty(&ftrace_trace_arrays)) + return NULL; + + tr = list_entry(ftrace_trace_arrays.prev, + typeof(*tr), list); + WARN_ON(!(tr->flags & TRACE_ARRAY_FL_GLOBAL)); + return tr; +} + +#define FTRACE_CMP_TYPE(var, type) \ + __builtin_types_compatible_p(typeof(var), type *) + +#undef IF_ASSIGN +#define IF_ASSIGN(var, entry, etype, id) \ + if (FTRACE_CMP_TYPE(var, etype)) { \ + var = (typeof(var))(entry); \ + WARN_ON(id && (entry)->type != id); \ + break; \ + } + +/* Will cause compile errors if type is not found. */ +extern void __ftrace_bad_type(void); + +/* + * The trace_assign_type is a verifier that the entry type is + * the same as the type being assigned. To add new types simply + * add a line with the following format: + * + * IF_ASSIGN(var, ent, type, id); + * + * Where "type" is the trace type that includes the trace_entry + * as the "ent" item. And "id" is the trace identifier that is + * used in the trace_type enum. + * + * If the type can have more than one id, then use zero. + */ +#define trace_assign_type(var, ent) \ + do { \ + IF_ASSIGN(var, ent, struct ftrace_entry, TRACE_FN); \ + IF_ASSIGN(var, ent, struct ctx_switch_entry, 0); \ + IF_ASSIGN(var, ent, struct stack_entry, TRACE_STACK); \ + IF_ASSIGN(var, ent, struct userstack_entry, TRACE_USER_STACK);\ + IF_ASSIGN(var, ent, struct print_entry, TRACE_PRINT); \ + IF_ASSIGN(var, ent, struct bprint_entry, TRACE_BPRINT); \ + IF_ASSIGN(var, ent, struct bputs_entry, TRACE_BPUTS); \ + IF_ASSIGN(var, ent, struct trace_mmiotrace_rw, \ + TRACE_MMIO_RW); \ + IF_ASSIGN(var, ent, struct trace_mmiotrace_map, \ + TRACE_MMIO_MAP); \ + IF_ASSIGN(var, ent, struct trace_branch, TRACE_BRANCH); \ + IF_ASSIGN(var, ent, struct ftrace_graph_ent_entry, \ + TRACE_GRAPH_ENT); \ + IF_ASSIGN(var, ent, struct ftrace_graph_ret_entry, \ + TRACE_GRAPH_RET); \ + __ftrace_bad_type(); \ + } while (0) + +/* + * An option specific to a tracer. This is a boolean value. + * The bit is the bit index that sets its value on the + * flags value in struct tracer_flags. + */ +struct tracer_opt { + const char *name; /* Will appear on the trace_options file */ + u32 bit; /* Mask assigned in val field in tracer_flags */ +}; + +/* + * The set of specific options for a tracer. Your tracer + * have to set the initial value of the flags val. + */ +struct tracer_flags { + u32 val; + struct tracer_opt *opts; +}; + +/* Makes more easy to define a tracer opt */ +#define TRACER_OPT(s, b) .name = #s, .bit = b + + +/** + * struct tracer - a specific tracer and its callbacks to interact with tracefs + * @name: the name chosen to select it on the available_tracers file + * @init: called when one switches to this tracer (echo name > current_tracer) + * @reset: called when one switches to another tracer + * @start: called when tracing is unpaused (echo 1 > tracing_enabled) + * @stop: called when tracing is paused (echo 0 > tracing_enabled) + * @update_thresh: called when tracing_thresh is updated + * @open: called when the trace file is opened + * @pipe_open: called when the trace_pipe file is opened + * @close: called when the trace file is released + * @pipe_close: called when the trace_pipe file is released + * @read: override the default read callback on trace_pipe + * @splice_read: override the default splice_read callback on trace_pipe + * @selftest: selftest to run on boot (see trace_selftest.c) + * @print_headers: override the first lines that describe your columns + * @print_line: callback that prints a trace + * @set_flag: signals one of your private flags changed (trace_options file) + * @flags: your private flags + */ +struct tracer { + const char *name; + int (*init)(struct trace_array *tr); + void (*reset)(struct trace_array *tr); + void (*start)(struct trace_array *tr); + void (*stop)(struct trace_array *tr); + int (*update_thresh)(struct trace_array *tr); + void (*open)(struct trace_iterator *iter); + void (*pipe_open)(struct trace_iterator *iter); + void (*close)(struct trace_iterator *iter); + void (*pipe_close)(struct trace_iterator *iter); + ssize_t (*read)(struct trace_iterator *iter, + struct file *filp, char __user *ubuf, + size_t cnt, loff_t *ppos); + ssize_t (*splice_read)(struct trace_iterator *iter, + struct file *filp, + loff_t *ppos, + struct pipe_inode_info *pipe, + size_t len, + unsigned int flags); +#ifdef CONFIG_FTRACE_STARTUP_TEST + int (*selftest)(struct tracer *trace, + struct trace_array *tr); +#endif + void (*print_header)(struct seq_file *m); + enum print_line_t (*print_line)(struct trace_iterator *iter); + /* If you handled the flag setting, return 0 */ + int (*set_flag)(struct trace_array *tr, + u32 old_flags, u32 bit, int set); + /* Return 0 if OK with change, else return non-zero */ + int (*flag_changed)(struct trace_array *tr, + u32 mask, int set); + struct tracer *next; + struct tracer_flags *flags; + int enabled; + int ref; + bool print_max; + bool allow_instances; +#ifdef CONFIG_TRACER_MAX_TRACE + bool use_max_tr; +#endif +}; + + +/* Only current can touch trace_recursion */ + +/* + * For function tracing recursion: + * The order of these bits are important. + * + * When function tracing occurs, the following steps are made: + * If arch does not support a ftrace feature: + * call internal function (uses INTERNAL bits) which calls... + * If callback is registered to the "global" list, the list + * function is called and recursion checks the GLOBAL bits. + * then this function calls... + * The function callback, which can use the FTRACE bits to + * check for recursion. + * + * Now if the arch does not suppport a feature, and it calls + * the global list function which calls the ftrace callback + * all three of these steps will do a recursion protection. + * There's no reason to do one if the previous caller already + * did. The recursion that we are protecting against will + * go through the same steps again. + * + * To prevent the multiple recursion checks, if a recursion + * bit is set that is higher than the MAX bit of the current + * check, then we know that the check was made by the previous + * caller, and we can skip the current check. + */ +enum { + TRACE_BUFFER_BIT, + TRACE_BUFFER_NMI_BIT, + TRACE_BUFFER_IRQ_BIT, + TRACE_BUFFER_SIRQ_BIT, + + /* Start of function recursion bits */ + TRACE_FTRACE_BIT, + TRACE_FTRACE_NMI_BIT, + TRACE_FTRACE_IRQ_BIT, + TRACE_FTRACE_SIRQ_BIT, + + /* INTERNAL_BITs must be greater than FTRACE_BITs */ + TRACE_INTERNAL_BIT, + TRACE_INTERNAL_NMI_BIT, + TRACE_INTERNAL_IRQ_BIT, + TRACE_INTERNAL_SIRQ_BIT, + + TRACE_CONTROL_BIT, + +/* + * Abuse of the trace_recursion. + * As we need a way to maintain state if we are tracing the function + * graph in irq because we want to trace a particular function that + * was called in irq context but we have irq tracing off. Since this + * can only be modified by current, we can reuse trace_recursion. + */ + TRACE_IRQ_BIT, +}; + +#define trace_recursion_set(bit) do { (current)->trace_recursion |= (1<<(bit)); } while (0) +#define trace_recursion_clear(bit) do { (current)->trace_recursion &= ~(1<<(bit)); } while (0) +#define trace_recursion_test(bit) ((current)->trace_recursion & (1<<(bit))) + +#define TRACE_CONTEXT_BITS 4 + +#define TRACE_FTRACE_START TRACE_FTRACE_BIT +#define TRACE_FTRACE_MAX ((1 << (TRACE_FTRACE_START + TRACE_CONTEXT_BITS)) - 1) + +#define TRACE_LIST_START TRACE_INTERNAL_BIT +#define TRACE_LIST_MAX ((1 << (TRACE_LIST_START + TRACE_CONTEXT_BITS)) - 1) + +#define TRACE_CONTEXT_MASK TRACE_LIST_MAX + +static __always_inline int trace_get_context_bit(void) +{ + int bit; + + if (in_interrupt()) { + if (in_nmi()) + bit = 0; + + else if (in_irq()) + bit = 1; + else + bit = 2; + } else + bit = 3; + + return bit; +} + +static __always_inline int trace_test_and_set_recursion(int start, int max) +{ + unsigned int val = current->trace_recursion; + int bit; + + /* A previous recursion check was made */ + if ((val & TRACE_CONTEXT_MASK) > max) + return 0; + + bit = trace_get_context_bit() + start; + if (unlikely(val & (1 << bit))) + return -1; + + val |= 1 << bit; + current->trace_recursion = val; + barrier(); + + return bit; +} + +static __always_inline void trace_clear_recursion(int bit) +{ + unsigned int val = current->trace_recursion; + + if (!bit) + return; + + bit = 1 << bit; + val &= ~bit; + + barrier(); + current->trace_recursion = val; +} + +static inline struct ring_buffer_iter * +trace_buffer_iter(struct trace_iterator *iter, int cpu) +{ + if (iter->buffer_iter && iter->buffer_iter[cpu]) + return iter->buffer_iter[cpu]; + return NULL; +} + +int tracer_init(struct tracer *t, struct trace_array *tr); +int tracing_is_enabled(void); +void tracing_reset(struct trace_buffer *buf, int cpu); +void tracing_reset_online_cpus(struct trace_buffer *buf); +void tracing_reset_current(int cpu); +void tracing_reset_all_online_cpus(void); +int tracing_open_generic(struct inode *inode, struct file *filp); +bool tracing_is_disabled(void); +struct dentry *trace_create_file(const char *name, + umode_t mode, + struct dentry *parent, + void *data, + const struct file_operations *fops); + +struct dentry *tracing_init_dentry(void); + +struct ring_buffer_event; + +struct ring_buffer_event * +trace_buffer_lock_reserve(struct ring_buffer *buffer, + int type, + unsigned long len, + unsigned long flags, + int pc); + +struct trace_entry *tracing_get_trace_entry(struct trace_array *tr, + struct trace_array_cpu *data); + +struct trace_entry *trace_find_next_entry(struct trace_iterator *iter, + int *ent_cpu, u64 *ent_ts); + +void __buffer_unlock_commit(struct ring_buffer *buffer, + struct ring_buffer_event *event); + +int trace_empty(struct trace_iterator *iter); + +void *trace_find_next_entry_inc(struct trace_iterator *iter); + +void trace_init_global_iter(struct trace_iterator *iter); + +void tracing_iter_reset(struct trace_iterator *iter, int cpu); + +void trace_function(struct trace_array *tr, + unsigned long ip, + unsigned long parent_ip, + unsigned long flags, int pc); +void trace_graph_function(struct trace_array *tr, + unsigned long ip, + unsigned long parent_ip, + unsigned long flags, int pc); +void trace_latency_header(struct seq_file *m); +void trace_default_header(struct seq_file *m); +void print_trace_header(struct seq_file *m, struct trace_iterator *iter); +int trace_empty(struct trace_iterator *iter); + +void trace_graph_return(struct ftrace_graph_ret *trace); +int trace_graph_entry(struct ftrace_graph_ent *trace); +void set_graph_array(struct trace_array *tr); + +void tracing_start_cmdline_record(void); +void tracing_stop_cmdline_record(void); +int register_tracer(struct tracer *type); +int is_tracing_stopped(void); + +loff_t tracing_lseek(struct file *file, loff_t offset, int whence); + +extern cpumask_var_t __read_mostly tracing_buffer_mask; + +#define for_each_tracing_cpu(cpu) \ + for_each_cpu(cpu, tracing_buffer_mask) + +extern unsigned long nsecs_to_usecs(unsigned long nsecs); + +extern unsigned long tracing_thresh; + +#ifdef CONFIG_TRACER_MAX_TRACE +void update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu); +void update_max_tr_single(struct trace_array *tr, + struct task_struct *tsk, int cpu); +#endif /* CONFIG_TRACER_MAX_TRACE */ + +#ifdef CONFIG_STACKTRACE +void ftrace_trace_stack(struct ring_buffer *buffer, unsigned long flags, + int skip, int pc); + +void ftrace_trace_stack_regs(struct ring_buffer *buffer, unsigned long flags, + int skip, int pc, struct pt_regs *regs); + +void ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags, + int pc); + +void __trace_stack(struct trace_array *tr, unsigned long flags, int skip, + int pc); +#else +static inline void ftrace_trace_stack(struct ring_buffer *buffer, + unsigned long flags, int skip, int pc) +{ +} + +static inline void ftrace_trace_stack_regs(struct ring_buffer *buffer, + unsigned long flags, int skip, + int pc, struct pt_regs *regs) +{ +} + +static inline void ftrace_trace_userstack(struct ring_buffer *buffer, + unsigned long flags, int pc) +{ +} + +static inline void __trace_stack(struct trace_array *tr, unsigned long flags, + int skip, int pc) +{ +} +#endif /* CONFIG_STACKTRACE */ + +extern cycle_t ftrace_now(int cpu); + +extern void trace_find_cmdline(int pid, char comm[]); + +#ifdef CONFIG_DYNAMIC_FTRACE +extern unsigned long ftrace_update_tot_cnt; +#endif +#define DYN_FTRACE_TEST_NAME trace_selftest_dynamic_test_func +extern int DYN_FTRACE_TEST_NAME(void); +#define DYN_FTRACE_TEST_NAME2 trace_selftest_dynamic_test_func2 +extern int DYN_FTRACE_TEST_NAME2(void); + +extern bool ring_buffer_expanded; +extern bool tracing_selftest_disabled; +DECLARE_PER_CPU(int, ftrace_cpu_disabled); + +#ifdef CONFIG_FTRACE_STARTUP_TEST +extern int trace_selftest_startup_function(struct tracer *trace, + struct trace_array *tr); +extern int trace_selftest_startup_function_graph(struct tracer *trace, + struct trace_array *tr); +extern int trace_selftest_startup_irqsoff(struct tracer *trace, + struct trace_array *tr); +extern int trace_selftest_startup_preemptoff(struct tracer *trace, + struct trace_array *tr); +extern int trace_selftest_startup_preemptirqsoff(struct tracer *trace, + struct trace_array *tr); +extern int trace_selftest_startup_wakeup(struct tracer *trace, + struct trace_array *tr); +extern int trace_selftest_startup_nop(struct tracer *trace, + struct trace_array *tr); +extern int trace_selftest_startup_sched_switch(struct tracer *trace, + struct trace_array *tr); +extern int trace_selftest_startup_branch(struct tracer *trace, + struct trace_array *tr); +/* + * Tracer data references selftest functions that only occur + * on boot up. These can be __init functions. Thus, when selftests + * are enabled, then the tracers need to reference __init functions. + */ +#define __tracer_data __refdata +#else +/* Tracers are seldom changed. Optimize when selftests are disabled. */ +#define __tracer_data __read_mostly +#endif /* CONFIG_FTRACE_STARTUP_TEST */ + +extern void *head_page(struct trace_array_cpu *data); +extern unsigned long long ns2usecs(cycle_t nsec); +extern int +trace_vbprintk(unsigned long ip, const char *fmt, va_list args); +extern int +trace_vprintk(unsigned long ip, const char *fmt, va_list args); +extern int +trace_array_vprintk(struct trace_array *tr, + unsigned long ip, const char *fmt, va_list args); +int trace_array_printk(struct trace_array *tr, + unsigned long ip, const char *fmt, ...); +int trace_array_printk_buf(struct ring_buffer *buffer, + unsigned long ip, const char *fmt, ...); +void trace_printk_seq(struct trace_seq *s); +enum print_line_t print_trace_line(struct trace_iterator *iter); + +extern unsigned long trace_flags; + +extern char trace_find_mark(unsigned long long duration); + +/* Standard output formatting function used for function return traces */ +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + +/* Flag options */ +#define TRACE_GRAPH_PRINT_OVERRUN 0x1 +#define TRACE_GRAPH_PRINT_CPU 0x2 +#define TRACE_GRAPH_PRINT_OVERHEAD 0x4 +#define TRACE_GRAPH_PRINT_PROC 0x8 +#define TRACE_GRAPH_PRINT_DURATION 0x10 +#define TRACE_GRAPH_PRINT_ABS_TIME 0x20 +#define TRACE_GRAPH_PRINT_IRQS 0x40 +#define TRACE_GRAPH_PRINT_TAIL 0x80 +#define TRACE_GRAPH_PRINT_FILL_SHIFT 28 +#define TRACE_GRAPH_PRINT_FILL_MASK (0x3 << TRACE_GRAPH_PRINT_FILL_SHIFT) + +extern enum print_line_t +print_graph_function_flags(struct trace_iterator *iter, u32 flags); +extern void print_graph_headers_flags(struct seq_file *s, u32 flags); +extern void +trace_print_graph_duration(unsigned long long duration, struct trace_seq *s); +extern void graph_trace_open(struct trace_iterator *iter); +extern void graph_trace_close(struct trace_iterator *iter); +extern int __trace_graph_entry(struct trace_array *tr, + struct ftrace_graph_ent *trace, + unsigned long flags, int pc); +extern void __trace_graph_return(struct trace_array *tr, + struct ftrace_graph_ret *trace, + unsigned long flags, int pc); + + +#ifdef CONFIG_DYNAMIC_FTRACE +/* TODO: make this variable */ +#define FTRACE_GRAPH_MAX_FUNCS 32 +extern int ftrace_graph_count; +extern unsigned long ftrace_graph_funcs[FTRACE_GRAPH_MAX_FUNCS]; +extern int ftrace_graph_notrace_count; +extern unsigned long ftrace_graph_notrace_funcs[FTRACE_GRAPH_MAX_FUNCS]; + +static inline int ftrace_graph_addr(unsigned long addr) +{ + int i; + + if (!ftrace_graph_count) + return 1; + + for (i = 0; i < ftrace_graph_count; i++) { + if (addr == ftrace_graph_funcs[i]) { + /* + * If no irqs are to be traced, but a set_graph_function + * is set, and called by an interrupt handler, we still + * want to trace it. + */ + if (in_irq()) + trace_recursion_set(TRACE_IRQ_BIT); + else + trace_recursion_clear(TRACE_IRQ_BIT); + return 1; + } + } + + return 0; +} + +static inline int ftrace_graph_notrace_addr(unsigned long addr) +{ + int i; + + if (!ftrace_graph_notrace_count) + return 0; + + for (i = 0; i < ftrace_graph_notrace_count; i++) { + if (addr == ftrace_graph_notrace_funcs[i]) + return 1; + } + + return 0; +} +#else +static inline int ftrace_graph_addr(unsigned long addr) +{ + return 1; +} + +static inline int ftrace_graph_notrace_addr(unsigned long addr) +{ + return 0; +} +#endif /* CONFIG_DYNAMIC_FTRACE */ +#else /* CONFIG_FUNCTION_GRAPH_TRACER */ +static inline enum print_line_t +print_graph_function_flags(struct trace_iterator *iter, u32 flags) +{ + return TRACE_TYPE_UNHANDLED; +} +#endif /* CONFIG_FUNCTION_GRAPH_TRACER */ + +extern struct list_head ftrace_pids; + +#ifdef CONFIG_FUNCTION_TRACER +extern bool ftrace_filter_param __initdata; +static inline int ftrace_trace_task(struct task_struct *task) +{ + if (list_empty(&ftrace_pids)) + return 1; + + return test_tsk_trace_trace(task); +} +extern int ftrace_is_dead(void); +int ftrace_create_function_files(struct trace_array *tr, + struct dentry *parent); +void ftrace_destroy_function_files(struct trace_array *tr); +void ftrace_init_global_array_ops(struct trace_array *tr); +void ftrace_init_array_ops(struct trace_array *tr, ftrace_func_t func); +void ftrace_reset_array_ops(struct trace_array *tr); +int using_ftrace_ops_list_func(void); +#else +static inline int ftrace_trace_task(struct task_struct *task) +{ + return 1; +} +static inline int ftrace_is_dead(void) { return 0; } +static inline int +ftrace_create_function_files(struct trace_array *tr, + struct dentry *parent) +{ + return 0; +} +static inline void ftrace_destroy_function_files(struct trace_array *tr) { } +static inline __init void +ftrace_init_global_array_ops(struct trace_array *tr) { } +static inline void ftrace_reset_array_ops(struct trace_array *tr) { } +/* ftace_func_t type is not defined, use macro instead of static inline */ +#define ftrace_init_array_ops(tr, func) do { } while (0) +#endif /* CONFIG_FUNCTION_TRACER */ + +#if defined(CONFIG_FUNCTION_TRACER) && defined(CONFIG_DYNAMIC_FTRACE) +void ftrace_create_filter_files(struct ftrace_ops *ops, + struct dentry *parent); +void ftrace_destroy_filter_files(struct ftrace_ops *ops); +#else +/* + * The ops parameter passed in is usually undefined. + * This must be a macro. + */ +#define ftrace_create_filter_files(ops, parent) do { } while (0) +#define ftrace_destroy_filter_files(ops) do { } while (0) +#endif /* CONFIG_FUNCTION_TRACER && CONFIG_DYNAMIC_FTRACE */ + +int ftrace_event_is_function(struct ftrace_event_call *call); + +/* + * struct trace_parser - servers for reading the user input separated by spaces + * @cont: set if the input is not complete - no final space char was found + * @buffer: holds the parsed user input + * @idx: user input length + * @size: buffer size + */ +struct trace_parser { + bool cont; + char *buffer; + unsigned idx; + unsigned size; +}; + +static inline bool trace_parser_loaded(struct trace_parser *parser) +{ + return (parser->idx != 0); +} + +static inline bool trace_parser_cont(struct trace_parser *parser) +{ + return parser->cont; +} + +static inline void trace_parser_clear(struct trace_parser *parser) +{ + parser->cont = false; + parser->idx = 0; +} + +extern int trace_parser_get_init(struct trace_parser *parser, int size); +extern void trace_parser_put(struct trace_parser *parser); +extern int trace_get_user(struct trace_parser *parser, const char __user *ubuf, + size_t cnt, loff_t *ppos); + +/* + * trace_iterator_flags is an enumeration that defines bit + * positions into trace_flags that controls the output. + * + * NOTE: These bits must match the trace_options array in + * trace.c. + */ +enum trace_iterator_flags { + TRACE_ITER_PRINT_PARENT = 0x01, + TRACE_ITER_SYM_OFFSET = 0x02, + TRACE_ITER_SYM_ADDR = 0x04, + TRACE_ITER_VERBOSE = 0x08, + TRACE_ITER_RAW = 0x10, + TRACE_ITER_HEX = 0x20, + TRACE_ITER_BIN = 0x40, + TRACE_ITER_BLOCK = 0x80, + TRACE_ITER_STACKTRACE = 0x100, + TRACE_ITER_PRINTK = 0x200, + TRACE_ITER_PREEMPTONLY = 0x400, + TRACE_ITER_BRANCH = 0x800, + TRACE_ITER_ANNOTATE = 0x1000, + TRACE_ITER_USERSTACKTRACE = 0x2000, + TRACE_ITER_SYM_USEROBJ = 0x4000, + TRACE_ITER_PRINTK_MSGONLY = 0x8000, + TRACE_ITER_CONTEXT_INFO = 0x10000, /* Print pid/cpu/time */ + TRACE_ITER_LATENCY_FMT = 0x20000, + TRACE_ITER_SLEEP_TIME = 0x40000, + TRACE_ITER_GRAPH_TIME = 0x80000, + TRACE_ITER_RECORD_CMD = 0x100000, + TRACE_ITER_OVERWRITE = 0x200000, + TRACE_ITER_STOP_ON_FREE = 0x400000, + TRACE_ITER_IRQ_INFO = 0x800000, + TRACE_ITER_MARKERS = 0x1000000, + TRACE_ITER_FUNCTION = 0x2000000, +}; + +/* + * TRACE_ITER_SYM_MASK masks the options in trace_flags that + * control the output of kernel symbols. + */ +#define TRACE_ITER_SYM_MASK \ + (TRACE_ITER_PRINT_PARENT|TRACE_ITER_SYM_OFFSET|TRACE_ITER_SYM_ADDR) + +extern struct tracer nop_trace; + +#ifdef CONFIG_BRANCH_TRACER +extern int enable_branch_tracing(struct trace_array *tr); +extern void disable_branch_tracing(void); +static inline int trace_branch_enable(struct trace_array *tr) +{ + if (trace_flags & TRACE_ITER_BRANCH) + return enable_branch_tracing(tr); + return 0; +} +static inline void trace_branch_disable(void) +{ + /* due to races, always disable */ + disable_branch_tracing(); +} +#else +static inline int trace_branch_enable(struct trace_array *tr) +{ + return 0; +} +static inline void trace_branch_disable(void) +{ +} +#endif /* CONFIG_BRANCH_TRACER */ + +/* set ring buffers to default size if not already done so */ +int tracing_update_buffers(void); + +struct ftrace_event_field { + struct list_head link; + const char *name; + const char *type; + int filter_type; + int offset; + int size; + int is_signed; +}; + +struct event_filter { + int n_preds; /* Number assigned */ + int a_preds; /* allocated */ + struct filter_pred *preds; + struct filter_pred *root; + char *filter_string; +}; + +struct event_subsystem { + struct list_head list; + const char *name; + struct event_filter *filter; + int ref_count; +}; + +struct ftrace_subsystem_dir { + struct list_head list; + struct event_subsystem *subsystem; + struct trace_array *tr; + struct dentry *entry; + int ref_count; + int nr_events; +}; + +#define FILTER_PRED_INVALID ((unsigned short)-1) +#define FILTER_PRED_IS_RIGHT (1 << 15) +#define FILTER_PRED_FOLD (1 << 15) + +/* + * The max preds is the size of unsigned short with + * two flags at the MSBs. One bit is used for both the IS_RIGHT + * and FOLD flags. The other is reserved. + * + * 2^14 preds is way more than enough. + */ +#define MAX_FILTER_PRED 16384 + +struct filter_pred; +struct regex; + +typedef int (*filter_pred_fn_t) (struct filter_pred *pred, void *event); + +typedef int (*regex_match_func)(char *str, struct regex *r, int len); + +enum regex_type { + MATCH_FULL = 0, + MATCH_FRONT_ONLY, + MATCH_MIDDLE_ONLY, + MATCH_END_ONLY, +}; + +struct regex { + char pattern[MAX_FILTER_STR_VAL]; + int len; + int field_len; + regex_match_func match; +}; + +struct filter_pred { + filter_pred_fn_t fn; + u64 val; + struct regex regex; + unsigned short *ops; + struct ftrace_event_field *field; + int offset; + int not; + int op; + unsigned short index; + unsigned short parent; + unsigned short left; + unsigned short right; +}; + +extern enum regex_type +filter_parse_regex(char *buff, int len, char **search, int *not); +extern void print_event_filter(struct ftrace_event_file *file, + struct trace_seq *s); +extern int apply_event_filter(struct ftrace_event_file *file, + char *filter_string); +extern int apply_subsystem_event_filter(struct ftrace_subsystem_dir *dir, + char *filter_string); +extern void print_subsystem_event_filter(struct event_subsystem *system, + struct trace_seq *s); +extern int filter_assign_type(const char *type); +extern int create_event_filter(struct ftrace_event_call *call, + char *filter_str, bool set_str, + struct event_filter **filterp); +extern void free_event_filter(struct event_filter *filter); + +struct ftrace_event_field * +trace_find_event_field(struct ftrace_event_call *call, char *name); + +extern void trace_event_enable_cmd_record(bool enable); +extern int event_trace_add_tracer(struct dentry *parent, struct trace_array *tr); +extern int event_trace_del_tracer(struct trace_array *tr); + +extern struct ftrace_event_file *find_event_file(struct trace_array *tr, + const char *system, + const char *event); + +static inline void *event_file_data(struct file *filp) +{ + return ACCESS_ONCE(file_inode(filp)->i_private); +} + +extern struct mutex event_mutex; +extern struct list_head ftrace_events; + +extern const struct file_operations event_trigger_fops; + +extern int register_trigger_cmds(void); +extern void clear_event_triggers(struct trace_array *tr); + +struct event_trigger_data { + unsigned long count; + int ref; + struct event_trigger_ops *ops; + struct event_command *cmd_ops; + struct event_filter __rcu *filter; + char *filter_str; + void *private_data; + struct list_head list; +}; + +/** + * struct event_trigger_ops - callbacks for trace event triggers + * + * The methods in this structure provide per-event trigger hooks for + * various trigger operations. + * + * All the methods below, except for @init() and @free(), must be + * implemented. + * + * @func: The trigger 'probe' function called when the triggering + * event occurs. The data passed into this callback is the data + * that was supplied to the event_command @reg() function that + * registered the trigger (see struct event_command). + * + * @init: An optional initialization function called for the trigger + * when the trigger is registered (via the event_command reg() + * function). This can be used to perform per-trigger + * initialization such as incrementing a per-trigger reference + * count, for instance. This is usually implemented by the + * generic utility function @event_trigger_init() (see + * trace_event_triggers.c). + * + * @free: An optional de-initialization function called for the + * trigger when the trigger is unregistered (via the + * event_command @reg() function). This can be used to perform + * per-trigger de-initialization such as decrementing a + * per-trigger reference count and freeing corresponding trigger + * data, for instance. This is usually implemented by the + * generic utility function @event_trigger_free() (see + * trace_event_triggers.c). + * + * @print: The callback function invoked to have the trigger print + * itself. This is usually implemented by a wrapper function + * that calls the generic utility function @event_trigger_print() + * (see trace_event_triggers.c). + */ +struct event_trigger_ops { + void (*func)(struct event_trigger_data *data); + int (*init)(struct event_trigger_ops *ops, + struct event_trigger_data *data); + void (*free)(struct event_trigger_ops *ops, + struct event_trigger_data *data); + int (*print)(struct seq_file *m, + struct event_trigger_ops *ops, + struct event_trigger_data *data); +}; + +/** + * struct event_command - callbacks and data members for event commands + * + * Event commands are invoked by users by writing the command name + * into the 'trigger' file associated with a trace event. The + * parameters associated with a specific invocation of an event + * command are used to create an event trigger instance, which is + * added to the list of trigger instances associated with that trace + * event. When the event is hit, the set of triggers associated with + * that event is invoked. + * + * The data members in this structure provide per-event command data + * for various event commands. + * + * All the data members below, except for @post_trigger, must be set + * for each event command. + * + * @name: The unique name that identifies the event command. This is + * the name used when setting triggers via trigger files. + * + * @trigger_type: A unique id that identifies the event command + * 'type'. This value has two purposes, the first to ensure that + * only one trigger of the same type can be set at a given time + * for a particular event e.g. it doesn't make sense to have both + * a traceon and traceoff trigger attached to a single event at + * the same time, so traceon and traceoff have the same type + * though they have different names. The @trigger_type value is + * also used as a bit value for deferring the actual trigger + * action until after the current event is finished. Some + * commands need to do this if they themselves log to the trace + * buffer (see the @post_trigger() member below). @trigger_type + * values are defined by adding new values to the trigger_type + * enum in include/linux/ftrace_event.h. + * + * @post_trigger: A flag that says whether or not this command needs + * to have its action delayed until after the current event has + * been closed. Some triggers need to avoid being invoked while + * an event is currently in the process of being logged, since + * the trigger may itself log data into the trace buffer. Thus + * we make sure the current event is committed before invoking + * those triggers. To do that, the trigger invocation is split + * in two - the first part checks the filter using the current + * trace record; if a command has the @post_trigger flag set, it + * sets a bit for itself in the return value, otherwise it + * directly invokes the trigger. Once all commands have been + * either invoked or set their return flag, the current record is + * either committed or discarded. At that point, if any commands + * have deferred their triggers, those commands are finally + * invoked following the close of the current event. In other + * words, if the event_trigger_ops @func() probe implementation + * itself logs to the trace buffer, this flag should be set, + * otherwise it can be left unspecified. + * + * All the methods below, except for @set_filter(), must be + * implemented. + * + * @func: The callback function responsible for parsing and + * registering the trigger written to the 'trigger' file by the + * user. It allocates the trigger instance and registers it with + * the appropriate trace event. It makes use of the other + * event_command callback functions to orchestrate this, and is + * usually implemented by the generic utility function + * @event_trigger_callback() (see trace_event_triggers.c). + * + * @reg: Adds the trigger to the list of triggers associated with the + * event, and enables the event trigger itself, after + * initializing it (via the event_trigger_ops @init() function). + * This is also where commands can use the @trigger_type value to + * make the decision as to whether or not multiple instances of + * the trigger should be allowed. This is usually implemented by + * the generic utility function @register_trigger() (see + * trace_event_triggers.c). + * + * @unreg: Removes the trigger from the list of triggers associated + * with the event, and disables the event trigger itself, after + * initializing it (via the event_trigger_ops @free() function). + * This is usually implemented by the generic utility function + * @unregister_trigger() (see trace_event_triggers.c). + * + * @set_filter: An optional function called to parse and set a filter + * for the trigger. If no @set_filter() method is set for the + * event command, filters set by the user for the command will be + * ignored. This is usually implemented by the generic utility + * function @set_trigger_filter() (see trace_event_triggers.c). + * + * @get_trigger_ops: The callback function invoked to retrieve the + * event_trigger_ops implementation associated with the command. + */ +struct event_command { + struct list_head list; + char *name; + enum event_trigger_type trigger_type; + bool post_trigger; + int (*func)(struct event_command *cmd_ops, + struct ftrace_event_file *file, + char *glob, char *cmd, char *params); + int (*reg)(char *glob, + struct event_trigger_ops *ops, + struct event_trigger_data *data, + struct ftrace_event_file *file); + void (*unreg)(char *glob, + struct event_trigger_ops *ops, + struct event_trigger_data *data, + struct ftrace_event_file *file); + int (*set_filter)(char *filter_str, + struct event_trigger_data *data, + struct ftrace_event_file *file); + struct event_trigger_ops *(*get_trigger_ops)(char *cmd, char *param); +}; + +extern int trace_event_enable_disable(struct ftrace_event_file *file, + int enable, int soft_disable); +extern int tracing_alloc_snapshot(void); + +extern const char *__start___trace_bprintk_fmt[]; +extern const char *__stop___trace_bprintk_fmt[]; + +extern const char *__start___tracepoint_str[]; +extern const char *__stop___tracepoint_str[]; + +void trace_printk_init_buffers(void); +void trace_printk_start_comm(void); +int trace_keep_overwrite(struct tracer *tracer, u32 mask, int set); +int set_tracer_flag(struct trace_array *tr, unsigned int mask, int enabled); + +/* + * Normal trace_printk() and friends allocates special buffers + * to do the manipulation, as well as saves the print formats + * into sections to display. But the trace infrastructure wants + * to use these without the added overhead at the price of being + * a bit slower (used mainly for warnings, where we don't care + * about performance). The internal_trace_puts() is for such + * a purpose. + */ +#define internal_trace_puts(str) __trace_puts(_THIS_IP_, str, strlen(str)) + +#undef FTRACE_ENTRY +#define FTRACE_ENTRY(call, struct_name, id, tstruct, print, filter) \ + extern struct ftrace_event_call \ + __aligned(4) event_##call; +#undef FTRACE_ENTRY_DUP +#define FTRACE_ENTRY_DUP(call, struct_name, id, tstruct, print, filter) \ + FTRACE_ENTRY(call, struct_name, id, PARAMS(tstruct), PARAMS(print), \ + filter) +#include "trace_entries.h" + +#if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_FUNCTION_TRACER) +int perf_ftrace_event_register(struct ftrace_event_call *call, + enum trace_reg type, void *data); +#else +#define perf_ftrace_event_register NULL +#endif + +#ifdef CONFIG_FTRACE_SYSCALLS +void init_ftrace_syscalls(void); +#else +static inline void init_ftrace_syscalls(void) { } +#endif + +#ifdef CONFIG_EVENT_TRACING +void trace_event_init(void); +void trace_event_enum_update(struct trace_enum_map **map, int len); +#else +static inline void __init trace_event_init(void) { } +static inlin void trace_event_enum_update(struct trace_enum_map **map, int len) { } +#endif + +extern struct trace_iterator *tracepoint_print_iter; + +#endif /* _LINUX_KERNEL_TRACE_H */ diff --git a/kernel/kernel/trace/trace_benchmark.c b/kernel/kernel/trace/trace_benchmark.c new file mode 100644 index 000000000..40a14cbcf --- /dev/null +++ b/kernel/kernel/trace/trace_benchmark.c @@ -0,0 +1,198 @@ +#include +#include +#include +#include + +#define CREATE_TRACE_POINTS +#include "trace_benchmark.h" + +static struct task_struct *bm_event_thread; + +static char bm_str[BENCHMARK_EVENT_STRLEN] = "START"; + +static u64 bm_total; +static u64 bm_totalsq; +static u64 bm_last; +static u64 bm_max; +static u64 bm_min; +static u64 bm_first; +static u64 bm_cnt; +static u64 bm_stddev; +static unsigned int bm_avg; +static unsigned int bm_std; + +/* + * This gets called in a loop recording the time it took to write + * the tracepoint. What it writes is the time statistics of the last + * tracepoint write. As there is nothing to write the first time + * it simply writes "START". As the first write is cold cache and + * the rest is hot, we save off that time in bm_first and it is + * reported as "first", which is shown in the second write to the + * tracepoint. The "first" field is writen within the statics from + * then on but never changes. + */ +static void trace_do_benchmark(void) +{ + u64 start; + u64 stop; + u64 delta; + u64 stddev; + u64 seed; + u64 last_seed; + unsigned int avg; + unsigned int std = 0; + + /* Only run if the tracepoint is actually active */ + if (!trace_benchmark_event_enabled()) + return; + + local_irq_disable(); + start = trace_clock_local(); + trace_benchmark_event(bm_str); + stop = trace_clock_local(); + local_irq_enable(); + + bm_cnt++; + + delta = stop - start; + + /* + * The first read is cold cached, keep it separate from the + * other calculations. + */ + if (bm_cnt == 1) { + bm_first = delta; + scnprintf(bm_str, BENCHMARK_EVENT_STRLEN, + "first=%llu [COLD CACHED]", bm_first); + return; + } + + bm_last = delta; + + if (delta > bm_max) + bm_max = delta; + if (!bm_min || delta < bm_min) + bm_min = delta; + + /* + * When bm_cnt is greater than UINT_MAX, it breaks the statistics + * accounting. Freeze the statistics when that happens. + * We should have enough data for the avg and stddev anyway. + */ + if (bm_cnt > UINT_MAX) { + scnprintf(bm_str, BENCHMARK_EVENT_STRLEN, + "last=%llu first=%llu max=%llu min=%llu ** avg=%u std=%d std^2=%lld", + bm_last, bm_first, bm_max, bm_min, bm_avg, bm_std, bm_stddev); + return; + } + + bm_total += delta; + bm_totalsq += delta * delta; + + + if (bm_cnt > 1) { + /* + * Apply Welford's method to calculate standard deviation: + * s^2 = 1 / (n * (n-1)) * (n * \Sum (x_i)^2 - (\Sum x_i)^2) + */ + stddev = (u64)bm_cnt * bm_totalsq - bm_total * bm_total; + do_div(stddev, (u32)bm_cnt); + do_div(stddev, (u32)bm_cnt - 1); + } else + stddev = 0; + + delta = bm_total; + do_div(delta, bm_cnt); + avg = delta; + + if (stddev > 0) { + int i = 0; + /* + * stddev is the square of standard deviation but + * we want the actualy number. Use the average + * as our seed to find the std. + * + * The next try is: + * x = (x + N/x) / 2 + * + * Where N is the squared number to find the square + * root of. + */ + seed = avg; + do { + last_seed = seed; + seed = stddev; + if (!last_seed) + break; + do_div(seed, last_seed); + seed += last_seed; + do_div(seed, 2); + } while (i++ < 10 && last_seed != seed); + + std = seed; + } + + scnprintf(bm_str, BENCHMARK_EVENT_STRLEN, + "last=%llu first=%llu max=%llu min=%llu avg=%u std=%d std^2=%lld", + bm_last, bm_first, bm_max, bm_min, avg, std, stddev); + + bm_std = std; + bm_avg = avg; + bm_stddev = stddev; +} + +static int benchmark_event_kthread(void *arg) +{ + /* sleep a bit to make sure the tracepoint gets activated */ + msleep(100); + + while (!kthread_should_stop()) { + + trace_do_benchmark(); + + /* + * We don't go to sleep, but let others + * run as well. + */ + cond_resched(); + } + + return 0; +} + +/* + * When the benchmark tracepoint is enabled, it calls this + * function and the thread that calls the tracepoint is created. + */ +void trace_benchmark_reg(void) +{ + bm_event_thread = kthread_run(benchmark_event_kthread, + NULL, "event_benchmark"); + WARN_ON(!bm_event_thread); +} + +/* + * When the benchmark tracepoint is disabled, it calls this + * function and the thread that calls the tracepoint is deleted + * and all the numbers are reset. + */ +void trace_benchmark_unreg(void) +{ + if (!bm_event_thread) + return; + + kthread_stop(bm_event_thread); + + strcpy(bm_str, "START"); + bm_total = 0; + bm_totalsq = 0; + bm_last = 0; + bm_max = 0; + bm_min = 0; + bm_cnt = 0; + /* These don't need to be reset but reset them anyway */ + bm_first = 0; + bm_std = 0; + bm_avg = 0; + bm_stddev = 0; +} diff --git a/kernel/kernel/trace/trace_benchmark.h b/kernel/kernel/trace/trace_benchmark.h new file mode 100644 index 000000000..3c1df1df4 --- /dev/null +++ b/kernel/kernel/trace/trace_benchmark.h @@ -0,0 +1,41 @@ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM benchmark + +#if !defined(_TRACE_BENCHMARK_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_BENCHMARK_H + +#include + +extern void trace_benchmark_reg(void); +extern void trace_benchmark_unreg(void); + +#define BENCHMARK_EVENT_STRLEN 128 + +TRACE_EVENT_FN(benchmark_event, + + TP_PROTO(const char *str), + + TP_ARGS(str), + + TP_STRUCT__entry( + __array( char, str, BENCHMARK_EVENT_STRLEN ) + ), + + TP_fast_assign( + memcpy(__entry->str, str, BENCHMARK_EVENT_STRLEN); + ), + + TP_printk("%s", __entry->str), + + trace_benchmark_reg, trace_benchmark_unreg +); + +#endif /* _TRACE_BENCHMARK_H */ + +#undef TRACE_INCLUDE_FILE +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH . +#define TRACE_INCLUDE_FILE trace_benchmark + +/* This part must be outside protection */ +#include diff --git a/kernel/kernel/trace/trace_branch.c b/kernel/kernel/trace/trace_branch.c new file mode 100644 index 000000000..57cbf1efd --- /dev/null +++ b/kernel/kernel/trace/trace_branch.c @@ -0,0 +1,411 @@ +/* + * unlikely profiler + * + * Copyright (C) 2008 Steven Rostedt + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "trace.h" +#include "trace_stat.h" +#include "trace_output.h" + +#ifdef CONFIG_BRANCH_TRACER + +static struct tracer branch_trace; +static int branch_tracing_enabled __read_mostly; +static DEFINE_MUTEX(branch_tracing_mutex); + +static struct trace_array *branch_tracer; + +static void +probe_likely_condition(struct ftrace_branch_data *f, int val, int expect) +{ + struct ftrace_event_call *call = &event_branch; + struct trace_array *tr = branch_tracer; + struct trace_array_cpu *data; + struct ring_buffer_event *event; + struct trace_branch *entry; + struct ring_buffer *buffer; + unsigned long flags; + int cpu, pc; + const char *p; + + /* + * I would love to save just the ftrace_likely_data pointer, but + * this code can also be used by modules. Ugly things can happen + * if the module is unloaded, and then we go and read the + * pointer. This is slower, but much safer. + */ + + if (unlikely(!tr)) + return; + + local_irq_save(flags); + cpu = raw_smp_processor_id(); + data = per_cpu_ptr(tr->trace_buffer.data, cpu); + if (atomic_inc_return(&data->disabled) != 1) + goto out; + + pc = preempt_count(); + buffer = tr->trace_buffer.buffer; + event = trace_buffer_lock_reserve(buffer, TRACE_BRANCH, + sizeof(*entry), flags, pc); + if (!event) + goto out; + + entry = ring_buffer_event_data(event); + + /* Strip off the path, only save the file */ + p = f->file + strlen(f->file); + while (p >= f->file && *p != '/') + p--; + p++; + + strncpy(entry->func, f->func, TRACE_FUNC_SIZE); + strncpy(entry->file, p, TRACE_FILE_SIZE); + entry->func[TRACE_FUNC_SIZE] = 0; + entry->file[TRACE_FILE_SIZE] = 0; + entry->line = f->line; + entry->correct = val == expect; + + if (!call_filter_check_discard(call, entry, buffer, event)) + __buffer_unlock_commit(buffer, event); + + out: + atomic_dec(&data->disabled); + local_irq_restore(flags); +} + +static inline +void trace_likely_condition(struct ftrace_branch_data *f, int val, int expect) +{ + if (!branch_tracing_enabled) + return; + + probe_likely_condition(f, val, expect); +} + +int enable_branch_tracing(struct trace_array *tr) +{ + mutex_lock(&branch_tracing_mutex); + branch_tracer = tr; + /* + * Must be seen before enabling. The reader is a condition + * where we do not need a matching rmb() + */ + smp_wmb(); + branch_tracing_enabled++; + mutex_unlock(&branch_tracing_mutex); + + return 0; +} + +void disable_branch_tracing(void) +{ + mutex_lock(&branch_tracing_mutex); + + if (!branch_tracing_enabled) + goto out_unlock; + + branch_tracing_enabled--; + + out_unlock: + mutex_unlock(&branch_tracing_mutex); +} + +static void start_branch_trace(struct trace_array *tr) +{ + enable_branch_tracing(tr); +} + +static void stop_branch_trace(struct trace_array *tr) +{ + disable_branch_tracing(); +} + +static int branch_trace_init(struct trace_array *tr) +{ + start_branch_trace(tr); + return 0; +} + +static void branch_trace_reset(struct trace_array *tr) +{ + stop_branch_trace(tr); +} + +static enum print_line_t trace_branch_print(struct trace_iterator *iter, + int flags, struct trace_event *event) +{ + struct trace_branch *field; + + trace_assign_type(field, iter->ent); + + trace_seq_printf(&iter->seq, "[%s] %s:%s:%d\n", + field->correct ? " ok " : " MISS ", + field->func, + field->file, + field->line); + + return trace_handle_return(&iter->seq); +} + +static void branch_print_header(struct seq_file *s) +{ + seq_puts(s, "# TASK-PID CPU# TIMESTAMP CORRECT" + " FUNC:FILE:LINE\n" + "# | | | | | " + " |\n"); +} + +static struct trace_event_functions trace_branch_funcs = { + .trace = trace_branch_print, +}; + +static struct trace_event trace_branch_event = { + .type = TRACE_BRANCH, + .funcs = &trace_branch_funcs, +}; + +static struct tracer branch_trace __read_mostly = +{ + .name = "branch", + .init = branch_trace_init, + .reset = branch_trace_reset, +#ifdef CONFIG_FTRACE_SELFTEST + .selftest = trace_selftest_startup_branch, +#endif /* CONFIG_FTRACE_SELFTEST */ + .print_header = branch_print_header, +}; + +__init static int init_branch_tracer(void) +{ + int ret; + + ret = register_ftrace_event(&trace_branch_event); + if (!ret) { + printk(KERN_WARNING "Warning: could not register " + "branch events\n"); + return 1; + } + return register_tracer(&branch_trace); +} +core_initcall(init_branch_tracer); + +#else +static inline +void trace_likely_condition(struct ftrace_branch_data *f, int val, int expect) +{ +} +#endif /* CONFIG_BRANCH_TRACER */ + +void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect) +{ + /* + * I would love to have a trace point here instead, but the + * trace point code is so inundated with unlikely and likely + * conditions that the recursive nightmare that exists is too + * much to try to get working. At least for now. + */ + trace_likely_condition(f, val, expect); + + /* FIXME: Make this atomic! */ + if (val == expect) + f->correct++; + else + f->incorrect++; +} +EXPORT_SYMBOL(ftrace_likely_update); + +extern unsigned long __start_annotated_branch_profile[]; +extern unsigned long __stop_annotated_branch_profile[]; + +static int annotated_branch_stat_headers(struct seq_file *m) +{ + seq_puts(m, " correct incorrect % " + " Function " + " File Line\n" + " ------- --------- - " + " -------- " + " ---- ----\n"); + return 0; +} + +static inline long get_incorrect_percent(struct ftrace_branch_data *p) +{ + long percent; + + if (p->correct) { + percent = p->incorrect * 100; + percent /= p->correct + p->incorrect; + } else + percent = p->incorrect ? 100 : -1; + + return percent; +} + +static int branch_stat_show(struct seq_file *m, void *v) +{ + struct ftrace_branch_data *p = v; + const char *f; + long percent; + + /* Only print the file, not the path */ + f = p->file + strlen(p->file); + while (f >= p->file && *f != '/') + f--; + f++; + + /* + * The miss is overlayed on correct, and hit on incorrect. + */ + percent = get_incorrect_percent(p); + + seq_printf(m, "%8lu %8lu ", p->correct, p->incorrect); + if (percent < 0) + seq_puts(m, " X "); + else + seq_printf(m, "%3ld ", percent); + seq_printf(m, "%-30.30s %-20.20s %d\n", p->func, f, p->line); + return 0; +} + +static void *annotated_branch_stat_start(struct tracer_stat *trace) +{ + return __start_annotated_branch_profile; +} + +static void * +annotated_branch_stat_next(void *v, int idx) +{ + struct ftrace_branch_data *p = v; + + ++p; + + if ((void *)p >= (void *)__stop_annotated_branch_profile) + return NULL; + + return p; +} + +static int annotated_branch_stat_cmp(void *p1, void *p2) +{ + struct ftrace_branch_data *a = p1; + struct ftrace_branch_data *b = p2; + + long percent_a, percent_b; + + percent_a = get_incorrect_percent(a); + percent_b = get_incorrect_percent(b); + + if (percent_a < percent_b) + return -1; + if (percent_a > percent_b) + return 1; + + if (a->incorrect < b->incorrect) + return -1; + if (a->incorrect > b->incorrect) + return 1; + + /* + * Since the above shows worse (incorrect) cases + * first, we continue that by showing best (correct) + * cases last. + */ + if (a->correct > b->correct) + return -1; + if (a->correct < b->correct) + return 1; + + return 0; +} + +static struct tracer_stat annotated_branch_stats = { + .name = "branch_annotated", + .stat_start = annotated_branch_stat_start, + .stat_next = annotated_branch_stat_next, + .stat_cmp = annotated_branch_stat_cmp, + .stat_headers = annotated_branch_stat_headers, + .stat_show = branch_stat_show +}; + +__init static int init_annotated_branch_stats(void) +{ + int ret; + + ret = register_stat_tracer(&annotated_branch_stats); + if (!ret) { + printk(KERN_WARNING "Warning: could not register " + "annotated branches stats\n"); + return 1; + } + return 0; +} +fs_initcall(init_annotated_branch_stats); + +#ifdef CONFIG_PROFILE_ALL_BRANCHES + +extern unsigned long __start_branch_profile[]; +extern unsigned long __stop_branch_profile[]; + +static int all_branch_stat_headers(struct seq_file *m) +{ + seq_puts(m, " miss hit % " + " Function " + " File Line\n" + " ------- --------- - " + " -------- " + " ---- ----\n"); + return 0; +} + +static void *all_branch_stat_start(struct tracer_stat *trace) +{ + return __start_branch_profile; +} + +static void * +all_branch_stat_next(void *v, int idx) +{ + struct ftrace_branch_data *p = v; + + ++p; + + if ((void *)p >= (void *)__stop_branch_profile) + return NULL; + + return p; +} + +static struct tracer_stat all_branch_stats = { + .name = "branch_all", + .stat_start = all_branch_stat_start, + .stat_next = all_branch_stat_next, + .stat_headers = all_branch_stat_headers, + .stat_show = branch_stat_show +}; + +__init static int all_annotated_branch_stats(void) +{ + int ret; + + ret = register_stat_tracer(&all_branch_stats); + if (!ret) { + printk(KERN_WARNING "Warning: could not register " + "all branches stats\n"); + return 1; + } + return 0; +} +fs_initcall(all_annotated_branch_stats); +#endif /* CONFIG_PROFILE_ALL_BRANCHES */ diff --git a/kernel/kernel/trace/trace_clock.c b/kernel/kernel/trace/trace_clock.c new file mode 100644 index 000000000..57b67b1f2 --- /dev/null +++ b/kernel/kernel/trace/trace_clock.c @@ -0,0 +1,137 @@ +/* + * tracing clocks + * + * Copyright (C) 2009 Red Hat, Inc., Ingo Molnar + * + * Implements 3 trace clock variants, with differing scalability/precision + * tradeoffs: + * + * - local: CPU-local trace clock + * - medium: scalable global clock with some jitter + * - global: globally monotonic, serialized clock + * + * Tracer plugins will chose a default from these clocks. + */ +#include +#include +#include +#include +#include +#include +#include +#include + +/* + * trace_clock_local(): the simplest and least coherent tracing clock. + * + * Useful for tracing that does not cross to other CPUs nor + * does it go through idle events. + */ +u64 notrace trace_clock_local(void) +{ + u64 clock; + + /* + * sched_clock() is an architecture implemented, fast, scalable, + * lockless clock. It is not guaranteed to be coherent across + * CPUs, nor across CPU idle events. + */ + preempt_disable_notrace(); + clock = sched_clock(); + preempt_enable_notrace(); + + return clock; +} +EXPORT_SYMBOL_GPL(trace_clock_local); + +/* + * trace_clock(): 'between' trace clock. Not completely serialized, + * but not completely incorrect when crossing CPUs either. + * + * This is based on cpu_clock(), which will allow at most ~1 jiffy of + * jitter between CPUs. So it's a pretty scalable clock, but there + * can be offsets in the trace data. + */ +u64 notrace trace_clock(void) +{ + return local_clock(); +} + +/* + * trace_jiffy_clock(): Simply use jiffies as a clock counter. + * Note that this use of jiffies_64 is not completely safe on + * 32-bit systems. But the window is tiny, and the effect if + * we are affected is that we will have an obviously bogus + * timestamp on a trace event - i.e. not life threatening. + */ +u64 notrace trace_clock_jiffies(void) +{ + return jiffies_64_to_clock_t(jiffies_64 - INITIAL_JIFFIES); +} + +/* + * trace_clock_global(): special globally coherent trace clock + * + * It has higher overhead than the other trace clocks but is still + * an order of magnitude faster than GTOD derived hardware clocks. + * + * Used by plugins that need globally coherent timestamps. + */ + +/* keep prev_time and lock in the same cacheline. */ +static struct { + u64 prev_time; + arch_spinlock_t lock; +} trace_clock_struct ____cacheline_aligned_in_smp = + { + .lock = (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED, + }; + +u64 notrace trace_clock_global(void) +{ + unsigned long flags; + int this_cpu; + u64 now; + + local_irq_save(flags); + + this_cpu = raw_smp_processor_id(); + now = sched_clock_cpu(this_cpu); + /* + * If in an NMI context then dont risk lockups and return the + * cpu_clock() time: + */ + if (unlikely(in_nmi())) + goto out; + + arch_spin_lock(&trace_clock_struct.lock); + + /* + * TODO: if this happens often then maybe we should reset + * my_scd->clock to prev_time+1, to make sure + * we start ticking with the local clock from now on? + */ + if ((s64)(now - trace_clock_struct.prev_time) < 0) + now = trace_clock_struct.prev_time + 1; + + trace_clock_struct.prev_time = now; + + arch_spin_unlock(&trace_clock_struct.lock); + + out: + local_irq_restore(flags); + + return now; +} + +static atomic64_t trace_counter; + +/* + * trace_clock_counter(): simply an atomic counter. + * Use the trace_counter "counter" for cases where you do not care + * about timings, but are interested in strict ordering. + */ +u64 notrace trace_clock_counter(void) +{ + return atomic64_add_return(1, &trace_counter); +} diff --git a/kernel/kernel/trace/trace_entries.h b/kernel/kernel/trace/trace_entries.h new file mode 100644 index 000000000..ee7b94a48 --- /dev/null +++ b/kernel/kernel/trace/trace_entries.h @@ -0,0 +1,324 @@ +/* + * This file defines the trace event structures that go into the ring + * buffer directly. They are created via macros so that changes for them + * appear in the format file. Using macros will automate this process. + * + * The macro used to create a ftrace data structure is: + * + * FTRACE_ENTRY( name, struct_name, id, structure, print ) + * + * @name: the name used the event name, as well as the name of + * the directory that holds the format file. + * + * @struct_name: the name of the structure that is created. + * + * @id: The event identifier that is used to detect what event + * this is from the ring buffer. + * + * @structure: the structure layout + * + * - __field( type, item ) + * This is equivalent to declaring + * type item; + * in the structure. + * - __array( type, item, size ) + * This is equivalent to declaring + * type item[size]; + * in the structure. + * + * * for structures within structures, the format of the internal + * structure is laid out. This allows the internal structure + * to be deciphered for the format file. Although these macros + * may become out of sync with the internal structure, they + * will create a compile error if it happens. Since the + * internel structures are just tracing helpers, this is not + * an issue. + * + * When an internal structure is used, it should use: + * + * __field_struct( type, item ) + * + * instead of __field. This will prevent it from being shown in + * the output file. The fields in the structure should use. + * + * __field_desc( type, container, item ) + * __array_desc( type, container, item, len ) + * + * type, item and len are the same as __field and __array, but + * container is added. This is the name of the item in + * __field_struct that this is describing. + * + * + * @print: the print format shown to users in the format file. + */ + +/* + * Function trace entry - function address and parent function address: + */ +FTRACE_ENTRY_REG(function, ftrace_entry, + + TRACE_FN, + + F_STRUCT( + __field( unsigned long, ip ) + __field( unsigned long, parent_ip ) + ), + + F_printk(" %lx <-- %lx", __entry->ip, __entry->parent_ip), + + FILTER_TRACE_FN, + + perf_ftrace_event_register +); + +/* Function call entry */ +FTRACE_ENTRY(funcgraph_entry, ftrace_graph_ent_entry, + + TRACE_GRAPH_ENT, + + F_STRUCT( + __field_struct( struct ftrace_graph_ent, graph_ent ) + __field_desc( unsigned long, graph_ent, func ) + __field_desc( int, graph_ent, depth ) + ), + + F_printk("--> %lx (%d)", __entry->func, __entry->depth), + + FILTER_OTHER +); + +/* Function return entry */ +FTRACE_ENTRY(funcgraph_exit, ftrace_graph_ret_entry, + + TRACE_GRAPH_RET, + + F_STRUCT( + __field_struct( struct ftrace_graph_ret, ret ) + __field_desc( unsigned long, ret, func ) + __field_desc( unsigned long long, ret, calltime) + __field_desc( unsigned long long, ret, rettime ) + __field_desc( unsigned long, ret, overrun ) + __field_desc( int, ret, depth ) + ), + + F_printk("<-- %lx (%d) (start: %llx end: %llx) over: %d", + __entry->func, __entry->depth, + __entry->calltime, __entry->rettime, + __entry->depth), + + FILTER_OTHER +); + +/* + * Context switch trace entry - which task (and prio) we switched from/to: + * + * This is used for both wakeup and context switches. We only want + * to create one structure, but we need two outputs for it. + */ +#define FTRACE_CTX_FIELDS \ + __field( unsigned int, prev_pid ) \ + __field( unsigned int, next_pid ) \ + __field( unsigned int, next_cpu ) \ + __field( unsigned char, prev_prio ) \ + __field( unsigned char, prev_state ) \ + __field( unsigned char, next_prio ) \ + __field( unsigned char, next_state ) + +FTRACE_ENTRY(context_switch, ctx_switch_entry, + + TRACE_CTX, + + F_STRUCT( + FTRACE_CTX_FIELDS + ), + + F_printk("%u:%u:%u ==> %u:%u:%u [%03u]", + __entry->prev_pid, __entry->prev_prio, __entry->prev_state, + __entry->next_pid, __entry->next_prio, __entry->next_state, + __entry->next_cpu), + + FILTER_OTHER +); + +/* + * FTRACE_ENTRY_DUP only creates the format file, it will not + * create another structure. + */ +FTRACE_ENTRY_DUP(wakeup, ctx_switch_entry, + + TRACE_WAKE, + + F_STRUCT( + FTRACE_CTX_FIELDS + ), + + F_printk("%u:%u:%u ==+ %u:%u:%u [%03u]", + __entry->prev_pid, __entry->prev_prio, __entry->prev_state, + __entry->next_pid, __entry->next_prio, __entry->next_state, + __entry->next_cpu), + + FILTER_OTHER +); + +/* + * Stack-trace entry: + */ + +#define FTRACE_STACK_ENTRIES 8 + +#ifndef CONFIG_64BIT +# define IP_FMT "%08lx" +#else +# define IP_FMT "%016lx" +#endif + +FTRACE_ENTRY(kernel_stack, stack_entry, + + TRACE_STACK, + + F_STRUCT( + __field( int, size ) + __dynamic_array(unsigned long, caller ) + ), + + F_printk("\t=> (" IP_FMT ")\n\t=> (" IP_FMT ")\n\t=> (" IP_FMT ")\n" + "\t=> (" IP_FMT ")\n\t=> (" IP_FMT ")\n\t=> (" IP_FMT ")\n" + "\t=> (" IP_FMT ")\n\t=> (" IP_FMT ")\n", + __entry->caller[0], __entry->caller[1], __entry->caller[2], + __entry->caller[3], __entry->caller[4], __entry->caller[5], + __entry->caller[6], __entry->caller[7]), + + FILTER_OTHER +); + +FTRACE_ENTRY(user_stack, userstack_entry, + + TRACE_USER_STACK, + + F_STRUCT( + __field( unsigned int, tgid ) + __array( unsigned long, caller, FTRACE_STACK_ENTRIES ) + ), + + F_printk("\t=> (" IP_FMT ")\n\t=> (" IP_FMT ")\n\t=> (" IP_FMT ")\n" + "\t=> (" IP_FMT ")\n\t=> (" IP_FMT ")\n\t=> (" IP_FMT ")\n" + "\t=> (" IP_FMT ")\n\t=> (" IP_FMT ")\n", + __entry->caller[0], __entry->caller[1], __entry->caller[2], + __entry->caller[3], __entry->caller[4], __entry->caller[5], + __entry->caller[6], __entry->caller[7]), + + FILTER_OTHER +); + +/* + * trace_printk entry: + */ +FTRACE_ENTRY(bprint, bprint_entry, + + TRACE_BPRINT, + + F_STRUCT( + __field( unsigned long, ip ) + __field( const char *, fmt ) + __dynamic_array( u32, buf ) + ), + + F_printk("%ps: %s", + (void *)__entry->ip, __entry->fmt), + + FILTER_OTHER +); + +FTRACE_ENTRY(print, print_entry, + + TRACE_PRINT, + + F_STRUCT( + __field( unsigned long, ip ) + __dynamic_array( char, buf ) + ), + + F_printk("%ps: %s", + (void *)__entry->ip, __entry->buf), + + FILTER_OTHER +); + +FTRACE_ENTRY(bputs, bputs_entry, + + TRACE_BPUTS, + + F_STRUCT( + __field( unsigned long, ip ) + __field( const char *, str ) + ), + + F_printk("%ps: %s", + (void *)__entry->ip, __entry->str), + + FILTER_OTHER +); + +FTRACE_ENTRY(mmiotrace_rw, trace_mmiotrace_rw, + + TRACE_MMIO_RW, + + F_STRUCT( + __field_struct( struct mmiotrace_rw, rw ) + __field_desc( resource_size_t, rw, phys ) + __field_desc( unsigned long, rw, value ) + __field_desc( unsigned long, rw, pc ) + __field_desc( int, rw, map_id ) + __field_desc( unsigned char, rw, opcode ) + __field_desc( unsigned char, rw, width ) + ), + + F_printk("%lx %lx %lx %d %x %x", + (unsigned long)__entry->phys, __entry->value, __entry->pc, + __entry->map_id, __entry->opcode, __entry->width), + + FILTER_OTHER +); + +FTRACE_ENTRY(mmiotrace_map, trace_mmiotrace_map, + + TRACE_MMIO_MAP, + + F_STRUCT( + __field_struct( struct mmiotrace_map, map ) + __field_desc( resource_size_t, map, phys ) + __field_desc( unsigned long, map, virt ) + __field_desc( unsigned long, map, len ) + __field_desc( int, map, map_id ) + __field_desc( unsigned char, map, opcode ) + ), + + F_printk("%lx %lx %lx %d %x", + (unsigned long)__entry->phys, __entry->virt, __entry->len, + __entry->map_id, __entry->opcode), + + FILTER_OTHER +); + + +#define TRACE_FUNC_SIZE 30 +#define TRACE_FILE_SIZE 20 + +FTRACE_ENTRY(branch, trace_branch, + + TRACE_BRANCH, + + F_STRUCT( + __field( unsigned int, line ) + __array( char, func, TRACE_FUNC_SIZE+1 ) + __array( char, file, TRACE_FILE_SIZE+1 ) + __field( char, correct ) + ), + + F_printk("%u:%s:%s (%u)", + __entry->line, + __entry->func, __entry->file, __entry->correct), + + FILTER_OTHER +); + diff --git a/kernel/kernel/trace/trace_event_perf.c b/kernel/kernel/trace/trace_event_perf.c new file mode 100644 index 000000000..6fa484de2 --- /dev/null +++ b/kernel/kernel/trace/trace_event_perf.c @@ -0,0 +1,384 @@ +/* + * trace event based perf event profiling/tracing + * + * Copyright (C) 2009 Red Hat Inc, Peter Zijlstra + * Copyright (C) 2009-2010 Frederic Weisbecker + */ + +#include +#include +#include "trace.h" + +static char __percpu *perf_trace_buf[PERF_NR_CONTEXTS]; + +/* + * Force it to be aligned to unsigned long to avoid misaligned accesses + * suprises + */ +typedef typeof(unsigned long [PERF_MAX_TRACE_SIZE / sizeof(unsigned long)]) + perf_trace_t; + +/* Count the events in use (per event id, not per instance) */ +static int total_ref_count; + +static int perf_trace_event_perm(struct ftrace_event_call *tp_event, + struct perf_event *p_event) +{ + if (tp_event->perf_perm) { + int ret = tp_event->perf_perm(tp_event, p_event); + if (ret) + return ret; + } + + /* + * We checked and allowed to create parent, + * allow children without checking. + */ + if (p_event->parent) + return 0; + + /* + * It's ok to check current process (owner) permissions in here, + * because code below is called only via perf_event_open syscall. + */ + + /* The ftrace function trace is allowed only for root. */ + if (ftrace_event_is_function(tp_event)) { + if (perf_paranoid_tracepoint_raw() && !capable(CAP_SYS_ADMIN)) + return -EPERM; + + /* + * We don't allow user space callchains for function trace + * event, due to issues with page faults while tracing page + * fault handler and its overall trickiness nature. + */ + if (!p_event->attr.exclude_callchain_user) + return -EINVAL; + + /* + * Same reason to disable user stack dump as for user space + * callchains above. + */ + if (p_event->attr.sample_type & PERF_SAMPLE_STACK_USER) + return -EINVAL; + } + + /* No tracing, just counting, so no obvious leak */ + if (!(p_event->attr.sample_type & PERF_SAMPLE_RAW)) + return 0; + + /* Some events are ok to be traced by non-root users... */ + if (p_event->attach_state == PERF_ATTACH_TASK) { + if (tp_event->flags & TRACE_EVENT_FL_CAP_ANY) + return 0; + } + + /* + * ...otherwise raw tracepoint data can be a severe data leak, + * only allow root to have these. + */ + if (perf_paranoid_tracepoint_raw() && !capable(CAP_SYS_ADMIN)) + return -EPERM; + + return 0; +} + +static int perf_trace_event_reg(struct ftrace_event_call *tp_event, + struct perf_event *p_event) +{ + struct hlist_head __percpu *list; + int ret = -ENOMEM; + int cpu; + + p_event->tp_event = tp_event; + if (tp_event->perf_refcount++ > 0) + return 0; + + list = alloc_percpu(struct hlist_head); + if (!list) + goto fail; + + for_each_possible_cpu(cpu) + INIT_HLIST_HEAD(per_cpu_ptr(list, cpu)); + + tp_event->perf_events = list; + + if (!total_ref_count) { + char __percpu *buf; + int i; + + for (i = 0; i < PERF_NR_CONTEXTS; i++) { + buf = (char __percpu *)alloc_percpu(perf_trace_t); + if (!buf) + goto fail; + + perf_trace_buf[i] = buf; + } + } + + ret = tp_event->class->reg(tp_event, TRACE_REG_PERF_REGISTER, NULL); + if (ret) + goto fail; + + total_ref_count++; + return 0; + +fail: + if (!total_ref_count) { + int i; + + for (i = 0; i < PERF_NR_CONTEXTS; i++) { + free_percpu(perf_trace_buf[i]); + perf_trace_buf[i] = NULL; + } + } + + if (!--tp_event->perf_refcount) { + free_percpu(tp_event->perf_events); + tp_event->perf_events = NULL; + } + + return ret; +} + +static void perf_trace_event_unreg(struct perf_event *p_event) +{ + struct ftrace_event_call *tp_event = p_event->tp_event; + int i; + + if (--tp_event->perf_refcount > 0) + goto out; + + tp_event->class->reg(tp_event, TRACE_REG_PERF_UNREGISTER, NULL); + + /* + * Ensure our callback won't be called anymore. The buffers + * will be freed after that. + */ + tracepoint_synchronize_unregister(); + + free_percpu(tp_event->perf_events); + tp_event->perf_events = NULL; + + if (!--total_ref_count) { + for (i = 0; i < PERF_NR_CONTEXTS; i++) { + free_percpu(perf_trace_buf[i]); + perf_trace_buf[i] = NULL; + } + } +out: + module_put(tp_event->mod); +} + +static int perf_trace_event_open(struct perf_event *p_event) +{ + struct ftrace_event_call *tp_event = p_event->tp_event; + return tp_event->class->reg(tp_event, TRACE_REG_PERF_OPEN, p_event); +} + +static void perf_trace_event_close(struct perf_event *p_event) +{ + struct ftrace_event_call *tp_event = p_event->tp_event; + tp_event->class->reg(tp_event, TRACE_REG_PERF_CLOSE, p_event); +} + +static int perf_trace_event_init(struct ftrace_event_call *tp_event, + struct perf_event *p_event) +{ + int ret; + + ret = perf_trace_event_perm(tp_event, p_event); + if (ret) + return ret; + + ret = perf_trace_event_reg(tp_event, p_event); + if (ret) + return ret; + + ret = perf_trace_event_open(p_event); + if (ret) { + perf_trace_event_unreg(p_event); + return ret; + } + + return 0; +} + +int perf_trace_init(struct perf_event *p_event) +{ + struct ftrace_event_call *tp_event; + u64 event_id = p_event->attr.config; + int ret = -EINVAL; + + mutex_lock(&event_mutex); + list_for_each_entry(tp_event, &ftrace_events, list) { + if (tp_event->event.type == event_id && + tp_event->class && tp_event->class->reg && + try_module_get(tp_event->mod)) { + ret = perf_trace_event_init(tp_event, p_event); + if (ret) + module_put(tp_event->mod); + break; + } + } + mutex_unlock(&event_mutex); + + return ret; +} + +void perf_trace_destroy(struct perf_event *p_event) +{ + mutex_lock(&event_mutex); + perf_trace_event_close(p_event); + perf_trace_event_unreg(p_event); + mutex_unlock(&event_mutex); +} + +int perf_trace_add(struct perf_event *p_event, int flags) +{ + struct ftrace_event_call *tp_event = p_event->tp_event; + struct hlist_head __percpu *pcpu_list; + struct hlist_head *list; + + pcpu_list = tp_event->perf_events; + if (WARN_ON_ONCE(!pcpu_list)) + return -EINVAL; + + if (!(flags & PERF_EF_START)) + p_event->hw.state = PERF_HES_STOPPED; + + list = this_cpu_ptr(pcpu_list); + hlist_add_head_rcu(&p_event->hlist_entry, list); + + return tp_event->class->reg(tp_event, TRACE_REG_PERF_ADD, p_event); +} + +void perf_trace_del(struct perf_event *p_event, int flags) +{ + struct ftrace_event_call *tp_event = p_event->tp_event; + hlist_del_rcu(&p_event->hlist_entry); + tp_event->class->reg(tp_event, TRACE_REG_PERF_DEL, p_event); +} + +void *perf_trace_buf_prepare(int size, unsigned short type, + struct pt_regs **regs, int *rctxp) +{ + struct trace_entry *entry; + unsigned long flags; + char *raw_data; + int pc; + + BUILD_BUG_ON(PERF_MAX_TRACE_SIZE % sizeof(unsigned long)); + + if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE, + "perf buffer not large enough")) + return NULL; + + pc = preempt_count(); + + *rctxp = perf_swevent_get_recursion_context(); + if (*rctxp < 0) + return NULL; + + if (regs) + *regs = this_cpu_ptr(&__perf_regs[*rctxp]); + raw_data = this_cpu_ptr(perf_trace_buf[*rctxp]); + + /* zero the dead bytes from align to not leak stack to user */ + memset(&raw_data[size - sizeof(u64)], 0, sizeof(u64)); + + entry = (struct trace_entry *)raw_data; + local_save_flags(flags); + tracing_generic_entry_update(entry, flags, pc); + entry->type = type; + + return raw_data; +} +EXPORT_SYMBOL_GPL(perf_trace_buf_prepare); +NOKPROBE_SYMBOL(perf_trace_buf_prepare); + +#ifdef CONFIG_FUNCTION_TRACER +static void +perf_ftrace_function_call(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *ops, struct pt_regs *pt_regs) +{ + struct ftrace_entry *entry; + struct hlist_head *head; + struct pt_regs regs; + int rctx; + + head = this_cpu_ptr(event_function.perf_events); + if (hlist_empty(head)) + return; + +#define ENTRY_SIZE (ALIGN(sizeof(struct ftrace_entry) + sizeof(u32), \ + sizeof(u64)) - sizeof(u32)) + + BUILD_BUG_ON(ENTRY_SIZE > PERF_MAX_TRACE_SIZE); + + perf_fetch_caller_regs(®s); + + entry = perf_trace_buf_prepare(ENTRY_SIZE, TRACE_FN, NULL, &rctx); + if (!entry) + return; + + entry->ip = ip; + entry->parent_ip = parent_ip; + perf_trace_buf_submit(entry, ENTRY_SIZE, rctx, 0, + 1, ®s, head, NULL); + +#undef ENTRY_SIZE +} + +static int perf_ftrace_function_register(struct perf_event *event) +{ + struct ftrace_ops *ops = &event->ftrace_ops; + + ops->flags |= FTRACE_OPS_FL_CONTROL; + ops->func = perf_ftrace_function_call; + return register_ftrace_function(ops); +} + +static int perf_ftrace_function_unregister(struct perf_event *event) +{ + struct ftrace_ops *ops = &event->ftrace_ops; + int ret = unregister_ftrace_function(ops); + ftrace_free_filter(ops); + return ret; +} + +static void perf_ftrace_function_enable(struct perf_event *event) +{ + ftrace_function_local_enable(&event->ftrace_ops); +} + +static void perf_ftrace_function_disable(struct perf_event *event) +{ + ftrace_function_local_disable(&event->ftrace_ops); +} + +int perf_ftrace_event_register(struct ftrace_event_call *call, + enum trace_reg type, void *data) +{ + switch (type) { + case TRACE_REG_REGISTER: + case TRACE_REG_UNREGISTER: + break; + case TRACE_REG_PERF_REGISTER: + case TRACE_REG_PERF_UNREGISTER: + return 0; + case TRACE_REG_PERF_OPEN: + return perf_ftrace_function_register(data); + case TRACE_REG_PERF_CLOSE: + return perf_ftrace_function_unregister(data); + case TRACE_REG_PERF_ADD: + perf_ftrace_function_enable(data); + return 0; + case TRACE_REG_PERF_DEL: + perf_ftrace_function_disable(data); + return 0; + } + + return -EINVAL; +} +#endif /* CONFIG_FUNCTION_TRACER */ diff --git a/kernel/kernel/trace/trace_events.c b/kernel/kernel/trace/trace_events.c new file mode 100644 index 000000000..711529bba --- /dev/null +++ b/kernel/kernel/trace/trace_events.c @@ -0,0 +1,2945 @@ +/* + * event tracer + * + * Copyright (C) 2008 Red Hat Inc, Steven Rostedt + * + * - Added format output of fields of the trace point. + * This was based off of work by Tom Zanussi . + * + */ + +#define pr_fmt(fmt) fmt + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +#include "trace_output.h" + +#undef TRACE_SYSTEM +#define TRACE_SYSTEM "TRACE_SYSTEM" + +DEFINE_MUTEX(event_mutex); + +LIST_HEAD(ftrace_events); +static LIST_HEAD(ftrace_common_fields); + +#define GFP_TRACE (GFP_KERNEL | __GFP_ZERO) + +static struct kmem_cache *field_cachep; +static struct kmem_cache *file_cachep; + +#define SYSTEM_FL_FREE_NAME (1 << 31) + +static inline int system_refcount(struct event_subsystem *system) +{ + return system->ref_count & ~SYSTEM_FL_FREE_NAME; +} + +static int system_refcount_inc(struct event_subsystem *system) +{ + return (system->ref_count++) & ~SYSTEM_FL_FREE_NAME; +} + +static int system_refcount_dec(struct event_subsystem *system) +{ + return (--system->ref_count) & ~SYSTEM_FL_FREE_NAME; +} + +/* Double loops, do not use break, only goto's work */ +#define do_for_each_event_file(tr, file) \ + list_for_each_entry(tr, &ftrace_trace_arrays, list) { \ + list_for_each_entry(file, &tr->events, list) + +#define do_for_each_event_file_safe(tr, file) \ + list_for_each_entry(tr, &ftrace_trace_arrays, list) { \ + struct ftrace_event_file *___n; \ + list_for_each_entry_safe(file, ___n, &tr->events, list) + +#define while_for_each_event_file() \ + } + +static struct list_head * +trace_get_fields(struct ftrace_event_call *event_call) +{ + if (!event_call->class->get_fields) + return &event_call->class->fields; + return event_call->class->get_fields(event_call); +} + +static struct ftrace_event_field * +__find_event_field(struct list_head *head, char *name) +{ + struct ftrace_event_field *field; + + list_for_each_entry(field, head, link) { + if (!strcmp(field->name, name)) + return field; + } + + return NULL; +} + +struct ftrace_event_field * +trace_find_event_field(struct ftrace_event_call *call, char *name) +{ + struct ftrace_event_field *field; + struct list_head *head; + + field = __find_event_field(&ftrace_common_fields, name); + if (field) + return field; + + head = trace_get_fields(call); + return __find_event_field(head, name); +} + +static int __trace_define_field(struct list_head *head, const char *type, + const char *name, int offset, int size, + int is_signed, int filter_type) +{ + struct ftrace_event_field *field; + + field = kmem_cache_alloc(field_cachep, GFP_TRACE); + if (!field) + return -ENOMEM; + + field->name = name; + field->type = type; + + if (filter_type == FILTER_OTHER) + field->filter_type = filter_assign_type(type); + else + field->filter_type = filter_type; + + field->offset = offset; + field->size = size; + field->is_signed = is_signed; + + list_add(&field->link, head); + + return 0; +} + +int trace_define_field(struct ftrace_event_call *call, const char *type, + const char *name, int offset, int size, int is_signed, + int filter_type) +{ + struct list_head *head; + + if (WARN_ON(!call->class)) + return 0; + + head = trace_get_fields(call); + return __trace_define_field(head, type, name, offset, size, + is_signed, filter_type); +} +EXPORT_SYMBOL_GPL(trace_define_field); + +#define __common_field(type, item) \ + ret = __trace_define_field(&ftrace_common_fields, #type, \ + "common_" #item, \ + offsetof(typeof(ent), item), \ + sizeof(ent.item), \ + is_signed_type(type), FILTER_OTHER); \ + if (ret) \ + return ret; + +static int trace_define_common_fields(void) +{ + int ret; + struct trace_entry ent; + + __common_field(unsigned short, type); + __common_field(unsigned char, flags); + __common_field(unsigned char, preempt_count); + __common_field(int, pid); + __common_field(unsigned short, migrate_disable); + __common_field(unsigned short, padding); + + return ret; +} + +static void trace_destroy_fields(struct ftrace_event_call *call) +{ + struct ftrace_event_field *field, *next; + struct list_head *head; + + head = trace_get_fields(call); + list_for_each_entry_safe(field, next, head, link) { + list_del(&field->link); + kmem_cache_free(field_cachep, field); + } +} + +int trace_event_raw_init(struct ftrace_event_call *call) +{ + int id; + + id = register_ftrace_event(&call->event); + if (!id) + return -ENODEV; + + return 0; +} +EXPORT_SYMBOL_GPL(trace_event_raw_init); + +void *ftrace_event_buffer_reserve(struct ftrace_event_buffer *fbuffer, + struct ftrace_event_file *ftrace_file, + unsigned long len) +{ + struct ftrace_event_call *event_call = ftrace_file->event_call; + + local_save_flags(fbuffer->flags); + fbuffer->pc = preempt_count(); + fbuffer->ftrace_file = ftrace_file; + + fbuffer->event = + trace_event_buffer_lock_reserve(&fbuffer->buffer, ftrace_file, + event_call->event.type, len, + fbuffer->flags, fbuffer->pc); + if (!fbuffer->event) + return NULL; + + fbuffer->entry = ring_buffer_event_data(fbuffer->event); + return fbuffer->entry; +} +EXPORT_SYMBOL_GPL(ftrace_event_buffer_reserve); + +static DEFINE_SPINLOCK(tracepoint_iter_lock); + +static void output_printk(struct ftrace_event_buffer *fbuffer) +{ + struct ftrace_event_call *event_call; + struct trace_event *event; + unsigned long flags; + struct trace_iterator *iter = tracepoint_print_iter; + + if (!iter) + return; + + event_call = fbuffer->ftrace_file->event_call; + if (!event_call || !event_call->event.funcs || + !event_call->event.funcs->trace) + return; + + event = &fbuffer->ftrace_file->event_call->event; + + spin_lock_irqsave(&tracepoint_iter_lock, flags); + trace_seq_init(&iter->seq); + iter->ent = fbuffer->entry; + event_call->event.funcs->trace(iter, 0, event); + trace_seq_putc(&iter->seq, 0); + printk("%s", iter->seq.buffer); + + spin_unlock_irqrestore(&tracepoint_iter_lock, flags); +} + +void ftrace_event_buffer_commit(struct ftrace_event_buffer *fbuffer) +{ + if (tracepoint_printk) + output_printk(fbuffer); + + event_trigger_unlock_commit(fbuffer->ftrace_file, fbuffer->buffer, + fbuffer->event, fbuffer->entry, + fbuffer->flags, fbuffer->pc); +} +EXPORT_SYMBOL_GPL(ftrace_event_buffer_commit); + +int ftrace_event_reg(struct ftrace_event_call *call, + enum trace_reg type, void *data) +{ + struct ftrace_event_file *file = data; + + WARN_ON(!(call->flags & TRACE_EVENT_FL_TRACEPOINT)); + switch (type) { + case TRACE_REG_REGISTER: + return tracepoint_probe_register(call->tp, + call->class->probe, + file); + case TRACE_REG_UNREGISTER: + tracepoint_probe_unregister(call->tp, + call->class->probe, + file); + return 0; + +#ifdef CONFIG_PERF_EVENTS + case TRACE_REG_PERF_REGISTER: + return tracepoint_probe_register(call->tp, + call->class->perf_probe, + call); + case TRACE_REG_PERF_UNREGISTER: + tracepoint_probe_unregister(call->tp, + call->class->perf_probe, + call); + return 0; + case TRACE_REG_PERF_OPEN: + case TRACE_REG_PERF_CLOSE: + case TRACE_REG_PERF_ADD: + case TRACE_REG_PERF_DEL: + return 0; +#endif + } + return 0; +} +EXPORT_SYMBOL_GPL(ftrace_event_reg); + +void trace_event_enable_cmd_record(bool enable) +{ + struct ftrace_event_file *file; + struct trace_array *tr; + + mutex_lock(&event_mutex); + do_for_each_event_file(tr, file) { + + if (!(file->flags & FTRACE_EVENT_FL_ENABLED)) + continue; + + if (enable) { + tracing_start_cmdline_record(); + set_bit(FTRACE_EVENT_FL_RECORDED_CMD_BIT, &file->flags); + } else { + tracing_stop_cmdline_record(); + clear_bit(FTRACE_EVENT_FL_RECORDED_CMD_BIT, &file->flags); + } + } while_for_each_event_file(); + mutex_unlock(&event_mutex); +} + +static int __ftrace_event_enable_disable(struct ftrace_event_file *file, + int enable, int soft_disable) +{ + struct ftrace_event_call *call = file->event_call; + int ret = 0; + int disable; + + switch (enable) { + case 0: + /* + * When soft_disable is set and enable is cleared, the sm_ref + * reference counter is decremented. If it reaches 0, we want + * to clear the SOFT_DISABLED flag but leave the event in the + * state that it was. That is, if the event was enabled and + * SOFT_DISABLED isn't set, then do nothing. But if SOFT_DISABLED + * is set we do not want the event to be enabled before we + * clear the bit. + * + * When soft_disable is not set but the SOFT_MODE flag is, + * we do nothing. Do not disable the tracepoint, otherwise + * "soft enable"s (clearing the SOFT_DISABLED bit) wont work. + */ + if (soft_disable) { + if (atomic_dec_return(&file->sm_ref) > 0) + break; + disable = file->flags & FTRACE_EVENT_FL_SOFT_DISABLED; + clear_bit(FTRACE_EVENT_FL_SOFT_MODE_BIT, &file->flags); + } else + disable = !(file->flags & FTRACE_EVENT_FL_SOFT_MODE); + + if (disable && (file->flags & FTRACE_EVENT_FL_ENABLED)) { + clear_bit(FTRACE_EVENT_FL_ENABLED_BIT, &file->flags); + if (file->flags & FTRACE_EVENT_FL_RECORDED_CMD) { + tracing_stop_cmdline_record(); + clear_bit(FTRACE_EVENT_FL_RECORDED_CMD_BIT, &file->flags); + } + call->class->reg(call, TRACE_REG_UNREGISTER, file); + } + /* If in SOFT_MODE, just set the SOFT_DISABLE_BIT, else clear it */ + if (file->flags & FTRACE_EVENT_FL_SOFT_MODE) + set_bit(FTRACE_EVENT_FL_SOFT_DISABLED_BIT, &file->flags); + else + clear_bit(FTRACE_EVENT_FL_SOFT_DISABLED_BIT, &file->flags); + break; + case 1: + /* + * When soft_disable is set and enable is set, we want to + * register the tracepoint for the event, but leave the event + * as is. That means, if the event was already enabled, we do + * nothing (but set SOFT_MODE). If the event is disabled, we + * set SOFT_DISABLED before enabling the event tracepoint, so + * it still seems to be disabled. + */ + if (!soft_disable) + clear_bit(FTRACE_EVENT_FL_SOFT_DISABLED_BIT, &file->flags); + else { + if (atomic_inc_return(&file->sm_ref) > 1) + break; + set_bit(FTRACE_EVENT_FL_SOFT_MODE_BIT, &file->flags); + } + + if (!(file->flags & FTRACE_EVENT_FL_ENABLED)) { + + /* Keep the event disabled, when going to SOFT_MODE. */ + if (soft_disable) + set_bit(FTRACE_EVENT_FL_SOFT_DISABLED_BIT, &file->flags); + + if (trace_flags & TRACE_ITER_RECORD_CMD) { + tracing_start_cmdline_record(); + set_bit(FTRACE_EVENT_FL_RECORDED_CMD_BIT, &file->flags); + } + ret = call->class->reg(call, TRACE_REG_REGISTER, file); + if (ret) { + tracing_stop_cmdline_record(); + pr_info("event trace: Could not enable event " + "%s\n", ftrace_event_name(call)); + break; + } + set_bit(FTRACE_EVENT_FL_ENABLED_BIT, &file->flags); + + /* WAS_ENABLED gets set but never cleared. */ + call->flags |= TRACE_EVENT_FL_WAS_ENABLED; + } + break; + } + + return ret; +} + +int trace_event_enable_disable(struct ftrace_event_file *file, + int enable, int soft_disable) +{ + return __ftrace_event_enable_disable(file, enable, soft_disable); +} + +static int ftrace_event_enable_disable(struct ftrace_event_file *file, + int enable) +{ + return __ftrace_event_enable_disable(file, enable, 0); +} + +static void ftrace_clear_events(struct trace_array *tr) +{ + struct ftrace_event_file *file; + + mutex_lock(&event_mutex); + list_for_each_entry(file, &tr->events, list) { + ftrace_event_enable_disable(file, 0); + } + mutex_unlock(&event_mutex); +} + +static void __put_system(struct event_subsystem *system) +{ + struct event_filter *filter = system->filter; + + WARN_ON_ONCE(system_refcount(system) == 0); + if (system_refcount_dec(system)) + return; + + list_del(&system->list); + + if (filter) { + kfree(filter->filter_string); + kfree(filter); + } + if (system->ref_count & SYSTEM_FL_FREE_NAME) + kfree(system->name); + kfree(system); +} + +static void __get_system(struct event_subsystem *system) +{ + WARN_ON_ONCE(system_refcount(system) == 0); + system_refcount_inc(system); +} + +static void __get_system_dir(struct ftrace_subsystem_dir *dir) +{ + WARN_ON_ONCE(dir->ref_count == 0); + dir->ref_count++; + __get_system(dir->subsystem); +} + +static void __put_system_dir(struct ftrace_subsystem_dir *dir) +{ + WARN_ON_ONCE(dir->ref_count == 0); + /* If the subsystem is about to be freed, the dir must be too */ + WARN_ON_ONCE(system_refcount(dir->subsystem) == 1 && dir->ref_count != 1); + + __put_system(dir->subsystem); + if (!--dir->ref_count) + kfree(dir); +} + +static void put_system(struct ftrace_subsystem_dir *dir) +{ + mutex_lock(&event_mutex); + __put_system_dir(dir); + mutex_unlock(&event_mutex); +} + +static void remove_subsystem(struct ftrace_subsystem_dir *dir) +{ + if (!dir) + return; + + if (!--dir->nr_events) { + tracefs_remove_recursive(dir->entry); + list_del(&dir->list); + __put_system_dir(dir); + } +} + +static void remove_event_file_dir(struct ftrace_event_file *file) +{ + struct dentry *dir = file->dir; + struct dentry *child; + + if (dir) { + spin_lock(&dir->d_lock); /* probably unneeded */ + list_for_each_entry(child, &dir->d_subdirs, d_child) { + if (d_really_is_positive(child)) /* probably unneeded */ + d_inode(child)->i_private = NULL; + } + spin_unlock(&dir->d_lock); + + tracefs_remove_recursive(dir); + } + + list_del(&file->list); + remove_subsystem(file->system); + free_event_filter(file->filter); + kmem_cache_free(file_cachep, file); +} + +/* + * __ftrace_set_clr_event(NULL, NULL, NULL, set) will set/unset all events. + */ +static int +__ftrace_set_clr_event_nolock(struct trace_array *tr, const char *match, + const char *sub, const char *event, int set) +{ + struct ftrace_event_file *file; + struct ftrace_event_call *call; + const char *name; + int ret = -EINVAL; + + list_for_each_entry(file, &tr->events, list) { + + call = file->event_call; + name = ftrace_event_name(call); + + if (!name || !call->class || !call->class->reg) + continue; + + if (call->flags & TRACE_EVENT_FL_IGNORE_ENABLE) + continue; + + if (match && + strcmp(match, name) != 0 && + strcmp(match, call->class->system) != 0) + continue; + + if (sub && strcmp(sub, call->class->system) != 0) + continue; + + if (event && strcmp(event, name) != 0) + continue; + + ftrace_event_enable_disable(file, set); + + ret = 0; + } + + return ret; +} + +static int __ftrace_set_clr_event(struct trace_array *tr, const char *match, + const char *sub, const char *event, int set) +{ + int ret; + + mutex_lock(&event_mutex); + ret = __ftrace_set_clr_event_nolock(tr, match, sub, event, set); + mutex_unlock(&event_mutex); + + return ret; +} + +static int ftrace_set_clr_event(struct trace_array *tr, char *buf, int set) +{ + char *event = NULL, *sub = NULL, *match; + int ret; + + /* + * The buf format can be : + * *: means any event by that name. + * : is the same. + * + * :* means all events in that subsystem + * : means the same. + * + * (no ':') means all events in a subsystem with + * the name or any event that matches + */ + + match = strsep(&buf, ":"); + if (buf) { + sub = match; + event = buf; + match = NULL; + + if (!strlen(sub) || strcmp(sub, "*") == 0) + sub = NULL; + if (!strlen(event) || strcmp(event, "*") == 0) + event = NULL; + } + + ret = __ftrace_set_clr_event(tr, match, sub, event, set); + + /* Put back the colon to allow this to be called again */ + if (buf) + *(buf - 1) = ':'; + + return ret; +} + +/** + * trace_set_clr_event - enable or disable an event + * @system: system name to match (NULL for any system) + * @event: event name to match (NULL for all events, within system) + * @set: 1 to enable, 0 to disable + * + * This is a way for other parts of the kernel to enable or disable + * event recording. + * + * Returns 0 on success, -EINVAL if the parameters do not match any + * registered events. + */ +int trace_set_clr_event(const char *system, const char *event, int set) +{ + struct trace_array *tr = top_trace_array(); + + if (!tr) + return -ENODEV; + + return __ftrace_set_clr_event(tr, NULL, system, event, set); +} +EXPORT_SYMBOL_GPL(trace_set_clr_event); + +/* 128 should be much more than enough */ +#define EVENT_BUF_SIZE 127 + +static ssize_t +ftrace_event_write(struct file *file, const char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + struct trace_parser parser; + struct seq_file *m = file->private_data; + struct trace_array *tr = m->private; + ssize_t read, ret; + + if (!cnt) + return 0; + + ret = tracing_update_buffers(); + if (ret < 0) + return ret; + + if (trace_parser_get_init(&parser, EVENT_BUF_SIZE + 1)) + return -ENOMEM; + + read = trace_get_user(&parser, ubuf, cnt, ppos); + + if (read >= 0 && trace_parser_loaded((&parser))) { + int set = 1; + + if (*parser.buffer == '!') + set = 0; + + parser.buffer[parser.idx] = 0; + + ret = ftrace_set_clr_event(tr, parser.buffer + !set, set); + if (ret) + goto out_put; + } + + ret = read; + + out_put: + trace_parser_put(&parser); + + return ret; +} + +static void * +t_next(struct seq_file *m, void *v, loff_t *pos) +{ + struct ftrace_event_file *file = v; + struct ftrace_event_call *call; + struct trace_array *tr = m->private; + + (*pos)++; + + list_for_each_entry_continue(file, &tr->events, list) { + call = file->event_call; + /* + * The ftrace subsystem is for showing formats only. + * They can not be enabled or disabled via the event files. + */ + if (call->class && call->class->reg) + return file; + } + + return NULL; +} + +static void *t_start(struct seq_file *m, loff_t *pos) +{ + struct ftrace_event_file *file; + struct trace_array *tr = m->private; + loff_t l; + + mutex_lock(&event_mutex); + + file = list_entry(&tr->events, struct ftrace_event_file, list); + for (l = 0; l <= *pos; ) { + file = t_next(m, file, &l); + if (!file) + break; + } + return file; +} + +static void * +s_next(struct seq_file *m, void *v, loff_t *pos) +{ + struct ftrace_event_file *file = v; + struct trace_array *tr = m->private; + + (*pos)++; + + list_for_each_entry_continue(file, &tr->events, list) { + if (file->flags & FTRACE_EVENT_FL_ENABLED) + return file; + } + + return NULL; +} + +static void *s_start(struct seq_file *m, loff_t *pos) +{ + struct ftrace_event_file *file; + struct trace_array *tr = m->private; + loff_t l; + + mutex_lock(&event_mutex); + + file = list_entry(&tr->events, struct ftrace_event_file, list); + for (l = 0; l <= *pos; ) { + file = s_next(m, file, &l); + if (!file) + break; + } + return file; +} + +static int t_show(struct seq_file *m, void *v) +{ + struct ftrace_event_file *file = v; + struct ftrace_event_call *call = file->event_call; + + if (strcmp(call->class->system, TRACE_SYSTEM) != 0) + seq_printf(m, "%s:", call->class->system); + seq_printf(m, "%s\n", ftrace_event_name(call)); + + return 0; +} + +static void t_stop(struct seq_file *m, void *p) +{ + mutex_unlock(&event_mutex); +} + +static ssize_t +event_enable_read(struct file *filp, char __user *ubuf, size_t cnt, + loff_t *ppos) +{ + struct ftrace_event_file *file; + unsigned long flags; + char buf[4] = "0"; + + mutex_lock(&event_mutex); + file = event_file_data(filp); + if (likely(file)) + flags = file->flags; + mutex_unlock(&event_mutex); + + if (!file) + return -ENODEV; + + if (flags & FTRACE_EVENT_FL_ENABLED && + !(flags & FTRACE_EVENT_FL_SOFT_DISABLED)) + strcpy(buf, "1"); + + if (flags & FTRACE_EVENT_FL_SOFT_DISABLED || + flags & FTRACE_EVENT_FL_SOFT_MODE) + strcat(buf, "*"); + + strcat(buf, "\n"); + + return simple_read_from_buffer(ubuf, cnt, ppos, buf, strlen(buf)); +} + +static ssize_t +event_enable_write(struct file *filp, const char __user *ubuf, size_t cnt, + loff_t *ppos) +{ + struct ftrace_event_file *file; + unsigned long val; + int ret; + + ret = kstrtoul_from_user(ubuf, cnt, 10, &val); + if (ret) + return ret; + + ret = tracing_update_buffers(); + if (ret < 0) + return ret; + + switch (val) { + case 0: + case 1: + ret = -ENODEV; + mutex_lock(&event_mutex); + file = event_file_data(filp); + if (likely(file)) + ret = ftrace_event_enable_disable(file, val); + mutex_unlock(&event_mutex); + break; + + default: + return -EINVAL; + } + + *ppos += cnt; + + return ret ? ret : cnt; +} + +static ssize_t +system_enable_read(struct file *filp, char __user *ubuf, size_t cnt, + loff_t *ppos) +{ + const char set_to_char[4] = { '?', '0', '1', 'X' }; + struct ftrace_subsystem_dir *dir = filp->private_data; + struct event_subsystem *system = dir->subsystem; + struct ftrace_event_call *call; + struct ftrace_event_file *file; + struct trace_array *tr = dir->tr; + char buf[2]; + int set = 0; + int ret; + + mutex_lock(&event_mutex); + list_for_each_entry(file, &tr->events, list) { + call = file->event_call; + if (!ftrace_event_name(call) || !call->class || !call->class->reg) + continue; + + if (system && strcmp(call->class->system, system->name) != 0) + continue; + + /* + * We need to find out if all the events are set + * or if all events or cleared, or if we have + * a mixture. + */ + set |= (1 << !!(file->flags & FTRACE_EVENT_FL_ENABLED)); + + /* + * If we have a mixture, no need to look further. + */ + if (set == 3) + break; + } + mutex_unlock(&event_mutex); + + buf[0] = set_to_char[set]; + buf[1] = '\n'; + + ret = simple_read_from_buffer(ubuf, cnt, ppos, buf, 2); + + return ret; +} + +static ssize_t +system_enable_write(struct file *filp, const char __user *ubuf, size_t cnt, + loff_t *ppos) +{ + struct ftrace_subsystem_dir *dir = filp->private_data; + struct event_subsystem *system = dir->subsystem; + const char *name = NULL; + unsigned long val; + ssize_t ret; + + ret = kstrtoul_from_user(ubuf, cnt, 10, &val); + if (ret) + return ret; + + ret = tracing_update_buffers(); + if (ret < 0) + return ret; + + if (val != 0 && val != 1) + return -EINVAL; + + /* + * Opening of "enable" adds a ref count to system, + * so the name is safe to use. + */ + if (system) + name = system->name; + + ret = __ftrace_set_clr_event(dir->tr, NULL, name, NULL, val); + if (ret) + goto out; + + ret = cnt; + +out: + *ppos += cnt; + + return ret; +} + +enum { + FORMAT_HEADER = 1, + FORMAT_FIELD_SEPERATOR = 2, + FORMAT_PRINTFMT = 3, +}; + +static void *f_next(struct seq_file *m, void *v, loff_t *pos) +{ + struct ftrace_event_call *call = event_file_data(m->private); + struct list_head *common_head = &ftrace_common_fields; + struct list_head *head = trace_get_fields(call); + struct list_head *node = v; + + (*pos)++; + + switch ((unsigned long)v) { + case FORMAT_HEADER: + node = common_head; + break; + + case FORMAT_FIELD_SEPERATOR: + node = head; + break; + + case FORMAT_PRINTFMT: + /* all done */ + return NULL; + } + + node = node->prev; + if (node == common_head) + return (void *)FORMAT_FIELD_SEPERATOR; + else if (node == head) + return (void *)FORMAT_PRINTFMT; + else + return node; +} + +static int f_show(struct seq_file *m, void *v) +{ + struct ftrace_event_call *call = event_file_data(m->private); + struct ftrace_event_field *field; + const char *array_descriptor; + + switch ((unsigned long)v) { + case FORMAT_HEADER: + seq_printf(m, "name: %s\n", ftrace_event_name(call)); + seq_printf(m, "ID: %d\n", call->event.type); + seq_puts(m, "format:\n"); + return 0; + + case FORMAT_FIELD_SEPERATOR: + seq_putc(m, '\n'); + return 0; + + case FORMAT_PRINTFMT: + seq_printf(m, "\nprint fmt: %s\n", + call->print_fmt); + return 0; + } + + field = list_entry(v, struct ftrace_event_field, link); + /* + * Smartly shows the array type(except dynamic array). + * Normal: + * field:TYPE VAR + * If TYPE := TYPE[LEN], it is shown: + * field:TYPE VAR[LEN] + */ + array_descriptor = strchr(field->type, '['); + + if (!strncmp(field->type, "__data_loc", 10)) + array_descriptor = NULL; + + if (!array_descriptor) + seq_printf(m, "\tfield:%s %s;\toffset:%u;\tsize:%u;\tsigned:%d;\n", + field->type, field->name, field->offset, + field->size, !!field->is_signed); + else + seq_printf(m, "\tfield:%.*s %s%s;\toffset:%u;\tsize:%u;\tsigned:%d;\n", + (int)(array_descriptor - field->type), + field->type, field->name, + array_descriptor, field->offset, + field->size, !!field->is_signed); + + return 0; +} + +static void *f_start(struct seq_file *m, loff_t *pos) +{ + void *p = (void *)FORMAT_HEADER; + loff_t l = 0; + + /* ->stop() is called even if ->start() fails */ + mutex_lock(&event_mutex); + if (!event_file_data(m->private)) + return ERR_PTR(-ENODEV); + + while (l < *pos && p) + p = f_next(m, p, &l); + + return p; +} + +static void f_stop(struct seq_file *m, void *p) +{ + mutex_unlock(&event_mutex); +} + +static const struct seq_operations trace_format_seq_ops = { + .start = f_start, + .next = f_next, + .stop = f_stop, + .show = f_show, +}; + +static int trace_format_open(struct inode *inode, struct file *file) +{ + struct seq_file *m; + int ret; + + ret = seq_open(file, &trace_format_seq_ops); + if (ret < 0) + return ret; + + m = file->private_data; + m->private = file; + + return 0; +} + +static ssize_t +event_id_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) +{ + int id = (long)event_file_data(filp); + char buf[32]; + int len; + + if (*ppos) + return 0; + + if (unlikely(!id)) + return -ENODEV; + + len = sprintf(buf, "%d\n", id); + + return simple_read_from_buffer(ubuf, cnt, ppos, buf, len); +} + +static ssize_t +event_filter_read(struct file *filp, char __user *ubuf, size_t cnt, + loff_t *ppos) +{ + struct ftrace_event_file *file; + struct trace_seq *s; + int r = -ENODEV; + + if (*ppos) + return 0; + + s = kmalloc(sizeof(*s), GFP_KERNEL); + + if (!s) + return -ENOMEM; + + trace_seq_init(s); + + mutex_lock(&event_mutex); + file = event_file_data(filp); + if (file) + print_event_filter(file, s); + mutex_unlock(&event_mutex); + + if (file) + r = simple_read_from_buffer(ubuf, cnt, ppos, + s->buffer, trace_seq_used(s)); + + kfree(s); + + return r; +} + +static ssize_t +event_filter_write(struct file *filp, const char __user *ubuf, size_t cnt, + loff_t *ppos) +{ + struct ftrace_event_file *file; + char *buf; + int err = -ENODEV; + + if (cnt >= PAGE_SIZE) + return -EINVAL; + + buf = (char *)__get_free_page(GFP_TEMPORARY); + if (!buf) + return -ENOMEM; + + if (copy_from_user(buf, ubuf, cnt)) { + free_page((unsigned long) buf); + return -EFAULT; + } + buf[cnt] = '\0'; + + mutex_lock(&event_mutex); + file = event_file_data(filp); + if (file) + err = apply_event_filter(file, buf); + mutex_unlock(&event_mutex); + + free_page((unsigned long) buf); + if (err < 0) + return err; + + *ppos += cnt; + + return cnt; +} + +static LIST_HEAD(event_subsystems); + +static int subsystem_open(struct inode *inode, struct file *filp) +{ + struct event_subsystem *system = NULL; + struct ftrace_subsystem_dir *dir = NULL; /* Initialize for gcc */ + struct trace_array *tr; + int ret; + + if (tracing_is_disabled()) + return -ENODEV; + + /* Make sure the system still exists */ + mutex_lock(&trace_types_lock); + mutex_lock(&event_mutex); + list_for_each_entry(tr, &ftrace_trace_arrays, list) { + list_for_each_entry(dir, &tr->systems, list) { + if (dir == inode->i_private) { + /* Don't open systems with no events */ + if (dir->nr_events) { + __get_system_dir(dir); + system = dir->subsystem; + } + goto exit_loop; + } + } + } + exit_loop: + mutex_unlock(&event_mutex); + mutex_unlock(&trace_types_lock); + + if (!system) + return -ENODEV; + + /* Some versions of gcc think dir can be uninitialized here */ + WARN_ON(!dir); + + /* Still need to increment the ref count of the system */ + if (trace_array_get(tr) < 0) { + put_system(dir); + return -ENODEV; + } + + ret = tracing_open_generic(inode, filp); + if (ret < 0) { + trace_array_put(tr); + put_system(dir); + } + + return ret; +} + +static int system_tr_open(struct inode *inode, struct file *filp) +{ + struct ftrace_subsystem_dir *dir; + struct trace_array *tr = inode->i_private; + int ret; + + if (tracing_is_disabled()) + return -ENODEV; + + if (trace_array_get(tr) < 0) + return -ENODEV; + + /* Make a temporary dir that has no system but points to tr */ + dir = kzalloc(sizeof(*dir), GFP_KERNEL); + if (!dir) { + trace_array_put(tr); + return -ENOMEM; + } + + dir->tr = tr; + + ret = tracing_open_generic(inode, filp); + if (ret < 0) { + trace_array_put(tr); + kfree(dir); + return ret; + } + + filp->private_data = dir; + + return 0; +} + +static int subsystem_release(struct inode *inode, struct file *file) +{ + struct ftrace_subsystem_dir *dir = file->private_data; + + trace_array_put(dir->tr); + + /* + * If dir->subsystem is NULL, then this is a temporary + * descriptor that was made for a trace_array to enable + * all subsystems. + */ + if (dir->subsystem) + put_system(dir); + else + kfree(dir); + + return 0; +} + +static ssize_t +subsystem_filter_read(struct file *filp, char __user *ubuf, size_t cnt, + loff_t *ppos) +{ + struct ftrace_subsystem_dir *dir = filp->private_data; + struct event_subsystem *system = dir->subsystem; + struct trace_seq *s; + int r; + + if (*ppos) + return 0; + + s = kmalloc(sizeof(*s), GFP_KERNEL); + if (!s) + return -ENOMEM; + + trace_seq_init(s); + + print_subsystem_event_filter(system, s); + r = simple_read_from_buffer(ubuf, cnt, ppos, + s->buffer, trace_seq_used(s)); + + kfree(s); + + return r; +} + +static ssize_t +subsystem_filter_write(struct file *filp, const char __user *ubuf, size_t cnt, + loff_t *ppos) +{ + struct ftrace_subsystem_dir *dir = filp->private_data; + char *buf; + int err; + + if (cnt >= PAGE_SIZE) + return -EINVAL; + + buf = (char *)__get_free_page(GFP_TEMPORARY); + if (!buf) + return -ENOMEM; + + if (copy_from_user(buf, ubuf, cnt)) { + free_page((unsigned long) buf); + return -EFAULT; + } + buf[cnt] = '\0'; + + err = apply_subsystem_event_filter(dir, buf); + free_page((unsigned long) buf); + if (err < 0) + return err; + + *ppos += cnt; + + return cnt; +} + +static ssize_t +show_header(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) +{ + int (*func)(struct trace_seq *s) = filp->private_data; + struct trace_seq *s; + int r; + + if (*ppos) + return 0; + + s = kmalloc(sizeof(*s), GFP_KERNEL); + if (!s) + return -ENOMEM; + + trace_seq_init(s); + + func(s); + r = simple_read_from_buffer(ubuf, cnt, ppos, + s->buffer, trace_seq_used(s)); + + kfree(s); + + return r; +} + +static int ftrace_event_avail_open(struct inode *inode, struct file *file); +static int ftrace_event_set_open(struct inode *inode, struct file *file); +static int ftrace_event_release(struct inode *inode, struct file *file); + +static const struct seq_operations show_event_seq_ops = { + .start = t_start, + .next = t_next, + .show = t_show, + .stop = t_stop, +}; + +static const struct seq_operations show_set_event_seq_ops = { + .start = s_start, + .next = s_next, + .show = t_show, + .stop = t_stop, +}; + +static const struct file_operations ftrace_avail_fops = { + .open = ftrace_event_avail_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, +}; + +static const struct file_operations ftrace_set_event_fops = { + .open = ftrace_event_set_open, + .read = seq_read, + .write = ftrace_event_write, + .llseek = seq_lseek, + .release = ftrace_event_release, +}; + +static const struct file_operations ftrace_enable_fops = { + .open = tracing_open_generic, + .read = event_enable_read, + .write = event_enable_write, + .llseek = default_llseek, +}; + +static const struct file_operations ftrace_event_format_fops = { + .open = trace_format_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, +}; + +static const struct file_operations ftrace_event_id_fops = { + .read = event_id_read, + .llseek = default_llseek, +}; + +static const struct file_operations ftrace_event_filter_fops = { + .open = tracing_open_generic, + .read = event_filter_read, + .write = event_filter_write, + .llseek = default_llseek, +}; + +static const struct file_operations ftrace_subsystem_filter_fops = { + .open = subsystem_open, + .read = subsystem_filter_read, + .write = subsystem_filter_write, + .llseek = default_llseek, + .release = subsystem_release, +}; + +static const struct file_operations ftrace_system_enable_fops = { + .open = subsystem_open, + .read = system_enable_read, + .write = system_enable_write, + .llseek = default_llseek, + .release = subsystem_release, +}; + +static const struct file_operations ftrace_tr_enable_fops = { + .open = system_tr_open, + .read = system_enable_read, + .write = system_enable_write, + .llseek = default_llseek, + .release = subsystem_release, +}; + +static const struct file_operations ftrace_show_header_fops = { + .open = tracing_open_generic, + .read = show_header, + .llseek = default_llseek, +}; + +static int +ftrace_event_open(struct inode *inode, struct file *file, + const struct seq_operations *seq_ops) +{ + struct seq_file *m; + int ret; + + ret = seq_open(file, seq_ops); + if (ret < 0) + return ret; + m = file->private_data; + /* copy tr over to seq ops */ + m->private = inode->i_private; + + return ret; +} + +static int ftrace_event_release(struct inode *inode, struct file *file) +{ + struct trace_array *tr = inode->i_private; + + trace_array_put(tr); + + return seq_release(inode, file); +} + +static int +ftrace_event_avail_open(struct inode *inode, struct file *file) +{ + const struct seq_operations *seq_ops = &show_event_seq_ops; + + return ftrace_event_open(inode, file, seq_ops); +} + +static int +ftrace_event_set_open(struct inode *inode, struct file *file) +{ + const struct seq_operations *seq_ops = &show_set_event_seq_ops; + struct trace_array *tr = inode->i_private; + int ret; + + if (trace_array_get(tr) < 0) + return -ENODEV; + + if ((file->f_mode & FMODE_WRITE) && + (file->f_flags & O_TRUNC)) + ftrace_clear_events(tr); + + ret = ftrace_event_open(inode, file, seq_ops); + if (ret < 0) + trace_array_put(tr); + return ret; +} + +static struct event_subsystem * +create_new_subsystem(const char *name) +{ + struct event_subsystem *system; + + /* need to create new entry */ + system = kmalloc(sizeof(*system), GFP_KERNEL); + if (!system) + return NULL; + + system->ref_count = 1; + + /* Only allocate if dynamic (kprobes and modules) */ + if (!core_kernel_data((unsigned long)name)) { + system->ref_count |= SYSTEM_FL_FREE_NAME; + system->name = kstrdup(name, GFP_KERNEL); + if (!system->name) + goto out_free; + } else + system->name = name; + + system->filter = NULL; + + system->filter = kzalloc(sizeof(struct event_filter), GFP_KERNEL); + if (!system->filter) + goto out_free; + + list_add(&system->list, &event_subsystems); + + return system; + + out_free: + if (system->ref_count & SYSTEM_FL_FREE_NAME) + kfree(system->name); + kfree(system); + return NULL; +} + +static struct dentry * +event_subsystem_dir(struct trace_array *tr, const char *name, + struct ftrace_event_file *file, struct dentry *parent) +{ + struct ftrace_subsystem_dir *dir; + struct event_subsystem *system; + struct dentry *entry; + + /* First see if we did not already create this dir */ + list_for_each_entry(dir, &tr->systems, list) { + system = dir->subsystem; + if (strcmp(system->name, name) == 0) { + dir->nr_events++; + file->system = dir; + return dir->entry; + } + } + + /* Now see if the system itself exists. */ + list_for_each_entry(system, &event_subsystems, list) { + if (strcmp(system->name, name) == 0) + break; + } + /* Reset system variable when not found */ + if (&system->list == &event_subsystems) + system = NULL; + + dir = kmalloc(sizeof(*dir), GFP_KERNEL); + if (!dir) + goto out_fail; + + if (!system) { + system = create_new_subsystem(name); + if (!system) + goto out_free; + } else + __get_system(system); + + dir->entry = tracefs_create_dir(name, parent); + if (!dir->entry) { + pr_warn("Failed to create system directory %s\n", name); + __put_system(system); + goto out_free; + } + + dir->tr = tr; + dir->ref_count = 1; + dir->nr_events = 1; + dir->subsystem = system; + file->system = dir; + + entry = tracefs_create_file("filter", 0644, dir->entry, dir, + &ftrace_subsystem_filter_fops); + if (!entry) { + kfree(system->filter); + system->filter = NULL; + pr_warn("Could not create tracefs '%s/filter' entry\n", name); + } + + trace_create_file("enable", 0644, dir->entry, dir, + &ftrace_system_enable_fops); + + list_add(&dir->list, &tr->systems); + + return dir->entry; + + out_free: + kfree(dir); + out_fail: + /* Only print this message if failed on memory allocation */ + if (!dir || !system) + pr_warn("No memory to create event subsystem %s\n", name); + return NULL; +} + +static int +event_create_dir(struct dentry *parent, struct ftrace_event_file *file) +{ + struct ftrace_event_call *call = file->event_call; + struct trace_array *tr = file->tr; + struct list_head *head; + struct dentry *d_events; + const char *name; + int ret; + + /* + * If the trace point header did not define TRACE_SYSTEM + * then the system would be called "TRACE_SYSTEM". + */ + if (strcmp(call->class->system, TRACE_SYSTEM) != 0) { + d_events = event_subsystem_dir(tr, call->class->system, file, parent); + if (!d_events) + return -ENOMEM; + } else + d_events = parent; + + name = ftrace_event_name(call); + file->dir = tracefs_create_dir(name, d_events); + if (!file->dir) { + pr_warn("Could not create tracefs '%s' directory\n", name); + return -1; + } + + if (call->class->reg && !(call->flags & TRACE_EVENT_FL_IGNORE_ENABLE)) + trace_create_file("enable", 0644, file->dir, file, + &ftrace_enable_fops); + +#ifdef CONFIG_PERF_EVENTS + if (call->event.type && call->class->reg) + trace_create_file("id", 0444, file->dir, + (void *)(long)call->event.type, + &ftrace_event_id_fops); +#endif + + /* + * Other events may have the same class. Only update + * the fields if they are not already defined. + */ + head = trace_get_fields(call); + if (list_empty(head)) { + ret = call->class->define_fields(call); + if (ret < 0) { + pr_warn("Could not initialize trace point events/%s\n", + name); + return -1; + } + } + trace_create_file("filter", 0644, file->dir, file, + &ftrace_event_filter_fops); + + trace_create_file("trigger", 0644, file->dir, file, + &event_trigger_fops); + + trace_create_file("format", 0444, file->dir, call, + &ftrace_event_format_fops); + + return 0; +} + +static void remove_event_from_tracers(struct ftrace_event_call *call) +{ + struct ftrace_event_file *file; + struct trace_array *tr; + + do_for_each_event_file_safe(tr, file) { + if (file->event_call != call) + continue; + + remove_event_file_dir(file); + /* + * The do_for_each_event_file_safe() is + * a double loop. After finding the call for this + * trace_array, we use break to jump to the next + * trace_array. + */ + break; + } while_for_each_event_file(); +} + +static void event_remove(struct ftrace_event_call *call) +{ + struct trace_array *tr; + struct ftrace_event_file *file; + + do_for_each_event_file(tr, file) { + if (file->event_call != call) + continue; + ftrace_event_enable_disable(file, 0); + /* + * The do_for_each_event_file() is + * a double loop. After finding the call for this + * trace_array, we use break to jump to the next + * trace_array. + */ + break; + } while_for_each_event_file(); + + if (call->event.funcs) + __unregister_ftrace_event(&call->event); + remove_event_from_tracers(call); + list_del(&call->list); +} + +static int event_init(struct ftrace_event_call *call) +{ + int ret = 0; + const char *name; + + name = ftrace_event_name(call); + if (WARN_ON(!name)) + return -EINVAL; + + if (call->class->raw_init) { + ret = call->class->raw_init(call); + if (ret < 0 && ret != -ENOSYS) + pr_warn("Could not initialize trace events/%s\n", name); + } + + return ret; +} + +static int +__register_event(struct ftrace_event_call *call, struct module *mod) +{ + int ret; + + ret = event_init(call); + if (ret < 0) + return ret; + + list_add(&call->list, &ftrace_events); + call->mod = mod; + + return 0; +} + +static char *enum_replace(char *ptr, struct trace_enum_map *map, int len) +{ + int rlen; + int elen; + + /* Find the length of the enum value as a string */ + elen = snprintf(ptr, 0, "%ld", map->enum_value); + /* Make sure there's enough room to replace the string with the value */ + if (len < elen) + return NULL; + + snprintf(ptr, elen + 1, "%ld", map->enum_value); + + /* Get the rest of the string of ptr */ + rlen = strlen(ptr + len); + memmove(ptr + elen, ptr + len, rlen); + /* Make sure we end the new string */ + ptr[elen + rlen] = 0; + + return ptr + elen; +} + +static void update_event_printk(struct ftrace_event_call *call, + struct trace_enum_map *map) +{ + char *ptr; + int quote = 0; + int len = strlen(map->enum_string); + + for (ptr = call->print_fmt; *ptr; ptr++) { + if (*ptr == '\\') { + ptr++; + /* paranoid */ + if (!*ptr) + break; + continue; + } + if (*ptr == '"') { + quote ^= 1; + continue; + } + if (quote) + continue; + if (isdigit(*ptr)) { + /* skip numbers */ + do { + ptr++; + /* Check for alpha chars like ULL */ + } while (isalnum(*ptr)); + if (!*ptr) + break; + /* + * A number must have some kind of delimiter after + * it, and we can ignore that too. + */ + continue; + } + if (isalpha(*ptr) || *ptr == '_') { + if (strncmp(map->enum_string, ptr, len) == 0 && + !isalnum(ptr[len]) && ptr[len] != '_') { + ptr = enum_replace(ptr, map, len); + /* Hmm, enum string smaller than value */ + if (WARN_ON_ONCE(!ptr)) + return; + /* + * No need to decrement here, as enum_replace() + * returns the pointer to the character passed + * the enum, and two enums can not be placed + * back to back without something in between. + * We can skip that something in between. + */ + continue; + } + skip_more: + do { + ptr++; + } while (isalnum(*ptr) || *ptr == '_'); + if (!*ptr) + break; + /* + * If what comes after this variable is a '.' or + * '->' then we can continue to ignore that string. + */ + if (*ptr == '.' || (ptr[0] == '-' && ptr[1] == '>')) { + ptr += *ptr == '.' ? 1 : 2; + if (!*ptr) + break; + goto skip_more; + } + /* + * Once again, we can skip the delimiter that came + * after the string. + */ + continue; + } + } +} + +void trace_event_enum_update(struct trace_enum_map **map, int len) +{ + struct ftrace_event_call *call, *p; + const char *last_system = NULL; + int last_i; + int i; + + down_write(&trace_event_sem); + list_for_each_entry_safe(call, p, &ftrace_events, list) { + /* events are usually grouped together with systems */ + if (!last_system || call->class->system != last_system) { + last_i = 0; + last_system = call->class->system; + } + + for (i = last_i; i < len; i++) { + if (call->class->system == map[i]->system) { + /* Save the first system if need be */ + if (!last_i) + last_i = i; + update_event_printk(call, map[i]); + } + } + } + up_write(&trace_event_sem); +} + +static struct ftrace_event_file * +trace_create_new_event(struct ftrace_event_call *call, + struct trace_array *tr) +{ + struct ftrace_event_file *file; + + file = kmem_cache_alloc(file_cachep, GFP_TRACE); + if (!file) + return NULL; + + file->event_call = call; + file->tr = tr; + atomic_set(&file->sm_ref, 0); + atomic_set(&file->tm_ref, 0); + INIT_LIST_HEAD(&file->triggers); + list_add(&file->list, &tr->events); + + return file; +} + +/* Add an event to a trace directory */ +static int +__trace_add_new_event(struct ftrace_event_call *call, struct trace_array *tr) +{ + struct ftrace_event_file *file; + + file = trace_create_new_event(call, tr); + if (!file) + return -ENOMEM; + + return event_create_dir(tr->event_dir, file); +} + +/* + * Just create a decriptor for early init. A descriptor is required + * for enabling events at boot. We want to enable events before + * the filesystem is initialized. + */ +static __init int +__trace_early_add_new_event(struct ftrace_event_call *call, + struct trace_array *tr) +{ + struct ftrace_event_file *file; + + file = trace_create_new_event(call, tr); + if (!file) + return -ENOMEM; + + return 0; +} + +struct ftrace_module_file_ops; +static void __add_event_to_tracers(struct ftrace_event_call *call); + +/* Add an additional event_call dynamically */ +int trace_add_event_call(struct ftrace_event_call *call) +{ + int ret; + mutex_lock(&trace_types_lock); + mutex_lock(&event_mutex); + + ret = __register_event(call, NULL); + if (ret >= 0) + __add_event_to_tracers(call); + + mutex_unlock(&event_mutex); + mutex_unlock(&trace_types_lock); + return ret; +} + +/* + * Must be called under locking of trace_types_lock, event_mutex and + * trace_event_sem. + */ +static void __trace_remove_event_call(struct ftrace_event_call *call) +{ + event_remove(call); + trace_destroy_fields(call); + free_event_filter(call->filter); + call->filter = NULL; +} + +static int probe_remove_event_call(struct ftrace_event_call *call) +{ + struct trace_array *tr; + struct ftrace_event_file *file; + +#ifdef CONFIG_PERF_EVENTS + if (call->perf_refcount) + return -EBUSY; +#endif + do_for_each_event_file(tr, file) { + if (file->event_call != call) + continue; + /* + * We can't rely on ftrace_event_enable_disable(enable => 0) + * we are going to do, FTRACE_EVENT_FL_SOFT_MODE can suppress + * TRACE_REG_UNREGISTER. + */ + if (file->flags & FTRACE_EVENT_FL_ENABLED) + return -EBUSY; + /* + * The do_for_each_event_file_safe() is + * a double loop. After finding the call for this + * trace_array, we use break to jump to the next + * trace_array. + */ + break; + } while_for_each_event_file(); + + __trace_remove_event_call(call); + + return 0; +} + +/* Remove an event_call */ +int trace_remove_event_call(struct ftrace_event_call *call) +{ + int ret; + + mutex_lock(&trace_types_lock); + mutex_lock(&event_mutex); + down_write(&trace_event_sem); + ret = probe_remove_event_call(call); + up_write(&trace_event_sem); + mutex_unlock(&event_mutex); + mutex_unlock(&trace_types_lock); + + return ret; +} + +#define for_each_event(event, start, end) \ + for (event = start; \ + (unsigned long)event < (unsigned long)end; \ + event++) + +#ifdef CONFIG_MODULES + +static void trace_module_add_events(struct module *mod) +{ + struct ftrace_event_call **call, **start, **end; + + if (!mod->num_trace_events) + return; + + /* Don't add infrastructure for mods without tracepoints */ + if (trace_module_has_bad_taint(mod)) { + pr_err("%s: module has bad taint, not creating trace events\n", + mod->name); + return; + } + + start = mod->trace_events; + end = mod->trace_events + mod->num_trace_events; + + for_each_event(call, start, end) { + __register_event(*call, mod); + __add_event_to_tracers(*call); + } +} + +static void trace_module_remove_events(struct module *mod) +{ + struct ftrace_event_call *call, *p; + bool clear_trace = false; + + down_write(&trace_event_sem); + list_for_each_entry_safe(call, p, &ftrace_events, list) { + if (call->mod == mod) { + if (call->flags & TRACE_EVENT_FL_WAS_ENABLED) + clear_trace = true; + __trace_remove_event_call(call); + } + } + up_write(&trace_event_sem); + + /* + * It is safest to reset the ring buffer if the module being unloaded + * registered any events that were used. The only worry is if + * a new module gets loaded, and takes on the same id as the events + * of this module. When printing out the buffer, traced events left + * over from this module may be passed to the new module events and + * unexpected results may occur. + */ + if (clear_trace) + tracing_reset_all_online_cpus(); +} + +static int trace_module_notify(struct notifier_block *self, + unsigned long val, void *data) +{ + struct module *mod = data; + + mutex_lock(&trace_types_lock); + mutex_lock(&event_mutex); + switch (val) { + case MODULE_STATE_COMING: + trace_module_add_events(mod); + break; + case MODULE_STATE_GOING: + trace_module_remove_events(mod); + break; + } + mutex_unlock(&event_mutex); + mutex_unlock(&trace_types_lock); + + return 0; +} + +static struct notifier_block trace_module_nb = { + .notifier_call = trace_module_notify, + .priority = 1, /* higher than trace.c module notify */ +}; +#endif /* CONFIG_MODULES */ + +/* Create a new event directory structure for a trace directory. */ +static void +__trace_add_event_dirs(struct trace_array *tr) +{ + struct ftrace_event_call *call; + int ret; + + list_for_each_entry(call, &ftrace_events, list) { + ret = __trace_add_new_event(call, tr); + if (ret < 0) + pr_warn("Could not create directory for event %s\n", + ftrace_event_name(call)); + } +} + +struct ftrace_event_file * +find_event_file(struct trace_array *tr, const char *system, const char *event) +{ + struct ftrace_event_file *file; + struct ftrace_event_call *call; + const char *name; + + list_for_each_entry(file, &tr->events, list) { + + call = file->event_call; + name = ftrace_event_name(call); + + if (!name || !call->class || !call->class->reg) + continue; + + if (call->flags & TRACE_EVENT_FL_IGNORE_ENABLE) + continue; + + if (strcmp(event, name) == 0 && + strcmp(system, call->class->system) == 0) + return file; + } + return NULL; +} + +#ifdef CONFIG_DYNAMIC_FTRACE + +/* Avoid typos */ +#define ENABLE_EVENT_STR "enable_event" +#define DISABLE_EVENT_STR "disable_event" + +struct event_probe_data { + struct ftrace_event_file *file; + unsigned long count; + int ref; + bool enable; +}; + +static void +event_enable_probe(unsigned long ip, unsigned long parent_ip, void **_data) +{ + struct event_probe_data **pdata = (struct event_probe_data **)_data; + struct event_probe_data *data = *pdata; + + if (!data) + return; + + if (data->enable) + clear_bit(FTRACE_EVENT_FL_SOFT_DISABLED_BIT, &data->file->flags); + else + set_bit(FTRACE_EVENT_FL_SOFT_DISABLED_BIT, &data->file->flags); +} + +static void +event_enable_count_probe(unsigned long ip, unsigned long parent_ip, void **_data) +{ + struct event_probe_data **pdata = (struct event_probe_data **)_data; + struct event_probe_data *data = *pdata; + + if (!data) + return; + + if (!data->count) + return; + + /* Skip if the event is in a state we want to switch to */ + if (data->enable == !(data->file->flags & FTRACE_EVENT_FL_SOFT_DISABLED)) + return; + + if (data->count != -1) + (data->count)--; + + event_enable_probe(ip, parent_ip, _data); +} + +static int +event_enable_print(struct seq_file *m, unsigned long ip, + struct ftrace_probe_ops *ops, void *_data) +{ + struct event_probe_data *data = _data; + + seq_printf(m, "%ps:", (void *)ip); + + seq_printf(m, "%s:%s:%s", + data->enable ? ENABLE_EVENT_STR : DISABLE_EVENT_STR, + data->file->event_call->class->system, + ftrace_event_name(data->file->event_call)); + + if (data->count == -1) + seq_puts(m, ":unlimited\n"); + else + seq_printf(m, ":count=%ld\n", data->count); + + return 0; +} + +static int +event_enable_init(struct ftrace_probe_ops *ops, unsigned long ip, + void **_data) +{ + struct event_probe_data **pdata = (struct event_probe_data **)_data; + struct event_probe_data *data = *pdata; + + data->ref++; + return 0; +} + +static void +event_enable_free(struct ftrace_probe_ops *ops, unsigned long ip, + void **_data) +{ + struct event_probe_data **pdata = (struct event_probe_data **)_data; + struct event_probe_data *data = *pdata; + + if (WARN_ON_ONCE(data->ref <= 0)) + return; + + data->ref--; + if (!data->ref) { + /* Remove the SOFT_MODE flag */ + __ftrace_event_enable_disable(data->file, 0, 1); + module_put(data->file->event_call->mod); + kfree(data); + } + *pdata = NULL; +} + +static struct ftrace_probe_ops event_enable_probe_ops = { + .func = event_enable_probe, + .print = event_enable_print, + .init = event_enable_init, + .free = event_enable_free, +}; + +static struct ftrace_probe_ops event_enable_count_probe_ops = { + .func = event_enable_count_probe, + .print = event_enable_print, + .init = event_enable_init, + .free = event_enable_free, +}; + +static struct ftrace_probe_ops event_disable_probe_ops = { + .func = event_enable_probe, + .print = event_enable_print, + .init = event_enable_init, + .free = event_enable_free, +}; + +static struct ftrace_probe_ops event_disable_count_probe_ops = { + .func = event_enable_count_probe, + .print = event_enable_print, + .init = event_enable_init, + .free = event_enable_free, +}; + +static int +event_enable_func(struct ftrace_hash *hash, + char *glob, char *cmd, char *param, int enabled) +{ + struct trace_array *tr = top_trace_array(); + struct ftrace_event_file *file; + struct ftrace_probe_ops *ops; + struct event_probe_data *data; + const char *system; + const char *event; + char *number; + bool enable; + int ret; + + if (!tr) + return -ENODEV; + + /* hash funcs only work with set_ftrace_filter */ + if (!enabled || !param) + return -EINVAL; + + system = strsep(¶m, ":"); + if (!param) + return -EINVAL; + + event = strsep(¶m, ":"); + + mutex_lock(&event_mutex); + + ret = -EINVAL; + file = find_event_file(tr, system, event); + if (!file) + goto out; + + enable = strcmp(cmd, ENABLE_EVENT_STR) == 0; + + if (enable) + ops = param ? &event_enable_count_probe_ops : &event_enable_probe_ops; + else + ops = param ? &event_disable_count_probe_ops : &event_disable_probe_ops; + + if (glob[0] == '!') { + unregister_ftrace_function_probe_func(glob+1, ops); + ret = 0; + goto out; + } + + ret = -ENOMEM; + data = kzalloc(sizeof(*data), GFP_KERNEL); + if (!data) + goto out; + + data->enable = enable; + data->count = -1; + data->file = file; + + if (!param) + goto out_reg; + + number = strsep(¶m, ":"); + + ret = -EINVAL; + if (!strlen(number)) + goto out_free; + + /* + * We use the callback data field (which is a pointer) + * as our counter. + */ + ret = kstrtoul(number, 0, &data->count); + if (ret) + goto out_free; + + out_reg: + /* Don't let event modules unload while probe registered */ + ret = try_module_get(file->event_call->mod); + if (!ret) { + ret = -EBUSY; + goto out_free; + } + + ret = __ftrace_event_enable_disable(file, 1, 1); + if (ret < 0) + goto out_put; + ret = register_ftrace_function_probe(glob, ops, data); + /* + * The above returns on success the # of functions enabled, + * but if it didn't find any functions it returns zero. + * Consider no functions a failure too. + */ + if (!ret) { + ret = -ENOENT; + goto out_disable; + } else if (ret < 0) + goto out_disable; + /* Just return zero, not the number of enabled functions */ + ret = 0; + out: + mutex_unlock(&event_mutex); + return ret; + + out_disable: + __ftrace_event_enable_disable(file, 0, 1); + out_put: + module_put(file->event_call->mod); + out_free: + kfree(data); + goto out; +} + +static struct ftrace_func_command event_enable_cmd = { + .name = ENABLE_EVENT_STR, + .func = event_enable_func, +}; + +static struct ftrace_func_command event_disable_cmd = { + .name = DISABLE_EVENT_STR, + .func = event_enable_func, +}; + +static __init int register_event_cmds(void) +{ + int ret; + + ret = register_ftrace_command(&event_enable_cmd); + if (WARN_ON(ret < 0)) + return ret; + ret = register_ftrace_command(&event_disable_cmd); + if (WARN_ON(ret < 0)) + unregister_ftrace_command(&event_enable_cmd); + return ret; +} +#else +static inline int register_event_cmds(void) { return 0; } +#endif /* CONFIG_DYNAMIC_FTRACE */ + +/* + * The top level array has already had its ftrace_event_file + * descriptors created in order to allow for early events to + * be recorded. This function is called after the tracefs has been + * initialized, and we now have to create the files associated + * to the events. + */ +static __init void +__trace_early_add_event_dirs(struct trace_array *tr) +{ + struct ftrace_event_file *file; + int ret; + + + list_for_each_entry(file, &tr->events, list) { + ret = event_create_dir(tr->event_dir, file); + if (ret < 0) + pr_warn("Could not create directory for event %s\n", + ftrace_event_name(file->event_call)); + } +} + +/* + * For early boot up, the top trace array requires to have + * a list of events that can be enabled. This must be done before + * the filesystem is set up in order to allow events to be traced + * early. + */ +static __init void +__trace_early_add_events(struct trace_array *tr) +{ + struct ftrace_event_call *call; + int ret; + + list_for_each_entry(call, &ftrace_events, list) { + /* Early boot up should not have any modules loaded */ + if (WARN_ON_ONCE(call->mod)) + continue; + + ret = __trace_early_add_new_event(call, tr); + if (ret < 0) + pr_warn("Could not create early event %s\n", + ftrace_event_name(call)); + } +} + +/* Remove the event directory structure for a trace directory. */ +static void +__trace_remove_event_dirs(struct trace_array *tr) +{ + struct ftrace_event_file *file, *next; + + list_for_each_entry_safe(file, next, &tr->events, list) + remove_event_file_dir(file); +} + +static void __add_event_to_tracers(struct ftrace_event_call *call) +{ + struct trace_array *tr; + + list_for_each_entry(tr, &ftrace_trace_arrays, list) + __trace_add_new_event(call, tr); +} + +extern struct ftrace_event_call *__start_ftrace_events[]; +extern struct ftrace_event_call *__stop_ftrace_events[]; + +static char bootup_event_buf[COMMAND_LINE_SIZE] __initdata; + +static __init int setup_trace_event(char *str) +{ + strlcpy(bootup_event_buf, str, COMMAND_LINE_SIZE); + ring_buffer_expanded = true; + tracing_selftest_disabled = true; + + return 1; +} +__setup("trace_event=", setup_trace_event); + +/* Expects to have event_mutex held when called */ +static int +create_event_toplevel_files(struct dentry *parent, struct trace_array *tr) +{ + struct dentry *d_events; + struct dentry *entry; + + entry = tracefs_create_file("set_event", 0644, parent, + tr, &ftrace_set_event_fops); + if (!entry) { + pr_warn("Could not create tracefs 'set_event' entry\n"); + return -ENOMEM; + } + + d_events = tracefs_create_dir("events", parent); + if (!d_events) { + pr_warn("Could not create tracefs 'events' directory\n"); + return -ENOMEM; + } + + /* ring buffer internal formats */ + trace_create_file("header_page", 0444, d_events, + ring_buffer_print_page_header, + &ftrace_show_header_fops); + + trace_create_file("header_event", 0444, d_events, + ring_buffer_print_entry_header, + &ftrace_show_header_fops); + + trace_create_file("enable", 0644, d_events, + tr, &ftrace_tr_enable_fops); + + tr->event_dir = d_events; + + return 0; +} + +/** + * event_trace_add_tracer - add a instance of a trace_array to events + * @parent: The parent dentry to place the files/directories for events in + * @tr: The trace array associated with these events + * + * When a new instance is created, it needs to set up its events + * directory, as well as other files associated with events. It also + * creates the event hierachry in the @parent/events directory. + * + * Returns 0 on success. + */ +int event_trace_add_tracer(struct dentry *parent, struct trace_array *tr) +{ + int ret; + + mutex_lock(&event_mutex); + + ret = create_event_toplevel_files(parent, tr); + if (ret) + goto out_unlock; + + down_write(&trace_event_sem); + __trace_add_event_dirs(tr); + up_write(&trace_event_sem); + + out_unlock: + mutex_unlock(&event_mutex); + + return ret; +} + +/* + * The top trace array already had its file descriptors created. + * Now the files themselves need to be created. + */ +static __init int +early_event_add_tracer(struct dentry *parent, struct trace_array *tr) +{ + int ret; + + mutex_lock(&event_mutex); + + ret = create_event_toplevel_files(parent, tr); + if (ret) + goto out_unlock; + + down_write(&trace_event_sem); + __trace_early_add_event_dirs(tr); + up_write(&trace_event_sem); + + out_unlock: + mutex_unlock(&event_mutex); + + return ret; +} + +int event_trace_del_tracer(struct trace_array *tr) +{ + mutex_lock(&event_mutex); + + /* Disable any event triggers and associated soft-disabled events */ + clear_event_triggers(tr); + + /* Disable any running events */ + __ftrace_set_clr_event_nolock(tr, NULL, NULL, NULL, 0); + + /* Access to events are within rcu_read_lock_sched() */ + synchronize_sched(); + + down_write(&trace_event_sem); + __trace_remove_event_dirs(tr); + tracefs_remove_recursive(tr->event_dir); + up_write(&trace_event_sem); + + tr->event_dir = NULL; + + mutex_unlock(&event_mutex); + + return 0; +} + +static __init int event_trace_memsetup(void) +{ + field_cachep = KMEM_CACHE(ftrace_event_field, SLAB_PANIC); + file_cachep = KMEM_CACHE(ftrace_event_file, SLAB_PANIC); + return 0; +} + +static __init void +early_enable_events(struct trace_array *tr, bool disable_first) +{ + char *buf = bootup_event_buf; + char *token; + int ret; + + while (true) { + token = strsep(&buf, ","); + + if (!token) + break; + if (!*token) + continue; + + /* Restarting syscalls requires that we stop them first */ + if (disable_first) + ftrace_set_clr_event(tr, token, 0); + + ret = ftrace_set_clr_event(tr, token, 1); + if (ret) + pr_warn("Failed to enable trace event: %s\n", token); + + /* Put back the comma to allow this to be called again */ + if (buf) + *(buf - 1) = ','; + } +} + +static __init int event_trace_enable(void) +{ + struct trace_array *tr = top_trace_array(); + struct ftrace_event_call **iter, *call; + int ret; + + if (!tr) + return -ENODEV; + + for_each_event(iter, __start_ftrace_events, __stop_ftrace_events) { + + call = *iter; + ret = event_init(call); + if (!ret) + list_add(&call->list, &ftrace_events); + } + + /* + * We need the top trace array to have a working set of trace + * points at early init, before the debug files and directories + * are created. Create the file entries now, and attach them + * to the actual file dentries later. + */ + __trace_early_add_events(tr); + + early_enable_events(tr, false); + + trace_printk_start_comm(); + + register_event_cmds(); + + register_trigger_cmds(); + + return 0; +} + +/* + * event_trace_enable() is called from trace_event_init() first to + * initialize events and perhaps start any events that are on the + * command line. Unfortunately, there are some events that will not + * start this early, like the system call tracepoints that need + * to set the TIF_SYSCALL_TRACEPOINT flag of pid 1. But event_trace_enable() + * is called before pid 1 starts, and this flag is never set, making + * the syscall tracepoint never get reached, but the event is enabled + * regardless (and not doing anything). + */ +static __init int event_trace_enable_again(void) +{ + struct trace_array *tr; + + tr = top_trace_array(); + if (!tr) + return -ENODEV; + + early_enable_events(tr, true); + + return 0; +} + +early_initcall(event_trace_enable_again); + +static __init int event_trace_init(void) +{ + struct trace_array *tr; + struct dentry *d_tracer; + struct dentry *entry; + int ret; + + tr = top_trace_array(); + if (!tr) + return -ENODEV; + + d_tracer = tracing_init_dentry(); + if (IS_ERR(d_tracer)) + return 0; + + entry = tracefs_create_file("available_events", 0444, d_tracer, + tr, &ftrace_avail_fops); + if (!entry) + pr_warn("Could not create tracefs 'available_events' entry\n"); + + if (trace_define_common_fields()) + pr_warn("tracing: Failed to allocate common fields"); + + ret = early_event_add_tracer(d_tracer, tr); + if (ret) + return ret; + +#ifdef CONFIG_MODULES + ret = register_module_notifier(&trace_module_nb); + if (ret) + pr_warn("Failed to register trace events module notifier\n"); +#endif + return 0; +} + +void __init trace_event_init(void) +{ + event_trace_memsetup(); + init_ftrace_syscalls(); + event_trace_enable(); +} + +fs_initcall(event_trace_init); + +#ifdef CONFIG_FTRACE_STARTUP_TEST + +static DEFINE_SPINLOCK(test_spinlock); +static DEFINE_SPINLOCK(test_spinlock_irq); +static DEFINE_MUTEX(test_mutex); + +static __init void test_work(struct work_struct *dummy) +{ + spin_lock(&test_spinlock); + spin_lock_irq(&test_spinlock_irq); + udelay(1); + spin_unlock_irq(&test_spinlock_irq); + spin_unlock(&test_spinlock); + + mutex_lock(&test_mutex); + msleep(1); + mutex_unlock(&test_mutex); +} + +static __init int event_test_thread(void *unused) +{ + void *test_malloc; + + test_malloc = kmalloc(1234, GFP_KERNEL); + if (!test_malloc) + pr_info("failed to kmalloc\n"); + + schedule_on_each_cpu(test_work); + + kfree(test_malloc); + + set_current_state(TASK_INTERRUPTIBLE); + while (!kthread_should_stop()) { + schedule(); + set_current_state(TASK_INTERRUPTIBLE); + } + __set_current_state(TASK_RUNNING); + + return 0; +} + +/* + * Do various things that may trigger events. + */ +static __init void event_test_stuff(void) +{ + struct task_struct *test_thread; + + test_thread = kthread_run(event_test_thread, NULL, "test-events"); + msleep(1); + kthread_stop(test_thread); +} + +/* + * For every trace event defined, we will test each trace point separately, + * and then by groups, and finally all trace points. + */ +static __init void event_trace_self_tests(void) +{ + struct ftrace_subsystem_dir *dir; + struct ftrace_event_file *file; + struct ftrace_event_call *call; + struct event_subsystem *system; + struct trace_array *tr; + int ret; + + tr = top_trace_array(); + if (!tr) + return; + + pr_info("Running tests on trace events:\n"); + + list_for_each_entry(file, &tr->events, list) { + + call = file->event_call; + + /* Only test those that have a probe */ + if (!call->class || !call->class->probe) + continue; + +/* + * Testing syscall events here is pretty useless, but + * we still do it if configured. But this is time consuming. + * What we really need is a user thread to perform the + * syscalls as we test. + */ +#ifndef CONFIG_EVENT_TRACE_TEST_SYSCALLS + if (call->class->system && + strcmp(call->class->system, "syscalls") == 0) + continue; +#endif + + pr_info("Testing event %s: ", ftrace_event_name(call)); + + /* + * If an event is already enabled, someone is using + * it and the self test should not be on. + */ + if (file->flags & FTRACE_EVENT_FL_ENABLED) { + pr_warn("Enabled event during self test!\n"); + WARN_ON_ONCE(1); + continue; + } + + ftrace_event_enable_disable(file, 1); + event_test_stuff(); + ftrace_event_enable_disable(file, 0); + + pr_cont("OK\n"); + } + + /* Now test at the sub system level */ + + pr_info("Running tests on trace event systems:\n"); + + list_for_each_entry(dir, &tr->systems, list) { + + system = dir->subsystem; + + /* the ftrace system is special, skip it */ + if (strcmp(system->name, "ftrace") == 0) + continue; + + pr_info("Testing event system %s: ", system->name); + + ret = __ftrace_set_clr_event(tr, NULL, system->name, NULL, 1); + if (WARN_ON_ONCE(ret)) { + pr_warn("error enabling system %s\n", + system->name); + continue; + } + + event_test_stuff(); + + ret = __ftrace_set_clr_event(tr, NULL, system->name, NULL, 0); + if (WARN_ON_ONCE(ret)) { + pr_warn("error disabling system %s\n", + system->name); + continue; + } + + pr_cont("OK\n"); + } + + /* Test with all events enabled */ + + pr_info("Running tests on all trace events:\n"); + pr_info("Testing all events: "); + + ret = __ftrace_set_clr_event(tr, NULL, NULL, NULL, 1); + if (WARN_ON_ONCE(ret)) { + pr_warn("error enabling all events\n"); + return; + } + + event_test_stuff(); + + /* reset sysname */ + ret = __ftrace_set_clr_event(tr, NULL, NULL, NULL, 0); + if (WARN_ON_ONCE(ret)) { + pr_warn("error disabling all events\n"); + return; + } + + pr_cont("OK\n"); +} + +#ifdef CONFIG_FUNCTION_TRACER + +static DEFINE_PER_CPU(atomic_t, ftrace_test_event_disable); + +static void +function_test_events_call(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct pt_regs *pt_regs) +{ + struct ring_buffer_event *event; + struct ring_buffer *buffer; + struct ftrace_entry *entry; + unsigned long flags; + long disabled; + int cpu; + int pc; + + pc = preempt_count(); + preempt_disable_notrace(); + cpu = raw_smp_processor_id(); + disabled = atomic_inc_return(&per_cpu(ftrace_test_event_disable, cpu)); + + if (disabled != 1) + goto out; + + local_save_flags(flags); + + event = trace_current_buffer_lock_reserve(&buffer, + TRACE_FN, sizeof(*entry), + flags, pc); + if (!event) + goto out; + entry = ring_buffer_event_data(event); + entry->ip = ip; + entry->parent_ip = parent_ip; + + trace_buffer_unlock_commit(buffer, event, flags, pc); + + out: + atomic_dec(&per_cpu(ftrace_test_event_disable, cpu)); + preempt_enable_notrace(); +} + +static struct ftrace_ops trace_ops __initdata = +{ + .func = function_test_events_call, + .flags = FTRACE_OPS_FL_RECURSION_SAFE, +}; + +static __init void event_trace_self_test_with_function(void) +{ + int ret; + ret = register_ftrace_function(&trace_ops); + if (WARN_ON(ret < 0)) { + pr_info("Failed to enable function tracer for event tests\n"); + return; + } + pr_info("Running tests again, along with the function tracer\n"); + event_trace_self_tests(); + unregister_ftrace_function(&trace_ops); +} +#else +static __init void event_trace_self_test_with_function(void) +{ +} +#endif + +static __init int event_trace_self_tests_init(void) +{ + if (!tracing_selftest_disabled) { + event_trace_self_tests(); + event_trace_self_test_with_function(); + } + + return 0; +} + +late_initcall(event_trace_self_tests_init); + +#endif diff --git a/kernel/kernel/trace/trace_events_filter.c b/kernel/kernel/trace/trace_events_filter.c new file mode 100644 index 000000000..7f2e97ce7 --- /dev/null +++ b/kernel/kernel/trace/trace_events_filter.c @@ -0,0 +1,2432 @@ +/* + * trace_events_filter - generic event filtering + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * + * Copyright (C) 2009 Tom Zanussi + */ + +#include +#include +#include +#include +#include + +#include "trace.h" +#include "trace_output.h" + +#define DEFAULT_SYS_FILTER_MESSAGE \ + "### global filter ###\n" \ + "# Use this to set filters for multiple events.\n" \ + "# Only events with the given fields will be affected.\n" \ + "# If no events are modified, an error message will be displayed here" + +enum filter_op_ids +{ + OP_OR, + OP_AND, + OP_GLOB, + OP_NE, + OP_EQ, + OP_LT, + OP_LE, + OP_GT, + OP_GE, + OP_BAND, + OP_NOT, + OP_NONE, + OP_OPEN_PAREN, +}; + +struct filter_op { + int id; + char *string; + int precedence; +}; + +/* Order must be the same as enum filter_op_ids above */ +static struct filter_op filter_ops[] = { + { OP_OR, "||", 1 }, + { OP_AND, "&&", 2 }, + { OP_GLOB, "~", 4 }, + { OP_NE, "!=", 4 }, + { OP_EQ, "==", 4 }, + { OP_LT, "<", 5 }, + { OP_LE, "<=", 5 }, + { OP_GT, ">", 5 }, + { OP_GE, ">=", 5 }, + { OP_BAND, "&", 6 }, + { OP_NOT, "!", 6 }, + { OP_NONE, "OP_NONE", 0 }, + { OP_OPEN_PAREN, "(", 0 }, +}; + +enum { + FILT_ERR_NONE, + FILT_ERR_INVALID_OP, + FILT_ERR_UNBALANCED_PAREN, + FILT_ERR_TOO_MANY_OPERANDS, + FILT_ERR_OPERAND_TOO_LONG, + FILT_ERR_FIELD_NOT_FOUND, + FILT_ERR_ILLEGAL_FIELD_OP, + FILT_ERR_ILLEGAL_INTVAL, + FILT_ERR_BAD_SUBSYS_FILTER, + FILT_ERR_TOO_MANY_PREDS, + FILT_ERR_MISSING_FIELD, + FILT_ERR_INVALID_FILTER, + FILT_ERR_IP_FIELD_ONLY, + FILT_ERR_ILLEGAL_NOT_OP, +}; + +static char *err_text[] = { + "No error", + "Invalid operator", + "Unbalanced parens", + "Too many operands", + "Operand too long", + "Field not found", + "Illegal operation for field type", + "Illegal integer value", + "Couldn't find or set field in one of a subsystem's events", + "Too many terms in predicate expression", + "Missing field name and/or value", + "Meaningless filter expression", + "Only 'ip' field is supported for function trace", + "Illegal use of '!'", +}; + +struct opstack_op { + int op; + struct list_head list; +}; + +struct postfix_elt { + int op; + char *operand; + struct list_head list; +}; + +struct filter_parse_state { + struct filter_op *ops; + struct list_head opstack; + struct list_head postfix; + int lasterr; + int lasterr_pos; + + struct { + char *string; + unsigned int cnt; + unsigned int tail; + } infix; + + struct { + char string[MAX_FILTER_STR_VAL]; + int pos; + unsigned int tail; + } operand; +}; + +struct pred_stack { + struct filter_pred **preds; + int index; +}; + +/* If not of not match is equal to not of not, then it is a match */ +#define DEFINE_COMPARISON_PRED(type) \ +static int filter_pred_##type(struct filter_pred *pred, void *event) \ +{ \ + type *addr = (type *)(event + pred->offset); \ + type val = (type)pred->val; \ + int match = 0; \ + \ + switch (pred->op) { \ + case OP_LT: \ + match = (*addr < val); \ + break; \ + case OP_LE: \ + match = (*addr <= val); \ + break; \ + case OP_GT: \ + match = (*addr > val); \ + break; \ + case OP_GE: \ + match = (*addr >= val); \ + break; \ + case OP_BAND: \ + match = (*addr & val); \ + break; \ + default: \ + break; \ + } \ + \ + return !!match == !pred->not; \ +} + +#define DEFINE_EQUALITY_PRED(size) \ +static int filter_pred_##size(struct filter_pred *pred, void *event) \ +{ \ + u##size *addr = (u##size *)(event + pred->offset); \ + u##size val = (u##size)pred->val; \ + int match; \ + \ + match = (val == *addr) ^ pred->not; \ + \ + return match; \ +} + +DEFINE_COMPARISON_PRED(s64); +DEFINE_COMPARISON_PRED(u64); +DEFINE_COMPARISON_PRED(s32); +DEFINE_COMPARISON_PRED(u32); +DEFINE_COMPARISON_PRED(s16); +DEFINE_COMPARISON_PRED(u16); +DEFINE_COMPARISON_PRED(s8); +DEFINE_COMPARISON_PRED(u8); + +DEFINE_EQUALITY_PRED(64); +DEFINE_EQUALITY_PRED(32); +DEFINE_EQUALITY_PRED(16); +DEFINE_EQUALITY_PRED(8); + +/* Filter predicate for fixed sized arrays of characters */ +static int filter_pred_string(struct filter_pred *pred, void *event) +{ + char *addr = (char *)(event + pred->offset); + int cmp, match; + + cmp = pred->regex.match(addr, &pred->regex, pred->regex.field_len); + + match = cmp ^ pred->not; + + return match; +} + +/* Filter predicate for char * pointers */ +static int filter_pred_pchar(struct filter_pred *pred, void *event) +{ + char **addr = (char **)(event + pred->offset); + int cmp, match; + int len = strlen(*addr) + 1; /* including tailing '\0' */ + + cmp = pred->regex.match(*addr, &pred->regex, len); + + match = cmp ^ pred->not; + + return match; +} + +/* + * Filter predicate for dynamic sized arrays of characters. + * These are implemented through a list of strings at the end + * of the entry. + * Also each of these strings have a field in the entry which + * contains its offset from the beginning of the entry. + * We have then first to get this field, dereference it + * and add it to the address of the entry, and at last we have + * the address of the string. + */ +static int filter_pred_strloc(struct filter_pred *pred, void *event) +{ + u32 str_item = *(u32 *)(event + pred->offset); + int str_loc = str_item & 0xffff; + int str_len = str_item >> 16; + char *addr = (char *)(event + str_loc); + int cmp, match; + + cmp = pred->regex.match(addr, &pred->regex, str_len); + + match = cmp ^ pred->not; + + return match; +} + +static int filter_pred_none(struct filter_pred *pred, void *event) +{ + return 0; +} + +/* + * regex_match_foo - Basic regex callbacks + * + * @str: the string to be searched + * @r: the regex structure containing the pattern string + * @len: the length of the string to be searched (including '\0') + * + * Note: + * - @str might not be NULL-terminated if it's of type DYN_STRING + * or STATIC_STRING + */ + +static int regex_match_full(char *str, struct regex *r, int len) +{ + if (strncmp(str, r->pattern, len) == 0) + return 1; + return 0; +} + +static int regex_match_front(char *str, struct regex *r, int len) +{ + if (strncmp(str, r->pattern, r->len) == 0) + return 1; + return 0; +} + +static int regex_match_middle(char *str, struct regex *r, int len) +{ + if (strnstr(str, r->pattern, len)) + return 1; + return 0; +} + +static int regex_match_end(char *str, struct regex *r, int len) +{ + int strlen = len - 1; + + if (strlen >= r->len && + memcmp(str + strlen - r->len, r->pattern, r->len) == 0) + return 1; + return 0; +} + +/** + * filter_parse_regex - parse a basic regex + * @buff: the raw regex + * @len: length of the regex + * @search: will point to the beginning of the string to compare + * @not: tell whether the match will have to be inverted + * + * This passes in a buffer containing a regex and this function will + * set search to point to the search part of the buffer and + * return the type of search it is (see enum above). + * This does modify buff. + * + * Returns enum type. + * search returns the pointer to use for comparison. + * not returns 1 if buff started with a '!' + * 0 otherwise. + */ +enum regex_type filter_parse_regex(char *buff, int len, char **search, int *not) +{ + int type = MATCH_FULL; + int i; + + if (buff[0] == '!') { + *not = 1; + buff++; + len--; + } else + *not = 0; + + *search = buff; + + for (i = 0; i < len; i++) { + if (buff[i] == '*') { + if (!i) { + *search = buff + 1; + type = MATCH_END_ONLY; + } else { + if (type == MATCH_END_ONLY) + type = MATCH_MIDDLE_ONLY; + else + type = MATCH_FRONT_ONLY; + buff[i] = 0; + break; + } + } + } + + return type; +} + +static void filter_build_regex(struct filter_pred *pred) +{ + struct regex *r = &pred->regex; + char *search; + enum regex_type type = MATCH_FULL; + int not = 0; + + if (pred->op == OP_GLOB) { + type = filter_parse_regex(r->pattern, r->len, &search, ¬); + r->len = strlen(search); + memmove(r->pattern, search, r->len+1); + } + + switch (type) { + case MATCH_FULL: + r->match = regex_match_full; + break; + case MATCH_FRONT_ONLY: + r->match = regex_match_front; + break; + case MATCH_MIDDLE_ONLY: + r->match = regex_match_middle; + break; + case MATCH_END_ONLY: + r->match = regex_match_end; + break; + } + + pred->not ^= not; +} + +enum move_type { + MOVE_DOWN, + MOVE_UP_FROM_LEFT, + MOVE_UP_FROM_RIGHT +}; + +static struct filter_pred * +get_pred_parent(struct filter_pred *pred, struct filter_pred *preds, + int index, enum move_type *move) +{ + if (pred->parent & FILTER_PRED_IS_RIGHT) + *move = MOVE_UP_FROM_RIGHT; + else + *move = MOVE_UP_FROM_LEFT; + pred = &preds[pred->parent & ~FILTER_PRED_IS_RIGHT]; + + return pred; +} + +enum walk_return { + WALK_PRED_ABORT, + WALK_PRED_PARENT, + WALK_PRED_DEFAULT, +}; + +typedef int (*filter_pred_walkcb_t) (enum move_type move, + struct filter_pred *pred, + int *err, void *data); + +static int walk_pred_tree(struct filter_pred *preds, + struct filter_pred *root, + filter_pred_walkcb_t cb, void *data) +{ + struct filter_pred *pred = root; + enum move_type move = MOVE_DOWN; + int done = 0; + + if (!preds) + return -EINVAL; + + do { + int err = 0, ret; + + ret = cb(move, pred, &err, data); + if (ret == WALK_PRED_ABORT) + return err; + if (ret == WALK_PRED_PARENT) + goto get_parent; + + switch (move) { + case MOVE_DOWN: + if (pred->left != FILTER_PRED_INVALID) { + pred = &preds[pred->left]; + continue; + } + goto get_parent; + case MOVE_UP_FROM_LEFT: + pred = &preds[pred->right]; + move = MOVE_DOWN; + continue; + case MOVE_UP_FROM_RIGHT: + get_parent: + if (pred == root) + break; + pred = get_pred_parent(pred, preds, + pred->parent, + &move); + continue; + } + done = 1; + } while (!done); + + /* We are fine. */ + return 0; +} + +/* + * A series of AND or ORs where found together. Instead of + * climbing up and down the tree branches, an array of the + * ops were made in order of checks. We can just move across + * the array and short circuit if needed. + */ +static int process_ops(struct filter_pred *preds, + struct filter_pred *op, void *rec) +{ + struct filter_pred *pred; + int match = 0; + int type; + int i; + + /* + * Micro-optimization: We set type to true if op + * is an OR and false otherwise (AND). Then we + * just need to test if the match is equal to + * the type, and if it is, we can short circuit the + * rest of the checks: + * + * if ((match && op->op == OP_OR) || + * (!match && op->op == OP_AND)) + * return match; + */ + type = op->op == OP_OR; + + for (i = 0; i < op->val; i++) { + pred = &preds[op->ops[i]]; + if (!WARN_ON_ONCE(!pred->fn)) + match = pred->fn(pred, rec); + if (!!match == type) + break; + } + /* If not of not match is equal to not of not, then it is a match */ + return !!match == !op->not; +} + +struct filter_match_preds_data { + struct filter_pred *preds; + int match; + void *rec; +}; + +static int filter_match_preds_cb(enum move_type move, struct filter_pred *pred, + int *err, void *data) +{ + struct filter_match_preds_data *d = data; + + *err = 0; + switch (move) { + case MOVE_DOWN: + /* only AND and OR have children */ + if (pred->left != FILTER_PRED_INVALID) { + /* If ops is set, then it was folded. */ + if (!pred->ops) + return WALK_PRED_DEFAULT; + /* We can treat folded ops as a leaf node */ + d->match = process_ops(d->preds, pred, d->rec); + } else { + if (!WARN_ON_ONCE(!pred->fn)) + d->match = pred->fn(pred, d->rec); + } + + return WALK_PRED_PARENT; + case MOVE_UP_FROM_LEFT: + /* + * Check for short circuits. + * + * Optimization: !!match == (pred->op == OP_OR) + * is the same as: + * if ((match && pred->op == OP_OR) || + * (!match && pred->op == OP_AND)) + */ + if (!!d->match == (pred->op == OP_OR)) + return WALK_PRED_PARENT; + break; + case MOVE_UP_FROM_RIGHT: + break; + } + + return WALK_PRED_DEFAULT; +} + +/* return 1 if event matches, 0 otherwise (discard) */ +int filter_match_preds(struct event_filter *filter, void *rec) +{ + struct filter_pred *preds; + struct filter_pred *root; + struct filter_match_preds_data data = { + /* match is currently meaningless */ + .match = -1, + .rec = rec, + }; + int n_preds, ret; + + /* no filter is considered a match */ + if (!filter) + return 1; + + n_preds = filter->n_preds; + if (!n_preds) + return 1; + + /* + * n_preds, root and filter->preds are protect with preemption disabled. + */ + root = rcu_dereference_sched(filter->root); + if (!root) + return 1; + + data.preds = preds = rcu_dereference_sched(filter->preds); + ret = walk_pred_tree(preds, root, filter_match_preds_cb, &data); + WARN_ON(ret); + return data.match; +} +EXPORT_SYMBOL_GPL(filter_match_preds); + +static void parse_error(struct filter_parse_state *ps, int err, int pos) +{ + ps->lasterr = err; + ps->lasterr_pos = pos; +} + +static void remove_filter_string(struct event_filter *filter) +{ + if (!filter) + return; + + kfree(filter->filter_string); + filter->filter_string = NULL; +} + +static int replace_filter_string(struct event_filter *filter, + char *filter_string) +{ + kfree(filter->filter_string); + filter->filter_string = kstrdup(filter_string, GFP_KERNEL); + if (!filter->filter_string) + return -ENOMEM; + + return 0; +} + +static int append_filter_string(struct event_filter *filter, + char *string) +{ + int newlen; + char *new_filter_string; + + BUG_ON(!filter->filter_string); + newlen = strlen(filter->filter_string) + strlen(string) + 1; + new_filter_string = kmalloc(newlen, GFP_KERNEL); + if (!new_filter_string) + return -ENOMEM; + + strcpy(new_filter_string, filter->filter_string); + strcat(new_filter_string, string); + kfree(filter->filter_string); + filter->filter_string = new_filter_string; + + return 0; +} + +static void append_filter_err(struct filter_parse_state *ps, + struct event_filter *filter) +{ + int pos = ps->lasterr_pos; + char *buf, *pbuf; + + buf = (char *)__get_free_page(GFP_TEMPORARY); + if (!buf) + return; + + append_filter_string(filter, "\n"); + memset(buf, ' ', PAGE_SIZE); + if (pos > PAGE_SIZE - 128) + pos = 0; + buf[pos] = '^'; + pbuf = &buf[pos] + 1; + + sprintf(pbuf, "\nparse_error: %s\n", err_text[ps->lasterr]); + append_filter_string(filter, buf); + free_page((unsigned long) buf); +} + +static inline struct event_filter *event_filter(struct ftrace_event_file *file) +{ + if (file->event_call->flags & TRACE_EVENT_FL_USE_CALL_FILTER) + return file->event_call->filter; + else + return file->filter; +} + +/* caller must hold event_mutex */ +void print_event_filter(struct ftrace_event_file *file, struct trace_seq *s) +{ + struct event_filter *filter = event_filter(file); + + if (filter && filter->filter_string) + trace_seq_printf(s, "%s\n", filter->filter_string); + else + trace_seq_puts(s, "none\n"); +} + +void print_subsystem_event_filter(struct event_subsystem *system, + struct trace_seq *s) +{ + struct event_filter *filter; + + mutex_lock(&event_mutex); + filter = system->filter; + if (filter && filter->filter_string) + trace_seq_printf(s, "%s\n", filter->filter_string); + else + trace_seq_puts(s, DEFAULT_SYS_FILTER_MESSAGE "\n"); + mutex_unlock(&event_mutex); +} + +static int __alloc_pred_stack(struct pred_stack *stack, int n_preds) +{ + stack->preds = kcalloc(n_preds + 1, sizeof(*stack->preds), GFP_KERNEL); + if (!stack->preds) + return -ENOMEM; + stack->index = n_preds; + return 0; +} + +static void __free_pred_stack(struct pred_stack *stack) +{ + kfree(stack->preds); + stack->index = 0; +} + +static int __push_pred_stack(struct pred_stack *stack, + struct filter_pred *pred) +{ + int index = stack->index; + + if (WARN_ON(index == 0)) + return -ENOSPC; + + stack->preds[--index] = pred; + stack->index = index; + return 0; +} + +static struct filter_pred * +__pop_pred_stack(struct pred_stack *stack) +{ + struct filter_pred *pred; + int index = stack->index; + + pred = stack->preds[index++]; + if (!pred) + return NULL; + + stack->index = index; + return pred; +} + +static int filter_set_pred(struct event_filter *filter, + int idx, + struct pred_stack *stack, + struct filter_pred *src) +{ + struct filter_pred *dest = &filter->preds[idx]; + struct filter_pred *left; + struct filter_pred *right; + + *dest = *src; + dest->index = idx; + + if (dest->op == OP_OR || dest->op == OP_AND) { + right = __pop_pred_stack(stack); + left = __pop_pred_stack(stack); + if (!left || !right) + return -EINVAL; + /* + * If both children can be folded + * and they are the same op as this op or a leaf, + * then this op can be folded. + */ + if (left->index & FILTER_PRED_FOLD && + ((left->op == dest->op && !left->not) || + left->left == FILTER_PRED_INVALID) && + right->index & FILTER_PRED_FOLD && + ((right->op == dest->op && !right->not) || + right->left == FILTER_PRED_INVALID)) + dest->index |= FILTER_PRED_FOLD; + + dest->left = left->index & ~FILTER_PRED_FOLD; + dest->right = right->index & ~FILTER_PRED_FOLD; + left->parent = dest->index & ~FILTER_PRED_FOLD; + right->parent = dest->index | FILTER_PRED_IS_RIGHT; + } else { + /* + * Make dest->left invalid to be used as a quick + * way to know this is a leaf node. + */ + dest->left = FILTER_PRED_INVALID; + + /* All leafs allow folding the parent ops. */ + dest->index |= FILTER_PRED_FOLD; + } + + return __push_pred_stack(stack, dest); +} + +static void __free_preds(struct event_filter *filter) +{ + int i; + + if (filter->preds) { + for (i = 0; i < filter->n_preds; i++) + kfree(filter->preds[i].ops); + kfree(filter->preds); + filter->preds = NULL; + } + filter->a_preds = 0; + filter->n_preds = 0; +} + +static void filter_disable(struct ftrace_event_file *file) +{ + struct ftrace_event_call *call = file->event_call; + + if (call->flags & TRACE_EVENT_FL_USE_CALL_FILTER) + call->flags &= ~TRACE_EVENT_FL_FILTERED; + else + file->flags &= ~FTRACE_EVENT_FL_FILTERED; +} + +static void __free_filter(struct event_filter *filter) +{ + if (!filter) + return; + + __free_preds(filter); + kfree(filter->filter_string); + kfree(filter); +} + +void free_event_filter(struct event_filter *filter) +{ + __free_filter(filter); +} + +static struct event_filter *__alloc_filter(void) +{ + struct event_filter *filter; + + filter = kzalloc(sizeof(*filter), GFP_KERNEL); + return filter; +} + +static int __alloc_preds(struct event_filter *filter, int n_preds) +{ + struct filter_pred *pred; + int i; + + if (filter->preds) + __free_preds(filter); + + filter->preds = kcalloc(n_preds, sizeof(*filter->preds), GFP_KERNEL); + + if (!filter->preds) + return -ENOMEM; + + filter->a_preds = n_preds; + filter->n_preds = 0; + + for (i = 0; i < n_preds; i++) { + pred = &filter->preds[i]; + pred->fn = filter_pred_none; + } + + return 0; +} + +static inline void __remove_filter(struct ftrace_event_file *file) +{ + struct ftrace_event_call *call = file->event_call; + + filter_disable(file); + if (call->flags & TRACE_EVENT_FL_USE_CALL_FILTER) + remove_filter_string(call->filter); + else + remove_filter_string(file->filter); +} + +static void filter_free_subsystem_preds(struct ftrace_subsystem_dir *dir, + struct trace_array *tr) +{ + struct ftrace_event_file *file; + + list_for_each_entry(file, &tr->events, list) { + if (file->system != dir) + continue; + __remove_filter(file); + } +} + +static inline void __free_subsystem_filter(struct ftrace_event_file *file) +{ + struct ftrace_event_call *call = file->event_call; + + if (call->flags & TRACE_EVENT_FL_USE_CALL_FILTER) { + __free_filter(call->filter); + call->filter = NULL; + } else { + __free_filter(file->filter); + file->filter = NULL; + } +} + +static void filter_free_subsystem_filters(struct ftrace_subsystem_dir *dir, + struct trace_array *tr) +{ + struct ftrace_event_file *file; + + list_for_each_entry(file, &tr->events, list) { + if (file->system != dir) + continue; + __free_subsystem_filter(file); + } +} + +static int filter_add_pred(struct filter_parse_state *ps, + struct event_filter *filter, + struct filter_pred *pred, + struct pred_stack *stack) +{ + int err; + + if (WARN_ON(filter->n_preds == filter->a_preds)) { + parse_error(ps, FILT_ERR_TOO_MANY_PREDS, 0); + return -ENOSPC; + } + + err = filter_set_pred(filter, filter->n_preds, stack, pred); + if (err) + return err; + + filter->n_preds++; + + return 0; +} + +int filter_assign_type(const char *type) +{ + if (strstr(type, "__data_loc") && strstr(type, "char")) + return FILTER_DYN_STRING; + + if (strchr(type, '[') && strstr(type, "char")) + return FILTER_STATIC_STRING; + + return FILTER_OTHER; +} + +static bool is_function_field(struct ftrace_event_field *field) +{ + return field->filter_type == FILTER_TRACE_FN; +} + +static bool is_string_field(struct ftrace_event_field *field) +{ + return field->filter_type == FILTER_DYN_STRING || + field->filter_type == FILTER_STATIC_STRING || + field->filter_type == FILTER_PTR_STRING; +} + +static int is_legal_op(struct ftrace_event_field *field, int op) +{ + if (is_string_field(field) && + (op != OP_EQ && op != OP_NE && op != OP_GLOB)) + return 0; + if (!is_string_field(field) && op == OP_GLOB) + return 0; + + return 1; +} + +static filter_pred_fn_t select_comparison_fn(int op, int field_size, + int field_is_signed) +{ + filter_pred_fn_t fn = NULL; + + switch (field_size) { + case 8: + if (op == OP_EQ || op == OP_NE) + fn = filter_pred_64; + else if (field_is_signed) + fn = filter_pred_s64; + else + fn = filter_pred_u64; + break; + case 4: + if (op == OP_EQ || op == OP_NE) + fn = filter_pred_32; + else if (field_is_signed) + fn = filter_pred_s32; + else + fn = filter_pred_u32; + break; + case 2: + if (op == OP_EQ || op == OP_NE) + fn = filter_pred_16; + else if (field_is_signed) + fn = filter_pred_s16; + else + fn = filter_pred_u16; + break; + case 1: + if (op == OP_EQ || op == OP_NE) + fn = filter_pred_8; + else if (field_is_signed) + fn = filter_pred_s8; + else + fn = filter_pred_u8; + break; + } + + return fn; +} + +static int init_pred(struct filter_parse_state *ps, + struct ftrace_event_field *field, + struct filter_pred *pred) + +{ + filter_pred_fn_t fn = filter_pred_none; + unsigned long long val; + int ret; + + pred->offset = field->offset; + + if (!is_legal_op(field, pred->op)) { + parse_error(ps, FILT_ERR_ILLEGAL_FIELD_OP, 0); + return -EINVAL; + } + + if (is_string_field(field)) { + filter_build_regex(pred); + + if (field->filter_type == FILTER_STATIC_STRING) { + fn = filter_pred_string; + pred->regex.field_len = field->size; + } else if (field->filter_type == FILTER_DYN_STRING) + fn = filter_pred_strloc; + else + fn = filter_pred_pchar; + } else if (is_function_field(field)) { + if (strcmp(field->name, "ip")) { + parse_error(ps, FILT_ERR_IP_FIELD_ONLY, 0); + return -EINVAL; + } + } else { + if (field->is_signed) + ret = kstrtoll(pred->regex.pattern, 0, &val); + else + ret = kstrtoull(pred->regex.pattern, 0, &val); + if (ret) { + parse_error(ps, FILT_ERR_ILLEGAL_INTVAL, 0); + return -EINVAL; + } + pred->val = val; + + fn = select_comparison_fn(pred->op, field->size, + field->is_signed); + if (!fn) { + parse_error(ps, FILT_ERR_INVALID_OP, 0); + return -EINVAL; + } + } + + if (pred->op == OP_NE) + pred->not ^= 1; + + pred->fn = fn; + return 0; +} + +static void parse_init(struct filter_parse_state *ps, + struct filter_op *ops, + char *infix_string) +{ + memset(ps, '\0', sizeof(*ps)); + + ps->infix.string = infix_string; + ps->infix.cnt = strlen(infix_string); + ps->ops = ops; + + INIT_LIST_HEAD(&ps->opstack); + INIT_LIST_HEAD(&ps->postfix); +} + +static char infix_next(struct filter_parse_state *ps) +{ + ps->infix.cnt--; + + return ps->infix.string[ps->infix.tail++]; +} + +static char infix_peek(struct filter_parse_state *ps) +{ + if (ps->infix.tail == strlen(ps->infix.string)) + return 0; + + return ps->infix.string[ps->infix.tail]; +} + +static void infix_advance(struct filter_parse_state *ps) +{ + ps->infix.cnt--; + ps->infix.tail++; +} + +static inline int is_precedence_lower(struct filter_parse_state *ps, + int a, int b) +{ + return ps->ops[a].precedence < ps->ops[b].precedence; +} + +static inline int is_op_char(struct filter_parse_state *ps, char c) +{ + int i; + + for (i = 0; strcmp(ps->ops[i].string, "OP_NONE"); i++) { + if (ps->ops[i].string[0] == c) + return 1; + } + + return 0; +} + +static int infix_get_op(struct filter_parse_state *ps, char firstc) +{ + char nextc = infix_peek(ps); + char opstr[3]; + int i; + + opstr[0] = firstc; + opstr[1] = nextc; + opstr[2] = '\0'; + + for (i = 0; strcmp(ps->ops[i].string, "OP_NONE"); i++) { + if (!strcmp(opstr, ps->ops[i].string)) { + infix_advance(ps); + return ps->ops[i].id; + } + } + + opstr[1] = '\0'; + + for (i = 0; strcmp(ps->ops[i].string, "OP_NONE"); i++) { + if (!strcmp(opstr, ps->ops[i].string)) + return ps->ops[i].id; + } + + return OP_NONE; +} + +static inline void clear_operand_string(struct filter_parse_state *ps) +{ + memset(ps->operand.string, '\0', MAX_FILTER_STR_VAL); + ps->operand.tail = 0; +} + +static inline int append_operand_char(struct filter_parse_state *ps, char c) +{ + if (ps->operand.tail == MAX_FILTER_STR_VAL - 1) + return -EINVAL; + + ps->operand.string[ps->operand.tail++] = c; + + return 0; +} + +static int filter_opstack_push(struct filter_parse_state *ps, int op) +{ + struct opstack_op *opstack_op; + + opstack_op = kmalloc(sizeof(*opstack_op), GFP_KERNEL); + if (!opstack_op) + return -ENOMEM; + + opstack_op->op = op; + list_add(&opstack_op->list, &ps->opstack); + + return 0; +} + +static int filter_opstack_empty(struct filter_parse_state *ps) +{ + return list_empty(&ps->opstack); +} + +static int filter_opstack_top(struct filter_parse_state *ps) +{ + struct opstack_op *opstack_op; + + if (filter_opstack_empty(ps)) + return OP_NONE; + + opstack_op = list_first_entry(&ps->opstack, struct opstack_op, list); + + return opstack_op->op; +} + +static int filter_opstack_pop(struct filter_parse_state *ps) +{ + struct opstack_op *opstack_op; + int op; + + if (filter_opstack_empty(ps)) + return OP_NONE; + + opstack_op = list_first_entry(&ps->opstack, struct opstack_op, list); + op = opstack_op->op; + list_del(&opstack_op->list); + + kfree(opstack_op); + + return op; +} + +static void filter_opstack_clear(struct filter_parse_state *ps) +{ + while (!filter_opstack_empty(ps)) + filter_opstack_pop(ps); +} + +static char *curr_operand(struct filter_parse_state *ps) +{ + return ps->operand.string; +} + +static int postfix_append_operand(struct filter_parse_state *ps, char *operand) +{ + struct postfix_elt *elt; + + elt = kmalloc(sizeof(*elt), GFP_KERNEL); + if (!elt) + return -ENOMEM; + + elt->op = OP_NONE; + elt->operand = kstrdup(operand, GFP_KERNEL); + if (!elt->operand) { + kfree(elt); + return -ENOMEM; + } + + list_add_tail(&elt->list, &ps->postfix); + + return 0; +} + +static int postfix_append_op(struct filter_parse_state *ps, int op) +{ + struct postfix_elt *elt; + + elt = kmalloc(sizeof(*elt), GFP_KERNEL); + if (!elt) + return -ENOMEM; + + elt->op = op; + elt->operand = NULL; + + list_add_tail(&elt->list, &ps->postfix); + + return 0; +} + +static void postfix_clear(struct filter_parse_state *ps) +{ + struct postfix_elt *elt; + + while (!list_empty(&ps->postfix)) { + elt = list_first_entry(&ps->postfix, struct postfix_elt, list); + list_del(&elt->list); + kfree(elt->operand); + kfree(elt); + } +} + +static int filter_parse(struct filter_parse_state *ps) +{ + int in_string = 0; + int op, top_op; + char ch; + + while ((ch = infix_next(ps))) { + if (ch == '"') { + in_string ^= 1; + continue; + } + + if (in_string) + goto parse_operand; + + if (isspace(ch)) + continue; + + if (is_op_char(ps, ch)) { + op = infix_get_op(ps, ch); + if (op == OP_NONE) { + parse_error(ps, FILT_ERR_INVALID_OP, 0); + return -EINVAL; + } + + if (strlen(curr_operand(ps))) { + postfix_append_operand(ps, curr_operand(ps)); + clear_operand_string(ps); + } + + while (!filter_opstack_empty(ps)) { + top_op = filter_opstack_top(ps); + if (!is_precedence_lower(ps, top_op, op)) { + top_op = filter_opstack_pop(ps); + postfix_append_op(ps, top_op); + continue; + } + break; + } + + filter_opstack_push(ps, op); + continue; + } + + if (ch == '(') { + filter_opstack_push(ps, OP_OPEN_PAREN); + continue; + } + + if (ch == ')') { + if (strlen(curr_operand(ps))) { + postfix_append_operand(ps, curr_operand(ps)); + clear_operand_string(ps); + } + + top_op = filter_opstack_pop(ps); + while (top_op != OP_NONE) { + if (top_op == OP_OPEN_PAREN) + break; + postfix_append_op(ps, top_op); + top_op = filter_opstack_pop(ps); + } + if (top_op == OP_NONE) { + parse_error(ps, FILT_ERR_UNBALANCED_PAREN, 0); + return -EINVAL; + } + continue; + } +parse_operand: + if (append_operand_char(ps, ch)) { + parse_error(ps, FILT_ERR_OPERAND_TOO_LONG, 0); + return -EINVAL; + } + } + + if (strlen(curr_operand(ps))) + postfix_append_operand(ps, curr_operand(ps)); + + while (!filter_opstack_empty(ps)) { + top_op = filter_opstack_pop(ps); + if (top_op == OP_NONE) + break; + if (top_op == OP_OPEN_PAREN) { + parse_error(ps, FILT_ERR_UNBALANCED_PAREN, 0); + return -EINVAL; + } + postfix_append_op(ps, top_op); + } + + return 0; +} + +static struct filter_pred *create_pred(struct filter_parse_state *ps, + struct ftrace_event_call *call, + int op, char *operand1, char *operand2) +{ + struct ftrace_event_field *field; + static struct filter_pred pred; + + memset(&pred, 0, sizeof(pred)); + pred.op = op; + + if (op == OP_AND || op == OP_OR) + return &pred; + + if (!operand1 || !operand2) { + parse_error(ps, FILT_ERR_MISSING_FIELD, 0); + return NULL; + } + + field = trace_find_event_field(call, operand1); + if (!field) { + parse_error(ps, FILT_ERR_FIELD_NOT_FOUND, 0); + return NULL; + } + + strcpy(pred.regex.pattern, operand2); + pred.regex.len = strlen(pred.regex.pattern); + pred.field = field; + return init_pred(ps, field, &pred) ? NULL : &pred; +} + +static int check_preds(struct filter_parse_state *ps) +{ + int n_normal_preds = 0, n_logical_preds = 0; + struct postfix_elt *elt; + int cnt = 0; + + list_for_each_entry(elt, &ps->postfix, list) { + if (elt->op == OP_NONE) { + cnt++; + continue; + } + + if (elt->op == OP_AND || elt->op == OP_OR) { + n_logical_preds++; + cnt--; + continue; + } + if (elt->op != OP_NOT) + cnt--; + n_normal_preds++; + WARN_ON_ONCE(cnt < 0); + } + + if (cnt != 1 || !n_normal_preds || n_logical_preds >= n_normal_preds) { + parse_error(ps, FILT_ERR_INVALID_FILTER, 0); + return -EINVAL; + } + + return 0; +} + +static int count_preds(struct filter_parse_state *ps) +{ + struct postfix_elt *elt; + int n_preds = 0; + + list_for_each_entry(elt, &ps->postfix, list) { + if (elt->op == OP_NONE) + continue; + n_preds++; + } + + return n_preds; +} + +struct check_pred_data { + int count; + int max; +}; + +static int check_pred_tree_cb(enum move_type move, struct filter_pred *pred, + int *err, void *data) +{ + struct check_pred_data *d = data; + + if (WARN_ON(d->count++ > d->max)) { + *err = -EINVAL; + return WALK_PRED_ABORT; + } + return WALK_PRED_DEFAULT; +} + +/* + * The tree is walked at filtering of an event. If the tree is not correctly + * built, it may cause an infinite loop. Check here that the tree does + * indeed terminate. + */ +static int check_pred_tree(struct event_filter *filter, + struct filter_pred *root) +{ + struct check_pred_data data = { + /* + * The max that we can hit a node is three times. + * Once going down, once coming up from left, and + * once coming up from right. This is more than enough + * since leafs are only hit a single time. + */ + .max = 3 * filter->n_preds, + .count = 0, + }; + + return walk_pred_tree(filter->preds, root, + check_pred_tree_cb, &data); +} + +static int count_leafs_cb(enum move_type move, struct filter_pred *pred, + int *err, void *data) +{ + int *count = data; + + if ((move == MOVE_DOWN) && + (pred->left == FILTER_PRED_INVALID)) + (*count)++; + + return WALK_PRED_DEFAULT; +} + +static int count_leafs(struct filter_pred *preds, struct filter_pred *root) +{ + int count = 0, ret; + + ret = walk_pred_tree(preds, root, count_leafs_cb, &count); + WARN_ON(ret); + return count; +} + +struct fold_pred_data { + struct filter_pred *root; + int count; + int children; +}; + +static int fold_pred_cb(enum move_type move, struct filter_pred *pred, + int *err, void *data) +{ + struct fold_pred_data *d = data; + struct filter_pred *root = d->root; + + if (move != MOVE_DOWN) + return WALK_PRED_DEFAULT; + if (pred->left != FILTER_PRED_INVALID) + return WALK_PRED_DEFAULT; + + if (WARN_ON(d->count == d->children)) { + *err = -EINVAL; + return WALK_PRED_ABORT; + } + + pred->index &= ~FILTER_PRED_FOLD; + root->ops[d->count++] = pred->index; + return WALK_PRED_DEFAULT; +} + +static int fold_pred(struct filter_pred *preds, struct filter_pred *root) +{ + struct fold_pred_data data = { + .root = root, + .count = 0, + }; + int children; + + /* No need to keep the fold flag */ + root->index &= ~FILTER_PRED_FOLD; + + /* If the root is a leaf then do nothing */ + if (root->left == FILTER_PRED_INVALID) + return 0; + + /* count the children */ + children = count_leafs(preds, &preds[root->left]); + children += count_leafs(preds, &preds[root->right]); + + root->ops = kcalloc(children, sizeof(*root->ops), GFP_KERNEL); + if (!root->ops) + return -ENOMEM; + + root->val = children; + data.children = children; + return walk_pred_tree(preds, root, fold_pred_cb, &data); +} + +static int fold_pred_tree_cb(enum move_type move, struct filter_pred *pred, + int *err, void *data) +{ + struct filter_pred *preds = data; + + if (move != MOVE_DOWN) + return WALK_PRED_DEFAULT; + if (!(pred->index & FILTER_PRED_FOLD)) + return WALK_PRED_DEFAULT; + + *err = fold_pred(preds, pred); + if (*err) + return WALK_PRED_ABORT; + + /* eveyrhing below is folded, continue with parent */ + return WALK_PRED_PARENT; +} + +/* + * To optimize the processing of the ops, if we have several "ors" or + * "ands" together, we can put them in an array and process them all + * together speeding up the filter logic. + */ +static int fold_pred_tree(struct event_filter *filter, + struct filter_pred *root) +{ + return walk_pred_tree(filter->preds, root, fold_pred_tree_cb, + filter->preds); +} + +static int replace_preds(struct ftrace_event_call *call, + struct event_filter *filter, + struct filter_parse_state *ps, + bool dry_run) +{ + char *operand1 = NULL, *operand2 = NULL; + struct filter_pred *pred; + struct filter_pred *root; + struct postfix_elt *elt; + struct pred_stack stack = { }; /* init to NULL */ + int err; + int n_preds = 0; + + n_preds = count_preds(ps); + if (n_preds >= MAX_FILTER_PRED) { + parse_error(ps, FILT_ERR_TOO_MANY_PREDS, 0); + return -ENOSPC; + } + + err = check_preds(ps); + if (err) + return err; + + if (!dry_run) { + err = __alloc_pred_stack(&stack, n_preds); + if (err) + return err; + err = __alloc_preds(filter, n_preds); + if (err) + goto fail; + } + + n_preds = 0; + list_for_each_entry(elt, &ps->postfix, list) { + if (elt->op == OP_NONE) { + if (!operand1) + operand1 = elt->operand; + else if (!operand2) + operand2 = elt->operand; + else { + parse_error(ps, FILT_ERR_TOO_MANY_OPERANDS, 0); + err = -EINVAL; + goto fail; + } + continue; + } + + if (elt->op == OP_NOT) { + if (!n_preds || operand1 || operand2) { + parse_error(ps, FILT_ERR_ILLEGAL_NOT_OP, 0); + err = -EINVAL; + goto fail; + } + if (!dry_run) + filter->preds[n_preds - 1].not ^= 1; + continue; + } + + if (WARN_ON(n_preds++ == MAX_FILTER_PRED)) { + parse_error(ps, FILT_ERR_TOO_MANY_PREDS, 0); + err = -ENOSPC; + goto fail; + } + + pred = create_pred(ps, call, elt->op, operand1, operand2); + if (!pred) { + err = -EINVAL; + goto fail; + } + + if (!dry_run) { + err = filter_add_pred(ps, filter, pred, &stack); + if (err) + goto fail; + } + + operand1 = operand2 = NULL; + } + + if (!dry_run) { + /* We should have one item left on the stack */ + pred = __pop_pred_stack(&stack); + if (!pred) + return -EINVAL; + /* This item is where we start from in matching */ + root = pred; + /* Make sure the stack is empty */ + pred = __pop_pred_stack(&stack); + if (WARN_ON(pred)) { + err = -EINVAL; + filter->root = NULL; + goto fail; + } + err = check_pred_tree(filter, root); + if (err) + goto fail; + + /* Optimize the tree */ + err = fold_pred_tree(filter, root); + if (err) + goto fail; + + /* We don't set root until we know it works */ + barrier(); + filter->root = root; + } + + err = 0; +fail: + __free_pred_stack(&stack); + return err; +} + +static inline void event_set_filtered_flag(struct ftrace_event_file *file) +{ + struct ftrace_event_call *call = file->event_call; + + if (call->flags & TRACE_EVENT_FL_USE_CALL_FILTER) + call->flags |= TRACE_EVENT_FL_FILTERED; + else + file->flags |= FTRACE_EVENT_FL_FILTERED; +} + +static inline void event_set_filter(struct ftrace_event_file *file, + struct event_filter *filter) +{ + struct ftrace_event_call *call = file->event_call; + + if (call->flags & TRACE_EVENT_FL_USE_CALL_FILTER) + rcu_assign_pointer(call->filter, filter); + else + rcu_assign_pointer(file->filter, filter); +} + +static inline void event_clear_filter(struct ftrace_event_file *file) +{ + struct ftrace_event_call *call = file->event_call; + + if (call->flags & TRACE_EVENT_FL_USE_CALL_FILTER) + RCU_INIT_POINTER(call->filter, NULL); + else + RCU_INIT_POINTER(file->filter, NULL); +} + +static inline void +event_set_no_set_filter_flag(struct ftrace_event_file *file) +{ + struct ftrace_event_call *call = file->event_call; + + if (call->flags & TRACE_EVENT_FL_USE_CALL_FILTER) + call->flags |= TRACE_EVENT_FL_NO_SET_FILTER; + else + file->flags |= FTRACE_EVENT_FL_NO_SET_FILTER; +} + +static inline void +event_clear_no_set_filter_flag(struct ftrace_event_file *file) +{ + struct ftrace_event_call *call = file->event_call; + + if (call->flags & TRACE_EVENT_FL_USE_CALL_FILTER) + call->flags &= ~TRACE_EVENT_FL_NO_SET_FILTER; + else + file->flags &= ~FTRACE_EVENT_FL_NO_SET_FILTER; +} + +static inline bool +event_no_set_filter_flag(struct ftrace_event_file *file) +{ + struct ftrace_event_call *call = file->event_call; + + if (file->flags & FTRACE_EVENT_FL_NO_SET_FILTER) + return true; + + if ((call->flags & TRACE_EVENT_FL_USE_CALL_FILTER) && + (call->flags & TRACE_EVENT_FL_NO_SET_FILTER)) + return true; + + return false; +} + +struct filter_list { + struct list_head list; + struct event_filter *filter; +}; + +static int replace_system_preds(struct ftrace_subsystem_dir *dir, + struct trace_array *tr, + struct filter_parse_state *ps, + char *filter_string) +{ + struct ftrace_event_file *file; + struct filter_list *filter_item; + struct filter_list *tmp; + LIST_HEAD(filter_list); + bool fail = true; + int err; + + list_for_each_entry(file, &tr->events, list) { + if (file->system != dir) + continue; + + /* + * Try to see if the filter can be applied + * (filter arg is ignored on dry_run) + */ + err = replace_preds(file->event_call, NULL, ps, true); + if (err) + event_set_no_set_filter_flag(file); + else + event_clear_no_set_filter_flag(file); + } + + list_for_each_entry(file, &tr->events, list) { + struct event_filter *filter; + + if (file->system != dir) + continue; + + if (event_no_set_filter_flag(file)) + continue; + + filter_item = kzalloc(sizeof(*filter_item), GFP_KERNEL); + if (!filter_item) + goto fail_mem; + + list_add_tail(&filter_item->list, &filter_list); + + filter_item->filter = __alloc_filter(); + if (!filter_item->filter) + goto fail_mem; + filter = filter_item->filter; + + /* Can only fail on no memory */ + err = replace_filter_string(filter, filter_string); + if (err) + goto fail_mem; + + err = replace_preds(file->event_call, filter, ps, false); + if (err) { + filter_disable(file); + parse_error(ps, FILT_ERR_BAD_SUBSYS_FILTER, 0); + append_filter_err(ps, filter); + } else + event_set_filtered_flag(file); + /* + * Regardless of if this returned an error, we still + * replace the filter for the call. + */ + filter = event_filter(file); + event_set_filter(file, filter_item->filter); + filter_item->filter = filter; + + fail = false; + } + + if (fail) + goto fail; + + /* + * The calls can still be using the old filters. + * Do a synchronize_sched() to ensure all calls are + * done with them before we free them. + */ + synchronize_sched(); + list_for_each_entry_safe(filter_item, tmp, &filter_list, list) { + __free_filter(filter_item->filter); + list_del(&filter_item->list); + kfree(filter_item); + } + return 0; + fail: + /* No call succeeded */ + list_for_each_entry_safe(filter_item, tmp, &filter_list, list) { + list_del(&filter_item->list); + kfree(filter_item); + } + parse_error(ps, FILT_ERR_BAD_SUBSYS_FILTER, 0); + return -EINVAL; + fail_mem: + /* If any call succeeded, we still need to sync */ + if (!fail) + synchronize_sched(); + list_for_each_entry_safe(filter_item, tmp, &filter_list, list) { + __free_filter(filter_item->filter); + list_del(&filter_item->list); + kfree(filter_item); + } + return -ENOMEM; +} + +static int create_filter_start(char *filter_str, bool set_str, + struct filter_parse_state **psp, + struct event_filter **filterp) +{ + struct event_filter *filter; + struct filter_parse_state *ps = NULL; + int err = 0; + + WARN_ON_ONCE(*psp || *filterp); + + /* allocate everything, and if any fails, free all and fail */ + filter = __alloc_filter(); + if (filter && set_str) + err = replace_filter_string(filter, filter_str); + + ps = kzalloc(sizeof(*ps), GFP_KERNEL); + + if (!filter || !ps || err) { + kfree(ps); + __free_filter(filter); + return -ENOMEM; + } + + /* we're committed to creating a new filter */ + *filterp = filter; + *psp = ps; + + parse_init(ps, filter_ops, filter_str); + err = filter_parse(ps); + if (err && set_str) + append_filter_err(ps, filter); + return err; +} + +static void create_filter_finish(struct filter_parse_state *ps) +{ + if (ps) { + filter_opstack_clear(ps); + postfix_clear(ps); + kfree(ps); + } +} + +/** + * create_filter - create a filter for a ftrace_event_call + * @call: ftrace_event_call to create a filter for + * @filter_str: filter string + * @set_str: remember @filter_str and enable detailed error in filter + * @filterp: out param for created filter (always updated on return) + * + * Creates a filter for @call with @filter_str. If @set_str is %true, + * @filter_str is copied and recorded in the new filter. + * + * On success, returns 0 and *@filterp points to the new filter. On + * failure, returns -errno and *@filterp may point to %NULL or to a new + * filter. In the latter case, the returned filter contains error + * information if @set_str is %true and the caller is responsible for + * freeing it. + */ +static int create_filter(struct ftrace_event_call *call, + char *filter_str, bool set_str, + struct event_filter **filterp) +{ + struct event_filter *filter = NULL; + struct filter_parse_state *ps = NULL; + int err; + + err = create_filter_start(filter_str, set_str, &ps, &filter); + if (!err) { + err = replace_preds(call, filter, ps, false); + if (err && set_str) + append_filter_err(ps, filter); + } + create_filter_finish(ps); + + *filterp = filter; + return err; +} + +int create_event_filter(struct ftrace_event_call *call, + char *filter_str, bool set_str, + struct event_filter **filterp) +{ + return create_filter(call, filter_str, set_str, filterp); +} + +/** + * create_system_filter - create a filter for an event_subsystem + * @system: event_subsystem to create a filter for + * @filter_str: filter string + * @filterp: out param for created filter (always updated on return) + * + * Identical to create_filter() except that it creates a subsystem filter + * and always remembers @filter_str. + */ +static int create_system_filter(struct ftrace_subsystem_dir *dir, + struct trace_array *tr, + char *filter_str, struct event_filter **filterp) +{ + struct event_filter *filter = NULL; + struct filter_parse_state *ps = NULL; + int err; + + err = create_filter_start(filter_str, true, &ps, &filter); + if (!err) { + err = replace_system_preds(dir, tr, ps, filter_str); + if (!err) { + /* System filters just show a default message */ + kfree(filter->filter_string); + filter->filter_string = NULL; + } else { + append_filter_err(ps, filter); + } + } + create_filter_finish(ps); + + *filterp = filter; + return err; +} + +/* caller must hold event_mutex */ +int apply_event_filter(struct ftrace_event_file *file, char *filter_string) +{ + struct ftrace_event_call *call = file->event_call; + struct event_filter *filter; + int err; + + if (!strcmp(strstrip(filter_string), "0")) { + filter_disable(file); + filter = event_filter(file); + + if (!filter) + return 0; + + event_clear_filter(file); + + /* Make sure the filter is not being used */ + synchronize_sched(); + __free_filter(filter); + + return 0; + } + + err = create_filter(call, filter_string, true, &filter); + + /* + * Always swap the call filter with the new filter + * even if there was an error. If there was an error + * in the filter, we disable the filter and show the error + * string + */ + if (filter) { + struct event_filter *tmp; + + tmp = event_filter(file); + if (!err) + event_set_filtered_flag(file); + else + filter_disable(file); + + event_set_filter(file, filter); + + if (tmp) { + /* Make sure the call is done with the filter */ + synchronize_sched(); + __free_filter(tmp); + } + } + + return err; +} + +int apply_subsystem_event_filter(struct ftrace_subsystem_dir *dir, + char *filter_string) +{ + struct event_subsystem *system = dir->subsystem; + struct trace_array *tr = dir->tr; + struct event_filter *filter; + int err = 0; + + mutex_lock(&event_mutex); + + /* Make sure the system still has events */ + if (!dir->nr_events) { + err = -ENODEV; + goto out_unlock; + } + + if (!strcmp(strstrip(filter_string), "0")) { + filter_free_subsystem_preds(dir, tr); + remove_filter_string(system->filter); + filter = system->filter; + system->filter = NULL; + /* Ensure all filters are no longer used */ + synchronize_sched(); + filter_free_subsystem_filters(dir, tr); + __free_filter(filter); + goto out_unlock; + } + + err = create_system_filter(dir, tr, filter_string, &filter); + if (filter) { + /* + * No event actually uses the system filter + * we can free it without synchronize_sched(). + */ + __free_filter(system->filter); + system->filter = filter; + } +out_unlock: + mutex_unlock(&event_mutex); + + return err; +} + +#ifdef CONFIG_PERF_EVENTS + +void ftrace_profile_free_filter(struct perf_event *event) +{ + struct event_filter *filter = event->filter; + + event->filter = NULL; + __free_filter(filter); +} + +struct function_filter_data { + struct ftrace_ops *ops; + int first_filter; + int first_notrace; +}; + +#ifdef CONFIG_FUNCTION_TRACER +static char ** +ftrace_function_filter_re(char *buf, int len, int *count) +{ + char *str, *sep, **re; + + str = kstrndup(buf, len, GFP_KERNEL); + if (!str) + return NULL; + + /* + * The argv_split function takes white space + * as a separator, so convert ',' into spaces. + */ + while ((sep = strchr(str, ','))) + *sep = ' '; + + re = argv_split(GFP_KERNEL, str, count); + kfree(str); + return re; +} + +static int ftrace_function_set_regexp(struct ftrace_ops *ops, int filter, + int reset, char *re, int len) +{ + int ret; + + if (filter) + ret = ftrace_set_filter(ops, re, len, reset); + else + ret = ftrace_set_notrace(ops, re, len, reset); + + return ret; +} + +static int __ftrace_function_set_filter(int filter, char *buf, int len, + struct function_filter_data *data) +{ + int i, re_cnt, ret = -EINVAL; + int *reset; + char **re; + + reset = filter ? &data->first_filter : &data->first_notrace; + + /* + * The 'ip' field could have multiple filters set, separated + * either by space or comma. We first cut the filter and apply + * all pieces separatelly. + */ + re = ftrace_function_filter_re(buf, len, &re_cnt); + if (!re) + return -EINVAL; + + for (i = 0; i < re_cnt; i++) { + ret = ftrace_function_set_regexp(data->ops, filter, *reset, + re[i], strlen(re[i])); + if (ret) + break; + + if (*reset) + *reset = 0; + } + + argv_free(re); + return ret; +} + +static int ftrace_function_check_pred(struct filter_pred *pred, int leaf) +{ + struct ftrace_event_field *field = pred->field; + + if (leaf) { + /* + * Check the leaf predicate for function trace, verify: + * - only '==' and '!=' is used + * - the 'ip' field is used + */ + if ((pred->op != OP_EQ) && (pred->op != OP_NE)) + return -EINVAL; + + if (strcmp(field->name, "ip")) + return -EINVAL; + } else { + /* + * Check the non leaf predicate for function trace, verify: + * - only '||' is used + */ + if (pred->op != OP_OR) + return -EINVAL; + } + + return 0; +} + +static int ftrace_function_set_filter_cb(enum move_type move, + struct filter_pred *pred, + int *err, void *data) +{ + /* Checking the node is valid for function trace. */ + if ((move != MOVE_DOWN) || + (pred->left != FILTER_PRED_INVALID)) { + *err = ftrace_function_check_pred(pred, 0); + } else { + *err = ftrace_function_check_pred(pred, 1); + if (*err) + return WALK_PRED_ABORT; + + *err = __ftrace_function_set_filter(pred->op == OP_EQ, + pred->regex.pattern, + pred->regex.len, + data); + } + + return (*err) ? WALK_PRED_ABORT : WALK_PRED_DEFAULT; +} + +static int ftrace_function_set_filter(struct perf_event *event, + struct event_filter *filter) +{ + struct function_filter_data data = { + .first_filter = 1, + .first_notrace = 1, + .ops = &event->ftrace_ops, + }; + + return walk_pred_tree(filter->preds, filter->root, + ftrace_function_set_filter_cb, &data); +} +#else +static int ftrace_function_set_filter(struct perf_event *event, + struct event_filter *filter) +{ + return -ENODEV; +} +#endif /* CONFIG_FUNCTION_TRACER */ + +int ftrace_profile_set_filter(struct perf_event *event, int event_id, + char *filter_str) +{ + int err; + struct event_filter *filter; + struct ftrace_event_call *call; + + mutex_lock(&event_mutex); + + call = event->tp_event; + + err = -EINVAL; + if (!call) + goto out_unlock; + + err = -EEXIST; + if (event->filter) + goto out_unlock; + + err = create_filter(call, filter_str, false, &filter); + if (err) + goto free_filter; + + if (ftrace_event_is_function(call)) + err = ftrace_function_set_filter(event, filter); + else + event->filter = filter; + +free_filter: + if (err || ftrace_event_is_function(call)) + __free_filter(filter); + +out_unlock: + mutex_unlock(&event_mutex); + + return err; +} + +#endif /* CONFIG_PERF_EVENTS */ + +#ifdef CONFIG_FTRACE_STARTUP_TEST + +#include +#include + +#define CREATE_TRACE_POINTS +#include "trace_events_filter_test.h" + +#define DATA_REC(m, va, vb, vc, vd, ve, vf, vg, vh, nvisit) \ +{ \ + .filter = FILTER, \ + .rec = { .a = va, .b = vb, .c = vc, .d = vd, \ + .e = ve, .f = vf, .g = vg, .h = vh }, \ + .match = m, \ + .not_visited = nvisit, \ +} +#define YES 1 +#define NO 0 + +static struct test_filter_data_t { + char *filter; + struct ftrace_raw_ftrace_test_filter rec; + int match; + char *not_visited; +} test_filter_data[] = { +#define FILTER "a == 1 && b == 1 && c == 1 && d == 1 && " \ + "e == 1 && f == 1 && g == 1 && h == 1" + DATA_REC(YES, 1, 1, 1, 1, 1, 1, 1, 1, ""), + DATA_REC(NO, 0, 1, 1, 1, 1, 1, 1, 1, "bcdefgh"), + DATA_REC(NO, 1, 1, 1, 1, 1, 1, 1, 0, ""), +#undef FILTER +#define FILTER "a == 1 || b == 1 || c == 1 || d == 1 || " \ + "e == 1 || f == 1 || g == 1 || h == 1" + DATA_REC(NO, 0, 0, 0, 0, 0, 0, 0, 0, ""), + DATA_REC(YES, 0, 0, 0, 0, 0, 0, 0, 1, ""), + DATA_REC(YES, 1, 0, 0, 0, 0, 0, 0, 0, "bcdefgh"), +#undef FILTER +#define FILTER "(a == 1 || b == 1) && (c == 1 || d == 1) && " \ + "(e == 1 || f == 1) && (g == 1 || h == 1)" + DATA_REC(NO, 0, 0, 1, 1, 1, 1, 1, 1, "dfh"), + DATA_REC(YES, 0, 1, 0, 1, 0, 1, 0, 1, ""), + DATA_REC(YES, 1, 0, 1, 0, 0, 1, 0, 1, "bd"), + DATA_REC(NO, 1, 0, 1, 0, 0, 1, 0, 0, "bd"), +#undef FILTER +#define FILTER "(a == 1 && b == 1) || (c == 1 && d == 1) || " \ + "(e == 1 && f == 1) || (g == 1 && h == 1)" + DATA_REC(YES, 1, 0, 1, 1, 1, 1, 1, 1, "efgh"), + DATA_REC(YES, 0, 0, 0, 0, 0, 0, 1, 1, ""), + DATA_REC(NO, 0, 0, 0, 0, 0, 0, 0, 1, ""), +#undef FILTER +#define FILTER "(a == 1 && b == 1) && (c == 1 && d == 1) && " \ + "(e == 1 && f == 1) || (g == 1 && h == 1)" + DATA_REC(YES, 1, 1, 1, 1, 1, 1, 0, 0, "gh"), + DATA_REC(NO, 0, 0, 0, 0, 0, 0, 0, 1, ""), + DATA_REC(YES, 1, 1, 1, 1, 1, 0, 1, 1, ""), +#undef FILTER +#define FILTER "((a == 1 || b == 1) || (c == 1 || d == 1) || " \ + "(e == 1 || f == 1)) && (g == 1 || h == 1)" + DATA_REC(YES, 1, 1, 1, 1, 1, 1, 0, 1, "bcdef"), + DATA_REC(NO, 0, 0, 0, 0, 0, 0, 0, 0, ""), + DATA_REC(YES, 1, 1, 1, 1, 1, 0, 1, 1, "h"), +#undef FILTER +#define FILTER "((((((((a == 1) && (b == 1)) || (c == 1)) && (d == 1)) || " \ + "(e == 1)) && (f == 1)) || (g == 1)) && (h == 1))" + DATA_REC(YES, 1, 1, 1, 1, 1, 1, 1, 1, "ceg"), + DATA_REC(NO, 0, 1, 0, 1, 0, 1, 0, 1, ""), + DATA_REC(NO, 1, 0, 1, 0, 1, 0, 1, 0, ""), +#undef FILTER +#define FILTER "((((((((a == 1) || (b == 1)) && (c == 1)) || (d == 1)) && " \ + "(e == 1)) || (f == 1)) && (g == 1)) || (h == 1))" + DATA_REC(YES, 1, 1, 1, 1, 1, 1, 1, 1, "bdfh"), + DATA_REC(YES, 0, 1, 0, 1, 0, 1, 0, 1, ""), + DATA_REC(YES, 1, 0, 1, 0, 1, 0, 1, 0, "bdfh"), +}; + +#undef DATA_REC +#undef FILTER +#undef YES +#undef NO + +#define DATA_CNT (sizeof(test_filter_data)/sizeof(struct test_filter_data_t)) + +static int test_pred_visited; + +static int test_pred_visited_fn(struct filter_pred *pred, void *event) +{ + struct ftrace_event_field *field = pred->field; + + test_pred_visited = 1; + printk(KERN_INFO "\npred visited %s\n", field->name); + return 1; +} + +static int test_walk_pred_cb(enum move_type move, struct filter_pred *pred, + int *err, void *data) +{ + char *fields = data; + + if ((move == MOVE_DOWN) && + (pred->left == FILTER_PRED_INVALID)) { + struct ftrace_event_field *field = pred->field; + + if (!field) { + WARN(1, "all leafs should have field defined"); + return WALK_PRED_DEFAULT; + } + if (!strchr(fields, *field->name)) + return WALK_PRED_DEFAULT; + + WARN_ON(!pred->fn); + pred->fn = test_pred_visited_fn; + } + return WALK_PRED_DEFAULT; +} + +static __init int ftrace_test_event_filter(void) +{ + int i; + + printk(KERN_INFO "Testing ftrace filter: "); + + for (i = 0; i < DATA_CNT; i++) { + struct event_filter *filter = NULL; + struct test_filter_data_t *d = &test_filter_data[i]; + int err; + + err = create_filter(&event_ftrace_test_filter, d->filter, + false, &filter); + if (err) { + printk(KERN_INFO + "Failed to get filter for '%s', err %d\n", + d->filter, err); + __free_filter(filter); + break; + } + + /* + * The preemption disabling is not really needed for self + * tests, but the rcu dereference will complain without it. + */ + preempt_disable(); + if (*d->not_visited) + walk_pred_tree(filter->preds, filter->root, + test_walk_pred_cb, + d->not_visited); + + test_pred_visited = 0; + err = filter_match_preds(filter, &d->rec); + preempt_enable(); + + __free_filter(filter); + + if (test_pred_visited) { + printk(KERN_INFO + "Failed, unwanted pred visited for filter %s\n", + d->filter); + break; + } + + if (err != d->match) { + printk(KERN_INFO + "Failed to match filter '%s', expected %d\n", + d->filter, d->match); + break; + } + } + + if (i == DATA_CNT) + printk(KERN_CONT "OK\n"); + + return 0; +} + +late_initcall(ftrace_test_event_filter); + +#endif /* CONFIG_FTRACE_STARTUP_TEST */ diff --git a/kernel/kernel/trace/trace_events_filter_test.h b/kernel/kernel/trace/trace_events_filter_test.h new file mode 100644 index 000000000..bfd4dba0d --- /dev/null +++ b/kernel/kernel/trace/trace_events_filter_test.h @@ -0,0 +1,50 @@ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM test + +#if !defined(_TRACE_TEST_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_TEST_H + +#include + +TRACE_EVENT(ftrace_test_filter, + + TP_PROTO(int a, int b, int c, int d, int e, int f, int g, int h), + + TP_ARGS(a, b, c, d, e, f, g, h), + + TP_STRUCT__entry( + __field(int, a) + __field(int, b) + __field(int, c) + __field(int, d) + __field(int, e) + __field(int, f) + __field(int, g) + __field(int, h) + ), + + TP_fast_assign( + __entry->a = a; + __entry->b = b; + __entry->c = c; + __entry->d = d; + __entry->e = e; + __entry->f = f; + __entry->g = g; + __entry->h = h; + ), + + TP_printk("a %d, b %d, c %d, d %d, e %d, f %d, g %d, h %d", + __entry->a, __entry->b, __entry->c, __entry->d, + __entry->e, __entry->f, __entry->g, __entry->h) +); + +#endif /* _TRACE_TEST_H || TRACE_HEADER_MULTI_READ */ + +#undef TRACE_INCLUDE_PATH +#undef TRACE_INCLUDE_FILE +#define TRACE_INCLUDE_PATH . +#define TRACE_INCLUDE_FILE trace_events_filter_test + +/* This part must be outside protection */ +#include diff --git a/kernel/kernel/trace/trace_events_trigger.c b/kernel/kernel/trace/trace_events_trigger.c new file mode 100644 index 000000000..8712df9de --- /dev/null +++ b/kernel/kernel/trace/trace_events_trigger.c @@ -0,0 +1,1437 @@ +/* + * trace_events_trigger - trace event triggers + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * + * Copyright (C) 2013 Tom Zanussi + */ + +#include +#include +#include +#include + +#include "trace.h" + +static LIST_HEAD(trigger_commands); +static DEFINE_MUTEX(trigger_cmd_mutex); + +static void +trigger_data_free(struct event_trigger_data *data) +{ + if (data->cmd_ops->set_filter) + data->cmd_ops->set_filter(NULL, data, NULL); + + synchronize_sched(); /* make sure current triggers exit before free */ + kfree(data); +} + +/** + * event_triggers_call - Call triggers associated with a trace event + * @file: The ftrace_event_file associated with the event + * @rec: The trace entry for the event, NULL for unconditional invocation + * + * For each trigger associated with an event, invoke the trigger + * function registered with the associated trigger command. If rec is + * non-NULL, it means that the trigger requires further processing and + * shouldn't be unconditionally invoked. If rec is non-NULL and the + * trigger has a filter associated with it, rec will checked against + * the filter and if the record matches the trigger will be invoked. + * If the trigger is a 'post_trigger', meaning it shouldn't be invoked + * in any case until the current event is written, the trigger + * function isn't invoked but the bit associated with the deferred + * trigger is set in the return value. + * + * Returns an enum event_trigger_type value containing a set bit for + * any trigger that should be deferred, ETT_NONE if nothing to defer. + * + * Called from tracepoint handlers (with rcu_read_lock_sched() held). + * + * Return: an enum event_trigger_type value containing a set bit for + * any trigger that should be deferred, ETT_NONE if nothing to defer. + */ +enum event_trigger_type +event_triggers_call(struct ftrace_event_file *file, void *rec) +{ + struct event_trigger_data *data; + enum event_trigger_type tt = ETT_NONE; + struct event_filter *filter; + + if (list_empty(&file->triggers)) + return tt; + + list_for_each_entry_rcu(data, &file->triggers, list) { + if (!rec) { + data->ops->func(data); + continue; + } + filter = rcu_dereference_sched(data->filter); + if (filter && !filter_match_preds(filter, rec)) + continue; + if (data->cmd_ops->post_trigger) { + tt |= data->cmd_ops->trigger_type; + continue; + } + data->ops->func(data); + } + return tt; +} +EXPORT_SYMBOL_GPL(event_triggers_call); + +/** + * event_triggers_post_call - Call 'post_triggers' for a trace event + * @file: The ftrace_event_file associated with the event + * @tt: enum event_trigger_type containing a set bit for each trigger to invoke + * + * For each trigger associated with an event, invoke the trigger + * function registered with the associated trigger command, if the + * corresponding bit is set in the tt enum passed into this function. + * See @event_triggers_call for details on how those bits are set. + * + * Called from tracepoint handlers (with rcu_read_lock_sched() held). + */ +void +event_triggers_post_call(struct ftrace_event_file *file, + enum event_trigger_type tt) +{ + struct event_trigger_data *data; + + list_for_each_entry_rcu(data, &file->triggers, list) { + if (data->cmd_ops->trigger_type & tt) + data->ops->func(data); + } +} +EXPORT_SYMBOL_GPL(event_triggers_post_call); + +#define SHOW_AVAILABLE_TRIGGERS (void *)(1UL) + +static void *trigger_next(struct seq_file *m, void *t, loff_t *pos) +{ + struct ftrace_event_file *event_file = event_file_data(m->private); + + if (t == SHOW_AVAILABLE_TRIGGERS) + return NULL; + + return seq_list_next(t, &event_file->triggers, pos); +} + +static void *trigger_start(struct seq_file *m, loff_t *pos) +{ + struct ftrace_event_file *event_file; + + /* ->stop() is called even if ->start() fails */ + mutex_lock(&event_mutex); + event_file = event_file_data(m->private); + if (unlikely(!event_file)) + return ERR_PTR(-ENODEV); + + if (list_empty(&event_file->triggers)) + return *pos == 0 ? SHOW_AVAILABLE_TRIGGERS : NULL; + + return seq_list_start(&event_file->triggers, *pos); +} + +static void trigger_stop(struct seq_file *m, void *t) +{ + mutex_unlock(&event_mutex); +} + +static int trigger_show(struct seq_file *m, void *v) +{ + struct event_trigger_data *data; + struct event_command *p; + + if (v == SHOW_AVAILABLE_TRIGGERS) { + seq_puts(m, "# Available triggers:\n"); + seq_putc(m, '#'); + mutex_lock(&trigger_cmd_mutex); + list_for_each_entry_reverse(p, &trigger_commands, list) + seq_printf(m, " %s", p->name); + seq_putc(m, '\n'); + mutex_unlock(&trigger_cmd_mutex); + return 0; + } + + data = list_entry(v, struct event_trigger_data, list); + data->ops->print(m, data->ops, data); + + return 0; +} + +static const struct seq_operations event_triggers_seq_ops = { + .start = trigger_start, + .next = trigger_next, + .stop = trigger_stop, + .show = trigger_show, +}; + +static int event_trigger_regex_open(struct inode *inode, struct file *file) +{ + int ret = 0; + + mutex_lock(&event_mutex); + + if (unlikely(!event_file_data(file))) { + mutex_unlock(&event_mutex); + return -ENODEV; + } + + if (file->f_mode & FMODE_READ) { + ret = seq_open(file, &event_triggers_seq_ops); + if (!ret) { + struct seq_file *m = file->private_data; + m->private = file; + } + } + + mutex_unlock(&event_mutex); + + return ret; +} + +static int trigger_process_regex(struct ftrace_event_file *file, char *buff) +{ + char *command, *next = buff; + struct event_command *p; + int ret = -EINVAL; + + command = strsep(&next, ": \t"); + command = (command[0] != '!') ? command : command + 1; + + mutex_lock(&trigger_cmd_mutex); + list_for_each_entry(p, &trigger_commands, list) { + if (strcmp(p->name, command) == 0) { + ret = p->func(p, file, buff, command, next); + goto out_unlock; + } + } + out_unlock: + mutex_unlock(&trigger_cmd_mutex); + + return ret; +} + +static ssize_t event_trigger_regex_write(struct file *file, + const char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + struct ftrace_event_file *event_file; + ssize_t ret; + char *buf; + + if (!cnt) + return 0; + + if (cnt >= PAGE_SIZE) + return -EINVAL; + + buf = (char *)__get_free_page(GFP_TEMPORARY); + if (!buf) + return -ENOMEM; + + if (copy_from_user(buf, ubuf, cnt)) { + free_page((unsigned long)buf); + return -EFAULT; + } + buf[cnt] = '\0'; + strim(buf); + + mutex_lock(&event_mutex); + event_file = event_file_data(file); + if (unlikely(!event_file)) { + mutex_unlock(&event_mutex); + free_page((unsigned long)buf); + return -ENODEV; + } + ret = trigger_process_regex(event_file, buf); + mutex_unlock(&event_mutex); + + free_page((unsigned long)buf); + if (ret < 0) + goto out; + + *ppos += cnt; + ret = cnt; + out: + return ret; +} + +static int event_trigger_regex_release(struct inode *inode, struct file *file) +{ + mutex_lock(&event_mutex); + + if (file->f_mode & FMODE_READ) + seq_release(inode, file); + + mutex_unlock(&event_mutex); + + return 0; +} + +static ssize_t +event_trigger_write(struct file *filp, const char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + return event_trigger_regex_write(filp, ubuf, cnt, ppos); +} + +static int +event_trigger_open(struct inode *inode, struct file *filp) +{ + return event_trigger_regex_open(inode, filp); +} + +static int +event_trigger_release(struct inode *inode, struct file *file) +{ + return event_trigger_regex_release(inode, file); +} + +const struct file_operations event_trigger_fops = { + .open = event_trigger_open, + .read = seq_read, + .write = event_trigger_write, + .llseek = tracing_lseek, + .release = event_trigger_release, +}; + +/* + * Currently we only register event commands from __init, so mark this + * __init too. + */ +static __init int register_event_command(struct event_command *cmd) +{ + struct event_command *p; + int ret = 0; + + mutex_lock(&trigger_cmd_mutex); + list_for_each_entry(p, &trigger_commands, list) { + if (strcmp(cmd->name, p->name) == 0) { + ret = -EBUSY; + goto out_unlock; + } + } + list_add(&cmd->list, &trigger_commands); + out_unlock: + mutex_unlock(&trigger_cmd_mutex); + + return ret; +} + +/* + * Currently we only unregister event commands from __init, so mark + * this __init too. + */ +static __init int unregister_event_command(struct event_command *cmd) +{ + struct event_command *p, *n; + int ret = -ENODEV; + + mutex_lock(&trigger_cmd_mutex); + list_for_each_entry_safe(p, n, &trigger_commands, list) { + if (strcmp(cmd->name, p->name) == 0) { + ret = 0; + list_del_init(&p->list); + goto out_unlock; + } + } + out_unlock: + mutex_unlock(&trigger_cmd_mutex); + + return ret; +} + +/** + * event_trigger_print - Generic event_trigger_ops @print implementation + * @name: The name of the event trigger + * @m: The seq_file being printed to + * @data: Trigger-specific data + * @filter_str: filter_str to print, if present + * + * Common implementation for event triggers to print themselves. + * + * Usually wrapped by a function that simply sets the @name of the + * trigger command and then invokes this. + * + * Return: 0 on success, errno otherwise + */ +static int +event_trigger_print(const char *name, struct seq_file *m, + void *data, char *filter_str) +{ + long count = (long)data; + + seq_puts(m, name); + + if (count == -1) + seq_puts(m, ":unlimited"); + else + seq_printf(m, ":count=%ld", count); + + if (filter_str) + seq_printf(m, " if %s\n", filter_str); + else + seq_putc(m, '\n'); + + return 0; +} + +/** + * event_trigger_init - Generic event_trigger_ops @init implementation + * @ops: The trigger ops associated with the trigger + * @data: Trigger-specific data + * + * Common implementation of event trigger initialization. + * + * Usually used directly as the @init method in event trigger + * implementations. + * + * Return: 0 on success, errno otherwise + */ +static int +event_trigger_init(struct event_trigger_ops *ops, + struct event_trigger_data *data) +{ + data->ref++; + return 0; +} + +/** + * event_trigger_free - Generic event_trigger_ops @free implementation + * @ops: The trigger ops associated with the trigger + * @data: Trigger-specific data + * + * Common implementation of event trigger de-initialization. + * + * Usually used directly as the @free method in event trigger + * implementations. + */ +static void +event_trigger_free(struct event_trigger_ops *ops, + struct event_trigger_data *data) +{ + if (WARN_ON_ONCE(data->ref <= 0)) + return; + + data->ref--; + if (!data->ref) + trigger_data_free(data); +} + +static int trace_event_trigger_enable_disable(struct ftrace_event_file *file, + int trigger_enable) +{ + int ret = 0; + + if (trigger_enable) { + if (atomic_inc_return(&file->tm_ref) > 1) + return ret; + set_bit(FTRACE_EVENT_FL_TRIGGER_MODE_BIT, &file->flags); + ret = trace_event_enable_disable(file, 1, 1); + } else { + if (atomic_dec_return(&file->tm_ref) > 0) + return ret; + clear_bit(FTRACE_EVENT_FL_TRIGGER_MODE_BIT, &file->flags); + ret = trace_event_enable_disable(file, 0, 1); + } + + return ret; +} + +/** + * clear_event_triggers - Clear all triggers associated with a trace array + * @tr: The trace array to clear + * + * For each trigger, the triggering event has its tm_ref decremented + * via trace_event_trigger_enable_disable(), and any associated event + * (in the case of enable/disable_event triggers) will have its sm_ref + * decremented via free()->trace_event_enable_disable(). That + * combination effectively reverses the soft-mode/trigger state added + * by trigger registration. + * + * Must be called with event_mutex held. + */ +void +clear_event_triggers(struct trace_array *tr) +{ + struct ftrace_event_file *file; + + list_for_each_entry(file, &tr->events, list) { + struct event_trigger_data *data; + list_for_each_entry_rcu(data, &file->triggers, list) { + trace_event_trigger_enable_disable(file, 0); + if (data->ops->free) + data->ops->free(data->ops, data); + } + } +} + +/** + * update_cond_flag - Set or reset the TRIGGER_COND bit + * @file: The ftrace_event_file associated with the event + * + * If an event has triggers and any of those triggers has a filter or + * a post_trigger, trigger invocation needs to be deferred until after + * the current event has logged its data, and the event should have + * its TRIGGER_COND bit set, otherwise the TRIGGER_COND bit should be + * cleared. + */ +static void update_cond_flag(struct ftrace_event_file *file) +{ + struct event_trigger_data *data; + bool set_cond = false; + + list_for_each_entry_rcu(data, &file->triggers, list) { + if (data->filter || data->cmd_ops->post_trigger) { + set_cond = true; + break; + } + } + + if (set_cond) + set_bit(FTRACE_EVENT_FL_TRIGGER_COND_BIT, &file->flags); + else + clear_bit(FTRACE_EVENT_FL_TRIGGER_COND_BIT, &file->flags); +} + +/** + * register_trigger - Generic event_command @reg implementation + * @glob: The raw string used to register the trigger + * @ops: The trigger ops associated with the trigger + * @data: Trigger-specific data to associate with the trigger + * @file: The ftrace_event_file associated with the event + * + * Common implementation for event trigger registration. + * + * Usually used directly as the @reg method in event command + * implementations. + * + * Return: 0 on success, errno otherwise + */ +static int register_trigger(char *glob, struct event_trigger_ops *ops, + struct event_trigger_data *data, + struct ftrace_event_file *file) +{ + struct event_trigger_data *test; + int ret = 0; + + list_for_each_entry_rcu(test, &file->triggers, list) { + if (test->cmd_ops->trigger_type == data->cmd_ops->trigger_type) { + ret = -EEXIST; + goto out; + } + } + + if (data->ops->init) { + ret = data->ops->init(data->ops, data); + if (ret < 0) + goto out; + } + + list_add_rcu(&data->list, &file->triggers); + ret++; + + if (trace_event_trigger_enable_disable(file, 1) < 0) { + list_del_rcu(&data->list); + ret--; + } + update_cond_flag(file); +out: + return ret; +} + +/** + * unregister_trigger - Generic event_command @unreg implementation + * @glob: The raw string used to register the trigger + * @ops: The trigger ops associated with the trigger + * @test: Trigger-specific data used to find the trigger to remove + * @file: The ftrace_event_file associated with the event + * + * Common implementation for event trigger unregistration. + * + * Usually used directly as the @unreg method in event command + * implementations. + */ +static void unregister_trigger(char *glob, struct event_trigger_ops *ops, + struct event_trigger_data *test, + struct ftrace_event_file *file) +{ + struct event_trigger_data *data; + bool unregistered = false; + + list_for_each_entry_rcu(data, &file->triggers, list) { + if (data->cmd_ops->trigger_type == test->cmd_ops->trigger_type) { + unregistered = true; + list_del_rcu(&data->list); + update_cond_flag(file); + trace_event_trigger_enable_disable(file, 0); + break; + } + } + + if (unregistered && data->ops->free) + data->ops->free(data->ops, data); +} + +/** + * event_trigger_callback - Generic event_command @func implementation + * @cmd_ops: The command ops, used for trigger registration + * @file: The ftrace_event_file associated with the event + * @glob: The raw string used to register the trigger + * @cmd: The cmd portion of the string used to register the trigger + * @param: The params portion of the string used to register the trigger + * + * Common implementation for event command parsing and trigger + * instantiation. + * + * Usually used directly as the @func method in event command + * implementations. + * + * Return: 0 on success, errno otherwise + */ +static int +event_trigger_callback(struct event_command *cmd_ops, + struct ftrace_event_file *file, + char *glob, char *cmd, char *param) +{ + struct event_trigger_data *trigger_data; + struct event_trigger_ops *trigger_ops; + char *trigger = NULL; + char *number; + int ret; + + /* separate the trigger from the filter (t:n [if filter]) */ + if (param && isdigit(param[0])) + trigger = strsep(¶m, " \t"); + + trigger_ops = cmd_ops->get_trigger_ops(cmd, trigger); + + ret = -ENOMEM; + trigger_data = kzalloc(sizeof(*trigger_data), GFP_KERNEL); + if (!trigger_data) + goto out; + + trigger_data->count = -1; + trigger_data->ops = trigger_ops; + trigger_data->cmd_ops = cmd_ops; + INIT_LIST_HEAD(&trigger_data->list); + + if (glob[0] == '!') { + cmd_ops->unreg(glob+1, trigger_ops, trigger_data, file); + kfree(trigger_data); + ret = 0; + goto out; + } + + if (trigger) { + number = strsep(&trigger, ":"); + + ret = -EINVAL; + if (!strlen(number)) + goto out_free; + + /* + * We use the callback data field (which is a pointer) + * as our counter. + */ + ret = kstrtoul(number, 0, &trigger_data->count); + if (ret) + goto out_free; + } + + if (!param) /* if param is non-empty, it's supposed to be a filter */ + goto out_reg; + + if (!cmd_ops->set_filter) + goto out_reg; + + ret = cmd_ops->set_filter(param, trigger_data, file); + if (ret < 0) + goto out_free; + + out_reg: + ret = cmd_ops->reg(glob, trigger_ops, trigger_data, file); + /* + * The above returns on success the # of functions enabled, + * but if it didn't find any functions it returns zero. + * Consider no functions a failure too. + */ + if (!ret) { + ret = -ENOENT; + goto out_free; + } else if (ret < 0) + goto out_free; + ret = 0; + out: + return ret; + + out_free: + if (cmd_ops->set_filter) + cmd_ops->set_filter(NULL, trigger_data, NULL); + kfree(trigger_data); + goto out; +} + +/** + * set_trigger_filter - Generic event_command @set_filter implementation + * @filter_str: The filter string for the trigger, NULL to remove filter + * @trigger_data: Trigger-specific data + * @file: The ftrace_event_file associated with the event + * + * Common implementation for event command filter parsing and filter + * instantiation. + * + * Usually used directly as the @set_filter method in event command + * implementations. + * + * Also used to remove a filter (if filter_str = NULL). + * + * Return: 0 on success, errno otherwise + */ +static int set_trigger_filter(char *filter_str, + struct event_trigger_data *trigger_data, + struct ftrace_event_file *file) +{ + struct event_trigger_data *data = trigger_data; + struct event_filter *filter = NULL, *tmp; + int ret = -EINVAL; + char *s; + + if (!filter_str) /* clear the current filter */ + goto assign; + + s = strsep(&filter_str, " \t"); + + if (!strlen(s) || strcmp(s, "if") != 0) + goto out; + + if (!filter_str) + goto out; + + /* The filter is for the 'trigger' event, not the triggered event */ + ret = create_event_filter(file->event_call, filter_str, false, &filter); + if (ret) + goto out; + assign: + tmp = rcu_access_pointer(data->filter); + + rcu_assign_pointer(data->filter, filter); + + if (tmp) { + /* Make sure the call is done with the filter */ + synchronize_sched(); + free_event_filter(tmp); + } + + kfree(data->filter_str); + data->filter_str = NULL; + + if (filter_str) { + data->filter_str = kstrdup(filter_str, GFP_KERNEL); + if (!data->filter_str) { + free_event_filter(rcu_access_pointer(data->filter)); + data->filter = NULL; + ret = -ENOMEM; + } + } + out: + return ret; +} + +static void +traceon_trigger(struct event_trigger_data *data) +{ + if (tracing_is_on()) + return; + + tracing_on(); +} + +static void +traceon_count_trigger(struct event_trigger_data *data) +{ + if (tracing_is_on()) + return; + + if (!data->count) + return; + + if (data->count != -1) + (data->count)--; + + tracing_on(); +} + +static void +traceoff_trigger(struct event_trigger_data *data) +{ + if (!tracing_is_on()) + return; + + tracing_off(); +} + +static void +traceoff_count_trigger(struct event_trigger_data *data) +{ + if (!tracing_is_on()) + return; + + if (!data->count) + return; + + if (data->count != -1) + (data->count)--; + + tracing_off(); +} + +static int +traceon_trigger_print(struct seq_file *m, struct event_trigger_ops *ops, + struct event_trigger_data *data) +{ + return event_trigger_print("traceon", m, (void *)data->count, + data->filter_str); +} + +static int +traceoff_trigger_print(struct seq_file *m, struct event_trigger_ops *ops, + struct event_trigger_data *data) +{ + return event_trigger_print("traceoff", m, (void *)data->count, + data->filter_str); +} + +static struct event_trigger_ops traceon_trigger_ops = { + .func = traceon_trigger, + .print = traceon_trigger_print, + .init = event_trigger_init, + .free = event_trigger_free, +}; + +static struct event_trigger_ops traceon_count_trigger_ops = { + .func = traceon_count_trigger, + .print = traceon_trigger_print, + .init = event_trigger_init, + .free = event_trigger_free, +}; + +static struct event_trigger_ops traceoff_trigger_ops = { + .func = traceoff_trigger, + .print = traceoff_trigger_print, + .init = event_trigger_init, + .free = event_trigger_free, +}; + +static struct event_trigger_ops traceoff_count_trigger_ops = { + .func = traceoff_count_trigger, + .print = traceoff_trigger_print, + .init = event_trigger_init, + .free = event_trigger_free, +}; + +static struct event_trigger_ops * +onoff_get_trigger_ops(char *cmd, char *param) +{ + struct event_trigger_ops *ops; + + /* we register both traceon and traceoff to this callback */ + if (strcmp(cmd, "traceon") == 0) + ops = param ? &traceon_count_trigger_ops : + &traceon_trigger_ops; + else + ops = param ? &traceoff_count_trigger_ops : + &traceoff_trigger_ops; + + return ops; +} + +static struct event_command trigger_traceon_cmd = { + .name = "traceon", + .trigger_type = ETT_TRACE_ONOFF, + .func = event_trigger_callback, + .reg = register_trigger, + .unreg = unregister_trigger, + .get_trigger_ops = onoff_get_trigger_ops, + .set_filter = set_trigger_filter, +}; + +static struct event_command trigger_traceoff_cmd = { + .name = "traceoff", + .trigger_type = ETT_TRACE_ONOFF, + .func = event_trigger_callback, + .reg = register_trigger, + .unreg = unregister_trigger, + .get_trigger_ops = onoff_get_trigger_ops, + .set_filter = set_trigger_filter, +}; + +#ifdef CONFIG_TRACER_SNAPSHOT +static void +snapshot_trigger(struct event_trigger_data *data) +{ + tracing_snapshot(); +} + +static void +snapshot_count_trigger(struct event_trigger_data *data) +{ + if (!data->count) + return; + + if (data->count != -1) + (data->count)--; + + snapshot_trigger(data); +} + +static int +register_snapshot_trigger(char *glob, struct event_trigger_ops *ops, + struct event_trigger_data *data, + struct ftrace_event_file *file) +{ + int ret = register_trigger(glob, ops, data, file); + + if (ret > 0 && tracing_alloc_snapshot() != 0) { + unregister_trigger(glob, ops, data, file); + ret = 0; + } + + return ret; +} + +static int +snapshot_trigger_print(struct seq_file *m, struct event_trigger_ops *ops, + struct event_trigger_data *data) +{ + return event_trigger_print("snapshot", m, (void *)data->count, + data->filter_str); +} + +static struct event_trigger_ops snapshot_trigger_ops = { + .func = snapshot_trigger, + .print = snapshot_trigger_print, + .init = event_trigger_init, + .free = event_trigger_free, +}; + +static struct event_trigger_ops snapshot_count_trigger_ops = { + .func = snapshot_count_trigger, + .print = snapshot_trigger_print, + .init = event_trigger_init, + .free = event_trigger_free, +}; + +static struct event_trigger_ops * +snapshot_get_trigger_ops(char *cmd, char *param) +{ + return param ? &snapshot_count_trigger_ops : &snapshot_trigger_ops; +} + +static struct event_command trigger_snapshot_cmd = { + .name = "snapshot", + .trigger_type = ETT_SNAPSHOT, + .func = event_trigger_callback, + .reg = register_snapshot_trigger, + .unreg = unregister_trigger, + .get_trigger_ops = snapshot_get_trigger_ops, + .set_filter = set_trigger_filter, +}; + +static __init int register_trigger_snapshot_cmd(void) +{ + int ret; + + ret = register_event_command(&trigger_snapshot_cmd); + WARN_ON(ret < 0); + + return ret; +} +#else +static __init int register_trigger_snapshot_cmd(void) { return 0; } +#endif /* CONFIG_TRACER_SNAPSHOT */ + +#ifdef CONFIG_STACKTRACE +/* + * Skip 3: + * stacktrace_trigger() + * event_triggers_post_call() + * ftrace_raw_event_xxx() + */ +#define STACK_SKIP 3 + +static void +stacktrace_trigger(struct event_trigger_data *data) +{ + trace_dump_stack(STACK_SKIP); +} + +static void +stacktrace_count_trigger(struct event_trigger_data *data) +{ + if (!data->count) + return; + + if (data->count != -1) + (data->count)--; + + stacktrace_trigger(data); +} + +static int +stacktrace_trigger_print(struct seq_file *m, struct event_trigger_ops *ops, + struct event_trigger_data *data) +{ + return event_trigger_print("stacktrace", m, (void *)data->count, + data->filter_str); +} + +static struct event_trigger_ops stacktrace_trigger_ops = { + .func = stacktrace_trigger, + .print = stacktrace_trigger_print, + .init = event_trigger_init, + .free = event_trigger_free, +}; + +static struct event_trigger_ops stacktrace_count_trigger_ops = { + .func = stacktrace_count_trigger, + .print = stacktrace_trigger_print, + .init = event_trigger_init, + .free = event_trigger_free, +}; + +static struct event_trigger_ops * +stacktrace_get_trigger_ops(char *cmd, char *param) +{ + return param ? &stacktrace_count_trigger_ops : &stacktrace_trigger_ops; +} + +static struct event_command trigger_stacktrace_cmd = { + .name = "stacktrace", + .trigger_type = ETT_STACKTRACE, + .post_trigger = true, + .func = event_trigger_callback, + .reg = register_trigger, + .unreg = unregister_trigger, + .get_trigger_ops = stacktrace_get_trigger_ops, + .set_filter = set_trigger_filter, +}; + +static __init int register_trigger_stacktrace_cmd(void) +{ + int ret; + + ret = register_event_command(&trigger_stacktrace_cmd); + WARN_ON(ret < 0); + + return ret; +} +#else +static __init int register_trigger_stacktrace_cmd(void) { return 0; } +#endif /* CONFIG_STACKTRACE */ + +static __init void unregister_trigger_traceon_traceoff_cmds(void) +{ + unregister_event_command(&trigger_traceon_cmd); + unregister_event_command(&trigger_traceoff_cmd); +} + +/* Avoid typos */ +#define ENABLE_EVENT_STR "enable_event" +#define DISABLE_EVENT_STR "disable_event" + +struct enable_trigger_data { + struct ftrace_event_file *file; + bool enable; +}; + +static void +event_enable_trigger(struct event_trigger_data *data) +{ + struct enable_trigger_data *enable_data = data->private_data; + + if (enable_data->enable) + clear_bit(FTRACE_EVENT_FL_SOFT_DISABLED_BIT, &enable_data->file->flags); + else + set_bit(FTRACE_EVENT_FL_SOFT_DISABLED_BIT, &enable_data->file->flags); +} + +static void +event_enable_count_trigger(struct event_trigger_data *data) +{ + struct enable_trigger_data *enable_data = data->private_data; + + if (!data->count) + return; + + /* Skip if the event is in a state we want to switch to */ + if (enable_data->enable == !(enable_data->file->flags & FTRACE_EVENT_FL_SOFT_DISABLED)) + return; + + if (data->count != -1) + (data->count)--; + + event_enable_trigger(data); +} + +static int +event_enable_trigger_print(struct seq_file *m, struct event_trigger_ops *ops, + struct event_trigger_data *data) +{ + struct enable_trigger_data *enable_data = data->private_data; + + seq_printf(m, "%s:%s:%s", + enable_data->enable ? ENABLE_EVENT_STR : DISABLE_EVENT_STR, + enable_data->file->event_call->class->system, + ftrace_event_name(enable_data->file->event_call)); + + if (data->count == -1) + seq_puts(m, ":unlimited"); + else + seq_printf(m, ":count=%ld", data->count); + + if (data->filter_str) + seq_printf(m, " if %s\n", data->filter_str); + else + seq_putc(m, '\n'); + + return 0; +} + +static void +event_enable_trigger_free(struct event_trigger_ops *ops, + struct event_trigger_data *data) +{ + struct enable_trigger_data *enable_data = data->private_data; + + if (WARN_ON_ONCE(data->ref <= 0)) + return; + + data->ref--; + if (!data->ref) { + /* Remove the SOFT_MODE flag */ + trace_event_enable_disable(enable_data->file, 0, 1); + module_put(enable_data->file->event_call->mod); + trigger_data_free(data); + kfree(enable_data); + } +} + +static struct event_trigger_ops event_enable_trigger_ops = { + .func = event_enable_trigger, + .print = event_enable_trigger_print, + .init = event_trigger_init, + .free = event_enable_trigger_free, +}; + +static struct event_trigger_ops event_enable_count_trigger_ops = { + .func = event_enable_count_trigger, + .print = event_enable_trigger_print, + .init = event_trigger_init, + .free = event_enable_trigger_free, +}; + +static struct event_trigger_ops event_disable_trigger_ops = { + .func = event_enable_trigger, + .print = event_enable_trigger_print, + .init = event_trigger_init, + .free = event_enable_trigger_free, +}; + +static struct event_trigger_ops event_disable_count_trigger_ops = { + .func = event_enable_count_trigger, + .print = event_enable_trigger_print, + .init = event_trigger_init, + .free = event_enable_trigger_free, +}; + +static int +event_enable_trigger_func(struct event_command *cmd_ops, + struct ftrace_event_file *file, + char *glob, char *cmd, char *param) +{ + struct ftrace_event_file *event_enable_file; + struct enable_trigger_data *enable_data; + struct event_trigger_data *trigger_data; + struct event_trigger_ops *trigger_ops; + struct trace_array *tr = file->tr; + const char *system; + const char *event; + char *trigger; + char *number; + bool enable; + int ret; + + if (!param) + return -EINVAL; + + /* separate the trigger from the filter (s:e:n [if filter]) */ + trigger = strsep(¶m, " \t"); + if (!trigger) + return -EINVAL; + + system = strsep(&trigger, ":"); + if (!trigger) + return -EINVAL; + + event = strsep(&trigger, ":"); + + ret = -EINVAL; + event_enable_file = find_event_file(tr, system, event); + if (!event_enable_file) + goto out; + + enable = strcmp(cmd, ENABLE_EVENT_STR) == 0; + + trigger_ops = cmd_ops->get_trigger_ops(cmd, trigger); + + ret = -ENOMEM; + trigger_data = kzalloc(sizeof(*trigger_data), GFP_KERNEL); + if (!trigger_data) + goto out; + + enable_data = kzalloc(sizeof(*enable_data), GFP_KERNEL); + if (!enable_data) { + kfree(trigger_data); + goto out; + } + + trigger_data->count = -1; + trigger_data->ops = trigger_ops; + trigger_data->cmd_ops = cmd_ops; + INIT_LIST_HEAD(&trigger_data->list); + RCU_INIT_POINTER(trigger_data->filter, NULL); + + enable_data->enable = enable; + enable_data->file = event_enable_file; + trigger_data->private_data = enable_data; + + if (glob[0] == '!') { + cmd_ops->unreg(glob+1, trigger_ops, trigger_data, file); + kfree(trigger_data); + kfree(enable_data); + ret = 0; + goto out; + } + + if (trigger) { + number = strsep(&trigger, ":"); + + ret = -EINVAL; + if (!strlen(number)) + goto out_free; + + /* + * We use the callback data field (which is a pointer) + * as our counter. + */ + ret = kstrtoul(number, 0, &trigger_data->count); + if (ret) + goto out_free; + } + + if (!param) /* if param is non-empty, it's supposed to be a filter */ + goto out_reg; + + if (!cmd_ops->set_filter) + goto out_reg; + + ret = cmd_ops->set_filter(param, trigger_data, file); + if (ret < 0) + goto out_free; + + out_reg: + /* Don't let event modules unload while probe registered */ + ret = try_module_get(event_enable_file->event_call->mod); + if (!ret) { + ret = -EBUSY; + goto out_free; + } + + ret = trace_event_enable_disable(event_enable_file, 1, 1); + if (ret < 0) + goto out_put; + ret = cmd_ops->reg(glob, trigger_ops, trigger_data, file); + /* + * The above returns on success the # of functions enabled, + * but if it didn't find any functions it returns zero. + * Consider no functions a failure too. + */ + if (!ret) { + ret = -ENOENT; + goto out_disable; + } else if (ret < 0) + goto out_disable; + /* Just return zero, not the number of enabled functions */ + ret = 0; + out: + return ret; + + out_disable: + trace_event_enable_disable(event_enable_file, 0, 1); + out_put: + module_put(event_enable_file->event_call->mod); + out_free: + if (cmd_ops->set_filter) + cmd_ops->set_filter(NULL, trigger_data, NULL); + kfree(trigger_data); + kfree(enable_data); + goto out; +} + +static int event_enable_register_trigger(char *glob, + struct event_trigger_ops *ops, + struct event_trigger_data *data, + struct ftrace_event_file *file) +{ + struct enable_trigger_data *enable_data = data->private_data; + struct enable_trigger_data *test_enable_data; + struct event_trigger_data *test; + int ret = 0; + + list_for_each_entry_rcu(test, &file->triggers, list) { + test_enable_data = test->private_data; + if (test_enable_data && + (test_enable_data->file == enable_data->file)) { + ret = -EEXIST; + goto out; + } + } + + if (data->ops->init) { + ret = data->ops->init(data->ops, data); + if (ret < 0) + goto out; + } + + list_add_rcu(&data->list, &file->triggers); + ret++; + + if (trace_event_trigger_enable_disable(file, 1) < 0) { + list_del_rcu(&data->list); + ret--; + } + update_cond_flag(file); +out: + return ret; +} + +static void event_enable_unregister_trigger(char *glob, + struct event_trigger_ops *ops, + struct event_trigger_data *test, + struct ftrace_event_file *file) +{ + struct enable_trigger_data *test_enable_data = test->private_data; + struct enable_trigger_data *enable_data; + struct event_trigger_data *data; + bool unregistered = false; + + list_for_each_entry_rcu(data, &file->triggers, list) { + enable_data = data->private_data; + if (enable_data && + (enable_data->file == test_enable_data->file)) { + unregistered = true; + list_del_rcu(&data->list); + update_cond_flag(file); + trace_event_trigger_enable_disable(file, 0); + break; + } + } + + if (unregistered && data->ops->free) + data->ops->free(data->ops, data); +} + +static struct event_trigger_ops * +event_enable_get_trigger_ops(char *cmd, char *param) +{ + struct event_trigger_ops *ops; + bool enable; + + enable = strcmp(cmd, ENABLE_EVENT_STR) == 0; + + if (enable) + ops = param ? &event_enable_count_trigger_ops : + &event_enable_trigger_ops; + else + ops = param ? &event_disable_count_trigger_ops : + &event_disable_trigger_ops; + + return ops; +} + +static struct event_command trigger_enable_cmd = { + .name = ENABLE_EVENT_STR, + .trigger_type = ETT_EVENT_ENABLE, + .func = event_enable_trigger_func, + .reg = event_enable_register_trigger, + .unreg = event_enable_unregister_trigger, + .get_trigger_ops = event_enable_get_trigger_ops, + .set_filter = set_trigger_filter, +}; + +static struct event_command trigger_disable_cmd = { + .name = DISABLE_EVENT_STR, + .trigger_type = ETT_EVENT_ENABLE, + .func = event_enable_trigger_func, + .reg = event_enable_register_trigger, + .unreg = event_enable_unregister_trigger, + .get_trigger_ops = event_enable_get_trigger_ops, + .set_filter = set_trigger_filter, +}; + +static __init void unregister_trigger_enable_disable_cmds(void) +{ + unregister_event_command(&trigger_enable_cmd); + unregister_event_command(&trigger_disable_cmd); +} + +static __init int register_trigger_enable_disable_cmds(void) +{ + int ret; + + ret = register_event_command(&trigger_enable_cmd); + if (WARN_ON(ret < 0)) + return ret; + ret = register_event_command(&trigger_disable_cmd); + if (WARN_ON(ret < 0)) + unregister_trigger_enable_disable_cmds(); + + return ret; +} + +static __init int register_trigger_traceon_traceoff_cmds(void) +{ + int ret; + + ret = register_event_command(&trigger_traceon_cmd); + if (WARN_ON(ret < 0)) + return ret; + ret = register_event_command(&trigger_traceoff_cmd); + if (WARN_ON(ret < 0)) + unregister_trigger_traceon_traceoff_cmds(); + + return ret; +} + +__init int register_trigger_cmds(void) +{ + register_trigger_traceon_traceoff_cmds(); + register_trigger_snapshot_cmd(); + register_trigger_stacktrace_cmd(); + register_trigger_enable_disable_cmds(); + + return 0; +} diff --git a/kernel/kernel/trace/trace_export.c b/kernel/kernel/trace/trace_export.c new file mode 100644 index 000000000..174a6a711 --- /dev/null +++ b/kernel/kernel/trace/trace_export.c @@ -0,0 +1,195 @@ +/* + * trace_export.c - export basic ftrace utilities to user space + * + * Copyright (C) 2009 Steven Rostedt + */ +#include +#include +#include +#include +#include +#include +#include + +#include "trace_output.h" + +#undef TRACE_SYSTEM +#define TRACE_SYSTEM ftrace + +/* + * The FTRACE_ENTRY_REG macro allows ftrace entry to define register + * function and thus become accesible via perf. + */ +#undef FTRACE_ENTRY_REG +#define FTRACE_ENTRY_REG(name, struct_name, id, tstruct, print, \ + filter, regfn) \ + FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print), \ + filter) + +/* not needed for this file */ +#undef __field_struct +#define __field_struct(type, item) + +#undef __field +#define __field(type, item) type item; + +#undef __field_desc +#define __field_desc(type, container, item) type item; + +#undef __array +#define __array(type, item, size) type item[size]; + +#undef __array_desc +#define __array_desc(type, container, item, size) type item[size]; + +#undef __dynamic_array +#define __dynamic_array(type, item) type item[]; + +#undef F_STRUCT +#define F_STRUCT(args...) args + +#undef F_printk +#define F_printk(fmt, args...) fmt, args + +#undef FTRACE_ENTRY +#define FTRACE_ENTRY(name, struct_name, id, tstruct, print, filter) \ +struct ____ftrace_##name { \ + tstruct \ +}; \ +static void __always_unused ____ftrace_check_##name(void) \ +{ \ + struct ____ftrace_##name *__entry = NULL; \ + \ + /* force compile-time check on F_printk() */ \ + printk(print); \ +} + +#undef FTRACE_ENTRY_DUP +#define FTRACE_ENTRY_DUP(name, struct_name, id, tstruct, print, filter) \ + FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print), \ + filter) + +#include "trace_entries.h" + +#undef __field +#define __field(type, item) \ + ret = trace_define_field(event_call, #type, #item, \ + offsetof(typeof(field), item), \ + sizeof(field.item), \ + is_signed_type(type), filter_type); \ + if (ret) \ + return ret; + +#undef __field_desc +#define __field_desc(type, container, item) \ + ret = trace_define_field(event_call, #type, #item, \ + offsetof(typeof(field), \ + container.item), \ + sizeof(field.container.item), \ + is_signed_type(type), filter_type); \ + if (ret) \ + return ret; + +#undef __array +#define __array(type, item, len) \ + do { \ + char *type_str = #type"["__stringify(len)"]"; \ + BUILD_BUG_ON(len > MAX_FILTER_STR_VAL); \ + ret = trace_define_field(event_call, type_str, #item, \ + offsetof(typeof(field), item), \ + sizeof(field.item), \ + is_signed_type(type), filter_type); \ + if (ret) \ + return ret; \ + } while (0); + +#undef __array_desc +#define __array_desc(type, container, item, len) \ + BUILD_BUG_ON(len > MAX_FILTER_STR_VAL); \ + ret = trace_define_field(event_call, #type "[" #len "]", #item, \ + offsetof(typeof(field), \ + container.item), \ + sizeof(field.container.item), \ + is_signed_type(type), filter_type); \ + if (ret) \ + return ret; + +#undef __dynamic_array +#define __dynamic_array(type, item) \ + ret = trace_define_field(event_call, #type, #item, \ + offsetof(typeof(field), item), \ + 0, is_signed_type(type), filter_type);\ + if (ret) \ + return ret; + +#undef FTRACE_ENTRY +#define FTRACE_ENTRY(name, struct_name, id, tstruct, print, filter) \ +static int __init \ +ftrace_define_fields_##name(struct ftrace_event_call *event_call) \ +{ \ + struct struct_name field; \ + int ret; \ + int filter_type = filter; \ + \ + tstruct; \ + \ + return ret; \ +} + +#include "trace_entries.h" + +#undef __entry +#define __entry REC + +#undef __field +#define __field(type, item) + +#undef __field_desc +#define __field_desc(type, container, item) + +#undef __array +#define __array(type, item, len) + +#undef __array_desc +#define __array_desc(type, container, item, len) + +#undef __dynamic_array +#define __dynamic_array(type, item) + +#undef F_printk +#define F_printk(fmt, args...) __stringify(fmt) ", " __stringify(args) + +#undef FTRACE_ENTRY_REG +#define FTRACE_ENTRY_REG(call, struct_name, etype, tstruct, print, filter,\ + regfn) \ + \ +struct ftrace_event_class __refdata event_class_ftrace_##call = { \ + .system = __stringify(TRACE_SYSTEM), \ + .define_fields = ftrace_define_fields_##call, \ + .fields = LIST_HEAD_INIT(event_class_ftrace_##call.fields),\ + .reg = regfn, \ +}; \ + \ +struct ftrace_event_call __used event_##call = { \ + .class = &event_class_ftrace_##call, \ + { \ + .name = #call, \ + }, \ + .event.type = etype, \ + .print_fmt = print, \ + .flags = TRACE_EVENT_FL_IGNORE_ENABLE, \ +}; \ +struct ftrace_event_call __used \ +__attribute__((section("_ftrace_events"))) *__event_##call = &event_##call; + +#undef FTRACE_ENTRY +#define FTRACE_ENTRY(call, struct_name, etype, tstruct, print, filter) \ + FTRACE_ENTRY_REG(call, struct_name, etype, \ + PARAMS(tstruct), PARAMS(print), filter, NULL) + +int ftrace_event_is_function(struct ftrace_event_call *call) +{ + return call == &event_function; +} + +#include "trace_entries.h" diff --git a/kernel/kernel/trace/trace_functions.c b/kernel/kernel/trace/trace_functions.c new file mode 100644 index 000000000..fcd41a166 --- /dev/null +++ b/kernel/kernel/trace/trace_functions.c @@ -0,0 +1,689 @@ +/* + * ring buffer based function tracer + * + * Copyright (C) 2007-2008 Steven Rostedt + * Copyright (C) 2008 Ingo Molnar + * + * Based on code from the latency_tracer, that is: + * + * Copyright (C) 2004-2006 Ingo Molnar + * Copyright (C) 2004 Nadia Yvette Chambers + */ +#include +#include +#include +#include +#include +#include + +#include "trace.h" + +static void tracing_start_function_trace(struct trace_array *tr); +static void tracing_stop_function_trace(struct trace_array *tr); +static void +function_trace_call(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct pt_regs *pt_regs); +static void +function_stack_trace_call(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct pt_regs *pt_regs); +static struct tracer_flags func_flags; + +/* Our option */ +enum { + TRACE_FUNC_OPT_STACK = 0x1, +}; + +static int allocate_ftrace_ops(struct trace_array *tr) +{ + struct ftrace_ops *ops; + + ops = kzalloc(sizeof(*ops), GFP_KERNEL); + if (!ops) + return -ENOMEM; + + /* Currently only the non stack verision is supported */ + ops->func = function_trace_call; + ops->flags = FTRACE_OPS_FL_RECURSION_SAFE; + + tr->ops = ops; + ops->private = tr; + return 0; +} + + +int ftrace_create_function_files(struct trace_array *tr, + struct dentry *parent) +{ + int ret; + + /* + * The top level array uses the "global_ops", and the files are + * created on boot up. + */ + if (tr->flags & TRACE_ARRAY_FL_GLOBAL) + return 0; + + ret = allocate_ftrace_ops(tr); + if (ret) + return ret; + + ftrace_create_filter_files(tr->ops, parent); + + return 0; +} + +void ftrace_destroy_function_files(struct trace_array *tr) +{ + ftrace_destroy_filter_files(tr->ops); + kfree(tr->ops); + tr->ops = NULL; +} + +static int function_trace_init(struct trace_array *tr) +{ + ftrace_func_t func; + + /* + * Instance trace_arrays get their ops allocated + * at instance creation. Unless it failed + * the allocation. + */ + if (!tr->ops) + return -ENOMEM; + + /* Currently only the global instance can do stack tracing */ + if (tr->flags & TRACE_ARRAY_FL_GLOBAL && + func_flags.val & TRACE_FUNC_OPT_STACK) + func = function_stack_trace_call; + else + func = function_trace_call; + + ftrace_init_array_ops(tr, func); + + tr->trace_buffer.cpu = get_cpu(); + put_cpu(); + + tracing_start_cmdline_record(); + tracing_start_function_trace(tr); + return 0; +} + +static void function_trace_reset(struct trace_array *tr) +{ + tracing_stop_function_trace(tr); + tracing_stop_cmdline_record(); + ftrace_reset_array_ops(tr); +} + +static void function_trace_start(struct trace_array *tr) +{ + tracing_reset_online_cpus(&tr->trace_buffer); +} + +static void +function_trace_call(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct pt_regs *pt_regs) +{ + struct trace_array *tr = op->private; + struct trace_array_cpu *data; + unsigned long flags; + int bit; + int cpu; + int pc; + + if (unlikely(!tr->function_enabled)) + return; + + pc = preempt_count(); + preempt_disable_notrace(); + + bit = trace_test_and_set_recursion(TRACE_FTRACE_START, TRACE_FTRACE_MAX); + if (bit < 0) + goto out; + + cpu = smp_processor_id(); + data = per_cpu_ptr(tr->trace_buffer.data, cpu); + if (!atomic_read(&data->disabled)) { + local_save_flags(flags); + trace_function(tr, ip, parent_ip, flags, pc); + } + trace_clear_recursion(bit); + + out: + preempt_enable_notrace(); +} + +static void +function_stack_trace_call(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct pt_regs *pt_regs) +{ + struct trace_array *tr = op->private; + struct trace_array_cpu *data; + unsigned long flags; + long disabled; + int cpu; + int pc; + + if (unlikely(!tr->function_enabled)) + return; + + /* + * Need to use raw, since this must be called before the + * recursive protection is performed. + */ + local_irq_save(flags); + cpu = raw_smp_processor_id(); + data = per_cpu_ptr(tr->trace_buffer.data, cpu); + disabled = atomic_inc_return(&data->disabled); + + if (likely(disabled == 1)) { + pc = preempt_count(); + trace_function(tr, ip, parent_ip, flags, pc); + /* + * skip over 5 funcs: + * __ftrace_trace_stack, + * __trace_stack, + * function_stack_trace_call + * ftrace_list_func + * ftrace_call + */ + __trace_stack(tr, flags, 5, pc); + } + + atomic_dec(&data->disabled); + local_irq_restore(flags); +} + +static struct tracer_opt func_opts[] = { +#ifdef CONFIG_STACKTRACE + { TRACER_OPT(func_stack_trace, TRACE_FUNC_OPT_STACK) }, +#endif + { } /* Always set a last empty entry */ +}; + +static struct tracer_flags func_flags = { + .val = 0, /* By default: all flags disabled */ + .opts = func_opts +}; + +static void tracing_start_function_trace(struct trace_array *tr) +{ + tr->function_enabled = 0; + register_ftrace_function(tr->ops); + tr->function_enabled = 1; +} + +static void tracing_stop_function_trace(struct trace_array *tr) +{ + tr->function_enabled = 0; + unregister_ftrace_function(tr->ops); +} + +static int +func_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set) +{ + switch (bit) { + case TRACE_FUNC_OPT_STACK: + /* do nothing if already set */ + if (!!set == !!(func_flags.val & TRACE_FUNC_OPT_STACK)) + break; + + unregister_ftrace_function(tr->ops); + + if (set) { + tr->ops->func = function_stack_trace_call; + register_ftrace_function(tr->ops); + } else { + tr->ops->func = function_trace_call; + register_ftrace_function(tr->ops); + } + + break; + default: + return -EINVAL; + } + + return 0; +} + +static struct tracer function_trace __tracer_data = +{ + .name = "function", + .init = function_trace_init, + .reset = function_trace_reset, + .start = function_trace_start, + .flags = &func_flags, + .set_flag = func_set_flag, + .allow_instances = true, +#ifdef CONFIG_FTRACE_SELFTEST + .selftest = trace_selftest_startup_function, +#endif +}; + +#ifdef CONFIG_DYNAMIC_FTRACE +static void update_traceon_count(void **data, bool on) +{ + long *count = (long *)data; + long old_count = *count; + + /* + * Tracing gets disabled (or enabled) once per count. + * This function can be called at the same time on multiple CPUs. + * It is fine if both disable (or enable) tracing, as disabling + * (or enabling) the second time doesn't do anything as the + * state of the tracer is already disabled (or enabled). + * What needs to be synchronized in this case is that the count + * only gets decremented once, even if the tracer is disabled + * (or enabled) twice, as the second one is really a nop. + * + * The memory barriers guarantee that we only decrement the + * counter once. First the count is read to a local variable + * and a read barrier is used to make sure that it is loaded + * before checking if the tracer is in the state we want. + * If the tracer is not in the state we want, then the count + * is guaranteed to be the old count. + * + * Next the tracer is set to the state we want (disabled or enabled) + * then a write memory barrier is used to make sure that + * the new state is visible before changing the counter by + * one minus the old counter. This guarantees that another CPU + * executing this code will see the new state before seeing + * the new counter value, and would not do anything if the new + * counter is seen. + * + * Note, there is no synchronization between this and a user + * setting the tracing_on file. But we currently don't care + * about that. + */ + if (!old_count) + return; + + /* Make sure we see count before checking tracing state */ + smp_rmb(); + + if (on == !!tracing_is_on()) + return; + + if (on) + tracing_on(); + else + tracing_off(); + + /* unlimited? */ + if (old_count == -1) + return; + + /* Make sure tracing state is visible before updating count */ + smp_wmb(); + + *count = old_count - 1; +} + +static void +ftrace_traceon_count(unsigned long ip, unsigned long parent_ip, void **data) +{ + update_traceon_count(data, 1); +} + +static void +ftrace_traceoff_count(unsigned long ip, unsigned long parent_ip, void **data) +{ + update_traceon_count(data, 0); +} + +static void +ftrace_traceon(unsigned long ip, unsigned long parent_ip, void **data) +{ + if (tracing_is_on()) + return; + + tracing_on(); +} + +static void +ftrace_traceoff(unsigned long ip, unsigned long parent_ip, void **data) +{ + if (!tracing_is_on()) + return; + + tracing_off(); +} + +/* + * Skip 4: + * ftrace_stacktrace() + * function_trace_probe_call() + * ftrace_ops_list_func() + * ftrace_call() + */ +#define STACK_SKIP 4 + +static void +ftrace_stacktrace(unsigned long ip, unsigned long parent_ip, void **data) +{ + trace_dump_stack(STACK_SKIP); +} + +static void +ftrace_stacktrace_count(unsigned long ip, unsigned long parent_ip, void **data) +{ + long *count = (long *)data; + long old_count; + long new_count; + + /* + * Stack traces should only execute the number of times the + * user specified in the counter. + */ + do { + + if (!tracing_is_on()) + return; + + old_count = *count; + + if (!old_count) + return; + + /* unlimited? */ + if (old_count == -1) { + trace_dump_stack(STACK_SKIP); + return; + } + + new_count = old_count - 1; + new_count = cmpxchg(count, old_count, new_count); + if (new_count == old_count) + trace_dump_stack(STACK_SKIP); + + } while (new_count != old_count); +} + +static int update_count(void **data) +{ + unsigned long *count = (long *)data; + + if (!*count) + return 0; + + if (*count != -1) + (*count)--; + + return 1; +} + +static void +ftrace_dump_probe(unsigned long ip, unsigned long parent_ip, void **data) +{ + if (update_count(data)) + ftrace_dump(DUMP_ALL); +} + +/* Only dump the current CPU buffer. */ +static void +ftrace_cpudump_probe(unsigned long ip, unsigned long parent_ip, void **data) +{ + if (update_count(data)) + ftrace_dump(DUMP_ORIG); +} + +static int +ftrace_probe_print(const char *name, struct seq_file *m, + unsigned long ip, void *data) +{ + long count = (long)data; + + seq_printf(m, "%ps:%s", (void *)ip, name); + + if (count == -1) + seq_puts(m, ":unlimited\n"); + else + seq_printf(m, ":count=%ld\n", count); + + return 0; +} + +static int +ftrace_traceon_print(struct seq_file *m, unsigned long ip, + struct ftrace_probe_ops *ops, void *data) +{ + return ftrace_probe_print("traceon", m, ip, data); +} + +static int +ftrace_traceoff_print(struct seq_file *m, unsigned long ip, + struct ftrace_probe_ops *ops, void *data) +{ + return ftrace_probe_print("traceoff", m, ip, data); +} + +static int +ftrace_stacktrace_print(struct seq_file *m, unsigned long ip, + struct ftrace_probe_ops *ops, void *data) +{ + return ftrace_probe_print("stacktrace", m, ip, data); +} + +static int +ftrace_dump_print(struct seq_file *m, unsigned long ip, + struct ftrace_probe_ops *ops, void *data) +{ + return ftrace_probe_print("dump", m, ip, data); +} + +static int +ftrace_cpudump_print(struct seq_file *m, unsigned long ip, + struct ftrace_probe_ops *ops, void *data) +{ + return ftrace_probe_print("cpudump", m, ip, data); +} + +static struct ftrace_probe_ops traceon_count_probe_ops = { + .func = ftrace_traceon_count, + .print = ftrace_traceon_print, +}; + +static struct ftrace_probe_ops traceoff_count_probe_ops = { + .func = ftrace_traceoff_count, + .print = ftrace_traceoff_print, +}; + +static struct ftrace_probe_ops stacktrace_count_probe_ops = { + .func = ftrace_stacktrace_count, + .print = ftrace_stacktrace_print, +}; + +static struct ftrace_probe_ops dump_probe_ops = { + .func = ftrace_dump_probe, + .print = ftrace_dump_print, +}; + +static struct ftrace_probe_ops cpudump_probe_ops = { + .func = ftrace_cpudump_probe, + .print = ftrace_cpudump_print, +}; + +static struct ftrace_probe_ops traceon_probe_ops = { + .func = ftrace_traceon, + .print = ftrace_traceon_print, +}; + +static struct ftrace_probe_ops traceoff_probe_ops = { + .func = ftrace_traceoff, + .print = ftrace_traceoff_print, +}; + +static struct ftrace_probe_ops stacktrace_probe_ops = { + .func = ftrace_stacktrace, + .print = ftrace_stacktrace_print, +}; + +static int +ftrace_trace_probe_callback(struct ftrace_probe_ops *ops, + struct ftrace_hash *hash, char *glob, + char *cmd, char *param, int enable) +{ + void *count = (void *)-1; + char *number; + int ret; + + /* hash funcs only work with set_ftrace_filter */ + if (!enable) + return -EINVAL; + + if (glob[0] == '!') { + unregister_ftrace_function_probe_func(glob+1, ops); + return 0; + } + + if (!param) + goto out_reg; + + number = strsep(¶m, ":"); + + if (!strlen(number)) + goto out_reg; + + /* + * We use the callback data field (which is a pointer) + * as our counter. + */ + ret = kstrtoul(number, 0, (unsigned long *)&count); + if (ret) + return ret; + + out_reg: + ret = register_ftrace_function_probe(glob, ops, count); + + return ret < 0 ? ret : 0; +} + +static int +ftrace_trace_onoff_callback(struct ftrace_hash *hash, + char *glob, char *cmd, char *param, int enable) +{ + struct ftrace_probe_ops *ops; + + /* we register both traceon and traceoff to this callback */ + if (strcmp(cmd, "traceon") == 0) + ops = param ? &traceon_count_probe_ops : &traceon_probe_ops; + else + ops = param ? &traceoff_count_probe_ops : &traceoff_probe_ops; + + return ftrace_trace_probe_callback(ops, hash, glob, cmd, + param, enable); +} + +static int +ftrace_stacktrace_callback(struct ftrace_hash *hash, + char *glob, char *cmd, char *param, int enable) +{ + struct ftrace_probe_ops *ops; + + ops = param ? &stacktrace_count_probe_ops : &stacktrace_probe_ops; + + return ftrace_trace_probe_callback(ops, hash, glob, cmd, + param, enable); +} + +static int +ftrace_dump_callback(struct ftrace_hash *hash, + char *glob, char *cmd, char *param, int enable) +{ + struct ftrace_probe_ops *ops; + + ops = &dump_probe_ops; + + /* Only dump once. */ + return ftrace_trace_probe_callback(ops, hash, glob, cmd, + "1", enable); +} + +static int +ftrace_cpudump_callback(struct ftrace_hash *hash, + char *glob, char *cmd, char *param, int enable) +{ + struct ftrace_probe_ops *ops; + + ops = &cpudump_probe_ops; + + /* Only dump once. */ + return ftrace_trace_probe_callback(ops, hash, glob, cmd, + "1", enable); +} + +static struct ftrace_func_command ftrace_traceon_cmd = { + .name = "traceon", + .func = ftrace_trace_onoff_callback, +}; + +static struct ftrace_func_command ftrace_traceoff_cmd = { + .name = "traceoff", + .func = ftrace_trace_onoff_callback, +}; + +static struct ftrace_func_command ftrace_stacktrace_cmd = { + .name = "stacktrace", + .func = ftrace_stacktrace_callback, +}; + +static struct ftrace_func_command ftrace_dump_cmd = { + .name = "dump", + .func = ftrace_dump_callback, +}; + +static struct ftrace_func_command ftrace_cpudump_cmd = { + .name = "cpudump", + .func = ftrace_cpudump_callback, +}; + +static int __init init_func_cmd_traceon(void) +{ + int ret; + + ret = register_ftrace_command(&ftrace_traceoff_cmd); + if (ret) + return ret; + + ret = register_ftrace_command(&ftrace_traceon_cmd); + if (ret) + goto out_free_traceoff; + + ret = register_ftrace_command(&ftrace_stacktrace_cmd); + if (ret) + goto out_free_traceon; + + ret = register_ftrace_command(&ftrace_dump_cmd); + if (ret) + goto out_free_stacktrace; + + ret = register_ftrace_command(&ftrace_cpudump_cmd); + if (ret) + goto out_free_dump; + + return 0; + + out_free_dump: + unregister_ftrace_command(&ftrace_dump_cmd); + out_free_stacktrace: + unregister_ftrace_command(&ftrace_stacktrace_cmd); + out_free_traceon: + unregister_ftrace_command(&ftrace_traceon_cmd); + out_free_traceoff: + unregister_ftrace_command(&ftrace_traceoff_cmd); + + return ret; +} +#else +static inline int init_func_cmd_traceon(void) +{ + return 0; +} +#endif /* CONFIG_DYNAMIC_FTRACE */ + +static __init int init_function_trace(void) +{ + init_func_cmd_traceon(); + return register_tracer(&function_trace); +} +core_initcall(init_function_trace); diff --git a/kernel/kernel/trace/trace_functions_graph.c b/kernel/kernel/trace/trace_functions_graph.c new file mode 100644 index 000000000..a51e79688 --- /dev/null +++ b/kernel/kernel/trace/trace_functions_graph.c @@ -0,0 +1,1470 @@ +/* + * + * Function graph tracer. + * Copyright (c) 2008-2009 Frederic Weisbecker + * Mostly borrowed from function tracer which + * is Copyright (c) Steven Rostedt + * + */ +#include +#include +#include +#include + +#include "trace.h" +#include "trace_output.h" + +static bool kill_ftrace_graph; + +/** + * ftrace_graph_is_dead - returns true if ftrace_graph_stop() was called + * + * ftrace_graph_stop() is called when a severe error is detected in + * the function graph tracing. This function is called by the critical + * paths of function graph to keep those paths from doing any more harm. + */ +bool ftrace_graph_is_dead(void) +{ + return kill_ftrace_graph; +} + +/** + * ftrace_graph_stop - set to permanently disable function graph tracincg + * + * In case of an error int function graph tracing, this is called + * to try to keep function graph tracing from causing any more harm. + * Usually this is pretty severe and this is called to try to at least + * get a warning out to the user. + */ +void ftrace_graph_stop(void) +{ + kill_ftrace_graph = true; +} + +/* When set, irq functions will be ignored */ +static int ftrace_graph_skip_irqs; + +struct fgraph_cpu_data { + pid_t last_pid; + int depth; + int depth_irq; + int ignore; + unsigned long enter_funcs[FTRACE_RETFUNC_DEPTH]; +}; + +struct fgraph_data { + struct fgraph_cpu_data __percpu *cpu_data; + + /* Place to preserve last processed entry. */ + struct ftrace_graph_ent_entry ent; + struct ftrace_graph_ret_entry ret; + int failed; + int cpu; +}; + +#define TRACE_GRAPH_INDENT 2 + +static unsigned int max_depth; + +static struct tracer_opt trace_opts[] = { + /* Display overruns? (for self-debug purpose) */ + { TRACER_OPT(funcgraph-overrun, TRACE_GRAPH_PRINT_OVERRUN) }, + /* Display CPU ? */ + { TRACER_OPT(funcgraph-cpu, TRACE_GRAPH_PRINT_CPU) }, + /* Display Overhead ? */ + { TRACER_OPT(funcgraph-overhead, TRACE_GRAPH_PRINT_OVERHEAD) }, + /* Display proc name/pid */ + { TRACER_OPT(funcgraph-proc, TRACE_GRAPH_PRINT_PROC) }, + /* Display duration of execution */ + { TRACER_OPT(funcgraph-duration, TRACE_GRAPH_PRINT_DURATION) }, + /* Display absolute time of an entry */ + { TRACER_OPT(funcgraph-abstime, TRACE_GRAPH_PRINT_ABS_TIME) }, + /* Display interrupts */ + { TRACER_OPT(funcgraph-irqs, TRACE_GRAPH_PRINT_IRQS) }, + /* Display function name after trailing } */ + { TRACER_OPT(funcgraph-tail, TRACE_GRAPH_PRINT_TAIL) }, + { } /* Empty entry */ +}; + +static struct tracer_flags tracer_flags = { + /* Don't display overruns, proc, or tail by default */ + .val = TRACE_GRAPH_PRINT_CPU | TRACE_GRAPH_PRINT_OVERHEAD | + TRACE_GRAPH_PRINT_DURATION | TRACE_GRAPH_PRINT_IRQS, + .opts = trace_opts +}; + +static struct trace_array *graph_array; + +/* + * DURATION column is being also used to display IRQ signs, + * following values are used by print_graph_irq and others + * to fill in space into DURATION column. + */ +enum { + FLAGS_FILL_FULL = 1 << TRACE_GRAPH_PRINT_FILL_SHIFT, + FLAGS_FILL_START = 2 << TRACE_GRAPH_PRINT_FILL_SHIFT, + FLAGS_FILL_END = 3 << TRACE_GRAPH_PRINT_FILL_SHIFT, +}; + +static void +print_graph_duration(unsigned long long duration, struct trace_seq *s, + u32 flags); + +/* Add a function return address to the trace stack on thread info.*/ +int +ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth, + unsigned long frame_pointer) +{ + unsigned long long calltime; + int index; + + if (unlikely(ftrace_graph_is_dead())) + return -EBUSY; + + if (!current->ret_stack) + return -EBUSY; + + /* + * We must make sure the ret_stack is tested before we read + * anything else. + */ + smp_rmb(); + + /* The return trace stack is full */ + if (current->curr_ret_stack == FTRACE_RETFUNC_DEPTH - 1) { + atomic_inc(¤t->trace_overrun); + return -EBUSY; + } + + /* + * The curr_ret_stack is an index to ftrace return stack of + * current task. Its value should be in [0, FTRACE_RETFUNC_ + * DEPTH) when the function graph tracer is used. To support + * filtering out specific functions, it makes the index + * negative by subtracting huge value (FTRACE_NOTRACE_DEPTH) + * so when it sees a negative index the ftrace will ignore + * the record. And the index gets recovered when returning + * from the filtered function by adding the FTRACE_NOTRACE_ + * DEPTH and then it'll continue to record functions normally. + * + * The curr_ret_stack is initialized to -1 and get increased + * in this function. So it can be less than -1 only if it was + * filtered out via ftrace_graph_notrace_addr() which can be + * set from set_graph_notrace file in tracefs by user. + */ + if (current->curr_ret_stack < -1) + return -EBUSY; + + calltime = trace_clock_local(); + + index = ++current->curr_ret_stack; + if (ftrace_graph_notrace_addr(func)) + current->curr_ret_stack -= FTRACE_NOTRACE_DEPTH; + barrier(); + current->ret_stack[index].ret = ret; + current->ret_stack[index].func = func; + current->ret_stack[index].calltime = calltime; + current->ret_stack[index].subtime = 0; + current->ret_stack[index].fp = frame_pointer; + *depth = current->curr_ret_stack; + + return 0; +} + +/* Retrieve a function return address to the trace stack on thread info.*/ +static void +ftrace_pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret, + unsigned long frame_pointer) +{ + int index; + + index = current->curr_ret_stack; + + /* + * A negative index here means that it's just returned from a + * notrace'd function. Recover index to get an original + * return address. See ftrace_push_return_trace(). + * + * TODO: Need to check whether the stack gets corrupted. + */ + if (index < 0) + index += FTRACE_NOTRACE_DEPTH; + + if (unlikely(index < 0 || index >= FTRACE_RETFUNC_DEPTH)) { + ftrace_graph_stop(); + WARN_ON(1); + /* Might as well panic, otherwise we have no where to go */ + *ret = (unsigned long)panic; + return; + } + +#if defined(CONFIG_HAVE_FUNCTION_GRAPH_FP_TEST) && !defined(CC_USING_FENTRY) + /* + * The arch may choose to record the frame pointer used + * and check it here to make sure that it is what we expect it + * to be. If gcc does not set the place holder of the return + * address in the frame pointer, and does a copy instead, then + * the function graph trace will fail. This test detects this + * case. + * + * Currently, x86_32 with optimize for size (-Os) makes the latest + * gcc do the above. + * + * Note, -mfentry does not use frame pointers, and this test + * is not needed if CC_USING_FENTRY is set. + */ + if (unlikely(current->ret_stack[index].fp != frame_pointer)) { + ftrace_graph_stop(); + WARN(1, "Bad frame pointer: expected %lx, received %lx\n" + " from func %ps return to %lx\n", + current->ret_stack[index].fp, + frame_pointer, + (void *)current->ret_stack[index].func, + current->ret_stack[index].ret); + *ret = (unsigned long)panic; + return; + } +#endif + + *ret = current->ret_stack[index].ret; + trace->func = current->ret_stack[index].func; + trace->calltime = current->ret_stack[index].calltime; + trace->overrun = atomic_read(¤t->trace_overrun); + trace->depth = index; +} + +/* + * Send the trace to the ring-buffer. + * @return the original return address. + */ +unsigned long ftrace_return_to_handler(unsigned long frame_pointer) +{ + struct ftrace_graph_ret trace; + unsigned long ret; + + ftrace_pop_return_trace(&trace, &ret, frame_pointer); + trace.rettime = trace_clock_local(); + barrier(); + current->curr_ret_stack--; + /* + * The curr_ret_stack can be less than -1 only if it was + * filtered out and it's about to return from the function. + * Recover the index and continue to trace normal functions. + */ + if (current->curr_ret_stack < -1) { + current->curr_ret_stack += FTRACE_NOTRACE_DEPTH; + return ret; + } + + /* + * The trace should run after decrementing the ret counter + * in case an interrupt were to come in. We don't want to + * lose the interrupt if max_depth is set. + */ + ftrace_graph_return(&trace); + + if (unlikely(!ret)) { + ftrace_graph_stop(); + WARN_ON(1); + /* Might as well panic. What else to do? */ + ret = (unsigned long)panic; + } + + return ret; +} + +int __trace_graph_entry(struct trace_array *tr, + struct ftrace_graph_ent *trace, + unsigned long flags, + int pc) +{ + struct ftrace_event_call *call = &event_funcgraph_entry; + struct ring_buffer_event *event; + struct ring_buffer *buffer = tr->trace_buffer.buffer; + struct ftrace_graph_ent_entry *entry; + + if (unlikely(__this_cpu_read(ftrace_cpu_disabled))) + return 0; + + event = trace_buffer_lock_reserve(buffer, TRACE_GRAPH_ENT, + sizeof(*entry), flags, pc); + if (!event) + return 0; + entry = ring_buffer_event_data(event); + entry->graph_ent = *trace; + if (!call_filter_check_discard(call, entry, buffer, event)) + __buffer_unlock_commit(buffer, event); + + return 1; +} + +static inline int ftrace_graph_ignore_irqs(void) +{ + if (!ftrace_graph_skip_irqs || trace_recursion_test(TRACE_IRQ_BIT)) + return 0; + + return in_irq(); +} + +int trace_graph_entry(struct ftrace_graph_ent *trace) +{ + struct trace_array *tr = graph_array; + struct trace_array_cpu *data; + unsigned long flags; + long disabled; + int ret; + int cpu; + int pc; + + if (!ftrace_trace_task(current)) + return 0; + + /* trace it when it is-nested-in or is a function enabled. */ + if ((!(trace->depth || ftrace_graph_addr(trace->func)) || + ftrace_graph_ignore_irqs()) || (trace->depth < 0) || + (max_depth && trace->depth >= max_depth)) + return 0; + + /* + * Do not trace a function if it's filtered by set_graph_notrace. + * Make the index of ret stack negative to indicate that it should + * ignore further functions. But it needs its own ret stack entry + * to recover the original index in order to continue tracing after + * returning from the function. + */ + if (ftrace_graph_notrace_addr(trace->func)) + return 1; + + local_irq_save(flags); + cpu = raw_smp_processor_id(); + data = per_cpu_ptr(tr->trace_buffer.data, cpu); + disabled = atomic_inc_return(&data->disabled); + if (likely(disabled == 1)) { + pc = preempt_count(); + ret = __trace_graph_entry(tr, trace, flags, pc); + } else { + ret = 0; + } + + atomic_dec(&data->disabled); + local_irq_restore(flags); + + return ret; +} + +static int trace_graph_thresh_entry(struct ftrace_graph_ent *trace) +{ + if (tracing_thresh) + return 1; + else + return trace_graph_entry(trace); +} + +static void +__trace_graph_function(struct trace_array *tr, + unsigned long ip, unsigned long flags, int pc) +{ + u64 time = trace_clock_local(); + struct ftrace_graph_ent ent = { + .func = ip, + .depth = 0, + }; + struct ftrace_graph_ret ret = { + .func = ip, + .depth = 0, + .calltime = time, + .rettime = time, + }; + + __trace_graph_entry(tr, &ent, flags, pc); + __trace_graph_return(tr, &ret, flags, pc); +} + +void +trace_graph_function(struct trace_array *tr, + unsigned long ip, unsigned long parent_ip, + unsigned long flags, int pc) +{ + __trace_graph_function(tr, ip, flags, pc); +} + +void __trace_graph_return(struct trace_array *tr, + struct ftrace_graph_ret *trace, + unsigned long flags, + int pc) +{ + struct ftrace_event_call *call = &event_funcgraph_exit; + struct ring_buffer_event *event; + struct ring_buffer *buffer = tr->trace_buffer.buffer; + struct ftrace_graph_ret_entry *entry; + + if (unlikely(__this_cpu_read(ftrace_cpu_disabled))) + return; + + event = trace_buffer_lock_reserve(buffer, TRACE_GRAPH_RET, + sizeof(*entry), flags, pc); + if (!event) + return; + entry = ring_buffer_event_data(event); + entry->ret = *trace; + if (!call_filter_check_discard(call, entry, buffer, event)) + __buffer_unlock_commit(buffer, event); +} + +void trace_graph_return(struct ftrace_graph_ret *trace) +{ + struct trace_array *tr = graph_array; + struct trace_array_cpu *data; + unsigned long flags; + long disabled; + int cpu; + int pc; + + local_irq_save(flags); + cpu = raw_smp_processor_id(); + data = per_cpu_ptr(tr->trace_buffer.data, cpu); + disabled = atomic_inc_return(&data->disabled); + if (likely(disabled == 1)) { + pc = preempt_count(); + __trace_graph_return(tr, trace, flags, pc); + } + atomic_dec(&data->disabled); + local_irq_restore(flags); +} + +void set_graph_array(struct trace_array *tr) +{ + graph_array = tr; + + /* Make graph_array visible before we start tracing */ + + smp_mb(); +} + +static void trace_graph_thresh_return(struct ftrace_graph_ret *trace) +{ + if (tracing_thresh && + (trace->rettime - trace->calltime < tracing_thresh)) + return; + else + trace_graph_return(trace); +} + +static int graph_trace_init(struct trace_array *tr) +{ + int ret; + + set_graph_array(tr); + if (tracing_thresh) + ret = register_ftrace_graph(&trace_graph_thresh_return, + &trace_graph_thresh_entry); + else + ret = register_ftrace_graph(&trace_graph_return, + &trace_graph_entry); + if (ret) + return ret; + tracing_start_cmdline_record(); + + return 0; +} + +static void graph_trace_reset(struct trace_array *tr) +{ + tracing_stop_cmdline_record(); + unregister_ftrace_graph(); +} + +static int graph_trace_update_thresh(struct trace_array *tr) +{ + graph_trace_reset(tr); + return graph_trace_init(tr); +} + +static int max_bytes_for_cpu; + +static void print_graph_cpu(struct trace_seq *s, int cpu) +{ + /* + * Start with a space character - to make it stand out + * to the right a bit when trace output is pasted into + * email: + */ + trace_seq_printf(s, " %*d) ", max_bytes_for_cpu, cpu); +} + +#define TRACE_GRAPH_PROCINFO_LENGTH 14 + +static void print_graph_proc(struct trace_seq *s, pid_t pid) +{ + char comm[TASK_COMM_LEN]; + /* sign + log10(MAX_INT) + '\0' */ + char pid_str[11]; + int spaces = 0; + int len; + int i; + + trace_find_cmdline(pid, comm); + comm[7] = '\0'; + sprintf(pid_str, "%d", pid); + + /* 1 stands for the "-" character */ + len = strlen(comm) + strlen(pid_str) + 1; + + if (len < TRACE_GRAPH_PROCINFO_LENGTH) + spaces = TRACE_GRAPH_PROCINFO_LENGTH - len; + + /* First spaces to align center */ + for (i = 0; i < spaces / 2; i++) + trace_seq_putc(s, ' '); + + trace_seq_printf(s, "%s-%s", comm, pid_str); + + /* Last spaces to align center */ + for (i = 0; i < spaces - (spaces / 2); i++) + trace_seq_putc(s, ' '); +} + + +static void print_graph_lat_fmt(struct trace_seq *s, struct trace_entry *entry) +{ + trace_seq_putc(s, ' '); + trace_print_lat_fmt(s, entry); +} + +/* If the pid changed since the last trace, output this event */ +static void +verif_pid(struct trace_seq *s, pid_t pid, int cpu, struct fgraph_data *data) +{ + pid_t prev_pid; + pid_t *last_pid; + + if (!data) + return; + + last_pid = &(per_cpu_ptr(data->cpu_data, cpu)->last_pid); + + if (*last_pid == pid) + return; + + prev_pid = *last_pid; + *last_pid = pid; + + if (prev_pid == -1) + return; +/* + * Context-switch trace line: + + ------------------------------------------ + | 1) migration/0--1 => sshd-1755 + ------------------------------------------ + + */ + trace_seq_puts(s, " ------------------------------------------\n"); + print_graph_cpu(s, cpu); + print_graph_proc(s, prev_pid); + trace_seq_puts(s, " => "); + print_graph_proc(s, pid); + trace_seq_puts(s, "\n ------------------------------------------\n\n"); +} + +static struct ftrace_graph_ret_entry * +get_return_for_leaf(struct trace_iterator *iter, + struct ftrace_graph_ent_entry *curr) +{ + struct fgraph_data *data = iter->private; + struct ring_buffer_iter *ring_iter = NULL; + struct ring_buffer_event *event; + struct ftrace_graph_ret_entry *next; + + /* + * If the previous output failed to write to the seq buffer, + * then we just reuse the data from before. + */ + if (data && data->failed) { + curr = &data->ent; + next = &data->ret; + } else { + + ring_iter = trace_buffer_iter(iter, iter->cpu); + + /* First peek to compare current entry and the next one */ + if (ring_iter) + event = ring_buffer_iter_peek(ring_iter, NULL); + else { + /* + * We need to consume the current entry to see + * the next one. + */ + ring_buffer_consume(iter->trace_buffer->buffer, iter->cpu, + NULL, NULL); + event = ring_buffer_peek(iter->trace_buffer->buffer, iter->cpu, + NULL, NULL); + } + + if (!event) + return NULL; + + next = ring_buffer_event_data(event); + + if (data) { + /* + * Save current and next entries for later reference + * if the output fails. + */ + data->ent = *curr; + /* + * If the next event is not a return type, then + * we only care about what type it is. Otherwise we can + * safely copy the entire event. + */ + if (next->ent.type == TRACE_GRAPH_RET) + data->ret = *next; + else + data->ret.ent.type = next->ent.type; + } + } + + if (next->ent.type != TRACE_GRAPH_RET) + return NULL; + + if (curr->ent.pid != next->ent.pid || + curr->graph_ent.func != next->ret.func) + return NULL; + + /* this is a leaf, now advance the iterator */ + if (ring_iter) + ring_buffer_read(ring_iter, NULL); + + return next; +} + +static void print_graph_abs_time(u64 t, struct trace_seq *s) +{ + unsigned long usecs_rem; + + usecs_rem = do_div(t, NSEC_PER_SEC); + usecs_rem /= 1000; + + trace_seq_printf(s, "%5lu.%06lu | ", + (unsigned long)t, usecs_rem); +} + +static void +print_graph_irq(struct trace_iterator *iter, unsigned long addr, + enum trace_type type, int cpu, pid_t pid, u32 flags) +{ + struct trace_seq *s = &iter->seq; + struct trace_entry *ent = iter->ent; + + if (addr < (unsigned long)__irqentry_text_start || + addr >= (unsigned long)__irqentry_text_end) + return; + + if (trace_flags & TRACE_ITER_CONTEXT_INFO) { + /* Absolute time */ + if (flags & TRACE_GRAPH_PRINT_ABS_TIME) + print_graph_abs_time(iter->ts, s); + + /* Cpu */ + if (flags & TRACE_GRAPH_PRINT_CPU) + print_graph_cpu(s, cpu); + + /* Proc */ + if (flags & TRACE_GRAPH_PRINT_PROC) { + print_graph_proc(s, pid); + trace_seq_puts(s, " | "); + } + + /* Latency format */ + if (trace_flags & TRACE_ITER_LATENCY_FMT) + print_graph_lat_fmt(s, ent); + } + + /* No overhead */ + print_graph_duration(0, s, flags | FLAGS_FILL_START); + + if (type == TRACE_GRAPH_ENT) + trace_seq_puts(s, "==========>"); + else + trace_seq_puts(s, "<=========="); + + print_graph_duration(0, s, flags | FLAGS_FILL_END); + trace_seq_putc(s, '\n'); +} + +void +trace_print_graph_duration(unsigned long long duration, struct trace_seq *s) +{ + unsigned long nsecs_rem = do_div(duration, 1000); + /* log10(ULONG_MAX) + '\0' */ + char usecs_str[21]; + char nsecs_str[5]; + int len; + int i; + + sprintf(usecs_str, "%lu", (unsigned long) duration); + + /* Print msecs */ + trace_seq_printf(s, "%s", usecs_str); + + len = strlen(usecs_str); + + /* Print nsecs (we don't want to exceed 7 numbers) */ + if (len < 7) { + size_t slen = min_t(size_t, sizeof(nsecs_str), 8UL - len); + + snprintf(nsecs_str, slen, "%03lu", nsecs_rem); + trace_seq_printf(s, ".%s", nsecs_str); + len += strlen(nsecs_str); + } + + trace_seq_puts(s, " us "); + + /* Print remaining spaces to fit the row's width */ + for (i = len; i < 7; i++) + trace_seq_putc(s, ' '); +} + +static void +print_graph_duration(unsigned long long duration, struct trace_seq *s, + u32 flags) +{ + if (!(flags & TRACE_GRAPH_PRINT_DURATION) || + !(trace_flags & TRACE_ITER_CONTEXT_INFO)) + return; + + /* No real adata, just filling the column with spaces */ + switch (flags & TRACE_GRAPH_PRINT_FILL_MASK) { + case FLAGS_FILL_FULL: + trace_seq_puts(s, " | "); + return; + case FLAGS_FILL_START: + trace_seq_puts(s, " "); + return; + case FLAGS_FILL_END: + trace_seq_puts(s, " |"); + return; + } + + /* Signal a overhead of time execution to the output */ + if (flags & TRACE_GRAPH_PRINT_OVERHEAD) + trace_seq_printf(s, "%c ", trace_find_mark(duration)); + else + trace_seq_puts(s, " "); + + trace_print_graph_duration(duration, s); + trace_seq_puts(s, "| "); +} + +/* Case of a leaf function on its call entry */ +static enum print_line_t +print_graph_entry_leaf(struct trace_iterator *iter, + struct ftrace_graph_ent_entry *entry, + struct ftrace_graph_ret_entry *ret_entry, + struct trace_seq *s, u32 flags) +{ + struct fgraph_data *data = iter->private; + struct ftrace_graph_ret *graph_ret; + struct ftrace_graph_ent *call; + unsigned long long duration; + int i; + + graph_ret = &ret_entry->ret; + call = &entry->graph_ent; + duration = graph_ret->rettime - graph_ret->calltime; + + if (data) { + struct fgraph_cpu_data *cpu_data; + int cpu = iter->cpu; + + cpu_data = per_cpu_ptr(data->cpu_data, cpu); + + /* + * Comments display at + 1 to depth. Since + * this is a leaf function, keep the comments + * equal to this depth. + */ + cpu_data->depth = call->depth - 1; + + /* No need to keep this function around for this depth */ + if (call->depth < FTRACE_RETFUNC_DEPTH) + cpu_data->enter_funcs[call->depth] = 0; + } + + /* Overhead and duration */ + print_graph_duration(duration, s, flags); + + /* Function */ + for (i = 0; i < call->depth * TRACE_GRAPH_INDENT; i++) + trace_seq_putc(s, ' '); + + trace_seq_printf(s, "%ps();\n", (void *)call->func); + + return trace_handle_return(s); +} + +static enum print_line_t +print_graph_entry_nested(struct trace_iterator *iter, + struct ftrace_graph_ent_entry *entry, + struct trace_seq *s, int cpu, u32 flags) +{ + struct ftrace_graph_ent *call = &entry->graph_ent; + struct fgraph_data *data = iter->private; + int i; + + if (data) { + struct fgraph_cpu_data *cpu_data; + int cpu = iter->cpu; + + cpu_data = per_cpu_ptr(data->cpu_data, cpu); + cpu_data->depth = call->depth; + + /* Save this function pointer to see if the exit matches */ + if (call->depth < FTRACE_RETFUNC_DEPTH) + cpu_data->enter_funcs[call->depth] = call->func; + } + + /* No time */ + print_graph_duration(0, s, flags | FLAGS_FILL_FULL); + + /* Function */ + for (i = 0; i < call->depth * TRACE_GRAPH_INDENT; i++) + trace_seq_putc(s, ' '); + + trace_seq_printf(s, "%ps() {\n", (void *)call->func); + + if (trace_seq_has_overflowed(s)) + return TRACE_TYPE_PARTIAL_LINE; + + /* + * we already consumed the current entry to check the next one + * and see if this is a leaf. + */ + return TRACE_TYPE_NO_CONSUME; +} + +static void +print_graph_prologue(struct trace_iterator *iter, struct trace_seq *s, + int type, unsigned long addr, u32 flags) +{ + struct fgraph_data *data = iter->private; + struct trace_entry *ent = iter->ent; + int cpu = iter->cpu; + + /* Pid */ + verif_pid(s, ent->pid, cpu, data); + + if (type) + /* Interrupt */ + print_graph_irq(iter, addr, type, cpu, ent->pid, flags); + + if (!(trace_flags & TRACE_ITER_CONTEXT_INFO)) + return; + + /* Absolute time */ + if (flags & TRACE_GRAPH_PRINT_ABS_TIME) + print_graph_abs_time(iter->ts, s); + + /* Cpu */ + if (flags & TRACE_GRAPH_PRINT_CPU) + print_graph_cpu(s, cpu); + + /* Proc */ + if (flags & TRACE_GRAPH_PRINT_PROC) { + print_graph_proc(s, ent->pid); + trace_seq_puts(s, " | "); + } + + /* Latency format */ + if (trace_flags & TRACE_ITER_LATENCY_FMT) + print_graph_lat_fmt(s, ent); + + return; +} + +/* + * Entry check for irq code + * + * returns 1 if + * - we are inside irq code + * - we just entered irq code + * + * retunns 0 if + * - funcgraph-interrupts option is set + * - we are not inside irq code + */ +static int +check_irq_entry(struct trace_iterator *iter, u32 flags, + unsigned long addr, int depth) +{ + int cpu = iter->cpu; + int *depth_irq; + struct fgraph_data *data = iter->private; + + /* + * If we are either displaying irqs, or we got called as + * a graph event and private data does not exist, + * then we bypass the irq check. + */ + if ((flags & TRACE_GRAPH_PRINT_IRQS) || + (!data)) + return 0; + + depth_irq = &(per_cpu_ptr(data->cpu_data, cpu)->depth_irq); + + /* + * We are inside the irq code + */ + if (*depth_irq >= 0) + return 1; + + if ((addr < (unsigned long)__irqentry_text_start) || + (addr >= (unsigned long)__irqentry_text_end)) + return 0; + + /* + * We are entering irq code. + */ + *depth_irq = depth; + return 1; +} + +/* + * Return check for irq code + * + * returns 1 if + * - we are inside irq code + * - we just left irq code + * + * returns 0 if + * - funcgraph-interrupts option is set + * - we are not inside irq code + */ +static int +check_irq_return(struct trace_iterator *iter, u32 flags, int depth) +{ + int cpu = iter->cpu; + int *depth_irq; + struct fgraph_data *data = iter->private; + + /* + * If we are either displaying irqs, or we got called as + * a graph event and private data does not exist, + * then we bypass the irq check. + */ + if ((flags & TRACE_GRAPH_PRINT_IRQS) || + (!data)) + return 0; + + depth_irq = &(per_cpu_ptr(data->cpu_data, cpu)->depth_irq); + + /* + * We are not inside the irq code. + */ + if (*depth_irq == -1) + return 0; + + /* + * We are inside the irq code, and this is returning entry. + * Let's not trace it and clear the entry depth, since + * we are out of irq code. + * + * This condition ensures that we 'leave the irq code' once + * we are out of the entry depth. Thus protecting us from + * the RETURN entry loss. + */ + if (*depth_irq >= depth) { + *depth_irq = -1; + return 1; + } + + /* + * We are inside the irq code, and this is not the entry. + */ + return 1; +} + +static enum print_line_t +print_graph_entry(struct ftrace_graph_ent_entry *field, struct trace_seq *s, + struct trace_iterator *iter, u32 flags) +{ + struct fgraph_data *data = iter->private; + struct ftrace_graph_ent *call = &field->graph_ent; + struct ftrace_graph_ret_entry *leaf_ret; + static enum print_line_t ret; + int cpu = iter->cpu; + + if (check_irq_entry(iter, flags, call->func, call->depth)) + return TRACE_TYPE_HANDLED; + + print_graph_prologue(iter, s, TRACE_GRAPH_ENT, call->func, flags); + + leaf_ret = get_return_for_leaf(iter, field); + if (leaf_ret) + ret = print_graph_entry_leaf(iter, field, leaf_ret, s, flags); + else + ret = print_graph_entry_nested(iter, field, s, cpu, flags); + + if (data) { + /* + * If we failed to write our output, then we need to make + * note of it. Because we already consumed our entry. + */ + if (s->full) { + data->failed = 1; + data->cpu = cpu; + } else + data->failed = 0; + } + + return ret; +} + +static enum print_line_t +print_graph_return(struct ftrace_graph_ret *trace, struct trace_seq *s, + struct trace_entry *ent, struct trace_iterator *iter, + u32 flags) +{ + unsigned long long duration = trace->rettime - trace->calltime; + struct fgraph_data *data = iter->private; + pid_t pid = ent->pid; + int cpu = iter->cpu; + int func_match = 1; + int i; + + if (check_irq_return(iter, flags, trace->depth)) + return TRACE_TYPE_HANDLED; + + if (data) { + struct fgraph_cpu_data *cpu_data; + int cpu = iter->cpu; + + cpu_data = per_cpu_ptr(data->cpu_data, cpu); + + /* + * Comments display at + 1 to depth. This is the + * return from a function, we now want the comments + * to display at the same level of the bracket. + */ + cpu_data->depth = trace->depth - 1; + + if (trace->depth < FTRACE_RETFUNC_DEPTH) { + if (cpu_data->enter_funcs[trace->depth] != trace->func) + func_match = 0; + cpu_data->enter_funcs[trace->depth] = 0; + } + } + + print_graph_prologue(iter, s, 0, 0, flags); + + /* Overhead and duration */ + print_graph_duration(duration, s, flags); + + /* Closing brace */ + for (i = 0; i < trace->depth * TRACE_GRAPH_INDENT; i++) + trace_seq_putc(s, ' '); + + /* + * If the return function does not have a matching entry, + * then the entry was lost. Instead of just printing + * the '}' and letting the user guess what function this + * belongs to, write out the function name. Always do + * that if the funcgraph-tail option is enabled. + */ + if (func_match && !(flags & TRACE_GRAPH_PRINT_TAIL)) + trace_seq_puts(s, "}\n"); + else + trace_seq_printf(s, "} /* %ps */\n", (void *)trace->func); + + /* Overrun */ + if (flags & TRACE_GRAPH_PRINT_OVERRUN) + trace_seq_printf(s, " (Overruns: %lu)\n", + trace->overrun); + + print_graph_irq(iter, trace->func, TRACE_GRAPH_RET, + cpu, pid, flags); + + return trace_handle_return(s); +} + +static enum print_line_t +print_graph_comment(struct trace_seq *s, struct trace_entry *ent, + struct trace_iterator *iter, u32 flags) +{ + unsigned long sym_flags = (trace_flags & TRACE_ITER_SYM_MASK); + struct fgraph_data *data = iter->private; + struct trace_event *event; + int depth = 0; + int ret; + int i; + + if (data) + depth = per_cpu_ptr(data->cpu_data, iter->cpu)->depth; + + print_graph_prologue(iter, s, 0, 0, flags); + + /* No time */ + print_graph_duration(0, s, flags | FLAGS_FILL_FULL); + + /* Indentation */ + if (depth > 0) + for (i = 0; i < (depth + 1) * TRACE_GRAPH_INDENT; i++) + trace_seq_putc(s, ' '); + + /* The comment */ + trace_seq_puts(s, "/* "); + + switch (iter->ent->type) { + case TRACE_BPRINT: + ret = trace_print_bprintk_msg_only(iter); + if (ret != TRACE_TYPE_HANDLED) + return ret; + break; + case TRACE_PRINT: + ret = trace_print_printk_msg_only(iter); + if (ret != TRACE_TYPE_HANDLED) + return ret; + break; + default: + event = ftrace_find_event(ent->type); + if (!event) + return TRACE_TYPE_UNHANDLED; + + ret = event->funcs->trace(iter, sym_flags, event); + if (ret != TRACE_TYPE_HANDLED) + return ret; + } + + if (trace_seq_has_overflowed(s)) + goto out; + + /* Strip ending newline */ + if (s->buffer[s->seq.len - 1] == '\n') { + s->buffer[s->seq.len - 1] = '\0'; + s->seq.len--; + } + + trace_seq_puts(s, " */\n"); + out: + return trace_handle_return(s); +} + + +enum print_line_t +print_graph_function_flags(struct trace_iterator *iter, u32 flags) +{ + struct ftrace_graph_ent_entry *field; + struct fgraph_data *data = iter->private; + struct trace_entry *entry = iter->ent; + struct trace_seq *s = &iter->seq; + int cpu = iter->cpu; + int ret; + + if (data && per_cpu_ptr(data->cpu_data, cpu)->ignore) { + per_cpu_ptr(data->cpu_data, cpu)->ignore = 0; + return TRACE_TYPE_HANDLED; + } + + /* + * If the last output failed, there's a possibility we need + * to print out the missing entry which would never go out. + */ + if (data && data->failed) { + field = &data->ent; + iter->cpu = data->cpu; + ret = print_graph_entry(field, s, iter, flags); + if (ret == TRACE_TYPE_HANDLED && iter->cpu != cpu) { + per_cpu_ptr(data->cpu_data, iter->cpu)->ignore = 1; + ret = TRACE_TYPE_NO_CONSUME; + } + iter->cpu = cpu; + return ret; + } + + switch (entry->type) { + case TRACE_GRAPH_ENT: { + /* + * print_graph_entry() may consume the current event, + * thus @field may become invalid, so we need to save it. + * sizeof(struct ftrace_graph_ent_entry) is very small, + * it can be safely saved at the stack. + */ + struct ftrace_graph_ent_entry saved; + trace_assign_type(field, entry); + saved = *field; + return print_graph_entry(&saved, s, iter, flags); + } + case TRACE_GRAPH_RET: { + struct ftrace_graph_ret_entry *field; + trace_assign_type(field, entry); + return print_graph_return(&field->ret, s, entry, iter, flags); + } + case TRACE_STACK: + case TRACE_FN: + /* dont trace stack and functions as comments */ + return TRACE_TYPE_UNHANDLED; + + default: + return print_graph_comment(s, entry, iter, flags); + } + + return TRACE_TYPE_HANDLED; +} + +static enum print_line_t +print_graph_function(struct trace_iterator *iter) +{ + return print_graph_function_flags(iter, tracer_flags.val); +} + +static enum print_line_t +print_graph_function_event(struct trace_iterator *iter, int flags, + struct trace_event *event) +{ + return print_graph_function(iter); +} + +static void print_lat_header(struct seq_file *s, u32 flags) +{ + static const char spaces[] = " " /* 16 spaces */ + " " /* 4 spaces */ + " "; /* 17 spaces */ + int size = 0; + + if (flags & TRACE_GRAPH_PRINT_ABS_TIME) + size += 16; + if (flags & TRACE_GRAPH_PRINT_CPU) + size += 4; + if (flags & TRACE_GRAPH_PRINT_PROC) + size += 17; + + seq_printf(s, "#%.*s _-----=> irqs-off \n", size, spaces); + seq_printf(s, "#%.*s / _----=> need-resched \n", size, spaces); + seq_printf(s, "#%.*s| / _---=> hardirq/softirq \n", size, spaces); + seq_printf(s, "#%.*s|| / _--=> preempt-depth \n", size, spaces); + seq_printf(s, "#%.*s||| / \n", size, spaces); +} + +static void __print_graph_headers_flags(struct seq_file *s, u32 flags) +{ + int lat = trace_flags & TRACE_ITER_LATENCY_FMT; + + if (lat) + print_lat_header(s, flags); + + /* 1st line */ + seq_putc(s, '#'); + if (flags & TRACE_GRAPH_PRINT_ABS_TIME) + seq_puts(s, " TIME "); + if (flags & TRACE_GRAPH_PRINT_CPU) + seq_puts(s, " CPU"); + if (flags & TRACE_GRAPH_PRINT_PROC) + seq_puts(s, " TASK/PID "); + if (lat) + seq_puts(s, "||||"); + if (flags & TRACE_GRAPH_PRINT_DURATION) + seq_puts(s, " DURATION "); + seq_puts(s, " FUNCTION CALLS\n"); + + /* 2nd line */ + seq_putc(s, '#'); + if (flags & TRACE_GRAPH_PRINT_ABS_TIME) + seq_puts(s, " | "); + if (flags & TRACE_GRAPH_PRINT_CPU) + seq_puts(s, " | "); + if (flags & TRACE_GRAPH_PRINT_PROC) + seq_puts(s, " | | "); + if (lat) + seq_puts(s, "||||"); + if (flags & TRACE_GRAPH_PRINT_DURATION) + seq_puts(s, " | | "); + seq_puts(s, " | | | |\n"); +} + +static void print_graph_headers(struct seq_file *s) +{ + print_graph_headers_flags(s, tracer_flags.val); +} + +void print_graph_headers_flags(struct seq_file *s, u32 flags) +{ + struct trace_iterator *iter = s->private; + + if (!(trace_flags & TRACE_ITER_CONTEXT_INFO)) + return; + + if (trace_flags & TRACE_ITER_LATENCY_FMT) { + /* print nothing if the buffers are empty */ + if (trace_empty(iter)) + return; + + print_trace_header(s, iter); + } + + __print_graph_headers_flags(s, flags); +} + +void graph_trace_open(struct trace_iterator *iter) +{ + /* pid and depth on the last trace processed */ + struct fgraph_data *data; + gfp_t gfpflags; + int cpu; + + iter->private = NULL; + + /* We can be called in atomic context via ftrace_dump() */ + gfpflags = (in_atomic() || irqs_disabled()) ? GFP_ATOMIC : GFP_KERNEL; + + data = kzalloc(sizeof(*data), gfpflags); + if (!data) + goto out_err; + + data->cpu_data = alloc_percpu_gfp(struct fgraph_cpu_data, gfpflags); + if (!data->cpu_data) + goto out_err_free; + + for_each_possible_cpu(cpu) { + pid_t *pid = &(per_cpu_ptr(data->cpu_data, cpu)->last_pid); + int *depth = &(per_cpu_ptr(data->cpu_data, cpu)->depth); + int *ignore = &(per_cpu_ptr(data->cpu_data, cpu)->ignore); + int *depth_irq = &(per_cpu_ptr(data->cpu_data, cpu)->depth_irq); + + *pid = -1; + *depth = 0; + *ignore = 0; + *depth_irq = -1; + } + + iter->private = data; + + return; + + out_err_free: + kfree(data); + out_err: + pr_warning("function graph tracer: not enough memory\n"); +} + +void graph_trace_close(struct trace_iterator *iter) +{ + struct fgraph_data *data = iter->private; + + if (data) { + free_percpu(data->cpu_data); + kfree(data); + } +} + +static int +func_graph_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set) +{ + if (bit == TRACE_GRAPH_PRINT_IRQS) + ftrace_graph_skip_irqs = !set; + + return 0; +} + +static struct trace_event_functions graph_functions = { + .trace = print_graph_function_event, +}; + +static struct trace_event graph_trace_entry_event = { + .type = TRACE_GRAPH_ENT, + .funcs = &graph_functions, +}; + +static struct trace_event graph_trace_ret_event = { + .type = TRACE_GRAPH_RET, + .funcs = &graph_functions +}; + +static struct tracer graph_trace __tracer_data = { + .name = "function_graph", + .update_thresh = graph_trace_update_thresh, + .open = graph_trace_open, + .pipe_open = graph_trace_open, + .close = graph_trace_close, + .pipe_close = graph_trace_close, + .init = graph_trace_init, + .reset = graph_trace_reset, + .print_line = print_graph_function, + .print_header = print_graph_headers, + .flags = &tracer_flags, + .set_flag = func_graph_set_flag, +#ifdef CONFIG_FTRACE_SELFTEST + .selftest = trace_selftest_startup_function_graph, +#endif +}; + + +static ssize_t +graph_depth_write(struct file *filp, const char __user *ubuf, size_t cnt, + loff_t *ppos) +{ + unsigned long val; + int ret; + + ret = kstrtoul_from_user(ubuf, cnt, 10, &val); + if (ret) + return ret; + + max_depth = val; + + *ppos += cnt; + + return cnt; +} + +static ssize_t +graph_depth_read(struct file *filp, char __user *ubuf, size_t cnt, + loff_t *ppos) +{ + char buf[15]; /* More than enough to hold UINT_MAX + "\n"*/ + int n; + + n = sprintf(buf, "%d\n", max_depth); + + return simple_read_from_buffer(ubuf, cnt, ppos, buf, n); +} + +static const struct file_operations graph_depth_fops = { + .open = tracing_open_generic, + .write = graph_depth_write, + .read = graph_depth_read, + .llseek = generic_file_llseek, +}; + +static __init int init_graph_tracefs(void) +{ + struct dentry *d_tracer; + + d_tracer = tracing_init_dentry(); + if (IS_ERR(d_tracer)) + return 0; + + trace_create_file("max_graph_depth", 0644, d_tracer, + NULL, &graph_depth_fops); + + return 0; +} +fs_initcall(init_graph_tracefs); + +static __init int init_graph_trace(void) +{ + max_bytes_for_cpu = snprintf(NULL, 0, "%d", nr_cpu_ids - 1); + + if (!register_ftrace_event(&graph_trace_entry_event)) { + pr_warning("Warning: could not register graph trace events\n"); + return 1; + } + + if (!register_ftrace_event(&graph_trace_ret_event)) { + pr_warning("Warning: could not register graph trace events\n"); + return 1; + } + + return register_tracer(&graph_trace); +} + +core_initcall(init_graph_trace); diff --git a/kernel/kernel/trace/trace_irqsoff.c b/kernel/kernel/trace/trace_irqsoff.c new file mode 100644 index 000000000..aaade2efc --- /dev/null +++ b/kernel/kernel/trace/trace_irqsoff.c @@ -0,0 +1,775 @@ +/* + * trace irqs off critical timings + * + * Copyright (C) 2007-2008 Steven Rostedt + * Copyright (C) 2008 Ingo Molnar + * + * From code in the latency_tracer, that is: + * + * Copyright (C) 2004-2006 Ingo Molnar + * Copyright (C) 2004 Nadia Yvette Chambers + */ +#include +#include +#include +#include +#include + +#include "trace.h" + +static struct trace_array *irqsoff_trace __read_mostly; +static int tracer_enabled __read_mostly; + +static DEFINE_PER_CPU(int, tracing_cpu); + +static DEFINE_RAW_SPINLOCK(max_trace_lock); + +enum { + TRACER_IRQS_OFF = (1 << 1), + TRACER_PREEMPT_OFF = (1 << 2), +}; + +static int trace_type __read_mostly; + +static int save_flags; +static bool function_enabled; + +static void stop_irqsoff_tracer(struct trace_array *tr, int graph); +static int start_irqsoff_tracer(struct trace_array *tr, int graph); + +#ifdef CONFIG_PREEMPT_TRACER +static inline int +preempt_trace(void) +{ + return ((trace_type & TRACER_PREEMPT_OFF) && preempt_count()); +} +#else +# define preempt_trace() (0) +#endif + +#ifdef CONFIG_IRQSOFF_TRACER +static inline int +irq_trace(void) +{ + return ((trace_type & TRACER_IRQS_OFF) && + irqs_disabled()); +} +#else +# define irq_trace() (0) +#endif + +#define TRACE_DISPLAY_GRAPH 1 + +static struct tracer_opt trace_opts[] = { +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + /* display latency trace as call graph */ + { TRACER_OPT(display-graph, TRACE_DISPLAY_GRAPH) }, +#endif + { } /* Empty entry */ +}; + +static struct tracer_flags tracer_flags = { + .val = 0, + .opts = trace_opts, +}; + +#define is_graph() (tracer_flags.val & TRACE_DISPLAY_GRAPH) + +/* + * Sequence count - we record it when starting a measurement and + * skip the latency if the sequence has changed - some other section + * did a maximum and could disturb our measurement with serial console + * printouts, etc. Truly coinciding maximum latencies should be rare + * and what happens together happens separately as well, so this doesn't + * decrease the validity of the maximum found: + */ +static __cacheline_aligned_in_smp unsigned long max_sequence; + +#ifdef CONFIG_FUNCTION_TRACER +/* + * Prologue for the preempt and irqs off function tracers. + * + * Returns 1 if it is OK to continue, and data->disabled is + * incremented. + * 0 if the trace is to be ignored, and data->disabled + * is kept the same. + * + * Note, this function is also used outside this ifdef but + * inside the #ifdef of the function graph tracer below. + * This is OK, since the function graph tracer is + * dependent on the function tracer. + */ +static int func_prolog_dec(struct trace_array *tr, + struct trace_array_cpu **data, + unsigned long *flags) +{ + long disabled; + int cpu; + + /* + * Does not matter if we preempt. We test the flags + * afterward, to see if irqs are disabled or not. + * If we preempt and get a false positive, the flags + * test will fail. + */ + cpu = raw_smp_processor_id(); + if (likely(!per_cpu(tracing_cpu, cpu))) + return 0; + + local_save_flags(*flags); + /* slight chance to get a false positive on tracing_cpu */ + if (!irqs_disabled_flags(*flags)) + return 0; + + *data = per_cpu_ptr(tr->trace_buffer.data, cpu); + disabled = atomic_inc_return(&(*data)->disabled); + + if (likely(disabled == 1)) + return 1; + + atomic_dec(&(*data)->disabled); + + return 0; +} + +/* + * irqsoff uses its own tracer function to keep the overhead down: + */ +static void +irqsoff_tracer_call(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct pt_regs *pt_regs) +{ + struct trace_array *tr = irqsoff_trace; + struct trace_array_cpu *data; + unsigned long flags; + + if (!func_prolog_dec(tr, &data, &flags)) + return; + + trace_function(tr, ip, parent_ip, flags, preempt_count()); + + atomic_dec(&data->disabled); +} +#endif /* CONFIG_FUNCTION_TRACER */ + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER +static int +irqsoff_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set) +{ + int cpu; + + if (!(bit & TRACE_DISPLAY_GRAPH)) + return -EINVAL; + + if (!(is_graph() ^ set)) + return 0; + + stop_irqsoff_tracer(irqsoff_trace, !set); + + for_each_possible_cpu(cpu) + per_cpu(tracing_cpu, cpu) = 0; + + tr->max_latency = 0; + tracing_reset_online_cpus(&irqsoff_trace->trace_buffer); + + return start_irqsoff_tracer(irqsoff_trace, set); +} + +static int irqsoff_graph_entry(struct ftrace_graph_ent *trace) +{ + struct trace_array *tr = irqsoff_trace; + struct trace_array_cpu *data; + unsigned long flags; + int ret; + int pc; + + if (!func_prolog_dec(tr, &data, &flags)) + return 0; + + pc = preempt_count(); + ret = __trace_graph_entry(tr, trace, flags, pc); + atomic_dec(&data->disabled); + + return ret; +} + +static void irqsoff_graph_return(struct ftrace_graph_ret *trace) +{ + struct trace_array *tr = irqsoff_trace; + struct trace_array_cpu *data; + unsigned long flags; + int pc; + + if (!func_prolog_dec(tr, &data, &flags)) + return; + + pc = preempt_count(); + __trace_graph_return(tr, trace, flags, pc); + atomic_dec(&data->disabled); +} + +static void irqsoff_trace_open(struct trace_iterator *iter) +{ + if (is_graph()) + graph_trace_open(iter); + +} + +static void irqsoff_trace_close(struct trace_iterator *iter) +{ + if (iter->private) + graph_trace_close(iter); +} + +#define GRAPH_TRACER_FLAGS (TRACE_GRAPH_PRINT_CPU | \ + TRACE_GRAPH_PRINT_PROC | \ + TRACE_GRAPH_PRINT_ABS_TIME | \ + TRACE_GRAPH_PRINT_DURATION) + +static enum print_line_t irqsoff_print_line(struct trace_iterator *iter) +{ + /* + * In graph mode call the graph tracer output function, + * otherwise go with the TRACE_FN event handler + */ + if (is_graph()) + return print_graph_function_flags(iter, GRAPH_TRACER_FLAGS); + + return TRACE_TYPE_UNHANDLED; +} + +static void irqsoff_print_header(struct seq_file *s) +{ + if (is_graph()) + print_graph_headers_flags(s, GRAPH_TRACER_FLAGS); + else + trace_default_header(s); +} + +static void +__trace_function(struct trace_array *tr, + unsigned long ip, unsigned long parent_ip, + unsigned long flags, int pc) +{ + if (is_graph()) + trace_graph_function(tr, ip, parent_ip, flags, pc); + else + trace_function(tr, ip, parent_ip, flags, pc); +} + +#else +#define __trace_function trace_function + +static int +irqsoff_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set) +{ + return -EINVAL; +} + +static int irqsoff_graph_entry(struct ftrace_graph_ent *trace) +{ + return -1; +} + +static enum print_line_t irqsoff_print_line(struct trace_iterator *iter) +{ + return TRACE_TYPE_UNHANDLED; +} + +static void irqsoff_graph_return(struct ftrace_graph_ret *trace) { } +static void irqsoff_trace_open(struct trace_iterator *iter) { } +static void irqsoff_trace_close(struct trace_iterator *iter) { } + +#ifdef CONFIG_FUNCTION_TRACER +static void irqsoff_print_header(struct seq_file *s) +{ + trace_default_header(s); +} +#else +static void irqsoff_print_header(struct seq_file *s) +{ + trace_latency_header(s); +} +#endif /* CONFIG_FUNCTION_TRACER */ +#endif /* CONFIG_FUNCTION_GRAPH_TRACER */ + +/* + * Should this new latency be reported/recorded? + */ +static int report_latency(struct trace_array *tr, cycle_t delta) +{ + if (tracing_thresh) { + if (delta < tracing_thresh) + return 0; + } else { + if (delta <= tr->max_latency) + return 0; + } + return 1; +} + +static void +check_critical_timing(struct trace_array *tr, + struct trace_array_cpu *data, + unsigned long parent_ip, + int cpu) +{ + cycle_t T0, T1, delta; + unsigned long flags; + int pc; + + T0 = data->preempt_timestamp; + T1 = ftrace_now(cpu); + delta = T1-T0; + + local_save_flags(flags); + + pc = preempt_count(); + + if (!report_latency(tr, delta)) + goto out; + + raw_spin_lock_irqsave(&max_trace_lock, flags); + + /* check if we are still the max latency */ + if (!report_latency(tr, delta)) + goto out_unlock; + + __trace_function(tr, CALLER_ADDR0, parent_ip, flags, pc); + /* Skip 5 functions to get to the irq/preempt enable function */ + __trace_stack(tr, flags, 5, pc); + + if (data->critical_sequence != max_sequence) + goto out_unlock; + + data->critical_end = parent_ip; + + if (likely(!is_tracing_stopped())) { + tr->max_latency = delta; + update_max_tr_single(tr, current, cpu); + } + + max_sequence++; + +out_unlock: + raw_spin_unlock_irqrestore(&max_trace_lock, flags); + +out: + data->critical_sequence = max_sequence; + data->preempt_timestamp = ftrace_now(cpu); + __trace_function(tr, CALLER_ADDR0, parent_ip, flags, pc); +} + +static inline void +start_critical_timing(unsigned long ip, unsigned long parent_ip) +{ + int cpu; + struct trace_array *tr = irqsoff_trace; + struct trace_array_cpu *data; + unsigned long flags; + + if (!tracer_enabled || !tracing_is_enabled()) + return; + + cpu = raw_smp_processor_id(); + + if (per_cpu(tracing_cpu, cpu)) + return; + + data = per_cpu_ptr(tr->trace_buffer.data, cpu); + + if (unlikely(!data) || atomic_read(&data->disabled)) + return; + + atomic_inc(&data->disabled); + + data->critical_sequence = max_sequence; + data->preempt_timestamp = ftrace_now(cpu); + data->critical_start = parent_ip ? : ip; + + local_save_flags(flags); + + __trace_function(tr, ip, parent_ip, flags, preempt_count()); + + per_cpu(tracing_cpu, cpu) = 1; + + atomic_dec(&data->disabled); +} + +static inline void +stop_critical_timing(unsigned long ip, unsigned long parent_ip) +{ + int cpu; + struct trace_array *tr = irqsoff_trace; + struct trace_array_cpu *data; + unsigned long flags; + + cpu = raw_smp_processor_id(); + /* Always clear the tracing cpu on stopping the trace */ + if (unlikely(per_cpu(tracing_cpu, cpu))) + per_cpu(tracing_cpu, cpu) = 0; + else + return; + + if (!tracer_enabled || !tracing_is_enabled()) + return; + + data = per_cpu_ptr(tr->trace_buffer.data, cpu); + + if (unlikely(!data) || + !data->critical_start || atomic_read(&data->disabled)) + return; + + atomic_inc(&data->disabled); + + local_save_flags(flags); + __trace_function(tr, ip, parent_ip, flags, preempt_count()); + check_critical_timing(tr, data, parent_ip ? : ip, cpu); + data->critical_start = 0; + atomic_dec(&data->disabled); +} + +/* start and stop critical timings used to for stoppage (in idle) */ +void start_critical_timings(void) +{ + if (preempt_trace() || irq_trace()) + start_critical_timing(CALLER_ADDR0, CALLER_ADDR1); + trace_preemptirqsoff_hist(TRACE_START, 1); +} +EXPORT_SYMBOL_GPL(start_critical_timings); + +void stop_critical_timings(void) +{ + trace_preemptirqsoff_hist(TRACE_STOP, 0); + if (preempt_trace() || irq_trace()) + stop_critical_timing(CALLER_ADDR0, CALLER_ADDR1); +} +EXPORT_SYMBOL_GPL(stop_critical_timings); + +#ifdef CONFIG_IRQSOFF_TRACER +#ifdef CONFIG_PROVE_LOCKING +void time_hardirqs_on(unsigned long a0, unsigned long a1) +{ + trace_preemptirqsoff_hist(IRQS_ON, 0); + if (!preempt_trace() && irq_trace()) + stop_critical_timing(a0, a1); +} + +void time_hardirqs_off(unsigned long a0, unsigned long a1) +{ + if (!preempt_trace() && irq_trace()) + start_critical_timing(a0, a1); + trace_preemptirqsoff_hist(IRQS_OFF, 1); +} + +#else /* !CONFIG_PROVE_LOCKING */ + +/* + * Stubs: + */ + +void trace_softirqs_on(unsigned long ip) +{ +} + +void trace_softirqs_off(unsigned long ip) +{ +} + +inline void print_irqtrace_events(struct task_struct *curr) +{ +} + +/* + * We are only interested in hardirq on/off events: + */ +void trace_hardirqs_on(void) +{ + trace_preemptirqsoff_hist(IRQS_ON, 0); + if (!preempt_trace() && irq_trace()) + stop_critical_timing(CALLER_ADDR0, CALLER_ADDR1); +} +EXPORT_SYMBOL(trace_hardirqs_on); + +void trace_hardirqs_off(void) +{ + if (!preempt_trace() && irq_trace()) + start_critical_timing(CALLER_ADDR0, CALLER_ADDR1); + trace_preemptirqsoff_hist(IRQS_OFF, 1); +} +EXPORT_SYMBOL(trace_hardirqs_off); + +__visible void trace_hardirqs_on_caller(unsigned long caller_addr) +{ + trace_preemptirqsoff_hist(IRQS_ON, 0); + if (!preempt_trace() && irq_trace()) + stop_critical_timing(CALLER_ADDR0, caller_addr); +} +EXPORT_SYMBOL(trace_hardirqs_on_caller); + +__visible void trace_hardirqs_off_caller(unsigned long caller_addr) +{ + if (!preempt_trace() && irq_trace()) + start_critical_timing(CALLER_ADDR0, caller_addr); + trace_preemptirqsoff_hist(IRQS_OFF, 1); +} +EXPORT_SYMBOL(trace_hardirqs_off_caller); + +#endif /* CONFIG_PROVE_LOCKING */ +#endif /* CONFIG_IRQSOFF_TRACER */ + +#ifdef CONFIG_PREEMPT_TRACER +void trace_preempt_on(unsigned long a0, unsigned long a1) +{ + trace_preemptirqsoff_hist(PREEMPT_ON, 0); + if (preempt_trace() && !irq_trace()) + stop_critical_timing(a0, a1); +} + +void trace_preempt_off(unsigned long a0, unsigned long a1) +{ + trace_preemptirqsoff_hist(PREEMPT_ON, 1); + if (preempt_trace() && !irq_trace()) + start_critical_timing(a0, a1); +} +#endif /* CONFIG_PREEMPT_TRACER */ + +static int register_irqsoff_function(struct trace_array *tr, int graph, int set) +{ + int ret; + + /* 'set' is set if TRACE_ITER_FUNCTION is about to be set */ + if (function_enabled || (!set && !(trace_flags & TRACE_ITER_FUNCTION))) + return 0; + + if (graph) + ret = register_ftrace_graph(&irqsoff_graph_return, + &irqsoff_graph_entry); + else + ret = register_ftrace_function(tr->ops); + + if (!ret) + function_enabled = true; + + return ret; +} + +static void unregister_irqsoff_function(struct trace_array *tr, int graph) +{ + if (!function_enabled) + return; + + if (graph) + unregister_ftrace_graph(); + else + unregister_ftrace_function(tr->ops); + + function_enabled = false; +} + +static void irqsoff_function_set(struct trace_array *tr, int set) +{ + if (set) + register_irqsoff_function(tr, is_graph(), 1); + else + unregister_irqsoff_function(tr, is_graph()); +} + +static int irqsoff_flag_changed(struct trace_array *tr, u32 mask, int set) +{ + struct tracer *tracer = tr->current_trace; + + if (mask & TRACE_ITER_FUNCTION) + irqsoff_function_set(tr, set); + + return trace_keep_overwrite(tracer, mask, set); +} + +static int start_irqsoff_tracer(struct trace_array *tr, int graph) +{ + int ret; + + ret = register_irqsoff_function(tr, graph, 0); + + if (!ret && tracing_is_enabled()) + tracer_enabled = 1; + else + tracer_enabled = 0; + + return ret; +} + +static void stop_irqsoff_tracer(struct trace_array *tr, int graph) +{ + tracer_enabled = 0; + + unregister_irqsoff_function(tr, graph); +} + +static bool irqsoff_busy; + +static int __irqsoff_tracer_init(struct trace_array *tr) +{ + if (irqsoff_busy) + return -EBUSY; + + save_flags = trace_flags; + + /* non overwrite screws up the latency tracers */ + set_tracer_flag(tr, TRACE_ITER_OVERWRITE, 1); + set_tracer_flag(tr, TRACE_ITER_LATENCY_FMT, 1); + + tr->max_latency = 0; + irqsoff_trace = tr; + /* make sure that the tracer is visible */ + smp_wmb(); + tracing_reset_online_cpus(&tr->trace_buffer); + + ftrace_init_array_ops(tr, irqsoff_tracer_call); + + /* Only toplevel instance supports graph tracing */ + if (start_irqsoff_tracer(tr, (tr->flags & TRACE_ARRAY_FL_GLOBAL && + is_graph()))) + printk(KERN_ERR "failed to start irqsoff tracer\n"); + + irqsoff_busy = true; + return 0; +} + +static void irqsoff_tracer_reset(struct trace_array *tr) +{ + int lat_flag = save_flags & TRACE_ITER_LATENCY_FMT; + int overwrite_flag = save_flags & TRACE_ITER_OVERWRITE; + + stop_irqsoff_tracer(tr, is_graph()); + + set_tracer_flag(tr, TRACE_ITER_LATENCY_FMT, lat_flag); + set_tracer_flag(tr, TRACE_ITER_OVERWRITE, overwrite_flag); + ftrace_reset_array_ops(tr); + + irqsoff_busy = false; +} + +static void irqsoff_tracer_start(struct trace_array *tr) +{ + tracer_enabled = 1; +} + +static void irqsoff_tracer_stop(struct trace_array *tr) +{ + tracer_enabled = 0; +} + +#ifdef CONFIG_IRQSOFF_TRACER +static int irqsoff_tracer_init(struct trace_array *tr) +{ + trace_type = TRACER_IRQS_OFF; + + return __irqsoff_tracer_init(tr); +} +static struct tracer irqsoff_tracer __read_mostly = +{ + .name = "irqsoff", + .init = irqsoff_tracer_init, + .reset = irqsoff_tracer_reset, + .start = irqsoff_tracer_start, + .stop = irqsoff_tracer_stop, + .print_max = true, + .print_header = irqsoff_print_header, + .print_line = irqsoff_print_line, + .flags = &tracer_flags, + .set_flag = irqsoff_set_flag, + .flag_changed = irqsoff_flag_changed, +#ifdef CONFIG_FTRACE_SELFTEST + .selftest = trace_selftest_startup_irqsoff, +#endif + .open = irqsoff_trace_open, + .close = irqsoff_trace_close, + .allow_instances = true, + .use_max_tr = true, +}; +# define register_irqsoff(trace) register_tracer(&trace) +#else +# define register_irqsoff(trace) do { } while (0) +#endif + +#ifdef CONFIG_PREEMPT_TRACER +static int preemptoff_tracer_init(struct trace_array *tr) +{ + trace_type = TRACER_PREEMPT_OFF; + + return __irqsoff_tracer_init(tr); +} + +static struct tracer preemptoff_tracer __read_mostly = +{ + .name = "preemptoff", + .init = preemptoff_tracer_init, + .reset = irqsoff_tracer_reset, + .start = irqsoff_tracer_start, + .stop = irqsoff_tracer_stop, + .print_max = true, + .print_header = irqsoff_print_header, + .print_line = irqsoff_print_line, + .flags = &tracer_flags, + .set_flag = irqsoff_set_flag, + .flag_changed = irqsoff_flag_changed, +#ifdef CONFIG_FTRACE_SELFTEST + .selftest = trace_selftest_startup_preemptoff, +#endif + .open = irqsoff_trace_open, + .close = irqsoff_trace_close, + .allow_instances = true, + .use_max_tr = true, +}; +# define register_preemptoff(trace) register_tracer(&trace) +#else +# define register_preemptoff(trace) do { } while (0) +#endif + +#if defined(CONFIG_IRQSOFF_TRACER) && \ + defined(CONFIG_PREEMPT_TRACER) + +static int preemptirqsoff_tracer_init(struct trace_array *tr) +{ + trace_type = TRACER_IRQS_OFF | TRACER_PREEMPT_OFF; + + return __irqsoff_tracer_init(tr); +} + +static struct tracer preemptirqsoff_tracer __read_mostly = +{ + .name = "preemptirqsoff", + .init = preemptirqsoff_tracer_init, + .reset = irqsoff_tracer_reset, + .start = irqsoff_tracer_start, + .stop = irqsoff_tracer_stop, + .print_max = true, + .print_header = irqsoff_print_header, + .print_line = irqsoff_print_line, + .flags = &tracer_flags, + .set_flag = irqsoff_set_flag, + .flag_changed = irqsoff_flag_changed, +#ifdef CONFIG_FTRACE_SELFTEST + .selftest = trace_selftest_startup_preemptirqsoff, +#endif + .open = irqsoff_trace_open, + .close = irqsoff_trace_close, + .allow_instances = true, + .use_max_tr = true, +}; + +# define register_preemptirqsoff(trace) register_tracer(&trace) +#else +# define register_preemptirqsoff(trace) do { } while (0) +#endif + +__init static int init_irqsoff_tracer(void) +{ + register_irqsoff(irqsoff_tracer); + register_preemptoff(preemptoff_tracer); + register_preemptirqsoff(preemptirqsoff_tracer); + + return 0; +} +core_initcall(init_irqsoff_tracer); diff --git a/kernel/kernel/trace/trace_kdb.c b/kernel/kernel/trace/trace_kdb.c new file mode 100644 index 000000000..3ccf5c2c1 --- /dev/null +++ b/kernel/kernel/trace/trace_kdb.c @@ -0,0 +1,140 @@ +/* + * kdb helper for dumping the ftrace buffer + * + * Copyright (C) 2010 Jason Wessel + * + * ftrace_dump_buf based on ftrace_dump: + * Copyright (C) 2007-2008 Steven Rostedt + * Copyright (C) 2008 Ingo Molnar + * + */ +#include +#include +#include +#include + +#include "trace.h" +#include "trace_output.h" + +static void ftrace_dump_buf(int skip_lines, long cpu_file) +{ + /* use static because iter can be a bit big for the stack */ + static struct trace_iterator iter; + static struct ring_buffer_iter *buffer_iter[CONFIG_NR_CPUS]; + unsigned int old_userobj; + int cnt = 0, cpu; + + trace_init_global_iter(&iter); + iter.buffer_iter = buffer_iter; + + for_each_tracing_cpu(cpu) { + atomic_inc(&per_cpu_ptr(iter.trace_buffer->data, cpu)->disabled); + } + + old_userobj = trace_flags; + + /* don't look at user memory in panic mode */ + trace_flags &= ~TRACE_ITER_SYM_USEROBJ; + + kdb_printf("Dumping ftrace buffer:\n"); + + /* reset all but tr, trace, and overruns */ + memset(&iter.seq, 0, + sizeof(struct trace_iterator) - + offsetof(struct trace_iterator, seq)); + iter.iter_flags |= TRACE_FILE_LAT_FMT; + iter.pos = -1; + + if (cpu_file == RING_BUFFER_ALL_CPUS) { + for_each_tracing_cpu(cpu) { + iter.buffer_iter[cpu] = + ring_buffer_read_prepare(iter.trace_buffer->buffer, cpu); + ring_buffer_read_start(iter.buffer_iter[cpu]); + tracing_iter_reset(&iter, cpu); + } + } else { + iter.cpu_file = cpu_file; + iter.buffer_iter[cpu_file] = + ring_buffer_read_prepare(iter.trace_buffer->buffer, cpu_file); + ring_buffer_read_start(iter.buffer_iter[cpu_file]); + tracing_iter_reset(&iter, cpu_file); + } + + while (trace_find_next_entry_inc(&iter)) { + if (!cnt) + kdb_printf("---------------------------------\n"); + cnt++; + + if (!skip_lines) { + print_trace_line(&iter); + trace_printk_seq(&iter.seq); + } else { + skip_lines--; + } + + if (KDB_FLAG(CMD_INTERRUPT)) + goto out; + } + + if (!cnt) + kdb_printf(" (ftrace buffer empty)\n"); + else + kdb_printf("---------------------------------\n"); + +out: + trace_flags = old_userobj; + + for_each_tracing_cpu(cpu) { + atomic_dec(&per_cpu_ptr(iter.trace_buffer->data, cpu)->disabled); + } + + for_each_tracing_cpu(cpu) { + if (iter.buffer_iter[cpu]) { + ring_buffer_read_finish(iter.buffer_iter[cpu]); + iter.buffer_iter[cpu] = NULL; + } + } +} + +/* + * kdb_ftdump - Dump the ftrace log buffer + */ +static int kdb_ftdump(int argc, const char **argv) +{ + int skip_lines = 0; + long cpu_file; + char *cp; + + if (argc > 2) + return KDB_ARGCOUNT; + + if (argc) { + skip_lines = simple_strtol(argv[1], &cp, 0); + if (*cp) + skip_lines = 0; + } + + if (argc == 2) { + cpu_file = simple_strtol(argv[2], &cp, 0); + if (*cp || cpu_file >= NR_CPUS || cpu_file < 0 || + !cpu_online(cpu_file)) + return KDB_BADINT; + } else { + cpu_file = RING_BUFFER_ALL_CPUS; + } + + kdb_trap_printk++; + ftrace_dump_buf(skip_lines, cpu_file); + kdb_trap_printk--; + + return 0; +} + +static __init int kdb_ftrace_register(void) +{ + kdb_register_flags("ftdump", kdb_ftdump, "[skip_#lines] [cpu]", + "Dump ftrace log", 0, KDB_ENABLE_ALWAYS_SAFE); + return 0; +} + +late_initcall(kdb_ftrace_register); diff --git a/kernel/kernel/trace/trace_kprobe.c b/kernel/kernel/trace/trace_kprobe.c new file mode 100644 index 000000000..d0ce590f0 --- /dev/null +++ b/kernel/kernel/trace/trace_kprobe.c @@ -0,0 +1,1495 @@ +/* + * Kprobes-based tracing events + * + * Created by Masami Hiramatsu + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + */ + +#include +#include + +#include "trace_probe.h" + +#define KPROBE_EVENT_SYSTEM "kprobes" + +/** + * Kprobe event core functions + */ +struct trace_kprobe { + struct list_head list; + struct kretprobe rp; /* Use rp.kp for kprobe use */ + unsigned long nhit; + const char *symbol; /* symbol name */ + struct trace_probe tp; +}; + +#define SIZEOF_TRACE_KPROBE(n) \ + (offsetof(struct trace_kprobe, tp.args) + \ + (sizeof(struct probe_arg) * (n))) + + +static nokprobe_inline bool trace_kprobe_is_return(struct trace_kprobe *tk) +{ + return tk->rp.handler != NULL; +} + +static nokprobe_inline const char *trace_kprobe_symbol(struct trace_kprobe *tk) +{ + return tk->symbol ? tk->symbol : "unknown"; +} + +static nokprobe_inline unsigned long trace_kprobe_offset(struct trace_kprobe *tk) +{ + return tk->rp.kp.offset; +} + +static nokprobe_inline bool trace_kprobe_has_gone(struct trace_kprobe *tk) +{ + return !!(kprobe_gone(&tk->rp.kp)); +} + +static nokprobe_inline bool trace_kprobe_within_module(struct trace_kprobe *tk, + struct module *mod) +{ + int len = strlen(mod->name); + const char *name = trace_kprobe_symbol(tk); + return strncmp(mod->name, name, len) == 0 && name[len] == ':'; +} + +static nokprobe_inline bool trace_kprobe_is_on_module(struct trace_kprobe *tk) +{ + return !!strchr(trace_kprobe_symbol(tk), ':'); +} + +static int register_kprobe_event(struct trace_kprobe *tk); +static int unregister_kprobe_event(struct trace_kprobe *tk); + +static DEFINE_MUTEX(probe_lock); +static LIST_HEAD(probe_list); + +static int kprobe_dispatcher(struct kprobe *kp, struct pt_regs *regs); +static int kretprobe_dispatcher(struct kretprobe_instance *ri, + struct pt_regs *regs); + +/* Memory fetching by symbol */ +struct symbol_cache { + char *symbol; + long offset; + unsigned long addr; +}; + +unsigned long update_symbol_cache(struct symbol_cache *sc) +{ + sc->addr = (unsigned long)kallsyms_lookup_name(sc->symbol); + + if (sc->addr) + sc->addr += sc->offset; + + return sc->addr; +} + +void free_symbol_cache(struct symbol_cache *sc) +{ + kfree(sc->symbol); + kfree(sc); +} + +struct symbol_cache *alloc_symbol_cache(const char *sym, long offset) +{ + struct symbol_cache *sc; + + if (!sym || strlen(sym) == 0) + return NULL; + + sc = kzalloc(sizeof(struct symbol_cache), GFP_KERNEL); + if (!sc) + return NULL; + + sc->symbol = kstrdup(sym, GFP_KERNEL); + if (!sc->symbol) { + kfree(sc); + return NULL; + } + sc->offset = offset; + update_symbol_cache(sc); + + return sc; +} + +/* + * Kprobes-specific fetch functions + */ +#define DEFINE_FETCH_stack(type) \ +static void FETCH_FUNC_NAME(stack, type)(struct pt_regs *regs, \ + void *offset, void *dest) \ +{ \ + *(type *)dest = (type)regs_get_kernel_stack_nth(regs, \ + (unsigned int)((unsigned long)offset)); \ +} \ +NOKPROBE_SYMBOL(FETCH_FUNC_NAME(stack, type)); + +DEFINE_BASIC_FETCH_FUNCS(stack) +/* No string on the stack entry */ +#define fetch_stack_string NULL +#define fetch_stack_string_size NULL + +#define DEFINE_FETCH_memory(type) \ +static void FETCH_FUNC_NAME(memory, type)(struct pt_regs *regs, \ + void *addr, void *dest) \ +{ \ + type retval; \ + if (probe_kernel_address(addr, retval)) \ + *(type *)dest = 0; \ + else \ + *(type *)dest = retval; \ +} \ +NOKPROBE_SYMBOL(FETCH_FUNC_NAME(memory, type)); + +DEFINE_BASIC_FETCH_FUNCS(memory) +/* + * Fetch a null-terminated string. Caller MUST set *(u32 *)dest with max + * length and relative data location. + */ +static void FETCH_FUNC_NAME(memory, string)(struct pt_regs *regs, + void *addr, void *dest) +{ + long ret; + int maxlen = get_rloc_len(*(u32 *)dest); + u8 *dst = get_rloc_data(dest); + u8 *src = addr; + mm_segment_t old_fs = get_fs(); + + if (!maxlen) + return; + + /* + * Try to get string again, since the string can be changed while + * probing. + */ + set_fs(KERNEL_DS); + pagefault_disable(); + + do + ret = __copy_from_user_inatomic(dst++, src++, 1); + while (dst[-1] && ret == 0 && src - (u8 *)addr < maxlen); + + dst[-1] = '\0'; + pagefault_enable(); + set_fs(old_fs); + + if (ret < 0) { /* Failed to fetch string */ + ((u8 *)get_rloc_data(dest))[0] = '\0'; + *(u32 *)dest = make_data_rloc(0, get_rloc_offs(*(u32 *)dest)); + } else { + *(u32 *)dest = make_data_rloc(src - (u8 *)addr, + get_rloc_offs(*(u32 *)dest)); + } +} +NOKPROBE_SYMBOL(FETCH_FUNC_NAME(memory, string)); + +/* Return the length of string -- including null terminal byte */ +static void FETCH_FUNC_NAME(memory, string_size)(struct pt_regs *regs, + void *addr, void *dest) +{ + mm_segment_t old_fs; + int ret, len = 0; + u8 c; + + old_fs = get_fs(); + set_fs(KERNEL_DS); + pagefault_disable(); + + do { + ret = __copy_from_user_inatomic(&c, (u8 *)addr + len, 1); + len++; + } while (c && ret == 0 && len < MAX_STRING_SIZE); + + pagefault_enable(); + set_fs(old_fs); + + if (ret < 0) /* Failed to check the length */ + *(u32 *)dest = 0; + else + *(u32 *)dest = len; +} +NOKPROBE_SYMBOL(FETCH_FUNC_NAME(memory, string_size)); + +#define DEFINE_FETCH_symbol(type) \ +void FETCH_FUNC_NAME(symbol, type)(struct pt_regs *regs, void *data, void *dest)\ +{ \ + struct symbol_cache *sc = data; \ + if (sc->addr) \ + fetch_memory_##type(regs, (void *)sc->addr, dest); \ + else \ + *(type *)dest = 0; \ +} \ +NOKPROBE_SYMBOL(FETCH_FUNC_NAME(symbol, type)); + +DEFINE_BASIC_FETCH_FUNCS(symbol) +DEFINE_FETCH_symbol(string) +DEFINE_FETCH_symbol(string_size) + +/* kprobes don't support file_offset fetch methods */ +#define fetch_file_offset_u8 NULL +#define fetch_file_offset_u16 NULL +#define fetch_file_offset_u32 NULL +#define fetch_file_offset_u64 NULL +#define fetch_file_offset_string NULL +#define fetch_file_offset_string_size NULL + +/* Fetch type information table */ +static const struct fetch_type kprobes_fetch_type_table[] = { + /* Special types */ + [FETCH_TYPE_STRING] = __ASSIGN_FETCH_TYPE("string", string, string, + sizeof(u32), 1, "__data_loc char[]"), + [FETCH_TYPE_STRSIZE] = __ASSIGN_FETCH_TYPE("string_size", u32, + string_size, sizeof(u32), 0, "u32"), + /* Basic types */ + ASSIGN_FETCH_TYPE(u8, u8, 0), + ASSIGN_FETCH_TYPE(u16, u16, 0), + ASSIGN_FETCH_TYPE(u32, u32, 0), + ASSIGN_FETCH_TYPE(u64, u64, 0), + ASSIGN_FETCH_TYPE(s8, u8, 1), + ASSIGN_FETCH_TYPE(s16, u16, 1), + ASSIGN_FETCH_TYPE(s32, u32, 1), + ASSIGN_FETCH_TYPE(s64, u64, 1), + + ASSIGN_FETCH_TYPE_END +}; + +/* + * Allocate new trace_probe and initialize it (including kprobes). + */ +static struct trace_kprobe *alloc_trace_kprobe(const char *group, + const char *event, + void *addr, + const char *symbol, + unsigned long offs, + int nargs, bool is_return) +{ + struct trace_kprobe *tk; + int ret = -ENOMEM; + + tk = kzalloc(SIZEOF_TRACE_KPROBE(nargs), GFP_KERNEL); + if (!tk) + return ERR_PTR(ret); + + if (symbol) { + tk->symbol = kstrdup(symbol, GFP_KERNEL); + if (!tk->symbol) + goto error; + tk->rp.kp.symbol_name = tk->symbol; + tk->rp.kp.offset = offs; + } else + tk->rp.kp.addr = addr; + + if (is_return) + tk->rp.handler = kretprobe_dispatcher; + else + tk->rp.kp.pre_handler = kprobe_dispatcher; + + if (!event || !is_good_name(event)) { + ret = -EINVAL; + goto error; + } + + tk->tp.call.class = &tk->tp.class; + tk->tp.call.name = kstrdup(event, GFP_KERNEL); + if (!tk->tp.call.name) + goto error; + + if (!group || !is_good_name(group)) { + ret = -EINVAL; + goto error; + } + + tk->tp.class.system = kstrdup(group, GFP_KERNEL); + if (!tk->tp.class.system) + goto error; + + INIT_LIST_HEAD(&tk->list); + INIT_LIST_HEAD(&tk->tp.files); + return tk; +error: + kfree(tk->tp.call.name); + kfree(tk->symbol); + kfree(tk); + return ERR_PTR(ret); +} + +static void free_trace_kprobe(struct trace_kprobe *tk) +{ + int i; + + for (i = 0; i < tk->tp.nr_args; i++) + traceprobe_free_probe_arg(&tk->tp.args[i]); + + kfree(tk->tp.call.class->system); + kfree(tk->tp.call.name); + kfree(tk->symbol); + kfree(tk); +} + +static struct trace_kprobe *find_trace_kprobe(const char *event, + const char *group) +{ + struct trace_kprobe *tk; + + list_for_each_entry(tk, &probe_list, list) + if (strcmp(ftrace_event_name(&tk->tp.call), event) == 0 && + strcmp(tk->tp.call.class->system, group) == 0) + return tk; + return NULL; +} + +/* + * Enable trace_probe + * if the file is NULL, enable "perf" handler, or enable "trace" handler. + */ +static int +enable_trace_kprobe(struct trace_kprobe *tk, struct ftrace_event_file *file) +{ + int ret = 0; + + if (file) { + struct event_file_link *link; + + link = kmalloc(sizeof(*link), GFP_KERNEL); + if (!link) { + ret = -ENOMEM; + goto out; + } + + link->file = file; + list_add_tail_rcu(&link->list, &tk->tp.files); + + tk->tp.flags |= TP_FLAG_TRACE; + } else + tk->tp.flags |= TP_FLAG_PROFILE; + + if (trace_probe_is_registered(&tk->tp) && !trace_kprobe_has_gone(tk)) { + if (trace_kprobe_is_return(tk)) + ret = enable_kretprobe(&tk->rp); + else + ret = enable_kprobe(&tk->rp.kp); + } + out: + return ret; +} + +/* + * Disable trace_probe + * if the file is NULL, disable "perf" handler, or disable "trace" handler. + */ +static int +disable_trace_kprobe(struct trace_kprobe *tk, struct ftrace_event_file *file) +{ + struct event_file_link *link = NULL; + int wait = 0; + int ret = 0; + + if (file) { + link = find_event_file_link(&tk->tp, file); + if (!link) { + ret = -EINVAL; + goto out; + } + + list_del_rcu(&link->list); + wait = 1; + if (!list_empty(&tk->tp.files)) + goto out; + + tk->tp.flags &= ~TP_FLAG_TRACE; + } else + tk->tp.flags &= ~TP_FLAG_PROFILE; + + if (!trace_probe_is_enabled(&tk->tp) && trace_probe_is_registered(&tk->tp)) { + if (trace_kprobe_is_return(tk)) + disable_kretprobe(&tk->rp); + else + disable_kprobe(&tk->rp.kp); + wait = 1; + } + out: + if (wait) { + /* + * Synchronize with kprobe_trace_func/kretprobe_trace_func + * to ensure disabled (all running handlers are finished). + * This is not only for kfree(), but also the caller, + * trace_remove_event_call() supposes it for releasing + * event_call related objects, which will be accessed in + * the kprobe_trace_func/kretprobe_trace_func. + */ + synchronize_sched(); + kfree(link); /* Ignored if link == NULL */ + } + + return ret; +} + +/* Internal register function - just handle k*probes and flags */ +static int __register_trace_kprobe(struct trace_kprobe *tk) +{ + int i, ret; + + if (trace_probe_is_registered(&tk->tp)) + return -EINVAL; + + for (i = 0; i < tk->tp.nr_args; i++) + traceprobe_update_arg(&tk->tp.args[i]); + + /* Set/clear disabled flag according to tp->flag */ + if (trace_probe_is_enabled(&tk->tp)) + tk->rp.kp.flags &= ~KPROBE_FLAG_DISABLED; + else + tk->rp.kp.flags |= KPROBE_FLAG_DISABLED; + + if (trace_kprobe_is_return(tk)) + ret = register_kretprobe(&tk->rp); + else + ret = register_kprobe(&tk->rp.kp); + + if (ret == 0) + tk->tp.flags |= TP_FLAG_REGISTERED; + else { + pr_warning("Could not insert probe at %s+%lu: %d\n", + trace_kprobe_symbol(tk), trace_kprobe_offset(tk), ret); + if (ret == -ENOENT && trace_kprobe_is_on_module(tk)) { + pr_warning("This probe might be able to register after" + "target module is loaded. Continue.\n"); + ret = 0; + } else if (ret == -EILSEQ) { + pr_warning("Probing address(0x%p) is not an " + "instruction boundary.\n", + tk->rp.kp.addr); + ret = -EINVAL; + } + } + + return ret; +} + +/* Internal unregister function - just handle k*probes and flags */ +static void __unregister_trace_kprobe(struct trace_kprobe *tk) +{ + if (trace_probe_is_registered(&tk->tp)) { + if (trace_kprobe_is_return(tk)) + unregister_kretprobe(&tk->rp); + else + unregister_kprobe(&tk->rp.kp); + tk->tp.flags &= ~TP_FLAG_REGISTERED; + /* Cleanup kprobe for reuse */ + if (tk->rp.kp.symbol_name) + tk->rp.kp.addr = NULL; + } +} + +/* Unregister a trace_probe and probe_event: call with locking probe_lock */ +static int unregister_trace_kprobe(struct trace_kprobe *tk) +{ + /* Enabled event can not be unregistered */ + if (trace_probe_is_enabled(&tk->tp)) + return -EBUSY; + + /* Will fail if probe is being used by ftrace or perf */ + if (unregister_kprobe_event(tk)) + return -EBUSY; + + __unregister_trace_kprobe(tk); + list_del(&tk->list); + + return 0; +} + +/* Register a trace_probe and probe_event */ +static int register_trace_kprobe(struct trace_kprobe *tk) +{ + struct trace_kprobe *old_tk; + int ret; + + mutex_lock(&probe_lock); + + /* Delete old (same name) event if exist */ + old_tk = find_trace_kprobe(ftrace_event_name(&tk->tp.call), + tk->tp.call.class->system); + if (old_tk) { + ret = unregister_trace_kprobe(old_tk); + if (ret < 0) + goto end; + free_trace_kprobe(old_tk); + } + + /* Register new event */ + ret = register_kprobe_event(tk); + if (ret) { + pr_warning("Failed to register probe event(%d)\n", ret); + goto end; + } + + /* Register k*probe */ + ret = __register_trace_kprobe(tk); + if (ret < 0) + unregister_kprobe_event(tk); + else + list_add_tail(&tk->list, &probe_list); + +end: + mutex_unlock(&probe_lock); + return ret; +} + +/* Module notifier call back, checking event on the module */ +static int trace_kprobe_module_callback(struct notifier_block *nb, + unsigned long val, void *data) +{ + struct module *mod = data; + struct trace_kprobe *tk; + int ret; + + if (val != MODULE_STATE_COMING) + return NOTIFY_DONE; + + /* Update probes on coming module */ + mutex_lock(&probe_lock); + list_for_each_entry(tk, &probe_list, list) { + if (trace_kprobe_within_module(tk, mod)) { + /* Don't need to check busy - this should have gone. */ + __unregister_trace_kprobe(tk); + ret = __register_trace_kprobe(tk); + if (ret) + pr_warning("Failed to re-register probe %s on" + "%s: %d\n", + ftrace_event_name(&tk->tp.call), + mod->name, ret); + } + } + mutex_unlock(&probe_lock); + + return NOTIFY_DONE; +} + +static struct notifier_block trace_kprobe_module_nb = { + .notifier_call = trace_kprobe_module_callback, + .priority = 1 /* Invoked after kprobe module callback */ +}; + +static int create_trace_kprobe(int argc, char **argv) +{ + /* + * Argument syntax: + * - Add kprobe: p[:[GRP/]EVENT] [MOD:]KSYM[+OFFS]|KADDR [FETCHARGS] + * - Add kretprobe: r[:[GRP/]EVENT] [MOD:]KSYM[+0] [FETCHARGS] + * Fetch args: + * $retval : fetch return value + * $stack : fetch stack address + * $stackN : fetch Nth of stack (N:0-) + * @ADDR : fetch memory at ADDR (ADDR should be in kernel) + * @SYM[+|-offs] : fetch memory at SYM +|- offs (SYM is a data symbol) + * %REG : fetch register REG + * Dereferencing memory fetch: + * +|-offs(ARG) : fetch memory at ARG +|- offs address. + * Alias name of args: + * NAME=FETCHARG : set NAME as alias of FETCHARG. + * Type of args: + * FETCHARG:TYPE : use TYPE instead of unsigned long. + */ + struct trace_kprobe *tk; + int i, ret = 0; + bool is_return = false, is_delete = false; + char *symbol = NULL, *event = NULL, *group = NULL; + char *arg; + unsigned long offset = 0; + void *addr = NULL; + char buf[MAX_EVENT_NAME_LEN]; + + /* argc must be >= 1 */ + if (argv[0][0] == 'p') + is_return = false; + else if (argv[0][0] == 'r') + is_return = true; + else if (argv[0][0] == '-') + is_delete = true; + else { + pr_info("Probe definition must be started with 'p', 'r' or" + " '-'.\n"); + return -EINVAL; + } + + if (argv[0][1] == ':') { + event = &argv[0][2]; + if (strchr(event, '/')) { + group = event; + event = strchr(group, '/') + 1; + event[-1] = '\0'; + if (strlen(group) == 0) { + pr_info("Group name is not specified\n"); + return -EINVAL; + } + } + if (strlen(event) == 0) { + pr_info("Event name is not specified\n"); + return -EINVAL; + } + } + if (!group) + group = KPROBE_EVENT_SYSTEM; + + if (is_delete) { + if (!event) { + pr_info("Delete command needs an event name.\n"); + return -EINVAL; + } + mutex_lock(&probe_lock); + tk = find_trace_kprobe(event, group); + if (!tk) { + mutex_unlock(&probe_lock); + pr_info("Event %s/%s doesn't exist.\n", group, event); + return -ENOENT; + } + /* delete an event */ + ret = unregister_trace_kprobe(tk); + if (ret == 0) + free_trace_kprobe(tk); + mutex_unlock(&probe_lock); + return ret; + } + + if (argc < 2) { + pr_info("Probe point is not specified.\n"); + return -EINVAL; + } + if (isdigit(argv[1][0])) { + if (is_return) { + pr_info("Return probe point must be a symbol.\n"); + return -EINVAL; + } + /* an address specified */ + ret = kstrtoul(&argv[1][0], 0, (unsigned long *)&addr); + if (ret) { + pr_info("Failed to parse address.\n"); + return ret; + } + } else { + /* a symbol specified */ + symbol = argv[1]; + /* TODO: support .init module functions */ + ret = traceprobe_split_symbol_offset(symbol, &offset); + if (ret) { + pr_info("Failed to parse symbol.\n"); + return ret; + } + if (offset && is_return) { + pr_info("Return probe must be used without offset.\n"); + return -EINVAL; + } + } + argc -= 2; argv += 2; + + /* setup a probe */ + if (!event) { + /* Make a new event name */ + if (symbol) + snprintf(buf, MAX_EVENT_NAME_LEN, "%c_%s_%ld", + is_return ? 'r' : 'p', symbol, offset); + else + snprintf(buf, MAX_EVENT_NAME_LEN, "%c_0x%p", + is_return ? 'r' : 'p', addr); + event = buf; + } + tk = alloc_trace_kprobe(group, event, addr, symbol, offset, argc, + is_return); + if (IS_ERR(tk)) { + pr_info("Failed to allocate trace_probe.(%d)\n", + (int)PTR_ERR(tk)); + return PTR_ERR(tk); + } + + /* parse arguments */ + ret = 0; + for (i = 0; i < argc && i < MAX_TRACE_ARGS; i++) { + struct probe_arg *parg = &tk->tp.args[i]; + + /* Increment count for freeing args in error case */ + tk->tp.nr_args++; + + /* Parse argument name */ + arg = strchr(argv[i], '='); + if (arg) { + *arg++ = '\0'; + parg->name = kstrdup(argv[i], GFP_KERNEL); + } else { + arg = argv[i]; + /* If argument name is omitted, set "argN" */ + snprintf(buf, MAX_EVENT_NAME_LEN, "arg%d", i + 1); + parg->name = kstrdup(buf, GFP_KERNEL); + } + + if (!parg->name) { + pr_info("Failed to allocate argument[%d] name.\n", i); + ret = -ENOMEM; + goto error; + } + + if (!is_good_name(parg->name)) { + pr_info("Invalid argument[%d] name: %s\n", + i, parg->name); + ret = -EINVAL; + goto error; + } + + if (traceprobe_conflict_field_name(parg->name, + tk->tp.args, i)) { + pr_info("Argument[%d] name '%s' conflicts with " + "another field.\n", i, argv[i]); + ret = -EINVAL; + goto error; + } + + /* Parse fetch argument */ + ret = traceprobe_parse_probe_arg(arg, &tk->tp.size, parg, + is_return, true, + kprobes_fetch_type_table); + if (ret) { + pr_info("Parse error at argument[%d]. (%d)\n", i, ret); + goto error; + } + } + + ret = register_trace_kprobe(tk); + if (ret) + goto error; + return 0; + +error: + free_trace_kprobe(tk); + return ret; +} + +static int release_all_trace_kprobes(void) +{ + struct trace_kprobe *tk; + int ret = 0; + + mutex_lock(&probe_lock); + /* Ensure no probe is in use. */ + list_for_each_entry(tk, &probe_list, list) + if (trace_probe_is_enabled(&tk->tp)) { + ret = -EBUSY; + goto end; + } + /* TODO: Use batch unregistration */ + while (!list_empty(&probe_list)) { + tk = list_entry(probe_list.next, struct trace_kprobe, list); + ret = unregister_trace_kprobe(tk); + if (ret) + goto end; + free_trace_kprobe(tk); + } + +end: + mutex_unlock(&probe_lock); + + return ret; +} + +/* Probes listing interfaces */ +static void *probes_seq_start(struct seq_file *m, loff_t *pos) +{ + mutex_lock(&probe_lock); + return seq_list_start(&probe_list, *pos); +} + +static void *probes_seq_next(struct seq_file *m, void *v, loff_t *pos) +{ + return seq_list_next(v, &probe_list, pos); +} + +static void probes_seq_stop(struct seq_file *m, void *v) +{ + mutex_unlock(&probe_lock); +} + +static int probes_seq_show(struct seq_file *m, void *v) +{ + struct trace_kprobe *tk = v; + int i; + + seq_putc(m, trace_kprobe_is_return(tk) ? 'r' : 'p'); + seq_printf(m, ":%s/%s", tk->tp.call.class->system, + ftrace_event_name(&tk->tp.call)); + + if (!tk->symbol) + seq_printf(m, " 0x%p", tk->rp.kp.addr); + else if (tk->rp.kp.offset) + seq_printf(m, " %s+%u", trace_kprobe_symbol(tk), + tk->rp.kp.offset); + else + seq_printf(m, " %s", trace_kprobe_symbol(tk)); + + for (i = 0; i < tk->tp.nr_args; i++) + seq_printf(m, " %s=%s", tk->tp.args[i].name, tk->tp.args[i].comm); + seq_putc(m, '\n'); + + return 0; +} + +static const struct seq_operations probes_seq_op = { + .start = probes_seq_start, + .next = probes_seq_next, + .stop = probes_seq_stop, + .show = probes_seq_show +}; + +static int probes_open(struct inode *inode, struct file *file) +{ + int ret; + + if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) { + ret = release_all_trace_kprobes(); + if (ret < 0) + return ret; + } + + return seq_open(file, &probes_seq_op); +} + +static ssize_t probes_write(struct file *file, const char __user *buffer, + size_t count, loff_t *ppos) +{ + return traceprobe_probes_write(file, buffer, count, ppos, + create_trace_kprobe); +} + +static const struct file_operations kprobe_events_ops = { + .owner = THIS_MODULE, + .open = probes_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, + .write = probes_write, +}; + +/* Probes profiling interfaces */ +static int probes_profile_seq_show(struct seq_file *m, void *v) +{ + struct trace_kprobe *tk = v; + + seq_printf(m, " %-44s %15lu %15lu\n", + ftrace_event_name(&tk->tp.call), tk->nhit, + tk->rp.kp.nmissed); + + return 0; +} + +static const struct seq_operations profile_seq_op = { + .start = probes_seq_start, + .next = probes_seq_next, + .stop = probes_seq_stop, + .show = probes_profile_seq_show +}; + +static int profile_open(struct inode *inode, struct file *file) +{ + return seq_open(file, &profile_seq_op); +} + +static const struct file_operations kprobe_profile_ops = { + .owner = THIS_MODULE, + .open = profile_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, +}; + +/* Kprobe handler */ +static nokprobe_inline void +__kprobe_trace_func(struct trace_kprobe *tk, struct pt_regs *regs, + struct ftrace_event_file *ftrace_file) +{ + struct kprobe_trace_entry_head *entry; + struct ring_buffer_event *event; + struct ring_buffer *buffer; + int size, dsize, pc; + unsigned long irq_flags; + struct ftrace_event_call *call = &tk->tp.call; + + WARN_ON(call != ftrace_file->event_call); + + if (ftrace_trigger_soft_disabled(ftrace_file)) + return; + + local_save_flags(irq_flags); + pc = preempt_count(); + + dsize = __get_data_size(&tk->tp, regs); + size = sizeof(*entry) + tk->tp.size + dsize; + + event = trace_event_buffer_lock_reserve(&buffer, ftrace_file, + call->event.type, + size, irq_flags, pc); + if (!event) + return; + + entry = ring_buffer_event_data(event); + entry->ip = (unsigned long)tk->rp.kp.addr; + store_trace_args(sizeof(*entry), &tk->tp, regs, (u8 *)&entry[1], dsize); + + event_trigger_unlock_commit_regs(ftrace_file, buffer, event, + entry, irq_flags, pc, regs); +} + +static void +kprobe_trace_func(struct trace_kprobe *tk, struct pt_regs *regs) +{ + struct event_file_link *link; + + list_for_each_entry_rcu(link, &tk->tp.files, list) + __kprobe_trace_func(tk, regs, link->file); +} +NOKPROBE_SYMBOL(kprobe_trace_func); + +/* Kretprobe handler */ +static nokprobe_inline void +__kretprobe_trace_func(struct trace_kprobe *tk, struct kretprobe_instance *ri, + struct pt_regs *regs, + struct ftrace_event_file *ftrace_file) +{ + struct kretprobe_trace_entry_head *entry; + struct ring_buffer_event *event; + struct ring_buffer *buffer; + int size, pc, dsize; + unsigned long irq_flags; + struct ftrace_event_call *call = &tk->tp.call; + + WARN_ON(call != ftrace_file->event_call); + + if (ftrace_trigger_soft_disabled(ftrace_file)) + return; + + local_save_flags(irq_flags); + pc = preempt_count(); + + dsize = __get_data_size(&tk->tp, regs); + size = sizeof(*entry) + tk->tp.size + dsize; + + event = trace_event_buffer_lock_reserve(&buffer, ftrace_file, + call->event.type, + size, irq_flags, pc); + if (!event) + return; + + entry = ring_buffer_event_data(event); + entry->func = (unsigned long)tk->rp.kp.addr; + entry->ret_ip = (unsigned long)ri->ret_addr; + store_trace_args(sizeof(*entry), &tk->tp, regs, (u8 *)&entry[1], dsize); + + event_trigger_unlock_commit_regs(ftrace_file, buffer, event, + entry, irq_flags, pc, regs); +} + +static void +kretprobe_trace_func(struct trace_kprobe *tk, struct kretprobe_instance *ri, + struct pt_regs *regs) +{ + struct event_file_link *link; + + list_for_each_entry_rcu(link, &tk->tp.files, list) + __kretprobe_trace_func(tk, ri, regs, link->file); +} +NOKPROBE_SYMBOL(kretprobe_trace_func); + +/* Event entry printers */ +static enum print_line_t +print_kprobe_event(struct trace_iterator *iter, int flags, + struct trace_event *event) +{ + struct kprobe_trace_entry_head *field; + struct trace_seq *s = &iter->seq; + struct trace_probe *tp; + u8 *data; + int i; + + field = (struct kprobe_trace_entry_head *)iter->ent; + tp = container_of(event, struct trace_probe, call.event); + + trace_seq_printf(s, "%s: (", ftrace_event_name(&tp->call)); + + if (!seq_print_ip_sym(s, field->ip, flags | TRACE_ITER_SYM_OFFSET)) + goto out; + + trace_seq_putc(s, ')'); + + data = (u8 *)&field[1]; + for (i = 0; i < tp->nr_args; i++) + if (!tp->args[i].type->print(s, tp->args[i].name, + data + tp->args[i].offset, field)) + goto out; + + trace_seq_putc(s, '\n'); + out: + return trace_handle_return(s); +} + +static enum print_line_t +print_kretprobe_event(struct trace_iterator *iter, int flags, + struct trace_event *event) +{ + struct kretprobe_trace_entry_head *field; + struct trace_seq *s = &iter->seq; + struct trace_probe *tp; + u8 *data; + int i; + + field = (struct kretprobe_trace_entry_head *)iter->ent; + tp = container_of(event, struct trace_probe, call.event); + + trace_seq_printf(s, "%s: (", ftrace_event_name(&tp->call)); + + if (!seq_print_ip_sym(s, field->ret_ip, flags | TRACE_ITER_SYM_OFFSET)) + goto out; + + trace_seq_puts(s, " <- "); + + if (!seq_print_ip_sym(s, field->func, flags & ~TRACE_ITER_SYM_OFFSET)) + goto out; + + trace_seq_putc(s, ')'); + + data = (u8 *)&field[1]; + for (i = 0; i < tp->nr_args; i++) + if (!tp->args[i].type->print(s, tp->args[i].name, + data + tp->args[i].offset, field)) + goto out; + + trace_seq_putc(s, '\n'); + + out: + return trace_handle_return(s); +} + + +static int kprobe_event_define_fields(struct ftrace_event_call *event_call) +{ + int ret, i; + struct kprobe_trace_entry_head field; + struct trace_kprobe *tk = (struct trace_kprobe *)event_call->data; + + DEFINE_FIELD(unsigned long, ip, FIELD_STRING_IP, 0); + /* Set argument names as fields */ + for (i = 0; i < tk->tp.nr_args; i++) { + struct probe_arg *parg = &tk->tp.args[i]; + + ret = trace_define_field(event_call, parg->type->fmttype, + parg->name, + sizeof(field) + parg->offset, + parg->type->size, + parg->type->is_signed, + FILTER_OTHER); + if (ret) + return ret; + } + return 0; +} + +static int kretprobe_event_define_fields(struct ftrace_event_call *event_call) +{ + int ret, i; + struct kretprobe_trace_entry_head field; + struct trace_kprobe *tk = (struct trace_kprobe *)event_call->data; + + DEFINE_FIELD(unsigned long, func, FIELD_STRING_FUNC, 0); + DEFINE_FIELD(unsigned long, ret_ip, FIELD_STRING_RETIP, 0); + /* Set argument names as fields */ + for (i = 0; i < tk->tp.nr_args; i++) { + struct probe_arg *parg = &tk->tp.args[i]; + + ret = trace_define_field(event_call, parg->type->fmttype, + parg->name, + sizeof(field) + parg->offset, + parg->type->size, + parg->type->is_signed, + FILTER_OTHER); + if (ret) + return ret; + } + return 0; +} + +#ifdef CONFIG_PERF_EVENTS + +/* Kprobe profile handler */ +static void +kprobe_perf_func(struct trace_kprobe *tk, struct pt_regs *regs) +{ + struct ftrace_event_call *call = &tk->tp.call; + struct bpf_prog *prog = call->prog; + struct kprobe_trace_entry_head *entry; + struct hlist_head *head; + int size, __size, dsize; + int rctx; + + if (prog && !trace_call_bpf(prog, regs)) + return; + + head = this_cpu_ptr(call->perf_events); + if (hlist_empty(head)) + return; + + dsize = __get_data_size(&tk->tp, regs); + __size = sizeof(*entry) + tk->tp.size + dsize; + size = ALIGN(__size + sizeof(u32), sizeof(u64)); + size -= sizeof(u32); + + entry = perf_trace_buf_prepare(size, call->event.type, NULL, &rctx); + if (!entry) + return; + + entry->ip = (unsigned long)tk->rp.kp.addr; + memset(&entry[1], 0, dsize); + store_trace_args(sizeof(*entry), &tk->tp, regs, (u8 *)&entry[1], dsize); + perf_trace_buf_submit(entry, size, rctx, 0, 1, regs, head, NULL); +} +NOKPROBE_SYMBOL(kprobe_perf_func); + +/* Kretprobe profile handler */ +static void +kretprobe_perf_func(struct trace_kprobe *tk, struct kretprobe_instance *ri, + struct pt_regs *regs) +{ + struct ftrace_event_call *call = &tk->tp.call; + struct bpf_prog *prog = call->prog; + struct kretprobe_trace_entry_head *entry; + struct hlist_head *head; + int size, __size, dsize; + int rctx; + + if (prog && !trace_call_bpf(prog, regs)) + return; + + head = this_cpu_ptr(call->perf_events); + if (hlist_empty(head)) + return; + + dsize = __get_data_size(&tk->tp, regs); + __size = sizeof(*entry) + tk->tp.size + dsize; + size = ALIGN(__size + sizeof(u32), sizeof(u64)); + size -= sizeof(u32); + + entry = perf_trace_buf_prepare(size, call->event.type, NULL, &rctx); + if (!entry) + return; + + entry->func = (unsigned long)tk->rp.kp.addr; + entry->ret_ip = (unsigned long)ri->ret_addr; + store_trace_args(sizeof(*entry), &tk->tp, regs, (u8 *)&entry[1], dsize); + perf_trace_buf_submit(entry, size, rctx, 0, 1, regs, head, NULL); +} +NOKPROBE_SYMBOL(kretprobe_perf_func); +#endif /* CONFIG_PERF_EVENTS */ + +/* + * called by perf_trace_init() or __ftrace_set_clr_event() under event_mutex. + * + * kprobe_trace_self_tests_init() does enable_trace_probe/disable_trace_probe + * lockless, but we can't race with this __init function. + */ +static int kprobe_register(struct ftrace_event_call *event, + enum trace_reg type, void *data) +{ + struct trace_kprobe *tk = (struct trace_kprobe *)event->data; + struct ftrace_event_file *file = data; + + switch (type) { + case TRACE_REG_REGISTER: + return enable_trace_kprobe(tk, file); + case TRACE_REG_UNREGISTER: + return disable_trace_kprobe(tk, file); + +#ifdef CONFIG_PERF_EVENTS + case TRACE_REG_PERF_REGISTER: + return enable_trace_kprobe(tk, NULL); + case TRACE_REG_PERF_UNREGISTER: + return disable_trace_kprobe(tk, NULL); + case TRACE_REG_PERF_OPEN: + case TRACE_REG_PERF_CLOSE: + case TRACE_REG_PERF_ADD: + case TRACE_REG_PERF_DEL: + return 0; +#endif + } + return 0; +} + +static int kprobe_dispatcher(struct kprobe *kp, struct pt_regs *regs) +{ + struct trace_kprobe *tk = container_of(kp, struct trace_kprobe, rp.kp); + + tk->nhit++; + + if (tk->tp.flags & TP_FLAG_TRACE) + kprobe_trace_func(tk, regs); +#ifdef CONFIG_PERF_EVENTS + if (tk->tp.flags & TP_FLAG_PROFILE) + kprobe_perf_func(tk, regs); +#endif + return 0; /* We don't tweek kernel, so just return 0 */ +} +NOKPROBE_SYMBOL(kprobe_dispatcher); + +static int +kretprobe_dispatcher(struct kretprobe_instance *ri, struct pt_regs *regs) +{ + struct trace_kprobe *tk = container_of(ri->rp, struct trace_kprobe, rp); + + tk->nhit++; + + if (tk->tp.flags & TP_FLAG_TRACE) + kretprobe_trace_func(tk, ri, regs); +#ifdef CONFIG_PERF_EVENTS + if (tk->tp.flags & TP_FLAG_PROFILE) + kretprobe_perf_func(tk, ri, regs); +#endif + return 0; /* We don't tweek kernel, so just return 0 */ +} +NOKPROBE_SYMBOL(kretprobe_dispatcher); + +static struct trace_event_functions kretprobe_funcs = { + .trace = print_kretprobe_event +}; + +static struct trace_event_functions kprobe_funcs = { + .trace = print_kprobe_event +}; + +static int register_kprobe_event(struct trace_kprobe *tk) +{ + struct ftrace_event_call *call = &tk->tp.call; + int ret; + + /* Initialize ftrace_event_call */ + INIT_LIST_HEAD(&call->class->fields); + if (trace_kprobe_is_return(tk)) { + call->event.funcs = &kretprobe_funcs; + call->class->define_fields = kretprobe_event_define_fields; + } else { + call->event.funcs = &kprobe_funcs; + call->class->define_fields = kprobe_event_define_fields; + } + if (set_print_fmt(&tk->tp, trace_kprobe_is_return(tk)) < 0) + return -ENOMEM; + ret = register_ftrace_event(&call->event); + if (!ret) { + kfree(call->print_fmt); + return -ENODEV; + } + call->flags = TRACE_EVENT_FL_KPROBE; + call->class->reg = kprobe_register; + call->data = tk; + ret = trace_add_event_call(call); + if (ret) { + pr_info("Failed to register kprobe event: %s\n", + ftrace_event_name(call)); + kfree(call->print_fmt); + unregister_ftrace_event(&call->event); + } + return ret; +} + +static int unregister_kprobe_event(struct trace_kprobe *tk) +{ + int ret; + + /* tp->event is unregistered in trace_remove_event_call() */ + ret = trace_remove_event_call(&tk->tp.call); + if (!ret) + kfree(tk->tp.call.print_fmt); + return ret; +} + +/* Make a tracefs interface for controlling probe points */ +static __init int init_kprobe_trace(void) +{ + struct dentry *d_tracer; + struct dentry *entry; + + if (register_module_notifier(&trace_kprobe_module_nb)) + return -EINVAL; + + d_tracer = tracing_init_dentry(); + if (IS_ERR(d_tracer)) + return 0; + + entry = tracefs_create_file("kprobe_events", 0644, d_tracer, + NULL, &kprobe_events_ops); + + /* Event list interface */ + if (!entry) + pr_warning("Could not create tracefs " + "'kprobe_events' entry\n"); + + /* Profile interface */ + entry = tracefs_create_file("kprobe_profile", 0444, d_tracer, + NULL, &kprobe_profile_ops); + + if (!entry) + pr_warning("Could not create tracefs " + "'kprobe_profile' entry\n"); + return 0; +} +fs_initcall(init_kprobe_trace); + + +#ifdef CONFIG_FTRACE_STARTUP_TEST + +/* + * The "__used" keeps gcc from removing the function symbol + * from the kallsyms table. + */ +static __used int kprobe_trace_selftest_target(int a1, int a2, int a3, + int a4, int a5, int a6) +{ + return a1 + a2 + a3 + a4 + a5 + a6; +} + +static struct ftrace_event_file * +find_trace_probe_file(struct trace_kprobe *tk, struct trace_array *tr) +{ + struct ftrace_event_file *file; + + list_for_each_entry(file, &tr->events, list) + if (file->event_call == &tk->tp.call) + return file; + + return NULL; +} + +/* + * Nobody but us can call enable_trace_kprobe/disable_trace_kprobe at this + * stage, we can do this lockless. + */ +static __init int kprobe_trace_self_tests_init(void) +{ + int ret, warn = 0; + int (*target)(int, int, int, int, int, int); + struct trace_kprobe *tk; + struct ftrace_event_file *file; + + if (tracing_is_disabled()) + return -ENODEV; + + target = kprobe_trace_selftest_target; + + pr_info("Testing kprobe tracing: "); + + ret = traceprobe_command("p:testprobe kprobe_trace_selftest_target " + "$stack $stack0 +0($stack)", + create_trace_kprobe); + if (WARN_ON_ONCE(ret)) { + pr_warn("error on probing function entry.\n"); + warn++; + } else { + /* Enable trace point */ + tk = find_trace_kprobe("testprobe", KPROBE_EVENT_SYSTEM); + if (WARN_ON_ONCE(tk == NULL)) { + pr_warn("error on getting new probe.\n"); + warn++; + } else { + file = find_trace_probe_file(tk, top_trace_array()); + if (WARN_ON_ONCE(file == NULL)) { + pr_warn("error on getting probe file.\n"); + warn++; + } else + enable_trace_kprobe(tk, file); + } + } + + ret = traceprobe_command("r:testprobe2 kprobe_trace_selftest_target " + "$retval", create_trace_kprobe); + if (WARN_ON_ONCE(ret)) { + pr_warn("error on probing function return.\n"); + warn++; + } else { + /* Enable trace point */ + tk = find_trace_kprobe("testprobe2", KPROBE_EVENT_SYSTEM); + if (WARN_ON_ONCE(tk == NULL)) { + pr_warn("error on getting 2nd new probe.\n"); + warn++; + } else { + file = find_trace_probe_file(tk, top_trace_array()); + if (WARN_ON_ONCE(file == NULL)) { + pr_warn("error on getting probe file.\n"); + warn++; + } else + enable_trace_kprobe(tk, file); + } + } + + if (warn) + goto end; + + ret = target(1, 2, 3, 4, 5, 6); + + /* Disable trace points before removing it */ + tk = find_trace_kprobe("testprobe", KPROBE_EVENT_SYSTEM); + if (WARN_ON_ONCE(tk == NULL)) { + pr_warn("error on getting test probe.\n"); + warn++; + } else { + file = find_trace_probe_file(tk, top_trace_array()); + if (WARN_ON_ONCE(file == NULL)) { + pr_warn("error on getting probe file.\n"); + warn++; + } else + disable_trace_kprobe(tk, file); + } + + tk = find_trace_kprobe("testprobe2", KPROBE_EVENT_SYSTEM); + if (WARN_ON_ONCE(tk == NULL)) { + pr_warn("error on getting 2nd test probe.\n"); + warn++; + } else { + file = find_trace_probe_file(tk, top_trace_array()); + if (WARN_ON_ONCE(file == NULL)) { + pr_warn("error on getting probe file.\n"); + warn++; + } else + disable_trace_kprobe(tk, file); + } + + ret = traceprobe_command("-:testprobe", create_trace_kprobe); + if (WARN_ON_ONCE(ret)) { + pr_warn("error on deleting a probe.\n"); + warn++; + } + + ret = traceprobe_command("-:testprobe2", create_trace_kprobe); + if (WARN_ON_ONCE(ret)) { + pr_warn("error on deleting a probe.\n"); + warn++; + } + +end: + release_all_trace_kprobes(); + if (warn) + pr_cont("NG: Some tests are failed. Please check them.\n"); + else + pr_cont("OK\n"); + return 0; +} + +late_initcall(kprobe_trace_self_tests_init); + +#endif diff --git a/kernel/kernel/trace/trace_mmiotrace.c b/kernel/kernel/trace/trace_mmiotrace.c new file mode 100644 index 000000000..7a9ba62e9 --- /dev/null +++ b/kernel/kernel/trace/trace_mmiotrace.c @@ -0,0 +1,364 @@ +/* + * Memory mapped I/O tracing + * + * Copyright (C) 2008 Pekka Paalanen + */ + +#define DEBUG 1 + +#include +#include +#include +#include +#include + +#include + +#include "trace.h" +#include "trace_output.h" + +struct header_iter { + struct pci_dev *dev; +}; + +static struct trace_array *mmio_trace_array; +static bool overrun_detected; +static unsigned long prev_overruns; +static atomic_t dropped_count; + +static void mmio_reset_data(struct trace_array *tr) +{ + overrun_detected = false; + prev_overruns = 0; + + tracing_reset_online_cpus(&tr->trace_buffer); +} + +static int mmio_trace_init(struct trace_array *tr) +{ + pr_debug("in %s\n", __func__); + mmio_trace_array = tr; + + mmio_reset_data(tr); + enable_mmiotrace(); + return 0; +} + +static void mmio_trace_reset(struct trace_array *tr) +{ + pr_debug("in %s\n", __func__); + + disable_mmiotrace(); + mmio_reset_data(tr); + mmio_trace_array = NULL; +} + +static void mmio_trace_start(struct trace_array *tr) +{ + pr_debug("in %s\n", __func__); + mmio_reset_data(tr); +} + +static void mmio_print_pcidev(struct trace_seq *s, const struct pci_dev *dev) +{ + int i; + resource_size_t start, end; + const struct pci_driver *drv = pci_dev_driver(dev); + + trace_seq_printf(s, "PCIDEV %02x%02x %04x%04x %x", + dev->bus->number, dev->devfn, + dev->vendor, dev->device, dev->irq); + /* + * XXX: is pci_resource_to_user() appropriate, since we are + * supposed to interpret the __ioremap() phys_addr argument based on + * these printed values? + */ + for (i = 0; i < 7; i++) { + pci_resource_to_user(dev, i, &dev->resource[i], &start, &end); + trace_seq_printf(s, " %llx", + (unsigned long long)(start | + (dev->resource[i].flags & PCI_REGION_FLAG_MASK))); + } + for (i = 0; i < 7; i++) { + pci_resource_to_user(dev, i, &dev->resource[i], &start, &end); + trace_seq_printf(s, " %llx", + dev->resource[i].start < dev->resource[i].end ? + (unsigned long long)(end - start) + 1 : 0); + } + if (drv) + trace_seq_printf(s, " %s\n", drv->name); + else + trace_seq_puts(s, " \n"); +} + +static void destroy_header_iter(struct header_iter *hiter) +{ + if (!hiter) + return; + pci_dev_put(hiter->dev); + kfree(hiter); +} + +static void mmio_pipe_open(struct trace_iterator *iter) +{ + struct header_iter *hiter; + struct trace_seq *s = &iter->seq; + + trace_seq_puts(s, "VERSION 20070824\n"); + + hiter = kzalloc(sizeof(*hiter), GFP_KERNEL); + if (!hiter) + return; + + hiter->dev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, NULL); + iter->private = hiter; +} + +/* XXX: This is not called when the pipe is closed! */ +static void mmio_close(struct trace_iterator *iter) +{ + struct header_iter *hiter = iter->private; + destroy_header_iter(hiter); + iter->private = NULL; +} + +static unsigned long count_overruns(struct trace_iterator *iter) +{ + unsigned long cnt = atomic_xchg(&dropped_count, 0); + unsigned long over = ring_buffer_overruns(iter->trace_buffer->buffer); + + if (over > prev_overruns) + cnt += over - prev_overruns; + prev_overruns = over; + return cnt; +} + +static ssize_t mmio_read(struct trace_iterator *iter, struct file *filp, + char __user *ubuf, size_t cnt, loff_t *ppos) +{ + ssize_t ret; + struct header_iter *hiter = iter->private; + struct trace_seq *s = &iter->seq; + unsigned long n; + + n = count_overruns(iter); + if (n) { + /* XXX: This is later than where events were lost. */ + trace_seq_printf(s, "MARK 0.000000 Lost %lu events.\n", n); + if (!overrun_detected) + pr_warning("mmiotrace has lost events.\n"); + overrun_detected = true; + goto print_out; + } + + if (!hiter) + return 0; + + mmio_print_pcidev(s, hiter->dev); + hiter->dev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, hiter->dev); + + if (!hiter->dev) { + destroy_header_iter(hiter); + iter->private = NULL; + } + +print_out: + ret = trace_seq_to_user(s, ubuf, cnt); + return (ret == -EBUSY) ? 0 : ret; +} + +static enum print_line_t mmio_print_rw(struct trace_iterator *iter) +{ + struct trace_entry *entry = iter->ent; + struct trace_mmiotrace_rw *field; + struct mmiotrace_rw *rw; + struct trace_seq *s = &iter->seq; + unsigned long long t = ns2usecs(iter->ts); + unsigned long usec_rem = do_div(t, USEC_PER_SEC); + unsigned secs = (unsigned long)t; + + trace_assign_type(field, entry); + rw = &field->rw; + + switch (rw->opcode) { + case MMIO_READ: + trace_seq_printf(s, + "R %d %u.%06lu %d 0x%llx 0x%lx 0x%lx %d\n", + rw->width, secs, usec_rem, rw->map_id, + (unsigned long long)rw->phys, + rw->value, rw->pc, 0); + break; + case MMIO_WRITE: + trace_seq_printf(s, + "W %d %u.%06lu %d 0x%llx 0x%lx 0x%lx %d\n", + rw->width, secs, usec_rem, rw->map_id, + (unsigned long long)rw->phys, + rw->value, rw->pc, 0); + break; + case MMIO_UNKNOWN_OP: + trace_seq_printf(s, + "UNKNOWN %u.%06lu %d 0x%llx %02lx,%02lx," + "%02lx 0x%lx %d\n", + secs, usec_rem, rw->map_id, + (unsigned long long)rw->phys, + (rw->value >> 16) & 0xff, (rw->value >> 8) & 0xff, + (rw->value >> 0) & 0xff, rw->pc, 0); + break; + default: + trace_seq_puts(s, "rw what?\n"); + break; + } + + return trace_handle_return(s); +} + +static enum print_line_t mmio_print_map(struct trace_iterator *iter) +{ + struct trace_entry *entry = iter->ent; + struct trace_mmiotrace_map *field; + struct mmiotrace_map *m; + struct trace_seq *s = &iter->seq; + unsigned long long t = ns2usecs(iter->ts); + unsigned long usec_rem = do_div(t, USEC_PER_SEC); + unsigned secs = (unsigned long)t; + + trace_assign_type(field, entry); + m = &field->map; + + switch (m->opcode) { + case MMIO_PROBE: + trace_seq_printf(s, + "MAP %u.%06lu %d 0x%llx 0x%lx 0x%lx 0x%lx %d\n", + secs, usec_rem, m->map_id, + (unsigned long long)m->phys, m->virt, m->len, + 0UL, 0); + break; + case MMIO_UNPROBE: + trace_seq_printf(s, + "UNMAP %u.%06lu %d 0x%lx %d\n", + secs, usec_rem, m->map_id, 0UL, 0); + break; + default: + trace_seq_puts(s, "map what?\n"); + break; + } + + return trace_handle_return(s); +} + +static enum print_line_t mmio_print_mark(struct trace_iterator *iter) +{ + struct trace_entry *entry = iter->ent; + struct print_entry *print = (struct print_entry *)entry; + const char *msg = print->buf; + struct trace_seq *s = &iter->seq; + unsigned long long t = ns2usecs(iter->ts); + unsigned long usec_rem = do_div(t, USEC_PER_SEC); + unsigned secs = (unsigned long)t; + + /* The trailing newline must be in the message. */ + trace_seq_printf(s, "MARK %u.%06lu %s", secs, usec_rem, msg); + + return trace_handle_return(s); +} + +static enum print_line_t mmio_print_line(struct trace_iterator *iter) +{ + switch (iter->ent->type) { + case TRACE_MMIO_RW: + return mmio_print_rw(iter); + case TRACE_MMIO_MAP: + return mmio_print_map(iter); + case TRACE_PRINT: + return mmio_print_mark(iter); + default: + return TRACE_TYPE_HANDLED; /* ignore unknown entries */ + } +} + +static struct tracer mmio_tracer __read_mostly = +{ + .name = "mmiotrace", + .init = mmio_trace_init, + .reset = mmio_trace_reset, + .start = mmio_trace_start, + .pipe_open = mmio_pipe_open, + .close = mmio_close, + .read = mmio_read, + .print_line = mmio_print_line, +}; + +__init static int init_mmio_trace(void) +{ + return register_tracer(&mmio_tracer); +} +device_initcall(init_mmio_trace); + +static void __trace_mmiotrace_rw(struct trace_array *tr, + struct trace_array_cpu *data, + struct mmiotrace_rw *rw) +{ + struct ftrace_event_call *call = &event_mmiotrace_rw; + struct ring_buffer *buffer = tr->trace_buffer.buffer; + struct ring_buffer_event *event; + struct trace_mmiotrace_rw *entry; + int pc = preempt_count(); + + event = trace_buffer_lock_reserve(buffer, TRACE_MMIO_RW, + sizeof(*entry), 0, pc); + if (!event) { + atomic_inc(&dropped_count); + return; + } + entry = ring_buffer_event_data(event); + entry->rw = *rw; + + if (!call_filter_check_discard(call, entry, buffer, event)) + trace_buffer_unlock_commit(buffer, event, 0, pc); +} + +void mmio_trace_rw(struct mmiotrace_rw *rw) +{ + struct trace_array *tr = mmio_trace_array; + struct trace_array_cpu *data = per_cpu_ptr(tr->trace_buffer.data, smp_processor_id()); + __trace_mmiotrace_rw(tr, data, rw); +} + +static void __trace_mmiotrace_map(struct trace_array *tr, + struct trace_array_cpu *data, + struct mmiotrace_map *map) +{ + struct ftrace_event_call *call = &event_mmiotrace_map; + struct ring_buffer *buffer = tr->trace_buffer.buffer; + struct ring_buffer_event *event; + struct trace_mmiotrace_map *entry; + int pc = preempt_count(); + + event = trace_buffer_lock_reserve(buffer, TRACE_MMIO_MAP, + sizeof(*entry), 0, pc); + if (!event) { + atomic_inc(&dropped_count); + return; + } + entry = ring_buffer_event_data(event); + entry->map = *map; + + if (!call_filter_check_discard(call, entry, buffer, event)) + trace_buffer_unlock_commit(buffer, event, 0, pc); +} + +void mmio_trace_mapping(struct mmiotrace_map *map) +{ + struct trace_array *tr = mmio_trace_array; + struct trace_array_cpu *data; + + preempt_disable(); + data = per_cpu_ptr(tr->trace_buffer.data, smp_processor_id()); + __trace_mmiotrace_map(tr, data, map); + preempt_enable(); +} + +int mmio_trace_printk(const char *fmt, va_list args) +{ + return trace_vprintk(0, fmt, args); +} diff --git a/kernel/kernel/trace/trace_nop.c b/kernel/kernel/trace/trace_nop.c new file mode 100644 index 000000000..8bb207147 --- /dev/null +++ b/kernel/kernel/trace/trace_nop.c @@ -0,0 +1,99 @@ +/* + * nop tracer + * + * Copyright (C) 2008 Steven Noonan + * + */ + +#include +#include + +#include "trace.h" + +/* Our two options */ +enum { + TRACE_NOP_OPT_ACCEPT = 0x1, + TRACE_NOP_OPT_REFUSE = 0x2 +}; + +/* Options for the tracer (see trace_options file) */ +static struct tracer_opt nop_opts[] = { + /* Option that will be accepted by set_flag callback */ + { TRACER_OPT(test_nop_accept, TRACE_NOP_OPT_ACCEPT) }, + /* Option that will be refused by set_flag callback */ + { TRACER_OPT(test_nop_refuse, TRACE_NOP_OPT_REFUSE) }, + { } /* Always set a last empty entry */ +}; + +static struct tracer_flags nop_flags = { + /* You can check your flags value here when you want. */ + .val = 0, /* By default: all flags disabled */ + .opts = nop_opts +}; + +static struct trace_array *ctx_trace; + +static void start_nop_trace(struct trace_array *tr) +{ + /* Nothing to do! */ +} + +static void stop_nop_trace(struct trace_array *tr) +{ + /* Nothing to do! */ +} + +static int nop_trace_init(struct trace_array *tr) +{ + ctx_trace = tr; + start_nop_trace(tr); + return 0; +} + +static void nop_trace_reset(struct trace_array *tr) +{ + stop_nop_trace(tr); +} + +/* It only serves as a signal handler and a callback to + * accept or refuse tthe setting of a flag. + * If you don't implement it, then the flag setting will be + * automatically accepted. + */ +static int nop_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set) +{ + /* + * Note that you don't need to update nop_flags.val yourself. + * The tracing Api will do it automatically if you return 0 + */ + if (bit == TRACE_NOP_OPT_ACCEPT) { + printk(KERN_DEBUG "nop_test_accept flag set to %d: we accept." + " Now cat trace_options to see the result\n", + set); + return 0; + } + + if (bit == TRACE_NOP_OPT_REFUSE) { + printk(KERN_DEBUG "nop_test_refuse flag set to %d: we refuse." + "Now cat trace_options to see the result\n", + set); + return -EINVAL; + } + + return 0; +} + + +struct tracer nop_trace __read_mostly = +{ + .name = "nop", + .init = nop_trace_init, + .reset = nop_trace_reset, +#ifdef CONFIG_FTRACE_SELFTEST + .selftest = trace_selftest_startup_nop, +#endif + .flags = &nop_flags, + .set_flag = nop_set_flag, + .allow_instances = true, +}; + diff --git a/kernel/kernel/trace/trace_output.c b/kernel/kernel/trace/trace_output.c new file mode 100644 index 000000000..c86bed272 --- /dev/null +++ b/kernel/kernel/trace/trace_output.c @@ -0,0 +1,1270 @@ +/* + * trace_output.c + * + * Copyright (C) 2008 Red Hat Inc, Steven Rostedt + * + */ + +#include +#include +#include + +#include "trace_output.h" + +/* must be a power of 2 */ +#define EVENT_HASHSIZE 128 + +DECLARE_RWSEM(trace_event_sem); + +static struct hlist_head event_hash[EVENT_HASHSIZE] __read_mostly; + +static int next_event_type = __TRACE_LAST_TYPE + 1; + +enum print_line_t trace_print_bputs_msg_only(struct trace_iterator *iter) +{ + struct trace_seq *s = &iter->seq; + struct trace_entry *entry = iter->ent; + struct bputs_entry *field; + + trace_assign_type(field, entry); + + trace_seq_puts(s, field->str); + + return trace_handle_return(s); +} + +enum print_line_t trace_print_bprintk_msg_only(struct trace_iterator *iter) +{ + struct trace_seq *s = &iter->seq; + struct trace_entry *entry = iter->ent; + struct bprint_entry *field; + + trace_assign_type(field, entry); + + trace_seq_bprintf(s, field->fmt, field->buf); + + return trace_handle_return(s); +} + +enum print_line_t trace_print_printk_msg_only(struct trace_iterator *iter) +{ + struct trace_seq *s = &iter->seq; + struct trace_entry *entry = iter->ent; + struct print_entry *field; + + trace_assign_type(field, entry); + + trace_seq_puts(s, field->buf); + + return trace_handle_return(s); +} + +const char * +ftrace_print_flags_seq(struct trace_seq *p, const char *delim, + unsigned long flags, + const struct trace_print_flags *flag_array) +{ + unsigned long mask; + const char *str; + const char *ret = trace_seq_buffer_ptr(p); + int i, first = 1; + + for (i = 0; flag_array[i].name && flags; i++) { + + mask = flag_array[i].mask; + if ((flags & mask) != mask) + continue; + + str = flag_array[i].name; + flags &= ~mask; + if (!first && delim) + trace_seq_puts(p, delim); + else + first = 0; + trace_seq_puts(p, str); + } + + /* check for left over flags */ + if (flags) { + if (!first && delim) + trace_seq_puts(p, delim); + trace_seq_printf(p, "0x%lx", flags); + } + + trace_seq_putc(p, 0); + + return ret; +} +EXPORT_SYMBOL(ftrace_print_flags_seq); + +const char * +ftrace_print_symbols_seq(struct trace_seq *p, unsigned long val, + const struct trace_print_flags *symbol_array) +{ + int i; + const char *ret = trace_seq_buffer_ptr(p); + + for (i = 0; symbol_array[i].name; i++) { + + if (val != symbol_array[i].mask) + continue; + + trace_seq_puts(p, symbol_array[i].name); + break; + } + + if (ret == (const char *)(trace_seq_buffer_ptr(p))) + trace_seq_printf(p, "0x%lx", val); + + trace_seq_putc(p, 0); + + return ret; +} +EXPORT_SYMBOL(ftrace_print_symbols_seq); + +#if BITS_PER_LONG == 32 +const char * +ftrace_print_symbols_seq_u64(struct trace_seq *p, unsigned long long val, + const struct trace_print_flags_u64 *symbol_array) +{ + int i; + const char *ret = trace_seq_buffer_ptr(p); + + for (i = 0; symbol_array[i].name; i++) { + + if (val != symbol_array[i].mask) + continue; + + trace_seq_puts(p, symbol_array[i].name); + break; + } + + if (ret == (const char *)(trace_seq_buffer_ptr(p))) + trace_seq_printf(p, "0x%llx", val); + + trace_seq_putc(p, 0); + + return ret; +} +EXPORT_SYMBOL(ftrace_print_symbols_seq_u64); +#endif + +const char * +ftrace_print_bitmask_seq(struct trace_seq *p, void *bitmask_ptr, + unsigned int bitmask_size) +{ + const char *ret = trace_seq_buffer_ptr(p); + + trace_seq_bitmask(p, bitmask_ptr, bitmask_size * 8); + trace_seq_putc(p, 0); + + return ret; +} +EXPORT_SYMBOL_GPL(ftrace_print_bitmask_seq); + +const char * +ftrace_print_hex_seq(struct trace_seq *p, const unsigned char *buf, int buf_len) +{ + int i; + const char *ret = trace_seq_buffer_ptr(p); + + for (i = 0; i < buf_len; i++) + trace_seq_printf(p, "%s%2.2x", i == 0 ? "" : " ", buf[i]); + + trace_seq_putc(p, 0); + + return ret; +} +EXPORT_SYMBOL(ftrace_print_hex_seq); + +const char * +ftrace_print_array_seq(struct trace_seq *p, const void *buf, int count, + size_t el_size) +{ + const char *ret = trace_seq_buffer_ptr(p); + const char *prefix = ""; + void *ptr = (void *)buf; + size_t buf_len = count * el_size; + + trace_seq_putc(p, '{'); + + while (ptr < buf + buf_len) { + switch (el_size) { + case 1: + trace_seq_printf(p, "%s0x%x", prefix, + *(u8 *)ptr); + break; + case 2: + trace_seq_printf(p, "%s0x%x", prefix, + *(u16 *)ptr); + break; + case 4: + trace_seq_printf(p, "%s0x%x", prefix, + *(u32 *)ptr); + break; + case 8: + trace_seq_printf(p, "%s0x%llx", prefix, + *(u64 *)ptr); + break; + default: + trace_seq_printf(p, "BAD SIZE:%zu 0x%x", el_size, + *(u8 *)ptr); + el_size = 1; + } + prefix = ","; + ptr += el_size; + } + + trace_seq_putc(p, '}'); + trace_seq_putc(p, 0); + + return ret; +} +EXPORT_SYMBOL(ftrace_print_array_seq); + +int ftrace_raw_output_prep(struct trace_iterator *iter, + struct trace_event *trace_event) +{ + struct ftrace_event_call *event; + struct trace_seq *s = &iter->seq; + struct trace_seq *p = &iter->tmp_seq; + struct trace_entry *entry; + + event = container_of(trace_event, struct ftrace_event_call, event); + entry = iter->ent; + + if (entry->type != event->event.type) { + WARN_ON_ONCE(1); + return TRACE_TYPE_UNHANDLED; + } + + trace_seq_init(p); + trace_seq_printf(s, "%s: ", ftrace_event_name(event)); + + return trace_handle_return(s); +} +EXPORT_SYMBOL(ftrace_raw_output_prep); + +static int ftrace_output_raw(struct trace_iterator *iter, char *name, + char *fmt, va_list ap) +{ + struct trace_seq *s = &iter->seq; + + trace_seq_printf(s, "%s: ", name); + trace_seq_vprintf(s, fmt, ap); + + return trace_handle_return(s); +} + +int ftrace_output_call(struct trace_iterator *iter, char *name, char *fmt, ...) +{ + va_list ap; + int ret; + + va_start(ap, fmt); + ret = ftrace_output_raw(iter, name, fmt, ap); + va_end(ap); + + return ret; +} +EXPORT_SYMBOL_GPL(ftrace_output_call); + +#ifdef CONFIG_KRETPROBES +static inline const char *kretprobed(const char *name) +{ + static const char tramp_name[] = "kretprobe_trampoline"; + int size = sizeof(tramp_name); + + if (strncmp(tramp_name, name, size) == 0) + return "[unknown/kretprobe'd]"; + return name; +} +#else +static inline const char *kretprobed(const char *name) +{ + return name; +} +#endif /* CONFIG_KRETPROBES */ + +static void +seq_print_sym_short(struct trace_seq *s, const char *fmt, unsigned long address) +{ +#ifdef CONFIG_KALLSYMS + char str[KSYM_SYMBOL_LEN]; + const char *name; + + kallsyms_lookup(address, NULL, NULL, NULL, str); + + name = kretprobed(str); + + trace_seq_printf(s, fmt, name); +#endif +} + +static void +seq_print_sym_offset(struct trace_seq *s, const char *fmt, + unsigned long address) +{ +#ifdef CONFIG_KALLSYMS + char str[KSYM_SYMBOL_LEN]; + const char *name; + + sprint_symbol(str, address); + name = kretprobed(str); + + trace_seq_printf(s, fmt, name); +#endif +} + +#ifndef CONFIG_64BIT +# define IP_FMT "%08lx" +#else +# define IP_FMT "%016lx" +#endif + +int seq_print_user_ip(struct trace_seq *s, struct mm_struct *mm, + unsigned long ip, unsigned long sym_flags) +{ + struct file *file = NULL; + unsigned long vmstart = 0; + int ret = 1; + + if (s->full) + return 0; + + if (mm) { + const struct vm_area_struct *vma; + + down_read(&mm->mmap_sem); + vma = find_vma(mm, ip); + if (vma) { + file = vma->vm_file; + vmstart = vma->vm_start; + } + if (file) { + ret = trace_seq_path(s, &file->f_path); + if (ret) + trace_seq_printf(s, "[+0x%lx]", + ip - vmstart); + } + up_read(&mm->mmap_sem); + } + if (ret && ((sym_flags & TRACE_ITER_SYM_ADDR) || !file)) + trace_seq_printf(s, " <" IP_FMT ">", ip); + return !trace_seq_has_overflowed(s); +} + +int +seq_print_userip_objs(const struct userstack_entry *entry, struct trace_seq *s, + unsigned long sym_flags) +{ + struct mm_struct *mm = NULL; + unsigned int i; + + if (trace_flags & TRACE_ITER_SYM_USEROBJ) { + struct task_struct *task; + /* + * we do the lookup on the thread group leader, + * since individual threads might have already quit! + */ + rcu_read_lock(); + task = find_task_by_vpid(entry->tgid); + if (task) + mm = get_task_mm(task); + rcu_read_unlock(); + } + + for (i = 0; i < FTRACE_STACK_ENTRIES; i++) { + unsigned long ip = entry->caller[i]; + + if (ip == ULONG_MAX || trace_seq_has_overflowed(s)) + break; + + trace_seq_puts(s, " => "); + + if (!ip) { + trace_seq_puts(s, "??"); + trace_seq_putc(s, '\n'); + continue; + } + + seq_print_user_ip(s, mm, ip, sym_flags); + trace_seq_putc(s, '\n'); + } + + if (mm) + mmput(mm); + + return !trace_seq_has_overflowed(s); +} + +int +seq_print_ip_sym(struct trace_seq *s, unsigned long ip, unsigned long sym_flags) +{ + if (!ip) { + trace_seq_putc(s, '0'); + goto out; + } + + if (sym_flags & TRACE_ITER_SYM_OFFSET) + seq_print_sym_offset(s, "%s", ip); + else + seq_print_sym_short(s, "%s", ip); + + if (sym_flags & TRACE_ITER_SYM_ADDR) + trace_seq_printf(s, " <" IP_FMT ">", ip); + + out: + return !trace_seq_has_overflowed(s); +} + +/** + * trace_print_lat_fmt - print the irq, preempt and lockdep fields + * @s: trace seq struct to write to + * @entry: The trace entry field from the ring buffer + * + * Prints the generic fields of irqs off, in hard or softirq, preempt + * count. + */ +int trace_print_lat_fmt(struct trace_seq *s, struct trace_entry *entry) +{ + char hardsoft_irq; + char need_resched; + char need_resched_lazy; + char irqs_off; + int hardirq; + int softirq; + + hardirq = entry->flags & TRACE_FLAG_HARDIRQ; + softirq = entry->flags & TRACE_FLAG_SOFTIRQ; + + irqs_off = + (entry->flags & TRACE_FLAG_IRQS_OFF) ? 'd' : + (entry->flags & TRACE_FLAG_IRQS_NOSUPPORT) ? 'X' : + '.'; + + switch (entry->flags & (TRACE_FLAG_NEED_RESCHED | + TRACE_FLAG_PREEMPT_RESCHED)) { + case TRACE_FLAG_NEED_RESCHED | TRACE_FLAG_PREEMPT_RESCHED: + need_resched = 'N'; + break; + case TRACE_FLAG_NEED_RESCHED: + need_resched = 'n'; + break; + case TRACE_FLAG_PREEMPT_RESCHED: + need_resched = 'p'; + break; + default: + need_resched = '.'; + break; + } + need_resched_lazy = + (entry->flags & TRACE_FLAG_NEED_RESCHED_LAZY) ? 'L' : '.'; + + hardsoft_irq = + (hardirq && softirq) ? 'H' : + hardirq ? 'h' : + softirq ? 's' : + '.'; + + trace_seq_printf(s, "%c%c%c%c", + irqs_off, need_resched, need_resched_lazy, + hardsoft_irq); + + if (entry->preempt_count) + trace_seq_printf(s, "%x", entry->preempt_count); + else + trace_seq_putc(s, '.'); + + if (entry->preempt_lazy_count) + trace_seq_printf(s, "%x", entry->preempt_lazy_count); + else + trace_seq_putc(s, '.'); + + if (entry->migrate_disable) + trace_seq_printf(s, "%x", entry->migrate_disable); + else + trace_seq_putc(s, '.'); + + return !trace_seq_has_overflowed(s); +} + +static int +lat_print_generic(struct trace_seq *s, struct trace_entry *entry, int cpu) +{ + char comm[TASK_COMM_LEN]; + + trace_find_cmdline(entry->pid, comm); + + trace_seq_printf(s, "%8.8s-%-5d %3d", + comm, entry->pid, cpu); + + return trace_print_lat_fmt(s, entry); +} + +#undef MARK +#define MARK(v, s) {.val = v, .sym = s} +/* trace overhead mark */ +static const struct trace_mark { + unsigned long long val; /* unit: nsec */ + char sym; +} mark[] = { + MARK(1000000000ULL , '$'), /* 1 sec */ + MARK(1000000ULL , '#'), /* 1000 usecs */ + MARK(100000ULL , '!'), /* 100 usecs */ + MARK(10000ULL , '+'), /* 10 usecs */ +}; +#undef MARK + +char trace_find_mark(unsigned long long d) +{ + int i; + int size = ARRAY_SIZE(mark); + + for (i = 0; i < size; i++) { + if (d >= mark[i].val) + break; + } + + return (i == size) ? ' ' : mark[i].sym; +} + +static int +lat_print_timestamp(struct trace_iterator *iter, u64 next_ts) +{ + unsigned long verbose = trace_flags & TRACE_ITER_VERBOSE; + unsigned long in_ns = iter->iter_flags & TRACE_FILE_TIME_IN_NS; + unsigned long long abs_ts = iter->ts - iter->trace_buffer->time_start; + unsigned long long rel_ts = next_ts - iter->ts; + struct trace_seq *s = &iter->seq; + + if (in_ns) { + abs_ts = ns2usecs(abs_ts); + rel_ts = ns2usecs(rel_ts); + } + + if (verbose && in_ns) { + unsigned long abs_usec = do_div(abs_ts, USEC_PER_MSEC); + unsigned long abs_msec = (unsigned long)abs_ts; + unsigned long rel_usec = do_div(rel_ts, USEC_PER_MSEC); + unsigned long rel_msec = (unsigned long)rel_ts; + + trace_seq_printf( + s, "[%08llx] %ld.%03ldms (+%ld.%03ldms): ", + ns2usecs(iter->ts), + abs_msec, abs_usec, + rel_msec, rel_usec); + + } else if (verbose && !in_ns) { + trace_seq_printf( + s, "[%016llx] %lld (+%lld): ", + iter->ts, abs_ts, rel_ts); + + } else if (!verbose && in_ns) { + trace_seq_printf( + s, " %4lldus%c: ", + abs_ts, + trace_find_mark(rel_ts * NSEC_PER_USEC)); + + } else { /* !verbose && !in_ns */ + trace_seq_printf(s, " %4lld: ", abs_ts); + } + + return !trace_seq_has_overflowed(s); +} + +int trace_print_context(struct trace_iterator *iter) +{ + struct trace_seq *s = &iter->seq; + struct trace_entry *entry = iter->ent; + unsigned long long t; + unsigned long secs, usec_rem; + char comm[TASK_COMM_LEN]; + + trace_find_cmdline(entry->pid, comm); + + trace_seq_printf(s, "%16s-%-5d [%03d] ", + comm, entry->pid, iter->cpu); + + if (trace_flags & TRACE_ITER_IRQ_INFO) + trace_print_lat_fmt(s, entry); + + if (iter->iter_flags & TRACE_FILE_TIME_IN_NS) { + t = ns2usecs(iter->ts); + usec_rem = do_div(t, USEC_PER_SEC); + secs = (unsigned long)t; + trace_seq_printf(s, " %5lu.%06lu: ", secs, usec_rem); + } else + trace_seq_printf(s, " %12llu: ", iter->ts); + + return !trace_seq_has_overflowed(s); +} + +int trace_print_lat_context(struct trace_iterator *iter) +{ + u64 next_ts; + /* trace_find_next_entry will reset ent_size */ + int ent_size = iter->ent_size; + struct trace_seq *s = &iter->seq; + struct trace_entry *entry = iter->ent, + *next_entry = trace_find_next_entry(iter, NULL, + &next_ts); + unsigned long verbose = (trace_flags & TRACE_ITER_VERBOSE); + + /* Restore the original ent_size */ + iter->ent_size = ent_size; + + if (!next_entry) + next_ts = iter->ts; + + if (verbose) { + char comm[TASK_COMM_LEN]; + + trace_find_cmdline(entry->pid, comm); + + trace_seq_printf( + s, "%16s %5d %3d %d %08x %08lx ", + comm, entry->pid, iter->cpu, entry->flags, + entry->preempt_count, iter->idx); + } else { + lat_print_generic(s, entry, iter->cpu); + } + + lat_print_timestamp(iter, next_ts); + + return !trace_seq_has_overflowed(s); +} + +static const char state_to_char[] = TASK_STATE_TO_CHAR_STR; + +static int task_state_char(unsigned long state) +{ + int bit = state ? __ffs(state) + 1 : 0; + + return bit < sizeof(state_to_char) - 1 ? state_to_char[bit] : '?'; +} + +/** + * ftrace_find_event - find a registered event + * @type: the type of event to look for + * + * Returns an event of type @type otherwise NULL + * Called with trace_event_read_lock() held. + */ +struct trace_event *ftrace_find_event(int type) +{ + struct trace_event *event; + unsigned key; + + key = type & (EVENT_HASHSIZE - 1); + + hlist_for_each_entry(event, &event_hash[key], node) { + if (event->type == type) + return event; + } + + return NULL; +} + +static LIST_HEAD(ftrace_event_list); + +static int trace_search_list(struct list_head **list) +{ + struct trace_event *e; + int last = __TRACE_LAST_TYPE; + + if (list_empty(&ftrace_event_list)) { + *list = &ftrace_event_list; + return last + 1; + } + + /* + * We used up all possible max events, + * lets see if somebody freed one. + */ + list_for_each_entry(e, &ftrace_event_list, list) { + if (e->type != last + 1) + break; + last++; + } + + /* Did we used up all 65 thousand events??? */ + if ((last + 1) > FTRACE_MAX_EVENT) + return 0; + + *list = &e->list; + return last + 1; +} + +void trace_event_read_lock(void) +{ + down_read(&trace_event_sem); +} + +void trace_event_read_unlock(void) +{ + up_read(&trace_event_sem); +} + +/** + * register_ftrace_event - register output for an event type + * @event: the event type to register + * + * Event types are stored in a hash and this hash is used to + * find a way to print an event. If the @event->type is set + * then it will use that type, otherwise it will assign a + * type to use. + * + * If you assign your own type, please make sure it is added + * to the trace_type enum in trace.h, to avoid collisions + * with the dynamic types. + * + * Returns the event type number or zero on error. + */ +int register_ftrace_event(struct trace_event *event) +{ + unsigned key; + int ret = 0; + + down_write(&trace_event_sem); + + if (WARN_ON(!event)) + goto out; + + if (WARN_ON(!event->funcs)) + goto out; + + INIT_LIST_HEAD(&event->list); + + if (!event->type) { + struct list_head *list = NULL; + + if (next_event_type > FTRACE_MAX_EVENT) { + + event->type = trace_search_list(&list); + if (!event->type) + goto out; + + } else { + + event->type = next_event_type++; + list = &ftrace_event_list; + } + + if (WARN_ON(ftrace_find_event(event->type))) + goto out; + + list_add_tail(&event->list, list); + + } else if (event->type > __TRACE_LAST_TYPE) { + printk(KERN_WARNING "Need to add type to trace.h\n"); + WARN_ON(1); + goto out; + } else { + /* Is this event already used */ + if (ftrace_find_event(event->type)) + goto out; + } + + if (event->funcs->trace == NULL) + event->funcs->trace = trace_nop_print; + if (event->funcs->raw == NULL) + event->funcs->raw = trace_nop_print; + if (event->funcs->hex == NULL) + event->funcs->hex = trace_nop_print; + if (event->funcs->binary == NULL) + event->funcs->binary = trace_nop_print; + + key = event->type & (EVENT_HASHSIZE - 1); + + hlist_add_head(&event->node, &event_hash[key]); + + ret = event->type; + out: + up_write(&trace_event_sem); + + return ret; +} +EXPORT_SYMBOL_GPL(register_ftrace_event); + +/* + * Used by module code with the trace_event_sem held for write. + */ +int __unregister_ftrace_event(struct trace_event *event) +{ + hlist_del(&event->node); + list_del(&event->list); + return 0; +} + +/** + * unregister_ftrace_event - remove a no longer used event + * @event: the event to remove + */ +int unregister_ftrace_event(struct trace_event *event) +{ + down_write(&trace_event_sem); + __unregister_ftrace_event(event); + up_write(&trace_event_sem); + + return 0; +} +EXPORT_SYMBOL_GPL(unregister_ftrace_event); + +/* + * Standard events + */ + +enum print_line_t trace_nop_print(struct trace_iterator *iter, int flags, + struct trace_event *event) +{ + trace_seq_printf(&iter->seq, "type: %d\n", iter->ent->type); + + return trace_handle_return(&iter->seq); +} + +/* TRACE_FN */ +static enum print_line_t trace_fn_trace(struct trace_iterator *iter, int flags, + struct trace_event *event) +{ + struct ftrace_entry *field; + struct trace_seq *s = &iter->seq; + + trace_assign_type(field, iter->ent); + + seq_print_ip_sym(s, field->ip, flags); + + if ((flags & TRACE_ITER_PRINT_PARENT) && field->parent_ip) { + trace_seq_puts(s, " <-"); + seq_print_ip_sym(s, field->parent_ip, flags); + } + + trace_seq_putc(s, '\n'); + + return trace_handle_return(s); +} + +static enum print_line_t trace_fn_raw(struct trace_iterator *iter, int flags, + struct trace_event *event) +{ + struct ftrace_entry *field; + + trace_assign_type(field, iter->ent); + + trace_seq_printf(&iter->seq, "%lx %lx\n", + field->ip, + field->parent_ip); + + return trace_handle_return(&iter->seq); +} + +static enum print_line_t trace_fn_hex(struct trace_iterator *iter, int flags, + struct trace_event *event) +{ + struct ftrace_entry *field; + struct trace_seq *s = &iter->seq; + + trace_assign_type(field, iter->ent); + + SEQ_PUT_HEX_FIELD(s, field->ip); + SEQ_PUT_HEX_FIELD(s, field->parent_ip); + + return trace_handle_return(s); +} + +static enum print_line_t trace_fn_bin(struct trace_iterator *iter, int flags, + struct trace_event *event) +{ + struct ftrace_entry *field; + struct trace_seq *s = &iter->seq; + + trace_assign_type(field, iter->ent); + + SEQ_PUT_FIELD(s, field->ip); + SEQ_PUT_FIELD(s, field->parent_ip); + + return trace_handle_return(s); +} + +static struct trace_event_functions trace_fn_funcs = { + .trace = trace_fn_trace, + .raw = trace_fn_raw, + .hex = trace_fn_hex, + .binary = trace_fn_bin, +}; + +static struct trace_event trace_fn_event = { + .type = TRACE_FN, + .funcs = &trace_fn_funcs, +}; + +/* TRACE_CTX an TRACE_WAKE */ +static enum print_line_t trace_ctxwake_print(struct trace_iterator *iter, + char *delim) +{ + struct ctx_switch_entry *field; + char comm[TASK_COMM_LEN]; + int S, T; + + + trace_assign_type(field, iter->ent); + + T = task_state_char(field->next_state); + S = task_state_char(field->prev_state); + trace_find_cmdline(field->next_pid, comm); + trace_seq_printf(&iter->seq, + " %5d:%3d:%c %s [%03d] %5d:%3d:%c %s\n", + field->prev_pid, + field->prev_prio, + S, delim, + field->next_cpu, + field->next_pid, + field->next_prio, + T, comm); + + return trace_handle_return(&iter->seq); +} + +static enum print_line_t trace_ctx_print(struct trace_iterator *iter, int flags, + struct trace_event *event) +{ + return trace_ctxwake_print(iter, "==>"); +} + +static enum print_line_t trace_wake_print(struct trace_iterator *iter, + int flags, struct trace_event *event) +{ + return trace_ctxwake_print(iter, " +"); +} + +static int trace_ctxwake_raw(struct trace_iterator *iter, char S) +{ + struct ctx_switch_entry *field; + int T; + + trace_assign_type(field, iter->ent); + + if (!S) + S = task_state_char(field->prev_state); + T = task_state_char(field->next_state); + trace_seq_printf(&iter->seq, "%d %d %c %d %d %d %c\n", + field->prev_pid, + field->prev_prio, + S, + field->next_cpu, + field->next_pid, + field->next_prio, + T); + + return trace_handle_return(&iter->seq); +} + +static enum print_line_t trace_ctx_raw(struct trace_iterator *iter, int flags, + struct trace_event *event) +{ + return trace_ctxwake_raw(iter, 0); +} + +static enum print_line_t trace_wake_raw(struct trace_iterator *iter, int flags, + struct trace_event *event) +{ + return trace_ctxwake_raw(iter, '+'); +} + + +static int trace_ctxwake_hex(struct trace_iterator *iter, char S) +{ + struct ctx_switch_entry *field; + struct trace_seq *s = &iter->seq; + int T; + + trace_assign_type(field, iter->ent); + + if (!S) + S = task_state_char(field->prev_state); + T = task_state_char(field->next_state); + + SEQ_PUT_HEX_FIELD(s, field->prev_pid); + SEQ_PUT_HEX_FIELD(s, field->prev_prio); + SEQ_PUT_HEX_FIELD(s, S); + SEQ_PUT_HEX_FIELD(s, field->next_cpu); + SEQ_PUT_HEX_FIELD(s, field->next_pid); + SEQ_PUT_HEX_FIELD(s, field->next_prio); + SEQ_PUT_HEX_FIELD(s, T); + + return trace_handle_return(s); +} + +static enum print_line_t trace_ctx_hex(struct trace_iterator *iter, int flags, + struct trace_event *event) +{ + return trace_ctxwake_hex(iter, 0); +} + +static enum print_line_t trace_wake_hex(struct trace_iterator *iter, int flags, + struct trace_event *event) +{ + return trace_ctxwake_hex(iter, '+'); +} + +static enum print_line_t trace_ctxwake_bin(struct trace_iterator *iter, + int flags, struct trace_event *event) +{ + struct ctx_switch_entry *field; + struct trace_seq *s = &iter->seq; + + trace_assign_type(field, iter->ent); + + SEQ_PUT_FIELD(s, field->prev_pid); + SEQ_PUT_FIELD(s, field->prev_prio); + SEQ_PUT_FIELD(s, field->prev_state); + SEQ_PUT_FIELD(s, field->next_cpu); + SEQ_PUT_FIELD(s, field->next_pid); + SEQ_PUT_FIELD(s, field->next_prio); + SEQ_PUT_FIELD(s, field->next_state); + + return trace_handle_return(s); +} + +static struct trace_event_functions trace_ctx_funcs = { + .trace = trace_ctx_print, + .raw = trace_ctx_raw, + .hex = trace_ctx_hex, + .binary = trace_ctxwake_bin, +}; + +static struct trace_event trace_ctx_event = { + .type = TRACE_CTX, + .funcs = &trace_ctx_funcs, +}; + +static struct trace_event_functions trace_wake_funcs = { + .trace = trace_wake_print, + .raw = trace_wake_raw, + .hex = trace_wake_hex, + .binary = trace_ctxwake_bin, +}; + +static struct trace_event trace_wake_event = { + .type = TRACE_WAKE, + .funcs = &trace_wake_funcs, +}; + +/* TRACE_STACK */ + +static enum print_line_t trace_stack_print(struct trace_iterator *iter, + int flags, struct trace_event *event) +{ + struct stack_entry *field; + struct trace_seq *s = &iter->seq; + unsigned long *p; + unsigned long *end; + + trace_assign_type(field, iter->ent); + end = (unsigned long *)((long)iter->ent + iter->ent_size); + + trace_seq_puts(s, "\n"); + + for (p = field->caller; p && *p != ULONG_MAX && p < end; p++) { + + if (trace_seq_has_overflowed(s)) + break; + + trace_seq_puts(s, " => "); + seq_print_ip_sym(s, *p, flags); + trace_seq_putc(s, '\n'); + } + + return trace_handle_return(s); +} + +static struct trace_event_functions trace_stack_funcs = { + .trace = trace_stack_print, +}; + +static struct trace_event trace_stack_event = { + .type = TRACE_STACK, + .funcs = &trace_stack_funcs, +}; + +/* TRACE_USER_STACK */ +static enum print_line_t trace_user_stack_print(struct trace_iterator *iter, + int flags, struct trace_event *event) +{ + struct userstack_entry *field; + struct trace_seq *s = &iter->seq; + + trace_assign_type(field, iter->ent); + + trace_seq_puts(s, "\n"); + seq_print_userip_objs(field, s, flags); + + return trace_handle_return(s); +} + +static struct trace_event_functions trace_user_stack_funcs = { + .trace = trace_user_stack_print, +}; + +static struct trace_event trace_user_stack_event = { + .type = TRACE_USER_STACK, + .funcs = &trace_user_stack_funcs, +}; + +/* TRACE_BPUTS */ +static enum print_line_t +trace_bputs_print(struct trace_iterator *iter, int flags, + struct trace_event *event) +{ + struct trace_entry *entry = iter->ent; + struct trace_seq *s = &iter->seq; + struct bputs_entry *field; + + trace_assign_type(field, entry); + + seq_print_ip_sym(s, field->ip, flags); + trace_seq_puts(s, ": "); + trace_seq_puts(s, field->str); + + return trace_handle_return(s); +} + + +static enum print_line_t +trace_bputs_raw(struct trace_iterator *iter, int flags, + struct trace_event *event) +{ + struct bputs_entry *field; + struct trace_seq *s = &iter->seq; + + trace_assign_type(field, iter->ent); + + trace_seq_printf(s, ": %lx : ", field->ip); + trace_seq_puts(s, field->str); + + return trace_handle_return(s); +} + +static struct trace_event_functions trace_bputs_funcs = { + .trace = trace_bputs_print, + .raw = trace_bputs_raw, +}; + +static struct trace_event trace_bputs_event = { + .type = TRACE_BPUTS, + .funcs = &trace_bputs_funcs, +}; + +/* TRACE_BPRINT */ +static enum print_line_t +trace_bprint_print(struct trace_iterator *iter, int flags, + struct trace_event *event) +{ + struct trace_entry *entry = iter->ent; + struct trace_seq *s = &iter->seq; + struct bprint_entry *field; + + trace_assign_type(field, entry); + + seq_print_ip_sym(s, field->ip, flags); + trace_seq_puts(s, ": "); + trace_seq_bprintf(s, field->fmt, field->buf); + + return trace_handle_return(s); +} + + +static enum print_line_t +trace_bprint_raw(struct trace_iterator *iter, int flags, + struct trace_event *event) +{ + struct bprint_entry *field; + struct trace_seq *s = &iter->seq; + + trace_assign_type(field, iter->ent); + + trace_seq_printf(s, ": %lx : ", field->ip); + trace_seq_bprintf(s, field->fmt, field->buf); + + return trace_handle_return(s); +} + +static struct trace_event_functions trace_bprint_funcs = { + .trace = trace_bprint_print, + .raw = trace_bprint_raw, +}; + +static struct trace_event trace_bprint_event = { + .type = TRACE_BPRINT, + .funcs = &trace_bprint_funcs, +}; + +/* TRACE_PRINT */ +static enum print_line_t trace_print_print(struct trace_iterator *iter, + int flags, struct trace_event *event) +{ + struct print_entry *field; + struct trace_seq *s = &iter->seq; + + trace_assign_type(field, iter->ent); + + seq_print_ip_sym(s, field->ip, flags); + trace_seq_printf(s, ": %s", field->buf); + + return trace_handle_return(s); +} + +static enum print_line_t trace_print_raw(struct trace_iterator *iter, int flags, + struct trace_event *event) +{ + struct print_entry *field; + + trace_assign_type(field, iter->ent); + + trace_seq_printf(&iter->seq, "# %lx %s", field->ip, field->buf); + + return trace_handle_return(&iter->seq); +} + +static struct trace_event_functions trace_print_funcs = { + .trace = trace_print_print, + .raw = trace_print_raw, +}; + +static struct trace_event trace_print_event = { + .type = TRACE_PRINT, + .funcs = &trace_print_funcs, +}; + + +static struct trace_event *events[] __initdata = { + &trace_fn_event, + &trace_ctx_event, + &trace_wake_event, + &trace_stack_event, + &trace_user_stack_event, + &trace_bputs_event, + &trace_bprint_event, + &trace_print_event, + NULL +}; + +__init static int init_events(void) +{ + struct trace_event *event; + int i, ret; + + for (i = 0; events[i]; i++) { + event = events[i]; + + ret = register_ftrace_event(event); + if (!ret) { + printk(KERN_WARNING "event %d failed to register\n", + event->type); + WARN_ON_ONCE(1); + } + } + + return 0; +} +early_initcall(init_events); diff --git a/kernel/kernel/trace/trace_output.h b/kernel/kernel/trace/trace_output.h new file mode 100644 index 000000000..8ef2c40ef --- /dev/null +++ b/kernel/kernel/trace/trace_output.h @@ -0,0 +1,45 @@ +#ifndef __TRACE_EVENTS_H +#define __TRACE_EVENTS_H + +#include +#include "trace.h" + +extern enum print_line_t +trace_print_bputs_msg_only(struct trace_iterator *iter); +extern enum print_line_t +trace_print_bprintk_msg_only(struct trace_iterator *iter); +extern enum print_line_t +trace_print_printk_msg_only(struct trace_iterator *iter); + +extern int +seq_print_ip_sym(struct trace_seq *s, unsigned long ip, + unsigned long sym_flags); +extern int seq_print_userip_objs(const struct userstack_entry *entry, + struct trace_seq *s, unsigned long sym_flags); +extern int seq_print_user_ip(struct trace_seq *s, struct mm_struct *mm, + unsigned long ip, unsigned long sym_flags); + +extern int trace_print_context(struct trace_iterator *iter); +extern int trace_print_lat_context(struct trace_iterator *iter); + +extern void trace_event_read_lock(void); +extern void trace_event_read_unlock(void); +extern struct trace_event *ftrace_find_event(int type); + +extern enum print_line_t trace_nop_print(struct trace_iterator *iter, + int flags, struct trace_event *event); +extern int +trace_print_lat_fmt(struct trace_seq *s, struct trace_entry *entry); + +/* used by module unregistering */ +extern int __unregister_ftrace_event(struct trace_event *event); +extern struct rw_semaphore trace_event_sem; + +#define SEQ_PUT_FIELD(s, x) \ + trace_seq_putmem(s, &(x), sizeof(x)) + +#define SEQ_PUT_HEX_FIELD(s, x) \ + trace_seq_putmem_hex(s, &(x), sizeof(x)) + +#endif + diff --git a/kernel/kernel/trace/trace_printk.c b/kernel/kernel/trace/trace_printk.c new file mode 100644 index 000000000..36c1455b7 --- /dev/null +++ b/kernel/kernel/trace/trace_printk.c @@ -0,0 +1,366 @@ +/* + * trace binary printk + * + * Copyright (C) 2008 Lai Jiangshan + * + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "trace.h" + +#ifdef CONFIG_MODULES + +/* + * modules trace_printk()'s formats are autosaved in struct trace_bprintk_fmt + * which are queued on trace_bprintk_fmt_list. + */ +static LIST_HEAD(trace_bprintk_fmt_list); + +/* serialize accesses to trace_bprintk_fmt_list */ +static DEFINE_MUTEX(btrace_mutex); + +struct trace_bprintk_fmt { + struct list_head list; + const char *fmt; +}; + +static inline struct trace_bprintk_fmt *lookup_format(const char *fmt) +{ + struct trace_bprintk_fmt *pos; + list_for_each_entry(pos, &trace_bprintk_fmt_list, list) { + if (!strcmp(pos->fmt, fmt)) + return pos; + } + return NULL; +} + +static +void hold_module_trace_bprintk_format(const char **start, const char **end) +{ + const char **iter; + char *fmt; + + /* allocate the trace_printk per cpu buffers */ + if (start != end) + trace_printk_init_buffers(); + + mutex_lock(&btrace_mutex); + for (iter = start; iter < end; iter++) { + struct trace_bprintk_fmt *tb_fmt = lookup_format(*iter); + if (tb_fmt) { + *iter = tb_fmt->fmt; + continue; + } + + fmt = NULL; + tb_fmt = kmalloc(sizeof(*tb_fmt), GFP_KERNEL); + if (tb_fmt) { + fmt = kmalloc(strlen(*iter) + 1, GFP_KERNEL); + if (fmt) { + list_add_tail(&tb_fmt->list, &trace_bprintk_fmt_list); + strcpy(fmt, *iter); + tb_fmt->fmt = fmt; + } else + kfree(tb_fmt); + } + *iter = fmt; + + } + mutex_unlock(&btrace_mutex); +} + +static int module_trace_bprintk_format_notify(struct notifier_block *self, + unsigned long val, void *data) +{ + struct module *mod = data; + if (mod->num_trace_bprintk_fmt) { + const char **start = mod->trace_bprintk_fmt_start; + const char **end = start + mod->num_trace_bprintk_fmt; + + if (val == MODULE_STATE_COMING) + hold_module_trace_bprintk_format(start, end); + } + return 0; +} + +/* + * The debugfs/tracing/printk_formats file maps the addresses with + * the ASCII formats that are used in the bprintk events in the + * buffer. For userspace tools to be able to decode the events from + * the buffer, they need to be able to map the address with the format. + * + * The addresses of the bprintk formats are in their own section + * __trace_printk_fmt. But for modules we copy them into a link list. + * The code to print the formats and their addresses passes around the + * address of the fmt string. If the fmt address passed into the seq + * functions is within the kernel core __trace_printk_fmt section, then + * it simply uses the next pointer in the list. + * + * When the fmt pointer is outside the kernel core __trace_printk_fmt + * section, then we need to read the link list pointers. The trick is + * we pass the address of the string to the seq function just like + * we do for the kernel core formats. To get back the structure that + * holds the format, we simply use containerof() and then go to the + * next format in the list. + */ +static const char ** +find_next_mod_format(int start_index, void *v, const char **fmt, loff_t *pos) +{ + struct trace_bprintk_fmt *mod_fmt; + + if (list_empty(&trace_bprintk_fmt_list)) + return NULL; + + /* + * v will point to the address of the fmt record from t_next + * v will be NULL from t_start. + * If this is the first pointer or called from start + * then we need to walk the list. + */ + if (!v || start_index == *pos) { + struct trace_bprintk_fmt *p; + + /* search the module list */ + list_for_each_entry(p, &trace_bprintk_fmt_list, list) { + if (start_index == *pos) + return &p->fmt; + start_index++; + } + /* pos > index */ + return NULL; + } + + /* + * v points to the address of the fmt field in the mod list + * structure that holds the module print format. + */ + mod_fmt = container_of(v, typeof(*mod_fmt), fmt); + if (mod_fmt->list.next == &trace_bprintk_fmt_list) + return NULL; + + mod_fmt = container_of(mod_fmt->list.next, typeof(*mod_fmt), list); + + return &mod_fmt->fmt; +} + +static void format_mod_start(void) +{ + mutex_lock(&btrace_mutex); +} + +static void format_mod_stop(void) +{ + mutex_unlock(&btrace_mutex); +} + +#else /* !CONFIG_MODULES */ +__init static int +module_trace_bprintk_format_notify(struct notifier_block *self, + unsigned long val, void *data) +{ + return 0; +} +static inline const char ** +find_next_mod_format(int start_index, void *v, const char **fmt, loff_t *pos) +{ + return NULL; +} +static inline void format_mod_start(void) { } +static inline void format_mod_stop(void) { } +#endif /* CONFIG_MODULES */ + + +__initdata_or_module static +struct notifier_block module_trace_bprintk_format_nb = { + .notifier_call = module_trace_bprintk_format_notify, +}; + +int __trace_bprintk(unsigned long ip, const char *fmt, ...) + { + int ret; + va_list ap; + + if (unlikely(!fmt)) + return 0; + + if (!(trace_flags & TRACE_ITER_PRINTK)) + return 0; + + va_start(ap, fmt); + ret = trace_vbprintk(ip, fmt, ap); + va_end(ap); + return ret; +} +EXPORT_SYMBOL_GPL(__trace_bprintk); + +int __ftrace_vbprintk(unsigned long ip, const char *fmt, va_list ap) + { + if (unlikely(!fmt)) + return 0; + + if (!(trace_flags & TRACE_ITER_PRINTK)) + return 0; + + return trace_vbprintk(ip, fmt, ap); +} +EXPORT_SYMBOL_GPL(__ftrace_vbprintk); + +int __trace_printk(unsigned long ip, const char *fmt, ...) +{ + int ret; + va_list ap; + + if (!(trace_flags & TRACE_ITER_PRINTK)) + return 0; + + va_start(ap, fmt); + ret = trace_vprintk(ip, fmt, ap); + va_end(ap); + return ret; +} +EXPORT_SYMBOL_GPL(__trace_printk); + +int __ftrace_vprintk(unsigned long ip, const char *fmt, va_list ap) +{ + if (!(trace_flags & TRACE_ITER_PRINTK)) + return 0; + + return trace_vprintk(ip, fmt, ap); +} +EXPORT_SYMBOL_GPL(__ftrace_vprintk); + +static const char **find_next(void *v, loff_t *pos) +{ + const char **fmt = v; + int start_index; + int last_index; + + start_index = __stop___trace_bprintk_fmt - __start___trace_bprintk_fmt; + + if (*pos < start_index) + return __start___trace_bprintk_fmt + *pos; + + /* + * The __tracepoint_str section is treated the same as the + * __trace_printk_fmt section. The difference is that the + * __trace_printk_fmt section should only be used by trace_printk() + * in a debugging environment, as if anything exists in that section + * the trace_prink() helper buffers are allocated, which would just + * waste space in a production environment. + * + * The __tracepoint_str sections on the other hand are used by + * tracepoints which need to map pointers to their strings to + * the ASCII text for userspace. + */ + last_index = start_index; + start_index = __stop___tracepoint_str - __start___tracepoint_str; + + if (*pos < last_index + start_index) + return __start___tracepoint_str + (*pos - last_index); + + return find_next_mod_format(start_index, v, fmt, pos); +} + +static void * +t_start(struct seq_file *m, loff_t *pos) +{ + format_mod_start(); + return find_next(NULL, pos); +} + +static void *t_next(struct seq_file *m, void * v, loff_t *pos) +{ + (*pos)++; + return find_next(v, pos); +} + +static int t_show(struct seq_file *m, void *v) +{ + const char **fmt = v; + const char *str = *fmt; + int i; + + seq_printf(m, "0x%lx : \"", *(unsigned long *)fmt); + + /* + * Tabs and new lines need to be converted. + */ + for (i = 0; str[i]; i++) { + switch (str[i]) { + case '\n': + seq_puts(m, "\\n"); + break; + case '\t': + seq_puts(m, "\\t"); + break; + case '\\': + seq_putc(m, '\\'); + break; + case '"': + seq_puts(m, "\\\""); + break; + default: + seq_putc(m, str[i]); + } + } + seq_puts(m, "\"\n"); + + return 0; +} + +static void t_stop(struct seq_file *m, void *p) +{ + format_mod_stop(); +} + +static const struct seq_operations show_format_seq_ops = { + .start = t_start, + .next = t_next, + .show = t_show, + .stop = t_stop, +}; + +static int +ftrace_formats_open(struct inode *inode, struct file *file) +{ + return seq_open(file, &show_format_seq_ops); +} + +static const struct file_operations ftrace_formats_fops = { + .open = ftrace_formats_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, +}; + +static __init int init_trace_printk_function_export(void) +{ + struct dentry *d_tracer; + + d_tracer = tracing_init_dentry(); + if (IS_ERR(d_tracer)) + return 0; + + trace_create_file("printk_formats", 0444, d_tracer, + NULL, &ftrace_formats_fops); + + return 0; +} + +fs_initcall(init_trace_printk_function_export); + +static __init int init_trace_printk(void) +{ + return register_module_notifier(&module_trace_bprintk_format_nb); +} + +early_initcall(init_trace_printk); diff --git a/kernel/kernel/trace/trace_probe.c b/kernel/kernel/trace/trace_probe.c new file mode 100644 index 000000000..1769a81da --- /dev/null +++ b/kernel/kernel/trace/trace_probe.c @@ -0,0 +1,723 @@ +/* + * Common code for probe-based Dynamic events. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * + * This code was copied from kernel/trace/trace_kprobe.c written by + * Masami Hiramatsu + * + * Updates to make this generic: + * Copyright (C) IBM Corporation, 2010-2011 + * Author: Srikar Dronamraju + */ + +#include "trace_probe.h" + +const char *reserved_field_names[] = { + "common_type", + "common_flags", + "common_preempt_count", + "common_pid", + "common_tgid", + FIELD_STRING_IP, + FIELD_STRING_RETIP, + FIELD_STRING_FUNC, +}; + +/* Printing in basic type function template */ +#define DEFINE_BASIC_PRINT_TYPE_FUNC(type, fmt) \ +int PRINT_TYPE_FUNC_NAME(type)(struct trace_seq *s, const char *name, \ + void *data, void *ent) \ +{ \ + trace_seq_printf(s, " %s=" fmt, name, *(type *)data); \ + return !trace_seq_has_overflowed(s); \ +} \ +const char PRINT_TYPE_FMT_NAME(type)[] = fmt; \ +NOKPROBE_SYMBOL(PRINT_TYPE_FUNC_NAME(type)); + +DEFINE_BASIC_PRINT_TYPE_FUNC(u8 , "0x%x") +DEFINE_BASIC_PRINT_TYPE_FUNC(u16, "0x%x") +DEFINE_BASIC_PRINT_TYPE_FUNC(u32, "0x%x") +DEFINE_BASIC_PRINT_TYPE_FUNC(u64, "0x%Lx") +DEFINE_BASIC_PRINT_TYPE_FUNC(s8, "%d") +DEFINE_BASIC_PRINT_TYPE_FUNC(s16, "%d") +DEFINE_BASIC_PRINT_TYPE_FUNC(s32, "%d") +DEFINE_BASIC_PRINT_TYPE_FUNC(s64, "%Ld") + +/* Print type function for string type */ +int PRINT_TYPE_FUNC_NAME(string)(struct trace_seq *s, const char *name, + void *data, void *ent) +{ + int len = *(u32 *)data >> 16; + + if (!len) + trace_seq_printf(s, " %s=(fault)", name); + else + trace_seq_printf(s, " %s=\"%s\"", name, + (const char *)get_loc_data(data, ent)); + return !trace_seq_has_overflowed(s); +} +NOKPROBE_SYMBOL(PRINT_TYPE_FUNC_NAME(string)); + +const char PRINT_TYPE_FMT_NAME(string)[] = "\\\"%s\\\""; + +#define CHECK_FETCH_FUNCS(method, fn) \ + (((FETCH_FUNC_NAME(method, u8) == fn) || \ + (FETCH_FUNC_NAME(method, u16) == fn) || \ + (FETCH_FUNC_NAME(method, u32) == fn) || \ + (FETCH_FUNC_NAME(method, u64) == fn) || \ + (FETCH_FUNC_NAME(method, string) == fn) || \ + (FETCH_FUNC_NAME(method, string_size) == fn)) \ + && (fn != NULL)) + +/* Data fetch function templates */ +#define DEFINE_FETCH_reg(type) \ +void FETCH_FUNC_NAME(reg, type)(struct pt_regs *regs, void *offset, void *dest) \ +{ \ + *(type *)dest = (type)regs_get_register(regs, \ + (unsigned int)((unsigned long)offset)); \ +} \ +NOKPROBE_SYMBOL(FETCH_FUNC_NAME(reg, type)); +DEFINE_BASIC_FETCH_FUNCS(reg) +/* No string on the register */ +#define fetch_reg_string NULL +#define fetch_reg_string_size NULL + +#define DEFINE_FETCH_retval(type) \ +void FETCH_FUNC_NAME(retval, type)(struct pt_regs *regs, \ + void *dummy, void *dest) \ +{ \ + *(type *)dest = (type)regs_return_value(regs); \ +} \ +NOKPROBE_SYMBOL(FETCH_FUNC_NAME(retval, type)); +DEFINE_BASIC_FETCH_FUNCS(retval) +/* No string on the retval */ +#define fetch_retval_string NULL +#define fetch_retval_string_size NULL + +/* Dereference memory access function */ +struct deref_fetch_param { + struct fetch_param orig; + long offset; + fetch_func_t fetch; + fetch_func_t fetch_size; +}; + +#define DEFINE_FETCH_deref(type) \ +void FETCH_FUNC_NAME(deref, type)(struct pt_regs *regs, \ + void *data, void *dest) \ +{ \ + struct deref_fetch_param *dprm = data; \ + unsigned long addr; \ + call_fetch(&dprm->orig, regs, &addr); \ + if (addr) { \ + addr += dprm->offset; \ + dprm->fetch(regs, (void *)addr, dest); \ + } else \ + *(type *)dest = 0; \ +} \ +NOKPROBE_SYMBOL(FETCH_FUNC_NAME(deref, type)); +DEFINE_BASIC_FETCH_FUNCS(deref) +DEFINE_FETCH_deref(string) + +void FETCH_FUNC_NAME(deref, string_size)(struct pt_regs *regs, + void *data, void *dest) +{ + struct deref_fetch_param *dprm = data; + unsigned long addr; + + call_fetch(&dprm->orig, regs, &addr); + if (addr && dprm->fetch_size) { + addr += dprm->offset; + dprm->fetch_size(regs, (void *)addr, dest); + } else + *(string_size *)dest = 0; +} +NOKPROBE_SYMBOL(FETCH_FUNC_NAME(deref, string_size)); + +static void update_deref_fetch_param(struct deref_fetch_param *data) +{ + if (CHECK_FETCH_FUNCS(deref, data->orig.fn)) + update_deref_fetch_param(data->orig.data); + else if (CHECK_FETCH_FUNCS(symbol, data->orig.fn)) + update_symbol_cache(data->orig.data); +} +NOKPROBE_SYMBOL(update_deref_fetch_param); + +static void free_deref_fetch_param(struct deref_fetch_param *data) +{ + if (CHECK_FETCH_FUNCS(deref, data->orig.fn)) + free_deref_fetch_param(data->orig.data); + else if (CHECK_FETCH_FUNCS(symbol, data->orig.fn)) + free_symbol_cache(data->orig.data); + kfree(data); +} +NOKPROBE_SYMBOL(free_deref_fetch_param); + +/* Bitfield fetch function */ +struct bitfield_fetch_param { + struct fetch_param orig; + unsigned char hi_shift; + unsigned char low_shift; +}; + +#define DEFINE_FETCH_bitfield(type) \ +void FETCH_FUNC_NAME(bitfield, type)(struct pt_regs *regs, \ + void *data, void *dest) \ +{ \ + struct bitfield_fetch_param *bprm = data; \ + type buf = 0; \ + call_fetch(&bprm->orig, regs, &buf); \ + if (buf) { \ + buf <<= bprm->hi_shift; \ + buf >>= bprm->low_shift; \ + } \ + *(type *)dest = buf; \ +} \ +NOKPROBE_SYMBOL(FETCH_FUNC_NAME(bitfield, type)); +DEFINE_BASIC_FETCH_FUNCS(bitfield) +#define fetch_bitfield_string NULL +#define fetch_bitfield_string_size NULL + +static void +update_bitfield_fetch_param(struct bitfield_fetch_param *data) +{ + /* + * Don't check the bitfield itself, because this must be the + * last fetch function. + */ + if (CHECK_FETCH_FUNCS(deref, data->orig.fn)) + update_deref_fetch_param(data->orig.data); + else if (CHECK_FETCH_FUNCS(symbol, data->orig.fn)) + update_symbol_cache(data->orig.data); +} + +static void +free_bitfield_fetch_param(struct bitfield_fetch_param *data) +{ + /* + * Don't check the bitfield itself, because this must be the + * last fetch function. + */ + if (CHECK_FETCH_FUNCS(deref, data->orig.fn)) + free_deref_fetch_param(data->orig.data); + else if (CHECK_FETCH_FUNCS(symbol, data->orig.fn)) + free_symbol_cache(data->orig.data); + + kfree(data); +} + +static const struct fetch_type *find_fetch_type(const char *type, + const struct fetch_type *ftbl) +{ + int i; + + if (!type) + type = DEFAULT_FETCH_TYPE_STR; + + /* Special case: bitfield */ + if (*type == 'b') { + unsigned long bs; + + type = strchr(type, '/'); + if (!type) + goto fail; + + type++; + if (kstrtoul(type, 0, &bs)) + goto fail; + + switch (bs) { + case 8: + return find_fetch_type("u8", ftbl); + case 16: + return find_fetch_type("u16", ftbl); + case 32: + return find_fetch_type("u32", ftbl); + case 64: + return find_fetch_type("u64", ftbl); + default: + goto fail; + } + } + + for (i = 0; ftbl[i].name; i++) { + if (strcmp(type, ftbl[i].name) == 0) + return &ftbl[i]; + } + +fail: + return NULL; +} + +/* Special function : only accept unsigned long */ +static void fetch_kernel_stack_address(struct pt_regs *regs, void *dummy, void *dest) +{ + *(unsigned long *)dest = kernel_stack_pointer(regs); +} +NOKPROBE_SYMBOL(fetch_kernel_stack_address); + +static void fetch_user_stack_address(struct pt_regs *regs, void *dummy, void *dest) +{ + *(unsigned long *)dest = user_stack_pointer(regs); +} +NOKPROBE_SYMBOL(fetch_user_stack_address); + +static fetch_func_t get_fetch_size_function(const struct fetch_type *type, + fetch_func_t orig_fn, + const struct fetch_type *ftbl) +{ + int i; + + if (type != &ftbl[FETCH_TYPE_STRING]) + return NULL; /* Only string type needs size function */ + + for (i = 0; i < FETCH_MTD_END; i++) + if (type->fetch[i] == orig_fn) + return ftbl[FETCH_TYPE_STRSIZE].fetch[i]; + + WARN_ON(1); /* This should not happen */ + + return NULL; +} + +/* Split symbol and offset. */ +int traceprobe_split_symbol_offset(char *symbol, unsigned long *offset) +{ + char *tmp; + int ret; + + if (!offset) + return -EINVAL; + + tmp = strchr(symbol, '+'); + if (tmp) { + /* skip sign because kstrtoul doesn't accept '+' */ + ret = kstrtoul(tmp + 1, 0, offset); + if (ret) + return ret; + + *tmp = '\0'; + } else + *offset = 0; + + return 0; +} + +#define PARAM_MAX_STACK (THREAD_SIZE / sizeof(unsigned long)) + +static int parse_probe_vars(char *arg, const struct fetch_type *t, + struct fetch_param *f, bool is_return, + bool is_kprobe) +{ + int ret = 0; + unsigned long param; + + if (strcmp(arg, "retval") == 0) { + if (is_return) + f->fn = t->fetch[FETCH_MTD_retval]; + else + ret = -EINVAL; + } else if (strncmp(arg, "stack", 5) == 0) { + if (arg[5] == '\0') { + if (strcmp(t->name, DEFAULT_FETCH_TYPE_STR)) + return -EINVAL; + + if (is_kprobe) + f->fn = fetch_kernel_stack_address; + else + f->fn = fetch_user_stack_address; + } else if (isdigit(arg[5])) { + ret = kstrtoul(arg + 5, 10, ¶m); + if (ret || (is_kprobe && param > PARAM_MAX_STACK)) + ret = -EINVAL; + else { + f->fn = t->fetch[FETCH_MTD_stack]; + f->data = (void *)param; + } + } else + ret = -EINVAL; + } else + ret = -EINVAL; + + return ret; +} + +/* Recursive argument parser */ +static int parse_probe_arg(char *arg, const struct fetch_type *t, + struct fetch_param *f, bool is_return, bool is_kprobe, + const struct fetch_type *ftbl) +{ + unsigned long param; + long offset; + char *tmp; + int ret = 0; + + switch (arg[0]) { + case '$': + ret = parse_probe_vars(arg + 1, t, f, is_return, is_kprobe); + break; + + case '%': /* named register */ + ret = regs_query_register_offset(arg + 1); + if (ret >= 0) { + f->fn = t->fetch[FETCH_MTD_reg]; + f->data = (void *)(unsigned long)ret; + ret = 0; + } + break; + + case '@': /* memory, file-offset or symbol */ + if (isdigit(arg[1])) { + ret = kstrtoul(arg + 1, 0, ¶m); + if (ret) + break; + + f->fn = t->fetch[FETCH_MTD_memory]; + f->data = (void *)param; + } else if (arg[1] == '+') { + /* kprobes don't support file offsets */ + if (is_kprobe) + return -EINVAL; + + ret = kstrtol(arg + 2, 0, &offset); + if (ret) + break; + + f->fn = t->fetch[FETCH_MTD_file_offset]; + f->data = (void *)offset; + } else { + /* uprobes don't support symbols */ + if (!is_kprobe) + return -EINVAL; + + ret = traceprobe_split_symbol_offset(arg + 1, &offset); + if (ret) + break; + + f->data = alloc_symbol_cache(arg + 1, offset); + if (f->data) + f->fn = t->fetch[FETCH_MTD_symbol]; + } + break; + + case '+': /* deref memory */ + arg++; /* Skip '+', because kstrtol() rejects it. */ + case '-': + tmp = strchr(arg, '('); + if (!tmp) + break; + + *tmp = '\0'; + ret = kstrtol(arg, 0, &offset); + + if (ret) + break; + + arg = tmp + 1; + tmp = strrchr(arg, ')'); + + if (tmp) { + struct deref_fetch_param *dprm; + const struct fetch_type *t2; + + t2 = find_fetch_type(NULL, ftbl); + *tmp = '\0'; + dprm = kzalloc(sizeof(struct deref_fetch_param), GFP_KERNEL); + + if (!dprm) + return -ENOMEM; + + dprm->offset = offset; + dprm->fetch = t->fetch[FETCH_MTD_memory]; + dprm->fetch_size = get_fetch_size_function(t, + dprm->fetch, ftbl); + ret = parse_probe_arg(arg, t2, &dprm->orig, is_return, + is_kprobe, ftbl); + if (ret) + kfree(dprm); + else { + f->fn = t->fetch[FETCH_MTD_deref]; + f->data = (void *)dprm; + } + } + break; + } + if (!ret && !f->fn) { /* Parsed, but do not find fetch method */ + pr_info("%s type has no corresponding fetch method.\n", t->name); + ret = -EINVAL; + } + + return ret; +} + +#define BYTES_TO_BITS(nb) ((BITS_PER_LONG * (nb)) / sizeof(long)) + +/* Bitfield type needs to be parsed into a fetch function */ +static int __parse_bitfield_probe_arg(const char *bf, + const struct fetch_type *t, + struct fetch_param *f) +{ + struct bitfield_fetch_param *bprm; + unsigned long bw, bo; + char *tail; + + if (*bf != 'b') + return 0; + + bprm = kzalloc(sizeof(*bprm), GFP_KERNEL); + if (!bprm) + return -ENOMEM; + + bprm->orig = *f; + f->fn = t->fetch[FETCH_MTD_bitfield]; + f->data = (void *)bprm; + bw = simple_strtoul(bf + 1, &tail, 0); /* Use simple one */ + + if (bw == 0 || *tail != '@') + return -EINVAL; + + bf = tail + 1; + bo = simple_strtoul(bf, &tail, 0); + + if (tail == bf || *tail != '/') + return -EINVAL; + + bprm->hi_shift = BYTES_TO_BITS(t->size) - (bw + bo); + bprm->low_shift = bprm->hi_shift + bo; + + return (BYTES_TO_BITS(t->size) < (bw + bo)) ? -EINVAL : 0; +} + +/* String length checking wrapper */ +int traceprobe_parse_probe_arg(char *arg, ssize_t *size, + struct probe_arg *parg, bool is_return, bool is_kprobe, + const struct fetch_type *ftbl) +{ + const char *t; + int ret; + + if (strlen(arg) > MAX_ARGSTR_LEN) { + pr_info("Argument is too long.: %s\n", arg); + return -ENOSPC; + } + parg->comm = kstrdup(arg, GFP_KERNEL); + if (!parg->comm) { + pr_info("Failed to allocate memory for command '%s'.\n", arg); + return -ENOMEM; + } + t = strchr(parg->comm, ':'); + if (t) { + arg[t - parg->comm] = '\0'; + t++; + } + parg->type = find_fetch_type(t, ftbl); + if (!parg->type) { + pr_info("Unsupported type: %s\n", t); + return -EINVAL; + } + parg->offset = *size; + *size += parg->type->size; + ret = parse_probe_arg(arg, parg->type, &parg->fetch, is_return, + is_kprobe, ftbl); + + if (ret >= 0 && t != NULL) + ret = __parse_bitfield_probe_arg(t, parg->type, &parg->fetch); + + if (ret >= 0) { + parg->fetch_size.fn = get_fetch_size_function(parg->type, + parg->fetch.fn, + ftbl); + parg->fetch_size.data = parg->fetch.data; + } + + return ret; +} + +/* Return 1 if name is reserved or already used by another argument */ +int traceprobe_conflict_field_name(const char *name, + struct probe_arg *args, int narg) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(reserved_field_names); i++) + if (strcmp(reserved_field_names[i], name) == 0) + return 1; + + for (i = 0; i < narg; i++) + if (strcmp(args[i].name, name) == 0) + return 1; + + return 0; +} + +void traceprobe_update_arg(struct probe_arg *arg) +{ + if (CHECK_FETCH_FUNCS(bitfield, arg->fetch.fn)) + update_bitfield_fetch_param(arg->fetch.data); + else if (CHECK_FETCH_FUNCS(deref, arg->fetch.fn)) + update_deref_fetch_param(arg->fetch.data); + else if (CHECK_FETCH_FUNCS(symbol, arg->fetch.fn)) + update_symbol_cache(arg->fetch.data); +} + +void traceprobe_free_probe_arg(struct probe_arg *arg) +{ + if (CHECK_FETCH_FUNCS(bitfield, arg->fetch.fn)) + free_bitfield_fetch_param(arg->fetch.data); + else if (CHECK_FETCH_FUNCS(deref, arg->fetch.fn)) + free_deref_fetch_param(arg->fetch.data); + else if (CHECK_FETCH_FUNCS(symbol, arg->fetch.fn)) + free_symbol_cache(arg->fetch.data); + + kfree(arg->name); + kfree(arg->comm); +} + +int traceprobe_command(const char *buf, int (*createfn)(int, char **)) +{ + char **argv; + int argc, ret; + + argc = 0; + ret = 0; + argv = argv_split(GFP_KERNEL, buf, &argc); + if (!argv) + return -ENOMEM; + + if (argc) + ret = createfn(argc, argv); + + argv_free(argv); + + return ret; +} + +#define WRITE_BUFSIZE 4096 + +ssize_t traceprobe_probes_write(struct file *file, const char __user *buffer, + size_t count, loff_t *ppos, + int (*createfn)(int, char **)) +{ + char *kbuf, *tmp; + int ret = 0; + size_t done = 0; + size_t size; + + kbuf = kmalloc(WRITE_BUFSIZE, GFP_KERNEL); + if (!kbuf) + return -ENOMEM; + + while (done < count) { + size = count - done; + + if (size >= WRITE_BUFSIZE) + size = WRITE_BUFSIZE - 1; + + if (copy_from_user(kbuf, buffer + done, size)) { + ret = -EFAULT; + goto out; + } + kbuf[size] = '\0'; + tmp = strchr(kbuf, '\n'); + + if (tmp) { + *tmp = '\0'; + size = tmp - kbuf + 1; + } else if (done + size < count) { + pr_warning("Line length is too long: " + "Should be less than %d.", WRITE_BUFSIZE); + ret = -EINVAL; + goto out; + } + done += size; + /* Remove comments */ + tmp = strchr(kbuf, '#'); + + if (tmp) + *tmp = '\0'; + + ret = traceprobe_command(kbuf, createfn); + if (ret) + goto out; + } + ret = done; + +out: + kfree(kbuf); + + return ret; +} + +static int __set_print_fmt(struct trace_probe *tp, char *buf, int len, + bool is_return) +{ + int i; + int pos = 0; + + const char *fmt, *arg; + + if (!is_return) { + fmt = "(%lx)"; + arg = "REC->" FIELD_STRING_IP; + } else { + fmt = "(%lx <- %lx)"; + arg = "REC->" FIELD_STRING_FUNC ", REC->" FIELD_STRING_RETIP; + } + + /* When len=0, we just calculate the needed length */ +#define LEN_OR_ZERO (len ? len - pos : 0) + + pos += snprintf(buf + pos, LEN_OR_ZERO, "\"%s", fmt); + + for (i = 0; i < tp->nr_args; i++) { + pos += snprintf(buf + pos, LEN_OR_ZERO, " %s=%s", + tp->args[i].name, tp->args[i].type->fmt); + } + + pos += snprintf(buf + pos, LEN_OR_ZERO, "\", %s", arg); + + for (i = 0; i < tp->nr_args; i++) { + if (strcmp(tp->args[i].type->name, "string") == 0) + pos += snprintf(buf + pos, LEN_OR_ZERO, + ", __get_str(%s)", + tp->args[i].name); + else + pos += snprintf(buf + pos, LEN_OR_ZERO, ", REC->%s", + tp->args[i].name); + } + +#undef LEN_OR_ZERO + + /* return the length of print_fmt */ + return pos; +} + +int set_print_fmt(struct trace_probe *tp, bool is_return) +{ + int len; + char *print_fmt; + + /* First: called with 0 length to calculate the needed length */ + len = __set_print_fmt(tp, NULL, 0, is_return); + print_fmt = kmalloc(len + 1, GFP_KERNEL); + if (!print_fmt) + return -ENOMEM; + + /* Second: actually write the @print_fmt */ + __set_print_fmt(tp, print_fmt, len + 1, is_return); + tp->call.print_fmt = print_fmt; + + return 0; +} diff --git a/kernel/kernel/trace/trace_probe.h b/kernel/kernel/trace/trace_probe.h new file mode 100644 index 000000000..ab283e146 --- /dev/null +++ b/kernel/kernel/trace/trace_probe.h @@ -0,0 +1,394 @@ +/* + * Common header file for probe-based Dynamic events. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * + * This code was copied from kernel/trace/trace_kprobe.h written by + * Masami Hiramatsu + * + * Updates to make this generic: + * Copyright (C) IBM Corporation, 2010-2011 + * Author: Srikar Dronamraju + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "trace.h" +#include "trace_output.h" + +#define MAX_TRACE_ARGS 128 +#define MAX_ARGSTR_LEN 63 +#define MAX_EVENT_NAME_LEN 64 +#define MAX_STRING_SIZE PATH_MAX + +/* Reserved field names */ +#define FIELD_STRING_IP "__probe_ip" +#define FIELD_STRING_RETIP "__probe_ret_ip" +#define FIELD_STRING_FUNC "__probe_func" + +#undef DEFINE_FIELD +#define DEFINE_FIELD(type, item, name, is_signed) \ + do { \ + ret = trace_define_field(event_call, #type, name, \ + offsetof(typeof(field), item), \ + sizeof(field.item), is_signed, \ + FILTER_OTHER); \ + if (ret) \ + return ret; \ + } while (0) + + +/* Flags for trace_probe */ +#define TP_FLAG_TRACE 1 +#define TP_FLAG_PROFILE 2 +#define TP_FLAG_REGISTERED 4 + + +/* data_rloc: data relative location, compatible with u32 */ +#define make_data_rloc(len, roffs) \ + (((u32)(len) << 16) | ((u32)(roffs) & 0xffff)) +#define get_rloc_len(dl) ((u32)(dl) >> 16) +#define get_rloc_offs(dl) ((u32)(dl) & 0xffff) + +/* + * Convert data_rloc to data_loc: + * data_rloc stores the offset from data_rloc itself, but data_loc + * stores the offset from event entry. + */ +#define convert_rloc_to_loc(dl, offs) ((u32)(dl) + (offs)) + +static nokprobe_inline void *get_rloc_data(u32 *dl) +{ + return (u8 *)dl + get_rloc_offs(*dl); +} + +/* For data_loc conversion */ +static nokprobe_inline void *get_loc_data(u32 *dl, void *ent) +{ + return (u8 *)ent + get_rloc_offs(*dl); +} + +/* Data fetch function type */ +typedef void (*fetch_func_t)(struct pt_regs *, void *, void *); +/* Printing function type */ +typedef int (*print_type_func_t)(struct trace_seq *, const char *, void *, void *); + +/* Fetch types */ +enum { + FETCH_MTD_reg = 0, + FETCH_MTD_stack, + FETCH_MTD_retval, + FETCH_MTD_memory, + FETCH_MTD_symbol, + FETCH_MTD_deref, + FETCH_MTD_bitfield, + FETCH_MTD_file_offset, + FETCH_MTD_END, +}; + +/* Fetch type information table */ +struct fetch_type { + const char *name; /* Name of type */ + size_t size; /* Byte size of type */ + int is_signed; /* Signed flag */ + print_type_func_t print; /* Print functions */ + const char *fmt; /* Fromat string */ + const char *fmttype; /* Name in format file */ + /* Fetch functions */ + fetch_func_t fetch[FETCH_MTD_END]; +}; + +struct fetch_param { + fetch_func_t fn; + void *data; +}; + +/* For defining macros, define string/string_size types */ +typedef u32 string; +typedef u32 string_size; + +#define PRINT_TYPE_FUNC_NAME(type) print_type_##type +#define PRINT_TYPE_FMT_NAME(type) print_type_format_##type + +/* Printing in basic type function template */ +#define DECLARE_BASIC_PRINT_TYPE_FUNC(type) \ +int PRINT_TYPE_FUNC_NAME(type)(struct trace_seq *s, const char *name, \ + void *data, void *ent); \ +extern const char PRINT_TYPE_FMT_NAME(type)[] + +DECLARE_BASIC_PRINT_TYPE_FUNC(u8); +DECLARE_BASIC_PRINT_TYPE_FUNC(u16); +DECLARE_BASIC_PRINT_TYPE_FUNC(u32); +DECLARE_BASIC_PRINT_TYPE_FUNC(u64); +DECLARE_BASIC_PRINT_TYPE_FUNC(s8); +DECLARE_BASIC_PRINT_TYPE_FUNC(s16); +DECLARE_BASIC_PRINT_TYPE_FUNC(s32); +DECLARE_BASIC_PRINT_TYPE_FUNC(s64); +DECLARE_BASIC_PRINT_TYPE_FUNC(string); + +#define FETCH_FUNC_NAME(method, type) fetch_##method##_##type + +/* Declare macro for basic types */ +#define DECLARE_FETCH_FUNC(method, type) \ +extern void FETCH_FUNC_NAME(method, type)(struct pt_regs *regs, \ + void *data, void *dest) + +#define DECLARE_BASIC_FETCH_FUNCS(method) \ +DECLARE_FETCH_FUNC(method, u8); \ +DECLARE_FETCH_FUNC(method, u16); \ +DECLARE_FETCH_FUNC(method, u32); \ +DECLARE_FETCH_FUNC(method, u64) + +DECLARE_BASIC_FETCH_FUNCS(reg); +#define fetch_reg_string NULL +#define fetch_reg_string_size NULL + +DECLARE_BASIC_FETCH_FUNCS(retval); +#define fetch_retval_string NULL +#define fetch_retval_string_size NULL + +DECLARE_BASIC_FETCH_FUNCS(symbol); +DECLARE_FETCH_FUNC(symbol, string); +DECLARE_FETCH_FUNC(symbol, string_size); + +DECLARE_BASIC_FETCH_FUNCS(deref); +DECLARE_FETCH_FUNC(deref, string); +DECLARE_FETCH_FUNC(deref, string_size); + +DECLARE_BASIC_FETCH_FUNCS(bitfield); +#define fetch_bitfield_string NULL +#define fetch_bitfield_string_size NULL + +/* + * Define macro for basic types - we don't need to define s* types, because + * we have to care only about bitwidth at recording time. + */ +#define DEFINE_BASIC_FETCH_FUNCS(method) \ +DEFINE_FETCH_##method(u8) \ +DEFINE_FETCH_##method(u16) \ +DEFINE_FETCH_##method(u32) \ +DEFINE_FETCH_##method(u64) + +/* Default (unsigned long) fetch type */ +#define __DEFAULT_FETCH_TYPE(t) u##t +#define _DEFAULT_FETCH_TYPE(t) __DEFAULT_FETCH_TYPE(t) +#define DEFAULT_FETCH_TYPE _DEFAULT_FETCH_TYPE(BITS_PER_LONG) +#define DEFAULT_FETCH_TYPE_STR __stringify(DEFAULT_FETCH_TYPE) + +#define ASSIGN_FETCH_FUNC(method, type) \ + [FETCH_MTD_##method] = FETCH_FUNC_NAME(method, type) + +#define __ASSIGN_FETCH_TYPE(_name, ptype, ftype, _size, sign, _fmttype) \ + {.name = _name, \ + .size = _size, \ + .is_signed = sign, \ + .print = PRINT_TYPE_FUNC_NAME(ptype), \ + .fmt = PRINT_TYPE_FMT_NAME(ptype), \ + .fmttype = _fmttype, \ + .fetch = { \ +ASSIGN_FETCH_FUNC(reg, ftype), \ +ASSIGN_FETCH_FUNC(stack, ftype), \ +ASSIGN_FETCH_FUNC(retval, ftype), \ +ASSIGN_FETCH_FUNC(memory, ftype), \ +ASSIGN_FETCH_FUNC(symbol, ftype), \ +ASSIGN_FETCH_FUNC(deref, ftype), \ +ASSIGN_FETCH_FUNC(bitfield, ftype), \ +ASSIGN_FETCH_FUNC(file_offset, ftype), \ + } \ + } + +#define ASSIGN_FETCH_TYPE(ptype, ftype, sign) \ + __ASSIGN_FETCH_TYPE(#ptype, ptype, ftype, sizeof(ftype), sign, #ptype) + +#define ASSIGN_FETCH_TYPE_END {} + +#define FETCH_TYPE_STRING 0 +#define FETCH_TYPE_STRSIZE 1 + +#ifdef CONFIG_KPROBE_EVENT +struct symbol_cache; +unsigned long update_symbol_cache(struct symbol_cache *sc); +void free_symbol_cache(struct symbol_cache *sc); +struct symbol_cache *alloc_symbol_cache(const char *sym, long offset); +#else +/* uprobes do not support symbol fetch methods */ +#define fetch_symbol_u8 NULL +#define fetch_symbol_u16 NULL +#define fetch_symbol_u32 NULL +#define fetch_symbol_u64 NULL +#define fetch_symbol_string NULL +#define fetch_symbol_string_size NULL + +struct symbol_cache { +}; +static inline unsigned long __used update_symbol_cache(struct symbol_cache *sc) +{ + return 0; +} + +static inline void __used free_symbol_cache(struct symbol_cache *sc) +{ +} + +static inline struct symbol_cache * __used +alloc_symbol_cache(const char *sym, long offset) +{ + return NULL; +} +#endif /* CONFIG_KPROBE_EVENT */ + +struct probe_arg { + struct fetch_param fetch; + struct fetch_param fetch_size; + unsigned int offset; /* Offset from argument entry */ + const char *name; /* Name of this argument */ + const char *comm; /* Command of this argument */ + const struct fetch_type *type; /* Type of this argument */ +}; + +struct trace_probe { + unsigned int flags; /* For TP_FLAG_* */ + struct ftrace_event_class class; + struct ftrace_event_call call; + struct list_head files; + ssize_t size; /* trace entry size */ + unsigned int nr_args; + struct probe_arg args[]; +}; + +struct event_file_link { + struct ftrace_event_file *file; + struct list_head list; +}; + +static inline bool trace_probe_is_enabled(struct trace_probe *tp) +{ + return !!(tp->flags & (TP_FLAG_TRACE | TP_FLAG_PROFILE)); +} + +static inline bool trace_probe_is_registered(struct trace_probe *tp) +{ + return !!(tp->flags & TP_FLAG_REGISTERED); +} + +static nokprobe_inline void call_fetch(struct fetch_param *fprm, + struct pt_regs *regs, void *dest) +{ + return fprm->fn(regs, fprm->data, dest); +} + +/* Check the name is good for event/group/fields */ +static inline int is_good_name(const char *name) +{ + if (!isalpha(*name) && *name != '_') + return 0; + while (*++name != '\0') { + if (!isalpha(*name) && !isdigit(*name) && *name != '_') + return 0; + } + return 1; +} + +static inline struct event_file_link * +find_event_file_link(struct trace_probe *tp, struct ftrace_event_file *file) +{ + struct event_file_link *link; + + list_for_each_entry(link, &tp->files, list) + if (link->file == file) + return link; + + return NULL; +} + +extern int traceprobe_parse_probe_arg(char *arg, ssize_t *size, + struct probe_arg *parg, bool is_return, bool is_kprobe, + const struct fetch_type *ftbl); + +extern int traceprobe_conflict_field_name(const char *name, + struct probe_arg *args, int narg); + +extern void traceprobe_update_arg(struct probe_arg *arg); +extern void traceprobe_free_probe_arg(struct probe_arg *arg); + +extern int traceprobe_split_symbol_offset(char *symbol, unsigned long *offset); + +extern ssize_t traceprobe_probes_write(struct file *file, + const char __user *buffer, size_t count, loff_t *ppos, + int (*createfn)(int, char**)); + +extern int traceprobe_command(const char *buf, int (*createfn)(int, char**)); + +/* Sum up total data length for dynamic arraies (strings) */ +static nokprobe_inline int +__get_data_size(struct trace_probe *tp, struct pt_regs *regs) +{ + int i, ret = 0; + u32 len; + + for (i = 0; i < tp->nr_args; i++) + if (unlikely(tp->args[i].fetch_size.fn)) { + call_fetch(&tp->args[i].fetch_size, regs, &len); + ret += len; + } + + return ret; +} + +/* Store the value of each argument */ +static nokprobe_inline void +store_trace_args(int ent_size, struct trace_probe *tp, struct pt_regs *regs, + u8 *data, int maxlen) +{ + int i; + u32 end = tp->size; + u32 *dl; /* Data (relative) location */ + + for (i = 0; i < tp->nr_args; i++) { + if (unlikely(tp->args[i].fetch_size.fn)) { + /* + * First, we set the relative location and + * maximum data length to *dl + */ + dl = (u32 *)(data + tp->args[i].offset); + *dl = make_data_rloc(maxlen, end - tp->args[i].offset); + /* Then try to fetch string or dynamic array data */ + call_fetch(&tp->args[i].fetch, regs, dl); + /* Reduce maximum length */ + end += get_rloc_len(*dl); + maxlen -= get_rloc_len(*dl); + /* Trick here, convert data_rloc to data_loc */ + *dl = convert_rloc_to_loc(*dl, + ent_size + tp->args[i].offset); + } else + /* Just fetching data normally */ + call_fetch(&tp->args[i].fetch, regs, + data + tp->args[i].offset); + } +} + +extern int set_print_fmt(struct trace_probe *tp, bool is_return); diff --git a/kernel/kernel/trace/trace_sched_switch.c b/kernel/kernel/trace/trace_sched_switch.c new file mode 100644 index 000000000..419ca37e7 --- /dev/null +++ b/kernel/kernel/trace/trace_sched_switch.c @@ -0,0 +1,101 @@ +/* + * trace context switch + * + * Copyright (C) 2007 Steven Rostedt + * + */ +#include +#include +#include +#include +#include + +#include "trace.h" + +static int sched_ref; +static DEFINE_MUTEX(sched_register_mutex); + +static void +probe_sched_switch(void *ignore, struct task_struct *prev, struct task_struct *next) +{ + if (unlikely(!sched_ref)) + return; + + tracing_record_cmdline(prev); + tracing_record_cmdline(next); +} + +static void +probe_sched_wakeup(void *ignore, struct task_struct *wakee, int success) +{ + if (unlikely(!sched_ref)) + return; + + tracing_record_cmdline(current); +} + +static int tracing_sched_register(void) +{ + int ret; + + ret = register_trace_sched_wakeup(probe_sched_wakeup, NULL); + if (ret) { + pr_info("wakeup trace: Couldn't activate tracepoint" + " probe to kernel_sched_wakeup\n"); + return ret; + } + + ret = register_trace_sched_wakeup_new(probe_sched_wakeup, NULL); + if (ret) { + pr_info("wakeup trace: Couldn't activate tracepoint" + " probe to kernel_sched_wakeup_new\n"); + goto fail_deprobe; + } + + ret = register_trace_sched_switch(probe_sched_switch, NULL); + if (ret) { + pr_info("sched trace: Couldn't activate tracepoint" + " probe to kernel_sched_switch\n"); + goto fail_deprobe_wake_new; + } + + return ret; +fail_deprobe_wake_new: + unregister_trace_sched_wakeup_new(probe_sched_wakeup, NULL); +fail_deprobe: + unregister_trace_sched_wakeup(probe_sched_wakeup, NULL); + return ret; +} + +static void tracing_sched_unregister(void) +{ + unregister_trace_sched_switch(probe_sched_switch, NULL); + unregister_trace_sched_wakeup_new(probe_sched_wakeup, NULL); + unregister_trace_sched_wakeup(probe_sched_wakeup, NULL); +} + +static void tracing_start_sched_switch(void) +{ + mutex_lock(&sched_register_mutex); + if (!(sched_ref++)) + tracing_sched_register(); + mutex_unlock(&sched_register_mutex); +} + +static void tracing_stop_sched_switch(void) +{ + mutex_lock(&sched_register_mutex); + if (!(--sched_ref)) + tracing_sched_unregister(); + mutex_unlock(&sched_register_mutex); +} + +void tracing_start_cmdline_record(void) +{ + tracing_start_sched_switch(); +} + +void tracing_stop_cmdline_record(void) +{ + tracing_stop_sched_switch(); +} diff --git a/kernel/kernel/trace/trace_sched_wakeup.c b/kernel/kernel/trace/trace_sched_wakeup.c new file mode 100644 index 000000000..d6e100372 --- /dev/null +++ b/kernel/kernel/trace/trace_sched_wakeup.c @@ -0,0 +1,816 @@ +/* + * trace task wakeup timings + * + * Copyright (C) 2007-2008 Steven Rostedt + * Copyright (C) 2008 Ingo Molnar + * + * Based on code from the latency_tracer, that is: + * + * Copyright (C) 2004-2006 Ingo Molnar + * Copyright (C) 2004 Nadia Yvette Chambers + */ +#include +#include +#include +#include +#include +#include +#include +#include "trace.h" + +static struct trace_array *wakeup_trace; +static int __read_mostly tracer_enabled; + +static struct task_struct *wakeup_task; +static int wakeup_cpu; +static int wakeup_current_cpu; +static unsigned wakeup_prio = -1; +static int wakeup_rt; +static int wakeup_dl; +static int tracing_dl = 0; + +static arch_spinlock_t wakeup_lock = + (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED; + +static void wakeup_reset(struct trace_array *tr); +static void __wakeup_reset(struct trace_array *tr); +static int wakeup_graph_entry(struct ftrace_graph_ent *trace); +static void wakeup_graph_return(struct ftrace_graph_ret *trace); + +static int save_flags; +static bool function_enabled; + +#define TRACE_DISPLAY_GRAPH 1 + +static struct tracer_opt trace_opts[] = { +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + /* display latency trace as call graph */ + { TRACER_OPT(display-graph, TRACE_DISPLAY_GRAPH) }, +#endif + { } /* Empty entry */ +}; + +static struct tracer_flags tracer_flags = { + .val = 0, + .opts = trace_opts, +}; + +#define is_graph() (tracer_flags.val & TRACE_DISPLAY_GRAPH) + +#ifdef CONFIG_FUNCTION_TRACER + +/* + * Prologue for the wakeup function tracers. + * + * Returns 1 if it is OK to continue, and preemption + * is disabled and data->disabled is incremented. + * 0 if the trace is to be ignored, and preemption + * is not disabled and data->disabled is + * kept the same. + * + * Note, this function is also used outside this ifdef but + * inside the #ifdef of the function graph tracer below. + * This is OK, since the function graph tracer is + * dependent on the function tracer. + */ +static int +func_prolog_preempt_disable(struct trace_array *tr, + struct trace_array_cpu **data, + int *pc) +{ + long disabled; + int cpu; + + if (likely(!wakeup_task)) + return 0; + + *pc = preempt_count(); + preempt_disable_notrace(); + + cpu = raw_smp_processor_id(); + if (cpu != wakeup_current_cpu) + goto out_enable; + + *data = per_cpu_ptr(tr->trace_buffer.data, cpu); + disabled = atomic_inc_return(&(*data)->disabled); + if (unlikely(disabled != 1)) + goto out; + + return 1; + +out: + atomic_dec(&(*data)->disabled); + +out_enable: + preempt_enable_notrace(); + return 0; +} + +/* + * wakeup uses its own tracer function to keep the overhead down: + */ +static void +wakeup_tracer_call(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct pt_regs *pt_regs) +{ + struct trace_array *tr = wakeup_trace; + struct trace_array_cpu *data; + unsigned long flags; + int pc; + + if (!func_prolog_preempt_disable(tr, &data, &pc)) + return; + + local_irq_save(flags); + trace_function(tr, ip, parent_ip, flags, pc); + local_irq_restore(flags); + + atomic_dec(&data->disabled); + preempt_enable_notrace(); +} +#endif /* CONFIG_FUNCTION_TRACER */ + +static int register_wakeup_function(struct trace_array *tr, int graph, int set) +{ + int ret; + + /* 'set' is set if TRACE_ITER_FUNCTION is about to be set */ + if (function_enabled || (!set && !(trace_flags & TRACE_ITER_FUNCTION))) + return 0; + + if (graph) + ret = register_ftrace_graph(&wakeup_graph_return, + &wakeup_graph_entry); + else + ret = register_ftrace_function(tr->ops); + + if (!ret) + function_enabled = true; + + return ret; +} + +static void unregister_wakeup_function(struct trace_array *tr, int graph) +{ + if (!function_enabled) + return; + + if (graph) + unregister_ftrace_graph(); + else + unregister_ftrace_function(tr->ops); + + function_enabled = false; +} + +static void wakeup_function_set(struct trace_array *tr, int set) +{ + if (set) + register_wakeup_function(tr, is_graph(), 1); + else + unregister_wakeup_function(tr, is_graph()); +} + +static int wakeup_flag_changed(struct trace_array *tr, u32 mask, int set) +{ + struct tracer *tracer = tr->current_trace; + + if (mask & TRACE_ITER_FUNCTION) + wakeup_function_set(tr, set); + + return trace_keep_overwrite(tracer, mask, set); +} + +static int start_func_tracer(struct trace_array *tr, int graph) +{ + int ret; + + ret = register_wakeup_function(tr, graph, 0); + + if (!ret && tracing_is_enabled()) + tracer_enabled = 1; + else + tracer_enabled = 0; + + return ret; +} + +static void stop_func_tracer(struct trace_array *tr, int graph) +{ + tracer_enabled = 0; + + unregister_wakeup_function(tr, graph); +} + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER +static int +wakeup_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set) +{ + + if (!(bit & TRACE_DISPLAY_GRAPH)) + return -EINVAL; + + if (!(is_graph() ^ set)) + return 0; + + stop_func_tracer(tr, !set); + + wakeup_reset(wakeup_trace); + tr->max_latency = 0; + + return start_func_tracer(tr, set); +} + +static int wakeup_graph_entry(struct ftrace_graph_ent *trace) +{ + struct trace_array *tr = wakeup_trace; + struct trace_array_cpu *data; + unsigned long flags; + int pc, ret = 0; + + if (!func_prolog_preempt_disable(tr, &data, &pc)) + return 0; + + local_save_flags(flags); + ret = __trace_graph_entry(tr, trace, flags, pc); + atomic_dec(&data->disabled); + preempt_enable_notrace(); + + return ret; +} + +static void wakeup_graph_return(struct ftrace_graph_ret *trace) +{ + struct trace_array *tr = wakeup_trace; + struct trace_array_cpu *data; + unsigned long flags; + int pc; + + if (!func_prolog_preempt_disable(tr, &data, &pc)) + return; + + local_save_flags(flags); + __trace_graph_return(tr, trace, flags, pc); + atomic_dec(&data->disabled); + + preempt_enable_notrace(); + return; +} + +static void wakeup_trace_open(struct trace_iterator *iter) +{ + if (is_graph()) + graph_trace_open(iter); +} + +static void wakeup_trace_close(struct trace_iterator *iter) +{ + if (iter->private) + graph_trace_close(iter); +} + +#define GRAPH_TRACER_FLAGS (TRACE_GRAPH_PRINT_PROC | \ + TRACE_GRAPH_PRINT_ABS_TIME | \ + TRACE_GRAPH_PRINT_DURATION) + +static enum print_line_t wakeup_print_line(struct trace_iterator *iter) +{ + /* + * In graph mode call the graph tracer output function, + * otherwise go with the TRACE_FN event handler + */ + if (is_graph()) + return print_graph_function_flags(iter, GRAPH_TRACER_FLAGS); + + return TRACE_TYPE_UNHANDLED; +} + +static void wakeup_print_header(struct seq_file *s) +{ + if (is_graph()) + print_graph_headers_flags(s, GRAPH_TRACER_FLAGS); + else + trace_default_header(s); +} + +static void +__trace_function(struct trace_array *tr, + unsigned long ip, unsigned long parent_ip, + unsigned long flags, int pc) +{ + if (is_graph()) + trace_graph_function(tr, ip, parent_ip, flags, pc); + else + trace_function(tr, ip, parent_ip, flags, pc); +} +#else +#define __trace_function trace_function + +static int +wakeup_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set) +{ + return -EINVAL; +} + +static int wakeup_graph_entry(struct ftrace_graph_ent *trace) +{ + return -1; +} + +static enum print_line_t wakeup_print_line(struct trace_iterator *iter) +{ + return TRACE_TYPE_UNHANDLED; +} + +static void wakeup_graph_return(struct ftrace_graph_ret *trace) { } +static void wakeup_trace_open(struct trace_iterator *iter) { } +static void wakeup_trace_close(struct trace_iterator *iter) { } + +#ifdef CONFIG_FUNCTION_TRACER +static void wakeup_print_header(struct seq_file *s) +{ + trace_default_header(s); +} +#else +static void wakeup_print_header(struct seq_file *s) +{ + trace_latency_header(s); +} +#endif /* CONFIG_FUNCTION_TRACER */ +#endif /* CONFIG_FUNCTION_GRAPH_TRACER */ + +/* + * Should this new latency be reported/recorded? + */ +static int report_latency(struct trace_array *tr, cycle_t delta) +{ + if (tracing_thresh) { + if (delta < tracing_thresh) + return 0; + } else { + if (delta <= tr->max_latency) + return 0; + } + return 1; +} + +static void +probe_wakeup_migrate_task(void *ignore, struct task_struct *task, int cpu) +{ + if (task != wakeup_task) + return; + + wakeup_current_cpu = cpu; +} + +static void +tracing_sched_switch_trace(struct trace_array *tr, + struct task_struct *prev, + struct task_struct *next, + unsigned long flags, int pc) +{ + struct ftrace_event_call *call = &event_context_switch; + struct ring_buffer *buffer = tr->trace_buffer.buffer; + struct ring_buffer_event *event; + struct ctx_switch_entry *entry; + + event = trace_buffer_lock_reserve(buffer, TRACE_CTX, + sizeof(*entry), flags, pc); + if (!event) + return; + entry = ring_buffer_event_data(event); + entry->prev_pid = prev->pid; + entry->prev_prio = prev->prio; + entry->prev_state = prev->state; + entry->next_pid = next->pid; + entry->next_prio = next->prio; + entry->next_state = next->state; + entry->next_cpu = task_cpu(next); + + if (!call_filter_check_discard(call, entry, buffer, event)) + trace_buffer_unlock_commit(buffer, event, flags, pc); +} + +static void +tracing_sched_wakeup_trace(struct trace_array *tr, + struct task_struct *wakee, + struct task_struct *curr, + unsigned long flags, int pc) +{ + struct ftrace_event_call *call = &event_wakeup; + struct ring_buffer_event *event; + struct ctx_switch_entry *entry; + struct ring_buffer *buffer = tr->trace_buffer.buffer; + + event = trace_buffer_lock_reserve(buffer, TRACE_WAKE, + sizeof(*entry), flags, pc); + if (!event) + return; + entry = ring_buffer_event_data(event); + entry->prev_pid = curr->pid; + entry->prev_prio = curr->prio; + entry->prev_state = curr->state; + entry->next_pid = wakee->pid; + entry->next_prio = wakee->prio; + entry->next_state = wakee->state; + entry->next_cpu = task_cpu(wakee); + + if (!call_filter_check_discard(call, entry, buffer, event)) + trace_buffer_unlock_commit(buffer, event, flags, pc); +} + +static void notrace +probe_wakeup_sched_switch(void *ignore, + struct task_struct *prev, struct task_struct *next) +{ + struct trace_array_cpu *data; + cycle_t T0, T1, delta; + unsigned long flags; + long disabled; + int cpu; + int pc; + + tracing_record_cmdline(prev); + + if (unlikely(!tracer_enabled)) + return; + + /* + * When we start a new trace, we set wakeup_task to NULL + * and then set tracer_enabled = 1. We want to make sure + * that another CPU does not see the tracer_enabled = 1 + * and the wakeup_task with an older task, that might + * actually be the same as next. + */ + smp_rmb(); + + if (next != wakeup_task) + return; + + pc = preempt_count(); + + /* disable local data, not wakeup_cpu data */ + cpu = raw_smp_processor_id(); + disabled = atomic_inc_return(&per_cpu_ptr(wakeup_trace->trace_buffer.data, cpu)->disabled); + if (likely(disabled != 1)) + goto out; + + local_irq_save(flags); + arch_spin_lock(&wakeup_lock); + + /* We could race with grabbing wakeup_lock */ + if (unlikely(!tracer_enabled || next != wakeup_task)) + goto out_unlock; + + /* The task we are waiting for is waking up */ + data = per_cpu_ptr(wakeup_trace->trace_buffer.data, wakeup_cpu); + + __trace_function(wakeup_trace, CALLER_ADDR0, CALLER_ADDR1, flags, pc); + tracing_sched_switch_trace(wakeup_trace, prev, next, flags, pc); + + T0 = data->preempt_timestamp; + T1 = ftrace_now(cpu); + delta = T1-T0; + + if (!report_latency(wakeup_trace, delta)) + goto out_unlock; + + if (likely(!is_tracing_stopped())) { + wakeup_trace->max_latency = delta; + update_max_tr(wakeup_trace, wakeup_task, wakeup_cpu); + } + +out_unlock: + __wakeup_reset(wakeup_trace); + arch_spin_unlock(&wakeup_lock); + local_irq_restore(flags); +out: + atomic_dec(&per_cpu_ptr(wakeup_trace->trace_buffer.data, cpu)->disabled); +} + +static void __wakeup_reset(struct trace_array *tr) +{ + wakeup_cpu = -1; + wakeup_prio = -1; + tracing_dl = 0; + + if (wakeup_task) + put_task_struct(wakeup_task); + + wakeup_task = NULL; +} + +static void wakeup_reset(struct trace_array *tr) +{ + unsigned long flags; + + tracing_reset_online_cpus(&tr->trace_buffer); + + local_irq_save(flags); + arch_spin_lock(&wakeup_lock); + __wakeup_reset(tr); + arch_spin_unlock(&wakeup_lock); + local_irq_restore(flags); +} + +static void +probe_wakeup(void *ignore, struct task_struct *p, int success) +{ + struct trace_array_cpu *data; + int cpu = smp_processor_id(); + unsigned long flags; + long disabled; + int pc; + + if (likely(!tracer_enabled)) + return; + + tracing_record_cmdline(p); + tracing_record_cmdline(current); + + /* + * Semantic is like this: + * - wakeup tracer handles all tasks in the system, independently + * from their scheduling class; + * - wakeup_rt tracer handles tasks belonging to sched_dl and + * sched_rt class; + * - wakeup_dl handles tasks belonging to sched_dl class only. + */ + if (tracing_dl || (wakeup_dl && !dl_task(p)) || + (wakeup_rt && !dl_task(p) && !rt_task(p)) || + (!dl_task(p) && (p->prio >= wakeup_prio || p->prio >= current->prio))) + return; + + pc = preempt_count(); + disabled = atomic_inc_return(&per_cpu_ptr(wakeup_trace->trace_buffer.data, cpu)->disabled); + if (unlikely(disabled != 1)) + goto out; + + /* interrupts should be off from try_to_wake_up */ + arch_spin_lock(&wakeup_lock); + + /* check for races. */ + if (!tracer_enabled || tracing_dl || + (!dl_task(p) && p->prio >= wakeup_prio)) + goto out_locked; + + /* reset the trace */ + __wakeup_reset(wakeup_trace); + + wakeup_cpu = task_cpu(p); + wakeup_current_cpu = wakeup_cpu; + wakeup_prio = p->prio; + + /* + * Once you start tracing a -deadline task, don't bother tracing + * another task until the first one wakes up. + */ + if (dl_task(p)) + tracing_dl = 1; + else + tracing_dl = 0; + + wakeup_task = p; + get_task_struct(wakeup_task); + + local_save_flags(flags); + + data = per_cpu_ptr(wakeup_trace->trace_buffer.data, wakeup_cpu); + data->preempt_timestamp = ftrace_now(cpu); + tracing_sched_wakeup_trace(wakeup_trace, p, current, flags, pc); + + /* + * We must be careful in using CALLER_ADDR2. But since wake_up + * is not called by an assembly function (where as schedule is) + * it should be safe to use it here. + */ + __trace_function(wakeup_trace, CALLER_ADDR1, CALLER_ADDR2, flags, pc); + +out_locked: + arch_spin_unlock(&wakeup_lock); +out: + atomic_dec(&per_cpu_ptr(wakeup_trace->trace_buffer.data, cpu)->disabled); +} + +static void start_wakeup_tracer(struct trace_array *tr) +{ + int ret; + + ret = register_trace_sched_wakeup(probe_wakeup, NULL); + if (ret) { + pr_info("wakeup trace: Couldn't activate tracepoint" + " probe to kernel_sched_wakeup\n"); + return; + } + + ret = register_trace_sched_wakeup_new(probe_wakeup, NULL); + if (ret) { + pr_info("wakeup trace: Couldn't activate tracepoint" + " probe to kernel_sched_wakeup_new\n"); + goto fail_deprobe; + } + + ret = register_trace_sched_switch(probe_wakeup_sched_switch, NULL); + if (ret) { + pr_info("sched trace: Couldn't activate tracepoint" + " probe to kernel_sched_switch\n"); + goto fail_deprobe_wake_new; + } + + ret = register_trace_sched_migrate_task(probe_wakeup_migrate_task, NULL); + if (ret) { + pr_info("wakeup trace: Couldn't activate tracepoint" + " probe to kernel_sched_migrate_task\n"); + return; + } + + wakeup_reset(tr); + + /* + * Don't let the tracer_enabled = 1 show up before + * the wakeup_task is reset. This may be overkill since + * wakeup_reset does a spin_unlock after setting the + * wakeup_task to NULL, but I want to be safe. + * This is a slow path anyway. + */ + smp_wmb(); + + if (start_func_tracer(tr, is_graph())) + printk(KERN_ERR "failed to start wakeup tracer\n"); + + return; +fail_deprobe_wake_new: + unregister_trace_sched_wakeup_new(probe_wakeup, NULL); +fail_deprobe: + unregister_trace_sched_wakeup(probe_wakeup, NULL); +} + +static void stop_wakeup_tracer(struct trace_array *tr) +{ + tracer_enabled = 0; + stop_func_tracer(tr, is_graph()); + unregister_trace_sched_switch(probe_wakeup_sched_switch, NULL); + unregister_trace_sched_wakeup_new(probe_wakeup, NULL); + unregister_trace_sched_wakeup(probe_wakeup, NULL); + unregister_trace_sched_migrate_task(probe_wakeup_migrate_task, NULL); +} + +static bool wakeup_busy; + +static int __wakeup_tracer_init(struct trace_array *tr) +{ + save_flags = trace_flags; + + /* non overwrite screws up the latency tracers */ + set_tracer_flag(tr, TRACE_ITER_OVERWRITE, 1); + set_tracer_flag(tr, TRACE_ITER_LATENCY_FMT, 1); + + tr->max_latency = 0; + wakeup_trace = tr; + ftrace_init_array_ops(tr, wakeup_tracer_call); + start_wakeup_tracer(tr); + + wakeup_busy = true; + return 0; +} + +static int wakeup_tracer_init(struct trace_array *tr) +{ + if (wakeup_busy) + return -EBUSY; + + wakeup_dl = 0; + wakeup_rt = 0; + return __wakeup_tracer_init(tr); +} + +static int wakeup_rt_tracer_init(struct trace_array *tr) +{ + if (wakeup_busy) + return -EBUSY; + + wakeup_dl = 0; + wakeup_rt = 1; + return __wakeup_tracer_init(tr); +} + +static int wakeup_dl_tracer_init(struct trace_array *tr) +{ + if (wakeup_busy) + return -EBUSY; + + wakeup_dl = 1; + wakeup_rt = 0; + return __wakeup_tracer_init(tr); +} + +static void wakeup_tracer_reset(struct trace_array *tr) +{ + int lat_flag = save_flags & TRACE_ITER_LATENCY_FMT; + int overwrite_flag = save_flags & TRACE_ITER_OVERWRITE; + + stop_wakeup_tracer(tr); + /* make sure we put back any tasks we are tracing */ + wakeup_reset(tr); + + set_tracer_flag(tr, TRACE_ITER_LATENCY_FMT, lat_flag); + set_tracer_flag(tr, TRACE_ITER_OVERWRITE, overwrite_flag); + ftrace_reset_array_ops(tr); + wakeup_busy = false; +} + +static void wakeup_tracer_start(struct trace_array *tr) +{ + wakeup_reset(tr); + tracer_enabled = 1; +} + +static void wakeup_tracer_stop(struct trace_array *tr) +{ + tracer_enabled = 0; +} + +static struct tracer wakeup_tracer __read_mostly = +{ + .name = "wakeup", + .init = wakeup_tracer_init, + .reset = wakeup_tracer_reset, + .start = wakeup_tracer_start, + .stop = wakeup_tracer_stop, + .print_max = true, + .print_header = wakeup_print_header, + .print_line = wakeup_print_line, + .flags = &tracer_flags, + .set_flag = wakeup_set_flag, + .flag_changed = wakeup_flag_changed, +#ifdef CONFIG_FTRACE_SELFTEST + .selftest = trace_selftest_startup_wakeup, +#endif + .open = wakeup_trace_open, + .close = wakeup_trace_close, + .allow_instances = true, + .use_max_tr = true, +}; + +static struct tracer wakeup_rt_tracer __read_mostly = +{ + .name = "wakeup_rt", + .init = wakeup_rt_tracer_init, + .reset = wakeup_tracer_reset, + .start = wakeup_tracer_start, + .stop = wakeup_tracer_stop, + .print_max = true, + .print_header = wakeup_print_header, + .print_line = wakeup_print_line, + .flags = &tracer_flags, + .set_flag = wakeup_set_flag, + .flag_changed = wakeup_flag_changed, +#ifdef CONFIG_FTRACE_SELFTEST + .selftest = trace_selftest_startup_wakeup, +#endif + .open = wakeup_trace_open, + .close = wakeup_trace_close, + .allow_instances = true, + .use_max_tr = true, +}; + +static struct tracer wakeup_dl_tracer __read_mostly = +{ + .name = "wakeup_dl", + .init = wakeup_dl_tracer_init, + .reset = wakeup_tracer_reset, + .start = wakeup_tracer_start, + .stop = wakeup_tracer_stop, + .print_max = true, + .print_header = wakeup_print_header, + .print_line = wakeup_print_line, + .flags = &tracer_flags, + .set_flag = wakeup_set_flag, + .flag_changed = wakeup_flag_changed, +#ifdef CONFIG_FTRACE_SELFTEST + .selftest = trace_selftest_startup_wakeup, +#endif + .open = wakeup_trace_open, + .close = wakeup_trace_close, + .use_max_tr = true, +}; + +__init static int init_wakeup_tracer(void) +{ + int ret; + + ret = register_tracer(&wakeup_tracer); + if (ret) + return ret; + + ret = register_tracer(&wakeup_rt_tracer); + if (ret) + return ret; + + ret = register_tracer(&wakeup_dl_tracer); + if (ret) + return ret; + + return 0; +} +core_initcall(init_wakeup_tracer); diff --git a/kernel/kernel/trace/trace_selftest.c b/kernel/kernel/trace/trace_selftest.c new file mode 100644 index 000000000..b0f86ea77 --- /dev/null +++ b/kernel/kernel/trace/trace_selftest.c @@ -0,0 +1,1215 @@ +/* Include in trace.c */ + +#include +#include +#include +#include + +static inline int trace_valid_entry(struct trace_entry *entry) +{ + switch (entry->type) { + case TRACE_FN: + case TRACE_CTX: + case TRACE_WAKE: + case TRACE_STACK: + case TRACE_PRINT: + case TRACE_BRANCH: + case TRACE_GRAPH_ENT: + case TRACE_GRAPH_RET: + return 1; + } + return 0; +} + +static int trace_test_buffer_cpu(struct trace_buffer *buf, int cpu) +{ + struct ring_buffer_event *event; + struct trace_entry *entry; + unsigned int loops = 0; + + while ((event = ring_buffer_consume(buf->buffer, cpu, NULL, NULL))) { + entry = ring_buffer_event_data(event); + + /* + * The ring buffer is a size of trace_buf_size, if + * we loop more than the size, there's something wrong + * with the ring buffer. + */ + if (loops++ > trace_buf_size) { + printk(KERN_CONT ".. bad ring buffer "); + goto failed; + } + if (!trace_valid_entry(entry)) { + printk(KERN_CONT ".. invalid entry %d ", + entry->type); + goto failed; + } + } + return 0; + + failed: + /* disable tracing */ + tracing_disabled = 1; + printk(KERN_CONT ".. corrupted trace buffer .. "); + return -1; +} + +/* + * Test the trace buffer to see if all the elements + * are still sane. + */ +static int trace_test_buffer(struct trace_buffer *buf, unsigned long *count) +{ + unsigned long flags, cnt = 0; + int cpu, ret = 0; + + /* Don't allow flipping of max traces now */ + local_irq_save(flags); + arch_spin_lock(&buf->tr->max_lock); + + cnt = ring_buffer_entries(buf->buffer); + + /* + * The trace_test_buffer_cpu runs a while loop to consume all data. + * If the calling tracer is broken, and is constantly filling + * the buffer, this will run forever, and hard lock the box. + * We disable the ring buffer while we do this test to prevent + * a hard lock up. + */ + tracing_off(); + for_each_possible_cpu(cpu) { + ret = trace_test_buffer_cpu(buf, cpu); + if (ret) + break; + } + tracing_on(); + arch_spin_unlock(&buf->tr->max_lock); + local_irq_restore(flags); + + if (count) + *count = cnt; + + return ret; +} + +static inline void warn_failed_init_tracer(struct tracer *trace, int init_ret) +{ + printk(KERN_WARNING "Failed to init %s tracer, init returned %d\n", + trace->name, init_ret); +} +#ifdef CONFIG_FUNCTION_TRACER + +#ifdef CONFIG_DYNAMIC_FTRACE + +static int trace_selftest_test_probe1_cnt; +static void trace_selftest_test_probe1_func(unsigned long ip, + unsigned long pip, + struct ftrace_ops *op, + struct pt_regs *pt_regs) +{ + trace_selftest_test_probe1_cnt++; +} + +static int trace_selftest_test_probe2_cnt; +static void trace_selftest_test_probe2_func(unsigned long ip, + unsigned long pip, + struct ftrace_ops *op, + struct pt_regs *pt_regs) +{ + trace_selftest_test_probe2_cnt++; +} + +static int trace_selftest_test_probe3_cnt; +static void trace_selftest_test_probe3_func(unsigned long ip, + unsigned long pip, + struct ftrace_ops *op, + struct pt_regs *pt_regs) +{ + trace_selftest_test_probe3_cnt++; +} + +static int trace_selftest_test_global_cnt; +static void trace_selftest_test_global_func(unsigned long ip, + unsigned long pip, + struct ftrace_ops *op, + struct pt_regs *pt_regs) +{ + trace_selftest_test_global_cnt++; +} + +static int trace_selftest_test_dyn_cnt; +static void trace_selftest_test_dyn_func(unsigned long ip, + unsigned long pip, + struct ftrace_ops *op, + struct pt_regs *pt_regs) +{ + trace_selftest_test_dyn_cnt++; +} + +static struct ftrace_ops test_probe1 = { + .func = trace_selftest_test_probe1_func, + .flags = FTRACE_OPS_FL_RECURSION_SAFE, +}; + +static struct ftrace_ops test_probe2 = { + .func = trace_selftest_test_probe2_func, + .flags = FTRACE_OPS_FL_RECURSION_SAFE, +}; + +static struct ftrace_ops test_probe3 = { + .func = trace_selftest_test_probe3_func, + .flags = FTRACE_OPS_FL_RECURSION_SAFE, +}; + +static void print_counts(void) +{ + printk("(%d %d %d %d %d) ", + trace_selftest_test_probe1_cnt, + trace_selftest_test_probe2_cnt, + trace_selftest_test_probe3_cnt, + trace_selftest_test_global_cnt, + trace_selftest_test_dyn_cnt); +} + +static void reset_counts(void) +{ + trace_selftest_test_probe1_cnt = 0; + trace_selftest_test_probe2_cnt = 0; + trace_selftest_test_probe3_cnt = 0; + trace_selftest_test_global_cnt = 0; + trace_selftest_test_dyn_cnt = 0; +} + +static int trace_selftest_ops(struct trace_array *tr, int cnt) +{ + int save_ftrace_enabled = ftrace_enabled; + struct ftrace_ops *dyn_ops; + char *func1_name; + char *func2_name; + int len1; + int len2; + int ret = -1; + + printk(KERN_CONT "PASSED\n"); + pr_info("Testing dynamic ftrace ops #%d: ", cnt); + + ftrace_enabled = 1; + reset_counts(); + + /* Handle PPC64 '.' name */ + func1_name = "*" __stringify(DYN_FTRACE_TEST_NAME); + func2_name = "*" __stringify(DYN_FTRACE_TEST_NAME2); + len1 = strlen(func1_name); + len2 = strlen(func2_name); + + /* + * Probe 1 will trace function 1. + * Probe 2 will trace function 2. + * Probe 3 will trace functions 1 and 2. + */ + ftrace_set_filter(&test_probe1, func1_name, len1, 1); + ftrace_set_filter(&test_probe2, func2_name, len2, 1); + ftrace_set_filter(&test_probe3, func1_name, len1, 1); + ftrace_set_filter(&test_probe3, func2_name, len2, 0); + + register_ftrace_function(&test_probe1); + register_ftrace_function(&test_probe2); + register_ftrace_function(&test_probe3); + /* First time we are running with main function */ + if (cnt > 1) { + ftrace_init_array_ops(tr, trace_selftest_test_global_func); + register_ftrace_function(tr->ops); + } + + DYN_FTRACE_TEST_NAME(); + + print_counts(); + + if (trace_selftest_test_probe1_cnt != 1) + goto out; + if (trace_selftest_test_probe2_cnt != 0) + goto out; + if (trace_selftest_test_probe3_cnt != 1) + goto out; + if (cnt > 1) { + if (trace_selftest_test_global_cnt == 0) + goto out; + } + + DYN_FTRACE_TEST_NAME2(); + + print_counts(); + + if (trace_selftest_test_probe1_cnt != 1) + goto out; + if (trace_selftest_test_probe2_cnt != 1) + goto out; + if (trace_selftest_test_probe3_cnt != 2) + goto out; + + /* Add a dynamic probe */ + dyn_ops = kzalloc(sizeof(*dyn_ops), GFP_KERNEL); + if (!dyn_ops) { + printk("MEMORY ERROR "); + goto out; + } + + dyn_ops->func = trace_selftest_test_dyn_func; + + register_ftrace_function(dyn_ops); + + trace_selftest_test_global_cnt = 0; + + DYN_FTRACE_TEST_NAME(); + + print_counts(); + + if (trace_selftest_test_probe1_cnt != 2) + goto out_free; + if (trace_selftest_test_probe2_cnt != 1) + goto out_free; + if (trace_selftest_test_probe3_cnt != 3) + goto out_free; + if (cnt > 1) { + if (trace_selftest_test_global_cnt == 0) + goto out; + } + if (trace_selftest_test_dyn_cnt == 0) + goto out_free; + + DYN_FTRACE_TEST_NAME2(); + + print_counts(); + + if (trace_selftest_test_probe1_cnt != 2) + goto out_free; + if (trace_selftest_test_probe2_cnt != 2) + goto out_free; + if (trace_selftest_test_probe3_cnt != 4) + goto out_free; + + ret = 0; + out_free: + unregister_ftrace_function(dyn_ops); + kfree(dyn_ops); + + out: + /* Purposely unregister in the same order */ + unregister_ftrace_function(&test_probe1); + unregister_ftrace_function(&test_probe2); + unregister_ftrace_function(&test_probe3); + if (cnt > 1) + unregister_ftrace_function(tr->ops); + ftrace_reset_array_ops(tr); + + /* Make sure everything is off */ + reset_counts(); + DYN_FTRACE_TEST_NAME(); + DYN_FTRACE_TEST_NAME(); + + if (trace_selftest_test_probe1_cnt || + trace_selftest_test_probe2_cnt || + trace_selftest_test_probe3_cnt || + trace_selftest_test_global_cnt || + trace_selftest_test_dyn_cnt) + ret = -1; + + ftrace_enabled = save_ftrace_enabled; + + return ret; +} + +/* Test dynamic code modification and ftrace filters */ +static int trace_selftest_startup_dynamic_tracing(struct tracer *trace, + struct trace_array *tr, + int (*func)(void)) +{ + int save_ftrace_enabled = ftrace_enabled; + unsigned long count; + char *func_name; + int ret; + + /* The ftrace test PASSED */ + printk(KERN_CONT "PASSED\n"); + pr_info("Testing dynamic ftrace: "); + + /* enable tracing, and record the filter function */ + ftrace_enabled = 1; + + /* passed in by parameter to fool gcc from optimizing */ + func(); + + /* + * Some archs *cough*PowerPC*cough* add characters to the + * start of the function names. We simply put a '*' to + * accommodate them. + */ + func_name = "*" __stringify(DYN_FTRACE_TEST_NAME); + + /* filter only on our function */ + ftrace_set_global_filter(func_name, strlen(func_name), 1); + + /* enable tracing */ + ret = tracer_init(trace, tr); + if (ret) { + warn_failed_init_tracer(trace, ret); + goto out; + } + + /* Sleep for a 1/10 of a second */ + msleep(100); + + /* we should have nothing in the buffer */ + ret = trace_test_buffer(&tr->trace_buffer, &count); + if (ret) + goto out; + + if (count) { + ret = -1; + printk(KERN_CONT ".. filter did not filter .. "); + goto out; + } + + /* call our function again */ + func(); + + /* sleep again */ + msleep(100); + + /* stop the tracing. */ + tracing_stop(); + ftrace_enabled = 0; + + /* check the trace buffer */ + ret = trace_test_buffer(&tr->trace_buffer, &count); + + ftrace_enabled = 1; + tracing_start(); + + /* we should only have one item */ + if (!ret && count != 1) { + trace->reset(tr); + printk(KERN_CONT ".. filter failed count=%ld ..", count); + ret = -1; + goto out; + } + + /* Test the ops with global tracing running */ + ret = trace_selftest_ops(tr, 1); + trace->reset(tr); + + out: + ftrace_enabled = save_ftrace_enabled; + + /* Enable tracing on all functions again */ + ftrace_set_global_filter(NULL, 0, 1); + + /* Test the ops with global tracing off */ + if (!ret) + ret = trace_selftest_ops(tr, 2); + + return ret; +} + +static int trace_selftest_recursion_cnt; +static void trace_selftest_test_recursion_func(unsigned long ip, + unsigned long pip, + struct ftrace_ops *op, + struct pt_regs *pt_regs) +{ + /* + * This function is registered without the recursion safe flag. + * The ftrace infrastructure should provide the recursion + * protection. If not, this will crash the kernel! + */ + if (trace_selftest_recursion_cnt++ > 10) + return; + DYN_FTRACE_TEST_NAME(); +} + +static void trace_selftest_test_recursion_safe_func(unsigned long ip, + unsigned long pip, + struct ftrace_ops *op, + struct pt_regs *pt_regs) +{ + /* + * We said we would provide our own recursion. By calling + * this function again, we should recurse back into this function + * and count again. But this only happens if the arch supports + * all of ftrace features and nothing else is using the function + * tracing utility. + */ + if (trace_selftest_recursion_cnt++) + return; + DYN_FTRACE_TEST_NAME(); +} + +static struct ftrace_ops test_rec_probe = { + .func = trace_selftest_test_recursion_func, +}; + +static struct ftrace_ops test_recsafe_probe = { + .func = trace_selftest_test_recursion_safe_func, + .flags = FTRACE_OPS_FL_RECURSION_SAFE, +}; + +static int +trace_selftest_function_recursion(void) +{ + int save_ftrace_enabled = ftrace_enabled; + char *func_name; + int len; + int ret; + + /* The previous test PASSED */ + pr_cont("PASSED\n"); + pr_info("Testing ftrace recursion: "); + + + /* enable tracing, and record the filter function */ + ftrace_enabled = 1; + + /* Handle PPC64 '.' name */ + func_name = "*" __stringify(DYN_FTRACE_TEST_NAME); + len = strlen(func_name); + + ret = ftrace_set_filter(&test_rec_probe, func_name, len, 1); + if (ret) { + pr_cont("*Could not set filter* "); + goto out; + } + + ret = register_ftrace_function(&test_rec_probe); + if (ret) { + pr_cont("*could not register callback* "); + goto out; + } + + DYN_FTRACE_TEST_NAME(); + + unregister_ftrace_function(&test_rec_probe); + + ret = -1; + if (trace_selftest_recursion_cnt != 1) { + pr_cont("*callback not called once (%d)* ", + trace_selftest_recursion_cnt); + goto out; + } + + trace_selftest_recursion_cnt = 1; + + pr_cont("PASSED\n"); + pr_info("Testing ftrace recursion safe: "); + + ret = ftrace_set_filter(&test_recsafe_probe, func_name, len, 1); + if (ret) { + pr_cont("*Could not set filter* "); + goto out; + } + + ret = register_ftrace_function(&test_recsafe_probe); + if (ret) { + pr_cont("*could not register callback* "); + goto out; + } + + DYN_FTRACE_TEST_NAME(); + + unregister_ftrace_function(&test_recsafe_probe); + + ret = -1; + if (trace_selftest_recursion_cnt != 2) { + pr_cont("*callback not called expected 2 times (%d)* ", + trace_selftest_recursion_cnt); + goto out; + } + + ret = 0; +out: + ftrace_enabled = save_ftrace_enabled; + + return ret; +} +#else +# define trace_selftest_startup_dynamic_tracing(trace, tr, func) ({ 0; }) +# define trace_selftest_function_recursion() ({ 0; }) +#endif /* CONFIG_DYNAMIC_FTRACE */ + +static enum { + TRACE_SELFTEST_REGS_START, + TRACE_SELFTEST_REGS_FOUND, + TRACE_SELFTEST_REGS_NOT_FOUND, +} trace_selftest_regs_stat; + +static void trace_selftest_test_regs_func(unsigned long ip, + unsigned long pip, + struct ftrace_ops *op, + struct pt_regs *pt_regs) +{ + if (pt_regs) + trace_selftest_regs_stat = TRACE_SELFTEST_REGS_FOUND; + else + trace_selftest_regs_stat = TRACE_SELFTEST_REGS_NOT_FOUND; +} + +static struct ftrace_ops test_regs_probe = { + .func = trace_selftest_test_regs_func, + .flags = FTRACE_OPS_FL_RECURSION_SAFE | FTRACE_OPS_FL_SAVE_REGS, +}; + +static int +trace_selftest_function_regs(void) +{ + int save_ftrace_enabled = ftrace_enabled; + char *func_name; + int len; + int ret; + int supported = 0; + +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS + supported = 1; +#endif + + /* The previous test PASSED */ + pr_cont("PASSED\n"); + pr_info("Testing ftrace regs%s: ", + !supported ? "(no arch support)" : ""); + + /* enable tracing, and record the filter function */ + ftrace_enabled = 1; + + /* Handle PPC64 '.' name */ + func_name = "*" __stringify(DYN_FTRACE_TEST_NAME); + len = strlen(func_name); + + ret = ftrace_set_filter(&test_regs_probe, func_name, len, 1); + /* + * If DYNAMIC_FTRACE is not set, then we just trace all functions. + * This test really doesn't care. + */ + if (ret && ret != -ENODEV) { + pr_cont("*Could not set filter* "); + goto out; + } + + ret = register_ftrace_function(&test_regs_probe); + /* + * Now if the arch does not support passing regs, then this should + * have failed. + */ + if (!supported) { + if (!ret) { + pr_cont("*registered save-regs without arch support* "); + goto out; + } + test_regs_probe.flags |= FTRACE_OPS_FL_SAVE_REGS_IF_SUPPORTED; + ret = register_ftrace_function(&test_regs_probe); + } + if (ret) { + pr_cont("*could not register callback* "); + goto out; + } + + + DYN_FTRACE_TEST_NAME(); + + unregister_ftrace_function(&test_regs_probe); + + ret = -1; + + switch (trace_selftest_regs_stat) { + case TRACE_SELFTEST_REGS_START: + pr_cont("*callback never called* "); + goto out; + + case TRACE_SELFTEST_REGS_FOUND: + if (supported) + break; + pr_cont("*callback received regs without arch support* "); + goto out; + + case TRACE_SELFTEST_REGS_NOT_FOUND: + if (!supported) + break; + pr_cont("*callback received NULL regs* "); + goto out; + } + + ret = 0; +out: + ftrace_enabled = save_ftrace_enabled; + + return ret; +} + +/* + * Simple verification test of ftrace function tracer. + * Enable ftrace, sleep 1/10 second, and then read the trace + * buffer to see if all is in order. + */ +__init int +trace_selftest_startup_function(struct tracer *trace, struct trace_array *tr) +{ + int save_ftrace_enabled = ftrace_enabled; + unsigned long count; + int ret; + +#ifdef CONFIG_DYNAMIC_FTRACE + if (ftrace_filter_param) { + printk(KERN_CONT " ... kernel command line filter set: force PASS ... "); + return 0; + } +#endif + + /* make sure msleep has been recorded */ + msleep(1); + + /* start the tracing */ + ftrace_enabled = 1; + + ret = tracer_init(trace, tr); + if (ret) { + warn_failed_init_tracer(trace, ret); + goto out; + } + + /* Sleep for a 1/10 of a second */ + msleep(100); + /* stop the tracing. */ + tracing_stop(); + ftrace_enabled = 0; + + /* check the trace buffer */ + ret = trace_test_buffer(&tr->trace_buffer, &count); + + ftrace_enabled = 1; + trace->reset(tr); + tracing_start(); + + if (!ret && !count) { + printk(KERN_CONT ".. no entries found .."); + ret = -1; + goto out; + } + + ret = trace_selftest_startup_dynamic_tracing(trace, tr, + DYN_FTRACE_TEST_NAME); + if (ret) + goto out; + + ret = trace_selftest_function_recursion(); + if (ret) + goto out; + + ret = trace_selftest_function_regs(); + out: + ftrace_enabled = save_ftrace_enabled; + + /* kill ftrace totally if we failed */ + if (ret) + ftrace_kill(); + + return ret; +} +#endif /* CONFIG_FUNCTION_TRACER */ + + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + +/* Maximum number of functions to trace before diagnosing a hang */ +#define GRAPH_MAX_FUNC_TEST 100000000 + +static unsigned int graph_hang_thresh; + +/* Wrap the real function entry probe to avoid possible hanging */ +static int trace_graph_entry_watchdog(struct ftrace_graph_ent *trace) +{ + /* This is harmlessly racy, we want to approximately detect a hang */ + if (unlikely(++graph_hang_thresh > GRAPH_MAX_FUNC_TEST)) { + ftrace_graph_stop(); + printk(KERN_WARNING "BUG: Function graph tracer hang!\n"); + if (ftrace_dump_on_oops) { + ftrace_dump(DUMP_ALL); + /* ftrace_dump() disables tracing */ + tracing_on(); + } + return 0; + } + + return trace_graph_entry(trace); +} + +/* + * Pretty much the same than for the function tracer from which the selftest + * has been borrowed. + */ +__init int +trace_selftest_startup_function_graph(struct tracer *trace, + struct trace_array *tr) +{ + int ret; + unsigned long count; + +#ifdef CONFIG_DYNAMIC_FTRACE + if (ftrace_filter_param) { + printk(KERN_CONT " ... kernel command line filter set: force PASS ... "); + return 0; + } +#endif + + /* + * Simulate the init() callback but we attach a watchdog callback + * to detect and recover from possible hangs + */ + tracing_reset_online_cpus(&tr->trace_buffer); + set_graph_array(tr); + ret = register_ftrace_graph(&trace_graph_return, + &trace_graph_entry_watchdog); + if (ret) { + warn_failed_init_tracer(trace, ret); + goto out; + } + tracing_start_cmdline_record(); + + /* Sleep for a 1/10 of a second */ + msleep(100); + + /* Have we just recovered from a hang? */ + if (graph_hang_thresh > GRAPH_MAX_FUNC_TEST) { + tracing_selftest_disabled = true; + ret = -1; + goto out; + } + + tracing_stop(); + + /* check the trace buffer */ + ret = trace_test_buffer(&tr->trace_buffer, &count); + + trace->reset(tr); + tracing_start(); + + if (!ret && !count) { + printk(KERN_CONT ".. no entries found .."); + ret = -1; + goto out; + } + + /* Don't test dynamic tracing, the function tracer already did */ + +out: + /* Stop it if we failed */ + if (ret) + ftrace_graph_stop(); + + return ret; +} +#endif /* CONFIG_FUNCTION_GRAPH_TRACER */ + + +#ifdef CONFIG_IRQSOFF_TRACER +int +trace_selftest_startup_irqsoff(struct tracer *trace, struct trace_array *tr) +{ + unsigned long save_max = tr->max_latency; + unsigned long count; + int ret; + + /* start the tracing */ + ret = tracer_init(trace, tr); + if (ret) { + warn_failed_init_tracer(trace, ret); + return ret; + } + + /* reset the max latency */ + tr->max_latency = 0; + /* disable interrupts for a bit */ + local_irq_disable(); + udelay(100); + local_irq_enable(); + + /* + * Stop the tracer to avoid a warning subsequent + * to buffer flipping failure because tracing_stop() + * disables the tr and max buffers, making flipping impossible + * in case of parallels max irqs off latencies. + */ + trace->stop(tr); + /* stop the tracing. */ + tracing_stop(); + /* check both trace buffers */ + ret = trace_test_buffer(&tr->trace_buffer, NULL); + if (!ret) + ret = trace_test_buffer(&tr->max_buffer, &count); + trace->reset(tr); + tracing_start(); + + if (!ret && !count) { + printk(KERN_CONT ".. no entries found .."); + ret = -1; + } + + tr->max_latency = save_max; + + return ret; +} +#endif /* CONFIG_IRQSOFF_TRACER */ + +#ifdef CONFIG_PREEMPT_TRACER +int +trace_selftest_startup_preemptoff(struct tracer *trace, struct trace_array *tr) +{ + unsigned long save_max = tr->max_latency; + unsigned long count; + int ret; + + /* + * Now that the big kernel lock is no longer preemptable, + * and this is called with the BKL held, it will always + * fail. If preemption is already disabled, simply + * pass the test. When the BKL is removed, or becomes + * preemptible again, we will once again test this, + * so keep it in. + */ + if (preempt_count()) { + printk(KERN_CONT "can not test ... force "); + return 0; + } + + /* start the tracing */ + ret = tracer_init(trace, tr); + if (ret) { + warn_failed_init_tracer(trace, ret); + return ret; + } + + /* reset the max latency */ + tr->max_latency = 0; + /* disable preemption for a bit */ + preempt_disable(); + udelay(100); + preempt_enable(); + + /* + * Stop the tracer to avoid a warning subsequent + * to buffer flipping failure because tracing_stop() + * disables the tr and max buffers, making flipping impossible + * in case of parallels max preempt off latencies. + */ + trace->stop(tr); + /* stop the tracing. */ + tracing_stop(); + /* check both trace buffers */ + ret = trace_test_buffer(&tr->trace_buffer, NULL); + if (!ret) + ret = trace_test_buffer(&tr->max_buffer, &count); + trace->reset(tr); + tracing_start(); + + if (!ret && !count) { + printk(KERN_CONT ".. no entries found .."); + ret = -1; + } + + tr->max_latency = save_max; + + return ret; +} +#endif /* CONFIG_PREEMPT_TRACER */ + +#if defined(CONFIG_IRQSOFF_TRACER) && defined(CONFIG_PREEMPT_TRACER) +int +trace_selftest_startup_preemptirqsoff(struct tracer *trace, struct trace_array *tr) +{ + unsigned long save_max = tr->max_latency; + unsigned long count; + int ret; + + /* + * Now that the big kernel lock is no longer preemptable, + * and this is called with the BKL held, it will always + * fail. If preemption is already disabled, simply + * pass the test. When the BKL is removed, or becomes + * preemptible again, we will once again test this, + * so keep it in. + */ + if (preempt_count()) { + printk(KERN_CONT "can not test ... force "); + return 0; + } + + /* start the tracing */ + ret = tracer_init(trace, tr); + if (ret) { + warn_failed_init_tracer(trace, ret); + goto out_no_start; + } + + /* reset the max latency */ + tr->max_latency = 0; + + /* disable preemption and interrupts for a bit */ + preempt_disable(); + local_irq_disable(); + udelay(100); + preempt_enable(); + /* reverse the order of preempt vs irqs */ + local_irq_enable(); + + /* + * Stop the tracer to avoid a warning subsequent + * to buffer flipping failure because tracing_stop() + * disables the tr and max buffers, making flipping impossible + * in case of parallels max irqs/preempt off latencies. + */ + trace->stop(tr); + /* stop the tracing. */ + tracing_stop(); + /* check both trace buffers */ + ret = trace_test_buffer(&tr->trace_buffer, NULL); + if (ret) + goto out; + + ret = trace_test_buffer(&tr->max_buffer, &count); + if (ret) + goto out; + + if (!ret && !count) { + printk(KERN_CONT ".. no entries found .."); + ret = -1; + goto out; + } + + /* do the test by disabling interrupts first this time */ + tr->max_latency = 0; + tracing_start(); + trace->start(tr); + + preempt_disable(); + local_irq_disable(); + udelay(100); + preempt_enable(); + /* reverse the order of preempt vs irqs */ + local_irq_enable(); + + trace->stop(tr); + /* stop the tracing. */ + tracing_stop(); + /* check both trace buffers */ + ret = trace_test_buffer(&tr->trace_buffer, NULL); + if (ret) + goto out; + + ret = trace_test_buffer(&tr->max_buffer, &count); + + if (!ret && !count) { + printk(KERN_CONT ".. no entries found .."); + ret = -1; + goto out; + } + +out: + tracing_start(); +out_no_start: + trace->reset(tr); + tr->max_latency = save_max; + + return ret; +} +#endif /* CONFIG_IRQSOFF_TRACER && CONFIG_PREEMPT_TRACER */ + +#ifdef CONFIG_NOP_TRACER +int +trace_selftest_startup_nop(struct tracer *trace, struct trace_array *tr) +{ + /* What could possibly go wrong? */ + return 0; +} +#endif + +#ifdef CONFIG_SCHED_TRACER + +struct wakeup_test_data { + struct completion is_ready; + int go; +}; + +static int trace_wakeup_test_thread(void *data) +{ + /* Make this a -deadline thread */ + static const struct sched_attr attr = { + .sched_policy = SCHED_DEADLINE, + .sched_runtime = 100000ULL, + .sched_deadline = 10000000ULL, + .sched_period = 10000000ULL + }; + struct wakeup_test_data *x = data; + + sched_setattr(current, &attr); + + /* Make it know we have a new prio */ + complete(&x->is_ready); + + /* now go to sleep and let the test wake us up */ + set_current_state(TASK_INTERRUPTIBLE); + while (!x->go) { + schedule(); + set_current_state(TASK_INTERRUPTIBLE); + } + + complete(&x->is_ready); + + set_current_state(TASK_INTERRUPTIBLE); + + /* we are awake, now wait to disappear */ + while (!kthread_should_stop()) { + schedule(); + set_current_state(TASK_INTERRUPTIBLE); + } + + __set_current_state(TASK_RUNNING); + + return 0; +} +int +trace_selftest_startup_wakeup(struct tracer *trace, struct trace_array *tr) +{ + unsigned long save_max = tr->max_latency; + struct task_struct *p; + struct wakeup_test_data data; + unsigned long count; + int ret; + + memset(&data, 0, sizeof(data)); + + init_completion(&data.is_ready); + + /* create a -deadline thread */ + p = kthread_run(trace_wakeup_test_thread, &data, "ftrace-test"); + if (IS_ERR(p)) { + printk(KERN_CONT "Failed to create ftrace wakeup test thread "); + return -1; + } + + /* make sure the thread is running at -deadline policy */ + wait_for_completion(&data.is_ready); + + /* start the tracing */ + ret = tracer_init(trace, tr); + if (ret) { + warn_failed_init_tracer(trace, ret); + return ret; + } + + /* reset the max latency */ + tr->max_latency = 0; + + while (p->on_rq) { + /* + * Sleep to make sure the -deadline thread is asleep too. + * On virtual machines we can't rely on timings, + * but we want to make sure this test still works. + */ + msleep(100); + } + + init_completion(&data.is_ready); + + data.go = 1; + /* memory barrier is in the wake_up_process() */ + + wake_up_process(p); + + /* Wait for the task to wake up */ + wait_for_completion(&data.is_ready); + + /* stop the tracing. */ + tracing_stop(); + /* check both trace buffers */ + ret = trace_test_buffer(&tr->trace_buffer, NULL); + if (!ret) + ret = trace_test_buffer(&tr->max_buffer, &count); + + + trace->reset(tr); + tracing_start(); + + tr->max_latency = save_max; + + /* kill the thread */ + kthread_stop(p); + + if (!ret && !count) { + printk(KERN_CONT ".. no entries found .."); + ret = -1; + } + + return ret; +} +#endif /* CONFIG_SCHED_TRACER */ + +#ifdef CONFIG_CONTEXT_SWITCH_TRACER +int +trace_selftest_startup_sched_switch(struct tracer *trace, struct trace_array *tr) +{ + unsigned long count; + int ret; + + /* start the tracing */ + ret = tracer_init(trace, tr); + if (ret) { + warn_failed_init_tracer(trace, ret); + return ret; + } + + /* Sleep for a 1/10 of a second */ + msleep(100); + /* stop the tracing. */ + tracing_stop(); + /* check the trace buffer */ + ret = trace_test_buffer(&tr->trace_buffer, &count); + trace->reset(tr); + tracing_start(); + + if (!ret && !count) { + printk(KERN_CONT ".. no entries found .."); + ret = -1; + } + + return ret; +} +#endif /* CONFIG_CONTEXT_SWITCH_TRACER */ + +#ifdef CONFIG_BRANCH_TRACER +int +trace_selftest_startup_branch(struct tracer *trace, struct trace_array *tr) +{ + unsigned long count; + int ret; + + /* start the tracing */ + ret = tracer_init(trace, tr); + if (ret) { + warn_failed_init_tracer(trace, ret); + return ret; + } + + /* Sleep for a 1/10 of a second */ + msleep(100); + /* stop the tracing. */ + tracing_stop(); + /* check the trace buffer */ + ret = trace_test_buffer(&tr->trace_buffer, &count); + trace->reset(tr); + tracing_start(); + + if (!ret && !count) { + printk(KERN_CONT ".. no entries found .."); + ret = -1; + } + + return ret; +} +#endif /* CONFIG_BRANCH_TRACER */ + diff --git a/kernel/kernel/trace/trace_selftest_dynamic.c b/kernel/kernel/trace/trace_selftest_dynamic.c new file mode 100644 index 000000000..b4c475a0a --- /dev/null +++ b/kernel/kernel/trace/trace_selftest_dynamic.c @@ -0,0 +1,13 @@ +#include "trace.h" + +int DYN_FTRACE_TEST_NAME(void) +{ + /* used to call mcount */ + return 0; +} + +int DYN_FTRACE_TEST_NAME2(void) +{ + /* used to call mcount */ + return 0; +} diff --git a/kernel/kernel/trace/trace_seq.c b/kernel/kernel/trace/trace_seq.c new file mode 100644 index 000000000..e694c9f9e --- /dev/null +++ b/kernel/kernel/trace/trace_seq.c @@ -0,0 +1,377 @@ +/* + * trace_seq.c + * + * Copyright (C) 2008-2014 Red Hat Inc, Steven Rostedt + * + * The trace_seq is a handy tool that allows you to pass a descriptor around + * to a buffer that other functions can write to. It is similar to the + * seq_file functionality but has some differences. + * + * To use it, the trace_seq must be initialized with trace_seq_init(). + * This will set up the counters within the descriptor. You can call + * trace_seq_init() more than once to reset the trace_seq to start + * from scratch. + * + * The buffer size is currently PAGE_SIZE, although it may become dynamic + * in the future. + * + * A write to the buffer will either succed or fail. That is, unlike + * sprintf() there will not be a partial write (well it may write into + * the buffer but it wont update the pointers). This allows users to + * try to write something into the trace_seq buffer and if it fails + * they can flush it and try again. + * + */ +#include +#include +#include + +/* How much buffer is left on the trace_seq? */ +#define TRACE_SEQ_BUF_LEFT(s) seq_buf_buffer_left(&(s)->seq) + +/* How much buffer is written? */ +#define TRACE_SEQ_BUF_USED(s) seq_buf_used(&(s)->seq) + +/* + * trace_seq should work with being initialized with 0s. + */ +static inline void __trace_seq_init(struct trace_seq *s) +{ + if (unlikely(!s->seq.size)) + trace_seq_init(s); +} + +/** + * trace_print_seq - move the contents of trace_seq into a seq_file + * @m: the seq_file descriptor that is the destination + * @s: the trace_seq descriptor that is the source. + * + * Returns 0 on success and non zero on error. If it succeeds to + * write to the seq_file it will reset the trace_seq, otherwise + * it does not modify the trace_seq to let the caller try again. + */ +int trace_print_seq(struct seq_file *m, struct trace_seq *s) +{ + int ret; + + __trace_seq_init(s); + + ret = seq_buf_print_seq(m, &s->seq); + + /* + * Only reset this buffer if we successfully wrote to the + * seq_file buffer. This lets the caller try again or + * do something else with the contents. + */ + if (!ret) + trace_seq_init(s); + + return ret; +} + +/** + * trace_seq_printf - sequence printing of trace information + * @s: trace sequence descriptor + * @fmt: printf format string + * + * The tracer may use either sequence operations or its own + * copy to user routines. To simplify formating of a trace + * trace_seq_printf() is used to store strings into a special + * buffer (@s). Then the output may be either used by + * the sequencer or pulled into another buffer. + */ +void trace_seq_printf(struct trace_seq *s, const char *fmt, ...) +{ + unsigned int save_len = s->seq.len; + va_list ap; + + if (s->full) + return; + + __trace_seq_init(s); + + va_start(ap, fmt); + seq_buf_vprintf(&s->seq, fmt, ap); + va_end(ap); + + /* If we can't write it all, don't bother writing anything */ + if (unlikely(seq_buf_has_overflowed(&s->seq))) { + s->seq.len = save_len; + s->full = 1; + } +} +EXPORT_SYMBOL_GPL(trace_seq_printf); + +/** + * trace_seq_bitmask - write a bitmask array in its ASCII representation + * @s: trace sequence descriptor + * @maskp: points to an array of unsigned longs that represent a bitmask + * @nmaskbits: The number of bits that are valid in @maskp + * + * Writes a ASCII representation of a bitmask string into @s. + */ +void trace_seq_bitmask(struct trace_seq *s, const unsigned long *maskp, + int nmaskbits) +{ + unsigned int save_len = s->seq.len; + + if (s->full) + return; + + __trace_seq_init(s); + + seq_buf_printf(&s->seq, "%*pb", nmaskbits, maskp); + + if (unlikely(seq_buf_has_overflowed(&s->seq))) { + s->seq.len = save_len; + s->full = 1; + } +} +EXPORT_SYMBOL_GPL(trace_seq_bitmask); + +/** + * trace_seq_vprintf - sequence printing of trace information + * @s: trace sequence descriptor + * @fmt: printf format string + * + * The tracer may use either sequence operations or its own + * copy to user routines. To simplify formating of a trace + * trace_seq_printf is used to store strings into a special + * buffer (@s). Then the output may be either used by + * the sequencer or pulled into another buffer. + */ +void trace_seq_vprintf(struct trace_seq *s, const char *fmt, va_list args) +{ + unsigned int save_len = s->seq.len; + + if (s->full) + return; + + __trace_seq_init(s); + + seq_buf_vprintf(&s->seq, fmt, args); + + /* If we can't write it all, don't bother writing anything */ + if (unlikely(seq_buf_has_overflowed(&s->seq))) { + s->seq.len = save_len; + s->full = 1; + } +} +EXPORT_SYMBOL_GPL(trace_seq_vprintf); + +/** + * trace_seq_bprintf - Write the printf string from binary arguments + * @s: trace sequence descriptor + * @fmt: The format string for the @binary arguments + * @binary: The binary arguments for @fmt. + * + * When recording in a fast path, a printf may be recorded with just + * saving the format and the arguments as they were passed to the + * function, instead of wasting cycles converting the arguments into + * ASCII characters. Instead, the arguments are saved in a 32 bit + * word array that is defined by the format string constraints. + * + * This function will take the format and the binary array and finish + * the conversion into the ASCII string within the buffer. + */ +void trace_seq_bprintf(struct trace_seq *s, const char *fmt, const u32 *binary) +{ + unsigned int save_len = s->seq.len; + + if (s->full) + return; + + __trace_seq_init(s); + + seq_buf_bprintf(&s->seq, fmt, binary); + + /* If we can't write it all, don't bother writing anything */ + if (unlikely(seq_buf_has_overflowed(&s->seq))) { + s->seq.len = save_len; + s->full = 1; + return; + } +} +EXPORT_SYMBOL_GPL(trace_seq_bprintf); + +/** + * trace_seq_puts - trace sequence printing of simple string + * @s: trace sequence descriptor + * @str: simple string to record + * + * The tracer may use either the sequence operations or its own + * copy to user routines. This function records a simple string + * into a special buffer (@s) for later retrieval by a sequencer + * or other mechanism. + */ +void trace_seq_puts(struct trace_seq *s, const char *str) +{ + unsigned int len = strlen(str); + + if (s->full) + return; + + __trace_seq_init(s); + + if (len > TRACE_SEQ_BUF_LEFT(s)) { + s->full = 1; + return; + } + + seq_buf_putmem(&s->seq, str, len); +} +EXPORT_SYMBOL_GPL(trace_seq_puts); + +/** + * trace_seq_putc - trace sequence printing of simple character + * @s: trace sequence descriptor + * @c: simple character to record + * + * The tracer may use either the sequence operations or its own + * copy to user routines. This function records a simple charater + * into a special buffer (@s) for later retrieval by a sequencer + * or other mechanism. + */ +void trace_seq_putc(struct trace_seq *s, unsigned char c) +{ + if (s->full) + return; + + __trace_seq_init(s); + + if (TRACE_SEQ_BUF_LEFT(s) < 1) { + s->full = 1; + return; + } + + seq_buf_putc(&s->seq, c); +} +EXPORT_SYMBOL_GPL(trace_seq_putc); + +/** + * trace_seq_putmem - write raw data into the trace_seq buffer + * @s: trace sequence descriptor + * @mem: The raw memory to copy into the buffer + * @len: The length of the raw memory to copy (in bytes) + * + * There may be cases where raw memory needs to be written into the + * buffer and a strcpy() would not work. Using this function allows + * for such cases. + */ +void trace_seq_putmem(struct trace_seq *s, const void *mem, unsigned int len) +{ + if (s->full) + return; + + __trace_seq_init(s); + + if (len > TRACE_SEQ_BUF_LEFT(s)) { + s->full = 1; + return; + } + + seq_buf_putmem(&s->seq, mem, len); +} +EXPORT_SYMBOL_GPL(trace_seq_putmem); + +/** + * trace_seq_putmem_hex - write raw memory into the buffer in ASCII hex + * @s: trace sequence descriptor + * @mem: The raw memory to write its hex ASCII representation of + * @len: The length of the raw memory to copy (in bytes) + * + * This is similar to trace_seq_putmem() except instead of just copying the + * raw memory into the buffer it writes its ASCII representation of it + * in hex characters. + */ +void trace_seq_putmem_hex(struct trace_seq *s, const void *mem, + unsigned int len) +{ + unsigned int save_len = s->seq.len; + + if (s->full) + return; + + __trace_seq_init(s); + + /* Each byte is represented by two chars */ + if (len * 2 > TRACE_SEQ_BUF_LEFT(s)) { + s->full = 1; + return; + } + + /* The added spaces can still cause an overflow */ + seq_buf_putmem_hex(&s->seq, mem, len); + + if (unlikely(seq_buf_has_overflowed(&s->seq))) { + s->seq.len = save_len; + s->full = 1; + return; + } +} +EXPORT_SYMBOL_GPL(trace_seq_putmem_hex); + +/** + * trace_seq_path - copy a path into the sequence buffer + * @s: trace sequence descriptor + * @path: path to write into the sequence buffer. + * + * Write a path name into the sequence buffer. + * + * Returns 1 if we successfully written all the contents to + * the buffer. + * Returns 0 if we the length to write is bigger than the + * reserved buffer space. In this case, nothing gets written. + */ +int trace_seq_path(struct trace_seq *s, const struct path *path) +{ + unsigned int save_len = s->seq.len; + + if (s->full) + return 0; + + __trace_seq_init(s); + + if (TRACE_SEQ_BUF_LEFT(s) < 1) { + s->full = 1; + return 0; + } + + seq_buf_path(&s->seq, path, "\n"); + + if (unlikely(seq_buf_has_overflowed(&s->seq))) { + s->seq.len = save_len; + s->full = 1; + return 0; + } + + return 1; +} +EXPORT_SYMBOL_GPL(trace_seq_path); + +/** + * trace_seq_to_user - copy the squence buffer to user space + * @s: trace sequence descriptor + * @ubuf: The userspace memory location to copy to + * @cnt: The amount to copy + * + * Copies the sequence buffer into the userspace memory pointed to + * by @ubuf. It starts from the last read position (@s->readpos) + * and writes up to @cnt characters or till it reaches the end of + * the content in the buffer (@s->len), which ever comes first. + * + * On success, it returns a positive number of the number of bytes + * it copied. + * + * On failure it returns -EBUSY if all of the content in the + * sequence has been already read, which includes nothing in the + * sequenc (@s->len == @s->readpos). + * + * Returns -EFAULT if the copy to userspace fails. + */ +int trace_seq_to_user(struct trace_seq *s, char __user *ubuf, int cnt) +{ + __trace_seq_init(s); + return seq_buf_to_user(&s->seq, ubuf, cnt); +} +EXPORT_SYMBOL_GPL(trace_seq_to_user); diff --git a/kernel/kernel/trace/trace_stack.c b/kernel/kernel/trace/trace_stack.c new file mode 100644 index 000000000..3f3449624 --- /dev/null +++ b/kernel/kernel/trace/trace_stack.c @@ -0,0 +1,484 @@ +/* + * Copyright (C) 2008 Steven Rostedt + * + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +#include "trace.h" + +#define STACK_TRACE_ENTRIES 500 + +#ifdef CC_USING_FENTRY +# define fentry 1 +#else +# define fentry 0 +#endif + +static unsigned long stack_dump_trace[STACK_TRACE_ENTRIES+1] = + { [0 ... (STACK_TRACE_ENTRIES)] = ULONG_MAX }; +static unsigned stack_dump_index[STACK_TRACE_ENTRIES]; + +/* + * Reserve one entry for the passed in ip. This will allow + * us to remove most or all of the stack size overhead + * added by the stack tracer itself. + */ +static struct stack_trace max_stack_trace = { + .max_entries = STACK_TRACE_ENTRIES - 1, + .entries = &stack_dump_trace[1], +}; + +static unsigned long max_stack_size; +static arch_spinlock_t max_stack_lock = + (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED; + +static DEFINE_PER_CPU(int, trace_active); +static DEFINE_MUTEX(stack_sysctl_mutex); + +int stack_tracer_enabled; +static int last_stack_tracer_enabled; + +static inline void print_max_stack(void) +{ + long i; + int size; + + pr_emerg(" Depth Size Location (%d entries)\n" + " ----- ---- --------\n", + max_stack_trace.nr_entries - 1); + + for (i = 0; i < max_stack_trace.nr_entries; i++) { + if (stack_dump_trace[i] == ULONG_MAX) + break; + if (i+1 == max_stack_trace.nr_entries || + stack_dump_trace[i+1] == ULONG_MAX) + size = stack_dump_index[i]; + else + size = stack_dump_index[i] - stack_dump_index[i+1]; + + pr_emerg("%3ld) %8d %5d %pS\n", i, stack_dump_index[i], + size, (void *)stack_dump_trace[i]); + } +} + +static inline void +check_stack(unsigned long ip, unsigned long *stack) +{ + unsigned long this_size, flags; unsigned long *p, *top, *start; + static int tracer_frame; + int frame_size = ACCESS_ONCE(tracer_frame); + int i; + + this_size = ((unsigned long)stack) & (THREAD_SIZE-1); + this_size = THREAD_SIZE - this_size; + /* Remove the frame of the tracer */ + this_size -= frame_size; + + if (this_size <= max_stack_size) + return; + + /* we do not handle interrupt stacks yet */ + if (!object_is_on_stack(stack)) + return; + + local_irq_save(flags); + arch_spin_lock(&max_stack_lock); + + /* In case another CPU set the tracer_frame on us */ + if (unlikely(!frame_size)) + this_size -= tracer_frame; + + /* a race could have already updated it */ + if (this_size <= max_stack_size) + goto out; + + max_stack_size = this_size; + + max_stack_trace.nr_entries = 0; + + if (using_ftrace_ops_list_func()) + max_stack_trace.skip = 4; + else + max_stack_trace.skip = 3; + + save_stack_trace(&max_stack_trace); + + /* + * Add the passed in ip from the function tracer. + * Searching for this on the stack will skip over + * most of the overhead from the stack tracer itself. + */ + stack_dump_trace[0] = ip; + max_stack_trace.nr_entries++; + + /* + * Now find where in the stack these are. + */ + i = 0; + start = stack; + top = (unsigned long *) + (((unsigned long)start & ~(THREAD_SIZE-1)) + THREAD_SIZE); + + /* + * Loop through all the entries. One of the entries may + * for some reason be missed on the stack, so we may + * have to account for them. If they are all there, this + * loop will only happen once. This code only takes place + * on a new max, so it is far from a fast path. + */ + while (i < max_stack_trace.nr_entries) { + int found = 0; + + stack_dump_index[i] = this_size; + p = start; + + for (; p < top && i < max_stack_trace.nr_entries; p++) { + if (*p == stack_dump_trace[i]) { + this_size = stack_dump_index[i++] = + (top - p) * sizeof(unsigned long); + found = 1; + /* Start the search from here */ + start = p + 1; + /* + * We do not want to show the overhead + * of the stack tracer stack in the + * max stack. If we haven't figured + * out what that is, then figure it out + * now. + */ + if (unlikely(!tracer_frame) && i == 1) { + tracer_frame = (p - stack) * + sizeof(unsigned long); + max_stack_size -= tracer_frame; + } + } + } + + if (!found) + i++; + } + + if (task_stack_end_corrupted(current)) { + print_max_stack(); + BUG(); + } + + out: + arch_spin_unlock(&max_stack_lock); + local_irq_restore(flags); +} + +static void +stack_trace_call(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct pt_regs *pt_regs) +{ + unsigned long stack; + int cpu; + + preempt_disable_notrace(); + + cpu = raw_smp_processor_id(); + /* no atomic needed, we only modify this variable by this cpu */ + if (per_cpu(trace_active, cpu)++ != 0) + goto out; + + /* + * When fentry is used, the traced function does not get + * its stack frame set up, and we lose the parent. + * The ip is pretty useless because the function tracer + * was called before that function set up its stack frame. + * In this case, we use the parent ip. + * + * By adding the return address of either the parent ip + * or the current ip we can disregard most of the stack usage + * caused by the stack tracer itself. + * + * The function tracer always reports the address of where the + * mcount call was, but the stack will hold the return address. + */ + if (fentry) + ip = parent_ip; + else + ip += MCOUNT_INSN_SIZE; + + check_stack(ip, &stack); + + out: + per_cpu(trace_active, cpu)--; + /* prevent recursion in schedule */ + preempt_enable_notrace(); +} + +static struct ftrace_ops trace_ops __read_mostly = +{ + .func = stack_trace_call, + .flags = FTRACE_OPS_FL_RECURSION_SAFE, +}; + +static ssize_t +stack_max_size_read(struct file *filp, char __user *ubuf, + size_t count, loff_t *ppos) +{ + unsigned long *ptr = filp->private_data; + char buf[64]; + int r; + + r = snprintf(buf, sizeof(buf), "%ld\n", *ptr); + if (r > sizeof(buf)) + r = sizeof(buf); + return simple_read_from_buffer(ubuf, count, ppos, buf, r); +} + +static ssize_t +stack_max_size_write(struct file *filp, const char __user *ubuf, + size_t count, loff_t *ppos) +{ + long *ptr = filp->private_data; + unsigned long val, flags; + int ret; + int cpu; + + ret = kstrtoul_from_user(ubuf, count, 10, &val); + if (ret) + return ret; + + local_irq_save(flags); + + /* + * In case we trace inside arch_spin_lock() or after (NMI), + * we will cause circular lock, so we also need to increase + * the percpu trace_active here. + */ + cpu = smp_processor_id(); + per_cpu(trace_active, cpu)++; + + arch_spin_lock(&max_stack_lock); + *ptr = val; + arch_spin_unlock(&max_stack_lock); + + per_cpu(trace_active, cpu)--; + local_irq_restore(flags); + + return count; +} + +static const struct file_operations stack_max_size_fops = { + .open = tracing_open_generic, + .read = stack_max_size_read, + .write = stack_max_size_write, + .llseek = default_llseek, +}; + +static void * +__next(struct seq_file *m, loff_t *pos) +{ + long n = *pos - 1; + + if (n >= max_stack_trace.nr_entries || stack_dump_trace[n] == ULONG_MAX) + return NULL; + + m->private = (void *)n; + return &m->private; +} + +static void * +t_next(struct seq_file *m, void *v, loff_t *pos) +{ + (*pos)++; + return __next(m, pos); +} + +static void *t_start(struct seq_file *m, loff_t *pos) +{ + int cpu; + + local_irq_disable(); + + cpu = smp_processor_id(); + per_cpu(trace_active, cpu)++; + + arch_spin_lock(&max_stack_lock); + + if (*pos == 0) + return SEQ_START_TOKEN; + + return __next(m, pos); +} + +static void t_stop(struct seq_file *m, void *p) +{ + int cpu; + + arch_spin_unlock(&max_stack_lock); + + cpu = smp_processor_id(); + per_cpu(trace_active, cpu)--; + + local_irq_enable(); +} + +static void trace_lookup_stack(struct seq_file *m, long i) +{ + unsigned long addr = stack_dump_trace[i]; + + seq_printf(m, "%pS\n", (void *)addr); +} + +static void print_disabled(struct seq_file *m) +{ + seq_puts(m, "#\n" + "# Stack tracer disabled\n" + "#\n" + "# To enable the stack tracer, either add 'stacktrace' to the\n" + "# kernel command line\n" + "# or 'echo 1 > /proc/sys/kernel/stack_tracer_enabled'\n" + "#\n"); +} + +static int t_show(struct seq_file *m, void *v) +{ + long i; + int size; + + if (v == SEQ_START_TOKEN) { + seq_printf(m, " Depth Size Location" + " (%d entries)\n" + " ----- ---- --------\n", + max_stack_trace.nr_entries - 1); + + if (!stack_tracer_enabled && !max_stack_size) + print_disabled(m); + + return 0; + } + + i = *(long *)v; + + if (i >= max_stack_trace.nr_entries || + stack_dump_trace[i] == ULONG_MAX) + return 0; + + if (i+1 == max_stack_trace.nr_entries || + stack_dump_trace[i+1] == ULONG_MAX) + size = stack_dump_index[i]; + else + size = stack_dump_index[i] - stack_dump_index[i+1]; + + seq_printf(m, "%3ld) %8d %5d ", i, stack_dump_index[i], size); + + trace_lookup_stack(m, i); + + return 0; +} + +static const struct seq_operations stack_trace_seq_ops = { + .start = t_start, + .next = t_next, + .stop = t_stop, + .show = t_show, +}; + +static int stack_trace_open(struct inode *inode, struct file *file) +{ + return seq_open(file, &stack_trace_seq_ops); +} + +static const struct file_operations stack_trace_fops = { + .open = stack_trace_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, +}; + +static int +stack_trace_filter_open(struct inode *inode, struct file *file) +{ + return ftrace_regex_open(&trace_ops, FTRACE_ITER_FILTER, + inode, file); +} + +static const struct file_operations stack_trace_filter_fops = { + .open = stack_trace_filter_open, + .read = seq_read, + .write = ftrace_filter_write, + .llseek = tracing_lseek, + .release = ftrace_regex_release, +}; + +int +stack_trace_sysctl(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos) +{ + int ret; + + mutex_lock(&stack_sysctl_mutex); + + ret = proc_dointvec(table, write, buffer, lenp, ppos); + + if (ret || !write || + (last_stack_tracer_enabled == !!stack_tracer_enabled)) + goto out; + + last_stack_tracer_enabled = !!stack_tracer_enabled; + + if (stack_tracer_enabled) + register_ftrace_function(&trace_ops); + else + unregister_ftrace_function(&trace_ops); + + out: + mutex_unlock(&stack_sysctl_mutex); + return ret; +} + +static char stack_trace_filter_buf[COMMAND_LINE_SIZE+1] __initdata; + +static __init int enable_stacktrace(char *str) +{ + if (strncmp(str, "_filter=", 8) == 0) + strncpy(stack_trace_filter_buf, str+8, COMMAND_LINE_SIZE); + + stack_tracer_enabled = 1; + last_stack_tracer_enabled = 1; + return 1; +} +__setup("stacktrace", enable_stacktrace); + +static __init int stack_trace_init(void) +{ + struct dentry *d_tracer; + + d_tracer = tracing_init_dentry(); + if (IS_ERR(d_tracer)) + return 0; + + trace_create_file("stack_max_size", 0644, d_tracer, + &max_stack_size, &stack_max_size_fops); + + trace_create_file("stack_trace", 0444, d_tracer, + NULL, &stack_trace_fops); + + trace_create_file("stack_trace_filter", 0444, d_tracer, + NULL, &stack_trace_filter_fops); + + if (stack_trace_filter_buf[0]) + ftrace_set_early_filter(&trace_ops, stack_trace_filter_buf, 1); + + if (stack_tracer_enabled) + register_ftrace_function(&trace_ops); + + return 0; +} + +device_initcall(stack_trace_init); diff --git a/kernel/kernel/trace/trace_stat.c b/kernel/kernel/trace/trace_stat.c new file mode 100644 index 000000000..6cf935316 --- /dev/null +++ b/kernel/kernel/trace/trace_stat.c @@ -0,0 +1,359 @@ +/* + * Infrastructure for statistic tracing (histogram output). + * + * Copyright (C) 2008-2009 Frederic Weisbecker + * + * Based on the code from trace_branch.c which is + * Copyright (C) 2008 Steven Rostedt + * + */ + + +#include +#include +#include +#include +#include "trace_stat.h" +#include "trace.h" + + +/* + * List of stat red-black nodes from a tracer + * We use a such tree to sort quickly the stat + * entries from the tracer. + */ +struct stat_node { + struct rb_node node; + void *stat; +}; + +/* A stat session is the stats output in one file */ +struct stat_session { + struct list_head session_list; + struct tracer_stat *ts; + struct rb_root stat_root; + struct mutex stat_mutex; + struct dentry *file; +}; + +/* All of the sessions currently in use. Each stat file embed one session */ +static LIST_HEAD(all_stat_sessions); +static DEFINE_MUTEX(all_stat_sessions_mutex); + +/* The root directory for all stat files */ +static struct dentry *stat_dir; + +static void __reset_stat_session(struct stat_session *session) +{ + struct stat_node *snode, *n; + + rbtree_postorder_for_each_entry_safe(snode, n, &session->stat_root, node) { + if (session->ts->stat_release) + session->ts->stat_release(snode->stat); + kfree(snode); + } + + session->stat_root = RB_ROOT; +} + +static void reset_stat_session(struct stat_session *session) +{ + mutex_lock(&session->stat_mutex); + __reset_stat_session(session); + mutex_unlock(&session->stat_mutex); +} + +static void destroy_session(struct stat_session *session) +{ + tracefs_remove(session->file); + __reset_stat_session(session); + mutex_destroy(&session->stat_mutex); + kfree(session); +} + +typedef int (*cmp_stat_t)(void *, void *); + +static int insert_stat(struct rb_root *root, void *stat, cmp_stat_t cmp) +{ + struct rb_node **new = &(root->rb_node), *parent = NULL; + struct stat_node *data; + + data = kzalloc(sizeof(*data), GFP_KERNEL); + if (!data) + return -ENOMEM; + data->stat = stat; + + /* + * Figure out where to put new node + * This is a descendent sorting + */ + while (*new) { + struct stat_node *this; + int result; + + this = container_of(*new, struct stat_node, node); + result = cmp(data->stat, this->stat); + + parent = *new; + if (result >= 0) + new = &((*new)->rb_left); + else + new = &((*new)->rb_right); + } + + rb_link_node(&data->node, parent, new); + rb_insert_color(&data->node, root); + return 0; +} + +/* + * For tracers that don't provide a stat_cmp callback. + * This one will force an insertion as right-most node + * in the rbtree. + */ +static int dummy_cmp(void *p1, void *p2) +{ + return -1; +} + +/* + * Initialize the stat rbtree at each trace_stat file opening. + * All of these copies and sorting are required on all opening + * since the stats could have changed between two file sessions. + */ +static int stat_seq_init(struct stat_session *session) +{ + struct tracer_stat *ts = session->ts; + struct rb_root *root = &session->stat_root; + void *stat; + int ret = 0; + int i; + + mutex_lock(&session->stat_mutex); + __reset_stat_session(session); + + if (!ts->stat_cmp) + ts->stat_cmp = dummy_cmp; + + stat = ts->stat_start(ts); + if (!stat) + goto exit; + + ret = insert_stat(root, stat, ts->stat_cmp); + if (ret) + goto exit; + + /* + * Iterate over the tracer stat entries and store them in an rbtree. + */ + for (i = 1; ; i++) { + stat = ts->stat_next(stat, i); + + /* End of insertion */ + if (!stat) + break; + + ret = insert_stat(root, stat, ts->stat_cmp); + if (ret) + goto exit_free_rbtree; + } + +exit: + mutex_unlock(&session->stat_mutex); + return ret; + +exit_free_rbtree: + __reset_stat_session(session); + mutex_unlock(&session->stat_mutex); + return ret; +} + + +static void *stat_seq_start(struct seq_file *s, loff_t *pos) +{ + struct stat_session *session = s->private; + struct rb_node *node; + int n = *pos; + int i; + + /* Prevent from tracer switch or rbtree modification */ + mutex_lock(&session->stat_mutex); + + /* If we are in the beginning of the file, print the headers */ + if (session->ts->stat_headers) { + if (n == 0) + return SEQ_START_TOKEN; + n--; + } + + node = rb_first(&session->stat_root); + for (i = 0; node && i < n; i++) + node = rb_next(node); + + return node; +} + +static void *stat_seq_next(struct seq_file *s, void *p, loff_t *pos) +{ + struct stat_session *session = s->private; + struct rb_node *node = p; + + (*pos)++; + + if (p == SEQ_START_TOKEN) + return rb_first(&session->stat_root); + + return rb_next(node); +} + +static void stat_seq_stop(struct seq_file *s, void *p) +{ + struct stat_session *session = s->private; + mutex_unlock(&session->stat_mutex); +} + +static int stat_seq_show(struct seq_file *s, void *v) +{ + struct stat_session *session = s->private; + struct stat_node *l = container_of(v, struct stat_node, node); + + if (v == SEQ_START_TOKEN) + return session->ts->stat_headers(s); + + return session->ts->stat_show(s, l->stat); +} + +static const struct seq_operations trace_stat_seq_ops = { + .start = stat_seq_start, + .next = stat_seq_next, + .stop = stat_seq_stop, + .show = stat_seq_show +}; + +/* The session stat is refilled and resorted at each stat file opening */ +static int tracing_stat_open(struct inode *inode, struct file *file) +{ + int ret; + struct seq_file *m; + struct stat_session *session = inode->i_private; + + ret = stat_seq_init(session); + if (ret) + return ret; + + ret = seq_open(file, &trace_stat_seq_ops); + if (ret) { + reset_stat_session(session); + return ret; + } + + m = file->private_data; + m->private = session; + return ret; +} + +/* + * Avoid consuming memory with our now useless rbtree. + */ +static int tracing_stat_release(struct inode *i, struct file *f) +{ + struct stat_session *session = i->i_private; + + reset_stat_session(session); + + return seq_release(i, f); +} + +static const struct file_operations tracing_stat_fops = { + .open = tracing_stat_open, + .read = seq_read, + .llseek = seq_lseek, + .release = tracing_stat_release +}; + +static int tracing_stat_init(void) +{ + struct dentry *d_tracing; + + d_tracing = tracing_init_dentry(); + if (IS_ERR(d_tracing)) + return 0; + + stat_dir = tracefs_create_dir("trace_stat", d_tracing); + if (!stat_dir) + pr_warning("Could not create tracefs " + "'trace_stat' entry\n"); + return 0; +} + +static int init_stat_file(struct stat_session *session) +{ + if (!stat_dir && tracing_stat_init()) + return -ENODEV; + + session->file = tracefs_create_file(session->ts->name, 0644, + stat_dir, + session, &tracing_stat_fops); + if (!session->file) + return -ENOMEM; + return 0; +} + +int register_stat_tracer(struct tracer_stat *trace) +{ + struct stat_session *session, *node; + int ret; + + if (!trace) + return -EINVAL; + + if (!trace->stat_start || !trace->stat_next || !trace->stat_show) + return -EINVAL; + + /* Already registered? */ + mutex_lock(&all_stat_sessions_mutex); + list_for_each_entry(node, &all_stat_sessions, session_list) { + if (node->ts == trace) { + mutex_unlock(&all_stat_sessions_mutex); + return -EINVAL; + } + } + mutex_unlock(&all_stat_sessions_mutex); + + /* Init the session */ + session = kzalloc(sizeof(*session), GFP_KERNEL); + if (!session) + return -ENOMEM; + + session->ts = trace; + INIT_LIST_HEAD(&session->session_list); + mutex_init(&session->stat_mutex); + + ret = init_stat_file(session); + if (ret) { + destroy_session(session); + return ret; + } + + /* Register */ + mutex_lock(&all_stat_sessions_mutex); + list_add_tail(&session->session_list, &all_stat_sessions); + mutex_unlock(&all_stat_sessions_mutex); + + return 0; +} + +void unregister_stat_tracer(struct tracer_stat *trace) +{ + struct stat_session *node, *tmp; + + mutex_lock(&all_stat_sessions_mutex); + list_for_each_entry_safe(node, tmp, &all_stat_sessions, session_list) { + if (node->ts == trace) { + list_del(&node->session_list); + destroy_session(node); + break; + } + } + mutex_unlock(&all_stat_sessions_mutex); +} diff --git a/kernel/kernel/trace/trace_stat.h b/kernel/kernel/trace/trace_stat.h new file mode 100644 index 000000000..8f03914b9 --- /dev/null +++ b/kernel/kernel/trace/trace_stat.h @@ -0,0 +1,33 @@ +#ifndef __TRACE_STAT_H +#define __TRACE_STAT_H + +#include + +/* + * If you want to provide a stat file (one-shot statistics), fill + * an iterator with stat_start/stat_next and a stat_show callbacks. + * The others callbacks are optional. + */ +struct tracer_stat { + /* The name of your stat file */ + const char *name; + /* Iteration over statistic entries */ + void *(*stat_start)(struct tracer_stat *trace); + void *(*stat_next)(void *prev, int idx); + /* Compare two entries for stats sorting */ + int (*stat_cmp)(void *p1, void *p2); + /* Print a stat entry */ + int (*stat_show)(struct seq_file *s, void *p); + /* Release an entry */ + void (*stat_release)(void *stat); + /* Print the headers of your stat entries */ + int (*stat_headers)(struct seq_file *s); +}; + +/* + * Destroy or create a stat file + */ +extern int register_stat_tracer(struct tracer_stat *trace); +extern void unregister_stat_tracer(struct tracer_stat *trace); + +#endif /* __TRACE_STAT_H */ diff --git a/kernel/kernel/trace/trace_syscalls.c b/kernel/kernel/trace/trace_syscalls.c new file mode 100644 index 000000000..f97f6e3a6 --- /dev/null +++ b/kernel/kernel/trace/trace_syscalls.c @@ -0,0 +1,750 @@ +#include +#include +#include +#include +#include +#include /* for MODULE_NAME_LEN via KSYM_SYMBOL_LEN */ +#include +#include +#include + +#include "trace_output.h" +#include "trace.h" + +static DEFINE_MUTEX(syscall_trace_lock); + +static int syscall_enter_register(struct ftrace_event_call *event, + enum trace_reg type, void *data); +static int syscall_exit_register(struct ftrace_event_call *event, + enum trace_reg type, void *data); + +static struct list_head * +syscall_get_enter_fields(struct ftrace_event_call *call) +{ + struct syscall_metadata *entry = call->data; + + return &entry->enter_fields; +} + +extern struct syscall_metadata *__start_syscalls_metadata[]; +extern struct syscall_metadata *__stop_syscalls_metadata[]; + +static struct syscall_metadata **syscalls_metadata; + +#ifndef ARCH_HAS_SYSCALL_MATCH_SYM_NAME +static inline bool arch_syscall_match_sym_name(const char *sym, const char *name) +{ + /* + * Only compare after the "sys" prefix. Archs that use + * syscall wrappers may have syscalls symbols aliases prefixed + * with ".SyS" or ".sys" instead of "sys", leading to an unwanted + * mismatch. + */ + return !strcmp(sym + 3, name + 3); +} +#endif + +#ifdef ARCH_TRACE_IGNORE_COMPAT_SYSCALLS +/* + * Some architectures that allow for 32bit applications + * to run on a 64bit kernel, do not map the syscalls for + * the 32bit tasks the same as they do for 64bit tasks. + * + * *cough*x86*cough* + * + * In such a case, instead of reporting the wrong syscalls, + * simply ignore them. + * + * For an arch to ignore the compat syscalls it needs to + * define ARCH_TRACE_IGNORE_COMPAT_SYSCALLS as well as + * define the function arch_trace_is_compat_syscall() to let + * the tracing system know that it should ignore it. + */ +static int +trace_get_syscall_nr(struct task_struct *task, struct pt_regs *regs) +{ + if (unlikely(arch_trace_is_compat_syscall(regs))) + return -1; + + return syscall_get_nr(task, regs); +} +#else +static inline int +trace_get_syscall_nr(struct task_struct *task, struct pt_regs *regs) +{ + return syscall_get_nr(task, regs); +} +#endif /* ARCH_TRACE_IGNORE_COMPAT_SYSCALLS */ + +static __init struct syscall_metadata * +find_syscall_meta(unsigned long syscall) +{ + struct syscall_metadata **start; + struct syscall_metadata **stop; + char str[KSYM_SYMBOL_LEN]; + + + start = __start_syscalls_metadata; + stop = __stop_syscalls_metadata; + kallsyms_lookup(syscall, NULL, NULL, NULL, str); + + if (arch_syscall_match_sym_name(str, "sys_ni_syscall")) + return NULL; + + for ( ; start < stop; start++) { + if ((*start)->name && arch_syscall_match_sym_name(str, (*start)->name)) + return *start; + } + return NULL; +} + +static struct syscall_metadata *syscall_nr_to_meta(int nr) +{ + if (!syscalls_metadata || nr >= NR_syscalls || nr < 0) + return NULL; + + return syscalls_metadata[nr]; +} + +static enum print_line_t +print_syscall_enter(struct trace_iterator *iter, int flags, + struct trace_event *event) +{ + struct trace_seq *s = &iter->seq; + struct trace_entry *ent = iter->ent; + struct syscall_trace_enter *trace; + struct syscall_metadata *entry; + int i, syscall; + + trace = (typeof(trace))ent; + syscall = trace->nr; + entry = syscall_nr_to_meta(syscall); + + if (!entry) + goto end; + + if (entry->enter_event->event.type != ent->type) { + WARN_ON_ONCE(1); + goto end; + } + + trace_seq_printf(s, "%s(", entry->name); + + for (i = 0; i < entry->nb_args; i++) { + + if (trace_seq_has_overflowed(s)) + goto end; + + /* parameter types */ + if (trace_flags & TRACE_ITER_VERBOSE) + trace_seq_printf(s, "%s ", entry->types[i]); + + /* parameter values */ + trace_seq_printf(s, "%s: %lx%s", entry->args[i], + trace->args[i], + i == entry->nb_args - 1 ? "" : ", "); + } + + trace_seq_putc(s, ')'); +end: + trace_seq_putc(s, '\n'); + + return trace_handle_return(s); +} + +static enum print_line_t +print_syscall_exit(struct trace_iterator *iter, int flags, + struct trace_event *event) +{ + struct trace_seq *s = &iter->seq; + struct trace_entry *ent = iter->ent; + struct syscall_trace_exit *trace; + int syscall; + struct syscall_metadata *entry; + + trace = (typeof(trace))ent; + syscall = trace->nr; + entry = syscall_nr_to_meta(syscall); + + if (!entry) { + trace_seq_putc(s, '\n'); + goto out; + } + + if (entry->exit_event->event.type != ent->type) { + WARN_ON_ONCE(1); + return TRACE_TYPE_UNHANDLED; + } + + trace_seq_printf(s, "%s -> 0x%lx\n", entry->name, + trace->ret); + + out: + return trace_handle_return(s); +} + +extern char *__bad_type_size(void); + +#define SYSCALL_FIELD(type, name) \ + sizeof(type) != sizeof(trace.name) ? \ + __bad_type_size() : \ + #type, #name, offsetof(typeof(trace), name), \ + sizeof(trace.name), is_signed_type(type) + +static int __init +__set_enter_print_fmt(struct syscall_metadata *entry, char *buf, int len) +{ + int i; + int pos = 0; + + /* When len=0, we just calculate the needed length */ +#define LEN_OR_ZERO (len ? len - pos : 0) + + pos += snprintf(buf + pos, LEN_OR_ZERO, "\""); + for (i = 0; i < entry->nb_args; i++) { + pos += snprintf(buf + pos, LEN_OR_ZERO, "%s: 0x%%0%zulx%s", + entry->args[i], sizeof(unsigned long), + i == entry->nb_args - 1 ? "" : ", "); + } + pos += snprintf(buf + pos, LEN_OR_ZERO, "\""); + + for (i = 0; i < entry->nb_args; i++) { + pos += snprintf(buf + pos, LEN_OR_ZERO, + ", ((unsigned long)(REC->%s))", entry->args[i]); + } + +#undef LEN_OR_ZERO + + /* return the length of print_fmt */ + return pos; +} + +static int __init set_syscall_print_fmt(struct ftrace_event_call *call) +{ + char *print_fmt; + int len; + struct syscall_metadata *entry = call->data; + + if (entry->enter_event != call) { + call->print_fmt = "\"0x%lx\", REC->ret"; + return 0; + } + + /* First: called with 0 length to calculate the needed length */ + len = __set_enter_print_fmt(entry, NULL, 0); + + print_fmt = kmalloc(len + 1, GFP_KERNEL); + if (!print_fmt) + return -ENOMEM; + + /* Second: actually write the @print_fmt */ + __set_enter_print_fmt(entry, print_fmt, len + 1); + call->print_fmt = print_fmt; + + return 0; +} + +static void __init free_syscall_print_fmt(struct ftrace_event_call *call) +{ + struct syscall_metadata *entry = call->data; + + if (entry->enter_event == call) + kfree(call->print_fmt); +} + +static int __init syscall_enter_define_fields(struct ftrace_event_call *call) +{ + struct syscall_trace_enter trace; + struct syscall_metadata *meta = call->data; + int ret; + int i; + int offset = offsetof(typeof(trace), args); + + ret = trace_define_field(call, SYSCALL_FIELD(int, nr), FILTER_OTHER); + if (ret) + return ret; + + for (i = 0; i < meta->nb_args; i++) { + ret = trace_define_field(call, meta->types[i], + meta->args[i], offset, + sizeof(unsigned long), 0, + FILTER_OTHER); + offset += sizeof(unsigned long); + } + + return ret; +} + +static int __init syscall_exit_define_fields(struct ftrace_event_call *call) +{ + struct syscall_trace_exit trace; + int ret; + + ret = trace_define_field(call, SYSCALL_FIELD(int, nr), FILTER_OTHER); + if (ret) + return ret; + + ret = trace_define_field(call, SYSCALL_FIELD(long, ret), + FILTER_OTHER); + + return ret; +} + +static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id) +{ + struct trace_array *tr = data; + struct ftrace_event_file *ftrace_file; + struct syscall_trace_enter *entry; + struct syscall_metadata *sys_data; + struct ring_buffer_event *event; + struct ring_buffer *buffer; + unsigned long irq_flags; + int pc; + int syscall_nr; + int size; + + syscall_nr = trace_get_syscall_nr(current, regs); + if (syscall_nr < 0 || syscall_nr >= NR_syscalls) + return; + + /* Here we're inside tp handler's rcu_read_lock_sched (__DO_TRACE) */ + ftrace_file = rcu_dereference_sched(tr->enter_syscall_files[syscall_nr]); + if (!ftrace_file) + return; + + if (ftrace_trigger_soft_disabled(ftrace_file)) + return; + + sys_data = syscall_nr_to_meta(syscall_nr); + if (!sys_data) + return; + + size = sizeof(*entry) + sizeof(unsigned long) * sys_data->nb_args; + + local_save_flags(irq_flags); + pc = preempt_count(); + + buffer = tr->trace_buffer.buffer; + event = trace_buffer_lock_reserve(buffer, + sys_data->enter_event->event.type, size, irq_flags, pc); + if (!event) + return; + + entry = ring_buffer_event_data(event); + entry->nr = syscall_nr; + syscall_get_arguments(current, regs, 0, sys_data->nb_args, entry->args); + + event_trigger_unlock_commit(ftrace_file, buffer, event, entry, + irq_flags, pc); +} + +static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret) +{ + struct trace_array *tr = data; + struct ftrace_event_file *ftrace_file; + struct syscall_trace_exit *entry; + struct syscall_metadata *sys_data; + struct ring_buffer_event *event; + struct ring_buffer *buffer; + unsigned long irq_flags; + int pc; + int syscall_nr; + + syscall_nr = trace_get_syscall_nr(current, regs); + if (syscall_nr < 0 || syscall_nr >= NR_syscalls) + return; + + /* Here we're inside tp handler's rcu_read_lock_sched (__DO_TRACE()) */ + ftrace_file = rcu_dereference_sched(tr->exit_syscall_files[syscall_nr]); + if (!ftrace_file) + return; + + if (ftrace_trigger_soft_disabled(ftrace_file)) + return; + + sys_data = syscall_nr_to_meta(syscall_nr); + if (!sys_data) + return; + + local_save_flags(irq_flags); + pc = preempt_count(); + + buffer = tr->trace_buffer.buffer; + event = trace_buffer_lock_reserve(buffer, + sys_data->exit_event->event.type, sizeof(*entry), + irq_flags, pc); + if (!event) + return; + + entry = ring_buffer_event_data(event); + entry->nr = syscall_nr; + entry->ret = syscall_get_return_value(current, regs); + + event_trigger_unlock_commit(ftrace_file, buffer, event, entry, + irq_flags, pc); +} + +static int reg_event_syscall_enter(struct ftrace_event_file *file, + struct ftrace_event_call *call) +{ + struct trace_array *tr = file->tr; + int ret = 0; + int num; + + num = ((struct syscall_metadata *)call->data)->syscall_nr; + if (WARN_ON_ONCE(num < 0 || num >= NR_syscalls)) + return -ENOSYS; + mutex_lock(&syscall_trace_lock); + if (!tr->sys_refcount_enter) + ret = register_trace_sys_enter(ftrace_syscall_enter, tr); + if (!ret) { + rcu_assign_pointer(tr->enter_syscall_files[num], file); + tr->sys_refcount_enter++; + } + mutex_unlock(&syscall_trace_lock); + return ret; +} + +static void unreg_event_syscall_enter(struct ftrace_event_file *file, + struct ftrace_event_call *call) +{ + struct trace_array *tr = file->tr; + int num; + + num = ((struct syscall_metadata *)call->data)->syscall_nr; + if (WARN_ON_ONCE(num < 0 || num >= NR_syscalls)) + return; + mutex_lock(&syscall_trace_lock); + tr->sys_refcount_enter--; + RCU_INIT_POINTER(tr->enter_syscall_files[num], NULL); + if (!tr->sys_refcount_enter) + unregister_trace_sys_enter(ftrace_syscall_enter, tr); + mutex_unlock(&syscall_trace_lock); +} + +static int reg_event_syscall_exit(struct ftrace_event_file *file, + struct ftrace_event_call *call) +{ + struct trace_array *tr = file->tr; + int ret = 0; + int num; + + num = ((struct syscall_metadata *)call->data)->syscall_nr; + if (WARN_ON_ONCE(num < 0 || num >= NR_syscalls)) + return -ENOSYS; + mutex_lock(&syscall_trace_lock); + if (!tr->sys_refcount_exit) + ret = register_trace_sys_exit(ftrace_syscall_exit, tr); + if (!ret) { + rcu_assign_pointer(tr->exit_syscall_files[num], file); + tr->sys_refcount_exit++; + } + mutex_unlock(&syscall_trace_lock); + return ret; +} + +static void unreg_event_syscall_exit(struct ftrace_event_file *file, + struct ftrace_event_call *call) +{ + struct trace_array *tr = file->tr; + int num; + + num = ((struct syscall_metadata *)call->data)->syscall_nr; + if (WARN_ON_ONCE(num < 0 || num >= NR_syscalls)) + return; + mutex_lock(&syscall_trace_lock); + tr->sys_refcount_exit--; + RCU_INIT_POINTER(tr->exit_syscall_files[num], NULL); + if (!tr->sys_refcount_exit) + unregister_trace_sys_exit(ftrace_syscall_exit, tr); + mutex_unlock(&syscall_trace_lock); +} + +static int __init init_syscall_trace(struct ftrace_event_call *call) +{ + int id; + int num; + + num = ((struct syscall_metadata *)call->data)->syscall_nr; + if (num < 0 || num >= NR_syscalls) { + pr_debug("syscall %s metadata not mapped, disabling ftrace event\n", + ((struct syscall_metadata *)call->data)->name); + return -ENOSYS; + } + + if (set_syscall_print_fmt(call) < 0) + return -ENOMEM; + + id = trace_event_raw_init(call); + + if (id < 0) { + free_syscall_print_fmt(call); + return id; + } + + return id; +} + +struct trace_event_functions enter_syscall_print_funcs = { + .trace = print_syscall_enter, +}; + +struct trace_event_functions exit_syscall_print_funcs = { + .trace = print_syscall_exit, +}; + +struct ftrace_event_class __refdata event_class_syscall_enter = { + .system = "syscalls", + .reg = syscall_enter_register, + .define_fields = syscall_enter_define_fields, + .get_fields = syscall_get_enter_fields, + .raw_init = init_syscall_trace, +}; + +struct ftrace_event_class __refdata event_class_syscall_exit = { + .system = "syscalls", + .reg = syscall_exit_register, + .define_fields = syscall_exit_define_fields, + .fields = LIST_HEAD_INIT(event_class_syscall_exit.fields), + .raw_init = init_syscall_trace, +}; + +unsigned long __init __weak arch_syscall_addr(int nr) +{ + return (unsigned long)sys_call_table[nr]; +} + +void __init init_ftrace_syscalls(void) +{ + struct syscall_metadata *meta; + unsigned long addr; + int i; + + syscalls_metadata = kcalloc(NR_syscalls, sizeof(*syscalls_metadata), + GFP_KERNEL); + if (!syscalls_metadata) { + WARN_ON(1); + return; + } + + for (i = 0; i < NR_syscalls; i++) { + addr = arch_syscall_addr(i); + meta = find_syscall_meta(addr); + if (!meta) + continue; + + meta->syscall_nr = i; + syscalls_metadata[i] = meta; + } +} + +#ifdef CONFIG_PERF_EVENTS + +static DECLARE_BITMAP(enabled_perf_enter_syscalls, NR_syscalls); +static DECLARE_BITMAP(enabled_perf_exit_syscalls, NR_syscalls); +static int sys_perf_refcount_enter; +static int sys_perf_refcount_exit; + +static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id) +{ + struct syscall_metadata *sys_data; + struct syscall_trace_enter *rec; + struct hlist_head *head; + int syscall_nr; + int rctx; + int size; + + syscall_nr = trace_get_syscall_nr(current, regs); + if (syscall_nr < 0 || syscall_nr >= NR_syscalls) + return; + if (!test_bit(syscall_nr, enabled_perf_enter_syscalls)) + return; + + sys_data = syscall_nr_to_meta(syscall_nr); + if (!sys_data) + return; + + head = this_cpu_ptr(sys_data->enter_event->perf_events); + if (hlist_empty(head)) + return; + + /* get the size after alignment with the u32 buffer size field */ + size = sizeof(unsigned long) * sys_data->nb_args + sizeof(*rec); + size = ALIGN(size + sizeof(u32), sizeof(u64)); + size -= sizeof(u32); + + rec = (struct syscall_trace_enter *)perf_trace_buf_prepare(size, + sys_data->enter_event->event.type, NULL, &rctx); + if (!rec) + return; + + rec->nr = syscall_nr; + syscall_get_arguments(current, regs, 0, sys_data->nb_args, + (unsigned long *)&rec->args); + perf_trace_buf_submit(rec, size, rctx, 0, 1, regs, head, NULL); +} + +static int perf_sysenter_enable(struct ftrace_event_call *call) +{ + int ret = 0; + int num; + + num = ((struct syscall_metadata *)call->data)->syscall_nr; + + mutex_lock(&syscall_trace_lock); + if (!sys_perf_refcount_enter) + ret = register_trace_sys_enter(perf_syscall_enter, NULL); + if (ret) { + pr_info("event trace: Could not activate" + "syscall entry trace point"); + } else { + set_bit(num, enabled_perf_enter_syscalls); + sys_perf_refcount_enter++; + } + mutex_unlock(&syscall_trace_lock); + return ret; +} + +static void perf_sysenter_disable(struct ftrace_event_call *call) +{ + int num; + + num = ((struct syscall_metadata *)call->data)->syscall_nr; + + mutex_lock(&syscall_trace_lock); + sys_perf_refcount_enter--; + clear_bit(num, enabled_perf_enter_syscalls); + if (!sys_perf_refcount_enter) + unregister_trace_sys_enter(perf_syscall_enter, NULL); + mutex_unlock(&syscall_trace_lock); +} + +static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret) +{ + struct syscall_metadata *sys_data; + struct syscall_trace_exit *rec; + struct hlist_head *head; + int syscall_nr; + int rctx; + int size; + + syscall_nr = trace_get_syscall_nr(current, regs); + if (syscall_nr < 0 || syscall_nr >= NR_syscalls) + return; + if (!test_bit(syscall_nr, enabled_perf_exit_syscalls)) + return; + + sys_data = syscall_nr_to_meta(syscall_nr); + if (!sys_data) + return; + + head = this_cpu_ptr(sys_data->exit_event->perf_events); + if (hlist_empty(head)) + return; + + /* We can probably do that at build time */ + size = ALIGN(sizeof(*rec) + sizeof(u32), sizeof(u64)); + size -= sizeof(u32); + + rec = (struct syscall_trace_exit *)perf_trace_buf_prepare(size, + sys_data->exit_event->event.type, NULL, &rctx); + if (!rec) + return; + + rec->nr = syscall_nr; + rec->ret = syscall_get_return_value(current, regs); + perf_trace_buf_submit(rec, size, rctx, 0, 1, regs, head, NULL); +} + +static int perf_sysexit_enable(struct ftrace_event_call *call) +{ + int ret = 0; + int num; + + num = ((struct syscall_metadata *)call->data)->syscall_nr; + + mutex_lock(&syscall_trace_lock); + if (!sys_perf_refcount_exit) + ret = register_trace_sys_exit(perf_syscall_exit, NULL); + if (ret) { + pr_info("event trace: Could not activate" + "syscall exit trace point"); + } else { + set_bit(num, enabled_perf_exit_syscalls); + sys_perf_refcount_exit++; + } + mutex_unlock(&syscall_trace_lock); + return ret; +} + +static void perf_sysexit_disable(struct ftrace_event_call *call) +{ + int num; + + num = ((struct syscall_metadata *)call->data)->syscall_nr; + + mutex_lock(&syscall_trace_lock); + sys_perf_refcount_exit--; + clear_bit(num, enabled_perf_exit_syscalls); + if (!sys_perf_refcount_exit) + unregister_trace_sys_exit(perf_syscall_exit, NULL); + mutex_unlock(&syscall_trace_lock); +} + +#endif /* CONFIG_PERF_EVENTS */ + +static int syscall_enter_register(struct ftrace_event_call *event, + enum trace_reg type, void *data) +{ + struct ftrace_event_file *file = data; + + switch (type) { + case TRACE_REG_REGISTER: + return reg_event_syscall_enter(file, event); + case TRACE_REG_UNREGISTER: + unreg_event_syscall_enter(file, event); + return 0; + +#ifdef CONFIG_PERF_EVENTS + case TRACE_REG_PERF_REGISTER: + return perf_sysenter_enable(event); + case TRACE_REG_PERF_UNREGISTER: + perf_sysenter_disable(event); + return 0; + case TRACE_REG_PERF_OPEN: + case TRACE_REG_PERF_CLOSE: + case TRACE_REG_PERF_ADD: + case TRACE_REG_PERF_DEL: + return 0; +#endif + } + return 0; +} + +static int syscall_exit_register(struct ftrace_event_call *event, + enum trace_reg type, void *data) +{ + struct ftrace_event_file *file = data; + + switch (type) { + case TRACE_REG_REGISTER: + return reg_event_syscall_exit(file, event); + case TRACE_REG_UNREGISTER: + unreg_event_syscall_exit(file, event); + return 0; + +#ifdef CONFIG_PERF_EVENTS + case TRACE_REG_PERF_REGISTER: + return perf_sysexit_enable(event); + case TRACE_REG_PERF_UNREGISTER: + perf_sysexit_disable(event); + return 0; + case TRACE_REG_PERF_OPEN: + case TRACE_REG_PERF_CLOSE: + case TRACE_REG_PERF_ADD: + case TRACE_REG_PERF_DEL: + return 0; +#endif + } + return 0; +} diff --git a/kernel/kernel/trace/trace_uprobe.c b/kernel/kernel/trace/trace_uprobe.c new file mode 100644 index 000000000..6dd022c7b --- /dev/null +++ b/kernel/kernel/trace/trace_uprobe.c @@ -0,0 +1,1336 @@ +/* + * uprobes-based tracing events + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * + * Copyright (C) IBM Corporation, 2010-2012 + * Author: Srikar Dronamraju + */ + +#include +#include +#include +#include +#include + +#include "trace_probe.h" + +#define UPROBE_EVENT_SYSTEM "uprobes" + +struct uprobe_trace_entry_head { + struct trace_entry ent; + unsigned long vaddr[]; +}; + +#define SIZEOF_TRACE_ENTRY(is_return) \ + (sizeof(struct uprobe_trace_entry_head) + \ + sizeof(unsigned long) * (is_return ? 2 : 1)) + +#define DATAOF_TRACE_ENTRY(entry, is_return) \ + ((void*)(entry) + SIZEOF_TRACE_ENTRY(is_return)) + +struct trace_uprobe_filter { + rwlock_t rwlock; + int nr_systemwide; + struct list_head perf_events; +}; + +/* + * uprobe event core functions + */ +struct trace_uprobe { + struct list_head list; + struct trace_uprobe_filter filter; + struct uprobe_consumer consumer; + struct inode *inode; + char *filename; + unsigned long offset; + unsigned long nhit; + struct trace_probe tp; +}; + +#define SIZEOF_TRACE_UPROBE(n) \ + (offsetof(struct trace_uprobe, tp.args) + \ + (sizeof(struct probe_arg) * (n))) + +static int register_uprobe_event(struct trace_uprobe *tu); +static int unregister_uprobe_event(struct trace_uprobe *tu); + +static DEFINE_MUTEX(uprobe_lock); +static LIST_HEAD(uprobe_list); + +struct uprobe_dispatch_data { + struct trace_uprobe *tu; + unsigned long bp_addr; +}; + +static int uprobe_dispatcher(struct uprobe_consumer *con, struct pt_regs *regs); +static int uretprobe_dispatcher(struct uprobe_consumer *con, + unsigned long func, struct pt_regs *regs); + +#ifdef CONFIG_STACK_GROWSUP +static unsigned long adjust_stack_addr(unsigned long addr, unsigned int n) +{ + return addr - (n * sizeof(long)); +} +#else +static unsigned long adjust_stack_addr(unsigned long addr, unsigned int n) +{ + return addr + (n * sizeof(long)); +} +#endif + +static unsigned long get_user_stack_nth(struct pt_regs *regs, unsigned int n) +{ + unsigned long ret; + unsigned long addr = user_stack_pointer(regs); + + addr = adjust_stack_addr(addr, n); + + if (copy_from_user(&ret, (void __force __user *) addr, sizeof(ret))) + return 0; + + return ret; +} + +/* + * Uprobes-specific fetch functions + */ +#define DEFINE_FETCH_stack(type) \ +static void FETCH_FUNC_NAME(stack, type)(struct pt_regs *regs, \ + void *offset, void *dest) \ +{ \ + *(type *)dest = (type)get_user_stack_nth(regs, \ + ((unsigned long)offset)); \ +} +DEFINE_BASIC_FETCH_FUNCS(stack) +/* No string on the stack entry */ +#define fetch_stack_string NULL +#define fetch_stack_string_size NULL + +#define DEFINE_FETCH_memory(type) \ +static void FETCH_FUNC_NAME(memory, type)(struct pt_regs *regs, \ + void *addr, void *dest) \ +{ \ + type retval; \ + void __user *vaddr = (void __force __user *) addr; \ + \ + if (copy_from_user(&retval, vaddr, sizeof(type))) \ + *(type *)dest = 0; \ + else \ + *(type *) dest = retval; \ +} +DEFINE_BASIC_FETCH_FUNCS(memory) +/* + * Fetch a null-terminated string. Caller MUST set *(u32 *)dest with max + * length and relative data location. + */ +static void FETCH_FUNC_NAME(memory, string)(struct pt_regs *regs, + void *addr, void *dest) +{ + long ret; + u32 rloc = *(u32 *)dest; + int maxlen = get_rloc_len(rloc); + u8 *dst = get_rloc_data(dest); + void __user *src = (void __force __user *) addr; + + if (!maxlen) + return; + + ret = strncpy_from_user(dst, src, maxlen); + + if (ret < 0) { /* Failed to fetch string */ + ((u8 *)get_rloc_data(dest))[0] = '\0'; + *(u32 *)dest = make_data_rloc(0, get_rloc_offs(rloc)); + } else { + *(u32 *)dest = make_data_rloc(ret, get_rloc_offs(rloc)); + } +} + +static void FETCH_FUNC_NAME(memory, string_size)(struct pt_regs *regs, + void *addr, void *dest) +{ + int len; + void __user *vaddr = (void __force __user *) addr; + + len = strnlen_user(vaddr, MAX_STRING_SIZE); + + if (len == 0 || len > MAX_STRING_SIZE) /* Failed to check length */ + *(u32 *)dest = 0; + else + *(u32 *)dest = len; +} + +static unsigned long translate_user_vaddr(void *file_offset) +{ + unsigned long base_addr; + struct uprobe_dispatch_data *udd; + + udd = (void *) current->utask->vaddr; + + base_addr = udd->bp_addr - udd->tu->offset; + return base_addr + (unsigned long)file_offset; +} + +#define DEFINE_FETCH_file_offset(type) \ +static void FETCH_FUNC_NAME(file_offset, type)(struct pt_regs *regs, \ + void *offset, void *dest)\ +{ \ + void *vaddr = (void *)translate_user_vaddr(offset); \ + \ + FETCH_FUNC_NAME(memory, type)(regs, vaddr, dest); \ +} +DEFINE_BASIC_FETCH_FUNCS(file_offset) +DEFINE_FETCH_file_offset(string) +DEFINE_FETCH_file_offset(string_size) + +/* Fetch type information table */ +static const struct fetch_type uprobes_fetch_type_table[] = { + /* Special types */ + [FETCH_TYPE_STRING] = __ASSIGN_FETCH_TYPE("string", string, string, + sizeof(u32), 1, "__data_loc char[]"), + [FETCH_TYPE_STRSIZE] = __ASSIGN_FETCH_TYPE("string_size", u32, + string_size, sizeof(u32), 0, "u32"), + /* Basic types */ + ASSIGN_FETCH_TYPE(u8, u8, 0), + ASSIGN_FETCH_TYPE(u16, u16, 0), + ASSIGN_FETCH_TYPE(u32, u32, 0), + ASSIGN_FETCH_TYPE(u64, u64, 0), + ASSIGN_FETCH_TYPE(s8, u8, 1), + ASSIGN_FETCH_TYPE(s16, u16, 1), + ASSIGN_FETCH_TYPE(s32, u32, 1), + ASSIGN_FETCH_TYPE(s64, u64, 1), + + ASSIGN_FETCH_TYPE_END +}; + +static inline void init_trace_uprobe_filter(struct trace_uprobe_filter *filter) +{ + rwlock_init(&filter->rwlock); + filter->nr_systemwide = 0; + INIT_LIST_HEAD(&filter->perf_events); +} + +static inline bool uprobe_filter_is_empty(struct trace_uprobe_filter *filter) +{ + return !filter->nr_systemwide && list_empty(&filter->perf_events); +} + +static inline bool is_ret_probe(struct trace_uprobe *tu) +{ + return tu->consumer.ret_handler != NULL; +} + +/* + * Allocate new trace_uprobe and initialize it (including uprobes). + */ +static struct trace_uprobe * +alloc_trace_uprobe(const char *group, const char *event, int nargs, bool is_ret) +{ + struct trace_uprobe *tu; + + if (!event || !is_good_name(event)) + return ERR_PTR(-EINVAL); + + if (!group || !is_good_name(group)) + return ERR_PTR(-EINVAL); + + tu = kzalloc(SIZEOF_TRACE_UPROBE(nargs), GFP_KERNEL); + if (!tu) + return ERR_PTR(-ENOMEM); + + tu->tp.call.class = &tu->tp.class; + tu->tp.call.name = kstrdup(event, GFP_KERNEL); + if (!tu->tp.call.name) + goto error; + + tu->tp.class.system = kstrdup(group, GFP_KERNEL); + if (!tu->tp.class.system) + goto error; + + INIT_LIST_HEAD(&tu->list); + INIT_LIST_HEAD(&tu->tp.files); + tu->consumer.handler = uprobe_dispatcher; + if (is_ret) + tu->consumer.ret_handler = uretprobe_dispatcher; + init_trace_uprobe_filter(&tu->filter); + return tu; + +error: + kfree(tu->tp.call.name); + kfree(tu); + + return ERR_PTR(-ENOMEM); +} + +static void free_trace_uprobe(struct trace_uprobe *tu) +{ + int i; + + for (i = 0; i < tu->tp.nr_args; i++) + traceprobe_free_probe_arg(&tu->tp.args[i]); + + iput(tu->inode); + kfree(tu->tp.call.class->system); + kfree(tu->tp.call.name); + kfree(tu->filename); + kfree(tu); +} + +static struct trace_uprobe *find_probe_event(const char *event, const char *group) +{ + struct trace_uprobe *tu; + + list_for_each_entry(tu, &uprobe_list, list) + if (strcmp(ftrace_event_name(&tu->tp.call), event) == 0 && + strcmp(tu->tp.call.class->system, group) == 0) + return tu; + + return NULL; +} + +/* Unregister a trace_uprobe and probe_event: call with locking uprobe_lock */ +static int unregister_trace_uprobe(struct trace_uprobe *tu) +{ + int ret; + + ret = unregister_uprobe_event(tu); + if (ret) + return ret; + + list_del(&tu->list); + free_trace_uprobe(tu); + return 0; +} + +/* Register a trace_uprobe and probe_event */ +static int register_trace_uprobe(struct trace_uprobe *tu) +{ + struct trace_uprobe *old_tu; + int ret; + + mutex_lock(&uprobe_lock); + + /* register as an event */ + old_tu = find_probe_event(ftrace_event_name(&tu->tp.call), + tu->tp.call.class->system); + if (old_tu) { + /* delete old event */ + ret = unregister_trace_uprobe(old_tu); + if (ret) + goto end; + } + + ret = register_uprobe_event(tu); + if (ret) { + pr_warning("Failed to register probe event(%d)\n", ret); + goto end; + } + + list_add_tail(&tu->list, &uprobe_list); + +end: + mutex_unlock(&uprobe_lock); + + return ret; +} + +/* + * Argument syntax: + * - Add uprobe: p|r[:[GRP/]EVENT] PATH:OFFSET [FETCHARGS] + * + * - Remove uprobe: -:[GRP/]EVENT + */ +static int create_trace_uprobe(int argc, char **argv) +{ + struct trace_uprobe *tu; + struct inode *inode; + char *arg, *event, *group, *filename; + char buf[MAX_EVENT_NAME_LEN]; + struct path path; + unsigned long offset; + bool is_delete, is_return; + int i, ret; + + inode = NULL; + ret = 0; + is_delete = false; + is_return = false; + event = NULL; + group = NULL; + + /* argc must be >= 1 */ + if (argv[0][0] == '-') + is_delete = true; + else if (argv[0][0] == 'r') + is_return = true; + else if (argv[0][0] != 'p') { + pr_info("Probe definition must be started with 'p', 'r' or '-'.\n"); + return -EINVAL; + } + + if (argv[0][1] == ':') { + event = &argv[0][2]; + arg = strchr(event, '/'); + + if (arg) { + group = event; + event = arg + 1; + event[-1] = '\0'; + + if (strlen(group) == 0) { + pr_info("Group name is not specified\n"); + return -EINVAL; + } + } + if (strlen(event) == 0) { + pr_info("Event name is not specified\n"); + return -EINVAL; + } + } + if (!group) + group = UPROBE_EVENT_SYSTEM; + + if (is_delete) { + int ret; + + if (!event) { + pr_info("Delete command needs an event name.\n"); + return -EINVAL; + } + mutex_lock(&uprobe_lock); + tu = find_probe_event(event, group); + + if (!tu) { + mutex_unlock(&uprobe_lock); + pr_info("Event %s/%s doesn't exist.\n", group, event); + return -ENOENT; + } + /* delete an event */ + ret = unregister_trace_uprobe(tu); + mutex_unlock(&uprobe_lock); + return ret; + } + + if (argc < 2) { + pr_info("Probe point is not specified.\n"); + return -EINVAL; + } + if (isdigit(argv[1][0])) { + pr_info("probe point must be have a filename.\n"); + return -EINVAL; + } + arg = strchr(argv[1], ':'); + if (!arg) { + ret = -EINVAL; + goto fail_address_parse; + } + + *arg++ = '\0'; + filename = argv[1]; + ret = kern_path(filename, LOOKUP_FOLLOW, &path); + if (ret) + goto fail_address_parse; + + inode = igrab(d_inode(path.dentry)); + path_put(&path); + + if (!inode || !S_ISREG(inode->i_mode)) { + ret = -EINVAL; + goto fail_address_parse; + } + + ret = kstrtoul(arg, 0, &offset); + if (ret) + goto fail_address_parse; + + argc -= 2; + argv += 2; + + /* setup a probe */ + if (!event) { + char *tail; + char *ptr; + + tail = kstrdup(kbasename(filename), GFP_KERNEL); + if (!tail) { + ret = -ENOMEM; + goto fail_address_parse; + } + + ptr = strpbrk(tail, ".-_"); + if (ptr) + *ptr = '\0'; + + snprintf(buf, MAX_EVENT_NAME_LEN, "%c_%s_0x%lx", 'p', tail, offset); + event = buf; + kfree(tail); + } + + tu = alloc_trace_uprobe(group, event, argc, is_return); + if (IS_ERR(tu)) { + pr_info("Failed to allocate trace_uprobe.(%d)\n", (int)PTR_ERR(tu)); + ret = PTR_ERR(tu); + goto fail_address_parse; + } + tu->offset = offset; + tu->inode = inode; + tu->filename = kstrdup(filename, GFP_KERNEL); + + if (!tu->filename) { + pr_info("Failed to allocate filename.\n"); + ret = -ENOMEM; + goto error; + } + + /* parse arguments */ + ret = 0; + for (i = 0; i < argc && i < MAX_TRACE_ARGS; i++) { + struct probe_arg *parg = &tu->tp.args[i]; + + /* Increment count for freeing args in error case */ + tu->tp.nr_args++; + + /* Parse argument name */ + arg = strchr(argv[i], '='); + if (arg) { + *arg++ = '\0'; + parg->name = kstrdup(argv[i], GFP_KERNEL); + } else { + arg = argv[i]; + /* If argument name is omitted, set "argN" */ + snprintf(buf, MAX_EVENT_NAME_LEN, "arg%d", i + 1); + parg->name = kstrdup(buf, GFP_KERNEL); + } + + if (!parg->name) { + pr_info("Failed to allocate argument[%d] name.\n", i); + ret = -ENOMEM; + goto error; + } + + if (!is_good_name(parg->name)) { + pr_info("Invalid argument[%d] name: %s\n", i, parg->name); + ret = -EINVAL; + goto error; + } + + if (traceprobe_conflict_field_name(parg->name, tu->tp.args, i)) { + pr_info("Argument[%d] name '%s' conflicts with " + "another field.\n", i, argv[i]); + ret = -EINVAL; + goto error; + } + + /* Parse fetch argument */ + ret = traceprobe_parse_probe_arg(arg, &tu->tp.size, parg, + is_return, false, + uprobes_fetch_type_table); + if (ret) { + pr_info("Parse error at argument[%d]. (%d)\n", i, ret); + goto error; + } + } + + ret = register_trace_uprobe(tu); + if (ret) + goto error; + return 0; + +error: + free_trace_uprobe(tu); + return ret; + +fail_address_parse: + iput(inode); + + pr_info("Failed to parse address or file.\n"); + + return ret; +} + +static int cleanup_all_probes(void) +{ + struct trace_uprobe *tu; + int ret = 0; + + mutex_lock(&uprobe_lock); + while (!list_empty(&uprobe_list)) { + tu = list_entry(uprobe_list.next, struct trace_uprobe, list); + ret = unregister_trace_uprobe(tu); + if (ret) + break; + } + mutex_unlock(&uprobe_lock); + return ret; +} + +/* Probes listing interfaces */ +static void *probes_seq_start(struct seq_file *m, loff_t *pos) +{ + mutex_lock(&uprobe_lock); + return seq_list_start(&uprobe_list, *pos); +} + +static void *probes_seq_next(struct seq_file *m, void *v, loff_t *pos) +{ + return seq_list_next(v, &uprobe_list, pos); +} + +static void probes_seq_stop(struct seq_file *m, void *v) +{ + mutex_unlock(&uprobe_lock); +} + +static int probes_seq_show(struct seq_file *m, void *v) +{ + struct trace_uprobe *tu = v; + char c = is_ret_probe(tu) ? 'r' : 'p'; + int i; + + seq_printf(m, "%c:%s/%s", c, tu->tp.call.class->system, + ftrace_event_name(&tu->tp.call)); + seq_printf(m, " %s:0x%p", tu->filename, (void *)tu->offset); + + for (i = 0; i < tu->tp.nr_args; i++) + seq_printf(m, " %s=%s", tu->tp.args[i].name, tu->tp.args[i].comm); + + seq_putc(m, '\n'); + return 0; +} + +static const struct seq_operations probes_seq_op = { + .start = probes_seq_start, + .next = probes_seq_next, + .stop = probes_seq_stop, + .show = probes_seq_show +}; + +static int probes_open(struct inode *inode, struct file *file) +{ + int ret; + + if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) { + ret = cleanup_all_probes(); + if (ret) + return ret; + } + + return seq_open(file, &probes_seq_op); +} + +static ssize_t probes_write(struct file *file, const char __user *buffer, + size_t count, loff_t *ppos) +{ + return traceprobe_probes_write(file, buffer, count, ppos, create_trace_uprobe); +} + +static const struct file_operations uprobe_events_ops = { + .owner = THIS_MODULE, + .open = probes_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, + .write = probes_write, +}; + +/* Probes profiling interfaces */ +static int probes_profile_seq_show(struct seq_file *m, void *v) +{ + struct trace_uprobe *tu = v; + + seq_printf(m, " %s %-44s %15lu\n", tu->filename, + ftrace_event_name(&tu->tp.call), tu->nhit); + return 0; +} + +static const struct seq_operations profile_seq_op = { + .start = probes_seq_start, + .next = probes_seq_next, + .stop = probes_seq_stop, + .show = probes_profile_seq_show +}; + +static int profile_open(struct inode *inode, struct file *file) +{ + return seq_open(file, &profile_seq_op); +} + +static const struct file_operations uprobe_profile_ops = { + .owner = THIS_MODULE, + .open = profile_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, +}; + +struct uprobe_cpu_buffer { + struct mutex mutex; + void *buf; +}; +static struct uprobe_cpu_buffer __percpu *uprobe_cpu_buffer; +static int uprobe_buffer_refcnt; + +static int uprobe_buffer_init(void) +{ + int cpu, err_cpu; + + uprobe_cpu_buffer = alloc_percpu(struct uprobe_cpu_buffer); + if (uprobe_cpu_buffer == NULL) + return -ENOMEM; + + for_each_possible_cpu(cpu) { + struct page *p = alloc_pages_node(cpu_to_node(cpu), + GFP_KERNEL, 0); + if (p == NULL) { + err_cpu = cpu; + goto err; + } + per_cpu_ptr(uprobe_cpu_buffer, cpu)->buf = page_address(p); + mutex_init(&per_cpu_ptr(uprobe_cpu_buffer, cpu)->mutex); + } + + return 0; + +err: + for_each_possible_cpu(cpu) { + if (cpu == err_cpu) + break; + free_page((unsigned long)per_cpu_ptr(uprobe_cpu_buffer, cpu)->buf); + } + + free_percpu(uprobe_cpu_buffer); + return -ENOMEM; +} + +static int uprobe_buffer_enable(void) +{ + int ret = 0; + + BUG_ON(!mutex_is_locked(&event_mutex)); + + if (uprobe_buffer_refcnt++ == 0) { + ret = uprobe_buffer_init(); + if (ret < 0) + uprobe_buffer_refcnt--; + } + + return ret; +} + +static void uprobe_buffer_disable(void) +{ + int cpu; + + BUG_ON(!mutex_is_locked(&event_mutex)); + + if (--uprobe_buffer_refcnt == 0) { + for_each_possible_cpu(cpu) + free_page((unsigned long)per_cpu_ptr(uprobe_cpu_buffer, + cpu)->buf); + + free_percpu(uprobe_cpu_buffer); + uprobe_cpu_buffer = NULL; + } +} + +static struct uprobe_cpu_buffer *uprobe_buffer_get(void) +{ + struct uprobe_cpu_buffer *ucb; + int cpu; + + cpu = raw_smp_processor_id(); + ucb = per_cpu_ptr(uprobe_cpu_buffer, cpu); + + /* + * Use per-cpu buffers for fastest access, but we might migrate + * so the mutex makes sure we have sole access to it. + */ + mutex_lock(&ucb->mutex); + + return ucb; +} + +static void uprobe_buffer_put(struct uprobe_cpu_buffer *ucb) +{ + mutex_unlock(&ucb->mutex); +} + +static void __uprobe_trace_func(struct trace_uprobe *tu, + unsigned long func, struct pt_regs *regs, + struct uprobe_cpu_buffer *ucb, int dsize, + struct ftrace_event_file *ftrace_file) +{ + struct uprobe_trace_entry_head *entry; + struct ring_buffer_event *event; + struct ring_buffer *buffer; + void *data; + int size, esize; + struct ftrace_event_call *call = &tu->tp.call; + + WARN_ON(call != ftrace_file->event_call); + + if (WARN_ON_ONCE(tu->tp.size + dsize > PAGE_SIZE)) + return; + + if (ftrace_trigger_soft_disabled(ftrace_file)) + return; + + esize = SIZEOF_TRACE_ENTRY(is_ret_probe(tu)); + size = esize + tu->tp.size + dsize; + event = trace_event_buffer_lock_reserve(&buffer, ftrace_file, + call->event.type, size, 0, 0); + if (!event) + return; + + entry = ring_buffer_event_data(event); + if (is_ret_probe(tu)) { + entry->vaddr[0] = func; + entry->vaddr[1] = instruction_pointer(regs); + data = DATAOF_TRACE_ENTRY(entry, true); + } else { + entry->vaddr[0] = instruction_pointer(regs); + data = DATAOF_TRACE_ENTRY(entry, false); + } + + memcpy(data, ucb->buf, tu->tp.size + dsize); + + event_trigger_unlock_commit(ftrace_file, buffer, event, entry, 0, 0); +} + +/* uprobe handler */ +static int uprobe_trace_func(struct trace_uprobe *tu, struct pt_regs *regs, + struct uprobe_cpu_buffer *ucb, int dsize) +{ + struct event_file_link *link; + + if (is_ret_probe(tu)) + return 0; + + rcu_read_lock(); + list_for_each_entry_rcu(link, &tu->tp.files, list) + __uprobe_trace_func(tu, 0, regs, ucb, dsize, link->file); + rcu_read_unlock(); + + return 0; +} + +static void uretprobe_trace_func(struct trace_uprobe *tu, unsigned long func, + struct pt_regs *regs, + struct uprobe_cpu_buffer *ucb, int dsize) +{ + struct event_file_link *link; + + rcu_read_lock(); + list_for_each_entry_rcu(link, &tu->tp.files, list) + __uprobe_trace_func(tu, func, regs, ucb, dsize, link->file); + rcu_read_unlock(); +} + +/* Event entry printers */ +static enum print_line_t +print_uprobe_event(struct trace_iterator *iter, int flags, struct trace_event *event) +{ + struct uprobe_trace_entry_head *entry; + struct trace_seq *s = &iter->seq; + struct trace_uprobe *tu; + u8 *data; + int i; + + entry = (struct uprobe_trace_entry_head *)iter->ent; + tu = container_of(event, struct trace_uprobe, tp.call.event); + + if (is_ret_probe(tu)) { + trace_seq_printf(s, "%s: (0x%lx <- 0x%lx)", + ftrace_event_name(&tu->tp.call), + entry->vaddr[1], entry->vaddr[0]); + data = DATAOF_TRACE_ENTRY(entry, true); + } else { + trace_seq_printf(s, "%s: (0x%lx)", + ftrace_event_name(&tu->tp.call), + entry->vaddr[0]); + data = DATAOF_TRACE_ENTRY(entry, false); + } + + for (i = 0; i < tu->tp.nr_args; i++) { + struct probe_arg *parg = &tu->tp.args[i]; + + if (!parg->type->print(s, parg->name, data + parg->offset, entry)) + goto out; + } + + trace_seq_putc(s, '\n'); + + out: + return trace_handle_return(s); +} + +typedef bool (*filter_func_t)(struct uprobe_consumer *self, + enum uprobe_filter_ctx ctx, + struct mm_struct *mm); + +static int +probe_event_enable(struct trace_uprobe *tu, struct ftrace_event_file *file, + filter_func_t filter) +{ + bool enabled = trace_probe_is_enabled(&tu->tp); + struct event_file_link *link = NULL; + int ret; + + if (file) { + if (tu->tp.flags & TP_FLAG_PROFILE) + return -EINTR; + + link = kmalloc(sizeof(*link), GFP_KERNEL); + if (!link) + return -ENOMEM; + + link->file = file; + list_add_tail_rcu(&link->list, &tu->tp.files); + + tu->tp.flags |= TP_FLAG_TRACE; + } else { + if (tu->tp.flags & TP_FLAG_TRACE) + return -EINTR; + + tu->tp.flags |= TP_FLAG_PROFILE; + } + + WARN_ON(!uprobe_filter_is_empty(&tu->filter)); + + if (enabled) + return 0; + + ret = uprobe_buffer_enable(); + if (ret) + goto err_flags; + + tu->consumer.filter = filter; + ret = uprobe_register(tu->inode, tu->offset, &tu->consumer); + if (ret) + goto err_buffer; + + return 0; + + err_buffer: + uprobe_buffer_disable(); + + err_flags: + if (file) { + list_del(&link->list); + kfree(link); + tu->tp.flags &= ~TP_FLAG_TRACE; + } else { + tu->tp.flags &= ~TP_FLAG_PROFILE; + } + return ret; +} + +static void +probe_event_disable(struct trace_uprobe *tu, struct ftrace_event_file *file) +{ + if (!trace_probe_is_enabled(&tu->tp)) + return; + + if (file) { + struct event_file_link *link; + + link = find_event_file_link(&tu->tp, file); + if (!link) + return; + + list_del_rcu(&link->list); + /* synchronize with u{,ret}probe_trace_func */ + synchronize_sched(); + kfree(link); + + if (!list_empty(&tu->tp.files)) + return; + } + + WARN_ON(!uprobe_filter_is_empty(&tu->filter)); + + uprobe_unregister(tu->inode, tu->offset, &tu->consumer); + tu->tp.flags &= file ? ~TP_FLAG_TRACE : ~TP_FLAG_PROFILE; + + uprobe_buffer_disable(); +} + +static int uprobe_event_define_fields(struct ftrace_event_call *event_call) +{ + int ret, i, size; + struct uprobe_trace_entry_head field; + struct trace_uprobe *tu = event_call->data; + + if (is_ret_probe(tu)) { + DEFINE_FIELD(unsigned long, vaddr[0], FIELD_STRING_FUNC, 0); + DEFINE_FIELD(unsigned long, vaddr[1], FIELD_STRING_RETIP, 0); + size = SIZEOF_TRACE_ENTRY(true); + } else { + DEFINE_FIELD(unsigned long, vaddr[0], FIELD_STRING_IP, 0); + size = SIZEOF_TRACE_ENTRY(false); + } + /* Set argument names as fields */ + for (i = 0; i < tu->tp.nr_args; i++) { + struct probe_arg *parg = &tu->tp.args[i]; + + ret = trace_define_field(event_call, parg->type->fmttype, + parg->name, size + parg->offset, + parg->type->size, parg->type->is_signed, + FILTER_OTHER); + + if (ret) + return ret; + } + return 0; +} + +#ifdef CONFIG_PERF_EVENTS +static bool +__uprobe_perf_filter(struct trace_uprobe_filter *filter, struct mm_struct *mm) +{ + struct perf_event *event; + + if (filter->nr_systemwide) + return true; + + list_for_each_entry(event, &filter->perf_events, hw.tp_list) { + if (event->hw.target->mm == mm) + return true; + } + + return false; +} + +static inline bool +uprobe_filter_event(struct trace_uprobe *tu, struct perf_event *event) +{ + return __uprobe_perf_filter(&tu->filter, event->hw.target->mm); +} + +static int uprobe_perf_close(struct trace_uprobe *tu, struct perf_event *event) +{ + bool done; + + write_lock(&tu->filter.rwlock); + if (event->hw.target) { + list_del(&event->hw.tp_list); + done = tu->filter.nr_systemwide || + (event->hw.target->flags & PF_EXITING) || + uprobe_filter_event(tu, event); + } else { + tu->filter.nr_systemwide--; + done = tu->filter.nr_systemwide; + } + write_unlock(&tu->filter.rwlock); + + if (!done) + return uprobe_apply(tu->inode, tu->offset, &tu->consumer, false); + + return 0; +} + +static int uprobe_perf_open(struct trace_uprobe *tu, struct perf_event *event) +{ + bool done; + int err; + + write_lock(&tu->filter.rwlock); + if (event->hw.target) { + /* + * event->parent != NULL means copy_process(), we can avoid + * uprobe_apply(). current->mm must be probed and we can rely + * on dup_mmap() which preserves the already installed bp's. + * + * attr.enable_on_exec means that exec/mmap will install the + * breakpoints we need. + */ + done = tu->filter.nr_systemwide || + event->parent || event->attr.enable_on_exec || + uprobe_filter_event(tu, event); + list_add(&event->hw.tp_list, &tu->filter.perf_events); + } else { + done = tu->filter.nr_systemwide; + tu->filter.nr_systemwide++; + } + write_unlock(&tu->filter.rwlock); + + err = 0; + if (!done) { + err = uprobe_apply(tu->inode, tu->offset, &tu->consumer, true); + if (err) + uprobe_perf_close(tu, event); + } + return err; +} + +static bool uprobe_perf_filter(struct uprobe_consumer *uc, + enum uprobe_filter_ctx ctx, struct mm_struct *mm) +{ + struct trace_uprobe *tu; + int ret; + + tu = container_of(uc, struct trace_uprobe, consumer); + read_lock(&tu->filter.rwlock); + ret = __uprobe_perf_filter(&tu->filter, mm); + read_unlock(&tu->filter.rwlock); + + return ret; +} + +static void __uprobe_perf_func(struct trace_uprobe *tu, + unsigned long func, struct pt_regs *regs, + struct uprobe_cpu_buffer *ucb, int dsize) +{ + struct ftrace_event_call *call = &tu->tp.call; + struct uprobe_trace_entry_head *entry; + struct hlist_head *head; + void *data; + int size, esize; + int rctx; + + esize = SIZEOF_TRACE_ENTRY(is_ret_probe(tu)); + + size = esize + tu->tp.size + dsize; + size = ALIGN(size + sizeof(u32), sizeof(u64)) - sizeof(u32); + if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE, "profile buffer not large enough")) + return; + + preempt_disable(); + head = this_cpu_ptr(call->perf_events); + if (hlist_empty(head)) + goto out; + + entry = perf_trace_buf_prepare(size, call->event.type, NULL, &rctx); + if (!entry) + goto out; + + if (is_ret_probe(tu)) { + entry->vaddr[0] = func; + entry->vaddr[1] = instruction_pointer(regs); + data = DATAOF_TRACE_ENTRY(entry, true); + } else { + entry->vaddr[0] = instruction_pointer(regs); + data = DATAOF_TRACE_ENTRY(entry, false); + } + + memcpy(data, ucb->buf, tu->tp.size + dsize); + + if (size - esize > tu->tp.size + dsize) { + int len = tu->tp.size + dsize; + + memset(data + len, 0, size - esize - len); + } + + perf_trace_buf_submit(entry, size, rctx, 0, 1, regs, head, NULL); + out: + preempt_enable(); +} + +/* uprobe profile handler */ +static int uprobe_perf_func(struct trace_uprobe *tu, struct pt_regs *regs, + struct uprobe_cpu_buffer *ucb, int dsize) +{ + if (!uprobe_perf_filter(&tu->consumer, 0, current->mm)) + return UPROBE_HANDLER_REMOVE; + + if (!is_ret_probe(tu)) + __uprobe_perf_func(tu, 0, regs, ucb, dsize); + return 0; +} + +static void uretprobe_perf_func(struct trace_uprobe *tu, unsigned long func, + struct pt_regs *regs, + struct uprobe_cpu_buffer *ucb, int dsize) +{ + __uprobe_perf_func(tu, func, regs, ucb, dsize); +} +#endif /* CONFIG_PERF_EVENTS */ + +static int +trace_uprobe_register(struct ftrace_event_call *event, enum trace_reg type, + void *data) +{ + struct trace_uprobe *tu = event->data; + struct ftrace_event_file *file = data; + + switch (type) { + case TRACE_REG_REGISTER: + return probe_event_enable(tu, file, NULL); + + case TRACE_REG_UNREGISTER: + probe_event_disable(tu, file); + return 0; + +#ifdef CONFIG_PERF_EVENTS + case TRACE_REG_PERF_REGISTER: + return probe_event_enable(tu, NULL, uprobe_perf_filter); + + case TRACE_REG_PERF_UNREGISTER: + probe_event_disable(tu, NULL); + return 0; + + case TRACE_REG_PERF_OPEN: + return uprobe_perf_open(tu, data); + + case TRACE_REG_PERF_CLOSE: + return uprobe_perf_close(tu, data); + +#endif + default: + return 0; + } + return 0; +} + +static int uprobe_dispatcher(struct uprobe_consumer *con, struct pt_regs *regs) +{ + struct trace_uprobe *tu; + struct uprobe_dispatch_data udd; + struct uprobe_cpu_buffer *ucb; + int dsize, esize; + int ret = 0; + + + tu = container_of(con, struct trace_uprobe, consumer); + tu->nhit++; + + udd.tu = tu; + udd.bp_addr = instruction_pointer(regs); + + current->utask->vaddr = (unsigned long) &udd; + + if (WARN_ON_ONCE(!uprobe_cpu_buffer)) + return 0; + + dsize = __get_data_size(&tu->tp, regs); + esize = SIZEOF_TRACE_ENTRY(is_ret_probe(tu)); + + ucb = uprobe_buffer_get(); + store_trace_args(esize, &tu->tp, regs, ucb->buf, dsize); + + if (tu->tp.flags & TP_FLAG_TRACE) + ret |= uprobe_trace_func(tu, regs, ucb, dsize); + +#ifdef CONFIG_PERF_EVENTS + if (tu->tp.flags & TP_FLAG_PROFILE) + ret |= uprobe_perf_func(tu, regs, ucb, dsize); +#endif + uprobe_buffer_put(ucb); + return ret; +} + +static int uretprobe_dispatcher(struct uprobe_consumer *con, + unsigned long func, struct pt_regs *regs) +{ + struct trace_uprobe *tu; + struct uprobe_dispatch_data udd; + struct uprobe_cpu_buffer *ucb; + int dsize, esize; + + tu = container_of(con, struct trace_uprobe, consumer); + + udd.tu = tu; + udd.bp_addr = func; + + current->utask->vaddr = (unsigned long) &udd; + + if (WARN_ON_ONCE(!uprobe_cpu_buffer)) + return 0; + + dsize = __get_data_size(&tu->tp, regs); + esize = SIZEOF_TRACE_ENTRY(is_ret_probe(tu)); + + ucb = uprobe_buffer_get(); + store_trace_args(esize, &tu->tp, regs, ucb->buf, dsize); + + if (tu->tp.flags & TP_FLAG_TRACE) + uretprobe_trace_func(tu, func, regs, ucb, dsize); + +#ifdef CONFIG_PERF_EVENTS + if (tu->tp.flags & TP_FLAG_PROFILE) + uretprobe_perf_func(tu, func, regs, ucb, dsize); +#endif + uprobe_buffer_put(ucb); + return 0; +} + +static struct trace_event_functions uprobe_funcs = { + .trace = print_uprobe_event +}; + +static int register_uprobe_event(struct trace_uprobe *tu) +{ + struct ftrace_event_call *call = &tu->tp.call; + int ret; + + /* Initialize ftrace_event_call */ + INIT_LIST_HEAD(&call->class->fields); + call->event.funcs = &uprobe_funcs; + call->class->define_fields = uprobe_event_define_fields; + + if (set_print_fmt(&tu->tp, is_ret_probe(tu)) < 0) + return -ENOMEM; + + ret = register_ftrace_event(&call->event); + if (!ret) { + kfree(call->print_fmt); + return -ENODEV; + } + + call->class->reg = trace_uprobe_register; + call->data = tu; + ret = trace_add_event_call(call); + + if (ret) { + pr_info("Failed to register uprobe event: %s\n", + ftrace_event_name(call)); + kfree(call->print_fmt); + unregister_ftrace_event(&call->event); + } + + return ret; +} + +static int unregister_uprobe_event(struct trace_uprobe *tu) +{ + int ret; + + /* tu->event is unregistered in trace_remove_event_call() */ + ret = trace_remove_event_call(&tu->tp.call); + if (ret) + return ret; + kfree(tu->tp.call.print_fmt); + tu->tp.call.print_fmt = NULL; + return 0; +} + +/* Make a trace interface for controling probe points */ +static __init int init_uprobe_trace(void) +{ + struct dentry *d_tracer; + + d_tracer = tracing_init_dentry(); + if (IS_ERR(d_tracer)) + return 0; + + trace_create_file("uprobe_events", 0644, d_tracer, + NULL, &uprobe_events_ops); + /* Profile interface */ + trace_create_file("uprobe_profile", 0444, d_tracer, + NULL, &uprobe_profile_ops); + return 0; +} + +fs_initcall(init_uprobe_trace); diff --git a/kernel/kernel/tracepoint.c b/kernel/kernel/tracepoint.c new file mode 100644 index 000000000..3490407dc --- /dev/null +++ b/kernel/kernel/tracepoint.c @@ -0,0 +1,520 @@ +/* + * Copyright (C) 2008-2014 Mathieu Desnoyers + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +extern struct tracepoint * const __start___tracepoints_ptrs[]; +extern struct tracepoint * const __stop___tracepoints_ptrs[]; + +/* Set to 1 to enable tracepoint debug output */ +static const int tracepoint_debug; + +#ifdef CONFIG_MODULES +/* + * Tracepoint module list mutex protects the local module list. + */ +static DEFINE_MUTEX(tracepoint_module_list_mutex); + +/* Local list of struct tp_module */ +static LIST_HEAD(tracepoint_module_list); +#endif /* CONFIG_MODULES */ + +/* + * tracepoints_mutex protects the builtin and module tracepoints. + * tracepoints_mutex nests inside tracepoint_module_list_mutex. + */ +static DEFINE_MUTEX(tracepoints_mutex); + +/* + * Note about RCU : + * It is used to delay the free of multiple probes array until a quiescent + * state is reached. + */ +struct tp_probes { + struct rcu_head rcu; + struct tracepoint_func probes[0]; +}; + +static inline void *allocate_probes(int count) +{ + struct tp_probes *p = kmalloc(count * sizeof(struct tracepoint_func) + + sizeof(struct tp_probes), GFP_KERNEL); + return p == NULL ? NULL : p->probes; +} + +static void rcu_free_old_probes(struct rcu_head *head) +{ + kfree(container_of(head, struct tp_probes, rcu)); +} + +static inline void release_probes(struct tracepoint_func *old) +{ + if (old) { + struct tp_probes *tp_probes = container_of(old, + struct tp_probes, probes[0]); + call_rcu_sched(&tp_probes->rcu, rcu_free_old_probes); + } +} + +static void debug_print_probes(struct tracepoint_func *funcs) +{ + int i; + + if (!tracepoint_debug || !funcs) + return; + + for (i = 0; funcs[i].func; i++) + printk(KERN_DEBUG "Probe %d : %p\n", i, funcs[i].func); +} + +static struct tracepoint_func *func_add(struct tracepoint_func **funcs, + struct tracepoint_func *tp_func) +{ + int nr_probes = 0; + struct tracepoint_func *old, *new; + + if (WARN_ON(!tp_func->func)) + return ERR_PTR(-EINVAL); + + debug_print_probes(*funcs); + old = *funcs; + if (old) { + /* (N -> N+1), (N != 0, 1) probes */ + for (nr_probes = 0; old[nr_probes].func; nr_probes++) + if (old[nr_probes].func == tp_func->func && + old[nr_probes].data == tp_func->data) + return ERR_PTR(-EEXIST); + } + /* + 2 : one for new probe, one for NULL func */ + new = allocate_probes(nr_probes + 2); + if (new == NULL) + return ERR_PTR(-ENOMEM); + if (old) + memcpy(new, old, nr_probes * sizeof(struct tracepoint_func)); + new[nr_probes] = *tp_func; + new[nr_probes + 1].func = NULL; + *funcs = new; + debug_print_probes(*funcs); + return old; +} + +static void *func_remove(struct tracepoint_func **funcs, + struct tracepoint_func *tp_func) +{ + int nr_probes = 0, nr_del = 0, i; + struct tracepoint_func *old, *new; + + old = *funcs; + + if (!old) + return ERR_PTR(-ENOENT); + + debug_print_probes(*funcs); + /* (N -> M), (N > 1, M >= 0) probes */ + if (tp_func->func) { + for (nr_probes = 0; old[nr_probes].func; nr_probes++) { + if (old[nr_probes].func == tp_func->func && + old[nr_probes].data == tp_func->data) + nr_del++; + } + } + + /* + * If probe is NULL, then nr_probes = nr_del = 0, and then the + * entire entry will be removed. + */ + if (nr_probes - nr_del == 0) { + /* N -> 0, (N > 1) */ + *funcs = NULL; + debug_print_probes(*funcs); + return old; + } else { + int j = 0; + /* N -> M, (N > 1, M > 0) */ + /* + 1 for NULL */ + new = allocate_probes(nr_probes - nr_del + 1); + if (new == NULL) + return ERR_PTR(-ENOMEM); + for (i = 0; old[i].func; i++) + if (old[i].func != tp_func->func + || old[i].data != tp_func->data) + new[j++] = old[i]; + new[nr_probes - nr_del].func = NULL; + *funcs = new; + } + debug_print_probes(*funcs); + return old; +} + +/* + * Add the probe function to a tracepoint. + */ +static int tracepoint_add_func(struct tracepoint *tp, + struct tracepoint_func *func) +{ + struct tracepoint_func *old, *tp_funcs; + + if (tp->regfunc && !static_key_enabled(&tp->key)) + tp->regfunc(); + + tp_funcs = rcu_dereference_protected(tp->funcs, + lockdep_is_held(&tracepoints_mutex)); + old = func_add(&tp_funcs, func); + if (IS_ERR(old)) { + WARN_ON_ONCE(1); + return PTR_ERR(old); + } + + /* + * rcu_assign_pointer has a smp_wmb() which makes sure that the new + * probe callbacks array is consistent before setting a pointer to it. + * This array is referenced by __DO_TRACE from + * include/linux/tracepoints.h. A matching smp_read_barrier_depends() + * is used. + */ + rcu_assign_pointer(tp->funcs, tp_funcs); + if (!static_key_enabled(&tp->key)) + static_key_slow_inc(&tp->key); + release_probes(old); + return 0; +} + +/* + * Remove a probe function from a tracepoint. + * Note: only waiting an RCU period after setting elem->call to the empty + * function insures that the original callback is not used anymore. This insured + * by preempt_disable around the call site. + */ +static int tracepoint_remove_func(struct tracepoint *tp, + struct tracepoint_func *func) +{ + struct tracepoint_func *old, *tp_funcs; + + tp_funcs = rcu_dereference_protected(tp->funcs, + lockdep_is_held(&tracepoints_mutex)); + old = func_remove(&tp_funcs, func); + if (IS_ERR(old)) { + WARN_ON_ONCE(1); + return PTR_ERR(old); + } + + if (!tp_funcs) { + /* Removed last function */ + if (tp->unregfunc && static_key_enabled(&tp->key)) + tp->unregfunc(); + + if (static_key_enabled(&tp->key)) + static_key_slow_dec(&tp->key); + } + rcu_assign_pointer(tp->funcs, tp_funcs); + release_probes(old); + return 0; +} + +/** + * tracepoint_probe_register - Connect a probe to a tracepoint + * @tp: tracepoint + * @probe: probe handler + * @data: tracepoint data + * + * Returns 0 if ok, error value on error. + * Note: if @tp is within a module, the caller is responsible for + * unregistering the probe before the module is gone. This can be + * performed either with a tracepoint module going notifier, or from + * within module exit functions. + */ +int tracepoint_probe_register(struct tracepoint *tp, void *probe, void *data) +{ + struct tracepoint_func tp_func; + int ret; + + mutex_lock(&tracepoints_mutex); + tp_func.func = probe; + tp_func.data = data; + ret = tracepoint_add_func(tp, &tp_func); + mutex_unlock(&tracepoints_mutex); + return ret; +} +EXPORT_SYMBOL_GPL(tracepoint_probe_register); + +/** + * tracepoint_probe_unregister - Disconnect a probe from a tracepoint + * @tp: tracepoint + * @probe: probe function pointer + * @data: tracepoint data + * + * Returns 0 if ok, error value on error. + */ +int tracepoint_probe_unregister(struct tracepoint *tp, void *probe, void *data) +{ + struct tracepoint_func tp_func; + int ret; + + mutex_lock(&tracepoints_mutex); + tp_func.func = probe; + tp_func.data = data; + ret = tracepoint_remove_func(tp, &tp_func); + mutex_unlock(&tracepoints_mutex); + return ret; +} +EXPORT_SYMBOL_GPL(tracepoint_probe_unregister); + +#ifdef CONFIG_MODULES +bool trace_module_has_bad_taint(struct module *mod) +{ + return mod->taints & ~((1 << TAINT_OOT_MODULE) | (1 << TAINT_CRAP) | + (1 << TAINT_UNSIGNED_MODULE)); +} + +static BLOCKING_NOTIFIER_HEAD(tracepoint_notify_list); + +/** + * register_tracepoint_notifier - register tracepoint coming/going notifier + * @nb: notifier block + * + * Notifiers registered with this function are called on module + * coming/going with the tracepoint_module_list_mutex held. + * The notifier block callback should expect a "struct tp_module" data + * pointer. + */ +int register_tracepoint_module_notifier(struct notifier_block *nb) +{ + struct tp_module *tp_mod; + int ret; + + mutex_lock(&tracepoint_module_list_mutex); + ret = blocking_notifier_chain_register(&tracepoint_notify_list, nb); + if (ret) + goto end; + list_for_each_entry(tp_mod, &tracepoint_module_list, list) + (void) nb->notifier_call(nb, MODULE_STATE_COMING, tp_mod); +end: + mutex_unlock(&tracepoint_module_list_mutex); + return ret; +} +EXPORT_SYMBOL_GPL(register_tracepoint_module_notifier); + +/** + * unregister_tracepoint_notifier - unregister tracepoint coming/going notifier + * @nb: notifier block + * + * The notifier block callback should expect a "struct tp_module" data + * pointer. + */ +int unregister_tracepoint_module_notifier(struct notifier_block *nb) +{ + struct tp_module *tp_mod; + int ret; + + mutex_lock(&tracepoint_module_list_mutex); + ret = blocking_notifier_chain_unregister(&tracepoint_notify_list, nb); + if (ret) + goto end; + list_for_each_entry(tp_mod, &tracepoint_module_list, list) + (void) nb->notifier_call(nb, MODULE_STATE_GOING, tp_mod); +end: + mutex_unlock(&tracepoint_module_list_mutex); + return ret; + +} +EXPORT_SYMBOL_GPL(unregister_tracepoint_module_notifier); + +/* + * Ensure the tracer unregistered the module's probes before the module + * teardown is performed. Prevents leaks of probe and data pointers. + */ +static void tp_module_going_check_quiescent(struct tracepoint * const *begin, + struct tracepoint * const *end) +{ + struct tracepoint * const *iter; + + if (!begin) + return; + for (iter = begin; iter < end; iter++) + WARN_ON_ONCE((*iter)->funcs); +} + +static int tracepoint_module_coming(struct module *mod) +{ + struct tp_module *tp_mod; + int ret = 0; + + if (!mod->num_tracepoints) + return 0; + + /* + * We skip modules that taint the kernel, especially those with different + * module headers (for forced load), to make sure we don't cause a crash. + * Staging, out-of-tree, and unsigned GPL modules are fine. + */ + if (trace_module_has_bad_taint(mod)) + return 0; + mutex_lock(&tracepoint_module_list_mutex); + tp_mod = kmalloc(sizeof(struct tp_module), GFP_KERNEL); + if (!tp_mod) { + ret = -ENOMEM; + goto end; + } + tp_mod->mod = mod; + list_add_tail(&tp_mod->list, &tracepoint_module_list); + blocking_notifier_call_chain(&tracepoint_notify_list, + MODULE_STATE_COMING, tp_mod); +end: + mutex_unlock(&tracepoint_module_list_mutex); + return ret; +} + +static void tracepoint_module_going(struct module *mod) +{ + struct tp_module *tp_mod; + + if (!mod->num_tracepoints) + return; + + mutex_lock(&tracepoint_module_list_mutex); + list_for_each_entry(tp_mod, &tracepoint_module_list, list) { + if (tp_mod->mod == mod) { + blocking_notifier_call_chain(&tracepoint_notify_list, + MODULE_STATE_GOING, tp_mod); + list_del(&tp_mod->list); + kfree(tp_mod); + /* + * Called the going notifier before checking for + * quiescence. + */ + tp_module_going_check_quiescent(mod->tracepoints_ptrs, + mod->tracepoints_ptrs + mod->num_tracepoints); + break; + } + } + /* + * In the case of modules that were tainted at "coming", we'll simply + * walk through the list without finding it. We cannot use the "tainted" + * flag on "going", in case a module taints the kernel only after being + * loaded. + */ + mutex_unlock(&tracepoint_module_list_mutex); +} + +static int tracepoint_module_notify(struct notifier_block *self, + unsigned long val, void *data) +{ + struct module *mod = data; + int ret = 0; + + switch (val) { + case MODULE_STATE_COMING: + ret = tracepoint_module_coming(mod); + break; + case MODULE_STATE_LIVE: + break; + case MODULE_STATE_GOING: + tracepoint_module_going(mod); + break; + case MODULE_STATE_UNFORMED: + break; + } + return ret; +} + +static struct notifier_block tracepoint_module_nb = { + .notifier_call = tracepoint_module_notify, + .priority = 0, +}; + +static __init int init_tracepoints(void) +{ + int ret; + + ret = register_module_notifier(&tracepoint_module_nb); + if (ret) + pr_warning("Failed to register tracepoint module enter notifier\n"); + + return ret; +} +__initcall(init_tracepoints); +#endif /* CONFIG_MODULES */ + +static void for_each_tracepoint_range(struct tracepoint * const *begin, + struct tracepoint * const *end, + void (*fct)(struct tracepoint *tp, void *priv), + void *priv) +{ + struct tracepoint * const *iter; + + if (!begin) + return; + for (iter = begin; iter < end; iter++) + fct(*iter, priv); +} + +/** + * for_each_kernel_tracepoint - iteration on all kernel tracepoints + * @fct: callback + * @priv: private data + */ +void for_each_kernel_tracepoint(void (*fct)(struct tracepoint *tp, void *priv), + void *priv) +{ + for_each_tracepoint_range(__start___tracepoints_ptrs, + __stop___tracepoints_ptrs, fct, priv); +} +EXPORT_SYMBOL_GPL(for_each_kernel_tracepoint); + +#ifdef CONFIG_HAVE_SYSCALL_TRACEPOINTS + +/* NB: reg/unreg are called while guarded with the tracepoints_mutex */ +static int sys_tracepoint_refcount; + +void syscall_regfunc(void) +{ + struct task_struct *p, *t; + + if (!sys_tracepoint_refcount) { + read_lock(&tasklist_lock); + for_each_process_thread(p, t) { + set_tsk_thread_flag(t, TIF_SYSCALL_TRACEPOINT); + } + read_unlock(&tasklist_lock); + } + sys_tracepoint_refcount++; +} + +void syscall_unregfunc(void) +{ + struct task_struct *p, *t; + + sys_tracepoint_refcount--; + if (!sys_tracepoint_refcount) { + read_lock(&tasklist_lock); + for_each_process_thread(p, t) { + clear_tsk_thread_flag(t, TIF_SYSCALL_TRACEPOINT); + } + read_unlock(&tasklist_lock); + } +} +#endif diff --git a/kernel/kernel/tsacct.c b/kernel/kernel/tsacct.c new file mode 100644 index 000000000..975cb49e3 --- /dev/null +++ b/kernel/kernel/tsacct.c @@ -0,0 +1,180 @@ +/* + * tsacct.c - System accounting over taskstats interface + * + * Copyright (C) Jay Lan, + * + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + */ + +#include +#include +#include +#include +#include +#include + +/* + * fill in basic accounting fields + */ +void bacct_add_tsk(struct user_namespace *user_ns, + struct pid_namespace *pid_ns, + struct taskstats *stats, struct task_struct *tsk) +{ + const struct cred *tcred; + cputime_t utime, stime, utimescaled, stimescaled; + u64 delta; + + BUILD_BUG_ON(TS_COMM_LEN < TASK_COMM_LEN); + + /* calculate task elapsed time in nsec */ + delta = ktime_get_ns() - tsk->start_time; + /* Convert to micro seconds */ + do_div(delta, NSEC_PER_USEC); + stats->ac_etime = delta; + /* Convert to seconds for btime */ + do_div(delta, USEC_PER_SEC); + stats->ac_btime = get_seconds() - delta; + if (thread_group_leader(tsk)) { + stats->ac_exitcode = tsk->exit_code; + if (tsk->flags & PF_FORKNOEXEC) + stats->ac_flag |= AFORK; + } + if (tsk->flags & PF_SUPERPRIV) + stats->ac_flag |= ASU; + if (tsk->flags & PF_DUMPCORE) + stats->ac_flag |= ACORE; + if (tsk->flags & PF_SIGNALED) + stats->ac_flag |= AXSIG; + stats->ac_nice = task_nice(tsk); + stats->ac_sched = tsk->policy; + stats->ac_pid = task_pid_nr_ns(tsk, pid_ns); + rcu_read_lock(); + tcred = __task_cred(tsk); + stats->ac_uid = from_kuid_munged(user_ns, tcred->uid); + stats->ac_gid = from_kgid_munged(user_ns, tcred->gid); + stats->ac_ppid = pid_alive(tsk) ? + task_tgid_nr_ns(rcu_dereference(tsk->real_parent), pid_ns) : 0; + rcu_read_unlock(); + + task_cputime(tsk, &utime, &stime); + stats->ac_utime = cputime_to_usecs(utime); + stats->ac_stime = cputime_to_usecs(stime); + + task_cputime_scaled(tsk, &utimescaled, &stimescaled); + stats->ac_utimescaled = cputime_to_usecs(utimescaled); + stats->ac_stimescaled = cputime_to_usecs(stimescaled); + + stats->ac_minflt = tsk->min_flt; + stats->ac_majflt = tsk->maj_flt; + + strncpy(stats->ac_comm, tsk->comm, sizeof(stats->ac_comm)); +} + + +#ifdef CONFIG_TASK_XACCT + +#define KB 1024 +#define MB (1024*KB) +#define KB_MASK (~(KB-1)) +/* + * fill in extended accounting fields + */ +void xacct_add_tsk(struct taskstats *stats, struct task_struct *p) +{ + struct mm_struct *mm; + + /* convert pages-usec to Mbyte-usec */ + stats->coremem = p->acct_rss_mem1 * PAGE_SIZE / MB; + stats->virtmem = p->acct_vm_mem1 * PAGE_SIZE / MB; + mm = get_task_mm(p); + if (mm) { + /* adjust to KB unit */ + stats->hiwater_rss = get_mm_hiwater_rss(mm) * PAGE_SIZE / KB; + stats->hiwater_vm = get_mm_hiwater_vm(mm) * PAGE_SIZE / KB; + mmput(mm); + } + stats->read_char = p->ioac.rchar & KB_MASK; + stats->write_char = p->ioac.wchar & KB_MASK; + stats->read_syscalls = p->ioac.syscr & KB_MASK; + stats->write_syscalls = p->ioac.syscw & KB_MASK; +#ifdef CONFIG_TASK_IO_ACCOUNTING + stats->read_bytes = p->ioac.read_bytes & KB_MASK; + stats->write_bytes = p->ioac.write_bytes & KB_MASK; + stats->cancelled_write_bytes = p->ioac.cancelled_write_bytes & KB_MASK; +#else + stats->read_bytes = 0; + stats->write_bytes = 0; + stats->cancelled_write_bytes = 0; +#endif +} +#undef KB +#undef MB + +static void __acct_update_integrals(struct task_struct *tsk, + cputime_t utime, cputime_t stime) +{ + if (likely(tsk->mm)) { + cputime_t time, dtime; + struct timeval value; + unsigned long flags; + u64 delta; + + local_irq_save(flags); + time = stime + utime; + dtime = time - tsk->acct_timexpd; + jiffies_to_timeval(cputime_to_jiffies(dtime), &value); + delta = value.tv_sec; + delta = delta * USEC_PER_SEC + value.tv_usec; + + if (delta == 0) + goto out; + tsk->acct_timexpd = time; + tsk->acct_rss_mem1 += delta * get_mm_rss(tsk->mm); + tsk->acct_vm_mem1 += delta * tsk->mm->total_vm; + out: + local_irq_restore(flags); + } +} + +/** + * acct_update_integrals - update mm integral fields in task_struct + * @tsk: task_struct for accounting + */ +void acct_update_integrals(struct task_struct *tsk) +{ + cputime_t utime, stime; + + task_cputime(tsk, &utime, &stime); + __acct_update_integrals(tsk, utime, stime); +} + +/** + * acct_account_cputime - update mm integral after cputime update + * @tsk: task_struct for accounting + */ +void acct_account_cputime(struct task_struct *tsk) +{ + __acct_update_integrals(tsk, tsk->utime, tsk->stime); +} + +/** + * acct_clear_integrals - clear the mm integral fields in task_struct + * @tsk: task_struct whose accounting fields are cleared + */ +void acct_clear_integrals(struct task_struct *tsk) +{ + tsk->acct_timexpd = 0; + tsk->acct_rss_mem1 = 0; + tsk->acct_vm_mem1 = 0; +} +#endif diff --git a/kernel/kernel/uid16.c b/kernel/kernel/uid16.c new file mode 100644 index 000000000..d58cc4d8f --- /dev/null +++ b/kernel/kernel/uid16.c @@ -0,0 +1,217 @@ +/* + * Wrapper functions for 16bit uid back compatibility. All nicely tied + * together in the faint hope we can take the out in five years time. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +SYSCALL_DEFINE3(chown16, const char __user *, filename, old_uid_t, user, old_gid_t, group) +{ + return sys_chown(filename, low2highuid(user), low2highgid(group)); +} + +SYSCALL_DEFINE3(lchown16, const char __user *, filename, old_uid_t, user, old_gid_t, group) +{ + return sys_lchown(filename, low2highuid(user), low2highgid(group)); +} + +SYSCALL_DEFINE3(fchown16, unsigned int, fd, old_uid_t, user, old_gid_t, group) +{ + return sys_fchown(fd, low2highuid(user), low2highgid(group)); +} + +SYSCALL_DEFINE2(setregid16, old_gid_t, rgid, old_gid_t, egid) +{ + return sys_setregid(low2highgid(rgid), low2highgid(egid)); +} + +SYSCALL_DEFINE1(setgid16, old_gid_t, gid) +{ + return sys_setgid(low2highgid(gid)); +} + +SYSCALL_DEFINE2(setreuid16, old_uid_t, ruid, old_uid_t, euid) +{ + return sys_setreuid(low2highuid(ruid), low2highuid(euid)); +} + +SYSCALL_DEFINE1(setuid16, old_uid_t, uid) +{ + return sys_setuid(low2highuid(uid)); +} + +SYSCALL_DEFINE3(setresuid16, old_uid_t, ruid, old_uid_t, euid, old_uid_t, suid) +{ + return sys_setresuid(low2highuid(ruid), low2highuid(euid), + low2highuid(suid)); +} + +SYSCALL_DEFINE3(getresuid16, old_uid_t __user *, ruidp, old_uid_t __user *, euidp, old_uid_t __user *, suidp) +{ + const struct cred *cred = current_cred(); + int retval; + old_uid_t ruid, euid, suid; + + ruid = high2lowuid(from_kuid_munged(cred->user_ns, cred->uid)); + euid = high2lowuid(from_kuid_munged(cred->user_ns, cred->euid)); + suid = high2lowuid(from_kuid_munged(cred->user_ns, cred->suid)); + + if (!(retval = put_user(ruid, ruidp)) && + !(retval = put_user(euid, euidp))) + retval = put_user(suid, suidp); + + return retval; +} + +SYSCALL_DEFINE3(setresgid16, old_gid_t, rgid, old_gid_t, egid, old_gid_t, sgid) +{ + return sys_setresgid(low2highgid(rgid), low2highgid(egid), + low2highgid(sgid)); +} + + +SYSCALL_DEFINE3(getresgid16, old_gid_t __user *, rgidp, old_gid_t __user *, egidp, old_gid_t __user *, sgidp) +{ + const struct cred *cred = current_cred(); + int retval; + old_gid_t rgid, egid, sgid; + + rgid = high2lowgid(from_kgid_munged(cred->user_ns, cred->gid)); + egid = high2lowgid(from_kgid_munged(cred->user_ns, cred->egid)); + sgid = high2lowgid(from_kgid_munged(cred->user_ns, cred->sgid)); + + if (!(retval = put_user(rgid, rgidp)) && + !(retval = put_user(egid, egidp))) + retval = put_user(sgid, sgidp); + + return retval; +} + +SYSCALL_DEFINE1(setfsuid16, old_uid_t, uid) +{ + return sys_setfsuid(low2highuid(uid)); +} + +SYSCALL_DEFINE1(setfsgid16, old_gid_t, gid) +{ + return sys_setfsgid(low2highgid(gid)); +} + +static int groups16_to_user(old_gid_t __user *grouplist, + struct group_info *group_info) +{ + struct user_namespace *user_ns = current_user_ns(); + int i; + old_gid_t group; + kgid_t kgid; + + for (i = 0; i < group_info->ngroups; i++) { + kgid = GROUP_AT(group_info, i); + group = high2lowgid(from_kgid_munged(user_ns, kgid)); + if (put_user(group, grouplist+i)) + return -EFAULT; + } + + return 0; +} + +static int groups16_from_user(struct group_info *group_info, + old_gid_t __user *grouplist) +{ + struct user_namespace *user_ns = current_user_ns(); + int i; + old_gid_t group; + kgid_t kgid; + + for (i = 0; i < group_info->ngroups; i++) { + if (get_user(group, grouplist+i)) + return -EFAULT; + + kgid = make_kgid(user_ns, low2highgid(group)); + if (!gid_valid(kgid)) + return -EINVAL; + + GROUP_AT(group_info, i) = kgid; + } + + return 0; +} + +SYSCALL_DEFINE2(getgroups16, int, gidsetsize, old_gid_t __user *, grouplist) +{ + const struct cred *cred = current_cred(); + int i; + + if (gidsetsize < 0) + return -EINVAL; + + i = cred->group_info->ngroups; + if (gidsetsize) { + if (i > gidsetsize) { + i = -EINVAL; + goto out; + } + if (groups16_to_user(grouplist, cred->group_info)) { + i = -EFAULT; + goto out; + } + } +out: + return i; +} + +SYSCALL_DEFINE2(setgroups16, int, gidsetsize, old_gid_t __user *, grouplist) +{ + struct group_info *group_info; + int retval; + + if (!may_setgroups()) + return -EPERM; + if ((unsigned)gidsetsize > NGROUPS_MAX) + return -EINVAL; + + group_info = groups_alloc(gidsetsize); + if (!group_info) + return -ENOMEM; + retval = groups16_from_user(group_info, grouplist); + if (retval) { + put_group_info(group_info); + return retval; + } + + retval = set_current_groups(group_info); + put_group_info(group_info); + + return retval; +} + +SYSCALL_DEFINE0(getuid16) +{ + return high2lowuid(from_kuid_munged(current_user_ns(), current_uid())); +} + +SYSCALL_DEFINE0(geteuid16) +{ + return high2lowuid(from_kuid_munged(current_user_ns(), current_euid())); +} + +SYSCALL_DEFINE0(getgid16) +{ + return high2lowgid(from_kgid_munged(current_user_ns(), current_gid())); +} + +SYSCALL_DEFINE0(getegid16) +{ + return high2lowgid(from_kgid_munged(current_user_ns(), current_egid())); +} diff --git a/kernel/kernel/up.c b/kernel/kernel/up.c new file mode 100644 index 000000000..1760bf3d1 --- /dev/null +++ b/kernel/kernel/up.c @@ -0,0 +1,84 @@ +/* + * Uniprocessor-only support functions. The counterpart to kernel/smp.c + */ + +#include +#include +#include +#include + +int smp_call_function_single(int cpu, void (*func) (void *info), void *info, + int wait) +{ + unsigned long flags; + + WARN_ON(cpu != 0); + + local_irq_save(flags); + func(info); + local_irq_restore(flags); + + return 0; +} +EXPORT_SYMBOL(smp_call_function_single); + +int smp_call_function_single_async(int cpu, struct call_single_data *csd) +{ + unsigned long flags; + + local_irq_save(flags); + csd->func(csd->info); + local_irq_restore(flags); + return 0; +} +EXPORT_SYMBOL(smp_call_function_single_async); + +int on_each_cpu(smp_call_func_t func, void *info, int wait) +{ + unsigned long flags; + + local_irq_save(flags); + func(info); + local_irq_restore(flags); + return 0; +} +EXPORT_SYMBOL(on_each_cpu); + +/* + * Note we still need to test the mask even for UP + * because we actually can get an empty mask from + * code that on SMP might call us without the local + * CPU in the mask. + */ +void on_each_cpu_mask(const struct cpumask *mask, + smp_call_func_t func, void *info, bool wait) +{ + unsigned long flags; + + if (cpumask_test_cpu(0, mask)) { + local_irq_save(flags); + func(info); + local_irq_restore(flags); + } +} +EXPORT_SYMBOL(on_each_cpu_mask); + +/* + * Preemption is disabled here to make sure the cond_func is called under the + * same condtions in UP and SMP. + */ +void on_each_cpu_cond(bool (*cond_func)(int cpu, void *info), + smp_call_func_t func, void *info, bool wait, + gfp_t gfp_flags) +{ + unsigned long flags; + + preempt_disable(); + if (cond_func(0, info)) { + local_irq_save(flags); + func(info); + local_irq_restore(flags); + } + preempt_enable(); +} +EXPORT_SYMBOL(on_each_cpu_cond); diff --git a/kernel/kernel/user-return-notifier.c b/kernel/kernel/user-return-notifier.c new file mode 100644 index 000000000..9586b670a --- /dev/null +++ b/kernel/kernel/user-return-notifier.c @@ -0,0 +1,44 @@ + +#include +#include +#include +#include + +static DEFINE_PER_CPU(struct hlist_head, return_notifier_list); + +/* + * Request a notification when the current cpu returns to userspace. Must be + * called in atomic context. The notifier will also be called in atomic + * context. + */ +void user_return_notifier_register(struct user_return_notifier *urn) +{ + set_tsk_thread_flag(current, TIF_USER_RETURN_NOTIFY); + hlist_add_head(&urn->link, this_cpu_ptr(&return_notifier_list)); +} +EXPORT_SYMBOL_GPL(user_return_notifier_register); + +/* + * Removes a registered user return notifier. Must be called from atomic + * context, and from the same cpu registration occurred in. + */ +void user_return_notifier_unregister(struct user_return_notifier *urn) +{ + hlist_del(&urn->link); + if (hlist_empty(this_cpu_ptr(&return_notifier_list))) + clear_tsk_thread_flag(current, TIF_USER_RETURN_NOTIFY); +} +EXPORT_SYMBOL_GPL(user_return_notifier_unregister); + +/* Calls registered user return notifiers */ +void fire_user_return_notifiers(void) +{ + struct user_return_notifier *urn; + struct hlist_node *tmp2; + struct hlist_head *head; + + head = &get_cpu_var(return_notifier_list); + hlist_for_each_entry_safe(urn, tmp2, head, link) + urn->on_user_return(urn); + put_cpu_var(return_notifier_list); +} diff --git a/kernel/kernel/user.c b/kernel/kernel/user.c new file mode 100644 index 000000000..1a2e88e98 --- /dev/null +++ b/kernel/kernel/user.c @@ -0,0 +1,228 @@ +/* + * The "user cache". + * + * (C) Copyright 1991-2000 Linus Torvalds + * + * We have a per-user structure to keep track of how many + * processes, files etc the user has claimed, in order to be + * able to have per-user limits for system resources. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +/* + * userns count is 1 for root user, 1 for init_uts_ns, + * and 1 for... ? + */ +struct user_namespace init_user_ns = { + .uid_map = { + .nr_extents = 1, + .extent[0] = { + .first = 0, + .lower_first = 0, + .count = 4294967295U, + }, + }, + .gid_map = { + .nr_extents = 1, + .extent[0] = { + .first = 0, + .lower_first = 0, + .count = 4294967295U, + }, + }, + .projid_map = { + .nr_extents = 1, + .extent[0] = { + .first = 0, + .lower_first = 0, + .count = 4294967295U, + }, + }, + .count = ATOMIC_INIT(3), + .owner = GLOBAL_ROOT_UID, + .group = GLOBAL_ROOT_GID, + .ns.inum = PROC_USER_INIT_INO, +#ifdef CONFIG_USER_NS + .ns.ops = &userns_operations, +#endif + .flags = USERNS_INIT_FLAGS, +#ifdef CONFIG_PERSISTENT_KEYRINGS + .persistent_keyring_register_sem = + __RWSEM_INITIALIZER(init_user_ns.persistent_keyring_register_sem), +#endif +}; +EXPORT_SYMBOL_GPL(init_user_ns); + +/* + * UID task count cache, to get fast user lookup in "alloc_uid" + * when changing user ID's (ie setuid() and friends). + */ + +#define UIDHASH_BITS (CONFIG_BASE_SMALL ? 3 : 7) +#define UIDHASH_SZ (1 << UIDHASH_BITS) +#define UIDHASH_MASK (UIDHASH_SZ - 1) +#define __uidhashfn(uid) (((uid >> UIDHASH_BITS) + uid) & UIDHASH_MASK) +#define uidhashentry(uid) (uidhash_table + __uidhashfn((__kuid_val(uid)))) + +static struct kmem_cache *uid_cachep; +struct hlist_head uidhash_table[UIDHASH_SZ]; + +/* + * The uidhash_lock is mostly taken from process context, but it is + * occasionally also taken from softirq/tasklet context, when + * task-structs get RCU-freed. Hence all locking must be softirq-safe. + * But free_uid() is also called with local interrupts disabled, and running + * local_bh_enable() with local interrupts disabled is an error - we'll run + * softirq callbacks, and they can unconditionally enable interrupts, and + * the caller of free_uid() didn't expect that.. + */ +static DEFINE_SPINLOCK(uidhash_lock); + +/* root_user.__count is 1, for init task cred */ +struct user_struct root_user = { + .__count = ATOMIC_INIT(1), + .processes = ATOMIC_INIT(1), + .sigpending = ATOMIC_INIT(0), + .locked_shm = 0, + .uid = GLOBAL_ROOT_UID, +}; + +/* + * These routines must be called with the uidhash spinlock held! + */ +static void uid_hash_insert(struct user_struct *up, struct hlist_head *hashent) +{ + hlist_add_head(&up->uidhash_node, hashent); +} + +static void uid_hash_remove(struct user_struct *up) +{ + hlist_del_init(&up->uidhash_node); +} + +static struct user_struct *uid_hash_find(kuid_t uid, struct hlist_head *hashent) +{ + struct user_struct *user; + + hlist_for_each_entry(user, hashent, uidhash_node) { + if (uid_eq(user->uid, uid)) { + atomic_inc(&user->__count); + return user; + } + } + + return NULL; +} + +/* IRQs are disabled and uidhash_lock is held upon function entry. + * IRQ state (as stored in flags) is restored and uidhash_lock released + * upon function exit. + */ +static void free_user(struct user_struct *up, unsigned long flags) + __releases(&uidhash_lock) +{ + uid_hash_remove(up); + spin_unlock_irqrestore(&uidhash_lock, flags); + key_put(up->uid_keyring); + key_put(up->session_keyring); + kmem_cache_free(uid_cachep, up); +} + +/* + * Locate the user_struct for the passed UID. If found, take a ref on it. The + * caller must undo that ref with free_uid(). + * + * If the user_struct could not be found, return NULL. + */ +struct user_struct *find_user(kuid_t uid) +{ + struct user_struct *ret; + unsigned long flags; + + spin_lock_irqsave(&uidhash_lock, flags); + ret = uid_hash_find(uid, uidhashentry(uid)); + spin_unlock_irqrestore(&uidhash_lock, flags); + return ret; +} + +void free_uid(struct user_struct *up) +{ + unsigned long flags; + + if (!up) + return; + + local_irq_save_nort(flags); + if (atomic_dec_and_lock(&up->__count, &uidhash_lock)) + free_user(up, flags); + else + local_irq_restore_nort(flags); +} + +struct user_struct *alloc_uid(kuid_t uid) +{ + struct hlist_head *hashent = uidhashentry(uid); + struct user_struct *up, *new; + + spin_lock_irq(&uidhash_lock); + up = uid_hash_find(uid, hashent); + spin_unlock_irq(&uidhash_lock); + + if (!up) { + new = kmem_cache_zalloc(uid_cachep, GFP_KERNEL); + if (!new) + goto out_unlock; + + new->uid = uid; + atomic_set(&new->__count, 1); + + /* + * Before adding this, check whether we raced + * on adding the same user already.. + */ + spin_lock_irq(&uidhash_lock); + up = uid_hash_find(uid, hashent); + if (up) { + key_put(new->uid_keyring); + key_put(new->session_keyring); + kmem_cache_free(uid_cachep, new); + } else { + uid_hash_insert(new, hashent); + up = new; + } + spin_unlock_irq(&uidhash_lock); + } + + return up; + +out_unlock: + return NULL; +} + +static int __init uid_cache_init(void) +{ + int n; + + uid_cachep = kmem_cache_create("uid_cache", sizeof(struct user_struct), + 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL); + + for(n = 0; n < UIDHASH_SZ; ++n) + INIT_HLIST_HEAD(uidhash_table + n); + + /* Insert the root user immediately (init already runs as root) */ + spin_lock_irq(&uidhash_lock); + uid_hash_insert(&root_user, uidhashentry(GLOBAL_ROOT_UID)); + spin_unlock_irq(&uidhash_lock); + + return 0; +} +subsys_initcall(uid_cache_init); diff --git a/kernel/kernel/user_namespace.c b/kernel/kernel/user_namespace.c new file mode 100644 index 000000000..4109f8320 --- /dev/null +++ b/kernel/kernel/user_namespace.c @@ -0,0 +1,1012 @@ +/* + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License as + * published by the Free Software Foundation, version 2 of the + * License. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +static struct kmem_cache *user_ns_cachep __read_mostly; +static DEFINE_MUTEX(userns_state_mutex); + +static bool new_idmap_permitted(const struct file *file, + struct user_namespace *ns, int cap_setid, + struct uid_gid_map *map); + +static void set_cred_user_ns(struct cred *cred, struct user_namespace *user_ns) +{ + /* Start with the same capabilities as init but useless for doing + * anything as the capabilities are bound to the new user namespace. + */ + cred->securebits = SECUREBITS_DEFAULT; + cred->cap_inheritable = CAP_EMPTY_SET; + cred->cap_permitted = CAP_FULL_SET; + cred->cap_effective = CAP_FULL_SET; + cred->cap_bset = CAP_FULL_SET; +#ifdef CONFIG_KEYS + key_put(cred->request_key_auth); + cred->request_key_auth = NULL; +#endif + /* tgcred will be cleared in our caller bc CLONE_THREAD won't be set */ + cred->user_ns = user_ns; +} + +/* + * Create a new user namespace, deriving the creator from the user in the + * passed credentials, and replacing that user with the new root user for the + * new namespace. + * + * This is called by copy_creds(), which will finish setting the target task's + * credentials. + */ +int create_user_ns(struct cred *new) +{ + struct user_namespace *ns, *parent_ns = new->user_ns; + kuid_t owner = new->euid; + kgid_t group = new->egid; + int ret; + + if (parent_ns->level > 32) + return -EUSERS; + + /* + * Verify that we can not violate the policy of which files + * may be accessed that is specified by the root directory, + * by verifing that the root directory is at the root of the + * mount namespace which allows all files to be accessed. + */ + if (current_chrooted()) + return -EPERM; + + /* The creator needs a mapping in the parent user namespace + * or else we won't be able to reasonably tell userspace who + * created a user_namespace. + */ + if (!kuid_has_mapping(parent_ns, owner) || + !kgid_has_mapping(parent_ns, group)) + return -EPERM; + + ns = kmem_cache_zalloc(user_ns_cachep, GFP_KERNEL); + if (!ns) + return -ENOMEM; + + ret = ns_alloc_inum(&ns->ns); + if (ret) { + kmem_cache_free(user_ns_cachep, ns); + return ret; + } + ns->ns.ops = &userns_operations; + + atomic_set(&ns->count, 1); + /* Leave the new->user_ns reference with the new user namespace. */ + ns->parent = parent_ns; + ns->level = parent_ns->level + 1; + ns->owner = owner; + ns->group = group; + + /* Inherit USERNS_SETGROUPS_ALLOWED from our parent */ + mutex_lock(&userns_state_mutex); + ns->flags = parent_ns->flags; + mutex_unlock(&userns_state_mutex); + + set_cred_user_ns(new, ns); + +#ifdef CONFIG_PERSISTENT_KEYRINGS + init_rwsem(&ns->persistent_keyring_register_sem); +#endif + return 0; +} + +int unshare_userns(unsigned long unshare_flags, struct cred **new_cred) +{ + struct cred *cred; + int err = -ENOMEM; + + if (!(unshare_flags & CLONE_NEWUSER)) + return 0; + + cred = prepare_creds(); + if (cred) { + err = create_user_ns(cred); + if (err) + put_cred(cred); + else + *new_cred = cred; + } + + return err; +} + +void free_user_ns(struct user_namespace *ns) +{ + struct user_namespace *parent; + + do { + parent = ns->parent; +#ifdef CONFIG_PERSISTENT_KEYRINGS + key_put(ns->persistent_keyring_register); +#endif + ns_free_inum(&ns->ns); + kmem_cache_free(user_ns_cachep, ns); + ns = parent; + } while (atomic_dec_and_test(&parent->count)); +} +EXPORT_SYMBOL(free_user_ns); + +static u32 map_id_range_down(struct uid_gid_map *map, u32 id, u32 count) +{ + unsigned idx, extents; + u32 first, last, id2; + + id2 = id + count - 1; + + /* Find the matching extent */ + extents = map->nr_extents; + smp_rmb(); + for (idx = 0; idx < extents; idx++) { + first = map->extent[idx].first; + last = first + map->extent[idx].count - 1; + if (id >= first && id <= last && + (id2 >= first && id2 <= last)) + break; + } + /* Map the id or note failure */ + if (idx < extents) + id = (id - first) + map->extent[idx].lower_first; + else + id = (u32) -1; + + return id; +} + +static u32 map_id_down(struct uid_gid_map *map, u32 id) +{ + unsigned idx, extents; + u32 first, last; + + /* Find the matching extent */ + extents = map->nr_extents; + smp_rmb(); + for (idx = 0; idx < extents; idx++) { + first = map->extent[idx].first; + last = first + map->extent[idx].count - 1; + if (id >= first && id <= last) + break; + } + /* Map the id or note failure */ + if (idx < extents) + id = (id - first) + map->extent[idx].lower_first; + else + id = (u32) -1; + + return id; +} + +static u32 map_id_up(struct uid_gid_map *map, u32 id) +{ + unsigned idx, extents; + u32 first, last; + + /* Find the matching extent */ + extents = map->nr_extents; + smp_rmb(); + for (idx = 0; idx < extents; idx++) { + first = map->extent[idx].lower_first; + last = first + map->extent[idx].count - 1; + if (id >= first && id <= last) + break; + } + /* Map the id or note failure */ + if (idx < extents) + id = (id - first) + map->extent[idx].first; + else + id = (u32) -1; + + return id; +} + +/** + * make_kuid - Map a user-namespace uid pair into a kuid. + * @ns: User namespace that the uid is in + * @uid: User identifier + * + * Maps a user-namespace uid pair into a kernel internal kuid, + * and returns that kuid. + * + * When there is no mapping defined for the user-namespace uid + * pair INVALID_UID is returned. Callers are expected to test + * for and handle INVALID_UID being returned. INVALID_UID + * may be tested for using uid_valid(). + */ +kuid_t make_kuid(struct user_namespace *ns, uid_t uid) +{ + /* Map the uid to a global kernel uid */ + return KUIDT_INIT(map_id_down(&ns->uid_map, uid)); +} +EXPORT_SYMBOL(make_kuid); + +/** + * from_kuid - Create a uid from a kuid user-namespace pair. + * @targ: The user namespace we want a uid in. + * @kuid: The kernel internal uid to start with. + * + * Map @kuid into the user-namespace specified by @targ and + * return the resulting uid. + * + * There is always a mapping into the initial user_namespace. + * + * If @kuid has no mapping in @targ (uid_t)-1 is returned. + */ +uid_t from_kuid(struct user_namespace *targ, kuid_t kuid) +{ + /* Map the uid from a global kernel uid */ + return map_id_up(&targ->uid_map, __kuid_val(kuid)); +} +EXPORT_SYMBOL(from_kuid); + +/** + * from_kuid_munged - Create a uid from a kuid user-namespace pair. + * @targ: The user namespace we want a uid in. + * @kuid: The kernel internal uid to start with. + * + * Map @kuid into the user-namespace specified by @targ and + * return the resulting uid. + * + * There is always a mapping into the initial user_namespace. + * + * Unlike from_kuid from_kuid_munged never fails and always + * returns a valid uid. This makes from_kuid_munged appropriate + * for use in syscalls like stat and getuid where failing the + * system call and failing to provide a valid uid are not an + * options. + * + * If @kuid has no mapping in @targ overflowuid is returned. + */ +uid_t from_kuid_munged(struct user_namespace *targ, kuid_t kuid) +{ + uid_t uid; + uid = from_kuid(targ, kuid); + + if (uid == (uid_t) -1) + uid = overflowuid; + return uid; +} +EXPORT_SYMBOL(from_kuid_munged); + +/** + * make_kgid - Map a user-namespace gid pair into a kgid. + * @ns: User namespace that the gid is in + * @gid: group identifier + * + * Maps a user-namespace gid pair into a kernel internal kgid, + * and returns that kgid. + * + * When there is no mapping defined for the user-namespace gid + * pair INVALID_GID is returned. Callers are expected to test + * for and handle INVALID_GID being returned. INVALID_GID may be + * tested for using gid_valid(). + */ +kgid_t make_kgid(struct user_namespace *ns, gid_t gid) +{ + /* Map the gid to a global kernel gid */ + return KGIDT_INIT(map_id_down(&ns->gid_map, gid)); +} +EXPORT_SYMBOL(make_kgid); + +/** + * from_kgid - Create a gid from a kgid user-namespace pair. + * @targ: The user namespace we want a gid in. + * @kgid: The kernel internal gid to start with. + * + * Map @kgid into the user-namespace specified by @targ and + * return the resulting gid. + * + * There is always a mapping into the initial user_namespace. + * + * If @kgid has no mapping in @targ (gid_t)-1 is returned. + */ +gid_t from_kgid(struct user_namespace *targ, kgid_t kgid) +{ + /* Map the gid from a global kernel gid */ + return map_id_up(&targ->gid_map, __kgid_val(kgid)); +} +EXPORT_SYMBOL(from_kgid); + +/** + * from_kgid_munged - Create a gid from a kgid user-namespace pair. + * @targ: The user namespace we want a gid in. + * @kgid: The kernel internal gid to start with. + * + * Map @kgid into the user-namespace specified by @targ and + * return the resulting gid. + * + * There is always a mapping into the initial user_namespace. + * + * Unlike from_kgid from_kgid_munged never fails and always + * returns a valid gid. This makes from_kgid_munged appropriate + * for use in syscalls like stat and getgid where failing the + * system call and failing to provide a valid gid are not options. + * + * If @kgid has no mapping in @targ overflowgid is returned. + */ +gid_t from_kgid_munged(struct user_namespace *targ, kgid_t kgid) +{ + gid_t gid; + gid = from_kgid(targ, kgid); + + if (gid == (gid_t) -1) + gid = overflowgid; + return gid; +} +EXPORT_SYMBOL(from_kgid_munged); + +/** + * make_kprojid - Map a user-namespace projid pair into a kprojid. + * @ns: User namespace that the projid is in + * @projid: Project identifier + * + * Maps a user-namespace uid pair into a kernel internal kuid, + * and returns that kuid. + * + * When there is no mapping defined for the user-namespace projid + * pair INVALID_PROJID is returned. Callers are expected to test + * for and handle handle INVALID_PROJID being returned. INVALID_PROJID + * may be tested for using projid_valid(). + */ +kprojid_t make_kprojid(struct user_namespace *ns, projid_t projid) +{ + /* Map the uid to a global kernel uid */ + return KPROJIDT_INIT(map_id_down(&ns->projid_map, projid)); +} +EXPORT_SYMBOL(make_kprojid); + +/** + * from_kprojid - Create a projid from a kprojid user-namespace pair. + * @targ: The user namespace we want a projid in. + * @kprojid: The kernel internal project identifier to start with. + * + * Map @kprojid into the user-namespace specified by @targ and + * return the resulting projid. + * + * There is always a mapping into the initial user_namespace. + * + * If @kprojid has no mapping in @targ (projid_t)-1 is returned. + */ +projid_t from_kprojid(struct user_namespace *targ, kprojid_t kprojid) +{ + /* Map the uid from a global kernel uid */ + return map_id_up(&targ->projid_map, __kprojid_val(kprojid)); +} +EXPORT_SYMBOL(from_kprojid); + +/** + * from_kprojid_munged - Create a projiid from a kprojid user-namespace pair. + * @targ: The user namespace we want a projid in. + * @kprojid: The kernel internal projid to start with. + * + * Map @kprojid into the user-namespace specified by @targ and + * return the resulting projid. + * + * There is always a mapping into the initial user_namespace. + * + * Unlike from_kprojid from_kprojid_munged never fails and always + * returns a valid projid. This makes from_kprojid_munged + * appropriate for use in syscalls like stat and where + * failing the system call and failing to provide a valid projid are + * not an options. + * + * If @kprojid has no mapping in @targ OVERFLOW_PROJID is returned. + */ +projid_t from_kprojid_munged(struct user_namespace *targ, kprojid_t kprojid) +{ + projid_t projid; + projid = from_kprojid(targ, kprojid); + + if (projid == (projid_t) -1) + projid = OVERFLOW_PROJID; + return projid; +} +EXPORT_SYMBOL(from_kprojid_munged); + + +static int uid_m_show(struct seq_file *seq, void *v) +{ + struct user_namespace *ns = seq->private; + struct uid_gid_extent *extent = v; + struct user_namespace *lower_ns; + uid_t lower; + + lower_ns = seq_user_ns(seq); + if ((lower_ns == ns) && lower_ns->parent) + lower_ns = lower_ns->parent; + + lower = from_kuid(lower_ns, KUIDT_INIT(extent->lower_first)); + + seq_printf(seq, "%10u %10u %10u\n", + extent->first, + lower, + extent->count); + + return 0; +} + +static int gid_m_show(struct seq_file *seq, void *v) +{ + struct user_namespace *ns = seq->private; + struct uid_gid_extent *extent = v; + struct user_namespace *lower_ns; + gid_t lower; + + lower_ns = seq_user_ns(seq); + if ((lower_ns == ns) && lower_ns->parent) + lower_ns = lower_ns->parent; + + lower = from_kgid(lower_ns, KGIDT_INIT(extent->lower_first)); + + seq_printf(seq, "%10u %10u %10u\n", + extent->first, + lower, + extent->count); + + return 0; +} + +static int projid_m_show(struct seq_file *seq, void *v) +{ + struct user_namespace *ns = seq->private; + struct uid_gid_extent *extent = v; + struct user_namespace *lower_ns; + projid_t lower; + + lower_ns = seq_user_ns(seq); + if ((lower_ns == ns) && lower_ns->parent) + lower_ns = lower_ns->parent; + + lower = from_kprojid(lower_ns, KPROJIDT_INIT(extent->lower_first)); + + seq_printf(seq, "%10u %10u %10u\n", + extent->first, + lower, + extent->count); + + return 0; +} + +static void *m_start(struct seq_file *seq, loff_t *ppos, + struct uid_gid_map *map) +{ + struct uid_gid_extent *extent = NULL; + loff_t pos = *ppos; + + if (pos < map->nr_extents) + extent = &map->extent[pos]; + + return extent; +} + +static void *uid_m_start(struct seq_file *seq, loff_t *ppos) +{ + struct user_namespace *ns = seq->private; + + return m_start(seq, ppos, &ns->uid_map); +} + +static void *gid_m_start(struct seq_file *seq, loff_t *ppos) +{ + struct user_namespace *ns = seq->private; + + return m_start(seq, ppos, &ns->gid_map); +} + +static void *projid_m_start(struct seq_file *seq, loff_t *ppos) +{ + struct user_namespace *ns = seq->private; + + return m_start(seq, ppos, &ns->projid_map); +} + +static void *m_next(struct seq_file *seq, void *v, loff_t *pos) +{ + (*pos)++; + return seq->op->start(seq, pos); +} + +static void m_stop(struct seq_file *seq, void *v) +{ + return; +} + +const struct seq_operations proc_uid_seq_operations = { + .start = uid_m_start, + .stop = m_stop, + .next = m_next, + .show = uid_m_show, +}; + +const struct seq_operations proc_gid_seq_operations = { + .start = gid_m_start, + .stop = m_stop, + .next = m_next, + .show = gid_m_show, +}; + +const struct seq_operations proc_projid_seq_operations = { + .start = projid_m_start, + .stop = m_stop, + .next = m_next, + .show = projid_m_show, +}; + +static bool mappings_overlap(struct uid_gid_map *new_map, + struct uid_gid_extent *extent) +{ + u32 upper_first, lower_first, upper_last, lower_last; + unsigned idx; + + upper_first = extent->first; + lower_first = extent->lower_first; + upper_last = upper_first + extent->count - 1; + lower_last = lower_first + extent->count - 1; + + for (idx = 0; idx < new_map->nr_extents; idx++) { + u32 prev_upper_first, prev_lower_first; + u32 prev_upper_last, prev_lower_last; + struct uid_gid_extent *prev; + + prev = &new_map->extent[idx]; + + prev_upper_first = prev->first; + prev_lower_first = prev->lower_first; + prev_upper_last = prev_upper_first + prev->count - 1; + prev_lower_last = prev_lower_first + prev->count - 1; + + /* Does the upper range intersect a previous extent? */ + if ((prev_upper_first <= upper_last) && + (prev_upper_last >= upper_first)) + return true; + + /* Does the lower range intersect a previous extent? */ + if ((prev_lower_first <= lower_last) && + (prev_lower_last >= lower_first)) + return true; + } + return false; +} + +static ssize_t map_write(struct file *file, const char __user *buf, + size_t count, loff_t *ppos, + int cap_setid, + struct uid_gid_map *map, + struct uid_gid_map *parent_map) +{ + struct seq_file *seq = file->private_data; + struct user_namespace *ns = seq->private; + struct uid_gid_map new_map; + unsigned idx; + struct uid_gid_extent *extent = NULL; + unsigned long page = 0; + char *kbuf, *pos, *next_line; + ssize_t ret = -EINVAL; + + /* + * The userns_state_mutex serializes all writes to any given map. + * + * Any map is only ever written once. + * + * An id map fits within 1 cache line on most architectures. + * + * On read nothing needs to be done unless you are on an + * architecture with a crazy cache coherency model like alpha. + * + * There is a one time data dependency between reading the + * count of the extents and the values of the extents. The + * desired behavior is to see the values of the extents that + * were written before the count of the extents. + * + * To achieve this smp_wmb() is used on guarantee the write + * order and smp_rmb() is guaranteed that we don't have crazy + * architectures returning stale data. + */ + mutex_lock(&userns_state_mutex); + + ret = -EPERM; + /* Only allow one successful write to the map */ + if (map->nr_extents != 0) + goto out; + + /* + * Adjusting namespace settings requires capabilities on the target. + */ + if (cap_valid(cap_setid) && !file_ns_capable(file, ns, CAP_SYS_ADMIN)) + goto out; + + /* Get a buffer */ + ret = -ENOMEM; + page = __get_free_page(GFP_TEMPORARY); + kbuf = (char *) page; + if (!page) + goto out; + + /* Only allow < page size writes at the beginning of the file */ + ret = -EINVAL; + if ((*ppos != 0) || (count >= PAGE_SIZE)) + goto out; + + /* Slurp in the user data */ + ret = -EFAULT; + if (copy_from_user(kbuf, buf, count)) + goto out; + kbuf[count] = '\0'; + + /* Parse the user data */ + ret = -EINVAL; + pos = kbuf; + new_map.nr_extents = 0; + for (; pos; pos = next_line) { + extent = &new_map.extent[new_map.nr_extents]; + + /* Find the end of line and ensure I don't look past it */ + next_line = strchr(pos, '\n'); + if (next_line) { + *next_line = '\0'; + next_line++; + if (*next_line == '\0') + next_line = NULL; + } + + pos = skip_spaces(pos); + extent->first = simple_strtoul(pos, &pos, 10); + if (!isspace(*pos)) + goto out; + + pos = skip_spaces(pos); + extent->lower_first = simple_strtoul(pos, &pos, 10); + if (!isspace(*pos)) + goto out; + + pos = skip_spaces(pos); + extent->count = simple_strtoul(pos, &pos, 10); + if (*pos && !isspace(*pos)) + goto out; + + /* Verify there is not trailing junk on the line */ + pos = skip_spaces(pos); + if (*pos != '\0') + goto out; + + /* Verify we have been given valid starting values */ + if ((extent->first == (u32) -1) || + (extent->lower_first == (u32) -1)) + goto out; + + /* Verify count is not zero and does not cause the + * extent to wrap + */ + if ((extent->first + extent->count) <= extent->first) + goto out; + if ((extent->lower_first + extent->count) <= + extent->lower_first) + goto out; + + /* Do the ranges in extent overlap any previous extents? */ + if (mappings_overlap(&new_map, extent)) + goto out; + + new_map.nr_extents++; + + /* Fail if the file contains too many extents */ + if ((new_map.nr_extents == UID_GID_MAP_MAX_EXTENTS) && + (next_line != NULL)) + goto out; + } + /* Be very certaint the new map actually exists */ + if (new_map.nr_extents == 0) + goto out; + + ret = -EPERM; + /* Validate the user is allowed to use user id's mapped to. */ + if (!new_idmap_permitted(file, ns, cap_setid, &new_map)) + goto out; + + /* Map the lower ids from the parent user namespace to the + * kernel global id space. + */ + for (idx = 0; idx < new_map.nr_extents; idx++) { + u32 lower_first; + extent = &new_map.extent[idx]; + + lower_first = map_id_range_down(parent_map, + extent->lower_first, + extent->count); + + /* Fail if we can not map the specified extent to + * the kernel global id space. + */ + if (lower_first == (u32) -1) + goto out; + + extent->lower_first = lower_first; + } + + /* Install the map */ + memcpy(map->extent, new_map.extent, + new_map.nr_extents*sizeof(new_map.extent[0])); + smp_wmb(); + map->nr_extents = new_map.nr_extents; + + *ppos = count; + ret = count; +out: + mutex_unlock(&userns_state_mutex); + if (page) + free_page(page); + return ret; +} + +ssize_t proc_uid_map_write(struct file *file, const char __user *buf, + size_t size, loff_t *ppos) +{ + struct seq_file *seq = file->private_data; + struct user_namespace *ns = seq->private; + struct user_namespace *seq_ns = seq_user_ns(seq); + + if (!ns->parent) + return -EPERM; + + if ((seq_ns != ns) && (seq_ns != ns->parent)) + return -EPERM; + + return map_write(file, buf, size, ppos, CAP_SETUID, + &ns->uid_map, &ns->parent->uid_map); +} + +ssize_t proc_gid_map_write(struct file *file, const char __user *buf, + size_t size, loff_t *ppos) +{ + struct seq_file *seq = file->private_data; + struct user_namespace *ns = seq->private; + struct user_namespace *seq_ns = seq_user_ns(seq); + + if (!ns->parent) + return -EPERM; + + if ((seq_ns != ns) && (seq_ns != ns->parent)) + return -EPERM; + + return map_write(file, buf, size, ppos, CAP_SETGID, + &ns->gid_map, &ns->parent->gid_map); +} + +ssize_t proc_projid_map_write(struct file *file, const char __user *buf, + size_t size, loff_t *ppos) +{ + struct seq_file *seq = file->private_data; + struct user_namespace *ns = seq->private; + struct user_namespace *seq_ns = seq_user_ns(seq); + + if (!ns->parent) + return -EPERM; + + if ((seq_ns != ns) && (seq_ns != ns->parent)) + return -EPERM; + + /* Anyone can set any valid project id no capability needed */ + return map_write(file, buf, size, ppos, -1, + &ns->projid_map, &ns->parent->projid_map); +} + +static bool new_idmap_permitted(const struct file *file, + struct user_namespace *ns, int cap_setid, + struct uid_gid_map *new_map) +{ + const struct cred *cred = file->f_cred; + /* Don't allow mappings that would allow anything that wouldn't + * be allowed without the establishment of unprivileged mappings. + */ + if ((new_map->nr_extents == 1) && (new_map->extent[0].count == 1) && + uid_eq(ns->owner, cred->euid)) { + u32 id = new_map->extent[0].lower_first; + if (cap_setid == CAP_SETUID) { + kuid_t uid = make_kuid(ns->parent, id); + if (uid_eq(uid, cred->euid)) + return true; + } else if (cap_setid == CAP_SETGID) { + kgid_t gid = make_kgid(ns->parent, id); + if (!(ns->flags & USERNS_SETGROUPS_ALLOWED) && + gid_eq(gid, cred->egid)) + return true; + } + } + + /* Allow anyone to set a mapping that doesn't require privilege */ + if (!cap_valid(cap_setid)) + return true; + + /* Allow the specified ids if we have the appropriate capability + * (CAP_SETUID or CAP_SETGID) over the parent user namespace. + * And the opener of the id file also had the approprpiate capability. + */ + if (ns_capable(ns->parent, cap_setid) && + file_ns_capable(file, ns->parent, cap_setid)) + return true; + + return false; +} + +int proc_setgroups_show(struct seq_file *seq, void *v) +{ + struct user_namespace *ns = seq->private; + unsigned long userns_flags = ACCESS_ONCE(ns->flags); + + seq_printf(seq, "%s\n", + (userns_flags & USERNS_SETGROUPS_ALLOWED) ? + "allow" : "deny"); + return 0; +} + +ssize_t proc_setgroups_write(struct file *file, const char __user *buf, + size_t count, loff_t *ppos) +{ + struct seq_file *seq = file->private_data; + struct user_namespace *ns = seq->private; + char kbuf[8], *pos; + bool setgroups_allowed; + ssize_t ret; + + /* Only allow a very narrow range of strings to be written */ + ret = -EINVAL; + if ((*ppos != 0) || (count >= sizeof(kbuf))) + goto out; + + /* What was written? */ + ret = -EFAULT; + if (copy_from_user(kbuf, buf, count)) + goto out; + kbuf[count] = '\0'; + pos = kbuf; + + /* What is being requested? */ + ret = -EINVAL; + if (strncmp(pos, "allow", 5) == 0) { + pos += 5; + setgroups_allowed = true; + } + else if (strncmp(pos, "deny", 4) == 0) { + pos += 4; + setgroups_allowed = false; + } + else + goto out; + + /* Verify there is not trailing junk on the line */ + pos = skip_spaces(pos); + if (*pos != '\0') + goto out; + + ret = -EPERM; + mutex_lock(&userns_state_mutex); + if (setgroups_allowed) { + /* Enabling setgroups after setgroups has been disabled + * is not allowed. + */ + if (!(ns->flags & USERNS_SETGROUPS_ALLOWED)) + goto out_unlock; + } else { + /* Permanently disabling setgroups after setgroups has + * been enabled by writing the gid_map is not allowed. + */ + if (ns->gid_map.nr_extents != 0) + goto out_unlock; + ns->flags &= ~USERNS_SETGROUPS_ALLOWED; + } + mutex_unlock(&userns_state_mutex); + + /* Report a successful write */ + *ppos = count; + ret = count; +out: + return ret; +out_unlock: + mutex_unlock(&userns_state_mutex); + goto out; +} + +bool userns_may_setgroups(const struct user_namespace *ns) +{ + bool allowed; + + mutex_lock(&userns_state_mutex); + /* It is not safe to use setgroups until a gid mapping in + * the user namespace has been established. + */ + allowed = ns->gid_map.nr_extents != 0; + /* Is setgroups allowed? */ + allowed = allowed && (ns->flags & USERNS_SETGROUPS_ALLOWED); + mutex_unlock(&userns_state_mutex); + + return allowed; +} + +static inline struct user_namespace *to_user_ns(struct ns_common *ns) +{ + return container_of(ns, struct user_namespace, ns); +} + +static struct ns_common *userns_get(struct task_struct *task) +{ + struct user_namespace *user_ns; + + rcu_read_lock(); + user_ns = get_user_ns(__task_cred(task)->user_ns); + rcu_read_unlock(); + + return user_ns ? &user_ns->ns : NULL; +} + +static void userns_put(struct ns_common *ns) +{ + put_user_ns(to_user_ns(ns)); +} + +static int userns_install(struct nsproxy *nsproxy, struct ns_common *ns) +{ + struct user_namespace *user_ns = to_user_ns(ns); + struct cred *cred; + + /* Don't allow gaining capabilities by reentering + * the same user namespace. + */ + if (user_ns == current_user_ns()) + return -EINVAL; + + /* Threaded processes may not enter a different user namespace */ + if (atomic_read(¤t->mm->mm_users) > 1) + return -EINVAL; + + if (current->fs->users != 1) + return -EINVAL; + + if (!ns_capable(user_ns, CAP_SYS_ADMIN)) + return -EPERM; + + cred = prepare_creds(); + if (!cred) + return -ENOMEM; + + put_user_ns(cred->user_ns); + set_cred_user_ns(cred, get_user_ns(user_ns)); + + return commit_creds(cred); +} + +const struct proc_ns_operations userns_operations = { + .name = "user", + .type = CLONE_NEWUSER, + .get = userns_get, + .put = userns_put, + .install = userns_install, +}; + +static __init int user_namespaces_init(void) +{ + user_ns_cachep = KMEM_CACHE(user_namespace, SLAB_PANIC); + return 0; +} +subsys_initcall(user_namespaces_init); diff --git a/kernel/kernel/utsname.c b/kernel/kernel/utsname.c new file mode 100644 index 000000000..831ea7108 --- /dev/null +++ b/kernel/kernel/utsname.c @@ -0,0 +1,139 @@ +/* + * Copyright (C) 2004 IBM Corporation + * + * Author: Serge Hallyn + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License as + * published by the Free Software Foundation, version 2 of the + * License. + */ + +#include +#include +#include +#include +#include +#include +#include + +static struct uts_namespace *create_uts_ns(void) +{ + struct uts_namespace *uts_ns; + + uts_ns = kmalloc(sizeof(struct uts_namespace), GFP_KERNEL); + if (uts_ns) + kref_init(&uts_ns->kref); + return uts_ns; +} + +/* + * Clone a new ns copying an original utsname, setting refcount to 1 + * @old_ns: namespace to clone + * Return ERR_PTR(-ENOMEM) on error (failure to kmalloc), new ns otherwise + */ +static struct uts_namespace *clone_uts_ns(struct user_namespace *user_ns, + struct uts_namespace *old_ns) +{ + struct uts_namespace *ns; + int err; + + ns = create_uts_ns(); + if (!ns) + return ERR_PTR(-ENOMEM); + + err = ns_alloc_inum(&ns->ns); + if (err) { + kfree(ns); + return ERR_PTR(err); + } + + ns->ns.ops = &utsns_operations; + + down_read(&uts_sem); + memcpy(&ns->name, &old_ns->name, sizeof(ns->name)); + ns->user_ns = get_user_ns(user_ns); + up_read(&uts_sem); + return ns; +} + +/* + * Copy task tsk's utsname namespace, or clone it if flags + * specifies CLONE_NEWUTS. In latter case, changes to the + * utsname of this process won't be seen by parent, and vice + * versa. + */ +struct uts_namespace *copy_utsname(unsigned long flags, + struct user_namespace *user_ns, struct uts_namespace *old_ns) +{ + struct uts_namespace *new_ns; + + BUG_ON(!old_ns); + get_uts_ns(old_ns); + + if (!(flags & CLONE_NEWUTS)) + return old_ns; + + new_ns = clone_uts_ns(user_ns, old_ns); + + put_uts_ns(old_ns); + return new_ns; +} + +void free_uts_ns(struct kref *kref) +{ + struct uts_namespace *ns; + + ns = container_of(kref, struct uts_namespace, kref); + put_user_ns(ns->user_ns); + ns_free_inum(&ns->ns); + kfree(ns); +} + +static inline struct uts_namespace *to_uts_ns(struct ns_common *ns) +{ + return container_of(ns, struct uts_namespace, ns); +} + +static struct ns_common *utsns_get(struct task_struct *task) +{ + struct uts_namespace *ns = NULL; + struct nsproxy *nsproxy; + + task_lock(task); + nsproxy = task->nsproxy; + if (nsproxy) { + ns = nsproxy->uts_ns; + get_uts_ns(ns); + } + task_unlock(task); + + return ns ? &ns->ns : NULL; +} + +static void utsns_put(struct ns_common *ns) +{ + put_uts_ns(to_uts_ns(ns)); +} + +static int utsns_install(struct nsproxy *nsproxy, struct ns_common *new) +{ + struct uts_namespace *ns = to_uts_ns(new); + + if (!ns_capable(ns->user_ns, CAP_SYS_ADMIN) || + !ns_capable(current_user_ns(), CAP_SYS_ADMIN)) + return -EPERM; + + get_uts_ns(ns); + put_uts_ns(nsproxy->uts_ns); + nsproxy->uts_ns = ns; + return 0; +} + +const struct proc_ns_operations utsns_operations = { + .name = "uts", + .type = CLONE_NEWUTS, + .get = utsns_get, + .put = utsns_put, + .install = utsns_install, +}; diff --git a/kernel/kernel/utsname_sysctl.c b/kernel/kernel/utsname_sysctl.c new file mode 100644 index 000000000..c8eac4326 --- /dev/null +++ b/kernel/kernel/utsname_sysctl.c @@ -0,0 +1,138 @@ +/* + * Copyright (C) 2007 + * + * Author: Eric Biederman + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License as + * published by the Free Software Foundation, version 2 of the + * License. + */ + +#include +#include +#include +#include +#include + +#ifdef CONFIG_PROC_SYSCTL + +static void *get_uts(struct ctl_table *table, int write) +{ + char *which = table->data; + struct uts_namespace *uts_ns; + + uts_ns = current->nsproxy->uts_ns; + which = (which - (char *)&init_uts_ns) + (char *)uts_ns; + + if (!write) + down_read(&uts_sem); + else + down_write(&uts_sem); + return which; +} + +static void put_uts(struct ctl_table *table, int write, void *which) +{ + if (!write) + up_read(&uts_sem); + else + up_write(&uts_sem); +} + +/* + * Special case of dostring for the UTS structure. This has locks + * to observe. Should this be in kernel/sys.c ???? + */ +static int proc_do_uts_string(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + struct ctl_table uts_table; + int r; + memcpy(&uts_table, table, sizeof(uts_table)); + uts_table.data = get_uts(table, write); + r = proc_dostring(&uts_table, write, buffer, lenp, ppos); + put_uts(table, write, uts_table.data); + + if (write) + proc_sys_poll_notify(table->poll); + + return r; +} +#else +#define proc_do_uts_string NULL +#endif + +static DEFINE_CTL_TABLE_POLL(hostname_poll); +static DEFINE_CTL_TABLE_POLL(domainname_poll); + +static struct ctl_table uts_kern_table[] = { + { + .procname = "ostype", + .data = init_uts_ns.name.sysname, + .maxlen = sizeof(init_uts_ns.name.sysname), + .mode = 0444, + .proc_handler = proc_do_uts_string, + }, + { + .procname = "osrelease", + .data = init_uts_ns.name.release, + .maxlen = sizeof(init_uts_ns.name.release), + .mode = 0444, + .proc_handler = proc_do_uts_string, + }, + { + .procname = "version", + .data = init_uts_ns.name.version, + .maxlen = sizeof(init_uts_ns.name.version), + .mode = 0444, + .proc_handler = proc_do_uts_string, + }, + { + .procname = "hostname", + .data = init_uts_ns.name.nodename, + .maxlen = sizeof(init_uts_ns.name.nodename), + .mode = 0644, + .proc_handler = proc_do_uts_string, + .poll = &hostname_poll, + }, + { + .procname = "domainname", + .data = init_uts_ns.name.domainname, + .maxlen = sizeof(init_uts_ns.name.domainname), + .mode = 0644, + .proc_handler = proc_do_uts_string, + .poll = &domainname_poll, + }, + {} +}; + +static struct ctl_table uts_root_table[] = { + { + .procname = "kernel", + .mode = 0555, + .child = uts_kern_table, + }, + {} +}; + +#ifdef CONFIG_PROC_SYSCTL +/* + * Notify userspace about a change in a certain entry of uts_kern_table, + * identified by the parameter proc. + */ +void uts_proc_notify(enum uts_proc proc) +{ + struct ctl_table *table = &uts_kern_table[proc]; + + proc_sys_poll_notify(table->poll); +} +#endif + +static int __init utsname_sysctl_init(void) +{ + register_sysctl_table(uts_root_table); + return 0; +} + +device_initcall(utsname_sysctl_init); diff --git a/kernel/kernel/watchdog.c b/kernel/kernel/watchdog.c new file mode 100644 index 000000000..3b8e827ee --- /dev/null +++ b/kernel/kernel/watchdog.c @@ -0,0 +1,901 @@ +/* + * Detect hard and soft lockups on a system + * + * started by Don Zickus, Copyright (C) 2010 Red Hat, Inc. + * + * Note: Most of this code is borrowed heavily from the original softlockup + * detector, so thanks to Ingo for the initial implementation. + * Some chunks also taken from the old x86-specific nmi watchdog code, thanks + * to those contributors as well. + */ + +#define pr_fmt(fmt) "NMI watchdog: " fmt + +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include + +/* + * The run state of the lockup detectors is controlled by the content of the + * 'watchdog_enabled' variable. Each lockup detector has its dedicated bit - + * bit 0 for the hard lockup detector and bit 1 for the soft lockup detector. + * + * 'watchdog_user_enabled', 'nmi_watchdog_enabled' and 'soft_watchdog_enabled' + * are variables that are only used as an 'interface' between the parameters + * in /proc/sys/kernel and the internal state bits in 'watchdog_enabled'. The + * 'watchdog_thresh' variable is handled differently because its value is not + * boolean, and the lockup detectors are 'suspended' while 'watchdog_thresh' + * is equal zero. + */ +#define NMI_WATCHDOG_ENABLED_BIT 0 +#define SOFT_WATCHDOG_ENABLED_BIT 1 +#define NMI_WATCHDOG_ENABLED (1 << NMI_WATCHDOG_ENABLED_BIT) +#define SOFT_WATCHDOG_ENABLED (1 << SOFT_WATCHDOG_ENABLED_BIT) + +static DEFINE_MUTEX(watchdog_proc_mutex); + +#ifdef CONFIG_HARDLOCKUP_DETECTOR +static unsigned long __read_mostly watchdog_enabled = SOFT_WATCHDOG_ENABLED|NMI_WATCHDOG_ENABLED; +#else +static unsigned long __read_mostly watchdog_enabled = SOFT_WATCHDOG_ENABLED; +#endif +int __read_mostly nmi_watchdog_enabled; +int __read_mostly soft_watchdog_enabled; +int __read_mostly watchdog_user_enabled; +int __read_mostly watchdog_thresh = 10; + +#ifdef CONFIG_SMP +int __read_mostly sysctl_softlockup_all_cpu_backtrace; +#else +#define sysctl_softlockup_all_cpu_backtrace 0 +#endif + +static int __read_mostly watchdog_running; +static u64 __read_mostly sample_period; + +static DEFINE_PER_CPU(unsigned long, watchdog_touch_ts); +static DEFINE_PER_CPU(struct task_struct *, softlockup_watchdog); +static DEFINE_PER_CPU(struct hrtimer, watchdog_hrtimer); +static DEFINE_PER_CPU(bool, softlockup_touch_sync); +static DEFINE_PER_CPU(bool, soft_watchdog_warn); +static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts); +static DEFINE_PER_CPU(unsigned long, soft_lockup_hrtimer_cnt); +static DEFINE_PER_CPU(struct task_struct *, softlockup_task_ptr_saved); +#ifdef CONFIG_HARDLOCKUP_DETECTOR +static DEFINE_PER_CPU(bool, hard_watchdog_warn); +static DEFINE_PER_CPU(bool, watchdog_nmi_touch); +static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts_saved); +static DEFINE_PER_CPU(struct perf_event *, watchdog_ev); +#endif +static unsigned long soft_lockup_nmi_warn; + +/* boot commands */ +/* + * Should we panic when a soft-lockup or hard-lockup occurs: + */ +#ifdef CONFIG_HARDLOCKUP_DETECTOR +static int hardlockup_panic = + CONFIG_BOOTPARAM_HARDLOCKUP_PANIC_VALUE; +/* + * We may not want to enable hard lockup detection by default in all cases, + * for example when running the kernel as a guest on a hypervisor. In these + * cases this function can be called to disable hard lockup detection. This + * function should only be executed once by the boot processor before the + * kernel command line parameters are parsed, because otherwise it is not + * possible to override this in hardlockup_panic_setup(). + */ +void hardlockup_detector_disable(void) +{ + watchdog_enabled &= ~NMI_WATCHDOG_ENABLED; +} + +static int __init hardlockup_panic_setup(char *str) +{ + if (!strncmp(str, "panic", 5)) + hardlockup_panic = 1; + else if (!strncmp(str, "nopanic", 7)) + hardlockup_panic = 0; + else if (!strncmp(str, "0", 1)) + watchdog_enabled &= ~NMI_WATCHDOG_ENABLED; + else if (!strncmp(str, "1", 1)) + watchdog_enabled |= NMI_WATCHDOG_ENABLED; + return 1; +} +__setup("nmi_watchdog=", hardlockup_panic_setup); +#endif + +unsigned int __read_mostly softlockup_panic = + CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE; + +static int __init softlockup_panic_setup(char *str) +{ + softlockup_panic = simple_strtoul(str, NULL, 0); + + return 1; +} +__setup("softlockup_panic=", softlockup_panic_setup); + +static int __init nowatchdog_setup(char *str) +{ + watchdog_enabled = 0; + return 1; +} +__setup("nowatchdog", nowatchdog_setup); + +static int __init nosoftlockup_setup(char *str) +{ + watchdog_enabled &= ~SOFT_WATCHDOG_ENABLED; + return 1; +} +__setup("nosoftlockup", nosoftlockup_setup); + +#ifdef CONFIG_SMP +static int __init softlockup_all_cpu_backtrace_setup(char *str) +{ + sysctl_softlockup_all_cpu_backtrace = + !!simple_strtol(str, NULL, 0); + return 1; +} +__setup("softlockup_all_cpu_backtrace=", softlockup_all_cpu_backtrace_setup); +#endif + +/* + * Hard-lockup warnings should be triggered after just a few seconds. Soft- + * lockups can have false positives under extreme conditions. So we generally + * want a higher threshold for soft lockups than for hard lockups. So we couple + * the thresholds with a factor: we make the soft threshold twice the amount of + * time the hard threshold is. + */ +static int get_softlockup_thresh(void) +{ + return watchdog_thresh * 2; +} + +/* + * Returns seconds, approximately. We don't need nanosecond + * resolution, and we don't need to waste time with a big divide when + * 2^30ns == 1.074s. + */ +static unsigned long get_timestamp(void) +{ + return running_clock() >> 30LL; /* 2^30 ~= 10^9 */ +} + +static void set_sample_period(void) +{ + /* + * convert watchdog_thresh from seconds to ns + * the divide by 5 is to give hrtimer several chances (two + * or three with the current relation between the soft + * and hard thresholds) to increment before the + * hardlockup detector generates a warning + */ + sample_period = get_softlockup_thresh() * ((u64)NSEC_PER_SEC / 5); +} + +/* Commands for resetting the watchdog */ +static void __touch_watchdog(void) +{ + __this_cpu_write(watchdog_touch_ts, get_timestamp()); +} + +void touch_softlockup_watchdog(void) +{ + /* + * Preemption can be enabled. It doesn't matter which CPU's timestamp + * gets zeroed here, so use the raw_ operation. + */ + raw_cpu_write(watchdog_touch_ts, 0); +} +EXPORT_SYMBOL(touch_softlockup_watchdog); + +void touch_all_softlockup_watchdogs(void) +{ + int cpu; + + /* + * this is done lockless + * do we care if a 0 races with a timestamp? + * all it means is the softlock check starts one cycle later + */ + for_each_online_cpu(cpu) + per_cpu(watchdog_touch_ts, cpu) = 0; +} + +#ifdef CONFIG_HARDLOCKUP_DETECTOR +void touch_nmi_watchdog(void) +{ + /* + * Using __raw here because some code paths have + * preemption enabled. If preemption is enabled + * then interrupts should be enabled too, in which + * case we shouldn't have to worry about the watchdog + * going off. + */ + raw_cpu_write(watchdog_nmi_touch, true); + touch_softlockup_watchdog(); +} +EXPORT_SYMBOL(touch_nmi_watchdog); + +#endif + +void touch_softlockup_watchdog_sync(void) +{ + __this_cpu_write(softlockup_touch_sync, true); + __this_cpu_write(watchdog_touch_ts, 0); +} + +#ifdef CONFIG_HARDLOCKUP_DETECTOR +/* watchdog detector functions */ +static int is_hardlockup(void) +{ + unsigned long hrint = __this_cpu_read(hrtimer_interrupts); + + if (__this_cpu_read(hrtimer_interrupts_saved) == hrint) + return 1; + + __this_cpu_write(hrtimer_interrupts_saved, hrint); + return 0; +} +#endif + +static int is_softlockup(unsigned long touch_ts) +{ + unsigned long now = get_timestamp(); + + if (watchdog_enabled & SOFT_WATCHDOG_ENABLED) { + /* Warn about unreasonable delays. */ + if (time_after(now, touch_ts + get_softlockup_thresh())) + return now - touch_ts; + } + return 0; +} + +#ifdef CONFIG_HARDLOCKUP_DETECTOR + +static DEFINE_RAW_SPINLOCK(watchdog_output_lock); + +static struct perf_event_attr wd_hw_attr = { + .type = PERF_TYPE_HARDWARE, + .config = PERF_COUNT_HW_CPU_CYCLES, + .size = sizeof(struct perf_event_attr), + .pinned = 1, + .disabled = 1, +}; + +/* Callback function for perf event subsystem */ +static void watchdog_overflow_callback(struct perf_event *event, + struct perf_sample_data *data, + struct pt_regs *regs) +{ + /* Ensure the watchdog never gets throttled */ + event->hw.interrupts = 0; + + if (__this_cpu_read(watchdog_nmi_touch) == true) { + __this_cpu_write(watchdog_nmi_touch, false); + return; + } + + /* check for a hardlockup + * This is done by making sure our timer interrupt + * is incrementing. The timer interrupt should have + * fired multiple times before we overflow'd. If it hasn't + * then this is a good indication the cpu is stuck + */ + if (is_hardlockup()) { + int this_cpu = smp_processor_id(); + + /* only print hardlockups once */ + if (__this_cpu_read(hard_watchdog_warn) == true) + return; + /* + * If early-printk is enabled then make sure we do not + * lock up in printk() and kill console logging: + */ + printk_kill(); + + if (hardlockup_panic) { + panic("Watchdog detected hard LOCKUP on cpu %d", + this_cpu); + } else { + raw_spin_lock(&watchdog_output_lock); + WARN(1, "Watchdog detected hard LOCKUP on cpu %d", + this_cpu); + raw_spin_unlock(&watchdog_output_lock); + } + + __this_cpu_write(hard_watchdog_warn, true); + return; + } + + __this_cpu_write(hard_watchdog_warn, false); + return; +} +#endif /* CONFIG_HARDLOCKUP_DETECTOR */ + +static void watchdog_interrupt_count(void) +{ + __this_cpu_inc(hrtimer_interrupts); +} + +static int watchdog_nmi_enable(unsigned int cpu); +static void watchdog_nmi_disable(unsigned int cpu); + +/* watchdog kicker functions */ +static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) +{ + unsigned long touch_ts = __this_cpu_read(watchdog_touch_ts); + struct pt_regs *regs = get_irq_regs(); + int duration; + int softlockup_all_cpu_backtrace = sysctl_softlockup_all_cpu_backtrace; + + /* kick the hardlockup detector */ + watchdog_interrupt_count(); + + /* kick the softlockup detector */ + wake_up_process(__this_cpu_read(softlockup_watchdog)); + + /* .. and repeat */ + hrtimer_forward_now(hrtimer, ns_to_ktime(sample_period)); + + if (touch_ts == 0) { + if (unlikely(__this_cpu_read(softlockup_touch_sync))) { + /* + * If the time stamp was touched atomically + * make sure the scheduler tick is up to date. + */ + __this_cpu_write(softlockup_touch_sync, false); + sched_clock_tick(); + } + + /* Clear the guest paused flag on watchdog reset */ + kvm_check_and_clear_guest_paused(); + __touch_watchdog(); + return HRTIMER_RESTART; + } + + /* check for a softlockup + * This is done by making sure a high priority task is + * being scheduled. The task touches the watchdog to + * indicate it is getting cpu time. If it hasn't then + * this is a good indication some task is hogging the cpu + */ + duration = is_softlockup(touch_ts); + if (unlikely(duration)) { + /* + * If a virtual machine is stopped by the host it can look to + * the watchdog like a soft lockup, check to see if the host + * stopped the vm before we issue the warning + */ + if (kvm_check_and_clear_guest_paused()) + return HRTIMER_RESTART; + + /* only warn once */ + if (__this_cpu_read(soft_watchdog_warn) == true) { + /* + * When multiple processes are causing softlockups the + * softlockup detector only warns on the first one + * because the code relies on a full quiet cycle to + * re-arm. The second process prevents the quiet cycle + * and never gets reported. Use task pointers to detect + * this. + */ + if (__this_cpu_read(softlockup_task_ptr_saved) != + current) { + __this_cpu_write(soft_watchdog_warn, false); + __touch_watchdog(); + } + return HRTIMER_RESTART; + } + + if (softlockup_all_cpu_backtrace) { + /* Prevent multiple soft-lockup reports if one cpu is already + * engaged in dumping cpu back traces + */ + if (test_and_set_bit(0, &soft_lockup_nmi_warn)) { + /* Someone else will report us. Let's give up */ + __this_cpu_write(soft_watchdog_warn, true); + return HRTIMER_RESTART; + } + } + + pr_emerg("BUG: soft lockup - CPU#%d stuck for %us! [%s:%d]\n", + smp_processor_id(), duration, + current->comm, task_pid_nr(current)); + __this_cpu_write(softlockup_task_ptr_saved, current); + print_modules(); + print_irqtrace_events(current); + if (regs) + show_regs(regs); + else + dump_stack(); + + if (softlockup_all_cpu_backtrace) { + /* Avoid generating two back traces for current + * given that one is already made above + */ + trigger_allbutself_cpu_backtrace(); + + clear_bit(0, &soft_lockup_nmi_warn); + /* Barrier to sync with other cpus */ + smp_mb__after_atomic(); + } + + add_taint(TAINT_SOFTLOCKUP, LOCKDEP_STILL_OK); + if (softlockup_panic) + panic("softlockup: hung tasks"); + __this_cpu_write(soft_watchdog_warn, true); + } else + __this_cpu_write(soft_watchdog_warn, false); + + return HRTIMER_RESTART; +} + +static void watchdog_set_prio(unsigned int policy, unsigned int prio) +{ + struct sched_param param = { .sched_priority = prio }; + + sched_setscheduler(current, policy, ¶m); +} + +static void watchdog_enable(unsigned int cpu) +{ + struct hrtimer *hrtimer = raw_cpu_ptr(&watchdog_hrtimer); + + /* kick off the timer for the hardlockup detector */ + hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + hrtimer->function = watchdog_timer_fn; + hrtimer->irqsafe = 1; + + /* Enable the perf event */ + watchdog_nmi_enable(cpu); + + /* done here because hrtimer_start can only pin to smp_processor_id() */ + hrtimer_start(hrtimer, ns_to_ktime(sample_period), + HRTIMER_MODE_REL_PINNED); + + /* initialize timestamp */ + watchdog_set_prio(SCHED_FIFO, MAX_RT_PRIO - 1); + __touch_watchdog(); +} + +static void watchdog_disable(unsigned int cpu) +{ + struct hrtimer *hrtimer = raw_cpu_ptr(&watchdog_hrtimer); + + watchdog_set_prio(SCHED_NORMAL, 0); + hrtimer_cancel(hrtimer); + /* disable the perf event */ + watchdog_nmi_disable(cpu); +} + +static void watchdog_cleanup(unsigned int cpu, bool online) +{ + watchdog_disable(cpu); +} + +static int watchdog_should_run(unsigned int cpu) +{ + return __this_cpu_read(hrtimer_interrupts) != + __this_cpu_read(soft_lockup_hrtimer_cnt); +} + +/* + * The watchdog thread function - touches the timestamp. + * + * It only runs once every sample_period seconds (4 seconds by + * default) to reset the softlockup timestamp. If this gets delayed + * for more than 2*watchdog_thresh seconds then the debug-printout + * triggers in watchdog_timer_fn(). + */ +static void watchdog(unsigned int cpu) +{ + __this_cpu_write(soft_lockup_hrtimer_cnt, + __this_cpu_read(hrtimer_interrupts)); + __touch_watchdog(); + + /* + * watchdog_nmi_enable() clears the NMI_WATCHDOG_ENABLED bit in the + * failure path. Check for failures that can occur asynchronously - + * for example, when CPUs are on-lined - and shut down the hardware + * perf event on each CPU accordingly. + * + * The only non-obvious place this bit can be cleared is through + * watchdog_nmi_enable(), so a pr_info() is placed there. Placing a + * pr_info here would be too noisy as it would result in a message + * every few seconds if the hardlockup was disabled but the softlockup + * enabled. + */ + if (!(watchdog_enabled & NMI_WATCHDOG_ENABLED)) + watchdog_nmi_disable(cpu); +} + +#ifdef CONFIG_HARDLOCKUP_DETECTOR +/* + * People like the simple clean cpu node info on boot. + * Reduce the watchdog noise by only printing messages + * that are different from what cpu0 displayed. + */ +static unsigned long cpu0_err; + +static int watchdog_nmi_enable(unsigned int cpu) +{ + struct perf_event_attr *wd_attr; + struct perf_event *event = per_cpu(watchdog_ev, cpu); + + /* nothing to do if the hard lockup detector is disabled */ + if (!(watchdog_enabled & NMI_WATCHDOG_ENABLED)) + goto out; + + /* is it already setup and enabled? */ + if (event && event->state > PERF_EVENT_STATE_OFF) + goto out; + + /* it is setup but not enabled */ + if (event != NULL) + goto out_enable; + + wd_attr = &wd_hw_attr; + wd_attr->sample_period = hw_nmi_get_sample_period(watchdog_thresh); + + /* Try to register using hardware perf events */ + event = perf_event_create_kernel_counter(wd_attr, cpu, NULL, watchdog_overflow_callback, NULL); + + /* save cpu0 error for future comparision */ + if (cpu == 0 && IS_ERR(event)) + cpu0_err = PTR_ERR(event); + + if (!IS_ERR(event)) { + /* only print for cpu0 or different than cpu0 */ + if (cpu == 0 || cpu0_err) + pr_info("enabled on all CPUs, permanently consumes one hw-PMU counter.\n"); + goto out_save; + } + + /* + * Disable the hard lockup detector if _any_ CPU fails to set up + * set up the hardware perf event. The watchdog() function checks + * the NMI_WATCHDOG_ENABLED bit periodically. + * + * The barriers are for syncing up watchdog_enabled across all the + * cpus, as clear_bit() does not use barriers. + */ + smp_mb__before_atomic(); + clear_bit(NMI_WATCHDOG_ENABLED_BIT, &watchdog_enabled); + smp_mb__after_atomic(); + + /* skip displaying the same error again */ + if (cpu > 0 && (PTR_ERR(event) == cpu0_err)) + return PTR_ERR(event); + + /* vary the KERN level based on the returned errno */ + if (PTR_ERR(event) == -EOPNOTSUPP) + pr_info("disabled (cpu%i): not supported (no LAPIC?)\n", cpu); + else if (PTR_ERR(event) == -ENOENT) + pr_warn("disabled (cpu%i): hardware events not enabled\n", + cpu); + else + pr_err("disabled (cpu%i): unable to create perf event: %ld\n", + cpu, PTR_ERR(event)); + + pr_info("Shutting down hard lockup detector on all cpus\n"); + + return PTR_ERR(event); + + /* success path */ +out_save: + per_cpu(watchdog_ev, cpu) = event; +out_enable: + perf_event_enable(per_cpu(watchdog_ev, cpu)); +out: + return 0; +} + +static void watchdog_nmi_disable(unsigned int cpu) +{ + struct perf_event *event = per_cpu(watchdog_ev, cpu); + + if (event) { + perf_event_disable(event); + per_cpu(watchdog_ev, cpu) = NULL; + + /* should be in cleanup, but blocks oprofile */ + perf_event_release_kernel(event); + } + if (cpu == 0) { + /* watchdog_nmi_enable() expects this to be zero initially. */ + cpu0_err = 0; + } +} + +void watchdog_nmi_enable_all(void) +{ + int cpu; + + mutex_lock(&watchdog_proc_mutex); + + if (!(watchdog_enabled & NMI_WATCHDOG_ENABLED)) + goto unlock; + + get_online_cpus(); + for_each_online_cpu(cpu) + watchdog_nmi_enable(cpu); + put_online_cpus(); + +unlock: + mutex_unlock(&watchdog_proc_mutex); +} + +void watchdog_nmi_disable_all(void) +{ + int cpu; + + mutex_lock(&watchdog_proc_mutex); + + if (!watchdog_running) + goto unlock; + + get_online_cpus(); + for_each_online_cpu(cpu) + watchdog_nmi_disable(cpu); + put_online_cpus(); + +unlock: + mutex_unlock(&watchdog_proc_mutex); +} +#else +static int watchdog_nmi_enable(unsigned int cpu) { return 0; } +static void watchdog_nmi_disable(unsigned int cpu) { return; } +void watchdog_nmi_enable_all(void) {} +void watchdog_nmi_disable_all(void) {} +#endif /* CONFIG_HARDLOCKUP_DETECTOR */ + +static struct smp_hotplug_thread watchdog_threads = { + .store = &softlockup_watchdog, + .thread_should_run = watchdog_should_run, + .thread_fn = watchdog, + .thread_comm = "watchdog/%u", + .setup = watchdog_enable, + .cleanup = watchdog_cleanup, + .park = watchdog_disable, + .unpark = watchdog_enable, +}; + +static void restart_watchdog_hrtimer(void *info) +{ + struct hrtimer *hrtimer = raw_cpu_ptr(&watchdog_hrtimer); + int ret; + + /* + * No need to cancel and restart hrtimer if it is currently executing + * because it will reprogram itself with the new period now. + * We should never see it unqueued here because we are running per-cpu + * with interrupts disabled. + */ + ret = hrtimer_try_to_cancel(hrtimer); + if (ret == 1) + hrtimer_start(hrtimer, ns_to_ktime(sample_period), + HRTIMER_MODE_REL_PINNED); +} + +static void update_watchdog(int cpu) +{ + /* + * Make sure that perf event counter will adopt to a new + * sampling period. Updating the sampling period directly would + * be much nicer but we do not have an API for that now so + * let's use a big hammer. + * Hrtimer will adopt the new period on the next tick but this + * might be late already so we have to restart the timer as well. + */ + watchdog_nmi_disable(cpu); + smp_call_function_single(cpu, restart_watchdog_hrtimer, NULL, 1); + watchdog_nmi_enable(cpu); +} + +static void update_watchdog_all_cpus(void) +{ + int cpu; + + get_online_cpus(); + for_each_online_cpu(cpu) + update_watchdog(cpu); + put_online_cpus(); +} + +static int watchdog_enable_all_cpus(void) +{ + int err = 0; + + if (!watchdog_running) { + err = smpboot_register_percpu_thread(&watchdog_threads); + if (err) + pr_err("Failed to create watchdog threads, disabled\n"); + else + watchdog_running = 1; + } else { + /* + * Enable/disable the lockup detectors or + * change the sample period 'on the fly'. + */ + update_watchdog_all_cpus(); + } + + return err; +} + +/* prepare/enable/disable routines */ +/* sysctl functions */ +#ifdef CONFIG_SYSCTL +static void watchdog_disable_all_cpus(void) +{ + if (watchdog_running) { + watchdog_running = 0; + smpboot_unregister_percpu_thread(&watchdog_threads); + } +} + +/* + * Update the run state of the lockup detectors. + */ +static int proc_watchdog_update(void) +{ + int err = 0; + + /* + * Watchdog threads won't be started if they are already active. + * The 'watchdog_running' variable in watchdog_*_all_cpus() takes + * care of this. If those threads are already active, the sample + * period will be updated and the lockup detectors will be enabled + * or disabled 'on the fly'. + */ + if (watchdog_enabled && watchdog_thresh) + err = watchdog_enable_all_cpus(); + else + watchdog_disable_all_cpus(); + + return err; + +} + +/* + * common function for watchdog, nmi_watchdog and soft_watchdog parameter + * + * caller | table->data points to | 'which' contains the flag(s) + * -------------------|-----------------------|----------------------------- + * proc_watchdog | watchdog_user_enabled | NMI_WATCHDOG_ENABLED or'ed + * | | with SOFT_WATCHDOG_ENABLED + * -------------------|-----------------------|----------------------------- + * proc_nmi_watchdog | nmi_watchdog_enabled | NMI_WATCHDOG_ENABLED + * -------------------|-----------------------|----------------------------- + * proc_soft_watchdog | soft_watchdog_enabled | SOFT_WATCHDOG_ENABLED + */ +static int proc_watchdog_common(int which, struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + int err, old, new; + int *watchdog_param = (int *)table->data; + + mutex_lock(&watchdog_proc_mutex); + + /* + * If the parameter is being read return the state of the corresponding + * bit(s) in 'watchdog_enabled', else update 'watchdog_enabled' and the + * run state of the lockup detectors. + */ + if (!write) { + *watchdog_param = (watchdog_enabled & which) != 0; + err = proc_dointvec_minmax(table, write, buffer, lenp, ppos); + } else { + err = proc_dointvec_minmax(table, write, buffer, lenp, ppos); + if (err) + goto out; + + /* + * There is a race window between fetching the current value + * from 'watchdog_enabled' and storing the new value. During + * this race window, watchdog_nmi_enable() can sneak in and + * clear the NMI_WATCHDOG_ENABLED bit in 'watchdog_enabled'. + * The 'cmpxchg' detects this race and the loop retries. + */ + do { + old = watchdog_enabled; + /* + * If the parameter value is not zero set the + * corresponding bit(s), else clear it(them). + */ + if (*watchdog_param) + new = old | which; + else + new = old & ~which; + } while (cmpxchg(&watchdog_enabled, old, new) != old); + + /* + * Update the run state of the lockup detectors. + * Restore 'watchdog_enabled' on failure. + */ + err = proc_watchdog_update(); + if (err) + watchdog_enabled = old; + } +out: + mutex_unlock(&watchdog_proc_mutex); + return err; +} + +/* + * /proc/sys/kernel/watchdog + */ +int proc_watchdog(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + return proc_watchdog_common(NMI_WATCHDOG_ENABLED|SOFT_WATCHDOG_ENABLED, + table, write, buffer, lenp, ppos); +} + +/* + * /proc/sys/kernel/nmi_watchdog + */ +int proc_nmi_watchdog(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + return proc_watchdog_common(NMI_WATCHDOG_ENABLED, + table, write, buffer, lenp, ppos); +} + +/* + * /proc/sys/kernel/soft_watchdog + */ +int proc_soft_watchdog(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + return proc_watchdog_common(SOFT_WATCHDOG_ENABLED, + table, write, buffer, lenp, ppos); +} + +/* + * /proc/sys/kernel/watchdog_thresh + */ +int proc_watchdog_thresh(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + int err, old; + + mutex_lock(&watchdog_proc_mutex); + + old = ACCESS_ONCE(watchdog_thresh); + err = proc_dointvec_minmax(table, write, buffer, lenp, ppos); + + if (err || !write) + goto out; + + /* + * Update the sample period. + * Restore 'watchdog_thresh' on failure. + */ + set_sample_period(); + err = proc_watchdog_update(); + if (err) + watchdog_thresh = old; +out: + mutex_unlock(&watchdog_proc_mutex); + return err; +} +#endif /* CONFIG_SYSCTL */ + +void __init lockup_detector_init(void) +{ + set_sample_period(); + + if (watchdog_enabled) + watchdog_enable_all_cpus(); +} diff --git a/kernel/kernel/workqueue.c b/kernel/kernel/workqueue.c new file mode 100644 index 000000000..21daecdfd --- /dev/null +++ b/kernel/kernel/workqueue.c @@ -0,0 +1,5180 @@ +/* + * kernel/workqueue.c - generic async execution with shared worker pool + * + * Copyright (C) 2002 Ingo Molnar + * + * Derived from the taskqueue/keventd code by: + * David Woodhouse + * Andrew Morton + * Kai Petzke + * Theodore Ts'o + * + * Made to use alloc_percpu by Christoph Lameter. + * + * Copyright (C) 2010 SUSE Linux Products GmbH + * Copyright (C) 2010 Tejun Heo + * + * This is the generic async execution mechanism. Work items as are + * executed in process context. The worker pool is shared and + * automatically managed. There are two worker pools for each CPU (one for + * normal work items and the other for high priority ones) and some extra + * pools for workqueues which are not bound to any specific CPU - the + * number of these backing pools is dynamic. + * + * Please read Documentation/workqueue.txt for details. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "workqueue_internal.h" + +enum { + /* + * worker_pool flags + * + * A bound pool is either associated or disassociated with its CPU. + * While associated (!DISASSOCIATED), all workers are bound to the + * CPU and none has %WORKER_UNBOUND set and concurrency management + * is in effect. + * + * While DISASSOCIATED, the cpu may be offline and all workers have + * %WORKER_UNBOUND set and concurrency management disabled, and may + * be executing on any CPU. The pool behaves as an unbound one. + * + * Note that DISASSOCIATED should be flipped only while holding + * attach_mutex to avoid changing binding state while + * worker_attach_to_pool() is in progress. + */ + POOL_DISASSOCIATED = 1 << 2, /* cpu can't serve workers */ + + /* worker flags */ + WORKER_DIE = 1 << 1, /* die die die */ + WORKER_IDLE = 1 << 2, /* is idle */ + WORKER_PREP = 1 << 3, /* preparing to run works */ + WORKER_CPU_INTENSIVE = 1 << 6, /* cpu intensive */ + WORKER_UNBOUND = 1 << 7, /* worker is unbound */ + WORKER_REBOUND = 1 << 8, /* worker was rebound */ + + WORKER_NOT_RUNNING = WORKER_PREP | WORKER_CPU_INTENSIVE | + WORKER_UNBOUND | WORKER_REBOUND, + + NR_STD_WORKER_POOLS = 2, /* # standard pools per cpu */ + + UNBOUND_POOL_HASH_ORDER = 6, /* hashed by pool->attrs */ + BUSY_WORKER_HASH_ORDER = 6, /* 64 pointers */ + + MAX_IDLE_WORKERS_RATIO = 4, /* 1/4 of busy can be idle */ + IDLE_WORKER_TIMEOUT = 300 * HZ, /* keep idle ones for 5 mins */ + + MAYDAY_INITIAL_TIMEOUT = HZ / 100 >= 2 ? HZ / 100 : 2, + /* call for help after 10ms + (min two ticks) */ + MAYDAY_INTERVAL = HZ / 10, /* and then every 100ms */ + CREATE_COOLDOWN = HZ, /* time to breath after fail */ + + /* + * Rescue workers are used only on emergencies and shared by + * all cpus. Give MIN_NICE. + */ + RESCUER_NICE_LEVEL = MIN_NICE, + HIGHPRI_NICE_LEVEL = MIN_NICE, + + WQ_NAME_LEN = 24, +}; + +/* + * Structure fields follow one of the following exclusion rules. + * + * I: Modifiable by initialization/destruction paths and read-only for + * everyone else. + * + * P: Preemption protected. Disabling preemption is enough and should + * only be modified and accessed from the local cpu. + * + * L: pool->lock protected. Access with pool->lock held. + * + * X: During normal operation, modification requires pool->lock and should + * be done only from local cpu. Either disabling preemption on local + * cpu or grabbing pool->lock is enough for read access. If + * POOL_DISASSOCIATED is set, it's identical to L. + * + * On RT we need the extra protection via rt_lock_idle_list() for + * the list manipulations against read access from + * wq_worker_sleeping(). All other places are nicely serialized via + * pool->lock. + * + * A: pool->attach_mutex protected. + * + * PL: wq_pool_mutex protected. + * + * PR: wq_pool_mutex protected for writes. RCU protected for reads. + * + * WQ: wq->mutex protected. + * + * WR: wq->mutex protected for writes. RCU protected for reads. + * + * MD: wq_mayday_lock protected. + */ + +/* struct worker is defined in workqueue_internal.h */ + +struct worker_pool { + spinlock_t lock; /* the pool lock */ + int cpu; /* I: the associated cpu */ + int node; /* I: the associated node ID */ + int id; /* I: pool ID */ + unsigned int flags; /* X: flags */ + + struct list_head worklist; /* L: list of pending works */ + int nr_workers; /* L: total number of workers */ + + /* nr_idle includes the ones off idle_list for rebinding */ + int nr_idle; /* L: currently idle ones */ + + struct list_head idle_list; /* X: list of idle workers */ + struct timer_list idle_timer; /* L: worker idle timeout */ + struct timer_list mayday_timer; /* L: SOS timer for workers */ + + /* a workers is either on busy_hash or idle_list, or the manager */ + DECLARE_HASHTABLE(busy_hash, BUSY_WORKER_HASH_ORDER); + /* L: hash of busy workers */ + + /* see manage_workers() for details on the two manager mutexes */ + struct mutex manager_arb; /* manager arbitration */ + struct worker *manager; /* L: purely informational */ + struct mutex attach_mutex; /* attach/detach exclusion */ + struct list_head workers; /* A: attached workers */ + struct completion *detach_completion; /* all workers detached */ + + struct ida worker_ida; /* worker IDs for task name */ + + struct workqueue_attrs *attrs; /* I: worker attributes */ + struct hlist_node hash_node; /* PL: unbound_pool_hash node */ + int refcnt; /* PL: refcnt for unbound pools */ + + /* + * The current concurrency level. As it's likely to be accessed + * from other CPUs during try_to_wake_up(), put it in a separate + * cacheline. + */ + atomic_t nr_running ____cacheline_aligned_in_smp; + + /* + * Destruction of pool is RCU protected to allow dereferences + * from get_work_pool(). + */ + struct rcu_head rcu; +} ____cacheline_aligned_in_smp; + +/* + * The per-pool workqueue. While queued, the lower WORK_STRUCT_FLAG_BITS + * of work_struct->data are used for flags and the remaining high bits + * point to the pwq; thus, pwqs need to be aligned at two's power of the + * number of flag bits. + */ +struct pool_workqueue { + struct worker_pool *pool; /* I: the associated pool */ + struct workqueue_struct *wq; /* I: the owning workqueue */ + int work_color; /* L: current color */ + int flush_color; /* L: flushing color */ + int refcnt; /* L: reference count */ + int nr_in_flight[WORK_NR_COLORS]; + /* L: nr of in_flight works */ + int nr_active; /* L: nr of active works */ + int max_active; /* L: max active works */ + struct list_head delayed_works; /* L: delayed works */ + struct list_head pwqs_node; /* WR: node on wq->pwqs */ + struct list_head mayday_node; /* MD: node on wq->maydays */ + + /* + * Release of unbound pwq is punted to system_wq. See put_pwq() + * and pwq_unbound_release_workfn() for details. pool_workqueue + * itself is also RCU protected so that the first pwq can be + * determined without grabbing wq->mutex. + */ + struct work_struct unbound_release_work; + struct rcu_head rcu; +} __aligned(1 << WORK_STRUCT_FLAG_BITS); + +/* + * Structure used to wait for workqueue flush. + */ +struct wq_flusher { + struct list_head list; /* WQ: list of flushers */ + int flush_color; /* WQ: flush color waiting for */ + struct completion done; /* flush completion */ +}; + +struct wq_device; + +/* + * The externally visible workqueue. It relays the issued work items to + * the appropriate worker_pool through its pool_workqueues. + */ +struct workqueue_struct { + struct list_head pwqs; /* WR: all pwqs of this wq */ + struct list_head list; /* PR: list of all workqueues */ + + struct mutex mutex; /* protects this wq */ + int work_color; /* WQ: current work color */ + int flush_color; /* WQ: current flush color */ + atomic_t nr_pwqs_to_flush; /* flush in progress */ + struct wq_flusher *first_flusher; /* WQ: first flusher */ + struct list_head flusher_queue; /* WQ: flush waiters */ + struct list_head flusher_overflow; /* WQ: flush overflow list */ + + struct list_head maydays; /* MD: pwqs requesting rescue */ + struct worker *rescuer; /* I: rescue worker */ + + int nr_drainers; /* WQ: drain in progress */ + int saved_max_active; /* WQ: saved pwq max_active */ + + struct workqueue_attrs *unbound_attrs; /* WQ: only for unbound wqs */ + struct pool_workqueue *dfl_pwq; /* WQ: only for unbound wqs */ + +#ifdef CONFIG_SYSFS + struct wq_device *wq_dev; /* I: for sysfs interface */ +#endif +#ifdef CONFIG_LOCKDEP + struct lockdep_map lockdep_map; +#endif + char name[WQ_NAME_LEN]; /* I: workqueue name */ + + /* + * Destruction of workqueue_struct is sched-RCU protected to allow + * walking the workqueues list without grabbing wq_pool_mutex. + * This is used to dump all workqueues from sysrq. + */ + struct rcu_head rcu; + + /* hot fields used during command issue, aligned to cacheline */ + unsigned int flags ____cacheline_aligned; /* WQ: WQ_* flags */ + struct pool_workqueue __percpu *cpu_pwqs; /* I: per-cpu pwqs */ + struct pool_workqueue __rcu *numa_pwq_tbl[]; /* FR: unbound pwqs indexed by node */ +}; + +static struct kmem_cache *pwq_cache; + +static cpumask_var_t *wq_numa_possible_cpumask; + /* possible CPUs of each node */ + +static bool wq_disable_numa; +module_param_named(disable_numa, wq_disable_numa, bool, 0444); + +/* see the comment above the definition of WQ_POWER_EFFICIENT */ +#ifdef CONFIG_WQ_POWER_EFFICIENT_DEFAULT +static bool wq_power_efficient = true; +#else +static bool wq_power_efficient; +#endif + +module_param_named(power_efficient, wq_power_efficient, bool, 0444); + +static bool wq_numa_enabled; /* unbound NUMA affinity enabled */ + +/* buf for wq_update_unbound_numa_attrs(), protected by CPU hotplug exclusion */ +static struct workqueue_attrs *wq_update_unbound_numa_attrs_buf; + +static DEFINE_MUTEX(wq_pool_mutex); /* protects pools and workqueues list */ +static DEFINE_SPINLOCK(wq_mayday_lock); /* protects wq->maydays list */ + +static LIST_HEAD(workqueues); /* PR: list of all workqueues */ +static bool workqueue_freezing; /* PL: have wqs started freezing? */ + +/* the per-cpu worker pools */ +static DEFINE_PER_CPU_SHARED_ALIGNED(struct worker_pool [NR_STD_WORKER_POOLS], + cpu_worker_pools); + +static DEFINE_IDR(worker_pool_idr); /* PR: idr of all pools */ + +/* PL: hash of all unbound pools keyed by pool->attrs */ +static DEFINE_HASHTABLE(unbound_pool_hash, UNBOUND_POOL_HASH_ORDER); + +/* I: attributes used when instantiating standard unbound pools on demand */ +static struct workqueue_attrs *unbound_std_wq_attrs[NR_STD_WORKER_POOLS]; + +/* I: attributes used when instantiating ordered pools on demand */ +static struct workqueue_attrs *ordered_wq_attrs[NR_STD_WORKER_POOLS]; + +struct workqueue_struct *system_wq __read_mostly; +EXPORT_SYMBOL(system_wq); +struct workqueue_struct *system_highpri_wq __read_mostly; +EXPORT_SYMBOL_GPL(system_highpri_wq); +struct workqueue_struct *system_long_wq __read_mostly; +EXPORT_SYMBOL_GPL(system_long_wq); +struct workqueue_struct *system_unbound_wq __read_mostly; +EXPORT_SYMBOL_GPL(system_unbound_wq); +struct workqueue_struct *system_freezable_wq __read_mostly; +EXPORT_SYMBOL_GPL(system_freezable_wq); +struct workqueue_struct *system_power_efficient_wq __read_mostly; +EXPORT_SYMBOL_GPL(system_power_efficient_wq); +struct workqueue_struct *system_freezable_power_efficient_wq __read_mostly; +EXPORT_SYMBOL_GPL(system_freezable_power_efficient_wq); + +static DEFINE_LOCAL_IRQ_LOCK(pendingb_lock); + +static int worker_thread(void *__worker); +static void copy_workqueue_attrs(struct workqueue_attrs *to, + const struct workqueue_attrs *from); +static void workqueue_sysfs_unregister(struct workqueue_struct *wq); + +#define CREATE_TRACE_POINTS +#include + +#define assert_rcu_or_pool_mutex() \ + rcu_lockdep_assert(rcu_read_lock_held() || \ + lockdep_is_held(&wq_pool_mutex), \ + "RCU or wq_pool_mutex should be held") + +#define assert_rcu_or_wq_mutex(wq) \ + rcu_lockdep_assert(rcu_read_lock_held() || \ + lockdep_is_held(&wq->mutex), \ + "RCU or wq->mutex should be held") + +#define for_each_cpu_worker_pool(pool, cpu) \ + for ((pool) = &per_cpu(cpu_worker_pools, cpu)[0]; \ + (pool) < &per_cpu(cpu_worker_pools, cpu)[NR_STD_WORKER_POOLS]; \ + (pool)++) + +/** + * for_each_pool - iterate through all worker_pools in the system + * @pool: iteration cursor + * @pi: integer used for iteration + * + * This must be called either with wq_pool_mutex held or RCU read + * locked. If the pool needs to be used beyond the locking in effect, the + * caller is responsible for guaranteeing that the pool stays online. + * + * The if/else clause exists only for the lockdep assertion and can be + * ignored. + */ +#define for_each_pool(pool, pi) \ + idr_for_each_entry(&worker_pool_idr, pool, pi) \ + if (({ assert_rcu_or_pool_mutex(); false; })) { } \ + else + +/** + * for_each_pool_worker - iterate through all workers of a worker_pool + * @worker: iteration cursor + * @pool: worker_pool to iterate workers of + * + * This must be called with @pool->attach_mutex. + * + * The if/else clause exists only for the lockdep assertion and can be + * ignored. + */ +#define for_each_pool_worker(worker, pool) \ + list_for_each_entry((worker), &(pool)->workers, node) \ + if (({ lockdep_assert_held(&pool->attach_mutex); false; })) { } \ + else + +/** + * for_each_pwq - iterate through all pool_workqueues of the specified workqueue + * @pwq: iteration cursor + * @wq: the target workqueue + * + * This must be called either with wq->mutex held or RCU read locked. + * If the pwq needs to be used beyond the locking in effect, the caller is + * responsible for guaranteeing that the pwq stays online. + * + * The if/else clause exists only for the lockdep assertion and can be + * ignored. + */ +#define for_each_pwq(pwq, wq) \ + list_for_each_entry_rcu((pwq), &(wq)->pwqs, pwqs_node) \ + if (({ assert_rcu_or_wq_mutex(wq); false; })) { } \ + else + +#ifdef CONFIG_PREEMPT_RT_BASE +static inline void rt_lock_idle_list(struct worker_pool *pool) +{ + preempt_disable(); +} +static inline void rt_unlock_idle_list(struct worker_pool *pool) +{ + preempt_enable(); +} +static inline void sched_lock_idle_list(struct worker_pool *pool) { } +static inline void sched_unlock_idle_list(struct worker_pool *pool) { } +#else +static inline void rt_lock_idle_list(struct worker_pool *pool) { } +static inline void rt_unlock_idle_list(struct worker_pool *pool) { } +static inline void sched_lock_idle_list(struct worker_pool *pool) +{ + spin_lock_irq(&pool->lock); +} +static inline void sched_unlock_idle_list(struct worker_pool *pool) +{ + spin_unlock_irq(&pool->lock); +} +#endif + + +#ifdef CONFIG_DEBUG_OBJECTS_WORK + +static struct debug_obj_descr work_debug_descr; + +static void *work_debug_hint(void *addr) +{ + return ((struct work_struct *) addr)->func; +} + +/* + * fixup_init is called when: + * - an active object is initialized + */ +static int work_fixup_init(void *addr, enum debug_obj_state state) +{ + struct work_struct *work = addr; + + switch (state) { + case ODEBUG_STATE_ACTIVE: + cancel_work_sync(work); + debug_object_init(work, &work_debug_descr); + return 1; + default: + return 0; + } +} + +/* + * fixup_activate is called when: + * - an active object is activated + * - an unknown object is activated (might be a statically initialized object) + */ +static int work_fixup_activate(void *addr, enum debug_obj_state state) +{ + struct work_struct *work = addr; + + switch (state) { + + case ODEBUG_STATE_NOTAVAILABLE: + /* + * This is not really a fixup. The work struct was + * statically initialized. We just make sure that it + * is tracked in the object tracker. + */ + if (test_bit(WORK_STRUCT_STATIC_BIT, work_data_bits(work))) { + debug_object_init(work, &work_debug_descr); + debug_object_activate(work, &work_debug_descr); + return 0; + } + WARN_ON_ONCE(1); + return 0; + + case ODEBUG_STATE_ACTIVE: + WARN_ON(1); + + default: + return 0; + } +} + +/* + * fixup_free is called when: + * - an active object is freed + */ +static int work_fixup_free(void *addr, enum debug_obj_state state) +{ + struct work_struct *work = addr; + + switch (state) { + case ODEBUG_STATE_ACTIVE: + cancel_work_sync(work); + debug_object_free(work, &work_debug_descr); + return 1; + default: + return 0; + } +} + +static struct debug_obj_descr work_debug_descr = { + .name = "work_struct", + .debug_hint = work_debug_hint, + .fixup_init = work_fixup_init, + .fixup_activate = work_fixup_activate, + .fixup_free = work_fixup_free, +}; + +static inline void debug_work_activate(struct work_struct *work) +{ + debug_object_activate(work, &work_debug_descr); +} + +static inline void debug_work_deactivate(struct work_struct *work) +{ + debug_object_deactivate(work, &work_debug_descr); +} + +void __init_work(struct work_struct *work, int onstack) +{ + if (onstack) + debug_object_init_on_stack(work, &work_debug_descr); + else + debug_object_init(work, &work_debug_descr); +} +EXPORT_SYMBOL_GPL(__init_work); + +void destroy_work_on_stack(struct work_struct *work) +{ + debug_object_free(work, &work_debug_descr); +} +EXPORT_SYMBOL_GPL(destroy_work_on_stack); + +void destroy_delayed_work_on_stack(struct delayed_work *work) +{ + destroy_timer_on_stack(&work->timer); + debug_object_free(&work->work, &work_debug_descr); +} +EXPORT_SYMBOL_GPL(destroy_delayed_work_on_stack); + +#else +static inline void debug_work_activate(struct work_struct *work) { } +static inline void debug_work_deactivate(struct work_struct *work) { } +#endif + +/** + * worker_pool_assign_id - allocate ID and assing it to @pool + * @pool: the pool pointer of interest + * + * Returns 0 if ID in [0, WORK_OFFQ_POOL_NONE) is allocated and assigned + * successfully, -errno on failure. + */ +static int worker_pool_assign_id(struct worker_pool *pool) +{ + int ret; + + lockdep_assert_held(&wq_pool_mutex); + + ret = idr_alloc(&worker_pool_idr, pool, 0, WORK_OFFQ_POOL_NONE, + GFP_KERNEL); + if (ret >= 0) { + pool->id = ret; + return 0; + } + return ret; +} + +/** + * unbound_pwq_by_node - return the unbound pool_workqueue for the given node + * @wq: the target workqueue + * @node: the node ID + * + * This must be called either with pwq_lock held or RCU read locked. + * If the pwq needs to be used beyond the locking in effect, the caller is + * responsible for guaranteeing that the pwq stays online. + * + * Return: The unbound pool_workqueue for @node. + */ +static struct pool_workqueue *unbound_pwq_by_node(struct workqueue_struct *wq, + int node) +{ + assert_rcu_or_wq_mutex(wq); + return rcu_dereference_raw(wq->numa_pwq_tbl[node]); +} + +static unsigned int work_color_to_flags(int color) +{ + return color << WORK_STRUCT_COLOR_SHIFT; +} + +static int get_work_color(struct work_struct *work) +{ + return (*work_data_bits(work) >> WORK_STRUCT_COLOR_SHIFT) & + ((1 << WORK_STRUCT_COLOR_BITS) - 1); +} + +static int work_next_color(int color) +{ + return (color + 1) % WORK_NR_COLORS; +} + +/* + * While queued, %WORK_STRUCT_PWQ is set and non flag bits of a work's data + * contain the pointer to the queued pwq. Once execution starts, the flag + * is cleared and the high bits contain OFFQ flags and pool ID. + * + * set_work_pwq(), set_work_pool_and_clear_pending(), mark_work_canceling() + * and clear_work_data() can be used to set the pwq, pool or clear + * work->data. These functions should only be called while the work is + * owned - ie. while the PENDING bit is set. + * + * get_work_pool() and get_work_pwq() can be used to obtain the pool or pwq + * corresponding to a work. Pool is available once the work has been + * queued anywhere after initialization until it is sync canceled. pwq is + * available only while the work item is queued. + * + * %WORK_OFFQ_CANCELING is used to mark a work item which is being + * canceled. While being canceled, a work item may have its PENDING set + * but stay off timer and worklist for arbitrarily long and nobody should + * try to steal the PENDING bit. + */ +static inline void set_work_data(struct work_struct *work, unsigned long data, + unsigned long flags) +{ + WARN_ON_ONCE(!work_pending(work)); + atomic_long_set(&work->data, data | flags | work_static(work)); +} + +static void set_work_pwq(struct work_struct *work, struct pool_workqueue *pwq, + unsigned long extra_flags) +{ + set_work_data(work, (unsigned long)pwq, + WORK_STRUCT_PENDING | WORK_STRUCT_PWQ | extra_flags); +} + +static void set_work_pool_and_keep_pending(struct work_struct *work, + int pool_id) +{ + set_work_data(work, (unsigned long)pool_id << WORK_OFFQ_POOL_SHIFT, + WORK_STRUCT_PENDING); +} + +static void set_work_pool_and_clear_pending(struct work_struct *work, + int pool_id) +{ + /* + * The following wmb is paired with the implied mb in + * test_and_set_bit(PENDING) and ensures all updates to @work made + * here are visible to and precede any updates by the next PENDING + * owner. + */ + smp_wmb(); + set_work_data(work, (unsigned long)pool_id << WORK_OFFQ_POOL_SHIFT, 0); +} + +static void clear_work_data(struct work_struct *work) +{ + smp_wmb(); /* see set_work_pool_and_clear_pending() */ + set_work_data(work, WORK_STRUCT_NO_POOL, 0); +} + +static struct pool_workqueue *get_work_pwq(struct work_struct *work) +{ + unsigned long data = atomic_long_read(&work->data); + + if (data & WORK_STRUCT_PWQ) + return (void *)(data & WORK_STRUCT_WQ_DATA_MASK); + else + return NULL; +} + +/** + * get_work_pool - return the worker_pool a given work was associated with + * @work: the work item of interest + * + * Pools are created and destroyed under wq_pool_mutex, and allows read + * access under RCU read lock. As such, this function should be + * called under wq_pool_mutex or inside of a rcu_read_lock() region. + * + * All fields of the returned pool are accessible as long as the above + * mentioned locking is in effect. If the returned pool needs to be used + * beyond the critical section, the caller is responsible for ensuring the + * returned pool is and stays online. + * + * Return: The worker_pool @work was last associated with. %NULL if none. + */ +static struct worker_pool *get_work_pool(struct work_struct *work) +{ + unsigned long data = atomic_long_read(&work->data); + int pool_id; + + assert_rcu_or_pool_mutex(); + + if (data & WORK_STRUCT_PWQ) + return ((struct pool_workqueue *) + (data & WORK_STRUCT_WQ_DATA_MASK))->pool; + + pool_id = data >> WORK_OFFQ_POOL_SHIFT; + if (pool_id == WORK_OFFQ_POOL_NONE) + return NULL; + + return idr_find(&worker_pool_idr, pool_id); +} + +/** + * get_work_pool_id - return the worker pool ID a given work is associated with + * @work: the work item of interest + * + * Return: The worker_pool ID @work was last associated with. + * %WORK_OFFQ_POOL_NONE if none. + */ +static int get_work_pool_id(struct work_struct *work) +{ + unsigned long data = atomic_long_read(&work->data); + + if (data & WORK_STRUCT_PWQ) + return ((struct pool_workqueue *) + (data & WORK_STRUCT_WQ_DATA_MASK))->pool->id; + + return data >> WORK_OFFQ_POOL_SHIFT; +} + +static void mark_work_canceling(struct work_struct *work) +{ + unsigned long pool_id = get_work_pool_id(work); + + pool_id <<= WORK_OFFQ_POOL_SHIFT; + set_work_data(work, pool_id | WORK_OFFQ_CANCELING, WORK_STRUCT_PENDING); +} + +static bool work_is_canceling(struct work_struct *work) +{ + unsigned long data = atomic_long_read(&work->data); + + return !(data & WORK_STRUCT_PWQ) && (data & WORK_OFFQ_CANCELING); +} + +/* + * Policy functions. These define the policies on how the global worker + * pools are managed. Unless noted otherwise, these functions assume that + * they're being called with pool->lock held. + */ + +static bool __need_more_worker(struct worker_pool *pool) +{ + return !atomic_read(&pool->nr_running); +} + +/* + * Need to wake up a worker? Called from anything but currently + * running workers. + * + * Note that, because unbound workers never contribute to nr_running, this + * function will always return %true for unbound pools as long as the + * worklist isn't empty. + */ +static bool need_more_worker(struct worker_pool *pool) +{ + return !list_empty(&pool->worklist) && __need_more_worker(pool); +} + +/* Can I start working? Called from busy but !running workers. */ +static bool may_start_working(struct worker_pool *pool) +{ + return pool->nr_idle; +} + +/* Do I need to keep working? Called from currently running workers. */ +static bool keep_working(struct worker_pool *pool) +{ + return !list_empty(&pool->worklist) && + atomic_read(&pool->nr_running) <= 1; +} + +/* Do we need a new worker? Called from manager. */ +static bool need_to_create_worker(struct worker_pool *pool) +{ + return need_more_worker(pool) && !may_start_working(pool); +} + +/* Do we have too many workers and should some go away? */ +static bool too_many_workers(struct worker_pool *pool) +{ + bool managing = mutex_is_locked(&pool->manager_arb); + int nr_idle = pool->nr_idle + managing; /* manager is considered idle */ + int nr_busy = pool->nr_workers - nr_idle; + + return nr_idle > 2 && (nr_idle - 2) * MAX_IDLE_WORKERS_RATIO >= nr_busy; +} + +/* + * Wake up functions. + */ + +/* Return the first idle worker. Safe with preemption disabled */ +static struct worker *first_idle_worker(struct worker_pool *pool) +{ + if (unlikely(list_empty(&pool->idle_list))) + return NULL; + + return list_first_entry(&pool->idle_list, struct worker, entry); +} + +/** + * wake_up_worker - wake up an idle worker + * @pool: worker pool to wake worker from + * + * Wake up the first idle worker of @pool. + * + * CONTEXT: + * spin_lock_irq(pool->lock). + */ +static void wake_up_worker(struct worker_pool *pool) +{ + struct worker *worker; + + rt_lock_idle_list(pool); + + worker = first_idle_worker(pool); + + if (likely(worker)) + wake_up_process(worker->task); + + rt_unlock_idle_list(pool); +} + +/** + * wq_worker_running - a worker is running again + * @task: task returning from sleep + * + * This function is called when a worker returns from schedule() + */ +void wq_worker_running(struct task_struct *task) +{ + struct worker *worker = kthread_data(task); + + if (!worker->sleeping) + return; + if (!(worker->flags & WORKER_NOT_RUNNING)) + atomic_inc(&worker->pool->nr_running); + worker->sleeping = 0; +} + +/** + * wq_worker_sleeping - a worker is going to sleep + * @task: task going to sleep + * This function is called from schedule() when a busy worker is + * going to sleep. + */ +void wq_worker_sleeping(struct task_struct *task) +{ + struct worker *worker = kthread_data(task); + struct worker_pool *pool; + + /* + * Rescuers, which may not have all the fields set up like normal + * workers, also reach here, let's not access anything before + * checking NOT_RUNNING. + */ + if (worker->flags & WORKER_NOT_RUNNING) + return; + + pool = worker->pool; + + if (WARN_ON_ONCE(worker->sleeping)) + return; + + worker->sleeping = 1; + + /* + * The counterpart of the following dec_and_test, implied mb, + * worklist not empty test sequence is in insert_work(). + * Please read comment there. + */ + if (atomic_dec_and_test(&pool->nr_running) && + !list_empty(&pool->worklist)) { + sched_lock_idle_list(pool); + wake_up_worker(pool); + sched_unlock_idle_list(pool); + } +} + +/** + * worker_set_flags - set worker flags and adjust nr_running accordingly + * @worker: self + * @flags: flags to set + * + * Set @flags in @worker->flags and adjust nr_running accordingly. + * + * CONTEXT: + * spin_lock_irq(pool->lock) + */ +static inline void worker_set_flags(struct worker *worker, unsigned int flags) +{ + struct worker_pool *pool = worker->pool; + + WARN_ON_ONCE(worker->task != current); + + /* If transitioning into NOT_RUNNING, adjust nr_running. */ + if ((flags & WORKER_NOT_RUNNING) && + !(worker->flags & WORKER_NOT_RUNNING)) { + atomic_dec(&pool->nr_running); + } + + worker->flags |= flags; +} + +/** + * worker_clr_flags - clear worker flags and adjust nr_running accordingly + * @worker: self + * @flags: flags to clear + * + * Clear @flags in @worker->flags and adjust nr_running accordingly. + * + * CONTEXT: + * spin_lock_irq(pool->lock) + */ +static inline void worker_clr_flags(struct worker *worker, unsigned int flags) +{ + struct worker_pool *pool = worker->pool; + unsigned int oflags = worker->flags; + + WARN_ON_ONCE(worker->task != current); + + worker->flags &= ~flags; + + /* + * If transitioning out of NOT_RUNNING, increment nr_running. Note + * that the nested NOT_RUNNING is not a noop. NOT_RUNNING is mask + * of multiple flags, not a single flag. + */ + if ((flags & WORKER_NOT_RUNNING) && (oflags & WORKER_NOT_RUNNING)) + if (!(worker->flags & WORKER_NOT_RUNNING)) + atomic_inc(&pool->nr_running); +} + +/** + * find_worker_executing_work - find worker which is executing a work + * @pool: pool of interest + * @work: work to find worker for + * + * Find a worker which is executing @work on @pool by searching + * @pool->busy_hash which is keyed by the address of @work. For a worker + * to match, its current execution should match the address of @work and + * its work function. This is to avoid unwanted dependency between + * unrelated work executions through a work item being recycled while still + * being executed. + * + * This is a bit tricky. A work item may be freed once its execution + * starts and nothing prevents the freed area from being recycled for + * another work item. If the same work item address ends up being reused + * before the original execution finishes, workqueue will identify the + * recycled work item as currently executing and make it wait until the + * current execution finishes, introducing an unwanted dependency. + * + * This function checks the work item address and work function to avoid + * false positives. Note that this isn't complete as one may construct a + * work function which can introduce dependency onto itself through a + * recycled work item. Well, if somebody wants to shoot oneself in the + * foot that badly, there's only so much we can do, and if such deadlock + * actually occurs, it should be easy to locate the culprit work function. + * + * CONTEXT: + * spin_lock_irq(pool->lock). + * + * Return: + * Pointer to worker which is executing @work if found, %NULL + * otherwise. + */ +static struct worker *find_worker_executing_work(struct worker_pool *pool, + struct work_struct *work) +{ + struct worker *worker; + + hash_for_each_possible(pool->busy_hash, worker, hentry, + (unsigned long)work) + if (worker->current_work == work && + worker->current_func == work->func) + return worker; + + return NULL; +} + +/** + * move_linked_works - move linked works to a list + * @work: start of series of works to be scheduled + * @head: target list to append @work to + * @nextp: out paramter for nested worklist walking + * + * Schedule linked works starting from @work to @head. Work series to + * be scheduled starts at @work and includes any consecutive work with + * WORK_STRUCT_LINKED set in its predecessor. + * + * If @nextp is not NULL, it's updated to point to the next work of + * the last scheduled work. This allows move_linked_works() to be + * nested inside outer list_for_each_entry_safe(). + * + * CONTEXT: + * spin_lock_irq(pool->lock). + */ +static void move_linked_works(struct work_struct *work, struct list_head *head, + struct work_struct **nextp) +{ + struct work_struct *n; + + /* + * Linked worklist will always end before the end of the list, + * use NULL for list head. + */ + list_for_each_entry_safe_from(work, n, NULL, entry) { + list_move_tail(&work->entry, head); + if (!(*work_data_bits(work) & WORK_STRUCT_LINKED)) + break; + } + + /* + * If we're already inside safe list traversal and have moved + * multiple works to the scheduled queue, the next position + * needs to be updated. + */ + if (nextp) + *nextp = n; +} + +/** + * get_pwq - get an extra reference on the specified pool_workqueue + * @pwq: pool_workqueue to get + * + * Obtain an extra reference on @pwq. The caller should guarantee that + * @pwq has positive refcnt and be holding the matching pool->lock. + */ +static void get_pwq(struct pool_workqueue *pwq) +{ + lockdep_assert_held(&pwq->pool->lock); + WARN_ON_ONCE(pwq->refcnt <= 0); + pwq->refcnt++; +} + +/** + * put_pwq - put a pool_workqueue reference + * @pwq: pool_workqueue to put + * + * Drop a reference of @pwq. If its refcnt reaches zero, schedule its + * destruction. The caller should be holding the matching pool->lock. + */ +static void put_pwq(struct pool_workqueue *pwq) +{ + lockdep_assert_held(&pwq->pool->lock); + if (likely(--pwq->refcnt)) + return; + if (WARN_ON_ONCE(!(pwq->wq->flags & WQ_UNBOUND))) + return; + /* + * @pwq can't be released under pool->lock, bounce to + * pwq_unbound_release_workfn(). This never recurses on the same + * pool->lock as this path is taken only for unbound workqueues and + * the release work item is scheduled on a per-cpu workqueue. To + * avoid lockdep warning, unbound pool->locks are given lockdep + * subclass of 1 in get_unbound_pool(). + */ + schedule_work(&pwq->unbound_release_work); +} + +/** + * put_pwq_unlocked - put_pwq() with surrounding pool lock/unlock + * @pwq: pool_workqueue to put (can be %NULL) + * + * put_pwq() with locking. This function also allows %NULL @pwq. + */ +static void put_pwq_unlocked(struct pool_workqueue *pwq) +{ + if (pwq) { + /* + * As both pwqs and pools are RCU protected, the + * following lock operations are safe. + */ + local_spin_lock_irq(pendingb_lock, &pwq->pool->lock); + put_pwq(pwq); + local_spin_unlock_irq(pendingb_lock, &pwq->pool->lock); + } +} + +static void pwq_activate_delayed_work(struct work_struct *work) +{ + struct pool_workqueue *pwq = get_work_pwq(work); + + trace_workqueue_activate_work(work); + move_linked_works(work, &pwq->pool->worklist, NULL); + __clear_bit(WORK_STRUCT_DELAYED_BIT, work_data_bits(work)); + pwq->nr_active++; +} + +static void pwq_activate_first_delayed(struct pool_workqueue *pwq) +{ + struct work_struct *work = list_first_entry(&pwq->delayed_works, + struct work_struct, entry); + + pwq_activate_delayed_work(work); +} + +/** + * pwq_dec_nr_in_flight - decrement pwq's nr_in_flight + * @pwq: pwq of interest + * @color: color of work which left the queue + * + * A work either has completed or is removed from pending queue, + * decrement nr_in_flight of its pwq and handle workqueue flushing. + * + * CONTEXT: + * spin_lock_irq(pool->lock). + */ +static void pwq_dec_nr_in_flight(struct pool_workqueue *pwq, int color) +{ + /* uncolored work items don't participate in flushing or nr_active */ + if (color == WORK_NO_COLOR) + goto out_put; + + pwq->nr_in_flight[color]--; + + pwq->nr_active--; + if (!list_empty(&pwq->delayed_works)) { + /* one down, submit a delayed one */ + if (pwq->nr_active < pwq->max_active) + pwq_activate_first_delayed(pwq); + } + + /* is flush in progress and are we at the flushing tip? */ + if (likely(pwq->flush_color != color)) + goto out_put; + + /* are there still in-flight works? */ + if (pwq->nr_in_flight[color]) + goto out_put; + + /* this pwq is done, clear flush_color */ + pwq->flush_color = -1; + + /* + * If this was the last pwq, wake up the first flusher. It + * will handle the rest. + */ + if (atomic_dec_and_test(&pwq->wq->nr_pwqs_to_flush)) + complete(&pwq->wq->first_flusher->done); +out_put: + put_pwq(pwq); +} + +/** + * try_to_grab_pending - steal work item from worklist and disable irq + * @work: work item to steal + * @is_dwork: @work is a delayed_work + * @flags: place to store irq state + * + * Try to grab PENDING bit of @work. This function can handle @work in any + * stable state - idle, on timer or on worklist. + * + * Return: + * 1 if @work was pending and we successfully stole PENDING + * 0 if @work was idle and we claimed PENDING + * -EAGAIN if PENDING couldn't be grabbed at the moment, safe to busy-retry + * -ENOENT if someone else is canceling @work, this state may persist + * for arbitrarily long + * + * Note: + * On >= 0 return, the caller owns @work's PENDING bit. To avoid getting + * interrupted while holding PENDING and @work off queue, irq must be + * disabled on entry. This, combined with delayed_work->timer being + * irqsafe, ensures that we return -EAGAIN for finite short period of time. + * + * On successful return, >= 0, irq is disabled and the caller is + * responsible for releasing it using local_irq_restore(*@flags). + * + * This function is safe to call from any context including IRQ handler. + */ +static int try_to_grab_pending(struct work_struct *work, bool is_dwork, + unsigned long *flags) +{ + struct worker_pool *pool; + struct pool_workqueue *pwq; + + local_lock_irqsave(pendingb_lock, *flags); + + /* try to steal the timer if it exists */ + if (is_dwork) { + struct delayed_work *dwork = to_delayed_work(work); + + /* + * dwork->timer is irqsafe. If del_timer() fails, it's + * guaranteed that the timer is not queued anywhere and not + * running on the local CPU. + */ + if (likely(del_timer(&dwork->timer))) + return 1; + } + + /* try to claim PENDING the normal way */ + if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) + return 0; + + rcu_read_lock(); + /* + * The queueing is in progress, or it is already queued. Try to + * steal it from ->worklist without clearing WORK_STRUCT_PENDING. + */ + pool = get_work_pool(work); + if (!pool) + goto fail; + + spin_lock(&pool->lock); + /* + * work->data is guaranteed to point to pwq only while the work + * item is queued on pwq->wq, and both updating work->data to point + * to pwq on queueing and to pool on dequeueing are done under + * pwq->pool->lock. This in turn guarantees that, if work->data + * points to pwq which is associated with a locked pool, the work + * item is currently queued on that pool. + */ + pwq = get_work_pwq(work); + if (pwq && pwq->pool == pool) { + debug_work_deactivate(work); + + /* + * A delayed work item cannot be grabbed directly because + * it might have linked NO_COLOR work items which, if left + * on the delayed_list, will confuse pwq->nr_active + * management later on and cause stall. Make sure the work + * item is activated before grabbing. + */ + if (*work_data_bits(work) & WORK_STRUCT_DELAYED) + pwq_activate_delayed_work(work); + + list_del_init(&work->entry); + pwq_dec_nr_in_flight(pwq, get_work_color(work)); + + /* work->data points to pwq iff queued, point to pool */ + set_work_pool_and_keep_pending(work, pool->id); + + spin_unlock(&pool->lock); + rcu_read_unlock(); + return 1; + } + spin_unlock(&pool->lock); +fail: + rcu_read_unlock(); + local_unlock_irqrestore(pendingb_lock, *flags); + if (work_is_canceling(work)) + return -ENOENT; + cpu_chill(); + return -EAGAIN; +} + +/** + * insert_work - insert a work into a pool + * @pwq: pwq @work belongs to + * @work: work to insert + * @head: insertion point + * @extra_flags: extra WORK_STRUCT_* flags to set + * + * Insert @work which belongs to @pwq after @head. @extra_flags is or'd to + * work_struct flags. + * + * CONTEXT: + * spin_lock_irq(pool->lock). + */ +static void insert_work(struct pool_workqueue *pwq, struct work_struct *work, + struct list_head *head, unsigned int extra_flags) +{ + struct worker_pool *pool = pwq->pool; + + /* we own @work, set data and link */ + set_work_pwq(work, pwq, extra_flags); + list_add_tail(&work->entry, head); + get_pwq(pwq); + + /* + * Ensure either wq_worker_sleeping() sees the above + * list_add_tail() or we see zero nr_running to avoid workers lying + * around lazily while there are works to be processed. + */ + smp_mb(); + + if (__need_more_worker(pool)) + wake_up_worker(pool); +} + +/* + * Test whether @work is being queued from another work executing on the + * same workqueue. + */ +static bool is_chained_work(struct workqueue_struct *wq) +{ + struct worker *worker; + + worker = current_wq_worker(); + /* + * Return %true iff I'm a worker execuing a work item on @wq. If + * I'm @worker, it's safe to dereference it without locking. + */ + return worker && worker->current_pwq->wq == wq; +} + +static void __queue_work(int cpu, struct workqueue_struct *wq, + struct work_struct *work) +{ + struct pool_workqueue *pwq; + struct worker_pool *last_pool; + struct list_head *worklist; + unsigned int work_flags; + unsigned int req_cpu = cpu; + + /* + * While a work item is PENDING && off queue, a task trying to + * steal the PENDING will busy-loop waiting for it to either get + * queued or lose PENDING. Grabbing PENDING and queueing should + * happen with IRQ disabled. + */ + WARN_ON_ONCE_NONRT(!irqs_disabled()); + + debug_work_activate(work); + + /* if draining, only works from the same workqueue are allowed */ + if (unlikely(wq->flags & __WQ_DRAINING) && + WARN_ON_ONCE(!is_chained_work(wq))) + return; + + rcu_read_lock(); +retry: + if (req_cpu == WORK_CPU_UNBOUND) + cpu = raw_smp_processor_id(); + + /* pwq which will be used unless @work is executing elsewhere */ + if (!(wq->flags & WQ_UNBOUND)) + pwq = per_cpu_ptr(wq->cpu_pwqs, cpu); + else + pwq = unbound_pwq_by_node(wq, cpu_to_node(cpu)); + + /* + * If @work was previously on a different pool, it might still be + * running there, in which case the work needs to be queued on that + * pool to guarantee non-reentrancy. + */ + last_pool = get_work_pool(work); + if (last_pool && last_pool != pwq->pool) { + struct worker *worker; + + spin_lock(&last_pool->lock); + + worker = find_worker_executing_work(last_pool, work); + + if (worker && worker->current_pwq->wq == wq) { + pwq = worker->current_pwq; + } else { + /* meh... not running there, queue here */ + spin_unlock(&last_pool->lock); + spin_lock(&pwq->pool->lock); + } + } else { + spin_lock(&pwq->pool->lock); + } + + /* + * pwq is determined and locked. For unbound pools, we could have + * raced with pwq release and it could already be dead. If its + * refcnt is zero, repeat pwq selection. Note that pwqs never die + * without another pwq replacing it in the numa_pwq_tbl or while + * work items are executing on it, so the retrying is guaranteed to + * make forward-progress. + */ + if (unlikely(!pwq->refcnt)) { + if (wq->flags & WQ_UNBOUND) { + spin_unlock(&pwq->pool->lock); + cpu_relax(); + goto retry; + } + /* oops */ + WARN_ONCE(true, "workqueue: per-cpu pwq for %s on cpu%d has 0 refcnt", + wq->name, cpu); + } + + /* pwq determined, queue */ + trace_workqueue_queue_work(req_cpu, pwq, work); + + if (WARN_ON(!list_empty(&work->entry))) + goto out; + + pwq->nr_in_flight[pwq->work_color]++; + work_flags = work_color_to_flags(pwq->work_color); + + if (likely(pwq->nr_active < pwq->max_active)) { + trace_workqueue_activate_work(work); + pwq->nr_active++; + worklist = &pwq->pool->worklist; + } else { + work_flags |= WORK_STRUCT_DELAYED; + worklist = &pwq->delayed_works; + } + + insert_work(pwq, work, worklist, work_flags); + +out: + spin_unlock(&pwq->pool->lock); + rcu_read_unlock(); +} + +/** + * queue_work_on - queue work on specific cpu + * @cpu: CPU number to execute work on + * @wq: workqueue to use + * @work: work to queue + * + * We queue the work to a specific CPU, the caller must ensure it + * can't go away. + * + * Return: %false if @work was already on a queue, %true otherwise. + */ +bool queue_work_on(int cpu, struct workqueue_struct *wq, + struct work_struct *work) +{ + bool ret = false; + unsigned long flags; + + local_lock_irqsave(pendingb_lock,flags); + + if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) { + __queue_work(cpu, wq, work); + ret = true; + } + + local_unlock_irqrestore(pendingb_lock, flags); + return ret; +} +EXPORT_SYMBOL(queue_work_on); + +void delayed_work_timer_fn(unsigned long __data) +{ + struct delayed_work *dwork = (struct delayed_work *)__data; + + /* should have been called from irqsafe timer with irq already off */ + __queue_work(dwork->cpu, dwork->wq, &dwork->work); +} +EXPORT_SYMBOL(delayed_work_timer_fn); + +static void __queue_delayed_work(int cpu, struct workqueue_struct *wq, + struct delayed_work *dwork, unsigned long delay) +{ + struct timer_list *timer = &dwork->timer; + struct work_struct *work = &dwork->work; + + WARN_ON_ONCE(timer->function != delayed_work_timer_fn || + timer->data != (unsigned long)dwork); + WARN_ON_ONCE(timer_pending(timer)); + WARN_ON_ONCE(!list_empty(&work->entry)); + + /* + * If @delay is 0, queue @dwork->work immediately. This is for + * both optimization and correctness. The earliest @timer can + * expire is on the closest next tick and delayed_work users depend + * on that there's no such delay when @delay is 0. + */ + if (!delay) { + __queue_work(cpu, wq, &dwork->work); + return; + } + + timer_stats_timer_set_start_info(&dwork->timer); + + dwork->wq = wq; + dwork->cpu = cpu; + timer->expires = jiffies + delay; + + if (unlikely(cpu != WORK_CPU_UNBOUND)) + add_timer_on(timer, cpu); + else + add_timer(timer); +} + +/** + * queue_delayed_work_on - queue work on specific CPU after delay + * @cpu: CPU number to execute work on + * @wq: workqueue to use + * @dwork: work to queue + * @delay: number of jiffies to wait before queueing + * + * Return: %false if @work was already on a queue, %true otherwise. If + * @delay is zero and @dwork is idle, it will be scheduled for immediate + * execution. + */ +bool queue_delayed_work_on(int cpu, struct workqueue_struct *wq, + struct delayed_work *dwork, unsigned long delay) +{ + struct work_struct *work = &dwork->work; + bool ret = false; + unsigned long flags; + + /* read the comment in __queue_work() */ + local_lock_irqsave(pendingb_lock, flags); + + if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) { + __queue_delayed_work(cpu, wq, dwork, delay); + ret = true; + } + + local_unlock_irqrestore(pendingb_lock, flags); + return ret; +} +EXPORT_SYMBOL(queue_delayed_work_on); + +/** + * mod_delayed_work_on - modify delay of or queue a delayed work on specific CPU + * @cpu: CPU number to execute work on + * @wq: workqueue to use + * @dwork: work to queue + * @delay: number of jiffies to wait before queueing + * + * If @dwork is idle, equivalent to queue_delayed_work_on(); otherwise, + * modify @dwork's timer so that it expires after @delay. If @delay is + * zero, @work is guaranteed to be scheduled immediately regardless of its + * current state. + * + * Return: %false if @dwork was idle and queued, %true if @dwork was + * pending and its timer was modified. + * + * This function is safe to call from any context including IRQ handler. + * See try_to_grab_pending() for details. + */ +bool mod_delayed_work_on(int cpu, struct workqueue_struct *wq, + struct delayed_work *dwork, unsigned long delay) +{ + unsigned long flags; + int ret; + + do { + ret = try_to_grab_pending(&dwork->work, true, &flags); + } while (unlikely(ret == -EAGAIN)); + + if (likely(ret >= 0)) { + __queue_delayed_work(cpu, wq, dwork, delay); + local_unlock_irqrestore(pendingb_lock, flags); + } + + /* -ENOENT from try_to_grab_pending() becomes %true */ + return ret; +} +EXPORT_SYMBOL_GPL(mod_delayed_work_on); + +/** + * worker_enter_idle - enter idle state + * @worker: worker which is entering idle state + * + * @worker is entering idle state. Update stats and idle timer if + * necessary. + * + * LOCKING: + * spin_lock_irq(pool->lock). + */ +static void worker_enter_idle(struct worker *worker) +{ + struct worker_pool *pool = worker->pool; + + if (WARN_ON_ONCE(worker->flags & WORKER_IDLE) || + WARN_ON_ONCE(!list_empty(&worker->entry) && + (worker->hentry.next || worker->hentry.pprev))) + return; + + /* can't use worker_set_flags(), also called from create_worker() */ + worker->flags |= WORKER_IDLE; + pool->nr_idle++; + worker->last_active = jiffies; + + /* idle_list is LIFO */ + rt_lock_idle_list(pool); + list_add(&worker->entry, &pool->idle_list); + rt_unlock_idle_list(pool); + + if (too_many_workers(pool) && !timer_pending(&pool->idle_timer)) + mod_timer(&pool->idle_timer, jiffies + IDLE_WORKER_TIMEOUT); + + /* + * Sanity check nr_running. Because wq_unbind_fn() releases + * pool->lock between setting %WORKER_UNBOUND and zapping + * nr_running, the warning may trigger spuriously. Check iff + * unbind is not in progress. + */ + WARN_ON_ONCE(!(pool->flags & POOL_DISASSOCIATED) && + pool->nr_workers == pool->nr_idle && + atomic_read(&pool->nr_running)); +} + +/** + * worker_leave_idle - leave idle state + * @worker: worker which is leaving idle state + * + * @worker is leaving idle state. Update stats. + * + * LOCKING: + * spin_lock_irq(pool->lock). + */ +static void worker_leave_idle(struct worker *worker) +{ + struct worker_pool *pool = worker->pool; + + if (WARN_ON_ONCE(!(worker->flags & WORKER_IDLE))) + return; + worker_clr_flags(worker, WORKER_IDLE); + pool->nr_idle--; + rt_lock_idle_list(pool); + list_del_init(&worker->entry); + rt_unlock_idle_list(pool); +} + +static struct worker *alloc_worker(int node) +{ + struct worker *worker; + + worker = kzalloc_node(sizeof(*worker), GFP_KERNEL, node); + if (worker) { + INIT_LIST_HEAD(&worker->entry); + INIT_LIST_HEAD(&worker->scheduled); + INIT_LIST_HEAD(&worker->node); + /* on creation a worker is in !idle && prep state */ + worker->flags = WORKER_PREP; + } + return worker; +} + +/** + * worker_attach_to_pool() - attach a worker to a pool + * @worker: worker to be attached + * @pool: the target pool + * + * Attach @worker to @pool. Once attached, the %WORKER_UNBOUND flag and + * cpu-binding of @worker are kept coordinated with the pool across + * cpu-[un]hotplugs. + */ +static void worker_attach_to_pool(struct worker *worker, + struct worker_pool *pool) +{ + mutex_lock(&pool->attach_mutex); + + /* + * set_cpus_allowed_ptr() will fail if the cpumask doesn't have any + * online CPUs. It'll be re-applied when any of the CPUs come up. + */ + set_cpus_allowed_ptr(worker->task, pool->attrs->cpumask); + + /* + * The pool->attach_mutex ensures %POOL_DISASSOCIATED remains + * stable across this function. See the comments above the + * flag definition for details. + */ + if (pool->flags & POOL_DISASSOCIATED) + worker->flags |= WORKER_UNBOUND; + + list_add_tail(&worker->node, &pool->workers); + + mutex_unlock(&pool->attach_mutex); +} + +/** + * worker_detach_from_pool() - detach a worker from its pool + * @worker: worker which is attached to its pool + * @pool: the pool @worker is attached to + * + * Undo the attaching which had been done in worker_attach_to_pool(). The + * caller worker shouldn't access to the pool after detached except it has + * other reference to the pool. + */ +static void worker_detach_from_pool(struct worker *worker, + struct worker_pool *pool) +{ + struct completion *detach_completion = NULL; + + mutex_lock(&pool->attach_mutex); + list_del(&worker->node); + if (list_empty(&pool->workers)) + detach_completion = pool->detach_completion; + mutex_unlock(&pool->attach_mutex); + + /* clear leftover flags without pool->lock after it is detached */ + worker->flags &= ~(WORKER_UNBOUND | WORKER_REBOUND); + + if (detach_completion) + complete(detach_completion); +} + +/** + * create_worker - create a new workqueue worker + * @pool: pool the new worker will belong to + * + * Create and start a new worker which is attached to @pool. + * + * CONTEXT: + * Might sleep. Does GFP_KERNEL allocations. + * + * Return: + * Pointer to the newly created worker. + */ +static struct worker *create_worker(struct worker_pool *pool) +{ + struct worker *worker = NULL; + int id = -1; + char id_buf[16]; + + /* ID is needed to determine kthread name */ + id = ida_simple_get(&pool->worker_ida, 0, 0, GFP_KERNEL); + if (id < 0) + goto fail; + + worker = alloc_worker(pool->node); + if (!worker) + goto fail; + + worker->pool = pool; + worker->id = id; + + if (pool->cpu >= 0) + snprintf(id_buf, sizeof(id_buf), "%d:%d%s", pool->cpu, id, + pool->attrs->nice < 0 ? "H" : ""); + else + snprintf(id_buf, sizeof(id_buf), "u%d:%d", pool->id, id); + + worker->task = kthread_create_on_node(worker_thread, worker, pool->node, + "kworker/%s", id_buf); + if (IS_ERR(worker->task)) + goto fail; + + set_user_nice(worker->task, pool->attrs->nice); + + /* prevent userland from meddling with cpumask of workqueue workers */ + worker->task->flags |= PF_NO_SETAFFINITY; + + /* successful, attach the worker to the pool */ + worker_attach_to_pool(worker, pool); + + /* start the newly created worker */ + spin_lock_irq(&pool->lock); + worker->pool->nr_workers++; + worker_enter_idle(worker); + wake_up_process(worker->task); + spin_unlock_irq(&pool->lock); + + return worker; + +fail: + if (id >= 0) + ida_simple_remove(&pool->worker_ida, id); + kfree(worker); + return NULL; +} + +/** + * destroy_worker - destroy a workqueue worker + * @worker: worker to be destroyed + * + * Destroy @worker and adjust @pool stats accordingly. The worker should + * be idle. + * + * CONTEXT: + * spin_lock_irq(pool->lock). + */ +static void destroy_worker(struct worker *worker) +{ + struct worker_pool *pool = worker->pool; + + lockdep_assert_held(&pool->lock); + + /* sanity check frenzy */ + if (WARN_ON(worker->current_work) || + WARN_ON(!list_empty(&worker->scheduled)) || + WARN_ON(!(worker->flags & WORKER_IDLE))) + return; + + pool->nr_workers--; + pool->nr_idle--; + + rt_lock_idle_list(pool); + list_del_init(&worker->entry); + rt_unlock_idle_list(pool); + worker->flags |= WORKER_DIE; + wake_up_process(worker->task); +} + +static void idle_worker_timeout(unsigned long __pool) +{ + struct worker_pool *pool = (void *)__pool; + + spin_lock_irq(&pool->lock); + + while (too_many_workers(pool)) { + struct worker *worker; + unsigned long expires; + + /* idle_list is kept in LIFO order, check the last one */ + worker = list_entry(pool->idle_list.prev, struct worker, entry); + expires = worker->last_active + IDLE_WORKER_TIMEOUT; + + if (time_before(jiffies, expires)) { + mod_timer(&pool->idle_timer, expires); + break; + } + + destroy_worker(worker); + } + + spin_unlock_irq(&pool->lock); +} + +static void send_mayday(struct work_struct *work) +{ + struct pool_workqueue *pwq = get_work_pwq(work); + struct workqueue_struct *wq = pwq->wq; + + lockdep_assert_held(&wq_mayday_lock); + + if (!wq->rescuer) + return; + + /* mayday mayday mayday */ + if (list_empty(&pwq->mayday_node)) { + /* + * If @pwq is for an unbound wq, its base ref may be put at + * any time due to an attribute change. Pin @pwq until the + * rescuer is done with it. + */ + get_pwq(pwq); + list_add_tail(&pwq->mayday_node, &wq->maydays); + wake_up_process(wq->rescuer->task); + } +} + +static void pool_mayday_timeout(unsigned long __pool) +{ + struct worker_pool *pool = (void *)__pool; + struct work_struct *work; + + spin_lock_irq(&pool->lock); + spin_lock(&wq_mayday_lock); /* for wq->maydays */ + + if (need_to_create_worker(pool)) { + /* + * We've been trying to create a new worker but + * haven't been successful. We might be hitting an + * allocation deadlock. Send distress signals to + * rescuers. + */ + list_for_each_entry(work, &pool->worklist, entry) + send_mayday(work); + } + + spin_unlock(&wq_mayday_lock); + spin_unlock_irq(&pool->lock); + + mod_timer(&pool->mayday_timer, jiffies + MAYDAY_INTERVAL); +} + +/** + * maybe_create_worker - create a new worker if necessary + * @pool: pool to create a new worker for + * + * Create a new worker for @pool if necessary. @pool is guaranteed to + * have at least one idle worker on return from this function. If + * creating a new worker takes longer than MAYDAY_INTERVAL, mayday is + * sent to all rescuers with works scheduled on @pool to resolve + * possible allocation deadlock. + * + * On return, need_to_create_worker() is guaranteed to be %false and + * may_start_working() %true. + * + * LOCKING: + * spin_lock_irq(pool->lock) which may be released and regrabbed + * multiple times. Does GFP_KERNEL allocations. Called only from + * manager. + */ +static void maybe_create_worker(struct worker_pool *pool) +__releases(&pool->lock) +__acquires(&pool->lock) +{ +restart: + spin_unlock_irq(&pool->lock); + + /* if we don't make progress in MAYDAY_INITIAL_TIMEOUT, call for help */ + mod_timer(&pool->mayday_timer, jiffies + MAYDAY_INITIAL_TIMEOUT); + + while (true) { + if (create_worker(pool) || !need_to_create_worker(pool)) + break; + + schedule_timeout_interruptible(CREATE_COOLDOWN); + + if (!need_to_create_worker(pool)) + break; + } + + del_timer_sync(&pool->mayday_timer); + spin_lock_irq(&pool->lock); + /* + * This is necessary even after a new worker was just successfully + * created as @pool->lock was dropped and the new worker might have + * already become busy. + */ + if (need_to_create_worker(pool)) + goto restart; +} + +/** + * manage_workers - manage worker pool + * @worker: self + * + * Assume the manager role and manage the worker pool @worker belongs + * to. At any given time, there can be only zero or one manager per + * pool. The exclusion is handled automatically by this function. + * + * The caller can safely start processing works on false return. On + * true return, it's guaranteed that need_to_create_worker() is false + * and may_start_working() is true. + * + * CONTEXT: + * spin_lock_irq(pool->lock) which may be released and regrabbed + * multiple times. Does GFP_KERNEL allocations. + * + * Return: + * %false if the pool doesn't need management and the caller can safely + * start processing works, %true if management function was performed and + * the conditions that the caller verified before calling the function may + * no longer be true. + */ +static bool manage_workers(struct worker *worker) +{ + struct worker_pool *pool = worker->pool; + + /* + * Anyone who successfully grabs manager_arb wins the arbitration + * and becomes the manager. mutex_trylock() on pool->manager_arb + * failure while holding pool->lock reliably indicates that someone + * else is managing the pool and the worker which failed trylock + * can proceed to executing work items. This means that anyone + * grabbing manager_arb is responsible for actually performing + * manager duties. If manager_arb is grabbed and released without + * actual management, the pool may stall indefinitely. + */ + if (!mutex_trylock(&pool->manager_arb)) + return false; + pool->manager = worker; + + maybe_create_worker(pool); + + pool->manager = NULL; + mutex_unlock(&pool->manager_arb); + return true; +} + +/** + * process_one_work - process single work + * @worker: self + * @work: work to process + * + * Process @work. This function contains all the logics necessary to + * process a single work including synchronization against and + * interaction with other workers on the same cpu, queueing and + * flushing. As long as context requirement is met, any worker can + * call this function to process a work. + * + * CONTEXT: + * spin_lock_irq(pool->lock) which is released and regrabbed. + */ +static void process_one_work(struct worker *worker, struct work_struct *work) +__releases(&pool->lock) +__acquires(&pool->lock) +{ + struct pool_workqueue *pwq = get_work_pwq(work); + struct worker_pool *pool = worker->pool; + bool cpu_intensive = pwq->wq->flags & WQ_CPU_INTENSIVE; + int work_color; + struct worker *collision; +#ifdef CONFIG_LOCKDEP + /* + * It is permissible to free the struct work_struct from + * inside the function that is called from it, this we need to + * take into account for lockdep too. To avoid bogus "held + * lock freed" warnings as well as problems when looking into + * work->lockdep_map, make a copy and use that here. + */ + struct lockdep_map lockdep_map; + + lockdep_copy_map(&lockdep_map, &work->lockdep_map); +#endif + /* ensure we're on the correct CPU */ + WARN_ON_ONCE(!(pool->flags & POOL_DISASSOCIATED) && + raw_smp_processor_id() != pool->cpu); + + /* + * A single work shouldn't be executed concurrently by + * multiple workers on a single cpu. Check whether anyone is + * already processing the work. If so, defer the work to the + * currently executing one. + */ + collision = find_worker_executing_work(pool, work); + if (unlikely(collision)) { + move_linked_works(work, &collision->scheduled, NULL); + return; + } + + /* claim and dequeue */ + debug_work_deactivate(work); + hash_add(pool->busy_hash, &worker->hentry, (unsigned long)work); + worker->current_work = work; + worker->current_func = work->func; + worker->current_pwq = pwq; + work_color = get_work_color(work); + + list_del_init(&work->entry); + + /* + * CPU intensive works don't participate in concurrency management. + * They're the scheduler's responsibility. This takes @worker out + * of concurrency management and the next code block will chain + * execution of the pending work items. + */ + if (unlikely(cpu_intensive)) + worker_set_flags(worker, WORKER_CPU_INTENSIVE); + + /* + * Wake up another worker if necessary. The condition is always + * false for normal per-cpu workers since nr_running would always + * be >= 1 at this point. This is used to chain execution of the + * pending work items for WORKER_NOT_RUNNING workers such as the + * UNBOUND and CPU_INTENSIVE ones. + */ + if (need_more_worker(pool)) + wake_up_worker(pool); + + /* + * Record the last pool and clear PENDING which should be the last + * update to @work. Also, do this inside @pool->lock so that + * PENDING and queued state changes happen together while IRQ is + * disabled. + */ + set_work_pool_and_clear_pending(work, pool->id); + + spin_unlock_irq(&pool->lock); + + lock_map_acquire_read(&pwq->wq->lockdep_map); + lock_map_acquire(&lockdep_map); + trace_workqueue_execute_start(work); + worker->current_func(work); + /* + * While we must be careful to not use "work" after this, the trace + * point will only record its address. + */ + trace_workqueue_execute_end(work); + lock_map_release(&lockdep_map); + lock_map_release(&pwq->wq->lockdep_map); + + if (unlikely(in_atomic() || lockdep_depth(current) > 0)) { + pr_err("BUG: workqueue leaked lock or atomic: %s/0x%08x/%d\n" + " last function: %pf\n", + current->comm, preempt_count(), task_pid_nr(current), + worker->current_func); + debug_show_held_locks(current); + dump_stack(); + } + + /* + * The following prevents a kworker from hogging CPU on !PREEMPT + * kernels, where a requeueing work item waiting for something to + * happen could deadlock with stop_machine as such work item could + * indefinitely requeue itself while all other CPUs are trapped in + * stop_machine. At the same time, report a quiescent RCU state so + * the same condition doesn't freeze RCU. + */ + cond_resched_rcu_qs(); + + spin_lock_irq(&pool->lock); + + /* clear cpu intensive status */ + if (unlikely(cpu_intensive)) + worker_clr_flags(worker, WORKER_CPU_INTENSIVE); + + /* we're done with it, release */ + hash_del(&worker->hentry); + worker->current_work = NULL; + worker->current_func = NULL; + worker->current_pwq = NULL; + worker->desc_valid = false; + pwq_dec_nr_in_flight(pwq, work_color); +} + +/** + * process_scheduled_works - process scheduled works + * @worker: self + * + * Process all scheduled works. Please note that the scheduled list + * may change while processing a work, so this function repeatedly + * fetches a work from the top and executes it. + * + * CONTEXT: + * spin_lock_irq(pool->lock) which may be released and regrabbed + * multiple times. + */ +static void process_scheduled_works(struct worker *worker) +{ + while (!list_empty(&worker->scheduled)) { + struct work_struct *work = list_first_entry(&worker->scheduled, + struct work_struct, entry); + process_one_work(worker, work); + } +} + +/** + * worker_thread - the worker thread function + * @__worker: self + * + * The worker thread function. All workers belong to a worker_pool - + * either a per-cpu one or dynamic unbound one. These workers process all + * work items regardless of their specific target workqueue. The only + * exception is work items which belong to workqueues with a rescuer which + * will be explained in rescuer_thread(). + * + * Return: 0 + */ +static int worker_thread(void *__worker) +{ + struct worker *worker = __worker; + struct worker_pool *pool = worker->pool; + + /* tell the scheduler that this is a workqueue worker */ + worker->task->flags |= PF_WQ_WORKER; +woke_up: + spin_lock_irq(&pool->lock); + + /* am I supposed to die? */ + if (unlikely(worker->flags & WORKER_DIE)) { + spin_unlock_irq(&pool->lock); + WARN_ON_ONCE(!list_empty(&worker->entry)); + worker->task->flags &= ~PF_WQ_WORKER; + + set_task_comm(worker->task, "kworker/dying"); + ida_simple_remove(&pool->worker_ida, worker->id); + worker_detach_from_pool(worker, pool); + kfree(worker); + return 0; + } + + worker_leave_idle(worker); +recheck: + /* no more worker necessary? */ + if (!need_more_worker(pool)) + goto sleep; + + /* do we need to manage? */ + if (unlikely(!may_start_working(pool)) && manage_workers(worker)) + goto recheck; + + /* + * ->scheduled list can only be filled while a worker is + * preparing to process a work or actually processing it. + * Make sure nobody diddled with it while I was sleeping. + */ + WARN_ON_ONCE(!list_empty(&worker->scheduled)); + + /* + * Finish PREP stage. We're guaranteed to have at least one idle + * worker or that someone else has already assumed the manager + * role. This is where @worker starts participating in concurrency + * management if applicable and concurrency management is restored + * after being rebound. See rebind_workers() for details. + */ + worker_clr_flags(worker, WORKER_PREP | WORKER_REBOUND); + + do { + struct work_struct *work = + list_first_entry(&pool->worklist, + struct work_struct, entry); + + if (likely(!(*work_data_bits(work) & WORK_STRUCT_LINKED))) { + /* optimization path, not strictly necessary */ + process_one_work(worker, work); + if (unlikely(!list_empty(&worker->scheduled))) + process_scheduled_works(worker); + } else { + move_linked_works(work, &worker->scheduled, NULL); + process_scheduled_works(worker); + } + } while (keep_working(pool)); + + worker_set_flags(worker, WORKER_PREP); +sleep: + /* + * pool->lock is held and there's no work to process and no need to + * manage, sleep. Workers are woken up only while holding + * pool->lock or from local cpu, so setting the current state + * before releasing pool->lock is enough to prevent losing any + * event. + */ + worker_enter_idle(worker); + __set_current_state(TASK_INTERRUPTIBLE); + spin_unlock_irq(&pool->lock); + schedule(); + goto woke_up; +} + +/** + * rescuer_thread - the rescuer thread function + * @__rescuer: self + * + * Workqueue rescuer thread function. There's one rescuer for each + * workqueue which has WQ_MEM_RECLAIM set. + * + * Regular work processing on a pool may block trying to create a new + * worker which uses GFP_KERNEL allocation which has slight chance of + * developing into deadlock if some works currently on the same queue + * need to be processed to satisfy the GFP_KERNEL allocation. This is + * the problem rescuer solves. + * + * When such condition is possible, the pool summons rescuers of all + * workqueues which have works queued on the pool and let them process + * those works so that forward progress can be guaranteed. + * + * This should happen rarely. + * + * Return: 0 + */ +static int rescuer_thread(void *__rescuer) +{ + struct worker *rescuer = __rescuer; + struct workqueue_struct *wq = rescuer->rescue_wq; + struct list_head *scheduled = &rescuer->scheduled; + bool should_stop; + + set_user_nice(current, RESCUER_NICE_LEVEL); + + /* + * Mark rescuer as worker too. As WORKER_PREP is never cleared, it + * doesn't participate in concurrency management. + */ + rescuer->task->flags |= PF_WQ_WORKER; +repeat: + set_current_state(TASK_INTERRUPTIBLE); + + /* + * By the time the rescuer is requested to stop, the workqueue + * shouldn't have any work pending, but @wq->maydays may still have + * pwq(s) queued. This can happen by non-rescuer workers consuming + * all the work items before the rescuer got to them. Go through + * @wq->maydays processing before acting on should_stop so that the + * list is always empty on exit. + */ + should_stop = kthread_should_stop(); + + /* see whether any pwq is asking for help */ + spin_lock_irq(&wq_mayday_lock); + + while (!list_empty(&wq->maydays)) { + struct pool_workqueue *pwq = list_first_entry(&wq->maydays, + struct pool_workqueue, mayday_node); + struct worker_pool *pool = pwq->pool; + struct work_struct *work, *n; + + __set_current_state(TASK_RUNNING); + list_del_init(&pwq->mayday_node); + + spin_unlock_irq(&wq_mayday_lock); + + worker_attach_to_pool(rescuer, pool); + + spin_lock_irq(&pool->lock); + rescuer->pool = pool; + + /* + * Slurp in all works issued via this workqueue and + * process'em. + */ + WARN_ON_ONCE(!list_empty(scheduled)); + list_for_each_entry_safe(work, n, &pool->worklist, entry) + if (get_work_pwq(work) == pwq) + move_linked_works(work, scheduled, &n); + + if (!list_empty(scheduled)) { + process_scheduled_works(rescuer); + + /* + * The above execution of rescued work items could + * have created more to rescue through + * pwq_activate_first_delayed() or chained + * queueing. Let's put @pwq back on mayday list so + * that such back-to-back work items, which may be + * being used to relieve memory pressure, don't + * incur MAYDAY_INTERVAL delay inbetween. + */ + if (need_to_create_worker(pool)) { + spin_lock(&wq_mayday_lock); + get_pwq(pwq); + list_move_tail(&pwq->mayday_node, &wq->maydays); + spin_unlock(&wq_mayday_lock); + } + } + + /* + * Put the reference grabbed by send_mayday(). @pool won't + * go away while we're still attached to it. + */ + put_pwq(pwq); + + /* + * Leave this pool. If need_more_worker() is %true, notify a + * regular worker; otherwise, we end up with 0 concurrency + * and stalling the execution. + */ + if (need_more_worker(pool)) + wake_up_worker(pool); + + rescuer->pool = NULL; + spin_unlock_irq(&pool->lock); + + worker_detach_from_pool(rescuer, pool); + + spin_lock_irq(&wq_mayday_lock); + } + + spin_unlock_irq(&wq_mayday_lock); + + if (should_stop) { + __set_current_state(TASK_RUNNING); + rescuer->task->flags &= ~PF_WQ_WORKER; + return 0; + } + + /* rescuers should never participate in concurrency management */ + WARN_ON_ONCE(!(rescuer->flags & WORKER_NOT_RUNNING)); + schedule(); + goto repeat; +} + +struct wq_barrier { + struct work_struct work; + struct completion done; + struct task_struct *task; /* purely informational */ +}; + +static void wq_barrier_func(struct work_struct *work) +{ + struct wq_barrier *barr = container_of(work, struct wq_barrier, work); + complete(&barr->done); +} + +/** + * insert_wq_barrier - insert a barrier work + * @pwq: pwq to insert barrier into + * @barr: wq_barrier to insert + * @target: target work to attach @barr to + * @worker: worker currently executing @target, NULL if @target is not executing + * + * @barr is linked to @target such that @barr is completed only after + * @target finishes execution. Please note that the ordering + * guarantee is observed only with respect to @target and on the local + * cpu. + * + * Currently, a queued barrier can't be canceled. This is because + * try_to_grab_pending() can't determine whether the work to be + * grabbed is at the head of the queue and thus can't clear LINKED + * flag of the previous work while there must be a valid next work + * after a work with LINKED flag set. + * + * Note that when @worker is non-NULL, @target may be modified + * underneath us, so we can't reliably determine pwq from @target. + * + * CONTEXT: + * spin_lock_irq(pool->lock). + */ +static void insert_wq_barrier(struct pool_workqueue *pwq, + struct wq_barrier *barr, + struct work_struct *target, struct worker *worker) +{ + struct list_head *head; + unsigned int linked = 0; + + /* + * debugobject calls are safe here even with pool->lock locked + * as we know for sure that this will not trigger any of the + * checks and call back into the fixup functions where we + * might deadlock. + */ + INIT_WORK_ONSTACK(&barr->work, wq_barrier_func); + __set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(&barr->work)); + init_completion(&barr->done); + barr->task = current; + + /* + * If @target is currently being executed, schedule the + * barrier to the worker; otherwise, put it after @target. + */ + if (worker) + head = worker->scheduled.next; + else { + unsigned long *bits = work_data_bits(target); + + head = target->entry.next; + /* there can already be other linked works, inherit and set */ + linked = *bits & WORK_STRUCT_LINKED; + __set_bit(WORK_STRUCT_LINKED_BIT, bits); + } + + debug_work_activate(&barr->work); + insert_work(pwq, &barr->work, head, + work_color_to_flags(WORK_NO_COLOR) | linked); +} + +/** + * flush_workqueue_prep_pwqs - prepare pwqs for workqueue flushing + * @wq: workqueue being flushed + * @flush_color: new flush color, < 0 for no-op + * @work_color: new work color, < 0 for no-op + * + * Prepare pwqs for workqueue flushing. + * + * If @flush_color is non-negative, flush_color on all pwqs should be + * -1. If no pwq has in-flight commands at the specified color, all + * pwq->flush_color's stay at -1 and %false is returned. If any pwq + * has in flight commands, its pwq->flush_color is set to + * @flush_color, @wq->nr_pwqs_to_flush is updated accordingly, pwq + * wakeup logic is armed and %true is returned. + * + * The caller should have initialized @wq->first_flusher prior to + * calling this function with non-negative @flush_color. If + * @flush_color is negative, no flush color update is done and %false + * is returned. + * + * If @work_color is non-negative, all pwqs should have the same + * work_color which is previous to @work_color and all will be + * advanced to @work_color. + * + * CONTEXT: + * mutex_lock(wq->mutex). + * + * Return: + * %true if @flush_color >= 0 and there's something to flush. %false + * otherwise. + */ +static bool flush_workqueue_prep_pwqs(struct workqueue_struct *wq, + int flush_color, int work_color) +{ + bool wait = false; + struct pool_workqueue *pwq; + + if (flush_color >= 0) { + WARN_ON_ONCE(atomic_read(&wq->nr_pwqs_to_flush)); + atomic_set(&wq->nr_pwqs_to_flush, 1); + } + + for_each_pwq(pwq, wq) { + struct worker_pool *pool = pwq->pool; + + spin_lock_irq(&pool->lock); + + if (flush_color >= 0) { + WARN_ON_ONCE(pwq->flush_color != -1); + + if (pwq->nr_in_flight[flush_color]) { + pwq->flush_color = flush_color; + atomic_inc(&wq->nr_pwqs_to_flush); + wait = true; + } + } + + if (work_color >= 0) { + WARN_ON_ONCE(work_color != work_next_color(pwq->work_color)); + pwq->work_color = work_color; + } + + spin_unlock_irq(&pool->lock); + } + + if (flush_color >= 0 && atomic_dec_and_test(&wq->nr_pwqs_to_flush)) + complete(&wq->first_flusher->done); + + return wait; +} + +/** + * flush_workqueue - ensure that any scheduled work has run to completion. + * @wq: workqueue to flush + * + * This function sleeps until all work items which were queued on entry + * have finished execution, but it is not livelocked by new incoming ones. + */ +void flush_workqueue(struct workqueue_struct *wq) +{ + struct wq_flusher this_flusher = { + .list = LIST_HEAD_INIT(this_flusher.list), + .flush_color = -1, + .done = COMPLETION_INITIALIZER_ONSTACK(this_flusher.done), + }; + int next_color; + + lock_map_acquire(&wq->lockdep_map); + lock_map_release(&wq->lockdep_map); + + mutex_lock(&wq->mutex); + + /* + * Start-to-wait phase + */ + next_color = work_next_color(wq->work_color); + + if (next_color != wq->flush_color) { + /* + * Color space is not full. The current work_color + * becomes our flush_color and work_color is advanced + * by one. + */ + WARN_ON_ONCE(!list_empty(&wq->flusher_overflow)); + this_flusher.flush_color = wq->work_color; + wq->work_color = next_color; + + if (!wq->first_flusher) { + /* no flush in progress, become the first flusher */ + WARN_ON_ONCE(wq->flush_color != this_flusher.flush_color); + + wq->first_flusher = &this_flusher; + + if (!flush_workqueue_prep_pwqs(wq, wq->flush_color, + wq->work_color)) { + /* nothing to flush, done */ + wq->flush_color = next_color; + wq->first_flusher = NULL; + goto out_unlock; + } + } else { + /* wait in queue */ + WARN_ON_ONCE(wq->flush_color == this_flusher.flush_color); + list_add_tail(&this_flusher.list, &wq->flusher_queue); + flush_workqueue_prep_pwqs(wq, -1, wq->work_color); + } + } else { + /* + * Oops, color space is full, wait on overflow queue. + * The next flush completion will assign us + * flush_color and transfer to flusher_queue. + */ + list_add_tail(&this_flusher.list, &wq->flusher_overflow); + } + + mutex_unlock(&wq->mutex); + + wait_for_completion(&this_flusher.done); + + /* + * Wake-up-and-cascade phase + * + * First flushers are responsible for cascading flushes and + * handling overflow. Non-first flushers can simply return. + */ + if (wq->first_flusher != &this_flusher) + return; + + mutex_lock(&wq->mutex); + + /* we might have raced, check again with mutex held */ + if (wq->first_flusher != &this_flusher) + goto out_unlock; + + wq->first_flusher = NULL; + + WARN_ON_ONCE(!list_empty(&this_flusher.list)); + WARN_ON_ONCE(wq->flush_color != this_flusher.flush_color); + + while (true) { + struct wq_flusher *next, *tmp; + + /* complete all the flushers sharing the current flush color */ + list_for_each_entry_safe(next, tmp, &wq->flusher_queue, list) { + if (next->flush_color != wq->flush_color) + break; + list_del_init(&next->list); + complete(&next->done); + } + + WARN_ON_ONCE(!list_empty(&wq->flusher_overflow) && + wq->flush_color != work_next_color(wq->work_color)); + + /* this flush_color is finished, advance by one */ + wq->flush_color = work_next_color(wq->flush_color); + + /* one color has been freed, handle overflow queue */ + if (!list_empty(&wq->flusher_overflow)) { + /* + * Assign the same color to all overflowed + * flushers, advance work_color and append to + * flusher_queue. This is the start-to-wait + * phase for these overflowed flushers. + */ + list_for_each_entry(tmp, &wq->flusher_overflow, list) + tmp->flush_color = wq->work_color; + + wq->work_color = work_next_color(wq->work_color); + + list_splice_tail_init(&wq->flusher_overflow, + &wq->flusher_queue); + flush_workqueue_prep_pwqs(wq, -1, wq->work_color); + } + + if (list_empty(&wq->flusher_queue)) { + WARN_ON_ONCE(wq->flush_color != wq->work_color); + break; + } + + /* + * Need to flush more colors. Make the next flusher + * the new first flusher and arm pwqs. + */ + WARN_ON_ONCE(wq->flush_color == wq->work_color); + WARN_ON_ONCE(wq->flush_color != next->flush_color); + + list_del_init(&next->list); + wq->first_flusher = next; + + if (flush_workqueue_prep_pwqs(wq, wq->flush_color, -1)) + break; + + /* + * Meh... this color is already done, clear first + * flusher and repeat cascading. + */ + wq->first_flusher = NULL; + } + +out_unlock: + mutex_unlock(&wq->mutex); +} +EXPORT_SYMBOL_GPL(flush_workqueue); + +/** + * drain_workqueue - drain a workqueue + * @wq: workqueue to drain + * + * Wait until the workqueue becomes empty. While draining is in progress, + * only chain queueing is allowed. IOW, only currently pending or running + * work items on @wq can queue further work items on it. @wq is flushed + * repeatedly until it becomes empty. The number of flushing is detemined + * by the depth of chaining and should be relatively short. Whine if it + * takes too long. + */ +void drain_workqueue(struct workqueue_struct *wq) +{ + unsigned int flush_cnt = 0; + struct pool_workqueue *pwq; + + /* + * __queue_work() needs to test whether there are drainers, is much + * hotter than drain_workqueue() and already looks at @wq->flags. + * Use __WQ_DRAINING so that queue doesn't have to check nr_drainers. + */ + mutex_lock(&wq->mutex); + if (!wq->nr_drainers++) + wq->flags |= __WQ_DRAINING; + mutex_unlock(&wq->mutex); +reflush: + flush_workqueue(wq); + + mutex_lock(&wq->mutex); + + for_each_pwq(pwq, wq) { + bool drained; + + spin_lock_irq(&pwq->pool->lock); + drained = !pwq->nr_active && list_empty(&pwq->delayed_works); + spin_unlock_irq(&pwq->pool->lock); + + if (drained) + continue; + + if (++flush_cnt == 10 || + (flush_cnt % 100 == 0 && flush_cnt <= 1000)) + pr_warn("workqueue %s: drain_workqueue() isn't complete after %u tries\n", + wq->name, flush_cnt); + + mutex_unlock(&wq->mutex); + goto reflush; + } + + if (!--wq->nr_drainers) + wq->flags &= ~__WQ_DRAINING; + mutex_unlock(&wq->mutex); +} +EXPORT_SYMBOL_GPL(drain_workqueue); + +static bool start_flush_work(struct work_struct *work, struct wq_barrier *barr) +{ + struct worker *worker = NULL; + struct worker_pool *pool; + struct pool_workqueue *pwq; + + might_sleep(); + + rcu_read_lock(); + pool = get_work_pool(work); + if (!pool) { + rcu_read_unlock(); + return false; + } + + spin_lock_irq(&pool->lock); + /* see the comment in try_to_grab_pending() with the same code */ + pwq = get_work_pwq(work); + if (pwq) { + if (unlikely(pwq->pool != pool)) + goto already_gone; + } else { + worker = find_worker_executing_work(pool, work); + if (!worker) + goto already_gone; + pwq = worker->current_pwq; + } + + insert_wq_barrier(pwq, barr, work, worker); + spin_unlock_irq(&pool->lock); + + /* + * If @max_active is 1 or rescuer is in use, flushing another work + * item on the same workqueue may lead to deadlock. Make sure the + * flusher is not running on the same workqueue by verifying write + * access. + */ + if (pwq->wq->saved_max_active == 1 || pwq->wq->rescuer) + lock_map_acquire(&pwq->wq->lockdep_map); + else + lock_map_acquire_read(&pwq->wq->lockdep_map); + lock_map_release(&pwq->wq->lockdep_map); + rcu_read_unlock(); + return true; +already_gone: + spin_unlock_irq(&pool->lock); + rcu_read_unlock(); + return false; +} + +/** + * flush_work - wait for a work to finish executing the last queueing instance + * @work: the work to flush + * + * Wait until @work has finished execution. @work is guaranteed to be idle + * on return if it hasn't been requeued since flush started. + * + * Return: + * %true if flush_work() waited for the work to finish execution, + * %false if it was already idle. + */ +bool flush_work(struct work_struct *work) +{ + struct wq_barrier barr; + + lock_map_acquire(&work->lockdep_map); + lock_map_release(&work->lockdep_map); + + if (start_flush_work(work, &barr)) { + wait_for_completion(&barr.done); + destroy_work_on_stack(&barr.work); + return true; + } else { + return false; + } +} +EXPORT_SYMBOL_GPL(flush_work); + +struct cwt_wait { + wait_queue_t wait; + struct work_struct *work; +}; + +static int cwt_wakefn(wait_queue_t *wait, unsigned mode, int sync, void *key) +{ + struct cwt_wait *cwait = container_of(wait, struct cwt_wait, wait); + + if (cwait->work != key) + return 0; + return autoremove_wake_function(wait, mode, sync, key); +} + +static bool __cancel_work_timer(struct work_struct *work, bool is_dwork) +{ + static DECLARE_WAIT_QUEUE_HEAD(cancel_waitq); + unsigned long flags; + int ret; + + do { + ret = try_to_grab_pending(work, is_dwork, &flags); + /* + * If someone else is already canceling, wait for it to + * finish. flush_work() doesn't work for PREEMPT_NONE + * because we may get scheduled between @work's completion + * and the other canceling task resuming and clearing + * CANCELING - flush_work() will return false immediately + * as @work is no longer busy, try_to_grab_pending() will + * return -ENOENT as @work is still being canceled and the + * other canceling task won't be able to clear CANCELING as + * we're hogging the CPU. + * + * Let's wait for completion using a waitqueue. As this + * may lead to the thundering herd problem, use a custom + * wake function which matches @work along with exclusive + * wait and wakeup. + */ + if (unlikely(ret == -ENOENT)) { + struct cwt_wait cwait; + + init_wait(&cwait.wait); + cwait.wait.func = cwt_wakefn; + cwait.work = work; + + prepare_to_wait_exclusive(&cancel_waitq, &cwait.wait, + TASK_UNINTERRUPTIBLE); + if (work_is_canceling(work)) + schedule(); + finish_wait(&cancel_waitq, &cwait.wait); + } + } while (unlikely(ret < 0)); + + /* tell other tasks trying to grab @work to back off */ + mark_work_canceling(work); + local_unlock_irqrestore(pendingb_lock, flags); + + flush_work(work); + clear_work_data(work); + + /* + * Paired with prepare_to_wait() above so that either + * waitqueue_active() is visible here or !work_is_canceling() is + * visible there. + */ + smp_mb(); + if (waitqueue_active(&cancel_waitq)) + __wake_up(&cancel_waitq, TASK_NORMAL, 1, work); + + return ret; +} + +/** + * cancel_work_sync - cancel a work and wait for it to finish + * @work: the work to cancel + * + * Cancel @work and wait for its execution to finish. This function + * can be used even if the work re-queues itself or migrates to + * another workqueue. On return from this function, @work is + * guaranteed to be not pending or executing on any CPU. + * + * cancel_work_sync(&delayed_work->work) must not be used for + * delayed_work's. Use cancel_delayed_work_sync() instead. + * + * The caller must ensure that the workqueue on which @work was last + * queued can't be destroyed before this function returns. + * + * Return: + * %true if @work was pending, %false otherwise. + */ +bool cancel_work_sync(struct work_struct *work) +{ + return __cancel_work_timer(work, false); +} +EXPORT_SYMBOL_GPL(cancel_work_sync); + +/** + * flush_delayed_work - wait for a dwork to finish executing the last queueing + * @dwork: the delayed work to flush + * + * Delayed timer is cancelled and the pending work is queued for + * immediate execution. Like flush_work(), this function only + * considers the last queueing instance of @dwork. + * + * Return: + * %true if flush_work() waited for the work to finish execution, + * %false if it was already idle. + */ +bool flush_delayed_work(struct delayed_work *dwork) +{ + local_lock_irq(pendingb_lock); + if (del_timer_sync(&dwork->timer)) + __queue_work(dwork->cpu, dwork->wq, &dwork->work); + local_unlock_irq(pendingb_lock); + return flush_work(&dwork->work); +} +EXPORT_SYMBOL(flush_delayed_work); + +/** + * cancel_delayed_work - cancel a delayed work + * @dwork: delayed_work to cancel + * + * Kill off a pending delayed_work. + * + * Return: %true if @dwork was pending and canceled; %false if it wasn't + * pending. + * + * Note: + * The work callback function may still be running on return, unless + * it returns %true and the work doesn't re-arm itself. Explicitly flush or + * use cancel_delayed_work_sync() to wait on it. + * + * This function is safe to call from any context including IRQ handler. + */ +bool cancel_delayed_work(struct delayed_work *dwork) +{ + unsigned long flags; + int ret; + + do { + ret = try_to_grab_pending(&dwork->work, true, &flags); + } while (unlikely(ret == -EAGAIN)); + + if (unlikely(ret < 0)) + return false; + + set_work_pool_and_clear_pending(&dwork->work, + get_work_pool_id(&dwork->work)); + local_unlock_irqrestore(pendingb_lock, flags); + return ret; +} +EXPORT_SYMBOL(cancel_delayed_work); + +/** + * cancel_delayed_work_sync - cancel a delayed work and wait for it to finish + * @dwork: the delayed work cancel + * + * This is cancel_work_sync() for delayed works. + * + * Return: + * %true if @dwork was pending, %false otherwise. + */ +bool cancel_delayed_work_sync(struct delayed_work *dwork) +{ + return __cancel_work_timer(&dwork->work, true); +} +EXPORT_SYMBOL(cancel_delayed_work_sync); + +/** + * schedule_on_each_cpu - execute a function synchronously on each online CPU + * @func: the function to call + * + * schedule_on_each_cpu() executes @func on each online CPU using the + * system workqueue and blocks until all CPUs have completed. + * schedule_on_each_cpu() is very slow. + * + * Return: + * 0 on success, -errno on failure. + */ +int schedule_on_each_cpu(work_func_t func) +{ + int cpu; + struct work_struct __percpu *works; + + works = alloc_percpu(struct work_struct); + if (!works) + return -ENOMEM; + + get_online_cpus(); + + for_each_online_cpu(cpu) { + struct work_struct *work = per_cpu_ptr(works, cpu); + + INIT_WORK(work, func); + schedule_work_on(cpu, work); + } + + for_each_online_cpu(cpu) + flush_work(per_cpu_ptr(works, cpu)); + + put_online_cpus(); + free_percpu(works); + return 0; +} + +/** + * flush_scheduled_work - ensure that any scheduled work has run to completion. + * + * Forces execution of the kernel-global workqueue and blocks until its + * completion. + * + * Think twice before calling this function! It's very easy to get into + * trouble if you don't take great care. Either of the following situations + * will lead to deadlock: + * + * One of the work items currently on the workqueue needs to acquire + * a lock held by your code or its caller. + * + * Your code is running in the context of a work routine. + * + * They will be detected by lockdep when they occur, but the first might not + * occur very often. It depends on what work items are on the workqueue and + * what locks they need, which you have no control over. + * + * In most situations flushing the entire workqueue is overkill; you merely + * need to know that a particular work item isn't queued and isn't running. + * In such cases you should use cancel_delayed_work_sync() or + * cancel_work_sync() instead. + */ +void flush_scheduled_work(void) +{ + flush_workqueue(system_wq); +} +EXPORT_SYMBOL(flush_scheduled_work); + +/** + * execute_in_process_context - reliably execute the routine with user context + * @fn: the function to execute + * @ew: guaranteed storage for the execute work structure (must + * be available when the work executes) + * + * Executes the function immediately if process context is available, + * otherwise schedules the function for delayed execution. + * + * Return: 0 - function was executed + * 1 - function was scheduled for execution + */ +int execute_in_process_context(work_func_t fn, struct execute_work *ew) +{ + if (!in_interrupt()) { + fn(&ew->work); + return 0; + } + + INIT_WORK(&ew->work, fn); + schedule_work(&ew->work); + + return 1; +} +EXPORT_SYMBOL_GPL(execute_in_process_context); + +/** + * free_workqueue_attrs - free a workqueue_attrs + * @attrs: workqueue_attrs to free + * + * Undo alloc_workqueue_attrs(). + */ +void free_workqueue_attrs(struct workqueue_attrs *attrs) +{ + if (attrs) { + free_cpumask_var(attrs->cpumask); + kfree(attrs); + } +} + +/** + * alloc_workqueue_attrs - allocate a workqueue_attrs + * @gfp_mask: allocation mask to use + * + * Allocate a new workqueue_attrs, initialize with default settings and + * return it. + * + * Return: The allocated new workqueue_attr on success. %NULL on failure. + */ +struct workqueue_attrs *alloc_workqueue_attrs(gfp_t gfp_mask) +{ + struct workqueue_attrs *attrs; + + attrs = kzalloc(sizeof(*attrs), gfp_mask); + if (!attrs) + goto fail; + if (!alloc_cpumask_var(&attrs->cpumask, gfp_mask)) + goto fail; + + cpumask_copy(attrs->cpumask, cpu_possible_mask); + return attrs; +fail: + free_workqueue_attrs(attrs); + return NULL; +} + +static void copy_workqueue_attrs(struct workqueue_attrs *to, + const struct workqueue_attrs *from) +{ + to->nice = from->nice; + cpumask_copy(to->cpumask, from->cpumask); + /* + * Unlike hash and equality test, this function doesn't ignore + * ->no_numa as it is used for both pool and wq attrs. Instead, + * get_unbound_pool() explicitly clears ->no_numa after copying. + */ + to->no_numa = from->no_numa; +} + +/* hash value of the content of @attr */ +static u32 wqattrs_hash(const struct workqueue_attrs *attrs) +{ + u32 hash = 0; + + hash = jhash_1word(attrs->nice, hash); + hash = jhash(cpumask_bits(attrs->cpumask), + BITS_TO_LONGS(nr_cpumask_bits) * sizeof(long), hash); + return hash; +} + +/* content equality test */ +static bool wqattrs_equal(const struct workqueue_attrs *a, + const struct workqueue_attrs *b) +{ + if (a->nice != b->nice) + return false; + if (!cpumask_equal(a->cpumask, b->cpumask)) + return false; + return true; +} + +/** + * init_worker_pool - initialize a newly zalloc'd worker_pool + * @pool: worker_pool to initialize + * + * Initiailize a newly zalloc'd @pool. It also allocates @pool->attrs. + * + * Return: 0 on success, -errno on failure. Even on failure, all fields + * inside @pool proper are initialized and put_unbound_pool() can be called + * on @pool safely to release it. + */ +static int init_worker_pool(struct worker_pool *pool) +{ + spin_lock_init(&pool->lock); + pool->id = -1; + pool->cpu = -1; + pool->node = NUMA_NO_NODE; + pool->flags |= POOL_DISASSOCIATED; + INIT_LIST_HEAD(&pool->worklist); + INIT_LIST_HEAD(&pool->idle_list); + hash_init(pool->busy_hash); + + init_timer_deferrable(&pool->idle_timer); + pool->idle_timer.function = idle_worker_timeout; + pool->idle_timer.data = (unsigned long)pool; + + setup_timer(&pool->mayday_timer, pool_mayday_timeout, + (unsigned long)pool); + + mutex_init(&pool->manager_arb); + mutex_init(&pool->attach_mutex); + INIT_LIST_HEAD(&pool->workers); + + ida_init(&pool->worker_ida); + INIT_HLIST_NODE(&pool->hash_node); + pool->refcnt = 1; + + /* shouldn't fail above this point */ + pool->attrs = alloc_workqueue_attrs(GFP_KERNEL); + if (!pool->attrs) + return -ENOMEM; + return 0; +} + +static void rcu_free_wq(struct rcu_head *rcu) +{ + struct workqueue_struct *wq = + container_of(rcu, struct workqueue_struct, rcu); + + if (!(wq->flags & WQ_UNBOUND)) + free_percpu(wq->cpu_pwqs); + else + free_workqueue_attrs(wq->unbound_attrs); + + kfree(wq->rescuer); + kfree(wq); +} + +static void rcu_free_pool(struct rcu_head *rcu) +{ + struct worker_pool *pool = container_of(rcu, struct worker_pool, rcu); + + ida_destroy(&pool->worker_ida); + free_workqueue_attrs(pool->attrs); + kfree(pool); +} + +/** + * put_unbound_pool - put a worker_pool + * @pool: worker_pool to put + * + * Put @pool. If its refcnt reaches zero, it gets destroyed in RCU + * safe manner. get_unbound_pool() calls this function on its failure path + * and this function should be able to release pools which went through, + * successfully or not, init_worker_pool(). + * + * Should be called with wq_pool_mutex held. + */ +static void put_unbound_pool(struct worker_pool *pool) +{ + DECLARE_COMPLETION_ONSTACK(detach_completion); + struct worker *worker; + + lockdep_assert_held(&wq_pool_mutex); + + if (--pool->refcnt) + return; + + /* sanity checks */ + if (WARN_ON(!(pool->cpu < 0)) || + WARN_ON(!list_empty(&pool->worklist))) + return; + + /* release id and unhash */ + if (pool->id >= 0) + idr_remove(&worker_pool_idr, pool->id); + hash_del(&pool->hash_node); + + /* + * Become the manager and destroy all workers. Grabbing + * manager_arb prevents @pool's workers from blocking on + * attach_mutex. + */ + mutex_lock(&pool->manager_arb); + + spin_lock_irq(&pool->lock); + while ((worker = first_idle_worker(pool))) + destroy_worker(worker); + WARN_ON(pool->nr_workers || pool->nr_idle); + spin_unlock_irq(&pool->lock); + + mutex_lock(&pool->attach_mutex); + if (!list_empty(&pool->workers)) + pool->detach_completion = &detach_completion; + mutex_unlock(&pool->attach_mutex); + + if (pool->detach_completion) + wait_for_completion(pool->detach_completion); + + mutex_unlock(&pool->manager_arb); + + /* shut down the timers */ + del_timer_sync(&pool->idle_timer); + del_timer_sync(&pool->mayday_timer); + + /* RCU protected to allow dereferences from get_work_pool() */ + call_rcu(&pool->rcu, rcu_free_pool); +} + +/** + * get_unbound_pool - get a worker_pool with the specified attributes + * @attrs: the attributes of the worker_pool to get + * + * Obtain a worker_pool which has the same attributes as @attrs, bump the + * reference count and return it. If there already is a matching + * worker_pool, it will be used; otherwise, this function attempts to + * create a new one. + * + * Should be called with wq_pool_mutex held. + * + * Return: On success, a worker_pool with the same attributes as @attrs. + * On failure, %NULL. + */ +static struct worker_pool *get_unbound_pool(const struct workqueue_attrs *attrs) +{ + u32 hash = wqattrs_hash(attrs); + struct worker_pool *pool; + int node; + + lockdep_assert_held(&wq_pool_mutex); + + /* do we already have a matching pool? */ + hash_for_each_possible(unbound_pool_hash, pool, hash_node, hash) { + if (wqattrs_equal(pool->attrs, attrs)) { + pool->refcnt++; + return pool; + } + } + + /* nope, create a new one */ + pool = kzalloc(sizeof(*pool), GFP_KERNEL); + if (!pool || init_worker_pool(pool) < 0) + goto fail; + + lockdep_set_subclass(&pool->lock, 1); /* see put_pwq() */ + copy_workqueue_attrs(pool->attrs, attrs); + + /* + * no_numa isn't a worker_pool attribute, always clear it. See + * 'struct workqueue_attrs' comments for detail. + */ + pool->attrs->no_numa = false; + + /* if cpumask is contained inside a NUMA node, we belong to that node */ + if (wq_numa_enabled) { + for_each_node(node) { + if (cpumask_subset(pool->attrs->cpumask, + wq_numa_possible_cpumask[node])) { + pool->node = node; + break; + } + } + } + + if (worker_pool_assign_id(pool) < 0) + goto fail; + + /* create and start the initial worker */ + if (!create_worker(pool)) + goto fail; + + /* install */ + hash_add(unbound_pool_hash, &pool->hash_node, hash); + + return pool; +fail: + if (pool) + put_unbound_pool(pool); + return NULL; +} + +static void rcu_free_pwq(struct rcu_head *rcu) +{ + kmem_cache_free(pwq_cache, + container_of(rcu, struct pool_workqueue, rcu)); +} + +/* + * Scheduled on system_wq by put_pwq() when an unbound pwq hits zero refcnt + * and needs to be destroyed. + */ +static void pwq_unbound_release_workfn(struct work_struct *work) +{ + struct pool_workqueue *pwq = container_of(work, struct pool_workqueue, + unbound_release_work); + struct workqueue_struct *wq = pwq->wq; + struct worker_pool *pool = pwq->pool; + bool is_last; + + if (WARN_ON_ONCE(!(wq->flags & WQ_UNBOUND))) + return; + + mutex_lock(&wq->mutex); + list_del_rcu(&pwq->pwqs_node); + is_last = list_empty(&wq->pwqs); + mutex_unlock(&wq->mutex); + + mutex_lock(&wq_pool_mutex); + put_unbound_pool(pool); + mutex_unlock(&wq_pool_mutex); + + call_rcu(&pwq->rcu, rcu_free_pwq); + + /* + * If we're the last pwq going away, @wq is already dead and no one + * is gonna access it anymore. Schedule RCU free. + */ + if (is_last) + call_rcu(&wq->rcu, rcu_free_wq); +} + +/** + * pwq_adjust_max_active - update a pwq's max_active to the current setting + * @pwq: target pool_workqueue + * + * If @pwq isn't freezing, set @pwq->max_active to the associated + * workqueue's saved_max_active and activate delayed work items + * accordingly. If @pwq is freezing, clear @pwq->max_active to zero. + */ +static void pwq_adjust_max_active(struct pool_workqueue *pwq) +{ + struct workqueue_struct *wq = pwq->wq; + bool freezable = wq->flags & WQ_FREEZABLE; + + /* for @wq->saved_max_active */ + lockdep_assert_held(&wq->mutex); + + /* fast exit for non-freezable wqs */ + if (!freezable && pwq->max_active == wq->saved_max_active) + return; + + spin_lock_irq(&pwq->pool->lock); + + /* + * During [un]freezing, the caller is responsible for ensuring that + * this function is called at least once after @workqueue_freezing + * is updated and visible. + */ + if (!freezable || !workqueue_freezing) { + pwq->max_active = wq->saved_max_active; + + while (!list_empty(&pwq->delayed_works) && + pwq->nr_active < pwq->max_active) + pwq_activate_first_delayed(pwq); + + /* + * Need to kick a worker after thawed or an unbound wq's + * max_active is bumped. It's a slow path. Do it always. + */ + wake_up_worker(pwq->pool); + } else { + pwq->max_active = 0; + } + + spin_unlock_irq(&pwq->pool->lock); +} + +/* initialize newly alloced @pwq which is associated with @wq and @pool */ +static void init_pwq(struct pool_workqueue *pwq, struct workqueue_struct *wq, + struct worker_pool *pool) +{ + BUG_ON((unsigned long)pwq & WORK_STRUCT_FLAG_MASK); + + memset(pwq, 0, sizeof(*pwq)); + + pwq->pool = pool; + pwq->wq = wq; + pwq->flush_color = -1; + pwq->refcnt = 1; + INIT_LIST_HEAD(&pwq->delayed_works); + INIT_LIST_HEAD(&pwq->pwqs_node); + INIT_LIST_HEAD(&pwq->mayday_node); + INIT_WORK(&pwq->unbound_release_work, pwq_unbound_release_workfn); +} + +/* sync @pwq with the current state of its associated wq and link it */ +static void link_pwq(struct pool_workqueue *pwq) +{ + struct workqueue_struct *wq = pwq->wq; + + lockdep_assert_held(&wq->mutex); + + /* may be called multiple times, ignore if already linked */ + if (!list_empty(&pwq->pwqs_node)) + return; + + /* set the matching work_color */ + pwq->work_color = wq->work_color; + + /* sync max_active to the current setting */ + pwq_adjust_max_active(pwq); + + /* link in @pwq */ + list_add_rcu(&pwq->pwqs_node, &wq->pwqs); +} + +/* obtain a pool matching @attr and create a pwq associating the pool and @wq */ +static struct pool_workqueue *alloc_unbound_pwq(struct workqueue_struct *wq, + const struct workqueue_attrs *attrs) +{ + struct worker_pool *pool; + struct pool_workqueue *pwq; + + lockdep_assert_held(&wq_pool_mutex); + + pool = get_unbound_pool(attrs); + if (!pool) + return NULL; + + pwq = kmem_cache_alloc_node(pwq_cache, GFP_KERNEL, pool->node); + if (!pwq) { + put_unbound_pool(pool); + return NULL; + } + + init_pwq(pwq, wq, pool); + return pwq; +} + +/* undo alloc_unbound_pwq(), used only in the error path */ +static void free_unbound_pwq(struct pool_workqueue *pwq) +{ + lockdep_assert_held(&wq_pool_mutex); + + if (pwq) { + put_unbound_pool(pwq->pool); + kmem_cache_free(pwq_cache, pwq); + } +} + +/** + * wq_calc_node_mask - calculate a wq_attrs' cpumask for the specified node + * @attrs: the wq_attrs of interest + * @node: the target NUMA node + * @cpu_going_down: if >= 0, the CPU to consider as offline + * @cpumask: outarg, the resulting cpumask + * + * Calculate the cpumask a workqueue with @attrs should use on @node. If + * @cpu_going_down is >= 0, that cpu is considered offline during + * calculation. The result is stored in @cpumask. + * + * If NUMA affinity is not enabled, @attrs->cpumask is always used. If + * enabled and @node has online CPUs requested by @attrs, the returned + * cpumask is the intersection of the possible CPUs of @node and + * @attrs->cpumask. + * + * The caller is responsible for ensuring that the cpumask of @node stays + * stable. + * + * Return: %true if the resulting @cpumask is different from @attrs->cpumask, + * %false if equal. + */ +static bool wq_calc_node_cpumask(const struct workqueue_attrs *attrs, int node, + int cpu_going_down, cpumask_t *cpumask) +{ + if (!wq_numa_enabled || attrs->no_numa) + goto use_dfl; + + /* does @node have any online CPUs @attrs wants? */ + cpumask_and(cpumask, cpumask_of_node(node), attrs->cpumask); + if (cpu_going_down >= 0) + cpumask_clear_cpu(cpu_going_down, cpumask); + + if (cpumask_empty(cpumask)) + goto use_dfl; + + /* yeap, return possible CPUs in @node that @attrs wants */ + cpumask_and(cpumask, attrs->cpumask, wq_numa_possible_cpumask[node]); + return !cpumask_equal(cpumask, attrs->cpumask); + +use_dfl: + cpumask_copy(cpumask, attrs->cpumask); + return false; +} + +/* install @pwq into @wq's numa_pwq_tbl[] for @node and return the old pwq */ +static struct pool_workqueue *numa_pwq_tbl_install(struct workqueue_struct *wq, + int node, + struct pool_workqueue *pwq) +{ + struct pool_workqueue *old_pwq; + + lockdep_assert_held(&wq->mutex); + + /* link_pwq() can handle duplicate calls */ + link_pwq(pwq); + + old_pwq = rcu_access_pointer(wq->numa_pwq_tbl[node]); + rcu_assign_pointer(wq->numa_pwq_tbl[node], pwq); + return old_pwq; +} + +/** + * apply_workqueue_attrs - apply new workqueue_attrs to an unbound workqueue + * @wq: the target workqueue + * @attrs: the workqueue_attrs to apply, allocated with alloc_workqueue_attrs() + * + * Apply @attrs to an unbound workqueue @wq. Unless disabled, on NUMA + * machines, this function maps a separate pwq to each NUMA node with + * possibles CPUs in @attrs->cpumask so that work items are affine to the + * NUMA node it was issued on. Older pwqs are released as in-flight work + * items finish. Note that a work item which repeatedly requeues itself + * back-to-back will stay on its current pwq. + * + * Performs GFP_KERNEL allocations. + * + * Return: 0 on success and -errno on failure. + */ +int apply_workqueue_attrs(struct workqueue_struct *wq, + const struct workqueue_attrs *attrs) +{ + struct workqueue_attrs *new_attrs, *tmp_attrs; + struct pool_workqueue **pwq_tbl, *dfl_pwq; + int node, ret; + + /* only unbound workqueues can change attributes */ + if (WARN_ON(!(wq->flags & WQ_UNBOUND))) + return -EINVAL; + + /* creating multiple pwqs breaks ordering guarantee */ + if (WARN_ON((wq->flags & __WQ_ORDERED) && !list_empty(&wq->pwqs))) + return -EINVAL; + + pwq_tbl = kzalloc(nr_node_ids * sizeof(pwq_tbl[0]), GFP_KERNEL); + new_attrs = alloc_workqueue_attrs(GFP_KERNEL); + tmp_attrs = alloc_workqueue_attrs(GFP_KERNEL); + if (!pwq_tbl || !new_attrs || !tmp_attrs) + goto enomem; + + /* make a copy of @attrs and sanitize it */ + copy_workqueue_attrs(new_attrs, attrs); + cpumask_and(new_attrs->cpumask, new_attrs->cpumask, cpu_possible_mask); + + /* + * We may create multiple pwqs with differing cpumasks. Make a + * copy of @new_attrs which will be modified and used to obtain + * pools. + */ + copy_workqueue_attrs(tmp_attrs, new_attrs); + + /* + * CPUs should stay stable across pwq creations and installations. + * Pin CPUs, determine the target cpumask for each node and create + * pwqs accordingly. + */ + get_online_cpus(); + + mutex_lock(&wq_pool_mutex); + + /* + * If something goes wrong during CPU up/down, we'll fall back to + * the default pwq covering whole @attrs->cpumask. Always create + * it even if we don't use it immediately. + */ + dfl_pwq = alloc_unbound_pwq(wq, new_attrs); + if (!dfl_pwq) + goto enomem_pwq; + + for_each_node(node) { + if (wq_calc_node_cpumask(attrs, node, -1, tmp_attrs->cpumask)) { + pwq_tbl[node] = alloc_unbound_pwq(wq, tmp_attrs); + if (!pwq_tbl[node]) + goto enomem_pwq; + } else { + dfl_pwq->refcnt++; + pwq_tbl[node] = dfl_pwq; + } + } + + mutex_unlock(&wq_pool_mutex); + + /* all pwqs have been created successfully, let's install'em */ + mutex_lock(&wq->mutex); + + copy_workqueue_attrs(wq->unbound_attrs, new_attrs); + + /* save the previous pwq and install the new one */ + for_each_node(node) + pwq_tbl[node] = numa_pwq_tbl_install(wq, node, pwq_tbl[node]); + + /* @dfl_pwq might not have been used, ensure it's linked */ + link_pwq(dfl_pwq); + swap(wq->dfl_pwq, dfl_pwq); + + mutex_unlock(&wq->mutex); + + /* put the old pwqs */ + for_each_node(node) + put_pwq_unlocked(pwq_tbl[node]); + put_pwq_unlocked(dfl_pwq); + + put_online_cpus(); + ret = 0; + /* fall through */ +out_free: + free_workqueue_attrs(tmp_attrs); + free_workqueue_attrs(new_attrs); + kfree(pwq_tbl); + return ret; + +enomem_pwq: + free_unbound_pwq(dfl_pwq); + for_each_node(node) + if (pwq_tbl && pwq_tbl[node] != dfl_pwq) + free_unbound_pwq(pwq_tbl[node]); + mutex_unlock(&wq_pool_mutex); + put_online_cpus(); +enomem: + ret = -ENOMEM; + goto out_free; +} + +/** + * wq_update_unbound_numa - update NUMA affinity of a wq for CPU hot[un]plug + * @wq: the target workqueue + * @cpu: the CPU coming up or going down + * @online: whether @cpu is coming up or going down + * + * This function is to be called from %CPU_DOWN_PREPARE, %CPU_ONLINE and + * %CPU_DOWN_FAILED. @cpu is being hot[un]plugged, update NUMA affinity of + * @wq accordingly. + * + * If NUMA affinity can't be adjusted due to memory allocation failure, it + * falls back to @wq->dfl_pwq which may not be optimal but is always + * correct. + * + * Note that when the last allowed CPU of a NUMA node goes offline for a + * workqueue with a cpumask spanning multiple nodes, the workers which were + * already executing the work items for the workqueue will lose their CPU + * affinity and may execute on any CPU. This is similar to how per-cpu + * workqueues behave on CPU_DOWN. If a workqueue user wants strict + * affinity, it's the user's responsibility to flush the work item from + * CPU_DOWN_PREPARE. + */ +static void wq_update_unbound_numa(struct workqueue_struct *wq, int cpu, + bool online) +{ + int node = cpu_to_node(cpu); + int cpu_off = online ? -1 : cpu; + struct pool_workqueue *old_pwq = NULL, *pwq; + struct workqueue_attrs *target_attrs; + cpumask_t *cpumask; + + lockdep_assert_held(&wq_pool_mutex); + + if (!wq_numa_enabled || !(wq->flags & WQ_UNBOUND)) + return; + + /* + * We don't wanna alloc/free wq_attrs for each wq for each CPU. + * Let's use a preallocated one. The following buf is protected by + * CPU hotplug exclusion. + */ + target_attrs = wq_update_unbound_numa_attrs_buf; + cpumask = target_attrs->cpumask; + + mutex_lock(&wq->mutex); + if (wq->unbound_attrs->no_numa) + goto out_unlock; + + copy_workqueue_attrs(target_attrs, wq->unbound_attrs); + pwq = unbound_pwq_by_node(wq, node); + + /* + * Let's determine what needs to be done. If the target cpumask is + * different from wq's, we need to compare it to @pwq's and create + * a new one if they don't match. If the target cpumask equals + * wq's, the default pwq should be used. + */ + if (wq_calc_node_cpumask(wq->unbound_attrs, node, cpu_off, cpumask)) { + if (cpumask_equal(cpumask, pwq->pool->attrs->cpumask)) + goto out_unlock; + } else { + goto use_dfl_pwq; + } + + mutex_unlock(&wq->mutex); + + /* create a new pwq */ + pwq = alloc_unbound_pwq(wq, target_attrs); + if (!pwq) { + pr_warn("workqueue: allocation failed while updating NUMA affinity of \"%s\"\n", + wq->name); + mutex_lock(&wq->mutex); + goto use_dfl_pwq; + } + + /* + * Install the new pwq. As this function is called only from CPU + * hotplug callbacks and applying a new attrs is wrapped with + * get/put_online_cpus(), @wq->unbound_attrs couldn't have changed + * inbetween. + */ + mutex_lock(&wq->mutex); + old_pwq = numa_pwq_tbl_install(wq, node, pwq); + goto out_unlock; + +use_dfl_pwq: + spin_lock_irq(&wq->dfl_pwq->pool->lock); + get_pwq(wq->dfl_pwq); + spin_unlock_irq(&wq->dfl_pwq->pool->lock); + old_pwq = numa_pwq_tbl_install(wq, node, wq->dfl_pwq); +out_unlock: + mutex_unlock(&wq->mutex); + put_pwq_unlocked(old_pwq); +} + +static int alloc_and_link_pwqs(struct workqueue_struct *wq) +{ + bool highpri = wq->flags & WQ_HIGHPRI; + int cpu, ret; + + if (!(wq->flags & WQ_UNBOUND)) { + wq->cpu_pwqs = alloc_percpu(struct pool_workqueue); + if (!wq->cpu_pwqs) + return -ENOMEM; + + for_each_possible_cpu(cpu) { + struct pool_workqueue *pwq = + per_cpu_ptr(wq->cpu_pwqs, cpu); + struct worker_pool *cpu_pools = + per_cpu(cpu_worker_pools, cpu); + + init_pwq(pwq, wq, &cpu_pools[highpri]); + + mutex_lock(&wq->mutex); + link_pwq(pwq); + mutex_unlock(&wq->mutex); + } + return 0; + } else if (wq->flags & __WQ_ORDERED) { + ret = apply_workqueue_attrs(wq, ordered_wq_attrs[highpri]); + /* there should only be single pwq for ordering guarantee */ + WARN(!ret && (wq->pwqs.next != &wq->dfl_pwq->pwqs_node || + wq->pwqs.prev != &wq->dfl_pwq->pwqs_node), + "ordering guarantee broken for workqueue %s\n", wq->name); + return ret; + } else { + return apply_workqueue_attrs(wq, unbound_std_wq_attrs[highpri]); + } +} + +static int wq_clamp_max_active(int max_active, unsigned int flags, + const char *name) +{ + int lim = flags & WQ_UNBOUND ? WQ_UNBOUND_MAX_ACTIVE : WQ_MAX_ACTIVE; + + if (max_active < 1 || max_active > lim) + pr_warn("workqueue: max_active %d requested for %s is out of range, clamping between %d and %d\n", + max_active, name, 1, lim); + + return clamp_val(max_active, 1, lim); +} + +struct workqueue_struct *__alloc_workqueue_key(const char *fmt, + unsigned int flags, + int max_active, + struct lock_class_key *key, + const char *lock_name, ...) +{ + size_t tbl_size = 0; + va_list args; + struct workqueue_struct *wq; + struct pool_workqueue *pwq; + + /* see the comment above the definition of WQ_POWER_EFFICIENT */ + if ((flags & WQ_POWER_EFFICIENT) && wq_power_efficient) + flags |= WQ_UNBOUND; + + /* allocate wq and format name */ + if (flags & WQ_UNBOUND) + tbl_size = nr_node_ids * sizeof(wq->numa_pwq_tbl[0]); + + wq = kzalloc(sizeof(*wq) + tbl_size, GFP_KERNEL); + if (!wq) + return NULL; + + if (flags & WQ_UNBOUND) { + wq->unbound_attrs = alloc_workqueue_attrs(GFP_KERNEL); + if (!wq->unbound_attrs) + goto err_free_wq; + } + + va_start(args, lock_name); + vsnprintf(wq->name, sizeof(wq->name), fmt, args); + va_end(args); + + max_active = max_active ?: WQ_DFL_ACTIVE; + max_active = wq_clamp_max_active(max_active, flags, wq->name); + + /* init wq */ + wq->flags = flags; + wq->saved_max_active = max_active; + mutex_init(&wq->mutex); + atomic_set(&wq->nr_pwqs_to_flush, 0); + INIT_LIST_HEAD(&wq->pwqs); + INIT_LIST_HEAD(&wq->flusher_queue); + INIT_LIST_HEAD(&wq->flusher_overflow); + INIT_LIST_HEAD(&wq->maydays); + + lockdep_init_map(&wq->lockdep_map, lock_name, key, 0); + INIT_LIST_HEAD(&wq->list); + + if (alloc_and_link_pwqs(wq) < 0) + goto err_free_wq; + + /* + * Workqueues which may be used during memory reclaim should + * have a rescuer to guarantee forward progress. + */ + if (flags & WQ_MEM_RECLAIM) { + struct worker *rescuer; + + rescuer = alloc_worker(NUMA_NO_NODE); + if (!rescuer) + goto err_destroy; + + rescuer->rescue_wq = wq; + rescuer->task = kthread_create(rescuer_thread, rescuer, "%s", + wq->name); + if (IS_ERR(rescuer->task)) { + kfree(rescuer); + goto err_destroy; + } + + wq->rescuer = rescuer; + rescuer->task->flags |= PF_NO_SETAFFINITY; + wake_up_process(rescuer->task); + } + + if ((wq->flags & WQ_SYSFS) && workqueue_sysfs_register(wq)) + goto err_destroy; + + /* + * wq_pool_mutex protects global freeze state and workqueues list. + * Grab it, adjust max_active and add the new @wq to workqueues + * list. + */ + mutex_lock(&wq_pool_mutex); + + mutex_lock(&wq->mutex); + for_each_pwq(pwq, wq) + pwq_adjust_max_active(pwq); + mutex_unlock(&wq->mutex); + + list_add_tail_rcu(&wq->list, &workqueues); + + mutex_unlock(&wq_pool_mutex); + + return wq; + +err_free_wq: + free_workqueue_attrs(wq->unbound_attrs); + kfree(wq); + return NULL; +err_destroy: + destroy_workqueue(wq); + return NULL; +} +EXPORT_SYMBOL_GPL(__alloc_workqueue_key); + +/** + * destroy_workqueue - safely terminate a workqueue + * @wq: target workqueue + * + * Safely destroy a workqueue. All work currently pending will be done first. + */ +void destroy_workqueue(struct workqueue_struct *wq) +{ + struct pool_workqueue *pwq; + int node; + + /* drain it before proceeding with destruction */ + drain_workqueue(wq); + + /* sanity checks */ + mutex_lock(&wq->mutex); + for_each_pwq(pwq, wq) { + int i; + + for (i = 0; i < WORK_NR_COLORS; i++) { + if (WARN_ON(pwq->nr_in_flight[i])) { + mutex_unlock(&wq->mutex); + return; + } + } + + if (WARN_ON((pwq != wq->dfl_pwq) && (pwq->refcnt > 1)) || + WARN_ON(pwq->nr_active) || + WARN_ON(!list_empty(&pwq->delayed_works))) { + mutex_unlock(&wq->mutex); + return; + } + } + mutex_unlock(&wq->mutex); + + /* + * wq list is used to freeze wq, remove from list after + * flushing is complete in case freeze races us. + */ + mutex_lock(&wq_pool_mutex); + list_del_rcu(&wq->list); + mutex_unlock(&wq_pool_mutex); + + workqueue_sysfs_unregister(wq); + + if (wq->rescuer) + kthread_stop(wq->rescuer->task); + + if (!(wq->flags & WQ_UNBOUND)) { + /* + * The base ref is never dropped on per-cpu pwqs. Directly + * schedule RCU free. + */ + call_rcu(&wq->rcu, rcu_free_wq); + } else { + /* + * We're the sole accessor of @wq at this point. Directly + * access numa_pwq_tbl[] and dfl_pwq to put the base refs. + * @wq will be freed when the last pwq is released. + */ + for_each_node(node) { + pwq = rcu_access_pointer(wq->numa_pwq_tbl[node]); + RCU_INIT_POINTER(wq->numa_pwq_tbl[node], NULL); + put_pwq_unlocked(pwq); + } + + /* + * Put dfl_pwq. @wq may be freed any time after dfl_pwq is + * put. Don't access it afterwards. + */ + pwq = wq->dfl_pwq; + wq->dfl_pwq = NULL; + put_pwq_unlocked(pwq); + } +} +EXPORT_SYMBOL_GPL(destroy_workqueue); + +/** + * workqueue_set_max_active - adjust max_active of a workqueue + * @wq: target workqueue + * @max_active: new max_active value. + * + * Set max_active of @wq to @max_active. + * + * CONTEXT: + * Don't call from IRQ context. + */ +void workqueue_set_max_active(struct workqueue_struct *wq, int max_active) +{ + struct pool_workqueue *pwq; + + /* disallow meddling with max_active for ordered workqueues */ + if (WARN_ON(wq->flags & __WQ_ORDERED)) + return; + + max_active = wq_clamp_max_active(max_active, wq->flags, wq->name); + + mutex_lock(&wq->mutex); + + wq->saved_max_active = max_active; + + for_each_pwq(pwq, wq) + pwq_adjust_max_active(pwq); + + mutex_unlock(&wq->mutex); +} +EXPORT_SYMBOL_GPL(workqueue_set_max_active); + +/** + * current_is_workqueue_rescuer - is %current workqueue rescuer? + * + * Determine whether %current is a workqueue rescuer. Can be used from + * work functions to determine whether it's being run off the rescuer task. + * + * Return: %true if %current is a workqueue rescuer. %false otherwise. + */ +bool current_is_workqueue_rescuer(void) +{ + struct worker *worker = current_wq_worker(); + + return worker && worker->rescue_wq; +} + +/** + * workqueue_congested - test whether a workqueue is congested + * @cpu: CPU in question + * @wq: target workqueue + * + * Test whether @wq's cpu workqueue for @cpu is congested. There is + * no synchronization around this function and the test result is + * unreliable and only useful as advisory hints or for debugging. + * + * If @cpu is WORK_CPU_UNBOUND, the test is performed on the local CPU. + * Note that both per-cpu and unbound workqueues may be associated with + * multiple pool_workqueues which have separate congested states. A + * workqueue being congested on one CPU doesn't mean the workqueue is also + * contested on other CPUs / NUMA nodes. + * + * Return: + * %true if congested, %false otherwise. + */ +bool workqueue_congested(int cpu, struct workqueue_struct *wq) +{ + struct pool_workqueue *pwq; + bool ret; + + rcu_read_lock(); + preempt_disable(); + + if (cpu == WORK_CPU_UNBOUND) + cpu = smp_processor_id(); + + if (!(wq->flags & WQ_UNBOUND)) + pwq = per_cpu_ptr(wq->cpu_pwqs, cpu); + else + pwq = unbound_pwq_by_node(wq, cpu_to_node(cpu)); + + ret = !list_empty(&pwq->delayed_works); + preempt_enable(); + rcu_read_unlock(); + + return ret; +} +EXPORT_SYMBOL_GPL(workqueue_congested); + +/** + * work_busy - test whether a work is currently pending or running + * @work: the work to be tested + * + * Test whether @work is currently pending or running. There is no + * synchronization around this function and the test result is + * unreliable and only useful as advisory hints or for debugging. + * + * Return: + * OR'd bitmask of WORK_BUSY_* bits. + */ +unsigned int work_busy(struct work_struct *work) +{ + struct worker_pool *pool; + unsigned long flags; + unsigned int ret = 0; + + if (work_pending(work)) + ret |= WORK_BUSY_PENDING; + + rcu_read_lock(); + pool = get_work_pool(work); + if (pool) { + spin_lock_irqsave(&pool->lock, flags); + if (find_worker_executing_work(pool, work)) + ret |= WORK_BUSY_RUNNING; + spin_unlock_irqrestore(&pool->lock, flags); + } + rcu_read_unlock(); + + return ret; +} +EXPORT_SYMBOL_GPL(work_busy); + +/** + * set_worker_desc - set description for the current work item + * @fmt: printf-style format string + * @...: arguments for the format string + * + * This function can be called by a running work function to describe what + * the work item is about. If the worker task gets dumped, this + * information will be printed out together to help debugging. The + * description can be at most WORKER_DESC_LEN including the trailing '\0'. + */ +void set_worker_desc(const char *fmt, ...) +{ + struct worker *worker = current_wq_worker(); + va_list args; + + if (worker) { + va_start(args, fmt); + vsnprintf(worker->desc, sizeof(worker->desc), fmt, args); + va_end(args); + worker->desc_valid = true; + } +} + +/** + * print_worker_info - print out worker information and description + * @log_lvl: the log level to use when printing + * @task: target task + * + * If @task is a worker and currently executing a work item, print out the + * name of the workqueue being serviced and worker description set with + * set_worker_desc() by the currently executing work item. + * + * This function can be safely called on any task as long as the + * task_struct itself is accessible. While safe, this function isn't + * synchronized and may print out mixups or garbages of limited length. + */ +void print_worker_info(const char *log_lvl, struct task_struct *task) +{ + work_func_t *fn = NULL; + char name[WQ_NAME_LEN] = { }; + char desc[WORKER_DESC_LEN] = { }; + struct pool_workqueue *pwq = NULL; + struct workqueue_struct *wq = NULL; + bool desc_valid = false; + struct worker *worker; + + if (!(task->flags & PF_WQ_WORKER)) + return; + + /* + * This function is called without any synchronization and @task + * could be in any state. Be careful with dereferences. + */ + worker = probe_kthread_data(task); + + /* + * Carefully copy the associated workqueue's workfn and name. Keep + * the original last '\0' in case the original contains garbage. + */ + probe_kernel_read(&fn, &worker->current_func, sizeof(fn)); + probe_kernel_read(&pwq, &worker->current_pwq, sizeof(pwq)); + probe_kernel_read(&wq, &pwq->wq, sizeof(wq)); + probe_kernel_read(name, wq->name, sizeof(name) - 1); + + /* copy worker description */ + probe_kernel_read(&desc_valid, &worker->desc_valid, sizeof(desc_valid)); + if (desc_valid) + probe_kernel_read(desc, worker->desc, sizeof(desc) - 1); + + if (fn || name[0] || desc[0]) { + printk("%sWorkqueue: %s %pf", log_lvl, name, fn); + if (desc[0]) + pr_cont(" (%s)", desc); + pr_cont("\n"); + } +} + +static void pr_cont_pool_info(struct worker_pool *pool) +{ + pr_cont(" cpus=%*pbl", nr_cpumask_bits, pool->attrs->cpumask); + if (pool->node != NUMA_NO_NODE) + pr_cont(" node=%d", pool->node); + pr_cont(" flags=0x%x nice=%d", pool->flags, pool->attrs->nice); +} + +static void pr_cont_work(bool comma, struct work_struct *work) +{ + if (work->func == wq_barrier_func) { + struct wq_barrier *barr; + + barr = container_of(work, struct wq_barrier, work); + + pr_cont("%s BAR(%d)", comma ? "," : "", + task_pid_nr(barr->task)); + } else { + pr_cont("%s %pf", comma ? "," : "", work->func); + } +} + +static void show_pwq(struct pool_workqueue *pwq) +{ + struct worker_pool *pool = pwq->pool; + struct work_struct *work; + struct worker *worker; + bool has_in_flight = false, has_pending = false; + int bkt; + + pr_info(" pwq %d:", pool->id); + pr_cont_pool_info(pool); + + pr_cont(" active=%d/%d%s\n", pwq->nr_active, pwq->max_active, + !list_empty(&pwq->mayday_node) ? " MAYDAY" : ""); + + hash_for_each(pool->busy_hash, bkt, worker, hentry) { + if (worker->current_pwq == pwq) { + has_in_flight = true; + break; + } + } + if (has_in_flight) { + bool comma = false; + + pr_info(" in-flight:"); + hash_for_each(pool->busy_hash, bkt, worker, hentry) { + if (worker->current_pwq != pwq) + continue; + + pr_cont("%s %d%s:%pf", comma ? "," : "", + task_pid_nr(worker->task), + worker == pwq->wq->rescuer ? "(RESCUER)" : "", + worker->current_func); + list_for_each_entry(work, &worker->scheduled, entry) + pr_cont_work(false, work); + comma = true; + } + pr_cont("\n"); + } + + list_for_each_entry(work, &pool->worklist, entry) { + if (get_work_pwq(work) == pwq) { + has_pending = true; + break; + } + } + if (has_pending) { + bool comma = false; + + pr_info(" pending:"); + list_for_each_entry(work, &pool->worklist, entry) { + if (get_work_pwq(work) != pwq) + continue; + + pr_cont_work(comma, work); + comma = !(*work_data_bits(work) & WORK_STRUCT_LINKED); + } + pr_cont("\n"); + } + + if (!list_empty(&pwq->delayed_works)) { + bool comma = false; + + pr_info(" delayed:"); + list_for_each_entry(work, &pwq->delayed_works, entry) { + pr_cont_work(comma, work); + comma = !(*work_data_bits(work) & WORK_STRUCT_LINKED); + } + pr_cont("\n"); + } +} + +/** + * show_workqueue_state - dump workqueue state + * + * Called from a sysrq handler and prints out all busy workqueues and + * pools. + */ +void show_workqueue_state(void) +{ + struct workqueue_struct *wq; + struct worker_pool *pool; + unsigned long flags; + int pi; + + rcu_read_lock(); + + pr_info("Showing busy workqueues and worker pools:\n"); + + list_for_each_entry_rcu(wq, &workqueues, list) { + struct pool_workqueue *pwq; + bool idle = true; + + for_each_pwq(pwq, wq) { + if (pwq->nr_active || !list_empty(&pwq->delayed_works)) { + idle = false; + break; + } + } + if (idle) + continue; + + pr_info("workqueue %s: flags=0x%x\n", wq->name, wq->flags); + + for_each_pwq(pwq, wq) { + spin_lock_irqsave(&pwq->pool->lock, flags); + if (pwq->nr_active || !list_empty(&pwq->delayed_works)) + show_pwq(pwq); + spin_unlock_irqrestore(&pwq->pool->lock, flags); + } + } + + for_each_pool(pool, pi) { + struct worker *worker; + bool first = true; + + spin_lock_irqsave(&pool->lock, flags); + if (pool->nr_workers == pool->nr_idle) + goto next_pool; + + pr_info("pool %d:", pool->id); + pr_cont_pool_info(pool); + pr_cont(" workers=%d", pool->nr_workers); + if (pool->manager) + pr_cont(" manager: %d", + task_pid_nr(pool->manager->task)); + list_for_each_entry(worker, &pool->idle_list, entry) { + pr_cont(" %s%d", first ? "idle: " : "", + task_pid_nr(worker->task)); + first = false; + } + pr_cont("\n"); + next_pool: + spin_unlock_irqrestore(&pool->lock, flags); + } + + rcu_read_unlock(); +} + +/* + * CPU hotplug. + * + * There are two challenges in supporting CPU hotplug. Firstly, there + * are a lot of assumptions on strong associations among work, pwq and + * pool which make migrating pending and scheduled works very + * difficult to implement without impacting hot paths. Secondly, + * worker pools serve mix of short, long and very long running works making + * blocked draining impractical. + * + * This is solved by allowing the pools to be disassociated from the CPU + * running as an unbound one and allowing it to be reattached later if the + * cpu comes back online. + */ + +static void wq_unbind_fn(struct work_struct *work) +{ + int cpu = smp_processor_id(); + struct worker_pool *pool; + struct worker *worker; + + for_each_cpu_worker_pool(pool, cpu) { + mutex_lock(&pool->attach_mutex); + spin_lock_irq(&pool->lock); + + /* + * We've blocked all attach/detach operations. Make all workers + * unbound and set DISASSOCIATED. Before this, all workers + * except for the ones which are still executing works from + * before the last CPU down must be on the cpu. After + * this, they may become diasporas. + */ + for_each_pool_worker(worker, pool) + worker->flags |= WORKER_UNBOUND; + + pool->flags |= POOL_DISASSOCIATED; + + spin_unlock_irq(&pool->lock); + mutex_unlock(&pool->attach_mutex); + + /* + * Call schedule() so that we cross rq->lock and thus can + * guarantee sched callbacks see the %WORKER_UNBOUND flag. + * This is necessary as scheduler callbacks may be invoked + * from other cpus. + */ + schedule(); + + /* + * Sched callbacks are disabled now. Zap nr_running. + * After this, nr_running stays zero and need_more_worker() + * and keep_working() are always true as long as the + * worklist is not empty. This pool now behaves as an + * unbound (in terms of concurrency management) pool which + * are served by workers tied to the pool. + */ + atomic_set(&pool->nr_running, 0); + + /* + * With concurrency management just turned off, a busy + * worker blocking could lead to lengthy stalls. Kick off + * unbound chain execution of currently pending work items. + */ + spin_lock_irq(&pool->lock); + wake_up_worker(pool); + spin_unlock_irq(&pool->lock); + } +} + +/** + * rebind_workers - rebind all workers of a pool to the associated CPU + * @pool: pool of interest + * + * @pool->cpu is coming online. Rebind all workers to the CPU. + */ +static void rebind_workers(struct worker_pool *pool) +{ + struct worker *worker; + + lockdep_assert_held(&pool->attach_mutex); + + /* + * Restore CPU affinity of all workers. As all idle workers should + * be on the run-queue of the associated CPU before any local + * wake-ups for concurrency management happen, restore CPU affinty + * of all workers first and then clear UNBOUND. As we're called + * from CPU_ONLINE, the following shouldn't fail. + */ + for_each_pool_worker(worker, pool) + WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task, + pool->attrs->cpumask) < 0); + + spin_lock_irq(&pool->lock); + pool->flags &= ~POOL_DISASSOCIATED; + + for_each_pool_worker(worker, pool) { + unsigned int worker_flags = worker->flags; + + /* + * A bound idle worker should actually be on the runqueue + * of the associated CPU for local wake-ups targeting it to + * work. Kick all idle workers so that they migrate to the + * associated CPU. Doing this in the same loop as + * replacing UNBOUND with REBOUND is safe as no worker will + * be bound before @pool->lock is released. + */ + if (worker_flags & WORKER_IDLE) + wake_up_process(worker->task); + + /* + * We want to clear UNBOUND but can't directly call + * worker_clr_flags() or adjust nr_running. Atomically + * replace UNBOUND with another NOT_RUNNING flag REBOUND. + * @worker will clear REBOUND using worker_clr_flags() when + * it initiates the next execution cycle thus restoring + * concurrency management. Note that when or whether + * @worker clears REBOUND doesn't affect correctness. + * + * ACCESS_ONCE() is necessary because @worker->flags may be + * tested without holding any lock in + * wq_worker_waking_up(). Without it, NOT_RUNNING test may + * fail incorrectly leading to premature concurrency + * management operations. + */ + WARN_ON_ONCE(!(worker_flags & WORKER_UNBOUND)); + worker_flags |= WORKER_REBOUND; + worker_flags &= ~WORKER_UNBOUND; + ACCESS_ONCE(worker->flags) = worker_flags; + } + + spin_unlock_irq(&pool->lock); +} + +/** + * restore_unbound_workers_cpumask - restore cpumask of unbound workers + * @pool: unbound pool of interest + * @cpu: the CPU which is coming up + * + * An unbound pool may end up with a cpumask which doesn't have any online + * CPUs. When a worker of such pool get scheduled, the scheduler resets + * its cpus_allowed. If @cpu is in @pool's cpumask which didn't have any + * online CPU before, cpus_allowed of all its workers should be restored. + */ +static void restore_unbound_workers_cpumask(struct worker_pool *pool, int cpu) +{ + static cpumask_t cpumask; + struct worker *worker; + + lockdep_assert_held(&pool->attach_mutex); + + /* is @cpu allowed for @pool? */ + if (!cpumask_test_cpu(cpu, pool->attrs->cpumask)) + return; + + /* is @cpu the only online CPU? */ + cpumask_and(&cpumask, pool->attrs->cpumask, cpu_online_mask); + if (cpumask_weight(&cpumask) != 1) + return; + + /* as we're called from CPU_ONLINE, the following shouldn't fail */ + for_each_pool_worker(worker, pool) + WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task, + pool->attrs->cpumask) < 0); +} + +/* + * Workqueues should be brought up before normal priority CPU notifiers. + * This will be registered high priority CPU notifier. + */ +static int workqueue_cpu_up_callback(struct notifier_block *nfb, + unsigned long action, + void *hcpu) +{ + int cpu = (unsigned long)hcpu; + struct worker_pool *pool; + struct workqueue_struct *wq; + int pi; + + switch (action & ~CPU_TASKS_FROZEN) { + case CPU_UP_PREPARE: + for_each_cpu_worker_pool(pool, cpu) { + if (pool->nr_workers) + continue; + if (!create_worker(pool)) + return NOTIFY_BAD; + } + break; + + case CPU_DOWN_FAILED: + case CPU_ONLINE: + mutex_lock(&wq_pool_mutex); + + for_each_pool(pool, pi) { + mutex_lock(&pool->attach_mutex); + + if (pool->cpu == cpu) + rebind_workers(pool); + else if (pool->cpu < 0) + restore_unbound_workers_cpumask(pool, cpu); + + mutex_unlock(&pool->attach_mutex); + } + + /* update NUMA affinity of unbound workqueues */ + list_for_each_entry(wq, &workqueues, list) + wq_update_unbound_numa(wq, cpu, true); + + mutex_unlock(&wq_pool_mutex); + break; + } + return NOTIFY_OK; +} + +/* + * Workqueues should be brought down after normal priority CPU notifiers. + * This will be registered as low priority CPU notifier. + */ +static int workqueue_cpu_down_callback(struct notifier_block *nfb, + unsigned long action, + void *hcpu) +{ + int cpu = (unsigned long)hcpu; + struct work_struct unbind_work; + struct workqueue_struct *wq; + + switch (action & ~CPU_TASKS_FROZEN) { + case CPU_DOWN_PREPARE: + /* unbinding per-cpu workers should happen on the local CPU */ + INIT_WORK_ONSTACK(&unbind_work, wq_unbind_fn); + queue_work_on(cpu, system_highpri_wq, &unbind_work); + + /* update NUMA affinity of unbound workqueues */ + mutex_lock(&wq_pool_mutex); + list_for_each_entry(wq, &workqueues, list) + wq_update_unbound_numa(wq, cpu, false); + mutex_unlock(&wq_pool_mutex); + + /* wait for per-cpu unbinding to finish */ + flush_work(&unbind_work); + destroy_work_on_stack(&unbind_work); + break; + } + return NOTIFY_OK; +} + +#ifdef CONFIG_SMP + +struct work_for_cpu { + struct work_struct work; + long (*fn)(void *); + void *arg; + long ret; +}; + +static void work_for_cpu_fn(struct work_struct *work) +{ + struct work_for_cpu *wfc = container_of(work, struct work_for_cpu, work); + + wfc->ret = wfc->fn(wfc->arg); +} + +/** + * work_on_cpu - run a function in user context on a particular cpu + * @cpu: the cpu to run on + * @fn: the function to run + * @arg: the function arg + * + * It is up to the caller to ensure that the cpu doesn't go offline. + * The caller must not hold any locks which would prevent @fn from completing. + * + * Return: The value @fn returns. + */ +long work_on_cpu(int cpu, long (*fn)(void *), void *arg) +{ + struct work_for_cpu wfc = { .fn = fn, .arg = arg }; + + INIT_WORK_ONSTACK(&wfc.work, work_for_cpu_fn); + schedule_work_on(cpu, &wfc.work); + flush_work(&wfc.work); + destroy_work_on_stack(&wfc.work); + return wfc.ret; +} +EXPORT_SYMBOL_GPL(work_on_cpu); +#endif /* CONFIG_SMP */ + +#ifdef CONFIG_FREEZER + +/** + * freeze_workqueues_begin - begin freezing workqueues + * + * Start freezing workqueues. After this function returns, all freezable + * workqueues will queue new works to their delayed_works list instead of + * pool->worklist. + * + * CONTEXT: + * Grabs and releases wq_pool_mutex, wq->mutex and pool->lock's. + */ +void freeze_workqueues_begin(void) +{ + struct workqueue_struct *wq; + struct pool_workqueue *pwq; + + mutex_lock(&wq_pool_mutex); + + WARN_ON_ONCE(workqueue_freezing); + workqueue_freezing = true; + + list_for_each_entry(wq, &workqueues, list) { + mutex_lock(&wq->mutex); + for_each_pwq(pwq, wq) + pwq_adjust_max_active(pwq); + mutex_unlock(&wq->mutex); + } + + mutex_unlock(&wq_pool_mutex); +} + +/** + * freeze_workqueues_busy - are freezable workqueues still busy? + * + * Check whether freezing is complete. This function must be called + * between freeze_workqueues_begin() and thaw_workqueues(). + * + * CONTEXT: + * Grabs and releases wq_pool_mutex. + * + * Return: + * %true if some freezable workqueues are still busy. %false if freezing + * is complete. + */ +bool freeze_workqueues_busy(void) +{ + bool busy = false; + struct workqueue_struct *wq; + struct pool_workqueue *pwq; + + mutex_lock(&wq_pool_mutex); + + WARN_ON_ONCE(!workqueue_freezing); + + list_for_each_entry(wq, &workqueues, list) { + if (!(wq->flags & WQ_FREEZABLE)) + continue; + /* + * nr_active is monotonically decreasing. It's safe + * to peek without lock. + */ + rcu_read_lock(); + for_each_pwq(pwq, wq) { + WARN_ON_ONCE(pwq->nr_active < 0); + if (pwq->nr_active) { + busy = true; + rcu_read_unlock(); + goto out_unlock; + } + } + rcu_read_unlock(); + } +out_unlock: + mutex_unlock(&wq_pool_mutex); + return busy; +} + +/** + * thaw_workqueues - thaw workqueues + * + * Thaw workqueues. Normal queueing is restored and all collected + * frozen works are transferred to their respective pool worklists. + * + * CONTEXT: + * Grabs and releases wq_pool_mutex, wq->mutex and pool->lock's. + */ +void thaw_workqueues(void) +{ + struct workqueue_struct *wq; + struct pool_workqueue *pwq; + + mutex_lock(&wq_pool_mutex); + + if (!workqueue_freezing) + goto out_unlock; + + workqueue_freezing = false; + + /* restore max_active and repopulate worklist */ + list_for_each_entry(wq, &workqueues, list) { + mutex_lock(&wq->mutex); + for_each_pwq(pwq, wq) + pwq_adjust_max_active(pwq); + mutex_unlock(&wq->mutex); + } + +out_unlock: + mutex_unlock(&wq_pool_mutex); +} +#endif /* CONFIG_FREEZER */ + +#ifdef CONFIG_SYSFS +/* + * Workqueues with WQ_SYSFS flag set is visible to userland via + * /sys/bus/workqueue/devices/WQ_NAME. All visible workqueues have the + * following attributes. + * + * per_cpu RO bool : whether the workqueue is per-cpu or unbound + * max_active RW int : maximum number of in-flight work items + * + * Unbound workqueues have the following extra attributes. + * + * id RO int : the associated pool ID + * nice RW int : nice value of the workers + * cpumask RW mask : bitmask of allowed CPUs for the workers + */ +struct wq_device { + struct workqueue_struct *wq; + struct device dev; +}; + +static struct workqueue_struct *dev_to_wq(struct device *dev) +{ + struct wq_device *wq_dev = container_of(dev, struct wq_device, dev); + + return wq_dev->wq; +} + +static ssize_t per_cpu_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct workqueue_struct *wq = dev_to_wq(dev); + + return scnprintf(buf, PAGE_SIZE, "%d\n", (bool)!(wq->flags & WQ_UNBOUND)); +} +static DEVICE_ATTR_RO(per_cpu); + +static ssize_t max_active_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct workqueue_struct *wq = dev_to_wq(dev); + + return scnprintf(buf, PAGE_SIZE, "%d\n", wq->saved_max_active); +} + +static ssize_t max_active_store(struct device *dev, + struct device_attribute *attr, const char *buf, + size_t count) +{ + struct workqueue_struct *wq = dev_to_wq(dev); + int val; + + if (sscanf(buf, "%d", &val) != 1 || val <= 0) + return -EINVAL; + + workqueue_set_max_active(wq, val); + return count; +} +static DEVICE_ATTR_RW(max_active); + +static struct attribute *wq_sysfs_attrs[] = { + &dev_attr_per_cpu.attr, + &dev_attr_max_active.attr, + NULL, +}; +ATTRIBUTE_GROUPS(wq_sysfs); + +static ssize_t wq_pool_ids_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct workqueue_struct *wq = dev_to_wq(dev); + const char *delim = ""; + int node, written = 0; + + get_online_cpus(); + rcu_read_lock(); + for_each_node(node) { + written += scnprintf(buf + written, PAGE_SIZE - written, + "%s%d:%d", delim, node, + unbound_pwq_by_node(wq, node)->pool->id); + delim = " "; + } + written += scnprintf(buf + written, PAGE_SIZE - written, "\n"); + rcu_read_unlock(); + put_online_cpus(); + + return written; +} + +static ssize_t wq_nice_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct workqueue_struct *wq = dev_to_wq(dev); + int written; + + mutex_lock(&wq->mutex); + written = scnprintf(buf, PAGE_SIZE, "%d\n", wq->unbound_attrs->nice); + mutex_unlock(&wq->mutex); + + return written; +} + +/* prepare workqueue_attrs for sysfs store operations */ +static struct workqueue_attrs *wq_sysfs_prep_attrs(struct workqueue_struct *wq) +{ + struct workqueue_attrs *attrs; + + attrs = alloc_workqueue_attrs(GFP_KERNEL); + if (!attrs) + return NULL; + + mutex_lock(&wq->mutex); + copy_workqueue_attrs(attrs, wq->unbound_attrs); + mutex_unlock(&wq->mutex); + return attrs; +} + +static ssize_t wq_nice_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) +{ + struct workqueue_struct *wq = dev_to_wq(dev); + struct workqueue_attrs *attrs; + int ret; + + attrs = wq_sysfs_prep_attrs(wq); + if (!attrs) + return -ENOMEM; + + if (sscanf(buf, "%d", &attrs->nice) == 1 && + attrs->nice >= MIN_NICE && attrs->nice <= MAX_NICE) + ret = apply_workqueue_attrs(wq, attrs); + else + ret = -EINVAL; + + free_workqueue_attrs(attrs); + return ret ?: count; +} + +static ssize_t wq_cpumask_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct workqueue_struct *wq = dev_to_wq(dev); + int written; + + mutex_lock(&wq->mutex); + written = scnprintf(buf, PAGE_SIZE, "%*pb\n", + cpumask_pr_args(wq->unbound_attrs->cpumask)); + mutex_unlock(&wq->mutex); + return written; +} + +static ssize_t wq_cpumask_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct workqueue_struct *wq = dev_to_wq(dev); + struct workqueue_attrs *attrs; + int ret; + + attrs = wq_sysfs_prep_attrs(wq); + if (!attrs) + return -ENOMEM; + + ret = cpumask_parse(buf, attrs->cpumask); + if (!ret) + ret = apply_workqueue_attrs(wq, attrs); + + free_workqueue_attrs(attrs); + return ret ?: count; +} + +static ssize_t wq_numa_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct workqueue_struct *wq = dev_to_wq(dev); + int written; + + mutex_lock(&wq->mutex); + written = scnprintf(buf, PAGE_SIZE, "%d\n", + !wq->unbound_attrs->no_numa); + mutex_unlock(&wq->mutex); + + return written; +} + +static ssize_t wq_numa_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) +{ + struct workqueue_struct *wq = dev_to_wq(dev); + struct workqueue_attrs *attrs; + int v, ret; + + attrs = wq_sysfs_prep_attrs(wq); + if (!attrs) + return -ENOMEM; + + ret = -EINVAL; + if (sscanf(buf, "%d", &v) == 1) { + attrs->no_numa = !v; + ret = apply_workqueue_attrs(wq, attrs); + } + + free_workqueue_attrs(attrs); + return ret ?: count; +} + +static struct device_attribute wq_sysfs_unbound_attrs[] = { + __ATTR(pool_ids, 0444, wq_pool_ids_show, NULL), + __ATTR(nice, 0644, wq_nice_show, wq_nice_store), + __ATTR(cpumask, 0644, wq_cpumask_show, wq_cpumask_store), + __ATTR(numa, 0644, wq_numa_show, wq_numa_store), + __ATTR_NULL, +}; + +static struct bus_type wq_subsys = { + .name = "workqueue", + .dev_groups = wq_sysfs_groups, +}; + +static int __init wq_sysfs_init(void) +{ + return subsys_virtual_register(&wq_subsys, NULL); +} +core_initcall(wq_sysfs_init); + +static void wq_device_release(struct device *dev) +{ + struct wq_device *wq_dev = container_of(dev, struct wq_device, dev); + + kfree(wq_dev); +} + +/** + * workqueue_sysfs_register - make a workqueue visible in sysfs + * @wq: the workqueue to register + * + * Expose @wq in sysfs under /sys/bus/workqueue/devices. + * alloc_workqueue*() automatically calls this function if WQ_SYSFS is set + * which is the preferred method. + * + * Workqueue user should use this function directly iff it wants to apply + * workqueue_attrs before making the workqueue visible in sysfs; otherwise, + * apply_workqueue_attrs() may race against userland updating the + * attributes. + * + * Return: 0 on success, -errno on failure. + */ +int workqueue_sysfs_register(struct workqueue_struct *wq) +{ + struct wq_device *wq_dev; + int ret; + + /* + * Adjusting max_active or creating new pwqs by applyting + * attributes breaks ordering guarantee. Disallow exposing ordered + * workqueues. + */ + if (WARN_ON(wq->flags & __WQ_ORDERED)) + return -EINVAL; + + wq->wq_dev = wq_dev = kzalloc(sizeof(*wq_dev), GFP_KERNEL); + if (!wq_dev) + return -ENOMEM; + + wq_dev->wq = wq; + wq_dev->dev.bus = &wq_subsys; + wq_dev->dev.init_name = wq->name; + wq_dev->dev.release = wq_device_release; + + /* + * unbound_attrs are created separately. Suppress uevent until + * everything is ready. + */ + dev_set_uevent_suppress(&wq_dev->dev, true); + + ret = device_register(&wq_dev->dev); + if (ret) { + kfree(wq_dev); + wq->wq_dev = NULL; + return ret; + } + + if (wq->flags & WQ_UNBOUND) { + struct device_attribute *attr; + + for (attr = wq_sysfs_unbound_attrs; attr->attr.name; attr++) { + ret = device_create_file(&wq_dev->dev, attr); + if (ret) { + device_unregister(&wq_dev->dev); + wq->wq_dev = NULL; + return ret; + } + } + } + + dev_set_uevent_suppress(&wq_dev->dev, false); + kobject_uevent(&wq_dev->dev.kobj, KOBJ_ADD); + return 0; +} + +/** + * workqueue_sysfs_unregister - undo workqueue_sysfs_register() + * @wq: the workqueue to unregister + * + * If @wq is registered to sysfs by workqueue_sysfs_register(), unregister. + */ +static void workqueue_sysfs_unregister(struct workqueue_struct *wq) +{ + struct wq_device *wq_dev = wq->wq_dev; + + if (!wq->wq_dev) + return; + + wq->wq_dev = NULL; + device_unregister(&wq_dev->dev); +} +#else /* CONFIG_SYSFS */ +static void workqueue_sysfs_unregister(struct workqueue_struct *wq) { } +#endif /* CONFIG_SYSFS */ + +static void __init wq_numa_init(void) +{ + cpumask_var_t *tbl; + int node, cpu; + + if (num_possible_nodes() <= 1) + return; + + if (wq_disable_numa) { + pr_info("workqueue: NUMA affinity support disabled\n"); + return; + } + + wq_update_unbound_numa_attrs_buf = alloc_workqueue_attrs(GFP_KERNEL); + BUG_ON(!wq_update_unbound_numa_attrs_buf); + + /* + * We want masks of possible CPUs of each node which isn't readily + * available. Build one from cpu_to_node() which should have been + * fully initialized by now. + */ + tbl = kzalloc(nr_node_ids * sizeof(tbl[0]), GFP_KERNEL); + BUG_ON(!tbl); + + for_each_node(node) + BUG_ON(!zalloc_cpumask_var_node(&tbl[node], GFP_KERNEL, + node_online(node) ? node : NUMA_NO_NODE)); + + for_each_possible_cpu(cpu) { + node = cpu_to_node(cpu); + if (WARN_ON(node == NUMA_NO_NODE)) { + pr_warn("workqueue: NUMA node mapping not available for cpu%d, disabling NUMA support\n", cpu); + /* happens iff arch is bonkers, let's just proceed */ + return; + } + cpumask_set_cpu(cpu, tbl[node]); + } + + wq_numa_possible_cpumask = tbl; + wq_numa_enabled = true; +} + +static int __init init_workqueues(void) +{ + int std_nice[NR_STD_WORKER_POOLS] = { 0, HIGHPRI_NICE_LEVEL }; + int i, cpu; + + WARN_ON(__alignof__(struct pool_workqueue) < __alignof__(long long)); + + pwq_cache = KMEM_CACHE(pool_workqueue, SLAB_PANIC); + + cpu_notifier(workqueue_cpu_up_callback, CPU_PRI_WORKQUEUE_UP); + hotcpu_notifier(workqueue_cpu_down_callback, CPU_PRI_WORKQUEUE_DOWN); + + wq_numa_init(); + + /* initialize CPU pools */ + for_each_possible_cpu(cpu) { + struct worker_pool *pool; + + i = 0; + for_each_cpu_worker_pool(pool, cpu) { + BUG_ON(init_worker_pool(pool)); + pool->cpu = cpu; + cpumask_copy(pool->attrs->cpumask, cpumask_of(cpu)); + pool->attrs->nice = std_nice[i++]; + pool->node = cpu_to_node(cpu); + + /* alloc pool ID */ + mutex_lock(&wq_pool_mutex); + BUG_ON(worker_pool_assign_id(pool)); + mutex_unlock(&wq_pool_mutex); + } + } + + /* create the initial worker */ + for_each_online_cpu(cpu) { + struct worker_pool *pool; + + for_each_cpu_worker_pool(pool, cpu) { + pool->flags &= ~POOL_DISASSOCIATED; + BUG_ON(!create_worker(pool)); + } + } + + /* create default unbound and ordered wq attrs */ + for (i = 0; i < NR_STD_WORKER_POOLS; i++) { + struct workqueue_attrs *attrs; + + BUG_ON(!(attrs = alloc_workqueue_attrs(GFP_KERNEL))); + attrs->nice = std_nice[i]; + unbound_std_wq_attrs[i] = attrs; + + /* + * An ordered wq should have only one pwq as ordering is + * guaranteed by max_active which is enforced by pwqs. + * Turn off NUMA so that dfl_pwq is used for all nodes. + */ + BUG_ON(!(attrs = alloc_workqueue_attrs(GFP_KERNEL))); + attrs->nice = std_nice[i]; + attrs->no_numa = true; + ordered_wq_attrs[i] = attrs; + } + + system_wq = alloc_workqueue("events", 0, 0); + system_highpri_wq = alloc_workqueue("events_highpri", WQ_HIGHPRI, 0); + system_long_wq = alloc_workqueue("events_long", 0, 0); + system_unbound_wq = alloc_workqueue("events_unbound", WQ_UNBOUND, + WQ_UNBOUND_MAX_ACTIVE); + system_freezable_wq = alloc_workqueue("events_freezable", + WQ_FREEZABLE, 0); + system_power_efficient_wq = alloc_workqueue("events_power_efficient", + WQ_POWER_EFFICIENT, 0); + system_freezable_power_efficient_wq = alloc_workqueue("events_freezable_power_efficient", + WQ_FREEZABLE | WQ_POWER_EFFICIENT, + 0); + BUG_ON(!system_wq || !system_highpri_wq || !system_long_wq || + !system_unbound_wq || !system_freezable_wq || + !system_power_efficient_wq || + !system_freezable_power_efficient_wq); + return 0; +} +early_initcall(init_workqueues); diff --git a/kernel/kernel/workqueue_internal.h b/kernel/kernel/workqueue_internal.h new file mode 100644 index 000000000..f000c4d69 --- /dev/null +++ b/kernel/kernel/workqueue_internal.h @@ -0,0 +1,75 @@ +/* + * kernel/workqueue_internal.h + * + * Workqueue internal header file. Only to be included by workqueue and + * core kernel subsystems. + */ +#ifndef _KERNEL_WORKQUEUE_INTERNAL_H +#define _KERNEL_WORKQUEUE_INTERNAL_H + +#include +#include + +struct worker_pool; + +/* + * The poor guys doing the actual heavy lifting. All on-duty workers are + * either serving the manager role, on idle list or on busy hash. For + * details on the locking annotation (L, I, X...), refer to workqueue.c. + * + * Only to be used in workqueue and async. + */ +struct worker { + /* on idle list while idle, on busy hash table while busy */ + union { + struct list_head entry; /* L: while idle */ + struct hlist_node hentry; /* L: while busy */ + }; + + struct work_struct *current_work; /* L: work being processed */ + work_func_t current_func; /* L: current_work's fn */ + struct pool_workqueue *current_pwq; /* L: current_work's pwq */ + bool desc_valid; /* ->desc is valid */ + struct list_head scheduled; /* L: scheduled works */ + + /* 64 bytes boundary on 64bit, 32 on 32bit */ + + struct task_struct *task; /* I: worker task */ + struct worker_pool *pool; /* I: the associated pool */ + /* L: for rescuers */ + struct list_head node; /* A: anchored at pool->workers */ + /* A: runs through worker->node */ + + unsigned long last_active; /* L: last active timestamp */ + unsigned int flags; /* X: flags */ + int id; /* I: worker id */ + int sleeping; /* None */ + + /* + * Opaque string set with work_set_desc(). Printed out with task + * dump for debugging - WARN, BUG, panic or sysrq. + */ + char desc[WORKER_DESC_LEN]; + + /* used only by rescuers to point to the target workqueue */ + struct workqueue_struct *rescue_wq; /* I: the workqueue to rescue */ +}; + +/** + * current_wq_worker - return struct worker if %current is a workqueue worker + */ +static inline struct worker *current_wq_worker(void) +{ + if (current->flags & PF_WQ_WORKER) + return kthread_data(current); + return NULL; +} + +/* + * Scheduler hooks for concurrency managed workqueue. Only to be used from + * sched/core.c and workqueue.c. + */ +void wq_worker_running(struct task_struct *task); +void wq_worker_sleeping(struct task_struct *task); + +#endif /* _KERNEL_WORKQUEUE_INTERNAL_H */ -- cgit 1.2.3-korg